Wikiwordbōc angwiktionary https://ang.wiktionary.org/wiki/H%C4%93afodtramet MediaWiki 1.47.0-wmf.21 case-sensitive Media Syndrig Mōtung Brūcend Brūcendmōtung Wikiwordbōc Wikiwordbōcmōtung Ymele Ymelmōtung MediaWiki MediaWikimōtung Bysen Bysenmōtung Help Helpmōtung Flocc Floccmōtung Ætēaca Ætēacmōtung TimedText TimedText talk Module Module talk Event Event talk 0 6423 54913 54870 2026-09-28T23:26:06Z Deadend0914 7211 /* Wordstǣr */ 54913 wikitext text/x-wiki =={{sprǣc|ang}}== ===Āwendednessa=== * deað * dǣþ ===Rihtstefn=== * /dæːɑθ/ ===Wordstǣr=== Of {{inh|ang|gmw-pro|*dauþu}}, of {{inh|ang|gem-pro|*dauþuz}}, of {{inh|ang|ine-pro|*dʰautus}}. ====Sweostorword==== *Denisc: {{Wendung|da|død}} *[[Fresisc]]: {{Wendung|fy|dea}} ''wr'' *Īslendisc: {{Wendung|is|dauði}} ''wr'' *Niðerlendisc: {{Wendung|nl|dood}} ''wr'' *Norþwegisc: {{Wendung|no|død}} ''wr'' *[[Seaxisc]]: {{Wendung|nds|Dood}} ''wr'' *Swēonisc: {{Wendung|sv|död}} ''gm'' *Þēodisc: {{Wendung|de|Tod}} ''wr'' ===Werlīc Nama=== # Þæs līfes ende. #: '''''Dēaþ''' nis nān belimp on līfe. '''Dēaðes''' man ne gebītt. Gif man ēcnesse understent nā tō endelēasre tīdlengðe, ac tō tīdlēasnesse, þonne leofaþ sē on ēcnesse þe leofaþ on andweardnesse. Ūre līf is endelēas ealswā ūre gesihtfeld gemǣrelēas biþ.'' ====Nīwenglisc Andgiet==== # [[death]] ====Declīnung==== {{ang-decl-noun-a-m|dēaþ}} ====Gesetnyssum==== [[ær]]-dēaþ - early death, death before one's time, premature death <br> dēaþ-[[bēam]] "wr" - death tree <br> dēaþ-[[bedd]] "nw" - death bed, grave, bed of death, <br> dēaþ-[[cwalu]] "wf" - plague death, violent death, <br> dēaþ-[[dæg]] "wr" - death day, day of death, <br> dēaþ-denu "wf" - valley of death, <br> fær-dēaþ, dēaþ-ræs "wr" - sudden death, <br> dēaþ-scūa "wr", dēaþ-scufa "wr" - death shadow, shadow of death, <br> dēaþ-[[scyld]] "wf" - crime worthy of death <br> dēaþ-stede "wr" - place of death <br> dēaþ-[[wang]] "wr" - death plain, <br> dēaþ-wīc "nw" - death's place, dwelling of the dead, <br> dēaþ-[[wyrd]] "wf" - death fate, fate of death <br> [[ende]]-dēað -death as the end of life <br> [[gúð]]-dēað - battle death, death in battle <br> [[mere]]-dēaþ - sea death, death at sea, <br> [[swylt]]-dēaþ - death (die-death) <br> [[wæl]]-dēaþ - death in battle, <br> [[wundor]]-dēaþ - wondrous death <br> ====Wendunga==== *Frencisc: {{Wendung|fr|mort}} ''wf'' *Grēcisc: {{Wendung|el|θάνατος}} [ˈθa.na.to̞s] ''wr'', {{Wendung|el|θανατάς}} [θa.na.ˈtas] ''wr'', {{Wendung|el|πεθαμός}} [pe̞.θa.ˈmo̞s] ''wr'', {{Wendung|el|αποθαμός}} [a.po̞.θa.ˈmo̞s] {{m}}, {{Wendung|el|χάρος}} [ˈxa.ro̞s] ''wr'' *Hebrēisc: {{Wendung|he|מוות}} (mavet) ''wf'' *Italisc: {{Wendung|it|morte}} ''wf'' *Lǣden: {{Wendung|la|mors}} ''wf'', {{Wendung|la|exitium}} ''nā'', {{Wendung|la|quietus}} ''wr'' *Persisc: {{Wendung|fa|مرگ}} *Scyttisc Gǣlisc: {{Wendung|gd|bàs}} ''wr'' [[Flocc:Englisc nama]] [[Flocc: Englisc werlīc nama]] 331usa2sduy3gc6c978pto7lg5vxi3g 54915 54913 2026-09-28T23:27:33Z Deadend0914 7211 /* Werlīc Nama */ 54915 wikitext text/x-wiki =={{sprǣc|ang}}== ===Āwendednessa=== * deað * dǣþ ===Rihtstefn=== * /dæːɑθ/ ===Wordstǣr=== Of {{inh|ang|gmw-pro|*dauþu}}, of {{inh|ang|gem-pro|*dauþuz}}, of {{inh|ang|ine-pro|*dʰautus}}. ====Sweostorword==== *Denisc: {{Wendung|da|død}} *[[Fresisc]]: {{Wendung|fy|dea}} ''wr'' *Īslendisc: {{Wendung|is|dauði}} ''wr'' *Niðerlendisc: {{Wendung|nl|dood}} ''wr'' *Norþwegisc: {{Wendung|no|død}} ''wr'' *[[Seaxisc]]: {{Wendung|nds|Dood}} ''wr'' *Swēonisc: {{Wendung|sv|död}} ''gm'' *Þēodisc: {{Wendung|de|Tod}} ''wr'' ===Werlīc Nama=== {{ang-noun|m|head=dēaþ}} # Þæs līfes ende. #: '''''Dēaþ''' nis nān belimp on līfe. '''Dēaðes''' man ne gebītt. Gif man ēcnesse understent nā tō endelēasre tīdlengðe, ac tō tīdlēasnesse, þonne leofaþ sē on ēcnesse þe leofaþ on andweardnesse. Ūre līf is endelēas ealswā ūre gesihtfeld gemǣrelēas biþ.'' ====Nīwenglisc Andgiet==== # [[death]] ====Declīnung==== {{ang-decl-noun-a-m|dēaþ}} ====Gesetnyssum==== [[ær]]-dēaþ - early death, death before one's time, premature death <br> dēaþ-[[bēam]] "wr" - death tree <br> dēaþ-[[bedd]] "nw" - death bed, grave, bed of death, <br> dēaþ-[[cwalu]] "wf" - plague death, violent death, <br> dēaþ-[[dæg]] "wr" - death day, day of death, <br> dēaþ-denu "wf" - valley of death, <br> fær-dēaþ, dēaþ-ræs "wr" - sudden death, <br> dēaþ-scūa "wr", dēaþ-scufa "wr" - death shadow, shadow of death, <br> dēaþ-[[scyld]] "wf" - crime worthy of death <br> dēaþ-stede "wr" - place of death <br> dēaþ-[[wang]] "wr" - death plain, <br> dēaþ-wīc "nw" - death's place, dwelling of the dead, <br> dēaþ-[[wyrd]] "wf" - death fate, fate of death <br> [[ende]]-dēað -death as the end of life <br> [[gúð]]-dēað - battle death, death in battle <br> [[mere]]-dēaþ - sea death, death at sea, <br> [[swylt]]-dēaþ - death (die-death) <br> [[wæl]]-dēaþ - death in battle, <br> [[wundor]]-dēaþ - wondrous death <br> ====Wendunga==== *Frencisc: {{Wendung|fr|mort}} ''wf'' *Grēcisc: {{Wendung|el|θάνατος}} [ˈθa.na.to̞s] ''wr'', {{Wendung|el|θανατάς}} [θa.na.ˈtas] ''wr'', {{Wendung|el|πεθαμός}} [pe̞.θa.ˈmo̞s] ''wr'', {{Wendung|el|αποθαμός}} [a.po̞.θa.ˈmo̞s] {{m}}, {{Wendung|el|χάρος}} [ˈxa.ro̞s] ''wr'' *Hebrēisc: {{Wendung|he|מוות}} (mavet) ''wf'' *Italisc: {{Wendung|it|morte}} ''wf'' *Lǣden: {{Wendung|la|mors}} ''wf'', {{Wendung|la|exitium}} ''nā'', {{Wendung|la|quietus}} ''wr'' *Persisc: {{Wendung|fa|مرگ}} *Scyttisc Gǣlisc: {{Wendung|gd|bàs}} ''wr'' [[Flocc:Englisc nama]] [[Flocc: Englisc werlīc nama]] ki8g2f2ew9fh0ivmafarwma1ptv7rct 10 7569 54903 54789 2026-09-28T23:19:15Z Deadend0914 7211 54903 wikitext text/x-wiki <includeonly>{{#invoke:sprǣcnaman|sprǣc|{{{1|}}}|{{{2|}}}}}</includeonly><noinclude>{{Documentation}}</noinclude> t9y15oamh5dmc9itcudi2sonll1w1e2 828 7868 54897 54721 2026-09-28T22:28:57Z Deadend0914 7211 Replaced content with "local m_bases = require("Module:bases") local m_params = require("Module:parameters") local languagesData = mw.loadData("Module:languages/data") local p = {} p.specialCodes = { ["zh-Hans"] = "zh", ["zh-Hant"] = "zh", ["yue-Hant"] = "yue", ["wuu-Hant"] = "wuu", ["ko-Hani"] = "ko", ["vi-Hani"] = "vi", ["vi-Hans"] = "vi", ["vi-Hant"] = "vi", ["nan-Hani"] = "nan", ["nan-Hans"] = "nan", ["nan-Hant"] = "nan", } --- Return the name of the language m..." 54897 Scribunto text/plain local m_bases = require("Module:bases") local m_params = require("Module:parameters") local languagesData = mw.loadData("Module:languages/data") local p = {} p.specialCodes = { ["zh-Hans"] = "zh", ["zh-Hant"] = "zh", ["yue-Hant"] = "yue", ["wuu-Hant"] = "wuu", ["ko-Hani"] = "ko", ["vi-Hani"] = "vi", ["vi-Hans"] = "vi", ["vi-Hant"] = "vi", ["nan-Hani"] = "nan", ["nan-Hans"] = "nan", ["nan-Hant"] = "nan", } --- Return the name of the language matching the given language code. --- @param code string A language code. --- @param allowSpecial? boolean If true, codes marked as group or special also will be considered. --- @return string|nil # The matching language name, nil otherwise. function p.getName(code, allowSpecial) if not code or not languagesData[code] or not allowSpecial and (languagesData[code].isSpecial or languagesData[code].isGroup) then return nil end return languagesData[code].name end --- Return the sort key for the given language code. --- @param code string A language code. --- @param allowSpecial? boolean If true, codes marked as group or special will also be considered. --- @return string|nil # The sort key for the language, nil if the code is invalid. function p.getSortKey(code, allowSpecial) if not code or not languagesData[code] or not allowSpecial and (languagesData[code].isSpecial or languagesData[code].isGroup) then return nil end return languagesData[code].sortKey or languagesData[code].name end --- Return the name of the given language. Available to templates. --- @param frame frame --- Parameters: --- parent.args[1] (string): Language code. --- @return string # The name of the language or an empty string if the code is invalid. function p.languageName(frame) local args = m_params.process(frame:getParent().args, { [1] = {}, }) return p.getName(args[1]) or "" end --- Return the sort key for the given language code. Available to templates. --- @param frame frame --- Parameters: --- args[1] (string, optional): Language code. --- @return string|nil # The sort key for the language, nil if the code is invalid. function p.languageSortKey(frame) local args = m_params.process(frame:getParent().args, { [1] = {}, }) return p.getSortKey(args[1]) or "" end --- Return the name of the given language with its first letter capitalized. --- This function is used by the template {{L}}. --- @param frame frame --- Parameters: --- parent.args[1] (string, optional): A language code. --- @return string # The capitalized name of the language, an error message if none matched. function p.languageNameForList(frame) local args = m_params.process(frame:getParent().args, { [1] = {} }) local code = args[1] if not code then return '<span style="color: red">Sprǣce word missende</span>' .. m_bases.fait_categorie_contenu("Wikiwordbēc:Sprǣce word missende") end local languageName = p.getName(code, true) if not languageName then return mw.ustring.format('<span style="color: red">Sprǣce word ungecnāwen&nbsp;: %s*</span>', code) .. m_bases.fait_categorie_contenu("Wikiwordbēc:Sprǣce word ne sett") end return m_bases.ucfirst(languageName) end --- Return the Wikimedia language code for the given internal language code if it exists. --- @param code string A language code. --- @return string|nil # The corresponding Wikimedia language code, or nil if none matched. function p.getWikimediaCode(code) if not code or not languagesData[code] then return nil end return languagesData[code].wikimediaCode end --- Return the Wikimedia language code for the given internal language code if it exists. --- @param frame frame --- Parameters: --- parent.args[1] (string, optional): A language code. --- @return string # The corresponding Wikimedia language code, or an empty string if none matched. function p.wikimediaCode(frame) local args = m_params.process(frame:getParent().args, { [1] = {}, }) local code = args[1] return p.getWikimediaCode(code) or code end --- Check whether a page in the “Duru” namespace exists for the given language code. --- @param code string A language code. --- @return boolean # True if a “Duru” page exists, false otherwise. function p.hasPortal(code) return languagesData[code] ~= nil and languagesData[code].hasPortal end --- Check whether a Wiktionary exists for the given language code. --- @param code string Le code de langue. --- @return boolean # True if a Wiktionary exists, false otherwise. function p.hasWiktionary(code) return languagesData[code] ~= nil and languagesData[code].wiktionaryExists end --- Return the code corresponding to the given language name. --- @param languageName string A language name. --- @param allowSpecial? boolean If true, codes marked as group or special also will be considered. --- @return string | nil # The language’s code, or nil if none matched. function p.getLanguageCode(languageName, allowSpecial) for code, languageData in pairs(languagesData) do if languageName == languageData.name and (allowSpecial or (not languageData.isGroup and not languageData.isSpecial)) then return languageData.aliasOf or code end end return nil end --- Return the code corresponding to the given language name. --- If there are more than one, keep the shortest one. --- The function also takes code aliases into account (e.g. "anglo-saxon" for "vieil anglais"). --- Special case: if there exists a code that strictly equals a language name, --- it will be returned even if a shorter code exists (e.g. "vieil écossais" vs "vieux scots"), --- unless there exists a code with 3 characters or less (e.g. "créole guadeloupéen" vs "gcf"), --- except if the language name is "normand". --- @param frame frame --- Parameters: --- parent.args[1] (string, optional): A language name. Defaults to the current page’s title. --- parent.args["codes spéciaux"] (boolean, optional): If true, codes marked as group or special also will be considered. --- @return string # The language’s code, or an empty string if none matched. function p.languageCode(frame) local args = m_params.process(frame:getParent().args, { [1] = { default = mw.title.getCurrentTitle().text }, ["codes spéciaux"] = { type = m_params.BOOLEAN, default = false }, }) return p.getLanguageCode(args[1], args["codes spéciaux"]) or "" end return p oklj2oo5qnghkwu4c3o80a448skfcip 54899 54897 2026-09-28T22:40:08Z Deadend0914 7211 54899 Scribunto text/plain --[==[ intro: This module implements fetching of language-specific information and processing text in a given language. ===Types of languages=== There are two types of languages: full languages and etymology-only languages. The essential difference is that only full languages appear in L2 headings in vocabulary entries, and hence categories like [[:Category:French nouns]] exist only for full languages. Etymology-only languages have either a full language or another etymology-only language as their parent (in the parent-child inheritance sense), and for etymology-only languages with another etymology-only language as their parent, a full language can always be derived by following the parent links upwards. For example, "Canadian French", code `fr-CA`, is an etymology-only language whose parent is the full language "French", code `fr`. An example of an etymology-only language with another etymology-only parent is "Northumbrian Old English", code `ang-nor`, which has "Anglian Old English", code `ang-ang` as its parent; this is an etymology-only language whose parent is "Old English", code `ang`, which is a full language. (This is because Northumbrian Old English is considered a variety of Anglian Old English.) Sometimes the parent is the "Undetermined" language, code `und`; this is the case, for example, for "substrate" languages such as "Pre-Greek", code `qsb-grc`, and "the BMAC substrate", code `qsb-bma`. It is important to distinguish language ''parents'' from language ''ancestors''. The parent-child relationship is one of containment, i.e. if X is a child of Y, X is considered a variety of Y. On the other hand, the ancestor-descendant relationship is one of descent in time. For example, "Classical Latin", code `la-cla`, and "Late Latin", code `la-lat`, are both etymology-only languages with "Latin", code `la`, as their parents, because both of the former are varieties of Latin. However, Late Latin does *NOT* have Classical Latin as its parent because Late Latin is *not* a variety of Classical Latin; rather, it is a descendant. There is in fact a separate `ancestors` field that is used to express the ancestor-descendant relationship, and Late Latin's ancestor is given as Classical Latin. It is also important to note that sometimes an etymology-only language is actually the conceptual ancestor of its parent language. This happens, for example, with "Old Italian" (code `roa-oit`), which is an etymology-only variant of full language "Italian" (code `it`), and with "Old Latin" (code `itc-ola`), which is an etymology-only variant of Latin. In both cases, the full language has the etymology-only variant listed as an ancestor. This allows a Latin term to inherit from Old Latin using the {{tl|inh}} template (where in this template, "inheritance" refers to ancestral inheritance, i.e. inheritance in time, rather than in the parent-child sense); likewise for Italian and Old Italian. Full languages come in three subtypes: * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. Most constructed languages are of this subtype. Both full languages and etymology-only languages have a {Language} object associated with them, which is fetched using the {getByCode} function in [[Module:languages]] to convert a language code to a {Language} object. Depending on the options supplied to this function, etymology-only languages may or may not be accepted, and family codes may be accepted (returning a {Family} object as described in [[Module:families]]). There are also separate {getByCanonicalName} functions in [[Module:languages]] and [[Module:etymology languages]] to convert a language's canonical name to a {Language} object (depending on whether the canonical name refers to a full or etymology-only language). ===Textual representations=== Textual strings belonging to a given language come in several different ''text variants'': # The ''input text'' is what the user supplies in wikitext, in the parameters to {{tl|m}}, {{tl|l}}, {{tl|ux}}, {{tl|t}}, {{tl|lang}} and the like. # The ''corrected input text'' is the input text with some corrections and/or normalizations applied, such as bad-character replacements for certain languages, like replacing `l` or `1` to [[palochka]] in some languages written in Cyrillic. (FIXME: This currently goes under the name ''display text'' but that will be repurposed below. Also, [[User:Surjection]] suggests renaming this to ''normalized input text'', but "normalized" is used in a different sense in [[Module:usex]].) # The ''display text'' is the text in the form as it will be displayed to the user. This is what appears in headwords, in usexes, in displayed internal links, etc. This can include accent marks that are removed to form the stripped display text (see below), as well as embedded bracketed links that are variously processed further. The display text is generated from the corrected input text by applying language-specific transformations; for most languages, there will be no such transformations. The general reason for having a difference between input and display text is to allow for extra information in the input text that is not displayed to the user but is sent to the transliteration module. Note that having different display and input text is only supported currently through special-casing but will be generalized. Examples of transformations are: (1) Removing the {{cd|^}} that is used in certain East Asian (and possibly other unicameral) languages to indicate capitalization of the transliteration (which is currently special-cased); (2) for Korean, removing or otherwise processing hyphens (which is currently special-cased); (3) for Arabic, removing a ''sukūn'' diacritic placed over a ''tāʔ marbūṭa'' (like this: ةْ) to indicate that the ''tāʔ marbūṭa'' is pronounced and transliterated as /t/ instead of being silent [NOTE, NOT IMPLEMENTED YET]; (4) for Thai and Khmer, converting space-separated words to bracketed words and resolving respelling substitutions such as `[กรีน/กฺรีน]`, which indicate how to transliterate given words [NOTE, NOT IMPLEMENTED YET except in language-specific templates like {{tl|th-usex}}]. ## The ''right-resolved display text'' is the result of removing brackets around one-part embedded links and resolving two-part embedded links into their right-hand components (i.e. converting two-part links into the displayed form). The process of right-resolution is what happens when you call {{cd|remove_links()}} in [[Module:links]] on some text. When applied to the display text, it produces exactly what the user sees, without any link markup. # The ''stripped display text'' is the result of applying diacritic-stripping to the display text. ## The ''left-resolved stripped display text'' [NEED BETTER NAME] is the result of applying left-resolution to the stripped display text, i.e. similar to right-resolution but resolving two-part embedded links into their left-hand components (i.e. the linked-to page). If the display text refers to a single page, the resulting of applying diacritic stripping and left-resolution produces the ''logical pagename''. # The ''physical pagename text'' is the result of converting the stripped display text into physical page links. If the stripped display text contains embedded links, the left side of those links is converted into physical page links; otherwise, the entire text is considered a pagename and converted in the same fashion. The conversion does three things: (1) converts characters not allowed in pagenames into their "unsupported title" representation, e.g. {{cd|Unsupported titles/`gt`}} in place of the logical name {{cd|>}}; (2) handles certain special-cased unsupported-title logical pagenames, such as {{cd|Unsupported titles/Space}} in place of {{cd|[space]}} and {{cd|Unsupported titles/Ancient Greek dish}} in place of a very long Greek name for a gourmet dish as found in Aristophanes; (3) converts "mammoth" pagenames such as [[a]] into their appropriate split component, e.g. [[a/languages A to L]]. # The ''source translit text'' is the text as supplied to the language-specific {{cd|transliterate()}} method. The form of the source translit text may need to be language-specific, e.g Thai and Khmer will need the corrected input text, whereas other languages may need to work off the display text. [FIXME: It's still unclear to me how embedded bracketed links are handled in the existing code.] In general, embedded links need to be right-resolved (see above), but when this happens is unclear to me [FIXME]. Some languages have a chop-up-and-paste-together scheme that sends parts of the text through the transliterate mechanism, and for others (those listed with "cont" in {{cd|substitution}} in [[Module:languages/data]]) they receive the full input text, but preprocessed in certain ways. (The wisdom of this is still unclear to me.) # The ''transliterated text'' (or ''transliteration'') is the result of transliterating the source translit text. Unlike for all the other text variants except the transcribed text, it is always in the Latin script. # The ''transcribed text'' (or ''transcription'') is the result of transcribing the source translit text, where "transcription" here means a close approximation to the phonetic form of the language in languages (e.g. Akkadian, Sumerian, Ancient Egyptian, maybe Tibetan) that have a wide difference between the written letters and spoken form. Unlike for all the other text variants other than the transliterated text, it is always in the Latin script. Currently, the transcribed text is always supplied manually be the user; there is no such thing as a {{cd|transcribe()}} method on language objects. # The ''sort key'' is the text used in sort keys for determining the placing of pages in categories they belong to. The sort key is generated from the pagename or a specified ''sort base'' by lowercasing, doing language-specific transformations and then uppercasing the result. If the sort base is supplied and is generated from input text, it needs to be converted to display text, have embedded links removed through right-resolution and have diacritic-stripping applied. # There are other text variants that occur in usexes (specifically, there are normalized variants of several of the above text variants), but we can skip them for now. The following methods exist on {Language} objects to convert between different text variants: # {correctInputText} (currently called {makeDisplayText}): This converts input text to corrected input text. # {stripDiacritics}: This converts to stripped display text. [FIXME: This needs some rethinking. In particular, {stripDiacritics} is sometimes called on input text, corrected input text or display text (in various paths inside of [[Module:links]], and, in the case of input text, usually from other modules). We need to make sure we don't try to convert input text to display text twice, but at the same time we need to support calling it directly on input text since so many modules do this. This means we need to add a parameter indicating whether the passed-in text is input, corrected input, or display text; if the former two, we call {correctInputText} ourselves.] # {logicalToPhysical}: This converts logical pagenames to physical pagenames. # {transliterate}: This appears to convert input text with embedded brackets removed into a transliteration. [FIXME: This needs some rethinking. In particular, it calls {processDisplayText} on its input, which won't work for Thai and Khmer, so we may need language-specific flags indicating whether to pass the input text directly to the language transliterate method. In addition, I'm not sure how embedded links are handled in the existing translit code; a lot of callers remove the links themselves before calling {transliterate()}, which I assume is wrong.] # {makeSortKey}: This converts display text (?) to a sort key. [FIXME: Clarify this.] ]==] local export = {} local debug_track_module = "Module:debug/track" local etymology_languages_data_module = "Module:etymology languages/data" local families_module = "Module:families" local headword_page_module = "Module:headword/page" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_data_module = "Module:languages/data" local languages_data_patterns_module = "Module:languages/data/patterns" local links_data_module = "Module:links/data" local load_module = "Module:load" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local string_encode_entities_module = "Module:string/encode entities" local string_pattern_escape_module = "Module:string/patternEscape" local string_replacement_escape_module = "Module:string/replacementEscape" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local wikimedia_languages_module = "Module:wikimedia languages" local mw = mw local string = string local table = table local char = string.char local concat = table.concat local find = string.find local floor = math.floor local get_by_code -- Defined below. local get_data_module_name -- Defined below. local get_extra_data_module_name -- Defined below. local getmetatable = getmetatable local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local ipairs = ipairs local is_known_language_tag = mw.language.isKnownLanguageTag local make_object -- Defined below. local match = string.match local next = next local pairs = pairs local remove = table.remove local require = require local select = select local setmetatable = setmetatable local sub = string.sub local type = type local unstrip = mw.text.unstrip -- Loaded as needed by findBestScript. local Hans_chars local Hant_chars local function check_object(...) check_object = require(utilities_module).check_object return check_object(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function decode_uri(...) decode_uri = require(string_utilities_module).decode_uri return decode_uri(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function encode_entities(...) encode_entities = require(string_encode_entities_module) return encode_entities(...) end local function get_L2_sort_key(...) get_L2_sort_key = require(headword_page_module).get_L2_sort_key return get_L2_sort_key(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function get_family(...) get_family = require(families_module).getByCode return get_family(...) end local function get_plaintext(...) get_plaintext = require(utilities_module).get_plaintext return get_plaintext(...) end local function get_wikimedia_lang(...) get_wikimedia_lang = require(wikimedia_languages_module).getByCode return get_wikimedia_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_family_object(...) make_family_object = require(families_module).makeObject return make_family_object(...) end local function pattern_escape(...) pattern_escape = require(string_pattern_escape_module) return pattern_escape(...) end local function replacement_escape(...) replacement_escape = require(string_replacement_escape_module) return replacement_escape(...) end local function safe_require(...) safe_require = require(load_module).safe_require return safe_require(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ugsub(...) ugsub = require(string_utilities_module).gsub return ugsub(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end local function track(page) debug_track("languages/" .. page) return true end local function normalize_code(code) return load_data(languages_data_module).aliases[code] or code end local function check_inputs(self, check, default, ...) local n = select("#", ...) if n == 0 then return false end local ret = check(self, (...)) if ret ~= nil then return ret elseif n > 1 then local inputs = {...} for i = 2, n do ret = check(self, inputs[i]) if ret ~= nil then return ret end end end return default end local function make_link(self, target, display) local prefix, main if self:getFamilyCode() == "qfa-sub" then prefix, main = display:match("^(the )(.*)") if not prefix then prefix, main = display:match("^(a )(.*)") end end return (prefix or "") .. "[[" .. target .. "|" .. (main or display) .. "]]" end -- Convert risky characters to HTML entities, which minimizes interference once returned (e.g. for "sms:a", "<!-- -->" etc.). local function escape_risky_characters(text) -- Spacing characters in isolation generally need to be escaped in order to be properly processed by the MediaWiki -- software. if umatch(text, "^%s*$") then return encode_entities(text, text) end return encode_entities(text, "!#%&*+/:;<=>?@[\\]_{|}") end -- Temporarily convert various formatting characters to PUA to prevent them from being disrupted by the substitution process. local function doTempSubstitutions(text, subbedChars, keepCarets, noTrim) -- Clone so that we don't insert any extra patterns into the table in package.loaded. For some reason, using require -- seems to keep memory use down; probably because the table is always cloned. local patterns = shallow_copy(require(languages_data_patterns_module)) if keepCarets then insert(patterns, "((\\+)%^)") insert(patterns, "((%^))") end -- Ensure any whitespace at the beginning and end is temp substituted, to prevent it from being accidentally -- trimmed. We only want to trim any final spaces added during the substitution process (e.g. by a module), which -- means we only do this during the first round of temp substitutions. if not noTrim then insert(patterns, "^([\128-\191\244]*(%s+))") insert(patterns, "((%s+)[\128-\191\244]*)$") end -- Pre-substitution, of "[[" and "]]", which makes pattern matching more accurate. text = gsub(text, "%f[%[]%[%[", "\1"):gsub("%f[%]]%]%]", "\2") local i = #subbedChars for _, pattern in ipairs(patterns) do -- Patterns ending in \0 stand are for things like "[[" or "]]"), so the inserted PUA are treated as breaks -- between terms by modules that scrape info from pages. local term_divider pattern = gsub(pattern, "%z$", function(divider) term_divider = divider == "\0" return "" end) text = gsub(text, pattern, function(...) local m = {...} local m1New = m[1] for k = 2, #m do local n = i + k - 1 subbedChars[n] = m[k] local byte2 = floor(n / 4096) % 64 + (term_divider and 128 or 136) local byte3 = floor(n / 64) % 64 + 128 local byte4 = n % 64 + 128 m1New = gsub(m1New, pattern_escape(m[k]), "\244" .. char(byte2) .. char(byte3) .. char(byte4), 1) end i = i + #m - 1 return m1New end) end text = gsub(text, "\1", "%[%["):gsub("\2", "%]%]") return text, subbedChars end -- Reinsert any formatting that was temporarily substituted. local function undoTempSubstitutions(text, subbedChars) for i = 1, #subbedChars do local byte2 = floor(i / 4096) % 64 + 128 local byte3 = floor(i / 64) % 64 + 128 local byte4 = i % 64 + 128 text = gsub(text, "\244[" .. char(byte2) .. char(byte2+8) .. "]" .. char(byte3) .. char(byte4), replacement_escape(subbedChars[i])) end text = gsub(text, "\1", "%[%["):gsub("\2", "%]%]") return text end -- Check if the raw text is an unsupported title, and if so return that. Otherwise, remove HTML entities. We do the -- pre-conversion to avoid loading the unsupported title list unnecessarily. local function checkNoEntities(text) local textNoEnc = decode_entities(text) if textNoEnc ~= text and load_data(links_data_module).unsupported_titles[text] then return text else return textNoEnc end end -- If no script object is provided (or if it's invalid or None), get one. local function checkScript(text, self, sc) if not check_object("script", true, sc) or sc:getCode() == "None" then return self:findBestScript(text) end return sc end local function normalize(text, sc) text = sc:fixDiscouragedSequences(text) return sc:toFixedNFD(text) end --[=[ Subfunction of iterateSectionSubstitutions(). Process an individual chunk of text according to the specifications in `substitution_data`. The input parameters are all as in the documentation of iterateSectionSubstitutions() except for `recursed`, which is set to true if we called ourselves recursively to process a script-specific setting or script-wide fallback. Returns two values: the processed text and the actual substitution data used to do the substitutions (same as the `actual_substitution_data` return value to iterateSectionSubstitutions()). ]=] local function doSubstitutions(self, text, sc, substitution_data, data_field, function_name, recursed) -- BE CAREFUL in this function because the value at any level can be `false`, which causes no processing to be done -- and blocks any further fallback processing. local actual_substitution_data = substitution_data -- If there are language-specific substitutes given in the data module, use those. if type(substitution_data) == "table" then -- If a script is specified, run this function with the script-specific data before continuing. local sc_code = sc:getCode() local has_substitution_data = false if substitution_data[sc_code] ~= nil then has_substitution_data = true if substitution_data[sc_code] then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data[sc_code], data_field, function_name, true) end -- Hant, Hans and Hani are usually treated the same, so add a special case to avoid having to specify each one -- separately. elseif sc_code:match("^Han") and substitution_data.Hani ~= nil then has_substitution_data = true if substitution_data.Hani then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data.Hani, data_field, function_name, true) end -- Substitution data with key 1 in the outer table may be given as a fallback. elseif substitution_data[1] ~= nil then has_substitution_data = true if substitution_data[1] then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data[1], data_field, function_name, true) end end -- Iterate over all strings in the "from" subtable, and gsub with the corresponding string in "to". We work with -- the NFD decomposed forms, as this simplifies many substitutions. if substitution_data.from then has_substitution_data = true for i, from in ipairs(substitution_data.from) do -- Normalize each loop, to ensure multi-stage substitutions work correctly. text = sc:toFixedNFD(text) text = ugsub(text, sc:toFixedNFD(from), substitution_data.to[i] or "") end end if substitution_data.remove_diacritics then has_substitution_data = true text = sc:toFixedNFD(text) -- Convert exceptions to PUA. local remove_exceptions, substitutes = substitution_data.remove_exceptions if remove_exceptions then substitutes = {} local i = 0 for _, exception in ipairs(remove_exceptions) do exception = sc:toFixedNFD(exception) text = ugsub(text, exception, function(m) i = i + 1 local subst = u(0x80000 + i) substitutes[subst] = m return subst end) end end -- Strip diacritics. text = ugsub(text, "[" .. substitution_data.remove_diacritics .. "]", "") -- Convert exceptions back. if remove_exceptions then text = text:gsub("\242[\128-\191]*", substitutes) end end if not has_substitution_data and sc._data[data_field] then -- If language-specific sort key (etc.) is nil, fall back to script-wide sort key (etc.). text, actual_substitution_data = doSubstitutions(self, text, sc, sc._data[data_field], data_field, function_name, true) end elseif type(substitution_data) == "string" then -- If there is a dedicated function module, use that. local module = safe_require("Module:" .. substitution_data) if module then -- TODO: translit functions should take objects, not codes. -- TODO: translit functions should be called with form NFD. if function_name == "tr" then if not module[function_name] then error(("Internal error: Module [[%s]] has no function named 'tr'"):format(substitution_data)) end text = module[function_name](text, self._code, sc:getCode()) elseif function_name == "stripDiacritics" then -- FIXME, get rid of this arm after renaming makeEntryName -> stripDiacritics. if module[function_name] then text = module[function_name](sc:toFixedNFD(text), self, sc) elseif module.makeEntryName then text = module.makeEntryName(sc:toFixedNFD(text), self, sc) else error(("Internal error: Module [[%s]] has no function named 'stripDiacritics' or 'makeEntryName'" ):format(substitution_data)) end else if not module[function_name] then error(("Internal error: Module [[%s]] has no function named '%s'"):format( substitution_data, function_name)) end text = module[function_name](sc:toFixedNFD(text), self, sc) end else error("Substitution data '" .. substitution_data .. "' does not match an existing module.") end elseif substitution_data == nil and sc._data[data_field] then -- If language-specific sort key (etc.) is nil, fall back to script-wide sort key (etc.). text, actual_substitution_data = doSubstitutions(self, text, sc, sc._data[data_field], data_field, function_name, true) end -- Don't normalize to NFC if this is the inner loop or if a module returned nil. if recursed or not text then return text, actual_substitution_data end -- Fix any discouraged sequences created during the substitution process, and normalize into the final form. return sc:toFixedNFC(sc:fixDiscouragedSequences(text)), actual_substitution_data end --[=[ Split the text into sections, based on the presence of temporarily substituted formatting characters, then iterate over each section to apply substitutions (e.g. transliteration or diacritic stripping). This avoids putting PUA (Private Use Area) characters through language-specific modules, which may be unequipped for them. This function is passed the following values: * `self` (the Language object); * `text` (the text to process); * `sc` (the script of the text, which must be specified; callers should call checkScript() as needed to autodetect the script of the text if not given explicitly by the user); * `subbedChars` (an array of the same length as the text, indicating which characters have been substituted and by what, or {nil} if no substitutions are to happen); * `keepCarets` (DOCUMENT ME); * `substitution_data` (the data indicating which substitutions to apply, taken directly from `data_field` in the language's data structure in a submodule of [[Module:languages/data]]); * `data_field` (the field from which `substitution_data` was fetched, such as {"sort_key"} or {"strip_diacritics"}); * `function_name` (the name of the function to call to do the substitution, in case `substitution_data` specifies a module to do the substitution); * `notrim` (don't trim whitespace at the edges of `text`; set when computing the sort key, because whitespace at the beginning of a sort key is significant and causes the resulting page to be sorted at the beginning of the category it's in). Return three values: # the processed text; # the value of `subbedChars` that was passed in, possibly modified with additional character substitutions; will be {nil} if {nil} was passed in; # the actual substitution data that was used to apply substitutions to `text`; this may be different from the value of `substitution_data` passed in if that value recursively specified script-specific substitutions or if no substitution data could be found in the language-specific data (e.g. {nil} was passed in or a structure was passed in that had no setting for the script given in `sc`), but a script-wide fallback value was set; currently it is only used by {makeSortKey()}. ]=] local function iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, substitution_data, data_field, function_name, notrim) local sections -- See [[Module:languages/data]]. if not find(text, "\244") or load_data(languages_data_module).substitution[self._code] == "cont" then sections = {text} else sections = split(text, "\244[\128-\143][\128-\191]*", true) end local actual_substitution_data for _, section in ipairs(sections) do -- Don't bother processing empty strings or whitespace (which may also not be handled well by dedicated -- modules). if gsub(section, "%s+", "") ~= "" then local sub, this_actual_substitution_data = doSubstitutions(self, section, sc, substitution_data, data_field, function_name) actual_substitution_data = this_actual_substitution_data -- Second round of temporary substitutions, in case any formatting was added by the main substitution -- process. However, don't do this if the section contains formatting already (as it would have had to have -- been escaped to reach this stage, and therefore should be given as raw text). if sub and subbedChars then local noSub for _, pattern in ipairs(require(languages_data_patterns_module)) do if match(section, pattern .. "%z?") then noSub = true end end if not noSub then sub, subbedChars = doTempSubstitutions(sub, subbedChars, keepCarets, true) end end if not sub then text = sub break end text = sub and gsub(text, pattern_escape(section), replacement_escape(sub), 1) or text end end if not notrim then -- Trim, unless there are only spacing characters, while ignoring any final formatting characters. -- Do not trim sort keys because spaces at the beginning are significant. text = text and text:gsub("^([\128-\191\244]*)%s+(%S)", "%1%2"):gsub("(%S)%s+([\128-\191\244]*)$", "%1%2") or nil end return text, subbedChars, actual_substitution_data end -- Process carets (and any escapes). Default to simple removal, if no pattern/replacement is given. local function processCarets(text, pattern, repl) local rep repeat text, rep = gsub(text, "\\\\(\\*^)", "\3%1") until rep == 0 return (text:gsub("\\^", "\4") :gsub(pattern or "%^", repl or "") :gsub("\3", "\\") :gsub("\4", "^")) end -- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped). local function removeCarets(text, sc) if not sc:hasCapitalization() and sc:isTransliterated() and text:find("^", 1, true) then return processCarets(text) else return text end end local Language = {} --[==[ Return the language code of the language. Example: {fr"} for French. ]==] function Language:getCode() return self._code end --[==[ Return the canonical name of the language. This is the name used to represent that language on Wiktionary, and is guaranteed to be unique to that language alone. Example: {"French"} for French. ]==] function Language:getCanonicalName() local name = self._name if name == nil then name = self._data[1] self._name = name end return name end --[==[ Return the display form of the language. The display form of a language, family or script is the form it takes when appearing as the <code><var>source</var></code> in categories such as <code>English terms derived from <var>source</var></code> or <code>English given names from <var>source</var></code>, and is also the displayed text in `##makeCategoryLink()` links. For full and etymology-only languages, this is the same as the canonical name, but for families, it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}), and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). ]==] function Language:getDisplayForm() local form = self._displayForm if form == nil then form = self:getCanonicalName() -- Add article and " substrate" to substrates that lack them. if self:getFamilyCode() == "qfa-sub" then if not (sub(form, 1, 4) == "the " or sub(form, 1, 2) == "a ") then form = "a " .. form end if not match(form, " [Ss]ubstrate") then form = form .. " substrate" end end self._displayForm = form end return form end --[==[ Return the value which should be used in the HTML `lang=` attribute for tagged text in the language. ]==] function Language:getHTMLAttribute(sc, region) local code = self._code if not find(code, "-", 1, true) then return code .. "-" .. sc:getCode() .. (region and "-" .. region or "") end local parent = self:getParent() region = region or match(code, "%f[%u][%u-]+%f[%U]") if parent then return parent:getHTMLAttribute(sc, region) end -- TODO: ISO family codes can also be used. return "mis-" .. sc:getCode() .. (region and "-" .. region or "") end --[==[ Return a list of the aliases that the language is known by, excluding the canonical name. Aliases are synonyms for the language in question. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: { {"High German", "New High German", "Deutsch"}} for {{lnl|de}}. ]==] function Language:getAliases() self:loadInExtraData() return require(language_like_module).getAliases(self) end --[==[ Return a list of the known subvarieties of a given language, excluding subvarieties that have been given explicit etymology-only language codes. The names are not guaranteed to be unique, in that sometimes a given name refers to a subvariety of more than one language. Example: { {"Southern Aymara", "Central Aymara"}} for {{lnl|ay}}. Note that the returned value can have nested tables in it, when a subvariety goes by more than one name. Example: { {"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor"}} for {{lnl|az}}. Here, for example, Afshar, Afshari, Afshar Azerbaijani and Afchar all refer to the same subvariety, whose preferred name is Afshar (the one listed first). To avoid a return value with nested tables in it, specify a non-{nil} value for the `flatten` parameter; in that case, the return value would be { {"North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"}}. ]==] function Language:getVarieties(flatten) self:loadInExtraData() return require(language_like_module).getVarieties(self, flatten) end --[==[ Return a table of the "other names" that the language is known by, which are listed in the `other_names` field in the language's extra-data module. It should be noted that the `other_names` field itself is deprecated, and entries listed there should eventually be moved to either `aliases` or `varieties`, or removed if they refer to larger entities which the language in question is actually a part of. ]==] function Language:getOtherNames() -- To be eventually removed, once there are no more uses of the `other_names` field. self:loadInExtraData() return require(language_like_module).getOtherNames(self) end --[==[ Return a combined table of the canonical name, aliases, varieties and other names of a given language. ]==] function Language:getAllNames() self:loadInExtraData() return require(language_like_module).getAllNames(self) end --[==[ Return a table of types as a set (with the types as keys). The possible types are * {language}: This is a language, either full or etymology-only. * {full}: This is a "full" (not etymology-only) language, i.e. the union of {regular}, {reconstructed} and {appendix-constructed}. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for a full language and you have an object that might be a family, you should use {hasType("language", "full")} and not simply {hasType("full")}. * {etymology-only}: This is an etymology-only (not full) language, whose parent is another etymology-only language or a full language. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for an etymology-only language and you have an object that might be a family, you should use {hasType("language", "etymology-only")} and not simply {hasType("etymology-only")}. * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with `*` to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with `*`. Languages such as Proto-Indo-European and Proto-Germanic are in this category. '''Exception:''' Reconstructed languages can have entries in the mainspace using the ''anti-asterisk'' feature. This requires that both the headword for the mainspace term (as specified using {{para|head}}) and links to the term are prefixed with the anti-asterisk indicator `!!`. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ]==] function Language:getTypes() local types = self._types if types == nil then types = {language = true} if self:getFullCode() == self._code then types.full = true else types["etymology-only"] = true end for t in gmatch(self._data.type, "[^,]+") do types[t] = true end self._types = types end return types end --[==[ Given a list of types as strings, return {true} if the language has all of them. ]==] function Language:hasType(...) Language.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[ Return a list containing `WikimediaLanguage` objects (see [[Module:wikimedia languages]]), which represent languages and their codes as they are used in Wikimedia projects for interwiki linking and such. More than one object may be returned, as a single Wiktionary language may correspond to multiple Wikimedia languages. For example, Wiktionary's single code `sh` (Serbo-Croatian) maps to four Wikimedia codes: `sh` (Serbo-Croatian), `bs` (Bosnian), `hr` (Croatian) and `sr` (Serbian). The code for the Wikimedia language is retrieved from the `wikimedia_codes` property in the data modules. If that property is not present, the code of the current language is used. If none of the available codes is actually a valid Wikimedia code, an empty list is returned. ]==] function Language:getWikimediaLanguages() local wm_langs = self._wikimediaLanguageObjects if wm_langs == nil then local codes = self:getWikimediaLanguageCodes() wm_langs = {} for i = 1, #codes do wm_langs[i] = get_wikimedia_lang(codes[i]) end self._wikimediaLanguageObjects = wm_langs end return wm_langs end function Language:getWikimediaLanguageCodes() local wm_langs = self._wikimediaLanguageCodes if wm_langs == nil then wm_langs = self._data.wikimedia_codes if wm_langs then wm_langs = split(wm_langs, ",", true, true) else local code = self._code if is_known_language_tag(code) then wm_langs = {code} else -- Inherit, but only if no codes are specified in the data *and* -- the language code isn't a valid Wikimedia language code. local parent = self:getParent() wm_langs = parent and parent:getWikimediaLanguageCodes() or {} end end self._wikimediaLanguageCodes = wm_langs end return wm_langs end --[==[ Return the name of the Wikipedia article for the language. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, `##Language:getCategoryName` is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the language's category, but this won't normally happen for any other project. ]==] function Language:getWikipediaArticle(noCategoryFallback, project) Language.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Language:makeWikipediaLink() return make_link(self, "w:" .. self:getWikipediaArticle(), self:getCanonicalName()) end --[==[ Return the name of the Wikimedia Commons category page for the language. ]==] function Language:getCommonsCategory() Language.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end --[==[ Return the Wikidata item ID for the language or {nil}. This corresponds to the the second field in the data modules. ]==] function Language:getWikidataItem() Language.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[ Return a list of `Script` objects for all scripts that the language is written in. See [[Module:scripts]]. ]==] function Language:getScripts() local scripts = self._scriptObjects if scripts == nil then local codes = self:getScriptCodes() if codes[1] == "All" then scripts = load_data(scripts_data_module) else scripts = {} for i = 1, #codes do scripts[i] = get_script(codes[i]) end end self._scriptObjects = scripts end return scripts end --[==[ Return the list of script codes in the language's data file. ]==] function Language:getScriptCodes() local scripts = self._scriptCodes if scripts == nil then scripts = self._data[4] if scripts then local codes, n = {}, 0 for code in gmatch(scripts, "[^,]+") do n = n + 1 -- Special handling of "Hants", which represents "Hani", "Hant" and "Hans" collectively. if code == "Hants" then codes[n] = "Hani" codes[n + 1] = "Hant" codes[n + 2] = "Hans" n = n + 2 else codes[n] = code end end scripts = codes else scripts = {"None"} end self._scriptCodes = scripts end return scripts end --[==[ Given some text, iterate through the scripts of a given language trying to find the script that best matches the text. Return a {Script} object representing the script. If no match is found at all, it returns the {None} script object. ]==] function Language:findBestScript(text, forceDetect) if not text or text == "" or text == "-" then return get_script("None") end -- Differs from table returned by getScriptCodes, as Hants is not normalized into its constituents. local codes = self._bestScriptCodes if codes == nil then codes = self._data[4] codes = codes and split(codes, ",", true, true) or {"None"} self._bestScriptCodes = codes end local first_sc = codes[1] if first_sc == "All" then return find_best_script_without_lang(text) end local codes_len = #codes if not (forceDetect or first_sc == "Hants" or codes_len > 1) then first_sc = get_script(first_sc) local charset = first_sc.characters return charset and umatch(text, "[" .. charset .. "]") and first_sc or get_script("None") end -- Remove all formatting characters. text = get_plaintext(text) -- Remove all spaces and any ASCII punctuation. Some non-ASCII punctuation is script-specific, so can't be removed. text = ugsub(text, "[%s!\"#%%&'()*,%-./:;?@[\\%]_{}]+", "") if #text == 0 then return get_script("None") end -- Try to match every script against the text, -- and return the one with the most matching characters. local bestcount, bestscript, length = 0 for i = 1, codes_len do local sc = codes[i] -- Special case for "Hants", which is a special code that represents whichever of "Hant" or "Hans" best matches, -- or "Hani" if they match equally. This avoids having to list all three. In addition, "Hants" will be treated -- as the best match if there is at least one matching character, under the assumption that a Han script is -- desirable in terms that contain a mix of Han and other scripts (not counting those which use Jpan or Kore). if sc == "Hants" then local Hani = get_script("Hani") if not Hant_chars then Hant_chars = load_data("Module:zh/data/ts") Hans_chars = load_data("Module:zh/data/st") end local t, s, found = 0, 0 -- This is faster than using mw.ustring.gmatch directly. for ch in gmatch((ugsub(text, "[" .. Hani.characters .. "]", "\255%0")), "\255(.[\128-\191]*)") do found = true if Hant_chars[ch] then t = t + 1 if Hans_chars[ch] then s = s + 1 end elseif Hans_chars[ch] then s = s + 1 else t, s = t + 1, s + 1 end end if found then if t == s then return Hani end return get_script(t > s and "Hant" or "Hans") end else sc = get_script(sc) if not length then length = ulen(text) end -- Count characters by removing everything in the script's charset and comparing to the original length. local charset = sc.characters local count = charset and length - ulen((ugsub(text, "[" .. charset .. "]+", ""))) or 0 if count >= length then return sc elseif count > bestcount then bestcount = count bestscript = sc end end end -- Return best matching script, or otherwise None. return bestscript or get_script("None") end --[==[ Return a `Family` object for the language family that the language belongs to. See [[Module:families]]. ]==] function Language:getFamily() local family = self._familyObject if family == nil then family = self:getFamilyCode() -- If the value is nil, it's cached as false. family = family and get_family(family) or false self._familyObject = family end return family or nil end --[==[ Return the family code in the language's data file. ]==] function Language:getFamilyCode() local family = self._familyCode if family == nil then -- If the value is nil, it's cached as false. family = self._data[3] or false self._familyCode = family end return family or nil end function Language:getFamilyName() local family = self._familyName if family == nil then family = self:getFamily() -- If the value is nil, it's cached as false. family = family and family:getCanonicalName() or false self._familyName = family end return family or nil end do local function check_family(self, family) if type(family) == "table" then family = family:getCode() end if self:getFamilyCode() == family then return true end local self_family = self:getFamily() if self_family:inFamily(family) then return true -- If the family isn't a real family (e.g. creoles) check any ancestors. elseif self_family:inFamily("qfa-not") then local ancestors = self:getAncestors() for _, ancestor in ipairs(ancestors) do if ancestor:inFamily(family) then return true end end end end --[==[ Check whether the language belongs to `family` (which can be a family code or object). A list of objects can be given in place of `family`; in that case, return true if the language belongs to any of the specified families. Note that some languages (in particular, certain creoles) can have multiple immediate ancestors potentially belonging to different families; in that case, return true if the language belongs to any of the specified families. ]==] function Language:inFamily(...) if self:getFamilyCode() == nil then return false end return check_inputs(self, check_family, false, ...) end end function Language:getParent() local parent = self._parentObject if parent == nil then parent = self:getParentCode() -- If the value is nil, it's cached as false. parent = parent and get_by_code(parent, nil, true, true) or false self._parentObject = parent end return parent or nil end function Language:getParentCode() local parent = self._parentCode if parent == nil then -- If the value is nil, it's cached as false. parent = self._data.parent or false self._parentCode = parent end return parent or nil end function Language:getParentName() local parent = self._parentName if parent == nil then parent = self:getParent() -- If the value is nil, it's cached as false. parent = parent and parent:getCanonicalName() or false self._parentName = parent end return parent or nil end function Language:getParentChain() local chain = self._parentChain if chain == nil then chain = {} local parent, n = self:getParent(), 0 while parent do n = n + 1 chain[n] = parent parent = parent:getParent() end self._parentChain = chain end return chain end --[==[ Return a list of the pseudo-families (if any) that a language belongs to. The returned value is a list of Family objects. Pseudo-families are groupings of languages that are not clades but share some geographic, ethnic or other characteristic (e.g. [[:Category:Papuan languages]], [[:Category:Jewish languages]]). ]==] function Language:getPseudoFamilies() self:loadInExtraData() return require(language_like_module).getPseudoFamilies(self) end do local function check_lang(self, lang) for _, parent in ipairs(self:getParentChain()) do if (type(lang) == "string" and lang or lang:getCode()) == parent:getCode() then return true end end end function Language:hasParent(...) return check_inputs(self, check_lang, false, ...) end end --[==[ If the language is etymology-only, iterate through parents until a full language or family is found, and the corresponding object is returned. If the language is a full language, return that language. ]==] function Language:getFull() local full = self._fullObject if full == nil then full = self:getFullCode() full = full == self._code and self or get_by_code(full) self._fullObject = full end return full end --[==[ If the language is an etymology-only language, iterate through parents until a full language or family is found, and the corresponding code is returned. If the language is a full language, return that language's code. ]==] function Language:getFullCode() return self._fullCode or self._code end --[==[ If the language is an etymology-only language, iterate through parents until a full language or family is found, and the corresponding canonical name is returned. If the language is a full language, return that language's canonical name. ]==] function Language:getFullName() local full = self._fullName if full == nil then full = self:getFull():getCanonicalName() self._fullName = full end return full end --[==[ Return a list of {Language} objects for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors. ]==] function Language:getAncestors() local ancestors = self._ancestorObjects if ancestors == nil then ancestors = {} local ancestor_codes = self:getAncestorCodes() if #ancestor_codes > 0 then for _, ancestor in ipairs(ancestor_codes) do insert(ancestors, get_by_code(ancestor, nil, true)) end else local fam = self:getFamily() local protoLang = fam and fam:getProtoLanguage() or nil -- For the cases where the current language is the proto-language -- of its family, or an etymology-only language that is ancestral to that -- proto-language, we need to step up a level higher right from the -- start. if protoLang and ( protoLang:getCode() == self._code or (self:hasType("etymology-only") and protoLang:hasAncestor(self)) ) then fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end while not protoLang and not (not fam or fam:getCode() == "qfa-not") do fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end insert(ancestors, protoLang) end self._ancestorObjects = ancestors end return ancestors end do -- Avoid a language being its own ancestor via class inheritance. We only need to check for this if the language has -- inherited an ancestor table from its parent, because we never want to drop ancestors that have been explicitly -- set in the data. Recursively iterate over ancestors until we either find self or run out. If self is found, -- return true. local function check_ancestor(self, lang) local codes = lang:getAncestorCodes() if not codes then return nil end for i = 1, #codes do local code = codes[i] if code == self._code then return true end local anc = get_by_code(code, nil, true) if check_ancestor(self, anc) then return true end end end --[==[ Return a list of `Language` codes for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors. ]==] function Language:getAncestorCodes() if self._ancestorCodes then return self._ancestorCodes end local data = self._data local codes = data.ancestors if codes == nil then codes = {} self._ancestorCodes = codes return codes end codes = split(codes, ",", true, true) self._ancestorCodes = codes -- If there are no codes or the ancestors weren't inherited data, there's nothing left to check. if #codes == 0 or self:getData(false, "raw").ancestors ~= nil then return codes end local i = 1 while i <= #codes do if check_ancestor(self, self) then remove(codes, i) else i = i + 1 end end return codes end end --[==[ Given a list of language objects or codes, return true if at least one of them is an ancestor. This includes any etymology-only children of that ancestor. If the language's ancestor(s) are etymology-only languages, it will also return true for those language parent(s) (e.g. if Vulgar Latin is the ancestor, it will also return true for its parent, Latin). However, a parent is excluded from this if the ancestor is also ancestral to that parent (e.g. if Classical Persian is the ancestor, Persian would return {false}, because Classical Persian is also ancestral to Persian). ]==] function Language:hasAncestor(...) local function iterateOverAncestorTree(node, func, parent_check) local ancestors = node:getAncestors() local ancestorsParents = {} for _, ancestor in ipairs(ancestors) do -- When checking the parents of the other language, and the ancestor is also a parent, skip to the next -- ancestor, so that we exclude any etymology-only children of that parent that are not directly related -- (see below). local ret = (parent_check or not node:hasParent(ancestor)) and func(ancestor) or iterateOverAncestorTree(ancestor, func, parent_check) if ret then return ret end end -- Check the parents of any ancestors. We don't do this if checking the parents of the other language, so that -- we exclude any etymology-only children of those parents that are not directly related (e.g. if the ancestor -- is Vulgar Latin and we are checking New Latin, we want it to return false because they are on different -- ancestral branches. As such, if we're already checking the parent of New Latin (Latin) we don't want to -- compare it to the parent of the ancestor (Latin), as this would be a false positive; it should be one or the -- other). if not parent_check then return nil end for _, ancestor in ipairs(ancestors) do local ancestorParents = ancestor:getParentChain() for _, ancestorParent in ipairs(ancestorParents) do if ancestorParent:getCode() == self._code or ancestorParent:hasAncestor(ancestor) then break else insert(ancestorsParents, ancestorParent) end end end for _, ancestorParent in ipairs(ancestorsParents) do local ret = func(ancestorParent) if ret then return ret end end end local function do_iteration(otherlang, parent_check) -- otherlang can't be self if (type(otherlang) == "string" and otherlang or otherlang:getCode()) == self._code then return false end repeat if iterateOverAncestorTree( self, function(ancestor) return ancestor:getCode() == (type(otherlang) == "string" and otherlang or otherlang:getCode()) end, parent_check ) then return true elseif type(otherlang) == "string" then otherlang = get_by_code(otherlang, nil, true) end otherlang = otherlang:getParent() parent_check = false until not otherlang end local parent_check = true for _, otherlang in ipairs{...} do local ret = do_iteration(otherlang, parent_check) if ret then return true end end return false end do local function construct_node(lang, memo) local branch, ancestors = {lang = lang:getCode()} memo[lang:getCode()] = branch for _, ancestor in ipairs(lang:getAncestors()) do if ancestors == nil then ancestors = {} end insert(ancestors, memo[ancestor:getCode()] or construct_node(ancestor, memo)) end branch.ancestors = ancestors return branch end function Language:getAncestorChain() local chain = self._ancestorChain if chain == nil then chain = construct_node(self, {}) self._ancestorChain = chain end return chain end end function Language:getAncestorChainOld() local chain = self._ancestorChain if chain == nil then chain = {} local step = self while true do local ancestors = step:getAncestors() step = #ancestors == 1 and ancestors[1] or nil if not step then break end insert(chain, step) end self._ancestorChain = chain end return chain end local function fetch_descendants(self, fmt) local descendants, family = {}, self:getFamily() -- Iterate over all three datasets. for _, data in ipairs{ require("Module:languages/code to canonical name"), require("Module:etymology languages/code to canonical name"), require("Module:families/code to canonical name"), } do for code in pairs(data) do local lang = get_by_code(code, nil, true, true) if not lang then error(("Internal error: code '%s' can't be fetched"):format(code)) end -- Test for a descendant. Earlier tests weed out most candidates, while the more intensive tests are only used sparingly. if ( code ~= self._code and -- Not self. lang:inFamily(family) and -- In the same family. ( family:getProtoLanguageCode() == self._code or -- Self is the protolanguage. self:hasDescendant(lang) or -- Full hasDescendant check. (lang:getFullCode() == self._code and not self:hasAncestor(lang)) -- Etymology-only child which isn't an ancestor. ) ) then if fmt == "object" then insert(descendants, lang) elseif fmt == "code" then insert(descendants, code) elseif fmt == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Language:getDescendants() local descendants = self._descendantObjects if descendants == nil then descendants = fetch_descendants(self, "object") self._descendantObjects = descendants end return descendants end function Language:getDescendantCodes() local descendants = self._descendantCodes if descendants == nil then descendants = fetch_descendants(self, "code") self._descendantCodes = descendants end return descendants end function Language:getDescendantNames() local descendants = self._descendantNames if descendants == nil then descendants = fetch_descendants(self, "name") self._descendantNames = descendants end return descendants end do local function check_lang(self, lang) if type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasAncestor(self) then return true end end function Language:hasDescendant(...) return check_inputs(self, check_lang, false, ...) end end local function fetch_children(self, fmt) local m_etym_data = require(etymology_languages_data_module) local self_code, children = self._code, {} for code, lang in pairs(m_etym_data) do local _lang = lang repeat local parent = _lang.parent if parent == self_code then if fmt == "object" then insert(children, get_by_code(code, nil, true)) elseif fmt == "code" then insert(children, code) elseif fmt == "name" then insert(children, lang[1]) end break end _lang = m_etym_data[parent] until not _lang end return children end function Language:getChildren() local children = self._childObjects if children == nil then children = fetch_children(self, "object") self._childObjects = children end return children end function Language:getChildrenCodes() local children = self._childCodes if children == nil then children = fetch_children(self, "code") self._childCodes = children end return children end function Language:getChildrenNames() local children = self._childNames if children == nil then children = fetch_children(self, "name") self._childNames = children end return children end function Language:hasChild(...) local lang = ... if not lang then return false elseif type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasParent(self) then return true end return self:hasChild(select(2, ...)) end --[==[ Return the name of the main category of that language. Example: {French language"} for French, whose category is at [[:Category:French language]]. Unless optional argument `nocap` is given, the language name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the language name is lowercase and the returned value of this function is used in the middle of a sentence. ]==] function Language:getCategoryName(nocap) local name = self._categoryName if name == nil then name = self:getCanonicalName() -- If a substrate, omit any leading article. if self:getFamilyCode() == "qfa-sub" then name = name:gsub("^the ", ""):gsub("^a ", "") end -- Only add " language" if a full language. if self:hasType("full") then -- Unless the canonical name already ends with "language", "lect" or their derivatives, add " language". if not (match(name, "[Ll]anguage$") or match(name, "[Ll]ect$")) then name = name .. " language" end end self._categoryName = name end if nocap then return name end return mw.getContentLanguage():ucfirst(name) end --[==[ Create a link to the category; the link text is the canonical name. ]==] function Language:makeCategoryLink() return make_link(self, ":Category:" .. self:getCategoryName(), self:getDisplayForm()) end function Language:getStandardCharacters(sc) local standard_chars = self._data.standard_chars if type(standard_chars) ~= "table" then return standard_chars elseif sc and type(sc) ~= "string" then check_object("script", nil, sc) sc = sc:getCode() end if (not sc) or sc == "None" then local scripts = {} for _, script in pairs(standard_chars) do insert(scripts, script) end return concat(scripts) end if standard_chars[sc] then return standard_chars[sc] .. (standard_chars[1] or "") end end --[==[ Strip diacritics from display text `text` (in a language-specific fashion), which is in the script `sc`. If `sc` is omitted or {nil}, the script is autodetected. This also strips certain punctuation characters from the end and (in the case of Spanish upside-down question mark and exclamation points) from the beginning; strips any whitespace at the end of the text or between the text and final stripped punctuation characters; and applies some language-specific Unicode normalizations to replace discouraged characters with their prescribed alternatives. Return the stripped text. ]==] function Language:stripDiacritics(text, sc) if (not text) or text == "" then return text end sc = checkScript(text, self, sc) text = normalize(text, sc) -- FIXME, rename makeEntryName to stripDiacritics and get rid of second and third return values -- everywhere local _ text, _, _ = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.strip_diacritics or self._data.entry_name, "strip_diacritics", "stripDiacritics") text = umatch(text, "^[¿¡]?(.-[^%s%p].-)%s*[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]?$") or text return text end --[==[ Convert a ''logical'' pagename (the pagename as it appears to the user, after diacritics and punctuation have been stripped) to a ''physical'' pagename (the pagename as it appears in the MediaWiki database). Reasons for a difference between the two are (a) unsupported titles such as `[ ]` (with square brackets in them), `#` (pound/hash sign) and `¯\_(ツ)_/¯` (with underscores), as well as overly long titles of various sorts; (b) "mammoth" pages that are split into parts (e.g. `a`, which is split into physical pagenames `a/languages A to L` and `a/languages M to Z`). For almost all purposes, you should work with logical and not physical pagenames. But there are certain use cases that require physical pagenames, such as checking the existence of a page or retrieving a page's contents. `pagename` is the logical pagename to be converted. `is_reconstructed_or_appendix` indicates whether the page is in the `Reconstruction` or `Appendix` namespaces. If it is omitted or has the value {nil}, the pagename is checked for an initial asterisk, and if found, the page is assumed to be a `Reconstruction` page. Setting a value of `false` or `true` to `is_reconstructed_or_appendix` disables this check and allows for mainspace pagenames that begin with an asterisk. ]==] function Language:logicalToPhysical(pagename, is_reconstructed_or_appendix) -- FIXME: This probably shouldn't happen but it happens when makeEntryName() receives nil. if pagename == nil then track("nil-passed-to-logicalToPhysical") return nil end local initial_asterisk if is_reconstructed_or_appendix == nil then local pagename_minus_initial_asterisk initial_asterisk, pagename_minus_initial_asterisk = pagename:match("^(%*)(.*)$") if pagename_minus_initial_asterisk then is_reconstructed_or_appendix = true pagename = pagename_minus_initial_asterisk elseif self:hasType("appendix-constructed") then is_reconstructed_or_appendix = true end end if not is_reconstructed_or_appendix then -- Check if the pagename is a listed unsupported title. local unsupportedTitles = load_data(links_data_module).unsupported_titles if unsupportedTitles[pagename] then return "Unsupported titles/" .. unsupportedTitles[pagename] end end -- Set `unsupported` as true if certain conditions are met. local unsupported -- Check if there's an unsupported character. \239\191\189 is the replacement character U+FFFD, which can't be typed -- directly here due to an abuse filter. Unix-style dot-slash notation is also unsupported, as it is used for -- relative paths in links, as are 3 or more consecutive tildes. Note: match is faster with magic -- characters/charsets; find is faster with plaintext. if ( match(pagename, "[#<>%[%]_{|}]") or find(pagename, "\239\191\189") or match(pagename, "%f[^%z/]%.%.?%f[%z/]") or find(pagename, "~~~") ) then unsupported = true -- If it looks like an interwiki link. elseif find(pagename, ":") then local prefix = gsub(pagename, "^:*(.-):.*", ulower) if ( load_data("Module:data/namespaces")[prefix] or load_data("Module:data/interwikis")[prefix] ) then unsupported = true end end -- Escape unsupported characters so they can be used in titles. ` is used as a delimiter for this, so a raw use of -- it in an unsupported title is also escaped here to prevent interference; this is only done with unsupported -- titles, though, so inclusion won't in itself mean a title is treated as unsupported (which is why it's excluded -- from the earlier test). if unsupported then -- FIXME: This conversion needs to be different for reconstructed pages with unsupported characters. There -- aren't any currently, but if there ever are, we need to fix this e.g. to put them in something like -- Reconstruction:Proto-Indo-European/Unsupported titles/`lowbar``num`. local unsupported_characters = load_data(links_data_module).unsupported_characters pagename = pagename:gsub("[#<>%[%]_`{|}\239]\191?\189?", unsupported_characters) :gsub("%f[^%z/]%.%.?%f[%z/]", function(m) return (gsub(m, "%.", "`period`")) end) :gsub("~~~+", function(m) return (gsub(m, "~", "`tilde`")) end) pagename = "Unsupported titles/" .. pagename elseif not is_reconstructed_or_appendix then -- Check if this is a mammoth page. If so, which subpage should we link to? local m_links_data = load_data(links_data_module) local mammoth_page_type = m_links_data.mammoth_pages[pagename] if mammoth_page_type then local canonical_name = self:getFullName() if canonical_name ~= "Translingual" and canonical_name ~= "English" then local this_subpage local L2_sort_key = get_L2_sort_key(canonical_name) for _, subpage_spec in ipairs(m_links_data.mammoth_page_subpage_types[mammoth_page_type]) do -- unpack() fails utterly on data loaded using mw.loadData() even if offsets are given local subpage, pattern = subpage_spec[1], subpage_spec[2] if pattern == true or L2_sort_key:match(pattern) then this_subpage = subpage break end end if not this_subpage then error(("Internal error: Bad data in mammoth_page_subpage_pages in [[Module:links/data]] for mammoth page %s, type %s; last entry didn't have 'true' in it"):format( pagename, mammoth_page_type)) end pagename = pagename .. "/" .. this_subpage end end end return (initial_asterisk or "") .. pagename end --[==[ Strip the diacritics from a display pagename and convert the resulting logical pagename into a physical pagename. This allows you, for example, to retrieve the contents of the page or check its existence. WARNING: This is deprecated and will be going away. It is a simple composition of `##Language:stripDiacritics` and `##Language:logicalToPhysical`; most callers only want the former, and if you need both, call them both yourself. `text` and `sc` are as in `##Language:stripDiacritics`, and `is_reconstructed_or_appendix` is as in `##Language:logicalToPhysical`. ]==] function Language:makeEntryName(text, sc, is_reconstructed_or_appendix) track("makeEntryName called") return self:logicalToPhysical(self:stripDiacritics(text, sc), is_reconstructed_or_appendix) end --[==[ Generate term alternants (e.g. simplified versions of traditional Chinese terms) using a language-specific method, and return them as a table. If the language provides no method for generating alternants, return a table containing only the input term. ]==] function Language:generateAlternants(text, sc) local generate_alternants = self._data.generate_alternants if generate_alternants == nil then return {text} end sc = checkScript(text, self, sc) return require("Module:" .. generate_alternants).generateAlternants(text, self, sc) end --[==[ Create a sort key for the given stripped text, following the rules appropriate for the language. This removes diacritical marks from the stripped text if they are not considered significant for sorting, and may perform some other changes. Any initial hyphen is also removed, and anything in parentheses is removed as well. The `sort_key` setting for each language in the data modules defines the replacements made by this function, or it gives the name of the module that takes the stripped text and returns a sortkey. ]==] function Language:makeSortKey(text, sc) if (not text) or text == "" then return text end if match(text, "<[^<>]+>") then track("track HTML tag") end -- Remove directionality/control characters, bold, italics, soft hyphens, strip markers and HTML tags. -- FIXME: Partly duplicated with remove_formatting() in [[Module:links]]. text = ugsub(text, "[\194\173\216\156\226\128\142\226\128\143\226\128\170-\226\128\174\226\129\166-\226\129\175]", "") text = text:gsub("('*)'''(.-'*)'''", "%1%2"):gsub("('*)''(.-'*)''", "%1%2") text = gsub(unstrip(text), "<[^<>]+>", "") text = decode_uri(text, "PATH") text = checkNoEntities(text) -- Remove initial hyphens and * unless the term only consists of spacing + punctuation characters. text = ugsub(text, "^([􀀀-􏿽]*)[-־ـ᠊*]+([􀀀-􏿽]*)(.*[^%s%p].*)", "%1%2%3") sc = checkScript(text, self, sc) text = normalize(text, sc) text = removeCarets(text, sc) -- For languages with dotted dotless i, ensure that "İ" is sorted as "i", and "I" is sorted as "ı". if self:hasDottedDotlessI() then text = gsub(text, "I\204\135", "i") -- decomposed "İ" :gsub("I", "ı") text = sc:toFixedNFD(text) end -- Convert to lowercase, make the sortkey, then convert to uppercase. Where the language has dotted dotless i, it is -- usually not necessary to convert "i" to "İ" and "ı" to "I" first, because "I" will always be interpreted as -- conventional "I" (not dotless "İ") by any sorting algorithms, which will have been taken into account by the -- sortkey substitutions themselves. However, if no sortkey substitutions have been specified, then conversion is -- necessary so as to prevent "i" and "ı" both being sorted as "I". -- -- An exception is made for scripts that (sometimes) sort by scraping page content, as that means they are sensitive -- to changes in capitalization (as it changes the target page). if not sc:sortByScraping() then text = ulower(text) end local actual_substitution_data, _ -- Don't trim whitespace here because it's significant at the beginning of a sort key or sort base. text, _, actual_substitution_data = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.sort_key, "sort_key", "makeSortKey", "notrim") if not sc:sortByScraping() then if self:hasDottedDotlessI() and not actual_substitution_data then text = text:gsub("ı", "I"):gsub("i", "İ") text = sc:toFixedNFC(text) end text = uupper(text) end -- Remove parentheses, as long as they are either preceded or followed by something. text = gsub(text, "(.)[()]+", "%1"):gsub("[()]+(.)", "%1") text = escape_risky_characters(text) return text end --[==[ Create the form used as as a basis for display text and transliteration. FIXME: Rename to correctInputText(). ]==] local function processDisplayText(text, self, sc, keepCarets, keepPrefixes) local subbedChars = {} text, subbedChars = doTempSubstitutions(text, subbedChars, keepCarets) text = decode_uri(text, "PATH") text = checkNoEntities(text) sc = checkScript(text, self, sc) text = normalize(text, sc) text, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, self._data.display_text, "display_text", "makeDisplayText") text = removeCarets(text, sc) -- Remove any interwiki link prefixes (unless they have been escaped or this has been disabled). if find(text, ":") and not keepPrefixes then local rep repeat text, rep = gsub(text, "\\\\(\\*:)", "\3%1") until rep == 0 text = gsub(text, "\\:", "\4") while true do local prefix = gsub(text, "^(.-):.+", function(m1) return (gsub(m1, "\244[\128-\191]*", "")) end) -- Check if the prefix is an interwiki, though ignore capitalised Wiktionary:, which is a namespace. if not prefix or prefix == text or prefix == "Wiktionary" or not (load_data("Module:data/interwikis")[ulower(prefix)] or prefix == "") then break end text = gsub(text, "^(.-):(.*)", function(m1, m2) local ret = {} for subbedChar in gmatch(m1, "\244[\128-\191]*") do insert(ret, subbedChar) end return concat(ret) .. m2 end) end text = gsub(text, "\3", "\\"):gsub("\4", ":") end return text, subbedChars end --[==[ Make the display text (i.e. what is displayed on the page). ]==] function Language:makeDisplayText(text, sc, keepPrefixes) if not text or text == "" then return text end local subbedChars text, subbedChars = processDisplayText(text, self, sc, nil, keepPrefixes) text = escape_risky_characters(text) return undoTempSubstitutions(text, subbedChars) end --[==[ Transliterate the text from the given script into Latin script (see [[Wiktionary:Transliteration and romanization]]). The language must have the `translit` property for this to work; if it is not present, {nil} is returned. The `sc` parameter is handled by the transliteration module, and how it is handled is specific to that module. Some transliteration modules may tolerate {nil} as the script, others require it to be one of the possible scripts that the module can transliterate, and will throw an error if it's not one of them. For this reason, the `sc` parameter should always be provided when writing non-language-specific code. The `module_override` parameter is used to override the default module that is used to provide the transliteration. This is useful in cases where you need to demonstrate a particular module in use, but there is no default module yet, or you want to demonstrate an alternative version of a transliteration module before making it official. It should not be used in real modules or templates, only for testing. All uses of this parameter are tracked by [[Wiktionary:Tracking/languages/module_override]]. '''Known bugs''': * This function assumes {tr(s1) .. tr(s2) == tr(s1 .. s2)}. When this assertion fails, wikitext markups like <nowiki>'''</nowiki> can cause wrong transliterations. * HTML entities like `&amp;apos;`, often used to escape wikitext markups, do not work. ]==] function Language:transliterate(text, sc, module_override) -- If there is no text, or the language doesn't have transliteration data and there's no override, return nil. if not text or text == "" or text == "-" then return text end -- If the script is not transliteratable (and no override is given), return nil. sc = checkScript(text, self, sc) if not (sc:isTransliterated() or module_override) then -- temporary tracking to see if/when this gets triggered track("non-transliterable") track("non-transliterable/" .. self._code) track("non-transliterable/" .. sc:getCode()) track("non-transliterable/" .. sc:getCode() .. "/" .. self._code) return nil end -- Remove any strip markers. text = unstrip(text) -- Do not process the formatting into PUA characters for certain languages. local processed = load_data(languages_data_module).substitution[self._code] ~= "none" -- Get the display text with the keepCarets flag set. local subbedChars if processed then text, subbedChars = processDisplayText(text, self, sc, true) end -- Transliterate (using the module override if applicable). text, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, true, module_override or self._data.translit, "translit", "tr") if not text then return nil end -- Incomplete transliterations return nil. local charset = sc.characters if charset and umatch(text, "[" .. charset .. "]") then -- Remove any characters in Latin, which includes Latin characters also included in other scripts (as these are -- false positives), as well as any PUA substitutions. Anything remaining should only be script code "None" -- (e.g. numerals). local check_text = ugsub(text, "[" .. get_script("Latn").characters .. "􀀀-􏿽]+", "") -- Set none_is_last_resort_only flag, so that any non-None chars will cause a script other than "None" to be -- returned. if find_best_script_without_lang(check_text, true):getCode() ~= "None" then return nil end end if processed then text = escape_risky_characters(text) text = undoTempSubstitutions(text, subbedChars) end -- If the script does not use capitalization, then capitalize any letters of the transliteration which are -- immediately preceded by a caret (and remove the caret). if text and not sc:hasCapitalization() and text:find("^", 1, true) then text = processCarets(text, "%^([\128-\191\244]*%*?)([^\128-\191\244][\128-\191]*)", function(m1, m2) return m1 .. uupper(m2) end) end -- Track module overrides. if module_override ~= nil then track("module_override") end return text end do local function handle_language_spec(self, spec, sc) local ret = self["_" .. spec] if ret == nil then ret = self._data[spec] if type(ret) == "string" then ret = list_to_set(split(ret, ",", true, true)) end self["_" .. spec] = ret end if type(ret) == "table" then ret = ret[sc:getCode()] end return not not ret end function Language:overrideManualTranslit(sc) return handle_language_spec(self, "override_translit", sc) end function Language:link_tr(sc) return handle_language_spec(self, "link_tr", sc) end end --[==[ Return {true} if the language has a transliteration module, or {false} if it doesn't. ]==] function Language:hasTranslit() return not not self._data.translit end --[==[ Return {true} if the language uses the letters I/ı and İ/i, or {false} if it doesn't.]==] function Language:hasDottedDotlessI() return not not self._data.dotted_dotless_i end function Language:toJSON(opts) local strip_diacritics, strip_diacritics_patterns, strip_diacritics_remove_diacritics = self._data.strip_diacritics if strip_diacritics then if strip_diacritics.from then strip_diacritics_patterns = {} for i, from in ipairs(strip_diacritics.from) do insert(strip_diacritics_patterns, {from = from, to = strip_diacritics.to[i] or ""}) end end strip_diacritics_remove_diacritics = strip_diacritics.remove_diacritics end -- mainCode should only end up non-nil if dontCanonicalizeAliases is passed to make_object(). -- props should either contain zero-argument functions to compute the value, or the value itself. local props = { ancestors = function() return self:getAncestorCodes() end, canonicalName = function() return self:getCanonicalName() end, categoryName = function() return self:getCategoryName("nocap") end, code = self._code, mainCode = self._mainCode, parent = function() return self:getParentCode() end, full = function() return self:getFullCode() end, stripDiacriticsPatterns = strip_diacritics_patterns, stripDiacriticsRemoveDiacritics = strip_diacritics_remove_diacritics, family = function() return self:getFamilyCode() end, aliases = function() return self:getAliases() end, varieties = function() return self:getVarieties() end, otherNames = function() return self:getOtherNames() end, pseudoFamilies = function() return self:getPseudoFamilies() end, scripts = function() return self:getScriptCodes() end, type = function() return keys_to_list(self:getTypes()) end, wikimediaLanguages = function() return self:getWikimediaLanguageCodes() end, wikidataItem = function() return self:getWikidataItem() end, wikipediaArticle = function() return self:getWikipediaArticle(true) end, } local ret = {} for prop, val in pairs(props) do if not opts.skip_fields or not opts.skip_fields[prop] then if type(val) == "function" then ret[prop] = val() else ret[prop] = val end end end -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function export.getDataModuleName(code) local letter = match(code, "^(%l)%l%l?$") return "Module:" .. ( letter == nil and "languages/data/exceptional" or #code == 2 and "languages/data/2" or "languages/data/3/" .. letter ) end get_data_module_name = export.getDataModuleName function export.getExtraDataModuleName(code) return get_data_module_name(code) .. "/extra" end get_extra_data_module_name = export.getExtraDataModuleName do local function make_stack(data) local key_types = { [2] = "unique", aliases = "unique", other_names = "unique", type = "append", varieties = "unique", wikipedia_article = "unique", wikimedia_codes = "unique" } local function __index(self, k) local stack, key_type = getmetatable(self), key_types[k] -- Data that isn't inherited from the parent. if key_type == "unique" then local v = stack[stack[make_stack]][k] if v == nil then local layer = stack[0] if layer then -- Could be false if there's no extra data. v = layer[k] end end return v -- Data that is appended by each generation. elseif key_type == "append" then local parts, offset, n = {}, 0, stack[make_stack] for i = 1, n do local part = stack[i][k] if part == nil then offset = offset + 1 else parts[i - offset] = part end end return offset ~= n and concat(parts, ",") or nil end local n = stack[make_stack] while true do local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end local v = layer[k] if v ~= nil then return v end n = n - 1 end end local function __newindex() error("table is read-only") end local function __pairs(self) -- Iterate down the stack, caching keys to avoid duplicate returns. local stack, seen = getmetatable(self), {} local n = stack[make_stack] local iter, state, k, v = pairs(stack[n]) return function() repeat repeat k = iter(state, k) if k == nil then n = n - 1 local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end iter, state, k = pairs(layer) end until not (k == nil or seen[k]) -- Get the value via a lookup, as the one returned by the -- iterator will be the raw value from the current layer, -- which may not be the one __index will return for that -- key. Also memoize the key in `seen` (even if the lookup -- returns nil) so that it doesn't get looked up again. -- TODO: store values in `self`, avoiding the need to create -- the `seen` table. The iterator will need to iterate over -- `self` with `next` first to find these on future loops. v, seen[k] = self[k], true until v ~= nil return k, v end end local __ipairs = require(table_module).indexIpairs function make_stack(data) local stack = { data, [make_stack] = 1, -- stores the length and acts as a sentinel to confirm a given metatable is a stack. __index = __index, __newindex = __newindex, __pairs = __pairs, __ipairs = __ipairs, } stack.__metatable = stack return setmetatable({}, stack), stack end return make_stack(data) end local function get_stack(data) local stack = getmetatable(data) return stack and type(stack) == "table" and stack[make_stack] and stack or nil end --[==[ <span style="color: var(--wikt-palette-red,#BA0000)">This function is not for use in entries or other content pages.</span> Return a blob of data about the language. The format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes. If `extra` is set, any extra data in the relevant `/extra` module will be included. (Note that it will be included anyway if it has already been loaded into the language object.) If `raw` is set, then the returned data will not contain any data inherited from parent objects. -- Do NOT use these methods! -- All uses should be pre-approved on the talk page! ]==] function Language:getData(extra, raw) if extra then self:loadInExtraData() end local data = self._data -- If raw is not set, just return the data. if not raw then return data end local stack = get_stack(data) -- If there isn't a stack or its length is 1, return the data. Extra data (if any) will be included, as it's -- stored at key 0 and doesn't affect the reported length. if stack == nil then return data end local n = stack[make_stack] if n == 1 then return data end extra = stack[0] -- If there isn't any extra data, return the top layer of the stack. if extra == nil then return stack[n] end -- If there is, return a new stack which has the top layer at key 1 and the extra data at key 0. data, stack = make_stack(stack[n]) stack[0] = extra return data end function Language:loadInExtraData() -- Only full languages have extra data. if not self:hasType("language", "full") then return end local data = self._data -- If there's no stack, create one. local stack = get_stack(self._data) if stack == nil then data, stack = make_stack(data) -- If already loaded, return. elseif stack[0] ~= nil then return end self._data = data -- Load extra data from the relevant module and add it to the stack at key 0, so that the __index and __pairs -- metamethods will pick it up, since they iterate down the stack until they run out of layers. local code = self._code local modulename = get_extra_data_module_name(code) -- No data cached as false. stack[0] = modulename and load_data(modulename)[code] or false end --[==[ Return the name of the module containing the language's data, e.g. [[Module:languages/data/3/k]] for three-letter codes beginning with `k`. ]==] function Language:getDataModuleName() local name = self._dataModuleName if name == nil then name = self:hasType("etymology-only") and etymology_languages_data_module or get_data_module_name(self._mainCode or self._code) self._dataModuleName = name end return name end --[==[ Return the name of the module containing the language's extra data, e.g. [[Module:languages/data/3/k/extra]] for three-letter codes beginning with `k`. ]==] function Language:getExtraDataModuleName() local name = self._extraDataModuleName if name == nil then name = not self:hasType("etymology-only") and get_extra_data_module_name(self._mainCode or self._code) or false self._extraDataModuleName = name end return name or nil end function export.makeObject(code, data, dontCanonicalizeAliases) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end -- Convert any aliases. local input_code = code code = normalize_code(code) input_code = dontCanonicalizeAliases and input_code or code local parent if data.parent then parent = get_by_code(data.parent, nil, true, true) else parent = Language end parent.__index = parent local lang = {_code = input_code} -- This can only happen if dontCanonicalizeAliases is passed to make_object(). if code ~= input_code then lang._mainCode = code end local parent_data = parent._data if parent_data == nil then -- Full code is the same as the code. lang._fullCode = parent._code or code else -- Copy full code. lang._fullCode = parent._fullCode local stack = get_stack(parent_data) if stack == nil then parent_data, stack = make_stack(parent_data) end -- Insert the input data as the new top layer of the stack. local n = stack[make_stack] + 1 data, stack[n], stack[make_stack] = parent_data, data, n end lang._data = data return setmetatable(lang, parent) end make_object = export.makeObject end --[==[ Find the language whose code matches the one provided. If it exists, return a `Language` object representing the language. Otherwise, return {nil}, unless `paramForError` is given, in which case an error is generated. If `paramForError` is {true}, a generic error message mentioning the bad code is generated; otherwise `paramForError` should be a string or number specifying the parameter that the code came from, and this parameter will be mentioned in the error message along with the bad code. If `allowEtymLang` is specified, etymology-only language codes are allowed and looked up along with full language codes. If `allowFamily` is specified, language family codes are allowed and looked up along with normal language codes. ]==] function export.getByCode(code, paramForError, allowEtymLang, allowFamily) -- [[ Track uses of paramForError, ultimately so it can be removed, as error-handling should be done by -- [[Module:parameters]], not here. ]] -- I (Benwing) disagree; that is an idealistic goal unlikely to be achievable -- realistically. if paramForError ~= nil then track("paramForError") end if type(code) ~= "string" then local typ if not code then typ = "nil" elseif check_object("language", true, code) then typ = "a language object" elseif check_object("family", true, code) then typ = "a family object" else typ = "a " .. type(code) end error("The function getByCode expects a string as its first argument, but received " .. typ .. ".") end local m_data = load_data(languages_data_module) if m_data.aliases[code] or m_data.track[code] then track(code) end local norm_code = normalize_code(code) -- Get the data, checking for etymology-only languages if allowEtymLang is set. local data = load_data(get_data_module_name(norm_code))[norm_code] or allowEtymLang and load_data(etymology_languages_data_module)[norm_code] -- If no data was found and allowFamily is set, check the family data. If the main family data was found, make the -- object with [[Module:families]] instead, as family objects have different methods. However, if it's an -- etymology-only family, use make_object in this module (which handles object inheritance), and the -- family-specific methods will be inherited from the parent object. if data == nil and allowFamily then data = load_data("Module:families/data")[norm_code] if data ~= nil then if data.parent == nil then return make_family_object(norm_code, data) elseif not allowEtymLang then data = nil end end end local retval = code and data and make_object(code, data) if not retval and paramForError then require("Module:languages/errorGetBy").code(code, paramForError, allowEtymLang, allowFamily) end return retval end get_by_code = export.getByCode --[==[ Find the language whose canonical name (the name used to represent that language on Wiktionary) or other name matches the one provided. If it exists, return a `Language` object representing the language. Otherwise, return {nil}, unless `paramForError` is given, in which case an error is generated. If `allowEtymLang` is specified, etymology-only language codes are allowed and looked up along with full language codes. If `allowFamily` is specified, language family codes are allowed and looked up along with normal language codes. The canonical name of languages should always be unique (it is an error for two languages on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result. This function is powered by [[Module:languages/canonical names]], which contains a pre-generated mapping of full-language canonical names to codes. It is generated by going through the [[:Category:Language data modules]] for full languages. When `allowEtymLang` is specified for the above function, [[Module:etymology languages/canonical names]] may also be used, and when `allowFamily` is specified for the above function, [[Module:families/canonical names]] may also be used. ]==] function export.getByCanonicalName(name, errorIfInvalid, allowEtymLang, allowFamily) local byName = load_data("Module:languages/canonical names") local code = byName and byName[name] if not code and allowEtymLang then byName = load_data("Module:etymology languages/canonical names") code = byName and byName[name] or byName[gsub(name, " [Ss]ubstrate$", "")] or byName[gsub(name, "^a ", "")] or byName[gsub(name, "^a ", ""):gsub(" [Ss]ubstrate$", "")] or -- For etymology families like "ira-pro". -- FIXME: This is not ideal, as it allows " languages" to be appended to any etymology-only language, too. byName[match(name, "^(.*) languages$")] end if not code and allowFamily then byName = load_data("Module:families/canonical names") code = byName[name] or byName[match(name, "^(.*) languages$")] end local retval = code and get_by_code(code, errorIfInvalid, allowEtymLang, allowFamily) if not retval and errorIfInvalid then require("Module:languages/errorGetBy").canonicalName(name, allowEtymLang, allowFamily) end return retval end --[==[ Used by [[Module:languages/data/2]] (et al.) and [[Module:etymology languages/data]], [[Module:families/data]], [[Module:scripts/data]] and [[Module:writing systems/data]] to finalize the data into the format that is actually returned. ]==] function export.finalizeData(data, main_type, variety) local fields = {"type"} if main_type == "language" then insert(fields, 4) -- script codes insert(fields, "ancestors") insert(fields, "link_tr") insert(fields, "override_translit") insert(fields, "wikimedia_codes") elseif main_type == "script" then insert(fields, 3) -- writing system codes end -- Families and writing systems have no extra fields to process. local fields_len = #fields for _, entity in next, data do if variety then -- Move parent from 3 to "parent" and family from "family" to 3. These are different for the sake of -- convenience, since very few varieties have the family specified, whereas all of them have a parent. entity.parent, entity[3] = entity[3], entity.family entity.family = nil -- Give the type "regular" iff not a variety and no other types are assigned. elseif not (entity.type or entity.parent) then entity.type = "regular" end for i = 1, fields_len do local key = fields[i] local field = entity[key] if field and type(field) == "string" then entity[key] = gsub(field, "%s*,%s*", ",") end end end return data end --[==[ For backwards compatibility only; modules should require the error themselves. ]==] function export.err(lang_code, param, code_desc, template_tag, not_real_lang) return require("Module:languages/error")(lang_code, param, code_desc, template_tag, not_real_lang) end return export mz43zcz6drvto1xyal5io97jdfkt6jx 54917 54899 2026-09-28T23:58:09Z Deadend0914 7211 54917 Scribunto text/plain --[==[ intro: This module implements fetching of language-specific information and processing text in a given language. ===Types of languages=== There are two types of languages: full languages and etymology-only languages. The essential difference is that only full languages appear in L2 headings in vocabulary entries, and hence categories like [[:Category:French nouns]] exist only for full languages. Etymology-only languages have either a full language or another etymology-only language as their parent (in the parent-child inheritance sense), and for etymology-only languages with another etymology-only language as their parent, a full language can always be derived by following the parent links upwards. For example, "Canadian French", code `fr-CA`, is an etymology-only language whose parent is the full language "French", code `fr`. An example of an etymology-only language with another etymology-only parent is "Northumbrian Old English", code `ang-nor`, which has "Anglian Old English", code `ang-ang` as its parent; this is an etymology-only language whose parent is "Old English", code `ang`, which is a full language. (This is because Northumbrian Old English is considered a variety of Anglian Old English.) Sometimes the parent is the "Undetermined" language, code `und`; this is the case, for example, for "substrate" languages such as "Pre-Greek", code `qsb-grc`, and "the BMAC substrate", code `qsb-bma`. It is important to distinguish language ''parents'' from language ''ancestors''. The parent-child relationship is one of containment, i.e. if X is a child of Y, X is considered a variety of Y. On the other hand, the ancestor-descendant relationship is one of descent in time. For example, "Classical Latin", code `la-cla`, and "Late Latin", code `la-lat`, are both etymology-only languages with "Latin", code `la`, as their parents, because both of the former are varieties of Latin. However, Late Latin does *NOT* have Classical Latin as its parent because Late Latin is *not* a variety of Classical Latin; rather, it is a descendant. There is in fact a separate `ancestors` field that is used to express the ancestor-descendant relationship, and Late Latin's ancestor is given as Classical Latin. It is also important to note that sometimes an etymology-only language is actually the conceptual ancestor of its parent language. This happens, for example, with "Old Italian" (code `roa-oit`), which is an etymology-only variant of full language "Italian" (code `it`), and with "Old Latin" (code `itc-ola`), which is an etymology-only variant of Latin. In both cases, the full language has the etymology-only variant listed as an ancestor. This allows a Latin term to inherit from Old Latin using the {{tl|inh}} template (where in this template, "inheritance" refers to ancestral inheritance, i.e. inheritance in time, rather than in the parent-child sense); likewise for Italian and Old Italian. Full languages come in three subtypes: * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. Most constructed languages are of this subtype. Both full languages and etymology-only languages have a {Language} object associated with them, which is fetched using the {getByCode} function in [[Module:languages]] to convert a language code to a {Language} object. Depending on the options supplied to this function, etymology-only languages may or may not be accepted, and family codes may be accepted (returning a {Family} object as described in [[Module:families]]). There are also separate {getByCanonicalName} functions in [[Module:languages]] and [[Module:etymology languages]] to convert a language's canonical name to a {Language} object (depending on whether the canonical name refers to a full or etymology-only language). ===Textual representations=== Textual strings belonging to a given language come in several different ''text variants'': # The ''input text'' is what the user supplies in wikitext, in the parameters to {{tl|m}}, {{tl|l}}, {{tl|ux}}, {{tl|t}}, {{tl|lang}} and the like. # The ''corrected input text'' is the input text with some corrections and/or normalizations applied, such as bad-character replacements for certain languages, like replacing `l` or `1` to [[palochka]] in some languages written in Cyrillic. (FIXME: This currently goes under the name ''display text'' but that will be repurposed below. Also, [[User:Surjection]] suggests renaming this to ''normalized input text'', but "normalized" is used in a different sense in [[Module:usex]].) # The ''display text'' is the text in the form as it will be displayed to the user. This is what appears in headwords, in usexes, in displayed internal links, etc. This can include accent marks that are removed to form the stripped display text (see below), as well as embedded bracketed links that are variously processed further. The display text is generated from the corrected input text by applying language-specific transformations; for most languages, there will be no such transformations. The general reason for having a difference between input and display text is to allow for extra information in the input text that is not displayed to the user but is sent to the transliteration module. Note that having different display and input text is only supported currently through special-casing but will be generalized. Examples of transformations are: (1) Removing the {{cd|^}} that is used in certain East Asian (and possibly other unicameral) languages to indicate capitalization of the transliteration (which is currently special-cased); (2) for Korean, removing or otherwise processing hyphens (which is currently special-cased); (3) for Arabic, removing a ''sukūn'' diacritic placed over a ''tāʔ marbūṭa'' (like this: ةْ) to indicate that the ''tāʔ marbūṭa'' is pronounced and transliterated as /t/ instead of being silent [NOTE, NOT IMPLEMENTED YET]; (4) for Thai and Khmer, converting space-separated words to bracketed words and resolving respelling substitutions such as `[กรีน/กฺรีน]`, which indicate how to transliterate given words [NOTE, NOT IMPLEMENTED YET except in language-specific templates like {{tl|th-usex}}]. ## The ''right-resolved display text'' is the result of removing brackets around one-part embedded links and resolving two-part embedded links into their right-hand components (i.e. converting two-part links into the displayed form). The process of right-resolution is what happens when you call {{cd|remove_links()}} in [[Module:links]] on some text. When applied to the display text, it produces exactly what the user sees, without any link markup. # The ''stripped display text'' is the result of applying diacritic-stripping to the display text. ## The ''left-resolved stripped display text'' [NEED BETTER NAME] is the result of applying left-resolution to the stripped display text, i.e. similar to right-resolution but resolving two-part embedded links into their left-hand components (i.e. the linked-to page). If the display text refers to a single page, the resulting of applying diacritic stripping and left-resolution produces the ''logical pagename''. # The ''physical pagename text'' is the result of converting the stripped display text into physical page links. If the stripped display text contains embedded links, the left side of those links is converted into physical page links; otherwise, the entire text is considered a pagename and converted in the same fashion. The conversion does three things: (1) converts characters not allowed in pagenames into their "unsupported title" representation, e.g. {{cd|Unsupported titles/`gt`}} in place of the logical name {{cd|>}}; (2) handles certain special-cased unsupported-title logical pagenames, such as {{cd|Unsupported titles/Space}} in place of {{cd|[space]}} and {{cd|Unsupported titles/Ancient Greek dish}} in place of a very long Greek name for a gourmet dish as found in Aristophanes; (3) converts "mammoth" pagenames such as [[a]] into their appropriate split component, e.g. [[a/languages A to L]]. # The ''source translit text'' is the text as supplied to the language-specific {{cd|transliterate()}} method. The form of the source translit text may need to be language-specific, e.g Thai and Khmer will need the corrected input text, whereas other languages may need to work off the display text. [FIXME: It's still unclear to me how embedded bracketed links are handled in the existing code.] In general, embedded links need to be right-resolved (see above), but when this happens is unclear to me [FIXME]. Some languages have a chop-up-and-paste-together scheme that sends parts of the text through the transliterate mechanism, and for others (those listed with "cont" in {{cd|substitution}} in [[Module:languages/data]]) they receive the full input text, but preprocessed in certain ways. (The wisdom of this is still unclear to me.) # The ''transliterated text'' (or ''transliteration'') is the result of transliterating the source translit text. Unlike for all the other text variants except the transcribed text, it is always in the Latin script. # The ''transcribed text'' (or ''transcription'') is the result of transcribing the source translit text, where "transcription" here means a close approximation to the phonetic form of the language in languages (e.g. Akkadian, Sumerian, Ancient Egyptian, maybe Tibetan) that have a wide difference between the written letters and spoken form. Unlike for all the other text variants other than the transliterated text, it is always in the Latin script. Currently, the transcribed text is always supplied manually be the user; there is no such thing as a {{cd|transcribe()}} method on language objects. # The ''sort key'' is the text used in sort keys for determining the placing of pages in categories they belong to. The sort key is generated from the pagename or a specified ''sort base'' by lowercasing, doing language-specific transformations and then uppercasing the result. If the sort base is supplied and is generated from input text, it needs to be converted to display text, have embedded links removed through right-resolution and have diacritic-stripping applied. # There are other text variants that occur in usexes (specifically, there are normalized variants of several of the above text variants), but we can skip them for now. The following methods exist on {Language} objects to convert between different text variants: # {correctInputText} (currently called {makeDisplayText}): This converts input text to corrected input text. # {stripDiacritics}: This converts to stripped display text. [FIXME: This needs some rethinking. In particular, {stripDiacritics} is sometimes called on input text, corrected input text or display text (in various paths inside of [[Module:links]], and, in the case of input text, usually from other modules). We need to make sure we don't try to convert input text to display text twice, but at the same time we need to support calling it directly on input text since so many modules do this. This means we need to add a parameter indicating whether the passed-in text is input, corrected input, or display text; if the former two, we call {correctInputText} ourselves.] # {logicalToPhysical}: This converts logical pagenames to physical pagenames. # {transliterate}: This appears to convert input text with embedded brackets removed into a transliteration. [FIXME: This needs some rethinking. In particular, it calls {processDisplayText} on its input, which won't work for Thai and Khmer, so we may need language-specific flags indicating whether to pass the input text directly to the language transliterate method. In addition, I'm not sure how embedded links are handled in the existing translit code; a lot of callers remove the links themselves before calling {transliterate()}, which I assume is wrong.] # {makeSortKey}: This converts display text (?) to a sort key. [FIXME: Clarify this.] ]==] local export = {} local debug_track_module = "Module:debug/track" local etymology_languages_data_module = "Module:etymology languages/data" local families_module = "Module:families" local headword_page_module = "Module:headword/page" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_data_module = "Module:languages/data" local languages_data_patterns_module = "Module:languages/data/patterns" local links_data_module = "Module:links/data" local load_module = "Module:load" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local string_encode_entities_module = "Module:string/encode entities" local string_pattern_escape_module = "Module:string/patternEscape" local string_replacement_escape_module = "Module:string/replacementEscape" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local wikimedia_languages_module = "Module:wikimedia languages" -- Old English localization: language names come from [[Module:sprǣcnaman]], which is also what -- [[Bysen:sprǣc]] (the ==L2== heading template) uses, so L2 headings, categories, wordstǣr lines and -- links can never disagree with each other. The module is optional: if it is missing, the English -- names from the data modules are used exactly as before. local ang_names_module = "Module:sprǣcnaman" local ang_names local function get_ang_names() if ang_names == nil then local ok, mod = pcall(require, ang_names_module) ang_names = ok and mod or false end return ang_names or nil end -- Old English name of the given language, or nil. local function ang_name(lang) local mod = get_ang_names() return mod and mod.get_name(lang) or nil end -- Code of the language with the given Old English name, or nil. local function code_of_ang_name(name) local mod = get_ang_names() return mod and mod.get_code(name) or nil end local mw = mw local string = string local table = table local char = string.char local concat = table.concat local find = string.find local floor = math.floor local get_by_code -- Defined below. local get_data_module_name -- Defined below. local get_extra_data_module_name -- Defined below. local getmetatable = getmetatable local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local ipairs = ipairs local is_known_language_tag = mw.language.isKnownLanguageTag local make_object -- Defined below. local match = string.match local next = next local pairs = pairs local remove = table.remove local require = require local select = select local setmetatable = setmetatable local sub = string.sub local type = type local unstrip = mw.text.unstrip -- Loaded as needed by findBestScript. local Hans_chars local Hant_chars local function check_object(...) check_object = require(utilities_module).check_object return check_object(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function decode_uri(...) decode_uri = require(string_utilities_module).decode_uri return decode_uri(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function encode_entities(...) encode_entities = require(string_encode_entities_module) return encode_entities(...) end local function get_L2_sort_key(...) get_L2_sort_key = require(headword_page_module).get_L2_sort_key return get_L2_sort_key(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function get_family(...) get_family = require(families_module).getByCode return get_family(...) end local function get_plaintext(...) get_plaintext = require(utilities_module).get_plaintext return get_plaintext(...) end local function get_wikimedia_lang(...) get_wikimedia_lang = require(wikimedia_languages_module).getByCode return get_wikimedia_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_family_object(...) make_family_object = require(families_module).makeObject return make_family_object(...) end local function pattern_escape(...) pattern_escape = require(string_pattern_escape_module) return pattern_escape(...) end local function replacement_escape(...) replacement_escape = require(string_replacement_escape_module) return replacement_escape(...) end local function safe_require(...) safe_require = require(load_module).safe_require return safe_require(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ugsub(...) ugsub = require(string_utilities_module).gsub return ugsub(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end local function track(page) debug_track("languages/" .. page) return true end local function normalize_code(code) return load_data(languages_data_module).aliases[code] or code end local function check_inputs(self, check, default, ...) local n = select("#", ...) if n == 0 then return false end local ret = check(self, (...)) if ret ~= nil then return ret elseif n > 1 then local inputs = {...} for i = 2, n do ret = check(self, inputs[i]) if ret ~= nil then return ret end end end return default end local function make_link(self, target, display) local prefix, main if self:getFamilyCode() == "qfa-sub" then prefix, main = display:match("^(the )(.*)") if not prefix then prefix, main = display:match("^(a )(.*)") end end return (prefix or "") .. "[[" .. target .. "|" .. (main or display) .. "]]" end -- Convert risky characters to HTML entities, which minimizes interference once returned (e.g. for "sms:a", "<!-- -->" etc.). local function escape_risky_characters(text) -- Spacing characters in isolation generally need to be escaped in order to be properly processed by the MediaWiki -- software. if umatch(text, "^%s*$") then return encode_entities(text, text) end return encode_entities(text, "!#%&*+/:;<=>?@[\\]_{|}") end -- Temporarily convert various formatting characters to PUA to prevent them from being disrupted by the substitution process. local function doTempSubstitutions(text, subbedChars, keepCarets, noTrim) -- Clone so that we don't insert any extra patterns into the table in package.loaded. For some reason, using require -- seems to keep memory use down; probably because the table is always cloned. local patterns = shallow_copy(require(languages_data_patterns_module)) if keepCarets then insert(patterns, "((\\+)%^)") insert(patterns, "((%^))") end -- Ensure any whitespace at the beginning and end is temp substituted, to prevent it from being accidentally -- trimmed. We only want to trim any final spaces added during the substitution process (e.g. by a module), which -- means we only do this during the first round of temp substitutions. if not noTrim then insert(patterns, "^([\128-\191\244]*(%s+))") insert(patterns, "((%s+)[\128-\191\244]*)$") end -- Pre-substitution, of "[[" and "]]", which makes pattern matching more accurate. text = gsub(text, "%f[%[]%[%[", "\1"):gsub("%f[%]]%]%]", "\2") local i = #subbedChars for _, pattern in ipairs(patterns) do -- Patterns ending in \0 stand are for things like "[[" or "]]"), so the inserted PUA are treated as breaks -- between terms by modules that scrape info from pages. local term_divider pattern = gsub(pattern, "%z$", function(divider) term_divider = divider == "\0" return "" end) text = gsub(text, pattern, function(...) local m = {...} local m1New = m[1] for k = 2, #m do local n = i + k - 1 subbedChars[n] = m[k] local byte2 = floor(n / 4096) % 64 + (term_divider and 128 or 136) local byte3 = floor(n / 64) % 64 + 128 local byte4 = n % 64 + 128 m1New = gsub(m1New, pattern_escape(m[k]), "\244" .. char(byte2) .. char(byte3) .. char(byte4), 1) end i = i + #m - 1 return m1New end) end text = gsub(text, "\1", "%[%["):gsub("\2", "%]%]") return text, subbedChars end -- Reinsert any formatting that was temporarily substituted. local function undoTempSubstitutions(text, subbedChars) for i = 1, #subbedChars do local byte2 = floor(i / 4096) % 64 + 128 local byte3 = floor(i / 64) % 64 + 128 local byte4 = i % 64 + 128 text = gsub(text, "\244[" .. char(byte2) .. char(byte2+8) .. "]" .. char(byte3) .. char(byte4), replacement_escape(subbedChars[i])) end text = gsub(text, "\1", "%[%["):gsub("\2", "%]%]") return text end -- Check if the raw text is an unsupported title, and if so return that. Otherwise, remove HTML entities. We do the -- pre-conversion to avoid loading the unsupported title list unnecessarily. local function checkNoEntities(text) local textNoEnc = decode_entities(text) if textNoEnc ~= text and load_data(links_data_module).unsupported_titles[text] then return text else return textNoEnc end end -- If no script object is provided (or if it's invalid or None), get one. local function checkScript(text, self, sc) if not check_object("script", true, sc) or sc:getCode() == "None" then return self:findBestScript(text) end return sc end local function normalize(text, sc) text = sc:fixDiscouragedSequences(text) return sc:toFixedNFD(text) end --[=[ Subfunction of iterateSectionSubstitutions(). Process an individual chunk of text according to the specifications in `substitution_data`. The input parameters are all as in the documentation of iterateSectionSubstitutions() except for `recursed`, which is set to true if we called ourselves recursively to process a script-specific setting or script-wide fallback. Returns two values: the processed text and the actual substitution data used to do the substitutions (same as the `actual_substitution_data` return value to iterateSectionSubstitutions()). ]=] local function doSubstitutions(self, text, sc, substitution_data, data_field, function_name, recursed) -- BE CAREFUL in this function because the value at any level can be `false`, which causes no processing to be done -- and blocks any further fallback processing. local actual_substitution_data = substitution_data -- If there are language-specific substitutes given in the data module, use those. if type(substitution_data) == "table" then -- If a script is specified, run this function with the script-specific data before continuing. local sc_code = sc:getCode() local has_substitution_data = false if substitution_data[sc_code] ~= nil then has_substitution_data = true if substitution_data[sc_code] then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data[sc_code], data_field, function_name, true) end -- Hant, Hans and Hani are usually treated the same, so add a special case to avoid having to specify each one -- separately. elseif sc_code:match("^Han") and substitution_data.Hani ~= nil then has_substitution_data = true if substitution_data.Hani then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data.Hani, data_field, function_name, true) end -- Substitution data with key 1 in the outer table may be given as a fallback. elseif substitution_data[1] ~= nil then has_substitution_data = true if substitution_data[1] then text, actual_substitution_data = doSubstitutions(self, text, sc, substitution_data[1], data_field, function_name, true) end end -- Iterate over all strings in the "from" subtable, and gsub with the corresponding string in "to". We work with -- the NFD decomposed forms, as this simplifies many substitutions. if substitution_data.from then has_substitution_data = true for i, from in ipairs(substitution_data.from) do -- Normalize each loop, to ensure multi-stage substitutions work correctly. text = sc:toFixedNFD(text) text = ugsub(text, sc:toFixedNFD(from), substitution_data.to[i] or "") end end if substitution_data.remove_diacritics then has_substitution_data = true text = sc:toFixedNFD(text) -- Convert exceptions to PUA. local remove_exceptions, substitutes = substitution_data.remove_exceptions if remove_exceptions then substitutes = {} local i = 0 for _, exception in ipairs(remove_exceptions) do exception = sc:toFixedNFD(exception) text = ugsub(text, exception, function(m) i = i + 1 local subst = u(0x80000 + i) substitutes[subst] = m return subst end) end end -- Strip diacritics. text = ugsub(text, "[" .. substitution_data.remove_diacritics .. "]", "") -- Convert exceptions back. if remove_exceptions then text = text:gsub("\242[\128-\191]*", substitutes) end end if not has_substitution_data and sc._data[data_field] then -- If language-specific sort key (etc.) is nil, fall back to script-wide sort key (etc.). text, actual_substitution_data = doSubstitutions(self, text, sc, sc._data[data_field], data_field, function_name, true) end elseif type(substitution_data) == "string" then -- If there is a dedicated function module, use that. local module = safe_require("Module:" .. substitution_data) if module then -- TODO: translit functions should take objects, not codes. -- TODO: translit functions should be called with form NFD. if function_name == "tr" then if not module[function_name] then error(("Internal error: Module [[%s]] has no function named 'tr'"):format(substitution_data)) end text = module[function_name](text, self._code, sc:getCode()) elseif function_name == "stripDiacritics" then -- FIXME, get rid of this arm after renaming makeEntryName -> stripDiacritics. if module[function_name] then text = module[function_name](sc:toFixedNFD(text), self, sc) elseif module.makeEntryName then text = module.makeEntryName(sc:toFixedNFD(text), self, sc) else error(("Internal error: Module [[%s]] has no function named 'stripDiacritics' or 'makeEntryName'" ):format(substitution_data)) end else if not module[function_name] then error(("Internal error: Module [[%s]] has no function named '%s'"):format( substitution_data, function_name)) end text = module[function_name](sc:toFixedNFD(text), self, sc) end else error("Substitution data '" .. substitution_data .. "' does not match an existing module.") end elseif substitution_data == nil and sc._data[data_field] then -- If language-specific sort key (etc.) is nil, fall back to script-wide sort key (etc.). text, actual_substitution_data = doSubstitutions(self, text, sc, sc._data[data_field], data_field, function_name, true) end -- Don't normalize to NFC if this is the inner loop or if a module returned nil. if recursed or not text then return text, actual_substitution_data end -- Fix any discouraged sequences created during the substitution process, and normalize into the final form. return sc:toFixedNFC(sc:fixDiscouragedSequences(text)), actual_substitution_data end --[=[ Split the text into sections, based on the presence of temporarily substituted formatting characters, then iterate over each section to apply substitutions (e.g. transliteration or diacritic stripping). This avoids putting PUA (Private Use Area) characters through language-specific modules, which may be unequipped for them. This function is passed the following values: * `self` (the Language object); * `text` (the text to process); * `sc` (the script of the text, which must be specified; callers should call checkScript() as needed to autodetect the script of the text if not given explicitly by the user); * `subbedChars` (an array of the same length as the text, indicating which characters have been substituted and by what, or {nil} if no substitutions are to happen); * `keepCarets` (DOCUMENT ME); * `substitution_data` (the data indicating which substitutions to apply, taken directly from `data_field` in the language's data structure in a submodule of [[Module:languages/data]]); * `data_field` (the field from which `substitution_data` was fetched, such as {"sort_key"} or {"strip_diacritics"}); * `function_name` (the name of the function to call to do the substitution, in case `substitution_data` specifies a module to do the substitution); * `notrim` (don't trim whitespace at the edges of `text`; set when computing the sort key, because whitespace at the beginning of a sort key is significant and causes the resulting page to be sorted at the beginning of the category it's in). Return three values: # the processed text; # the value of `subbedChars` that was passed in, possibly modified with additional character substitutions; will be {nil} if {nil} was passed in; # the actual substitution data that was used to apply substitutions to `text`; this may be different from the value of `substitution_data` passed in if that value recursively specified script-specific substitutions or if no substitution data could be found in the language-specific data (e.g. {nil} was passed in or a structure was passed in that had no setting for the script given in `sc`), but a script-wide fallback value was set; currently it is only used by {makeSortKey()}. ]=] local function iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, substitution_data, data_field, function_name, notrim) local sections -- See [[Module:languages/data]]. if not find(text, "\244") or load_data(languages_data_module).substitution[self._code] == "cont" then sections = {text} else sections = split(text, "\244[\128-\143][\128-\191]*", true) end local actual_substitution_data for _, section in ipairs(sections) do -- Don't bother processing empty strings or whitespace (which may also not be handled well by dedicated -- modules). if gsub(section, "%s+", "") ~= "" then local sub, this_actual_substitution_data = doSubstitutions(self, section, sc, substitution_data, data_field, function_name) actual_substitution_data = this_actual_substitution_data -- Second round of temporary substitutions, in case any formatting was added by the main substitution -- process. However, don't do this if the section contains formatting already (as it would have had to have -- been escaped to reach this stage, and therefore should be given as raw text). if sub and subbedChars then local noSub for _, pattern in ipairs(require(languages_data_patterns_module)) do if match(section, pattern .. "%z?") then noSub = true end end if not noSub then sub, subbedChars = doTempSubstitutions(sub, subbedChars, keepCarets, true) end end if not sub then text = sub break end text = sub and gsub(text, pattern_escape(section), replacement_escape(sub), 1) or text end end if not notrim then -- Trim, unless there are only spacing characters, while ignoring any final formatting characters. -- Do not trim sort keys because spaces at the beginning are significant. text = text and text:gsub("^([\128-\191\244]*)%s+(%S)", "%1%2"):gsub("(%S)%s+([\128-\191\244]*)$", "%1%2") or nil end return text, subbedChars, actual_substitution_data end -- Process carets (and any escapes). Default to simple removal, if no pattern/replacement is given. local function processCarets(text, pattern, repl) local rep repeat text, rep = gsub(text, "\\\\(\\*^)", "\3%1") until rep == 0 return (text:gsub("\\^", "\4") :gsub(pattern or "%^", repl or "") :gsub("\3", "\\") :gsub("\4", "^")) end -- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped). local function removeCarets(text, sc) if not sc:hasCapitalization() and sc:isTransliterated() and text:find("^", 1, true) then return processCarets(text) else return text end end local Language = {} --[==[ Return the language code of the language. Example: {fr"} for French. ]==] function Language:getCode() return self._code end --[==[ Return the canonical name of the language. This is the name used to represent that language on Wiktionary, and is guaranteed to be unique to that language alone. Example: {"French"} for French. ]==] function Language:getCanonicalName() local name = self._name if name == nil then name = ang_name(self) or self._data[1] self._name = name end return name end --[==[ Return the display form of the language. The display form of a language, family or script is the form it takes when appearing as the <code><var>source</var></code> in categories such as <code>English terms derived from <var>source</var></code> or <code>English given names from <var>source</var></code>, and is also the displayed text in `##makeCategoryLink()` links. For full and etymology-only languages, this is the same as the canonical name, but for families, it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}), and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). ]==] function Language:getDisplayForm() local form = self._displayForm if form == nil then form = self:getCanonicalName() -- Add article and " substrate" to substrates that lack them. if self:getFamilyCode() == "qfa-sub" then if not (sub(form, 1, 4) == "the " or sub(form, 1, 2) == "a ") then form = "a " .. form end if not match(form, " [Ss]ubstrate") then form = form .. " substrate" end end self._displayForm = form end return form end --[==[ Return the value which should be used in the HTML `lang=` attribute for tagged text in the language. ]==] function Language:getHTMLAttribute(sc, region) local code = self._code if not find(code, "-", 1, true) then return code .. "-" .. sc:getCode() .. (region and "-" .. region or "") end local parent = self:getParent() region = region or match(code, "%f[%u][%u-]+%f[%U]") if parent then return parent:getHTMLAttribute(sc, region) end -- TODO: ISO family codes can also be used. return "mis-" .. sc:getCode() .. (region and "-" .. region or "") end --[==[ Return a list of the aliases that the language is known by, excluding the canonical name. Aliases are synonyms for the language in question. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: { {"High German", "New High German", "Deutsch"}} for {{lnl|de}}. ]==] function Language:getAliases() self:loadInExtraData() return require(language_like_module).getAliases(self) end --[==[ Return a list of the known subvarieties of a given language, excluding subvarieties that have been given explicit etymology-only language codes. The names are not guaranteed to be unique, in that sometimes a given name refers to a subvariety of more than one language. Example: { {"Southern Aymara", "Central Aymara"}} for {{lnl|ay}}. Note that the returned value can have nested tables in it, when a subvariety goes by more than one name. Example: { {"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor"}} for {{lnl|az}}. Here, for example, Afshar, Afshari, Afshar Azerbaijani and Afchar all refer to the same subvariety, whose preferred name is Afshar (the one listed first). To avoid a return value with nested tables in it, specify a non-{nil} value for the `flatten` parameter; in that case, the return value would be { {"North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"}}. ]==] function Language:getVarieties(flatten) self:loadInExtraData() return require(language_like_module).getVarieties(self, flatten) end --[==[ Return a table of the "other names" that the language is known by, which are listed in the `other_names` field in the language's extra-data module. It should be noted that the `other_names` field itself is deprecated, and entries listed there should eventually be moved to either `aliases` or `varieties`, or removed if they refer to larger entities which the language in question is actually a part of. ]==] function Language:getOtherNames() -- To be eventually removed, once there are no more uses of the `other_names` field. self:loadInExtraData() return require(language_like_module).getOtherNames(self) end --[==[ Return a combined table of the canonical name, aliases, varieties and other names of a given language. ]==] function Language:getAllNames() self:loadInExtraData() return require(language_like_module).getAllNames(self) end --[==[ Return a table of types as a set (with the types as keys). The possible types are * {language}: This is a language, either full or etymology-only. * {full}: This is a "full" (not etymology-only) language, i.e. the union of {regular}, {reconstructed} and {appendix-constructed}. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for a full language and you have an object that might be a family, you should use {hasType("language", "full")} and not simply {hasType("full")}. * {etymology-only}: This is an etymology-only (not full) language, whose parent is another etymology-only language or a full language. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for an etymology-only language and you have an object that might be a family, you should use {hasType("language", "etymology-only")} and not simply {hasType("etymology-only")}. * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with `*` to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with `*`. Languages such as Proto-Indo-European and Proto-Germanic are in this category. '''Exception:''' Reconstructed languages can have entries in the mainspace using the ''anti-asterisk'' feature. This requires that both the headword for the mainspace term (as specified using {{para|head}}) and links to the term are prefixed with the anti-asterisk indicator `!!`. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ]==] function Language:getTypes() local types = self._types if types == nil then types = {language = true} if self:getFullCode() == self._code then types.full = true else types["etymology-only"] = true end for t in gmatch(self._data.type, "[^,]+") do types[t] = true end self._types = types end return types end --[==[ Given a list of types as strings, return {true} if the language has all of them. ]==] function Language:hasType(...) Language.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[ Return a list containing `WikimediaLanguage` objects (see [[Module:wikimedia languages]]), which represent languages and their codes as they are used in Wikimedia projects for interwiki linking and such. More than one object may be returned, as a single Wiktionary language may correspond to multiple Wikimedia languages. For example, Wiktionary's single code `sh` (Serbo-Croatian) maps to four Wikimedia codes: `sh` (Serbo-Croatian), `bs` (Bosnian), `hr` (Croatian) and `sr` (Serbian). The code for the Wikimedia language is retrieved from the `wikimedia_codes` property in the data modules. If that property is not present, the code of the current language is used. If none of the available codes is actually a valid Wikimedia code, an empty list is returned. ]==] function Language:getWikimediaLanguages() local wm_langs = self._wikimediaLanguageObjects if wm_langs == nil then local codes = self:getWikimediaLanguageCodes() wm_langs = {} for i = 1, #codes do wm_langs[i] = get_wikimedia_lang(codes[i]) end self._wikimediaLanguageObjects = wm_langs end return wm_langs end function Language:getWikimediaLanguageCodes() local wm_langs = self._wikimediaLanguageCodes if wm_langs == nil then wm_langs = self._data.wikimedia_codes if wm_langs then wm_langs = split(wm_langs, ",", true, true) else local code = self._code if is_known_language_tag(code) then wm_langs = {code} else -- Inherit, but only if no codes are specified in the data *and* -- the language code isn't a valid Wikimedia language code. local parent = self:getParent() wm_langs = parent and parent:getWikimediaLanguageCodes() or {} end end self._wikimediaLanguageCodes = wm_langs end return wm_langs end --[==[ Return the name of the Wikipedia article for the language. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, `##Language:getCategoryName` is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the language's category, but this won't normally happen for any other project. ]==] function Language:getWikipediaArticle(noCategoryFallback, project) Language.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Language:makeWikipediaLink() return make_link(self, "w:" .. self:getWikipediaArticle(), self:getCanonicalName()) end --[==[ Return the name of the Wikimedia Commons category page for the language. ]==] function Language:getCommonsCategory() Language.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end --[==[ Return the Wikidata item ID for the language or {nil}. This corresponds to the the second field in the data modules. ]==] function Language:getWikidataItem() Language.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[ Return a list of `Script` objects for all scripts that the language is written in. See [[Module:scripts]]. ]==] function Language:getScripts() local scripts = self._scriptObjects if scripts == nil then local codes = self:getScriptCodes() if codes[1] == "All" then scripts = load_data(scripts_data_module) else scripts = {} for i = 1, #codes do scripts[i] = get_script(codes[i]) end end self._scriptObjects = scripts end return scripts end --[==[ Return the list of script codes in the language's data file. ]==] function Language:getScriptCodes() local scripts = self._scriptCodes if scripts == nil then scripts = self._data[4] if scripts then local codes, n = {}, 0 for code in gmatch(scripts, "[^,]+") do n = n + 1 -- Special handling of "Hants", which represents "Hani", "Hant" and "Hans" collectively. if code == "Hants" then codes[n] = "Hani" codes[n + 1] = "Hant" codes[n + 2] = "Hans" n = n + 2 else codes[n] = code end end scripts = codes else scripts = {"None"} end self._scriptCodes = scripts end return scripts end --[==[ Given some text, iterate through the scripts of a given language trying to find the script that best matches the text. Return a {Script} object representing the script. If no match is found at all, it returns the {None} script object. ]==] function Language:findBestScript(text, forceDetect) if not text or text == "" or text == "-" then return get_script("None") end -- Differs from table returned by getScriptCodes, as Hants is not normalized into its constituents. local codes = self._bestScriptCodes if codes == nil then codes = self._data[4] codes = codes and split(codes, ",", true, true) or {"None"} self._bestScriptCodes = codes end local first_sc = codes[1] if first_sc == "All" then return find_best_script_without_lang(text) end local codes_len = #codes if not (forceDetect or first_sc == "Hants" or codes_len > 1) then first_sc = get_script(first_sc) local charset = first_sc.characters return charset and umatch(text, "[" .. charset .. "]") and first_sc or get_script("None") end -- Remove all formatting characters. text = get_plaintext(text) -- Remove all spaces and any ASCII punctuation. Some non-ASCII punctuation is script-specific, so can't be removed. text = ugsub(text, "[%s!\"#%%&'()*,%-./:;?@[\\%]_{}]+", "") if #text == 0 then return get_script("None") end -- Try to match every script against the text, -- and return the one with the most matching characters. local bestcount, bestscript, length = 0 for i = 1, codes_len do local sc = codes[i] -- Special case for "Hants", which is a special code that represents whichever of "Hant" or "Hans" best matches, -- or "Hani" if they match equally. This avoids having to list all three. In addition, "Hants" will be treated -- as the best match if there is at least one matching character, under the assumption that a Han script is -- desirable in terms that contain a mix of Han and other scripts (not counting those which use Jpan or Kore). if sc == "Hants" then local Hani = get_script("Hani") if not Hant_chars then Hant_chars = load_data("Module:zh/data/ts") Hans_chars = load_data("Module:zh/data/st") end local t, s, found = 0, 0 -- This is faster than using mw.ustring.gmatch directly. for ch in gmatch((ugsub(text, "[" .. Hani.characters .. "]", "\255%0")), "\255(.[\128-\191]*)") do found = true if Hant_chars[ch] then t = t + 1 if Hans_chars[ch] then s = s + 1 end elseif Hans_chars[ch] then s = s + 1 else t, s = t + 1, s + 1 end end if found then if t == s then return Hani end return get_script(t > s and "Hant" or "Hans") end else sc = get_script(sc) if not length then length = ulen(text) end -- Count characters by removing everything in the script's charset and comparing to the original length. local charset = sc.characters local count = charset and length - ulen((ugsub(text, "[" .. charset .. "]+", ""))) or 0 if count >= length then return sc elseif count > bestcount then bestcount = count bestscript = sc end end end -- Return best matching script, or otherwise None. return bestscript or get_script("None") end --[==[ Return a `Family` object for the language family that the language belongs to. See [[Module:families]]. ]==] function Language:getFamily() local family = self._familyObject if family == nil then family = self:getFamilyCode() -- If the value is nil, it's cached as false. family = family and get_family(family) or false self._familyObject = family end return family or nil end --[==[ Return the family code in the language's data file. ]==] function Language:getFamilyCode() local family = self._familyCode if family == nil then -- If the value is nil, it's cached as false. family = self._data[3] or false self._familyCode = family end return family or nil end function Language:getFamilyName() local family = self._familyName if family == nil then family = self:getFamily() -- If the value is nil, it's cached as false. family = family and family:getCanonicalName() or false self._familyName = family end return family or nil end do local function check_family(self, family) if type(family) == "table" then family = family:getCode() end if self:getFamilyCode() == family then return true end local self_family = self:getFamily() if self_family:inFamily(family) then return true -- If the family isn't a real family (e.g. creoles) check any ancestors. elseif self_family:inFamily("qfa-not") then local ancestors = self:getAncestors() for _, ancestor in ipairs(ancestors) do if ancestor:inFamily(family) then return true end end end end --[==[ Check whether the language belongs to `family` (which can be a family code or object). A list of objects can be given in place of `family`; in that case, return true if the language belongs to any of the specified families. Note that some languages (in particular, certain creoles) can have multiple immediate ancestors potentially belonging to different families; in that case, return true if the language belongs to any of the specified families. ]==] function Language:inFamily(...) if self:getFamilyCode() == nil then return false end return check_inputs(self, check_family, false, ...) end end function Language:getParent() local parent = self._parentObject if parent == nil then parent = self:getParentCode() -- If the value is nil, it's cached as false. parent = parent and get_by_code(parent, nil, true, true) or false self._parentObject = parent end return parent or nil end function Language:getParentCode() local parent = self._parentCode if parent == nil then -- If the value is nil, it's cached as false. parent = self._data.parent or false self._parentCode = parent end return parent or nil end function Language:getParentName() local parent = self._parentName if parent == nil then parent = self:getParent() -- If the value is nil, it's cached as false. parent = parent and parent:getCanonicalName() or false self._parentName = parent end return parent or nil end function Language:getParentChain() local chain = self._parentChain if chain == nil then chain = {} local parent, n = self:getParent(), 0 while parent do n = n + 1 chain[n] = parent parent = parent:getParent() end self._parentChain = chain end return chain end --[==[ Return a list of the pseudo-families (if any) that a language belongs to. The returned value is a list of Family objects. Pseudo-families are groupings of languages that are not clades but share some geographic, ethnic or other characteristic (e.g. [[:Category:Papuan languages]], [[:Category:Jewish languages]]). ]==] function Language:getPseudoFamilies() self:loadInExtraData() return require(language_like_module).getPseudoFamilies(self) end do local function check_lang(self, lang) for _, parent in ipairs(self:getParentChain()) do if (type(lang) == "string" and lang or lang:getCode()) == parent:getCode() then return true end end end function Language:hasParent(...) return check_inputs(self, check_lang, false, ...) end end --[==[ If the language is etymology-only, iterate through parents until a full language or family is found, and the corresponding object is returned. If the language is a full language, return that language. ]==] function Language:getFull() local full = self._fullObject if full == nil then full = self:getFullCode() full = full == self._code and self or get_by_code(full) self._fullObject = full end return full end --[==[ If the language is an etymology-only language, iterate through parents until a full language or family is found, and the corresponding code is returned. If the language is a full language, return that language's code. ]==] function Language:getFullCode() return self._fullCode or self._code end --[==[ If the language is an etymology-only language, iterate through parents until a full language or family is found, and the corresponding canonical name is returned. If the language is a full language, return that language's canonical name. ]==] function Language:getFullName() local full = self._fullName if full == nil then full = self:getFull():getCanonicalName() self._fullName = full end return full end --[==[ Return a list of {Language} objects for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors. ]==] function Language:getAncestors() local ancestors = self._ancestorObjects if ancestors == nil then ancestors = {} local ancestor_codes = self:getAncestorCodes() if #ancestor_codes > 0 then for _, ancestor in ipairs(ancestor_codes) do insert(ancestors, get_by_code(ancestor, nil, true)) end else local fam = self:getFamily() local protoLang = fam and fam:getProtoLanguage() or nil -- For the cases where the current language is the proto-language -- of its family, or an etymology-only language that is ancestral to that -- proto-language, we need to step up a level higher right from the -- start. if protoLang and ( protoLang:getCode() == self._code or (self:hasType("etymology-only") and protoLang:hasAncestor(self)) ) then fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end while not protoLang and not (not fam or fam:getCode() == "qfa-not") do fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end insert(ancestors, protoLang) end self._ancestorObjects = ancestors end return ancestors end do -- Avoid a language being its own ancestor via class inheritance. We only need to check for this if the language has -- inherited an ancestor table from its parent, because we never want to drop ancestors that have been explicitly -- set in the data. Recursively iterate over ancestors until we either find self or run out. If self is found, -- return true. local function check_ancestor(self, lang) local codes = lang:getAncestorCodes() if not codes then return nil end for i = 1, #codes do local code = codes[i] if code == self._code then return true end local anc = get_by_code(code, nil, true) if check_ancestor(self, anc) then return true end end end --[==[ Return a list of `Language` codes for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors. ]==] function Language:getAncestorCodes() if self._ancestorCodes then return self._ancestorCodes end local data = self._data local codes = data.ancestors if codes == nil then codes = {} self._ancestorCodes = codes return codes end codes = split(codes, ",", true, true) self._ancestorCodes = codes -- If there are no codes or the ancestors weren't inherited data, there's nothing left to check. if #codes == 0 or self:getData(false, "raw").ancestors ~= nil then return codes end local i = 1 while i <= #codes do if check_ancestor(self, self) then remove(codes, i) else i = i + 1 end end return codes end end --[==[ Given a list of language objects or codes, return true if at least one of them is an ancestor. This includes any etymology-only children of that ancestor. If the language's ancestor(s) are etymology-only languages, it will also return true for those language parent(s) (e.g. if Vulgar Latin is the ancestor, it will also return true for its parent, Latin). However, a parent is excluded from this if the ancestor is also ancestral to that parent (e.g. if Classical Persian is the ancestor, Persian would return {false}, because Classical Persian is also ancestral to Persian). ]==] function Language:hasAncestor(...) local function iterateOverAncestorTree(node, func, parent_check) local ancestors = node:getAncestors() local ancestorsParents = {} for _, ancestor in ipairs(ancestors) do -- When checking the parents of the other language, and the ancestor is also a parent, skip to the next -- ancestor, so that we exclude any etymology-only children of that parent that are not directly related -- (see below). local ret = (parent_check or not node:hasParent(ancestor)) and func(ancestor) or iterateOverAncestorTree(ancestor, func, parent_check) if ret then return ret end end -- Check the parents of any ancestors. We don't do this if checking the parents of the other language, so that -- we exclude any etymology-only children of those parents that are not directly related (e.g. if the ancestor -- is Vulgar Latin and we are checking New Latin, we want it to return false because they are on different -- ancestral branches. As such, if we're already checking the parent of New Latin (Latin) we don't want to -- compare it to the parent of the ancestor (Latin), as this would be a false positive; it should be one or the -- other). if not parent_check then return nil end for _, ancestor in ipairs(ancestors) do local ancestorParents = ancestor:getParentChain() for _, ancestorParent in ipairs(ancestorParents) do if ancestorParent:getCode() == self._code or ancestorParent:hasAncestor(ancestor) then break else insert(ancestorsParents, ancestorParent) end end end for _, ancestorParent in ipairs(ancestorsParents) do local ret = func(ancestorParent) if ret then return ret end end end local function do_iteration(otherlang, parent_check) -- otherlang can't be self if (type(otherlang) == "string" and otherlang or otherlang:getCode()) == self._code then return false end repeat if iterateOverAncestorTree( self, function(ancestor) return ancestor:getCode() == (type(otherlang) == "string" and otherlang or otherlang:getCode()) end, parent_check ) then return true elseif type(otherlang) == "string" then otherlang = get_by_code(otherlang, nil, true) end otherlang = otherlang:getParent() parent_check = false until not otherlang end local parent_check = true for _, otherlang in ipairs{...} do local ret = do_iteration(otherlang, parent_check) if ret then return true end end return false end do local function construct_node(lang, memo) local branch, ancestors = {lang = lang:getCode()} memo[lang:getCode()] = branch for _, ancestor in ipairs(lang:getAncestors()) do if ancestors == nil then ancestors = {} end insert(ancestors, memo[ancestor:getCode()] or construct_node(ancestor, memo)) end branch.ancestors = ancestors return branch end function Language:getAncestorChain() local chain = self._ancestorChain if chain == nil then chain = construct_node(self, {}) self._ancestorChain = chain end return chain end end function Language:getAncestorChainOld() local chain = self._ancestorChain if chain == nil then chain = {} local step = self while true do local ancestors = step:getAncestors() step = #ancestors == 1 and ancestors[1] or nil if not step then break end insert(chain, step) end self._ancestorChain = chain end return chain end local function fetch_descendants(self, fmt) local descendants, family = {}, self:getFamily() -- Iterate over all three datasets. for _, data in ipairs{ require("Module:languages/code to canonical name"), require("Module:etymology languages/code to canonical name"), require("Module:families/code to canonical name"), } do for code in pairs(data) do local lang = get_by_code(code, nil, true, true) if not lang then error(("Internal error: code '%s' can't be fetched"):format(code)) end -- Test for a descendant. Earlier tests weed out most candidates, while the more intensive tests are only used sparingly. if ( code ~= self._code and -- Not self. lang:inFamily(family) and -- In the same family. ( family:getProtoLanguageCode() == self._code or -- Self is the protolanguage. self:hasDescendant(lang) or -- Full hasDescendant check. (lang:getFullCode() == self._code and not self:hasAncestor(lang)) -- Etymology-only child which isn't an ancestor. ) ) then if fmt == "object" then insert(descendants, lang) elseif fmt == "code" then insert(descendants, code) elseif fmt == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Language:getDescendants() local descendants = self._descendantObjects if descendants == nil then descendants = fetch_descendants(self, "object") self._descendantObjects = descendants end return descendants end function Language:getDescendantCodes() local descendants = self._descendantCodes if descendants == nil then descendants = fetch_descendants(self, "code") self._descendantCodes = descendants end return descendants end function Language:getDescendantNames() local descendants = self._descendantNames if descendants == nil then descendants = fetch_descendants(self, "name") self._descendantNames = descendants end return descendants end do local function check_lang(self, lang) if type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasAncestor(self) then return true end end function Language:hasDescendant(...) return check_inputs(self, check_lang, false, ...) end end local function fetch_children(self, fmt) local m_etym_data = require(etymology_languages_data_module) local self_code, children = self._code, {} for code, lang in pairs(m_etym_data) do local _lang = lang repeat local parent = _lang.parent if parent == self_code then if fmt == "object" then insert(children, get_by_code(code, nil, true)) elseif fmt == "code" then insert(children, code) elseif fmt == "name" then insert(children, lang[1]) end break end _lang = m_etym_data[parent] until not _lang end return children end function Language:getChildren() local children = self._childObjects if children == nil then children = fetch_children(self, "object") self._childObjects = children end return children end function Language:getChildrenCodes() local children = self._childCodes if children == nil then children = fetch_children(self, "code") self._childCodes = children end return children end function Language:getChildrenNames() local children = self._childNames if children == nil then children = fetch_children(self, "name") self._childNames = children end return children end function Language:hasChild(...) local lang = ... if not lang then return false elseif type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasParent(self) then return true end return self:hasChild(select(2, ...)) end --[==[ Return the name of the main category of that language. Example: {French language"} for French, whose category is at [[:Category:French language]]. Unless optional argument `nocap` is given, the language name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the language name is lowercase and the returned value of this function is used in the middle of a sentence. ]==] function Language:getCategoryName(nocap) local name = self._categoryName if name == nil then name = self:getCanonicalName() -- If a substrate, omit any leading article. if self:getFamilyCode() == "qfa-sub" then name = name:gsub("^the ", ""):gsub("^a ", "") end -- Only add " language" if a full language. if self:hasType("full") then -- Unless the canonical name already ends with "language", "lect" or their derivatives, add " language". if not (match(name, "[Ll]anguage$") or match(name, "[Ll]ect$")) then name = name .. " language" end end self._categoryName = name end if nocap then return name end return mw.getContentLanguage():ucfirst(name) end --[==[ Create a link to the category; the link text is the canonical name. ]==] function Language:makeCategoryLink() return make_link(self, ":Category:" .. self:getCategoryName(), self:getDisplayForm()) end function Language:getStandardCharacters(sc) local standard_chars = self._data.standard_chars if type(standard_chars) ~= "table" then return standard_chars elseif sc and type(sc) ~= "string" then check_object("script", nil, sc) sc = sc:getCode() end if (not sc) or sc == "None" then local scripts = {} for _, script in pairs(standard_chars) do insert(scripts, script) end return concat(scripts) end if standard_chars[sc] then return standard_chars[sc] .. (standard_chars[1] or "") end end --[==[ Strip diacritics from display text `text` (in a language-specific fashion), which is in the script `sc`. If `sc` is omitted or {nil}, the script is autodetected. This also strips certain punctuation characters from the end and (in the case of Spanish upside-down question mark and exclamation points) from the beginning; strips any whitespace at the end of the text or between the text and final stripped punctuation characters; and applies some language-specific Unicode normalizations to replace discouraged characters with their prescribed alternatives. Return the stripped text. ]==] function Language:stripDiacritics(text, sc) if (not text) or text == "" then return text end sc = checkScript(text, self, sc) text = normalize(text, sc) -- FIXME, rename makeEntryName to stripDiacritics and get rid of second and third return values -- everywhere local _ text, _, _ = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.strip_diacritics or self._data.entry_name, "strip_diacritics", "stripDiacritics") text = umatch(text, "^[¿¡]?(.-[^%s%p].-)%s*[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]?$") or text return text end --[==[ Convert a ''logical'' pagename (the pagename as it appears to the user, after diacritics and punctuation have been stripped) to a ''physical'' pagename (the pagename as it appears in the MediaWiki database). Reasons for a difference between the two are (a) unsupported titles such as `[ ]` (with square brackets in them), `#` (pound/hash sign) and `¯\_(ツ)_/¯` (with underscores), as well as overly long titles of various sorts; (b) "mammoth" pages that are split into parts (e.g. `a`, which is split into physical pagenames `a/languages A to L` and `a/languages M to Z`). For almost all purposes, you should work with logical and not physical pagenames. But there are certain use cases that require physical pagenames, such as checking the existence of a page or retrieving a page's contents. `pagename` is the logical pagename to be converted. `is_reconstructed_or_appendix` indicates whether the page is in the `Reconstruction` or `Appendix` namespaces. If it is omitted or has the value {nil}, the pagename is checked for an initial asterisk, and if found, the page is assumed to be a `Reconstruction` page. Setting a value of `false` or `true` to `is_reconstructed_or_appendix` disables this check and allows for mainspace pagenames that begin with an asterisk. ]==] function Language:logicalToPhysical(pagename, is_reconstructed_or_appendix) -- FIXME: This probably shouldn't happen but it happens when makeEntryName() receives nil. if pagename == nil then track("nil-passed-to-logicalToPhysical") return nil end local initial_asterisk if is_reconstructed_or_appendix == nil then local pagename_minus_initial_asterisk initial_asterisk, pagename_minus_initial_asterisk = pagename:match("^(%*)(.*)$") if pagename_minus_initial_asterisk then is_reconstructed_or_appendix = true pagename = pagename_minus_initial_asterisk elseif self:hasType("appendix-constructed") then is_reconstructed_or_appendix = true end end if not is_reconstructed_or_appendix then -- Check if the pagename is a listed unsupported title. local unsupportedTitles = load_data(links_data_module).unsupported_titles if unsupportedTitles[pagename] then return "Unsupported titles/" .. unsupportedTitles[pagename] end end -- Set `unsupported` as true if certain conditions are met. local unsupported -- Check if there's an unsupported character. \239\191\189 is the replacement character U+FFFD, which can't be typed -- directly here due to an abuse filter. Unix-style dot-slash notation is also unsupported, as it is used for -- relative paths in links, as are 3 or more consecutive tildes. Note: match is faster with magic -- characters/charsets; find is faster with plaintext. if ( match(pagename, "[#<>%[%]_{|}]") or find(pagename, "\239\191\189") or match(pagename, "%f[^%z/]%.%.?%f[%z/]") or find(pagename, "~~~") ) then unsupported = true -- If it looks like an interwiki link. elseif find(pagename, ":") then local prefix = gsub(pagename, "^:*(.-):.*", ulower) if ( load_data("Module:data/namespaces")[prefix] or load_data("Module:data/interwikis")[prefix] ) then unsupported = true end end -- Escape unsupported characters so they can be used in titles. ` is used as a delimiter for this, so a raw use of -- it in an unsupported title is also escaped here to prevent interference; this is only done with unsupported -- titles, though, so inclusion won't in itself mean a title is treated as unsupported (which is why it's excluded -- from the earlier test). if unsupported then -- FIXME: This conversion needs to be different for reconstructed pages with unsupported characters. There -- aren't any currently, but if there ever are, we need to fix this e.g. to put them in something like -- Reconstruction:Proto-Indo-European/Unsupported titles/`lowbar``num`. local unsupported_characters = load_data(links_data_module).unsupported_characters pagename = pagename:gsub("[#<>%[%]_`{|}\239]\191?\189?", unsupported_characters) :gsub("%f[^%z/]%.%.?%f[%z/]", function(m) return (gsub(m, "%.", "`period`")) end) :gsub("~~~+", function(m) return (gsub(m, "~", "`tilde`")) end) pagename = "Unsupported titles/" .. pagename elseif not is_reconstructed_or_appendix then -- Check if this is a mammoth page. If so, which subpage should we link to? local m_links_data = load_data(links_data_module) local mammoth_page_type = m_links_data.mammoth_pages[pagename] if mammoth_page_type then local canonical_name = self:getFullName() if canonical_name ~= "Translingual" and canonical_name ~= "English" then local this_subpage local L2_sort_key = get_L2_sort_key(canonical_name) for _, subpage_spec in ipairs(m_links_data.mammoth_page_subpage_types[mammoth_page_type]) do -- unpack() fails utterly on data loaded using mw.loadData() even if offsets are given local subpage, pattern = subpage_spec[1], subpage_spec[2] if pattern == true or L2_sort_key:match(pattern) then this_subpage = subpage break end end if not this_subpage then error(("Internal error: Bad data in mammoth_page_subpage_pages in [[Module:links/data]] for mammoth page %s, type %s; last entry didn't have 'true' in it"):format( pagename, mammoth_page_type)) end pagename = pagename .. "/" .. this_subpage end end end return (initial_asterisk or "") .. pagename end --[==[ Strip the diacritics from a display pagename and convert the resulting logical pagename into a physical pagename. This allows you, for example, to retrieve the contents of the page or check its existence. WARNING: This is deprecated and will be going away. It is a simple composition of `##Language:stripDiacritics` and `##Language:logicalToPhysical`; most callers only want the former, and if you need both, call them both yourself. `text` and `sc` are as in `##Language:stripDiacritics`, and `is_reconstructed_or_appendix` is as in `##Language:logicalToPhysical`. ]==] function Language:makeEntryName(text, sc, is_reconstructed_or_appendix) track("makeEntryName called") return self:logicalToPhysical(self:stripDiacritics(text, sc), is_reconstructed_or_appendix) end --[==[ Generate term alternants (e.g. simplified versions of traditional Chinese terms) using a language-specific method, and return them as a table. If the language provides no method for generating alternants, return a table containing only the input term. ]==] function Language:generateAlternants(text, sc) local generate_alternants = self._data.generate_alternants if generate_alternants == nil then return {text} end sc = checkScript(text, self, sc) return require("Module:" .. generate_alternants).generateAlternants(text, self, sc) end --[==[ Create a sort key for the given stripped text, following the rules appropriate for the language. This removes diacritical marks from the stripped text if they are not considered significant for sorting, and may perform some other changes. Any initial hyphen is also removed, and anything in parentheses is removed as well. The `sort_key` setting for each language in the data modules defines the replacements made by this function, or it gives the name of the module that takes the stripped text and returns a sortkey. ]==] function Language:makeSortKey(text, sc) if (not text) or text == "" then return text end if match(text, "<[^<>]+>") then track("track HTML tag") end -- Remove directionality/control characters, bold, italics, soft hyphens, strip markers and HTML tags. -- FIXME: Partly duplicated with remove_formatting() in [[Module:links]]. text = ugsub(text, "[\194\173\216\156\226\128\142\226\128\143\226\128\170-\226\128\174\226\129\166-\226\129\175]", "") text = text:gsub("('*)'''(.-'*)'''", "%1%2"):gsub("('*)''(.-'*)''", "%1%2") text = gsub(unstrip(text), "<[^<>]+>", "") text = decode_uri(text, "PATH") text = checkNoEntities(text) -- Remove initial hyphens and * unless the term only consists of spacing + punctuation characters. text = ugsub(text, "^([􀀀-􏿽]*)[-־ـ᠊*]+([􀀀-􏿽]*)(.*[^%s%p].*)", "%1%2%3") sc = checkScript(text, self, sc) text = normalize(text, sc) text = removeCarets(text, sc) -- For languages with dotted dotless i, ensure that "İ" is sorted as "i", and "I" is sorted as "ı". if self:hasDottedDotlessI() then text = gsub(text, "I\204\135", "i") -- decomposed "İ" :gsub("I", "ı") text = sc:toFixedNFD(text) end -- Convert to lowercase, make the sortkey, then convert to uppercase. Where the language has dotted dotless i, it is -- usually not necessary to convert "i" to "İ" and "ı" to "I" first, because "I" will always be interpreted as -- conventional "I" (not dotless "İ") by any sorting algorithms, which will have been taken into account by the -- sortkey substitutions themselves. However, if no sortkey substitutions have been specified, then conversion is -- necessary so as to prevent "i" and "ı" both being sorted as "I". -- -- An exception is made for scripts that (sometimes) sort by scraping page content, as that means they are sensitive -- to changes in capitalization (as it changes the target page). if not sc:sortByScraping() then text = ulower(text) end local actual_substitution_data, _ -- Don't trim whitespace here because it's significant at the beginning of a sort key or sort base. text, _, actual_substitution_data = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.sort_key, "sort_key", "makeSortKey", "notrim") if not sc:sortByScraping() then if self:hasDottedDotlessI() and not actual_substitution_data then text = text:gsub("ı", "I"):gsub("i", "İ") text = sc:toFixedNFC(text) end text = uupper(text) end -- Remove parentheses, as long as they are either preceded or followed by something. text = gsub(text, "(.)[()]+", "%1"):gsub("[()]+(.)", "%1") text = escape_risky_characters(text) return text end --[==[ Create the form used as as a basis for display text and transliteration. FIXME: Rename to correctInputText(). ]==] local function processDisplayText(text, self, sc, keepCarets, keepPrefixes) local subbedChars = {} text, subbedChars = doTempSubstitutions(text, subbedChars, keepCarets) text = decode_uri(text, "PATH") text = checkNoEntities(text) sc = checkScript(text, self, sc) text = normalize(text, sc) text, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, self._data.display_text, "display_text", "makeDisplayText") text = removeCarets(text, sc) -- Remove any interwiki link prefixes (unless they have been escaped or this has been disabled). if find(text, ":") and not keepPrefixes then local rep repeat text, rep = gsub(text, "\\\\(\\*:)", "\3%1") until rep == 0 text = gsub(text, "\\:", "\4") while true do local prefix = gsub(text, "^(.-):.+", function(m1) return (gsub(m1, "\244[\128-\191]*", "")) end) -- Check if the prefix is an interwiki, though ignore capitalised Wiktionary:, which is a namespace. if not prefix or prefix == text or prefix == "Wiktionary" or not (load_data("Module:data/interwikis")[ulower(prefix)] or prefix == "") then break end text = gsub(text, "^(.-):(.*)", function(m1, m2) local ret = {} for subbedChar in gmatch(m1, "\244[\128-\191]*") do insert(ret, subbedChar) end return concat(ret) .. m2 end) end text = gsub(text, "\3", "\\"):gsub("\4", ":") end return text, subbedChars end --[==[ Make the display text (i.e. what is displayed on the page). ]==] function Language:makeDisplayText(text, sc, keepPrefixes) if not text or text == "" then return text end local subbedChars text, subbedChars = processDisplayText(text, self, sc, nil, keepPrefixes) text = escape_risky_characters(text) return undoTempSubstitutions(text, subbedChars) end --[==[ Transliterate the text from the given script into Latin script (see [[Wiktionary:Transliteration and romanization]]). The language must have the `translit` property for this to work; if it is not present, {nil} is returned. The `sc` parameter is handled by the transliteration module, and how it is handled is specific to that module. Some transliteration modules may tolerate {nil} as the script, others require it to be one of the possible scripts that the module can transliterate, and will throw an error if it's not one of them. For this reason, the `sc` parameter should always be provided when writing non-language-specific code. The `module_override` parameter is used to override the default module that is used to provide the transliteration. This is useful in cases where you need to demonstrate a particular module in use, but there is no default module yet, or you want to demonstrate an alternative version of a transliteration module before making it official. It should not be used in real modules or templates, only for testing. All uses of this parameter are tracked by [[Wiktionary:Tracking/languages/module_override]]. '''Known bugs''': * This function assumes {tr(s1) .. tr(s2) == tr(s1 .. s2)}. When this assertion fails, wikitext markups like <nowiki>'''</nowiki> can cause wrong transliterations. * HTML entities like `&amp;apos;`, often used to escape wikitext markups, do not work. ]==] function Language:transliterate(text, sc, module_override) -- If there is no text, or the language doesn't have transliteration data and there's no override, return nil. if not text or text == "" or text == "-" then return text end -- If the script is not transliteratable (and no override is given), return nil. sc = checkScript(text, self, sc) if not (sc:isTransliterated() or module_override) then -- temporary tracking to see if/when this gets triggered track("non-transliterable") track("non-transliterable/" .. self._code) track("non-transliterable/" .. sc:getCode()) track("non-transliterable/" .. sc:getCode() .. "/" .. self._code) return nil end -- Remove any strip markers. text = unstrip(text) -- Do not process the formatting into PUA characters for certain languages. local processed = load_data(languages_data_module).substitution[self._code] ~= "none" -- Get the display text with the keepCarets flag set. local subbedChars if processed then text, subbedChars = processDisplayText(text, self, sc, true) end -- Transliterate (using the module override if applicable). text, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, true, module_override or self._data.translit, "translit", "tr") if not text then return nil end -- Incomplete transliterations return nil. local charset = sc.characters if charset and umatch(text, "[" .. charset .. "]") then -- Remove any characters in Latin, which includes Latin characters also included in other scripts (as these are -- false positives), as well as any PUA substitutions. Anything remaining should only be script code "None" -- (e.g. numerals). local check_text = ugsub(text, "[" .. get_script("Latn").characters .. "􀀀-􏿽]+", "") -- Set none_is_last_resort_only flag, so that any non-None chars will cause a script other than "None" to be -- returned. if find_best_script_without_lang(check_text, true):getCode() ~= "None" then return nil end end if processed then text = escape_risky_characters(text) text = undoTempSubstitutions(text, subbedChars) end -- If the script does not use capitalization, then capitalize any letters of the transliteration which are -- immediately preceded by a caret (and remove the caret). if text and not sc:hasCapitalization() and text:find("^", 1, true) then text = processCarets(text, "%^([\128-\191\244]*%*?)([^\128-\191\244][\128-\191]*)", function(m1, m2) return m1 .. uupper(m2) end) end -- Track module overrides. if module_override ~= nil then track("module_override") end return text end do local function handle_language_spec(self, spec, sc) local ret = self["_" .. spec] if ret == nil then ret = self._data[spec] if type(ret) == "string" then ret = list_to_set(split(ret, ",", true, true)) end self["_" .. spec] = ret end if type(ret) == "table" then ret = ret[sc:getCode()] end return not not ret end function Language:overrideManualTranslit(sc) return handle_language_spec(self, "override_translit", sc) end function Language:link_tr(sc) return handle_language_spec(self, "link_tr", sc) end end --[==[ Return {true} if the language has a transliteration module, or {false} if it doesn't. ]==] function Language:hasTranslit() return not not self._data.translit end --[==[ Return {true} if the language uses the letters I/ı and İ/i, or {false} if it doesn't.]==] function Language:hasDottedDotlessI() return not not self._data.dotted_dotless_i end function Language:toJSON(opts) local strip_diacritics, strip_diacritics_patterns, strip_diacritics_remove_diacritics = self._data.strip_diacritics if strip_diacritics then if strip_diacritics.from then strip_diacritics_patterns = {} for i, from in ipairs(strip_diacritics.from) do insert(strip_diacritics_patterns, {from = from, to = strip_diacritics.to[i] or ""}) end end strip_diacritics_remove_diacritics = strip_diacritics.remove_diacritics end -- mainCode should only end up non-nil if dontCanonicalizeAliases is passed to make_object(). -- props should either contain zero-argument functions to compute the value, or the value itself. local props = { ancestors = function() return self:getAncestorCodes() end, canonicalName = function() return self:getCanonicalName() end, categoryName = function() return self:getCategoryName("nocap") end, code = self._code, mainCode = self._mainCode, parent = function() return self:getParentCode() end, full = function() return self:getFullCode() end, stripDiacriticsPatterns = strip_diacritics_patterns, stripDiacriticsRemoveDiacritics = strip_diacritics_remove_diacritics, family = function() return self:getFamilyCode() end, aliases = function() return self:getAliases() end, varieties = function() return self:getVarieties() end, otherNames = function() return self:getOtherNames() end, pseudoFamilies = function() return self:getPseudoFamilies() end, scripts = function() return self:getScriptCodes() end, type = function() return keys_to_list(self:getTypes()) end, wikimediaLanguages = function() return self:getWikimediaLanguageCodes() end, wikidataItem = function() return self:getWikidataItem() end, wikipediaArticle = function() return self:getWikipediaArticle(true) end, } local ret = {} for prop, val in pairs(props) do if not opts.skip_fields or not opts.skip_fields[prop] then if type(val) == "function" then ret[prop] = val() else ret[prop] = val end end end -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function export.getDataModuleName(code) local letter = match(code, "^(%l)%l%l?$") return "Module:" .. ( letter == nil and "languages/data/exceptional" or #code == 2 and "languages/data/2" or "languages/data/3/" .. letter ) end get_data_module_name = export.getDataModuleName function export.getExtraDataModuleName(code) return get_data_module_name(code) .. "/extra" end get_extra_data_module_name = export.getExtraDataModuleName do local function make_stack(data) local key_types = { [2] = "unique", aliases = "unique", other_names = "unique", type = "append", varieties = "unique", wikipedia_article = "unique", wikimedia_codes = "unique" } local function __index(self, k) local stack, key_type = getmetatable(self), key_types[k] -- Data that isn't inherited from the parent. if key_type == "unique" then local v = stack[stack[make_stack]][k] if v == nil then local layer = stack[0] if layer then -- Could be false if there's no extra data. v = layer[k] end end return v -- Data that is appended by each generation. elseif key_type == "append" then local parts, offset, n = {}, 0, stack[make_stack] for i = 1, n do local part = stack[i][k] if part == nil then offset = offset + 1 else parts[i - offset] = part end end return offset ~= n and concat(parts, ",") or nil end local n = stack[make_stack] while true do local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end local v = layer[k] if v ~= nil then return v end n = n - 1 end end local function __newindex() error("table is read-only") end local function __pairs(self) -- Iterate down the stack, caching keys to avoid duplicate returns. local stack, seen = getmetatable(self), {} local n = stack[make_stack] local iter, state, k, v = pairs(stack[n]) return function() repeat repeat k = iter(state, k) if k == nil then n = n - 1 local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end iter, state, k = pairs(layer) end until not (k == nil or seen[k]) -- Get the value via a lookup, as the one returned by the -- iterator will be the raw value from the current layer, -- which may not be the one __index will return for that -- key. Also memoize the key in `seen` (even if the lookup -- returns nil) so that it doesn't get looked up again. -- TODO: store values in `self`, avoiding the need to create -- the `seen` table. The iterator will need to iterate over -- `self` with `next` first to find these on future loops. v, seen[k] = self[k], true until v ~= nil return k, v end end local __ipairs = require(table_module).indexIpairs function make_stack(data) local stack = { data, [make_stack] = 1, -- stores the length and acts as a sentinel to confirm a given metatable is a stack. __index = __index, __newindex = __newindex, __pairs = __pairs, __ipairs = __ipairs, } stack.__metatable = stack return setmetatable({}, stack), stack end return make_stack(data) end local function get_stack(data) local stack = getmetatable(data) return stack and type(stack) == "table" and stack[make_stack] and stack or nil end --[==[ <span style="color: var(--wikt-palette-red,#BA0000)">This function is not for use in entries or other content pages.</span> Return a blob of data about the language. The format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes. If `extra` is set, any extra data in the relevant `/extra` module will be included. (Note that it will be included anyway if it has already been loaded into the language object.) If `raw` is set, then the returned data will not contain any data inherited from parent objects. -- Do NOT use these methods! -- All uses should be pre-approved on the talk page! ]==] function Language:getData(extra, raw) if extra then self:loadInExtraData() end local data = self._data -- If raw is not set, just return the data. if not raw then return data end local stack = get_stack(data) -- If there isn't a stack or its length is 1, return the data. Extra data (if any) will be included, as it's -- stored at key 0 and doesn't affect the reported length. if stack == nil then return data end local n = stack[make_stack] if n == 1 then return data end extra = stack[0] -- If there isn't any extra data, return the top layer of the stack. if extra == nil then return stack[n] end -- If there is, return a new stack which has the top layer at key 1 and the extra data at key 0. data, stack = make_stack(stack[n]) stack[0] = extra return data end function Language:loadInExtraData() -- Only full languages have extra data. if not self:hasType("language", "full") then return end local data = self._data -- If there's no stack, create one. local stack = get_stack(self._data) if stack == nil then data, stack = make_stack(data) -- If already loaded, return. elseif stack[0] ~= nil then return end self._data = data -- Load extra data from the relevant module and add it to the stack at key 0, so that the __index and __pairs -- metamethods will pick it up, since they iterate down the stack until they run out of layers. local code = self._code local modulename = get_extra_data_module_name(code) -- No data cached as false. stack[0] = modulename and load_data(modulename)[code] or false end --[==[ Return the name of the module containing the language's data, e.g. [[Module:languages/data/3/k]] for three-letter codes beginning with `k`. ]==] function Language:getDataModuleName() local name = self._dataModuleName if name == nil then name = self:hasType("etymology-only") and etymology_languages_data_module or get_data_module_name(self._mainCode or self._code) self._dataModuleName = name end return name end --[==[ Return the name of the module containing the language's extra data, e.g. [[Module:languages/data/3/k/extra]] for three-letter codes beginning with `k`. ]==] function Language:getExtraDataModuleName() local name = self._extraDataModuleName if name == nil then name = not self:hasType("etymology-only") and get_extra_data_module_name(self._mainCode or self._code) or false self._extraDataModuleName = name end return name or nil end function export.makeObject(code, data, dontCanonicalizeAliases) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end -- Convert any aliases. local input_code = code code = normalize_code(code) input_code = dontCanonicalizeAliases and input_code or code local parent if data.parent then parent = get_by_code(data.parent, nil, true, true) else parent = Language end parent.__index = parent local lang = {_code = input_code} -- This can only happen if dontCanonicalizeAliases is passed to make_object(). if code ~= input_code then lang._mainCode = code end local parent_data = parent._data if parent_data == nil then -- Full code is the same as the code. lang._fullCode = parent._code or code else -- Copy full code. lang._fullCode = parent._fullCode local stack = get_stack(parent_data) if stack == nil then parent_data, stack = make_stack(parent_data) end -- Insert the input data as the new top layer of the stack. local n = stack[make_stack] + 1 data, stack[n], stack[make_stack] = parent_data, data, n end lang._data = data return setmetatable(lang, parent) end make_object = export.makeObject end --[==[ Find the language whose code matches the one provided. If it exists, return a `Language` object representing the language. Otherwise, return {nil}, unless `paramForError` is given, in which case an error is generated. If `paramForError` is {true}, a generic error message mentioning the bad code is generated; otherwise `paramForError` should be a string or number specifying the parameter that the code came from, and this parameter will be mentioned in the error message along with the bad code. If `allowEtymLang` is specified, etymology-only language codes are allowed and looked up along with full language codes. If `allowFamily` is specified, language family codes are allowed and looked up along with normal language codes. ]==] function export.getByCode(code, paramForError, allowEtymLang, allowFamily) -- [[ Track uses of paramForError, ultimately so it can be removed, as error-handling should be done by -- [[Module:parameters]], not here. ]] -- I (Benwing) disagree; that is an idealistic goal unlikely to be achievable -- realistically. if paramForError ~= nil then track("paramForError") end if type(code) ~= "string" then local typ if not code then typ = "nil" elseif check_object("language", true, code) then typ = "a language object" elseif check_object("family", true, code) then typ = "a family object" else typ = "a " .. type(code) end error("The function getByCode expects a string as its first argument, but received " .. typ .. ".") end local m_data = load_data(languages_data_module) if m_data.aliases[code] or m_data.track[code] then track(code) end local norm_code = normalize_code(code) -- Get the data, checking for etymology-only languages if allowEtymLang is set. local data = load_data(get_data_module_name(norm_code))[norm_code] or allowEtymLang and load_data(etymology_languages_data_module)[norm_code] -- If no data was found and allowFamily is set, check the family data. If the main family data was found, make the -- object with [[Module:families]] instead, as family objects have different methods. However, if it's an -- etymology-only family, use make_object in this module (which handles object inheritance), and the -- family-specific methods will be inherited from the parent object. if data == nil and allowFamily then data = load_data("Module:families/data")[norm_code] if data ~= nil then if data.parent == nil then return make_family_object(norm_code, data) elseif not allowEtymLang then data = nil end end end local retval = code and data and make_object(code, data) if not retval and paramForError then require("Module:languages/errorGetBy").code(code, paramForError, allowEtymLang, allowFamily) end return retval end get_by_code = export.getByCode --[==[ Find the language whose canonical name (the name used to represent that language on Wiktionary) or other name matches the one provided. If it exists, return a `Language` object representing the language. Otherwise, return {nil}, unless `paramForError` is given, in which case an error is generated. If `allowEtymLang` is specified, etymology-only language codes are allowed and looked up along with full language codes. If `allowFamily` is specified, language family codes are allowed and looked up along with normal language codes. The canonical name of languages should always be unique (it is an error for two languages on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result. This function is powered by [[Module:languages/canonical names]], which contains a pre-generated mapping of full-language canonical names to codes. It is generated by going through the [[:Category:Language data modules]] for full languages. When `allowEtymLang` is specified for the above function, [[Module:etymology languages/canonical names]] may also be used, and when `allowFamily` is specified for the above function, [[Module:families/canonical names]] may also be used. ]==] function export.getByCanonicalName(name, errorIfInvalid, allowEtymLang, allowFamily) local byName = load_data("Module:languages/canonical names") local code = byName and byName[name] -- Old English localization: also accept an Old English name (e.g. "Englisc"). if not code then code = code_of_ang_name(name) end if not code and allowEtymLang then byName = load_data("Module:etymology languages/canonical names") code = byName and byName[name] or byName[gsub(name, " [Ss]ubstrate$", "")] or byName[gsub(name, "^a ", "")] or byName[gsub(name, "^a ", ""):gsub(" [Ss]ubstrate$", "")] or -- For etymology families like "ira-pro". -- FIXME: This is not ideal, as it allows " languages" to be appended to any etymology-only language, too. byName[match(name, "^(.*) languages$")] end if not code and allowFamily then byName = load_data("Module:families/canonical names") code = byName[name] or byName[match(name, "^(.*) languages$")] end local retval = code and get_by_code(code, errorIfInvalid, allowEtymLang, allowFamily) if not retval and errorIfInvalid then require("Module:languages/errorGetBy").canonicalName(name, allowEtymLang, allowFamily) end return retval end --[==[ Used by [[Module:languages/data/2]] (et al.) and [[Module:etymology languages/data]], [[Module:families/data]], [[Module:scripts/data]] and [[Module:writing systems/data]] to finalize the data into the format that is actually returned. ]==] function export.finalizeData(data, main_type, variety) local fields = {"type"} if main_type == "language" then insert(fields, 4) -- script codes insert(fields, "ancestors") insert(fields, "link_tr") insert(fields, "override_translit") insert(fields, "wikimedia_codes") elseif main_type == "script" then insert(fields, 3) -- writing system codes end -- Families and writing systems have no extra fields to process. local fields_len = #fields for _, entity in next, data do if variety then -- Move parent from 3 to "parent" and family from "family" to 3. These are different for the sake of -- convenience, since very few varieties have the family specified, whereas all of them have a parent. entity.parent, entity[3] = entity[3], entity.family entity.family = nil -- Give the type "regular" iff not a variety and no other types are assigned. elseif not (entity.type or entity.parent) then entity.type = "regular" end for i = 1, fields_len do local key = fields[i] local field = entity[key] if field and type(field) == "string" then entity[key] = gsub(field, "%s*,%s*", ",") end end end return data end --[==[ For backwards compatibility only; modules should require the error themselves. ]==] function export.err(lang_code, param, code_desc, template_tag, not_real_lang) return require("Module:languages/error")(lang_code, param, code_desc, template_tag, not_real_lang) end return export bit1po5o6ftn0mb20est88wranzkyq1 828 7869 54896 54703 2026-09-28T22:15:40Z Deadend0914 7211 54896 Scribunto text/plain local l = {} l['ang'] = { name = 'Englisc', wiktionaryExists = true} l['af'] = { name = 'Affircanisc', wiktionaryExists = true} l['bn'] = {name = 'Bengalisc', wiktionaryExists = true} l['cn'] = {name = 'Catalānisc', wiktionaryExists = true} l['cs']={name = 'Bæmisc', wiktionaryExists = true} l['da']={name = 'Densic', wiktionaryExists = true} l['de']={name = 'Þēodisc', wiktionaryExists = true} l['el']={name= 'Crēacisc', wiktionaryExists = true} l['en']={name='Nīwenglisc', wiktionaryExists = true} l['eo']={name='Esperantisc', wiktionaryExists = true} l['es']={name='Spēonisc', wiktionaryExists = true} l['et']={name = 'Eotolisc', wiktionaryExists = true} l['eu']={name='Wascisc', wiktionaryExists = true} l['fa']={name='Persisc', wiktionaryExists = true} l['fi']={name='Finnisc', wiktionaryExists = true} l['fo']={name='Færisc', wiktionaryExists = true} l['fr']={name='Frencisc', wiktionaryExists = true} l['ga']={name='Īrisc', wiktionaryExists = true} l['gl']={name='Galizisc', wiktionaryExists = true} l['gn']={name='Awaisc', wiktionaryExists = true} l['gv']={name='Manisc', wiktionaryExists = true} l['haw']={name='Hawaiisc'} l['hi']={name='Hindisc', wiktionaryExists = true} l['hu']={name='Hungarisc', wiktionaryExists=true} l['id']={name='Indonesisc', wiktionaryExists = true} l['io']={name='Idoisc', wiktionaryExists=true} l['is']={name='Īslendisc', wiktionaryExists=true} l['it']={name='Italisc', wiktionaryExists=true} l['la']={name='Lǣden', wiktionaryExists=true} l['li']={name='Limburgisc', wiktionaryExists=true} l['lt']={name='Litwisc', wiktionaryExists=true} l['lv']={name='Lettisc', wiktionaryExists=true} l['nl']={name='Niðerlendisc', wiktionaryExists=true} l['no']={name='Norþwegisc', wiktionaryExists=true} l['pl']={name='Polisc', wiktionaryExists=true} l['pt']={name='Portugisc', wiktionaryExists=true} l['qu']={name='Kescwisc', wiktionaryExists=true} l['ro']={name='Rumǣnisc', wiktionaryExists=true} l['sa']={name='Sanscritisc', wiktionaryExists=true} l['sq']={name='Albānisc', wiktionaryExists=true} l['sv']={name='Swēonisc', wiktionaryExists=true} gxt99xn0sctlqj5wuct69vywrt6al8c 54900 54896 2026-09-28T22:40:50Z Deadend0914 7211 54900 Scribunto text/plain local export = {} -- We can't use mw.loadData() on [[Module:languages/chars]] because [[Module:languages/data]] itself is sometimes loaded -- using mw.loadData(), and calling mw.loadData() on [[Module:languages/chars]] will insert metatables into the -- character tables, which the second mw.loadData() will choke on. local m_chars = require("Module:languages/chars") local u = require("Module:string/char") local c = m_chars.chars export.chars = c local p = m_chars.puaChars export.puaChars = p local cs = m_chars.chars_substitutions export.chars_substitutions = cs -- FIXME! Many of the script-specific values below can be moved to [[Module:scripts/data]] to serve as script-wide -- fallback values instead of specifying them for each language using the script. local s = {} -- These values are placed here to make it possible to synchronise a group of languages without the need for a dedicated function module. -- cau do local cau_remove_diacritics = c.grave .. c.acute .. c.macron local cau_from = {"[IlΙІӀᴴ]"} local cau_to = {{ ["l"] = "ӏ", ["Ι"] = "ӏ", ["І"] = "ӏ", ["Ӏ"] = "ӏ", ["ᴴ"] = "ᵸ", }} s["cau-Cyrl-displaytext"] = { from = cau_from, to = cau_to, } s["cau-Cyrl-stripdiacritics"] = { remove_diacritics = cau_remove_diacritics, from = cau_from, to = cau_to, } s["cau-Latn-stripdiacritics"] = {remove_diacritics = cau_remove_diacritics} end s["itc-Latn-displaytext"] = { from = {c.caron}, to = {c.breve}, } s["itc-Latn-stripdiacritics"] = {remove_diacritics = c.macron .. c.breve .. c.diaer .. c.caron .. c.dinvbreve} s["itc-Latn-sortkey"] = { remove_diacritics = c.circ .. c.tilde .. c.macron .. c.breve .. c.diaer .. c.caron .. c.zigzag .. c.dmacron .. c.dtilde .. c.dinvbreve .. c.small_a .. c.small_e .. c.small_i .. c.small_o .. c.small_u, -- Chiefly medieval abbreviations. from = {"ᵃ", "æ", "[đꝱꟈ]", "ᵉ", "ⁱ", "ꝁ", "[ƚꝉꝲ]", "ꝳ", "ꝴ", "[ꝋᵒ]", "œ", "[ꝑꝓꝕ]", "[ꝗꝙ]", "[ꝛꝵꝶꝝ]", "[ꟊˢ]", "[ꝷᵗ]", "ᵘ", "ꝟ", "⁊"}, to = {"a", "ae", "d", "e", "i", "k", "l", "m", "n", "o", "oe", "p", "q", "r", "s", "t", "u", "v", "&"} } s["Jpan-standardchars"] = -- exclude ぢづヂヅ "ぁあぃいぅうぇえぉおかがきぎくぐけげこごさざしじすずせぜそぞただちっつてでとどなにぬねのはばぱひびぴふぶぷへべぺほぼぽまみむめもゃやゅゆょよらりるれろん" .. "ァアィイゥウェエォオカガキギクグケゲコゴサザシジスズセゼソゾタダチッツテデトドナニヌネノハバパヒビピフブプヘベペホボポマミムメモャヤュユョヨラリルレロン" local jpx_displaytext = { from = {"～", "＝"}, to = {"〜", "゠"} } s["jpx-displaytext"] = { Jpan = jpx_displaytext, Hani = jpx_displaytext, Hrkt = jpx_displaytext, Hira = jpx_displaytext, Kana = jpx_displaytext -- not Latn or Brai } s["jpx-stripdiacritics"] = s["jpx-displaytext"] s["jpx-sortkey"] = { Jpan = "Jpan-sortkey", Hani = "Hani-sortkey", Hrkt = "Hira-sortkey", -- sort general kana by normalizing to Hira Hira = "Hira-sortkey", Kana = "Kana-sortkey", Latn = {remove_diacritics = c.tilde .. c.macron .. c.diaer} } s["jpx-translit"] = { Hrkt = "Hrkt-translit", Hira = "Hrkt-translit", Kana = "Hrkt-translit" } s["roa-oil-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"æ", "œ", "·"}, to = {"ae", "oe", " "} } s["wen-sortkey"] = { from = {"ch", "[lłßꞩẜ]", "dz[" .. c.caron .. c.acute .. "]", "[bcefmnoprswz][" .. c.caron .. c.acute .. c.dotabove .. "]"}, to = { "h" .. p[1], { ["l"] = "l" .. p[1], ["ł"] = "l", ["ß"] = "s", ["ꞩ"] = "š", ["ẜ"] = "š", }, { ["dz" .. c.caron] = "d" .. p[1], ["dz" .. c.acute] = "d" .. p[2] }, { ["b" .. c.acute] = "b" .. p[1], ["c" .. c.caron] = "c" .. p[1], ["c" .. c.acute] = "c" .. p[2], ["e" .. c.caron] = "e" .. p[1], ["e" .. c.dotabove] = "e" .. p[1], ["f" .. c.acute] = "f" .. p[1], ["m" .. c.acute] = "m" .. p[1], ["n" .. c.acute] = "n" .. p[1], ["o" .. c.acute] = "o" .. p[1], ["p" .. c.acute] = "p" .. p[1], ["r" .. c.caron] = "r" .. p[1], ["r" .. c.acute] = "r" .. p[2], ["s" .. c.caron] = "s" .. p[1], ["s" .. c.acute] = "s" .. p[2], ["w" .. c.acute] = "w" .. p[1], ["z" .. c.caron] = "z" .. p[1], ["z" .. c.acute] = "z" .. p[2], } } } -- Myanmar dotted form : https://www.unicode.org/Public/UNIDATA/StandardizedVariants.txt s["aio-displaytext"] = { from = {"([ကဂငတထပမယလဝဢေၵၸၺႀꩠꩡꩢꩣꩤꩥꩦꩫꩬꩯꩺ])"}, to = {"%1" .. c.VS01} } s["aio-stripdiacritics"] = { remove_diacritics = c.VS01, } s["esx-displaytext"] = { from = {"ǝ"}, to = {"ə"}, } s["esx-stripdiacritics"] = s["esx-displaytext"] s["phk-displaytext"] = s["aio-displaytext"] s["phk-stripdiacritics"] = s["aio-stripdiacritics"] s["kht-displaytext"] = s["aio-displaytext"] s["kht-stripdiacritics"] = s["aio-stripdiacritics"] export.shared = s --[==[ var: Short-term solution to override the standard substitution process, by forcing the module to substitute the entire text in one pass, if "cont" is given. This results in any PUA characters that are used as stand-ins for formatting being handled by the language-specific substitution process, which is usually undesirable. If the value is "none" then the formatting tags do not get turned into PUA characters in the first place. This override is provided for languages which use formatting between strings of text which might need to interact with each other (e.g. Korean 값이 transliterates as "gaps-i", but [[값]] has the formatting '''값'''[[-이]]. The normal process would split the text at the second '''.) ]==] export.substitution = { ["gmy"] = "none", ["ja"] = "cont", ["jje"] = "cont", ["ket"] = "none", ["ko"] = "cont", ["ko-ear"] = "cont", ["ru"] = "cont", ["th-new"] = "cont", ["sa"] = "cont", ["zkt"] = "cont", } --[==[ var: Code aliases. The left side is the alias and the right side is the canonical code. NOTE: These are gradually being deprecated, so should not be added to on a permanent basis. Temporary additions are permitted under reasonable circumstances (e.g. to facilitate changing a language's code). When an alias is no longer used, it should be removed. Aliases in this table are tracked at [[Wiktionary:Tracking/languages/LANG]]; see e.g. [[Special:WhatLinksHere/Wiktionary:Tracking/languages/VL.]] for the `VL.` alias. ]==] export.aliases = { ["EL."] = "la-ecc", ["LL."] = "la-lat", ["ML."] = "la-med", ["NL."] = "la-new", ["VL."] = "la-vul", ["grc-epc"] = "grc-epi", ["nds-DE"] = "nds-de", ["nds-NL"] = "nds-nl", ["roa-oan"] = "roa-ona", ["sa-cls"] = "cls", ["sa-ved"] = "vsn", } --[==[ var: Codes which are tracked. Note that all aliases listed above are also tracked, so should not be duplicated here. Tracking uses the same mechanism described above in the comment above `export.aliases`. ]==] export.track = { -- Codes duplicated between full and etymology-only languages. ["lzh-lit"] = true, ["lzh"] = true, -- Languages actively being converted to families. ["bh"] = true, -- inc-bih ["nan"] = true, -- zhx-nan -- Transcription scheme being changed. ["trk-pro"] = true, } return export mpdv2gw5dmhuaq7h15kvelv3q6pv46b 828 7978 54925 54717 2026-09-29T00:05:09Z Deadend0914 7211 54925 Scribunto text/plain local export = {} local languages_module = "Module:languages" local maintenance_category_module = "Module:maintenance category" local pages_module = "Module:pages" local string_compare_module = "Module:string/compare" local string_decode_entities_module = "Module:string/decodeEntities" local string_remove_comments_module = "Module:string/removeComments" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local template_parser_module = "Module:template parser" local mw = mw local string = string local table = table local ustring = mw.ustring local concat = table.concat local find = string.find local format = string.format local gsub = string.gsub local insert = table.insert local load_data = mw.loadData local match = string.match local new_title = mw.title.new local pairs = pairs local require = require local sub = string.sub local toNFC = ustring.toNFC local toNFD = ustring.toNFD local ugsub = ustring.gsub local function class_else_type(...) class_else_type = require(template_parser_module).class_else_type return class_else_type(...) end local function decode_entities(...) decode_entities = require(string_decode_entities_module) return decode_entities(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end local function get_category(...) get_category = require(maintenance_category_module).get_category return get_category(...) end local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function parse(...) parse = require(template_parser_module).parse return parse(...) end local function remove_comments(...) remove_comments = require(string_remove_comments_module) return remove_comments(...) end local function physical_to_logical_pagename_if_mammoth(...) physical_to_logical_pagename_if_mammoth = require(pages_module).physical_to_logical_pagename_if_mammoth return physical_to_logical_pagename_if_mammoth(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function string_compare(...) string_compare = require(string_compare_module) return string_compare(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] -- Old English localization: the ==L2== headings are rendered by [[Bysen:sprǣc]] from -- [[Module:sprǣcnaman]], so those names have to be recognized as language names below as well. The -- module is optional: if it is missing, the English names are used exactly as before. local ang_names_module = "Module:sprǣcnaman" local ang_names local function get_ang_names() if ang_names == nil then local ok, mod = pcall(require, ang_names_module) ang_names = ok and mod or false end return ang_names or nil end local langnames local function get_langnames() langnames, get_langnames = load_data("Module:languages/canonical names"), nil -- Old English localization: add the Old English language names, so that an ==L2== heading -- written with {{Bysen:sprǣc}} is recognized as a canonical language name. local m_ang_names = get_ang_names() if m_ang_names then for _, ang_name in pairs(m_ang_names.names) do langnames[ang_name] = true end end return langnames end -- Combining character data used when categorising unusual characters. These resolve into two patterns, used to find -- single combining characters (i.e. character + diacritic(s)) or double combining characters (i.e. character + -- diacritic(s) + character). -- Charsets are in the format used by Unicode's UnicodeSet tool: https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp. -- Single combining characters. -- Charset: [[:M:]&[:^Canonical_Combining_Class=/^Double_/:]&[:^subhead=Grapheme joiner:]&[:^Variation_Selector=Yes:]] -- Note: concatenating hundreds of lines at once gives an error, so () are used every 150 lines to break it up into chunks. local comb_chars_single = ("\204\128-\205\142" .. -- U+0300-U+034E "\205\144-\205\155" .. -- U+0350-U+035B "\205\163-\205\175" .. -- U+0363-U+036F "\210\131-\210\137" .. -- U+0483-U+0489 "\214\145-\214\189" .. -- U+0591-U+05BD "\214\191" .. -- U+05BF "\215\129" .. -- U+05C1 "\215\130" .. -- U+05C2 "\215\132" .. -- U+05C4 "\215\133" .. -- U+05C5 "\215\135" .. -- U+05C7 "\216\144-\216\154" .. -- U+0610-U+061A "\217\139-\217\159" .. -- U+064B-U+065F "\217\176" .. -- U+0670 "\219\150-\219\156" .. -- U+06D6-U+06DC "\219\159-\219\164" .. -- U+06DF-U+06E4 "\219\167" .. -- U+06E7 "\219\168" .. -- U+06E8 "\219\170-\219\173" .. -- U+06EA-U+06ED "\220\145" .. -- U+0711 "\220\176-\221\138" .. -- U+0730-U+074A "\222\166-\222\176" .. -- U+07A6-U+07B0 "\223\171-\223\179" .. -- U+07EB-U+07F3 "\223\189" .. -- U+07FD "\224\160\150-\224\160\153" .. -- U+0816-U+0819 "\224\160\155-\224\160\163" .. -- U+081B-U+0823 "\224\160\165-\224\160\167" .. -- U+0825-U+0827 "\224\160\169-\224\160\173" .. -- U+0829-U+082D "\224\161\153-\224\161\155" .. -- U+0859-U+085B "\224\162\151-\224\162\159" .. -- U+0897-U+089F "\224\163\138-\224\163\161" .. -- U+08CA-U+08E1 "\224\163\163-\224\164\131" .. -- U+08E3-U+0903 "\224\164\186-\224\164\188" .. -- U+093A-U+093C "\224\164\190-\224\165\143" .. -- U+093E-U+094F "\224\165\145-\224\165\151" .. -- U+0951-U+0957 "\224\165\162" .. -- U+0962 "\224\165\163" .. -- U+0963 "\224\166\129-\224\166\131" .. -- U+0981-U+0983 "\224\166\188" .. -- U+09BC "\224\166\190-\224\167\132" .. -- U+09BE-U+09C4 "\224\167\135" .. -- U+09C7 "\224\167\136" .. -- U+09C8 "\224\167\139-\224\167\141" .. -- U+09CB-U+09CD "\224\167\151" .. -- U+09D7 "\224\167\162" .. -- U+09E2 "\224\167\163" .. -- U+09E3 "\224\167\190" .. -- U+09FE "\224\168\129-\224\168\131" .. -- U+0A01-U+0A03 "\224\168\188" .. -- U+0A3C "\224\168\190-\224\169\130" .. -- U+0A3E-U+0A42 "\224\169\135" .. -- U+0A47 "\224\169\136" .. -- U+0A48 "\224\169\139-\224\169\141" .. -- U+0A4B-U+0A4D "\224\169\145" .. -- U+0A51 "\224\169\176" .. -- U+0A70 "\224\169\177" .. -- U+0A71 "\224\169\181" .. -- U+0A75 "\224\170\129-\224\170\131" .. -- U+0A81-U+0A83 "\224\170\188" .. -- U+0ABC "\224\170\190-\224\171\133" .. -- U+0ABE-U+0AC5 "\224\171\135-\224\171\137" .. -- U+0AC7-U+0AC9 "\224\171\139-\224\171\141" .. -- U+0ACB-U+0ACD "\224\171\162" .. -- U+0AE2 "\224\171\163" .. -- U+0AE3 "\224\171\186-\224\171\191" .. -- U+0AFA-U+0AFF "\224\172\129-\224\172\131" .. -- U+0B01-U+0B03 "\224\172\188" .. -- U+0B3C "\224\172\190-\224\173\132" .. -- U+0B3E-U+0B44 "\224\173\135" .. -- U+0B47 "\224\173\136" .. -- U+0B48 "\224\173\139-\224\173\141" .. -- U+0B4B-U+0B4D "\224\173\149-\224\173\151" .. -- U+0B55-U+0B57 "\224\173\162" .. -- U+0B62 "\224\173\163" .. -- U+0B63 "\224\174\130" .. -- U+0B82 "\224\174\190-\224\175\130" .. -- U+0BBE-U+0BC2 "\224\175\134-\224\175\136" .. -- U+0BC6-U+0BC8 "\224\175\138-\224\175\141" .. -- U+0BCA-U+0BCD "\224\175\151" .. -- U+0BD7 "\224\176\128-\224\176\132" .. -- U+0C00-U+0C04 "\224\176\188" .. -- U+0C3C "\224\176\190-\224\177\132" .. -- U+0C3E-U+0C44 "\224\177\134-\224\177\136" .. -- U+0C46-U+0C48 "\224\177\138-\224\177\141" .. -- U+0C4A-U+0C4D "\224\177\149" .. -- U+0C55 "\224\177\150" .. -- U+0C56 "\224\177\162" .. -- U+0C62 "\224\177\163" .. -- U+0C63 "\224\178\129-\224\178\131" .. -- U+0C81-U+0C83 "\224\178\188" .. -- U+0CBC "\224\178\190-\224\179\132" .. -- U+0CBE-U+0CC4 "\224\179\134-\224\179\136" .. -- U+0CC6-U+0CC8 "\224\179\138-\224\179\141" .. -- U+0CCA-U+0CCD "\224\179\149" .. -- U+0CD5 "\224\179\150" .. -- U+0CD6 "\224\179\162" .. -- U+0CE2 "\224\179\163" .. -- U+0CE3 "\224\179\179" .. -- U+0CF3 "\224\180\128-\224\180\131" .. -- U+0D00-U+0D03 "\224\180\187" .. -- U+0D3B "\224\180\188" .. -- U+0D3C "\224\180\190-\224\181\132" .. -- U+0D3E-U+0D44 "\224\181\134-\224\181\136" .. -- U+0D46-U+0D48 "\224\181\138-\224\181\141" .. -- U+0D4A-U+0D4D "\224\181\151" .. -- U+0D57 "\224\181\162" .. -- U+0D62 "\224\181\163" .. -- U+0D63 "\224\182\129-\224\182\131" .. -- U+0D81-U+0D83 "\224\183\138" .. -- U+0DCA "\224\183\143-\224\183\148" .. -- U+0DCF-U+0DD4 "\224\183\150" .. -- U+0DD6 "\224\183\152-\224\183\159" .. -- U+0DD8-U+0DDF "\224\183\178" .. -- U+0DF2 "\224\183\179" .. -- U+0DF3 "\224\184\177" .. -- U+0E31 "\224\184\180-\224\184\186" .. -- U+0E34-U+0E3A "\224\185\135-\224\185\142" .. -- U+0E47-U+0E4E "\224\186\177" .. -- U+0EB1 "\224\186\180-\224\186\188" .. -- U+0EB4-U+0EBC "\224\187\136-\224\187\142" .. -- U+0EC8-U+0ECE "\224\188\152" .. -- U+0F18 "\224\188\153" .. -- U+0F19 "\224\188\181" .. -- U+0F35 "\224\188\183" .. -- U+0F37 "\224\188\185" .. -- U+0F39 "\224\188\190" .. -- U+0F3E "\224\188\191" .. -- U+0F3F "\224\189\177-\224\190\132" .. -- U+0F71-U+0F84 "\224\190\134" .. -- U+0F86 "\224\190\135" .. -- U+0F87 "\224\190\141-\224\190\151" .. -- U+0F8D-U+0F97 "\224\190\153-\224\190\188" .. -- U+0F99-U+0FBC "\224\191\134" .. -- U+0FC6 "\225\128\171-\225\128\190" .. -- U+102B-U+103E "\225\129\150-\225\129\153" .. -- U+1056-U+1059 "\225\129\158-\225\129\160" .. -- U+105E-U+1060 "\225\129\162-\225\129\164" .. -- U+1062-U+1064 "\225\129\167-\225\129\173" .. -- U+1067-U+106D "\225\129\177-\225\129\180" .. -- U+1071-U+1074 "\225\130\130-\225\130\141" .. -- U+1082-U+108D "\225\130\143" .. -- U+108F "\225\130\154-\225\130\157" .. -- U+109A-U+109D "\225\141\157-\225\141\159" .. -- U+135D-U+135F "\225\156\146-\225\156\149" .. -- U+1712-U+1715 "\225\156\178-\225\156\180" .. -- U+1732-U+1734 "\225\157\146" .. -- U+1752 "\225\157\147" .. -- U+1753 "\225\157\178" .. -- U+1772 "\225\157\179" .. -- U+1773 "\225\158\180-\225\159\147") .. -- U+17B4-U+17D3 ("\225\159\157" .. -- U+17DD "\225\162\133" .. -- U+1885 "\225\162\134" .. -- U+1886 "\225\162\169" .. -- U+18A9 "\225\164\160-\225\164\171" .. -- U+1920-U+192B "\225\164\176-\225\164\187" .. -- U+1930-U+193B "\225\168\151-\225\168\155" .. -- U+1A17-U+1A1B "\225\169\149-\225\169\158" .. -- U+1A55-U+1A5E "\225\169\160-\225\169\188" .. -- U+1A60-U+1A7C "\225\169\191" .. -- U+1A7F "\225\170\176-\225\171\142" .. -- U+1AB0-U+1ACE "\225\172\128-\225\172\132" .. -- U+1B00-U+1B04 "\225\172\180-\225\173\132" .. -- U+1B34-U+1B44 "\225\173\171-\225\173\179" .. -- U+1B6B-U+1B73 "\225\174\128-\225\174\130" .. -- U+1B80-U+1B82 "\225\174\161-\225\174\173" .. -- U+1BA1-U+1BAD "\225\175\166-\225\175\179" .. -- U+1BE6-U+1BF3 "\225\176\164-\225\176\183" .. -- U+1C24-U+1C37 "\225\179\144-\225\179\146" .. -- U+1CD0-U+1CD2 "\225\179\148-\225\179\168" .. -- U+1CD4-U+1CE8 "\225\179\173" .. -- U+1CED "\225\179\180" .. -- U+1CF4 "\225\179\183-\225\179\185" .. -- U+1CF7-U+1CF9 "\225\183\128-\225\183\140" .. -- U+1DC0-U+1DCC "\225\183\142-\225\183\187" .. -- U+1DCE-U+1DFB "\225\183\189-\225\183\191" .. -- U+1DFD-U+1DFF "\226\131\144-\226\131\176" .. -- U+20D0-U+20F0 "\226\179\175-\226\179\177" .. -- U+2CEF-U+2CF1 "\226\181\191" .. -- U+2D7F "\226\183\160-\226\183\191" .. -- U+2DE0-U+2DFF "\227\128\170-\227\128\175" .. -- U+302A-U+302F "\227\130\153" .. -- U+3099 "\227\130\154" .. -- U+309A "\234\153\175-\234\153\178" .. -- U+A66F-U+A672 "\234\153\180-\234\153\189" .. -- U+A674-U+A67D "\234\154\158" .. -- U+A69E "\234\154\159" .. -- U+A69F "\234\155\176" .. -- U+A6F0 "\234\155\177" .. -- U+A6F1 "\234\160\130" .. -- U+A802 "\234\160\134" .. -- U+A806 "\234\160\139" .. -- U+A80B "\234\160\163-\234\160\167" .. -- U+A823-U+A827 "\234\160\172" .. -- U+A82C "\234\162\128" .. -- U+A880 "\234\162\129" .. -- U+A881 "\234\162\180-\234\163\133" .. -- U+A8B4-U+A8C5 "\234\163\160-\234\163\177" .. -- U+A8E0-U+A8F1 "\234\163\191" .. -- U+A8FF "\234\164\166-\234\164\173" .. -- U+A926-U+A92D "\234\165\135-\234\165\147" .. -- U+A947-U+A953 "\234\166\128-\234\166\131" .. -- U+A980-U+A983 "\234\166\179-\234\167\128" .. -- U+A9B3-U+A9C0 "\234\167\165" .. -- U+A9E5 "\234\168\169-\234\168\182" .. -- U+AA29-U+AA36 "\234\169\131" .. -- U+AA43 "\234\169\140" .. -- U+AA4C "\234\169\141" .. -- U+AA4D "\234\169\187-\234\169\189" .. -- U+AA7B-U+AA7D "\234\170\176" .. -- U+AAB0 "\234\170\178-\234\170\180" .. -- U+AAB2-U+AAB4 "\234\170\183" .. -- U+AAB7 "\234\170\184" .. -- U+AAB8 "\234\170\190" .. -- U+AABE "\234\170\191" .. -- U+AABF "\234\171\129" .. -- U+AAC1 "\234\171\171-\234\171\175" .. -- U+AAEB-U+AAEF "\234\171\181" .. -- U+AAF5 "\234\171\182" .. -- U+AAF6 "\234\175\163-\234\175\170" .. -- U+ABE3-U+ABEA "\234\175\172" .. -- U+ABEC "\234\175\173" .. -- U+ABED "\239\172\158" .. -- U+FB1E "\239\184\160-\239\184\175" .. -- U+FE20-U+FE2F "\240\144\135\189" .. -- U+101FD "\240\144\139\160" .. -- U+102E0 "\240\144\141\182-\240\144\141\186" .. -- U+10376-U+1037A "\240\144\168\129-\240\144\168\131" .. -- U+10A01-U+10A03 "\240\144\168\133" .. -- U+10A05 "\240\144\168\134" .. -- U+10A06 "\240\144\168\140-\240\144\168\143" .. -- U+10A0C-U+10A0F "\240\144\168\184-\240\144\168\186" .. -- U+10A38-U+10A3A "\240\144\168\191" .. -- U+10A3F "\240\144\171\165" .. -- U+10AE5 "\240\144\171\166" .. -- U+10AE6 "\240\144\180\164-\240\144\180\167" .. -- U+10D24-U+10D27 "\240\144\181\169-\240\144\181\173" .. -- U+10D69-U+10D6D "\240\144\186\171" .. -- U+10EAB "\240\144\186\172" .. -- U+10EAC "\240\144\187\188-\240\144\187\191" .. -- U+10EFC-U+10EFF "\240\144\189\134-\240\144\189\144" .. -- U+10F46-U+10F50 "\240\144\190\130-\240\144\190\133" .. -- U+10F82-U+10F85 "\240\145\128\128-\240\145\128\130" .. -- U+11000-U+11002 "\240\145\128\184-\240\145\129\134" .. -- U+11038-U+11046 "\240\145\129\176" .. -- U+11070 "\240\145\129\179" .. -- U+11073 "\240\145\129\180" .. -- U+11074 "\240\145\129\191-\240\145\130\130" .. -- U+1107F-U+11082 "\240\145\130\176-\240\145\130\186" .. -- U+110B0-U+110BA "\240\145\131\130" .. -- U+110C2 "\240\145\132\128-\240\145\132\130" .. -- U+11100-U+11102 "\240\145\132\167-\240\145\132\180" .. -- U+11127-U+11134 "\240\145\133\133" .. -- U+11145 "\240\145\133\134" .. -- U+11146 "\240\145\133\179" .. -- U+11173 "\240\145\134\128-\240\145\134\130" .. -- U+11180-U+11182 "\240\145\134\179-\240\145\135\128" .. -- U+111B3-U+111C0 "\240\145\135\137-\240\145\135\140" .. -- U+111C9-U+111CC "\240\145\135\142" .. -- U+111CE "\240\145\135\143" .. -- U+111CF "\240\145\136\172-\240\145\136\183" .. -- U+1122C-U+11237 "\240\145\136\190" .. -- U+1123E "\240\145\137\129" .. -- U+11241 "\240\145\139\159-\240\145\139\170" .. -- U+112DF-U+112EA "\240\145\140\128-\240\145\140\131" .. -- U+11300-U+11303 "\240\145\140\187" .. -- U+1133B "\240\145\140\188" .. -- U+1133C "\240\145\140\190-\240\145\141\132" .. -- U+1133E-U+11344 "\240\145\141\135" .. -- U+11347 "\240\145\141\136" .. -- U+11348 "\240\145\141\139-\240\145\141\141" .. -- U+1134B-U+1134D "\240\145\141\151" .. -- U+11357 "\240\145\141\162" .. -- U+11362 "\240\145\141\163" .. -- U+11363 "\240\145\141\166-\240\145\141\172" .. -- U+11366-U+1136C "\240\145\141\176-\240\145\141\180" .. -- U+11370-U+11374 "\240\145\142\184-\240\145\143\128" .. -- U+113B8-U+113C0 "\240\145\143\130" .. -- U+113C2 "\240\145\143\133" .. -- U+113C5 "\240\145\143\135-\240\145\143\138" .. -- U+113C7-U+113CA "\240\145\143\140-\240\145\143\144" .. -- U+113CC-U+113D0 "\240\145\143\146" .. -- U+113D2 "\240\145\143\161" .. -- U+113E1 "\240\145\143\162" .. -- U+113E2 "\240\145\144\181-\240\145\145\134" .. -- U+11435-U+11446 "\240\145\145\158" .. -- U+1145E "\240\145\146\176-\240\145\147\131" .. -- U+114B0-U+114C3 "\240\145\150\175-\240\145\150\181" .. -- U+115AF-U+115B5 "\240\145\150\184-\240\145\151\128" .. -- U+115B8-U+115C0 "\240\145\151\156" .. -- U+115DC "\240\145\151\157" .. -- U+115DD "\240\145\152\176-\240\145\153\128" .. -- U+11630-U+11640 "\240\145\154\171-\240\145\154\183" .. -- U+116AB-U+116B7 "\240\145\156\157-\240\145\156\171" .. -- U+1171D-U+1172B "\240\145\160\172-\240\145\160\186" .. -- U+1182C-U+1183A "\240\145\164\176-\240\145\164\181" .. -- U+11930-U+11935 "\240\145\164\183" .. -- U+11937 "\240\145\164\184" .. -- U+11938 "\240\145\164\187-\240\145\164\190" .. -- U+1193B-U+1193E "\240\145\165\128") .. -- U+11940 ("\240\145\165\130" .. -- U+11942 "\240\145\165\131" .. -- U+11943 "\240\145\167\145-\240\145\167\151" .. -- U+119D1-U+119D7 "\240\145\167\154-\240\145\167\160" .. -- U+119DA-U+119E0 "\240\145\167\164" .. -- U+119E4 "\240\145\168\129-\240\145\168\138" .. -- U+11A01-U+11A0A "\240\145\168\179-\240\145\168\185" .. -- U+11A33-U+11A39 "\240\145\168\187-\240\145\168\190" .. -- U+11A3B-U+11A3E "\240\145\169\135" .. -- U+11A47 "\240\145\169\145-\240\145\169\155" .. -- U+11A51-U+11A5B "\240\145\170\138-\240\145\170\153" .. -- U+11A8A-U+11A99 "\240\145\176\175-\240\145\176\182" .. -- U+11C2F-U+11C36 "\240\145\176\184-\240\145\176\191" .. -- U+11C38-U+11C3F "\240\145\178\146-\240\145\178\167" .. -- U+11C92-U+11CA7 "\240\145\178\169-\240\145\178\182" .. -- U+11CA9-U+11CB6 "\240\145\180\177-\240\145\180\182" .. -- U+11D31-U+11D36 "\240\145\180\186" .. -- U+11D3A "\240\145\180\188" .. -- U+11D3C "\240\145\180\189" .. -- U+11D3D "\240\145\180\191-\240\145\181\133" .. -- U+11D3F-U+11D45 "\240\145\181\135" .. -- U+11D47 "\240\145\182\138-\240\145\182\142" .. -- U+11D8A-U+11D8E "\240\145\182\144" .. -- U+11D90 "\240\145\182\145" .. -- U+11D91 "\240\145\182\147-\240\145\182\151" .. -- U+11D93-U+11D97 "\240\145\187\179-\240\145\187\182" .. -- U+11EF3-U+11EF6 "\240\145\188\128" .. -- U+11F00 "\240\145\188\129" .. -- U+11F01 "\240\145\188\131" .. -- U+11F03 "\240\145\188\180-\240\145\188\186" .. -- U+11F34-U+11F3A "\240\145\188\190-\240\145\189\130" .. -- U+11F3E-U+11F42 "\240\145\189\154" .. -- U+11F5A "\240\147\145\128" .. -- U+13440 "\240\147\145\135-\240\147\145\149" .. -- U+13447-U+13455 "\240\150\132\158-\240\150\132\175" .. -- U+1611E-U+1612F "\240\150\171\176-\240\150\171\180" .. -- U+16AF0-U+16AF4 "\240\150\172\176-\240\150\172\182" .. -- U+16B30-U+16B36 "\240\150\189\143" .. -- U+16F4F "\240\150\189\145-\240\150\190\135" .. -- U+16F51-U+16F87 "\240\150\190\143-\240\150\190\146" .. -- U+16F8F-U+16F92 "\240\150\191\164" .. -- U+16FE4 "\240\150\191\176" .. -- U+16FF0 "\240\150\191\177" .. -- U+16FF1 "\240\155\178\157" .. -- U+1BC9D "\240\155\178\158" .. -- U+1BC9E "\240\156\188\128-\240\156\188\173" .. -- U+1CF00-U+1CF2D "\240\156\188\176-\240\156\189\134" .. -- U+1CF30-U+1CF46 "\240\157\133\165-\240\157\133\169" .. -- U+1D165-U+1D169 "\240\157\133\173-\240\157\133\178" .. -- U+1D16D-U+1D172 "\240\157\133\187-\240\157\134\130" .. -- U+1D17B-U+1D182 "\240\157\134\133-\240\157\134\139" .. -- U+1D185-U+1D18B "\240\157\134\170-\240\157\134\173" .. -- U+1D1AA-U+1D1AD "\240\157\137\130-\240\157\137\132" .. -- U+1D242-U+1D244 "\240\157\168\128-\240\157\168\182" .. -- U+1DA00-U+1DA36 "\240\157\168\187-\240\157\169\172" .. -- U+1DA3B-U+1DA6C "\240\157\169\181" .. -- U+1DA75 "\240\157\170\132" .. -- U+1DA84 "\240\157\170\155-\240\157\170\159" .. -- U+1DA9B-U+1DA9F "\240\157\170\161-\240\157\170\175" .. -- U+1DAA1-U+1DAAF "\240\158\128\128-\240\158\128\134" .. -- U+1E000-U+1E006 "\240\158\128\136-\240\158\128\152" .. -- U+1E008-U+1E018 "\240\158\128\155-\240\158\128\161" .. -- U+1E01B-U+1E021 "\240\158\128\163" .. -- U+1E023 "\240\158\128\164" .. -- U+1E024 "\240\158\128\166-\240\158\128\170" .. -- U+1E026-U+1E02A "\240\158\130\143" .. -- U+1E08F "\240\158\132\176-\240\158\132\182" .. -- U+1E130-U+1E136 "\240\158\138\174" .. -- U+1E2AE "\240\158\139\172-\240\158\139\175" .. -- U+1E2EC-U+1E2EF "\240\158\147\172-\240\158\147\175" .. -- U+1E4EC-U+1E4EF "\240\158\151\174" .. -- U+1E5EE "\240\158\151\175" .. -- U+1E5EF "\240\158\163\144-\240\158\163\150" .. -- U+1E8D0-U+1E8D6 "\240\158\165\132-\240\158\165\138") -- U+1E944-U+1E94A -- Double combining characters. -- Charset: [[:M:]&[:Canonical_Combining_Class=/^Double_/:]&[:^subhead=Grapheme joiner:]&[:^Variation_Selector=Yes:]] local comb_chars_double = "\205\156-\205\162" .. -- U+035C-U+0362 "\225\183\141" .. -- U+1DCD "\225\183\188" -- U+1DFC -- Variation selectors etc.; separated out so that we don't get categories for them. -- Charset: [[:M:]&[[:subhead=Grapheme joiner:][:Variation_Selector=Yes:]]]. local comb_chars_other = "\205\143" .. -- U+034F "\225\160\139-\225\160\141" .. -- U+180B-U+180D "\225\160\143" .. -- U+180F "\239\184\128-\239\184\143" .. -- U+FE00-U+FE0F "\243\160\132\128-\243\160\135\175" -- U+E0100-U+E01EF local comb_chars_all = comb_chars_single .. comb_chars_double .. comb_chars_other local comb_chars = { combined_single = "[^" .. comb_chars_all .. "][" .. comb_chars_single .. comb_chars_other .. "]+%f[^" .. comb_chars_all .. "]", combined_double = "[^" .. comb_chars_all .. "][" .. comb_chars_single .. comb_chars_other .. "]*[" .. comb_chars_double .. "]+[" .. comb_chars_all .. "]*.[" .. comb_chars_single .. comb_chars_other .. "]*", diacritics_single = "[" .. comb_chars_single .. "]", diacritics_double = "[" .. comb_chars_double .. "]", diacritics_all = "[" .. comb_chars_all .. "]" } -- Somewhat curated list from https://unicode.org/Public/emoji/16.0/emoji-sequences.txt. -- NOTE: There are lots more emoji sequences involving non-emoji Plane 0 symbols followed by 0xFE0F, which we don't -- (yet?) handle. local emoji_chars = "\226\140\154" .. -- U+231A (⌚) "\226\140\155" .. -- U+231B (⌛) "\226\140\168" .. -- U+2328 (⌨) "\226\143\143" .. -- U+23CF (⏏) "\226\143\169-\226\143\179" .. -- U+23E9-U+23F3 (⏩-⏳) "\226\143\184-\226\143\186" .. -- U+23F8-U+23FA (⏸-⏺) "\226\150\170" .. -- U+25AA (▪) "\226\150\171" .. -- U+25AB (▫) "\226\150\182" .. -- U+25B6 (▶) "\226\151\128" .. -- U+25C0 (◀) "\226\151\187-\226\151\190" .. -- U+25FB-U+25FE (◻-◾) "\226\152\128-\226\152\132" .. -- U+2600-U+2604 (☀-☄) "\226\152\142" .. -- U+260E (☎) "\226\152\145" .. -- U+2611 (☑) "\226\152\148" .. -- U+2614 (☔) "\226\152\149" .. -- U+2615 (☕) "\226\152\152" .. -- U+2618 (☘) "\226\152\157" .. -- U+261D (☝) "\226\152\160" .. -- U+2620 (☠) "\226\152\162" .. -- U+2622 (☢) "\226\152\163" .. -- U+2623 (☣) "\226\152\166" .. -- U+2626 (☦) "\226\152\170" .. -- U+262A (☪) "\226\152\174" .. -- U+262E (☮) "\226\152\175" .. -- U+262F (☯) "\226\152\184-\226\152\186" .. -- U+2638-U+263A (☸-☺) "\226\153\136-\226\153\147" .. -- U+2648-U+2653 (♈-♓) "\226\153\159" .. -- U+265F (♟) "\226\153\160" .. -- U+2660 (♠) "\226\153\163" .. -- U+2663 (♣) "\226\153\165" .. -- U+2665 (♥) "\226\153\166" .. -- U+2666 (♦) "\226\153\168" .. -- U+2668 (♨) "\226\153\187" .. -- U+267B (♻) "\226\153\190" .. -- U+267E (♾) "\226\153\191" .. -- U+267F (♿) "\226\154\146-\226\154\151" .. -- U+2692-U+2697 (⚒-⚗) "\226\154\153" .. -- U+2699 (⚙) "\226\154\155" .. -- U+269B (⚛) "\226\154\156" .. -- U+269C (⚜) "\226\154\160" .. -- U+26A0 (⚠) "\226\154\161" .. -- U+26A1 (⚡) "\226\154\170" .. -- U+26AA (⚪) "\226\154\171" .. -- U+26AB (⚫) "\226\154\176" .. -- U+26B0 (⚰) "\226\154\177" .. -- U+26B1 (⚱) "\226\154\189" .. -- U+26BD (⚽) "\226\154\190" .. -- U+26BE (⚾) "\226\155\132" .. -- U+26C4 (⛄) "\226\155\133" .. -- U+26C5 (⛅) "\226\155\136" .. -- U+26C8 (⛈) "\226\155\142" .. -- U+26CE (⛎) "\226\155\143" .. -- U+26CF (⛏) "\226\155\145" .. -- U+26D1 (⛑) "\226\155\147" .. -- U+26D3 (⛓) "\226\155\148" .. -- U+26D4 (⛔) "\226\155\169" .. -- U+26E9 (⛩) "\226\155\170" .. -- U+26EA (⛪) "\226\155\176-\226\155\181" .. -- U+26F0-U+26F5 (⛰-⛵) "\226\155\183-\226\155\186" .. -- U+26F7-U+26FA (⛷-⛺) "\226\155\189" .. -- U+26FD (⛽) "\226\156\130" .. -- U+2702 (✂) "\226\156\133" .. -- U+2705 (✅) "\226\156\136-\226\156\141" .. -- U+2708-U+270D (✈-✍) "\226\156\143" .. -- U+270F (✏) "\226\156\146" .. -- U+2712 (✒) "\226\156\148" .. -- U+2714 (✔) "\226\156\150" .. -- U+2716 (✖) "\226\156\157" .. -- U+271D (✝) "\226\156\161" .. -- U+2721 (✡) "\226\156\168" .. -- U+2728 (✨) "\226\156\179" .. -- U+2733 (✳) "\226\156\180" .. -- U+2734 (✴) "\226\157\132" .. -- U+2744 (❄) "\226\157\135" .. -- U+2747 (❇) "\226\157\140" .. -- U+274C (❌) "\226\157\142" .. -- U+274E (❎) "\226\157\147-\226\157\149" .. -- U+2753-U+2755 (❓-❕) "\226\157\151" .. -- U+2757 (❗) "\226\157\163" .. -- U+2763 (❣) "\226\157\164" .. -- U+2764 (❤) "\226\158\149-\226\158\151" .. -- U+2795-U+2797 (➕-➗) "\226\158\161" .. -- U+27A1 (➡) "\226\158\176" .. -- U+27B0 (➰) "\226\158\191" .. -- U+27BF (➿) "\226\164\180" .. -- U+2934 (⤴) "\226\164\181" .. -- U+2935 (⤵) "\226\172\133-\226\172\135" .. -- U+2B05-U+2B07 (⬅-⬇) "\226\172\155" .. -- U+2B1B (⬛) "\226\172\156" .. -- U+2B1C (⬜) "\226\173\144" .. -- U+2B50 (⭐) "\226\173\149" .. -- U+2B55 (⭕) "\227\128\176" .. -- U+3030 (〰) "\227\128\189" .. -- U+303D (〽) "\227\138\151" .. -- U+3297 (㊗) "\227\138\153" .. -- U+3299 (㊙) "\240\159\128\132" .. -- U+1F004 (🀄) "\240\159\131\143" .. -- U+1F0CF (🃏) "\240\159\133\176" .. -- U+1F170 (🅰) "\240\159\133\177" .. -- U+1F171 (🅱) "\240\159\133\190" .. -- U+1F17E (🅾) "\240\159\133\191" .. -- U+1F17F (🅿) "\240\159\134\142" .. -- U+1F18E (🆎) "\240\159\134\145-\240\159\134\154" .. -- U+1F191-U+1F19A (🆑-🆚) "\240\159\136\129" .. -- U+1F201 (🈁) "\240\159\136\130" .. -- U+1F202 (🈂) "\240\159\136\154" .. -- U+1F21A (🈚) "\240\159\136\175" .. -- U+1F22F (🈯) "\240\159\136\178-\240\159\136\186" .. -- U+1F232-U+1F23A (🈲-🈺) "\240\159\137\144" .. -- U+1F250 (🉐) "\240\159\137\145" .. -- U+1F251 (🉑) "\240\159\140\128-\240\159\153\143" .. -- U+1F300-U+1F64F (🌀-🙏) "\240\159\154\128-\240\159\155\151" .. -- U+1F680-U+1F6D7 (🚀-🛗) "\240\159\155\156-\240\159\155\172" .. -- U+1F6DC-U+1F6EC (🛜-🛬) "\240\159\155\176-\240\159\155\188" .. -- U+1F6F0-U+1F6FC (🛰-🛼) "\240\159\159\160-\240\159\159\171" .. -- U+1F7E0-U+1F7EB (🟠-🟫) "\240\159\159\176" .. -- U+1F7F0 (🟰) "\240\159\164\140-\240\159\169\147" .. -- U+1F90C-U+1FA53 (🤌-🩓) "\240\159\169\160-\240\159\169\173" .. -- U+1FA60-U+1FA6D (🩠-🩭) "\240\159\169\176-\240\159\169\188" .. -- U+1FA70-U+1FA7C (🩰-🩼) "\240\159\170\128-\240\159\170\137" .. -- U+1FA80-U+1FA89 (🪀-🪉) "\240\159\170\143-\240\159\171\134" .. -- U+1FA8F-U+1FAC6 (🪏-🫆) "\240\159\171\142-\240\159\171\156" .. -- U+1FACE-U+1FADC (🫎-🫜) "\240\159\171\159-\240\159\171\169" .. -- U+1FADF-U+1FAE9 (🫟-🫩) "\240\159\171\176-\240\159\171\184" -- U+1FAF0-U+1FAF8 (🫰-🫸) local unsupported_characters local function get_unsupported_characters() unsupported_characters, get_unsupported_characters = {}, nil for k, v in pairs(load_data("Module:links/data").unsupported_characters) do unsupported_characters[v] = k end return unsupported_characters end -- The list of unsupported titles and invert it (so the keys are pagenames and values are canonical titles). local unsupported_titles local function get_unsupported_titles() unsupported_titles, get_unsupported_titles = {}, nil for k, v in pairs(load_data("Module:links/data").unsupported_titles) do unsupported_titles[v] = k end return unsupported_titles end -- To save on memory, we only cache names with either non-ASCII characters in them or ASCII characters to be removed or -- transformed (apostrophe, double quote, hyphen). local L2_sort_key_cache = {} function export.get_L2_sort_key(L2) if L2 == "Translingual" then return "\1" elseif L2 == "English" then return "\2" elseif match(L2, "^[%z\1-\b\14-!#-&(-,.-\127]+$") then return L2 end local sort_key = L2_sort_key_cache[L2] if sort_key then return sort_key end sort_key = toNFC(ugsub(ugsub(toNFD(L2), "[" .. comb_chars_all .. "'\"ʻʼ]+", ""), "[%s%-]+", " ")) L2_sort_key_cache[L2] = sort_key return sort_key end --[==[ Given a pagename (or {nil} for the current page), create and return a data structure describing the page. The returned object includes the following fields: * `comb_chars`: A table containing various Lua character class patterns for different types of combined characters (those that decompose into multiple characters in the NFD decomposition). The patterns are meant to be used with {mw.ustring.find()}. The keys are: ** `single`: Single combining characters (character + diacritic), without surrounding brackets; ** `double`: Double combining characters (character + diacritic + character), without surrounding brackets; ** `vs`: Variation selectors, without surrounding brackets; ** `all`: Concatenation of `single` + `double` + `vs`, without surrounding brackets; ** `diacritics_single`: Like `single` but with surrounding brackets; ** `diacritics_double`: Like `double` but with surrounding brackets; ** `diacritics_all`: Like `all` but with surrounding brackets; ** `combined_single`: Lua pattern for matching a spacing character followed by one or more single combining characters; ** `combined_double`: Lua pattern for matching a combination of two spacing characters separated by one or more double combining characters, possibly also with single combining characters; * `emoji_pattern`: A Lua character class pattern (including surrounding brackets) that matches emojis. Meant to be used with {mw.ustring.find()}. * `L2_list`: Ordered list of L2 headings on the page, with the extra key `n` that gives the length of the list. * `L2_sections`: Lookup table of L2 headings on the page, where the key is the section number assigned by the preprocessor, and the value is the L2 heading name. Once an invocation has got its actual section number from get_current_L2 in [[Module:pages]], it can use this table to determine its parent L2. TODO: We could expand this to include subsections, to check POS headings are correct etc. * `unsupported_titles`: Map from pagenames to canonical titles for unsupported-title pages. * `namespace`: Namespace of the pagename. * `ns`: Namespace table for the page from mw.site.namespaces (TODO: merge with `namespace` above). * `full_raw_pagename`: Full version of the '''RAW''' pagename (i.e. unsupported-title pages aren't canonicalized); including the namespace and the base (portion before the slash). * `pagename`: Canonicalized subpage portion of the pagename (unsupported-title pages are canonicalized). * `pagename_with_base`: Same as `pagename` in the main namespace; otherwise, the whole pagename without the namespace. * `decompose_pagename`: Equivalent of `pagename` in NFD decomposition. * `pagename_len`: Length of `pagename` in Unicode chars, where combinations of spacing character + decomposed diacritic are treated as single characters. * `explode_pagename`: Set of characters found in `pagename`. The keys are characters (where combinations of spacing character + decomposed diacritic are treated as single characters). * `encoded_pagename`: FIXME: Document me. * `pagename_defaultsort`: FIXME: Document me. * `raw_defaultsort`: FIXME: Document me. * `wikitext_topic_cat`: FIXME: Document me. * `wikitext_langname_cat`: FIXME: Document me. `no_fetch_content` says to not fetch and parse the content or set a DEFAULTSORT sort key, in order to save time on test and documentation pages that have lots of template invocations that set `|pagename=`. It turns out nearly all the time of this function is contained in the line `frame:callParserFunction("DEFAULTSORT", data.pagename_defaultsort)`, so we skip it on test and documentation pages where it accomplishes nothing in any case. ]==] function export.process_page(pagename, no_fetch_content) local data = { comb_chars = comb_chars, emoji_pattern = "[" .. emoji_chars .. "]", unsupported_titles = unsupported_titles or get_unsupported_titles() } local cats = {} data.cats = cats -- We cannot store `raw_title` in `data` because it contains a metatable. local raw_title local function bad_pagename() if not pagename then error("Internal error: Something wrong, `data.pagename` not specified but current title contains illegal characters") else error(format("Bad value for `data.pagename`: '%s', which must not contain illegal characters", pagename)) end end if pagename then -- for testing, doc pages, etc. raw_title = new_title(pagename) if not raw_title then bad_pagename() end else raw_title = mw.title.getCurrentTitle() end local nsText = raw_title.nsText local namespace_is_reconstruction = nsText == "Reconstruction" data.namespace = nsText data.ns = mw.site.namespaces[raw_title.namespace] local full_raw_pagename = raw_title.fullText data.full_raw_pagename = full_raw_pagename local frame = mw.getCurrentFrame() -- WARNING: `content` may be nil, e.g. if we're substing a template like {{ja-new}} on a not-yet-created page -- or if the module specifies the subpage as `data.pagename` (which many modules do) and we're in an Appendix -- or other non-mainspace page. We used to make the latter an error but there are too many modules that do it, -- and substing on a nonexistent page is totally legit, and we don't actually need to be able to access the -- content of the page. local content = not no_fetch_content and raw_title:getContent() or nil -- Get the pagename. pagename = physical_to_logical_pagename_if_mammoth(raw_title) pagename = gsub(pagename, "^Unsupported titles/(.+)", function(m) insert(cats, "Unsupported titles") local title = (unsupported_titles or get_unsupported_titles())[m] if title then return title end -- Substitute pairs of "`". Those not used for escaping should be escaped as "`grave`", but might not be, -- so if a pair don't form a match, the closing "`" should become the opening "`" of the next match attempt. -- This has to be done manually, instead of using gsub. local open_pos = find(m, "`") if not open_pos then return m end title = {sub(m, 1, open_pos - 1)} while true do local close_pos = find(m, "`", open_pos + 1) if not close_pos then -- Add "`" plus any remaining characters. insert(title, sub(m, open_pos)) break end local escape = sub(m, open_pos, close_pos) local ch = (unsupported_characters or get_unsupported_characters())[escape] -- Match found, so substitute the character and move to the first "`" after the match if found, or -- otherwise return. if ch then insert(title, ch) local nxt_pos = close_pos + 1 open_pos = find(m, "`", nxt_pos) -- Add any characters between the match and the next "`" or end. if open_pos then insert(title, sub(m, nxt_pos, open_pos - 1)) else insert(title, sub(m, nxt_pos)) break end -- Match not found, so make the closing "`" the opening "`" of the next attempt. else -- Add the failed match, except for the closing "`". insert(title, sub(m, open_pos, close_pos - 1)) open_pos = close_pos end end return concat(title) end) -- Save pagename, as the local variable will be destructively modified. data.pagename = pagename if nsText == "" then data.pagename_with_base = pagename else data.pagename_with_base = raw_title.text end -- Decompose the pagename in Unicode normalization form D. data.decompose_pagename = toNFD(pagename) -- Explode the current page name into a character table, taking decomposed combining characters into account. local explode_pagename = {} local pagename_len = 0 local function explode(char) explode_pagename[char] = true pagename_len = pagename_len + 1 return "" end pagename = ugsub(pagename, comb_chars.combined_double, explode) pagename = gsub(ugsub(pagename, comb_chars.combined_single, explode), ".[\128-\191]*", explode) data.explode_pagename = explode_pagename data.pagename_len = pagename_len -- Generate DEFAULTSORT. data.encoded_pagename = encode_entities(data.pagename) data.pagename_defaultsort = get_lang("mul"):makeSortKey(data.encoded_pagename) if not no_fetch_content then frame:callParserFunction("DEFAULTSORT", data.pagename_defaultsort) end data.raw_defaultsort = uupper(raw_title.text) -- Make `L2_list` and `L2_sections`, note raw wikitext use of {{DEFAULTSORT:}} and {{DISPLAYTITLE:}}, then add categories if any unwanted L1 headings are found, the L2 headings are in the wrong order, or they don't match a canonical language name. -- Note: HTML comments shouldn't be removed from `content` until after this step, as they can affect the result. do local L2_list, L2_list_len, L2_sections = {}, 0, {} local prev, rc local new_cats, L2_wrong_order = {} local function handle_heading(heading) local level = heading.level if level > 2 then return end local name = heading:get_name() -- heading:get_name() will return nil if there are any newline characters in the preprocessed heading name (e.g. from an expanded template). In such cases, the preprocessor section count still increments (since it's calculated pre-expansion), but the heading will fail, so the L2 count shouldn't be incremented. if name == nil then return end L2_list_len = L2_list_len + 1 L2_list[L2_list_len] = name L2_sections[heading.section] = name -- Also add any L1s, since they terminate the preceding L2, but add a maintenance category since it's probably a mistake. if level == 1 then new_cats["Pages with unwanted L1 headings"] = true end -- Check the heading is in the right order. -- FIXME: we need a more sophisticated sorting method which handles non-diacritic special characters (e.g. Magɨ). if prev and not ( L2_wrong_order or string_compare(export.get_L2_sort_key(prev), export.get_L2_sort_key(name)) ) then new_cats["Pages with language headings in the wrong order"] = true L2_wrong_order = true end -- Check it's a canonical language name. if not (langnames or get_langnames())[name] then new_cats["Pages with nonstandard language headings"] = true end prev = name end local function handle_template(template) -- Turn off redirect checking except in the Reconstruction namespace because the rc flag is only -- used in the Reconstruction namespace and the other names are parser functions, which AFAIK can't -- be redirected to. local name = template:get_name(nil, not namespace_is_reconstruction and "no_redirect" or nil) if name == "DEFAULTSORT:" then new_cats["Pages with DEFAULTSORT conflicts"] = true elseif name == "DISPLAYTITLE:" then new_cats["Pages with DISPLAYTITLE conflicts"] = true elseif name == "reconstructed" then rc = true end end if content then for node in parse(content):iterate_nodes() do local node_class = class_else_type(node) if node_class == "heading" then handle_heading(node) elseif node_class == "template" then handle_template(node) elseif node_class == "parameter" then new_cats["Pages with raw triple-brace template parameters"] = true end end end L2_list.n = L2_list_len data.L2_list = L2_list data.L2_sections = L2_sections insert(cats, get_category("Pages with entries")) insert(cats, get_category(format("Pages with %s entr%s", L2_list_len, L2_list_len == 1 and "y" or "ies"))) for cat in pairs(new_cats) do insert(cats, get_category(cat)) end if namespace_is_reconstruction and not rc then local langname = match(full_raw_pagename, "^Reconstruction:([^/]+)/.") if langname then insert(cats, get_category(langname .. " entries missing Template:reconstructed")) end end end ------ 4. Parse page for maintenance categories. ------ -- Use of tab characters. if content and find(content, "\t", 1, true) then insert(cats, get_category("Pages with tab characters")) end -- Unencoded character(s) in title. local IDS = list_to_set{"⿰", "⿱", "⿲", "⿳", "⿴", "⿵", "⿶", "⿷", "⿸", "⿹", "⿺", "⿻", "⿼", "⿽", "⿾", "⿿", "㇯"} for char in pairs(explode_pagename) do if IDS[char] and char ~= data.pagename then insert(cats, "Terms containing unencoded characters") break end end -- Raw wikitext use of a topic or langname category. Also check if any raw sortkeys have been used. do local wikitext_topic_cat = {} local wikitext_langname_cat = {} local raw_sortkey -- If a raw sortkey has been found, add it to the relevant table. -- If there's no table (or the index is just `true`), create one first. local function add_cat_table(t, lang, sortkey) local t_lang = t[lang] if not sortkey then if not t_lang then t[lang] = true end return elseif t_lang == true or not t_lang then t_lang = {} t[lang] = t_lang end t_lang[uupper(decode_entities(sortkey))] = true end local function process_category(content, cat, colon, nxt) local pipe = find(cat, "|", colon + 1, true) -- Categories cannot end "|]]". if pipe == #cat then return end local title = new_title(pipe and sub(cat, 1, pipe - 1) or cat) if not (title and title.namespace == 14) then return end -- Get the sortkey (if any), then canonicalize category title. local sortkey = pipe and sub(cat, pipe + 1) or nil cat = title.text if sortkey then raw_sortkey = true -- If the sortkey contains "[", the first "]" of a final "]]]" is treated as part of the sortkey. if find(sortkey, "[", 1, true) and sub(content, nxt, nxt) == "]" then sortkey = sortkey .. "]" end end local code = match(cat, "^([%w%-.]+):") if code then add_cat_table(wikitext_topic_cat, code, sortkey) return end -- Split by word. cat = split(cat, " ", true, true) -- Formerly we looked for the language name anywhere in the category. This is simply wrong -- because there are no categories like 'Alsatian French lemmas' (only L2 languages -- have langname categories), but doing it this way wrongly catches things like [[Category:Shapsug Adyghe]] -- in [[Category:Adyghe entries with language name categories using raw markup]]. local n = #cat - 1 if n <= 0 then return end -- Go from longest to shortest and stop once we've found a language name. Going from shortest -- to longest or not stopping after a match risks falsely matching (e.g.) German Low German -- categories as German. repeat local name = concat(cat, " ", 1, n) if (langnames or get_langnames())[name] then add_cat_table(wikitext_langname_cat, name, sortkey) return end n = n - 1 until n == 0 end if content then -- Remove comments, then iterate over category links. content = remove_comments(content, "BOTH") local head = find(content, "[[", 1, true) while head do local close = find(content, "]]", head + 2, true) if not close then break end -- Make sure there are no intervening "[[" between head and close. local open = find(content, "[[", head + 2, true) while open and open < close do head = open open = find(content, "[[", head + 2, true) end local cat = sub(content, head + 2, close - 1) -- Locate the colon, and weed out most unwanted links. "[ _\128-\244]*" catches valid whitespace, and ensures any category links using the colon trick are ignored. We match all non-ASCII characters, as there could be multibyte spaces, and mw.title.new will filter out any remaining false-positives; this is a lot faster than running mw.title.new on every link. local colon = match(cat, "^[ _\128-\244]*[Cc][Aa][Tt][EeGgOoRrYy _\128-\244]*():") if colon then process_category(content, cat, colon, close + 2) end head = open end end data.wikitext_topic_cat = wikitext_topic_cat data.wikitext_langname_cat = wikitext_langname_cat if raw_sortkey then insert(cats, get_category("Pages with raw sortkeys")) end end return data end return export 7cubvdhwb3risefslzp6kxwcrr21b48 828 7987 54919 54733 2026-09-29T00:01:29Z Deadend0914 7211 54919 Scribunto text/plain local export = {} export.force_cat = false -- for testing; set to true to display categories even on non-mainspace pages local debug_track_module = "Module:debug/track" local etymology_module = "Module:etymology" local form_of_cats_module = "Module:form of/cats" local form_of_data_module = "Module:form of/data" local form_of_data1_module = "Module:form of/data/1" local form_of_data2_module = "Module:form of/data/2" local form_of_functions_module = "Module:form of/functions" local form_of_lang_data_module_prefix = "Module:form of/lang-data/" local function_module = "Module:fun" local headword_data_module = "Module:headword/data" local json_module = "Module:JSON" local labels_module = "Module:labels" local links_module = "Module:links" local load_module = "Module:load" local parse_utilities_module = "Module:parse utilities" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local table_deep_equals_module = "Module:table/deepEquals" local utilities_module = "Module:utilities" local anchor_encode = mw.uri.anchorEncode local concat = table.concat local dump = mw.dumpObject local fetch_categories_and_labels -- Defined below. local format_form_of -- Defined below. local get_tag_display_form -- Defined below. local get_tag_set_display_form -- Defined below. local insert = table.insert local ipairs = ipairs local is_link_or_html -- Defined below. local list_to_text = mw.text.listToText local lookup_shortcut -- Defined below. local lookup_tag -- Defined below. local normalize_tag_set -- Defined below. local parse_tag_set_properties -- Defined below. local require = require local sort = table.sort local split_tag_set -- Defined below. local type = type --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function append(...) append = require(table_module).append return append(...) end local function contains(...) contains = require(table_module).contains return contains(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function deep_equals(...) deep_equals = require(table_deep_equals_module) return deep_equals(...) end local function extend(...) extend = require(table_module).extend return extend(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function full_link(...) full_link = require(links_module).full_link return full_link(...) end local function insert_if_not(...) insert_if_not = require(table_module).insertIfNot return insert_if_not(...) end local function is_subset_list(...) is_subset_list = require(table_module).isSubsetList return is_subset_list(...) end local function iterate_from(...) iterate_from = require(function_module).iterateFrom return iterate_from(...) end local function join_multiparts(...) join_multiparts = require(form_of_functions_module).join_multiparts return join_multiparts(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function parse_inline_modifiers(...) parse_inline_modifiers = require(parse_utilities_module).parse_inline_modifiers return parse_inline_modifiers(...) end local function remove_links(...) remove_links = require(links_module).remove_links return remove_links(...) end local function safe_load_data(...) safe_load_data = require(load_module).safe_load_data return safe_load_data(...) end local function safe_require(...) safe_require = require(load_module).safe_require return safe_require(...) end local function serial_comma_join(...) serial_comma_join = require(table_module).serialCommaJoin return serial_comma_join(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function show_labels(...) show_labels = require(labels_module).show_labels return show_labels(...) end local function slice(...) slice = require(table_module).slice return slice(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function ucfirst(...) ucfirst = require(string_utilities_module).ucfirst return ucfirst(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local cat_functions local function get_cat_functions() cat_functions, get_cat_functions = require(form_of_functions_module).cat_functions, nil return cat_functions end local default_pagename local function get_default_pagename() default_pagename, get_default_pagename = load_data(headword_data_module).pagename, nil return default_pagename end local display_handlers local function get_display_handlers() display_handlers, get_display_handlers = require(form_of_functions_module).display_handlers, nil return display_handlers end local m_cats_data local function get_m_cats_data() m_cats_data, get_m_cats_data = load_data(form_of_cats_module), nil return m_cats_data end local m_data local function get_m_data() -- Needs require. m_data, get_m_data = require(form_of_data_module), nil return m_data end local m_data1 local function get_m_data1() m_data1, get_m_data1 = load_data(form_of_data1_module), nil return m_data1 end local m_data2 local function get_m_data2() m_data2, get_m_data2 = load_data(form_of_data2_module), nil return m_data2 end local m_pos_data local function get_m_pos_data() m_pos_data, get_m_pos_data = load_data(headword_data_module).pos_aliases, nil return m_pos_data end --[==[ intro: This module implements the underlying processing of {{tl|form of}}, {{tl|inflection of}} and specific variants such as {{tl|past participle of}} and {{tl|alternative spelling of}}. Most of the logic in this file is to handle tags in {{tl|inflection of}}. Other related files: * [[Module:form of/templates]] contains the majority of the logic that implements the templates themselves. * [[Module:form of/data/1]] is a data-only file containing information on the more common inflection tags, listing the tags, their shortcuts, the category they belong to (tense-aspect, case, gender, voice-valence, etc.), the appropriate glossary link and the wikidata ID. * [[Module:form of/data/2]] is a data-only file containing information on the less common inflection tags, in the same format as [[Module:form of/data/1]]. * [[Module:form of/lang-data/LANGCODE]] is a data-only file containing information on the language-specific inflection tags for the language with code LANGCODE, in the same format as [[Module:form of/data/1]]. Language-specific tags override general tags. * [[Module:form of/cats]] is a data-only file listing the language-specific categories that are added when the appropriate combinations of tags are seen for a given language. * [[Module:form of/functions]] contains functions for use with [[Module:form of/data/1]] and [[Module:form of/cats]]. They are contained in this module because data-only modules can't contain code. The functions in this file are of two types: *# Display handlers allow for customization of the display of multipart tags (see below). Currently there is only one such handler, for handling multipart person tags such as `1//2//3`. *# Cat functions allow for more complex categorization logic, and are referred to by name in [[Module:form of/cats]]. Currently no such functions exist. The following terminology is used in conjunction with {{tl|inflection of}}: * A ''tag'' is a single grammatical item, as specified in a single numbered parameter of {{tl|inflection of}}. Examples are `masculine`, `nominative`, or `first-person`. Tags may be abbreviated, e.g. `m` for `masculine`, `nom` for `nominative`, or `1` for `first-person`. Such abbreviations are called ''aliases'', and some tags have multiple equivalent aliases (e.g. `p` or `pl` for `plural`). The full, non-abbreviated form of a tag is called its ''canonical form''. * The ''display form'' of a tag is the way it's displayed to the user. Usually the displayed text of the tag is the same as its canonical form, and it normally functions as a link to a glossary entry explaining the tag. Usually the link is to an entry in [[Appendix:Glossary]], but sometimes the tag is linked to an individual dictionary entry or to a Wikipedia entry. Occasionally, the display text differs from the canonical form of the tag. An example is the tag `comparative case`, which has the display text read as simply `comparative`. Normally, tags referring to cases don't have the word "case" in them, but in this case the tag `comparative` was already used as an alias for the tag `comparative degree`, so the tag was named `comparative case` to avoid clashing. A similar situation occurs with `adverbial case` vs. the grammar tag `adverbial` (as in `adverbial participle`). * A ''tag set'' is an ordered list of tags, which together express a single inflection, for example, `1|s|pres|ind`, which can be expanded to canonical-form tags as `first-person|singular|present|indicative`. * A ''conjoined tag set'' is a tag set that consists of multiple individual tag sets separated by a semicolon, e.g. `1|s|pres|ind|;|2|s|imp`, which specifies two tag sets, `1|s|pres|ind` as above and `2|s|imp` (in canonical form, `second-person|singular|imperative`). Multiple tag sets specified in a single call to {{tl|inflection of}} are specified in this fashion. Conjoined tag sets can also occur in list-tag shortcuts. * A ''multipart tag'' is a tag that embeds multiple tags within it, such as `f//n` or `nom//acc//voc`. These are used in the case of [[syncretism]], when the same form applies to multiple inflections. Examples are the Spanish present subjunctive, where the first-person and third-person singular have the same form (e.g. {{m|es|siga}} from {{m|es|seguir|t=to follow}}), or Latin third-declension adjectives, where the dative and ablative plural of all genders have the same form (e.g. {{m|la|omnibus}} from {{m|la|omnis|t=all}}). These would be expressed respectively as `1//3|s|pres|sub` and `dat//abl|m//f//n|p`, where the use of the multipart tag compactly encodes the syncretism and avoids the need to individually list out all of the inflections. Multipart tags currently display as a list separated by a slash, e.g. ''dative/ablative'' or ''masculine/feminine/neuter'' where each individual word is linked appropriately. As a special case, multipart tags involving persons display specially; for example, the multipart tag `1//2//3` displays as ''first-, second- and third-person'', with the word "person" occurring only once. * A ''two-level multipart tag'' is a special type of multipart tag that joins two or more tag sets instead of joining individual tags. The tags within the tag set are joined by a colon, e.g. `1:s//3:p`, which is displayed as ''first-person singular and third-person plural'', e.g. for use with the form {{m|grc|μέλλον}} of the verb {{m|grc|μέλλω|t=to intend}}, which uses the tag set `1:s//3:p|impf|actv|indc|unaugmented` to express the syncretism between the first singular and third plural forms of the imperfect active indicative unaugmented conjugation. Two-level multipart tags should be used sparingly; if in doubt, list out the inflections separately. [FIXME: Make two-level multipart tags obsolete.] * A ''shortcut'' is a tag that expands to any type of tag described above, or to any type of tag set described above. Aliases are a particular type of shortcut whose expansion is a single non-multipart tag. * A ''multipart shortcut'' is a shortcut that expands into a multipart tag, for example `123`, which expands to the multipart tag `1//2//3`. Only the most common such combinations exist as shortcuts. * A ''list shortcut'' is a special type of shortcut that expands to a list of tags instead of a single tag. For example, the shortcut `1s` expands to `1|s` (first-person singular). Only the most common such combinations exist as shortcuts. * A ''conjoined shortcut'' is a special type of list shortcut that consists of a conjoined tag set (multiple logical tag sets). For example, the English language-specific shortcut `ed-form` expands to `spast|;|past|part`, expressing the common syncretism between simple past and past participle in English (and in this case, `spast` is itself a list shortcut that expands to `simple|past`).]==] -- Add tracking category for PAGE when called from {{inflection of}} or -- similar TEMPLATE. The tracking category linked to is -- [[Wiktionary:Tracking/inflection of/PAGE]]. local function track(page) debug_track("inflection of/" .. -- avoid including links in pages (may cause error) page:gsub("%[", "("):gsub("%]", ")"):gsub("|", "!") ) end local function wrap_in_span(text, classes) if classes then return ("<span class='%s'>%s</span>"):format(classes, text) else return text end end local function show_linked_term(data) local termobj, face, span_classes, ok_to_destructively_modify, overall_lang, text_classes = data.termobj, data.face, data.span_classes, data.ok_to_destructively_modify, data.overall_lang, data.text_classes local need_to_copy, pretext_lang local categories = {} if overall_lang and overall_lang:getCode() ~= termobj.lang:getCode() then local lang_display lang_display, categories = require(etymology_module).insert_source_cat_get_display { lang = data.overall_lang, source = termobj.lang, } pretext_lang = wrap_in_span(lang_display .. " ", text_classes) end local has_decoration = termobj.q or termobj.qq or termobj.a or termobj.aa or termobj.l or termobj.ll or termobj.refs -- `show_decorations` is set by parse_{term,list}_with_inline_modifiers_and_separate_params in -- [[Module:parameter utilities]], called in [[Module:form of/templates]], so in most circumstances -- it's already set and we don't need to do a shallow-copy to set it. local need_to_set_show_decorations = has_decoration and not termobj.show_decorations need_to_copy = not ok_to_destructively_modify and (pretext_lang or need_to_set_show_decorations) if need_to_copy then termobj = shallow_copy(termobj) end if pretext_lang then termobj.pretext = pretext_lang end if need_to_set_show_decorations then termobj.show_decorations = true end return wrap_in_span(full_link(termobj, face), span_classes), categories end --[==[ Lowest-level implementation of form-of templates, including the general {{tl|form of}} as well as those that deal with inflection tags, such as the general {{tl|inflection of}}, semi-specific variants such as {{tl|participle of}}, and specific variants such as {{tl|past participle of}}. `data` contains all the information controlling the display, with the following fields: * `.lang`: Overall language of the form-of template. If specified, any lemmas, enclitics or base lemmas that are of a different language will have that language displayed before the term in question. * `.text`: Text to insert before the lemmas. Wrapped in the value of `.text_classes`, or its default; see below. * `.lemmas`: List of objects describing the lemma(s) of which the term in question is a non-lemma form. These are passed directly to {full_link()} in [[Module:links]]. Each object should have at minimum a `.lang` field containing the language of the lemma and a `.term` field containing the lemma itself. Each object is formatted using {full_link()} and then if there are more than one, they are joined using {serialCommaJoin()} in [[Module:table]]. Alternatively, `.lemmas` can be a string, which is displayed directly, or omitted, to show no lemma links and omit the connecting text. * `.lemma_face`: "Face" to use when displaying the lemma objects. Usually should be set to {"term"}. * `.conj`: Conjunction or separator to use when joining multiple lemma objects. If {nil}, defaults to {"and"}. If this has the value {false}, the lemmas are preceded with the `.separator` field in each lemma. * `.enclitics`: List of enclitics to display after the lemmas, in parens. * `.enclitic_conj`: Conjunction or separator to use when joining multiple enclitics. Defaults to {"and"}. * `.base_lemmas`: List of base lemmas to display after the lemmas, in the case where the lemmas in `.lemmas` are themselves forms of another lemma (the base lemma), e.g. a comparative, superlative or participle. Each object is of the form { { paramobj = PARAM_OBJ, lemmas = {LEMMA_OBJ, LEMMA_OBJ, ...}, conj = "CONJ" }} where PARAM_OBJ describes the properties of the base lemma parameter (i.e. the relationship between the intermediate and base lemmas); LEMMA_OBJ is an object suitable to be passed to {full_link()} in [[Module:links]]; and CONJ is the conjunction to join multiple lemmas with, defaulting to {"and"}. PARAM_OBJ is of the format { { param = "PARAM", tags = {"TAG", "TAG", ...} } where PARAM is the name of the parameter to {{tl|inflection of}} etc. that holds the base lemma(s) of the specified relationship and the tags describe the relationship, such as { {"comd"}} or { {"past", "part"}}. * `.text_classes`: CSS classes used to wrap the tag text and lemma links. Default is {"form-of-definition use-with-mention"}. Use `false` for no wrapping. * `.lemma_classes`: Additional CSS classes used to wrap the lemma links. Default is {"form-of-definition-link"}. Use `false` for no wrapping. * `.posttext`: Additional text to display after the lemma links. * `.ok_to_destructively_modify`: If set, data structures (including the nested lemma structures) can be modified in-place to save memory; otherwise they will be copied before modifying. Returns two values, the formatted string and any categories to add the page to (which will arise if `.lang` is specified and a language other than `.lang` is given in one of the lemmas in `.lemmas` or enclitics in `.enclitics`). ]==] function export.format_form_of(data) if type(data) ~= "table" then error("Internal error: First argument must now be a table of arguments") end local text_classes = data.text_classes if text_classes == nil and not data.nowrap then text_classes = "form-of-definition use-with-mention" end local lemma_classes = data.lemma_classes if lemma_classes == nil then lemma_classes = "form-of-definition-link" end local parts = {} if text_classes then insert(parts, "<span class='" .. text_classes .. "'>") end insert(parts, data.text) if data.text ~= "" and data.lemmas then insert(parts, " ") end local categories = {} if data.lemmas then if type(data.lemmas) == "string" then insert(parts, wrap_in_span(data.lemmas, lemma_classes)) else local formatted_terms = {} for _, lemma in ipairs(data.lemmas) do local linked_term, this_categories = show_linked_term { termobj = lemma, face = data.lemma_face, span_classes = lemma_classes, ok_to_destructively_modify = data.ok_to_destructively_modify, overall_lang = data.lang, text_classes = text_classes } if this_categories[1] then extend(categories, this_categories) end if data.conj == false and lemma.separator then insert(formatted_terms, lemma.separator) end insert(formatted_terms, linked_term) end if data.conj == false then insert(parts, concat(formatted_terms)) else insert(parts, serial_comma_join(formatted_terms, {conj = data.conj or "and"})) end end if data.lit then insert(parts, ", literally " .. require(links_module).mark(data.lit, "gloss")) end end if data.enclitics and #data.enclitics > 0 then -- The outer parens need to be outside of the text_classes span so they show in upright instead of italic, or -- they will clash with upright parens generated by link annotations such as transliterations and pos=. if text_classes then insert(parts, "</span>") end local formatted_terms = {} for _, enclitic in ipairs(data.enclitics) do -- FIXME, should we have separate clitic face and/or classes? local linked_term, this_categories = show_linked_term { termobj = enclitic, face = data.lemma_face, span_classes = lemma_classes, ok_to_destructively_modify = data.ok_to_destructively_modify, overall_lang = data.lang, text_classes = text_classes } if this_categories[1] then extend(categories, this_categories) end insert(formatted_terms, linked_term) end insert(parts, " (") insert(parts, wrap_in_span("with enclitic" .. (#data.enclitics > 1 and "s" or "") .. " ", text_classes)) insert(parts, serial_comma_join(formatted_terms, {conj = data.enclitic_conj or "and"})) insert(parts, ")") if text_classes then insert(parts, "<span class='" .. text_classes .. "'>") end end if data.base_lemmas and #data.base_lemmas > 0 then for _, base_lemma in ipairs(data.base_lemmas) do insert(parts, ", the ") if text_classes then insert(parts, "</span>") end insert(parts, (export.tagged_inflections { lang = data.lang or base_lemma.lemmas[1].lang, tags = base_lemma.paramobj.tags, lemmas = base_lemma.lemmas, conj = base_lemma.conj or "and", lemma_face = data.lemma_face, no_format_categories = true, nocat = true, text_classes = data.text_classes, ok_to_destructively_modify = data.ok_to_destructively_modify, })) if text_classes then insert(parts, "<span class='" .. text_classes .. "'>") end end end -- FIXME, should posttext go before enclitics? If so we need to have separate handling for the -- final colon when there are multiple tag sets in tagged_inflections(). if data.posttext then insert(parts, data.posttext) end if text_classes then insert(parts, "</span>") end return concat(parts), categories end format_form_of = export.format_form_of --[==[ Return true if `tag` contains an internal link or HTML.]==] function export.is_link_or_html(tag) return tag:find("[[", nil, true) or tag:find("|", nil, true) or tag:find("<", nil, true) end is_link_or_html = export.is_link_or_html --[==[ Look up a tag (either a shortcut of any sort of a canonical long-form tag) and return its expansion. The expansion will be a string unless the shortcut is a list-tag shortcut such as `1s`; in that case, the expansion will be a list. The caller must handle both cases. Only one level of expansion happens; hence, `acc` expands to {"accusative"}, `1s` expands to { {"1", "s"}} (not to { {"first", "singular"}}) and `123` expands to {"1//2//3"}. The expansion will be the same as the passed-in tag in the following circumstances: # The tag is `;` (this is special-cased, and no lookup is done). # The tag is a multipart tag such as `nom//acc` (this is special-cased, and no lookup is done). # The tag contains a raw link (this is special-cased, and no lookup is done). # The tag contains HTML (this is special-cased, and no lookup is done). # The tag is already a canonical long-form tag. # The tag is unrecognized. This function first looks up in the lang-specific data module [[Module:form of/lang-data/LANGCODE]], then in [[Module:form of/data/1]] (which includes more common non-lang-specific tags) and finally (only if the tag is not recognized as a shortcut or canonical tag, and is not of types 1-4 above) in [[Module:form of/data/2]]. If the expansion is a string and is different from the tag, track it if `do_track` is true.]==] function export.lookup_shortcut(tag, lang, do_track) -- If there is HTML or a link in the tag, return it directly; don't try -- to look it up, which will fail. if tag == ";" or tag:find("//", nil, true) or is_link_or_html(tag) then return tag end local expansion while lang do local langdata = safe_load_data(form_of_lang_data_module_prefix .. lang:getCode()) -- If this is a canonical long-form tag, just return it, and don't check for shortcuts. This is an -- optimization; see below. if langdata then if langdata.tags[tag] then return tag end expansion = langdata.shortcuts[tag] if expansion then break end end -- If the language has a parent (i.e. a superordinate variety), try again with that. lang = lang:getParent() end if not expansion then -- If this is a canonical long-form tag, just return it, and don't check for shortcuts (which will cause -- [[Module:form of/data/2]] to be loaded, because there won't be a shortcut entry in [[Module:form of/data/1]] -- -- or, for that matter, in [[Module:form of/data/2]]). This is an optimization; the code will still work without -- it, but will use up more memory. if (m_data1 or get_m_data1()).tags[tag] then return tag end expansion = m_data1.shortcuts[tag] end if not expansion then expansion = (m_data2 or get_m_data2()).shortcuts[tag] end if not expansion then return tag end -- Maybe track the expansion if it's not the same as the raw tag. if do_track and expansion ~= tag and type(expansion) == "string" then track("tag/" .. tag) end return expansion end lookup_shortcut = export.lookup_shortcut --[==[ Look up a normalized/canonicalized tag and return the data object associated with it. If the tag isn't found, return nil. This first looks up in the lang-specific data module [[Module:form of/lang-data/LANGCODE]], then in [[Module:form of/data/1]] (which includes more common non-lang-specific tags) and then finally in [[Module:form of/data/2]].]==] function export.lookup_tag(tag, lang) while lang do local langdata = safe_load_data(form_of_lang_data_module_prefix .. lang:getCode()) local tag = langdata and langdata.tags[tag] if tag then return tag end -- If the language has a parent (i.e. a superordinate variety), try again with that. lang = lang:getParent() end local tagobj = (m_data1 or get_m_data1()).tags[tag] if tagobj then return tagobj end local tagobj2 = (m_data2 or get_m_data2()).tags[tag] if tagobj2 then return tagobj2 end return nil end lookup_tag = export.lookup_tag -- Normalize a single tag, which may be a shortcut but should not be a multipart tag, a multipart shortcut or a list -- shortcut. local function normalize_single_tag(tag, lang, do_track) local expansion = lookup_shortcut(tag, lang, do_track) if type(expansion) ~= "string" then error("Tag '" .. tag .. "' is a list shortcut, which is not allowed here") end tag = expansion if not lookup_tag(tag, lang) and do_track then -- If after all expansions and normalizations we don't recognize the canonical tag, track it. track("unknown") track("unknown/" .. tag) end return tag end --[=[ Normalize a component of a multipart tag. This should not have any // in it, but may join multiple individual tags with a colon, and may be a single list-tag shortcut, which is treated as if colon-separated. The return value may be a list of tags. ]=] local function normalize_multipart_component(tag, lang, do_track) -- If there is HTML or a link in the tag, don't try to split on colon. A colon may legitimately occur in either one, -- and we don't want these things parsed. Note that we don't do this check before splitting on //, which we don't -- expect to occur in links or HTML; see comment in normalize_tag(). if is_link_or_html(tag) then return tag end local components = split(tag, ":", true) if #components == 1 then -- We allow list-tag shortcuts inside of multipart tags, e.g. -- '1s//3p'. Check for this now. tag = lookup_shortcut(tag, lang, do_track) if type(tag) == "table" then -- Temporary tracking as we will disallow this. track("list-tag-inside-of-multipart") -- We found a list-tag shortcut; treat as if colon-separated. components = tag else return normalize_single_tag(tag, lang, do_track) end end local normtags = {} -- Temporary tracking as we will disallow this. track("two-level-multipart") for _, component in ipairs(components) do if do_track then -- There are multiple components; track each of the individual -- raw tags. track("tag/" .. component) end insert(normtags, normalize_single_tag(component, lang, do_track)) end return normtags end --[=[ Normalize a single tag. The return value may be a list (in the case of multipart tags), which will contain nested lists in the case of two-level multipart tags. ]=] local function normalize_tag(tag, lang, do_track) -- We don't check for links or HTML before splitting on //, which we don't expect to occur in links or HTML. Doing -- it this way allows for a tag like '{{lb|grc|Epic}}//{{lb|grc|Ionic}}' to function correctly (the template calls -- will be expanded before we process the tag, and will contain links and HTML). The only check we do is for a URL, -- which shouldn't normally occur, but might if the user tries to put an external link into the tag. URL's with // -- normally have the sequence ://, which should never normally occur when // and : are used in their normal ways. if tag:find("://", nil, true) then return tag end local split_tags = split(tag, "//", true) if #split_tags == 1 then local retval = normalize_multipart_component(tag, lang, do_track) if type(retval) == "table" then -- The user gave a tag like '1:s', i.e. with colon but without //. Allow this, but we need to return a -- nested list. return {retval} end return retval end local normtags = {} for _, single_tag in ipairs(split_tags) do if do_track then -- If the tag was a multipart tag, track each of individual raw tags. track("tag/" .. single_tag) end insert(normtags, normalize_multipart_component(single_tag, lang, do_track)) end return normtags end --[==[ Normalize a tag set (a list of tags) into its canonical-form tags. The return value is a list of normalized tag sets (a list because of there may be conjoined shortcuts among the input tags). A normalized tag set is a list of tag elements, where each element is either a string (the canonical form of a tag), a list of such strings (in the case of multipart tags) or a list of lists of such strings (in the case of two-level multipart tags). For example, the multipart tag `nom//acc//voc` will be represented in canonical form as { {"nominative", "accusative", "vocative"}}, and the two-level multipart tag `1:s//3:p` will be represented as { {{"first-person", "singular"}, {"third-person", "plural"}}}. Example 1: {normalize_tag_set({"nom//acc//voc", "n", "p"})} = { {{{"nominative", "accusative", "vocative"}, "masculine", "plural"}}} Example 2: {normalize_tag_set({"ed-form"}, ENGLISH)} = { {{"simple", "past"}, {"past", "participle"}}} Example 3: {normalize_tag_set({"archaic", "ed-form"}, ENGLISH)} = { {{"archaic", "simple", "past"}, {"archaic", "past", "participle"}}}]==] function export.normalize_tag_set(tag_set, lang, do_track) -- We track usage of shortcuts, normalized forms and (in the case of multipart tags or list tags) intermediate -- forms. For example, if the tags 1s|mn|gen|indefinite are passed in, we track the following: -- [[Wiktionary:Tracking/inflection of/tag/1s]] -- [[Wiktionary:Tracking/inflection of/tag/1]] -- [[Wiktionary:Tracking/inflection of/tag/s]] -- [[Wiktionary:Tracking/inflection of/tag/first-person]] -- [[Wiktionary:Tracking/inflection of/tag/singular]] -- [[Wiktionary:Tracking/inflection of/tag/mn]] -- [[Wiktionary:Tracking/inflection of/tag/m//n]] -- [[Wiktionary:Tracking/inflection of/tag/m]] -- [[Wiktionary:Tracking/inflection of/tag/n]] -- [[Wiktionary:Tracking/inflection of/tag/masculine]] -- [[Wiktionary:Tracking/inflection of/tag/neuter]] -- [[Wiktionary:Tracking/inflection of/tag/gen]] -- [[Wiktionary:Tracking/inflection of/tag/genitive]] -- [[Wiktionary:Tracking/inflection of/tag/indefinite]] local output_tag_set = {} local saw_semicolon = false for _, tag in ipairs(tag_set) do if do_track then -- Track the raw tag. track("tag/" .. tag) end -- Expand the tag, which may generate a new tag (either a fully canonicalized tag, a multipart tag, or a list -- of tags). tag = lookup_shortcut(tag, lang, do_track) if type(tag) == "table" then if contains(tag, ";") then -- If we saw a conjoined shortcut, we need to use a more general algorithm that can expand a single -- tag set into multiple. saw_semicolon = true break end for _, t in ipairs(tag) do if do_track then -- If the tag expands to a list of raw tags, track each of those. track("tag/" .. t) end insert(output_tag_set, normalize_tag(t, lang, do_track)) end else insert(output_tag_set, normalize_tag(tag, lang, do_track)) end end if not saw_semicolon then return {output_tag_set} end -- Use a more general algorithm that handles conjoined shortcuts. output_tag_set = {} for i, tag in ipairs(tag_set) do if do_track then -- Track the raw tag. track("tag/" .. tag) end -- Expand the tag, which may generate a new tag (either a fully canonicalized tag, a multipart tag, or a list -- of tags). tag = lookup_shortcut(tag, lang, do_track) if type(tag) == "table" then local output_tag_sets = {} local shortcut_tag_sets = split_tag_set(tag) local normalized_shortcut_tag_sets = {} for _, shortcut_tag_set in ipairs(shortcut_tag_sets) do extend(normalized_shortcut_tag_sets, normalize_tag_set(shortcut_tag_set, lang, do_track)) end local after_tags = slice(tag_set, i + 1) local normalized_after_tags_sets = normalize_tag_set(after_tags, lang, do_track) for _, normalized_shortcut_tag_set in ipairs(normalized_shortcut_tag_sets) do for _, normalized_after_tags_set in ipairs(normalized_after_tags_sets) do insert(output_tag_sets, append(output_tag_set, normalized_shortcut_tag_set, normalized_after_tags_set)) end end return output_tag_sets else insert(output_tag_set, normalize_tag(tag, lang, do_track)) end end error("Internal error: Should not get here") end normalize_tag_set = export.normalize_tag_set --[==[ Split a tag set that may consist of multiple semicolon-separated tag sets into the component tag sets.]==] function export.split_tag_set(tag_set) local split_tag_sets = {} local cur_tag_set = {} for _, tag in ipairs(tag_set) do if tag == ";" then if #cur_tag_set > 0 then insert(split_tag_sets, cur_tag_set) end cur_tag_set = {} else insert(cur_tag_set, tag) end end if #cur_tag_set > 0 then insert(split_tag_sets, cur_tag_set) end return split_tag_sets end split_tag_set = export.split_tag_set local tag_set_param_mods = { lb = { item_dest = "labels", convert = function(arg, _parse_err) return split(arg, "//", true) end, } } --[==[ Parse tag set properties from a tag set (list of tags). Currently no per-tag properties are recognized, and the only per-tag-set property recognized is `<lb:...>` for specifing label(s) for the tag set. Per-tag-set properties must be attached to the last tag.]==] function export.parse_tag_set_properties(tag_set) local function generate_tag_set_obj(last_tag) tag_set[#tag_set] = last_tag return {tags = tag_set} end local last_tag = tag_set[#tag_set] -- Check for inline modifier, e.g. מרים<tr:Miryem>. But exclude HTML entry with <span ...>, <i ...>, <br/> or -- similar in it, caused by wrapping an argument in {{l|...}}, {{af|...}} or similar. Basically, all tags of -- the sort we parse here should consist of a less-than sign, plus letters, plus a colon, e.g. <lb:...>, so if -- we see a tag on the outer level that isn't in this format, we don't try to parse it. The restriction to the -- outer level is to allow generated HTML inside of e.g. qualifier tags, such as foo<q:similar to {{m|fr|bar}}>. if last_tag:find("<", nil, true) and not last_tag:find("^[^<]*<%l*[^%l:]") then return parse_inline_modifiers(last_tag, { param_mods = tag_set_param_mods, generate_obj = generate_tag_set_obj, }) else return generate_tag_set_obj(last_tag) end end parse_tag_set_properties = export.parse_tag_set_properties local function normalize_pos(pos) if not pos then return nil end return (m_pos_data or get_m_pos_data())[pos] or pos end -- Return the display form of a single canonical-form tag. The value -- passed in must be a string (i.e. it cannot be a list describing a -- multipart tag). To handle multipart tags, use get_tag_display_form(). -- A truthy `nolink` suppresses linking. local function get_single_tag_display_form(normtag, lang, nolink) local data = lookup_tag(normtag, lang) local display = normtag -- If the tag has a special display form, use it if data and data.display then display = data.display if nolink then display = remove_links(display) end end -- If there is a nonempty glossary index, then show a link to it if not nolink then local glossary = data and data[(m_data or get_m_data()).GLOSSARY] if glossary ~= nil then if glossary == m_data.WIKT then display = "[[" .. normtag .. "|" .. display .. "]]" elseif glossary == m_data.WP then display = "[[w:" .. normtag .. "|" .. display .. "]]" elseif glossary == m_data.APPENDIX then display = "[[Appendix:Glossary#" .. anchor_encode(normtag) .. "|" .. display .. "]]" elseif type(glossary) ~= "string" then error(("Internal error: Wrong type %s for glossary value %s for tag %s"):format( type(glossary), dump(glossary), normtag)) else local link = glossary:match("^wikt:(.*)") if link then display = "[[" .. link .. "|" .. display .. "]]" end if not link then link = glossary:match("^w:(.*)") if link then display = "[[w:" .. link .. "|" .. display .. "]]" end end if not link then display = "[[Appendix:Glossary#" .. anchor_encode(glossary) .. "|" .. display .. "]]" end end end end return display end --[==[ Turn a canonicalized tag spec (which describes a single, possibly multipart tag) into the displayed form. The tag spec may be a string (a canonical-form tag); a list of canonical-form tags (in the case of a simple multipart tag); or a list of mixed canonical-form tags and lists of such tags (in the case of a two-level multipart tag). `joiner` indicates how to join the parts of a multipart tag, and can be either {"and"} ("foo and bar", or "foo, bar and baz" for 3 or more), {"slash"} ("foo/bar"), {"en-dash"} ("foo–bar") or {nil}, which uses the global default found in {multipart_join_strategy()} in [[Module:form of/functions]]. (NOTE: The global default is {"slash"} and this seems unlikely to change.) A truthy `nolink` suppresses linking.]==] function export.get_tag_display_form(tagspec, lang, joiner, nolink) if type(tagspec) == "string" then return get_single_tag_display_form(tagspec, lang, nolink) end -- We have a multipart tag. See if there's a display handler to display them specially. for _, handler in ipairs(display_handlers or get_display_handlers()) do local displayval = handler(tagspec, joiner) if displayval then if nolink then displayval = remove_links(displayval) end return displayval end end -- No display handler. local displayed_tags = {} for _, first_level_tag in ipairs(tagspec) do if type(first_level_tag) == "string" then insert(displayed_tags, get_single_tag_display_form(first_level_tag, lang, nolink)) else -- A first-level element of a two-level multipart tag. Currently we just separate the individual components -- with spaces, but other ways are possible, e.g. using an underscore, colon, parens or braces. local components = {} for _, component in ipairs(first_level_tag) do insert(components, get_single_tag_display_form(component, lang, nolink)) end insert(displayed_tags, concat(components, " ")) end end return join_multiparts(displayed_tags, joiner) end get_tag_display_form = export.get_tag_display_form --[==[ Given a normalized tag set (i.e. as output by {normalize_tag_set()}; all tags are in canonical form, multipart tags are represented as lists, and two-level multipart tags as lists of lists), convert to displayed form (a string). See {get_tag_display_form()} for the meaning of `joiner`. A truthy `nolink` suppresses linking.]==] function export.get_tag_set_display_form(normalized_tag_set, lang, joiner, nolink) local parts = {} for _, tagspec in ipairs(normalized_tag_set) do local to_insert = get_tag_display_form(tagspec, lang, joiner, nolink) -- Maybe insert a space before inserting the display form of the tag. We insert a space if -- (a) we're not the first tag; and -- (b) the tag we're about to insert doesn't have the "no_space_on_left" property; and -- (c) the preceding tag doesn't have the "no_space_on_right" property. -- NOTE: We depend here on the fact that -- (1) all tags with either of the above properties set have the same display form as canonical form, and -- (2) all tags with either of the above properties set are single-character tags. -- The second property is an optimization to avoid looking up display forms resulting from multipart tags, -- which won't be found and which will trigger loading of [[Module:form of/data/2]]. If multichar punctuation is -- added in the future, it's ok to change the == 1 below to <= 2 or <= 3. -- -- If the first property above fails to hold in the future, we need to track the canonical form of each tag -- (including the previous one) as well as the display form. This would also avoid the need for the == 1 check. if #parts > 0 then local most_recent_tagobj = parts[#parts]:match("^.[\128-\191]*$") and lookup_tag(parts[#parts], lang) local to_insert_tagobj = to_insert:match("^.[\128-\191]*$") and lookup_tag(to_insert, lang) if ( (not most_recent_tagobj or not most_recent_tagobj.no_space_on_right) and (not to_insert_tagobj or not to_insert_tagobj.no_space_on_left) ) then insert(parts, " ") end end insert(parts, to_insert) end return concat(parts) end get_tag_set_display_form = export.get_tag_set_display_form --[==[ Split a tag set containing two-level multipart tags into one or more tag sets not containing such tags. Single-level multipart tags are left alone. (If we need to, a slight modification of the following code will also split single-level multipart tags.) This assumes that multipart tags are represented as lists and two-level multipart tags are represented as lists of lists, as is output by {normalize_tag_set()}. NOTE: We have to be careful to properly handle imbalanced two-level multipart tags such as `def:s//p` (or the reverse, `s//def:p`).]==] local function split_two_level_multipart_tag_set(tag_set) for i, tag in ipairs(tag_set) do if type(tag) == "table" then -- We saw a multipart tag. Check if any of the parts are two-level. local saw_two_level_tag = false for _, first_level_tag in ipairs(tag) do if type(first_level_tag) == "table" then saw_two_level_tag = true break end end if saw_two_level_tag then -- We found a two-level multipart tag. -- (1) Extract the preceding tags. local pre_tags = slice(tag_set, 1, i - 1) -- (2) Extract the following tags. local post_tags = slice(tag_set, i + 1) -- (3) Loop over each tag set alternant in the two-level multipart tag. -- For each alternant, form the tag set consisting of pre_tags + alternant + post_tags, -- and recursively split that tag set. local resulting_tag_sets = {} for _, first_level_tag_set in ipairs(tag) do local expanded_tag_set = {} extend(expanded_tag_set, pre_tags) -- The second level may have a string or a list. if type(first_level_tag_set) == "table" then extend(expanded_tag_set, first_level_tag_set) else insert(expanded_tag_set, first_level_tag_set) end extend(expanded_tag_set, post_tags) extend(resulting_tag_sets, split_two_level_multipart_tag_set(expanded_tag_set)) end return resulting_tag_sets end end end return {tag_set} end local function try_lang_specific_module(langcode, modules_tried, name, data) local lang_specific_module = form_of_lang_data_module_prefix .. langcode .. "/functions" local langdata = safe_require(lang_specific_module) if langdata then insert(modules_tried, lang_specific_module) if langdata.cat_functions then local fn = langdata.cat_functions[name] if fn then return fn(data), true end end end return nil, false end -- Call a named function, either from the lang-specific data in -- [[Module:form of/lang-specific/LANGCODE/functions]] or in [[Module:form of/functions]]. local function call_named_function(name, funtype, normalized_tag_set, lang, POS, pagename, lemmas) local data = { pagename = pagename or default_pagename or get_default_pagename(), lemmas = lemmas, tag_set = normalized_tag_set, lang = lang, POS = POS } local modules_tried = {} -- First try lang-specific. while lang do local retval, found_it = try_lang_specific_module(lang:getCode(), modules_tried, name, data) if found_it then return retval end -- If the language has a parent (i.e. a superordinate variety), try again with that. lang = lang:getParent() end -- Try lang-independent. insert(modules_tried, form_of_functions_module) local fn = (cat_functions or get_cat_functions())[name] if fn then return fn(data) end for i, modname in ipairs(modules_tried) do modules_tried[i] = "[[" .. modname .. "]]" end error(("No %s function named '%s' in %s"):format(funtype, name, list_to_text(modules_tried, nil, " or "))) end -- Given a tag from the current tag set (which may be a list in case of a multipart tag), -- and a tag from a categorization spec, check that the two match. -- (1) If both are strings, we just check for equality. -- (2) If the spec tag is a string and the tag set tag is a list (i.e. it originates from a -- multipart tag), we check that the spec tag is in the list. This is because we want to treat -- multipart tags in user-specified tag sets as if the user had specified multiple tag sets. -- For example, if the user said "1//3|s|pres|ind" and the categorization spec says {"has", "1"}, -- we want this to match, because "1//3|s|pres|ind" should be treated equivalently to two tag -- sets "1|s|pres|ind" and "3|s|pres|ind", and the former matches the categorization spec. -- (3) If the spec tag is a list (i.e. it originates from a multipart tag), we check that the -- tag set tag is also a list and is a superset of the spec tag. For example, if the categorization -- spec says {"has", "1//3"}, then the tag set tag must be a multipart tag that has both "1" and "3" -- in it. "1//3" works, as does "1//2//3". local function tag_set_tag_matches_spec_tag(tag_set_tag, spec_tag) if type(spec_tag) == "table" then if type(tag_set_tag) == "table" and is_subset_list(spec_tag, tag_set_tag) then return true end elseif type(tag_set_tag) == "table" then if contains(tag_set_tag, spec_tag) then return true end elseif tag_set_tag == spec_tag then return true end return false end -- Check that the current tag set matches the given spec tag. This means that any of the tags -- in the current tag set match, according to tag_set_tag_matches_spec_tag(); see above. If the -- current tag set contains only string tags (i.e. no multipart tags), and the spec tag is a -- string (i.e. not a multipart tag), this boils down to list containment, but it gets more -- complex when multipart tags are present. local function tag_set_matches_spec_tag(spec_tag, tag_set, lang) spec_tag = normalize_tag(spec_tag, lang) for _, tag_set_tag in ipairs(tag_set) do if tag_set_tag_matches_spec_tag(tag_set_tag, spec_tag) then return true end end return false end -- Check whether the given spec matches the current tag set. Two values are returned: -- (1) whether the spec matches the tag set; (2) the index of the category to add if -- the spec matches. local function check_condition(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas) if type(spec) == "boolean" then return spec elseif type(spec) ~= "table" then error("Wrong type of condition " .. spec .. ": " .. type(spec)) end local predicate = spec[1] if predicate == "has" then return tag_set_matches_spec_tag(spec[2], tag_set, lang), 3 elseif predicate == "hasall" then for _, tag in ipairs(spec[2]) do if not tag_set_matches_spec_tag(tag, tag_set, lang) then return false, 3 end end return true, 3 elseif predicate == "hasany" then for _, tag in ipairs(spec[2]) do if tag_set_matches_spec_tag(tag, tag_set, lang) then return true, 3 end end return false, 3 elseif predicate == "tags=" then local normalized_spec_tag_sets = normalize_tag_set(spec[2], lang) if #normalized_spec_tag_sets > 1 then error("Internal error: No support for conjoined shortcuts in category/label specs in " .. "[[Module:form of/cats]] when processing spec tag set " .. concat(spec[2], "|")) end local normalized_spec_tag_set = normalized_spec_tag_sets[1] -- Check for and disallow two-level multipart tags in the specs. FIXME: Remove this when we remove -- support for two-level multipart tags. for _, tag in ipairs(normalized_spec_tag_set) do if type(tag) == "table" then for _, subtag in ipairs(tag) do if type(subtag) == "table" then error("Internal error: No support for two-level multipart tags in category/label specs" .. "[[Module:form of/cats]] when processing spec tag set " .. concat(spec[2], "|")) end end end end -- Allow tags to be in different orders, and multipart tags to be in different orders. To handle this, -- we first check that both tag set tags and spec tags have the same length. If so, we sort the -- multipart tags in the tag set tags and spec tags, and then check that all tags in the spec tags are -- in the tag set tags. if #tag_set ~= #normalized_spec_tag_set then return false, 3 end local tag_set_tags = deep_copy(tag_set) for i=1,#tag_set_tags do if type(tag_set_tags[i]) == "table" then sort(tag_set_tags[i]) end if type(normalized_spec_tag_set[i]) == "table" then sort(normalized_spec_tag_set[i]) end end for i=1,#tag_set_tags do if not contains(tag_set_tags, normalized_spec_tag_set[i]) then return false, 3 end end return true, 3 elseif predicate == "p=" then return POS == normalize_pos(spec[2]), 3 elseif predicate == "pany" then for _, specpos in ipairs(spec[2]) do if POS == normalize_pos(specpos) then return true, 3 end end return false, 3 elseif predicate == "pexists" then return POS ~= nil, 2 elseif predicate == "not" then local condval = check_condition(spec[2], tag_set, normalized_tag_set, lang, POS, pagename, lemmas) return not condval, 3 elseif predicate == "and" then local condval = check_condition(spec[2], tag_set, normalized_tag_set, lang, POS, pagename, lemmas) if condval then condval = check_condition(spec[3], tag_set, normalized_tag_set, lang, POS, pagename, lemmas) end return condval, 4 elseif predicate == "or" then local condval = check_condition(spec[2], tag_set, normalized_tag_set, lang, POS, pagename, lemmas) if not condval then condval = check_condition(spec[3], tag_set, normalized_tag_set, lang, POS, pagename, lemmas) end return condval, 4 elseif predicate == "call" then return call_named_function(spec[2], "condition", normalized_tag_set, lang, POS, pagename, lemmas), 3 else error("Unrecognized predicate: " .. predicate) end end -- Process a given spec. This checks any conditions in the spec against the -- tag set, and insert any resulting categories into `categories`. Return value -- is true if the outermost condition evaluated to true and a category was inserted -- (this is used in {"cond" ...} conditions, which stop when a subcondition evaluates -- to true). -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end local function process_spec(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) if not spec then return false elseif type(spec) == "string" then -- A category. Substitute POS request with user-specified part of speech or default. spec = spec:gsub("<<p=(.-)>>", function(default) return POS or normalize_pos(default) end) insert(categories, lang:getFullName() .. " " .. cat_word(lang, spec)) return true elseif type(spec) == "table" and spec.labels then -- A label spec. for _, label in ipairs(spec.labels) do insert_if_not(labels, label) end return true elseif type(spec) ~= "table" then error("Wrong type of specification " .. spec .. ": " .. type(spec)) end local predicate = spec[1] if predicate == "multi" then for _, sp in iterate_from(2, ipairs(spec)) do -- Iterate from 2. process_spec(sp, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) end return true elseif predicate == "cond" then for _, sp in iterate_from(2, ipairs(spec)) do -- Iterate from 2. if process_spec(sp, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) then return true end end return false elseif predicate == "call" then return process_spec( call_named_function(spec[2], "spec", normalized_tag_set, lang, POS, pagename, lemmas), tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels ) else local condval, ifspec = check_condition(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas) if condval then process_spec(spec[ifspec], tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) return true else process_spec(spec[ifspec + 1], tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) -- FIXME: Are we sure this is correct? return false end end end --[==[ Given a normalized tag set (i.e. as output by {normalize_tag_set()}; all tags are in canonical form, multipart tags are represented as lists, and two-level multipart tags as lists of lists), fetch the associated categories and labels. Return two values, a list of categories and a list of labels. `lang` is the language of term represented by the tag set, and `POS` is the user-provided part of speech (which may be {nil}).]==] function export.fetch_categories_and_labels(normalized_tag_set, lang, POS, pagename, lemmas) local categories, labels = {}, {} POS = normalize_pos(POS) -- First split any two-level multipart tags into multiple sets, to make our life easier. for _, tag_set in ipairs(split_two_level_multipart_tag_set(normalized_tag_set)) do local langcode = lang:getCode() local langspecs = (m_cats_data or get_m_cats_data())[langcode] if langspecs then for _, spec in ipairs(langspecs) do process_spec(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) end end local full_code = lang:getFullCode() if full_code ~= langcode then local langspecs = (m_cats_data or get_m_cats_data())[full_code] if langspecs then for _, spec in ipairs(langspecs) do process_spec(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) end end end if full_code ~= "und" then local langspecs = (m_cats_data or get_m_cats_data())["und"] if langspecs then for _, spec in ipairs(langspecs) do process_spec(spec, tag_set, normalized_tag_set, lang, POS, pagename, lemmas, categories, labels) end end end end return categories, labels end fetch_categories_and_labels = export.fetch_categories_and_labels local function format_labels(labels, data, notext) if labels and #labels > 0 then return show_labels{ labels = labels, lang = data.lang, sort = data.sort, nocat = data.nocat } .. (notext and (data.pretext or "") == "" and "" or " ") else return "" end end --[==[ Implementation of templates that display inflection tags, such as the general {{tl|inflection of}}, semi-specific variants such as {{tl|participle of}}, and specific variants such as {{tl|past participle of}}. `data` contains all the information controlling the display, with the following fields: * `.lang`: ('''''required''''') Language to use when looking up language-specific inflection tags, categories and labels, and for displaying categories and labels. * `.tags`: ('''''required''' unless `.tag_sets` is given'') List of non-canonicalized inflection tags. Multiple tag sets can be indicated by a {";"} as one of the tags, and tag-set properties may be attached to the last tag of a tag set. The tags themselves may come directly from the user (as in {{tl|inflection of}}); come partly from the user (as in {{tl|participle of}}, which adds the tag `part` to user-specified inflection tags); or be entirely specified by the template (as in {{tl|past participle of}}). * `.tag_sets`: ('''''required''' unless `.tags` is given'') List of non-canonicalized tag sets and associated per-tag-set properties. Each element of the list is an object of the form { {tags = {"TAG", "TAG", ...}, labels = {"LABEL", "LABEL", ...}}. If `.tag_sets` is specified, `.tags` should not be given and vice-versa. Specifying `.tag_sets` in place of tags allowed per-tag set labels to be specified; otherwise, there is no advantage. [[Module:pt-gl-inflections]] uses this functionality to supply labels like {"Brazil"} and {"Portugal"} associated with specific tag sets. * `.lemmas`: ('''''recommended''''') List of objects describing the lemma(s) of which the term in question is a non-lemma form. These are passed directly to {full_link()} in [[Module:links]]. Each object should have at minimum a `.lang` field containing the language of the lemma and a `.term` field containing the lemma itself. Each object is formatted using {full_link()} and then if there are more than one, they are joined using {serialCommaJoin()} in [[Module:table]]. Alternatively, `.lemmas` can be a string, which is displayed directly. If omitted entirely, no lemma links are shown and the connecting "of" is also omitted. * `.lemma_face`: ('''''recommended''''') "Face" to use when displaying the lemma objects. Usually should be set to {"term"}. * `.POS`: ('''''recommended''''') Categorizing part-of-speech tag. Comes from the {{para|p}} or {{para|POS}} argument of {{tl|inflection of}}. * `.pagename`: Page name of "current" page or nil to use the actual page title; for testing purposes. * `.conj`: Conjunction or separator to use when joining multiple lemma objects. Defaults to {"and"}. * `.enclitics`: List of enclitics to display after the lemmas, in parens. * `.enclitic_conj`: Conjunction or separator to use when joining multiple enclitics. Defaults to {"and"}. * `.no_format_categories`: If true, don't format the categories derived from the inflection tags; just return them. * `.sort`: Sort key for formatted categories. Ignored when `.no_format_categories` = {true}. * `.nocat`: Suppress computation of categories (even if `.no_format_categories` is not given). * `.notext`: Disable display of all tag text and `inflection of` text. (FIXME: Maybe not implemented correctly.) * `.nolink`: Suppress linking of terms in inflection tags. * `.capfirst`: Capitalize the first word displayed. * `.pretext`: Additional text to display before the inflection tags, but after any top-level labels. * `.posttext`: Additional text to display after the lemma links. * `.text_classes`: CSS classes used to wrap the tag text and lemma links. Default is {"form-of-definition use-with-mention"}. * `.lemma_classes`: Additional CSS classes used to wrap the lemma links. Default is {"form-of-definition-link"}. * `.joiner`: Override the joiner (normally a slash) used to join multipart tags. You should normally not specify this. * `.nowrap`: Do not wrap the form-of definitions in a span, unless `.text_classes` is specified. * `.ok_to_destructively_modify`: If set, data structures (including the nested lemma structures) can be modified in-place to save memory; otherwise they will be copied before modifying. A typical call might look like this (for {{m+|es|amo}}): { local lang = require("Module:languages").getByCode("es") local lemma_obj = { lang = lang, term = "amar", } return m_form_of.tagged_inflections({ lang = lang, tags = {"1", "s", "pres", "ind"}, lemmas = {lemma_obj}, lemma_face = "term", POS = "verb" }) } Normally, one value is returned, the formatted text, which has appended to it the formatted categories derived from the tag-set-related categories generated by the specs in [Module:form of/cats]]. To suppress this, set `data.no_format_categories` = {true}, in which case two values are returned, the formatted text without any formatted categories appended and a list of the categories to be formatted. NOTE: There are two sets of categories that may be generated: (1) categories derived directly from the tag sets, as specified in [[Module:form of/cats]]; (2) categories derived from tag-set labels, either (a) set explicitly by the caller in `data.tag_sets`, (b) specified by the user using `<lb:...>` attached to the last tag in a tag set, or (c) specified in [[Module:form of/cats]]. The second type (label-related categories) are currently not returned in the second return value of {tagged_inflections()}, and are currently inserted into the output text even if `data.no_format_categories` is set to {true}; but they can be suppressed by setting `data.nocat` = {true} (which also suppresses the first type of categories, those derived directly from tag sets, even if `data.no_format_categories` is set to {true}).]==] function export.tagged_inflections(data) if not data.tags and not data.tag_sets then error("First argument must be a table of arguments, and `.tags` or `.tag_sets` must be specified") end if data.tags and data.tag_sets then error("Both `.tags` and `.tag_sets` cannot be specified") end local tag_sets = data.tag_sets if not tag_sets then tag_sets = split_tag_set(data.tags) for i, tag_set in ipairs(tag_sets) do tag_sets[i] = parse_tag_set_properties(tag_set) end end local inflections = {} local categories = {} for _, tag_set in ipairs(tag_sets) do local normalized_tag_sets = normalize_tag_set(tag_set.tags, data.lang, "do-track") for _, normalized_tag_set in ipairs(normalized_tag_sets) do local this_categories, this_labels = fetch_categories_and_labels(normalized_tag_set, data.lang, data.POS, data.pagename, type(data.lemmas) == "table" and data.lemmas or nil) if not data.nocat then extend(categories, this_categories) end local cur_infl = get_tag_set_display_form(normalized_tag_set, data.lang, data.joiner, data.nolink) if #cur_infl > 0 then if tag_set.labels then this_labels = append(tag_set.labels, this_labels) end insert(inflections, {infl_text = cur_infl, labels = this_labels}) end end end local overall_labels, need_per_tag_set_labels for _, inflection in ipairs(inflections) do if overall_labels == nil then overall_labels = inflection.labels elseif not deep_equals(overall_labels, inflection.labels) then need_per_tag_set_labels = true overall_labels = nil break end end if not need_per_tag_set_labels then for _, inflection in ipairs(inflections) do inflection.labels = nil end end local format_data = shallow_copy(data) local of_text = data.lemmas and " of" or "" local formatted_text, this_categories if #inflections == 1 then if need_per_tag_set_labels then error("Internal error: need_per_tag_set_labels should not be set with one inflection") end format_data.text = format_labels(overall_labels, data, data.notext) .. (data.pretext or "") .. (data.notext and "" or ((data.capfirst and ucfirst(inflections[1].infl_text) or inflections[1].infl_text) .. of_text)) formatted_text, this_categories = format_form_of(format_data) else format_data.text = format_labels(overall_labels, data, data.notext) .. (data.pretext or "") .. (data.notext and "" or ((data.capfirst and "Inflection" or "inflection") .. of_text)) format_data.posttext = (data.posttext or "") .. ":" local link link, this_categories = format_form_of(format_data) local text_classes = data.text_classes if text_classes == nil and not data.nowrap then text_classes = "form-of-definition use-with-mention" end for i, inflection in ipairs(inflections) do inflections[i] = "\n## " .. format_labels(inflection.labels, data, false) .. wrap_in_span(inflection.infl_text, text_classes) end formatted_text = link .. concat(inflections) end if this_categories[1] then extend(categories, this_categories) end if not data.no_format_categories then if categories[1] then formatted_text = formatted_text .. format_categories(categories, data.lang, data.sort, nil, export.force_cat) end return formatted_text end return formatted_text, categories end function export.dump_form_of_data(_frame) local data = { require(form_of_data1_module), require(form_of_data2_module) } return require(json_module).toJSON(data) end export.form_of_cats_module = form_of_cats_module export.form_of_data1_module = form_of_data1_module export.form_of_data2_module = form_of_data2_module export.form_of_functions_module = form_of_functions_module export.form_of_lang_data_module_prefix = form_of_lang_data_module_prefix export.headword_data_module = headword_data_module -- so all form-of modules stay in sync return export 5372ao39gyqdgrcci64qhc133rbhken 828 7988 54920 54734 2026-09-29T00:02:01Z Deadend0914 7211 54920 Scribunto text/plain local export = {} local decorations_module = "Module:decorations" local load_module = "Module:load" local parameters_module = "Module:parameters" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local concat = table.concat local insert = table.insert local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function format_decorations(...) format_decorations = require(decorations_module).format_decorations return format_decorations(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function process_params(...) process_params = require(parameters_module).process return process_params(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local gender_and_number_data local function get_gender_and_number_data() gender_and_number_data, get_gender_and_number_data = load_data("Module:gender and number/data"), nil return gender_and_number_data end --[==[ intro: This module creates standardised displays for gender and number. It converts a gender specification into Wiki/HTML format. A gender/number specification consists of one or more gender/number elements, separated by hyphens. Examples are: {"n"} (neuter gender), {"f-p"} (feminine plural), {"m-an-p"} (masculine animate plural), {"pf"} (perfective aspect). Each gender/number element has the following properties: # A code, as used in the spec, e.g. {"f"} for feminine, {"p"} for plural. # A type, e.g. `gender`, `number` or `animacy`. Each element in a given spec must be of a different type. # A display form, which in turn consists of a display code and a tooltip gloss. The display code may not be the same as the spec code, e.g. the spec code {"an"} has display code {"anim"} and tooltip gloss ''animate''. # A category into which lemmas of the right part of speech are placed if they have a gender/number spec containing the given element. For example, a noun with gender/number spec {"m-an-p"} is placed into the categories `<var>lang</var> masculine nouns`, `<var>lang</var> animate nouns` and `<var>lang</var> pluralia tantum`. ]==] --[==[ Version of format_genders() that can be invoked from a template. ]==] function export.show_list(frame) local params = { [1] = {list = true}, ["lang"] = {type = "language"}, } local iargs = process_params(frame.args, params) local text, cats = export.format_genders(iargs[1], iargs.lang) if not cats then return text end return text .. format_categories(cats, iargs.lang) end function export.format_list(...) -- FIXME: Added 2026-09-17. Remove after 2026-10-17. error("Use format_genders instead of format_list") end local function autoadd_abbr(display) if not display then error("Internal error: '.display' for gender/number code is missing") end if display:find("<abbr", nil, true) then return display end return ('%s'):format(display, display) end --[=[ Add decorations (qualifiers, labels and references) to a formatted gender/number spec. `spec` is the object describing the gender/number spec, which should optionally contain: * left qualifiers in `q`, an array of strings; * right qualifiers in `qq`, an array of strings; * left labels in `l`, an array of strings; * right labels in `ll`, an array of strings; * references in `refs`, an array either of strings (formatted reference text) or objects containing fields `text` (formatted reference text) and optionally `name` and/or `group`; `formatted` is the formatted version of the term itself, and `lang` is the optional language object passed into format_genders(). ]=] local function add_decorations(formatted, spec, lang) local function field_non_empty(field) local list = spec[field] if not list then return nil end if type(list) ~= "table" then error(("Internal error: Wrong type for `spec.%s`=%s, should be \"table\""):format( field, mw.dumpObject(list))) end return list[1] end if field_non_empty("q") or field_non_empty("qq") or field_non_empty("l") or field_non_empty("ll") or field_non_empty("refs") then formatted = format_decorations { lang = lang, text = formatted, q = spec.q, qq = spec.qq, l = spec.l, ll = spec.ll, refs = spec.refs, } end return formatted end --[==[ Format one or more gender/number specifications. Each spec is either a string, e.g. {"f-p"}, or a table of the form { {spec = "SPEC", q = {"LEFT_QUALIFIER", "LEFT_QUALIFIER", ...}, qq = {"RIGHT_QUALIFIER", "RIGHT_QUALIFIER", ...}, l = {"LEFT_LABEL", "LEFT_LABEL", ...}, ll = {"RIGHT_LABEL", "RIGHT_LABEL", ...}, refs = {"FORMATTED_REFERENCE_TEXT", {text = "FORMATTED_REFERENCE_TEXT", name = "REFNAME", group = "REFGROUP"}, ...}, }} In the table format, only `spec` is required, and in the `refs` object format, only `text` is required. If `lang` is not given, the funtion returns only one value, the formatted text. If `lang` is given, the function returns two values: # the formatted text; # a list of the categories to add, which will be {nil} if there are no categories to add. If `lang` (which should be a language object) and `pos_for_cat` (which should be a plural part of speech) are given, gender categories such as `German masculine nouns` or `Russian imperfective verbs` are added to the categories, and request categories such as `Requests for gender in <var>lang</var> entries` or `Requests for animacy in <var>lang</var> entries` may also be added. Otherwise, if only `lang` is given, only request categories may be returned. If both are omitted, only one return value is returned, as mentioned above. ]==] -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end function export.format_genders(specs, lang, pos_for_cat) local formatted_specs, categories, seen_types = {} local all_is_nounclass = nil local full_langname = lang and lang:getFullName() or nil local function do_gender_spec(spec, parts) local types = {} local codes = (gender_and_number_data or get_gender_and_number_data()).codes for key, code in ipairs(parts) do -- Is this code valid? if not codes[code] then error('The tag "' .. code .. '" in the gender specification "' .. spec.spec .. '" is not valid. See [[Module:gender and number]] for a list of valid tags.') end -- Check for multiple genders/numbers/animacies in a single spec. local typ = codes[code].type if typ ~= "other" and types[typ] then error('The gender specification "' .. spec.spec .. '" contains multiple tags of type "' .. typ .. '".') end types[typ] = true parts[key] = autoadd_abbr(codes[code].display) -- Generate categories if called for. if lang and pos_for_cat then local cat = codes[code].cat if cat then if not categories then categories = {} end insert(categories, full_langname .. " " .. cat_word(lang, cat)) end if not seen_types then seen_types = {} elseif seen_types[typ] and seen_types[typ] ~= code then cat = (gender_and_number_data or get_gender_and_number_data()).multicode_cats[typ] if cat then if not categories then categories = {} end insert(categories, full_langname .. " " .. cat_word(lang, cat)) end end seen_types[typ] = code end if lang and codes[code].req then local type_for_req = typ if code == "?" then -- Keep in mind `pos_for_cat` may be nil here. type_for_req = pos_for_cat == "verbs" and "aspect" or "gender" end if not categories then categories = {} end insert(categories, "Requests for " .. type_for_req .. " in " .. full_langname .. " entries") end end -- Add the processed codes together with non-breaking spaces if not parts[2] and parts[1] then return parts[1] else return concat(parts, "&nbsp;") end end for _, spec in ipairs(specs) do if type(spec) ~= "table" then spec = {spec = spec} end local spec_spec, is_nounclass = spec.spec -- If the specification starts with cX, then it is a noun class specification. if spec_spec:match("^%d") or spec_spec:match("^c[^-]") then is_nounclass = true local code = spec_spec:gsub("^c", "") local text if code == "?" then text = '<abbr class="noun-class" title="noun class missing">?</abbr>' if lang then if not categories then categories = {} end insert(categories, "Requests for noun class in " .. full_langname .. " entries") end else text = '<abbr class="noun-class" title="noun class ' .. code .. '">' .. code .. "</abbr>" if lang and pos_for_cat then if not categories then categories = {} end insert(categories, full_langname .. " " .. cat_word(lang, "class " .. code .. " POS")) end end local text_with_decorations = add_decorations(text, spec, lang) insert(formatted_specs, text_with_decorations) else -- Split the parts and iterate over each part, converting it into its display form local parts = split(spec.spec, "-", true, true) local combined_codes = (gender_and_number_data or get_gender_and_number_data()).combinations if lang then -- Check if the specification is valid --elseif langinfo.genders then -- local valid_genders = {} -- for _, g in ipairs(langinfo.genders) do valid_genders[g] = true end -- -- if not valid_genders[spec.spec] then -- local valid_string = {} -- for i, g in ipairs(langinfo.genders) do valid_string[i] = g end -- error('The gender specification "' .. spec.spec .. '" is not valid for ' .. langinfo.names[1] .. ". Valid are: " .. concat(valid_string, ", ")) -- end --end end local has_combined = false for _, code in ipairs(parts) do if combined_codes[code] then has_combined = true break end end if not has_combined then if formatted_specs[1] then insert(formatted_specs, "or") end insert(formatted_specs, add_decorations(do_gender_spec(spec, parts), spec, lang)) else -- This logic is to handle combined gender specs like 'mf' and 'mfbysense'. local all_parts = {{}} local extra_displays local this_formatted_specs = {} for _, code in ipairs(parts) do if combined_codes[code] then local new_all_parts = {} for _, one_parts in ipairs(all_parts) do for _, one_code in ipairs(combined_codes[code].codes) do local new_combined_parts = deep_copy(one_parts) insert(new_combined_parts, one_code) insert(new_all_parts, new_combined_parts) end end all_parts = new_all_parts if lang and pos_for_cat then local extra_cat = combined_codes[code].cat if extra_cat then if not categories then categories = {} end insert(categories, full_langname .. " " .. cat_word(lang, extra_cat)) end end local extra_display = combined_codes[code].display if extra_display then if not extra_displays then extra_displays = {} end insert(extra_displays, autoadd_abbr(extra_display)) end else for _, one_parts in ipairs(all_parts) do insert(one_parts, code) end end end for _, this_parts in ipairs(all_parts) do if this_formatted_specs[1] then insert(this_formatted_specs, "or") end insert(this_formatted_specs, do_gender_spec(spec, this_parts)) end if extra_displays then for _, display in ipairs(extra_displays) do insert(this_formatted_specs, display) end end insert(formatted_specs, add_decorations( concat(this_formatted_specs, " "), spec, lang)) end is_nounclass = false end -- Ensure that the specifications are either all noun classes, or none are. if all_is_nounclass == nil then all_is_nounclass = is_nounclass elseif all_is_nounclass ~= is_nounclass then error("Noun classes and genders cannot be mixed. Please use either one or the other.") end end if categories and lang and pos_for_cat then for i, cat in ipairs(categories) do categories[i] = cat:gsub("POS", pos_for_cat) end end local formatted_retval if all_is_nounclass then -- Add the processed codes together with slashes formatted_retval = '<span class="gender">class ' .. concat(formatted_specs, "/") .. "</span>" else -- Add the processed codes together with spaces formatted_retval = '<span class="gender">' .. concat(formatted_specs, " ") .. "</span>" end if lang then return formatted_retval, categories else return formatted_retval end end return export 81r0wqc0am2fwupqoyj5a56p0oy78ki 828 8016 54914 54785 2026-09-28T23:27:21Z Deadend0914 7211 54914 Scribunto text/plain local export = {} local pos_functions = {} local lang = require("Module:languages").getByCode("ang") local insert = table.insert local remove = table.remove local function get_plaintext(...) get_plaintext = require("Module:utilities").get_plaintext return get_plaintext(...) end local function track(page) require("Module:debug").track("ang-headword/" .. page) return true end local function glossary_link(anchor, text) text = text or anchor return "[[Appendix:Glossary#" .. anchor .. "|" .. text .. "]]" end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local NAMESPACE = mw.title.getCurrentTitle().nsText -- unused -- local PAGENAME = mw.loadData("Module:headword/data").pagename local iparams = { [1] = {required = true}, ["def"] = true, ["suff_type"] = true, } local iargs = require("Module:parameters").process(frame.args, iparams) local args = frame:getParent().args local poscat = iargs[1] local def = iargs.def local suff_type = iargs.suff_type local postype = nil if suff_type then postype = poscat .. "-" .. suff_type else postype = poscat end local data = { lang = lang, heads = {}, genders = {}, inflections = {}, categories = {}, no_redundant_head_cat = true, -- we want the headword specified to specify whether it has long vowels } if poscat == "suffixes" then insert(data.categories, "Englisc " .. suff_type .. "-forming suffixes") end if pos_functions[postype] then local new_poscat = pos_functions[postype](def, args, data) if new_poscat then poscat = new_poscat end end data.pos_category = poscat return require("Module:headword").full_headword(data) end local function validate_genders(genders) for _, gspec in ipairs(genders) do local g = gspec.spec if g ~= "wer" and g ~= "wif" and g ~= "n" and g ~= "m-p" and g ~= "f-p" and g ~= "n-p" and g~="m" and g~="f" and g ~= "?" then error("Invalid gender: " .. g) end end end pos_functions["nouns"] = function(def, args, data) local params = { ["head"] = {list = true}, ["id"] = true, [1] = {type = "genders", list = "g", flatten = true, disallow_holes = true}, ["g"] = {alias_of = 1, list = false}, [2] = {list = "pl", disallow_holes = true}, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id validate_genders(args[1]) data.genders = args[1] local pl = args[2] if pl[1] then pl.label = "nominative plural" insert(data.inflections, pl) end end pos_functions["proper nouns"] = pos_functions["nouns"] pos_functions["verbs"] = function(def, args, data) local params = { [1] = {alias_of = "head", list = false}, ["head"] = {list = true}, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id end local function adjectives(pos, def, args, data) local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, ["head"] = list, ["comp"] = list, [2] = {alias_of = "comp", list = false}, ["sup"] = list, [3] = {alias_of = "sup", list = false}, ["adv"] = list, ["indecl"] = {type = "boolean"}, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) end local comp = args.comp if #comp > 0 then comp.label = "comparative" insert(data.inflections, comp) end local sup = args.sup if #sup > 0 then sup.label = "superlative" insert(data.inflections, sup) end if #args.adv > 0 then args.adv.label = "adverb" insert(data.inflections, args.adv) end end pos_functions["adjectives"] = function(def, args, data) return adjectives("adjectives", def, args, data) end pos_functions["participles"] = function(def, args, data) return adjectives("participles", def, args, data) end pos_functions["determiners"] = function(def, args, data) return adjectives("determiners", def, args, data) end pos_functions["pronouns"] = function(def, args, data) return adjectives("pronouns", def, args, data) end pos_functions["suffixes-adjective"] = function(def, args, data) return adjectives("suffixes", def, args, data) end pos_functions["numerals-adjective"] = function(def, args, data) return adjectives("numerals", def, args, data) end pos_functions["adverbs"] = function(def, args, data) local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, [2] = {alias_of = "comp", list = false}, [3] = {alias_of = "sup", list = false}, ["head"] = list, ["comp"] = list, ["sup"] = list, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id local comp, sup if args.comp[1] == "-" then comp = "-" elseif #args.comp > 0 then args.comp.label = glossary_link("comparative") comp = args.comp end if args.comp[1] == "-" or args.sup[1] == "-" then sup = "-" elseif #args.sup > 0 then args.sup.label = glossary_link("superlative") sup = args.sup end if comp == "-" then insert(data.inflections, {label = "not " .. glossary_link("comparable")}) insert(data.categories, "Englisc uncomparable adverbs") else insert(data.inflections, comp) end if sup == "-" then if comp ~= "-" then insert(data.inflections, {label = "no " .. glossary_link("superlative")}) end else insert(data.inflections, sup) end end pos_functions["suffixes-adverb"] = pos_functions["adverbs"] local function get_forms(forms) if #forms == 0 then return nil end local i, attested = 1, false while true do local form = forms[i] if form == nil then return forms, attested elseif form == "-" then remove(forms, i) else if not (attested or get_plaintext(form):sub(1, 1) == "*") then attested = true end i = i + 1 end end end local function degree(pos, deg, other_arg, other_label, args, data) local boolean = {type = "boolean"} local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, ["head"] = list, ["positive"] = list, [other_arg] = list, ["indecl"] = boolean, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) end local positive, positive_attested = get_forms(args.positive) if positive then if not positive_attested then insert(data.categories, "Englisc " .. deg .. "-only " .. pos) end if #positive > 0 then args.positive.label = "positive" insert(data.inflections, args.positive) else insert(data.inflections, {label = "no positive form"}) end end local other = get_forms(args[other_arg]) if other then if #other > 0 then args[other_arg].label = other_label insert(data.inflections, args[other_arg]) else insert(data.inflections, {label = "no " .. other_label .. " form"}) end end -- If a lemma, return the primary part of speech ("adjectives" or -- "adverbs"), so that the term is categorized in "Old English adjectives" -- or "Old English adverbs". Otherwise, return nothing, so that the term -- goes in the relevant non-lemma category (e.g. "Old English comparative -- adjectives"), and into "Old English non-lemma forms". if positive and not positive_attested then return pos end end pos_functions["comparative adjectives"] = function(def, args, data) return degree("adjectives", "comparative", "sup", "superlative", args, data) end pos_functions["superlative adjectives"] = function(def, args, data) return degree("adjectives", "superlative", "comp", "comparative", args, data) end pos_functions["comparative adverbs"] = function(def, args, data) return degree("adverbs", "comparative", "sup", "superlative", args, data) end pos_functions["superlative adverbs"] = function(def, args, data) return degree("adverbs", "superlative", "comp", "comparative", args, data) end local function non_lemma_forms(def, args, data) local params = { [1] = {required = true, default = def}, -- headword or cases ["head"] = {list = true, require_index = true}, ["g"] = {list = true}, ["id"] = true, } local args = require("Module:parameters").process(args, params) local heads = {args[1]} for _, head in ipairs(args.head) do insert(heads, head) end data.heads = heads data.genders = args.g data.id = args.id end pos_functions["noun forms"] = non_lemma_forms pos_functions["proper noun forms"] = non_lemma_forms pos_functions["pronoun forms"] = non_lemma_forms pos_functions["verb forms"] = non_lemma_forms pos_functions["adjective forms"] = non_lemma_forms pos_functions["participle forms"] = non_lemma_forms pos_functions["determiner forms"] = non_lemma_forms pos_functions["numeral forms"] = non_lemma_forms pos_functions["suffix forms"] = non_lemma_forms return export q0m8uxbouv15iu5krvl0uc0j27cj8ui 54924 54914 2026-09-29T00:04:06Z Deadend0914 7211 54924 Scribunto text/plain local export = {} local pos_functions = {} local lang = require("Module:languages").getByCode("ang") local insert = table.insert local remove = table.remove local function get_plaintext(...) get_plaintext = require("Module:utilities").get_plaintext return get_plaintext(...) end local function track(page) require("Module:debug").track("ang-headword/" .. page) return true end local function glossary_link(anchor, text) text = text or anchor return "[[Appendix:Glossary#" .. anchor .. "|" .. text .. "]]" end -- The main entry point. -- This is the only function that can be invoked from a template. -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end function export.show(frame) local NAMESPACE = mw.title.getCurrentTitle().nsText -- unused -- local PAGENAME = mw.loadData("Module:headword/data").pagename local iparams = { [1] = {required = true}, ["def"] = true, ["suff_type"] = true, } local iargs = require("Module:parameters").process(frame.args, iparams) local args = frame:getParent().args local poscat = iargs[1] local def = iargs.def local suff_type = iargs.suff_type local postype = nil if suff_type then postype = poscat .. "-" .. suff_type else postype = poscat end local data = { lang = lang, heads = {}, genders = {}, inflections = {}, categories = {}, no_redundant_head_cat = true, -- we want the headword specified to specify whether it has long vowels } if poscat == "suffixes" then insert(data.categories, "Englisc " .. cat_word(lang, "{type}-forming suffixes"):gsub("{type}", suff_type)) end if pos_functions[postype] then local new_poscat = pos_functions[postype](def, args, data) if new_poscat then poscat = new_poscat end end data.pos_category = poscat return require("Module:headword").full_headword(data) end local function validate_genders(genders) for _, gspec in ipairs(genders) do local g = gspec.spec if g ~= "wer" and g ~= "wif" and g ~= "n" and g ~= "m-p" and g ~= "f-p" and g ~= "n-p" and g~="m" and g~="f" and g ~= "?" then error("Invalid gender: " .. g) end end end pos_functions["nouns"] = function(def, args, data) local params = { ["head"] = {list = true}, ["id"] = true, [1] = {type = "genders", list = "g", flatten = true, disallow_holes = true}, ["g"] = {alias_of = 1, list = false}, [2] = {list = "pl", disallow_holes = true}, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id validate_genders(args[1]) data.genders = args[1] local pl = args[2] if pl[1] then pl.label = "nominative plural" insert(data.inflections, pl) end end pos_functions["proper nouns"] = pos_functions["nouns"] pos_functions["verbs"] = function(def, args, data) local params = { [1] = {alias_of = "head", list = false}, ["head"] = {list = true}, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id end local function adjectives(pos, def, args, data) local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, ["head"] = list, ["comp"] = list, [2] = {alias_of = "comp", list = false}, ["sup"] = list, [3] = {alias_of = "sup", list = false}, ["adv"] = list, ["indecl"] = {type = "boolean"}, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) end local comp = args.comp if #comp > 0 then comp.label = "comparative" insert(data.inflections, comp) end local sup = args.sup if #sup > 0 then sup.label = "superlative" insert(data.inflections, sup) end if #args.adv > 0 then args.adv.label = "adverb" insert(data.inflections, args.adv) end end pos_functions["adjectives"] = function(def, args, data) return adjectives("adjectives", def, args, data) end pos_functions["participles"] = function(def, args, data) return adjectives("participles", def, args, data) end pos_functions["determiners"] = function(def, args, data) return adjectives("determiners", def, args, data) end pos_functions["pronouns"] = function(def, args, data) return adjectives("pronouns", def, args, data) end pos_functions["suffixes-adjective"] = function(def, args, data) return adjectives("suffixes", def, args, data) end pos_functions["numerals-adjective"] = function(def, args, data) return adjectives("numerals", def, args, data) end pos_functions["adverbs"] = function(def, args, data) local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, [2] = {alias_of = "comp", list = false}, [3] = {alias_of = "sup", list = false}, ["head"] = list, ["comp"] = list, ["sup"] = list, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id local comp, sup if args.comp[1] == "-" then comp = "-" elseif #args.comp > 0 then args.comp.label = glossary_link("comparative") comp = args.comp end if args.comp[1] == "-" or args.sup[1] == "-" then sup = "-" elseif #args.sup > 0 then args.sup.label = glossary_link("superlative") sup = args.sup end if comp == "-" then insert(data.inflections, {label = "not " .. glossary_link("comparable")}) insert(data.categories, "Englisc uncomparable adverbs") else insert(data.inflections, comp) end if sup == "-" then if comp ~= "-" then insert(data.inflections, {label = "no " .. glossary_link("superlative")}) end else insert(data.inflections, sup) end end pos_functions["suffixes-adverb"] = pos_functions["adverbs"] local function get_forms(forms) if #forms == 0 then return nil end local i, attested = 1, false while true do local form = forms[i] if form == nil then return forms, attested elseif form == "-" then remove(forms, i) else if not (attested or get_plaintext(form):sub(1, 1) == "*") then attested = true end i = i + 1 end end end local function degree(pos, deg, other_arg, other_label, args, data) local boolean = {type = "boolean"} local list = {list = true} local params = { [1] = {alias_of = "head", list = false}, ["head"] = list, ["positive"] = list, [other_arg] = list, ["indecl"] = boolean, ["id"] = true, } local args = require("Module:parameters").process(args, params) data.heads = args.head data.id = args.id if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) end local positive, positive_attested = get_forms(args.positive) if positive then if not positive_attested then insert(data.categories, "Englisc " .. deg .. "-only " .. pos) end if #positive > 0 then args.positive.label = "positive" insert(data.inflections, args.positive) else insert(data.inflections, {label = "no positive form"}) end end local other = get_forms(args[other_arg]) if other then if #other > 0 then args[other_arg].label = other_label insert(data.inflections, args[other_arg]) else insert(data.inflections, {label = "no " .. other_label .. " form"}) end end -- If a lemma, return the primary part of speech ("adjectives" or -- "adverbs"), so that the term is categorized in "Old English adjectives" -- or "Old English adverbs". Otherwise, return nothing, so that the term -- goes in the relevant non-lemma category (e.g. "Old English comparative -- adjectives"), and into "Old English non-lemma forms". if positive and not positive_attested then return pos end end pos_functions["comparative adjectives"] = function(def, args, data) return degree("adjectives", "comparative", "sup", "superlative", args, data) end pos_functions["superlative adjectives"] = function(def, args, data) return degree("adjectives", "superlative", "comp", "comparative", args, data) end pos_functions["comparative adverbs"] = function(def, args, data) return degree("adverbs", "comparative", "sup", "superlative", args, data) end pos_functions["superlative adverbs"] = function(def, args, data) return degree("adverbs", "superlative", "comp", "comparative", args, data) end local function non_lemma_forms(def, args, data) local params = { [1] = {required = true, default = def}, -- headword or cases ["head"] = {list = true, require_index = true}, ["g"] = {list = true}, ["id"] = true, } local args = require("Module:parameters").process(args, params) local heads = {args[1]} for _, head in ipairs(args.head) do insert(heads, head) end data.heads = heads data.genders = args.g data.id = args.id end pos_functions["noun forms"] = non_lemma_forms pos_functions["proper noun forms"] = non_lemma_forms pos_functions["pronoun forms"] = non_lemma_forms pos_functions["verb forms"] = non_lemma_forms pos_functions["adjective forms"] = non_lemma_forms pos_functions["participle forms"] = non_lemma_forms pos_functions["determiner forms"] = non_lemma_forms pos_functions["numeral forms"] = non_lemma_forms pos_functions["suffix forms"] = non_lemma_forms return export 1r03t2m843ip73o8dodh02dy9g4cppf 828 8053 54918 54857 2026-09-29T00:01:00Z Deadend0914 7211 54918 Scribunto text/plain local export = {} local require_when_needed = require("Module:utilities/require when needed") local affix_module = "Module:affix" local debug_track_module = "Module:debug/track" local decorations_module = "Module:decorations" local en_utilities_module = "Module:en-utilities" local fun_is_callable_module = "Module:fun/isCallable" local headword_module = "Module:headword" local headword_data_module = "Module:headword/data" local languages_module = "Module:languages" local links_module = "Module:links" local parameters_module = "Module:parameters" local parse_interface_module = "Module:parse interface" local parse_utilities_module = "Module:parse utilities" local string_pattern_escape_module = "Module:string/patternEscape" local string_replacement_escape_module = "Module:string/replacementEscape" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local yesno_module = "Module:yesno" local dump = mw.dumpObject local unpack = unpack or table.unpack -- Lua 5.2 compatibility local insert = table.insert local concat = table.concat local remove = table.remove local sort = table.sort local deep_equals = require_when_needed(table_module, "deepEquals") local extend = require_when_needed(table_module, "extend") local insert_if_not = require_when_needed(table_module, "insertIfNot") local list_to_set = require_when_needed(table_module, "listToSet") local serial_comma_join = require_when_needed(table_module, "serialCommaJoin") local shallow_copy = require_when_needed(table_module, "shallowCopy") local split = require_when_needed(string_utilities_module, "split") local ugsub = require_when_needed(string_utilities_module, "gsub") local umatch = require_when_needed(string_utilities_module, "match") local pattern_escape = require_when_needed(string_pattern_escape_module) local replacement_escape = require_when_needed(string_replacement_escape_module) local escape_wikicode = require_when_needed(parse_utilities_module, "escape_wikicode") local parse_inline_modifiers = require_when_needed(parse_utilities_module, "parse_inline_modifiers") local term_contains_top_level_html = require_when_needed(parse_utilities_module, "term_contains_top_level_html") local get_lang_by_code = require_when_needed(languages_module, "getByCode") -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end local is_callable = require_when_needed(fun_is_callable_module) local format_decorations = require_when_needed(decorations_module, "format_decorations") local function split_on_comma(val) if val:find(",") then return require(parse_interface_module).split_on_comma(val) else return {val} end end local function ine(val) if val == "" then return nil else return val end end --[=[ Add decorations to a term. `termobj` is the object describing the term, which should optionally contain: * left qualifiers in `q`, an array of strings; * right qualifiers in `qq`, an array of strings; * left labels in `l`, an array of strings; * right labels in `ll`, an array of strings; * references in `refs`, an array either of strings (formatted reference text) or objects containing fields `text` (formatted reference text) and optionally `name` and/or `group`; `text` is the text of the term itself, and `lang` is the language object. ]=] local function add_decorations(text, termobj, lang) local function field_non_empty(field) local list = termobj[field] if not list then return nil end if type(list) ~= "table" then error(("Internal error: Wrong type for `termobj.%s`=%s, should be \"table\""):format( field, mw.dumpObject(list))) end return list[1] end if field_non_empty("q") or field_non_empty("qq") or field_non_empty("l") or field_non_empty("ll") or field_non_empty("refs") then text = format_decorations { lang = lang, text = text, q = termobj.q, qq = termobj.qq, l = termobj.l, ll = termobj.ll, refs = termobj.refs, } end return text end local param_mods = { id = {}, -- disabled when `is_head = true` q = {type = "qualifier"}, qq = {type = "qualifier"}, l = {type = "labels"}, ll = {type = "labels"}, -- [[Module:headword]] expects part references in `.refs`. ref = {item_dest = "refs", type = "references", store = "insert-flattened"}, } local optional_param_mods = { g = {item_dest = "genders", type = "genders"}, alt = {}, lang = {type = "language"}, sc = {type = "script"}, t = {item_dest = "gloss"}, gloss = {}, pos = {}, lit = {}, tr = {}, ts = {}, face = {}, nolinkinfl = {type = "boolean"}, } local optional_headword_param_mods = { sc = {type = "script"}, tr = {}, ts = {}, } --[==[ Parse a single inflection or headword form or list of such forms. In either case, inline modifiers may be attached. `data` is an object with the following fields: * `val`: The raw value to parse. Required. * `paramname`: The name of the parameter from which the value was taken; used in error messages. Required. * `is_head`: We are parsing a headword parameter (a value which goes into the `heads` field of `data`). This changes the allowed modifiers, disabling the `id` modifier and only allowing a subset of optional modifiers. * `frob`: An optional function of one value to apply to the form after inline modifiers have been removed (i.e. to apply to the `.term` field of the returned object). * `include_mods`: List of extra inline modifiers to include, besides the default ones (see below). Each list item is either a string specifying a recognized extra inline modifier (see `optional_param_mods` in the code), or a two-item list of modifier name and modifier spec, where the spec should follow the syntax for modifier specs in `parse_inline_modifiers` in [[Module:parse utilities]]. * `exclude_mods`: List of default inline modifiers to not include. * `splitchar`: If specified, the value in `val` can be a list of forms to parse, separated by the value of `splitchar` (which is a Lua pattern, as in `parse_inline_modifiers` in [[Module:parse utilities]]). Most commonly, `splitchar` is a single comma and the values are comma-separated (in this case, splitting will not happen if a space follows the comma). * `parse_lang_prefix`: If specified, allow a language prefix to precede a form, and if found, store into the `.lang` field of the returned object. * `preserve_splitchar`, `delimiter_key`, `escape_fun`, `unescape_fun`, `pre_normalize_modifiers`: As in `parse_inline_modifiers` in [[Module:parse utilities]]. Returns an object suitable for storing as one element of one of the lists in `headdata.inflections`, where `headdata` is the structure passed to [[Module:headword]]. If `splitchar` is specified, howeve, the return value is a list of such objects. The following default inline modifiers are currently recognized: * `q`: Left qualifier. * `qq`: Right qualifier. * `l`: Comma-separated list of left labels. No space should follow the comma. * `ll`: Comma-separated list of right labels. No space should follow the comma. * `ref`: Reference or references. See {{tl|IPA}} for the syntax. * `id`: Sense ID, in case there are multiple senses. See {{tl|l}}. The following are the recognized additional inline modifiers: * `g`: Comma-separated list of genders. * `alt`: Display text. * `lang`: Language code of language of the form, if different from the language of the headword. * `sc`: Script code of script of the form. Almost never needed. * `t`: Gloss for the form. * `gloss`: Gloss for the form (alias for `t`). * `pos`: Part of speech of the form. * `lit`: Literal meaning of the form. * `tr`: Manual transliteration of the form. * `ts`: Transcription of the form, for languages where the transliteration differs markedly from the pronunciation. * `face`: Face to display the form in, e.g. {"hypothetical"} for a hypothetical form (unlinkable and displayed in italics). * `nolinkinfl`: Make the form unlinkable. ]==] function export.parse_term_with_modifiers(data) local paramname, val, frob = data.paramname, data.val, data.frob local function generate_obj(term, parse_err) if frob then term = frob(term, parse_err) end if data.parse_lang_prefix and term:find(":") then return require(parse_utilities_module).generate_obj_maybe_parsing_lang_prefix { term = term, paramname = paramname, parse_lang_prefix = true, parse_err = parse_err, } else return {term = term} end end -- Check for inline modifier, e.g. מרים<tr:Miryem>. But exclude top-level HTML entry with <span ...>, -- <sup> or similar in it. if (val:find("<", nil, true) or data.splitchar) and not term_contains_top_level_html(val) and -- don't parse inline modifiers if is_head and the value begins with a ~ (link modifier syntax) (not data.is_head or not val:find("^~")) then local param_mods = param_mods if data.is_head then param_mods = shallow_copy(param_mods) param_mods.id = nil end if data.include_mods or data.exclude_mods then if not data.is_head then -- already copied when data.is_head param_mods = shallow_copy(param_mods) end if data.include_mods then local optional_mods = data.is_head and optional_headword_param_mods or optional_param_mods for _, mod in ipairs(data.include_mods) do if type(mod) == "table" then if #mod ~= 2 then error(("Internal error: Modifier spec %s in `include_mods` should be of length 2"):format( dump(mod))) end local modkey, modvalue = unpack(mod) param_mods[modkey] = modvalue elseif not optional_mods[mod] then error(("Internal error: Unrecognized modifier spec %s in `include_mods`"):format( dump(mod))) else param_mods[mod] = optional_mods[mod] end end end if data.exclude_mods then for _, mod in ipairs(data.exclude_mods) do if not param_mods[mod] then error(("Internal error: Modifier spec %s in `exclude_mods` not found among existing modifiers" ):format(dump(mod))) else param_mods[mod] = nil end end end end return parse_inline_modifiers(val, { paramname = paramname, param_mods = param_mods, generate_obj = generate_obj, splitchar = data.splitchar, preserve_splitchar = data.preserve_splitchar, delimiter_key = data.delimiter_key, escape_fun = data.escape_fun, unescape_fun = data.unescape_fun, pre_normalize_modifiers = data.pre_normalize_modifiers, }) else local retval = generate_obj(val) if data.splitchar then retval = {retval} end return retval end end --[==[ Parse a list of inflection forms that may have inline modifiers attached. `data` is an object with the following fields: * `forms`: The list of raw values to parse. Required. * `paramname`: The name of the first parameter from which the value was taken; used in error messages. If this is a two-element list, the first element is the first parameter and the second element is the prefix of the remaining parameters. Parameter names that are numbers are handled correctly, as are those with \1 in it marking where the parameter index goes. Required. * `qualifiers`: If specified, a possibly gappy list of left qualifiers to add to the parsed terms (for compatibility purposes). * `splitchar`: As in `parse_term_with_modifiers()`. The resulting per-term lists will be flattened. * `frob`, `include_mods`, `exclude_mods`, `is_head`, `preserve_splitchar`, `parse_lang_prefix`, `delimiter_key`, `escape_fun`, `unescape_fun`, `pre_normalize_modifiers`: As in `parse_term_with_modifiers()`. Returns a list of objects, suitable for storing as one of the lists in `headdata.inflections` (once a label is added), where `headdata` is the structure passed to [[Module:headword]]. ]==] function export.parse_term_list_with_modifiers(data) local paramname, forms = data.paramname, data.forms local qualifiers = data.qualifiers local first, restpref if type(paramname) == "table" then first = paramname[1] restpref = paramname[2] else first = paramname restpref = paramname end local terms = {} data = shallow_copy(data) for i, val in ipairs(forms) do data.paramname = i == 1 and first or type(restpref) == "number" and restpref + i - 1 or restpref:find("\1", nil, true) and restpref:gsub("\1", tostring(i)) or restpref .. i data.val = val local parsed = export.parse_term_with_modifiers(data) if qualifiers and qualifiers[i] then if data.splitchar then for _, term in ipairs(parsed) do term.q = {qualifiers[i]} end else parsed.q = {qualifiers[i]} end end if data.splitchar then extend(terms, parsed) else terms[i] = parsed end end return terms end --[==[ Construct a link to [[Appendix:Glossary]] for `entry`. If `text` is specified, it is the display text; otherwise, `entry` is used. ]==] function export.glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end function export.replace_glossary_links_in_label(label) if label:find("<<", nil, true) then label = label:gsub("<<(.-)|(.-)>>", export.glossary_link):gsub("<<(.-)>>", export.glossary_link) end return label end --[==[ Insert a fixed inflection (a label not associated with any inflection values) into an `inflections` field. The `inflections` field will be initialized if needed. `data` is an object with the following fields: * `headdata`: The headword structure passed to [[Module:headword]]. Required. * `inflobj`: The object whose `inflections` field the terms are inserted into. Defaults to `headdata`. Only needs to be set for nested inflections, which are specified for an inflection object rather than the headword data structure as a whole. * `label`: The label that the inflections are given; any parts of the label surrounded in `<<...>>` are linked to the glossary. (If the contents of `<<...>>` contain a `|` in them, they are a two-part link.) Required. * `originating_term`: The term object from which this label is derived. If specified, decorations will be taken from this object. ]==] function export.insert_fixed_inflection(data) local headdata, origterm, label = data.headdata, data.originating_term, data.label local inflobj = data.inflobj or headdata inflobj.inflections = inflobj.inflections or {} if not origterm then insert(inflobj.inflections, { label = export.replace_glossary_links_in_label(label) }) else if origterm.id then error(("It doesn't make sense to pass in an ID '%s' for label '%s' in conjunction with a term value '%s'" ):format(origterm.id, label, origterm.term)) end origterm = shallow_copy(origterm) -- Preserve decorations origterm.term = nil origterm.label = export.replace_glossary_links_in_label(label) insert(inflobj.inflections, origterm) end end --[==[ Insert previously-parsed terms into an `inflections` field. The `inflections` field will be initialized if needed. `data` is an object with the following fields: * `headdata`: The headword structure passed to [[Module:headword]]. Required. * `inflobj`: The object whose `inflections` field the terms are inserted into. Defaults to `headdata`. Only needs to be set for nested inflections, which are specified for an inflection object rather than the headword data structure as a whole. * `terms`: The list of parsed terms. If {nil} or omitted, nothing happens unless `request` is set. * `label`: The label that the inflections are given; any parts of the label surrounded in `<<...>>` are linked to the glossary. (If the contents of `<<...>>` contain a `|` in them, they are a two-part link.) Required. * `no_label`: If the term is {"-"} and there are no other terms, insert a fixed label with this value. Defaults to {"no "} plus the label. * `usually_no_label`: If the term is {"-"} and there are other terms, insert a fixed label with this value. Defaults to {"usually no "} plus the label. * `cats`: List of categories to insert when terms are given that are not {"-"}. Each category is a string naming a full category to insert (including the appropriate language name prefixed). * `no_cats`: List of categories to insert when a term is given as {"-"}. * `usually_no_cats`: List of categories to insert when a term is given as {"-"} and additional terms are specified as well (representing, e.g. for the inflection {"plural"}, a term which usually has no plural but does under some circumstances). If omitted, both the categories in `cats` and `no_cats` are inserted. * `accel`: If specified, a full accelerator object to add to the inflections. * `request`: If specified and no terms are given, insert a label with a request for inflections to be given. * `enable_auto_translit`: If specified and terms are given, display automatic transliteration of the terms. The return value indicates whether the inflection exists and how many terms are in it. It is an object with the following fields: * `exists`: {"yes"} if one or more terms were specified; {"no"} if the value was given as {"-"}; {"usually no"} if the first value was given as {"-"} but additional terms were supplied; otherwise {nil}, indicating that the status is unspecified. * `numterms`: Number of terms in the inflection. Will be 0 unless `exists` has the value {"yes"} or {"usually no"}. * `request`: True if no terms were specified but a term request was inserted into the inflection (because `data.request` was specified). Otherwise {nil}. ]==] function export.insert_inflection(data) local headdata, terms, label = data.headdata, data.terms, data.label local inflobj = data.inflobj or headdata local retval = {} local accel = data.accel if data.accel_form then if accel then error("Internal error: can't specify both data.accel and data.accel_form") end if headdata.heads then local lemmas = {} local lemma_translits = {} for i, headobj in ipairs(headdata.heads) do lemmas[i] = headobj.term if lemmas[i] == "+" then error("Internal error: If you use data.accel_form, you should have resolved all occurrences of + in heads appropriately") end lemma_translits[i] = headobj.tr end accel = { lemma = lemmas, lemma_translit = lemma_translits, form = data.accel_form, } else accel = { form = data.accel_form, } end end local function insert_cats(cats) for _, cat in ipairs(cats) do insert(headdata.categories, cat) end end if terms and terms[1] then terms = shallow_copy(terms) if terms[1].term == "-" then if terms[2] then export.insert_fixed_inflection { headdata = headdata, inflobj = inflobj, originating_term = terms[1], label = data.usually_no_label or "usually no " .. label, } remove(terms, 1) retval.numterms = #terms retval.exists = "usually no" if data.usually_no_cats then insert_cats(data.usually_no_cats) else if data.no_cats then insert_cats(data.no_cats) end if data.cats then insert_cats(data.cats) end end else export.insert_fixed_inflection { headdata = headdata, inflobj = inflobj, originating_term = terms[1], label = data.no_label or "no " .. label, } retval.numterms = 0 retval.exists = "no" if data.no_cats then insert_cats(data.no_cats) end return retval end else retval.numterms = #terms retval.exists = "yes" if data.cats then insert_cats(data.cats) end end if data.check_missing then error("Internal error: check_missing support removed; use checkredlinks=true in [[Module:headword]]") end terms.label = export.replace_glossary_links_in_label(label) if accel then terms.accel = accel end terms.enable_auto_translit = data.enable_auto_translit inflobj.inflections = inflobj.inflections or {} insert(inflobj.inflections, terms) elseif data.request then inflobj.inflections = inflobj.inflections or {} insert(inflobj.inflections, { label = export.replace_glossary_links_in_label(label), request = true, }) retval.numterms = 0 -- retval.exists = nil retval.request = true else retval.numterms = 0 -- retval.exists = nil end return retval end --[==[ Parse raw arguments from `forms` for inline modifiers, and insert the resulting terms (which should not require significant additional processing) into `headdata.inflections`. `data` is an object with the following fields: * `forms`: The list of raw values to parse. If {nil} or omitted, nothing happens. * `headdata`: The headword structure passed to [[Module:headword]]. Required. * `paramname`: As in `parse_term_list_with_modifiers()`. Required. * `label`: As in `insert_inflection()`. Required. * `qualifiers`, `frob`, `include_mods`, `exclude_mods`, `is_head`, `splitchar`, `preserve_splitchar`, `delimiter_key`, `escape_fun`, `unescape_fun`, `pre_normalize_modifiers`: As in `parse_term_list_with_modifiers()`. * `accel`: As in `insert_inflection()`. Return value is as in `insert_inflection()`. ]==] function export.parse_and_insert_inflection(data) local forms = data.forms if forms and forms[1] then data = shallow_copy(data) data.forms = forms data.terms = export.parse_term_list_with_modifiers(data) return export.insert_inflection(data) end return { numterms = 0 } end --[==[ Canonicalize a single term or term-like object or a list of either into a list of term-like objects. `abterms` is the term or list to canonicalize, and `field` is the name of the field holding the term (defaulting to {"term"}). This does the minimal work necessary, meaning that the return value may partly or completely share memory with the value passed in. As a special case, if `abterms` is {nil}, {nil} is returned. If `origin_val` is specified, add a field `origin` containing the value of `origin_val` to each resulting term-like object (in this case, the object will be copied a necessary to avoid side-effecting the passed-in objects). ]==] function export.canonicalize_termobj_list(abterms, field, origin_val) if abterms == nil then return nil end field = field or "term" if type(abterms) == "string" then return {{[field] = abterms, origin = origin_val}} elseif not abterms[1] then if origin_val ~= nil then abterms = shallow_copy(abterms) abterms.origin = origin_val end return {abterms} else -- Check if already in full list term and return directly if so (unless `origin_val` is given, in which case we -- need to shallow-copy both the list and each term in it). local must_convert = false for _, term in ipairs(abterms) do if type(term) == "string" then must_convert = true break end end if not must_convert then if origin_val ~= nil then abterms = shallow_copy(abterms) for i, abterm in ipairs(abterms) do abterms[i] = shallow_copy(abterm) abterms[i].origin = origin_val end end return abterms end end local retval = {} for _, term in ipairs(abterms) do if type(term) == "string" then insert(retval, {[field] = term, origin = origin_val}) else if origin_val ~= nil then term = shallow_copy(term) term.origin = origin_val end insert(retval, term) end end return retval end --[==[ Combine two sets of decorations. If either is {nil}, just return the other, and if both are {nil}, return {nil}. ]==] function export.combine_decorations(decs1, decs2) if not decs1 and not decs2 then return nil end if not decs1 then return decs2 end if not decs2 then return decs1 end local combined = shallow_copy(decs1) for _, dec in ipairs(decs2) do insert_if_not(combined, dec) end return combined end function export.combine_qualifiers_or_labels(...) -- FIXME: Added 2026-09-17. Remove after a month. error("Use combine_decorations instead") end --[==[ Combine the decorations (qualifiers, labels, references) and ID's of two term objects. `destobj` is the "destination term object" into which the combined properties are written, and `srcobj` is the "source object" into which the properties are merged. `destobj` is side-effected (but the lists inside of `destobj` are not); if this is undesirable, make sure to shallow-copy `destobj` first. If both objects have values for a given decoration, the values of `destobj` come first. If both objects have a value for `id`, the values must match or an error is thrown; otherwise, the resulting value of `id` comes from whichever one is defined. '''NOTE:''' This may not be the correct behavior when deduplicating a list of term objects. See `insert_termobj_combining_duplicates` for a different approach. ]==] function export.combine_termobj_decorations(destobj, srcobj) destobj.q = export.combine_decorations(destobj.q, srcobj.q) destobj.qq = export.combine_decorations(destobj.qq, srcobj.qq) destobj.l = export.combine_decorations(destobj.l, srcobj.l) destobj.ll = export.combine_decorations(destobj.ll, srcobj.ll) destobj.refs = export.combine_decorations(destobj.refs, srcobj.refs) if destobj.id and srcobj.id and destobj.id ~= srcobj.id then -- FIXME: We probably want to pass in an error function error(("Can't specify two different ID's %s and %s when combining objects"):format(srcobj.id, destobj.id)) end destobj.id = destobj.id or srcobj.id return destobj end function export.combine_termobj_qualifiers_labels(...) -- FIXME: Added 2026-09-17. Remove after a month. error("Use combine_termobj_decorations instead") end function export.termobj_has_decorations(obj) return obj.q and obj.q[1] or obj.qq and obj.qq[1] or obj.l and obj.l[1] or obj.ll and obj.ll[1] or obj.refs and obj.refs[1] end function export.termobj_has_qualifiers_or_labels(...) -- FIXME: Added 2026-09-17. Remove after a month. error("Use termobj_has_decorations instead") end local function one_decoration_equal(prop1, prop2) local prop1_is_nil = not prop1 or not prop1[1] local prop2_is_nil = not prop2 or not prop2[1] if prop1_is_nil and prop2_is_nil then return true end if prop1_is_nil or prop2_is_nil then return false end return deep_equals(prop1, prop2) end function export.termobj_decorations_equal(obj1, obj2) return one_decoration_equal(obj1.q, obj2.q) and one_decoration_equal(obj1.qq, obj2.qq) and one_decoration_equal(obj1.l, obj2.l) and one_decoration_equal(obj1.ll, obj2.ll) and one_decoration_equal(obj1.refs, obj2.refs) and obj1.id == obj2.id end function export.termobj_ancillary_properties_equal(...) -- FIXME: Added 2026-09-17. Remove after a month. error("Use termobj_decorations_equal instead") end function export.convert_termobj_to_formobj(termobj) local formobj = { form = termobj.term, translit = termobj.tr, } local footnotes local function mods_to_footnote(mod_prefix, mod_vals) if mod_vals and mod_vals[1] then footnotes = footnotes or {} for _, val in ipairs(mod_vals) do insert(footnotes, "[" .. mod_prefix .. ":" .. val .. "]") end end end mods_to_footnote("q", termobj.q) mods_to_footnote("qq", termobj.qq) mods_to_footnote("l", termobj.l) mods_to_footnote("ll", termobj.ll) mods_to_footnote("ref", termobj.refs) mods_to_footnote("id", termobj.id and {termobj.id} or nil) formobj.footnotes = footnotes return formobj end local recognized_multi_mods = { q = "q", qq = "qq", l = "l", ll = "ll", ref = "refs", } local recognized_single_mods = { id = "id", } function export.add_footnote_to_termobj(termobj, footnote) local stripped_footnote = footnote:match("^%[(.*)%]$") if not stripped_footnote then error("Internal error: Footnote should be surrounded by brackets at this stage: " .. footnote) end local prefix, rest = stripped_footnote:match("^([a-z]+):(.+)$") local field, is_multi if prefix then if recognized_multi_mods[prefix] then field = recognized_multi_mods[prefix] is_multi = true elseif recognized_single_mods[prefix] then field = recognized_single_mods[prefix] is_multi = false end end if not field then rest = stripped_footnote field = "l" is_multi = true end if is_multi then if not termobj[field] then termobj[field] = {} end insert(termobj[field], rest) else if termobj[field] and termobj[field] ~= rest then error(("Can't set two values for '%s': '%s' and '%s'"):format(field, termobj[field], rest)) end termobj[field] = rest end end function export.convert_formobj_to_termobj(formobj) local termobj = { term = formobj.form, tr = formobj.translit, } if formobj.footnotes then for _, footnote in ipairs(formobj.footnotes) do export.add_footnote_to_termobj(termobj, footnote) end end return termobj end local function extract_termobj_field_modifiers(fieldval) return fieldval:match("^([*+]?)(.*)$") end function export.remove_termobj_field_modifiers(termobj) local function remove_field_modifiers(field) if termobj[field] and termobj[field][1] then local any_field_modifiers = false for _, val in ipairs(termobj[field]) do local field_mods, _ = extract_termobj_field_modifiers(val) if field_mods ~= "" then any_field_modifiers = true break end end local new_field = {} if any_field_modifiers then for _, val in ipairs(termobj[field]) do local _, field_without_mods = extract_termobj_field_modifiers(val) insert_if_not(new_field, field_without_mods) end termobj[field] = new_field end end end remove_field_modifiers("q") remove_field_modifiers("qq") remove_field_modifiers("l") remove_field_modifiers("ll") remove_field_modifiers("refs") end function export.insert_termobj_combining_duplicates(destobjs, termobj) for _, destobj in ipairs(destobjs) do if destobj.term == termobj.term and destobj.tr == termobj.tr then -- Form already present; maybe combine footnotes. local function combine_field_values(field) if termobj[field] and termobj[field][1] then -- Check to see if there are existing values with *; if so, remove them. if destobj[field] and destobj[field][1] then local any_values_with_asterisk = false for _, val in ipairs(destobj[field]) do local field_mods, _ = extract_termobj_field_modifiers(val) if field_mods:find("%*") then any_values_with_asterisk = true break end end if any_values_with_asterisk then local filtered_values = {} for _, val in ipairs(destobj[field]) do local field_mods, _ = extract_termobj_field_modifiers(val) if not field_mods:find("%*") then insert(filtered_values, val) end end if filtered_values[1] then destobj[field] = filtered_values else destobj[field] = nil end end end local any_footnotes_with_plus = false for _, val in ipairs(termobj[field]) do local field_mods, _ = extract_termobj_field_modifiers(val) if field_mods:find("%+") then any_footnotes_with_plus = true break end end if any_footnotes_with_plus then if not destobj[field] then destobj[field] = {} else destobj[field] = shallow_copy(destobj[field]) end for _, val in ipairs(termobj[field]) do local already_seen = false local field_mods, field_without_mods = extract_termobj_field_modifiers(val) if field_mods:find("%+") then for _, existing_val in ipairs(destobj[field]) do local _, existing_field_without_mods = extract_termobj_field_modifiers(existing_val) if existing_field_without_mods == field_without_mods then already_seen = true break end end if not already_seen then insert(destobj[field], val) end end end end end end combine_field_values("q") combine_field_values("qq") combine_field_values("l") combine_field_values("ll") combine_field_values("refs") if destobj.id and termobj.id and destobj.id ~= termobj.id then -- FIXME: We probably want to pass in an error function error(("Can't specify two different ID's %s and %s when combining objects"):format(termobj.id, destobj.id)) end destobj.id = destobj.id or termobj.id return end end insert(destobjs, termobj) end export.allowed_special_indicators = { ["first"] = true, ["first-second"] = true, ["first-last"] = true, ["second"] = true, ["last"] = true, ["each"] = true, ["+"] = true, -- requests the default behavior with preposition handling } --[==[ Check for special indicators (values such as {"+first"} or {"+first-last"} that are used in a `pl`, `f`, etc. argument and indicate how to inflect a multiword term). If `form` is such an indicator, the return value is `form` minus the initial `+` sign; otherwise, if form begins with a `+` sign, an error is thrown; otherwise the return value is nil. ]==] function export.get_special_indicator(form, noerror) if form:find("^%+") then form = form:gsub("^%+", "") if not export.allowed_special_indicators[form] then if noerror then return nil end local indicators = {} for indic, _ in pairs(export.allowed_special_indicators) do insert(indicators, "+" .. indic) end sort(indicators) error("Special inflection indicator beginning with '+' can only be " .. mw.text.listToText(indicators) .. ": +" .. form) end return form end return nil end local function add_endings(bases, endings) local retval = {} if type(bases) ~= "table" then bases = {bases} end if type(endings) ~= "table" then endings = {endings} end for _, base in ipairs(bases) do for _, ending in ipairs(endings) do insert(retval, base .. ending) end end return retval end --[==[ Inflect a possibly multiword or hyphenated term `form` using the function `inflect`, which is a function of one argument that is called on a single word to inflect and should return either the inflected word or a list of inflected words. `special` indicates how to inflect the multiword term and should be e.g. {"first"} to inflect only the first word, {"first-last"} to inflect the first and last words, {"each"} to inflect each word, etc. See `allowed_special_indicators` above for the possibilities. If `special` is `+`, or is omitted and the term is multiword (i.e. containing a space character), and `prepositions` is supplied, the function checks for multiword or hyphenated terms containing the prepositions in `prepositions`, e.g. Italian [[senso di marcia]] or [[medaglia d'oro]] or Portuguese [[tartaruga-do-mar]]. If such a term is found, only the first word is inflected. Otherwise, the default is {"first-last"}. `prepositions` is a list of Lua patterns matching prepositions. The patterns will automatically have the separator character (space or hyphen) added to the left side but not the right side, so they should contain a space character (which will automatically be converted to the appropriate separator) on the right side unless the preposition is joined on the right side with an apostrophe. Examples of preposition patterns for Italian are {"di "}, {"sull'"} and {"d?all[oae] "} (which matches {"dallo "}, {"dalle "}, {"alla "}, etc.). The return value is always either a list of inflected multiword or hyphenated terms, or nil if `special` is omitted and `form` is not multiword. (If `special` is specified and `form` is not multiword or hyphenated, an error results.) ]==] function export.handle_multiword(form, special, inflect, prepositions, sep) sep = sep or form:find(" ") and " " or "%-" local raw_sep = sep == " " and " " or "-" -- Used to add regex version of separator in the replacement portion of ugsub() or :gsub() local sep_replacement = sep == " " and " " or "%%-" -- Given a Lua pattern, replace space with the appropriate separator. local function hack_re(re) if sep == " " then return re end return (re:gsub(" ", sep_replacement)) end if special == "first" then local first, rest = form:match(hack_re("^(.-)( .*)$")) if not first then error("Special indicator 'first' can only be used with a multiword term: " .. form) end return add_endings(inflect(first), rest) elseif special == "second" then local first, second, rest = form:match(hack_re("^([^ ]+ )([^ ]+)( .*)$")) if not first then error("Special indicator 'second' can only be used with a term with three or more words: " .. form) end return add_endings(add_endings({first}, inflect(second)), rest) elseif special == "first-second" then local first, space, second, rest = form:match(hack_re("^([^ ]+)( )([^ ]+)( .*)$")) if not first then error("Special indicator 'first-second' can only be used with a term with three or more words: " .. form) end return add_endings(add_endings(add_endings(inflect(first), space), inflect(second)), rest) elseif special == "each" then local terms = split(form, sep) if #terms < 2 then error("Special indicator 'each' can only be used with a multiword term: " .. form) end for i, term in ipairs(terms) do terms[i] = inflect(term) if i > 1 then terms[i] = add_endings(raw_sep, terms[i]) end end local result = "" for _, term in ipairs(terms) do result = add_endings(result, term) end return result elseif special == "first-last" then local first, middle, last = form:match(hack_re("^(.-)( .* )(.-)$")) if not first then first, middle, last = form:match(hack_re("^(.-)( )(.*)$")) end if not first then error("Special indicator 'first-last' can only be used with a multiword term: " .. form) end return add_endings(add_endings(inflect(first), middle), inflect(last)) elseif special == "last" then local rest, last = form:match(hack_re("^(.* )(.-)$")) if not rest then error("Special indicator 'last' can only be used with a multiword term: " .. form) end return add_endings(rest, inflect(last)) elseif special and special ~= "+" then error("Unrecognized special=" .. special) end -- Only do default behavior if special indicator '+' explicitly given or separator is space; otherwise we will -- break existing behavior with hyphenated words. if (special == "+" or sep == " ") and form:find(sep) then if prepositions then -- check for prepositions in the middle of the word; do it this way so we can handle -- more than one word before the preposition (and usually inflect each word) for _, prep in ipairs(prepositions) do local first, space_prep_rest = umatch(form, hack_re("^(.-)( " .. prep .. ".*)$")) if first then return add_endings(inflect(first), space_prep_rest) end end end -- multiword or hyphenated expressions default to first-last; we need to pass in the separator to avoid -- problems with multiword terms containing hyphens in the individual words return export.handle_multiword(form, "first-last", inflect, prepositions, sep) end return nil end local function link_hyphen_split_component(word, data) if data.link_hyphen_split_component then return data.link_hyphen_split_component(word) else return "[[" .. word .. "]]" end end -- Default function to split a word on apostrophes. Don't split apostrophes at the beginning or end of a word (e.g. -- [['ndrangheta]] or [[po']]). Handle multiple apostrophes correctly, e.g. [[l'altr'ieri]] -> [[l']][altr']][[ieri]]. function export.default_split_apostrophe(word, data) local apostrophe_parts = split(word, "'", true, true) local linked_apostrophe_parts = {} local apostrophes_at_beginning = "" local i = 1 -- Apostrophes at beginning get attached to the first word after (which will always exist but may -- be blank if the word consists only of apostrophes). while i < #apostrophe_parts do -- <, not <=, in case the word consists only of apostrophes local apostrophe_part = apostrophe_parts[i] i = i + 1 if apostrophe_part == "" then apostrophes_at_beginning = apostrophes_at_beginning .. "'" else break end end apostrophe_parts[i] = apostrophes_at_beginning .. apostrophe_parts[i] -- Now, do the remaining parts. A blank part indicates more than one apostrophe in a row; we join -- all of them to the preceding word. while i <= #apostrophe_parts do local apostrophe_part = apostrophe_parts[i] if apostrophe_part == "" then linked_apostrophe_parts[#linked_apostrophe_parts] = linked_apostrophe_parts[#linked_apostrophe_parts] .. "'" elseif i == #apostrophe_parts then insert(linked_apostrophe_parts, apostrophe_part) else insert(linked_apostrophe_parts, apostrophe_part .. "'") end i = i + 1 end for j, tolink in ipairs(linked_apostrophe_parts) do linked_apostrophe_parts[j] = link_hyphen_split_component(tolink, data) end return concat(linked_apostrophe_parts) end --[=[ Auto-add links to a word that should not have spaces but may have hyphens and/or apostrophes. We split off final punctuation, then split on hyphens if `data.split_hyphen` is given, and also split on apostrophes if `data.split_apostrophe` is given. We only split on hyphens if they are in the middle of the word, not at the beginning or end (hyphens at the beginning or end indicate suffixes or prefixes, respectively). `include_hyphen_prefixes`, if given, is a set of prefixes (not including the final hyphen) where we should include the final hyphen in the prefix. Hence, e.g. if "anti" is in the set, a Portuguese word like [[anti-herói]] "anti-hero" will be split [[anti-]][[herói]] (whereas a word like [[código-fonte]] "source code" will be split as [[código]]-[[fonte]]). If `data.split_apostrophe` is specified, we split on apostrophes unless `data.no_split_apostrophe_words` is given and the word is in the specified set, such as French [[c'est]] and [[quelqu'un]]. If `data.split_apostrophe` is true, the default algorithm applies, which splits on all apostrophes except those at the beginning and end of a word (as in Italian [['ndrangheta]] or [[po']]), and includes the apostrophe in the link to its left (so we auto-split French [[l'eau]] as [[l']][[eau]] and [[l'altr'ieri]] as [[l']][altr']][[ieri]]). If `data.split_apostrophe` is specified but not `true`, it should be a function of one argument that does custom apostrophe-splitting. The argument is the word to split, and the return value should be the split and linked word. ]=] local function add_single_word_links(space_word, data, term_has_spaces) local space_word_no_punct, punct local punct_pattern = data.punctuation if punct_pattern and is_callable(punct_pattern) then space_word_no_punct, punct = punct_pattern(space_word) else if punct_pattern == nil then punct_pattern = "[,;:?!]" end space_word_no_punct, punct = umatch(space_word, "^(.*)(" .. punct_pattern .. ")$") end space_word_no_punct = space_word_no_punct or space_word punct = punct or "" local words if space_word_no_punct:sub(1, 1) == "-" or space_word_no_punct:sub(-1) == "-" then -- don't split prefixes and suffixes words = {space_word_no_punct} else local splitter if term_has_spaces then splitter = data.split_hyphen_when_space else splitter = data.split_hyphen_when_no_space end if is_callable(splitter) then words = splitter(space_word_no_punct) if type(words) == "string" then return words .. punct end end end if not words then local split_hyphen if term_has_spaces then split_hyphen = data.split_hyphen_when_space else split_hyphen = data.split_hyphen_when_no_space if split_hyphen == nil then -- default to true; use `false` to avoid this split_hyphen = true end end if split_hyphen then words = split(space_word_no_punct, "-", true, true) else words = {space_word_no_punct} end end local linked_words = {} for j, word in ipairs(words) do if j < #words and data.include_hyphen_prefixes and data.include_hyphen_prefixes[word] then word = "[[" .. word .. "-]]" elseif j > 1 and data.include_hyphen_suffixes and data.include_hyphen_suffixes[word] then word = "[[-" .. word .. "]]" else -- Don't split on apostrophes if the word is in `no_split_apostrophe_words`. if (not data.no_split_apostrophe_words or not data.no_split_apostrophe_words[word]) and data.split_apostrophe and word:find("'", nil, true) then if data.split_apostrophe == true then word = export.default_split_apostrophe(word, data) else -- custom apostrophe splitter/linker word = data.split_apostrophe(word) end elseif word ~= "" then -- avoid -[[]]- (e.g. f--k) word = link_hyphen_split_component(word, data) end if j < #words then word = word .. "-" end end insert(linked_words, word) end return concat(linked_words) .. punct end --[=[ Auto-add links to a multiword term. `data` contains fields customizing how to do this. By default we proceed as follows: (1) If the term already has embedded links in it, they are left unchanged. (2) Otherwise, if there are spaces present, we split on spaces and link each word separately. (3) If a given space-separated component ends in punctuation (defaulting to [,;:?!]), it is separated off, the remainder of the algorithm run, and the punctuation pasted back on. (4) If there are hyphens in a given space-separated component, we may link each hyphenated term separately depending on the settings in `data`. Normally the hyphens are not included in the linked terms, but this can be overridden for specific prefixes and/or suffixes. By default, if there are spaces in the multiword term, we do not link hyphenated components (because of cases like "boire du petit-lait" where "petit-lait" should be linked as a whole), but do so otherwise (e.g. for "avant-avant-hier"); this can overridden for cases like "croyez-le ou non". Cases where only some of the hyphens should be split can always be handled by explicitly specifying the head (e.g. "Nord-Pas-de-Calais" given as head=[[Nord]]-[[Pas-de-Calais]]). (5) If there are apostrophes in a given component, we may link each apostrophe-separated term separately depending on the settings in `data`, including the apostrophe in the link to its left (so we split "de l'eau" as "[[de]] [[l']][[eau]]"). The settings in `data` are as follows: `split_hyphen_when_no_space`: Whether to split on hyphens when the term has no spaces. Defaults to true if set to `nil`. This can be a function of one argument, to implement a custom splitting algorithm for hyphen-separated terms. If this returns [FIXME: FINISH ME ...] If `data.split_apostrophe` is specified, we split on apostrophes unless `data.no_split_apostrophe_words` is given and the word is in the specified set, such as French [[c'est]] and [[quelqu'un]]. If `data.split_apostrophe` is true, the default algorithm applies, which splits on all apostrophes except those at the beginning and end of a word (as in Italian [['ndrangheta]] or [[po']]), and includes the apostrophe in the link to its left (so we auto-split French [[l'eau]] as [[l']][[eau]] and [[l'altr'ieri]] as [[l']][altr']][[ieri]]). If `data.split_apostrophe` is specified but not `true`, it should be a function of one argument that does custom apostrophe-splitting. The argument is the word to split, and the return value should be the split and linked word. We don't always split on hyphens because of cases like "boire du petit-lait" where "petit-lait" should be linked as a whole, but provide the option to do it for cases like "croyez-le ou non". If there's no space, however, then it makes sense to split on hyphens by `no_split_apostrophe_words` and `include_hyphen_prefixes` allow for special-case handling of particular words and are as described in the comment above add_single_word_links(). ]=] function export.add_links_to_multiword_term(term, data) if term:match("[%[%]]") then return term end local words = split(term, " ", true, true) local term_has_spaces = #words > 1 local linked_words = {} for _, word in ipairs(words) do insert(linked_words, add_single_word_links(word, data, term_has_spaces)) end local retval = concat(linked_words, " ") -- If we ended up with a single link consisting of the entire term, -- remove the link. return retval:match("^%[%[([^%[%]]*)%]%]$") or retval end local function canonicalize_begin_end_spec(spec) local from, to = spec:match("^(.-):(.*)$") if not from then from = spec to = "" end return from, to end --[==[ Given a `linked_term` that is the output of add_links_to_multiword_term(), apply modifications as given in `modifier_spec` to change the link destination of subterms (normally single-word non-lemma forms; sometimes collections of adjacent words). This is usually used to link non-lemma forms to their corresponding lemma, but can also be used to replace a span of adjacent separately-linked words to a single multiword lemma. The format of `modifier_spec` is one or more semicolon-separated subterm specs, where each such spec is of the form SUBTERM:DEST, where SUBTERM is one or more words in the `linked_term` but without brackets in them, and DEST is the corresponding link destination to link the subterm to. Any occurrence of ~ in DEST is replaced with SUBTERM. Alternatively, a single modifier spec can be of the form BEGIN[FROM:TO], which is equivalent to writing BEGINFROM:BEGINTO (see example below). For example, given the source phrase [[il bue che dice cornuto all'asino]] "the pot calling the kettle black" (literally "the ox that calls the donkey horned/cuckolded"), the result of calling add_links_to_multiword_term() is [[il]] [[bue]] [[che]] [[dice]] [[cornuto]] [[all']][[asino]]. With a modifier_spec of 'dice:dire', the result is [[il]] [[bue]] [[che]] [[dire|dice]] [[cornuto]] [[all']][[asino]]. Here, based on the modifier spec, the non-lemma form [[dice]] is replaced with the two-part link [[dire|dice]]. Another example: given the source phrase [[chi semina vento raccoglie tempesta]] "sow the wind, reap the whirlwind" (literally (he) who sows wind gathers [the] tempest"). The result of calling add_links_to_multiword_term() is [[chi]] [[semina]] [[vento]] [[raccoglie]] [[tempesta]], and with a modifier_spec of 'semina:~re; raccoglie:~re', the result is [[chi]] [[seminare|semina]] [[vento]] [[raccogliere|raccoglie]] [[tempesta]]. Here we use the ~ notation to stand for the non-lemma form in the destination link. A more complex example is [[se non hai altri moccoli puoi andare a letto al buio]], which becomes [[se]] [[non]] [[hai]] [[altri]] [[moccoli]] [[puoi]] [[andare]] [[a]] [[letto]] [[al]] [[buio]] after calling add_links_to_multiword_term(). With the following modifier_spec: 'hai:avere; altr[i:o]; moccol[i:o]; puoi: potere; andare a letto:~; al buio:~', the result of applying the spec is [[se]] [[non]] [[avere|hai]] [[altro|altri]] [[moccolo|moccoli]] [[potere|puoi]] [[andare a letto]] [[al buio]]. Here, we rely on the alternative notation mentioned above for e.g. 'altr[i:o]', which is equivalent to 'altri:altro', and link multiword subterms using e.g. 'andare a letto:~'. (The code knows how to handle multiword subexpressions properly, and if the link text and destination are the same, only a single-part link is formed.) ]==] function export.apply_link_modifiers(linked_term, modifier_spec, lang) local split_modspecs = split(modifier_spec, "%s*;%s*") for j, modspec in ipairs(split_modspecs) do local id if modspec:find("<") then local rest rest, id = modspec:match("^(.*)<id:(.-)>$") if rest then modspec = rest end end local subterm, dest, otherlang local begin_spec, rest, end_spec = modspec:match("^%[(.-)%]([^:]*)%[(.-)%]$") if begin_spec then local begin_from, begin_to = canonicalize_begin_end_spec(begin_spec) local end_from, end_to = canonicalize_begin_end_spec(end_spec) subterm = begin_from .. rest .. end_from dest = begin_to .. rest .. end_to end if not subterm then rest, end_spec = modspec:match("^([^:]*)%[(.-)%]$") if rest then local end_from, end_to = canonicalize_begin_end_spec(end_spec) subterm = rest .. end_from dest = rest .. end_to end end if not subterm then begin_spec, rest = modspec:match("^%[(.-)%]([^:]*)$") if begin_spec then local begin_from, begin_to = canonicalize_begin_end_spec(begin_spec) subterm = begin_from .. rest dest = begin_to .. rest end end if not subterm then subterm, dest = modspec:match("^(.-)%s*:%s*(.*)$") if subterm and subterm ~= "^" and subterm ~= "$" then local langdest -- Parse off an initial language code (e.g. 'en:Higgs', 'la:minūtia' or 'grc:σκατός'). Also handle -- Wikipedia prefixes ('w:Abatemarco' or 'w:it:Colle Val d'Elsa'). otherlang, langdest = dest:match("^([A-Za-z0-9._-]+):([^ ].*)$") if otherlang == "w" then local foreign_wikipedia, foreign_term = langdest:match("^([A-Za-z0-9._-]+):([^ ].*)$") if foreign_wikipedia then otherlang = otherlang .. ":" .. foreign_wikipedia langdest = foreign_term end dest = ("%s:%s"):format(otherlang, langdest) otherlang = nil elseif otherlang then otherlang = get_lang_by_code(otherlang, true, "allow etym") dest = langdest end end end if not subterm then if modspec == "?" or modspec == "!" then subterm = "$" dest = modspec elseif modspec == "..." or modspec == "...?" then subterm = "$" dest = " " .. modspec elseif modspec:find("^[A-Z]$") then -- X, Y, etc. by themselves are unlinked, to help with snowclones subterm = modspec dest = "_" else subterm = modspec dest = "~" end end if subterm == "^" then linked_term = dest:gsub("_", " ") .. linked_term elseif subterm == "$" then linked_term = linked_term .. dest:gsub("_", " ") else if subterm:find("[", nil, true) then error(("Subterm '%s' in modifier spec '%s' cannot have brackets in it"):format( escape_wikicode(subterm), escape_wikicode(modspec))) end local escaped_subterm = pattern_escape(subterm) local subterm_re = "%[%[" .. escaped_subterm:gsub("(%%?[ ',%-])", "%%]*%1%%[*") .. "%]%]" local expanded_dest if dest:find("~", nil, true) then expanded_dest = dest:gsub("~", replacement_escape(subterm)) else expanded_dest = dest end if otherlang then expanded_dest = expanded_dest .. "#" .. otherlang:getCanonicalName() end local subterm_replacement if expanded_dest == "_" then subterm_replacement = subterm if id then error("Can't supply <id:...> with an unlinked subterm") end if otherlang then error("Can't supply prefixed language with an unlinked subterm") end elseif id or otherlang then if id and expanded_dest:find("[", nil, true) then error("Can't supply <id:...> with destination with embedded brackets") end subterm_replacement = require(links_module).language_link { lang = otherlang or lang, term = expanded_dest, alt = subterm, id = id, } elseif expanded_dest:find("[", nil, true) then -- Use the destination directly if it has brackets in it (e.g. to put brackets around parts of a word). subterm_replacement = expanded_dest elseif expanded_dest == subterm then subterm_replacement = "[[" .. subterm .. "]]" else subterm_replacement = "[[" .. expanded_dest .. "|" .. subterm .. "]]" end local escaped_subterm_replacement = replacement_escape(subterm_replacement) local replaced_linked_term = ugsub(linked_term, subterm_re, escaped_subterm_replacement) if replaced_linked_term == linked_term then mw.log(("Attempted to replace %s with %s in %s"):format(subterm_re, escaped_subterm_replacement, linked_term)) error(("Subterm '%s' could not be located in %slinked expression %s, or replacement same as subterm"):format( subterm, j > 1 and "intermediate " or "", escape_wikicode(linked_term))) else linked_term = replaced_linked_term end end end return linked_term end local inflection_to_cats = { plural = { filter_plpos = function(plpos) -- plurals also occur with determiners, adjectives etc. and we don't want to generate categories like -- 'countable determiners', 'countable adjectives', etc. Note that the passed-in `plpos` has `proper nouns` -- converted to `nouns`. return plpos == "nouns" end, cats = {"countable {plpos}"}, no_cats = {"uncountable {plpos}"}, }, comparative = { cats = {"comparable {plpos}"}, no_cats = {"uncomparable {plpos}"}, }, ["female equivalent"] = { cats = {"{plpos} with other-gender equivalents"}, }, ["male equivalent"] = { cats = {"{plpos} with other-gender equivalents"}, }, } --[=[ Validate the items in `items` against the list or set of valid items in `valid_items`. If `field` is given, fetch the item to check from that-named field of each object in `items`; otherwise use the items in `items` directly. If an error occurs, `item_type` specifies the type of item to mention in the error message, which will also list the allowed items (either taken directly from `valid_items` if a list, or from the sorted keys if a set). ]=] local function validate_items(data) local items, field, valid_items, item_type = data.items, data.field, data.valid_items, data.item_type local valid_set if valid_items[1] then valid_set = list_to_set(valid_items) else valid_set = valid_items end for _, item in ipairs(items) do if field then item = item[field] end if not valid_set[item] then local valid_list if valid_items[1] then valid_list = valid_items else valid_list = {} for valid_item, _ in pairs(valid_items) do insert(valid_list, valid_item) end table.sort(valid_list) end error(("Invalid %s: %s; expected one of %s"):format(item_type, item, mw.text.listToText(valid_list))) end end end local Headdata = {} function Headdata:get_canonicalized_plpos() return (self.pos_category:gsub("proper noun", "noun")) end --[==[ Canonicalize a category. The category string will have the full language name (i.e. the name of the L2 language under which an entry is inserted, which may a parent language if the language in question is an etymology-only language) prepended to it, and any occurrences of `{plpos}` in the string replaced with the actual plural part of speech (with some canonicalization; specifically, `proper nouns` is converted to `nouns` when replacing `{plpos}`). To specify a full category and not have the language name prepended to it, precede it with {"Category:"}, which will be removed. ]==] function Headdata:canonicalize_category(category) if category:find("{plpos}") then local plpos = self:get_canonicalized_plpos() category = category:gsub("{plpos}", plpos) end if category:find("^Category:") then return (category:gsub("^Category:", "")) else return self.langfullname .. " " .. cat_word(self.lang, category) end end --[==[ Canonicalize a list of categories according to the process described in `Headdata:canonicalize_category`. This simply loops over each category in `categories` and calls `Headdata:canonicalize_category` on each one. ]==] function Headdata:canonicalize_categories(categories) if not categories then return categories end local canon_cats = {} for _, cat in ipairs(categories) do insert(canon_cats, self:canonicalize_category(cat)) end return canon_cats end --[==[ Insert a category into the `categories` list in the headword `data` structure. `category` is normally a string naming the category, which will have the full language name prepended to it and any occurrences of `{plpos}` in the string replaced with the actual plural part of speech (with some canonicalization; specifically, `proper nouns` is converted to `nouns` when replacing `{plpos}`). To specify a full category and not have the language name prepended to it, precede it with {"Category:"}. ]==] function Headdata:insert_category(category) insert(self.categories, self:canonicalize_category(category)) end --[==[ Validate the genders in `genders` (a list of gender spec objects, as produced by {type = "genders"} in [[Module:parameters]] and accepted by [[Module:gender and number]]), checking that all specified genders are in the list given in `valid_genders`. Optional `props` controls how the validation happens. In particular, unless `props.no_augment` is given, then for any gender beginning with `m`, if a corresponding gender beginning with `f` occurs, analogous genders beginning with `mf`, `mfbysense` and `mfequiv` are also allowed. For example, if `m-d` (masculine dual) and `f-d` (feminine dual) both occur, genders `mf-d`, `mfbysense-d` and `mfequiv-d` are also allowed. If a disallowed gender is given, an error occurs, giving the disallowed gender along with the list of all allowed genders. ]==] function Headdata:validate_genders(genders, valid_genders, props) if not genders then return end props = props or {} local gender_type, no_augment = props.gender_type, props.no_augment gender_type = gender_type or "headword" local valid_gender_set = list_to_set(valid_genders) local augmented_gender_set if no_augment then augmented_gender_set = valid_gender_set else augmented_gender_set = {} for g, _ in pairs(valid_gender_set) do augmented_gender_set[g] = true if g:find("^m") and not g:find("^mf") and valid_gender_set[g:gsub("^m", "f")] then augmented_gender_set[g:gsub("^m", "mf")] = true augmented_gender_set[g:gsub("^m", "mfbysense")] = true augmented_gender_set[g:gsub("^m", "mfequiv")] = true end end end validate_items { items = genders, field = "spec", valid_items = augmented_gender_set, item_type = ("%s gender"):format(gender_type), } end --[==[ Parse an inflection specified in `field`, the name of a parameter holding an inflection. If the parameter is numeric, the field should be given as a number (as with the `params` structure passed to [[Module:parameters]]), not a string containing the representation of a number. The field can specify multiple comma-separated terms, and each term can have associated inline modifiers that will be parsed (unless there is top-level HTML in the parameter, i.e. HTML not contained inside an inline modifier, e.g. as may be generated by using {{tl|l}} or similar template inside a parameter). This is a wrapper around the top-level `parse_term_with_modifiers()` function. `props` is an optional structure containing additional properties, including all additional properties documented for the top-level `parse_term_with_modifiers()` function. If the parameter in `field` is unspecified, the return value of this function will be an empty list, not {nil}, so it is always safe to iterate over the return value. By default, the allowed modifiers are the same as for `parse_term_with_modifiers()`, except that (normally) the `<tr:...>` modifier will be allowed if `include_tr` was specified in the original call to `process_headword()`; likewise for the `<ts:...>` modifier if `include_ts` was specified and the `<sc:...>` modifier if `include_sc` was specified. If If you pass in your own `include_mods` list of additional allowed modifiers, it will (normally) automatically be augmented with {"tr"}, {"ts"} and/or {"sc"} if `include_tr`, `include_ts` and/or `include_sc` was specified when calling `process_headword()`. To disable automatic augmentation of these modifiers (whether or not you specify an `include_mods` property), specify {no_augment_include_mods = true} in `props`. ]==] function Headdata:parse_inflection(field, props) local val = self.process_props.args[field] if not val then return {} end props = props and shallow_copy(props) or {} local include_mods = props.include_mods local data = self.process_props.data if not props.no_augment_include_mods and (data.include_tr or data.include_ts or data.include_sc) then include_mods = include_mods and shallow_copy(include_mods) or {} if data.include_tr then insert_if_not(include_mods, "tr") end if data.include_ts then insert_if_not(include_mods, "ts") end if data.include_sc then insert_if_not(include_mods, "sc") end end props.val = val props.paramname = field props.splitchar = props.splitchar or "," props.include_mods = include_mods return export.parse_term_with_modifiers(props) or {} end --[==[ Insert previously-parsed terms into the `inflections` of the headword `data` structure. This is a wrapper around the top-level `insert_inflection()` function. `terms` is the list of parsed terms. (If {nil}, nothing happens unless `request` is set in `props`.) `label` is the the label that the inflections are given; any parts of the label surrounded in `<<...>>` are linked to the glossary. (If the contents of `<<...>>` contain a `|` in them, they are a two-part link.) `props` is an optional structure containing additional properties, including all additional properties documented for the top-level `insert_inflection()` function. Unless `no_auto_cats` is given in `props`, certain labels automatically trigger the insertion of additional categories in specific circumstances. This is controlled by the `inflection_to_cats` structure in [[Module:headword utilities]]. For example, if the part of speech is {"nouns"} or {"proper nouns"} and the label (after removing any links and `<<...>>` glossary specs) is {"plural"}, an additional category <code><var>lang</var> countable nouns</code> will be added if a plural value is given (i.e. the value is not {"-"}). If the value is {"-"} (which indicates that there is no plural and triggers the insertion of the fixed inflection label {"no plural"}), <code><var>lang</var> uncountable nouns</code> will be inserted instead, and if both {"-"} and a value are given (which triggers the insertion of the {"usually no plural"} fixed inflection label), both categories are added. Similar categories are inserted when a comparative is given (with a label {"comparative"}), and if the label is {"female equivalent"} or {"male equivalent"} and the value is not {"-"}, a category such as <code><var>lang</var> nouns with other-gender equivalents</code> is inserted. ]==] function Headdata:insert_inflection(terms, label, props) props = props and shallow_copy(props) or {} if not props.no_auto_cats then local bare_label = label if bare_label:find("[[", nil, true) then bare_label = require(links_module).remove_links(bare_label) end if bare_label:find("<<", nil, true) then bare_label = bare_label:gsub("<<.-|(.-)>>", "%1"):gsub("<<(.-)>>", "%1") end local cats = inflection_to_cats[bare_label] if cats then if not cats.filter_plpos or cats.filter_plpos(self:get_canonicalized_plpos()) then if props.cats == nil then props.cats = self:canonicalize_categories(cats.cats) end if props.usually_no_cats == nil then props.usually_no_cats = self:canonicalize_categories(cats.usually_no_cats) end if props.no_cats == nil then props.no_cats = self:canonicalize_categories(cats.no_cats) end end end end props.headdata = self props.terms = terms props.label = label return export.insert_inflection(props) end --[==[ Insert a "fixed" inflection (a label without associated values) into the `inflections` table of the headword `data` structure, labeled according to `label` (which can have glossary links in it specified using `<<...>>`, exactly as for `:insert_inflection()`). An example label (from {{tl|mn-noun}} in [[Module:mn-headword]]) is {"hidden-g declension"}, specifying that the noun belongs to the hidden-''g'' declension. This is a direct wrapper around the top-level function `insert_fixed_inflection()`; see that function for more details on optional `props`. ]==] function Headdata:insert_fixed_inflection(label, props) props = props and shallow_copy(props) or {} props.headdata = self props.label = label export.insert_fixed_inflection(props) end --[==[ Parse the inflection(s) specified in `field` and insert them into the `inflections` table of the headword `data` structure, labeled according to `label`. This is equivalent to calling {terms = data:parse_inflection(field, props)} followed by {return data:insert_inflection(terms, label, props)} and behaves the same as the combination of those two functions. See their documentation for more details. ]==] function Headdata:parse_and_insert_inflection(field, label, props) local terms = self:parse_inflection(field, props) return self:insert_inflection(terms, label, props) end --[==[ Generate an inflection that may be specified explicitly or defaulted (which involves looping over the specified or defaulted heads and determining the script of each one, since the formation of the default depends on the script). `data` is the data object passed into the POS handler. `terms` is the list of terms to process. Those where the term itself is not `+` will be returned unchanged, while those where the term is `+` will be handled by generating the appropriate inflections from the headwords using `make_inflection` (which is passed three arguments, `head`, `tr` and `sccode`, i.e. the script code of `head`) and should return two values, term and translit, either of which can be nil. A nil head will be ignored, and otherwise the decorations specified on the `+` term will be combined with the decorations specified on the head. The return value is a list of inflections where no requests for the default inflection remain. ]==] function Headdata:resolve_special(terms, handle_special, props) props = props or {} local infls = {} local is_special = props.is_special or function(_data, infl) return infl.term == "+" end for _, termobj in ipairs(terms) do if not is_special(self, termobj) then insert(infls, termobj) else for _, headobj in ipairs(self.heads) do local head = headobj.term or self.pagename local head_no_links if props.with_links then head = head:find("%[") and head or require(headword_module).add_multiword_links(head, not headobj.term) head_no_links = require(links_module).remove_links(head) else head = require(links_module).remove_links(head) head_no_links = head end local newterms = handle_special { head = head, tr = headobj.tr, infl = termobj, sc = self.lang:findBestScript(head_no_links), } if newterms then newterms = export.canonicalize_termobj_list(newterms, "term", "resolve_special") for _, newterm in ipairs(newterms) do if not props.no_combine_handle_special_retval_with_origin then export.combine_termobj_decorations(newterm, termobj) end if not props.no_combine_handle_special_retval_with_head then export.combine_termobj_decorations(newterm, headobj) end insert(infls, newterm) end end end end end return infls end --[==[ Add the current page to a tracking page named `Wiktionary:Tracking/``lang``-headword/``page```, where ``lang`` is the language code of the current language. For example, if the current language is `mak` and `page` is {"redundant-lon"}, the current page will get added to the tracking page `Wiktionary:Tracking/mak-headword/redundant-lon`. All pages added to that tracking page can be seen by going to [[Special:WhatLinksHere/Wiktionary:Tracking/mak-headword/redundant-lon]]. This is typically used to track issues occurring in user-specified parameters that do not rise to the level of errors (e.g. redundant parameters, deprecated usages or other dispreferred values). ]==] function Headdata:track(page) return require(debug_track_module)(self.langcode .. "-headword/" .. page) end local boolean_param = {type = "boolean"} --[==[ Process an arbitrary headword in an arbitrary language, handling generic and language-specific arguments and calling `full_headword()` in [[Module:headword]]. This is intended for use in implementing headword modules (e.g. [[Module:uz-headword]] for Uzbek, [[Module:mn-headword]] for Uzbek, [[Module:gsw-headword]] for Alemannic German, etc.) and provides a general implementation of such modules. On input, `data` is an object with the following fields: * `lang`: The language object of the language being handled. '''Required.''' Use the special value {false} to indicate that the language is specified by the user in {{para|1}}. * `frame`: The frame object passed into the `show()` function of your module, which implements headword-handling for all parts of speech in the module, including a generic POS-handling template (e.g. {{tl|uz-head}} or {{tl|mn-head}}), which allows arbitrary parts of speech to be handled. '''Required.''' * `pos_functions`: A table listing, for each part of speech requiring special handling, the extra parameters (if any) that the part of speech accepts, along with how to handle them. See the examples below. '''Required.''' * `validate_lang`: If {lang = true} is specified, this is a function of one argument (a language object, based on the language specified in {{para|1}}) that should throw an error if the language object is disallowed. If omitted, all languages are allowed. * `numbered_head`: If true, explicit headwords are specified in a numbered param instead of in {{para|head}}. The param used is usually {{para|1}}, but is {{para|2}} for generic POS templates such as {{tl|mn-head}} or for POS-specific templates when {lang = true} is specified (e.g. {{tl|arb-noun}}), and is {{para|3}} for generic POS templates when {lang = true} is spcified (e.g. {{tl|arb-head}}). * `include_tr`: If true, allow explicit transliterations to be specified. The transliteration(s) for the headword(s) themselves is/are specified in {{para|tr}} or through the {{cd|<tr:...>}} inline modifier on headwords, and transliterations of inflections are specified through the {{cd|<tr:...>}} inline modifier. This should generally be given when a headword for the language may be in a script other than Latin. * `include_ts`: If true, allow explicit transcriptions to be specified. The transcription(s) for the headword(s) themselves is/are specified in {{para|ts}} or through the {{cd|<ts:...>}} inline modifier on headwords, and transcriptions of inflections are specified through the {{cd|<ts:...>}} inline modifier. This should generally only be given for certain languages where the spelling is radically different from the pronunciation (e.g. in cuneiform languages such as Hittite and Akkadian, and potentially in Tibetan), and represents a pronunciation-based rendering (usually not direct IPA). * `include_sc`: If true, allow an explicit script code to be specified. The overall script code for the headword(s) themselves can be specified using {{para|sc}}, and per-headword or per-inflection script codes are specified using the {{cd|<sc:...>}} inline modifier. This should generally be given when a language supports multiple scripts. * `infls`: An inflections structure specifying extra generic parameters that apply to all parts of speech and how to handle them. The format is the same as for the `infls` structure in `pos_functions`. * `augment_params`: A callback function to add extra generic parameters, or modify existing generic parameters in the `params` structure; but in general, extra generic parameters should be added through the `infls` structure instead. This callback should not be used to add part-of-speech-specific parameters; those are handled through the appropriate setting in `pos_functions`. It is passed two single arguments, the `headdata` object and the `params` table to be augmented. See below for extra fields stored in the `process_props` structure of the `headdata` object. This function is called after initializing the `params` table and processing the overall `infls` structure, but just before adding part-of-speech-specific parameters (from `pos_functions`) to `params`. Thus, it can override any generic parameters but may itself be overridden by a part-of-speech-specific parameter. * `augment_headdata`: A callback function to modify the `headdata` object passed to `full_headword()` in [[Module:headword]]. This should not be used to for part-of-speech-specific parameter handling; this is handled through the appropriate setting in `pos_functions`. It is passed a single argument, the `headdata` object, as for `augment_params`; but the `process_props` structure and other fields will be more filled out, as this callback is called later. This can be used, for example, to override the value of a generic setting in `headdata` (e.g. [[Module:uz-headword]] uses this to mark non-Latin terms as variant forms by setting `headdata.var`, being careful not to override a value already set by the user). This function is called after initializing the `headdata` table with all information taken from generic parameters and processing generic parameters specified in the overall `infls` structure, and just before processing the appropriate part-of-speech-specific `infls` structure in `pos_functions` (which in turn is followed by any handler function in `pos_functions`). Thus, it can override any value set during generic parameter processing but may itself be overridden by a part-of-speech-specific parameter or handler. * `force_cat`: If true, add the headword to the appropriate categories even on non-mainspace pages. This can be used for testing category handling in sample template calls on userspace test pages or template documentation pages. It should not be set in production code. * `enable_auto_translit`: If true, turn on automatic transliteration of inflections at a global level (i.e. applying to all inflections). This has no effect on headwords, which are automatically transliterated by default if in a non-Latin script and automatic transliteration is available for the language. You can also set this value for particular inflections in the `insert_inflection()` function. The `headdata` headword data structure has an extra field in it called `process_props` that is specific to the `process_headword()` function, containing various extra properies. As the operation of `process_headword()` proceeds, this object gets filled out with more fields. For example, once parameter parsing happens, the resulting values are available in the `args` field of `process_props`. The following fields are found in `process_props` (note that `poscat`, the canonicalized plural part of speech of the headword being processed, is *not* present here; it's directly on `headdata`): * `namespace`: The name of the current namespace; an empty string for the mainspace. This references the namespace of the actual page and isn't affected by the {{para|pagename}} parameter. * `indexing_poscat`: The canonicalized part of speech of the headword used to index into `pos_functions`. This is the same as `poscat` for specific part-of-speech templates such as {{tl|uz-noun}}, but has the value {"head"} for generic part-of-speech templates such as {{tl|uz-head}}. (Note that `poscat` is directly available on `headdata`.) * `generic_pos_template`: True if a generic POS templates like {{tl|uz-head}} or {{tl|mn-head}} was used. (This is signaled by omitting the invocation parameter {{para|1}} to `process_headword`.) * `lang_in_1`: True if the language code is to be fetched from {{para|1}}. * `pos_param`: The parameter holding the part of speech, if a generic POS tempalte like {{tl|mn-head}} is being processed (i.e. `generic_pos_template` is set). In such a case, it will have the value of {1} or {2}, depending on whether the language code is being fetched from {{para|1}} (see `lang_in_1`). Otherwise it will be {nil}. * `head_param`: The parameter holding the explicit headword. If `numbered_head` was specified (as for Mongolian headword templates), this has the value {1}, {2} or {3} depending on whether the language code is being fetched from {{para|1}} (see `lang_in_1`) and whether a generic POS template like {{tl|mn-head}} is being processed (see `generic_pos_template`). Otherwise, it has the value {"head"}. Also see the `lang` and `numbered_head` properties in the `data` structure sent to `process_headword()`. * `is_suffix`: True if the current term is a suffix. This is set when processing the `suffix`, `nosuffix` and `clitic` parameters; it is always {false} beforehand (i.e. during `augment_params` and processing of the general `infls` structure). * `insert_specs`: This is a table mapping parameter names to the return value of `Headdata:insert_inflection()`, filled out as parameter values are processed. This lets a given parameter processing function in `infls` gain access to the result of calling `insert_inflection()` on previous parameters (which indicates the number of items inserted as well as whether `-` was specified). The `pos_functions` table contains an entry for each part of speech needing special handling, where the key is the canonical plural part of speech (e.g. {"adverbs"} or {"proper nouns"}). The value associated with each key is a table normally containing a field `infls`, listing the extra part-of-speech-specific inflection and other parameters along with how to handle them. The specs in `infls` are used in three ways: # to augment the `params` object passed to the `process()` function in [[Module:parameters]], specifying how to parse the appropriate inflectional parameters; # to specify how to process any inflectional parameters given and insert them into the `headdata` object passed to `full_headword()` in [[Module:headword]]; # to generate appropriate documentation for the parameters and other changes made by the headword template (e.g. inserting categories). Alternatively, you can separately control the augmentation of the `params` object and the procesing of the resulting arguments. This is done by specifying two fields in place of `infls`, named `params` and `func`. `params` is a table containing extra parameters to add to the overall `params` object passed to the `process()` function in [[Module:parameters]]. `func` is a function of two arguments, normally called `data` (the headword data structure `headdata`) and `args` (the processed arguments table). However, this alternative method is not normally recommended because it leads to duplication between the `params and `func` fields and the documentation, which must be manually specified. A simple example, as used to handle pronouns for Turoyo, is { local valid_genders = {"m", "f", "m-p", "f-p", "p", "?"} pos_functions["pronouns"] = { infls = { {2, type = "genders", validate = valid_genders}, {"f", label = "feminine"}, {"pl", label = "plural"}, }, } } The equivalent using `params` and `func` is { local valid_genders = {"m", "f", "m-p", "f-p", "p", "?"} pos_functions["pronouns"] = { params = { [2] = {type = "genders"}, f = true, pl = true, }, func = function(data, args) data:validate_genders(args[2], valid_genders) data.genders = args[2] data:parse_and_insert_inflection("f", "feminine") data:parse_and_insert_inflection("pl", "plural") end } } Note how the version with separate `params and `func` is longer and splits information on the parameters between the two fields. The `params` structure sets extra user-specifiable parameters {{para|2}} for genders (since the headword is in {{para|1}}) as well a {{para|f}} and {{para|pl}}, and the `func` handler processes those parameters. Note how this is done by calling methods on the headword `data` structure. Each such parameter can have multiple comma-separated values, and each value can have inline modifiers attached to it to specify further properties of the value. The `infls` version ends up making the same method calls, but does it for you instead of you having to do it yourself. These methods are implemented through a metatable set on the headword `data` structure, which is removed before calling `full_headword()` in [[Module:headword]]. The methods access extra information related to headword processing (such as the `args` table) that is stored in the `process_props` field of the headword `data` strucuture. This field is also removed prior to calling `full_headword()`. The methods available on the headword `data` structure are as follows. Each one also has its own documentation. * {parse_inflection(field, props)}: Parse value(s) specified in `field` (a user-specified parameter in the `args` table) and return a list of term objects. Optional `props` specifies additional properties controlling the parsing. * {insert_inflection(terms, label, props)}: Insert the terms in `terms` (a list of term objects as returned by `parse_inflection()`) into the `inflections` list in the headword `data` structure, giving the inflection the label as specified in `label`. Optional `props` specifies additional properties controlling the parsing. * {parse_and_insert_inflection(field, label, props)}: A combination of `parse_inflection()` and `insert_inflection()`, if no further processing of the parsed values needs to be done before insertion. * {insert_fixed_inflection(label, props)}: Insert a "fixed" inflection (a label without associated values) into the `inflections` table. An example (from {{tl|mn-noun}} in [[Module:mn-headword]]) is {"hidden-g declension"}, specifying that the noun belongs to the hidden-''g'' declension. * {resolve_special(terms, handle_special, props)}: Resolve "special" indicators as specified by the user in an inflection parameter. A typical example is {"+"}, requesting a default value. `terms` is the list of parsed term objects and `handle_special` is a handler function to process special indicators and convert them to their actual values. * {validate_genders(genders, valid_genders, props)}: Validate that the user-specified genders in `genders` all belong to the list given in `valid_genders`, throwing an error if not. * {insert_category(category)}: Insert a category into the `categories` list in the headword `data` structure. `category` is normally a string naming the category, which will have the language prepended to it and any occurrences of `{plpos}` in the string replaced with the actual plural part of speech. ]==] function export.process_headword(data) local lang, frame, pos_functions, validate_lang, numbered_head, include_tr, include_ts, include_sc, force_cat, enable_auto_translit, infls, augment_params, augment_headdata = data.lang, data.frame, data.pos_functions, data.validate_lang, data.numbered_head, data.include_tr, data.include_ts, data.include_sc, data.force_cat, data.enable_auto_translit, data.infls, data.augment_params, data.augment_headdata local iparams = { [1] = true, def = true, } local iargs = require(parameters_module).process(frame.args, iparams) local parargs = frame:getParent().args local langcode if not lang then error("Internal error: `data.lang` must be specified; either a language object or `true` for a user-specified language") end local lang_in_1 if lang == true then lang_in_1 = true langcode = ine(parargs[1]) if langcode then langcode = mw.text.trim(langcode) lang = require(languages_module).getByCode(langcode, 1, true) if validate_lang then validate_lang(lang) end else error("Language code (see [[WT:Language codes]]) must be specified in 1=") end else langcode = lang:getCode() if validate_lang then error("Internal error: `data.validate_lang` must not be specified if a language code is given in `data.lang`") end end local poscat = iargs[1] local generic_pos_template = not poscat local pos_param if generic_pos_template then pos_param = lang_in_1 and 2 or 1 poscat = ine(parargs[pos_param]) or mw.title.getCurrentTitle().fullText == ("Template:%s-head"):format(langcode) and "interjection" or error(("Part of speech must be specified in %s="):format(pos_param)) poscat = require(headword_module).canonicalize_pos(poscat) end local head_param = numbered_head and (generic_pos_template and lang_in_1 and 3 or (generic_pos_template or lang_in_1) and 2 or 1) or "head" local indexing_poscat = generic_pos_template and "head" or poscat local namespace = mw.loadData(headword_data_module).page.namespace -- Partly initialize headdata now for use in generic infls callbacks. Will be further initialized later after -- processing parameters. local headdata = { lang = lang, langcode = langcode, langfullcode = lang:getFullCode(), langname = lang:getCanonicalName(), langfullname = lang:getFullName(), process_props = { namespace = namespace, data = data, indexing_poscat = indexing_poscat, generic_pos_template = generic_pos_template, lang_in_1 = lang_in_1, pos_param = pos_param, head_param = head_param, is_suffix = false, insert_specs = {}, }, pos_category = poscat, orig_poscat = poscat, -- preserve user-specified poscat in case pos_category is changed to 'suffixes' categories = {}, inflections = {enable_auto_translit = enable_auto_translit}, force_cat_output = force_cat, no_redundant_head_cat = true, } setmetatable(headdata, {__index = Headdata}) local params = { [head_param] = {template_default = iargs.def}, head2 = {replaced_by = false, instead = ("use comma-separated |%s="):format(head_param)}, id = true, sort = true, cat = true, nolink = boolean_param, nolinkhead = {type = "boolean", alias_of = "nolink"}, suffix = boolean_param, nosuffix = boolean_param, clitic = true, addlpos = true, var = {type = "boolean", allow = {"both"}}, json = boolean_param, pagename = true, -- for testing } if include_sc then params.sc = {type = "script"} end if include_tr then params.tr = true params.tr2 = {replaced_by = false, instead = "use comma-separated |tr= or <tr:...> inline modifier on head"} end if include_ts then params.ts = true params.ts2 = {replaced_by = false, instead = "use comma-separated |ts= or <ts:...> inline modifier on head"} end if lang_in_1 then params[1] = {required = true} -- required but ignored as already processed above end if generic_pos_template then params[pos_param] = {required = true} -- required but ignored as already processed above end local function resolve_prop(prop, ...) if type(prop) == "function" then prop = prop(headdata, ...) end return prop end local function augment_params_from_infls(infls) infls = resolve_prop(infls) for _, infl in ipairs(infls) do local function interr(txt) error(("Internal error: %s (coming from infls spec %s)"):format(txt, dump(infl))) end local param = infl[1] if param then param = resolve_prop(param) if type(param) ~= "string" and type(param) ~= "number" then interr(("Parameter name %s must be a string or number"):format(dump(param))) end -- We handle defaults as well as validation ourselves. local typ = resolve_prop(infl.type) or "string" if typ ~= "genders" and typ ~= "boolean" and typ ~= "string" then -- FIXME: Handle more types. interr(('Unrecognized type %s; can only currently handle "genders", "boolean" and "string" (the default)'):format( dump(typ))) end params[param] = {type = typ, required = resolve_prop(infl.required), template_default = resolve_prop(infl.template_default)} if typ ~= "boolean" and type(param) == "string" then params[param .. "2"] = {replaced_by = false, instead = ("use comma-separated |%s="):format(param)} end end end end if infls then augment_params_from_infls(infls) end if augment_params then augment_params(headdata, params) end if pos_functions[indexing_poscat] then local pos_infls = pos_functions[indexing_poscat].infls if pos_infls then augment_params_from_infls(pos_infls) end local pos_params = pos_functions[indexing_poscat].params if pos_params then for key, val in pairs(pos_params) do params[key] = val end end end local args = require("Module:parameters").process(parargs, params) local pagename = args.pagename or mw.loadData(headword_data_module).pagename local sc = args.sc or lang:findBestScript(pagename) headdata.pagename = pagename headdata.process_props.args = args headdata.sc = sc headdata.id = args.id headdata.sort = args.sort -- No redundant script cat unless the user explicitly gave sc= headdata.no_script_code_cat = not args.sc headdata.var = args.var local extra_term_mods = {} if include_tr then insert(extra_term_mods, "tr") end if include_ts then insert(extra_term_mods, "ts") end if include_sc then insert(extra_term_mods, "sc") end if not extra_term_mods[1] then extra_term_mods = nil end local trs = args.tr and split_on_comma(args.tr) or {} local num_trs = #trs local tss = args.ts and split_on_comma(args.ts) or {} local num_tss = #tss local heads = args[head_param] and export.parse_term_with_modifiers { val = args[head_param], paramname = head_param, splitchar = ",", is_head = true, include_mods = extra_term_mods, } or {} local num_heads = #heads if num_heads > 0 and num_trs > 0 and num_heads ~= num_trs then error(("%s head%s specified explicitly but %s translit%s; they must match; use '+' to stand for the default head (the pagename) or default automatic translit and '-' to stand for no translit"):format( num_heads, num_heads > 1 and "s" or "", num_trs, num_trs > 1 and "s" or "")) end if num_heads > 0 and num_tss > 0 and num_heads ~= num_tss then error(("%s head%s specified explicitly but %s transcription%s; they must match; use '+' to stand for the default head (the pagename) and '-' to stand for no transcription"):format( num_heads, num_heads > 1 and "s" or "", num_tss, num_tss > 1 and "s" or "")) end if num_trs > 0 and num_tss > 0 and num_trs ~= num_tss then error(("%s translit%s specified explicitly but %s transcription%s; they must match; use '+' to stand for default automatic translit and '-' to stand for no translit or transcription"):format( num_trs, num_trs > 1 and "s" or "", num_tss, num_tss > 1 and "s" or "")) end -- Be careful here not to overwrite user_specified_heads if it's empty so we can later check user_specified_heads -- to see if the user provided any heads. local max_tr_ts = math.max(num_trs, num_tss) if num_heads == 0 and max_tr_ts > 0 then heads = {} for i = 1, max_tr_ts do heads[i] = {term = "+"} end end if not heads[1] then heads = {{term = "+"}} end for i, headobj in ipairs(heads) do if headobj.tr and trs[i] then if headobj.tr ~= trs[i] then error(("Saw two different translits '%s' and '%s' for head #%s"):format( headobj.tr, trs[i], i)) end else headobj.tr = headobj.tr or trs[i] end if headobj.tr == "+" then headobj.tr = nil end if headobj.ts and tss[i] then if headobj.ts ~= tss[i] then error(("Saw two different transcriptions '%s' and '%s' for head #%s"):format( headobj.ts, tss[i], i)) end else headobj.ts = headobj.ts or tss[i] end if headobj.ts == "-" then headobj.ts = nil end if headobj.term == "+" then headobj.term = args.nolink and pagename or nil if headobj.term and namespace == "Reconstruction" then headobj.term = "*" .. headobj.term end end end headdata.heads = heads local function pagename_is_suffix() if sc:getCode() == "Latn" then -- shortcut Latin terms to avoid unnecessarily loading [[Module:affix]] return pagename:find("^%-") and not pagename:find("%-$") else local affix_type, _, _, _ = require(affix_module).parse_term_for_affixes(pagename, lang, sc) return affix_type == "suffix" end end local clitic_label if args.clitic then clitic_label = require(yesno_module)(args.clitic, args.clitic) end if clitic_label == true then clitic_label = "clitic" end if clitic_label then headdata:insert_category("clitics") headdata:insert_fixed_inflection(clitic_label) elseif args.suffix or ( not args.nosuffix and pagename_is_suffix() and poscat ~= "suffixes" and poscat ~= "suffix forms" ) then headdata.process_props.is_suffix = true local function handle_suffix_pos(pos, is_first) local form_type = pos:match("^(.*) forms$") local actual_poscat if form_type then headdata:insert_category(("%s suffix forms"):format(form_type)) headdata:insert_fixed_inflection(form_type .. " suffix form") else local singular_pos = require(en_utilities_module).singularize(pos) headdata:insert_category(("%s-forming suffixes"):format(singular_pos)) headdata:insert_fixed_inflection(singular_pos .. "-forming suffix") end local postype = require(headword_module).pos_lemma_or_nonlemma(pos) if not postype then error(("Unrecognized canonicalized part of speech '%s' in addlpos=, cannot determine whether lemma or non-lemma form"):format( pos )) end actual_poscat = postype == "lemma" and "suffixes" or "suffix forms" if is_first then headdata.pos_category = actual_poscat elseif headdata.pos_category ~= actual_poscat then error(("Cannot mix suffixes and suffix forms using addlpos=; '%s' is a %s while overall POS '%s' is a %s; use separate POS headers for the two"): format(pos, actual_poscat, poscat, headdata.pos_category)) end end handle_suffix_pos(poscat, true) if args.addlpos then for _, addlpos in ipairs(split(args.addlpos, "%s*,%s*")) do addlpos = require(headword_module).canonicalize_pos(addlpos) handle_suffix_pos(addlpos, false) end end end if args.cat then for _, cat in ipairs(split_on_comma(args.cat)) do headdata:insert_category(cat) end end local function augment_headdata_from_infls(infls) infls = resolve_prop(infls) for _, infl in ipairs(infls) do local function interr(txt) error(("Internal error: %s (coming from infls spec %s)"):format(txt, dump(infl))) end local function process_labelobjs(labelobjs, originating_term, handle_labelobj) if labelobjs == nil then return end if type(labelobjs) ~= "string" and type(labelobjs) ~= "table" then interr(("Wrong type '%s' for label object(s) %s, expected string or table"):format( type(labelobjs), dump(labelobjs) )) end if type(labelobjs) == "string" or type(labelobjs) == "table" and not labelobjs[1] then labelobjs = {labelobjs} end for _, labelobj in ipairs(labelobjs) do local label, termobj if type(labelobj) == "string" then label = labelobj termobj = originating_term elseif type(labelobj) ~= "table" then interr(("Wrong type '%s' for label object %s, expected string or table"):format( type(labelobj), dump(labelobj) )) label = labelobj.term if type(label) ~= "string" then interr(("Wrong type '%s' for label %s from label object %s, expected string"):format( type(label), dump(label), dump(labelobj) )) end termobj = labelobj end handle_labelobj(label, termobj) end end local param = infl[1] if param then local vals -- Fetch the param and make sure it's a string or number. param = resolve_prop(param) if type(param) ~= "string" and type(param) ~= "number" then interr(("Parameter name %s must be a string or number"):format(dump(param))) end -- Fetch the type and validate. local typ = resolve_prop(infl.type) if typ == nil then typ = "string" end if typ ~= "genders" and typ ~= "boolean" and typ ~= "string" then -- FIXME: Handle more types. interr(('Unrecognized type %s; can only currently handle "genders", "boolean" and "string" (the default)'):format( dump(typ))) end -- Fetch the value(s). if typ == "genders" or typ == "boolean" then vals = args[param] elseif typ == "string" then local parse_inflection_props = resolve_prop(infl.parse_inflection_props) local include_mods = resolve_prop(infl.include_mods) local no_augment_include_mods = resolve_prop(infl.no_augment_include_mods) if include_mods ~= nil or no_augment_include_mods ~= nil then if parse_inflection_props == nil then parse_inflection_props = {} else parse_inflection_props = shallow_copy(parse_inflection_props) end if include_mods ~= nil then parse_inflection_props.include_mods = include_mods end if no_augment_include_mods ~= nil then parse_inflection_props.no_augment_include_mods = no_augment_include_mods end end vals = headdata:parse_inflection(param, parse_inflection_props) -- Convert an empty list to nil for consistent checking below. if not vals[1] then vals = nil end else interr(("Unrecognized type '%s"):format(typ)) end -- If value(s) nil, fetch the default. if vals == nil and infl.default ~= nil then local default = resolve_prop(infl.default) if typ == "genders" then vals = export.canonicalize_termobj_list(default, "spec", "default") elseif typ == "boolean" then vals = default elseif typ == "string" then vals = export.canonicalize_termobj_list(default, "term", "default") else interr(("Unrecognized type '%s"):format(typ)) end end -- Resolve "special" values (special signals a string values, such as requesting the default with "+"). if vals ~= nil and infl.resolve_special then if typ ~= "string" then interr(("Cannot specify resolve_special= for type %s"):format(dump(typ))) end local resolve_special_props = resolve_prop(infl.resolve_special_props, vals) if infl.is_special ~= nil then if resolve_special_props == nil then resolve_special_props = {} else resolve_special_props = shallow_copy(resolve_special_props) end resolve_special_props.is_special = infl.is_special end vals = headdata:resolve_special(vals, infl.resolve_special, resolve_special_props) end -- Validate the value(s). if vals ~= nil and infl.validate ~= nil then if typ == "boolean" then interr('Cannot specify validate= when type is "boolean"') elseif type(infl.validate) == "function" then infl.validate(headdata, vals) elseif typ == "genders" then headdata:validate_genders(vals, infl.validate) elseif typ == "string" then validate_items { items = vals, field = "term", valid_items = infl.validate, item_type = ("values in |%s="):format(param), } else interr(("Unrecognized type '%s"):format(typ)) end end -- Run the process_after_parse handler, if it exists. if vals ~= nil and infl.process_after_parse ~= nil then local intentionally_nil vals, intentionally_nil = infl.process_after_parse(headdata, vals) if vals == nil and not intentionally_nil then interr("If you return nil from process_after_parse, you must return a second non-nil return " .. "value to indicate that the nil return value was intentional") end end -- "Implement" the values, if non-falsy (i.e. we don't want to fire on boolean false or empty list). -- If a fixed label is specified, insert it. Then, depending on the type, attach the values to a label -- as an inflection, set the `genders` field, or do nothing if boolean (throwing an error if there was -- no fixed label). if vals == true or type(vals) == "table" and vals[1] then if infl.fixed_label and infl.all_fixed_label then interr("Cannot specify both fixed_label= and all_fixed_label=; specify one or the other") end local function check_fixed_label_references_val(label) if type(label) == "table" and label[1] then for _, lab in ipairs(label) do if check_fixed_label_references_val(lab) then return true end end return false end if type(label) == "table" then if not label.term then interr(("Fixed label structure %s does not have a value for `.term`"):format(dump(label))) end label = label.term end if type(label) ~= "string" then interr(("Wrong type for fixed label %s, should be string"):format(type(label))) end return not not label:find("{val}") end local fixed_label = infl.fixed_label local all_fixed_label = infl.all_fixed_label -- If the value being processed is boolean, there's only one value so treat a fixed_label as an -- all_fixed_label and output only once; likewise if the caller specified a fixed_label without -- {val} in it. if fixed_label and (typ == "boolean" or type(fixed_label) ~= "function" and not check_fixed_label_references_val(fixed_label)) then all_fixed_label = fixed_label fixed_label = nil end local inserted_fixed_label if fixed_label then if typ == "boolean" then interr("Boolean fixed_label values should have been converted to all_fixed_label") end for _, valobj in ipairs(vals) do local labelobjs = resolve_prop(fixed_label, valobj) process_labelobjs(labelobjs, valobj, function(label, termobj) if label:find("{val}") then if typ ~= "string" then interr(('Cannot specify {val} in fixed_label %s when type is "%s"'):format(dump(label), typ)) end label = label:gsub("{val}", replacement_escape(valobj.term)) end headdata:insert_fixed_inflection(label, { originating_term = termobj }) inserted_fixed_label = true end) end elseif all_fixed_label then local labelobjs = resolve_prop(all_fixed_label, vals) process_labelobjs(labelobjs, nil, function(label, termobj) if label:find("{vals}") then if typ ~= "string" then interr(('Cannot specify {vals} in all_fixed_label %s when type is "%s"'):format(dump(label), typ)) end local formatted_labels = {} for _, valobj in ipairs(vals) do insert(formatted_labels, add_decorations(valobj.term, valobj, lang)) end label = label:gsub("{vals}", replacement_escape(serial_comma_join(formatted_labels))) end headdata:insert_fixed_inflection(label, termobj) inserted_fixed_label = true end) end local inserted_vals if infl.label ~= nil then if typ ~= "string" then interr(("label=%s can only be specified for type 'string', not '%s'"):format( dump(infl.label), typ )) end local label = resolve_prop(infl.label, vals) if label ~= nil then local insert_inflection_props = resolve_prop(infl.insert_inflection_props, vals) local no_auto_cats = resolve_prop(infl.no_auto_cats, vals) if no_auto_cats ~= nil then if insert_inflection_props == nil then insert_inflection_props = {} else insert_inflection_props = shallow_copy(insert_inflection_props) end insert_inflection_props.no_auto_cats = infl.no_auto_cats end local insert_spec = headdata:insert_inflection(vals, label, insert_inflection_props) headdata.process_props.insert_specs[param] = insert_spec inserted_vals = true end end if typ == "genders" then headdata.genders = vals end local inserted_cat if infl.cat then local allcats = {} for _, valobj in ipairs(vals) do local cats = resolve_prop(infl.cat, valobj) if type(cats) == "string" then cats = {cats} end if cats ~= nil then for _, cat in ipairs(cats) do if cat:find("{val}") then cat = cat:gsub("{val}", replacement_escape(valobj.term)) end insert_if_not(allcats, cat) end end end for _, cat in ipairs(allcats) do headdata:insert_category(cat) inserted_cat = true end end if typ == "boolean" then if not inserted_fixed_label and not inserted_cat then interr(("User set boolean setting for %s= but no fixed label added and no category " .. "inserted; if you took action in process_after_parse(), make sure to return " .. "`nil, true`"):format(param)) end elseif typ == "string" then if not inserted_vals and not inserted_fixed_label then interr(("User set value(s) %s for %s= but no inflection inserted and no fixed label " .. "added; if you took action in process_after_parse(), make sure to return " .. "`nil, true`"):format(dump(vals), param)) end end end else -- no param specified if infl.label or infl.all_fixed_label then interr("Cannot have label= or all_fixed_label= without specifying a param") end if infl.fixed_label then local labelobjs = resolve_prop(infl.fixed_label) process_labelobjs(labelobjs, nil, function(label, termobj) if label:find("{val}") then interr("Cannot specify {val} in a fixed_label= value without specifying a param") end headdata:insert_fixed_inflection(label, { originating_term = termobj }) end) end if infl.cat then local cats = resolve_prop(infl.cat) if type(cats) == "string" then cats = {cats} end if cats ~= nil then for _, cat in ipairs(cats) do if cat:find("{val}") then interr("Cannot specify {val} in a cat= value without specifying a param") end headdata:insert_category(cat) end end end end end end if infls then augment_headdata_from_infls(infls) end if augment_headdata then augment_headdata(headdata, args) end if pos_functions[indexing_poscat] then local pos_infls = pos_functions[indexing_poscat].infls if pos_infls then augment_headdata_from_infls(pos_infls) end local func = pos_functions[indexing_poscat].func if func then func(headdata, args) end end setmetatable(headdata, nil) if args.json then return require("Module:JSON").toJSON(headdata) end headdata.process_props = nil return require(headword_module).full_headword(headdata) end return export gqevnj4k9yxd2sb8km66y9rrlezxlk0 828 8054 54921 54860 2026-09-29T00:02:32Z Deadend0914 7211 54921 Scribunto text/plain local export = {} local debug_force_cat = false -- if set to true, always display categories even on userspace pages local m_links = require("Module:links") local m_str_utils = require("Module:string utilities") local m_table = require("Module:table") local decorations_module = "Module:decorations" local en_utilities_module = "Module:en-utilities" local etymology_module = "Module:etymology" local scripts_module = "Module:scripts" local utilities_module = "Module:utilities" -- Export this so the category code in [[Module:category tree/etymology]] can access it. export.affix_lang_data_module_prefix = "Module:affix/lang-data/" local ulen = m_str_utils.len local rfind = m_str_utils.find local rmatch = m_str_utils.match local pluralize = require(en_utilities_module).pluralize local singularize = require(en_utilities_module).singularize local u = m_str_utils.char local ucfirst = m_str_utils.ucfirst local unpack = unpack or table.unpack -- Lua 5.2 compatibility function export.affix_variants(canonical, variants) local mappings = {} for _, variant in ipairs(variants) do mappings[variant] = canonical end return mappings end function export.id_mapping(default, ids) local mapping = { default = default } if ids then for id, target in pairs(ids) do mapping[id] = target end end return mapping end function export.id_mapping_with_affix_variants(base, id_variants) local mappings = {} for id, variants in pairs(id_variants) do for _, variant in ipairs(variants) do mappings[variant] = export.id_mapping(base, {[id] = base}) end end return mappings end function export.merge_tables(...) local result = {} for i = 1, select('#', ...) do local t = select(i, ...) if t then for k, v in pairs(t) do result[k] = v end end end return result end -- Export this so the category code in [[Module:category tree/etymology]] can access it. export.langs_with_lang_specific_data = { ["az"] = true, ["fi"] = true, ["fr"] = true, ["izh"] = true, ["la"] = true, ["sah"] = true, ["tr"] = true, ["trk-pro"] = true, } local default_pos = "term" local function pluralize_pos(pos) return pluralize(singularize(pos)) end --[==[ intro: ===About different types of hyphens ("template", "display" and "lookup"):=== * The "template hyphen" is the per-script hyphen character that is used in template calls to indicate that a term is an affix. This is always a single Unicode char, but there may be multiple possible hyphens for a given script. Normally this is just the regular hyphen character "-", but for some non-Latin-script languages (currently only right-to-left languages), it is different. * The "display hyphen" is the string (which might be an empty string) that is added onto a term as displayed and linked, to indicate that a term is an affix. Currently this is always either the same as the template hyphen or an empty string, but the code below is written generally enough to handle arbitrary display hyphens. Specifically: *# For East Asian languages, the display hyphen is always blank. *# For Arabic-script languages, either tatweel (ـ) or ZWNJ (zero-width non-joiner) are allowed as template hyphens, where ZWNJ is supported primarily for Farsi, because some suffixes have non-joining behavior. The display hyphen corresponding to tatweel is also tatweel, but the display hyphen corresponding to ZWNJ is blank (tatweel is also the default display hyphen, for calls to {{tl|prefix}}/{{tl|suffix}}/etc. that don't include an explicit hyphen). * The "lookup hyphen" is the hyphen that is used when looking up language-specific affix mappings. (These mappings are discussed in more detail below when discussing link affixes.) It depends only on the script of the affix in question. Most scripts (including East Asian scripts) use a regular hyphen "-" as the lookup hyphen, but Hebrew and Arabic have their own lookup hyphens (respectively maqqef and tatweel). Note that for Arabic in particular, there are three possible template hyphens that are recognized (tatweel, ZWNJ and regular hyphen), but mappings must use tatweel. ===About different types of affixes ("template", "display", "link", "lookup" and "category"):=== * A "template affix" is an affix in its source form as it appears in a template call. Generally, a template affix has an attached template hyphen (see above) to indicate that it is an affix and indicate what type of affix it is (prefix, suffix, interfix or circumfix), but some of the older-style templates such as {{tl|suffix}}, {{tl|prefix}}, {{tl|confix}}, etc. have "positional" affixes where the presence of the affix in a certain position (e.g. the second or third parameter) indicates that it is a certain type of affix, whether or not it has an attached template hyphen. * A "display affix" is the corresponding affix as it is actually displayed to the user. The display affix may differ from the template affix for various reasons: *# The display affix may be specified explicitly using the {{para|alt<var>N</var>}} parameter, the `<alt:...>` inline modifier or a piped link of the form e.g. `<nowiki>[[-kas|-käs]]</nowiki>` (here indicating that the affix should display as `-käs` but be linked as `-kas`). Here, the template affix is arguably the entire piped link, while the display affix is `-käs`. *# Even in the absence of {{para|alt<var>N</var>}} parameters, `<alt:...>` inline modifiers and piped links, certain languages have differences between the "template hyphen" specified in the template (which always needs to be specified somehow or other in templates like {{tl|affix}}, to indicate that the term is an affix and what type of affix it is) and the display hyphen (see above), with corresponding differences between template and display affixes. * A (regular) "link affix" is the affix that is linked to when the affix is shown to the user. The link affix is usually the same as the display affix, but will differ in one of three circumstances: *# The display and link affixes are explicitly made different using {{para|alt<var>N</var>}} parameters, `<alt:...>` inline modifiers or piped links, as described above under "display affix". *# For certain languages, certain affixes are mapped to canonical form using language-specific mappings. For example, in Finnish, the adjective-forming suffix {{m|fi|-kas}} appears as {{m|fi|-käs}} after front vowels, but logically both forms are the same suffix and should be linked and categorized the same. Similarly, in Latin, the negative and intensive prefixes spelled {{m|la|in-}} (etymologically two distinct prefixes) appear variously as {{m|la|il-}}, {{m|la|im-}} or {{m|la|ir-}} before certain consonants. Mappings are supplied in [[Module:affix/lang-data/LANGCODE]] to convert Finnish {{m|fi|-käs}} to {{m|fi|-kas}} for linking and categorization purposes. Note that the affixes in the mappings use "lookup hyphens" to indicate the different types of affixes, which is usually the same as the template hyphen but differs for Arabic scripts, because there are multiple possible template hyphens recognized but only one lookup hyphen (tatweel). The form of the affix as used to look up in the mapping tables is called the "lookup affix"; see below. * A "stripped link affix" is a link affix that has been passed through the language's `stripDiacritics()` function, which may strip certain diacritics: e.g. macrons in Latin and Old English (indicating length); acute and grave accents in Russian and various other Slavic languages (indicating stress); vowel diacritics in most Arabic-script languages; and also tatweel in some Arabic-script languages (currently, for example, Persian, Arabic and Urdu strip tatweel, but Ottoman Turkish does not). Stripped link affixes are currently what are used in category names. * A "lookup affix" is the form of the affix as it is looked up in the language-specific lookup mappings described above under link affixes. There are actually two lookup stages: *# First, the affix is looked up in a modified display form (specifically, the same as the display affix but using lookup hyphens). Note that this lookup does not occur if an explicit display form is given using {{para|alt<var>N</var>}} or an `<alt:...>` inline modifier, or if the template affix contains a piped or embedded link. *# If no entry is found, the affix is then looked up in a modified link form (specifically, the modified display form passed through the language's `stripDiacritics()` function, which strips out certain diacritics, but with the lookup hyphen re-added if it was stripped out, as in the case of tatweel in many Arabic-script languages). The reason for this double lookup procedure is to allow for mappings that are sensitive to the extra diacritics, but also allow for mappings that are not sensitive in this fashion (e.g. Russian {{m|ru|-ливый}} occurs both stressed and unstressed, but is the same prefix either way). * A "category affix" is the affix as it appears in categories such as [[:Category:Finnish terms suffixed with -kas| Category:Finnish terms suffixed with ''-kas'']]. The category affix is currently always the same as the stripped link affix. This means that for Arabic-script languages, it may or may not have a tatweel, even if the correponding display affix and regular link affix have a tatweel. As mentioned above, stripDiacritics() strips tatweel for Arabic, Persian and Urdu, but not for Ottoman Turkish. Hence affix categories for Arabic, Persian and Urdu will be missing the tatweel, but affix categories for Ottoman Turkish will have it. An additional complication is that if the template affix contains a ZWNJ, the display (and hence the link and category affixes) will have no hyphen attached in any case. ]==] ----------------------------------------------------------------------------------------- -- Template and display hyphens -- ----------------------------------------------------------------------------------------- --[=[ Per-script template hyphens. The template hyphen is what appears in the {{affix}}/{{prefix}}/{{suffix}}/etc. template (in the wikicode). See above. They key below is a script code, after removing a hyphen and anything preceding. Hence, script codes like 'mnc-Mong' and 'xwo-Mong' will match 'Mong'. The value below is a string consisting of one or more hyphen characters. If there is more than one character, the default hyphen must come last and a non-default function must be specified for the script in display_hyphens[] so the correct display hyphen will be specified when no template hyphen is given (in {{suffix}}/{{prefix}}/etc.). Script detection is normally done when linking, but we need to do it earlier. However, under most circumstances we don't need to do script detection. Specifically, we only need to do script detection for a given language if (a) the language has multiple scripts; and (b) at least one of those scripts is listed below or in display_hyphens. ]=] local ZWNJ = u(0x200C) -- zero-width non-joiner local template_hyphens = { -- This covers all Arabic scripts. See above. ["Arab"] = "ـ" .. ZWNJ .. "-", -- tatweel + zero-width non-joiner + regular hyphen ["Aran"] = "ـ" .. ZWNJ .. "-", -- tatweel + zero-width non-joiner + regular hyphen ["Hebr"] = "־", -- Hebrew-specific hyphen termed "maqqef" ["Mong"] = "᠊", -- FIXME! What about the following right-to-left scripts? -- Adlm (Adlam) -- Armi (Imperial Aramaic) -- Avst (Avestan) -- Cprt (Cypriot) -- Khar (Kharoshthi) -- Mand (Mandaic/Mandaean) -- Mani (Manichaean) -- Mend (Mende/Mende Kikakui) -- Narb (Old North Arabian) -- Nbat (Nabataean/Nabatean) -- Nkoo (N'Ko) -- Orkh (Orkhon runes) -- Phli (Inscriptional Pahlavi) -- Phlp (Psalter Pahlavi) -- Phlv (Book Pahlavi) -- Phnx (Phoenician) -- Prti (Inscriptional Parthian) -- Rohg (Hanifi Rohingya) -- Samr (Samaritan) -- Sarb (Old South Arabian) -- Sogd (Sogdian) -- Sogo (Old Sogdian) -- Syrc (Syriac) -- Thaa (Thaana) } -- Hyphens used when looking up an affix in a lang-specific affix mapping. Defaults to regular hyphen (-). The keys -- are script codes, after removing a hyphen and anything preceding. Hence, script codes like 'mnc-Mong' and 'xwo-Mong' -- will match 'Mong'. The value should be a single character. local lookup_hyphens = { ["Hebr"] = "־", -- This covers all Arabic scripts. See above. ["Arab"] = "ـ", ["Aran"] = "ـ", } -- Default display-hyphen function. local function default_display_hyphen(script, hyph) if not hyph then return template_hyphens[script] or "-" end return hyph end local function arab_get_display_hyphen(_script, hyph) if not hyph then return "ـ" -- tatweel elseif hyph == ZWNJ then return "" else return hyph end end local function no_display_hyphen(_script, _hyph) return "" end -- Per-script function to return the correct display hyphen given the script and template hyphen. The function should -- also handle the case where the passed-in template hyphen is nil, corresponding to the situation in -- {{prefix}}/{{suffix}}/etc. where no template hyphen is specified. The key is the script code after removing a hyphen -- and anything preceding, so 'mnc-Mong', 'xwo-Mong' etc. will match 'Mong'. local display_hyphens = { -- This covers all Arabic scripts. See above. ["Arab"] = arab_get_display_hyphen, ["Aran"] = arab_get_display_hyphen, ["Bopo"] = no_display_hyphen, ["Hani"] = no_display_hyphen, ["Hans"] = no_display_hyphen, ["Hant"] = no_display_hyphen, -- The following is a mixture of several scripts. Hopefully the specs here are correct! ["Jpan"] = no_display_hyphen, ["Jurc"] = no_display_hyphen, ["Kitl"] = no_display_hyphen, ["Kits"] = no_display_hyphen, ["Laoo"] = no_display_hyphen, ["Nshu"] = no_display_hyphen, ["Shui"] = no_display_hyphen, ["Tang"] = no_display_hyphen, ["Thaa"] = no_display_hyphen, ["Thai"] = no_display_hyphen, ["Tibt"] = no_display_hyphen, } ----------------------------------------------------------------------------------------- -- Basic Utility functions -- ----------------------------------------------------------------------------------------- local function glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end local function track(page) if type(page) == "table" then for i, pg in ipairs(page) do page[i] = "affix/" .. pg end else page = "affix/" .. page end require("Module:debug/track")(page) end local function ine(val) return val ~= "" and val or nil end ----------------------------------------------------------------------------------------- -- Compound types -- ----------------------------------------------------------------------------------------- local function make_compound_type(typ, alttext) return { text = glossary_link(typ, alttext) .. " compound", cat = typ .. " compounds", } end -- Make a compound type entry with a simple rather than glossary link. -- These should be replaced with a glossary link when the entry in the glossary -- is created. local function make_non_glossary_compound_type(typ, alttext) local link = alttext and "[[" .. typ .. "|" .. alttext .. "]]" or "[[" .. typ .. "]]" return { text = link .. " compound", cat = typ .. " compounds", } end local function make_raw_compound_type(typ, alttext) return { text = glossary_link(typ, alttext), cat = pluralize(typ), } end local function make_borrowing_type(typ, alttext) return { text = glossary_link(typ, alttext), borrowing_type = pluralize(typ), } end export.etymology_types = { ["adapted borrowing"] = make_borrowing_type("adapted borrowing"), ["adap"] = "adapted borrowing", ["abor"] = "adapted borrowing", ["alliterative"] = make_non_glossary_compound_type("alliterative"), ["allit"] = "alliterative", ["antonymous"] = make_non_glossary_compound_type("antonymous"), ["ant"] = "antonymous", ["bahuvrihi"] = make_compound_type("bahuvrihi", "bahuvrīhi"), ["bahu"] = "bahuvrihi", ["bv"] = "bahuvrihi", ["coordinative"] = make_compound_type("coordinative"), ["coord"] = "coordinative", ["descriptive"] = make_compound_type("descriptive"), ["desc"] = "descriptive", ["determinative"] = make_compound_type("determinative"), ["det"] = "determinative", ["dvandva"] = make_compound_type("dvandva"), ["dva"] = "dvandva", ["dvigu"] = make_compound_type("dvigu"), ["dvi"] = "dvigu", ["endocentric"] = make_compound_type("endocentric"), ["endo"] = "endocentric", ["exocentric"] = make_compound_type("exocentric"), ["exo"] = "exocentric", ["izafet I"] = make_compound_type("izafet I"), ["iz1"] = "izafet I", ["izafet II"] = make_compound_type("izafet II"), ["iz2"] = "izafet II", ["izafet III"] = make_compound_type("izafet III"), ["iz3"] = "izafet III", ["karmadharaya"] = make_compound_type("karmadharaya", "karmadhāraya"), ["karma"] = "karmadharaya", ["kd"] = "karmadharaya", ["kenning"] = make_raw_compound_type("kenning"), ["ken"] = "kenning", ["rhyming"] = make_non_glossary_compound_type("rhyming"), ["rhy"] = "rhyming", ["synonymous"] = make_non_glossary_compound_type("synonymous"), ["syn"] = "synonymous", ["tatpurusa"] = make_compound_type("tatpurusa", "tatpuruṣa"), ["tat"] = "tatpurusa", ["tp"] = "tatpurusa", } local function process_etymology_type(typ, nocap, notext, has_parts) local text_sections = {} local categories = {} local borrowing_type if typ then local typdata = export.etymology_types[typ] if type(typdata) == "string" then typdata = export.etymology_types[typdata] end if not typdata then error("Internal error: Unrecognized type '" .. typ .. "'") end local text = typdata.text if not nocap then text = ucfirst(text) end local cat = typdata.cat borrowing_type = typdata.borrowing_type local oftext = typdata.oftext or " of" if not notext then table.insert(text_sections, text) if has_parts then table.insert(text_sections, oftext) table.insert(text_sections, " ") end end if cat then table.insert(categories, cat) end end return text_sections, categories, borrowing_type end ----------------------------------------------------------------------------------------- -- Utility functions -- ----------------------------------------------------------------------------------------- -- Iterate an array up to the greatest integer index found. local function ipairs_with_gaps(t) local indices = m_table.numKeys(t) local max_index = #indices > 0 and math.max(unpack(indices)) or 0 local i = 0 return function() if i < max_index then i = i + 1 return i, t[i] end end end export.ipairs_with_gaps = ipairs_with_gaps --[==[ Join formatted parts (in `parts_formatted`) together with any overall {{para|lit}} spec (in `lit`) plus categories, which are formatted by prepending the language name as found in `lang`. The value of an entry in `categories` can be either a string (which is formatted using `sort_key`) or a table of the form `{ {cat=<var>category</var>, sort_key=<var>sort_key</var>, sort_base=<var>sort_base</var>}`, specifying the sort key and sort base to use when formatting the category. If `nocat` is given, no categories are added; otherwise, `force_cat` causes categories to be added even on userspace pages. ]==] -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end function export.join_formatted_parts(data) local cattext local lang = data.data.lang local force_cat = data.data.force_cat or debug_force_cat if data.data.nocat then cattext = "" else for i, cat in ipairs(data.categories) do if type(cat) == "table" then data.categories[i] = require(utilities_module).format_categories(lang:getFullName() .. " " .. cat_word(lang, cat.cat), lang, cat.sort_key, cat.sort_base, force_cat) else data.categories[i] = require(utilities_module).format_categories(lang:getFullName() .. " " .. cat_word(lang, cat), lang, data.data.sort_key, nil, force_cat) end end cattext = table.concat(data.categories) end local result = table.concat(data.parts_formatted, not data.separator_already_added and " +&lrm; " or nil) .. (data.data.lit and ", literally " .. m_links.mark(data.data.lit, "gloss") or "") local q = data.data.q local qq = data.data.qq local l = data.data.l local ll = data.data.ll if q and q[1] or qq and qq[1] or l and l[1] or ll and ll[1] then result = require(decorations_module).format_decorations { lang = lang, text = result, q = q, qq = qq, l = l, ll = ll, } end return result .. cattext end -- Remove links and call lang:stripDiacritics(term). local function strip_diacritics_no_links(lang, term) return lang:stripDiacritics(m_links.remove_links(term)) end --[=[ Convert a raw part as passed into an entry point into a part ready for linking. `lang` and `sc` are the overall language and script objects. This uses the overall language and script objects as defaults for the part and parses off any fragment from the term. We need to do the latter so that fragments don't end up in categories and so that we correctly do affix mapping even in the presence of fragments. ]=] local function canonicalize_part(part, lang, sc) if not part then return end -- Save the original (user-specified, part-specific) value of `lang`. If such a value is specified, we don't insert -- a '*fixed with' category, and we format the part using format_derived() in [[Module:etymology]] rather than -- full_link() in [[Module:links]]. part.part_lang = part.lang part.lang = part.lang or lang part.sc = part.sc or sc local term = part.term if not term then return elseif not part.fragment then part.term, part.fragment = m_links.get_fragment(term) else part.term = m_links.get_fragment(term) end end --[==[ Construct a single linked part based on the information in `part`, for use by `show_affix()` and other entry points. This should be called after `canonicalize_part()` is called on the part. This is a thin wrapper around `full_link()` in [[Module:links]] unless `part.part_lang` is specified (indicating that a part-specific language was given), in which case `format_derived()` in [[Module:etymology]] is called to display a term in a language other than the language of the overall term (specified in `data.lang`). `data` contains the entire object passed into the entry point and is used to access information for constructing the categories added by `format_derived()`. ]==] function export.link_term(part, data, include_separator) local result if part.part_lang then result = require(etymology_module).format_derived { lang = data.lang, terms = {part}, sources = {part.lang}, sort_key = data.sort_key, nocat = data.nocat, template_name = "affix", decorations_on_outside = true, borrowing_type = data.borrowing_type, force_cat = data.force_cat or debug_force_cat, } else result = m_links.full_link(part, "term") end if include_separator and part.separator then return part.separator .. result else return result end end local function canonicalize_script_code(scode) -- Convert 'mnc-Mong', 'xwo-Mong' etc. to 'Mong'. return (scode:gsub("^.*%-", "")) end ----------------------------------------------------------------------------------------- -- Affix-handling functions -- ----------------------------------------------------------------------------------------- -- Figure out the appropriate script for the given affix and language (unless the script is explicitly passed in), and -- return the values of template_hyphens[], display_hyphens[] and lookup_hyphens[] for that script, substituting -- default values as appropriate. Four values are returned: -- DETECTED_SCRIPT, TEMPLATE_HYPHEN, DISPLAY_HYPHEN, LOOKUP_HYPHEN local function detect_script_and_hyphens(text, lang, sc) local scode -- 1. If the script is explicitly passed in, use it. if sc then scode = sc:getCode() else local possible_script_codes = lang:getScriptCodes() -- YUCK! `possible_script_codes` comes from loadData() so #possible_scripts doesn't work (always returns 0). local num_possible_script_codes = m_table.length(possible_script_codes) if num_possible_script_codes == 0 then -- This shouldn't happen; if the language has no script codes, -- the list {"None"} should be returned. error("Something is majorly wrong! Language " .. lang:getCanonicalName() .. " has no script codes.") end if num_possible_script_codes == 1 then -- 2. If the language has only one possible script, use it. scode = possible_script_codes[1] else -- 3. Check if any of the possible scripts for the language have non-default values for template_hyphens[] -- or display_hyphens[]. If so, we need to do script detection on the text. If not, just use "Latn", -- which may not be technically correct but produces the right results because Latn has all default -- values for template_hyphens[] and display_hyphens[]. local may_have_nondefault_hyphen = false for _, script_code in ipairs(possible_script_codes) do script_code = canonicalize_script_code(script_code) if template_hyphens[script_code] or display_hyphens[script_code] then may_have_nondefault_hyphen = true break end end if not may_have_nondefault_hyphen then scode = "Latn" else scode = lang:findBestScript(text):getCode() end end end scode = canonicalize_script_code(scode) local template_hyphen = template_hyphens[scode] or "-" local lookup_hyphen = lookup_hyphens[scode] or "-" local display_hyphen = display_hyphens[scode] or default_display_hyphen return scode, template_hyphen, display_hyphen, lookup_hyphen end --[=[ Given a template affix `term` and an affix type `affix_type`, change the relevant template hyphen(s) in the affix to the display or lookup hyphen specified in `new_hyphen`, or add them if they are missing. `new_hyphen` can be a string, specifying a fixed hyphen, or a function of two arguments (the script code `scode` and the discovered template hyphen, or nil of no relevant template hyphen is present). `thyph_re` is a Lua pattern (which must be enclosed in parens) that matches the possible template hyphens. Note that not all template hyphens present in the affix are changed, but only the "relevant" ones (e.g. for a prefix, a relevant template hyphen is one coming at the end of the affix). ]=] local function reconstruct_term_per_hyphens(term, affix_type, scode, thyph_re, new_hyphen) local function get_hyphen(hyph) if type(new_hyphen) == "string" then return new_hyphen end return new_hyphen(scode, hyph) end if affix_type == "non-affix" then return term elseif affix_type == "circumfix" then local before, before_hyphen, after_hyphen, after = rmatch(term, "^(.*)" .. thyph_re .. " " .. thyph_re .. "(.*)$") if not before or ulen(term) <= 3 then -- Unlike with other types of affixes, don't try to add hyphens in the middle of the term to convert it to -- a circumfix. Also, if the term is just hyphen + space + hyphen, return it. return term end return before .. get_hyphen(before_hyphen) .. " " .. get_hyphen(after_hyphen) .. after elseif affix_type == "infix" or affix_type == "interfix" then local before_hyphen, middle, after_hyphen = rmatch(term, "^" .. thyph_re .. "(.*)" .. thyph_re .. "$") if before_hyphen and ulen(term) <= 1 then -- If the term is just a hyphen, return it. return term end return get_hyphen(before_hyphen) .. (middle or term) .. get_hyphen(after_hyphen) elseif affix_type == "prefix" then local middle, after_hyphen = rmatch(term, "^(.*)" .. thyph_re .. "$") if middle and ulen(term) <= 1 then -- If the term is just a hyphen, return it. return term end return (middle or term) .. get_hyphen(after_hyphen) elseif affix_type == "suffix" then local before_hyphen, middle = rmatch(term, "^" .. thyph_re .. "(.*)$") if before_hyphen and ulen(term) <= 1 then -- If the term is just a hyphen, return it. return term end return get_hyphen(before_hyphen) .. (middle or term) else error(("Internal error: Unrecognized affix type '%s'"):format(affix_type)) end end --[=[ Look up a mapping from a given affix variant to the canonical form used in categories and links. The lookup tables are language-specific according to `lang`, and may be ID-specific according to `affix_id`. The affixes as they appear in the lookup tables (both the variant and the canonical form) are in "lookup affix" format (approximately speaking, they use a regular hyphen for most scripts, but a tatweel for Arabic-script entries and a maqqef for Hebrew-script entries), but the passed-in `affix` param is in "template affix" format (which differs from the lookup affix for Arabic-script entries, because more types of hyphens are allowed in template affixes; see the comments at the top of the file). The remaining parameters to this function are used to convert from template affixes to lookup affixes; see the reconstruct_term_per_hyphens() function above. If the affix contains brackets, no lookup is done. Otherwise, a two-stage process is used, first looking up the affix directly and then stripping diacritics and looking it up again. The reason for this is documented above in the comments at the top of the file (specifically, the comments describing lookup affixes). The value of a mapping can either be a string (do the mapping regardless of affix ID) or a table indexed by affix ID (where the special value `false` indicates no affix ID). The values of entries in this table can also be strings, or tables with keys `affix` and `id` (again, use `false` to indicate no ID). This allows an affix mapping to map from one ID to another (for example, this is used in English to map the [[an-]] prefix with no ID to the [[a-]] prefix with the ID 'not'). The Given a template affix `term` and an affix type `affix_type`, change the relevant template hyphen(s) in the affix to the display or lookup hyphen specified in `new_hyphen`, or add them if they are missing. `new_hyphen` can be a string, specifying a fixed hyphen, or a function of two arguments (the script code `scode` and the discovered template hyphen, or nil of no relevant template hyphen is present). `thyph_re` is a Lua pattern (which must be enclosed in parens) that matches the possible template hyphens. Note that not all template hyphens present in the affix are changed, but only the "relevant" ones (e.g. for a prefix, a relevant template hyphen is one coming at the end of the affix). ]=] local function lookup_affix_mapping(affix, affix_type, lang, scode, thyph_re, lookup_hyph, affix_id) local function do_lookup(afx) -- Ensure that the affix uses lookup hyphens regardless of whether it used a different type of hyphens before -- or no hyphens. local lookup_affix = reconstruct_term_per_hyphens(afx, affix_type, scode, thyph_re, lookup_hyph) local function do_lookup_for_langcode(langcode) if export.langs_with_lang_specific_data[langcode] then local langdata = mw.loadData(export.affix_lang_data_module_prefix .. langcode) if langdata.affix_mappings then local mapping = langdata.affix_mappings[lookup_affix] if mapping then if type(mapping) == "table" then mapping = mapping[affix_id] or mapping.default or mapping[affix_id or false] if mapping then return mapping end else return mapping end end end end end -- If `lang` is an etymology-only language, look for a mapping both for it and its full parent. local langcode = lang:getCode() local mapping = do_lookup_for_langcode(langcode) if mapping then return mapping end local full_langcode = lang:getFullCode() if full_langcode ~= langcode then mapping = do_lookup_for_langcode(full_langcode) if mapping then return mapping end end return nil end if affix:find("%[%[") then return nil end return do_lookup(affix) or do_lookup(lang:stripDiacritics(affix)) or nil end --[==[ For a given template term in a given language (see the definition of "template affix" near the top of the file), possibly in an explicitly specified script `sc` (but usually nil), return the term's affix type ({"prefix"}, {"interfix"}, {"suffix"}, {"circumfix"} or {"non-affix"}) along with the corresponding link and display affixes (see definitions near the top of the file); also the corresponding lookup affix (if `return_lookup_affix` is specified). The term passed in should already have any fragment (after the # sign) parsed off of it. Four values are returned: `affix_type`, `link_term`, `display_term` and `lookup_term`. The affix type can be passed in instead of autodetected; in this case, the template term need not have any attached hyphens, and the appropriate hyphens will be added in the appropriate places. If `do_affix_mapping` is specified, look up the affix in the lang-specific affix mappings, as described in the comment at the top of the file; otherwise, the link and display terms will always be the same. (They will be the same in any case if the template term has a bracketed link in it or is not an affix.) If `return_lookup_affix` is given, the fourth return value contains the term with appropriate lookup hyphens in the appropriate places; otherwise, it is the same as the display term. (This functionality is used in [[Module:category tree/affixes and compounds]] to convert link affixes into lookup affixes so that they can be looked up in the affix mapping tables.) Exported because used by [[Module:headword utilities]] to determine the affix type of a given pagename. ]==] function export.parse_term_for_affixes(term, lang, sc, affix_type, do_affix_mapping, return_lookup_affix, affix_id) if not term then return "non-affix", nil, nil, nil end if term == "^" then -- Indicates a null term to emulate the behavior of {{suffix|foo||bar}}. term = "" return "non-affix", term, term, term end if term:find("^%^") then -- HACK! ^ at the beginning of Korean languages has a special meaning, triggering capitalization of the -- transliteration. Don't interpret it as "force non-affix" for those languages. local langcode = lang:getCode() if langcode ~= "ko" and langcode ~= "okm" and langcode ~= "jje" then -- Formerly we allowed ^ to force non-affix type; this is now handled using an inline modifier -- <naf>, <root>, etc. Throw an error for the moment when the old way is encountered. error("Use of ^ to force non-affix status is no longer supported; use an inline modifier <naf> or <root> " .. "after the component") end end -- Remove an asterisk if the morpheme is reconstructed and add it back at the end. local reconstructed = "" if term:find("^%*") then reconstructed = "*" term = term:gsub("^%*", "") end local scode, thyph, dhyph, lhyph = detect_script_and_hyphens(term, lang, sc) thyph = "([" .. thyph .. "])" if not affix_type then if rfind(term, thyph .. " " .. thyph) then affix_type = "circumfix" else local has_beginning_hyphen = rfind(term, "^" .. thyph) local has_ending_hyphen = rfind(term, thyph .. "$") if has_beginning_hyphen and has_ending_hyphen then affix_type = "interfix" elseif has_ending_hyphen then affix_type = "prefix" elseif has_beginning_hyphen then affix_type = "suffix" else affix_type = "non-affix" end end end local link_term, display_term, lookup_term if affix_type == "non-affix" then link_term = term display_term = term lookup_term = term else display_term = reconstruct_term_per_hyphens(term, affix_type, scode, thyph, dhyph) if do_affix_mapping then link_term = lookup_affix_mapping(term, affix_type, lang, scode, thyph, lhyph, affix_id) -- The return value of lookup_affix_mapping() may be an affix mapping with lookup hyphens if a mapping -- was found, otherwise nil if a mapping was not found. We need to convert to display hyphens in -- either case, but in the latter case we can reuse the display term, which has already been converted. if link_term then link_term = reconstruct_term_per_hyphens(link_term, affix_type, scode, thyph, dhyph) else link_term = display_term end else link_term = display_term end if return_lookup_affix then lookup_term = reconstruct_term_per_hyphens(term, affix_type, scode, thyph, lhyph) else lookup_term = display_term end end link_term = reconstructed .. link_term display_term = reconstructed .. display_term lookup_term = reconstructed .. lookup_term return affix_type, link_term, display_term, lookup_term end --[==[ Add a hyphen to a term in the appropriate place, based on the specified affix type, stripping off any existing hyphens in that place. For example, if `affix_type` == {"prefix"}, we'll add a hyphen onto the end if it's not already there (or is of the wrong type). Three values are returned: the link term, display term and lookup term. This function is a thin wrapper around `parse_term_for_affixes`; see the comments above that function for more information. Note that this function is exposed externally because it is called by [[Module:category tree/affixes and compounds]]; see the comment in `parse_term_for_affixes` for more information. ]==] function export.make_affix(term, lang, sc, affix_type, do_affix_mapping, return_lookup_affix, affix_id) if not (affix_type == "prefix" or affix_type == "suffix" or affix_type == "circumfix" or affix_type == "infix" or affix_type == "interfix" or affix_type == "non-affix") then error("Internal error: Invalid affix type " .. (affix_type or "(nil)")) end local _, link_term, display_term, lookup_term = export.parse_term_for_affixes(term, lang, sc, affix_type, do_affix_mapping, return_lookup_affix, affix_id) return link_term, display_term, lookup_term end ----------------------------------------------------------------------------------------- -- Main entry points -- ----------------------------------------------------------------------------------------- --[==[ Core categorization logic for affixes. This is shared between show_affix(), show_compound_like() and get_affix_categories_only(). Returns the categories array and other metadata needed for formatting. ]==] local function generate_affix_categories(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) local text_sections, categories, borrowing_type = process_etymology_type(data.type, data.surface_analysis or data.nocap, data.notext, #data.parts > 0) data.borrowing_type = borrowing_type -- Process each part local whole_words = 0 local is_affix_or_compound = false -- Canonicalize and generate links for all the parts first; then do categorization in a separate step, because when -- processing the first part for categorization, we may access the second part and need it already canonicalized. for i, part in ipairs_with_gaps(data.parts) do part = part or {} data.parts[i] = part canonicalize_part(part, data.lang, data.sc) -- Determine affix type and get link and display terms (see text at top of file). Store them in the part -- (in fields that won't clash with fields used by full_link() in [[Module:links]] or link_term()), so they -- can be used in the loop below when categorizing. part.affix_type, part.affix_link_term, part.affix_display_term = export.parse_term_for_affixes(part.term, part.lang, part.sc, part.type, not part.alt, nil, part.id) -- If link_term is an empty string, either a bare ^ was specified or an empty term was used along with inline -- modifiers. The intention in either case is not to link the term. part.term = ine(part.affix_link_term) -- If part.alt would be the same as part.term, make it nil, so that it isn't erroneously tracked as being -- redundant alt text. part.alt = part.alt or (part.affix_display_term ~= part.affix_link_term and part.affix_display_term) or nil end if not data.noaffixcat then -- Now do categorization. for i, part in ipairs_with_gaps(data.parts) do local affix_type = part.affix_type if affix_type ~= "non-affix" then is_affix_or_compound = true -- Make a sort key. For the first part, use the second part as the sort key; the intention is that if the -- term has a prefix, sorting by the prefix won't be very useful so we sort by what follows, which is -- presumably the root. local part_sort_base = nil local part_sort = part.sort or data.sort_key if i == 1 and data.parts[2] and data.parts[2].term then local part2 = data.parts[2] -- If the second-part link term is empty, the user requested an unlinked term; avoid a wikitext error -- by using the alt value if available. part_sort_base = ine(part2.affix_link_term) or ine(part2.alt) if part_sort_base then part_sort_base = strip_diacritics_no_links(part2.lang, part_sort_base) end end if part.pos and rfind(part.pos, "patronym") then table.insert(categories, {cat = "patronymics", sort_key = part_sort, sort_base = part_sort_base}) end if data.pos ~= "terms" and part.pos and rfind(part.pos, "diminutive") then table.insert(categories, {cat = "diminutive " .. data.pos, sort_key = part_sort, sort_base = part_sort_base}) end -- Don't add a '*fixed with' category if the link term is empty or is in a different language. if ine(part.affix_link_term) and not part.part_lang then table.insert(categories, {cat = data.pos .. " " .. affix_type .. "ed with " .. strip_diacritics_no_links(part.lang, part.affix_link_term) .. (part.id and " (" .. part.id .. ")" or ""), sort_key = part_sort, sort_base = part_sort_base}) end else whole_words = whole_words + 1 if whole_words == 2 then is_affix_or_compound = true table.insert(categories, "compound " .. data.pos) end end end -- Make sure there was either an affix or a compound (two or more non-affix terms). if not is_affix_or_compound and not data.allow_no_affixes_or_compounds then error("The parameters did not include any affixes, and the term is not a compound. Please provide at least one affix.") end end return text_sections, categories, borrowing_type end --[==[ Implementation of {{tl|affix}} and {{tl|surface analysis}}. `data` contains all the information describing the affixes to be displayed, and contains the following: * `.lang` ('''required'''): Overall language object. Different from term-specific language objects (see `.parts` below). * `.sc`: Overall script object (usually omitted). Different from term-specific script objects. * `.parts` ('''required'''): List of objects describing the affixes to show. The general format of each object is as would be passed to `full_link()`, except that the `.lang` field should be missing unless the term is of a language different from the overall `.lang` value (in such a case, the language name is shown along with the term and an additional "derived from" category is added). '''WARNING''': The data in `.parts` will be destructively modified. * `.pos`: Overall part of speech (used in categories, defaults to {"terms"}). Different from term-specific part of speech. * `.sort_key`: Overall sort key. Normally omitted except e.g. in Japanese. * `.type`: Type of compound, if the parts in `.parts` describe a compound. Strictly optional, and if supplied, the compound type is displayed before the parts (normally capitalized, unless `.nocap` is given). * `.nocap`: Don't capitalize the first letter of text displayed before the parts (relevant only if `.type` or `.surface_analysis` is given). * `.notext`: Don't display any text before the parts (relevant only if `.type` or `.surface_analysis` is given). * `.nocat`: Disable all categorization. * `.noaffixcat`: Disable affix (and compound) categorization. Relevant for e.g. blends, which may otherwise be incorrectly categorized as compound terms. * `.lit`: Overall literal definition. Different from term-specific literal definitions. * `.force_cat`: Always display categories, even on userspace pages. * `.surface_analysis`: Implement {{surface analysis}}; adds `By surface analysis, ` before the parts. '''WARNING''': This destructively modifies both `data` and the individual structures within `.parts`. ]==] function export.show_affix(data) local text_sections, categories, _ = generate_affix_categories(data) -- Process each part for display local parts_formatted = {} for i, part in ipairs_with_gaps(data.parts) do -- Make a link for the part table.insert(parts_formatted, export.link_term(part, data, "include_separator")) end if data.surface_analysis then local text = "by " .. glossary_link("surface analysis") .. ", " if not data.nocap then text = ucfirst(text) end table.insert(text_sections, 1, text) end table.insert(text_sections, export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories, separator_already_added = true }) return table.concat(text_sections) end --[==[ Get only the categories that would be generated by show_affix(), without any text output or formatting. This is used by Module:etymon to get affix categorization. Returns an array of category objects, where each entry is either a string (simple category name) or a table with keys `cat`, `sort_key`, and `sort_base` for more complex categorization. `data` should have the same structure as passed to show_affix(): * `.lang` (required): Overall language object * `.parts` (required): Array of affix part objects with `.term`, `.lang`, `.id`, etc. * `.pos`: Part of speech (defaults to "terms") * `.sort_key`: Overall sort key for categories '''WARNING''': This destructively modifies both `data` and the individual structures within `.parts`. ]==] function export.get_affix_categories_only(data) local _, categories, _ = generate_affix_categories(data) return categories end function export.show_surface_analysis(data) data.surface_analysis = true data.allow_no_affixes_or_compounds = true return export.show_affix(data) end --[==[ Implementation of {{tl|compound}}. '''WARNING''': This destructively modifies both `data` and the individual structures within `.parts`. ]==] function export.show_compound(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) local text_sections, categories, borrowing_type = process_etymology_type(data.type, data.nocap, data.notext, #data.parts > 0) data.borrowing_type = borrowing_type local parts_formatted = {} table.insert(categories, "compound " .. data.pos) -- Make links out of all the parts local whole_words = 0 for i, part in ipairs(data.parts) do canonicalize_part(part, data.lang, data.sc) -- Determine affix type and get link and display terms (see text at top of file). local affix_type, link_term, display_term = export.parse_term_for_affixes(part.term, part.lang, part.sc, part.type, not part.alt, nil, part.id) -- If the term is an interfix or the type was explicitly given, recognize it as such (which means e.g. that we -- will display the term without hyphens for East Asian languages). Otherwise, ignore the fact that it looks -- like an affix and display as specified in the template (but pay attention to the detected affix type for -- certain tracking purposes). if affix_type == "interfix" or (part.type and part.type ~= "non-affix") then -- If link_term is an empty string, either a bare ^ was specified or an empty term was used along with -- inline modifiers. The intention in either case is not to link the term. Don't add a '*fixed with' -- category in this case, or if the term is in a different language. -- If part.alt would be the same as part.term, make it nil, so that it isn't erroneously tracked as being -- redundant alt text. if link_term and link_term ~= "" and not part.part_lang then table.insert(categories, {cat = data.pos .. " " .. affix_type .. "ed with " .. strip_diacritics_no_links(part.lang, link_term), sort_key = part.sort or data.sort_key}) end part.term = link_term ~= "" and link_term or nil part.alt = part.alt or (display_term ~= link_term and display_term) or nil else if affix_type ~= "non-affix" then local langcode = data.lang:getCode() -- If `data.lang` is an etymology-only language, track both using its code and its full parent's code. track { affix_type, affix_type .. "/lang/" .. langcode } local full_langcode = data.lang:getFullCode() if langcode ~= full_langcode then track(affix_type .. "/lang/" .. full_langcode) end else whole_words = whole_words + 1 end end table.insert(parts_formatted, export.link_term(part, data, "include_separator")) end if whole_words == 1 then track("one whole word") elseif whole_words == 0 then track("looks like confix") end table.insert(text_sections, export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories, separator_already_added = true }) return table.concat(text_sections) end --[==[ Implementation of {{tl|blend}}, {{tl|univerbation}} and similar "compound-like" templates. '''WARNING''': This destructively modifies both `data` and the individual structures within `.parts`. ]==] function export.show_compound_like(data) data.allow_no_affixes_or_compounds = true local text_sections, categories, _ = generate_affix_categories(data) if data.cat then table.insert(categories, data.cat) end -- Process each part for display local parts_formatted = {} for i, part in ipairs_with_gaps(data.parts) do -- Make a link for the part table.insert(parts_formatted, export.link_term(part, data, "include_separator")) end if #data.parts > 0 and data.oftext then table.insert(text_sections, 1, " " .. data.oftext .. " ") end if data.text then table.insert(text_sections, 1, data.text) end table.insert(text_sections, export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories, separator_already_added = true }) return table.concat(text_sections) end --[==[ Make `part` (a structure holding information on an affix part) into an affix of type `affix_type`, and apply any relevant affix mappings. For example, if the desired affix type is "suffix", this will (in general) add a hyphen onto the beginning of the term, alt, tr and ts components of the part if not already present. The hyphen that's added is the "display hyphen" (see above) and may be script-specific. (In the case of East Asian scripts, the display hyphen is an empty string whereas the template hyphen is the regular hyphen, meaning that any regular hyphen at the beginning of the part will be effectively removed.) `lang` and `sc` hold overall language and script objects. Note that this also applies any language-specific affix mappings, so that e.g. if the language is Finnish and the user specified [[-käs]] in the affix and didn't specify an `.alt` value, `part.term` will contain [[-kas]] and `part.alt` will contain [[-käs]]. This function is used by the "legacy" templates ({{tl|prefix}}, {{tl|suffix}}, {{tl|confix}}, etc.) where the nature of the affix is specified by the template itself rather than auto-determined from the affix, as is the case with {{tl|affix}}. '''WARNING''': This destructively modifies `part`. ]==] local function make_part_into_affix(part, lang, sc, affix_type) canonicalize_part(part, lang, sc) local link_term, display_term = export.make_affix(part.term, part.lang, part.sc, affix_type, not part.alt, nil, part.id) part.term = link_term -- When we don't specify `do_affix_mapping` to make_affix(), link and display terms (first and second retvals of -- make_affix()) are the same. -- If part.alt would be the same as part.term, make it nil, so that it isn't erroneously tracked as being -- redundant alt text. part.alt = part.alt and export.make_affix(part.alt, part.lang, part.sc, affix_type) or (display_term ~= link_term and display_term) or nil local Latn = require(scripts_module).getByCode("Latn") part.tr = export.make_affix(part.tr, part.lang, Latn, affix_type) part.ts = export.make_affix(part.ts, part.lang, Latn, affix_type) end local function track_wrong_affix_type(template, part, expected_affix_type) if part and not part.type then local affix_type = export.parse_term_for_affixes(part.term, part.lang, part.sc) if affix_type ~= expected_affix_type then local part_name = expected_affix_type or "base" local langcode = part.lang:getCode() local full_langcode = part.lang:getFullCode() require("Module:debug/track") { template, template .. "/" .. part_name, template .. "/" .. part_name .. "/" .. (affix_type or "none"), template .. "/" .. part_name .. "/" .. (affix_type or "none") .. "/lang/" .. langcode } -- If `part.lang` is an etymology-only language, track both using its code and its full parent's code. if full_langcode ~= langcode then require("Module:debug/track")( template .. "/" .. part_name .. "/" .. (affix_type or "none") .. "/lang/" .. full_langcode ) end end end end local function insert_affix_category(categories, pos, affix_type, part, sort_key, sort_base) -- Don't add a '*fixed with' category if the link term is empty or is in a different language. if part.term and not part.part_lang then local cat = pos .. " " .. affix_type .. "ed with " .. strip_diacritics_no_links(part.lang, part.term) .. (part.id and " (" .. part.id .. ")" or "") if sort_key or sort_base then table.insert(categories, {cat = cat, sort_key = sort_key, sort_base = sort_base}) else table.insert(categories, cat) end end end --[==[ Implementation of {{tl|circumfix}}. '''WARNING''': This destructively modifies both `data` and `.prefix`, `.base` and `.suffix`. ]==] function export.show_circumfix(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) canonicalize_part(data.base, data.lang, data.sc) -- Hyphenate the affixes and apply any affix mappings. make_part_into_affix(data.prefix, data.lang, data.sc, "prefix") make_part_into_affix(data.suffix, data.lang, data.sc, "suffix") track_wrong_affix_type("circumfix", data.prefix, "prefix") track_wrong_affix_type("circumfix", data.base, nil) track_wrong_affix_type("circumfix", data.suffix, "suffix") -- Create circumfix term. local circumfix = nil if data.prefix.term and data.suffix.term then circumfix = data.prefix.term .. " " .. data.suffix.term data.prefix.alt = data.prefix.alt or data.prefix.term data.suffix.alt = data.suffix.alt or data.suffix.term data.prefix.term = circumfix data.suffix.term = circumfix end -- Make links out of all the parts. local parts_formatted = {} local categories = {} local sort_base if data.base.term then sort_base = strip_diacritics_no_links(data.base.lang, data.base.term) end table.insert(parts_formatted, export.link_term(data.prefix, data)) table.insert(parts_formatted, export.link_term(data.base, data)) table.insert(parts_formatted, export.link_term(data.suffix, data)) -- Insert the categories, but don't add a '*fixed with' category if the link term is in a different language. if not data.prefix.part_lang then table.insert(categories, {cat=data.pos .. " circumfixed with " .. strip_diacritics_no_links(data.prefix.lang, circumfix), sort_key=data.sort_key, sort_base=sort_base}) end return export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories } end --[==[ Implementation of {{tl|confix}}. '''WARNING''': This destructively modifies both `data` and `.prefix`, `.base` and `.suffix`. ]==] function export.show_confix(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) canonicalize_part(data.base, data.lang, data.sc) -- Hyphenate the affixes and apply any affix mappings. make_part_into_affix(data.prefix, data.lang, data.sc, "prefix") make_part_into_affix(data.suffix, data.lang, data.sc, "suffix") track_wrong_affix_type("confix", data.prefix, "prefix") track_wrong_affix_type("confix", data.base, nil) track_wrong_affix_type("confix", data.suffix, "suffix") -- Make links out of all the parts. local parts_formatted = {} local prefix_sort_base if data.base and data.base.term then prefix_sort_base = strip_diacritics_no_links(data.base.lang, data.base.term) elseif data.suffix.term then prefix_sort_base = strip_diacritics_no_links(data.suffix.lang, data.suffix.term) end -- Insert the categories and parts. local categories = {} table.insert(parts_formatted, export.link_term(data.prefix, data)) insert_affix_category(categories, data.pos, "prefix", data.prefix, data.sort_key, prefix_sort_base) if data.base then table.insert(parts_formatted, export.link_term(data.base, data)) end table.insert(parts_formatted, export.link_term(data.suffix, data)) -- FIXME, should we be specifying a sort base here? insert_affix_category(categories, data.pos, "suffix", data.suffix) return export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories } end --[==[ Implementation of {{tl|infix}}. '''WARNING''': This destructively modifies both `data` and `.base` and `.infix`. ]==] function export.show_infix(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) canonicalize_part(data.base, data.lang, data.sc) -- Hyphenate the affixes and apply any affix mappings. make_part_into_affix(data.infix, data.lang, data.sc, "infix") track_wrong_affix_type("infix", data.base, nil) track_wrong_affix_type("infix", data.infix, "infix") -- Make links out of all the parts. local parts_formatted = {} local categories = {} table.insert(parts_formatted, export.link_term(data.base, data)) table.insert(parts_formatted, export.link_term(data.infix, data)) -- Insert the categories. -- FIXME, should we be specifying a sort base here? insert_affix_category(categories, data.pos, "infix", data.infix) return export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories } end --[==[ Implementation of {{tl|prefix}}. '''WARNING''': This destructively modifies both `data` and the structures within `.prefixes`, as well as `.base`. ]==] function export.show_prefix(data) data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) canonicalize_part(data.base, data.lang, data.sc) -- Hyphenate the affixes and apply any affix mappings. for i, prefix in ipairs(data.prefixes) do make_part_into_affix(prefix, data.lang, data.sc, "prefix") end for i, prefix in ipairs(data.prefixes) do track_wrong_affix_type("prefix", prefix, "prefix") end track_wrong_affix_type("prefix", data.base, nil) -- Make links out of all the parts. local parts_formatted = {} local first_sort_base = nil local categories = {} if data.prefixes[2] then first_sort_base = ine(data.prefixes[2].term) or ine(data.prefixes[2].alt) if first_sort_base then first_sort_base = strip_diacritics_no_links(data.prefixes[2].lang, first_sort_base) end elseif data.base then first_sort_base = ine(data.base.term) or ine(data.base.alt) if first_sort_base then first_sort_base = strip_diacritics_no_links(data.base.lang, first_sort_base) end end for i, prefix in ipairs(data.prefixes) do table.insert(parts_formatted, export.link_term(prefix, data)) insert_affix_category(categories, data.pos, "prefix", prefix, data.sort_key, i == 1 and first_sort_base or nil) end if data.base then table.insert(parts_formatted, export.link_term(data.base, data)) else table.insert(parts_formatted, "") end return export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories } end --[==[ Implementation of {{tl|suffix}}. '''WARNING''': This destructively modifies both `data` and the structures within `.suffixes`, as well as `.base`. ]==] function export.show_suffix(data) local categories = {} data.pos = data.pos or default_pos data.pos = pluralize_pos(data.pos) canonicalize_part(data.base, data.lang, data.sc) -- Hyphenate the affixes and apply any affix mappings. for i, suffix in ipairs(data.suffixes) do make_part_into_affix(suffix, data.lang, data.sc, "suffix") end track_wrong_affix_type("suffix", data.base, nil) for i, suffix in ipairs(data.suffixes) do track_wrong_affix_type("suffix", suffix, "suffix") end -- Make links out of all the parts. local parts_formatted = {} if data.base then table.insert(parts_formatted, export.link_term(data.base, data)) else table.insert(parts_formatted, "") end for i, suffix in ipairs(data.suffixes) do table.insert(parts_formatted, export.link_term(suffix, data)) end -- Insert the categories. for i, suffix in ipairs(data.suffixes) do -- FIXME, should we be specifying a sort base here? insert_affix_category(categories, data.pos, "suffix", suffix) if suffix.pos and rfind(suffix.pos, "patronym") then table.insert(categories, "patronymics") end end return export.join_formatted_parts { data = data, parts_formatted = parts_formatted, categories = categories } end return export 4jetzdivz19atozyv52j2nrae70fe1o 828 8056 54894 54866 2026-09-28T21:04:49Z Deadend0914 7211 54894 Scribunto text/plain local export = {} local pos_functions = {} --[==[ Author from 2020 on: mostly Benwing2, with significant contributions from Theknightwho. Based on a prior version by Rua (by now mostly rewritten), with contributions from Erutuon and others (see history for full attribution). ]==] local force_cat = false -- for testing; if true, categories appear in non-mainspace pages local require = require local require_when_needed = require("Module:require when needed") local en_utilities_module = "Module:en-utilities" local headword_utilities_module = "Module:headword utilities" local headword_module = "Module:headword" local inflection_utilities_module = "Module:inflection utilities" local parse_utilities_module = "Module:parse utilities" local JSON_module = "Module:JSON" local labels_module = "Module:labels" local links_module = "Module:links" local parameters_module = "Module:parameters" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local yesno_module = "Module:yesno" local iut = require_when_needed(inflection_utilities_module) local put = require_when_needed(parse_utilities_module) local m_headword_utilities = require_when_needed(headword_utilities_module) local add_links_to_multiword_term = require_when_needed(headword_utilities_module, "add_links_to_multiword_term") local add_suffix = require_when_needed(en_utilities_module, "add_suffix") local apply_link_modifiers = require_when_needed(headword_utilities_module, "apply_link_modifiers") local concat = table.concat local deepEquals = require_when_needed(table_module, "deepEquals") local dump = mw.dumpObject local format_categories = require_when_needed(utilities_module, "format_categories") local full_headword = require_when_needed(headword_module, "full_headword") local get_label_info = require_when_needed(labels_module, "get_label_info") local get_link_page = require_when_needed(links_module, "get_link_page") local glossary_link = require_when_needed(headword_utilities_module, "glossary_link") local insert = table.insert local insertIfNot = require_when_needed(table_module, "insertIfNot") local ipairs = ipairs local is_regular_plural = require_when_needed(en_utilities_module, "is_regular_plural") local list_to_set = require_when_needed(table_module, "listToSet") local pairs = pairs local process_params = require_when_needed(parameters_module, "process") local remove = table.remove local remove_links = require_when_needed(links_module, "remove_links") local replacement_escape = require_when_needed(string_utilities_module, "replacement_escape") local shallowCopy = require_when_needed(table_module, "shallowCopy") local singularize = require_when_needed(en_utilities_module, "singularize") local split = require_when_needed(string_utilities_module, "split") local toJSON = require_when_needed(JSON_module, "toJSON") local toNFD = mw.ustring.toNFD local type = type local ulen = require_when_needed(string_utilities_module, "len") local ulower = require_when_needed(string_utilities_module, "lower") local umatch = require_when_needed(string_utilities_module, "match") local u = require_when_needed(string_utilities_module, "char") local ugsub = require_when_needed(string_utilities_module, "gsub") local lang = require("Module:languages").getByCode("en") local langname = lang:getCanonicalName() local list_param = {list = true, disallow_holes = true} local list_allow_holes = {list = true, allow_holes = true} local boolean_param = {type = "boolean"} local function ine(val) if val == "" then return nil else return val end end local function track(page) require("Module:debug/track")("en-headword/" .. page) return true end ------------------------------------------- UTILITY FUNCTIONS ------------------------------------------ -- Parse and return an inflection not requiring additional processing. The raw arguments come from `args[field]`, which -- is parsed for inline modifiers. local function parse_inflection(args, field, is_head) local argfield = field if type(argfield) == "table" then argfield = argfield[1] end return m_headword_utilities.parse_term_list_with_modifiers { paramname = field, forms = args[argfield], splitchar = ",", is_head = is_head, } end -- Insert the parsed inflections in `terms` (as parsed by `parse_inflection`) into `data.inflections`, with label -- `label` and optional accelerator spec `accel`. local function insert_inflection(data, terms, label, accel, no_label) for _, termobj in ipairs(terms) do m_headword_utilities.remove_termobj_field_modifiers(termobj) end m_headword_utilities.insert_inflection { headdata = data, terms = terms, label = label, no_label = no_label, accel = accel and {form = accel} or nil, } end -- Insert a fixed label `label` into the inflections for `data`. If `originating_term` is supplied, copy the decorations -- from it into the fixed label. local function insert_fixed_inflection(data, label, originating_term) m_headword_utilities.insert_fixed_inflection { headdata = data, originating_term = originating_term, label = label, } end -- Parse and insert an inflection not requiring additional processing into `data.inflections`. The raw arguments come -- from `args[field]`, which is parsed for inline modifiers. `label` is the label that the inflections are given; -- `accel` is the accelerator form, or nil. local function parse_and_insert_inflection(data, args, field, label, accel) m_headword_utilities.parse_and_insert_inflection { headdata = data, forms = args[field], paramname = field, splitchar = ",", label = label, accel = accel and {form = accel} or nil, } end -- These functions are used directly in the <> format as well as in the utility functions #2 below. local function compute_double_last_cons_stem(term) local last_cons = term:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("Verb stem '" .. term .. "' must end in a consonant to use ++") end return term .. last_cons end local function compute_plusplus_s_form(term, default_s_form) if term:find("[szx]$") then -- regas -> regasses, derez -> derezzes return compute_double_last_cons_stem(term) .. "es" else return default_s_form end end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local iparams = { [1] = true, } local iargs = require("Module:parameters").process(frame.args, iparams) local parargs = frame:getParent().args local poscat = iargs[1] local pos_in_1 = not poscat if pos_in_1 then poscat = ine(parargs[1]) or mw.title.getCurrentTitle().fullText == "Template:en-head" and "interjection" or error("Part of speech must be specified in 1=") poscat = require(headword_module).canonicalize_pos(poscat) end local indexing_poscat = pos_in_1 and "head" or poscat local params = { ["head"] = list_param, ["id"] = true, ["json"] = boolean_param, ["sort"] = true, ["splithyph"] = boolean_param, ["nosplithyph"] = boolean_param, ["hyphspace"] = boolean_param, ["nolink"] = boolean_param, ["nolinkhead"] = {type = "boolean_param", alias_of = "nolink"}, ["suffix"] = boolean_param, ["nosuffix"] = boolean_param, ["nomultiwordcat"] = boolean_param, ["abbr"] = list_param, ["the"] = true, ["def"] = {alias_of = "the"}, ["pagename"] = true, -- for testing } if pos_in_1 then params[1] = {required = true} -- required but ignored as already processed above end local pos_data = pos_functions[indexing_poscat] local pos_func if pos_data then local pos_params = pos_data.params if pos_params then for key, val in pairs(pos_params) do params[key] = val end end pos_func = pos_data.func end local args = process_params(parargs, params) -- Account for unsupported titles, e.g. 'C|N>K' instead of 'Unsupported titles/C through N to K'. local pagename = args.pagename or mw.loadData("Module:headword/data").pagename local user_specified_heads = parse_inflection(args, "head", "is_head") local heads = user_specified_heads local autohead if args.nolink or not pagename:find("[ '%-]") then autohead = pagename else local en_no_split_apostrophe_words = list_to_set { "one's", "someone's", "he's", "she's", "it's", } local en_include_hyphen_prefixes = list_to_set { -- We don't include things that are also words even though they are often (perhaps mostly) prefixes, e.g. -- "be", "counter", "cross", "extra", "half", "mid", "over", "pan", "under". "acro", "acousto", "Afro", "agro", "anarcho", "angio", "Anglo", "ante", "anti", "arch", "auto", "bi", "bio", "cis", "co", "cryo", "crypto", "de", "demi", "eco", "electro", "Euro", "ex", "Greco", "hemi", "hydro", "hyper", "hypo", "infra", "Indo", "inter", "intra", "Judeo", "macro", "meta", "micro", "mini", "multi", "neo", "neuro", "non", "para", "peri", "post", "pre", "pro", "proto", "pseudo", "re", "semi", "sub", "super", "trans", "un", "vice", } local function is_english(term) local title = mw.title.new(term) if title and title.exists then local content = title:getContent() if content and content:find("==English==\n") then return true end end return false end local function en_split_hyphen_when_space(word) if not word:find("-", nil, true) then return nil end if args.hyphspace then return "[[" .. word:gsub("%-+", " ") .. "|" .. word .. "]]" end if args.nosplithyph then return "[[" .. word .. "]]" end if not args.splithyph then local space_word = word:gsub("%-+", " ") if is_english(space_word) then return "[[" .. space_word .. "|" .. word .. "]]" end if is_english(word) then return "[[" .. word .. "]]" end end return nil end local function en_split_apostrophe(word) local base = word:match("^(.*)'s$") if base then return "[[" .. base .. "]][[-'s|'s]]" end -- Only treat final apostrophe as possessive if preceded by something that looks like a plural ending in /z/. -- In particular we don't want to do it for words like [[truckin']]. base = word:match("^(.*[sxz])'$") if base then if base:find("s$") then local sg = singularize(base) if is_english(sg) then return "[[" .. sg .. "|" .. base .. "]][[-'|']]" end end return "[[" .. base .. "]][[-'|']]" end return "[[" .. word .. "]]" end autohead = add_links_to_multiword_term(pagename, { split_hyphen_when_space = en_split_hyphen_when_space, split_apostrophe = en_split_apostrophe, no_split_apostrophe_words = en_no_split_apostrophe_words, include_hyphen_prefixes = en_include_hyphen_prefixes, }) end if not heads[1] then heads = {{term = autohead}} else for _, headobj in ipairs(heads) do local head = headobj.term if head:find("^~") then head = apply_link_modifiers(autohead, head:sub(2), lang) headobj.term = head elseif head:find("^[!?]$") then -- If explicit head= just consists of ! or ?, add it to the end of the default head. headobj.term = autohead .. head end if head == autohead then track("redundant-head") end end end -- handle the=/def= if args.the == "~" then local newheads = {} for _, headobj in ipairs(heads) do local barehead = shallowCopy(headobj) insert(newheads, barehead) headobj.term = "the " .. headobj.term insert(newheads, headobj) end heads = newheads elseif args.the then local the = require(yesno_module)(args.the) if the then for _, headobj in ipairs(heads) do headobj.term = "the " .. headobj.term end end end local data = { lang = lang, pos_category = poscat, categories = {}, heads = heads, user_specified_heads = user_specified_heads, -- We use our own splitting algorithm so the redundant head cat will be inaccurate. no_redundant_head_cat = true, inflections = {}, nomultiwordcat = args.nomultiwordcat, sort_key = args.sort, pagename = pagename, id = args.id, force_cat_output = force_cat, } local function inscat(cat) insert(data.categories, langname .. " " .. cat) end local is_suffix = false if args.suffix or not args.nosuffix and pagename:find("^%-") and not pagename:find("^%-%-") and poscat ~= "suffix forms" then is_suffix = true data.pos_category = "suffixes" local singular_poscat = singularize(poscat) inscat(singular_poscat .. "-maciende geendunga") insert(data.inflections, {label = singular_poscat .. "-maciende geendung"}) end if pos_func then pos_func(args, data, is_suffix) end local extra_categories = {} if pagename:find("[Qq]") then -- Check for q not followed by u. We want to exclude things like [[13q deletion syndrome]] and [[BFOQ]] that -- don't have a lowercase letter on either side, as well as things like [[& seq.]] and [[acq.]] that are -- abbreviations for words containing a following u. -- -- Approximate range of combining diacritics; we want to remove them so the checks below for -- a lowercase letter next to the q aren't tripped up by diacritics on the letter. local u300 = u(0x0300) local u36F = u(0x036F) local pagename_no_diacritics = ugsub(toNFD(pagename), "[" .. u300 .. "-" .. u36F .. "]", "") if pagename_no_diacritics:find("[Qq][a-tv-z]") or pagename_no_diacritics:find("[a-z]q[^u.]") or pagename_no_diacritics:find("[a-z]q$") then inscat("words containing Q not followed by U") end end -- toNFD performs decomposition, so letters that decompose to an ASCII -- vowel and a diacritic, such as é, are counted as vowels and do not do not -- need to be included in the pattern. if not umatch(ulower(toNFD(pagename)), "[aeiouyæœøəªºαεηιουω]") then inscat("words spelled without vowels") end if pagename:find("yre$") then inscat('word endiende in "-yre"') end if not pagename:find(" ") and ulen(pagename) >= 25 then insert(extra_categories, "Lange " .. langname .. " word") end if pagename:find("^[^aeiou ]*a[^aeiou ]*e[^aeiou ]*i[^aeiou ]*o[^aeiou ]*u[^aeiou ]*$") then inscat("words that use all vowels in alphabetical order") end parse_and_insert_inflection(data, args, "abbr", "abbreviation") if args.json then return toJSON(data) end return full_headword(data) .. (extra_categories[1] and format_categories(extra_categories, lang, args.sort) or "") end local function make_default_witmetendlic(word) if word == "good" or word == "well" then return {"better"} elseif word == "bad" or word == "badly" then return {"worse"} elseif word == "far" then return {"further", "farther"} else return {add_suffix(word, "r")} end end local function make_default_superlative(word) if word == "good" or word == "well" then return {"best"} elseif word == "bad" or word == "badly" then return {"worst"} elseif word == "far" then return {"furthest", "farthest"} else return {add_suffix(word, "st.superlative")} end end -- This function does the common work between adjectives and adverbs. local function process_witmetendlic_args(data, args, plpos) local pagename = data.pagename local comps = parse_inflection(args, 1) local sups = parse_inflection(args, "sup") local outcomps, outsups if args.componly then if comps[1] then error("Ne cann specify witmetendlic word of witmetendlic-only " .. plpos) end insert(data.inflections, {label = glossary_link("witmetendlic") .. " form only"}) insert(data.categories, langname .. " witmetendlic-only " .. plpos) -- Set to empty list so we don't get any comparatives output, but process superlatives if specified. outcomps = {} if not sups[1] then -- Set to empty list so we don't get any superlatives output unless explicitly given. outsups = {} end elseif args.suponly then if comps[1] or sups[1] then error("Can't specify witmetendlice or oferstigendlice word of or superlative-only " .. plpos) end insert(data.inflections, {label = glossary_link("oferstigendlic") .. " form only"}) insert(data.categories, langname .. " oferstigendlic-only " .. plpos) return end -- If the first parameter is ?, then don't show anything, just return. if comps[1] and comps[1].term == "?" then if comps[2] then error("Ne cann specify additional witmetendlice word along with '?'") end if sups[1] then error("Ne cann specify oferstigendlice word along with '?' for the witmetendlic") end return end if comps[1] and comps[1].term == "-" then local hyphencomp = remove(comps, 1) -- Remove the "-" but retain for decorations. -- Not (generally) comparable; may occasionally have a comparative if comps[1] then insert_fixed_inflection(data, "naht generally <<witmetendlic>>", hyphencomp) elseif not sups[1] then insert_fixed_inflection(data, "naht <<witmetendlic>>", hyphencomp) insert(data.categories, langname .. " unwitmetendlic " .. plpos) return else -- No comparative, but a superlative. insert_inflection() will correctly generate 'no comparative' if we -- pass in "-" as the value. outcomps = {hyphencomp} end elseif not comps[1] then comps = {{term = "more"}} end if not outcomps then -- not if we set `outcomps` to "-" above or processed a comparative-only term outcomps = {} -- Go over each parameter given and create a comparative and superlative form. for _, compobj in ipairs(comps) do local comp = compobj.term if comp == "-" then error("Witmetendlic of '-' only allowed as first witmetendlic") end if comp == "+" then comp = "+more" elseif comp == "more" and pagename ~= "many" and pagename ~= "much" then comp = "+more" elseif comp == "further" and pagename ~= "far" then comp = "+further" elseif comp == "better" and pagename ~= "good" and pagename ~= "well" then comp = "+better" elseif comp:find("~") then comp = comp:gsub("~", replacement_escape(pagename)) end compobj.origterm = comp if comp == "+more" then comp = "more [[" .. pagename .. "]]" elseif comp == "+further" then comp = {"further [[" .. pagename .. "]]", "farther [[" .. pagename .. "]]"} elseif comp == "+better" then comp = "better [[" .. pagename .. "]]" elseif comp == "er" then -- Add -er. comp = add_suffix(pagename, "r") elseif comp == "ier" then if pagename:sub(-1) ~= "y" then error("Can't specify 'ier' witmetendlic unless the term ends with 'y': " .. pagename) end comp = pagename:gsub("e?y$", "ier") elseif comp:find("^%+") then local special = m_headword_utilities.get_special_indicator(comp, "noerror") if special then comp = m_headword_utilities.handle_multiword(pagename, special, make_default_witmetendlic) end end if type(comp) == "table" and not comp[2] then comp = comp[1] end if type(comp) == "table" then for i = 1, #comp - 1 do local outobj = shallowCopy(compobj) outobj.term = comp[i] insert(outcomps, outobj) end compobj.term = comp[#comp] insert(outcomps, compobj) else compobj.term = comp insert(outcomps, compobj) end end end if sups[1] and sups[1].term == "-" then if sups[2] then error("Can't specify '-' as superlative followed by further values") end -- No superlative. insert_inflection() will correctly generate 'no superlative' if we pass in "-" as the value. outsups = sups else if not sups[1] then sups = {{term = "+"}} end end -- `outsups` will be set if we set `outsups` to "-" above or processed a comparative-only term without superlatives. if not outsups then outsups = {} local function process_sup(sup, special, supobj, compobj) if special then sup = m_headword_utilities.handle_multiword(pagename, special, make_default_superlative) elseif sup == "-" or sup == "+" then error(("Internal error: Oferstigendlic value of '%s' should have been handled earlier"):format(sup)) elseif sup == "+most" then sup = "most [[" .. pagename .. "]]" elseif sup == "+furthest" then sup = {"furthest [[" .. pagename .. "]]", "farthest [[" .. pagename .. "]]"} elseif sup == "+best" then sup = "best [[" .. pagename .. "]]" elseif sup == "est" then -- Add -est. sup = add_suffix(pagename, "st.oferstigendlic") elseif sup == "iest" then if pagename:sub(-1) ~= "y" then error("Can't specify 'iest' oferstigendlic unless the term ends with 'y': " .. pagename) end sup = pagename:gsub("e?y$", "iest") end if type(sup) == "table" and not sup[2] then sup = sup[1] end if compobj then supobj = shallowCopy(supobj) supobj = m_headword_utilities.combine_termobj_decorations(supobj, compobj) end if type(sup) == "table" then for i = 1, #sup - 1 do local outobj = shallowCopy(supobj) outobj.term = sup[i] insert(outsups, outobj) end supobj.term = sup[#sup] insert(outsups, supobj) else supobj.term = sup insert(outsups, supobj) end end for _, supobj in ipairs(sups) do local sup = supobj.term if sup == "-" then error("Oferstigendlic of '-' only allowed as first oferstigendlic word") end if sup == "+" then if not comps[1] then error("Oferstigendlic of '+' can't be specified when there are no witmetendlice") end for _, compobj in ipairs(comps) do local comp = compobj.origterm local special if comp == "+more" then sup = "+most" elseif comp == "+further" then sup = "+furthest" elseif comp == "+better" then sup = "+best" elseif comp == "er" then sup = "est" elseif comp == "ier" then sup = "iest" else if comp:find("^%+") then special = m_headword_utilities.get_special_indicator(comp, "noerror") end if not special then -- If the full comparative was given, then derive the superlative by replacing -er with -- -est. if comp:sub(-2) == "er" then sup = comp:sub(1, -3) .. "est" else error(("The oferstigendlic word cannot be derived automatically from witmetendlic '%s' because it doesn't end in -er"):format(comp)) end end end process_sup(sup, special, supobj, compobj) end else local special = m_headword_utilities.get_special_indicator(sup, "noerror") -- Do some work here rather than in process_sup() so we don't end up double-processing a term with a '~' -- in it or a term that happens to be 'most' or similar after substitution of ~ in the comparative. if not special then if sup == "most" and pagename ~= "many" and pagename ~= "much" then sup = "+most" elseif sup == "furthest" and pagename ~= "far" then sup = "+furthest" elseif sup == "best" and pagename ~= "good" and pagename ~= "well" then sup = "+best" elseif sup:find("~") then sup = sup:gsub("~", replacement_escape(pagename)) end end process_sup(sup, special, supobj) end end end insert_inflection(data, outcomps, "<<witmetendlic>>", "witmetendlic") insert_inflection(data, outsups, "<<oferstigendlic>>", "oferstigendlic") end pos_functions["adjectives"] = { params = { [1] = list_param, ["comp_qual"] = {list = "comp\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the witmetendlic value", }, ["sup"] = list_param, ["sup_qual"] = {list = "sup\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the oferstigendlic value", }, ["componly"] = boolean_param, ["suponly"] = boolean_param, }, func = function(args, data) -- Process the comparatives and superlatives. process_witmetendlic_args(data, args, "adjectives") end, } pos_functions["adverbs"] = { params = { [1] = list_param, ["comp_qual"] = {list = "comp\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the witmetendlic value", }, ["sup"] = list_param, ["sup_qual"] = {list = "sup\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the oferstigendlic value", }, ["componly"] = boolean_param, ["suponly"] = boolean_param, }, func = function(args, data) -- Process the comparatives and superlatives. process_witmetendlic_args(data, args, "adverbs") end, } local function escape(str) return (str:gsub("\\([:#])", "\\\\%1") :gsub("[:#]", "\\%0")) end local function canonicalize_plural(pl, pagename, pos) if pl == "+" then return escape(add_suffix(pagename, "s.plural", pos)) elseif pl == "++" then return escape(compute_plusplus_s_form(pagename, add_suffix(pagename, "s.plural", pos))) elseif pl == "*" then return escape(pagename) elseif pl == "ies" then if pagename:sub(-1) == "y" then return escape(pagename:gsub("e?y$", pl)) end error("Ne cann nemnet 'ies' manigfeald on laes se word endat wit 'y'.") elseif pl == "s" or pl == "es" or pl == "'s" then return escape(pagename .. pl) end end local function do_naman(args, data, pos) local pagename = data.pagename pos = pos or "nama" local plurals = parse_inflection(args, 1) local function insert_plurale_tantum_inflections(is_plural_only, originating_label) if args.sg[1] then insert_fixed_inflection(data, "gewunelice manigfeald", originating_label) parse_and_insert_inflection(data, args, "anf", "anfeald") elseif is_plural_only then insert_fixed_inflection(data, "manigfeald anlic", originating_label) end if args.attr[1] then parse_and_insert_inflection(data, args, "attr", "attributive") end end local function first_pl_term() return plurals[1] and plurals[1].term or nil end if first_pl_term() == "p" then -- plurale tantum if plurals[2] then error("With plurale tantum noun, can't specify more than one manigfeald") end data.genders = {"p"} -- this should auto-insert the correct 'pluralia tantum' category insert_plurale_tantum_inflections("manigfealdic anlic", plurals[1]) return end local function inscat(cat) insert(data.categories, langname .. " " .. cat) end local need_default_plural = pos == "nama" if first_pl_term() == "sp" then -- construed as singular or plural sp = remove(plurals, 1) -- Remove the "sp" but retain it for its decorations. inscat("naman macat eallswa anfealdic otte manigfealdic") data.genders = {"s", "p"} -- this should auto-insert the correct 'pluralia tantum' category insert_plurale_tantum_inflections(nil, sp) need_default_plural = false elseif first_pl_term() == "-" then -- Uncountable noun; may occasionally have a plural local hyphpl = remove(plurals, 1) -- Remove the "-" but retain for decorations. inscat("untellende naman") -- If plural forms were given explicitly, then show "usually" if plurals[1] then insert_fixed_inflection(data, "gewunelice <<untellende>>", hyphpl) else insert_fixed_inflection(data, "<<untellende>>", hyphpl) end need_default_plural = false elseif first_pl_term() == "#" then -- Usually tellende (e.g., "grilled cheese") local hashpl = remove(plurals, 1) -- Remove the "#" but retain for decorations. insert_fixed_inflection(data, "gewunelice <<tellende>>", hashpl) inscat("untellende naman") inscat("tellende naman") -- If no plural was given, add a default one now if not plurals[1] then plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end elseif first_pl_term() == "~" then -- Mixed countable/uncountable noun, always has a plural local tildepl = remove(plurals, 1) -- Remove the "~" but retain for decorations. insert_fixed_inflection(data, "<<tellende>> and <<untellende>>", tildepl) inscat("untellende naman") inscat("tellende naman") -- If no plural was given, add a default one now if not plurals[1] then plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end end -- Plural is unknown if first_pl_term() == "?" then local questionpl = remove(plurals, 1) -- Remove the "?" but retain for decorations. -- insert_fixed_inflection(data, "manigfeald unknown or uncertain", questionpl) inscat("naman with unknown or uncertain manigfealde") if plurals[1] then error("Can't specify explicit manigfealde along with '?' for unknown/uncertain manigfeald") end return end -- Plural is not attested if first_pl_term() == "!" then local exclampl = remove(plurals, 1) -- Remove the "!" but retain for decorations. insert_fixed_inflection(data, "manigfeald ne weahte", exclampl) inscat("naman with ne weahte manigfealde word") if plurals[1] then error("Can't specify explicit manigfealde along with '!' for ne weahte manigfeald") end return end -- If no plural was given, maybe add a default one, otherwise (when "-" was given or proper noun) return. if not plurals[1] then if not need_default_plural then inscat("untellende naman") return end plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end -- There are plural forms to show, so show them. inscat("tellende naman") local irregular, indeclinable for i, pl in ipairs(plurals) do local canon_pl = canonicalize_plural(pl.term, pagename, pos) if canon_pl then pl.term = canon_pl end local pl_term = get_link_page(pl.term, lang) if not (pagename:find(" ") or is_regular_plural(pl_term, pagename)) then irregular = true if pl_term == pagename then indeclinable = true end end end if irregular then inscat("naman with ungewunelic manigfealde") end if indeclinable then inscat("undeclinigendlic naman") end insert_inflection(data, plurals, "manigfeald", "mnf") end -- Return the parameters to be used for nouns and proper nouns. Currently the same. local nama_params = { [1] = list_param, ["pl\1qual"] = {list = true, allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the manigfeald", }, -- The following four only used for pluralia tantum (1=p) ["sg"] = list_param, ["attr"] = list_param, } pos_functions["naman"] = { params = nama_params, func = do_naman, } pos_functions["āgennaman"] = { params = nama_params, func = function(args, data) return do_naman(args, data, "āgennama") end, } local function base_default_verb_forms(verb) return escape(add_suffix(verb, "s.verb")), escape(add_suffix(verb, "ing")), escape(add_suffix(verb, "d")) end local function default_verb_forms(verb) local full_s_form, full_ing_form, full_ed_form = base_default_verb_forms(verb) if verb:find(" ") then local first, rest = verb:match("^(.-)( .*)$") local first_s_form, first_ing_form, first_ed_form = base_default_verb_forms(first) return full_s_form, full_ing_form, full_ed_form, first_s_form .. rest, first_ing_form .. rest, first_ed_form .. rest, first, rest else return full_s_form, full_ing_form, full_ed_form, nil, nil, nil, nil, nil end end local function compute_double_last_cons_stem_of_split_verb(verb, ending) local first, rest = verb:match("^(.-)( .*)$") if not first then error("Verb '" .. verb .. "' must have a space in it to use **") end local last_cons = first:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("First word '" .. first .. "' must end in a consonant to use **") end return first .. last_cons .. ending .. rest end local function check_non_nil_star_form(form, pagename) if form == nil then error("Verb '" .. pagename .. "' must have a space in it to use *, **, *l, *! or *'") end return form end local function sub_tilde(form, pagename) if not form then return nil end if form:find("~") then form = form:gsub("~", replacement_escape(pagename)) end return form end local deprecated_qual_replaced_by_inline_modifier = { list = true, allow_holes = true, replaced_by = false, instead = "use an inline modifier <q:...> or <l:...> on the value" } pos_functions["verbs"] = { params = { [1] = {list = "pres_3sg", disallow_holes = true}, ["pres_3sg\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [2] = {list = "pres_ptc", disallow_holes = true}, ["pres_ptc\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [3] = {list = "past", disallow_holes = true}, ["past\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [4] = {list = "past_ptc", allow_holes = true}, ["past_ptc\1_qual"] = deprecated_qual_replaced_by_inline_modifier, ["noautolinkverb"] = boolean_param, ["angle_bracket"] = boolean_param, }, func = function(args, data) -- Get parameters local par1s local par2s = parse_inflection(args, {2, "pres_ptc"}) local par3s = parse_inflection(args, {3, "past"}) local par4s = parse_inflection(args, {4, "past_ptc"}) local pres_3sgs, pres_ptcs, pasts, past_ptcs local pagename = data.pagename ------------------------------------------- UTILITY FUNCTIONS #2 ------------------------------------------ -- These functions are used in both in the separate-parameter format and in the override params such as past_ptc2=. local full_default_s, full_default_ing, full_default_ed, split_default_s, split_default_ing, split_default_ed local lemma local function set_lemma_and_default_forms(the_lemma) lemma = the_lemma full_default_s, full_default_ing, full_default_ed, split_default_s, split_default_ing, split_default_ed, lemma_first, lemma_rest = default_verb_forms(the_lemma) end local function canonicalize_s_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_s elseif form == "*" then return check_non_nil_star_form(split_default_s, lemma) elseif form == "++" then return compute_plusplus_s_form(lemma, full_default_s) elseif form == "**" then if lemma:find("^[^ ]*[szx] ") then return compute_double_last_cons_stem_of_split_verb(lemma, "es") else return check_non_nil_star_form(split_default_s, lemma) end elseif form == "+!" then return lemma .. "s" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "s" .. lemma_rest elseif form == "+'" then return lemma .. "'s" elseif form == "*'" then return check_non_nil_star_form(lemma_first) .. "'s" .. lemma_rest elseif form == "+l" then if lemma:find("[szx]$") then return {{term = full_default_s, l = {"US"}}, {term = compute_plusplus_s_form(lemma, full_default_s), l = {"UK"}}} else return compute_plusplus_s_form(lemma, full_default_s) end elseif form == "*l" then if lemma:find("^[^ ]*[szx] ") then return {{term = check_non_nil_star_form(split_default_s, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "es"), l = {"UK"}}} else return check_non_nil_star_form(split_default_s, lemma) end else return sub_tilde(form, lemma) end end local function canonicalize_ing_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_ing elseif form == "*" then return check_non_nil_star_form(split_default_ing, lemma) elseif form == "++" then return compute_double_last_cons_stem(lemma) .. "ing" elseif form == "**" then return compute_double_last_cons_stem_of_split_verb(lemma, "ing") elseif form == "+!" then return lemma .. "ing" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "ing" .. lemma_rest elseif form == "+'" then return lemma .. "'ing" elseif form == "*'" then return check_non_nil_star_form(lemma_first) .. "'ing" .. lemma_rest elseif form == "+l" then return {{term = full_default_ing, l = {"US"}}, {term = compute_double_last_cons_stem(lemma) .. "ing", l = {"UK"}}} elseif form == "*l" then return {{term = check_non_nil_star_form(split_default_ing, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "ing"), l = {"UK"}}} else return sub_tilde(form, lemma) end end local function canonicalize_ed_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_ed elseif form == "*" then return check_non_nil_star_form(split_default_ed, lemma) elseif form == "++" then return compute_double_last_cons_stem(lemma) .. "ed" elseif form == "+!" then return lemma .. "ed" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "ed" .. lemma_rest elseif form == "+'" then return {{term = lemma .. "'d"}, {term = lemma .. "'ed"}} elseif form == "*'" then return {{term = check_non_nil_star_form(lemma_first) .. "'d" .. lemma_rest}, {term = check_non_nil_star_form(lemma_first) .. "'ed" .. lemma_rest}} elseif form == "**" then return compute_double_last_cons_stem_of_split_verb(lemma, "ed") elseif form == "+l" then return {{term = full_default_ed, l = {"US"}}, {term = compute_double_last_cons_stem(lemma) .. "ed", l = {"UK"}}} elseif form == "*l" then return {{term = check_non_nil_star_form(split_default_ed, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "ed"), l = {"UK"}}} else return sub_tilde(form, lemma) end end -- FIXME: options should be "+", "*", "++", "**", "+n", "*n", "++n" and "**n", but not "n" local function canonicalize_en_form(form) if form == "n" then track("n4") return add_suffix(lemma, "n") end return canonicalize_ed_form(form) end --------------------------------- MAIN PARSING/CONJUGATING CODE -------------------------------- local is_angle_bracket = args.angle_bracket if is_angle_bracket then if par2s[1] or par3s[1] or par4s[1] then error("Can't specify explicit values for 2=, 3= or 4= along with the angle-bracket format") end elseif is_angle_bracket == nil and not par2s[1] and not par3s[1] and not par4s[1] and not args[1][2] and args[1][1] and args[1][1]:find("<") then if put.term_contains_top_level_html(args[1][1]) then -- Often, term_contains_top_level_html() returns true on the angle-bracket format, which would -- make the pcall() below succeed but leave the angle brackets as-is. Check for this and only do the -- pcall() if term_contains_top_level_html() returns false. is_angle_bracket = true else -- If it's ambiguous whether it's an angle-bracket format or separate params with an inline modifier, -- try to parse as the latter. If an error occurs, treat as the former. local ok ok, par1s = pcall(parse_inflection, args, {1, "pres_3sg"}) if not ok then par1s = nil is_angle_bracket = true end end end if is_angle_bracket then -------------------------- ANGLE-BRACKET FORMAT -------------------------- -- (0) Expand multiword term with angle brackets just on the first word. local arg11 = args[1][1] if arg11:find("^<.*>$") and pagename:find(" ") then local first, rest = pagename:match("^(.-)( .*)$") arg11 = first .. arg11 .. rest end -- (1) Parse the indicator specs inside of angle brackets. local function parse_indicator_spec(angle_bracket_spec) local inside = angle_bracket_spec:match("^<(.*)>$") assert(inside) local segments = put.parse_balanced_segment_run(inside, "[", "]") local comma_separated_groups = put.split_alternating_runs(segments, ",") if #comma_separated_groups > 4 then error("Too many comma-separated parts in indicator spec, expected at most 4: " .. angle_bracket_spec) end local function fetch_footnotes(separated_group) local footnotes for j = 2, #separated_group - 1, 2 do if separated_group[j + 1] ~= "" then error("Extraneous text after bracketed footnotes: '" .. concat(separated_group) .. "'") end if not footnotes then footnotes = {} end insert(footnotes, separated_group[j]) end return footnotes end local function fetch_specs(comma_separated_group) if not comma_separated_group then return {{term = "+"}} end local specs = {} local colon_separated_groups = put.split_alternating_runs(comma_separated_group, ":") for _, colon_separated_group in ipairs(colon_separated_groups) do local form = colon_separated_group[1] if form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then error("*, **, *l, *! and *' not allowed inside of indicator specs: " .. angle_bracket_spec) end if form == "" then form = "+" end local termobj = { term = form } local footnotes = fetch_footnotes(colon_separated_group) if footnotes then for _, footnote in ipairs(footnotes) do m_headword_utilities.add_footnote_to_termobj(termobj, footnote) end end insert(specs, termobj) end return specs end local s_specs = fetch_specs(comma_separated_groups[1]) local ing_specs = fetch_specs(comma_separated_groups[2]) local ed_specs = fetch_specs(comma_separated_groups[3]) local en_specs = fetch_specs(comma_separated_groups[4]) return { forms = {}, s_specs = s_specs, ing_specs = ing_specs, ed_specs = ed_specs, en_specs = en_specs, } end local parse_props = { parse_indicator_spec = parse_indicator_spec, } local alternant_multiword_spec = iut.parse_inflected_text(arg11, parse_props) -- (2) Check for user-specified brackets; remove any links from the lemma, but remember the original -- form so we can use it below in the 'lemma_linked' form. -- Check to see if there are brackets in the pre-text or post-text. If so, use the linked lemma (with the -- verb autolinked unless noautolinkverb is given). Otherwise, use the default headword algorithm. local function check_bracket(val) if val:find("%[%[") then alternant_multiword_spec.saw_bracket = true end end for _, alternant_or_word_spec in ipairs(alternant_multiword_spec.alternant_or_word_specs) do check_bracket(alternant_or_word_spec.before_text) if alternant_or_word_spec.alternants then for _, multiword_spec in ipairs(alternant_or_word_spec.alternants) do for _, word_spec in ipairs(multiword_spec.word_specs) do check_bracket(word_spec.before_text) end check_bracket(multiword_spec.post_text) end end end check_bracket(alternant_multiword_spec.post_text) iut.map_word_specs(alternant_multiword_spec, function(base) if base.lemma == "" then base.lemma = pagename end base.orig_lemma = base.lemma base.lemma = remove_links(base.lemma) if args.noautolinkverb or base.orig_lemma:find("%[%[") then base.linked_lemma = base.orig_lemma else base.linked_lemma = "[[" .. base.orig_lemma .. "]]" end end) -- (3) Conjugate the verbs according to the indicator specs parsed above. local all_verb_slots = { lemma = "ungeendigendlic", lemma_linked = "ungeendigendlic", s_form = "3|s|pres", ing_form = "pres|ptcp", ed_form = "past", en_form = "past|ptcp", } local function conjugate_verb(base) local function process_specs(slot, specs, canon_func, default_values, default_already_formobj) local function insert_termobj_into_slot(termobj) local formobj = m_headword_utilities.convert_termobj_to_formobj(termobj) -- If the form is -, don't insert any forms, which will result in there being no overall forms -- (in fact it will be nil). We check for that down below and substitute a single "-" as the -- form, which in turn gets turned into special labels like "no present participle". if formobj.form == "-" then if formobj.footnotes then error("Unable to preserve footnotes specified on missing form '-': FIXME: " .. dump(formobj.footnotes)) end else iut.insert_form(base.forms, slot, formobj) end end local function canonicalize_and_insert(arg) local canon_arg = canon_func(arg) if type(canon_arg) == "string" then arg.term = canon_arg insert_termobj_into_slot(arg) else for _, canon in ipairs(canon_arg) do m_headword_utilities.combine_termobj_decorations(canon, arg) insert_termobj_into_slot(canon) end end end for _, arg in ipairs(specs) do if arg.term == "+" then if default_values then -- will be nil if past tense specified as - and no past ptc given for _, val in ipairs(default_values) do val = shallowCopy(val) if default_already_formobj then local argformobj = m_headword_utilities.convert_termobj_to_formobj(arg) val.footnotes = iut.combine_footnotes(val.footnotes, argformobj.footnotes) iut.insert_form(base.forms, slot, val) else m_headword_utilities.combine_termobj_decorations(val, arg) canonicalize_and_insert(val) end end end else canonicalize_and_insert(arg) end end end set_lemma_and_default_forms(base.lemma) local all_part_default_specs = {} local function process_and_canonicalize_s_form(arg) local form = arg.term if form == "+" then error("Internal error: '+' should have been converted to '^' by now") end if form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then error(("Internal error: '%s' should have already thrown an error"):format(form)) end if form == "^" or form == "++" or form == "+l" or form == "+!" or form == "+'" then insert(all_part_default_specs, shallowCopy(arg)) end return canonicalize_s_form(form) end process_specs("s_form", base.s_specs, process_and_canonicalize_s_form, {{term = "^"}}) if not all_part_default_specs[1] then all_part_default_specs[1] = {term = "^"} end process_specs("ing_form", base.ing_specs, function(arg) return canonicalize_ing_form(arg.term) end, all_part_default_specs) process_specs("ed_form", base.ed_specs, function(arg) return canonicalize_ed_form(arg.term) end, all_part_default_specs) process_specs("en_form", base.en_specs, function(arg) return canonicalize_en_form(arg.term) end, base.forms.ed_form, "default already formobj") iut.insert_form(base.forms, "lemma", {form = base.lemma}) -- Add linked version of lemma for use in head=. We write this in a general fashion in case -- there are multiple lemma forms (which isn't possible currently at this level, although it's -- possible overall using the ((...,...)) notation). iut.insert_forms(base.forms, "lemma_linked", iut.map_forms(base.forms.lemma, function(form) if form == base.lemma and base.linked_lemma:find("%[%[") then return base.linked_lemma else return form end end)) end local inflect_props = { slot_table = all_verb_slots, inflect_word_spec = conjugate_verb, } iut.inflect_multiword_or_alternant_multiword_spec(alternant_multiword_spec, inflect_props) -- (4) Fetch the forms and put the conjugated lemmas in data.heads if not explicitly given. local function fetch_termobjs(slot) local forms = alternant_multiword_spec.forms[slot] -- See above. This should only occur if the user explicitly used - for a spec. if not forms or not forms[1] then return {{term = "-"}} end local termobjs = {} for _, formobj in ipairs(forms) do insert(termobjs, m_headword_utilities.convert_formobj_to_termobj(formobj)) end return termobjs end pres_3sgs = fetch_termobjs("s_form") pres_ptcs = fetch_termobjs("ing_form") pasts = fetch_termobjs("ed_form") past_ptcs = fetch_termobjs("en_form") -- Use the "linked" form of the lemma as the head if no head= explicitly given and the user specified -- brackets in one of the lemmas. Otherwise we use the default headword-linking algorithm. if not data.user_specified_heads[1] and alternant_multiword_spec.saw_bracket then data.heads = {} for _, lemma_obj in ipairs(alternant_multiword_spec.forms.lemma_linked) do insert(data.heads, m_headword_utilities.convert_formobj_to_termobj(lemma_obj)) end end else -------------------------- SEPARATE-PARAM FORMAT -------------------------- set_lemma_and_default_forms(pagename) par1s = par1s or parse_inflection(args, {1, "pres_3sg"}) pres_3sgs = {} pres_ptcs = {} pasts = {} past_ptcs = {} if not par1s[1] then par1s = {{term = "+"}} end if not par2s[1] then par2s = {{term = "+"}} end if not par3s[1] then par3s = {{term = "+"}} end if not par4s[1] then par4s = {{term = "+"}} end local function process_argument(args, dest, canon_func, default_values, default_already_canonicalized) local function canonicalize_and_insert(arg) local canon_arg = canon_func(arg) if type(canon_arg) == "string" then arg.term = canon_arg m_headword_utilities.insert_termobj_combining_duplicates(dest, arg) else for _, canon in ipairs(canon_arg) do m_headword_utilities.combine_termobj_decorations(canon, arg) m_headword_utilities.insert_termobj_combining_duplicates(dest, canon) end end end for _, arg in ipairs(args) do if arg.term == "+" then for _, val in ipairs(default_values) do val = shallowCopy(val) m_headword_utilities.combine_termobj_decorations(val, arg) if default_already_canonicalized then m_headword_utilities.insert_termobj_combining_duplicates(dest, val) else canonicalize_and_insert(val) end end else canonicalize_and_insert(arg) end end end local all_part_default_specs = {} local function process_and_canonicalize_s_form(arg) local form = arg.term if form == "+" then error("Internal error: '+' should have been converted to '^' by now") end if form == "^" or form == "++" or form == "+l" or form == "+!" or form == "+'" or form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then insert(all_part_default_specs, shallowCopy(arg)) end return canonicalize_s_form(form) end process_argument(par1s, pres_3sgs, process_and_canonicalize_s_form, {{term = "^"}}) if not all_part_default_specs[1] then all_part_default_specs[1] = {term = "^"} end process_argument(par2s, pres_ptcs, function(arg) return canonicalize_ing_form(arg.term) end, all_part_default_specs) process_argument(par3s, pasts, function(arg) return canonicalize_ed_form(arg.term) end, all_part_default_specs) process_argument(par4s, past_ptcs, function(arg) return canonicalize_en_form(arg.term) end, pasts, "default already canonicalized") end ------------------------------------------- INSERT INFLECTIONS ------------------------------------------ insert_inflection(data, pres_3sgs, "third-person singular simple present", "s-verb-form") insert_inflection(data, pres_ptcs, "present participle", "ing-form") if deepEquals(pasts, past_ptcs) then insert_inflection(data, pasts, "simple past and past participle", "ed-form", "no simple past or past participle") else insert_inflection(data, pasts, "simple past", "spast") insert_inflection(data, past_ptcs, "past participle", "past|part") end if pagename:find(" ") then -- Check for placeholder "it" local words = split(pagename, " ") for _, word in ipairs(words) do if word == "it" or word == "its" or word == "it's" then insert(data.categories, langname .. ' terms with placeholder "it"') break end end -- Check for phrasal verbs local phrasal_adverbs = list_to_set{ -- NOTE: This should only contain common phrasal adverbs, not random words like [[low]], -- [[adrift]], etc. "aback", "about", "above", "across", "after", "against", "ahead", "along", "apart", "around", "as", "aside", "at", "away", "back", "before", "behind", "below", "between", "beyond", "by", "down", "for", "forth", "from", "in", "into", "of", "off", "on", "onto", "out", "over", "past", "round", "through", "to", "together", "towards", "under", "up", "upon", "with", "without", } local allowed_non_adverb_words = list_to_set{ "it", "one", "oneself", "someone", } local base = pagename local seen_adverbs = {} -- Only consider a verb to be phrasal if it consists of a single base verb followed exclusively by either -- adverbs from `phrasal_adverbs` or placeholder words from `allowed_non_adverb_words`, where at -- least one following word is from `phrasal_adverbs` (hence [[can it]] is not a phrasal verb). while true do local prev, word = base:match("^(.+) (.-)$") if not prev then break end if phrasal_adverbs[word] then insert(seen_adverbs, word) elseif allowed_non_adverb_words[word] then -- do nothing else break end base = prev end if not base:find(" ") and seen_adverbs[1] then insert(data.categories, langname .. " phrasal verbs") for i = #seen_adverbs, 1, -1 do insert(data.categories, langname .. ' phrasal verbs formed with "' .. seen_adverbs[i] .. '"') end end end end, } ----------------------------------------------------------------------------------------- -- Suffix forms -- ----------------------------------------------------------------------------------------- pos_functions["geendung fiellas"] = { params = { [1] = {required = true, list = true, disallow_holes = true}, }, func = function(args, data, is_suffix) local suffix_type = {} for _, typ in ipairs(args[1]) do insert(suffix_type, typ .. "-maciende geendung") end insert(data.inflections, {label = "unfrumcenned fiell of " .. m_table.serialCommaJoin(suffix_type, {conj = "or"})}) end, } return export 3tjbcqhz0bk2kwj1jlbp3ypeiq5z0rl 54895 54894 2026-09-28T21:08:00Z Deadend0914 7211 54895 Scribunto text/plain local export = {} local pos_functions = {} --[==[ Author from 2020 on: mostly Benwing2, with significant contributions from Theknightwho. Based on a prior version by Rua (by now mostly rewritten), with contributions from Erutuon and others (see history for full attribution). ]==] local force_cat = false -- for testing; if true, categories appear in non-mainspace pages local require = require local require_when_needed = require("Module:require when needed") local en_utilities_module = "Module:en-utilities" local headword_utilities_module = "Module:headword utilities" local headword_module = "Module:headword" local inflection_utilities_module = "Module:inflection utilities" local parse_utilities_module = "Module:parse utilities" local JSON_module = "Module:JSON" local labels_module = "Module:labels" local links_module = "Module:links" local parameters_module = "Module:parameters" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local yesno_module = "Module:yesno" local iut = require_when_needed(inflection_utilities_module) local put = require_when_needed(parse_utilities_module) local m_headword_utilities = require_when_needed(headword_utilities_module) local add_links_to_multiword_term = require_when_needed(headword_utilities_module, "add_links_to_multiword_term") local add_suffix = require_when_needed(en_utilities_module, "add_suffix") local apply_link_modifiers = require_when_needed(headword_utilities_module, "apply_link_modifiers") local concat = table.concat local deepEquals = require_when_needed(table_module, "deepEquals") local dump = mw.dumpObject local format_categories = require_when_needed(utilities_module, "format_categories") local full_headword = require_when_needed(headword_module, "full_headword") local get_label_info = require_when_needed(labels_module, "get_label_info") local get_link_page = require_when_needed(links_module, "get_link_page") local glossary_link = require_when_needed(headword_utilities_module, "glossary_link") local insert = table.insert local insertIfNot = require_when_needed(table_module, "insertIfNot") local ipairs = ipairs local is_regular_plural = require_when_needed(en_utilities_module, "is_regular_plural") local list_to_set = require_when_needed(table_module, "listToSet") local pairs = pairs local process_params = require_when_needed(parameters_module, "process") local remove = table.remove local remove_links = require_when_needed(links_module, "remove_links") local replacement_escape = require_when_needed(string_utilities_module, "replacement_escape") local shallowCopy = require_when_needed(table_module, "shallowCopy") local singularize = require_when_needed(en_utilities_module, "singularize") local split = require_when_needed(string_utilities_module, "split") local toJSON = require_when_needed(JSON_module, "toJSON") local toNFD = mw.ustring.toNFD local type = type local ulen = require_when_needed(string_utilities_module, "len") local ulower = require_when_needed(string_utilities_module, "lower") local umatch = require_when_needed(string_utilities_module, "match") local u = require_when_needed(string_utilities_module, "char") local ugsub = require_when_needed(string_utilities_module, "gsub") local lang = require("Module:languages").getByCode("en") local langname = lang:getCanonicalName() local list_param = {list = true, disallow_holes = true} local list_allow_holes = {list = true, allow_holes = true} local boolean_param = {type = "boolean"} local function ine(val) if val == "" then return nil else return val end end local function track(page) require("Module:debug/track")("en-headword/" .. page) return true end ------------------------------------------- UTILITY FUNCTIONS ------------------------------------------ -- Parse and return an inflection not requiring additional processing. The raw arguments come from `args[field]`, which -- is parsed for inline modifiers. local function parse_inflection(args, field, is_head) local argfield = field if type(argfield) == "table" then argfield = argfield[1] end return m_headword_utilities.parse_term_list_with_modifiers { paramname = field, forms = args[argfield], splitchar = ",", is_head = is_head, } end -- Insert the parsed inflections in `terms` (as parsed by `parse_inflection`) into `data.inflections`, with label -- `label` and optional accelerator spec `accel`. local function insert_inflection(data, terms, label, accel, no_label) for _, termobj in ipairs(terms) do m_headword_utilities.remove_termobj_field_modifiers(termobj) end m_headword_utilities.insert_inflection { headdata = data, terms = terms, label = label, no_label = no_label, accel = accel and {form = accel} or nil, } end -- Insert a fixed label `label` into the inflections for `data`. If `originating_term` is supplied, copy the decorations -- from it into the fixed label. local function insert_fixed_inflection(data, label, originating_term) m_headword_utilities.insert_fixed_inflection { headdata = data, originating_term = originating_term, label = label, } end -- Parse and insert an inflection not requiring additional processing into `data.inflections`. The raw arguments come -- from `args[field]`, which is parsed for inline modifiers. `label` is the label that the inflections are given; -- `accel` is the accelerator form, or nil. local function parse_and_insert_inflection(data, args, field, label, accel) m_headword_utilities.parse_and_insert_inflection { headdata = data, forms = args[field], paramname = field, splitchar = ",", label = label, accel = accel and {form = accel} or nil, } end -- These functions are used directly in the <> format as well as in the utility functions #2 below. local function compute_double_last_cons_stem(term) local last_cons = term:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("Verb stem '" .. term .. "' must end in a consonant to use ++") end return term .. last_cons end local function compute_plusplus_s_form(term, default_s_form) if term:find("[szx]$") then -- regas -> regasses, derez -> derezzes return compute_double_last_cons_stem(term) .. "es" else return default_s_form end end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local iparams = { [1] = true, } local iargs = require("Module:parameters").process(frame.args, iparams) local parargs = frame:getParent().args local poscat = iargs[1] local pos_in_1 = not poscat if pos_in_1 then poscat = ine(parargs[1]) or mw.title.getCurrentTitle().fullText == "Template:en-head" and "interjection" or error("Part of speech must be specified in 1=") poscat = require(headword_module).canonicalize_pos(poscat) end local indexing_poscat = pos_in_1 and "head" or poscat local params = { ["head"] = list_param, ["id"] = true, ["json"] = boolean_param, ["sort"] = true, ["splithyph"] = boolean_param, ["nosplithyph"] = boolean_param, ["hyphspace"] = boolean_param, ["nolink"] = boolean_param, ["nolinkhead"] = {type = "boolean_param", alias_of = "nolink"}, ["suffix"] = boolean_param, ["nosuffix"] = boolean_param, ["nomultiwordcat"] = boolean_param, ["abbr"] = list_param, ["the"] = true, ["def"] = {alias_of = "the"}, ["pagename"] = true, -- for testing } if pos_in_1 then params[1] = {required = true} -- required but ignored as already processed above end local pos_data = pos_functions[indexing_poscat] local pos_func if pos_data then local pos_params = pos_data.params if pos_params then for key, val in pairs(pos_params) do params[key] = val end end pos_func = pos_data.func end local args = process_params(parargs, params) -- Account for unsupported titles, e.g. 'C|N>K' instead of 'Unsupported titles/C through N to K'. local pagename = args.pagename or mw.loadData("Module:headword/data").pagename local user_specified_heads = parse_inflection(args, "head", "is_head") local heads = user_specified_heads local autohead if args.nolink or not pagename:find("[ '%-]") then autohead = pagename else local en_no_split_apostrophe_words = list_to_set { "one's", "someone's", "he's", "she's", "it's", } local en_include_hyphen_prefixes = list_to_set { -- We don't include things that are also words even though they are often (perhaps mostly) prefixes, e.g. -- "be", "counter", "cross", "extra", "half", "mid", "over", "pan", "under". "acro", "acousto", "Afro", "agro", "anarcho", "angio", "Anglo", "ante", "anti", "arch", "auto", "bi", "bio", "cis", "co", "cryo", "crypto", "de", "demi", "eco", "electro", "Euro", "ex", "Greco", "hemi", "hydro", "hyper", "hypo", "infra", "Indo", "inter", "intra", "Judeo", "macro", "meta", "micro", "mini", "multi", "neo", "neuro", "non", "para", "peri", "post", "pre", "pro", "proto", "pseudo", "re", "semi", "sub", "super", "trans", "un", "vice", } local function is_english(term) local title = mw.title.new(term) if title and title.exists then local content = title:getContent() if content and content:find("==English==\n") then return true end end return false end local function en_split_hyphen_when_space(word) if not word:find("-", nil, true) then return nil end if args.hyphspace then return "[[" .. word:gsub("%-+", " ") .. "|" .. word .. "]]" end if args.nosplithyph then return "[[" .. word .. "]]" end if not args.splithyph then local space_word = word:gsub("%-+", " ") if is_english(space_word) then return "[[" .. space_word .. "|" .. word .. "]]" end if is_english(word) then return "[[" .. word .. "]]" end end return nil end local function en_split_apostrophe(word) local base = word:match("^(.*)'s$") if base then return "[[" .. base .. "]][[-'s|'s]]" end -- Only treat final apostrophe as possessive if preceded by something that looks like a plural ending in /z/. -- In particular we don't want to do it for words like [[truckin']]. base = word:match("^(.*[sxz])'$") if base then if base:find("s$") then local sg = singularize(base) if is_english(sg) then return "[[" .. sg .. "|" .. base .. "]][[-'|']]" end end return "[[" .. base .. "]][[-'|']]" end return "[[" .. word .. "]]" end autohead = add_links_to_multiword_term(pagename, { split_hyphen_when_space = en_split_hyphen_when_space, split_apostrophe = en_split_apostrophe, no_split_apostrophe_words = en_no_split_apostrophe_words, include_hyphen_prefixes = en_include_hyphen_prefixes, }) end if not heads[1] then heads = {{term = autohead}} else for _, headobj in ipairs(heads) do local head = headobj.term if head:find("^~") then head = apply_link_modifiers(autohead, head:sub(2), lang) headobj.term = head elseif head:find("^[!?]$") then -- If explicit head= just consists of ! or ?, add it to the end of the default head. headobj.term = autohead .. head end if head == autohead then track("redundant-head") end end end -- handle the=/def= if args.the == "~" then local newheads = {} for _, headobj in ipairs(heads) do local barehead = shallowCopy(headobj) insert(newheads, barehead) headobj.term = "the " .. headobj.term insert(newheads, headobj) end heads = newheads elseif args.the then local the = require(yesno_module)(args.the) if the then for _, headobj in ipairs(heads) do headobj.term = "the " .. headobj.term end end end local data = { lang = lang, pos_category = poscat, categories = {}, heads = heads, user_specified_heads = user_specified_heads, -- We use our own splitting algorithm so the redundant head cat will be inaccurate. no_redundant_head_cat = true, inflections = {}, nomultiwordcat = args.nomultiwordcat, sort_key = args.sort, pagename = pagename, id = args.id, force_cat_output = force_cat, } local function inscat(cat) insert(data.categories, langname .. " " .. cat) end local is_suffix = false if args.suffix or not args.nosuffix and pagename:find("^%-") and not pagename:find("^%-%-") and poscat ~= "suffix forms" then is_suffix = true data.pos_category = "suffixes" local singular_poscat = singularize(poscat) inscat(singular_poscat .. "-forming suffixes") insert(data.inflections, {label = singular_poscat .. "-forming suffix"}) end if pos_func then pos_func(args, data, is_suffix) end local extra_categories = {} if pagename:find("[Qq]") then -- Check for q not followed by u. We want to exclude things like [[13q deletion syndrome]] and [[BFOQ]] that -- don't have a lowercase letter on either side, as well as things like [[& seq.]] and [[acq.]] that are -- abbreviations for words containing a following u. -- -- Approximate range of combining diacritics; we want to remove them so the checks below for -- a lowercase letter next to the q aren't tripped up by diacritics on the letter. local u300 = u(0x0300) local u36F = u(0x036F) local pagename_no_diacritics = ugsub(toNFD(pagename), "[" .. u300 .. "-" .. u36F .. "]", "") if pagename_no_diacritics:find("[Qq][a-tv-z]") or pagename_no_diacritics:find("[a-z]q[^u.]") or pagename_no_diacritics:find("[a-z]q$") then inscat("words containing Q not followed by U") end end -- toNFD performs decomposition, so letters that decompose to an ASCII -- vowel and a diacritic, such as é, are counted as vowels and do not do not -- need to be included in the pattern. if not umatch(ulower(toNFD(pagename)), "[aeiouyæœøəªºαεηιουω]") then inscat("words spelled without vowels") end if pagename:find("yre$") then inscat('words ending in "-yre"') end if not pagename:find(" ") and ulen(pagename) >= 25 then insert(extra_categories, "Long " .. langname .. " words") end if pagename:find("^[^aeiou ]*a[^aeiou ]*e[^aeiou ]*i[^aeiou ]*o[^aeiou ]*u[^aeiou ]*$") then inscat("words that use all vowels in alphabetical order") end parse_and_insert_inflection(data, args, "abbr", "abbreviation") if args.json then return toJSON(data) end return full_headword(data) .. (extra_categories[1] and format_categories(extra_categories, lang, args.sort) or "") end local function make_default_comparative(word) if word == "good" or word == "well" then return {"better"} elseif word == "bad" or word == "badly" then return {"worse"} elseif word == "far" then return {"further", "farther"} else return {add_suffix(word, "r")} end end local function make_default_superlative(word) if word == "good" or word == "well" then return {"best"} elseif word == "bad" or word == "badly" then return {"worst"} elseif word == "far" then return {"furthest", "farthest"} else return {add_suffix(word, "st.superlative")} end end -- This function does the common work between adjectives and adverbs. local function process_comparative_args(data, args, plpos) local pagename = data.pagename local comps = parse_inflection(args, 1) local sups = parse_inflection(args, "sup") local outcomps, outsups if args.componly then if comps[1] then error("Can't specify comparatives of comparative-only " .. plpos) end insert(data.inflections, {label = glossary_link("comparative") .. " form only"}) insert(data.categories, langname .. " comparative-only " .. plpos) -- Set to empty list so we don't get any comparatives output, but process superlatives if specified. outcomps = {} if not sups[1] then -- Set to empty list so we don't get any superlatives output unless explicitly given. outsups = {} end elseif args.suponly then if comps[1] or sups[1] then error("Can't specify comparatives or superlatives of or superlative-only " .. plpos) end insert(data.inflections, {label = glossary_link("superlative") .. " form only"}) insert(data.categories, langname .. " superlative-only " .. plpos) return end -- If the first parameter is ?, then don't show anything, just return. if comps[1] and comps[1].term == "?" then if comps[2] then error("Can't specify additional comparatives along with '?'") end if sups[1] then error("Can't specify superlatives along with '?' for the comparative") end return end if comps[1] and comps[1].term == "-" then local hyphencomp = remove(comps, 1) -- Remove the "-" but retain for decorations. -- Not (generally) comparable; may occasionally have a comparative if comps[1] then insert_fixed_inflection(data, "not generally <<comparable>>", hyphencomp) elseif not sups[1] then insert_fixed_inflection(data, "not <<comparable>>", hyphencomp) insert(data.categories, langname .. " uncomparable " .. plpos) return else -- No comparative, but a superlative. insert_inflection() will correctly generate 'no comparative' if we -- pass in "-" as the value. outcomps = {hyphencomp} end elseif not comps[1] then comps = {{term = "more"}} end if not outcomps then -- not if we set `outcomps` to "-" above or processed a comparative-only term outcomps = {} -- Go over each parameter given and create a comparative and superlative form. for _, compobj in ipairs(comps) do local comp = compobj.term if comp == "-" then error("Comparative of '-' only allowed as first comparative") end if comp == "+" then comp = "+more" elseif comp == "more" and pagename ~= "many" and pagename ~= "much" then comp = "+more" elseif comp == "further" and pagename ~= "far" then comp = "+further" elseif comp == "better" and pagename ~= "good" and pagename ~= "well" then comp = "+better" elseif comp:find("~") then comp = comp:gsub("~", replacement_escape(pagename)) end compobj.origterm = comp if comp == "+more" then comp = "more [[" .. pagename .. "]]" elseif comp == "+further" then comp = {"further [[" .. pagename .. "]]", "farther [[" .. pagename .. "]]"} elseif comp == "+better" then comp = "better [[" .. pagename .. "]]" elseif comp == "er" then -- Add -er. comp = add_suffix(pagename, "r") elseif comp == "ier" then if pagename:sub(-1) ~= "y" then error("Can't specify 'ier' comparative unless the term ends with 'y': " .. pagename) end comp = pagename:gsub("e?y$", "ier") elseif comp:find("^%+") then local special = m_headword_utilities.get_special_indicator(comp, "noerror") if special then comp = m_headword_utilities.handle_multiword(pagename, special, make_default_comparative) end end if type(comp) == "table" and not comp[2] then comp = comp[1] end if type(comp) == "table" then for i = 1, #comp - 1 do local outobj = shallowCopy(compobj) outobj.term = comp[i] insert(outcomps, outobj) end compobj.term = comp[#comp] insert(outcomps, compobj) else compobj.term = comp insert(outcomps, compobj) end end end if sups[1] and sups[1].term == "-" then if sups[2] then error("Can't specify '-' as superlative followed by further values") end -- No superlative. insert_inflection() will correctly generate 'no superlative' if we pass in "-" as the value. outsups = sups else if not sups[1] then sups = {{term = "+"}} end end -- `outsups` will be set if we set `outsups` to "-" above or processed a comparative-only term without superlatives. if not outsups then outsups = {} local function process_sup(sup, special, supobj, compobj) if special then sup = m_headword_utilities.handle_multiword(pagename, special, make_default_superlative) elseif sup == "-" or sup == "+" then error(("Internal error: Superlative value of '%s' should have been handled earlier"):format(sup)) elseif sup == "+most" then sup = "most [[" .. pagename .. "]]" elseif sup == "+furthest" then sup = {"furthest [[" .. pagename .. "]]", "farthest [[" .. pagename .. "]]"} elseif sup == "+best" then sup = "best [[" .. pagename .. "]]" elseif sup == "est" then -- Add -est. sup = add_suffix(pagename, "st.superlative") elseif sup == "iest" then if pagename:sub(-1) ~= "y" then error("Can't specify 'iest' superlative unless the term ends with 'y': " .. pagename) end sup = pagename:gsub("e?y$", "iest") end if type(sup) == "table" and not sup[2] then sup = sup[1] end if compobj then supobj = shallowCopy(supobj) supobj = m_headword_utilities.combine_termobj_decorations(supobj, compobj) end if type(sup) == "table" then for i = 1, #sup - 1 do local outobj = shallowCopy(supobj) outobj.term = sup[i] insert(outsups, outobj) end supobj.term = sup[#sup] insert(outsups, supobj) else supobj.term = sup insert(outsups, supobj) end end for _, supobj in ipairs(sups) do local sup = supobj.term if sup == "-" then error("Superlative of '-' only allowed as first superlative") end if sup == "+" then if not comps[1] then error("Superlative of '+' can't be specified when there are no comparatives") end for _, compobj in ipairs(comps) do local comp = compobj.origterm local special if comp == "+more" then sup = "+most" elseif comp == "+further" then sup = "+furthest" elseif comp == "+better" then sup = "+best" elseif comp == "er" then sup = "est" elseif comp == "ier" then sup = "iest" else if comp:find("^%+") then special = m_headword_utilities.get_special_indicator(comp, "noerror") end if not special then -- If the full comparative was given, then derive the superlative by replacing -er with -- -est. if comp:sub(-2) == "er" then sup = comp:sub(1, -3) .. "est" else error(("The superlative cannot be derived automatically from comparative '%s' because it doesn't end in -er"):format(comp)) end end end process_sup(sup, special, supobj, compobj) end else local special = m_headword_utilities.get_special_indicator(sup, "noerror") -- Do some work here rather than in process_sup() so we don't end up double-processing a term with a '~' -- in it or a term that happens to be 'most' or similar after substitution of ~ in the comparative. if not special then if sup == "most" and pagename ~= "many" and pagename ~= "much" then sup = "+most" elseif sup == "furthest" and pagename ~= "far" then sup = "+furthest" elseif sup == "best" and pagename ~= "good" and pagename ~= "well" then sup = "+best" elseif sup:find("~") then sup = sup:gsub("~", replacement_escape(pagename)) end end process_sup(sup, special, supobj) end end end insert_inflection(data, outcomps, "<<comparative>>", "comparative") insert_inflection(data, outsups, "<<superlative>>", "superlative") end pos_functions["adjectives"] = { params = { [1] = list_param, ["comp_qual"] = {list = "comp\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the comparative value", }, ["sup"] = list_param, ["sup_qual"] = {list = "sup\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the superlative value", }, ["componly"] = boolean_param, ["suponly"] = boolean_param, }, func = function(args, data) -- Process the comparatives and superlatives. process_comparative_args(data, args, "adjectives") end, } pos_functions["adverbs"] = { params = { [1] = list_param, ["comp_qual"] = {list = "comp\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the comparative value", }, ["sup"] = list_param, ["sup_qual"] = {list = "sup\1_qual", allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the superlative value", }, ["componly"] = boolean_param, ["suponly"] = boolean_param, }, func = function(args, data) -- Process the comparatives and superlatives. process_comparative_args(data, args, "adverbs") end, } local function escape(str) return (str:gsub("\\([:#])", "\\\\%1") :gsub("[:#]", "\\%0")) end local function canonicalize_plural(pl, pagename, pos) if pl == "+" then return escape(add_suffix(pagename, "s.plural", pos)) elseif pl == "++" then return escape(compute_plusplus_s_form(pagename, add_suffix(pagename, "s.plural", pos))) elseif pl == "*" then return escape(pagename) elseif pl == "ies" then if pagename:sub(-1) == "y" then return escape(pagename:gsub("e?y$", pl)) end error("Can't specify 'ies' plural unless the term ends with 'y'.") elseif pl == "s" or pl == "es" or pl == "'s" then return escape(pagename .. pl) end end local function do_nouns(args, data, pos) local pagename = data.pagename pos = pos or "noun" local plurals = parse_inflection(args, 1) local function insert_plurale_tantum_inflections(is_plural_only, originating_label) if args.sg[1] then insert_fixed_inflection(data, "normally plural", originating_label) parse_and_insert_inflection(data, args, "sg", "singular") elseif is_plural_only then insert_fixed_inflection(data, "plural only", originating_label) end if args.attr[1] then parse_and_insert_inflection(data, args, "attr", "attributive") end end local function first_pl_term() return plurals[1] and plurals[1].term or nil end if first_pl_term() == "p" then -- plurale tantum if plurals[2] then error("With plurale tantum noun, can't specify more than one plural") end data.genders = {"p"} -- this should auto-insert the correct 'pluralia tantum' category insert_plurale_tantum_inflections("plural only", plurals[1]) return end local function inscat(cat) insert(data.categories, langname .. " " .. cat) end local need_default_plural = pos == "noun" if first_pl_term() == "sp" then -- construed as singular or plural sp = remove(plurals, 1) -- Remove the "sp" but retain it for its decorations. inscat("nouns construed as singular or plural") data.genders = {"s", "p"} -- this should auto-insert the correct 'pluralia tantum' category insert_plurale_tantum_inflections(nil, sp) need_default_plural = false elseif first_pl_term() == "-" then -- Uncountable noun; may occasionally have a plural local hyphpl = remove(plurals, 1) -- Remove the "-" but retain for decorations. inscat("uncountable nouns") -- If plural forms were given explicitly, then show "usually" if plurals[1] then insert_fixed_inflection(data, "usually <<uncountable>>", hyphpl) else insert_fixed_inflection(data, "<<uncountable>>", hyphpl) end need_default_plural = false elseif first_pl_term() == "#" then -- Usually countable (e.g., "grilled cheese") local hashpl = remove(plurals, 1) -- Remove the "#" but retain for decorations. insert_fixed_inflection(data, "usually <<countable>>", hashpl) inscat("uncountable nouns") inscat("countable nouns") -- If no plural was given, add a default one now if not plurals[1] then plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end elseif first_pl_term() == "~" then -- Mixed countable/uncountable noun, always has a plural local tildepl = remove(plurals, 1) -- Remove the "~" but retain for decorations. insert_fixed_inflection(data, "<<countable>> and <<uncountable>>", tildepl) inscat("uncountable nouns") inscat("countable nouns") -- If no plural was given, add a default one now if not plurals[1] then plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end end -- Plural is unknown if first_pl_term() == "?" then local questionpl = remove(plurals, 1) -- Remove the "?" but retain for decorations. -- Not desired; see [[Wiktionary:Tea_room/2021/August#"Plural unknown or uncertain"]] -- insert_fixed_inflection(data, "plural unknown or uncertain", questionpl) inscat("nouns with unknown or uncertain plurals") if plurals[1] then error("Can't specify explicit plurals along with '?' for unknown/uncertain plural") end return end -- Plural is not attested if first_pl_term() == "!" then local exclampl = remove(plurals, 1) -- Remove the "!" but retain for decorations. insert_fixed_inflection(data, "plural not attested", exclampl) inscat("nouns with unattested plurals") if plurals[1] then error("Can't specify explicit plurals along with '!' for unattested plural") end return end -- If no plural was given, maybe add a default one, otherwise (when "-" was given or proper noun) return. if not plurals[1] then if not need_default_plural then inscat("uncountable nouns") return end plurals[1] = {term = escape(add_suffix(pagename, "s.plural", pos))} end -- There are plural forms to show, so show them. inscat("countable nouns") local irregular, indeclinable for i, pl in ipairs(plurals) do local canon_pl = canonicalize_plural(pl.term, pagename, pos) if canon_pl then pl.term = canon_pl end local pl_term = get_link_page(pl.term, lang) if not (pagename:find(" ") or is_regular_plural(pl_term, pagename)) then irregular = true if pl_term == pagename then indeclinable = true end end end if irregular then inscat("nouns with irregular plurals") end if indeclinable then inscat("indeclinable nouns") end insert_inflection(data, plurals, "plural", "p") end -- Return the parameters to be used for nouns and proper nouns. Currently the same. local noun_params = { [1] = list_param, ["pl\1qual"] = {list = true, allow_holes = true, replaced_by = false, instead = "use <l:...> or <q:...> inline modifier on the plural", }, -- The following four only used for pluralia tantum (1=p) ["sg"] = list_param, ["attr"] = list_param, } pos_functions["nouns"] = { params = noun_params, func = do_nouns, } pos_functions["proper nouns"] = { params = noun_params, func = function(args, data) return do_nouns(args, data, "proper noun") end, } local function base_default_verb_forms(verb) return escape(add_suffix(verb, "s.verb")), escape(add_suffix(verb, "ing")), escape(add_suffix(verb, "d")) end local function default_verb_forms(verb) local full_s_form, full_ing_form, full_ed_form = base_default_verb_forms(verb) if verb:find(" ") then local first, rest = verb:match("^(.-)( .*)$") local first_s_form, first_ing_form, first_ed_form = base_default_verb_forms(first) return full_s_form, full_ing_form, full_ed_form, first_s_form .. rest, first_ing_form .. rest, first_ed_form .. rest, first, rest else return full_s_form, full_ing_form, full_ed_form, nil, nil, nil, nil, nil end end local function compute_double_last_cons_stem_of_split_verb(verb, ending) local first, rest = verb:match("^(.-)( .*)$") if not first then error("Verb '" .. verb .. "' must have a space in it to use **") end local last_cons = first:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("First word '" .. first .. "' must end in a consonant to use **") end return first .. last_cons .. ending .. rest end local function check_non_nil_star_form(form, pagename) if form == nil then error("Verb '" .. pagename .. "' must have a space in it to use *, **, *l, *! or *'") end return form end local function sub_tilde(form, pagename) if not form then return nil end if form:find("~") then form = form:gsub("~", replacement_escape(pagename)) end return form end local deprecated_qual_replaced_by_inline_modifier = { list = true, allow_holes = true, replaced_by = false, instead = "use an inline modifier <q:...> or <l:...> on the value" } pos_functions["verbs"] = { params = { [1] = {list = "pres_3sg", disallow_holes = true}, ["pres_3sg\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [2] = {list = "pres_ptc", disallow_holes = true}, ["pres_ptc\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [3] = {list = "past", disallow_holes = true}, ["past\1_qual"] = deprecated_qual_replaced_by_inline_modifier, [4] = {list = "past_ptc", allow_holes = true}, ["past_ptc\1_qual"] = deprecated_qual_replaced_by_inline_modifier, ["noautolinkverb"] = boolean_param, ["angle_bracket"] = boolean_param, }, func = function(args, data) -- Get parameters local par1s local par2s = parse_inflection(args, {2, "pres_ptc"}) local par3s = parse_inflection(args, {3, "past"}) local par4s = parse_inflection(args, {4, "past_ptc"}) local pres_3sgs, pres_ptcs, pasts, past_ptcs local pagename = data.pagename ------------------------------------------- UTILITY FUNCTIONS #2 ------------------------------------------ -- These functions are used in both in the separate-parameter format and in the override params such as past_ptc2=. local full_default_s, full_default_ing, full_default_ed, split_default_s, split_default_ing, split_default_ed local lemma local function set_lemma_and_default_forms(the_lemma) lemma = the_lemma full_default_s, full_default_ing, full_default_ed, split_default_s, split_default_ing, split_default_ed, lemma_first, lemma_rest = default_verb_forms(the_lemma) end local function canonicalize_s_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_s elseif form == "*" then return check_non_nil_star_form(split_default_s, lemma) elseif form == "++" then return compute_plusplus_s_form(lemma, full_default_s) elseif form == "**" then if lemma:find("^[^ ]*[szx] ") then return compute_double_last_cons_stem_of_split_verb(lemma, "es") else return check_non_nil_star_form(split_default_s, lemma) end elseif form == "+!" then return lemma .. "s" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "s" .. lemma_rest elseif form == "+'" then return lemma .. "'s" elseif form == "*'" then return check_non_nil_star_form(lemma_first) .. "'s" .. lemma_rest elseif form == "+l" then if lemma:find("[szx]$") then return {{term = full_default_s, l = {"US"}}, {term = compute_plusplus_s_form(lemma, full_default_s), l = {"UK"}}} else return compute_plusplus_s_form(lemma, full_default_s) end elseif form == "*l" then if lemma:find("^[^ ]*[szx] ") then return {{term = check_non_nil_star_form(split_default_s, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "es"), l = {"UK"}}} else return check_non_nil_star_form(split_default_s, lemma) end else return sub_tilde(form, lemma) end end local function canonicalize_ing_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_ing elseif form == "*" then return check_non_nil_star_form(split_default_ing, lemma) elseif form == "++" then return compute_double_last_cons_stem(lemma) .. "ing" elseif form == "**" then return compute_double_last_cons_stem_of_split_verb(lemma, "ing") elseif form == "+!" then return lemma .. "ing" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "ing" .. lemma_rest elseif form == "+'" then return lemma .. "'ing" elseif form == "*'" then return check_non_nil_star_form(lemma_first) .. "'ing" .. lemma_rest elseif form == "+l" then return {{term = full_default_ing, l = {"US"}}, {term = compute_double_last_cons_stem(lemma) .. "ing", l = {"UK"}}} elseif form == "*l" then return {{term = check_non_nil_star_form(split_default_ing, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "ing"), l = {"UK"}}} else return sub_tilde(form, lemma) end end local function canonicalize_ed_form(form) if form == "+" then error("Internal error: Should not see '+' here") elseif form == "^" then return full_default_ed elseif form == "*" then return check_non_nil_star_form(split_default_ed, lemma) elseif form == "++" then return compute_double_last_cons_stem(lemma) .. "ed" elseif form == "+!" then return lemma .. "ed" elseif form == "*!" then return check_non_nil_star_form(lemma_first) .. "ed" .. lemma_rest elseif form == "+'" then return {{term = lemma .. "'d"}, {term = lemma .. "'ed"}} elseif form == "*'" then return {{term = check_non_nil_star_form(lemma_first) .. "'d" .. lemma_rest}, {term = check_non_nil_star_form(lemma_first) .. "'ed" .. lemma_rest}} elseif form == "**" then return compute_double_last_cons_stem_of_split_verb(lemma, "ed") elseif form == "+l" then return {{term = full_default_ed, l = {"US"}}, {term = compute_double_last_cons_stem(lemma) .. "ed", l = {"UK"}}} elseif form == "*l" then return {{term = check_non_nil_star_form(split_default_ed, lemma), l = {"US"}}, {term = compute_double_last_cons_stem_of_split_verb(lemma, "ed"), l = {"UK"}}} else return sub_tilde(form, lemma) end end -- FIXME: options should be "+", "*", "++", "**", "+n", "*n", "++n" and "**n", but not "n" local function canonicalize_en_form(form) if form == "n" then track("n4") return add_suffix(lemma, "n") end return canonicalize_ed_form(form) end --------------------------------- MAIN PARSING/CONJUGATING CODE -------------------------------- local is_angle_bracket = args.angle_bracket if is_angle_bracket then if par2s[1] or par3s[1] or par4s[1] then error("Can't specify explicit values for 2=, 3= or 4= along with the angle-bracket format") end elseif is_angle_bracket == nil and not par2s[1] and not par3s[1] and not par4s[1] and not args[1][2] and args[1][1] and args[1][1]:find("<") then if put.term_contains_top_level_html(args[1][1]) then -- Often, term_contains_top_level_html() returns true on the angle-bracket format, which would -- make the pcall() below succeed but leave the angle brackets as-is. Check for this and only do the -- pcall() if term_contains_top_level_html() returns false. is_angle_bracket = true else -- If it's ambiguous whether it's an angle-bracket format or separate params with an inline modifier, -- try to parse as the latter. If an error occurs, treat as the former. local ok ok, par1s = pcall(parse_inflection, args, {1, "pres_3sg"}) if not ok then par1s = nil is_angle_bracket = true end end end if is_angle_bracket then -------------------------- ANGLE-BRACKET FORMAT -------------------------- -- (0) Expand multiword term with angle brackets just on the first word. local arg11 = args[1][1] if arg11:find("^<.*>$") and pagename:find(" ") then local first, rest = pagename:match("^(.-)( .*)$") arg11 = first .. arg11 .. rest end -- (1) Parse the indicator specs inside of angle brackets. local function parse_indicator_spec(angle_bracket_spec) local inside = angle_bracket_spec:match("^<(.*)>$") assert(inside) local segments = put.parse_balanced_segment_run(inside, "[", "]") local comma_separated_groups = put.split_alternating_runs(segments, ",") if #comma_separated_groups > 4 then error("Too many comma-separated parts in indicator spec, expected at most 4: " .. angle_bracket_spec) end local function fetch_footnotes(separated_group) local footnotes for j = 2, #separated_group - 1, 2 do if separated_group[j + 1] ~= "" then error("Extraneous text after bracketed footnotes: '" .. concat(separated_group) .. "'") end if not footnotes then footnotes = {} end insert(footnotes, separated_group[j]) end return footnotes end local function fetch_specs(comma_separated_group) if not comma_separated_group then return {{term = "+"}} end local specs = {} local colon_separated_groups = put.split_alternating_runs(comma_separated_group, ":") for _, colon_separated_group in ipairs(colon_separated_groups) do local form = colon_separated_group[1] if form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then error("*, **, *l, *! and *' not allowed inside of indicator specs: " .. angle_bracket_spec) end if form == "" then form = "+" end local termobj = { term = form } local footnotes = fetch_footnotes(colon_separated_group) if footnotes then for _, footnote in ipairs(footnotes) do m_headword_utilities.add_footnote_to_termobj(termobj, footnote) end end insert(specs, termobj) end return specs end local s_specs = fetch_specs(comma_separated_groups[1]) local ing_specs = fetch_specs(comma_separated_groups[2]) local ed_specs = fetch_specs(comma_separated_groups[3]) local en_specs = fetch_specs(comma_separated_groups[4]) return { forms = {}, s_specs = s_specs, ing_specs = ing_specs, ed_specs = ed_specs, en_specs = en_specs, } end local parse_props = { parse_indicator_spec = parse_indicator_spec, } local alternant_multiword_spec = iut.parse_inflected_text(arg11, parse_props) -- (2) Check for user-specified brackets; remove any links from the lemma, but remember the original -- form so we can use it below in the 'lemma_linked' form. -- Check to see if there are brackets in the pre-text or post-text. If so, use the linked lemma (with the -- verb autolinked unless noautolinkverb is given). Otherwise, use the default headword algorithm. local function check_bracket(val) if val:find("%[%[") then alternant_multiword_spec.saw_bracket = true end end for _, alternant_or_word_spec in ipairs(alternant_multiword_spec.alternant_or_word_specs) do check_bracket(alternant_or_word_spec.before_text) if alternant_or_word_spec.alternants then for _, multiword_spec in ipairs(alternant_or_word_spec.alternants) do for _, word_spec in ipairs(multiword_spec.word_specs) do check_bracket(word_spec.before_text) end check_bracket(multiword_spec.post_text) end end end check_bracket(alternant_multiword_spec.post_text) iut.map_word_specs(alternant_multiword_spec, function(base) if base.lemma == "" then base.lemma = pagename end base.orig_lemma = base.lemma base.lemma = remove_links(base.lemma) if args.noautolinkverb or base.orig_lemma:find("%[%[") then base.linked_lemma = base.orig_lemma else base.linked_lemma = "[[" .. base.orig_lemma .. "]]" end end) -- (3) Conjugate the verbs according to the indicator specs parsed above. local all_verb_slots = { lemma = "infinitive", lemma_linked = "infinitive", s_form = "3|s|pres", ing_form = "pres|ptcp", ed_form = "past", en_form = "past|ptcp", } local function conjugate_verb(base) local function process_specs(slot, specs, canon_func, default_values, default_already_formobj) local function insert_termobj_into_slot(termobj) local formobj = m_headword_utilities.convert_termobj_to_formobj(termobj) -- If the form is -, don't insert any forms, which will result in there being no overall forms -- (in fact it will be nil). We check for that down below and substitute a single "-" as the -- form, which in turn gets turned into special labels like "no present participle". if formobj.form == "-" then if formobj.footnotes then error("Unable to preserve footnotes specified on missing form '-': FIXME: " .. dump(formobj.footnotes)) end else iut.insert_form(base.forms, slot, formobj) end end local function canonicalize_and_insert(arg) local canon_arg = canon_func(arg) if type(canon_arg) == "string" then arg.term = canon_arg insert_termobj_into_slot(arg) else for _, canon in ipairs(canon_arg) do m_headword_utilities.combine_termobj_decorations(canon, arg) insert_termobj_into_slot(canon) end end end for _, arg in ipairs(specs) do if arg.term == "+" then if default_values then -- will be nil if past tense specified as - and no past ptc given for _, val in ipairs(default_values) do val = shallowCopy(val) if default_already_formobj then local argformobj = m_headword_utilities.convert_termobj_to_formobj(arg) val.footnotes = iut.combine_footnotes(val.footnotes, argformobj.footnotes) iut.insert_form(base.forms, slot, val) else m_headword_utilities.combine_termobj_decorations(val, arg) canonicalize_and_insert(val) end end end else canonicalize_and_insert(arg) end end end set_lemma_and_default_forms(base.lemma) local all_part_default_specs = {} local function process_and_canonicalize_s_form(arg) local form = arg.term if form == "+" then error("Internal error: '+' should have been converted to '^' by now") end if form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then error(("Internal error: '%s' should have already thrown an error"):format(form)) end if form == "^" or form == "++" or form == "+l" or form == "+!" or form == "+'" then insert(all_part_default_specs, shallowCopy(arg)) end return canonicalize_s_form(form) end process_specs("s_form", base.s_specs, process_and_canonicalize_s_form, {{term = "^"}}) if not all_part_default_specs[1] then all_part_default_specs[1] = {term = "^"} end process_specs("ing_form", base.ing_specs, function(arg) return canonicalize_ing_form(arg.term) end, all_part_default_specs) process_specs("ed_form", base.ed_specs, function(arg) return canonicalize_ed_form(arg.term) end, all_part_default_specs) process_specs("en_form", base.en_specs, function(arg) return canonicalize_en_form(arg.term) end, base.forms.ed_form, "default already formobj") iut.insert_form(base.forms, "lemma", {form = base.lemma}) -- Add linked version of lemma for use in head=. We write this in a general fashion in case -- there are multiple lemma forms (which isn't possible currently at this level, although it's -- possible overall using the ((...,...)) notation). iut.insert_forms(base.forms, "lemma_linked", iut.map_forms(base.forms.lemma, function(form) if form == base.lemma and base.linked_lemma:find("%[%[") then return base.linked_lemma else return form end end)) end local inflect_props = { slot_table = all_verb_slots, inflect_word_spec = conjugate_verb, } iut.inflect_multiword_or_alternant_multiword_spec(alternant_multiword_spec, inflect_props) -- (4) Fetch the forms and put the conjugated lemmas in data.heads if not explicitly given. local function fetch_termobjs(slot) local forms = alternant_multiword_spec.forms[slot] -- See above. This should only occur if the user explicitly used - for a spec. if not forms or not forms[1] then return {{term = "-"}} end local termobjs = {} for _, formobj in ipairs(forms) do insert(termobjs, m_headword_utilities.convert_formobj_to_termobj(formobj)) end return termobjs end pres_3sgs = fetch_termobjs("s_form") pres_ptcs = fetch_termobjs("ing_form") pasts = fetch_termobjs("ed_form") past_ptcs = fetch_termobjs("en_form") -- Use the "linked" form of the lemma as the head if no head= explicitly given and the user specified -- brackets in one of the lemmas. Otherwise we use the default headword-linking algorithm. if not data.user_specified_heads[1] and alternant_multiword_spec.saw_bracket then data.heads = {} for _, lemma_obj in ipairs(alternant_multiword_spec.forms.lemma_linked) do insert(data.heads, m_headword_utilities.convert_formobj_to_termobj(lemma_obj)) end end else -------------------------- SEPARATE-PARAM FORMAT -------------------------- set_lemma_and_default_forms(pagename) par1s = par1s or parse_inflection(args, {1, "pres_3sg"}) pres_3sgs = {} pres_ptcs = {} pasts = {} past_ptcs = {} if not par1s[1] then par1s = {{term = "+"}} end if not par2s[1] then par2s = {{term = "+"}} end if not par3s[1] then par3s = {{term = "+"}} end if not par4s[1] then par4s = {{term = "+"}} end local function process_argument(args, dest, canon_func, default_values, default_already_canonicalized) local function canonicalize_and_insert(arg) local canon_arg = canon_func(arg) if type(canon_arg) == "string" then arg.term = canon_arg m_headword_utilities.insert_termobj_combining_duplicates(dest, arg) else for _, canon in ipairs(canon_arg) do m_headword_utilities.combine_termobj_decorations(canon, arg) m_headword_utilities.insert_termobj_combining_duplicates(dest, canon) end end end for _, arg in ipairs(args) do if arg.term == "+" then for _, val in ipairs(default_values) do val = shallowCopy(val) m_headword_utilities.combine_termobj_decorations(val, arg) if default_already_canonicalized then m_headword_utilities.insert_termobj_combining_duplicates(dest, val) else canonicalize_and_insert(val) end end else canonicalize_and_insert(arg) end end end local all_part_default_specs = {} local function process_and_canonicalize_s_form(arg) local form = arg.term if form == "+" then error("Internal error: '+' should have been converted to '^' by now") end if form == "^" or form == "++" or form == "+l" or form == "+!" or form == "+'" or form == "*" or form == "**" or form == "*l" or form == "*!" or form == "*'" then insert(all_part_default_specs, shallowCopy(arg)) end return canonicalize_s_form(form) end process_argument(par1s, pres_3sgs, process_and_canonicalize_s_form, {{term = "^"}}) if not all_part_default_specs[1] then all_part_default_specs[1] = {term = "^"} end process_argument(par2s, pres_ptcs, function(arg) return canonicalize_ing_form(arg.term) end, all_part_default_specs) process_argument(par3s, pasts, function(arg) return canonicalize_ed_form(arg.term) end, all_part_default_specs) process_argument(par4s, past_ptcs, function(arg) return canonicalize_en_form(arg.term) end, pasts, "default already canonicalized") end ------------------------------------------- INSERT INFLECTIONS ------------------------------------------ insert_inflection(data, pres_3sgs, "third-person singular simple present", "s-verb-form") insert_inflection(data, pres_ptcs, "present participle", "ing-form") if deepEquals(pasts, past_ptcs) then insert_inflection(data, pasts, "simple past and past participle", "ed-form", "no simple past or past participle") else insert_inflection(data, pasts, "simple past", "spast") insert_inflection(data, past_ptcs, "past participle", "past|part") end if pagename:find(" ") then -- Check for placeholder "it" local words = split(pagename, " ") for _, word in ipairs(words) do if word == "it" or word == "its" or word == "it's" then insert(data.categories, langname .. ' terms with placeholder "it"') break end end -- Check for phrasal verbs local phrasal_adverbs = list_to_set{ -- NOTE: This should only contain common phrasal adverbs, not random words like [[low]], -- [[adrift]], etc. "aback", "about", "above", "across", "after", "against", "ahead", "along", "apart", "around", "as", "aside", "at", "away", "back", "before", "behind", "below", "between", "beyond", "by", "down", "for", "forth", "from", "in", "into", "of", "off", "on", "onto", "out", "over", "past", "round", "through", "to", "together", "towards", "under", "up", "upon", "with", "without", } local allowed_non_adverb_words = list_to_set{ "it", "one", "oneself", "someone", } local base = pagename local seen_adverbs = {} -- Only consider a verb to be phrasal if it consists of a single base verb followed exclusively by either -- adverbs from `phrasal_adverbs` or placeholder words from `allowed_non_adverb_words`, where at -- least one following word is from `phrasal_adverbs` (hence [[can it]] is not a phrasal verb). while true do local prev, word = base:match("^(.+) (.-)$") if not prev then break end if phrasal_adverbs[word] then insert(seen_adverbs, word) elseif allowed_non_adverb_words[word] then -- do nothing else break end base = prev end if not base:find(" ") and seen_adverbs[1] then insert(data.categories, langname .. " phrasal verbs") for i = #seen_adverbs, 1, -1 do insert(data.categories, langname .. ' phrasal verbs formed with "' .. seen_adverbs[i] .. '"') end end end end, } ----------------------------------------------------------------------------------------- -- Suffix forms -- ----------------------------------------------------------------------------------------- pos_functions["suffix forms"] = { params = { [1] = {required = true, list = true, disallow_holes = true}, }, func = function(args, data, is_suffix) local suffix_type = {} for _, typ in ipairs(args[1]) do insert(suffix_type, typ .. "-forming suffix") end insert(data.inflections, {label = "non-lemma form of " .. m_table.serialCommaJoin(suffix_type, {conj = "or"})}) end, } return export 16kpxx6u8rw55bh0m9lw3iuegl8ptae 0 8060 54911 54873 2026-09-28T23:24:24Z Deadend0914 7211 /* Wordstǣr */ 54911 wikitext text/x-wiki =={{sprǣc|en}}== ===Rihtstefn=== * IPA: /ˈænd ===Wordstǣr=== Of {{inh|en|ang|and}} ===Fégung=== # [[and]] [[Flocc: Nīwenglisc fégung]] rwbb8mm31st5hwkem0cg5m9d61hy4pw 828 8063 54906 54876 2026-09-28T23:20:44Z Deadend0914 7211 54906 Scribunto text/plain local export = {} local require_when_needed = require("Module:require when needed") local get_current_L2 = require_when_needed("Module:pages", "get_current_L2") local get_lang_by_name = require_when_needed("Module:languages", "getByCanonicalName") local is_content_page = require_when_needed("Module:pages", "is_content_page") local process_params = require_when_needed("Module:parameters", "process") local trim = mw.text.trim local lower = mw.ustring.lower local etymology_module = "Module:etymology" local headword_data_module = "Module:headword/data" local etymology_specialized_module = "Module:etymology/specialized" local parameter_utilities_module = "Module:parameter utilities" -- For testing local force_cat = false local allowed_conjs = {"and", "or", ",", "/", "~", ";"} -- Sinitic lects (Mandarin, Cantonese, Hokkien, etc.) are full languages, but Chinese entries sit -- under a single ==Chinese== L2, while romanization entries (pinyin, jyutping, pe̍h-ōe-jī) have lect -- L2s, and content is often shared between them. Contact languages (Chinese-based creoles and mixed -- languages) have their own L2s and are excluded. local function is_sinitic(lang) return lang:inFamily("zhx") and not lang:inFamily("qfa-cnt") end local content_page local function is_content_page_cached() if content_page == nil then content_page = is_content_page(mw.title.getCurrentTitle()) end return content_page end -- Old English localization: the ==L2== heading is rendered by [[Bysen:sprǣc]] from -- [[Module:sprǣcnaman]], so the comparison below has to use the same names. The module is -- optional: if it is missing, the English names are used exactly as before. local ang_names_module = "Module:sprǣcnaman" local ang_names local function get_ang_names() if ang_names == nil then local ok, mod = pcall(require, ang_names_module) ang_names = ok and mod or false end return ang_names or nil end -- Old English name of the language, or nil. local function ang_name(lang) local mod = get_ang_names() return mod and mod.get_name(lang) or nil end -- Code of the language with the given Old English name, or nil. local function code_of_ang_name(name) local mod = get_ang_names() return mod and mod.get_code(name) or nil end -- Throw an error if `lang` (the language of the entry) doesn't match -- the L2 header that the template is invoked under. local function check_lang_matches_L2(lang, nocat) if nocat or not lang or lang:getCode() == "und" or (lang.hasType and lang:hasType("family")) then return end local headword_data = mw.loadData(headword_data_module) if headword_data.large_pages[headword_data.pagename] then return end if not is_content_page_cached() then return end local current_L2 = get_current_L2() if not current_L2 then return end local full_name = ang_name(lang) or lang:getFullName() -- Old English localization: also accept an ==L2== heading written with an Old English name. local L2_code = code_of_ang_name(current_L2) if full_name == current_L2 or L2_code == lang:getCode() or L2_code == lang:getFullCode() then return end -- Accept any Sinitic language under any Sinitic L2. if is_sinitic(lang) then local L2_lang = get_lang_by_name(current_L2) if L2_lang and is_sinitic(L2_lang) then return end end local lang_desc = lang:getCode() .. " (" .. (ang_name(lang) or lang:getCanonicalName()) .. ")" if lang:getFullCode() ~= lang:getCode() then lang_desc = lang_desc .. ", an etymology-only language whose full language is " .. lang:getFullCode() .. " (" .. full_name .. ")" end -- TODO: translate this message into Old English. error("Language '" .. lang_desc .. "' does not match the L2 header (" .. current_L2 .. ").") end local function parse_etym_args(parent_args, base_params, has_dest_lang) local m_param_utils = require(parameter_utilities_module) local param_mods = m_param_utils.construct_param_mods { {group = {"link", "q", "l", "ref"}}, } local sourcearg, termarg if has_dest_lang then sourcearg, termarg = 2, 3 else sourcearg, termarg = 1, 2 end local terms, args = m_param_utils.parse_term_with_inline_modifiers_and_separate_params { params = base_params, param_mods = param_mods, raw_args = parent_args, termarg = termarg, track_module = "etymology", lang = function(args) return args[sourcearg][#args[sourcearg]] end, sc = "sc", -- Don't do this, doesn't seem to make sense. -- parse_lang_prefix = true, make_separate_g_into_list = true, splitchar = ",", subitem_param_handling = "last", } -- If term param 3= is empty, there will be no terms in terms.terms. To facilitate further code and for -- compatibility,, insert one. It will display as <small>[Term?]</small>. if not terms.terms[1] then terms.terms[1] = { lang = args[sourcearg][#args[sourcearg]], sc = args.sc, } end return terms.terms, args end function export.parse_2_lang_args(parent_args, has_text, no_family) local boolean = {type = "boolean"} local params = { [1] = { required = true, type = "language", default = "und" }, [2] = { required = true, sublist = true, type = "language", family = not no_family, default = "und" }, [3] = true, [4] = {alias_of = "alt"}, [5] = {alias_of = "t"}, ["senseid"] = true, ["nocat"] = boolean, ["sort"] = true, ["sourceconj"] = true, ["conj"] = {set = allowed_conjs, default = ","}, } if has_text then params["notext"] = boolean params["nocap"] = boolean end local terms, args = parse_etym_args(parent_args, params, "has dest lang") check_lang_matches_L2(args[1], args.nocat) return terms, args end -- Implementation of deprecated {{etyl}}. Provided to make histories more legible. function export.etyl(frame) local params = { [1] = {required = true, type = "language", default = "und"}, [2] = {type = "language", default = "en"}, ["sort"] = {}, } -- Empty language means English, but "-" means no language. Yes, confusing... local args = frame:getParent().args if args[2] and trim(args[2]) == "-" then params[2] = nil args = process_params({ [1] = args[1], ["sort"] = args.sort }, params) else args = process_params(args, params) end check_lang_matches_L2(args[2]) return require(etymology_module).format_source { lang = args[2], source = args[1], sort_key = args.sort, force_cat = force_cat, } end -- Implementation of {{derived}}/{{der}}. function export.derived(frame) local parent_args = frame:getParent().args local terms, args = export.parse_2_lang_args(parent_args) return require(etymology_module).format_derived { lang = args[1], sources = args[2], terms = terms, sort_key = args.sort, nocat = args.nocat, sourceconj = args.sourceconj, conj = args.conj, template_name = "derived", force_cat = force_cat, } end -- Implementation of {{borrowed}}/{{bor}}. function export.borrowed(frame) local parent_args = frame:getParent().args local terms, args = export.parse_2_lang_args(parent_args) return require(etymology_module).format_borrowed { lang = args[1], sources = args[2], terms = terms, sort_key = args.sort, nocat = args.nocat, sourceconj = args.sourceconj, conj = args.conj, force_cat = force_cat, } end function export.inherited(frame) local parent_args = frame:getParent().args local terms, args = export.parse_2_lang_args(parent_args) local sources = args[2] if sources[2] then -- Because this doesn't really make sense. error("[[Template:inherited]] doesn't support multiple comma-separated sources") end return require(etymology_module).format_inherited { lang = args[1], terms = terms, sort_key = args.sort, nocat = args.nocat, conj = args.conj, force_cat = force_cat, } end function export.cognate(frame) local params = { [1] = { required = true, sublist = true, type = "language", family = true, default = "und" }, [2] = true, [3] = {alias_of = "alt"}, [4] = {alias_of = "t"}, sourceconj = true, ["conj"] = {set = allowed_conjs, default = ","}, sort = true, } local parent_args = frame:getParent().args local terms, args = parse_etym_args(parent_args, params, false) return require(etymology_module).format_cognate { sources = args[1], terms = terms, sort_key = args.sort, sourceconj = args.sourceconj, conj = args.conj, force_cat = force_cat, } end function export.noncognate(frame) return export.cognate(frame) end -- Supports various specialized types of borrowings, according to `frame.args.bortype`: -- "learned" = {{lbor}}/{{learned borrowing}} -- "semi-learned" = {{slbor}}/{{semi-learned borrowing}} -- "orthographic" = {{obor}}/{{orthographic borrowing}} -- "unadapted" = {{ubor}}/{{unadapted borrowing}} -- "calque" = {{cal}}/{{calque}} -- "partial-calque" = {{pcal}}/{{partial calque}} -- "semantic-loan" = {{sl}}/{{semantic loan}} -- "transliteration" = {{translit}}/{{transliteration}} -- "phono-semantic-matching" = {{psm}}/{{phono-semantic matching}} function export.specialized_borrowing(frame) local parent_args = frame:getParent().args local terms, args = export.parse_2_lang_args(parent_args, "has text") local m_etymology_specialized = require(etymology_specialized_module) return m_etymology_specialized.specialized_borrowing { bortype = frame.args.bortype, lang = args[1], sources = args[2], terms = terms, sort_key = args.sort, nocap = args.nocap, notext = args.notext, nocat = args.nocat, sourceconj = args.sourceconj, conj = args.conj, senseid = args.senseid, force_cat = force_cat, } end -- Implementation of miscellaneous templates such as {{abbrev}}, {{back-formation}}, {{clipping}}, {{ellipsis}}, -- {{rebracketing}} and {{reduplication}} that have a single associated term. function export.misc_variant(frame) local iparams = { ["ignore-params"] = true, text = {required = true}, oftext = true, cat = {list = true}, -- allow and compress holes conj = true, } local iargs = process_params(frame.args, iparams) local boolean = {type = "boolean"} local params = { [1] = {required = true, type = "language", default = "und"}, [2] = true, [3] = {alias_of = "alt"}, [4] = {alias_of = "t"}, nocap = boolean, -- should be processed in the template itself notext = boolean, nocat = boolean, conj = {set = allowed_conjs}, sort = true, } -- |ignore-params= parameter to module invocation specifies -- additional parameter names to allow in template invocation, separated by -- commas. They must consist of ASCII letters or numbers or hyphens. local ignore_params = iargs["ignore-params"] if ignore_params then ignore_params = trim(ignore_params) if not ignore_params:match("^[%w%-,]+$") then error("Invalid characters in |ignore-params=: " .. ignore_params:gsub("[%w%-,]+", "")) end for param in ignore_params:gmatch("[%w%-]+") do if params[param] then error("Duplicate param |" .. param .. " in |ignore-params=: already specified in params") end params[param] = true end end local m_param_utils = require(parameter_utilities_module) local param_mods = m_param_utils.construct_param_mods { {group = {"link", "q", "l", "ref"}}, } local parent_args = frame:getParent().args local terms, args = m_param_utils.parse_term_with_inline_modifiers_and_separate_params { params = params, param_mods = param_mods, raw_args = parent_args, termarg = 2, track_module = "etymology", -- Don't set lang here as we want to know whether there was a lang prefix or not. sc = "sc", parse_lang_prefix = true, allow_multiple_lang_prefixes = true, make_separate_g_into_list = true, splitchar = ",", subitem_param_handling = "last", } check_lang_matches_L2(args[1], args.nocat) return require(etymology_module).format_misc_variant { lang = args[1], notext = args.notext, text = iargs.text, oftext = iargs.oftext, terms = terms.terms, sort_key = args.sort, conj = args.conj or iargs.conj or "and", nocat = args.nocat, cats = iargs.cat, force_cat = force_cat, } end -- Implementation of miscellaneous templates such as {{doublet}} that can take multiple terms. Doesn't handle {{blend}} -- or {{univerbation}}, which display + signs between elements and use compound_like in [[Module:affix/templates]]. function export.misc_variant_multiple_terms(frame) local iparams = { text = {required = true}, oftext = true, cat = {list = true}, -- allow and compress holes conj = true, } local iargs = process_params(frame.args, iparams) local boolean = {type = "boolean"} local params = { [1] = {required = true, type = "language", template_default = "und"}, [2] = {list = true, allow_holes = true}, nocap = boolean, -- should be processed in the template itself notext = boolean, nocat = boolean, conj = {set = allowed_conjs}, sort = true, } local m_param_utils = require(parameter_utilities_module) local param_mods = m_param_utils.construct_param_mods { -- We want to require an index for all params. {default = true, require_index = true}, {group = {"link", "q", "l", "ref"}}, } local parent_args = frame:getParent().args local terms, args = m_param_utils.parse_list_with_inline_modifiers_and_separate_params { params = params, param_mods = param_mods, raw_args = parent_args, termarg = 2, parse_lang_prefix = true, allow_multiple_lang_prefixes = true, track_module = "etymology-templates-doublet", disallow_custom_separators = true, -- For compatibility, we need to not skip completely unspecified items. It is common, for example, to do -- {{suffix|lang||foo}} to generate "+ -foo". dont_skip_items = true, -- Don't set lang here as we want to know whether there was a lang prefix or not. sc = "sc.default", } check_lang_matches_L2(args[1], args.nocat) return require(etymology_module).format_misc_variant { lang = args[1], notext = args.notext, text = iargs.text, oftext = iargs.oftext, terms = terms, sort_key = args.sort, conj = args.conj or iargs.conj or "and", nocat = args.nocat, cats = iargs.cat, force_cat = force_cat, } end -- Implementation of miscellaneous templates such as {{unknown}} that have no associated terms. do local function get_args(frame) local boolean = {type = "boolean"} local params = { [1] = {required = true, type = "language", default = "und"}, ["title"] = true, ["nocap"] = boolean, -- should be processed in the template itself ["notext"] = boolean, ["nocat"] = boolean, ["sort"] = true, } if frame.args.title2_alias then params[2] = {alias_of = "title"} end local args = process_params(frame:getParent().args, params) check_lang_matches_L2(args[1], args.nocat) return args end function export.misc_variant_no_term(frame) local args = get_args(frame) return require(etymology_module).format_misc_variant_no_term { lang = args[1], notext = args.notext, title = args.title or frame.args.text, nocat = args.nocat, cat = frame.args.cat, sort_key = args.sort, force_cat = force_cat, } end -- This function works similarly to misc_variant_no_term(), but with some automatic linking to the glossary in -- `title`. function export.onomatopoeia(frame) local args = get_args(frame) local title = args.title if title and (lower(title) == "imitative" or lower(title) == "imitation") then title = "[[Appendix:Glossary#imitative|" .. title .. "]]" end return require(etymology_module).format_misc_variant_no_term { lang = args[1], notext = args.notext, title = title or frame.args.text, nocat = args.nocat, cat = frame.args.cat, sort_key = args.sort, force_cat = force_cat, } end end return export syg6utaikdtm1mu22f7fk80qw5zgk37 828 8064 54905 54877 2026-09-28T23:20:13Z Deadend0914 7211 54905 Scribunto text/plain local export = {} -- For testing local force_cat = false local debug_track_module = "Module:debug/track" local languages_module = "Module:languages" local links_module = "Module:links" local table_module = "Module:table" local utilities_module = "Module:utilities" local concat = table.concat local insert = table.insert local new_title = mw.title.new local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function full_link(...) full_link = require(links_module).full_link return full_link(...) end local function get_language_data_module_name(...) get_language_data_module_name = require(languages_module).getDataModuleName return get_language_data_module_name(...) end local function get_link_page(...) get_link_page = require(links_module).get_link_page return get_link_page(...) end local function language_link(...) language_link = require(links_module).language_link return language_link(...) end local function serial_comma_join(...) serial_comma_join = require(table_module).serialCommaJoin return serial_comma_join(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end -- Old English localization: language names come from [[Module:sprǣcnaman]], which is also what -- [[Bysen:sprǣc]] (the ==L2== heading template) uses, so headings, wordstǣr lines and categories -- can never disagree with each other. The module is optional: if it is missing, the English names -- are used exactly as before. local ang_names_module = "Module:sprǣcnaman" local ang_names local function get_ang_names() if ang_names == nil then local ok, mod = pcall(require, ang_names_module) ang_names = ok and mod or false end return ang_names or nil end -- Old English name of the language, or nil. local function ang_name(lang) local mod = get_ang_names() return mod and mod.get_name(lang) or nil end -- Old English "of"-form of the language, or nil. local function ang_of(lang) local mod = get_ang_names() return mod and mod.get_of(lang) or nil end -- Replace the visible text of a language link, e.g. "[[w:Old English|Old English]]" -> "Englisce", -- keeping the link target. local function replace_display(display, text) local target = display:match("^%[%[(.-)|.-%]%]$") if target then return "[[" .. target .. "|" .. text .. "]]" end return text end -- Localized display text and category name for a source language. Returns nil when the language has -- no Old English name, in which case the original English name is used. local function ang_display_and_cat_name(source, raw) local name = ang_name(source) if not name then return nil end local display if raw then display = name else display = replace_display(source:makeWikipediaLink(), ang_of(source) or name) end return display, name end local function track(page, code) local tracking_page = "etymology/" .. page debug_track(tracking_page) if code then debug_track(tracking_page .. "/" .. code) end end local function join_segs(segs, conj) if not segs[2] then return segs[1] elseif conj == "and" or conj == "or" then return serial_comma_join(segs, {conj = conj}) end local sep if conj == "," or conj == ";" then sep = conj .. " " elseif conj == "/" then sep = "/" elseif conj == "~" then sep = " ~ " elseif conj then error(("Internal error: Unrecognized conjunction \"%s\""):format(conj)) else error(("Internal error: No value supplied for conjunction"):format(conj)) end return concat(segs, sep) end -- Returns true if `lang` is the same as `source`, or a variety of it. local function lang_is_source(lang, source) return lang:getCode() == source:getCode() or lang:hasParent(source) end --[==[ Format one or more links as specified in `termobjs`, a list of term objects of the format accepted by `full_link()` in [[Module:links]], including decorations (qualifiers, labels and references). `conj` is used to join multiple terms and must be specified if there is more than one term. `template_name` is the template name used in debug tracking and must be specified. Optional `sourcetext` is text to prepend to the concatenated terms, separated by a space if the concatenated terms are non-empty (which is always the case unless there is a single term with the value "-"). If `decorations_on_outside` is given, any decorations specified in the first term go on the outside of (i.e before) `sourcetext`; otherwise they will end up on the inside. ]==] function export.format_links(termobjs, conj, template_name, sourcetext, decorations_on_outside) if not template_name then error("Internal error: Must specify `template_name` to format_links()") end for i, termobj in ipairs(termobjs) do if termobj.lang:hasType("family") or termobj.lang:getFamilyCode() == "qfa-sub" then if termobj.term and termobj.term ~= "-" then debug_track(template_name .. "/family-with-term") end termobj.term = "-" end if termobj.term == "-" then --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/cognate/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/derived/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/borrowed/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/calque/no-term]] ]=] debug_track(template_name .. "/no-term") termobjs[i] = i == 1 and sourcetext or "" else if i == 1 and decorations_on_outside and sourcetext then termobj.pretext = sourcetext .. " " sourcetext = nil end termobjs[i] = (i == 1 and sourcetext and sourcetext .. " " or "") .. full_link(termobj, "term") end end return join_segs(termobjs, conj) end function export.get_display_and_cat_name(source, raw) local display, cat_name if source:getCode() == "und" then display = "undetermined" cat_name = "other languages" elseif source:getCode() == "mul" then display = raw and "translingual" or "[[w:Translingualism|translingual]]" cat_name = "Translingual" elseif source:getCode() == "mul-tax" then display = raw and "taxonomic name" or "[[w:Biological nomenclature|taxonomic name]]" cat_name = "taxonomic names" else -- Old English localization: use the "of"-form of the name, e.g. "Of Englisce and". local ang_display, ang_cat_name = ang_display_and_cat_name(source, raw) display = ang_display or raw and source:getCanonicalName() or source:makeWikipediaLink() cat_name = ang_cat_name or source:getDisplayForm() end return display, cat_name end function export.insert_source_cat_get_display(data) local categories, lang, source = data.categories, data.lang, data.source local display, cat_name = export.get_display_and_cat_name(source, data.raw) if lang and not data.nocat then -- Add the category, but only if there is a current language if not categories then categories = {} end local langname = ang_name(lang) or lang:getFullName() -- If `lang` is an etym-only language, we need to check both it and its parent full language against `source`. -- Otherwise if e.g. `lang` is Medieval Latin and `source` is Latin, we'll end up wrongly constructing a -- category 'Latin terms derived from Latin'. insert(categories, langname .. ( lang_is_source(lang, source) and " terms borrowed back into " .. cat_name or " " .. (data.borrowing_type or "terms derived") .. " from " .. cat_name )) end return display, categories end function export.format_source(data) local lang, sort_key = data.lang, data.sort_key -- [[Special:WhatLinksHere/Wiktionary:Tracking/etymology/sortkey]] if sort_key then track("sortkey") end local display, categories = export.insert_source_cat_get_display(data) if lang and not data.nocat then -- Format categories, but only if there is a current language; {{cog}} currently gets no categories categories = format_categories(categories, lang, sort_key, nil, data.force_cat or force_cat) else categories = "" end return "<span class=\"etyl\">" .. display .. categories .. "</span>" end --[==[ Format sources for etymology templates such as {{tl|bor}}, {{tl|der}}, {{tl|inh}} and {{tl|cog}}. There may potentially be more than one source language (except currently {{tl|inh}}, which doesn't support it because it doesn't really make sense). In that case, all but the last source language is linked to the first term, but only if there is such a term and this linking makes sense, i.e. either (1) the term page exists after stripping diacritics according to the source language in question, or (2) the result of stripping diacritics according to the source language in question results in a different page from the same process applied with the last source language. For example, {{m|ru|соля́нка}} will link to [[солянка]] but {{m|en|соля́нка}} will link to [[соля́нка]] with an accent, and since they are different pages, the use of English as a non-final source with term 'соля́нка' will link to [[соля́нка]] even though it doesn't exist, on the assumption that it is merely a redlink that might exist. If none of the above criteria apply, a non-final source language will be linked to the Wikipedia entry for the language, just as final source languages always are. `data` contains the following fields: * `lang`: The destination language object into which the terms were borrowed, inherited or otherwise derived. Used for categorization and can be nil, as with {{tl|cog}}. * `sources`: List of source objects. Most commonly there is only one. If there are multiple, the non-final ones are handled specially; see above. * `terms`: List of term objects. Most commonly there is only one. If there are multiple source objects as well as multiple term objects, the non-final source objects link to the first term object. * `sort_key`: Sort key for categories. Usually nil. * `categories`: Categories to add to the page. Additional categories may be added to `categories` based on the source languages ('''in which case `categories` is destructively modified'''). If `lang` is nil, no categories will be added. * `nocat`: Don't add any categories to the page. * `sourceconj`: Conjunction used to separate multiple source languages. Defaults to {"and"}. Currently recognized values are `and`, `or`, `,`, `;`, `/` and `~`. * `borrowing_type`: Borrowing type used in categories, such as {"learned borrowings"}. Defaults to {"terms derived"}. * `force_cat`: Force category generation on non-mainspace pages. ]==] function export.format_sources(data) local lang, sources, terms, borrowing_type, sort_key, categories, nocat = data.lang, data.sources, data.terms, data.borrowing_type, data.sort_key, data.categories, data.nocat local term1, sources_n, source_segs = terms[1], #sources, {} local final_link_page local term1_term, term1_sc = term1.term, term1.sc if sources_n > 1 and term1_term and term1_term ~= "-" then final_link_page = get_link_page(term1_term, sources[sources_n], term1_sc) end for i, source in ipairs(sources) do local seg, display_term if i < sources_n and term1_term and term1_term ~= "-" then local link_page = get_link_page(term1_term, source, term1_sc) display_term = (link_page ~= final_link_page) or (link_page and not not new_title(link_page):getContent()) end -- TODO: if the display forms or transliterations are different, display the terms separately. if display_term then local display, this_cats = export.insert_source_cat_get_display{ lang = lang, source = source, borrowing_type = borrowing_type, raw = true, categories = categories, nocat = nocat, } seg = language_link { lang = source, term = term1_term, alt = display, tr = "-", } if lang and not nocat then -- Format categories, but only if there is a current language; {{cog}} currently gets no categories this_cats = format_categories(this_cats, lang, sort_key, nil, data.force_cat or force_cat) else this_cats = "" end seg = "<span class=\"etyl\">" .. seg .. this_cats .. "</span>" else seg = export.format_source{ lang = lang, source = source, borrowing_type = borrowing_type, sort_key = sort_key, categories = categories, nocat = nocat, } end insert(source_segs, seg) end return join_segs(source_segs, data.sourceconj or "and") end -- Internal implementation of {{cognate}}/{{cog}} template. function export.format_cognate(data) return export.format_derived { sources = data.sources, terms = data.terms, sort_key = data.sort_key, sourceconj = data.sourceconj, conj = data.conj, template_name = "cognate", force_cat = data.force_cat, } end --[==[ Internal implementation of {{derived}}/{{der}} template. This is called externally from [[Module:affix]], [[Module:affixusex]] and [[Module:see]] and needs to support decorations (qualifiers, labels and references) on the outside of the sources for use by those modules. `data` contains the following fields: * `lang`: The destination language object into which the terms were derived. Used for categorization and can be nil, as with {{tl|cog}}; in this case, no categories are added. * `sources`: List of source objects. Most commonly there is only one. If there are multiple, the non-final ones are handled specially; see `format_sources()`. * `terms`: List of term objects. Most commonly there is only one. If there are multiple source objects as well as multiple term objects, the non-final source objects link to the first term object. * `conj`: Conjunction used to separate multiple terms. '''Required'''. Currently recognized values are `and`, `or`, `,`, `;`, `/` and `~`. * `sourceconj`: Conjunction used to separate multiple source languages. Defaults to {"and"}. Currently recognized values are as for `conj` above. * `decorations_on_outside`: If specified, any decorations (qualifiers, labels or references) in the first term in `terms` will be displayed on the outside of (before) the source language(s) in `sources`. Normally this should be specified if there is only one term possible in `terms`. * `template_name`: Name of the template invoking this function. Must be specified. Only used for tracking pages. * `sort_key`: Sort key for categories. Usually nil. * `categories`: Categories to add to the page. Additional categories may be added to `categories` based on the source languages ('''in which case `categories` is destructively modified'''). If `lang` is nil, no categories will be added. * `nocat`: Don't add any categories to the page. * `borrowing_type`: Borrowing type used in categories, such as {"learned borrowings"}. Defaults to {"terms derived"}. * `force_cat`: Force category generation on non-mainspace pages. ]==] function export.format_derived(data) local terms = data.terms local sourcetext = export.format_sources(data) return export.format_links(terms, data.conj, data.template_name, sourcetext, data.decorations_on_outside) end function export.insert_borrowed_cat(categories, lang, source) if lang_is_source(lang, source) then return end -- If both are the same, we want e.g. [[:Category:English terms borrowed back into English]] not -- [[:Category:English terms borrowed from English]]; the former is inserted automatically by format_source(). -- The second parameter here doesn't matter as it only affects `display`, which we don't use. insert(categories, (ang_name(lang) or lang:getFullName()) .. " terms borrowed from " .. select(2, export.get_display_and_cat_name(source, "raw"))) end -- Internal implementation of {{borrowed}}/{{bor}} template. function export.format_borrowed(data) local categories = {} if not data.nocat then local lang = data.lang for _, source in ipairs(data.sources) do export.insert_borrowed_cat(categories, lang, source) end end data = shallow_copy(data) data.categories = categories return export.format_links(data.terms, data.conj, "borrowed", export.format_sources(data)) end do -- Generate the non-ancestor error message. local function show_language(lang) local retval = ("%s (%s)"):format(lang:makeCategoryLink(), lang:getCode()) if lang:hasType("etymology-only") then retval = retval .. (" (an etymology-only language whose regular parent is %s)"):format( show_language(lang:getParent())) end return retval end -- Check that `lang` has `otherlang` (which may be an etymology-only language) as an ancestor. Throw an error if -- not. When `lang` is a family, verifies that `otherlang` is a language in that family. function export.check_ancestor(lang, otherlang) -- When `lang` is a family, verify `otherlang` is in that family or in its parent family. if lang.hasType and lang:hasType("family") then local family_code = lang:getCode() local function in_family_code(fcode, other) if not fcode or fcode == "" then return false end if other.inFamily and other:inFamily(fcode) then return true end if other.getFamilyCode and other:getFamilyCode() == fcode then return true end return false end local in_family = in_family_code(family_code, otherlang) if not in_family then local parent_code if lang.getParent then local parent_family = lang:getParent() if parent_family and parent_family.getCode then parent_code = parent_family:getCode() end end if not parent_code and family_code:find("-", 1, true) then parent_code = family_code:match("^(.+)-[^-]+$") end if parent_code then in_family = in_family_code(parent_code, otherlang) end end if not in_family then local other_display = (otherlang.getCanonicalName and otherlang:getCanonicalName()) or (otherlang.getCode and otherlang:getCode()) or tostring(otherlang) local fam_display = (lang.getCanonicalName and lang:getCanonicalName()) or family_code error(("%s is not in family %s; inherited ancestor under a family must be a language in that family or its parent family.") :format(other_display, fam_display)) end return end -- FIXME: I don't know if this function works correctly with etym-only languages in `lang`. I have fixed up -- the module link code appropriately (June 2024) but the remaining logic is untouched. if lang:hasAncestor(otherlang) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/etymology/variety]] -- Track inheritance from varieties of Latin that shouldn't have any descendants (everything except Old Latin, Classical Latin and Vulgar Latin). if otherlang:getFullCode() == "la" then otherlang = otherlang:getCode() if not (otherlang == "itc-ola" or otherlang == "la-cla" or otherlang == "la-vul") then track("bad ancestor", otherlang) end end return end local ancestors = lang:getAncestors() local postscript local etym_module_link = lang:hasType("etymology-only") and "[[Module:etymology languages/data]] or " or "" local module_link = "[[" .. get_language_data_module_name(lang:getFullCode()) .. "]]" if not ancestors[1] then postscript = show_language(lang) .. " has no ancestors." else local ancestor_list = {} for _, ancestor in ipairs(ancestors) do insert(ancestor_list, show_language(ancestor)) end postscript = ("The ancestor%s of %s %s %s."):format( ancestors[2] and "s" or "", lang:getCanonicalName(), ancestors[2] and "are" or "is", concat(ancestor_list, " and ")) end error(("%s is not set as an ancestor of %s in %s%s. %s") :format(show_language(otherlang), show_language(lang), etym_module_link, module_link, postscript)) end end -- Internal implementation of {{inherited}}/{{inh}} template. function export.format_inherited(data) local lang, terms, nocat = data.lang, data.terms, data.nocat local source = terms[1].lang local categories = {} if not nocat then insert(categories, (ang_name(lang) or lang:getFullName()) .. " terms inherited from " .. (ang_name(source) or source:getCanonicalName())) end export.check_ancestor(lang, source) data = shallow_copy(data) data.categories = categories data.source = source return export.format_links(terms, data.conj, "inherited", export.format_source(data)) end -- Internal implementation of "misc variant" templates such as {{abbrev}}, {{clipping}}, {{reduplication}} and the like. function export.format_misc_variant(data) local lang, notext, terms, cats, parts = data.lang, data.notext, data.terms, data.cats, {} if not notext then insert(parts, data.text) end if terms[1] then if not notext then -- FIXME: If term is given as '-', we should consider displaying just "Clipping" not "Clipping of". insert(parts, " " .. (data.oftext or "of")) end local termparts = {} -- Make links out of all the parts. for _, termobj in ipairs(terms) do local result if termobj.lang then result = export.format_derived { lang = lang, terms = {termobj}, sources = termobj.termlangs or {termobj.lang}, template_name = "misc_variant", decorations_on_outside = true, force_cat = data.force_cat, } else termobj.lang = lang result = export.format_links({termobj}, nil, "misc_variant") end table.insert(termparts, result) end local linktext = join_segs(termparts, data.conj) if not notext and linktext ~= "" then insert(parts, " ") end insert(parts, linktext) end local categories = {} if not data.nocat and cats then for _, cat in ipairs(cats) do insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. cat) end end if categories[1] then insert(parts, format_categories(categories, lang, data.sort_key, nil, data.force_cat or force_cat)) end return concat(parts) end -- Implementation of miscellaneous templates such as {{unknown}} and {{onomatopoeia}} that have no associated terms. function export.format_misc_variant_no_term(data) local parts = {} if not data.notext then insert(parts, data.title) end if not data.nocat and data.cat then local lang, categories = data.lang, {} insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. data.cat) insert(parts, format_categories(categories, lang, data.sort_key, nil, data.force_cat or force_cat)) end return concat(parts) end return export tme5lnxmobc95ub37jg1tqwmk1tlre9 54922 54905 2026-09-29T00:03:01Z Deadend0914 7211 54922 Scribunto text/plain local export = {} -- For testing local force_cat = false local debug_track_module = "Module:debug/track" local languages_module = "Module:languages" local links_module = "Module:links" local table_module = "Module:table" local utilities_module = "Module:utilities" local concat = table.concat local insert = table.insert local new_title = mw.title.new local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function full_link(...) full_link = require(links_module).full_link return full_link(...) end local function get_language_data_module_name(...) get_language_data_module_name = require(languages_module).getDataModuleName return get_language_data_module_name(...) end local function get_link_page(...) get_link_page = require(links_module).get_link_page return get_link_page(...) end local function language_link(...) language_link = require(links_module).language_link return language_link(...) end local function serial_comma_join(...) serial_comma_join = require(table_module).serialCommaJoin return serial_comma_join(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end -- Old English localization: language names come from [[Module:sprǣcnaman]], which is also what -- [[Bysen:sprǣc]] (the ==L2== heading template) uses, so headings, wordstǣr lines and categories -- can never disagree with each other. The module is optional: if it is missing, the English names -- are used exactly as before. local ang_names_module = "Module:sprǣcnaman" local ang_names local function get_ang_names() if ang_names == nil then local ok, mod = pcall(require, ang_names_module) ang_names = ok and mod or false end return ang_names or nil end -- Old English name of the language, or nil. local function ang_name(lang) local mod = get_ang_names() return mod and mod.get_name(lang) or nil end -- Old English "of"-form of the language, or nil. local function ang_of(lang) local mod = get_ang_names() return mod and mod.get_of(lang) or nil end -- Replace the visible text of a language link, e.g. "[[w:Old English|Old English]]" -> "Englisce", -- keeping the link target. local function replace_display(display, text) local target = display:match("^%[%[(.-)|.-%]%]$") if target then return "[[" .. target .. "|" .. text .. "]]" end return text end -- Localized display text and category name for a source language. Returns nil when the language has -- no Old English name, in which case the original English name is used. -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end local function ang_display_and_cat_name(source, raw) local name = ang_name(source) if not name then return nil end local display if raw then display = name else display = replace_display(source:makeWikipediaLink(), ang_of(source) or name) end return display, name end local function track(page, code) local tracking_page = "etymology/" .. page debug_track(tracking_page) if code then debug_track(tracking_page .. "/" .. code) end end local function join_segs(segs, conj) if not segs[2] then return segs[1] elseif conj == "and" or conj == "or" then return serial_comma_join(segs, {conj = conj}) end local sep if conj == "," or conj == ";" then sep = conj .. " " elseif conj == "/" then sep = "/" elseif conj == "~" then sep = " ~ " elseif conj then error(("Internal error: Unrecognized conjunction \"%s\""):format(conj)) else error(("Internal error: No value supplied for conjunction"):format(conj)) end return concat(segs, sep) end -- Returns true if `lang` is the same as `source`, or a variety of it. local function lang_is_source(lang, source) return lang:getCode() == source:getCode() or lang:hasParent(source) end --[==[ Format one or more links as specified in `termobjs`, a list of term objects of the format accepted by `full_link()` in [[Module:links]], including decorations (qualifiers, labels and references). `conj` is used to join multiple terms and must be specified if there is more than one term. `template_name` is the template name used in debug tracking and must be specified. Optional `sourcetext` is text to prepend to the concatenated terms, separated by a space if the concatenated terms are non-empty (which is always the case unless there is a single term with the value "-"). If `decorations_on_outside` is given, any decorations specified in the first term go on the outside of (i.e before) `sourcetext`; otherwise they will end up on the inside. ]==] function export.format_links(termobjs, conj, template_name, sourcetext, decorations_on_outside) if not template_name then error("Internal error: Must specify `template_name` to format_links()") end for i, termobj in ipairs(termobjs) do if termobj.lang:hasType("family") or termobj.lang:getFamilyCode() == "qfa-sub" then if termobj.term and termobj.term ~= "-" then debug_track(template_name .. "/family-with-term") end termobj.term = "-" end if termobj.term == "-" then --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/cognate/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/derived/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/borrowed/no-term]] [[Special:WhatLinksHere/Wiktionary:Tracking/calque/no-term]] ]=] debug_track(template_name .. "/no-term") termobjs[i] = i == 1 and sourcetext or "" else if i == 1 and decorations_on_outside and sourcetext then termobj.pretext = sourcetext .. " " sourcetext = nil end termobjs[i] = (i == 1 and sourcetext and sourcetext .. " " or "") .. full_link(termobj, "term") end end return join_segs(termobjs, conj) end function export.get_display_and_cat_name(source, raw) local display, cat_name if source:getCode() == "und" then display = "undetermined" cat_name = cat_word(source, "other languages") elseif source:getCode() == "mul" then display = raw and "translingual" or "[[w:Translingualism|translingual]]" cat_name = cat_word(source, "Translingual") elseif source:getCode() == "mul-tax" then display = raw and "taxonomic name" or "[[w:Biological nomenclature|taxonomic name]]" cat_name = cat_word(source, "taxonomic names") else -- Old English localization: use the "of"-form of the name, e.g. "Of Englisce and". local ang_display, ang_cat_name = ang_display_and_cat_name(source, raw) display = ang_display or raw and source:getCanonicalName() or source:makeWikipediaLink() cat_name = ang_cat_name or source:getDisplayForm() end return display, cat_name end function export.insert_source_cat_get_display(data) local categories, lang, source = data.categories, data.lang, data.source local display, cat_name = export.get_display_and_cat_name(source, data.raw) if lang and not data.nocat then -- Add the category, but only if there is a current language if not categories then categories = {} end local langname = ang_name(lang) or lang:getFullName() -- If `lang` is an etym-only language, we need to check both it and its parent full language against `source`. -- Otherwise if e.g. `lang` is Medieval Latin and `source` is Latin, we'll end up wrongly constructing a -- category 'Latin terms derived from Latin'. insert(categories, langname .. ( lang_is_source(lang, source) and (" " .. cat_word(lang, "terms borrowed back into") .. " " .. cat_name) or " " .. cat_word(lang, data.borrowing_type or "terms derived") .. " " .. cat_word(lang, "from") .. " " .. cat_name )) end return display, categories end function export.format_source(data) local lang, sort_key = data.lang, data.sort_key -- [[Special:WhatLinksHere/Wiktionary:Tracking/etymology/sortkey]] if sort_key then track("sortkey") end local display, categories = export.insert_source_cat_get_display(data) if lang and not data.nocat then -- Format categories, but only if there is a current language; {{cog}} currently gets no categories categories = format_categories(categories, lang, sort_key, nil, data.force_cat or force_cat) else categories = "" end return "<span class=\"etyl\">" .. display .. categories .. "</span>" end --[==[ Format sources for etymology templates such as {{tl|bor}}, {{tl|der}}, {{tl|inh}} and {{tl|cog}}. There may potentially be more than one source language (except currently {{tl|inh}}, which doesn't support it because it doesn't really make sense). In that case, all but the last source language is linked to the first term, but only if there is such a term and this linking makes sense, i.e. either (1) the term page exists after stripping diacritics according to the source language in question, or (2) the result of stripping diacritics according to the source language in question results in a different page from the same process applied with the last source language. For example, {{m|ru|соля́нка}} will link to [[солянка]] but {{m|en|соля́нка}} will link to [[соля́нка]] with an accent, and since they are different pages, the use of English as a non-final source with term 'соля́нка' will link to [[соля́нка]] even though it doesn't exist, on the assumption that it is merely a redlink that might exist. If none of the above criteria apply, a non-final source language will be linked to the Wikipedia entry for the language, just as final source languages always are. `data` contains the following fields: * `lang`: The destination language object into which the terms were borrowed, inherited or otherwise derived. Used for categorization and can be nil, as with {{tl|cog}}. * `sources`: List of source objects. Most commonly there is only one. If there are multiple, the non-final ones are handled specially; see above. * `terms`: List of term objects. Most commonly there is only one. If there are multiple source objects as well as multiple term objects, the non-final source objects link to the first term object. * `sort_key`: Sort key for categories. Usually nil. * `categories`: Categories to add to the page. Additional categories may be added to `categories` based on the source languages ('''in which case `categories` is destructively modified'''). If `lang` is nil, no categories will be added. * `nocat`: Don't add any categories to the page. * `sourceconj`: Conjunction used to separate multiple source languages. Defaults to {"and"}. Currently recognized values are `and`, `or`, `,`, `;`, `/` and `~`. * `borrowing_type`: Borrowing type used in categories, such as {"learned borrowings"}. Defaults to {"terms derived"}. * `force_cat`: Force category generation on non-mainspace pages. ]==] function export.format_sources(data) local lang, sources, terms, borrowing_type, sort_key, categories, nocat = data.lang, data.sources, data.terms, data.borrowing_type, data.sort_key, data.categories, data.nocat local term1, sources_n, source_segs = terms[1], #sources, {} local final_link_page local term1_term, term1_sc = term1.term, term1.sc if sources_n > 1 and term1_term and term1_term ~= "-" then final_link_page = get_link_page(term1_term, sources[sources_n], term1_sc) end for i, source in ipairs(sources) do local seg, display_term if i < sources_n and term1_term and term1_term ~= "-" then local link_page = get_link_page(term1_term, source, term1_sc) display_term = (link_page ~= final_link_page) or (link_page and not not new_title(link_page):getContent()) end -- TODO: if the display forms or transliterations are different, display the terms separately. if display_term then local display, this_cats = export.insert_source_cat_get_display{ lang = lang, source = source, borrowing_type = borrowing_type, raw = true, categories = categories, nocat = nocat, } seg = language_link { lang = source, term = term1_term, alt = display, tr = "-", } if lang and not nocat then -- Format categories, but only if there is a current language; {{cog}} currently gets no categories this_cats = format_categories(this_cats, lang, sort_key, nil, data.force_cat or force_cat) else this_cats = "" end seg = "<span class=\"etyl\">" .. seg .. this_cats .. "</span>" else seg = export.format_source{ lang = lang, source = source, borrowing_type = borrowing_type, sort_key = sort_key, categories = categories, nocat = nocat, } end insert(source_segs, seg) end return join_segs(source_segs, data.sourceconj or "and") end -- Internal implementation of {{cognate}}/{{cog}} template. function export.format_cognate(data) return export.format_derived { sources = data.sources, terms = data.terms, sort_key = data.sort_key, sourceconj = data.sourceconj, conj = data.conj, template_name = "cognate", force_cat = data.force_cat, } end --[==[ Internal implementation of {{derived}}/{{der}} template. This is called externally from [[Module:affix]], [[Module:affixusex]] and [[Module:see]] and needs to support decorations (qualifiers, labels and references) on the outside of the sources for use by those modules. `data` contains the following fields: * `lang`: The destination language object into which the terms were derived. Used for categorization and can be nil, as with {{tl|cog}}; in this case, no categories are added. * `sources`: List of source objects. Most commonly there is only one. If there are multiple, the non-final ones are handled specially; see `format_sources()`. * `terms`: List of term objects. Most commonly there is only one. If there are multiple source objects as well as multiple term objects, the non-final source objects link to the first term object. * `conj`: Conjunction used to separate multiple terms. '''Required'''. Currently recognized values are `and`, `or`, `,`, `;`, `/` and `~`. * `sourceconj`: Conjunction used to separate multiple source languages. Defaults to {"and"}. Currently recognized values are as for `conj` above. * `decorations_on_outside`: If specified, any decorations (qualifiers, labels or references) in the first term in `terms` will be displayed on the outside of (before) the source language(s) in `sources`. Normally this should be specified if there is only one term possible in `terms`. * `template_name`: Name of the template invoking this function. Must be specified. Only used for tracking pages. * `sort_key`: Sort key for categories. Usually nil. * `categories`: Categories to add to the page. Additional categories may be added to `categories` based on the source languages ('''in which case `categories` is destructively modified'''). If `lang` is nil, no categories will be added. * `nocat`: Don't add any categories to the page. * `borrowing_type`: Borrowing type used in categories, such as {"learned borrowings"}. Defaults to {"terms derived"}. * `force_cat`: Force category generation on non-mainspace pages. ]==] function export.format_derived(data) local terms = data.terms local sourcetext = export.format_sources(data) return export.format_links(terms, data.conj, data.template_name, sourcetext, data.decorations_on_outside) end function export.insert_borrowed_cat(categories, lang, source) if lang_is_source(lang, source) then return end -- If both are the same, we want e.g. [[:Category:English terms borrowed back into English]] not -- [[:Category:English terms borrowed from English]]; the former is inserted automatically by format_source(). -- The second parameter here doesn't matter as it only affects `display`, which we don't use. insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. cat_word(lang, "terms borrowed from") .. " " .. select(2, export.get_display_and_cat_name(source, "raw"))) end -- Internal implementation of {{borrowed}}/{{bor}} template. function export.format_borrowed(data) local categories = {} if not data.nocat then local lang = data.lang for _, source in ipairs(data.sources) do export.insert_borrowed_cat(categories, lang, source) end end data = shallow_copy(data) data.categories = categories return export.format_links(data.terms, data.conj, "borrowed", export.format_sources(data)) end do -- Generate the non-ancestor error message. local function show_language(lang) local retval = ("%s (%s)"):format(lang:makeCategoryLink(), lang:getCode()) if lang:hasType("etymology-only") then retval = retval .. (" (an etymology-only language whose regular parent is %s)"):format( show_language(lang:getParent())) end return retval end -- Check that `lang` has `otherlang` (which may be an etymology-only language) as an ancestor. Throw an error if -- not. When `lang` is a family, verifies that `otherlang` is a language in that family. function export.check_ancestor(lang, otherlang) -- When `lang` is a family, verify `otherlang` is in that family or in its parent family. if lang.hasType and lang:hasType("family") then local family_code = lang:getCode() local function in_family_code(fcode, other) if not fcode or fcode == "" then return false end if other.inFamily and other:inFamily(fcode) then return true end if other.getFamilyCode and other:getFamilyCode() == fcode then return true end return false end local in_family = in_family_code(family_code, otherlang) if not in_family then local parent_code if lang.getParent then local parent_family = lang:getParent() if parent_family and parent_family.getCode then parent_code = parent_family:getCode() end end if not parent_code and family_code:find("-", 1, true) then parent_code = family_code:match("^(.+)-[^-]+$") end if parent_code then in_family = in_family_code(parent_code, otherlang) end end if not in_family then local other_display = (otherlang.getCanonicalName and otherlang:getCanonicalName()) or (otherlang.getCode and otherlang:getCode()) or tostring(otherlang) local fam_display = (lang.getCanonicalName and lang:getCanonicalName()) or family_code error(("%s is not in family %s; inherited ancestor under a family must be a language in that family or its parent family.") :format(other_display, fam_display)) end return end -- FIXME: I don't know if this function works correctly with etym-only languages in `lang`. I have fixed up -- the module link code appropriately (June 2024) but the remaining logic is untouched. if lang:hasAncestor(otherlang) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/etymology/variety]] -- Track inheritance from varieties of Latin that shouldn't have any descendants (everything except Old Latin, Classical Latin and Vulgar Latin). if otherlang:getFullCode() == "la" then otherlang = otherlang:getCode() if not (otherlang == "itc-ola" or otherlang == "la-cla" or otherlang == "la-vul") then track("bad ancestor", otherlang) end end return end local ancestors = lang:getAncestors() local postscript local etym_module_link = lang:hasType("etymology-only") and "[[Module:etymology languages/data]] or " or "" local module_link = "[[" .. get_language_data_module_name(lang:getFullCode()) .. "]]" if not ancestors[1] then postscript = show_language(lang) .. " has no ancestors." else local ancestor_list = {} for _, ancestor in ipairs(ancestors) do insert(ancestor_list, show_language(ancestor)) end postscript = ("The ancestor%s of %s %s %s."):format( ancestors[2] and "s" or "", lang:getCanonicalName(), ancestors[2] and "are" or "is", concat(ancestor_list, " and ")) end error(("%s is not set as an ancestor of %s in %s%s. %s") :format(show_language(otherlang), show_language(lang), etym_module_link, module_link, postscript)) end end -- Internal implementation of {{inherited}}/{{inh}} template. function export.format_inherited(data) local lang, terms, nocat = data.lang, data.terms, data.nocat local source = terms[1].lang local categories = {} if not nocat then insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. cat_word(lang, "terms inherited from") .. " " .. (ang_name(source) or source:getCanonicalName())) end export.check_ancestor(lang, source) data = shallow_copy(data) data.categories = categories data.source = source return export.format_links(terms, data.conj, "inherited", export.format_source(data)) end -- Internal implementation of "misc variant" templates such as {{abbrev}}, {{clipping}}, {{reduplication}} and the like. function export.format_misc_variant(data) local lang, notext, terms, cats, parts = data.lang, data.notext, data.terms, data.cats, {} if not notext then insert(parts, data.text) end if terms[1] then if not notext then -- FIXME: If term is given as '-', we should consider displaying just "Clipping" not "Clipping of". insert(parts, " " .. (data.oftext or "of")) end local termparts = {} -- Make links out of all the parts. for _, termobj in ipairs(terms) do local result if termobj.lang then result = export.format_derived { lang = lang, terms = {termobj}, sources = termobj.termlangs or {termobj.lang}, template_name = "misc_variant", decorations_on_outside = true, force_cat = data.force_cat, } else termobj.lang = lang result = export.format_links({termobj}, nil, "misc_variant") end table.insert(termparts, result) end local linktext = join_segs(termparts, data.conj) if not notext and linktext ~= "" then insert(parts, " ") end insert(parts, linktext) end local categories = {} if not data.nocat and cats then for _, cat in ipairs(cats) do insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. cat_word(lang, cat)) end end if categories[1] then insert(parts, format_categories(categories, lang, data.sort_key, nil, data.force_cat or force_cat)) end return concat(parts) end -- Implementation of miscellaneous templates such as {{unknown}} and {{onomatopoeia}} that have no associated terms. function export.format_misc_variant_no_term(data) local parts = {} if not data.notext then insert(parts, data.title) end if not data.nocat and data.cat then local lang, categories = data.lang, {} insert(categories, (ang_name(lang) or lang:getFullName()) .. " " .. cat_word(lang, data.cat)) insert(parts, format_categories(categories, lang, data.sort_key, nil, data.force_cat or force_cat)) end return concat(parts) end return export tc1h50hma4xpgupok2rsigzjth6htgg 828 8065 54923 54878 2026-09-29T00:03:30Z Deadend0914 7211 54923 Scribunto text/plain local export = {} local m_str_utils = require("Module:string utilities") local en_utilities_module = "Module:en-utilities" local etymology_module = "Module:etymology" local gsub = m_str_utils.gsub local insert = table.insert local pluralize = require(en_utilities_module).pluralize local upper = m_str_utils.upper -- This function handles all the messiness of different types of specialized borrowings. It should insert any -- borrowing-type-specific categories into `categories` unless `nocat` is given, and return the text to display -- before the source + term (or "" for no text). -- Old English localization: category wordings come from [[Module:floccnaman]] (see that module); -- the English wording is kept when a translation is missing. Loaded lazily and optionally, so a -- missing module can never break a page. local floccnaman_module = "Module:floccnaman" local floccnaman local function get_floccnaman() if floccnaman == nil then local ok, mod = pcall(require, floccnaman_module) floccnaman = ok and mod or false end return floccnaman or nil end -- Old English wording for one category word, or the English wording unchanged. local function cat_word(lang, text) local mod = get_floccnaman() return mod and mod.get(lang, text) or text end local function get_specialized_borrowing_text_insert_cats(data) local bortype, categories, lang, terms, source, nocap, nocat, senseid = data.bortype, data.categories, data.lang, data.terms, data.source, data.nocap, data.nocat, data.senseid local function inscat(cat) if not nocat then local display, sourcedisp = require(etymology_module).get_display_and_cat_name(source, "raw") if cat:find("DISPLAY") then cat = cat:gsub("DISPLAY", display) elseif cat:find("SOURCE") then cat = cat:gsub("SOURCE", sourcedisp) else cat = cat .. " " .. sourcedisp end insert(categories, lang:getFullName() .. " " .. cat_word(lang, cat)) end end -- `text` is the display text for the borrowing type, which gets converted -- into a link. -- `appendix` is a the glossary anchor, which defaults to `text` -- `prep` is the preposition between the borrowing type and the language -- name (e.g. "of", "from") -- `pos` is the part of speech for the borrowing type ("noun" or -- "adjective"; defaults to "noun") -- `plural` is the plural form of the borrowing type; if not specified, -- the pluralize function is used local text, appendix, prep, pos, plural if bortype == "calque" then text, prep = "calque", "of" inscat("terms calqued from") elseif bortype == "partial-calque" then text, prep = "partial calque", "of" inscat("terms partially calqued from") elseif bortype == "semantic-loan" then text, prep = "semantic loan", "from" inscat("semantic loans from") elseif bortype == "transliteration" then text, prep = "transliteration", "of" inscat("terms borrowed from") inscat("transliterations of DISPLAY terms") elseif bortype == "phono-semantic-matching" then text, prep = "phono-semantic matching", "of" inscat("phono-semantic matchings from") else local langcode = lang:getCode() local lang_is_source = langcode == source:getCode() if lang_is_source then -- Track, because this shouldn't be happening. A language can only have itself as a source further up the chain after a borrowing, which is always "derived". require("Module:debug/track"){ "etymology/specialized/self-as-source", "etymology/specialized/self-as-source/" .. langcode } inscat("terms borrowed back into") else inscat("terms borrowed from") if bortype ~= "borrowing" then inscat(bortype .. " borrowings from") end end if bortype == "borrowing" then text, appendix, prep, pos = "borrowed", "loanword", "from", "adjective" elseif ( bortype == "learned" or bortype == "semi-learned" or bortype == "orthographic" or bortype == "unadapted" ) then text, prep = bortype .. " borrowing", "from" elseif bortype == "adapted" then text, prep = bortype .. " borrowing", "of" else error("Internal error: Unrecognized bortype: " .. bortype) end end -- If the term is suppressed, the preposition should always be "from": -- "Calque of Chinese 中國". -- "Calque from Chinese" (not "Calque of Chinese"). if terms[1].term == "-" then prep = "from" end appendix = "Appendix:Glossary#" .. (appendix or text) if senseid then local senseids, output = mw.text.split(senseid, '!!'), {} for i, id in ipairs(senseids) do -- FIXME: This should be done via a function. insert(output, mw.getCurrentFrame():preprocess('{{senseno|' .. lang:getCode() .. '|' .. id .. (i == 1 and not nocap and "|uc=1" or "") .. '}}')) end local link if senseid:find('!!') then link, text = "are", pos == "adjective" and text or plural or pluralize(text) else link = pos == "adjective" and "is" or "is a" end text = mw.text.listToText(output) .. " " .. link .. " " .. '[[' .. appendix .. '|' .. text .. ']]' else text = "[[" .. appendix .. "|" .. (nocap and text or gsub(text, "^.", upper)) .. "]]" end return text .. " " .. prep .. " " end function export.specialized_borrowing(data) local lang, sources, terms = data.lang, data.sources, data.terms local categories = {} local text for _, source in ipairs(sources) do text = get_specialized_borrowing_text_insert_cats { bortype = data.bortype, categories = categories, lang = lang, terms = terms, source = source, nocap = data.nocap, nocat = data.nocat, senseid = data.senseid, } end text = data.notext and "" or text local sourcetext = require(etymology_module).format_sources { lang = lang, sources = sources, terms = terms, sort_key = data.sort_key, categories = categories, nocat = data.nocat, sourceconj = data.sourceconj, } return text .. require(etymology_module).format_links(terms, data.conj, "etymology/specialized", sourcetext) end return export k0nrpxi8wtdfcl3hfg6iamh8tat8ooh 2 8070 54891 54887 2026-09-28T20:30:37Z Deadend0914 7211 /* Parts of Speach */ 54891 wikitext text/x-wiki =Standardization!= ==Parts of Speach== * (a lot of these are already established, this is just a list) *Noun - Nama ** Masculine - Werlic ** Feminine - Wīflic ** Neuter - Nāhwæðer *Adjective - Tōgeīecendlic (note: this is also an adjective) *Adverb - Bīword *Case - Cāsus ** Accusative - Wrēgendlic ** Dative - Forgifendlic ** Genitive - Āgniendlic ** Imperative - Bebēodendlic ** Instrumental - Tōllic ** Nominative - Nemniendlic ** Subjunctive - Underþēodendlic * Comparable or Comparative - Wiþmetendlīc *Conjunction - Fēgung *Declension(s) - Declīnung(a) *Gender - Cynn *Inflection - Gebīegednes *Infinitive (or Indefinite) - Ungeendigendlic *Interjection - Betwuxālegednes *Participle - Dǣlnimend *Person - Hād *Plural - Manigfealdlic (mnf.) *Preposition - Foresetednes *Pronoun - Bīnama *Singular - Ānfealdlic (anf.) *Time - Tīd ** Past - Forþgewiten ** Perfect - Fullfremed ** Present - Andweardnes *Verb - Word ** Strong - Strang ** Weak - Unstrang =Templates= ==Noun Example (use 2 "=")== *(script used is sprǣc|language-code surrounded by brackets ({}). =={{sprǣc|ang}}== ===Āwendednessa (use 3 "=")=== * Here, you put alternate forms of words. Optional. ===Rihtstefn (use 3 "=")=== * Here, you put the pronunciation of the word. * IPA: /whatever-word/ ===Wordstǣr (use 3 "=")=== * Here, you put where the word came from. I'm still working on the script but it will be inh|current-language|language-from|word * For now, use this format below * Of (language, use the dative) ====Gesibbword==== * Same language Cognates ====Sweostorword==== * Non-same language Cognates) ====Cildru==== * Descendants ===(Gender if applicable) Nama (use 3 "=")=== * Still working on the script here, for now use 3 ' around the word! '''example''' * For definitions, use a #, and for examples, use #: # It will look like this #: This is an example! ====Declīnung (use 4 "=")==== * Here, you put the inflection table! The script is depending on the specific noun's conjugation! I'll make a page for that soon! ====Wendunga (use 4 "=")==== * Here, you put translations! Only for Englisc words! * Categories go further down, but it doesn't really matter where, because they don't appear on the actual page anyway. We use Flocc:(whatever category name) inside square brackets "[]" a98udzvqkvko7wzpa256z96e3t0fxu8 54892 54891 2026-09-28T20:31:25Z Deadend0914 7211 /* Parts of Speach */ 54892 wikitext text/x-wiki =Standardization!= ==Parts of Speach== * (a lot of these are already established, this is just a list) *Noun - Nama ** Masculine - Werlic ** Feminine - Wīflic ** Neuter - Nāhwæðer *Adjective - Tōgeīecendlic (note: this is also an adjective) *Adverb - Bīword *Case - Cāsus ** Accusative - Wrēgendlic ** Dative - Forgifendlic ** Genitive - Āgniendlic ** Imperative - Bebēodendlic ** Instrumental - Tōllic ** Nominative - Nemniendlic ** Subjunctive - Underþēodendlic * Comparable or Comparative - Wiþmetendlīc *Conjunction - Fēgung *Declension(s) - Declīnung(a) *Gender - Cynn *Inflection - Gebīegednes *Infinitive (or Indefinite) - Ungeendigendlic *Interjection - Betwuxālegednes *Participle - Dǣlnimend *Person - Hād *Plural - Manigfealdlic (mnf.) *Preposition - Foresetednes *Pronoun - Bīnama *Proper Noun - Āgennama *Singular - Ānfealdlic (anf.) *Time - Tīd ** Past - Forþgewiten ** Perfect - Fullfremed ** Present - Andweardnes *Verb - Word ** Strong - Strang ** Weak - Unstrang =Templates= ==Noun Example (use 2 "=")== *(script used is sprǣc|language-code surrounded by brackets ({}). =={{sprǣc|ang}}== ===Āwendednessa (use 3 "=")=== * Here, you put alternate forms of words. Optional. ===Rihtstefn (use 3 "=")=== * Here, you put the pronunciation of the word. * IPA: /whatever-word/ ===Wordstǣr (use 3 "=")=== * Here, you put where the word came from. I'm still working on the script but it will be inh|current-language|language-from|word * For now, use this format below * Of (language, use the dative) ====Gesibbword==== * Same language Cognates ====Sweostorword==== * Non-same language Cognates) ====Cildru==== * Descendants ===(Gender if applicable) Nama (use 3 "=")=== * Still working on the script here, for now use 3 ' around the word! '''example''' * For definitions, use a #, and for examples, use #: # It will look like this #: This is an example! ====Declīnung (use 4 "=")==== * Here, you put the inflection table! The script is depending on the specific noun's conjugation! I'll make a page for that soon! ====Wendunga (use 4 "=")==== * Here, you put translations! Only for Englisc words! * Categories go further down, but it doesn't really matter where, because they don't appear on the actual page anyway. We use Flocc:(whatever category name) inside square brackets "[]" hjvpjsii9yw2liqk2a9z1jrfor16tdt 54893 54892 2026-09-28T20:33:54Z Deadend0914 7211 /* Parts of Speach */ 54893 wikitext text/x-wiki =Standardization!= ==Parts of Speach== * (a lot of these are already established, this is just a list) *Noun - Nama ** Masculine - Werlic ** Feminine - Wīflic ** Neuter - Nāhwæðer *Adjective - Tōgeīecendlic (note: this is also an adjective) *Adverb - Bīword *Case - Cāsus ** Accusative - Wrēgendlic ** Dative - Forgifendlic ** Genitive - Āgniendlic ** Imperative - Bebēodendlic ** Instrumental - Tōllic ** Nominative - Nemniendlic ** Subjunctive - Underþēodendlic * Comparable or Comparative - Wiþmetendlīc *Conjunction - Fēgung *Declension(s) - Declīnung(a) *Gender - Cynn *Inflection - Gebīegednes *Infinitive (or Indefinite) - Ungeendigendlic *Interjection - Betwuxālegednes *Lemma - Frumcenned *Participle - Dǣlnimend *Person - Hād *Plural - Manigfealdlic (mnf.) *Preposition - Foresetednes *Pronoun - Bīnama *Proper Noun - Āgennama *Singular - Ānfealdlic (anf.) *Time - Tīd ** Past - Forþgewiten ** Perfect - Fullfremed ** Present - Andweardnes *Verb - Word ** Strong - Strang ** Weak - Unstrang =Templates= ==Noun Example (use 2 "=")== *(script used is sprǣc|language-code surrounded by brackets ({}). =={{sprǣc|ang}}== ===Āwendednessa (use 3 "=")=== * Here, you put alternate forms of words. Optional. ===Rihtstefn (use 3 "=")=== * Here, you put the pronunciation of the word. * IPA: /whatever-word/ ===Wordstǣr (use 3 "=")=== * Here, you put where the word came from. I'm still working on the script but it will be inh|current-language|language-from|word * For now, use this format below * Of (language, use the dative) ====Gesibbword==== * Same language Cognates ====Sweostorword==== * Non-same language Cognates) ====Cildru==== * Descendants ===(Gender if applicable) Nama (use 3 "=")=== * Still working on the script here, for now use 3 ' around the word! '''example''' * For definitions, use a #, and for examples, use #: # It will look like this #: This is an example! ====Declīnung (use 4 "=")==== * Here, you put the inflection table! The script is depending on the specific noun's conjugation! I'll make a page for that soon! ====Wendunga (use 4 "=")==== * Here, you put translations! Only for Englisc words! * Categories go further down, but it doesn't really matter where, because they don't appear on the actual page anyway. We use Flocc:(whatever category name) inside square brackets "[]" m6oijpg8v9ursslq28j3g1i6gltvsv4 0 8071 54888 2026-09-28T17:30:39Z Deadend0914 7211 Gesceop tramet þe hafaþ '=={{sprǣc|en}}== ===Rihtstefn=== * IPA: /fuːd/ ===Wordstǣr=== * Of Middelenglisce ''[[fode]]'', of Englisce ''[[fōda]]'' ===Nama=== '''food''' # fōda [[Flocc: Nīwenglisc nama]] [[Flocc: Nīwenglisc nama ofgangen of Middelenglisce]]' 54888 wikitext text/x-wiki =={{sprǣc|en}}== ===Rihtstefn=== * IPA: /fuːd/ ===Wordstǣr=== * Of Middelenglisce ''[[fode]]'', of Englisce ''[[fōda]]'' ===Nama=== '''food''' # fōda [[Flocc: Nīwenglisc nama]] [[Flocc: Nīwenglisc nama ofgangen of Middelenglisce]] lyi4ye6jsquvqg6b2o6z0gopu2g9ebg 0 8072 54889 2026-09-28T19:54:20Z Deadend0914 7211 Gesceop tramet þe hafaþ '=={{sprǣc|en}}== ===Rihtstefn=== * IPA: /dɪʃ/ ===Wordstǣr=== Of Middelenglisce ''[[dissh]]'', of Englisce ''[[disc]]'' ===Nama=== '''dish''' (mnf. dishes) # [[disc]] [[Flocc: Nīwenglisc nama]] [[Flocc: Nīwenglisc nama ofgangen of Middelenglisce]]' 54889 wikitext text/x-wiki =={{sprǣc|en}}== ===Rihtstefn=== * IPA: /dɪʃ/ ===Wordstǣr=== Of Middelenglisce ''[[dissh]]'', of Englisce ''[[disc]]'' ===Nama=== '''dish''' (mnf. dishes) # [[disc]] [[Flocc: Nīwenglisc nama]] [[Flocc: Nīwenglisc nama ofgangen of Middelenglisce]] t11zl4u88tk165mk9s3ui31smeagbxv 54890 54889 2026-09-28T19:55:25Z Deadend0914 7211 /* {{sprǣc|en}} */ 54890 wikitext text/x-wiki =={{sprǣc|en}}== ===Rihtstefn=== * IPA: /dɪʃ/ ===Wordstǣr=== Of Middelenglisce ''[[dissh]]'', of Englisce ''[[disc]]'' ===Nama=== {{en-noun|~}} # [[disc]] [[Flocc: Nīwenglisc nama]] [[Flocc: Nīwenglisc nama ofgangen of Middelenglisce]] 0pz0k5ie8xrasfakrw2gf5d3yfmnhhs 828 8073 54898 2026-09-28T22:39:10Z Deadend0914 7211 Gesceop tramet þe hafaþ 'local p = {} local locale = mw.language.new('ang') local currentTitle = mw.title.getCurrentTitle() -- Namespaces p.NS_MEDIA = { id = -2, canonical_name = 'Media', local_name = 'Cræft', } p.NS_SPECIAL = { id = -1, canonical_name = 'Special', local_name = 'Synderlīċ', } p.NS_MAIN = { id = 0, canonical_name = '', local_name = '', } p.NS_TALK = { id = 1, canonical_name = 'Talk', local_name = 'Motung', } p.NS_USER = { id = 2, canonical...' 54898 Scribunto text/plain local p = {} local locale = mw.language.new('ang') local currentTitle = mw.title.getCurrentTitle() -- Namespaces p.NS_MEDIA = { id = -2, canonical_name = 'Media', local_name = 'Cræft', } p.NS_SPECIAL = { id = -1, canonical_name = 'Special', local_name = 'Synderlīċ', } p.NS_MAIN = { id = 0, canonical_name = '', local_name = '', } p.NS_TALK = { id = 1, canonical_name = 'Talk', local_name = 'Motung', } p.NS_USER = { id = 2, canonical_name = 'User', local_name = 'Brūcend', } p.NS_USER_TALK = { id = 3, canonical_name = 'User talk', local_name = 'Brūcend motung', } p.NS_PROJECT = { id = 4, canonical_name = 'Project', local_name = 'Wikiwordbēċ', } p.NS_PROJECT_TALK = { id = 5, canonical_name = 'Project talk', local_name = 'Wikiwordbēċ motung', } p.NS_FILE = { id = 6, canonical_name = 'File', local_name = 'Tabule', } p.NS_FILE_TALK = { id = 7, canonical_name = 'File talk', local_name = 'Tabule motung', } p.NS_MEDIAWIKI = { id = 8, canonical_name = 'MediaWiki', local_name = 'MediaWiki', } p.NS_MEDIAWIKI_TALK = { id = 9, canonical_name = 'MediaWiki talk', local_name = 'MediaWiki motung', } p.NS_TEMPLATE = { id = 10, canonical_name = 'Template', local_name = 'Bysen', } p.NS_TEMPLATE_TALK = { id = 11, canonical_name = 'Template talk', local_name = 'Bysen motung', } p.NS_HELP = { id = 12, canonical_name = 'Help', local_name = 'Help', } p.NS_HELP_TALK = { id = 13, canonical_name = 'Help talk', local_name = 'Help motung', } p.NS_CATEGORY = { id = 14, canonical_name = 'Category', local_name = 'Flocc', } p.NS_CATEGORY_TALK = { id = 15, canonical_name = 'Category talk', local_name = 'Flocc motung', } p.NS_ANNEXE = { id = 100, canonical_name = 'Annexe', local_name = 'Annexe', } p.NS_DISCUSSION_ANNEXE = { id = 101, canonical_name = 'Discussion Annexe', local_name = 'Discussion Annexe', } p.NS_TRANSWIKI = { id = 102, canonical_name = 'Transwiki', local_name = 'Transwiki', } p.NS_DISCUSSION_TRANSWIKI = { id = 103, canonical_name = 'Discussion Transwiki', local_name = 'Discussion Transwiki', } p.NS_PORTAIL = { id = 104, canonical_name = 'Portail', local_name = 'Portail', } p.NS_DISCUSSION_PORTAIL = { id = 105, canonical_name = 'Discussion Portail', local_name = 'Discussion Portail', } p.NS_THESAURUS = { id = 106, canonical_name = 'Thésaurus', local_name = 'Thésaurus', } p.NS_DISCUSSION_THESAURUS = { id = 107, canonical_name = 'Discussion Thésaurus', local_name = 'Discussion Thésaurus', } p.NS_PROJET = { id = 108, canonical_name = 'Projet', local_name = 'Projet', } p.NS_DISCUSSION_PROJET = { id = 109, canonical_name = 'Discussion Projet', local_name = 'Discussion Projet', } p.NS_RECONSTRUCTION = { id = 110, canonical_name = 'Reconstruction', local_name = 'Reconstruction', } p.NS_DISCUSSION_RECONSTRUCTION = { id = 111, canonical_name = 'Discussion Reconstruction', local_name = 'Discussion Reconstruction', } p.NS_TUTORIEL = { id = 112, canonical_name = 'Tutoriel', local_name = 'Tutoriel', } p.NS_DISCUSSION_TUTORIEL = { id = 113, canonical_name = 'Discussion Tutoriel', local_name = 'Discussion Tutoriel', } p.NS_RIME = { id = 114, canonical_name = 'Rime', local_name = 'Rime', } p.NS_DISCUSSION_RIME = { id = 115, canonical_name = 'Discussion Rime', local_name = 'Discussion Rime', } p.NS_CONJUGAISON = { id = 116, canonical_name = 'Conjugaison', local_name = 'Conjugaison', } p.NS_DISCUSSION_CONJUGAISON = { id = 117, canonical_name = 'Discussion Conjugaison', local_name = 'Discussion Conjugaison', } p.NS_RACINE = { id = 118, canonical_name = 'Racine', local_name = 'Racine', } p.NS_DISCUSSION_RACINE = { id = 119, canonical_name = 'Discussion Racine', local_name = 'Discussion Racine', } p.NS_MODULE = { id = 828, canonical_name = 'Module', local_name = 'Module', } p.NS_MODULE_TALK = { id = 829, canonical_name = 'Module talk', local_name = 'Discussion module', } p.NS_TRANSLATIONS = { id = 1198, canonical_name = 'Translations', local_name = 'Translations', } p.NS_TRANSLATIONS_TALK = { id = 1199, canonical_name = 'Translations talk', local_name = 'Translations talk', } p.NS_GADGET = { id = 2300, canonical_name = 'Gadget', local_name = 'Gadget', } p.NS_GADGET_TALK = { id = 2301, canonical_name = 'Gadget talk', local_name = 'Discussion gadget', } p.NS_GADGET_DEFINITION = { id = 2302, canonical_name = 'Gadget definition', local_name = 'Définition de gadget', } p.NS_GADGET_DEFINITION_TALK = { id = 2303, canonical_name = 'Gadget definition talk', local_name = 'Discussion définition de gadget', } p.NS_TOPIC = { id = 2600, canonical_name = 'Topic', local_name = 'Sujet', } -- Fonctions --- Indique si le mot donné déclenche une élision. --- NB: cas particuliers non pris en charge (p. ex. haricot) --- @param word string Le mot à tester. --- @return boolean Vrai si le mot déclenche l’élision, faux sinon. function p.is_elidable(word) return mw.ustring.match(p.lcfirst(word), "^h?[aáàâäeéèêëiíìîïoóòôöuúùûüǘǜ]") ~= nil end --- Indique si la page donnée existe. --- @param title string Le titre de la page. --- @return boolean Vrai si la page correspondante existe, faux sinon. function p.page_existe(title) return title ~= nil and mw.title.new(title).exists end --- Renvoie le texte avec la première lettre en majuscule (si le texte est en français). --- @param text string Le texte. --- @return string Le texte avec la première lettre en majuscule. function p.ucfirst(text) if text == nil then return nil end -- parenthèses nécessaires return (mw.ustring.gsub(text, "^([’ǂǃǀǁ]*.)", p.uc)) end --- Renvoie le texte avec la première lettre en minuscule (si le texte est en français). --- @param text string Le texte. --- @return string Le texte avec la première lettre en minuscule. function p.lcfirst(text) if text == nil then return nil end return locale:lcfirst(text) end --- Renvoie le texte avec en majuscule (si le texte est en français). --- @param text string Le texte. --- @return string Le texte en majuscule. function p.uc(text) if text == nil then return nil end return locale:uc(text) end --- Renvoie le texte avec en minuscule (si le texte est en français). --- @param text string Le texte. --- @return string Le texte en minuscule. function p.lc(text) if text == nil then return nil end return locale:lc(text) end --- Renvoie vrai si le contexte est une page de contenu (principal, annexe, thésaurus ou reconstruction). --- @return boolean function p.page_de_contenu() local ns = currentTitle.namespace return ns == p.NS_MAIN.id or ns == p.NS_ANNEXE.id or ns == p.NS_THESAURUS.id or ns == p.NS_RECONSTRUCTION.id or ns == p.NS_RIME.id or ns == p.NS_CONJUGAISON.id or ns == p.NS_RACINE.id end --- Renvoie vrai si on est dans une page de l’espace principal. --- @return boolean function p.page_principale() return currentTitle:inNamespace(p.NS_MAIN.id) end --- Génère une catégorie. --- @param name string Le nom de la catégorie. --- @param sortingKey string La clé de tri. --- @param asLink boolean Indique si la fonction doit retourner un lien (:Catégorie:…) ou non. --- @return string La catégorie ou une chaîne vide si le nom est nil. function p.fait_categorie(name, sortingKey, asLink) local cat = asLink and ':Catégorie:' or 'Catégorie:' if name ~= nil then if sortingKey ~= nil and sortingKey ~= '' then return '[[' .. cat .. name .. '|' .. sortingKey .. ']]' else return '[[' .. cat .. name .. ']]' end else return '' end end --- Génère une catégorie uniquement si le contexte est dans l’espace principal, --- annexe, thésaurus ou reconstruction. --- @param name string Le nom de la catégorie. --- @param sortingKey string La clé de tri. --- @param asLink boolean Indique si la fonction doit retourner un lien (:Catégorie:…) ou non. --- @return string La catégorie ou une chaîne vide si le nom est nil. function p.fait_categorie_contenu(name, sortingKey, asLink) if p.page_de_contenu() then return p.fait_categorie(name, sortingKey, asLink) or '' else return '' end end --- Génère une catégorie uniquement si le contexte est dans l’espace principal. --- @param name string Le nom de la catégorie. --- @param sortingKey string La clé de tri. --- @param asLink boolean Indique si la fonction doit retourner un lien (:Catégorie:…) ou non. --- @return string La catégorie ou une chaîne vide si le nom est nil. function p.fait_categorie_principale(name, sortingKey, asLink) if p.page_principale() then return p.fait_categorie(name, sortingKey, asLink) or '' else return '' end end --- Crée l’entête d’un tableau wiki triable. --- @param columnTitles table Les titres des colonnes. --- @return string L’entête du tableau. function p.tableau_entete(columnTitles) return '{| class="wikitable sortable"\n|-\n!' .. table.concat(columnTitles, ' !! ') end --- Crée une ligne de tableau wiki. --- @param elements table La liste des éléments de la ligne. --- @return string La ligne du tableau. function p.tableau_ligne(elements) return '|-\n|' .. table.concat(elements, ' || ') end --- Crée la fin d’un tableau wiki. --- @return string La fin du tableau. function p.tableau_fin() return '|}\n' end --- Met un texte en exposant. --- @param text string Le texte. --- @return string Le texte dans une balise <sup>. function p.exposant(text) return mw.ustring.format('<sup style="font-size:83%%;line-height:1">%s</sup>', text) end --- Balise un texte écrit en langue étrangère. --- @param text string Le texte. --- @param code string Le code de la langue ([[Module:langues/data]]). --- @return string Le texte balisé. function p.balise_langue(text, code) local escapedCode = mw.ustring.gsub(code, " ", "_") return mw.ustring.format('<bdi lang="%s" xml:lang="%s" class="lang-%s">%s</bdi>', code, code, escapedCode, text) end --- Enlève les espaces de part et d’autre de tous les paramètres fournis. --- @param args table La table des paramètres. --- @return table Une nouvelle table contenant les paramètres sans les espaces. --- @deprecated Utiliser le [[Module:paramètre]] à la place. function p.trim_parametres(args) if args == nil then return nil end local trim_args = {} for k, v in pairs(args) do trim_args[k] = mw.text.trim(v) end return trim_args end --- Crée un lien. --- @param word string Le mot vers lequel créer le lien. --- @param langCode string Le code langue. --- @param anchor string L’ancre, typiquement l’ID de la section dans la page. --- @param text string Le texte à afficher (optionnel). --- @param keepLangAnchor boolean Si vrai, le code langue est ajouté au lien --- même s’il pointe vers la page courante. --- @return string Le lien. function p.lien_modele(word, langCode, anchor, text, keepLangAnchor) if langCode and langCode == "" then langCode = nil end if text and text == "" then text = nil end if anchor and anchor == "" then anchor = nil end local m_unicode = require("Module:données Unicode") local m_langs = require("Module:langues") text = m_unicode.setWritingDirection(text or word) local langCodeForlink = m_langs.specialCodes[langCode] or langCode local link if word == currentTitle.prefixedText and not anchor then if keepLangAnchor and langCodeForlink then link = mw.ustring.format("[[%s#%s|%s]]", word, langCodeForlink, text) else link = mw.ustring.format("[[%s|%s]]", word, text) end else if langCodeForlink then if anchor and anchor ~= "" then anchor = langCodeForlink .. "-" .. anchor else anchor = langCodeForlink end end if anchor then link = mw.ustring.format("[[%s#%s|%s]]", word, anchor, text) else link = mw.ustring.format("[[%s|%s]]", word, text) end end if langCode then return p.balise_langue(link, langCode) end return link end --- Cherche la position de la dernière occurence de la seconde chaîne dans la première. --- @param subject string La chaîne dans laquelle chercher. --- @param s string La chaîne à rechercher. --- @return number La position de la dernière occurence de “s” dans “subject” ou 0 si aucune n’a été trouvée. function p.derniereOccurrence(subject, s) local dernier = 0 while subject:sub(dernier + 1, subject:len()):find(s) ~= nil do dernier = dernier + subject:sub(dernier + 1, subject:len()):find(s) end return dernier end return p 9r8s9c2fh4l5fihdopqset96ai43g7r 828 8074 54901 2026-09-28T23:17:51Z Deadend0914 7211 Gesceop tramet þe hafaþ '--[=[ Rēgister of sprǣcnaman (language names) for the Old English Wiktionary. This is the single place where the Old English name of a language is entered. Everything that displays a language name on this wiki reads it from here: * [[Bysen:sprǣc]] (the ==L2== heading template) is a thin wrapper around sprǣc() below. * [[Module:etymology]] and [[Module:etymology/templates]] use get_name() for headings and category names, and get_of() for the "of"-for...' 54901 Scribunto text/plain --[=[ Rēgister of sprǣcnaman (language names) for the Old English Wiktionary. This is the single place where the Old English name of a language is entered. Everything that displays a language name on this wiki reads it from here: * [[Bysen:sprǣc]] (the ==L2== heading template) is a thin wrapper around sprǣc() below. * [[Module:etymology]] and [[Module:etymology/templates]] use get_name() for headings and category names, and get_of() for the "of"-form, because Old English uses "of" + genitive when an ancestor or source language is mentioned, e.g. "Of Englisce and". Names are entered without leading or trailing spaces. get_of() applies the following rules in order: 1. an explicit entry in `of_names` (for names that follow no rule); 2. `-isc` + "e" (Englisc -> Englisce, Nīwenglisc -> Nīwenglisce, Þēodisc -> Þēodisce); 3. otherwise the nominative name is returned unchanged and the miss is tracked in [[Wiktionary:Tracking/sprǣcnaman/no of-form]] so that an entry can be supplied. Codes with no name at all display "?" (as [[Bysen:sprǣc]] always has) and are tracked in [[Wiktionary:Tracking/sprǣc/unknown code]], see [[Special:WhatLinksHere/Wiktionary:Tracking/sprǣc/unknown code]]. ]=] local export = {} local names = { af = "Affricanisc", ang = "Englisc", bn = "Bengalisc", ca = "Catalānisc", cs = "Bæmisc", da = "Denisc", de = "Þēodisc", el = "Crēacisc", en = "Nīwenglisc", eo = "Esperantisc", es = "Spēonisc", et = "Eotolisc", eu = "Wascisc", fa = "Persisc", fi = "Finnisc", fo = "Faerisc", fr = "Frencisc", frp = "Profencalisc", ga = "Īrisc", gl = "Galizisc", gn = "Awaisc", goh = "Ealdhēahþēodisc", got = "Gotisc", gv = "Manisc", haw = "Hawaiisc", hi = "Hindisc", hu = "Hungarisc", id = "Indonesisc", io = "Idoisc", is = "Īslendisc", it = "Italisc", iu = "Inuctitutisc", la = "Lǣden", li = "Limburgisc", lt = "Litwisc", lv = "Lettisc", mul = "Þēodeorþe", nap = "Neapolitisc", nl = "Niðerlendisc", no = "Norþwegisc", non = "Eald Noren", ovd = "Ælfdælisc", pl = "Polisc", pt = "Portugisc", qu = "Kescwisc", ro = "Rumǣnisc", sa = "Sanscritisc", sco = "Niderscyttisc", sq = "Albānisc", sv = "Swēonisc", tpi = "Tok Pisin", vo = "Volapük", } --[=[ Codes that are needed in etymology lines (ancestors and source languages) but that have no name yet. They currently display their '''English''' name (via [[Module:languages]]) and should be given an Old English name here. The forms below are suggestions only and are deliberately commented out until they have been checked against a source. -- gem-pro = "?", -- Proto-Germanic -- gmw-pro = "?", -- Proto-West Germanic -- ine-pro = "?", -- Proto-Indo-European -- enm = "Middelenglisc", -- Middle English -- gmh = "Middelhēahþēodisc", -- Middle High German -- odt = "Ealdniðerlendisc", -- Old Dutch -- dum = "Middelniðerlendisc", -- Middle Dutch -- ofs = "?", -- Old Frisian -- osx = "Ealdseaxisc", -- Old Saxon -- gml = "Middelniðersaxisc", -- Middle Low German -- cel-pro = "?", -- Proto-Celtic -- gmq-pro = "?", -- Proto-North Germanic ]=] --[=[ Explicit "of"-forms, for names that the `-isc` rule cannot handle. Add an entry whenever [[Wiktionary:Tracking/sprǣcnaman/no of-form]] lists a code that needs one. Suggestions (commented out until checked against a source): -- la = "Lǣdenes", -- Latin -- non = "Eald Norðrena", -- Old Norse -- mul = "Þēodeorðan", -- Translingual -- vo = "Volapük", -- Volapük (no ending to inflect) -- tpi = "Tok Pisin", -- Tok Pisin (no ending to inflect) ]=] local of_names = {} -- Spellings that may be passed to {{sprǣc}} or found in a ==L2== heading, mapped to their code. local aliases = { ["Ænglisc"] = "ang", } -- Codes with no name display "?" and are tracked, so that the gaps are visible. local function track(key) local ok, track_module = pcall(require, "Module:debug/track") if ok then track_module(key) end end function export.track_missing_name(code) code = tostring(code) if code == "" then code = "(empty)" end track("sprǣc/unknown code/" .. code) end local function track_no_of_form(code) track("sprǣcnaman/no of-form/" .. tostring(code)) end -- Accept either a language code or a language object (from [[Module:languages]]). local function code_candidates(x) if type(x) ~= "table" then return { x } end local codes = {} local code = x.getCode and x:getCode() if code then codes[#codes + 1] = code end local full_code = x.getFullCode and x:getFullCode() if full_code and full_code ~= code then codes[#codes + 1] = full_code end return codes end --[==[ Return the Old English name of the given language (code or language object), or nil if the language has no name yet. Used for ==L2== headings and for category names. ]==] function export.get_name(x) for _, code in ipairs(code_candidates(x)) do if names[code] then return names[code] end end return nil end --[==[ Return the "of"-form of the given language (code or language object), or nil if the language has no name yet. Used wherever Old English needs "of" + genitive, e.g. "Of Englisce and". Names that follow no rule fall back to the nominative and are tracked. ]==] function export.get_of(x) for _, code in ipairs(code_candidates(x)) do if names[code] then return export.get_of_for_code(code) end end return nil end function export.get_of_for_code(code) local name = names[code] if not name then return nil end if of_names[code] then return of_names[code] end if name:sub(-3) == "isc" then return name .. "e" end track_no_of_form(code) return name end local code_of_name, lower_code_of_name local function make_reverse_maps() if code_of_name then return end code_of_name, lower_code_of_name = {}, {} for alias, code in pairs(aliases) do code_of_name[alias] = code lower_code_of_name[mw.ustring.lower(alias)] = code end for code, name in pairs(names) do code_of_name[name] = code_of_name[name] or code local lower = mw.ustring.lower(name) lower_code_of_name[lower] = lower_code_of_name[lower] or code end end --[==[ Return the code of the language with the given Old English name, or nil. Used by [[Module:etymology/templates]] to match an ==L2== heading back to its language. ]==] function export.get_code(name) if type(name) ~= "string" then return nil end name = mw.text.trim(name) if name == "" then return nil end make_reverse_maps() return code_of_name[name] or lower_code_of_name[mw.ustring.lower(name)] end --[==[ Entry point for [[Bysen:sprǣc]]: {{sprǣc|CODE}} gives the name, {{sprǣc|CODE|of}} the "of"-form. A code with no name gives "?" and is tracked, exactly as the template always has. ]==] export["sprǣc"] = function(frame) local args = frame and frame.args or {} local code = mw.text.trim(args[1] or "") local mode = mw.text.trim(args[2] or "") if code == "" then export.track_missing_name("") return "?" end local name if mode == "of" or mode == "gen" or mode == "genitive" then name = export.get_of(code) else name = export.get_name(code) if not name then -- The argument may be a name rather than a code (e.g. "Englisc"). local matched_code = export.get_code(code) name = matched_code and names[matched_code] or nil end end if not name then export.track_missing_name(code) return "?" end return name end --[==[ Entry point for templates that need the "of"-form only: {{#invoke:sprǣcnaman|of|CODE}}. ]==] function export.of(frame) local args = frame and frame.args or {} local code = mw.text.trim(args[1] or "") if code == "" then export.track_missing_name("") return "?" end local name = export.get_of(code) if not name then export.track_missing_name(code) return "?" end return name end -- The tables are exposed for tests and maintenance scripts; use the getters elsewhere. export.names = names export.of_names = of_names return export 2myyfj8ae4x1vyyh89ecub3sr3d829r 828 8075 54902 2026-09-28T23:18:38Z Deadend0914 7211 Gesceop tramet þe hafaþ '--[=[ Wordstǣr (etymology) template handlers for the Old English Wiktionary. This module holds the Old English wording used by the wordstǣr templates. It deliberately does not re-implement argument handling, the ancestor check or the categories: the handlers here call the corresponding function in [[Module:etymology/templates]] (which in turn calls [[Module:etymology]]) and only add or replace the wording. * [[Bysen:inh]]: "Englisce and" -- source langu...' 54902 Scribunto text/plain --[=[ Wordstǣr (etymology) template handlers for the Old English Wiktionary. This module holds the Old English wording used by the wordstǣr templates. It deliberately does not re-implement argument handling, the ancestor check or the categories: the handlers here call the corresponding function in [[Module:etymology/templates]] (which in turn calls [[Module:etymology]]) and only add or replace the wording. * [[Bysen:inh]]: "Englisce and" -- source language in its "of"-form, then the term. * [[Bysen:inh+]]: "Of Englisce and" -- the same, plus the preposition that Old English needs. The "of"-form comes from [[Module:sprǣcnaman]] (see get_of() there); the same module names the ==L2== headings and the categories, so headings, wordstǣr lines and categories can never disagree with each other. Add the Old English wording for the other wordstǣr templates ({{bor}}, {{der}}, {{cog}}, ...) here in the same way: call the handler in [[Module:etymology/templates]] and replace or add only the wording. ]=] local export = {} --[==[ Entry point for [[Bysen:inh+]], i.e. [[Bysen:inh]] with "Of " in front. The arguments of {{inh+}} are exactly the arguments of {{inh}} and are passed through unchanged, so qualifiers, references, alternative forms, gender, transliteration, sort keys, the ancestor check and the categories of {{inh}} all keep working. The preposition can be set when invoking the module, e.g. {{#invoke:wordstǣr|inh_plus|of=of}} for a lower-case "of", or {{#invoke:wordstǣr|inh_plus|of=}} for no preposition at all. ]==] function export.inh_plus(frame) local preposition = frame.args.of if preposition == nil then preposition = "Of" end local text = require("Module:etymology/templates").inherited(frame) if preposition == "" then return text end return preposition .. " " .. text end return export ipd2claluv1q2mp23l3htfia5ruy6ri 10 8076 54904 2026-09-28T23:19:40Z Deadend0914 7211 Gesceop tramet þe hafaþ '<includeonly>{{#invoke:wordstǣr|inh_plus|of=Of}}</includeonly><noinclude>{{Documentation}}</noinclude>' 54904 wikitext text/x-wiki <includeonly>{{#invoke:wordstǣr|inh_plus|of=Of}}</includeonly><noinclude>{{Documentation}}</noinclude> gtczggwsqii2jkhhh2kb3rurvfjdxlo 828 8077 54907 2026-09-28T23:21:55Z Deadend0914 7211 Gesceop tramet þe hafaþ 'local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "a...' 54907 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawan", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-war"] = { "Old Warekena", 105320180, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-nic"] = { "Nicoleño", 50241488, "azc", "Latn", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-cpr"] = { "Chinese Pidgin Russian", nil, "crp", "Hani, Cyrl, Latn", ancestors = "ru, zh", translit = {Cyrl = "ru-translit"}, strip_diacritics = { Cyrl = {remove_diacritics = c.acute .. c.grave .. c.macron}, }, } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", display_text = s["esx-displaytext"], strip_diacritics = s["esx-stripdiacritics"], } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", display_text = s["esx-displaytext"], strip_diacritics = s["esx-stripdiacritics"], } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", display_text = s["esx-displaytext"], strip_diacritics = s["esx-stripdiacritics"], } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "Proto-Basque", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "Proto-Germanic", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "Proto-West Germanic", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-car"] = { "Cargesian Greek", 16549443, "grk", "Latn, Grek", ancestors = "gkm", } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron .. c.CGJ }}, display_text = {Latn = { from = {"([dlLt])" .. c.caron}, to = {"%1" .. c.CGJ .. c.caron}, }}, strip_diacritics = {Latn = { from = {"([dlLt])" .. c.caron}, to = {"%1" .. c.CGJ .. c.caron}, }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "Proto-Indo-Iranian", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "Ashokan Prakrit", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-khr"] = { "Khortha", 13406670, "inc-sad", "Deva, Kthi", translit = { Deva = "bho-translit", Kthi = "bho-Kthi-translit", }, } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, Aran", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", Aran = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, Aran", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Aran = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, Aran", translit = { Guru = "inc-opa-Guru-translit", Aran = "pa-Aran-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["inc-sar"] = { "Sarazi", 85799728, "him", "Aran, Deva, Takr", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Aran = "ur-translit", Deva = "hi-translit", -- Takr = "Takr-translit", }, } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "Proto-Indo-European", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoquean", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_alternants = "zh-generatealternants", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_alternants = "zh-generatealternants", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "njo", "Latn", } m["njo-mng"] = { "Mongsen Ao", 85383221, "njo", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-nes"] = { "Nese", 2157412, "poz-vnc", "Latn", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pcc-pro"] = { "Proto-Central Pacific", 111962726, "poz-pcc", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-krp"] = { "Karipuna (Panoan)", 136296616, "sai-pan", "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 134374036, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-tin", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-ptx"] = { "Pataxó", 7144304, "sai-mje", "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Sami", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "Arab", strip_diacritics = {Arab = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "Arab", strip_diacritics = {Arab = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-kaw"] = { "Kawahiva", 6346712, "tup-gua", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", display_text = s["esx-displaytext"], strip_diacritics = s["esx-stripdiacritics"], } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_alternants = "zh-generatealternants", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_alternants = "zh-generatealternants", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_alternants = "zh-generatealternants", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") dw5rxrt2l3v52omvn971c4y3m78x6ee 828 8078 54908 2026-09-28T23:23:01Z Deadend0914 7211 Gesceop tramet þe hafaþ 'local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["ebg"] = { "Ebughu", 35294, "nic-lcr", "Latn", } m["ebk"] = { "Eastern Bontoc", 62664215, "phi", "Latn", } m["ebr"] = { "Ebrié", 36644, "alv-...' 54908 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["ebg"] = { "Ebughu", 35294, "nic-lcr", "Latn", } m["ebk"] = { "Eastern Bontoc", 62664215, "phi", "Latn", } m["ebr"] = { "Ebrié", 36644, "alv-ptn", "Latn", } m["ebu"] = { "Embu", 35318, "bnt-kka", "Latn", } m["ecr"] = { "Eteocretan", 35461, "qfa-unc", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ecs"] = { "Ecuadorian Sign Language", 3436769, "sgn", "Latn", -- when documented } m["ecy"] = { "Eteocypriot", 35309, "qfa-unc", "Cprt", } m["eee"] = { "E", 35386, "qfa-mix", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["efa"] = { "Efai", 3813297, "nic-ief", "Latn", } m["efe"] = { "Efe", 56354, "csu-mle", "Latn", } m["efi"] = { "Efik", 35377, "nic-ief", "Latn", } m["ega"] = { "Ega", 3914927, "alv", "Latn", } m["egl"] = { "Emilian", 1057898, "roa-emr", ancestors = "egl-old", "Latn", wikimedia_codes = "eml", } m["ego"] = { "Eggon", 35300, "nic-pls", "Latn", } m["egy"] = { "Egyptian", 50868, "egx", "Latn, Egyp, Egyh", sort_key = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "y", "ꜥ", "w", "b", "p", "f", "m", "n", "r", "ḥ", "ḫ", "ẖ", "h", "z", "š", "s", "q", "k", "g", "ṯ", "t", "ḏ", "d", "%."}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[13], p[14], p[15], p[12], p[16], p[18], p[17], p[19], p[20], p[21], p[23], p[22], p[25], p[24], p[26]} }, } m["ehu"] = { "Ehueun", 3441392, "alv-nwd", "Latn", } m["eip"] = { "Eipomek", 5349839, "ngf-mek", "Latn", } m["eit"] = { "Eitiep", 5350030, "paa-kom", "Latn", } m["eiv"] = { "Askopan", 56324, "paa-nbo", "Latn", } m["eja"] = { "Ejamat", 6269820, "alv-jfe", "Latn", } m["eka"] = { "Ekajuk", 35250, "nic-eko", "Latn", } m["eke"] = { "Ekit", 3509628, "nic-ief", "Latn", } m["ekg"] = { "Ekari", 5350305, "ngf-pan", "Latn", } m["eki"] = { "Eki", 5350418, "nic-ief", "Latn", } m["ekl"] = { "Kolhe", 6426945, "mun", "Latn", } m["ekm"] = { "Elip", 12952414, "nic-ymb", "Latn", } m["eko"] = { "Koti", 29930, "bnt-mak", "Latn", } m["ekp"] = { "Ekpeye", 35254, "alv-igb", "Latn", } m["ekr"] = { "Yace", 36901, "alv-ido", "Latn", } m["eky"] = { "Eastern Kayah", 25559417, "kar", "Kali", } m["ele"] = { "Elepi", 5359444, "paa-mar", "Latn", } m["elh"] = { "El Hugeirat", 5351410, "nub-hil", "Latn", } m["eli"] = { "Nding", 36176, "alv-tal", "Latn", } m["elk"] = { "Elkei", 5364210, "paa-wap", "Latn", } m["elm"] = { "Eleme", 3914427, "nic-ogo", "Latn", } m["elo"] = { "El Molo", 56719, "cus-eas", "Latn", } m["elu"] = { "Elu", 3364594, "poz-aay", "Latn", } m["elx"] = { "Elamite", 35470, "qfa-iso", --ancient language of Iran "Xsux", } m["ema"] = { "Emai", 35428, "alv-eeo", "Latn", } m["emb"] = { "Embaloh", 5369424, "poz", "Latn", } m["eme"] = { "Emerillon", 3588942, "tup-gua", "Latn", } m["emg"] = { "Eastern Meohang", 12952840, "sit-kie", "Deva", } m["emi"] = { "Mussau-Emira", 6943093, "poz-stm", "Latn", } m["emk"] = { "Eastern Maninkakan", 11002130, "dmn-mnk", "Latn, Arab, Nkoo", } m["emm"] = { "Mamulique", 3285082, "nai-pak", "Latn", } m["emn"] = { "Eman", 5368975, "nic-tvc", "Latn", } m["emp"] = { "Northern Emberá", 2391297, "sai-chc", "Latn", } m["ems"] = { "Alutiiq", 27992, "ypk", "Latn", } m["emu"] = { "Eastern Muria", 12952883, "dra-mur", "Deva", } m["emw"] = { "Emplawas", 5374265, "poz-tim", "Latn", } m["emx"] = { "Erromintxela", 1122188, "qfa-mix", "Latn", ancestors = "rom, eu", } m["emy"] = { "Epigraphic Mayan", 301355, "myn", "Latn, Maya", } m["ena"] = { "Apali", 3504201, "ngf-sog", "Latn", } m["enb"] = { "Markweeta", 56874, "sdv-nma", "Latn", } m["enc"] = { "En", 3504110, "qfa-buy", "Latn", } m["end"] = { "Ende", 2067656, "poz-cet", "Latn", } m["enf"] = { "Forest Enets", 30249597, "syd-ene", "Cyrl", } m["enh"] = { "Tundra Enets", 25559411, "syd-ene", "Cyrl", } m["enl"] = { "Enlhet", 15462671, "sai-mas", "Latn", } m["enm"] = { "Middle English", 36395, "gmw-ang", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dacute .. c.dotbelow .. c.tacute}, sort_key = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dacute .. c.dotbelow .. c.tacute, from = {"[ꟓꟕ]", "[æðᵹꟑȝœẜþꟃƿ]"}, to = { { ["ꟓ"] = "þþ", ["ꟕ"] = "ƿƿ", -- finalized by the next substitution }, { ["æ"] = "ae", ["ð"] = "d" .. p[1], ["ᵹ"] = "g", ["ꟑ"] = "g", ["ȝ"] = "g" .. p[1], ["œ"] = "oe", ["ẜ"] = "s", ["þ"] = "t" .. p[1], ["ꟃ"] = "w", ["ƿ"] = "w", }, }, }, standard_chars = { Latn = "AaÆæBbCcDdÐðEeFfGgȜȝHhIiJjKkLlMmNnOoPpQqRrSsTtÞþUuVvWwXxYyZz", c.punc, }, } m["enn"] = { "Engenni", 3915365, "alv-dlt", "Latn", } m["eno"] = { "Enggano", 2669164, "poz", "Latn", } m["enq"] = { "Enga", 1143040, "ngf-enc", "Latn", } m["enr"] = { "Emem", 5370369, "paa-epw", "Latn", } m["enu"] = { "Enu", 5380858, "tbq-bka", } m["env"] = { "Enwan", 3438334, "alv-yek", "Latn", } m["enw"] = { "Enwang", 11134434, "nic-lcr", "Latn", } m["enx"] = { "Enxet", 15462609, "sai-mas", "Latn", } m["eot"] = { "Eotile", 3915347, "alv-ptn", "Latn", } m["epi"] = { "Epie", 35291, "alv-dlt", "Latn", } m["era"] = { "Eravallan", 5385061, "dra-tam", "Taml", } m["erg"] = { "Sie", 426254, "poz-vns", "Latn", } m["erh"] = { "Eruwa", 3441244, "alv-swd", "Latn", } m["eri"] = { "Ogea", 7079984, "ngf-nur", "Latn", } m["erk"] = { "South Efate", 3449070, "poz-vnc", "Latn", } m["err"] = { "Erre", 10488401, "qfa-iso", -- Evans (1997) put it in an Arnhem Land family "Latn", } m["ers"] = { "Ersu", 12952417, "sit-ers", "Latn", -- also Ersu Shaba } m["ert"] = { "Eritai", 56376, "paa-clp", "Latn", } m["erw"] = { "Erokwanas", 5395296, "poz-hce", "Latn", } m["ese"] = { "Ese Ejja", 2980381, "sai-tac", "Latn", } m["esh"] = { "Eshtehardi", 12952418, "xme-ttc", "Arab, Latn", ancestors = "xme-ttc-sou", } -- "esi" and "esk" moved to etymology-only per [[WT:LT]] and [[Wiktionary:Beer_parlour/2023/August#Issues_regarding_the_Inuit_languages]] m["esl"] = { "Egyptian Sign Language", 5348443, "sgn", } m["esm"] = { "Esuma", 16927555, "alv-kwa", "Latn", } m["esn"] = { "Salvadoran Sign Language", 7406492, "sgn", "Latn", -- when documented } m["eso"] = { "Estonian Sign Language", 3196221, "sgn", "Latn", -- when documented } m["esq"] = { "Esselen", 1294243, "qfa-dis", -- isolate or Hokan "Latn", } m["ess"] = { "Central Siberian Yupik", 27993, "ypk", "Cyrl, Latn", } m["esu"] = { "Yup'ik", 21117, "ypk", "Latn", } m["esy"] = { "Eskayan", 867086, "art", "Latn", -- also its own native script } m["etb"] = { "Etebi", 11002851, "nic-ief", "Latn", } m["etc"] = { "Etchemin", 5402493, "alg-eas", "Latn", } m["eth"] = { "Ethiopian Sign Language", 3501903, "sgn-asl", } m["etn"] = { "Eton (Vanuatu)", 3059362, "poz-vnc", "Latn", } m["eto"] = { "Eton (Cameroon)", 35317, "bnt-btb", "Latn", } m["etr"] = { "Edolo", 5340184, "ngf-bos", "Latn", } m["ets"] = { "Yekhee", 3915848, "alv-yek", "Latn", } m["ett"] = { "Etruscan", 35726, "qfa-tyn", "Ital", -- Ital translit in [[Module:scripts/data]] } m["etu"] = { "Ejagham", 35296, "nic-eko", "Latn", } m["etx"] = { "Eten", 3915392, "nic-beo", "Latn", } m["etz"] = { "Semimi", 10950308, "paa-mai", "Latn", } m["eve"] = { "Even", 29960, "tuw-ewe", "Cyrl, Latn", translit = {Cyrl = "eve-translit"}, strip_diacritics = {remove_diacritics = c.macron .. c.dotabove .. c.dotbelow}, sort_key = { Cyrl = { from = { "ӫ", -- 2 chars "ё", "ӈ", "ө" -- 1 char }, to = { "о" .. p[2], "е" .. p[1], "н" .. p[1], "о" .. p[1] }, }, }, } m["evh"] = { "Uvbie", 3441344, "alv-swd", "Latn", } m["evn"] = { "Evenki", 30004, "tuw-ewe", "Cyrl, Latn", translit = "evn-translit", strip_diacritics = {remove_diacritics = c.macron .. c.dotabove .. c.dotbelow}, sort_key = { from = {"ё", "ӈ"}, to = {"е" .. p[1], "н" .. p[1]} }, } m["ewo"] = { "Ewondo", 35459, "bnt-btb", "Latn", } m["ext"] = { "Extremaduran", 30007, "roa-asl", "Latn", } m["eya"] = { "Eyak", 27480, "xnd", "Latn", } m["eyo"] = { "Keiyo", 56856, "sdv-nma", "Latn", } m["eza"] = { "Ezaa", 11921436, "alv-igb", "Latn", ancestors = "izi", } m["eze"] = { "Uzekwe", 3502244, "nic-ucn", "Latn", } return require("Module:languages").finalizeData(m, "language") gqs0r2b6epvmorkjpe2oprwz8o2498u 828 8079 54909 2026-09-28T23:23:32Z Deadend0914 7211 Gesceop tramet þe hafaþ 'local export = {} local families_by_name_module = "Module:families/canonical names" local families_data_module = "Module:families/data" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_module = "Module:languages" local load_module = "Module:load" local table_module = "Module:table" local get_by_code -- Defined below. local gmatch = string.gmatch local insert = table.insert local ipairs = ipairs local make_obj...' 54909 Scribunto text/plain local export = {} local families_by_name_module = "Module:families/canonical names" local families_data_module = "Module:families/data" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_module = "Module:languages" local load_module = "Module:load" local table_module = "Module:table" local get_by_code -- Defined below. local gmatch = string.gmatch local insert = table.insert local ipairs = ipairs local make_object -- Defined below. local pairs = pairs local require = require local setmetatable = setmetatable local type = type --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function category_name_has_suffix(...) category_name_has_suffix = require(language_like_module).categoryNameHasSuffix return category_name_has_suffix(...) end local function category_name_to_code(...) category_name_to_code = require(language_like_module).categoryNameToCode return category_name_to_code(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_lang_object(...) make_lang_object = require(languages_module).makeObject return make_lang_object(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local families_by_name local function get_families_by_name() families_by_name, get_families_by_name = load_data(families_by_name_module), nil return families_by_name end local families_data local function get_families_data() families_data, get_families_data = load_data(families_data_module), nil return families_data end local families_suffixes local function get_families_suffixes() families_suffixes, get_families_suffixes = { "languages", "lects" }, nil return families_suffixes end local Family = {} Family.__index = Family --[==[ Return the family code of the family, e.g. {"ine"} for the Indo-European languages. ]==] function Family:getCode() return self._code end --[==[ Return the canonical name of the family. This is the name used to represent that language family on Wiktionary, and is guaranteed to be unique to that family alone. Example: {"Indo-European"} for the Indo-European languages. ]==] function Family:getCanonicalName() local name = self._name if name == nil then name = self._data[1] self._name = name end return name end --[==[ Return the display form of the family. For families, this is usually the same as the value returned by {getCategoryName("nocap")}, i.e. it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}). For full and etymology-only languages, this is the same as the canonical name, and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). The displayed text used in {makeCategoryLink()} is always the same as the display form. ]==] function Family:getDisplayForm() local name = self._data[1] if category_name_has_suffix(name, families_suffixes or get_families_suffixes()) then name = name .. " languages" end return name end function Family:getAliases() Family.getAliases = require(language_like_module).getAliases return self:getAliases() end function Family:getVarieties(flatten) Family.getVarieties = require(language_like_module).getVarieties return self:getVarieties(flatten) end function Family:getOtherNames() Family.getOtherNames = require(language_like_module).getOtherNames return self:getOtherNames() end function Family:getAllNames() Family.getAllNames = require(language_like_module).getAllNames return self:getAllNames() end --[==[ Return a list of the pseudo-families (if any) that a family belongs to. The returned value is a list of Family objects. Pseudo-families are groupings of languages that are not clades but share some geographic, ethnic or other characteristic (e.g. [[:Category:Papuan languages]], [[:Category:Jewish languages]]). ]==] function Family:getPseudoFamilies() Family.getPseudoFamilies = require(language_like_module).getPseudoFamilies return self:getPseudoFamilies() end --[==[Returns a table of types as a lookup table (with the types as keys). The possible types are * {family}: This object is a family. * {full}: This object is a "full" family. This includes all families but a couple of etymology-only families for Old and Middle Iranian languages. * {etymology-only}: This object is an etymology-only family, similar to etymology-only languages. There are currently only two such families, for Old Iranian languages and Middle Iranian languages (which do not represent proper clades and have no proto-languages, hence cannot be full families). ]==] function Family:getTypes() local types = self._types if types == nil then types = {family = true} if self:getFullCode() == self:getCode() then types.full = true else types["etymology-only"] = true end local rawtypes = self._data.type if rawtypes then for t in gmatch(rawtypes, "[^,]+") do types[t] = true end end self._types = types end return types end --[==[Given a list of types as strings, returns true if the family has all of them.]==] function Family:hasType(...) Family.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[Returns a {Family} object for the superfamily that the family belongs to.]==] function Family:getFamily() if self._familyObject == nil then local familyCode = self:getFamilyCode() if familyCode then self._familyObject = get_by_code(familyCode) else self._familyObject = false end end return self._familyObject or nil end --[==[Returns the code of the family's superfamily.]==] function Family:getFamilyCode() if not self._familyCode then self._familyCode = self._data[3] end return self._familyCode end --[==[Returns the canonical name of the family's superfamily.]==] function Family:getFamilyName() if self._familyName == nil then local family = self:getFamily() if family then self._familyName = family:getCanonicalName() else self._familyName = false end end return self._familyName or nil end --[==[Check whether the family belongs to {superfamily} (which can be a family code or object), and returns a boolean. If more than one is given, returns {true} if the family belongs to any of them. A family is '''not''' considered to belong to itself.]==] function Family:inFamily(...) for _, superfamily in ipairs{...} do if type(superfamily) == "table" then superfamily = superfamily:getCode() end local family, code = self:getFamily() while family do code = family:getCode() if code == superfamily then return true end family = family:getFamily() -- If family is parent to itself, return false. if family and family:getCode() == code then return false end end return false end end function Family:getParent() if self._parentObject == nil then local parentCode = self:getParentCode() if parentCode then self._parentObject = get_lang(parentCode, nil, true, true) else self._parentObject = false end end return self._parentObject or nil end function Family:getParentCode() if not self._parentCode then self._parentCode = self._data.parent end return self._parentCode end function Family:getParentName() if self._parentName == nil then local parent = self:getParent() if parent then self._parentName = parent:getCanonicalName() else self._parentName = false end end return self._parentName or nil end function Family:getParentChain() if not self._parentChain then self._parentChain = {} local parent = self:getParent() while parent do insert(self._parentChain, parent) parent = parent:getParent() end end return self._parentChain end function Family:hasParent(...) --checkObject("family", nil, ...) for _, other_family in ipairs{...} do for _, parent in ipairs(self:getParentChain()) do if type(other_family) == "string" then if other_family == parent:getCode() then return true end else if other_family:getCode() == parent:getCode() then return true end end end end return false end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding object is returned. If the family is a full family, then it simply returns itself. ]==] function Family:getFull() if not self._fullObject then local fullCode = self:getFullCode() if fullCode ~= self:getCode() then self._fullObject = get_lang(fullCode, nil, nil, true) else self._fullObject = self end end return self._fullObject end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding code is returned. If the family is a full family, then it simply returns the family code. ]==] function Family:getFullCode() return self._fullCode or self:getCode() end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding canonical name is returned. If the family is a full family, then it simply returns the canonical name of the family. ]==] function Family:getFullName() if self._fullName == nil then local full = self:getFull() if full then self._fullName = full:getCanonicalName() else self._fullName = false end end return self._fullName or nil end --[==[ Return a {Language} object (see [[Module:languages]]) for the proto-language of this family, if one exists. Otherwise, return {nil}. ]==] function Family:getProtoLanguage() if self._protoLanguageObject == nil then self._protoLanguageObject = get_lang(self._data.protoLanguage or self:getCode() .. "-pro", nil, true) or false end return self._protoLanguageObject or nil end function Family:getProtoLanguageCode() if self._protoLanguageCode == nil then local protoLanguage = self:getProtoLanguage() self._protoLanguageCode = protoLanguage and protoLanguage:getCode() or false end return self._protoLanguageCode or nil end function Family:getProtoLanguageName() if not self._protoLanguageName then self._protoLanguageName = self:getProtoLanguage():getCanonicalName() end return self._protoLanguageName end function Family:hasAncestor(...) -- Go up the family tree until a protolanguage is found. local family = self local protolang = family:getProtoLanguage() while not protolang do family = family:getFamily() protolang = family:getProtoLanguage() -- Return false if the family is its own family, to avoid an infinite loop. if family:getFamilyCode() == family:getCode() then return false end end -- If the protolanguage is not in the family, it must therefore be ancestral to it. Check if it is a match. for _, otherlang in ipairs{...} do if ( type(otherlang) == "string" and protolang:getCode() == otherlang or type(otherlang) == "table" and protolang:getCode() == otherlang:getCode() ) and not protolang:inFamily(self) then return true end end -- If not, check the protolanguage's ancestry. return protolang:hasAncestor(...) end local function fetch_descendants(self, format) local languages = require("Module:languages/code to canonical name") local etymology_languages = require("Module:etymology languages/code to canonical name") local families = require("Module:families/code to canonical name") local descendants = {} -- Iterate over all three datasets. for _, data in ipairs{languages, etymology_languages, families} do for code in pairs(data) do local lang = get_lang(code, nil, true, true) if lang:inFamily(self) then if format == "object" then insert(descendants, lang) elseif format == "code" then insert(descendants, code) elseif format == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Family:getDescendants() if not self._descendantObjects then self._descendantObjects = fetch_descendants(self, "object") end return self._descendantObjects end function Family:getDescendantCodes() if not self._descendantCodes then self._descendantCodes = fetch_descendants(self, "code") end return self._descendantCodes end function Family:getDescendantNames() if not self._descendantNames then self._descendantNames = fetch_descendants(self, "name") end return self._descendantNames end function Family:hasDescendant(...) for _, lang in ipairs{...} do if type(lang) == "string" then lang = get_lang(lang, nil, true) end if lang:inFamily(self) then return true end end return false end --[==[ Return the name of the main category of that family. Example: {"Germanic languages"} for the Germanic languages, whose category is at [[:Category:Germanic languages]]. Unless optional argument `nocap` is given, the family name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the family name is lowercase and the returned value of this function is used in the middle of a sentence. (For example, the pseudo-family with the code {qfa-mix} has the name {"mixed"}, which should remain lowercase when used as part of the category name [[:Category:Terms derived from mixed languages]] but should be capitalized in [[:Category:Mixed languages]].) If you are considering using {getCategoryName("nocap")}, use {getDisplayForm()} instead. ]==] function Family:getCategoryName(nocap) local name = self._data.categoryName or self:getDisplayForm() if not nocap then name = mw.getContentLanguage():ucfirst(name) end return name end function Family:makeCategoryLink() return "[[:Category:" .. self:getCategoryName() .. "|" .. self:getDisplayForm() .. "]]" end --[==[Returns the Wikidata item id for the family or <code>nil</code>. This corresponds to the the second field in the data modules.]==] function Family:getWikidataItem() Family.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[ Returns the name of the Wikipedia article for the family. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, {:getCategoryName} is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the family's category, but this won't normally happen for any other project. ]==] function Family:getWikipediaArticle(noCategoryFallback, project) Family.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Family:makeWikipediaLink() return "[[w:" .. self:getWikipediaArticle() .. "|" .. self:getCanonicalName() .. "]]" end --[==[Returns the name of the Wikimedia Commons category page for the family.]==] function Family:getCommonsCategory() Family.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end function Family:toJSON(opts) local ret = { canonicalName = self:getCanonicalName(), categoryName = self:getCategoryName("nocap"), code = self:getCode(), parent = self:getParentCode(), full = self:getFullCode(), family = self:getFamilyCode(), protoLanguage = self:getProtoLanguageCode(), aliases = self:getAliases(), varieties = self:getVarieties(), otherNames = self:getOtherNames(), type = keys_to_list(self:getTypes()), wikidataItem = self:getWikidataItem(), wikipediaArticle = self:getWikipediaArticle(true), } -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function Family:getData() return self._data end function export.makeObject(code, data) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end return setmetatable({_data = data, _code = code, _fullCode = code}, Family) end make_object = export.makeObject --[==[ Finds the family whose code matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}.]==] function export.getByCode(code) local data = (families_data or get_families_data())[code] if data == nil then return nil elseif data.parent == nil then return make_object(code, data) end return make_lang_object(code, data) end get_by_code = export.getByCode --[==[ Look for the family whose canonical name (the name used to represent that family on Wiktionary) matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}. The canonical name of families should always be unique (it is an error for two families on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result.]==] function export.getByCanonicalName(name) if name == nil then return nil end local code = (families_by_name or get_families_by_name())[name] if code == nil then return nil end return get_by_code(code) end --[==[ Look for the family whose category name (the name used in categories for that family) matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}. In almost all cases, the category name for a family is its canonical name plus the word "languages", e.g. "Indo-European" has the category name "Indo-European languages". Where a canonical name ends with "languages" or "lects", the category name is identical to the canonical name.]==] function export.getByCategoryName(name) if name == nil then return nil end local code = category_name_to_code( name, " languages", families_by_name or get_families_by_name(), families_suffixes or get_families_suffixes() ) if code == nil then return nil end return get_by_code(code) end return export fhlpo09ymhi7e748v1r3pkilvfhbwm5 828 8080 54910 2026-09-28T23:24:07Z Deadend0914 7211 Gesceop tramet þe hafaþ '--[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 333...' 54910 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 33392, "aql", } m["alg-abp"] = { "Abenaki-Penobscot", 197936, "alg-eas", } m["alg-ara"] = { "Arapahoan", 2153686, "alg", } m["alg-eas"] = { "Eastern Algonquian", 2257525, "alg", } m["alg-sfk"] = { "Sac-Fox-Kickapoo", 1440172, "alg", } m["alv"] = { "Atlantic-Congo", 771124, "nic", } m["alv-aah"] = { "Ayere-Ahan", 750953, "alv-von", } m["alv-ada"] = { "Adamawa", 32906, "alv-sav", } m["alv-bag"] = { "Baga", 2746083, "alv-mel", } m["alv-bak"] = { "Bak", 1708174, "alv-sng", } m["alv-bam"] = { "Bambukic", 4853456, "alv-ada", aliases = {"Yungur-Jen"}, } m["alv-bny"] = { "Banyum", 2892477, "alv-nyn", } m["alv-bua"] = { "Bua", 4982094, "alv-mbd", } m["alv-bwj"] = { "Bikwin-Jen", 84542501, "alv-bam", } m["alv-cng"] = { "Cangin", 1033184, "alv-fwo", } m["alv-ctn"] = { "Central Tano", 1658486, "alv-ptn", aliases = {"Akan"}, } m["alv-dlt"] = { "Delta Edoid", nil, "alv-edo", } m["alv-dur"] = { "Duru", 5316788, "alv-lni", } m["alv-ede"] = { "Ede", 35368, "alv-yor", } m["alv-edk"] = { "Edekiri", 5336735, "alv-yrd", } m["alv-edo"] = { "Edoid", 1287469, "alv-von", } m["alv-eeo"] = { "Edo-Esan-Ora", 12630439, "alv-nce", } m["alv-fli"] = { "Fali", 3450166, "alv", } m["alv-fwo"] = { "Fula-Wolof", 12631267, "alv-sng", } m["alv-gbe"] = { "Gbe", 668284, "alv-von", } m["alv-gda"] = { "Ga-Dangme", 3443338, "alv-kwa", } m["alv-gng"] = { "Guang", 684009, "alv-ptn", } m["alv-gtm"] = { "Ghana-Togo Mountain", 493020, "alv-kwa", aliases = {"Togo Remnant", "Central Togo"}, } m["alv-hei"] = { "Heiban", 108752116, "alv-the", } m["alv-ido"] = { "Idomoid", 974196, "alv-von", } m["alv-igb"] = { "Igboid", 1429100, "alv-von", } m["alv-jfe"] = { "Jola-Felupe", 1708174, "alv-jol", aliases = {"Ejamat"}, } m["alv-jol"] = { "Jola", 35176, "alv-bak", aliases = {"Diola"}, } m["alv-kim"] = { "Kim", 6409701, "alv-mbd", } m["alv-kis"] = { "Kissi", 35696, "alv-mel", } m["alv-krb"] = { "Karaboro", 4213541, "alv-snf", } m["alv-ktg"] = { "Ka-Togo", 5972796, "alv-gtm", } m["alv-kul"] = { "Kulango", 16977424, "alv-sav", aliases = {"Kulango-Lorhon", "Kulango-Lorom"}, } m["alv-kwa"] = { "Kwa", 33430, "nic-vco", } m["alv-lag"] = { "Lagoon", 111210042, "alv-kwa", } m["alv-lek"] = { "Leko", 6520642, other_names = {"Sambaic"}, -- appears to be an alias in Glottolog "alv-lni", } m["alv-lim"] = { "Limba", 35825, "alv", } m["alv-lni"] = { "Leko-Nimbari", 1708170, "alv-ada", other_names = {"Central Adamawa"}, aliases = {"Chamba-Mumuye"}, } m["alv-mbd"] = { "Mbum-Day", 6799816, "alv-ada", } m["alv-mbm"] = { "Mbum", 6799814, "alv-mbd", } m["alv-mel"] = { "Mel", 12122355, "alv", } m["alv-mum"] = { "Mumuye", 84607009, "alv-mye", } m["alv-mye"] = { "Mumuye-Yendang", 6935539, "alv-lni", } m["alv-nal"] = { "Nalu", nil, "alv-sng", } m["alv-nce"] = { "North-Central Edoid", 16110869, "alv-edo", } m["alv-ngb"] = { "Nupe-Gbagyi", 12638649, "alv-nup", aliases = {"Nupe-Gbari"}, } m["alv-ntg"] = { "Na-Togo", nil, "alv-gtm", } m["alv-nup"] = { "Nupoid", 1429143, "alv-von", } m["alv-nwd"] = { "Northwestern Edoid", 16111012, "alv-edo", } m["alv-nyn"] = { "Nyun", nil, "alv-fwo", } m["alv-pap"] = { "Papel", 7132562, "alv-bak", } m["alv-pph"] = { "Phla-Pherá", 3849625, "alv-gbe", } m["alv-ptn"] = { "Potou-Tano", 1475003, "alv-kwa", } m["alv-sav"] = { "Savanna", 4403672, "nic-vco", aliases = {"Savannas"}, } m["alv-sma"] = { "Supyire-Mamara", 4446348, "alv-snf", aliases = {"Suppire-Mamara"}, } m["alv-snf"] = { "Senufo", 33795, "alv", aliases = {"Senufic", "Senoufo", "Sénoufo"}, } m["alv-sng"] = { "Senegambian", 1708753, "alv", } m["alv-snr"] = { "Senari", 4416084, "alv-snf", } m["alv-swd"] = { "Southwestern Edoid", 12633903, "alv-edo", } m["alv-tal"] = { "Talodi", 12643302, "alv-the", } m["alv-tdj"] = { "Tagwana-Djimini", 7675362, "alv-snf", } m["alv-ten"] = { "Tenda", 3217535, "alv-fwo", } m["alv-the"] = { "Talodi-Heiban", 1521145, "alv", } m["alv-von"] = { "Volta-Niger", 34177, "nic-vco", } m["alv-wan"] = { "Wara-Natyoro", 7968830, "alv-sav", } m["alv-wjk"] = { "Waja-Kam", nil, "alv-ada", } m["alv-yek"] = { "Yekhee", nil, "alv-nce", } m["alv-yor"] = { "Yoruba", nil, "alv-edk", } m["alv-yrd"] = { "Yoruboid", 1789745, "alv-von", } m["alv-yun"] = { "Yungur", 84601642, "alv-bam", aliases = {"Bena-Mboi"}, } m["apa"] = { "Apachean", 27758, "ath", aliases = {"Southern Athabaskan"}, } m["aqa"] = { "Alacalufan", 1288430, pseudo_families = "sai", } m["aql"] = { "Algic", 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, pseudo_families = "nai", } m["art"] = { "constructed", 33215, "qfa-not", aliases = {"artificial", "planned"}, } m["ath"] = { "Athabaskan", 27475, "xnd", } m["ath-nor"] = { "North Athabaskan", 20738, "ath", aliases = {"Northern Athabaskan"}, } m["ath-pco"] = { "Pacific Coast Athabaskan", 20654, "ath", } m["auf"] = { "Arawan", 626772, aliases = {"Arahuan", "Arauán", "Arawa", "Arauan", "Arawán"}, pseudo_families = "sai", } --[=[ Exceptional language and family codes for Australian Aboriginal languages can use the prefix "aus-", though "aus" is no longer itself a family code. ]=]-- m["aus-arn"] = { "Arnhem", 2581700, aliases = {"Gunwinyguan", "Macro-Gunwinyguan"}, } m["aus-bub"] = { "Bunuban", 2495148, aliases = {"Bunaban"}, } m["aus-cww"] = { "Central New South Wales", 5061507, "aus-pam", } m["aus-dal"] = { "Daly", 2478079, } m["aus-dyb"] = { "Dyirbalic", 1850666, "aus-pam", } m["aus-gar"] = { "Garawan", 5521951, } m["aus-gun"] = { "Gunwinyguan", 2581700, "aus-arn", aliases = {"Gunwingguan"}, } m["aus-jar"] = { "Jarrakan", 2039423, } m["aus-kar"] = { "Karnic", 4215578, "aus-pam", } m["aus-mir"] = { "Mirndi", 4294095, } m["aus-nga"] = { "Ngayarda", 16153490, "aus-psw", } m["aus-nyu"] = { "Nyulnyulan", 2039408, } m["aus-pam"] = { "Pama-Nyungan", 33942, } m["aus-pmn"] = { "Paman", 2640654, "aus-pam", } m["aus-psw"] = { "Southwest Pama-Nyungan", 2258160, "aus-pam", } m["aus-rnd"] = { "Arandic", 4784071, "aus-pam", } m["aus-tnk"] = { "Tangkic", 1823065, } m["aus-wdj"] = { "Iwaidjan", 4196968, aliases = {"Yiwaidjan"}, } m["aus-wor"] = { "Worrorran", 2038619, } m["aus-yid"] = { "Yidinyic", 4205849, "aus-pam", } m["aus-yng"] = { "Yangmanic", 42727644, } m["aus-yol"] = { "Yolngu", 2511254, "aus-pam", aliases = {"Yolŋu", "Yolngu Matha"}, } m["aus-yuk"] = { "Yuin-Kuric", 3833021, "aus-pam", } m["awd"] = { "Arawak", 626753, aliases = {"Arawakan", "Maipurean", "Maipuran"}, } m["awd-nwk"] = { "Nawiki", nil, "awd", aliases = {"Newiki"}, pseudo_families = "sai", } m["awd-taa"] = { "Ta-Arawak", 7672731, "awd", aliases = {"Ta-Arawakan", "Ta-Maipurean"}, } m["azc"] = { "Uto-Aztecan", 34073, aliases = {"Uto-Aztekan"}, } m["azc-cup"] = { "Cupan", 19866871, "azc-tak", } m["azc-dur"] = { "Durango Nahuatl", 2386361, "azc-nah", aliases = {"Mexicanero"} } m["azc-hua"] = { "Huasteca Nahuatl", 3832950, "azc-nah", } m["azc-nah"] = { "Nahuan", 11965602, "azc", aliases = {"Aztecan"}, pseudo_families = "cai", } m["azc-num"] = { "Numic", 2657541, "azc", pseudo_families = "nai", } m["azc-pim"] = { "Piman", 7194600, "azc", aliases = {"Tepiman"}, pseudo_families = "nai", } m["azc-tak"] = { "Takic", 1280305, "azc", pseudo_families = "nai", } m["azc-trc"] = { "Taracahitic", 4245032, "azc", aliases = {"Taracahitan"}, pseudo_families = "nai", } m["bad"] = { "Banda", 806234, "nic-ubg", } m["bad-cnt"] = { "Central Banda", 3438391, "bad", } m["bai"] = { "Bamileke", 806005, "nic-gre", } m["bat"] = { "Baltic", 33136, "ine-bsl", } m["bat-eas"] = { "East Baltic", 149944, "bat", } m["bat-wes"] = { "West Baltic", 149946, "bat", } m["ber"] = { "Berber", 25448, "afa", aliases = {"Tamazight"}, } m["bnt"] = { "Bantu", 33146, "nic-bds", } m["bnt-baf"] = { "Bafia", 799784, "bnt", } m["bnt-bbo"] = { "Bafo-Bonkeng", nil, "bnt-saw", } m["bnt-bdz"] = { "Boma-Dzing", 1729203, "bnt", } m["bnt-bek"] = { "Bekwilic", nil, "bnt-ndb", } m["bnt-bki"] = { "Bena-Kinga", 16113307, "bnt-bne", } m["bnt-bmo"] = { "Bangi-Moi", nil, "bnt-bnm", } m["bnt-bne"] = { "Northeast Bantu", 7057832, "bnt", } m["bnt-bnm"] = { "Bangi-Ntomba", 806477, "bnt-bte", } m["bnt-boa"] = { "Boan", 4931250, "bnt", aliases = {"Buan", "Ababuan"}, } m["bnt-bot"] = { "Botatwe", 4948532, "bnt", } m["bnt-bsa"] = { "Basaa", 809739, "bnt", } m["bnt-bsh"] = { "Bushoong", 5001551, "bnt-bte", } m["bnt-bso"] = { "Southern Bantu", 980498, "bnt", } m["bnt-bta"] = { "Bati-Angba", 4869303, "bnt-boa", other_names = {"Late Bomokandian"}, aliases = {"Bwa"}, } m["bnt-btb"] = { "Beti", 35118, "bnt", } m["bnt-bte"] = { "Bangi-Tetela", 4855181, "bnt", } m["bnt-bun"] = { "Buja-Ngombe", 4986733, "bnt-mbb", } m["bnt-chg"] = { "Chaga", 33016, "bnt-cht", } m["bnt-cht"] = { "Chaga-Taita", nil, "bnt-bne", } m["bnt-clu"] = { "Chokwe-Luchazi", 3339273, "bnt", } m["bnt-com"] = { "Comorian", 33077, "bnt-sab", } m["bnt-glb"] = { "Great Lakes Bantu", 5599420, "bnt-bne", } m["bnt-haj"] = { "Haya-Jita", 25502360, "bnt-glb", } m["bnt-kak"] = { "Kako", nil, "bnt-pob", } m["bnt-kav"] = { "Kavango", 116544179, "bnt-ksb", } m["bnt-kbi"] = { "Komo-Bira", 6428591, "bnt-boa", } m["bnt-kel"] = { "Kele", 1738162, "bnt-kts", aliases = {"Sheke"}, } m["bnt-kil"] = { "Kilombero", 6408121, "bnt", } m["bnt-kka"] = { "Kikuyu-Kamba", 16114410, "bnt-bne", aliases = {"Thagiicu"}, } m["bnt-kmb"] = { "Kimbundu", 16947687, "bnt", } m["bnt-kng"] = { "Kongo", 6429214, "bnt", } m["bnt-kpw"] = { "Kpwe", 36428, "bnt-saw", } m["bnt-ksb"] = { "Kavango-Southwest Bantu", 6379098, "bnt", } m["bnt-kts"] = { "Kele-Tsogo", 6385577, "bnt", } m["bnt-lbn"] = { "Luban", 4536504, "bnt", } m["bnt-leb"] = { "Lebonya", 6511395, "bnt", } m["bnt-lgb"] = { "Lega-Binja", 6517694, "bnt", } m["bnt-lok"] = { "Logooli-Kuria", nil, "bnt-glb", } m["bnt-lub"] = { "Luba", nil, "bnt-lbn", } m["bnt-lun"] = { "Lunda", 6704091, "bnt", } m["bnt-mak"] = { "Makua", 6740431, "bnt-bso", aliases = {"Makhuwa"}, } m["bnt-mbb"] = { "Mboshi-Buja", 6799764, "bnt", } m["bnt-mbe"] = { "Mbole-Enya", 6799728, "bnt", } m["bnt-mbi"] = { "Mbinga", nil, "bnt-rur", } m["bnt-mbo"] = { "Mboshi", 6799763, "bnt-mbb", } m["bnt-mbt"] = { "Mbete", 1346910, "bnt-tmb", aliases = {"Mbere"}, } m["bnt-mby"] = { "Mbeya", nil, "bnt-ruk", } m["bnt-mij"] = { "Mijikenda", 6845474, "bnt-sab", } m["bnt-mka"] = { "Makaa", nil, "bnt-ndb", } m["bnt-mne"] = { "Manenguba", 31147471, "bnt", aliases = {"Mbo", "Ngoe"}, } m["bnt-mnj"] = { "Makaa-Njem", 1603899, "bnt-pob", } m["bnt-mon"] = { "Mongo", nil, "bnt-bnm", } m["bnt-mra"] = { "Mbugwe-Rangi", 6799795, "bnt", } m["bnt-msl"] = { "Masaba-Luhya", 12636428, "bnt-glb", } m["bnt-mwi"] = { "Mwika", nil, "bnt-ruk", } m["bnt-ncb"] = { "Northeast Coast Bantu", 7057848, "bnt-bne", } m["bnt-ndb"] = { "Ndzem-Bomwali", nil, "bnt-mnj", } m["bnt-ngn"] = { "Ngondi-Ngiri", 7022532, "bnt-mbb", } m["bnt-ngu"] = { "Nguni", 961559, "bnt-bso", aliases = {"Ngoni"}, } m["bnt-nya"] = { "Nyali", 7070832, "bnt-leb", } m["bnt-nyb"] = { "Nyanga-Buyi", 7070882, "bnt", } m["bnt-nyg"] = { "Nyoro-Ganda", 12638666, "bnt-glb", } m["bnt-nys"] = { "Nyasa", 7070921, "bnt", } m["bnt-nze"] = { "Nzebi", 1755498, "bnt-tmb", aliases = {"Njebi"}, } m["bnt-ova"] = { "Ovambo", 36489, "bnt-swb", aliases = {"Oshivambo", "Oshiwambo", "Owambo"}, } m["bnt-par"] = { "Pare", nil, "bnt-ncb", } m["bnt-pen"] = { "Pende", 7162373, "bnt", } m["bnt-pob"] = { "Pomo-Bomwali", nil, "bnt", } m["bnt-ruk"] = { "Rukwa", 7378902, "bnt", } m["bnt-run"] = { "Rungwe", nil, "bnt-ruk", } m["bnt-rur"] = { "Rufiji-Ruvuma", 7377947, "bnt", } m["bnt-ruv"] = { "Ruvu", nil, "bnt-ncb", } m["bnt-rvm"] = { "Ruvuma", nil, "bnt-rur", } m["bnt-sab"] = { "Sabaki", 2209395, "bnt-ncb", } m["bnt-saw"] = { "Sawabantu", 532003, "bnt", } m["bnt-sbi"] = { "Sabi", 7396071, "bnt", } m["bnt-seu"] = { "Seuta", nil, "bnt-ncb", } m["bnt-shh"] = { "Shi-Havu", nil, "bnt-glb", } m["bnt-sho"] = { "Shona", 2904660, "bnt", } m["bnt-sir"] = { "Sira", 1436372, "bnt", aliases = {"Shira-Punu"}, } m["bnt-ske"] = { "Soko-Kele", nil, "bnt-bte", } m["bnt-sna"] = { "Sena", nil, "bnt-nys", } m["bnt-sts"] = { "Sotho-Tswana", 2038386, "bnt-bso", } m["bnt-swb"] = { "Southwest Bantu", 116543539, "bnt-ksb", } m["bnt-swh"] = { "Swahili", nil, "bnt-sab", } m["bnt-tek"] = { "Teke", 36528, "bnt-tmb", } m["bnt-tet"] = { "Tetela", 7706059, "bnt-bte", } m["bnt-tkc"] = { "Central Teke", 36473, "bnt-tek", } m["bnt-tkm"] = { "Takama", nil, "bnt-bne", } m["bnt-tmb"] = { "Teke-Mbede", 7695332, "bnt", aliases = {"Teke-Mbere"}, } m["bnt-tso"] = { "Tsogo", 2458420, other_names = {"Okani"}, --appears to be an alias in Glottolog "bnt-kts", } m["bnt-tsr"] = { "Tswa-Ronga", 12643962, "bnt-bso", } m["bnt-yak"] = { "Yaka", 8047027, "bnt", } m["bnt-yko"] = { "Yasa-Kombe", nil, "bnt-saw", } m["bnt-zbi"] = { "Zamba-Binza", nil, "bnt-bnm", } m["btk"] = { "Batak", 1998595, "poz-nws", } m["cai"] = { "Mesoamerican", 2478413, "qfa-not", } --[=[ Exceptional language and family codes for Mesoamerican ("Central American Indian") languages may use the prefix "cai-", though "cai" is not a proper family (only a pseudo-family). ]=]-- --[=[ Exceptional language and family codes for Caucasian languages can use the prefix "cau-", though "cau" is no longer itself a family code. ]=]-- m["cau-abz"] = { "Abkhaz-Abaza", 4663617, "cau-nwc", other_names = {"Abkhaz-Tapanta"}, aliases = {"Abazgi"}, } m["cau-and"] = { "Andian", 492152, "cau-ava", aliases = {"Andic"}, } m["cau-ava"] = { "Avaro-Andian", 4055404, "cau-nec", aliases = {"Avar-Andian", "Avar-Andi", "Avar-Andic"}, } m["cau-cir"] = { "Circassian", 858543, "cau-nwc", aliases = {"Cherkess"}, } m["cau-drg"] = { "Dargwa", 5222637, "cau-nec", other_names = {"Dargin"}, } m["cau-esm"] = { "Eastern Samur", nil, "cau-sam", } m["cau-ets"] = { "East Tsezian", 121437666, "cau-tsz", aliases = {"East Tsezic", "East Didoic"}, } m["cau-lzg"] = { "Lezghian", 2144370, "cau-nec", aliases = {"Lezgi", "Lezgian", "Lezgic"}, } m["cau-nkh"] = { "Nakh", 24441, "cau-nec", aliases = {"North-Central Caucasian"}, } m["cau-nec"] = { "Northeast Caucasian", 27387, aliases = {"Dagestanian", "Nakho-Dagestanian", "Caspian"}, } m["cau-nwc"] = { "Northwest Caucasian", 33852, aliases = {"Abkhazo-Adyghean", "Abkhaz-Adyghe", "Pontic"}, } m["cau-sam"] = { "Samur", 15229151, "cau-lzg", } m["cau-ssm"] = { "Southern Samur", nil, "cau-sam", } m["cau-tsz"] = { "Tsezian", 1651530, "cau-nec", aliases = {"Tsezic", "Didoic"}, } m["cau-vay"] = { "Vainakh", 4102486, "cau-nkh", aliases = {"Veinakh", "Vaynakh"}, } m["cau-wsm"] = { "Western Samur", nil, "cau-sam", } m["cau-wts"] = { "West Tsezian", 121437697, "cau-tsz", aliases = {"West Tsezic", "West Didoic"}, } m["cba"] = { "Chibchan", 520478, "qfa-mch", -- or none if Macro-Chibchan is considered undemonstrated -- In both Central America and South America } m["ccs"] = { "Kartvelian", 34030, aliases = {"South Caucasian"}, } m["ccs-gzn"] = { "Georgian-Zan", 34030, "ccs", aliases = {"Karto-Zan"}, } m["ccs-zan"] = { "Zan", 2606912, "ccs-gzn", aliases = {"Zanuri", "Colchian"}, } m["cdc"] = { "Chadic", 33184, "afa", } m["cdc-cbm"] = { "Central Chadic", 2251547, "cdc", aliases = {"Biu-Mandara"}, } m["cdc-est"] = { "East Chadic", 2276221, "cdc", } m["cdc-mas"] = { "Masa", 2136092, "cdc", } m["cdc-wst"] = { "West Chadic", 2447774, "cdc", } m["cdd"] = { "Caddoan", 1025090, pseudo_families = "nai", } m["cel"] = { "Celtic", 25293, "ine", } m["cel-bry"] = { "Brythonic", 156877, "cel-ins", aliases = {"Brittonic"}, } m["cel-brs"] = { "Southwestern Brythonic", 2612853, "cel-bry", aliases = {"Southwestern Brittonic"}, } m["cel-brw"] = { "Western Brythonic", 593069, "cel-bry", aliases = {"Western Brittonic"}, } m["cel-gae"] = { "Goidelic", 56433, "cel-ins", aliases = {"Gaelic"}, protoLanguage = "pgl", } m["cel-his"] = { "Hispano-Celtic", 4204136, "cel", } m["cel-ins"] = { "Insular Celtic", 214506, "cel", } m["chi"] = { "Chimakuan", 1073088, pseudo_families = "nai", } m["chm"] = { "Mari", 973685, "urj", } m["cmc"] = { "Chamic", 2997506, "poz-mcm", } m["crp"] = { "creole or pidgin", 19682167, "qfa-cnt", } m["csu"] = { "Central Sudanic", 190822, "ssa", } m["csu-bba"] = { "Bongo-Bagirmi", 3505042, "csu", } m["csu-bbk"] = { "Bongo-Baka", 4941917, "csu-bba", } m["csu-bgr"] = { "Bagirmi", 4841948, "csu-bba", aliases = {"Bagirmic"}, } m["csu-bkr"] = { "Birri-Kresh", nil, "csu", } m["csu-ecs"] = { "Eastern Central Sudanic", 16911698, "csu", aliases = {"East Central Sudanic", "Central Sudanic East", "Lendu-Mangbetu"}, } m["csu-kab"] = { "Kaba", 6343715, "csu-bba", } m["csu-lnd"] = { "Lendu", 6522357, "csu-ecs", aliases = {"Lenduic"}, } m["csu-maa"] = { "Mangbetu", 6748874, "csu-ecs", aliases = {"Mangbetu-Asoa", "Mangbetu-Asua"}, } m["csu-mle"] = { "Mangbutu-Lese", 17009406, "csu-ecs", aliases = {"Mangbutu-Efe", "Mangbutu", "Membi-Mangbutu-Efe"}, } m["csu-mma"] = { "Moru-Madi", 6915156, "csu-ecs", } m["csu-sar"] = { "Sara", 2036691, "csu-bba", } m["csu-val"] = { "Vale", 7909520, "csu-bba", } m["cus"] = { "Cushitic", 33248, "afa", } m["cus-cen"] = { "Central Cushitic", 56569, "cus", } m["cus-eas"] = { "East Cushitic", 56568, "cus", } m["cus-hec"] = { "Highland East Cushitic", 56524, "cus-eas", } m["cus-som"] = { "Somaloid", 56774, "cus-eas", aliases = {"Sam", "Macro-Somali"}, } m["cus-sou"] = { "South Cushitic", 56525, "cus", } m["day"] = { "Land Dayak", 2760613, "poz", } m["del"] = { "Lenape", 2665761, "alg-eas", aliases = {"Delaware"}, } m["den"] = { "Slavey", 13272, "ath-nor", aliases = {"Slave", "Slavé"}, } m["dmn"] = { "Mande", 33681, "nic", } m["dmn-bbu"] = { "Bisa-Busa", 12627956, "dmn-mde", } m["dmn-emn"] = { "East Manding", nil, "dmn-man", } m["dmn-jje"] = { "Jogo-Jeri", nil, "dmn-mjo", } m["dmn-man"] = { "Manding", 35772, "dmn-mmo", } m["dmn-mda"] = { "Mano-Dan", nil, "dmn-mse", } m["dmn-mdc"] = { "Central Mande", 5972907, "dmn-mdw", } m["dmn-mde"] = { "Eastern Mande", 12633080, "dmn", } m["dmn-mdw"] = { "Western Mande", 16113831, "dmn", } m["dmn-mjo"] = { "Manding-Jogo", 12636153, "dmn-mdc", } m["dmn-mmo"] = { "Manding-Mokole", nil, "dmn-mva", } m["dmn-mnk"] = { "Maninka", 36186, "dmn-emn", } m["dmn-mnw"] = { "Northwestern Mande", 5972910, "dmn-mdw", } m["dmn-mok"] = { "Mokole", 16935447, "dmn-mmo", } m["dmn-mse"] = { "Southeastern Mande", 5972912, "dmn-mde", } m["dmn-msw"] = { "Southwestern Mande", 12633904, "dmn-mdw", } m["dmn-mva"] = { "Manding-Vai", nil, "dmn-mjo", } m["dmn-nbe"] = { "Nwa-Beng", nil, "dmn-mse", } m["dmn-sam"] = { "Samo", 36327, "dmn-bbu", aliases = {"Samuic"}, } m["dmn-smg"] = { "Samogo", 7410000, "dmn-mnw", aliases = {"Duun-Seenku"}, } m["dmn-snb"] = { "Soninke-Bobo", 16111680, "dmn-mnw", } m["dmn-sya"] = { "Susu-Yalunka", nil, "dmn-mdc", } m["dmn-vak"] = { "Vai-Kono", nil, "dmn-mva", } m["dmn-wmn"] = { "West Manding", nil, "dmn-man", } m["dra"] = { "Dravidian", 33311, } m["dra-cen"] = { "Central Dravidian", 12628823, "dra", } m["dra-gki"] = { "Gondi-Kui", 12631610, "dra-sdt", } m["dra-gon"] = { "Gondi", 55639812, "dra-gki", } m["dra-imd"] = { "Irula-Muduga", nil, "dra-tkn", } m["dra-kan"] = { "Kannadoid", 6363888, "dra-tkn", protoLanguage = "dra-okn", } m["dra-kki"] = { "Konda-Kui", nil, "dra-gki", } m["dra-kml"] = { "Kurux-Malto", 68002822, "dra-nor", } m["dra-knk"] = { "Kolami-Naiki", 10547037, "dra-cen", } m["dra-kod"] = { "Kodagu", 67983106, "dra-tkd", } m["dra-kor"] = { "Koraga", 33394, "dra-tlk", } m["dra-mal"] = { "Malayalamoid", 6741581, "dra-tml", } m["dra-mdy"] = { "Madiya", 27602, "dra-gon", } m["dra-mlo"] = { "Malto", nil, "dra-kml", } m["dra-mur"] = { "Muria", 6938499, "dra-gon", } m["dra-nor"] = { "North Dravidian", 16110967, "dra", } m["dra-pgd"] = { "Parji-Gadaba", 10620428, "dra-cen", } m["dra-sdo"] = { "South Dravidian I", 16112843, -- Wikipedia's "South Dravidian" is South Dravidian I in this scheme. "dra-sou", aliases = {"South Dravidian"}, -- This is why I and II are used. } m["dra-sdt"] = { "South Dravidian II", 12633975, "dra-sou", aliases = {"South-Central Dravidian"}, } m["dra-sou"] = { "South Dravidian", 128886618, "dra", aliases = {"Southern Dravidian"}, } m["dra-tam"] = { "Tamiloid", 7681417, "dra-tml", protoLanguage = "oty", } m["dra-tel"] = { "Teluguic", nil, "dra-sdt", protoLanguage = "dra-ote", } m["dra-tkd"] = { "Tamil-Kodagu", 25494510, "dra-tkn", } m["dra-tkn"] = { "Tamil-Kannada", 6478506, "dra-sdo", } m["dra-tkt"] = { "Toda-Kota", 67983857, "dra-tkd", } m["dra-tlk"] = { "Tulu-Koraga", nil, "dra-sdo", } m["dra-tml"] = { "Tamil-Malayalam", 10690507, "dra-tkd", } m["egx"] = { "Egyptian", 50868, "afa", protoLanguage = "egy", } m["ero"] = { "Horpa", 56854, "sit-wgy", } m["esx"] = { "Eskimo-Aleut", 25946, pseudo_families = "nai", } m["esx-esk"] = { "Eskimo", 25946, "esx", } m["esx-inu"] = { "Inuit", 27796, "esx-esk", } m["euq"] = { "Vasconic", 4669240, } m["gba"] = { "Gbaya", 3099986, "alv-sav", } m["gba-eas"] = { "Eastern Gbaya", nil, "gba", } m["gba-sou"] = { "Southern Gbaya", nil, "gba", } m["gba-wes"] = { "Western Gbaya", nil, "gba", } m["gem"] = { "Germanic", 21200, "ine", } m["gio"] = { "Gelao", 56401, "qfa-kra", } m["gme"] = { "East Germanic", 108662, "gem", } m["gmq"] = { "North Germanic", 106085, "gem", } m["gmq-eas"] = { "East Scandinavian", 3090263, "gmq", protoLanguage = "non-oen", } m["gmq-ins"] = { "Insular Scandinavian", nil, "gmq-wes", } m["gmq-wes"] = { "West Scandinavian", 1792570, "gmq", protoLanguage = "non-own", } m["gmw"] = { "West Germanic", 26721, "gem", } m["gmw-afr"] = { "Anglo-Frisian", 5329170, "gmw-nsg", } m["gmw-ang"] = { "Anglic", 1346342, "gmw-afr", protoLanguage = "ang", } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Low Franconian", 153050, "gmw", protoLanguage = "frk", } m["gmw-hgm"] = { "High German", 52040, "gmw", protoLanguage = "goh", } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Low German", 25433, "gmw-nsg", protoLanguage = "osx", } m["gmw-nsg"] = { "North Sea Germanic", 30134, "gmw", aliases = {"Ingvaeonic"}, } m["gn"] = { "Guarani", 35876, "tup-gua", aliases = {"Guaraní"}, } m["grb"] = { "Grebo proper", 35257, "kro-grb", } m["grk"] = { "Hellenic", 2042538, "ine", aliases = {"Greek"}, } m["him"] = { "Western Pahari", 10939493, "inc-pah", aliases = {"Himachali"}, } m["hmn"] = { "Hmongic", 3307894, "hmx", } m["hmx"] = { "Hmong-Mien", 33322, aliases = {"Miao-Yao"}, } m["hmx-mie"] = { "Mienic", 7992695, "hmx", } m["hok"] = { "Hokan", 33406, -- NOTE: Some Hokan languages are in Central America; they have `pseudo_families = "cai"`, -- which overrides the following. pseudo_families = "nai", } m["hyx"] = { "Armenian", 8785, "ine", } m["iir"] = { "Indo-Iranian", 33514, "ine", } m["iir-nur"] = { "Nuristani", 161804, "iir", } m["nur-nor"] = { "Northern Nuristani", nil, "iir-nur", } m["nur-sou"] = { "Southern Nuristani", nil, "iir-nur", } m["ijo"] = { "Ijoid", 1325759, "nic", other_names = {"Ijaw"}, -- Ijaw may be a subfamily } m["inc"] = { "Indo-Aryan", 33577, "iir", aliases = {"Indic"}, } m["inc-bas"] = { "Bengali-Assamese", 4179137, "inc-eas", aliases = {"Assamese-Bengali", "Gauda-Kamarupa"}, } m["inc-bhi"] = { "Bhil", 4901727, "inc-cen", } m["inc-bih"] = { "Bihari", 135305, "inc-eas", } m["inc-cen"] = { "Central Indo-Aryan", 10979187, "inc", protoLanguage = "inc-asa", } m["inc-chi"] = { "Chitrali", 11732797, "inc-dar", } m["inc-dar"] = { "Dardic", 161101, "inc", protoLanguage = "inc-ash", } m["inc-dre"] = { "Eastern Dardic", nil, "inc-dar", } m["inc-dng"] = { "Dangari", nil, "inc-shn", } m["inc-eas"] = { "Eastern Indo-Aryan", 12593391, "inc", protoLanguage = "inc-aav", } m["inc-hal"] = { "Halbic", 16910593, "inc-eas", aliases = {"Halbi"}, } m["inc-hie"] = { "Eastern Hindi", 4126648, "inc-cen", aliases = {"Purabiyā"}, protoLanguage = "inc-oaw", } m["inc-hiw"] = { "Western Hindi", 12600937, "inc-cen", protoLanguage = "inc-ohi", } m["inc-hnd"] = { "Hindustani", 11051, "inc-hiw", aliases = {"Hindi-Urdu"}, protoLanguage = "hi-mid", } m["inc-ins"] = { "Insular Indo-Aryan", 12179302, "inc", protoLanguage = "inc-apa", } m["inc-kas"] = { "Kashmiric", nil, "inc-dre", aliases = {"Kashmiri"}, } m["inc-koh"] = { "Kohistani", 13018610, "inc-dre", } m["inc-krd"] = { "KRDS languages", 6356154, "inc-eas", aliases = {"Kamta, Rajbanshi, Deshi and Surjapuri", "KRNB languages", "Kamta, Rajbanshi and Northern Deshi Bangla"}, } m["inc-kun"] = { "Kunar", nil, "inc-dar", } m["inc-mid"] = { "Middle Indo-Aryan", 3236316, "inc", aliases = {"Middle Indic"}, } m["inc-nwe"] = { "Northwestern Indo-Aryan", 16111018, "inc", protoLanguage = "inc-apa", } m["inc-nor"] = { "Northern Indo-Aryan", 946077, "inc", protoLanguage = "inc-aka", } m["inc-old"] = { "Old Indo-Aryan", 118976896, "inc", aliases = {"Old Indic"}, } m["inc-pac"] = { "Central Pahari", nil, "inc-pah", } m["inc-pae"] = { "Eastern Pahari", nil, "inc-pah", } m["inc-pah"] = { "Pahari", 946077, "inc-nor", aliases = {"Pahadi"}, protoLanguage = "inc-aka", } m["inc-pan"] = { "Punjabic", 2656685, "inc-nwe", aliases = {"Greater Punjabic"}, protoLanguage = "inc-opa", } m["inc-pas"] = { "Pashayi", 36670, "inc-dar", aliases = {"Pashai"}, } m["inc-rom"] = { "Romani", 13201, "inc-wes", aliases = {"Romany", "Gypsy", "Gipsy"}, } m["inc-sad"] = { "Sadanic", 109546827, "inc-bih", aliases = {"Sadani"}, } m["inc-shn"] = { "Shinaic", 12646125, "inc-dre", } m["inc-snd"] = { "Sindhic", 7522212, "inc-nwe", protoLanguage = "inc-avr", } m["inc-sou"] = { "Southern Indo-Aryan", 10856062, "inc", protoLanguage = "inc-ama", } m["inc-tha"] = { "Tharu", 34035, "inc-eas", } m["inc-wes"] = { "Western Indo-Aryan", nil, "inc", protoLanguage = "inc-agu", } m["ine"] = { "Indo-European", 19860, aliases = {"Indo-Germanic"}, } m["ine-ana"] = { "Anatolian", 147085, "ine", } m["ine-bsl"] = { "Balto-Slavic", 147356, "ine", } m["ine-luw"] = { "Luwic", 115748615, "ine-ana", aliases = {"Luvic"}, } m["ine-toc"] = { "Tocharian", 37029, "ine", aliases = {"Tokharian"}, } m["ira"] = { "Iranian", 33527, "iir", } m["ira-csp"] = { "Caspian", 5049123, "ira-mpr", } m["ira-cen"] = { "Central Iranian", nil, "ira", } m["ira-kms"] = { "Komisenian", nil, "ira-mpr", aliases = {"Semnani"}, } m["ira-lur"] = { "Luric", nil, -- ? "ira-swi", } m["ira-mid"] = { "Middle Iranian", 6841465, "ira", } m["ira-mny"] = { "Munji-Yidgha", nil, "ira-sym", aliases = {"Yidgha-Munji"}, } m["ira-msh"] = { "Mazanderani-Shahmirzadi", nil, "ira-csp", } m["ira-nei"] = { "Northeastern Iranian", 10775567, "ira", } m["ira-nwi"] = { "Northwestern Iranian", 390576, "ira-wes", } m["ira-old"] = { "Old Iranian", 23301845, "ira", } m["ira-orp"] = { "Ormuri-Parachi", nil, "ira-sei", } m["ira-pat"] = { "Pathan", nil, "ira-sei", } m["ira-sbc"] = { "Sogdo-Bactrian", nil, "ira-nei", } m["ira-mpr"] = { "Medo-Parthian", nil, "ira-nwi", aliases = {"Partho-Median"}, } m["ira-sgi"] = { "Sanglechi-Ishkashimi", 18711232, "ira-sei", } m["ira-shr"] = { "Shughni-Roshani", 11732824, "ira-shy", } m["ira-shy"] = { "Shughni-Yazghulami", nil, "ira-sym", } m["ira-sgc"] = { "Sogdic", nil, "ira-sbc", aliases = {"Sogdian"}, } m["ira-sei"] = { "Southeastern Iranian", 3833002, "ira", } m["ira-swi"] = { "Southwestern Iranian", 390424, "ira-wes", } m["ira-sym"] = { "Shughni-Yazghulami-Munji", nil, "ira-sei", } m["ira-wes"] = { "Western Iranian", 129850, "ira", } m["ira-zgr"] = { "Zaza-Gorani", 167854, "ira-mpr", aliases = {"Zaza-Gurani", "Gorani-Zaza"}, } m["iro"] = { "Iroquoian", 33623, pseudo_families = "nai", } m["iro-nor"] = { "North Iroquoian", nil, "iro", } m["itc"] = { "Italic", 131848, "ine", } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Japonic", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, } m["jpx-nry"] = { "Northern Ryukyuan", 20862796, "jpx-ryu", } m["jpx-ryu"] = { "Ryukyuan", 56393, "jpx", } m["jpx-sry"] = { "Southern Ryukyuan", 18392243, "jpx-ryu", } m["kar"] = { "Karen", 1364815, "sit", } m["kca"] = { "Khanty", 33563, "urj-ugr", aliases = {"Khantyic", "Khantic"}, } --[=[ Exceptional language and family codes for Khoisan and Kordofanian languages can use the prefix "khi-" and "kdo-" respectively, though they are no longer family codes themselves. ]=]-- m["khi-kal"] = { "Kalahari Khoe", nil, "khi-kho", } m["khi-khk"] = { "Khoekhoe", nil, "khi-kho", } m["khi-kkw"] = { "Khoe-Kwadi", 60785084, aliases = {"Kwadi-Khoe"}, } m["khi-kho"] = { "Khoe", 2736449, "khi-kkw", aliases = {"Central Khoisan"}, } m["khi-kxa"] = { "Kx'a", 6450587, aliases = {"Kxa", "Ju-ǂHoan"}, } m["khi-tuu"] = { "Tuu", 631046, aliases = {"Kwi", "Taa-Kwi", "Southern Khoisan", "Taa-ǃKwi", "Taa-ǃUi", "ǃUi-Taa"}, } m["kro"] = { "Kru", 33535, "nic-vco", } m["kro-aiz"] = { "Aizi", 4699431, "kro", } m["kro-bet"] = { "Bété", 32956, "kro-ekr", } m["kro-did"] = { "Dida", 32685, "kro-ekr", } m["kro-ekr"] = { "Eastern Kru", 5972899, "kro", } m["kro-grb"] = { "Grebo", 5601537, "kro-wkr", } m["kro-wee"] = { "Wee", nil, "kro-wkr", } m["kro-wkr"] = { "Western Kru", 5972897, "kro", } m["ku"] = { "Kurdish", 36368, "ira-nwi", } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Austronesian", 49228, } m["map-ata"] = { "Atayalic", 716610, "map", } m["mjg"] = { "Monguor", 34214, "xgn-shr", } m["mkh"] = { "Mon-Khmer", 33199, "aav", } m["mkh-asl"] = { "Aslian", 3111082, "mkh", } m["mkh-ban"] = { "Bahnaric", 56309, "mkh", } m["mkh-kat"] = { "Katuic", 56697, "mkh", } m["mkh-khm"] = { "Khmuic", 1323245, "mkh", } m["mkh-kmr"] = { "Khmeric", nil, "mkh", } m["mkh-mnc"] = { "Monic", 3217497, "mkh", } m["mkh-mng"] = { "Mangic", 3509556, "mkh", } m["mkh-nbn"] = { "North Bahnaric", 56309, "mkh-ban", } m["mkh-pal"] = { "Palaungic", 2391173, "mkh", } m["mkh-pea"] = { "Pearic", 3073022, "mkh", } m["mkh-pkn"] = { "Pakanic", nil, "mkh-mng", } m["mkh-vie"] = { "Vietic", 2355546, "mkh", } m["mno"] = { "Manobo", 3217483, "phi", } m["mns"] = { "Mansi", 33759, "urj-ugr", aliases = {"Mansic"}, } m["mun"] = { "Munda", 33892, "aav", } m["myn"] = { "Mayan", 33738, pseudo_families = "cai", } m["nai"] = { "North American Indigenous", 51739, "qfa-not", } --[=[ Exceptional language and family codes for North American Indigenous/Indian languages can use the prefix "nai-", though "nai" is not a proper family (only a pseudo-family). ]=]-- m["nai-cat"] = { "Catawban", 3446638, "nai-sca", } m["nai-chu"] = { "Chumash", 1288420, aliases = {"Chumashan"}, } m["nai-ckn"] = { "Chinookan", 610586, } m["nai-coo"] = { "Coosan", 940278, } m["nai-jcq"] = { "Jicaquean", 12179308, "hok", pseudo_families = "cai", } m["nai-ker"] = { "Keresan", 35878, } m["nai-klp"] = { "Kalapuyan", 1569040, } m["nai-kta"] = { "Kiowa-Tanoan", 386288, } m["nai-len"] = { "Lencan", 36189, aliases = {"Lenca"}, pseudo_families = "cai", } m["nai-mdu"] = { "Maiduan", 33502, } m["nai-miz"] = { "Mixe-Zoquean", 954016, aliases = {"Mixe-Zoque"}, pseudo_families = "cai", } m["nai-min"] = { "Misumalpan", 281693, "qfa-mch", aliases = {"Misuluan", "Misumalpa"}, pseudo_families = "cai", } m["nai-mus"] = { "Muskogean", 902978, aliases = {"Muskhogean"}, } m["nai-pak"] = { "Pakawan", 65085487, "hok", } m["nai-pal"] = { "Palaihnihan", 1288332, } m["nai-plp"] = { "Plateau Penutian", 2307476, } m["nai-pom"] = { "Pomoan", 2618420, "hok", aliases = {"Pomo", "Kulanapan"}, } m["nai-sca"] = { "Siouan-Catawban", 34181, } m["nai-shp"] = { "Sahaptian", 114782, "nai-plp", } m["nai-shs"] = { "Shastan", 2991735, "hok", } m["nai-tot"] = { "Totozoquean", 7828419, pseudo_families = "cai", } m["nai-ttn"] = { "Totonacan", 34039, aliases = {"Totonac-Tepehua", "Totonacan-Tepehuan"}, varieties = {"Totonac"}, pseudo_families = "cai", } m["nai-tqn"] = { "Tequistlatecan", 1568317, "hok", aliases = {"Tequistlatec", "Chontal", "Chontalan", "Oaxacan Chontal", "Chontal of Oaxaca"}, pseudo_families = "cai", } m["nai-tsi"] = { "Tsimshianic", 34134, } m["nai-utn"] = { "Utian", 13371763, "nai-you", aliases = {"Miwok-Costanoan", "Mutsun"}, } m["nai-wtq"] = { "Wintuan", 1294259, aliases = {"Wintun"}, } m["nai-xin"] = { "Xincan", 1546494, aliases = {"Xinca"}, pseudo_families = "cai", } m["nai-ykn"] = { "Yukian", 2406722, aliases = {"Yuki-Wappo"}, } m["nai-you"] = { "Yok-Utian", 2886186, } m["nai-yuc"] = { "Yuman-Cochimí", 579137, } m["ngf"] = { "Trans-New Guinea", 34018, pseudo_families = "paa", } m["ngf-ais"] = { "Aisian", nil, "ngf-eso", } m["ngf-ang"] = { "Angan", 3217366, "ngf", aliases = {"Kratke Range"}, -- Usher } m["ngf-ank"] = { "Angal-Kewa", 12626916, -- exist in dewiki and hrwiki "ngf-sak", } m["ngf-ask"] = { "Asmat-Kamoro", 3031400, "ngf", -- Wikipedia uses Asmat-Kamoro to refer to a narrower group excluding the Sabakor languages (Buruwai and Kamberau, -- which Glottolog splits into North Kamrau and South Kamrau [sic]), and uses Asmat-Kamrau to refer to what we and -- Glottolog call Asmat-Kamoro. Glottolog does not recognize the narrower grouping. aliases = {"Asmat-Kamrau", -- Wikipedia "Asmat-Kamrau Bay", -- Usher }, } m["ngf-asm"] = { "Asmat", 4807421, "ngf-ask", } m["ngf-ata"] = { "Ankave-Tainae-Akoye", nil, "ngf-ang", aliases = {"Southwest Kratke Range"}, -- Usher } m["ngf-awd"] = { "Awyu-Dumut", -- [[w:Awyu-Dumut languages]] redirects to [[w:Greater Awyu languages]] 4830163, -- exist in eswiki, hrwiki and ruwiki "ngf-gaw", aliases = {"Central Digul River"}, -- Usher } m["ngf-awy"] = { "Awyu", 96372866, "ngf-awd", } m["ngf-bda"] = { "Becking-Dawi", nil, -- Q55993716 ([[Category:Becking–Dawi languages]]) exists in enwiki "ngf-gaw", aliases = {"Becking and Dawi Rivers"}, -- Usher } m["ngf-bin"] = { "Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf-gbi", aliases = {"Oro"}, -- Usher (2020) } m["ngf-boa"] = { "Boane", nil, "ngf-era", aliases = {"Boana", -- Glottolog's name "Wain"}, -- not in Usher; "Wain" often excludes Mungkip, perhaps because it's poorly documented } m["ngf-bos"] = { "Bosavi", 4947122, "ngf", aliases = {"Papuan Plateau"}, -- alternative name given by Wikipedia } m["ngf-bsi"] = { "Baruya-Simbari", nil, "ngf-ang", aliases = {"Northwest Kratke Range"}, -- Usher } m["ngf-cda"] = { "Central Dani", nil, "ngf-dan", aliases = {"Dani"}, -- Usher } m["ngf-chw"] = { "Chimbu-Wahgi", 3217383, "ngf", aliases = {"Simbu-Western Highlands"}, -- alternative name given by Wikipedia } m["ngf-dag"] = { "Dagan", 5208454, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Meneao Range"}, } m["ngf-dal"] = { "Dallman", nil, "ngf-huo", aliases = {"Kinalakna-Kumukio", -- Pawley-Hammarström, who exclude Nomu, but they only had a numeral list of that language to work from "Northeast Huon", -- Usher }, } m["ngf-dan"] = { "Dani", 3217389, "ngf", -- Wikipedia renames the Dani languages to the Baliem Valley languages and sometimes (but not consistently) -- reserves the name Dani (or "Dani proper") for a narrower group excluding Wano and the poorly attested Ngalik -- languages (Nduga, Silimo, and the Yali dialect cluster, which we, following Ethnologue and Glottolog, split into -- Anggurk Yali, Ninia Yali and Pass Valley Yali). Glottolog does not recognize the narrower grouping. aliases = {"Baliem Valley", -- Wikipedia "Balim Valley", -- Usher }, } m["ngf-dum"] = { "Dumut", -- [[w:Dumut languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Wambon"}, -- Usher } m["ngf-ehu"] = { "Eastern Huon", -- Glottolog adds Ono and Sialum, Pawley-Hammarström adds Dedua 10567087, "ngf-huo", aliases = {"East Huon"}, -- Usher } m["ngf-eku"] = { "East Kutubuan", 5328752, "ngf", -- Not in TNG per Glottolog but accepted by all others. Sometimes grouped with Fasu to form a Kutubuan family. aliases = {"East Kutubu"}, -- Glottolog's name } m["ngf-enc"] = { "Engic", nil, "ngf-eng", aliases = {"Engan", -- Glottolog "Engan proper", -- Wikipedia "North Engan", -- alternative name given by Wikipedia "Trans-Enga", -- Usher }, } m["ngf-eng"] = { "Engan", 3217449, "ngf", aliases = {"Enga-Kewa-Huli", -- Glottolog, Pawley-Hammarström "Enga-Southern Highlands", -- Usher }, } m["ngf-era"] = { "Erap", nil, "ngf-fin", aliases = {"Erap River"}, -- Usher? } m["ngf-eso"] = { "East Sogeram", nil, "ngf-sog", } m["ngf-est"] = { "East Strickland", 5329440, "ngf", aliases = {"Strickland River"}, -- alternative name given by Wikipedia } m["ngf-eva"] = { "Evapia", nil, "ngf-rai", aliases = {"Evapia River"}, -- Usher } m["ngf-fgi"] = { "Fore-Gimi", nil, "ngf-gor", aliases = {"South Goroka"}, -- Usher } m["ngf-fhu"] = { "Finisterre-Huon", 3217453, "ngf", aliases = {"Finisterre Range-Huon Peninsula"}, -- per Usher } m["ngf-fin"] = { "Finisterre", 5450373, "ngf-fhu", aliases = {"Finisterre-Saruwaged", -- Glottolog's name "Finisterre Range"}, -- per Usher } m["ngf-gah"] = { "Gahuku", nil, "ngf-gor", aliases = {"Alekano-Asaro River"}, -- Usher } m["ngf-gau"] = { "Gauwa", nil, "ngf-kai", aliases = {"West Kainantu"}, -- Usher } m["ngf-gaw"] = { "Greater Awyu", 12627424, "ngf", aliases = {"Digul River"}, -- used by Usher (2020) } m["ngf-gbi"] = { "Greater Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf", -- not placed in Trans-New Guinea in Usher (2020) aliases = {"Guhu-Oro"}, -- Guhu-Oro is used in Usher (2020) } m["ngf-gko"] = { "Gaena-Korafe", 11732347, -- considered a single Korafe language by Wikipedia "ngf-bin", aliases = {"Gaina-Korafe"}, -- Usher } m["ngf-gmo"] = { "Gusap-Mot", 16110857, "ngf-fin", aliases = {"Mot River"}, -- Usher? } m["ngf-gor"] = { "Goroka", 15478597, "ngf-kgo", } m["ngf-gsu"] = { "Gogodala-Suki", 5577428, "ngf", -- Possibly in the proposed Papuan Gulf family. Not in TNG per Glottolog but accepted by all others. aliases = {"Suki-Gogodala", -- Glottolog's name "Suki-Aramia River", -- Used in Usher (2020) }, } m["ngf-gum"] = { "Gum", 5618008, "ngf-mab", } m["ngf-gvd"] = { "Grand Valley Dani", -- considered a single language by Wikipedia 5595219, "ngf-cda", } m["ngf-hag"] = { "Hagen", -- [[w:Hagen languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Melpa-Kaugel River"}, -- Usher } m["ngf-han"] = { "Hanseman", 5651020, "ngf-mab", aliases = {"Hansemann Range"}, -- Usher } m["ngf-huo"] = { "Huon", 5946109, "ngf-fhu", aliases = {"Huon Peninsula"}, -- per Usher } m["ngf-jim"] = { "Jimi", -- [[w:Jimi languages]] and [[w:Jimi River languages]] redirect to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Jimi River"}, -- Usher } m["ngf-kab"] = { "Kabwum", nil, "ngf-huo", aliases = {"Timbe-Selepet-Komba", -- Pawley-Hammarström, "Northwest Huon", -- Usher }, } m["ngf-kai"] = { "Kainantu", -- Kambaira: under "unclassified Kainantu" (Glottolog), Tairora (Pawley-Hammarström), Gauwa (Usher) 15478590, "ngf-kgo", aliases = {"Gadsup-Auyana-Awa-Tairora"}, -- Wurm, } m["ngf-kak"] = { "Kalam-Kobon", 6350303, "ngf-ksa", aliases = {"Kalam", "Kaironk River"}, -- Usher (2020) } m["ngf-kau"] = { "Kaukombar", nil, "ngf-nad", aliases = {"Kaukombaran", -- Glottolog following Z'graggen (1975) "Kaukombar River"}, -- Usher's term } m["ngf-kbm"] = { "Kosorong-Burum-Mindik", nil, "ngf-huo", aliases = {"Bulum River"}, -- Usher } m["ngf-kgo"] = { "Kainantu-Goroka", 3217463, "ngf", aliases = {"Eastern Highlands"}, -- per Usher (2020) } m["ngf-khu"] = { "Kewa-Huli", nil, "ngf-eng", aliases = {"Huli-Southern Highlands"}, -- Usher } m["ngf-kma"] = { "Kâte-Mape", nil, "ngf-ehu", aliases = {"Kate-Mape-Sene", -- Pawley-Hammarström (with Sene), "Southeast Huon", -- Usher }, } m["ngf-kme"] = { "Kapau-Menya", nil, "ngf-ang", aliases = {"Southeast Kratke Range"}, -- Usher } m["ngf-koi"] = { "Koiarian", 11154240, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Koiari-Managalas Plateau"}, } m["ngf-kok"] = { "Kokon", -- Usher calls it South Mabuso but includes Gum in it nil, "ngf-mab", } m["ngf-kow"] = { "Kowan", 6435004, "ngf-mad", aliases = {"Isumrud Strait"}, -- per Usher (2020) } m["ngf-ksa"] = { "Kalam-Southern Adelbert", nil, "ngf-mad", aliases = {"Kalamic-South Adelbert", -- Glottolog "West Madang"}, -- Usher (2020) } m["ngf-kto"] = { "Kube-Tobo", -- per Glottolog, one language "Kulungtfu-Yuanggeng-Tobo" 1173235, -- code for Tobo-Kube language "ngf-huo", aliases = {"Tobo-Kube"}, } m["ngf-kts"] = { "Komyandaret-Tsaukambo", nil, "ngf-bda", aliases = {"Becking River"}, -- Usher } m["ngf-kum"] = { "Kumil", nil, "ngf-nad", aliases = {"Kumilan", -- Pawley-Hammarström following Z'graggen (1975) "Kumil River"}, -- Usher's term } m["ngf-kya"] = { "Kamano-Yagaria", nil, "ngf-gor", aliases = {"Henganofi", -- Usher "Kamano-Yagaria-Keigana", }, } m["ngf-lok"] = { "Lowland Ok", nil, "ngf-okk", } m["ngf-mab"] = { "Mabuso", 6721668, "ngf-mad", } m["ngf-mad"] = { "Madang", 11217556, "ngf", aliases = {"Madang-Adelbert Range"}, -- Z'graggen (1975), corresponding to today's Madang except in lacking Kalam and Gants } m["ngf-mek"] = { "Mek", 6810515, "ngf", aliases = {"Goliath"}, -- outdated alternative name given by Wikipedia } m["ngf-min"] = { "Mindjim", 86749913, "ngf-mad", aliases = {"Lower Minjim", -- Glottolog, placed in Rai Coast by Glottolog and Pawley-Hammarström; Glottolog's -- Mindjim has 6 languages, including "Upper Minjim" (Rerau and Sgi Bara) "Mindjim River", -- Usher "Minjim", "Minjim River", }, } -- Add if Molet is separated from Asaro'o -- m["ngf-moa"] = { -- "Molet-Asaro'o", -- nil, -- "ngf-war", -- } m["ngf-mok"] = { "Mountain Ok", -- [[w:Mountain Ok languages]] redirects to [[w:Ok languages]] nil, "ngf-okk", } m["ngf-mom"] = { "Mombum", 6897077, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Mombum-Koneraw", "Komolom", "Muli Strait"}, -- Pawley-Hammarström uses Komolom, Usher uses Muli Strait } m["ngf-msu"] = { "Mian-Suganga", -- considred a single Mian language by Wikipedia 12952846, "ngf-mok", aliases = {"Mianic"}, -- Glottolog } m["ngf-nad"] = { "Northern Adelbert", -- not accepted by Pawley-Hammarström 16952821, -- code for Croisilles linkage "ngf-mad", aliases = {"Adelbert Range-Isumrud Strait", -- Usher (2020) "North Adelbert", "Pihom-Isumrud"}, -- Ross? } m["ngf-nbi"] = { "North Binanderean", nil, "ngf-bin", aliases = {"Suena-Zia"}, -- Usher } m["ngf-nde"] = { "Ndeiram", -- [[w:Ndeiram River languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Ndeiram River"}, -- Usher? } m["ngf-ngn"] = { "Ngalik-Nduga", -- [[w:Ngalik languages]] redirects to [[w:Baliem Valley languages]] = Dani languages nil, "ngf-dan", aliases = {"Ngalik"}, -- Usher } m["ngf-nso"] = { "North Sogeram", nil, "ngf-sog", aliases = {"Mum-Sirva", -- Usher "North Central Sogeram", -- used by those who accept Central Sogeram (= North Sogeram + Apali and Manat) "North-Central Sogeram", -- rarer than without the dash "Sikan"}, -- Z’graggen (1975?) } m["ngf-num"] = { "Numugen", nil, "ngf-nad", aliases = {"Numugenan", -- Glottolog following Z'graggen 1975 "Numugen River"}, -- Usher's term } m["ngf-nur"] = { "Nuru", -- Usher excludes Yangulam, Pawley-Hammarström include Jilim and Rerau nil, "ngf-rai", aliases = {"Nuru River"}, -- Usher? } m["ngf-nwh"] = { "Northwest Hanseman", -- Usher nil, "ngf-han", aliases = {"Wamas-Samosa-Murupi-Mosimo"}, -- Glottolog, Greenhill, and Pawley-Hammarström following Z'graggen; the most common name, but very unwieldy } m["ngf-oen"] = { "Outer Engan", -- considered a single Nete language by Wikipedia 6998869, "ngf-enc", aliases = {"Nete-Bisorio"}, -- Usher } m["ngf-okk"] = { "Ok", 7081687, "ngf", } m["ngf-omo"] = { "Omosan", -- not included in (Greater) Northern Adelbert by Glottolog, but a sister nil, "ngf-nad", } m["ngf-oro"] = { "Orokaivic", 7103752, -- considered a single Orokaiva language by Wikipedia "ngf-bin", aliases = {"Central Oro"}, -- Usher } m["ngf-pan"] = { "Paniai Lakes", 6035631, "ngf", aliases = {"Wissel Lakes", "Wissel Lakes-Kemandoga River"}, -- alternative names given by Wikipedia } m["ngf-pek"] = { "Peka", nil, "ngf-rai", aliases = {"Peka River"}, -- Usher? } m["ngf-pom"] = { "Pomoikan", nil, "ngf-sad", } m["ngf-rai"] = { "Rai Coast", 7283663, "ngf-mad", aliases = {"South Madang"}, -- Usher } m["ngf-sab"] = { "Sabakor", -- [[w:Sabakor languages]] redirects to [[w:Asmat–Kamrau languages]] nil, -- 55994614 is for [[Category:Kamrau Bay languages]], which exists on enwiki "ngf-ask", aliases = {"Kamrau Bay"}, -- Usher } m["ngf-sad"] = { "Southern Adelbert", 12633980, "ngf-ksa", aliases = {"South Adelbert", -- Glottolog "Southern Adelbert Range", -- Z'graggen (1980) "Sogeram and Tomul Rivers"}, -- Usher (2020)? } m["ngf-sak"] = { "Sau-Angal-Kewa", nil, "ngf-khu", aliases = {"Southern Highlands"}, -- Usher } m["ngf-san"] = { "Sankwep", nil, "ngf-huo", aliases = {"Nabak-Momolili", -- Pawley-Hammarström, "Southwest Huon", -- Usher }, } m["ngf-sbh"] = { "South Bird's Head", 7566330, "ngf", } m["ngf-sim"] = { "Simbu", nil, "ngf-chw", } m["ngf-sog"] = { "Sogeram", 86750419, "ngf-sad", aliases = {"Sogeram River", -- Usher "Wanang"}, } m["ngf-sop"] = { "Sopac", nil, "ngf-ehu", aliases = {"Momare-Migabac", -- Pawley-Hammarström, "Masaweng River", -- Usher }, } m["ngf-taa"] = { "Tainae-Akoye", nil, "ngf-ata", aliases = {"Akoye-Tainae"}, -- Usher } m["ngf-tai"] = { "Tairora", nil, "ngf-kai", aliases = {"Tairoric", -- Glottolog, "East Kainantu", -- Usher }, } m["ngf-tib"] = { "Tiboran", nil, "ngf-nad", aliases = {"Nuclear Tibor", -- Glottolog, excluding Wanambre/Mokati "Tiboran River", -- Usher (2020) "Tibor", -- Pick (2020) and Glottolog including Wanambre/Mokati } } m["ngf-tna"] = { "Tangko-Nakai", nil, "ngf-okk", aliases = {"Central Ok"}, -- Usher } m["ngf-uru"] = { "Uruwa", nil, "ngf-fin", aliases = {"Uruwa River"}, -- Usher? } m["ngf-usi"] = { "Utu-Silopi", nil, "ngf-han", aliases = {"Silopi-Utu"}, -- Usher } m["ngf-waa"] = { "Wantoat-Awara", -- not in Usher but Wantoat and Awara form a dialect chain nil, "ngf-wan", aliases = {"Awara-Wantoat"}, -- per Wikipedia } m["ngf-wah"] = { "Wahgi", -- [[w:Wahgi languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Wahgi Valley"}, -- Usher } m["ngf-wan"] = { "Wantoatic", nil, "ngf-fin", aliases = {"Wantoat", "Wantoat River", -- Usher? }, } m["ngf-war"] = { "Warup", 12645082, "ngf-fin", aliases = {"Warup River"}, -- Usher? } m["ngf-woj"] = { "Wojokesic", nil, "ngf-ang", aliases = {"Northeast Kratke Range"}, -- Usher } m["ngf-wok"] = { "West Ok", nil, "ngf-okk", aliases = {"Kwer-Kopkaka-Burumakok"}, -- Glottolog, Pawley-Hammarström } m["ngf-wso"] = { "West Sogeram", nil, "ngf-sog", aliases = {"Mand-Nend", -- Usher "Atan", -- Wurm following Z'graggen }, } m["ngf-yag"] = { "Yaganon", -- placed in Rai Coast by Glottolog and Pawley-Hammarström 35323986, "ngf-mad", aliases = {"Yaganon River"}, -- Usher } m["ngf-yal"] = { "Yali", -- considered a single language by Wikipedia 8047468, "ngf-ngn", aliases = {"Ngalik"}, -- Glottolog, Pawley-Hammarström } m["ngf-yar"] = { "Yareban", 16977672, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Musa River"}, } m["ngf-ynu"] = { "Yau-Nungon", 12953319, -- for the single Yau language in Wikipedia ([[w:Yau language (Trans–New Guinea)]]) "ngf-uru", } m["ngf-yup"] = { "Yupna", nil, "ngf-fin", aliases = {"Yupna River"}, -- Usher? } m["nic"] = { "Niger-Congo", 33838, aliases = {"Niger-Kordofanian"}, } m["nic-alu"] = { "Alumic", 4737355, "nic-plt", } m["nic-bas"] = { "Basa", 4866154, "nic-knj", } m["nic-bbe"] = { "Eastern Beboid", nil, "nic-beb", } m["nic-bco"] = { "Benue-Congo", 33253, "nic-vco", } m["nic-bcr"] = { "Bantoid-Cross", 806983, "nic-bco", } m["nic-bdn"] = { "Northern Bantoid", nil, "nic-bod", aliases = {"North Bantoid"}, } m["nic-bds"] = { "Southern Bantoid", 3183152, "nic-bod", aliases = {"Wide Bantu", "Bin"}, } m["nic-beb"] = { "Beboid", 813549, "nic-bds", } m["nic-ben"] = { "Bendi", 4887065, "nic-bcr", } m["nic-beo"] = { "Beromic", 4894642, "nic-plt", } m["nic-bod"] = { "Bantoid", 806992, "nic-bcr", } m["nic-buk"] = { "Buli-Koma", nil, "nic-ovo", } m["nic-bwa"] = { "Bwa", 12628562, "nic-gur", other_names = {"Bwamu", "Bomu"}, } m["nic-cde"] = { "Central Delta", 3813191, "nic-cri", } m["nic-cri"] = { "Cross River", 1141096, "nic-bcr", } m["nic-dag"] = { "Dagbani", nil, "nic-wov", } m["nic-dak"] = { "Dakoid", 1157745, "nic-bdn", } m["nic-dge"] = { "Escarpment Dogon", 5397128, "qfa-dgn", } m["nic-dgw"] = { "West Dogon", nil, "qfa-dgn", } m["nic-eko"] = { "Ekoid", 1323395, "nic-bds", } m["nic-eov"] = { "Eastern Oti-Volta", nil, "nic-ovo", aliases = {"Samba"}, } m["nic-fru"] = { "Furu", 5509783, "nic-bds", } m["nic-gne"] = { "Eastern Gurunsi", 12633072, "nic-gns", aliases = {"Eastern Grũsi"}, } m["nic-gnn"] = { "Northern Gurunsi", nil, "nic-gns", aliases = {"Northern Grũsi"}, } m["nic-gnw"] = { "Western Gurunsi", nil, "nic-gns", aliases = {"Western Grũsi"}, } m["nic-gns"] = { "Gurunsi", 721007, "nic-gur", aliases = {"Grũsi"}, } m["nic-gre"] = { "Eastern Grassfields", 5330160, "nic-grf", } m["nic-grf"] = { "Grassfields", 750932, "nic-bds", aliases = {"Grassfields Bantu", "Wide Grassfields"}, } m["nic-grm"] = { "Gurma", 30587833, "nic-ovo", } m["nic-grs"] = { "Southwest Grassfields", 7571285, "nic-grf", } m["nic-gur"] = { "Gur", 33536, "alv-sav", aliases = {"Voltaic"}, } m["nic-ief"] = { "Ibibio-Efik", 2743643, "nic-lcr", } m["nic-jer"] = { "Jera", nil, "nic-kne", } m["nic-jkn"] = { "Jukunoid", 1711622, "nic-pla", } m["nic-jrn"] = { "Jarawan", 1683430, "nic-mba", } m["nic-jrw"] = { "Jarawa", 35423, "nic-jrn", } m["nic-kam"] = { "Kambari", 6356294, "nic-knj", } m["nic-ktl"] = { "Katloid", nil, "nic", } m["nic-kau"] = { "Kauru", nil, "nic-kne", } m["nic-kmk"] = { "Kamuku", 6359821, "nic-knj", } m["nic-kne"] = { "East Kainji", 5328687, "nic-knj", } m["nic-knj"] = { "Kainji", 681495, "nic-pla", } m["nic-knn"] = { "Northwest Kainji", 7060098, "nic-knj", } m["nic-ktl"] = { "Katloid", 6377681, "nic", aliases = {"Katla", "Katla-Tima"}, } m["nic-lcr"] = { "Lower Cross River", 3813193, "nic-cri", } m["nic-mam"] = { "Mamfe", 2005898, "nic-bds", aliases = {"Nyang"}, } m["nic-mba"] = { "Mbam", 687826, "nic-bds", } m["nic-mbc"] = { "Mba", 6799561, "nic-ubg", } m["nic-mbw"] = { "West Mbam", nil, "nic-mba", } m["nic-mmb"] = { "Mambiloid", 1888151, other_names = {"North Bantoid"}, -- per Wikipedia, North Bantoid is the parent family "nic-bdn", } m["nic-mom"] = { "Momo", 6897393, "nic-grf", } m["nic-mre"] = { "Moré", nil, "nic-wov", } m["nic-ngd"] = { "Ngbandi", 36439, "nic-ubg", } m["nic-nge"] = { "Ngemba", 7022271, "nic-gre", } m["nic-ngk"] = { "Ngbaka", 3217499, "nic-ubg", } m["nic-nin"] = { "Ninzic", 7039282, "nic-plt", } m["nic-nka"] = { "Nkambe", 7042520, "nic-gre", } m["nic-nkb"] = { "Baka", nil, "nic-nkw", } m["nic-nke"] = { "Eastern Ngbaka", nil, "nic-ngk", } m["nic-nkg"] = { "Gbanziri", nil, "nic-nkw", } m["nic-nkk"] = { "Kpala", nil, "nic-nkw", } m["nic-nkm"] = { "Mbaka", nil, "nic-nkw", } m["nic-nkw"] = { "Western Ngbaka", nil, "nic-ngk", } m["nic-npd"] = { "North Plateau Dogon", nil, "qfa-dgn", } m["nic-nun"] = { "Nun", 13654297, "nic-gre", } m["nic-nwa"] = { "Nanga-Walo", nil, "qfa-dgn", } m["nic-ogo"] = { "Ogoni", 2350726, "nic-cri", aliases = {"Ogonoid"}, } m["nic-ovo"] = { "Oti-Volta", 1157178, "nic-gur", } m["nic-pla"] = { "Platoid", 453244, "nic-bco", aliases = {"Central Nigerian"}, } m["nic-plc"] = { "Central Plateau", 5061668, "nic-plt", } m["nic-pld"] = { "Plains Dogon", nil, "qfa-dgn", } m["nic-ple"] = { "East Plateau", 5329154, "nic-plt", } m["nic-pls"] = { "South Plateau", 7568236, "nic-plt", aliases = {"Jilic-Eggonic"}, } m["nic-plt"] = { "Plateau", 1267471, "nic-pla", } m["nic-ras"] = { "Rashad", 3401986, "nic", } m["nic-rnc"] = { "Central Ring", nil, "nic-rng", } m["nic-rng"] = { "Ring", 2269051, "nic-grf", aliases = {"Ring Road"}, } m["nic-rnn"] = { "Northern Ring", nil, "nic-rng", } m["nic-rnw"] = { "Western Ring", nil, "nic-rng", } m["nic-ser"] = { "Sere", 7453058, "nic-ubg", } m["nic-shi"] = { "Shiroro", 7498953, "nic-knj", aliases = {"Pongu"}, } m["nic-sis"] = { "Sisaala", 36532, "nic-gnw", } m["nic-tar"] = { "Tarokoid", 2394472, "nic-plt", } m["nic-tiv"] = { "Tivoid", 752377, "nic-bds", } m["nic-tvc"] = { "Central Tivoid", nil, "nic-tiv", } m["nic-tvn"] = { "Northern Tivoid", nil, "nic-tiv", } m["nic-ubg"] = { "Ubangian", 33932, "nic-vco", -- or none } m["nic-uce"] = { "East-West Upper Cross River", nil, "nic-ucr", } m["nic-ucn"] = { "North-South Upper Cross River", nil, "nic-ucr", } m["nic-ucr"] = { "Upper Cross River", 4108624, "nic-cri", aliases = {"Upper Cross"}, } m["nic-vco"] = { "Volta-Congo", 37228, "alv", } m["nic-wov"] = { "Western Oti-Volta", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nic-ykb"] = { "Yukubenic", 16909196, "nic-plt", aliases = {"Oohum"}, } m["nic-ymb"] = { "Yambasa", nil, "nic-mba", } m["nic-yon"] = { "Yom-Nawdm", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["njo"] = { "Ao", 28433, "sit-aao", aliases = {"Ao Naga"}, } m["nub"] = { "Nubian", 1517194, "sdv-nes", } m["nub-hil"] = { "Hill Nubian", 5762211, "nub", aliases = {"Kordofan Nubian"}, } m["omq"] = { "Oto-Manguean", 33669, pseudo_families = "cai", } m["omq-cha"] = { "Chatino", 35111, "omq-zap", } m["omq-chi"] = { "Chinantecan", 35828, "omq", } m["omq-cui"] = { "Cuicatec", 616024, "omq-mix", } m["omq-maz"] = { "Mazatec", 36230, "omq", aliases = {"Mazatecan"}, } m["omq-mix"] = { "Mixtecan", 21083066, "omq", } m["omq-mxt"] = { "Mixtec", 36363, "omq-mix", } m["omq-otp"] = { "Oto-Pamean", 1270220, "omq", } m["omq-pop"] = { "Popolocan", 5132273, "omq", } m["omq-tri"] = { "Triqui", 780200, "omq-mix", aliases = {"Trique"}, } m["omq-zap"] = { "Zapotecan", 8066463, "omq", } m["omq-zpc"] = { "Zapotec", 13214, "omq-zap", } m["omv"] = { "Omotic", 33860, "afa", } m["omv-aro"] = { "Aroid", 3699526, "omv", aliases = {"Ari-Banna", "South Omotic", "Somotic"}, } m["omv-diz"] = { "Dizoid", 430251, "omv", aliases = {"Maji", "Majoid"}, } m["omv-eom"] = { "East Ometo", 20527288, "omv-ome", } m["omv-gon"] = { "Gonga", 4143043, "omv", aliases = {"Kefoid"}, } m["omv-mao"] = { "Mao", 1351495, "omv", } m["omv-nom"] = { "North Ometo", nil, "omv-ome", } m["omv-ome"] = { "Ometo", 36310, "omv", } m["oto"] = { "Otomian", 130372545, "omq-otp", } m["oto-otm"] = { "Otomi", 36355, "oto", } m["paa"] = { "Papuan", 236425, "qfa-not", } m["paa-aia"] = { "Aian", 4767739, -- Annaberg languages "paa-ram", aliases = {"Middle Ramu", -- Foley (with Rao), "Annaberg", -- with Rao "Aram-Aren", -- Usher }, } m["paa-alp"] = { "Alor-Pantar", 3502429, "paa-tap", } m["paa-amu"] = { "Amto-Musan", 480281, aliases = {"Samaia River"}, } m["paa-ani"] = { "Anim", 55603991, aliases = {"Fly River"}, } m["paa-ara"] = { "Arapesh", 4784223, "paa-koa", aliases = {"Arapeshan"}, -- Foley } m["paa-arf"] = { "Arafundi", 4783702, } m["paa-ata"] = { "Ataitan", 4812652, "paa-ram", aliases = {"Tangu", -- Foley "Tanggu", -- alternative name given by Wikipedia "Moam River", -- Usher }, } m["paa-baa"] = { "Bayono-Awbono", 2424781, } m["paa-bai"] = { "Baining", 748487, aliases = {"East New Britain"}, } m["paa-baw"] = { "Bosngun-Awar", nil, "paa-ott", aliases = {"East Ramu Coast", -- Usher "Bosman-Awar", -- Wikipedia }, } m["paa-bew"] = { "Bewani", -- [[w:Bewani languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 16113460, "paa-bor", aliases = {"Poal River"}, -- Usher } m["paa-boa"] = { "Boazi", 48803717, "paa-mby", aliases = {"Lake Murray"}, -- Usher } m["paa-bor"] = { "Border", 1752158, aliases = {"Upper Tami", "Tami River-Bewani Range", -- Usher }, } m["paa-bul"] = { "Bulaka River", 4987195, aliases = {"Yelmek-Maklew", "Jabga"}, -- Yelmek-Maklew in Evans (2018) and Gregor (2021) } m["paa-bvi"] = { "Betaf-Vitou", -- Glottolog nil, "paa-tor", aliases = {"Vitou-Betaf", -- Wikipedia "Fitou-Tena", -- Usher "Manirem", }, } m["paa-clp"] = { "Central Lakes Plain", -- [[w:Central Lakes Plain languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86780132 is for the corresponding category, which exists in enwiki "paa-lpl", aliases = {"East Tariku", -- Glottolog "Central Lakes Plains", -- Usher }, } m["paa-dtu"] = { "Doso-Turumsa", 16917784, -- possibly related to East Strickland languages aliases = {"Soari River"}, -- Usher's name } m["paa-ebh"] = { "East Bird's Head", 338064, aliases = {"Mantion-Meax", "Mantion-Meyah", -- Mantion-Meax is Wikipedia's term "Southeast Bird's Head", -- Usher (2020) }, } m["paa-eel"] = { "Eastern Eleman", nil, "paa-ele", aliases = {"East Eleman"}, } m["paa-egb"] = { "East Geelvink Bay", 1497678, aliases = {"Geelvink Bay", "East Cenderawasih"}, -- Geelvink Bay per Glottolog } m["paa-eke"] = { "East Keram", nil, "paa-ker", } m["paa-ele"] = { "Eleman", 3034298, aliases = {"Kerema Bay"}, } m["paa-elp"] = { "East Lakes Plain", -- [[w:East Lakes Plain languages]] redirects to [[w:Lakes Plain languages]]; but Croatian Wikipedia has an entry 12633078, "paa-lpl", aliases = {"East Lakes Plains"}, -- Usher } m["paa-epw"] = { "Eastern Pauwasi", 16115496, aliases = {"East Pauwasi"}, } m["paa-etf"] = { "Eastern Trans-Fly", 5330530, aliases = {"Oriomo"}, -- in increasing recent use, probably originating in Evans (2018) } m["paa-eti"] = { "East Timor", 15496066, "paa-tap", aliases = {"Oirata-Makasae", -- Wikipedia's name "Eastern Timor", -- alternative name given by Wikipedia "Fataluku-Makasai", "Oirata-Makasai", -- alternative names given by Wikidata }, } m["paa-fas"] = { "Fas", 3502658, aliases = {"Baibai-Fas"}, -- Glottolog's name } m["paa-flp"] = { "Far West Lakes Plain", -- [[w:Wapoga River languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86808337 is for the corresponding Wapoga languages category, which exists in enwiki "paa-lpl", aliases = {"Rasawa", -- Clouse (1997) "Wapoga River", -- Usher, including Kehu/Keuw (unclassified by others) }, } m["paa-gkw"] = { "Greater Kwerba", 12635134, aliases = {"West Foja Range", -- Usher "Kwerbic", -- Wikipedia "Kwerba", -- Foley (2018) }, } m["paa-gto"] = { "Galela-Tobelo", nil, "paa-nnh", aliases = {"Mainland North Halmaheran", -- Glottolog "Mainland North Halmahera", "Northeast Halmahera", -- alternative names "Northeast Halmaheran", -- Wikipedia, from Verhoeve 1988 }, } m["paa-hya"] = { "Heyo-Yahang", nil, "paa-mam", aliases = {"Yahang-Heyo"}, -- Wikipedia's name } m["paa-ing"] = { "Inland Gulf", 6034783, "paa-ani", aliases = {"Inland Gulf of Papua"}, -- Glottolog } m["paa-isk"] = { "Inner Sko", 65043889, "paa-sko", aliases = {"Skouic", -- Glottolog "West Vanimo Coast", -- Usher "Western Skou", -- Wikipedia "Inner Skou", "Nuclear Skou", -- alternative names given by Wikipedia }, } m["paa-iwa"] = { "Iwam", 15147853, "paa-sep", } m["paa-kae"] = { "Kamula-Elevala", 130390498, -- often placed in TNG aliases = {"Kamula-Elevala River"}, } m["paa-kan"] = { "Kanum", -- removed from Tonda by Glottolog nil, "paa-ton", } m["paa-kay"] = { "Kayagaric", 7566330, aliases = {"Kayagar", -- formerly common "Cook River"}, -- per Usher (2020) } m["paa-ker"] = { "Keram", 48768173, -- often grouped within or coordinate with the Ramu languages aliases = {"Keram River"}, } m["paa-kiw"] = { "Kiwaian", 338449, aliases = {"Kiwai"}, -- formerly common, still sees some use } m["paa-kko"] = { "Kaure-Kosare", -- rejected by Pawley-Hammarström but accepted by Glottolog, Foley (2018) and Usher (2020) 48767891, aliases = {"Nawa River"}, -- Usher's term } m["paa-koa"] = { "Kombio-Arapesh", 16115049, "paa-trr", aliases = {"Kombio-Arapeshan", -- Laycock, who includes Wom "Kombio-Arapesh-Urat", -- Glottolog, including Urat }, } m["paa-kol"] = { "Kolopom", 6427807, } m["paa-kom"] = { "Kombio", 65044238, "paa-koa", aliases = {"Kombian", -- Laycock "Kombio-Yambes", -- Glottolog }, } m["paa-kun"] = { "Kunimaipan", 134973258, aliases = {"Northwest Wharton Range"}, -- per Usher (2020) -- often considered a subfamily of Goilalan } m["paa-kwa"] = { "Kwalean", 6450053, aliases = {"Humene-Uare"}, } m["paa-kwe"] = { "Kwerba proper", 12635134, "paa-gkw", aliases = {"Kwerba", -- Usher "Kwerbaic", -- Glottolog }, } m["paa-kwo"] = { "Kwomtari", 2075415, aliases = {"Kwomtari-Nai"}, -- Senu River is a larger unproven proposal } m["paa-lla"] = { "Loloda-Laba", -- a single language in Glottolog (Loloda-Laba) and Wikipedia (Loloda) 11732388, -- for the Loloda language "paa-gto", aliases = {"Loloda"}, -- Wikipedia's name } m["paa-lma"] = { "Left May", 614468, aliases = {"Arai River"}, -- per Usher (2020) -- Sometimes in a putative Arai-Samaia family along with Amto-Musan and the Pyu language } m["paa-lmu"] = { "Lepki-Murkim", -- Kembra accepted by Glottolog and Usher; not by Foley (2020) but does not exclude the possibility -- of a relationship 85776285, -- independent family per Glottolog, part of South Pauwasi River family (under Pauwasi) per Usher (2020) aliases = {"Lepki-Murkim-Kembra"}, -- Glottolog } m["paa-lpl"] = { "Lakes Plain", 6478969, aliases = {"Lakes Plains"}, } m["paa-lra"] = { "Lower Ramu", 65089469, "paa-ram", aliases = {"Ottilien-Misegian"}, -- alternative name given by Wikipedia } m["paa-lse"] = { "Lower Sepik", 7061700, aliases = {"Nor-Pondo"}, } m["paa-mai"] = { "Mairasi", 6736896, aliases = {"Mairasic"}, -- per Glottolog } m["paa-mal"] = { "Mailuan", 6735839, aliases = {"Cloudy Bay"}, } m["paa-mam"] = { "Maimai", -- Foley's Maimai is expanded 53679325, -- this is the code for the expanded Maimai with 6 languages, as opposed to the 3 in "Nuclear Maimai" "paa-trr", aliases = {"Nuclear Maimai", -- Glottolog's name "Maimai proper", -- Wikipedia's name }, } m["paa-man"] = { "Manubaran", 6752335, aliases = {"Mount Brown"}, } m["paa-mar"] = { "Marienberg", 1570589, "paa-trr", aliases = {"Marienberg Hills"}, -- Usher } m["paa-may"] = { "Maybratic", 4830892, -- the code for the Maybrat language in Wikipedia, which subsumes the two languages of this family -- putatively included in West Papuan but generally considered an isolated family aliases = {"Maybrat-Karon"}, } m["paa-mbi"] = { "Mbaham-Iha", 85784512, "qfa-dis", -- Papuan languages; Glottolog groups Karas (Kalamang) with Mbaham-Iha into a (mainland) West Bomberai -- family and stops there; Wikipedia, following Usher and Schapper (2022), groups Karas, Mbaham-Iha -- and the large Timor-Alor-Pantar family into a (Greater) West Bomberai family, saying that Karas is no -- closer to Mbaham-Iha than to Timor-Alor-Pantar. aliases = {"Mbahaam-Iha", -- used by Wikidata "Nuclear West Bomberai", -- Glottolog's name }, } m["paa-mby"] = { "Marind-Boazi-Yaqay", 3217484, "paa-ani", aliases = {"Marind-Boazi-Yaqai", -- Glottolog "Marind-Yakhai", -- Usher, without Boazi "Marind-Yaqai", -- Wikidata "Marind", -- alternative name given by Wikipedia "Marind-Arandai", -- alternative name given by Spanish Wikipedia }, } m["paa-mmu"] = { "Mandi-Muniwara", nil, "paa-mar", aliases = {"West Marienberg Hills"}, -- Usher } m["paa-mon"] = { "Monumbo", -- per Glottolog: "No evidence for the Bogia (Monumbo) languages being related to other Torricelli languages was ever presented" 16928417, aliases = {"Bogia", -- Glottolog "Bogia Bay", -- Usher (2020) }, } m["paa-mri"] = { "Marindic", -- [[w:Marindic languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Marind"}, -- Usher; a single language } m["paa-nam"] = { "Nambu", 6961418, "paa-yam", aliases = {"East Morehead River"}, -- Usher } m["paa-nbo"] = { "North Bougainville", 749496, } m["paa-ndu"] = { "Ndu", 3217498, "paa-sep", -- Not accepted by Glottolog aliases = {"Ndu-Nggala"}, -- Usher } m["paa-ngk"] = { "Ngkolmpu", -- considered a single language by Wikipedia 5908646, "paa-kan", aliases = {"Ngkantr", -- Glottolog "Ngkolmpu Kanum", -- Wikipedia "Ngkontar", -- alternative name given by Wikipedia "Kanum", -- used by Wikidata }, } m["paa-nha"] = { "North Halmahera", 3217358, -- possibly in a proposed West Papuan family or an independent family } m["paa-nim"] = { "Nimboran", 12638426, aliases = {"Nimboranic", -- per Glottolog "Grime River", -- per Usher (2020) } } m["paa-nnd"] = { "Nuclear Ndu", nil, "paa-ndu", aliases = {"Ndu", -- Usher, with Boiken/Boikin "Ndu proper", -- Wikipedia }, } m["paa-nnh"] = { "Northern North Halmahera", nil, "paa-nha", aliases = {"Northern North Halmaheran", -- Glottolog "Halmahera", -- Usher "Core Halmaheran", -- Wikipedia }, } m["paa-nto"] = { "Namla-Tofanma", 16918187, -- independent family per Glottolog and Foley (2018), part of West Pauwasi family (under Pauwasi) per Usher (2020) } m["paa-ott"] = { "Ottilien", 7109477, "paa-lra", aliases = {"Ramu Coast", -- Usher "Watam-Awar-Gamay", -- alternative name given by Wikipedia }, } m["paa-pah"] = { "Pahoturi River", 17049141, aliases = {"Pahoturi"}, -- per Glottolog } m["paa-pal"] = { "Palei", -- Laycock adds Agi and Nabi/Nambi(-Metan) 65089113, "paa-wpa", aliases = {"Nuclear Palai"}, } m["paa-pia"] = { "Piawi", -- per Wikipedia, grouped with Arafundi languages to form Upper Yuat, which is a sister to Madang 7190400, aliases = {"Schraeder Range", -- Usher? "Waibuk"}, } m["paa-pio"] = { "Piore River", 65043152, "paa-sko", aliases = {"Barupu Lagoon", -- Glottolog "Lagoon", -- alternative name given by Wikipedia }, } m["paa-por"] = { "Porapora", -- Foley includes Ambakich (which we, Glottolog, and Usher treat as Keram) 65044258, "paa-ram", aliases = {"Agoan", -- Glottolog "Porapora River", -- Usher "core Grass", -- alternative name given by Wikipedia }, } m["paa-ram"] = { "Ramu", 3442808, aliases = {"Ramu River"}, -- per Usher (2020) } m["paa-rsa"] = { "Rasawa-Saponi", -- [[w:Rasawa-Saponi languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q9859418 is for the coresponding category, which exists in the Piedmontese Wikipedia (?!) "paa-flp", aliases = {"Rombak River"}, -- Usher } m["paa-rub"] = { "Ruboni", 6875319, "paa-lra", aliases = {"Misegian", -- Wikipedia's name "Mikarew", -- alternative name given by Wikipedia "Ruboni Range"}, -- Usher } m["paa-saa"] = { "Samarokena-Airoran", 96417699, "paa-gkw", aliases = {"Apauwar Coast"}, -- Usher } m["paa-sah"] = { "Sahu", nil, "paa-nnh", } m["paa-sbo"] = { "South Bougainville", 3217380, } m["paa-sen"] = { "Sentani", 17044584, -- no consensus on higher affiliations, if any aliases = {"Sentanic", "Demta-Sentani", "Demta-Lake Sentani"}, -- Sentanic per Glottolog, Demta-Sentani per Wikipedia } m["paa-sep"] = { "Sepik", 3508772, } m["paa-shi"] = { "Serra Hills", 65043154, "paa-sko", } m["paa-sko"] = { "Sko", 953509, aliases = {"Skou"}, } m["paa-sng"] = { "Senagi", 2066550, } m["paa-taa"] = { "Taikat-Awyi", -- [[w:Taikat languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12643265, "paa-bor", aliases = {"Taikat", -- Foley "Upper Tami River", -- Usher }, } m["paa-tam"] = { "Tamolan", 7681634, "paa-ram", aliases = {"Guam River"}, -- Usher } m["paa-tap"] = { "Timor-Alor-Pantar", 16590002, } m["paa-teb"] = { "Teberan", 7692052, -- Often grouped with Trans-New Guinea, but per Pawley-Hammarström (2018), it has "weaker or disputed claims to membership in TNG". aliases = {"Dadibi-Folopa"}, } m["paa-tir"] = { "Tirio", 7809225, "paa-ani", aliases = {"Nuclear Lower Fly", -- Pawley-Hammarström ("Lower Fly" includes Abom) "Nuclear Tirio", -- Glottolog ("Tirio" includes Abom) "Lower Fly River", -- Usher (without Abom) }, } m["paa-tki"] = { "Turama-Kikori", 7853680, aliases = {"Turama-Kikorian", "Rumu-Omati River"}, } m["paa-ton"] = { "Tonda", 8581005, "paa-yam", aliases = {"West Morehead River"}, -- Usher } m["paa-too"] = { "Tor-Orya", 16590099, aliases = {"Orya-Tor"}, } m["paa-tor"] = { "Tor", -- [[w:Tor languages]] redirects to [[w:Orya–Tor languages]] nil, "paa-too", } m["paa-trr"] = { "Torricelli", 1333831, } m["paa-tti"] = { "Ternate-Tidore", nil, "paa-nnh", } m["paa-wal"] = { "Walio", 16919872, -- Often placed in Sepik (e.g. by Laycock and Z'graggen (1975)), but not by Foley (2018), and not accepted by Glottolog. aliases = {"Walioic", -- Glottolog "Central Leonhard Schultze River", }, } m["paa-wap"] = { "Wapei", -- Glottolog includes Nabi/Nambi(-Metan) in Wapeic 65089115, "paa-wpa", aliases = {"Wapeic"}, -- Glottolog } m["paa-war"] = { "Waris", -- [[w:Waris languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12645076, "paa-bor", aliases = {"Warisic", -- Glottolog "Bapi River", -- Usher (without Manem or Senggi) }, } m["paa-wbh"] = { "West Bird's Head", 5330530, -- Kuwani is sometimes included; probably related to North Halmahera languages. } m["paa-wel"] = { "Western Eleman", nil, "paa-ele", aliases = {"West Eleman"}, } m["paa-wig"] = { "West Inland Gulf", nil, "paa-ing", aliases = {"West Inland Gulf of Papua"}, -- Glottolog } m["paa-wke"] = { "West Keram", nil, "paa-ker", aliases = {"Koam", "Mongol-Langam", "Ulmapo"}, -- Koam used by Foley, Ulmapo used by Glottolog } m["paa-wko"] = { "Wára-Kómnzo", -- since we split out Kómnzo as a separate language 11732474, -- for the Wara language "paa-ton", aliases = {"Anta-Komnzo-Wára-Wérè-Kémä", -- Glottolog's name "Wára", "Wara", -- Wikipedia }, } m["paa-wlp"] = { "West Lakes Plain", -- [[w:Tariku languages]] redirects to [[w:Lakes Plain languages]] 47007503, -- actually for "Tariku languages", which per Wikipedia covers Fayu, Kirikiri, Iau and Tause "paa-lpl", aliases = {"West Tariku", -- Glottolog "West Lakes Plains"}, -- Usher, with Edopi/Iau } m["paa-wpa"] = { "Wapei-Palei", 65043156, "paa-trr", } m["paa-wpw"] = { -- paa-wpa already used by Wapei-Palei "Western Pauwasi", -- 2 langs per Glottolog and Pawley-Hammarström; Usher also includes Namla-Tofanma and Usku 85815062, aliases = {"West Pauwasi", -- Wikipedia, Usher "Tebi-Towe", "Dubu-Towei"}, } m["paa-yam"] = { "Yam", 15062272, aliases = {"Morehead and Upper Maro River", "Morehead River", -- Usher }, } m["paa-yaq"] = { "Yaqayic", -- [[w:Yaqai languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Yakhai-Warkay"}, -- Usher } m["paa-ysa"] = { "Yawa-Saweru", 3217545, aliases = {"Yawa", "Yawan", "Yapen"}, } m["paa-yua"] = { "Yuat", 8060096, } m["phi"] = { "Philippine", 947858, "poz", } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polynesian", 143158, "map", } m["poz-aay"] = { "Admiralty Islands", 2701306, "poz-oce", } m["poz-bnn"] = { "North Bornean", 1427907, "poz", } m["poz-bre"] = { "East Barito", 2701314, "poz", } m["poz-brw"] = { "West Barito", 2761679, "poz", } m["poz-bss"] = { "Bali-Sasak-Sumbawa", 3396043, "poz-msa", } m["poz-btk"] = { "Bungku-Tolaki", 3217381, "poz-clb", } m["poz-cet"] = { "Central-Eastern Malayo-Polynesian", 2269883, "poz", } m["poz-clb"] = { "Celebic", 1078041, "poz", } m["poz-cln"] = { "New Caledonian", 3091221, "poz-ocs", } m["poz-cma"] = { "Central Maluku", 3217479, "poz-cet", } m["poz-hce"] = { "Halmahera-Cenderawasih", 2526616, "pqe", } m["poz-kal"] = { "Kaili-Pamona", 3217465, "poz-clb", } m["poz-lgx"] = { "Lampungic", 49215, "poz", } m["poz-mcm"] = { "Malayo-Chamic", nil, "poz-msa", } m["poz-mic"] = { "Micronesian", 420591, "poz-occ", } m["poz-mly"] = { "Malayic", 662628, "poz-mcm", } m["poz-msa"] = { "Malayo-Sumbawan", 1363818, "poz", } m["poz-mun"] = { "Muna-Buton", 3037924, "poz-clb", } m["poz-nws"] = { "Northwest Sumatran", 2071308, "poz", } m["poz-occ"] = { "Central-Eastern Oceanic", 2068435, "poz-oce", } m["poz-oce"] = { "Oceanic", 324457, "pqe", } m["poz-ocs"] = { "Southern Oceanic", 3039118, "poz-occ", } m["poz-ocw"] = { "Western Oceanic", 2701282, "poz-oce", } m["poz-pcc"] = { "Central Pacific", 3130237, "poz-occ", } m["poz-pep"] = { "Eastern Polynesian", 390979, "poz-pnp", } m["poz-pnp"] = { "Nuclear Polynesian", 743851, "poz-pol", } m["poz-pol"] = { "Polynesian", 390979, "poz-pcc", } m["poz-san"] = { "Sabahan", 3217517, "poz-bnn", } m["poz-sbj"] = { "Sama-Bajaw", 2160409, "poz", } m["poz-slb"] = { "Saluan-Banggai", 3217519, "poz-clb", } m["poz-sls"] = { "Southeast Solomonic", 3119671, "poz-occ", } m["poz-ssw"] = { "South Sulawesi", 2778190, "poz", } m["poz-stm"] = { "St. Matthias", 6484143, "poz-oce", aliases = {"St Matthias"}, } m["poz-swa"] = { "North Sarawak", 538569, "poz-bnn", aliases = {"North Sarawakan"}, } m["poz-tem"] = { "Temotu", 3075769, "poz-oce", } m["poz-tim"] = { "Timoric", 7806987, "poz-cet", } m["poz-ton"] = { "Tongic", 3397263, "poz-pol", } m["poz-tot"] = { "Tomini-Tolitoli", 3217541, "poz-clb", } m["poz-vnc"] = { "Central Vanuatu", 5061988, "poz-ocs", } m["poz-vnn"] = { "North Vanuatu", 85789650, "poz-ocs", } m["poz-vns"] = { "South Vanuatu", 3070173, "poz-ocs", } m["poz-wot"] = { "Wotu-Wolio", 1041317, "poz-clb", aliases = {"Island Kaili-Wolio"}, -- Glottolog } m["pqe"] = { "Eastern Malayo-Polynesian", 2269883, "poz-cet", } m["qfa-adc"] = { "Central Great Andamanese", nil, "qfa-adm", } m["qfa-adm"] = { "Great Andamanese", 3515103, } m["qfa-adn"] = { "Northern Great Andamanese", nil, "qfa-adm", } m["qfa-ads"] = { "Southern Great Andamanese", nil, "qfa-adm", } m["qfa-ain"] = { "Ainuic", 50111972, aliases = {"Ainu"}, } m["qfa-bej"] = { "Be-Jizhao", nil, "qfa-bet", } m["qfa-bet"] = { "Be-Tai", 12627719, "qfa-tak", aliases = {"Tai-Be", "Daic-Beic", "Beic-Daic"}, } m["qfa-buy"] = { "Buyang", 1109927, "qfa-kra", } m["qfa-cka"] = { "Chukotko-Kamchatkan", 33255, } m["qfa-cre"] = { "creole", 33289, "crp", } m["qfa-ckn"] = { "Chukotkan", 2606732, "qfa-cka", } m["qfa-cnt"] = { "contact", 133253514, "qfa-not", } m["qfa-dis"] = { -- Languages that are not unclassifiable (qfa-unc) but where there is no consensus on classification. Usually -- this is because the languages are divergent and it's disputed whether they are isolates or distantly related -- to other languages. "disputed affiliation", nil, "qfa-not", categoryName = "Languages of disputed affiliation", } m["qfa-dgn"] = { "Dogon", 1234776, "nic", } m["qfa-dny"] = { "Dene-Yeniseian", 21103, aliases = {"Dené-Yeniseian"}, } m["qfa-hur"] = { "Hurro-Urartian", 1144159, } m["qfa-iso"] = { "isolate", 33648, "qfa-not", categoryName = "Language isolates", } m["qfa-jew"] = { "Jewish", 615948, "qfa-not", } m["qfa-kad"] = { "Kadu", -- considered either Nilo-Saharan or independent/none 1720989, } m["qfa-kms"] = { "Kam-Sui", 1023641, "qfa-tak", } m["qfa-kor"] = { "Koreanic", 11263525, } m["qfa-kra"] = { "Kra", 1022087, "qfa-tak", } m["qfa-lic"] = { "Hlai", 1023648, "qfa-tak", aliases = {"Hlaic"}, } m["qfa-mch"] = { -- used in both N and S America "Macro-Chibchan", 3438062, } m["qfa-mix"] = { "mixed", 33694, "qfa-cnt", } m["qfa-not"] = { "not a family", nil, "qfa-not", } m["qfa-onb"] = { "Be", nil, "qfa-bej", aliases = {"Ong-Be", "Beic"}, } m["qfa-ong"] = { "Ongan", 2090575, aliases = {"Angan", "South Andamanese", "Jarawa-Onge"}, } m["qfa-pid"] = { "pidgin", 33831, "crp", } m["qfa-sub"] = { "substrate", 20730913, "qfa-not", } m["qfa-tak"] = { "Kra-Dai", 34171, aliases = {"Tai-Kadai", "Kadai"}, } m["qfa-tyn"] = { "Tyrsenian", 1344038, } m["qfa-unc"] = { -- This corresponds to languages normally called "unclassified", i.e. there is insufficient data or research to -- classify them, whereas our [[:Category:Unclassified languages]] is just languages that no Wiktionary editor -- has classified yet (the family code in the language data is missing). "unclassifiable", 33956, "qfa-not", } m["qfa-xgs"] = { "Serbi-Mongolic", 108887939, } m["qfa-xgx"] = { "Para-Mongolic", 107619002, "qfa-xgs", } m["qfa-yen"] = { "Yeniseian", 27639, "qfa-dny", aliases = {"Yeniseic", "Yenisei-Ostyak"}, } m["qfa-yke"] = { "Ketic", nil, "qfa-yen", } m["qfa-yko"] = { "Kottic", nil, "qfa-yen", } m["qfa-yrn"] = { "Arinic", nil, "qfa-yen", } m["qfa-ypm"] = { "Pumpokolic", nil, "qfa-yen", } m["qfa-yuk"] = { "Yukaghir", 34164, aliases = {"Yukagir", "Jukagir"}, } m["qwe"] = { "Quechuan", 5218, pseudo_families = "sai", } m["raj"] = { "Rajasthani", 13196, "inc-wes", protoLanguage = "inc-ogu", } m["roa"] = { "Romance", 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Castilian", 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", } m["roa-dal"] = { "Dalmatian Romance", 97646077, "roa-itd", } m["roa-eas"] = { "Eastern Romance", 147576, "roa", } m["roa-emr"] = { "Emilian-Romagnol", 242648, "roa-git", } m["roa-gap"] = { "Galician-Portuguese", 9080204, "roa-ibe", aliases = {"Galician Romance", "Galaic-Portuguese"}, protoLanguage = "roa-opt", } m["roa-gar"] = { "Gallo-Romance", 500394, "roa-wes", } m["roa-itd"] = { "Italo-Dalmatian", 3313381, "roa-iwr", aliases = {"Central Romance"} } m["roa-itr"] = { "Italo-Romance", 3356483, "roa-itd", } m["roa-iwr"] = { "Italo-Western Romance", 112608, "roa", aliases = {"Italo-Western"}, } m["roa-git"] = { "Gallo-Italic", 516074, "roa-gar", aliases = {"Gallo-Italian", "Gallo-Cisalpine", "Cisalpine"}, } m["roa-grh"] = { "Gallo-Rhaetian", 97646466, "roa-gar", } m["roa-ibe"] = { "Ibero-Romance", 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"} } m["roa-nar"] = { "Navarro-Aragonese", 133252927, "roa-ibe", protoLanguage = "roa-ona", } m["roa-oil"] = { "Oïl", 37351, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, protoLanguage = "fro", } m["roa-ocr"] = { "Occitano-Romance", 599958, "roa-gar", aliases = {"Gallo-Narbonnese", "East Iberian", "Eastern Iberian"}, } m["roa-rhe"] = { "Rhaeto-Romance", 515593, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, } m["roa-sou"] = { "Southern Romance", 145345, "roa", } m["roa-wes"] = { "Western Romance", 2714388, "roa-iwr", } m["sai"] = { "South American Indigenous", 54801970, "qfa-not", } --[=[ Exceptional language and family codes for South American Indigenous/Indian languages can use the prefix "sai-", though "sai" is not a proper family (only a pseudo-family). ]=]-- m["sai-ara"] = { "Araucanian", 626630, } m["sai-aym"] = { "Aymaran", 33010, } m["sai-bar"] = { "Barbacoan", 807304, aliases = {"Barbakoan"}, } m["sai-bor"] = { "Boran", 5371776, } m["sai-cah"] = { "Cahuapanan", 1025793, } m["sai-car"] = { "Cariban", 33090, aliases = {"Carib"}, } m["sai-cer"] = { "Cerrado", 98078151, "sai-jee", aliases = {"Amazonian Jê"}, } m["sai-chc"] = { "Chocoan", 1075616, aliases = {"Choco", "Chocó"}, } m["sai-cho"] = { "Chonan", 33019, aliases = {"Chon"}, } m["sai-cje"] = { "Central Jê", 18010843, "sai-cer", aliases = {"Akuwẽ"}, } m["sai-cpc"] = { "Chapacuran", 1062626, } m["sai-crn"] = { "Charruan", 3112423, aliases = {"Charrúan"}, } m["sai-ctc"] = { "Catacaoan", 5051139, } m["sai-guc"] = { "Guaicuruan", 1974973, "sai-mgc", aliases = {"Guaicurú", "Guaycuruana", "Guaikurú", "Guaycuruano", "Guaykuruan", "Waikurúan"}, } m["sai-guh"] = { "Guahiban", 944056, aliases = {"Guahiboan", "Guajiboan", "Wahivoan"}, } m["sai-gui"] = { "Guianan", nil, "sai-car", aliases = {"Guianan Carib", "Guiana Carib"}, } m["sai-har"] = { "Harákmbut", 1584402, "sai-hkt", aliases = {"Harákmbet"}, } m["sai-hkt"] = { "Harákmbut-Katukinan", 17107635, } m["sai-hrp"] = { "Huarpean", 1578336, aliases = {"Warpean", "Huarpe", "Warpe"}, } m["sai-jee"] = { "Jê", 1483594, "sai-mje", aliases = {"Gê", "Jean", "Gean", "Jê-Kaingang", "Ye"}, } m["sai-jir"] = { "Jirajaran", 3028651, aliases = {"Hiraháran"}, } m["sai-jiv"] = { "Jivaroan", 1393074, aliases = {"Hívaro", "Jibaro", "Jibaroan", "Jibaroana", "Jívaro"}, } m["sai-ktk"] = { "Katukinan", 2636000, "sai-hkt", aliases = {"Catuquinan"}, } m["sai-kui"] = { "Kuikuroan", nil, "sai-car", aliases = {"Kuikuro", "Nahukwa"}, } m["sai-map"] = { "Mapoyan", 61096301, "sai-ven", aliases = {"Mapoyo", "Mapoyo-Yabarana", "Mapoyo-Yavarana", "Mapoyo-Yawarana"}, } m["sai-mas"] = { "Mascoian", 1906952, aliases = {"Mascoyan", "Maskoian", "Enlhet-Enenlhet"}, } m["sai-mgc"] = { "Mataco-Guaicuru", 255512, } m["sai-mje"] = { "Macro-Jê", 887133, aliases = {"Macro-Gê"}, } m["sai-mtc"] = { "Matacoan", 2447424, "sai-mgc", } m["sai-mur"] = { "Muran", 33826, aliases = {"Mura"}, } m["sai-nad"] = { "Nadahup", 1856439, aliases = {"Makú", "Macú", "Vaupés-Japurá"}, } m["sai-nje"] = { "Northern Jê", 98078225, "sai-cer", aliases = {"Core Jê"}, } m["sai-nmk"] = { "Nambikwaran", 15548027, aliases = {"Nambicuaran", "Nambiquaran", "Nambikuaran"}, } m["sai-otm"] = { "Otomacoan", 3217503, aliases = {"Otomákoan", "Otomakoan"}, } m["sai-pan"] = { "Panoan", 1544537, "sai-pat", aliases = {"Pano"}, } m["sai-pat"] = { "Pano-Tacanan", 2475746, aliases = {"Pano-Tacana", "Pano-Takana", "Páno-Takána", "Pano-Takánan"}, } m["sai-pek"] = { "Pekodian", 107451736, "sai-car", aliases = {"South Amazonian Carib", "Southern Cariban", "Pekodi"}, } m["sai-pem"] = { "Pemongan", nil, "sai-ven", aliases = {"Pemong", "Pemóng", "Purukoto"}, } m["sai-pey"] = { "Peba-Yaguan", 174015, aliases = {"Peba-Yagua", "Yaguan", "Peban", "Yáwan"}, } m["sai-prk"] = { "Parukotoan", 107451482, "sai-car", aliases = {"Parukoto"}, } m["sai-sje"] = { "Southern Jê", 98078245, "sai-jee", } m["sai-tac"] = { "Tacanan", 3113762, "sai-pat", } m["sai-tar"] = { "Taranoan", 105097814, "sai-gui", aliases = {"Trio", "Tarano"}, } m["sai-tin"] = { "Tiniguan", 2892258, aliases = {"Tinigua"}, } m["sai-tuc"] = { "Tucanoan", 788144, } m["sai-tyu"] = { "Ticuna-Yuri", 4467010, } m["sai-ucp"] = { "Uru-Chipaya", 2475488, aliases = {"Uru-Chipayan"}, } m["sai-ven"] = { "Venezuelan Cariban", nil, "sai-car", aliases = {"Venezuelan Carib", "Venezuelan", "Venezuelano"}, } m["sai-wic"] = { "Wichí", 3027047, } m["sai-wit"] = { "Witotoan", 43079317, aliases = {"Huitotoan", "Uitotoan"}, } m["sai-ynm"] = { "Yanomami", nil, aliases = {"Yanomam", "Shamatari", "Yamomami", "Yanomaman"}, } m["sai-yuk"] = { "Yukpan", nil, "sai-car", aliases = {"Yukpa", "Yukpano", "Yukpa-Japreria"}, } m["sai-zam"] = { "Zamucoan", 3048461, aliases = {"Samúkoan"}, } m["sai-zap"] = { "Zaparoan", 33911, aliases = {"Záparoan", "Saparoan", "Sáparoan", "Záparo", "Zaparoano", "Zaparoana"}, } m["sal"] = { "Salish", 33985, pseudo_families = "nai", } m["sdv"] = { "Eastern Sudanic", 2036148, "ssa", } m["sdv-bri"] = { "Bari", nil, "sdv-nie", } m["sdv-daj"] = { "Daju", 956724, "sdv", } m["sdv-dnu"] = { "Dinka-Nuer", nil, "sdv-niw", } m["sdv-eje"] = { "Eastern Jebel", 3408878, "sdv", } m["sdv-kln"] = { "Kalenjin", 637228, "sdv-nis", } m["sdv-lma"] = { "Lotuko-Maa", nil, "sdv-nie", } m["sdv-lon"] = { "Northern Luo", nil, "sdv-luo", } m["sdv-los"] = { "Southern Luo", 7570103, "sdv-luo", } m["sdv-luo"] = { "Luo", nil, "sdv-niw", } m["sdv-nes"] = { "Northern Eastern Sudanic", 4810496, "sdv", aliases = {"Astaboran", "Ek Sudanic"}, } m["sdv-nie"] = { "Eastern Nilotic", 153795, "sdv-nil", } m["sdv-nil"] = { "Nilotic", 513408, "sdv", } m["sdv-nis"] = { "Southern Nilotic", 1552410, "sdv-nil", } m["sdv-niw"] = { "Western Nilotic", 3114989, "sdv-nil", } m["sdv-nma"] = { "Nandi-Markweta", nil, "sdv-kln", } m["sdv-nyi"] = { "Nyima", 11688746, "sdv-nes", aliases = {"Nyimang"}, } m["sdv-tmn"] = { "Taman", 3408873, "sdv-nes", aliases = {"Tamaic"}, } m["sdv-ttu"] = { "Teso-Turkana", 7705551, "sdv-nie", aliases = {"Ateker"}, } m["sel"] = { "Selkup", 34008, "syd", } m["sem"] = { "Semitic", 34049, "afa", } m["sem-ara"] = { "Aramaic", 28602, "sem-nwe", protoLanguage = "arc", } m["sem-arb"] = { "Arabic", 164667, "sem-cen", protoLanguage = "ar", } m["sem-are"] = { "Eastern Aramaic", 3410322, "sem-ara", } m["sem-arw"] = { "Western Aramaic", 3394214, "sem-ara", } m["sem-ase"] = { "Southeastern Aramaic", 3410322, "sem-are", } m["sem-can"] = { "Canaanite", 747547, "sem-nwe", } m["sem-cen"] = { "Central Semitic", 3433228, "sem-wes", } m["sem-cna"] = { "Central Neo-Aramaic", 3410322, "sem-are", } m["sem-eas"] = { "East Semitic", 164273, "sem", } m["sem-eth"] = { "Ethiopian Semitic", 163629, "sem-wes", aliases = {"Afro-Semitic", "Ethiopian", "Ethiopic", "Ethiosemitic"}, } m["sem-nna"] = { "Northeastern Neo-Aramaic", 2560578, "sem-are", } m["sem-nwe"] = { "Northwest Semitic", 162996, "sem-cen", } m["sem-osa"] = { "Old South Arabian", 35025, "sem-cen", aliases = {"Epigraphic South Arabian", "Sayhadic"}, } m["sem-sar"] = { "Modern South Arabian", 1981908, "sem-wes", } m["sem-wes"] = { "West Semitic", 124901, "sem", } m["sgn"] = { "sign", 34228, "qfa-not", } m["sgn-asl"] = { "American Sign Languages", nil, "sgn-fsl", } m["sgn-fsl"] = { "French Sign Languages", 5501921, "sgn", } m["sgn-gsl"] = { "German Sign Languages", 5551235, "sgn", } m["sgn-jsl"] = { "Japanese Sign Languages", 11722508, "sgn", } m["sio"] = { "Siouan", 34181, "nai-sca", } m["sio-dhe"] = { "Dhegihan", 3217420, "sio-msv", } m["sio-dkt"] = { "Dakotan", 4154122, "sio-msv", } m["sio-mor"] = { "Missouri River Siouan", 26807266, "sio", } m["sio-msv"] = { "Mississippi Valley Siouan", 12637104, "sio", } m["sio-ohv"] = { "Ohio Valley Siouan", 21070931, "sio", } m["sit"] = { "Sino-Tibetan", 45961, aliases = {"Trans-Himalayan"}, } m["sit-aao"] = { "Central Naga", 615474, "sit", } m["sit-alm"] = { "Almora", nil, "sit-whm", } m["sit-bai"] = { "Bai", 35103, "sit-mba", } m["sit-bdi"] = { "Bodish", 1814078, "sit", } m["sit-cln"] = { "Cai-Long", 107182612, "sit-mba", aliases = {"Ta-Li"}, } m["sit-dhi"] = { "Dhimalish", 1207648, "sit", } m["sit-ebo"] = { "East Bodish", 56402, "sit-bdi", } m["sit-egy"] = { "East rGyalrongic", 832026, "sit-rgy", } m["sit-ers"] = { "Ersuic", 56335, "sit", } m["sit-gma"] = { "Greater Magaric", 55612963, "sit", } m["sit-gsi"] = { "Greater Siangic", 52698851, "sit", } m["sit-hrs"] = { "Hrusish", 1632501, "sit", aliases = {"Southeast Kamengic"}, } m["sit-jnp"] = { "Jingphoic", nil, "sit-jpl", aliases = {"Jingpho"}, } m["sit-jpl"] = { "Kachin-Luic", 1515454, "tbq-bkj", aliases = {"Jingpho-Luish", "Jingpho-Asakian", "Kachinic"}, } m["sit-kch"] = { "Konyak-Chang", nil, "sit-kon", } m["sit-kha"] = { "Kham", 33305, "sit-gma", } m["sit-khb"] = { "Kho-Bwa", 6401917, "sit", aliases = {"Bugunish", "Kamengic"}, } m["sit-khw"] = { "Western Kho-Bwa", nil, "sit-khb", } m["sit-khc"] = { "Chug-Lish", nil, "sit-khw", aliases = {"Duhumbi-Khispi"}, } m["sit-khm"] = { "Mey-Sartang", nil, "sit-khw", aliases = {"Sartang-Sherdukpen"}, } m["sit-kic"] = { "Central Kiranti", nil, "sit-kir", } m["sit-kie"] = { "Eastern Kiranti", nil, "sit-kir", } m["sit-kin"] = { "Kinnauric", nil, "sit-whm", aliases = {"Kinnauri"}, } m["sit-kir"] = { "Kiranti", 922148, "sit", } m["sit-kiw"] = { "Western Kiranti", 922148, "sit-kir", } m["sit-kon"] = { "Northern Naga", 774590, "tbq-bkj", aliases = {"Konyakian", "Konyak"}, } m["sit-kyk"] = { "Kyirong-Kagate", 6450957, "sit-tib", } m["sit-lab"] = { "Ladakhi-Balti", 6450957, "sit-tib", } m["sit-las"] = { "Lahuli-Spiti", 6473510, "sit-tib", } m["sit-luu"] = { "Luish", 55621439, "sit-jpl", aliases = {"Asakian", "Sak"}, } m["sit-mar"] = { "Maringic", nil, "sit-tma", } m["sit-mba"] = { "Macro-Bai", 16963847, "sit-sba", aliases = {"Greater Bai"}, } m["sit-mdz"] = { "Midzu", 6843504, "sit", aliases = {"Geman", "Midzuish", "Miju-Meyor", "Southern Mishmi"}, } m["sit-mnz"] = { "Mondzish", 6898839, "tbq-lob", aliases = {"Mangish"}, } m["sit-mru"] = { "Mruic", 16908870, "sit", aliases = {"Mru-Hkongso"}, } m["sit-nas"] = { "Naish", 25047956, "sit-nax", } m["sit-nax"] = { "Naic", 6982999, "tbq-buq", aliases = {"Naxish"}, } m["sit-nba"] = { "Northern Bai", 122463830, "sit-bai", } m["sit-new"] = { "Newaric", 55625069, "sit", } m["sit-nng"] = { "Nungish", 1515482, "sit", aliases = {"Nung"}, } m["sit-qia"] = { "Qiangic", 1636765, "tbq-buq", } m["sit-rgy"] = { "Rgyalrongic", 56936, "sit-qia", aliases = {"Jiarongic"}, } m["sit-sba"] = { "Sino-Bai", nil, "sit", aliases = {"Greater Bai"}, } m["sit-tam"] = { "Tamangic", 3309439, "sit", aliases = {"West Bodish"}, } m["sit-tan"] = { "Tani", 3217538, "sit", } m["sit-tib"] = { "Tibetic", 1641150, "sit-bdi", protoLanguage = "otb", } m["sit-tja"] = { "Tujia", nil, "sit", } m["sit-tma"] = { "Tangkhul-Maring", nil, "sit", } m["sit-tng"] = { "Tangkhulic", 1516657, "sit-tma", aliases = {"Tangkhul"}, } m["sit-tno"] = { "Tangsa-Nocte", nil, "sit-kon", } m["sit-tsk"] = { "Tshangla", nil, "sit", } m["sit-wgy"] = { "West rGyalrongic", nil, "sit-rgy" } m["sit-whm"] = { "West Himalayish", 2301695, "sit", } m["sit-zem"] = { "Zeme", 189291, "sit", aliases = {"Zeliangrong", "Zemeic"}, } m["sla"] = { "Slavic", 23526, "ine-bsl", aliases = {"Slavonic"}, } m["smi"] = { "Sami", 56463, "urj", aliases = {"Saami", "Samic", "Saamic"}, } m["son"] = { "Songhay", 505198, "ssa", aliases = {"Songhai"}, } m["sqj"] = { "Albanian", 8748, "ine", } m["ssa"] = { "Nilo-Saharan", -- possibly not a genetic grouping 33705, } m["ssa-fur"] = { "Fur", 2989512, "ssa", } m["ssa-klk"] = { "Kuliak", 1791476, "ssa", aliases = {"Rub"}, } m["ssa-kom"] = { "Koman", 1781084, "ssa", } m["ssa-sah"] = { "Saharan", 1757661, "ssa", } m["syd"] = { "Samoyedic", 34005, "urj", aliases = {"Samoyed", "Samodeic"}, } m["syd-ene"] = { "Enets", 29942, "syd", } m["tai"] = { "Tai", 749720, "qfa-bet", aliases = {"Daic"}, } m["tai-wen"] = { "Wenma-Southwestern Tai", nil, "tai", } m["tai-tay"] = { "Tày", nil, "tai-wen", } m["tai-sap"] = { "Sapa-Southwestern Tai", nil, "tai-wen", aliases = {"Sapa-Thai"}, } m["tai-swe"] = { "Southwestern Tai", 10889250, "tai-sap", } m["tai-cho"] = { "Chongzuo Tai", 13216, "tai", } m["tai-cen"] = { "Central Tai", 5061891, "tai", } m["tai-nor"] = { "Northern Tai", 7059014, "tai", } m["tbq"] = { "Tibeto-Burman", 34064, "sit", } m["tbq-anp"] = { "Angami-Pochuri", 530460, "sit", } m["tbq-axi"] = { "Axioid", nil, "tbq-sel", } m["tbq-bdg"] = { "Bodo-Garo", 4090000, "tbq-bkj", } m["tbq-bis"] = { "Bisoid", 48844742, "tbq-slo", } m["tbq-bka"] = { "Bi-Ka", 12627890, "tbq-slo", } m["tbq-bkj"] = { "Sal", 889900, "sit", -- Brahmaputran appears to be Glottolog's term aliases = {"Bodo-Konyak-Jinghpaw", "Brahmaputran", "Jingpho-Konyak-Bodo"}, } m["tbq-brm"] = { "Burmish", 865713, "tbq-lob", } m["tbq-buq"] = { "Burmo-Qiangic", 16056278, "sit", aliases = {"Eastern Tibeto-Burman"}, } m["tbq-drp"] = { "Downriver Phula", 7188378, "tbq-rph", } m["tbq-han"] = { "Hanoid", 17004185, "tbq-slo", } m["tbq-hph"] = { "Highland Phula", nil, "tbq-sel", } m["tbq-jin"] = { "Jino", 6202716, "tbq-slo", } m["tbq-kzh"] = { "Kazhuoish", 48834669, "tbq-lol", } m["tbq-kuk"] = { "Kuki-Chin", 832413, "sit", aliases = {"Kukish", "South-Central Tibeto-Burman"}, } m["tbq-lal"] = { "Lalo", 56548, "tbq-lso", } m["tbq-lho"] = { "Lahoish", nil, "tbq-lol", } m["tbq-llo"] = { "Lipo-Lolopo", nil, "tbq-lso", } m["tbq-lob"] = { "Lolo-Burmese", 1635712, "tbq-buq", } m["tbq-lol"] = { "Loloish", 37035, "tbq-lob", aliases = {"Yi", "Ngwi", "Nisoic"}, } m["tbq-lso"] = { "Lisoish", 6559055, "tbq-lol", } m["tbq-lwo"] = { "Lawoish", 48847673, "tbq-lol", } m["tbq-muj"] = { "Muji", 11221327, "tbq-hph", } m["tbq-nas"] = { "Nasoid", nil, "tbq-nlo", } m["tbq-nis"] = { "Nisu", 56404, "tbq-nlo", } m["tbq-nlo"] = { "Northern Loloish", 7058676, "tbq-nso", } m["tbq-nso"] = { "Nisoish", 56990, "tbq-lol", } m["tbq-nus"] = { "Nusoish", 114245231, "tbq-lol", } m["tbq-phw"] = { "Phowa", 7187959, "tbq-hph", } m["tbq-rph"] = { "Riverine Phula", nil, "tbq-sel", } m["tbq-sel"] = { "Southeastern Loloish", 16111894, "tbq-nso", } m["tbq-sil"] = { "Siloid", 60787071, "tbq-slo", } m["tbq-slo"] = { "Southern Loloish", 5649340, "tbq-lol", } m["tbq-tal"] = { "Taloid", 48804018, "tbq-lso", } m["tbq-urp"] = { "Upriver Phula", 7187058, "tbq-rph", } m["trk"] = { "Turkic", 34090, } m["trk-cmn"] = { "Common Turkic", 1126028, "trk", aliases = {"Shaz Turkic", "Shaz-Turkic"}, } m["trk-kar"] = { "Karluk", 703173, "trk-cmn", aliases = {"Qarluq", "Uyghur-Uzbek", "Southeastern Turkic"}, } m["trk-kbu"] = { "Kipchak-Bulgar", 3512539, "trk-kip", aliases = {"Uralian", "Uralo-Caspian"}, } m["trk-kcu"] = { "Kipchak-Cuman", 4370412, "trk-kip", aliases = {"Ponto-Caspian"}, } m["trk-kip"] = { "Kipchak", 1339898, "trk-cmn", -- Russian Wikipedia article [[w:ru:Западнотюркские_языки]] says "Western Turkic" is used by N.A. Baskakov and includes Oghuz, Kipchak and Karluk. -- Azerbaijani Wikipedia article [[w:az:Qərbi_türk_dilləri]] clarifies that "Western Turkic" is not a clade. other_names = {"Western Turkic"}, aliases = {"Kypchak", "Qypchaq", "Northwestern Turkic"}, protoLanguage = "qwm", } m["trk-kkp"] = { "Kyrgyz-Kipchak", 4221189, "trk-kip", } m["trk-kno"] = { "Kipchak-Nogai", 4326954, "trk-kip", aliases = {"Aralo-Caspian"}, } m["trk-nsb"] = { "North Siberian Turkic", 4537269, "trk-sib", aliases = {"Northern Siberian Turkic"}, } m["trk-ogr"] = { "Oghur", 1422731, "trk", aliases = {"Lir-Turkic", "r-Turkic"}, } m["trk-ogz"] = { "Oghuz", 494600, "trk-cmn", aliases = {"Southwestern Turkic"}, } m["trk-sib"] = { "Siberian Turkic", 354353, "trk-cmn", other_names = {"Northern Turkic"}, -- per [[w:ru:Восточнотюркские_языки]], "Eastern Turkic" is an alias for Siberian Turkic in the work of O.A. Mudrak, -- but has a different non-clade meaning in the older work of N.A. Baskakov. aliases = {"Eastern Turkic", "Northeastern Turkic"}, } m["trk-ssb"] = { "South Siberian Turkic", nil, "trk-sib", aliases = {"Southern Siberian Turkic"}, } m["tup"] = { "Tupian", 34070, aliases = {"Tupi"}, pseudo_families = "sai", } m["tup-gua"] = { "Tupi-Guarani", 148610, "tup", aliases = {"Tupí-Guaraní"}, } m["tuw"] = { "Tungusic", 34230, aliases = {"Manchu-Tungus", "Tungus"}, } m["tuw-ewe"] = { "Ewenic", 105889448, "tuw", aliases = {"Northern Tungusic"}, } m["tuw-jrc"] = { "Jurchenic", 105889432, "tuw", aliases = {"Manchuric"}, } m["tuw-nan"] = { "Nanaic", 105889264, "tuw", } m["tuw-udg"] = { "Udegheic", 105889266, "tuw", } m["urj"] = { "Uralic", 34113, varieties = {"Finno-Ugric"}, } m["urj-fin"] = { "Finnic", 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, } m["urj-mdv"] = { "Mordvinic", 627313, "urj", } m["urj-prm"] = { "Permic", 161493, "urj", } m["urj-ugr"] = { "Ugric", 156631, "urj", } m["wak"] = { "Wakashan", 60069, pseudo_families = "nai", } m["wen"] = { "Sorbian", 25442, "zlw", aliases = {"Lusatian", "Wendish"}, } m["xgn"] = { "Mongolic", 33750, "qfa-xgs", aliases = {"Mongolian"}, } m["xgn-cen"] = { "Central Mongolic", 28719447, "xgn", protoLanguage = "xng-lat", } m["xgn-sou"] = { "Southern Mongolic", nil, "xgn", protoLanguage = "xng-ear", } m["xgn-shr"] = { "Shirongolic", 107539435, "xgn-sou", } m["xme"] = { "Median", nil, "ira-mpr", protoLanguage = "xme-old", } m["xme-ttc"] = { "Tatic", nil, "xme", } m["xnd"] = { "Na-Dene", 26986, "qfa-dny", aliases = {"Na-Dené"}, pseudo_families = "nai", } m["xsc"] = { "Scythian", nil, "ira-nei", } m["xsc-sak"] = { "Saka", nil, "xsc-skw", aliases = {"Sakan"}, } m["xsc-sar"] = { "Sarmatian", nil, "xsc", } m["xsc-skw"] = { "Saka-Wakhi", nil, "xsc", } m["yok"] = { "Yokuts", 34249, "nai-you", aliases = {"Yokutsan", "Mariposan", "Mariposa"}, } m["ypk"] = { "Yupik", 27970, "esx-esk", aliases = {"Yup'ik", "Yuit"}, } m["yrk"] = { "Nenets", 36452, "syd", } m["zhx"] = { "Sinitic", 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", } m["zhx-com"] = { "Coastal Min", 20667215, "zhx-min", } m["zhx-inm"] = { "Inland Min", 20667237, "zhx-min", } m["zhx-man"] = { "Mandarinic", nil, "zhx", protoLanguage = "cmn-ear", } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Southern Min", 36495, "zhx-com", } m["zhx-pin"] = { "Pinghua", 2735715, "zhx", protoLanguage = "ltc", } m["zhx-yue"] = { "Yue", 7033959, "zhx", protoLanguage = "ltc", } m["zle"] = { "East Slavic", 144713, "sla", } m["zls"] = { "South Slavic", 146665, "sla", } m["zlw"] = { "West Slavic", 145852, "sla", } m["zlw-lch"] = { "Lechitic", 742782, "zlw", aliases = {"Lekhitic"}, } m["zlw-pom"] = { "Pomeranian", nil, "zlw-lch", } m["znd"] = { "Zande", 8066072, "nic-ubg", } return require("Module:languages").finalizeData(m, "family") 44lasaxndbabzsihcvtdja7fje1xoe3 828 8081 54912 2026-09-28T23:25:41Z Deadend0914 7211 Gesceop tramet þe hafaþ 'local data = {} local gsub = string.gsub local next = next local ulower = require("Module:string utilities").lower for _, interwiki in next, mw.site.interwikiMap() do data[ulower((gsub(interwiki.prefix, "_", " ")))] = interwiki.isCurrentWiki and "current" or interwiki.isLocal and "local" or "external" end return data' 54912 Scribunto text/plain local data = {} local gsub = string.gsub local next = next local ulower = require("Module:string utilities").lower for _, interwiki in next, mw.site.interwikiMap() do data[ulower((gsub(interwiki.prefix, "_", " ")))] = interwiki.isCurrentWiki and "current" or interwiki.isLocal and "local" or "external" end return data sj16ikp1xmfv7lsala0b7bnu9dlinm5 828 8082 54916 2026-09-28T23:57:16Z Deadend0914 7211 Gesceop tramet þe hafaþ '--[=[ Floccnaman (category names) for the Old English Wiktionary. Every category that a reader sees on an entry page is built as "<sprǣc> <word>" or "<sprǣc> <word> <word>", exactly like the categories that already exist by hand on this wiki ("Englisc nama", "Nīwenglisc fégung", "Eald Noren werlic nama"), so only the words need translating, never the word order. The modules that build such categories ([[Module:headword]], [[Module:headword utilities]]...' 54916 Scribunto text/plain --[=[ Floccnaman (category names) for the Old English Wiktionary. Every category that a reader sees on an entry page is built as "<sprǣc> <word>" or "<sprǣc> <word> <word>", exactly like the categories that already exist by hand on this wiki ("Englisc nama", "Nīwenglisc fégung", "Eald Noren werlic nama"), so only the words need translating, never the word order. The modules that build such categories ([[Module:headword]], [[Module:headword utilities]], [[Module:form of]], [[Module:gender and number]], [[Module:affix]], [[Module:etymology]], [[Module:etymology/specialized]], [[Module:ang-headword]]) ask this module for the Old English wording first and keep the English wording if it is not here yet. Every missing wording is tracked in [[Wiktionary:Tracking/flocc/untranslated/<wording>]], so the list of what still needs to be added is always up to date: [[Special:WhatLinksHere/Wiktionary:Tracking/flocc/untranslated]] Words are entered without leading or trailing spaces, in the singular for parts of speech ("nama", not "naman"), because that is what the pre-existing categories use. The plural forms used for the lemma categories are entered separately ("lemmas", "non-lemma forms", ...). Only categories a reader sees on an entry page are translated here. Maintenance and tracking categories (sortkeys, script codes, requests, pages with ...), the categories of the template namespace and the ones produced by MediaWiki itself stay English on purpose. ]=] local export = {} --[=[ English wording -> Old English wording. The words in this first group are already used by categories and template names that exist on this wiki, so their spelling is established ("Flocc:Nama", "Flocc:Bīnaman", "Flocc:Nīwenglisc fégung", "Bysen:Tōgeīecendlic-Tabule", "Cynn 1 strang forþgewiten dǣlnimend"), and the gender words match the existing "Eald Noren werlic nama" style. ]=] local words = { -- Parts of speech. ["nouns"] = "nama", ["verbs"] = "word", ["adjectives"] = "tōgeīecendlic", ["adverbs"] = "bīword", ["conjunctions"] = "fégung", ["pronouns"] = "bīnaman", ["prepositions"] = "ēowigendlic", ["participles"] = "dǣlnimend", ["past participles"] = "forþgewiten dǣlnimend", ["present participles"] = "andweard dǣlnimend", ["masculine"] = "werlic", ["feminine"] = "wīflic", ["neuter"] = "nāhwæðer", } --[=[ Wording still to be translated. Anything listed here (or used in a module but not listed at all) falls back to its English form and shows up in [[Wiktionary:Tracking/flocc/untranslated]], so nothing breaks while the table is filled in. Suggestions, commented out until checked against a source: -- ["lemmas"] = "?", -- the lemma category, e.g. "Englisc ?" -- ["non-lemma forms"] = "?", -- e.g. "Englisc ?" -- ["variant lemmas"] = "?", -- alternative forms -- ["variant non-lemma forms"] = "?", -- ["proper nouns"] = "?", -- e.g. "syndrig nama"? -- ["suffixes"] = "?", -- "Englisc ?" -- ["prefixes"] = "?", -- ["numerals"] = "?", -- cf. "Bysen:Getæl-Naman-Tabule" -- ["interjections"] = "?", -- ["particles"] = "?", -- ["determiners"] = "?", -- ["phrases"] = "?", -- ["proverbs"] = "?", -- ["abbreviations"] = "?", -- ["initialisms"] = "?", -- ["symbols"] = "?", -- ["letters"] = "?", -- ["countable nouns"] = "?", -- ["uncountable nouns"] = "?", -- ["compound words"] = "?", -- ["terms inherited from "] = "?", -- etymology, e.g. "Nīwenglisc ? Englisce" -- ["terms derived from "] = "?", -- ["terms borrowed from "] = "?", -- ["terms borrowed back into "] = "?", -- ["learned borrowings"] = "?", -- ["other languages"] = "?", -- ["Translingual"] = "?", -- ["taxonomic names"] = "?", ]=] --[=[ Wording that carries a variable part, as a leading phrase. For example the affix templates build categories such as "terms suffixed with -kas", where only the beginning is fixed; the language name is prepended by the caller. Longest phrase first, so the most specific rule wins. ]=] local prefixes = { -- {"terms suffixed with ", "?"}, -- {"terms prefixed with ", "?"}, -- {"terms circumfixed with ", "?"}, -- {"terms infixed with ", "?"}, -- {"terms interfixed with ", "?"}, } local function track(text) local ok, track_module = pcall(require, "Module:debug/track") if ok then track_module("flocc/untranslated/" .. tostring(text)) end end --[==[ Return the Old English wording for one category name, or nil if it is not known yet. `lang` is accepted so that a wording can later be made language-specific if that turns out to be needed. ]==] function export.translate(lang, text) if type(text) ~= "string" or text == "" then return nil end if words[text] then return words[text] end for _, rule in ipairs(prefixes) do if text:sub(1, #rule[1]) == rule[1] then return rule[2] .. text:sub(#rule[1] + 1) end end track(text) return nil end --[==[ Return the Old English wording for one category name, or the English wording unchanged if it is not known yet. Use this in the modules that build categories: the language name is prepended by the caller, so only the wording itself is passed in. ]==] function export.get(lang, text) return export.translate(lang, text) or text end -- The table is exposed for tests and maintenance scripts; use get() elsewhere. export.words = words return export 1n9fpnl2w348v8tuhblbul3ngapg3gy