ویکیفەرھەنگ ckbwiktionary https://ckb.wiktionary.org/wiki/%D9%88%DB%8C%DA%A9%DB%8C%D9%81%DB%95%D8%B1%DA%BE%DB%95%D9%86%DA%AF:%D8%AF%DB%95%D8%B3%D8%AA%D9%BE%DB%8E%DA%A9 MediaWiki 1.47.0-wmf.14 case-sensitive میدیا تایبەت وتووێژ بەکارھێنەر لێدوانی بەکارھێنەر ویکیفەرھەنگ لێدوانی ویکیفەرھەنگ پەڕگە وتووێژی پەڕگە میدیاویکی وتووێژی میدیاویکی داڕێژە وتووێژی داڕێژە یارمەتی وتووێژی یارمەتی پۆل وتووێژی پۆل TimedText TimedText talk مۆدیوول لێدوانی مۆدیوول Event Event talk 828 35 36721 36502 2026-08-11T23:15:44Z Ghybu 12 category: name + بە + langname (ex: ناو بە کوردیی باکووری) 36721 Scribunto text/plain local export = {} -- Named constants for all modules used, to make it easier to swap out sandbox versions. local debug_track_module = "Module:debug/track" local en_utilities_module = "Module:en-utilities" local gender_and_number_module = "Module:gender and number" local headword_data_module = "Module:headword/data" local headword_page_module = "Module:headword/page" local links_module = "Module:links" local load_module = "Module:load" local pages_module = "Module:pages" local palindromes_module = "Module:palindromes" local pron_qualifier_module = "Module:pron qualifier" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local script_utilities_module = "Module:script utilities" local script_utilities_data_module = "Module:script utilities/data" 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 ipairs = ipairs local max = math.max local new_title = mw.title.new local pairs = pairs local require = require local toNFC = mw.ustring.toNFC local toNFD = mw.ustring.toNFD local type = type local ufind = mw.ustring.find local ugmatch = mw.ustring.gmatch local ugsub = mw.ustring.gsub local umatch = mw.ustring.match --[==[ 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 debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end local function extend(...) extend = require(table_module).extend return extend(...) 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 format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function format_genders(...) format_genders = require(gender_and_number_module).format_genders return format_genders(...) end local function format_pron_qualifiers(...) format_pron_qualifiers = require(pron_qualifier_module).format_qualifiers return format_pron_qualifiers(...) end local function full_link(...) full_link = require(links_module).full_link return full_link(...) end local function get_current_L2(...) get_current_L2 = require(pages_module).get_current_L2 return get_current_L2(...) end local function get_link_page(...) get_link_page = require(links_module).get_link_page return get_link_page(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function is_palindrome(...) is_palindrome = require(palindromes_module).is_palindrome return is_palindrome(...) end local function language_link(...) language_link = require(links_module).language_link return language_link(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function pattern_escape(...) pattern_escape = require(string_utilities_module).pattern_escape return pattern_escape(...) end local function pluralize(...) pluralize = require(en_utilities_module).pluralize return pluralize(...) end local function process_page(...) process_page = require(headword_page_module).process_page return process_page(...) end local function remove_links(...) remove_links = require(links_module).remove_links return remove_links(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function tag_text(...) tag_text = require(script_utilities_module).tag_text return tag_text(...) end local function tag_transcription(...) tag_transcription = require(script_utilities_module).tag_transcription return tag_transcription(...) end local function tag_translit(...) tag_translit = require(script_utilities_module).tag_translit return tag_translit(...) end local function trim(...) trim = require(string_utilities_module).trim return trim(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) 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 m_data local function get_data() m_data = load_data(headword_data_module) return m_data end local script_data local function get_script_data() script_data = load_data(scripts_data_module) return script_data end local script_utilities_data local function get_script_utilities_data() script_utilities_data = load_data(script_utilities_data_module) return script_utilities_data end -- If set to true, categories always appear, even in non-mainspace pages local test_force_categories = false -- Add a tracking category to track entries with certain (unusually undesirable) properties. `track_id` is an identifier -- for the particular property being tracked and goes into the tracking page. Specifically, this adds a link in the -- page text to [[Wiktionary:Tracking/headword/TRACK_ID]], meaning you can find all entries with the `track_id` property -- by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID]]. -- -- If `lang` (a language object) is given, an additional tracking page [[Wiktionary:Tracking/headword/TRACK_ID/CODE]] is -- linked to where CODE is the language code of `lang`, and you can find all entries in the combination of `track_id` -- and `lang` by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID/CODE]]. This makes it possible to -- isolate only the entries with a specific tracking property that are in a given language. Note that if `lang` -- references at etymology-only language, both that language's code and its full parent's code are tracked. local function track(track_id, lang) local tracking_page = "headword/" .. track_id if lang and lang:hasType("etymology-only") then debug_track{tracking_page, tracking_page .. "/" .. lang:getCode(), tracking_page .. "/" .. lang:getFullCode()} elseif lang then debug_track{tracking_page, tracking_page .. "/" .. lang:getCode()} else debug_track(tracking_page) end return true end local function text_in_script(text, script_code) local sc = get_script(script_code) if not sc then error("Internal error: Bad script code " .. script_code) end local characters = sc.characters local out if characters then text = ugsub(text, "%W", "") out = ufind(text, "[" .. characters .. "]") end if out then return true else return false end end local spacingPunctuation = "[%s%p]+" --[[ List of punctuation or spacing characters that are found inside of words. Used to exclude characters from the regex above. ]] local wordPunc = "-#%%&@־׳״'.·*’་•:᠊" local notWordPunc = "[^" .. wordPunc .. "]+" -- Format a term (either a head term or an inflection term) along with any left or right qualifiers, labels, references -- or customized separator: `part` is the object specifying the term (and `lang` the language of 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`; -- * a separator in `separator`, defaulting to " <i>or</i> " if this is not the first term (j > 1), otherwise "". -- `formatted` is the formatted version of the term itself, and `j` is the index of the term. local function format_term_with_qualifiers_and_refs(lang, part, formatted, j) local function part_non_empty(field) local list = part[field] if not list then return nil end if type(list) ~= "table" then error(("Internal error: Wrong type for `part.%s`=%s, should be \"table\""):format(field, mw.dumpObject(list))) end return list[1] end if part_non_empty("q") or part_non_empty("qq") or part_non_empty("l") or part_non_empty("ll") or part_non_empty("refs") then formatted = format_pron_qualifiers { lang = lang, text = formatted, q = part.q, qq = part.qq, l = part.l, ll = part.ll, refs = part.refs, } end local separator = part.separator or j > 1 and " <i>or</i> " -- use "" to request no separator if separator then formatted = separator .. formatted end return formatted end --[==[Return true if the given head is multiword according to the algorithm used in full_headword().]==] function export.head_is_multiword(head) for possibleWordBreak in ugmatch(head, spacingPunctuation) do if umatch(possibleWordBreak, notWordPunc) then return true end end return false end do local function workaround_to_exclude_chars(s) return (ugsub(s, notWordPunc, "\2%1\1")) end --[==[Add links to a multiword head.]==] function export.add_multiword_links(head, default) head = "\1" .. ugsub(head, spacingPunctuation, workaround_to_exclude_chars) .. "\2" if default then head = head :gsub("(\1[^\2]*)\\([:#][^\2]*\2)", "%1\\\\%2") :gsub("(\1[^\2]*)([:#][^\2]*\2)", "%1\\%2") end --Escape any remaining square brackets to stop them breaking links (e.g. "[citation needed]"). head = encode_entities(head, "[]", true, true) --[=[ use this when workaround is no longer needed: head = "[[" .. ugsub(head, WORDBREAKCHARS, "]]%1[[") .. "]]" Remove any empty links, which could have been created above at the beginning or end of the string. ]=] return (head :gsub("\1\2", "") :gsub("[\1\2]", {["\1"] = "[[", ["\2"] = "]]"})) end end -- In ckb.wiktionary.org, we don't have these. So, we don't need them; disabled. -- local function non_categorizable(full_raw_pagename) -- return full_raw_pagename:find("^Appendix:Gestures/") or -- -- Unsupported titles with descriptive names. -- (full_raw_pagename:find("^Unsupported titles/") and not full_raw_pagename:find("`")) -- end local function tag_text_and_add_quals_and_refs(data, head, formatted, j) -- Add language and script wrapper. formatted = tag_text(formatted, data.lang, head.sc, "head", nil, j == 1 and data.id or nil) -- Add qualifiers, labels, references and separator. return format_term_with_qualifiers_and_refs(data.lang, head, formatted, j) end -- Format a headword with transliterations. local function format_headword(data) -- Are there non-empty transliterations? local has_translits = false local has_manual_translits = false ------ Format the headwords. ------ local head_parts = {} local unique_head_parts = {} local has_multiple_heads = not not data.heads[2] for j, head in ipairs(data.heads) do if head.tr or head.ts then has_translits = true end if head.tr and head.tr_manual or head.ts then has_manual_translits = true end local formatted -- Apply processing to the headword, for formatting links and such. if head.term:find("[[", nil, true) and head.sc:getCode() ~= "Image" then formatted = language_link{term = head.term, lang = data.lang} else formatted = data.lang:makeDisplayText(head.term, head.sc, true) end local head_part = tag_text_and_add_quals_and_refs(data, head, formatted, j) insert(head_parts, head_part) -- If multiple heads, try to determine whether all heads display the same. To do this we need to effectively -- rerun the text tagging and addition of qualifiers and references, using 1 for all indices. if has_multiple_heads then local unique_head_part if j == 1 then unique_head_part = head_part else unique_head_part = tag_text_and_add_quals_and_refs(data, head, formatted, 1) end unique_head_parts[unique_head_part] = true end end local set_size = 0 if has_multiple_heads then for _ in pairs(unique_head_parts) do set_size = set_size + 1 end end if set_size == 1 then head_parts = head_parts[1] else head_parts = concat(head_parts) end if has_manual_translits then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr/LANGCODE]] track("manual-tr", data.lang) end ------ Format the transliterations and transcriptions. ------ local translits_formatted if has_translits then local translit_parts = {} for _, head in ipairs(data.heads) do if head.tr or head.ts then local this_parts = {} if head.tr then insert(this_parts, tag_translit(head.tr, data.lang:getCode(), "head", nil, head.tr_manual)) if head.ts then insert(this_parts, " ") end end if head.ts then insert(this_parts, "/" .. tag_transcription(head.ts, data.lang:getCode(), "head") .. "/") end insert(translit_parts, concat(this_parts)) end end translits_formatted = " (" .. concat(translit_parts, " <i>or</i> ") .. ")" local langname = data.lang:getCanonicalName() local transliteration_page = new_title(langname .. " transliteration", "Wiktionary") local saw_translit_page = false if transliteration_page and transliteration_page.exists then translits_formatted = " [[Wiktionary:" .. langname .. " transliteration|•]]" .. translits_formatted saw_translit_page = true end -- If data.lang is an etymology-only language and we didn't find a translation page for it, fall back to the -- full parent. if not saw_translit_page and data.lang:hasType("etymology-only") then langname = data.lang:getFullName() transliteration_page = new_title(langname .. " transliteration", "Wiktionary") if transliteration_page and transliteration_page.exists then translits_formatted = " [[Wiktionary:" .. langname .. " transliteration|•]]" .. translits_formatted end end else translits_formatted = "" end ------ Paste heads and transliterations/transcriptions. ------ local lemma_gloss if data.gloss then lemma_gloss = ' <span class="ib-content qualifier-content">' .. data.gloss .. '</span>' else lemma_gloss = "" end return head_parts .. translits_formatted .. lemma_gloss end local function format_headword_genders(data) local retval = "" if data.genders and data.genders[1] then if data.gloss then retval = "," end local pos_for_cat if not data.nogendercat then local no_gender_cat = (m_data or get_data()).no_gender_cat if not (no_gender_cat[data.lang:getCode()] or no_gender_cat[data.lang:getFullCode()]) then pos_for_cat = (m_data or get_data()).pos_for_gender_number_cat[data.pos_category:gsub("^reconstructed ", "")] end end local text, cats = format_genders(data.genders, data.lang, pos_for_cat) if cats then extend(data.categories, cats) end retval = retval .. "&nbsp;" .. text end return retval end local function format_inflection_parts(data, parts) local any_part_translit = false for j, part in ipairs(parts) do if type(part) ~= "table" then part = {term = part} end local partaccel = part.accel local face = part.face or "bold" if face ~= "bold" and face ~= "plain" and face ~= "hypothetical" then error("The face `" .. face .. "` " .. ( (script_utilities_data or get_script_utilities_data()).faces[face] and "should not be used for non-headword terms on the headword line." or "is invalid." )) end -- Here the final part 'or data.nolinkinfl' allows to have 'nolinkinfl=true' -- right into the 'data' table to disable inflection links of the entire headword -- when inflected forms aren't entry-worthy, e.g.: in Vulgar Latin local nolinkinfl = part.face == "hypothetical" or (part.nolink and track("nolink") or part.nolinkinfl) or ( data.nolink and track("nolink") or data.nolinkinfl) local formatted if part.label then -- FIXME: There should be a better way of italicizing a label. As is, this isn't customizable. formatted = "<i>" .. part.label .. "</i>" else -- Convert the term into a full link. Don't show a transliteration here unless enable_auto_translit is -- requested, either at the `parts` level (i.e. per inflection) or at the `data.inflections` level (i.e. -- specified for all inflections). This is controllable in {{head}} using autotrinfl=1 for all inflections, -- or fNautotr=1 for an individual inflection (remember that a single inflection may be associated with -- multiple terms). The reason for doing this is to avoid clutter in headword lines by default in languages -- where the script is relatively straightforward to read by learners (e.g. Greek, Russian), but allow it -- to be enabled in languages with more complex scripts (e.g. Arabic). local tr = part.translit or (not (parts.enable_auto_translit or data.inflections.enable_auto_translit) and "-" or nil) if tr ~= "-" then any_part_translit = true end formatted = full_link( { term = not nolinkinfl and part.term or nil, alt = part.alt or (nolinkinfl and part.term or nil), lang = part.lang or data.lang, sc = part.sc or parts.sc or nil, gloss = part.gloss, pos = part.pos, lit = part.lit, id = part.id, genders = part.genders, tr = tr, ts = part.transcription, accel = partaccel or parts.accel, }, face ) end parts[j] = format_term_with_qualifiers_and_refs(part.lang or data.lang, part, formatted, j) end local parts_output if parts[1] then parts_output = (parts.label and " " or "") .. concat(parts) elseif parts.request then parts_output = " <small>[please provide]</small>" insert(data.categories, "Requests for inflections in " .. data.lang:getFullName() .. " entries") else parts_output = "" end local parts_label = parts.label and ("<i>" .. parts.label .. "</i>") or "" return format_term_with_qualifiers_and_refs(data.lang, parts, parts_label .. parts_output, 1), any_part_translit end -- Format the inflections following the headword. local function format_inflections(data) local any_part_translit = false if data.inflections and data.inflections[1] then -- Format each inflection individually. for key, infl in ipairs(data.inflections) do local this_any_part_translit data.inflections[key], this_any_part_translit = format_inflection_parts(data, infl) if this_any_part_translit then any_part_translit = true end end local concat_result = concat(data.inflections, ", ") return " (" .. concat_result .. ")" else return "" end end --[==[ Returns the plural form of `pos`, a raw part of speech input, which could be singular or plural. Irregular plural POS are taken into account (e.g. "kanji" pluralizes to "kanji"). ]==] function export.pluralize_pos(pos) -- Make the plural form of the part of speech return (m_data or get_data()).irregular_plurals[pos] or pos:sub(-1) == "s" and pos or pluralize(pos) end --[==[ Return "lemma" if the given POS is a lemma, "non-lemma form" if a non-lemma form, or nil if unknown. The POS passed in must be in its plural form ("nouns", "prefixes", etc.). If you have a POS in its singular form, call {export.pluralize_pos()} above to pluralize it in a smart fashion that knows when to add "-s" and when to add "-es", and also takes into account any irregular plurals. If `best_guess` is given and the POS is in neither the lemma nor non-lemma list, guess based on whether it ends in " forms"; otherwise, return nil. ]==] function export.pos_lemma_or_nonlemma(plpos, best_guess) local isLemma = (m_data or get_data()).lemmas -- Is it a lemma category? if isLemma[plpos] then return "lemma" end local plpos_no_recon = plpos:gsub("^reconstructed ", "") if isLemma[plpos_no_recon] then return "lemma" end -- Is it a nonlemma category? local isNonLemma = (m_data or get_data()).nonlemmas if isNonLemma[plpos] or isNonLemma[plpos_no_recon] then return "non-lemma form" end local plpos_no_mut = plpos:gsub("^mutated ", "") if isLemma[plpos_no_mut] or isNonLemma[plpos_no_mut] then return "non-lemma form" elseif best_guess then return plpos:find(" forms$") and "non-lemma form" or "lemma" else return nil end end --[==[ Canonicalize a part of speech as specified in 2= in {{tl|head}}. This checks for POS aliases and non-lemma form aliases ending in 'f', and then pluralizes if the POS term does not have an invariable plural. ]==] function export.canonicalize_pos(pos) -- FIXME: Temporary code to throw an error for alias 'pre' (= preposition) that will go away. if pos == "pre" then -- Don't throw error on 'pref' as it's an alias for "prefix". error("POS 'pre' for 'preposition' no longer allowed as it's too ambiguous; use 'prep'") end -- Likewise for pro = pronoun. if pos == "pro" or pos == "prof" then error("POS 'pro' for 'pronoun' no longer allowed as it's too ambiguous; use 'pron'") end local data = m_data or get_data() if data.pos_aliases[pos] then pos = data.pos_aliases[pos] elseif pos:sub(-1) == "f" then pos = pos:sub(1, -2) pos = (data.pos_aliases[pos] or pos) .. " forms" end return export.pluralize_pos(pos) end -- Find and return the maximum index in the array `data[element]` (which may have gaps in it), and initialize it to a -- zero-length array if unspecified. Check to make sure all keys are numeric (other than "maxindex", which is set by -- [[Module:parameters]] for list parameters), all values are strings, and unless `allow_blank_string` is given, -- no blank (zero-length) strings are present. local function init_and_find_maximum_index(data, element, allow_blank_string) local maxind = 0 if not data[element] then data[element] = {} end local typ = type(data[element]) if typ ~= "table" then error(("In full_headword(), `data.%s` must be an array but is a %s"):format(element, typ)) end for k, v in pairs(data[element]) do if k ~= "maxindex" then if type(k) ~= "number" then error(("Unrecognized non-numeric key '%s' in `data.%s`"):format(k, element)) end if k > maxind then maxind = k end if v then if type(v) ~= "string" then error(("For key '%s' in `data.%s`, value should be a string but is a %s"):format(k, element, type(v))) end if not allow_blank_string and v == "" then error(("For key '%s' in `data.%s`, blank string not allowed; use 'false' for the default"):format(k, element)) end end end end return maxind end --[==[ -- Add the page to various maintenance categories for the language and the -- whole page. These are placed in the headword somewhat arbitrarily, but -- mainly because headword templates are mandatory for entries (meaning that -- in theory it provides full coverage). -- -- This is provided as an external entry point so that modules which transclude -- information from other entries (such as {{tl|ja-see}}) can take advantage -- of this feature as well, because they are used in place of a conventional -- headword template.]==] do -- Handle any manual sortkeys that have been specified in raw categories -- by tracking if they are the same or different from the automatically- -- generated sortkey, so that we can track them in maintenance -- categories. local function handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) sortkey = sortkey or lang:makeSortKey(page.pagename) -- If there are raw categories with no sortkey, then they will be -- sorted based on the default MediaWiki sortkey, so we check against -- that. if tbl == true then if page.raw_defaultsort ~= sortkey then insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys") end return end local redundant, different for k in pairs(tbl) do if k == sortkey then redundant = true else different = true end end if redundant then insert(lang_cats, lang:getFullName() .. " terms with redundant sortkeys") end if different then insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys") end return sortkey end function export.maintenance_cats(page, lang, lang_cats, page_cats) extend(page_cats, page.cats) lang = lang:getFull() -- since we are just generating categories local canonical = lang:getCanonicalName() local tbl, sortkey = page.wikitext_topic_cat[lang:getCode()] if tbl then sortkey = handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) insert(lang_cats, canonical .. " entries with topic categories using raw markup") end tbl = page.wikitext_langname_cat[canonical] if tbl then handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) insert(lang_cats, canonical .. " entries with language name categories using raw markup") end if get_current_L2() ~= canonical then insert(lang_cats, canonical .. " entries with incorrect language header") -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/incorrect language header]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/incorrect language header/LANGCODE]] track("incorrect language header", lang) end end end --[==[This is the primary external entry point. {{lua|full_headword(data)}} This is used by {{temp|head}} and various language-specific headword templates (e.g. {{temp|ru-adj}} for Russian adjectives, {{temp|de-noun}} for German nouns, etc.) to display an entire headword line. See [[#Further explanations for full_headword()]] ]==] function export.full_headword(data) -- Prevent data from being destructively modified. local data = shallow_copy(data) ------------ 1. Basic checks for old-style (multi-arg) calling convention. ------------ if data.getCanonicalName then error("In full_headword(), the first argument `data` needs to be a Lua object (table) of properties, not a language object") end if not data.lang or type(data.lang) ~= "table" or not data.lang.getCode then error("In full_headword(), the first argument `data` needs to be a Lua object (table) and `data.lang` must be a language object") end if data.id and type(data.id) ~= "string" then error("The id in the data table should be a string.") end ------------ 2. Initialize pagename etc. ------------ local langcode = data.lang:getCode() local full_langcode = data.lang:getFullCode() local langname = data.lang:getCanonicalName() local full_langname = data.lang:getFullName() local raw_pagename, page = data.pagename if raw_pagename and raw_pagename ~= (m_data or get_data()).pagename then -- for testing, doc pages, etc. page = process_page(raw_pagename) else page = (m_data or get_data()).page end -- Check the namespace against the language type. local namespace = page.namespace if namespace == "" then if data.lang:hasType("reconstructed") then error("Entries in " .. langname .. " must be placed in the Reconstruction: namespace") elseif data.lang:hasType("appendix-constructed") then error("Entries in " .. langname .. " must be placed in the Appendix: namespace") end elseif namespace == "Citations" or namespace == "Thesaurus" then error("Headword templates should not be used in the " .. namespace .. ": namespace.") end ------------ 3. Initialize `data.heads` table; if old-style, convert to new-style. ------------ if type(data.heads) == "table" and type(data.heads[1]) == "table" then -- new-style if data.translits or data.transcriptions then error("In full_headword(), if `data.heads` is new-style (array of head objects), `data.translits` and `data.transcriptions` cannot be given") end else -- convert old-style `heads`, `translits` and `transcriptions` to new-style local maxind = max( init_and_find_maximum_index(data, "heads"), init_and_find_maximum_index(data, "translits", true), init_and_find_maximum_index(data, "transcriptions", true) ) for i = 1, maxind do data.heads[i] = { term = data.heads[i], tr = data.translits[i], ts = data.transcriptions[i], } end end -- Make sure there's at least one head. if not data.heads[1] then data.heads[1] = {} end ------------ 4. Initialize and validate `data.categories` and `data.whole_page_categories`, and determine `pos_category` if not given, and add basic categories. ------------ -- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]] if data.altform then data.noposcat = true end init_and_find_maximum_index(data, "categories") init_and_find_maximum_index(data, "whole_page_categories") local pos_category_already_present = false if data.categories[1] then local escaped_langname = pattern_escape(full_langname) local matches_lang_pattern = "^" .. escaped_langname .. " " for _, cat in ipairs(data.categories) do -- Does the category begin with the language name? If not, tag it with a tracking category. if not cat:find(matches_lang_pattern) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category/LANGCODE]] track("no lang category", data.lang) end end -- If `pos_category` not given, try to infer it from the first specified category. If this doesn't work, we -- throw an error below. if not data.pos_category and data.categories[1]:find(matches_lang_pattern) then data.pos_category = data.categories[1]:gsub(matches_lang_pattern, "") -- Optimization to avoid inserting category already present. pos_category_already_present = true end end if not data.pos_category then error("`data.pos_category` not specified and could not be inferred from the categories given in " .. "`data.categories`. Either specify the plural part of speech in `data.pos_category` " .. "(e.g. \"proper nouns\") or ensure that the first category in `data.categories` is formed from the " .. "language's canonical name plus the plural part of speech (e.g. \"Norwegian Bokmål proper nouns\")." ) end -- Insert a category at the beginning for the part of speech unless it's already present or `data.noposcat` given. if not pos_category_already_present and not data.noposcat then local pos_category = data.pos_category .. " بە " .. full_langname -- FIXME: [[User:Theknightwho]] Why is this special case here? Please add an explanatory comment. if pos_category ~= "Translingual Han characters" then insert(data.categories, 1, pos_category) end end -- Try to determine whether the part of speech refers to a lemma or a non-lemma form; if we can figure this out, -- add an appropriate category. local postype = export.pos_lemma_or_nonlemma(data.pos_category) if not postype then -- We don't know what this category is, so tag it with a tracking category. -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/LANGCODE]] track("unrecognized pos", data.lang) -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/POS]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/POS/LANGCODE]] track("unrecognized pos/pos/" .. data.pos_category, data.lang) elseif not data.noposcat then insert(data.categories, 1, full_langname .. " " .. postype .. "s") end -- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]] if data.altform then insert(data.categories, 1, full_langname .. " alternative forms") end ------------ 5. Create a default headword, and add links to multiword page names. ------------ -- Determine if term is reconstructed local is_reconstructed = namespace == "Reconstruction" or data.lang:hasType("reconstructed") -- Create a default headword based on the pagename, which is determined in -- advance by the data module so that it only needs to be done once. local default_head = page.pagename -- Add links to multi-word page names when appropriate if not (is_reconstructed or data.nolinkhead) then local no_links = (m_data or get_data()).no_multiword_links if not (no_links[langcode] or no_links[full_langcode]) and export.head_is_multiword(default_head) then default_head = export.add_multiword_links(default_head, true) end end if is_reconstructed then default_head = "*" .. default_head end ------------ 6. Fill in missing values in `data.heads`. ------------ -- True if any script among the headword scripts has spaces in it. local any_script_has_spaces = false -- True if any term has a redundant head= param. local has_redundant_head_param = false for _, head in ipairs(data.heads) do ------ 6a. If missing head, replace with default head. if not head.term then head.term = default_head elseif head.term == default_head then has_redundant_head_param = true elseif head.term:find("^[!?]$") then -- If explicit head= just consists of ! or ?, add it to the end of the default head. head.term = default_head .. head.term end if is_reconstructed then local head_term = head.term if head_term:find("%[%[") then head_term = remove_links(head_term) end if head_term:sub(1, 1) ~= "*" then error("The headword '" .. head_term .. "' must begin with '*' to indicate that it is reconstructed.") end end ------ 6b. Try to detect the script(s) if not provided. If a per-head script is provided, that takes precedence, ------ otherwise fall back to the overall script if given. If neither given, autodetect the script. local auto_sc = data.lang:findBestScript(head.term) if ( auto_sc:getCode() == "None" and find_best_script_without_lang(head.term):getCode() ~= "None" ) then insert(data.categories, full_langname .. " terms in nonstandard scripts") end if not (head.sc or data.sc) then -- No script code given, so use autodetected script. head.sc = auto_sc else if not head.sc then -- Overall script code given. head.sc = data.sc end -- Track uses of sc parameter. if head.sc:getCode() == auto_sc:getCode() then insert(data.categories, full_langname .. " terms with redundant script codes") else insert(data.categories, full_langname .. " terms with non-redundant manual script codes") end end -- If using a discouraged character sequence, add to maintenance category. if head.sc:hasNormalizationFixes() == true then local composed_head = toNFC(head.term) if head.sc:fixDiscouragedSequences(composed_head) ~= composed_head then insert(data.whole_page_categories, "Pages using discouraged character sequences") end end any_script_has_spaces = any_script_has_spaces or head.sc:hasSpaces() ------ 6c. Create automatic transliterations for any non-Latin headwords without manual translit given ------ (provided automatic translit is available, e.g. not in Persian or Hebrew). -- Make transliterations head.tr_manual = nil -- Try to generate a transliteration if necessary if head.tr == "-" then head.tr = nil else local notranslit = (m_data or get_data()).notranslit if not (notranslit[langcode] or notranslit[full_langcode]) and head.sc:isTransliterated() then head.tr_manual = not not head.tr local text = head.term if not data.lang:link_tr(head.sc) then text = remove_links(text) end local automated_tr, tr_categories automated_tr, head.tr_fail, tr_categories = data.lang:transliterate(text, head.sc) if automated_tr or head.tr_fail then local manual_tr = head.tr if manual_tr then if (remove_links(manual_tr) == remove_links(automated_tr)) and (not head.tr_fail) then insert(data.categories, full_langname .. " terms with redundant transliterations") elseif not head.tr_fail then insert(data.categories, full_langname .. " terms with non-redundant manual transliterations") end end if not manual_tr then head.tr = automated_tr extend(data.categories, tr_categories) end end -- There is still no transliteration? -- Add the entry to a cleanup category. if not head.tr then head.tr = "<small>transliteration needed</small>" -- FIXME: No current support for 'Request for transliteration of Classical Persian terms' or similar. -- Consider adding this support in [[Module:category tree/poscatboiler/data/entry maintenance]]. insert(data.categories, "Requests for transliteration of " .. full_langname .. " terms") else -- Otherwise, trim it. head.tr = trim(head.tr) end end end -- Link to the transliteration entry for languages that require this. if head.tr and data.lang:link_tr(head.sc) then head.tr = full_link{ term = head.tr, lang = data.lang, sc = get_script("Latn"), tr = "-" } end end ------------ 7. Maybe tag the title with the appropriate script code, using the `display_title` mechanism. ------------ -- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace. -- (FIXME: Don't make assumptions like this, and if you need to do so, throw an error if the assumption is violated.) -- Avoid tagging ASCII as Hani even when it is tagged as Hani in the headword, as in [[check]]. The check for ASCII -- might need to be expanded to a check for any Latin characters and whitespace or punctuation. local display_title -- Where there are multiple headwords, use the script for the first. This assumes the first headword is similar to -- the pagename, and that headwords that are in different scripts from the pagename aren't first. This seems to be -- about the best we can do (alternatively we could potentially do script detection on the pagename). local dt_script = data.heads[1].sc local dt_script_code = dt_script:getCode() local page_non_ascii = namespace == "" and not page.pagename:find("^[%z\1-\127]+$") local unsupported_pagename, unsupported = page.full_raw_pagename:gsub("^Unsupported titles/", "") if unsupported == 1 and page.unsupported_titles[unsupported_pagename] then display_title = 'Unsupported titles/<span class="' .. dt_script_code .. '">' .. page.unsupported_titles[unsupported_pagename] .. '</span>' elseif page_non_ascii and (m_data or get_data()).toBeTagged[dt_script_code] or (dt_script_code == "Jpan" and (text_in_script(page.pagename, "Hira") or text_in_script(page.pagename, "Kana"))) or (dt_script_code == "Kore" and text_in_script(page.pagename, "Hang")) then display_title = '<span class="' .. dt_script_code .. '">' .. page.full_raw_pagename .. '</span>' -- Keep Han entries region-neutral in the display title. elseif page_non_ascii and (dt_script_code == "Hant" or dt_script_code == "Hans") then display_title = '<span class="Hani">' .. page.full_raw_pagename .. '</span>' elseif namespace == "Reconstruction" then local matched display_title, matched = ugsub( page.full_raw_pagename, "^(Reconstruction:[^/]+/)(.+)$", function(before, term) return before .. tag_text(term, data.lang, dt_script) end ) if matched == 0 then display_title = nil end end -- FIXME: Generalize this. -- If the current language uses ur-Arab (for Urdu, etc.), ku-Arab (Central Kurdish) or pa-Arab -- (Shahmukhi, for Punjabi) and there's more than one language on the page, don't set the display title -- because these three scripts display in Nastaliq and we don't want this for terms that also exist in other -- languages that don't display in Nastaliq (e.g. Arabic or Persian) to display in Nastaliq. Because the word -- "Urdu" occurs near the end of the alphabet, Urdu fonts tend to override the fonts of other languages. -- FIXME: This is checking for more than one language on the page but instead needs to check if there are any -- languages using scripts other than the ones just mentioned. if (dt_script_code == "ur-Arab" or dt_script_code == "ku-Arab" or dt_script_code == "pa-Arab") and page.L2_list.n > 1 then display_title = nil end if display_title then mw.getCurrentFrame():callParserFunction( "DISPLAYTITLE", display_title ) end ------------ 8. Insert additional categories. ------------ if data.force_cat_output then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/force cat output]] track("force cat output") end if has_redundant_head_param then if not data.no_redundant_head_cat then insert(data.categories, full_langname .. " terms with redundant head parameter") end end -- If the first head is multiword (after removing links), maybe insert into "LANG multiword terms". if not data.nomultiwordcat and any_script_has_spaces and postype == "lemma" then local no_multiword_cat = (m_data or get_data()).no_multiword_cat if not (no_multiword_cat[langcode] or no_multiword_cat[full_langcode]) then -- Check for spaces or hyphens, but exclude prefixes and suffixes. -- Use the pagename, not the head= value, because the latter may have extra -- junk in it, e.g. superscripted text that throws off the algorithm. local no_hyphen = (m_data or get_data()).hyphen_not_multiword_sep -- Exclude hyphens if the data module states that they should for this language. local checkpattern = (no_hyphen[langcode] or no_hyphen[full_langcode]) and ".[%s፡]." or ".[%s%-፡]." if umatch(page.pagename, checkpattern) then insert(data.categories, full_langname .. " multiword terms") end end end if data.sccat then for _, head in ipairs(data.heads) do insert(data.categories, full_langname .. " " .. data.pos_category .. " in " .. head.sc:getDisplayForm()) end end -- Reconstructed terms often use weird combinations of scripts and realistically aren't spelled so much as notated. if namespace ~= "Reconstruction" then -- Map from languages to a string containing the characters to ignore when considering whether a term has -- multiple written scripts in it. Typically these are Greek or Cyrillic letters used for their phonetic -- values. local characters_to_ignore = { ["aaq"] = "α", -- Penobscot ["acy"] = "δθ", -- Cypriot Arabic ["anc"] = "γ", -- Ngas ["aou"] = "χ", -- A'ou ["awg"] = "β", -- Anguthimri ["bhp"] = "β", -- Bima ["byk"] = "θ", -- Biao ["cdy"] = "θ", -- Chadong ["clm"] = "χ", -- Klallam ["col"] = "χ", -- Colombia-Wenatchi ["coo"] = "χ", -- Comox; FIXME: others? E.g. Greek theta (θ)? ["ets"] = "θ", -- Yekhee ["gmw-gts"] = "χ", -- Gottscheerish ["hur"] = "θ", -- Halkomelem ["izh"] = "ь", -- Ingrian ["kic"] = "θ", -- Kickapoo ["lil"] = "χ", -- Lillooet ["mhz"] = "β", -- Mor (Austronesian) ["neg"]= "ӡ", -- Negidal (normally in Cyrillic) ["oui"] = "γβ", -- Old Uyghur: FIXME: others? E.g. Greek delta (δ)? ["pox"] = "χ", -- Polabian ["rom"] = "Θθ", -- Romani: International Standard; two different thetas??? ["sah"] = "ь", -- Yakut (1929 - 1939 Latin spelling) ["sjw"] = "θ", -- Shawnee ["squ"] = "χ", -- Squamish ["str"] = "χθ", -- Saanich; uses two Greek letters ["twa"] = "χ", -- Twana ["yha"] = "θ", -- Baha ["za"] = "зч", -- Zhuang; 1957-1982 alphabet used two Cyrillic letters (as well as some others like -- ƃ, ƅ, ƨ, ɯ and ɵ that look like Cyrillic or Greek but are actually Latin) ["zlw-slv"] = "χђћ", -- Slovincian; FIXME: χ is Greek, the other two are Cyrillic, but I'm not sure -- the currect characters are being chosen in the entry names ["zng"] = "θ", -- Mang } -- Determine how many real scripts are found in the pagename, where we exclude symbols and such. We exclude -- scripts whose `character_category` is false as well as Zmth (mathematical notation symbols), which has a -- category of "Mathematical notation symbols". When counting scripts, we need to elide language-specific -- variants because e.g. Beng and as-Beng have slightly different characters but we don't want to consider them -- two different scripts (e.g. [[এৰ]] has two characters which are detected respectively as Beng and as-Beng). local seen_scripts = {} local num_seen_scripts = 0 local num_loops = 0 local canon_pagename = page.pagename local ch_to_ignore = characters_to_ignore[full_langcode] if ch_to_ignore then canon_pagename = ugsub(canon_pagename, "[" .. ch_to_ignore .. "]", "") end while true do if canon_pagename == "" or num_seen_scripts >= 2 or num_loops >= 10 then break end -- Make sure we don't get into a loop checking the same script over and over again; happens with e.g. [[ᠪᡳ]] num_loops = num_loops + 1 local pagename_script = find_best_script_without_lang(canon_pagename, "None only as last resort") local script_chars = pagename_script.characters if not script_chars then -- we are stuck; this happens with None break end local script_code = pagename_script:getCode() local replaced canon_pagename, replaced = ugsub(canon_pagename, "[" .. script_chars .. "]", "") if ( replaced and script_code ~= "Zmth" and (script_data or get_script_data())[script_code] and script_data[script_code].character_category ~= false ) then script_code = script_code:gsub("^.-%-", "") if not seen_scripts[script_code] then seen_scripts[script_code] = true num_seen_scripts = num_seen_scripts + 1 end end end if num_seen_scripts > 1 then insert(data.categories, full_langname .. " terms written in multiple scripts") end end -- Categorise for unusual characters. Takes into account combining characters, so that we can categorise for characters with diacritics that aren't encoded as atomic characters (e.g. U̠). These can be in two formats: single combining characters (i.e. character + diacritic(s)) or double combining characters (i.e. character + diacritic(s) + character). Each can have any number of diacritics. local standard = data.lang:getStandardCharacters() if standard then local function char_category(char) local specials = { ["#"] = "number sign", ["("] = "parentheses", [")"] = "parentheses", ["<"] = "angle brackets", [">"] = "angle brackets", ["["] = "square brackets", ["]"] = "square brackets", ["_"] = "underscore", ["{"] = "braces", ["|"] = "vertical line", ["}"] = "braces", ["ß"] = "ẞ", ["\205\133"] = "", -- this is UTF-8 for U+0345 ( ͅ) ["\239\191\189"] = "replacement character", } char = toNFD(char) :gsub(".[\128-\191]*", function(m) local new_m = specials[m] new_m = new_m or m:uupper() return new_m end) return toNFC(char) end if full_langcode ~= "hi" and full_langcode ~= "lo" then local standard_chars_scripts = {} for _, head in ipairs(data.heads) do standard_chars_scripts[head.sc:getCode()] = true end -- Iterate over the scripts, in case there is more than one (as they can have different sets of standard characters). for code in pairs(standard_chars_scripts) do local sc_standard = data.lang:getStandardCharacters(code) if sc_standard then if page.pagename_len > 1 then local explode_standard = {} local function explode(char) explode_standard[char] = true return "" end local sc_standard = ugsub(sc_standard, page.comb_chars.combined_double, explode) sc_standard = ugsub(sc_standard,page.comb_chars.combined_single, explode) :gsub(".[\128-\191]*", explode) local num_cat_inserted for char in pairs(page.explode_pagename) do if not explode_standard[char] then if char:find("[0-9]") then if not num_cat_inserted then insert(data.categories, full_langname .. " terms spelled with numbers") num_cat_inserted = true end elseif ufind(char, page.emoji_pattern) then insert(data.categories, full_langname .. " terms spelled with emoji") else local upper = char_category(char) if not explode_standard[upper] then char = upper end insert(data.categories, full_langname .. " terms spelled with " .. char) end end end end -- If a diacritic doesn't appear in any of the standard characters, also categorise for it generally. sc_standard = toNFD(sc_standard) for diacritic in ugmatch(page.decompose_pagename, page.comb_chars.diacritics_single) do if not umatch(sc_standard, diacritic) then insert(data.categories, full_langname .. " terms spelled with ◌" .. diacritic) end end for diacritic in ugmatch(page.decompose_pagename, page.comb_chars.diacritics_double) do if not umatch(sc_standard, diacritic) then insert(data.categories, full_langname .. " terms spelled with ◌" .. diacritic .. "◌") end end end end -- Ancient Greek, Hindi and Lao handled the old way for now, as their standard chars still need to be converted to the new format (because there are a lot of them). elseif ulen(page.pagename) ~= 1 then for character in ugmatch(page.pagename, "([^" .. standard .. "])") do local upper = char_category(character) if not umatch(upper, "[" .. standard .. "]") then character = upper end insert(data.categories, full_langname .. " terms spelled with " .. character) end end end if data.heads[1].sc:isSystem("alphabet") then local pagename, i = page.pagename:ulower(), 2 while umatch(pagename, "(%a)" .. ("%1"):rep(i)) do i = i + 1 insert(data.categories, full_langname .. " terms with " .. i .. " consecutive instances of the same letter") end end -- Categorise for palindromes if not data.nopalindromecat and namespace ~= "Reconstruction" and ulen(page.pagename) > 2 -- FIXME: Use of first script here seems hacky. What is the clean way of doing this in the presence of -- multiple scripts? and is_palindrome(page.pagename, data.lang, data.heads[1].sc) then insert(data.categories, full_langname .. " palindromes") end if namespace == "" and not data.lang:hasType("reconstructed") then for _, head in ipairs(data.heads) do if page.full_raw_pagename ~= get_link_page(remove_links(head.term), data.lang, head.sc) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch/LANGCODE]] track("pagename spelling mismatch", data.lang) break end end end -- Add to various maintenance categories. export.maintenance_cats(page, data.lang, data.categories, data.whole_page_categories) ------------ 9. Format and return headwords, genders, inflections and categories. ------------ -- Format and return all the gathered information. This may add more categories (e.g. gender/number categories), -- so make sure we do it before evaluating `data.categories`. local text = '<span class="headword-line">' .. format_headword(data) .. format_headword_genders(data) .. format_inflections(data) .. '</span>' -- Language-specific categories. local cats = format_categories( data.categories, data.lang, data.sort_key, page.encoded_pagename, data.force_cat_output or test_force_categories, data.heads[1].sc ) -- Language-agnostic categories. local whole_page_cats = format_categories( data.whole_page_categories, nil, "-" ) return text .. cats .. whole_page_cats end return export tvzj9lv6j8ok5ejt4mcblkllb5zomoq 36727 36721 2026-08-12T00:40:37Z Ghybu 12 - pluralize_ 36727 Scribunto text/plain local export = {} -- Named constants for all modules used, to make it easier to swap out sandbox versions. local debug_track_module = "Module:debug/track" local en_utilities_module = "Module:en-utilities" local gender_and_number_module = "Module:gender and number" local headword_data_module = "Module:headword/data" local headword_page_module = "Module:headword/page" local links_module = "Module:links" local load_module = "Module:load" local pages_module = "Module:pages" local palindromes_module = "Module:palindromes" local pron_qualifier_module = "Module:pron qualifier" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local script_utilities_module = "Module:script utilities" local script_utilities_data_module = "Module:script utilities/data" 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 ipairs = ipairs local max = math.max local new_title = mw.title.new local pairs = pairs local require = require local toNFC = mw.ustring.toNFC local toNFD = mw.ustring.toNFD local type = type local ufind = mw.ustring.find local ugmatch = mw.ustring.gmatch local ugsub = mw.ustring.gsub local umatch = mw.ustring.match --[==[ 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 debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end local function extend(...) extend = require(table_module).extend return extend(...) 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 format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function format_genders(...) format_genders = require(gender_and_number_module).format_genders return format_genders(...) end local function format_pron_qualifiers(...) format_pron_qualifiers = require(pron_qualifier_module).format_qualifiers return format_pron_qualifiers(...) end local function full_link(...) full_link = require(links_module).full_link return full_link(...) end local function get_current_L2(...) get_current_L2 = require(pages_module).get_current_L2 return get_current_L2(...) end local function get_link_page(...) get_link_page = require(links_module).get_link_page return get_link_page(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function is_palindrome(...) is_palindrome = require(palindromes_module).is_palindrome return is_palindrome(...) end local function language_link(...) language_link = require(links_module).language_link return language_link(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function pattern_escape(...) pattern_escape = require(string_utilities_module).pattern_escape return pattern_escape(...) end local function pluralize(...) pluralize = require(en_utilities_module).pluralize return pluralize(...) end local function process_page(...) process_page = require(headword_page_module).process_page return process_page(...) end local function remove_links(...) remove_links = require(links_module).remove_links return remove_links(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function tag_text(...) tag_text = require(script_utilities_module).tag_text return tag_text(...) end local function tag_transcription(...) tag_transcription = require(script_utilities_module).tag_transcription return tag_transcription(...) end local function tag_translit(...) tag_translit = require(script_utilities_module).tag_translit return tag_translit(...) end local function trim(...) trim = require(string_utilities_module).trim return trim(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) 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 m_data local function get_data() m_data = load_data(headword_data_module) return m_data end local script_data local function get_script_data() script_data = load_data(scripts_data_module) return script_data end local script_utilities_data local function get_script_utilities_data() script_utilities_data = load_data(script_utilities_data_module) return script_utilities_data end -- If set to true, categories always appear, even in non-mainspace pages local test_force_categories = false -- Add a tracking category to track entries with certain (unusually undesirable) properties. `track_id` is an identifier -- for the particular property being tracked and goes into the tracking page. Specifically, this adds a link in the -- page text to [[Wiktionary:Tracking/headword/TRACK_ID]], meaning you can find all entries with the `track_id` property -- by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID]]. -- -- If `lang` (a language object) is given, an additional tracking page [[Wiktionary:Tracking/headword/TRACK_ID/CODE]] is -- linked to where CODE is the language code of `lang`, and you can find all entries in the combination of `track_id` -- and `lang` by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID/CODE]]. This makes it possible to -- isolate only the entries with a specific tracking property that are in a given language. Note that if `lang` -- references at etymology-only language, both that language's code and its full parent's code are tracked. local function track(track_id, lang) local tracking_page = "headword/" .. track_id if lang and lang:hasType("etymology-only") then debug_track{tracking_page, tracking_page .. "/" .. lang:getCode(), tracking_page .. "/" .. lang:getFullCode()} elseif lang then debug_track{tracking_page, tracking_page .. "/" .. lang:getCode()} else debug_track(tracking_page) end return true end local function text_in_script(text, script_code) local sc = get_script(script_code) if not sc then error("Internal error: Bad script code " .. script_code) end local characters = sc.characters local out if characters then text = ugsub(text, "%W", "") out = ufind(text, "[" .. characters .. "]") end if out then return true else return false end end local spacingPunctuation = "[%s%p]+" --[[ List of punctuation or spacing characters that are found inside of words. Used to exclude characters from the regex above. ]] local wordPunc = "-#%%&@־׳״'.·*’་•:᠊" local notWordPunc = "[^" .. wordPunc .. "]+" -- Format a term (either a head term or an inflection term) along with any left or right qualifiers, labels, references -- or customized separator: `part` is the object specifying the term (and `lang` the language of 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`; -- * a separator in `separator`, defaulting to " <i>or</i> " if this is not the first term (j > 1), otherwise "". -- `formatted` is the formatted version of the term itself, and `j` is the index of the term. local function format_term_with_qualifiers_and_refs(lang, part, formatted, j) local function part_non_empty(field) local list = part[field] if not list then return nil end if type(list) ~= "table" then error(("Internal error: Wrong type for `part.%s`=%s, should be \"table\""):format(field, mw.dumpObject(list))) end return list[1] end if part_non_empty("q") or part_non_empty("qq") or part_non_empty("l") or part_non_empty("ll") or part_non_empty("refs") then formatted = format_pron_qualifiers { lang = lang, text = formatted, q = part.q, qq = part.qq, l = part.l, ll = part.ll, refs = part.refs, } end local separator = part.separator or j > 1 and " <i>or</i> " -- use "" to request no separator if separator then formatted = separator .. formatted end return formatted end --[==[Return true if the given head is multiword according to the algorithm used in full_headword().]==] function export.head_is_multiword(head) for possibleWordBreak in ugmatch(head, spacingPunctuation) do if umatch(possibleWordBreak, notWordPunc) then return true end end return false end do local function workaround_to_exclude_chars(s) return (ugsub(s, notWordPunc, "\2%1\1")) end --[==[Add links to a multiword head.]==] function export.add_multiword_links(head, default) head = "\1" .. ugsub(head, spacingPunctuation, workaround_to_exclude_chars) .. "\2" if default then head = head :gsub("(\1[^\2]*)\\([:#][^\2]*\2)", "%1\\\\%2") :gsub("(\1[^\2]*)([:#][^\2]*\2)", "%1\\%2") end --Escape any remaining square brackets to stop them breaking links (e.g. "[citation needed]"). head = encode_entities(head, "[]", true, true) --[=[ use this when workaround is no longer needed: head = "[[" .. ugsub(head, WORDBREAKCHARS, "]]%1[[") .. "]]" Remove any empty links, which could have been created above at the beginning or end of the string. ]=] return (head :gsub("\1\2", "") :gsub("[\1\2]", {["\1"] = "[[", ["\2"] = "]]"})) end end -- In ckb.wiktionary.org, we don't have these. So, we don't need them; disabled. -- local function non_categorizable(full_raw_pagename) -- return full_raw_pagename:find("^Appendix:Gestures/") or -- -- Unsupported titles with descriptive names. -- (full_raw_pagename:find("^Unsupported titles/") and not full_raw_pagename:find("`")) -- end local function tag_text_and_add_quals_and_refs(data, head, formatted, j) -- Add language and script wrapper. formatted = tag_text(formatted, data.lang, head.sc, "head", nil, j == 1 and data.id or nil) -- Add qualifiers, labels, references and separator. return format_term_with_qualifiers_and_refs(data.lang, head, formatted, j) end -- Format a headword with transliterations. local function format_headword(data) -- Are there non-empty transliterations? local has_translits = false local has_manual_translits = false ------ Format the headwords. ------ local head_parts = {} local unique_head_parts = {} local has_multiple_heads = not not data.heads[2] for j, head in ipairs(data.heads) do if head.tr or head.ts then has_translits = true end if head.tr and head.tr_manual or head.ts then has_manual_translits = true end local formatted -- Apply processing to the headword, for formatting links and such. if head.term:find("[[", nil, true) and head.sc:getCode() ~= "Image" then formatted = language_link{term = head.term, lang = data.lang} else formatted = data.lang:makeDisplayText(head.term, head.sc, true) end local head_part = tag_text_and_add_quals_and_refs(data, head, formatted, j) insert(head_parts, head_part) -- If multiple heads, try to determine whether all heads display the same. To do this we need to effectively -- rerun the text tagging and addition of qualifiers and references, using 1 for all indices. if has_multiple_heads then local unique_head_part if j == 1 then unique_head_part = head_part else unique_head_part = tag_text_and_add_quals_and_refs(data, head, formatted, 1) end unique_head_parts[unique_head_part] = true end end local set_size = 0 if has_multiple_heads then for _ in pairs(unique_head_parts) do set_size = set_size + 1 end end if set_size == 1 then head_parts = head_parts[1] else head_parts = concat(head_parts) end if has_manual_translits then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr/LANGCODE]] track("manual-tr", data.lang) end ------ Format the transliterations and transcriptions. ------ local translits_formatted if has_translits then local translit_parts = {} for _, head in ipairs(data.heads) do if head.tr or head.ts then local this_parts = {} if head.tr then insert(this_parts, tag_translit(head.tr, data.lang:getCode(), "head", nil, head.tr_manual)) if head.ts then insert(this_parts, " ") end end if head.ts then insert(this_parts, "/" .. tag_transcription(head.ts, data.lang:getCode(), "head") .. "/") end insert(translit_parts, concat(this_parts)) end end translits_formatted = " (" .. concat(translit_parts, " <i>or</i> ") .. ")" local langname = data.lang:getCanonicalName() local transliteration_page = new_title(langname .. " transliteration", "Wiktionary") local saw_translit_page = false if transliteration_page and transliteration_page.exists then translits_formatted = " [[Wiktionary:" .. langname .. " transliteration|•]]" .. translits_formatted saw_translit_page = true end -- If data.lang is an etymology-only language and we didn't find a translation page for it, fall back to the -- full parent. if not saw_translit_page and data.lang:hasType("etymology-only") then langname = data.lang:getFullName() transliteration_page = new_title(langname .. " transliteration", "Wiktionary") if transliteration_page and transliteration_page.exists then translits_formatted = " [[Wiktionary:" .. langname .. " transliteration|•]]" .. translits_formatted end end else translits_formatted = "" end ------ Paste heads and transliterations/transcriptions. ------ local lemma_gloss if data.gloss then lemma_gloss = ' <span class="ib-content qualifier-content">' .. data.gloss .. '</span>' else lemma_gloss = "" end return head_parts .. translits_formatted .. lemma_gloss end local function format_headword_genders(data) local retval = "" if data.genders and data.genders[1] then if data.gloss then retval = "," end local pos_for_cat if not data.nogendercat then local no_gender_cat = (m_data or get_data()).no_gender_cat if not (no_gender_cat[data.lang:getCode()] or no_gender_cat[data.lang:getFullCode()]) then pos_for_cat = (m_data or get_data()).pos_for_gender_number_cat[data.pos_category:gsub("^reconstructed ", "")] end end local text, cats = format_genders(data.genders, data.lang, pos_for_cat) if cats then extend(data.categories, cats) end retval = retval .. "&nbsp;" .. text end return retval end local function format_inflection_parts(data, parts) local any_part_translit = false for j, part in ipairs(parts) do if type(part) ~= "table" then part = {term = part} end local partaccel = part.accel local face = part.face or "bold" if face ~= "bold" and face ~= "plain" and face ~= "hypothetical" then error("The face `" .. face .. "` " .. ( (script_utilities_data or get_script_utilities_data()).faces[face] and "should not be used for non-headword terms on the headword line." or "is invalid." )) end -- Here the final part 'or data.nolinkinfl' allows to have 'nolinkinfl=true' -- right into the 'data' table to disable inflection links of the entire headword -- when inflected forms aren't entry-worthy, e.g.: in Vulgar Latin local nolinkinfl = part.face == "hypothetical" or (part.nolink and track("nolink") or part.nolinkinfl) or ( data.nolink and track("nolink") or data.nolinkinfl) local formatted if part.label then -- FIXME: There should be a better way of italicizing a label. As is, this isn't customizable. formatted = "<i>" .. part.label .. "</i>" else -- Convert the term into a full link. Don't show a transliteration here unless enable_auto_translit is -- requested, either at the `parts` level (i.e. per inflection) or at the `data.inflections` level (i.e. -- specified for all inflections). This is controllable in {{head}} using autotrinfl=1 for all inflections, -- or fNautotr=1 for an individual inflection (remember that a single inflection may be associated with -- multiple terms). The reason for doing this is to avoid clutter in headword lines by default in languages -- where the script is relatively straightforward to read by learners (e.g. Greek, Russian), but allow it -- to be enabled in languages with more complex scripts (e.g. Arabic). local tr = part.translit or (not (parts.enable_auto_translit or data.inflections.enable_auto_translit) and "-" or nil) if tr ~= "-" then any_part_translit = true end formatted = full_link( { term = not nolinkinfl and part.term or nil, alt = part.alt or (nolinkinfl and part.term or nil), lang = part.lang or data.lang, sc = part.sc or parts.sc or nil, gloss = part.gloss, pos = part.pos, lit = part.lit, id = part.id, genders = part.genders, tr = tr, ts = part.transcription, accel = partaccel or parts.accel, }, face ) end parts[j] = format_term_with_qualifiers_and_refs(part.lang or data.lang, part, formatted, j) end local parts_output if parts[1] then parts_output = (parts.label and " " or "") .. concat(parts) elseif parts.request then parts_output = " <small>[please provide]</small>" insert(data.categories, "Requests for inflections in " .. data.lang:getFullName() .. " entries") else parts_output = "" end local parts_label = parts.label and ("<i>" .. parts.label .. "</i>") or "" return format_term_with_qualifiers_and_refs(data.lang, parts, parts_label .. parts_output, 1), any_part_translit end -- Format the inflections following the headword. local function format_inflections(data) local any_part_translit = false if data.inflections and data.inflections[1] then -- Format each inflection individually. for key, infl in ipairs(data.inflections) do local this_any_part_translit data.inflections[key], this_any_part_translit = format_inflection_parts(data, infl) if this_any_part_translit then any_part_translit = true end end local concat_result = concat(data.inflections, ", ") return " (" .. concat_result .. ")" else return "" end end --[==[ Returns the plural form of `pos`, a raw part of speech input, which could be singular or plural. Irregular plural POS are taken into account (e.g. "kanji" pluralizes to "kanji"). ]==] function export.pluralize_pos(pos) -- Make the plural form of the part of speech return (m_data or get_data()).irregular_plurals[pos] or pos:sub(-1) == "s" and pos or pluralize(pos) end --[==[ Return "lemma" if the given POS is a lemma, "non-lemma form" if a non-lemma form, or nil if unknown. The POS passed in must be in its plural form ("nouns", "prefixes", etc.). If you have a POS in its singular form, call {export.pluralize_pos()} above to pluralize it in a smart fashion that knows when to add "-s" and when to add "-es", and also takes into account any irregular plurals. If `best_guess` is given and the POS is in neither the lemma nor non-lemma list, guess based on whether it ends in " forms"; otherwise, return nil. ]==] function export.pos_lemma_or_nonlemma(plpos, best_guess) local isLemma = (m_data or get_data()).lemmas -- Is it a lemma category? if isLemma[plpos] then return "lemma" end local plpos_no_recon = plpos:gsub("^reconstructed ", "") if isLemma[plpos_no_recon] then return "lemma" end -- Is it a nonlemma category? local isNonLemma = (m_data or get_data()).nonlemmas if isNonLemma[plpos] or isNonLemma[plpos_no_recon] then return "non-lemma form" end local plpos_no_mut = plpos:gsub("^mutated ", "") if isLemma[plpos_no_mut] or isNonLemma[plpos_no_mut] then return "non-lemma form" elseif best_guess then return plpos:find(" forms$") and "non-lemma form" or "lemma" else return nil end end --[==[ Canonicalize a part of speech as specified in 2= in {{tl|head}}. This checks for POS aliases and non-lemma form aliases ending in 'f', and then pluralizes if the POS term does not have an invariable plural. ]==] function export.canonicalize_pos(pos) -- FIXME: Temporary code to throw an error for alias 'pre' (= preposition) that will go away. if pos == "pre" then -- Don't throw error on 'pref' as it's an alias for "prefix". error("POS 'pre' for 'preposition' no longer allowed as it's too ambiguous; use 'prep'") end -- Likewise for pro = pronoun. if pos == "pro" or pos == "prof" then error("POS 'pro' for 'pronoun' no longer allowed as it's too ambiguous; use 'pron'") end local data = m_data or get_data() if data.pos_aliases[pos] then pos = data.pos_aliases[pos] elseif pos:sub(-1) == "f" then pos = pos:sub(1, -2) pos = (data.pos_aliases[pos] or pos) .. " forms" end return pos end -- Find and return the maximum index in the array `data[element]` (which may have gaps in it), and initialize it to a -- zero-length array if unspecified. Check to make sure all keys are numeric (other than "maxindex", which is set by -- [[Module:parameters]] for list parameters), all values are strings, and unless `allow_blank_string` is given, -- no blank (zero-length) strings are present. local function init_and_find_maximum_index(data, element, allow_blank_string) local maxind = 0 if not data[element] then data[element] = {} end local typ = type(data[element]) if typ ~= "table" then error(("In full_headword(), `data.%s` must be an array but is a %s"):format(element, typ)) end for k, v in pairs(data[element]) do if k ~= "maxindex" then if type(k) ~= "number" then error(("Unrecognized non-numeric key '%s' in `data.%s`"):format(k, element)) end if k > maxind then maxind = k end if v then if type(v) ~= "string" then error(("For key '%s' in `data.%s`, value should be a string but is a %s"):format(k, element, type(v))) end if not allow_blank_string and v == "" then error(("For key '%s' in `data.%s`, blank string not allowed; use 'false' for the default"):format(k, element)) end end end end return maxind end --[==[ -- Add the page to various maintenance categories for the language and the -- whole page. These are placed in the headword somewhat arbitrarily, but -- mainly because headword templates are mandatory for entries (meaning that -- in theory it provides full coverage). -- -- This is provided as an external entry point so that modules which transclude -- information from other entries (such as {{tl|ja-see}}) can take advantage -- of this feature as well, because they are used in place of a conventional -- headword template.]==] do -- Handle any manual sortkeys that have been specified in raw categories -- by tracking if they are the same or different from the automatically- -- generated sortkey, so that we can track them in maintenance -- categories. local function handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) sortkey = sortkey or lang:makeSortKey(page.pagename) -- If there are raw categories with no sortkey, then they will be -- sorted based on the default MediaWiki sortkey, so we check against -- that. if tbl == true then if page.raw_defaultsort ~= sortkey then insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys") end return end local redundant, different for k in pairs(tbl) do if k == sortkey then redundant = true else different = true end end if redundant then insert(lang_cats, lang:getFullName() .. " terms with redundant sortkeys") end if different then insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys") end return sortkey end function export.maintenance_cats(page, lang, lang_cats, page_cats) extend(page_cats, page.cats) lang = lang:getFull() -- since we are just generating categories local canonical = lang:getCanonicalName() local tbl, sortkey = page.wikitext_topic_cat[lang:getCode()] if tbl then sortkey = handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) insert(lang_cats, canonical .. " entries with topic categories using raw markup") end tbl = page.wikitext_langname_cat[canonical] if tbl then handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats) insert(lang_cats, canonical .. " entries with language name categories using raw markup") end if get_current_L2() ~= canonical then insert(lang_cats, canonical .. " entries with incorrect language header") -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/incorrect language header]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/incorrect language header/LANGCODE]] track("incorrect language header", lang) end end end --[==[This is the primary external entry point. {{lua|full_headword(data)}} This is used by {{temp|head}} and various language-specific headword templates (e.g. {{temp|ru-adj}} for Russian adjectives, {{temp|de-noun}} for German nouns, etc.) to display an entire headword line. See [[#Further explanations for full_headword()]] ]==] function export.full_headword(data) -- Prevent data from being destructively modified. local data = shallow_copy(data) ------------ 1. Basic checks for old-style (multi-arg) calling convention. ------------ if data.getCanonicalName then error("In full_headword(), the first argument `data` needs to be a Lua object (table) of properties, not a language object") end if not data.lang or type(data.lang) ~= "table" or not data.lang.getCode then error("In full_headword(), the first argument `data` needs to be a Lua object (table) and `data.lang` must be a language object") end if data.id and type(data.id) ~= "string" then error("The id in the data table should be a string.") end ------------ 2. Initialize pagename etc. ------------ local langcode = data.lang:getCode() local full_langcode = data.lang:getFullCode() local langname = data.lang:getCanonicalName() local full_langname = data.lang:getFullName() local raw_pagename, page = data.pagename if raw_pagename and raw_pagename ~= (m_data or get_data()).pagename then -- for testing, doc pages, etc. page = process_page(raw_pagename) else page = (m_data or get_data()).page end -- Check the namespace against the language type. local namespace = page.namespace if namespace == "" then if data.lang:hasType("reconstructed") then error("Entries in " .. langname .. " must be placed in the Reconstruction: namespace") elseif data.lang:hasType("appendix-constructed") then error("Entries in " .. langname .. " must be placed in the Appendix: namespace") end elseif namespace == "Citations" or namespace == "Thesaurus" then error("Headword templates should not be used in the " .. namespace .. ": namespace.") end ------------ 3. Initialize `data.heads` table; if old-style, convert to new-style. ------------ if type(data.heads) == "table" and type(data.heads[1]) == "table" then -- new-style if data.translits or data.transcriptions then error("In full_headword(), if `data.heads` is new-style (array of head objects), `data.translits` and `data.transcriptions` cannot be given") end else -- convert old-style `heads`, `translits` and `transcriptions` to new-style local maxind = max( init_and_find_maximum_index(data, "heads"), init_and_find_maximum_index(data, "translits", true), init_and_find_maximum_index(data, "transcriptions", true) ) for i = 1, maxind do data.heads[i] = { term = data.heads[i], tr = data.translits[i], ts = data.transcriptions[i], } end end -- Make sure there's at least one head. if not data.heads[1] then data.heads[1] = {} end ------------ 4. Initialize and validate `data.categories` and `data.whole_page_categories`, and determine `pos_category` if not given, and add basic categories. ------------ -- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]] if data.altform then data.noposcat = true end init_and_find_maximum_index(data, "categories") init_and_find_maximum_index(data, "whole_page_categories") local pos_category_already_present = false if data.categories[1] then local escaped_langname = pattern_escape(full_langname) local matches_lang_pattern = "^" .. escaped_langname .. " " for _, cat in ipairs(data.categories) do -- Does the category begin with the language name? If not, tag it with a tracking category. if not cat:find(matches_lang_pattern) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category/LANGCODE]] track("no lang category", data.lang) end end -- If `pos_category` not given, try to infer it from the first specified category. If this doesn't work, we -- throw an error below. if not data.pos_category and data.categories[1]:find(matches_lang_pattern) then data.pos_category = data.categories[1]:gsub(matches_lang_pattern, "") -- Optimization to avoid inserting category already present. pos_category_already_present = true end end if not data.pos_category then error("`data.pos_category` not specified and could not be inferred from the categories given in " .. "`data.categories`. Either specify the plural part of speech in `data.pos_category` " .. "(e.g. \"proper nouns\") or ensure that the first category in `data.categories` is formed from the " .. "language's canonical name plus the plural part of speech (e.g. \"Norwegian Bokmål proper nouns\")." ) end -- Insert a category at the beginning for the part of speech unless it's already present or `data.noposcat` given. if not pos_category_already_present and not data.noposcat then local pos_category = data.pos_category .. " بە " .. full_langname -- FIXME: [[User:Theknightwho]] Why is this special case here? Please add an explanatory comment. if pos_category ~= "Translingual Han characters" then insert(data.categories, 1, pos_category) end end -- Try to determine whether the part of speech refers to a lemma or a non-lemma form; if we can figure this out, -- add an appropriate category. local postype = export.pos_lemma_or_nonlemma(data.pos_category) if not postype then -- We don't know what this category is, so tag it with a tracking category. -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/LANGCODE]] track("unrecognized pos", data.lang) -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/POS]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/POS/LANGCODE]] track("unrecognized pos/pos/" .. data.pos_category, data.lang) elseif not data.noposcat then insert(data.categories, 1, postype .. " بە " .. full_langname) end -- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]] if data.altform then insert(data.categories, 1, full_langname .. " alternative forms") end ------------ 5. Create a default headword, and add links to multiword page names. ------------ -- Determine if term is reconstructed local is_reconstructed = namespace == "Reconstruction" or data.lang:hasType("reconstructed") -- Create a default headword based on the pagename, which is determined in -- advance by the data module so that it only needs to be done once. local default_head = page.pagename -- Add links to multi-word page names when appropriate if not (is_reconstructed or data.nolinkhead) then local no_links = (m_data or get_data()).no_multiword_links if not (no_links[langcode] or no_links[full_langcode]) and export.head_is_multiword(default_head) then default_head = export.add_multiword_links(default_head, true) end end if is_reconstructed then default_head = "*" .. default_head end ------------ 6. Fill in missing values in `data.heads`. ------------ -- True if any script among the headword scripts has spaces in it. local any_script_has_spaces = false -- True if any term has a redundant head= param. local has_redundant_head_param = false for _, head in ipairs(data.heads) do ------ 6a. If missing head, replace with default head. if not head.term then head.term = default_head elseif head.term == default_head then has_redundant_head_param = true elseif head.term:find("^[!?]$") then -- If explicit head= just consists of ! or ?, add it to the end of the default head. head.term = default_head .. head.term end if is_reconstructed then local head_term = head.term if head_term:find("%[%[") then head_term = remove_links(head_term) end if head_term:sub(1, 1) ~= "*" then error("The headword '" .. head_term .. "' must begin with '*' to indicate that it is reconstructed.") end end ------ 6b. Try to detect the script(s) if not provided. If a per-head script is provided, that takes precedence, ------ otherwise fall back to the overall script if given. If neither given, autodetect the script. local auto_sc = data.lang:findBestScript(head.term) if ( auto_sc:getCode() == "None" and find_best_script_without_lang(head.term):getCode() ~= "None" ) then insert(data.categories, full_langname .. " terms in nonstandard scripts") end if not (head.sc or data.sc) then -- No script code given, so use autodetected script. head.sc = auto_sc else if not head.sc then -- Overall script code given. head.sc = data.sc end -- Track uses of sc parameter. if head.sc:getCode() == auto_sc:getCode() then insert(data.categories, full_langname .. " terms with redundant script codes") else insert(data.categories, full_langname .. " terms with non-redundant manual script codes") end end -- If using a discouraged character sequence, add to maintenance category. if head.sc:hasNormalizationFixes() == true then local composed_head = toNFC(head.term) if head.sc:fixDiscouragedSequences(composed_head) ~= composed_head then insert(data.whole_page_categories, "Pages using discouraged character sequences") end end any_script_has_spaces = any_script_has_spaces or head.sc:hasSpaces() ------ 6c. Create automatic transliterations for any non-Latin headwords without manual translit given ------ (provided automatic translit is available, e.g. not in Persian or Hebrew). -- Make transliterations head.tr_manual = nil -- Try to generate a transliteration if necessary if head.tr == "-" then head.tr = nil else local notranslit = (m_data or get_data()).notranslit if not (notranslit[langcode] or notranslit[full_langcode]) and head.sc:isTransliterated() then head.tr_manual = not not head.tr local text = head.term if not data.lang:link_tr(head.sc) then text = remove_links(text) end local automated_tr, tr_categories automated_tr, head.tr_fail, tr_categories = data.lang:transliterate(text, head.sc) if automated_tr or head.tr_fail then local manual_tr = head.tr if manual_tr then if (remove_links(manual_tr) == remove_links(automated_tr)) and (not head.tr_fail) then insert(data.categories, full_langname .. " terms with redundant transliterations") elseif not head.tr_fail then insert(data.categories, full_langname .. " terms with non-redundant manual transliterations") end end if not manual_tr then head.tr = automated_tr extend(data.categories, tr_categories) end end -- There is still no transliteration? -- Add the entry to a cleanup category. if not head.tr then head.tr = "<small>transliteration needed</small>" -- FIXME: No current support for 'Request for transliteration of Classical Persian terms' or similar. -- Consider adding this support in [[Module:category tree/poscatboiler/data/entry maintenance]]. insert(data.categories, "Requests for transliteration of " .. full_langname .. " terms") else -- Otherwise, trim it. head.tr = trim(head.tr) end end end -- Link to the transliteration entry for languages that require this. if head.tr and data.lang:link_tr(head.sc) then head.tr = full_link{ term = head.tr, lang = data.lang, sc = get_script("Latn"), tr = "-" } end end ------------ 7. Maybe tag the title with the appropriate script code, using the `display_title` mechanism. ------------ -- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace. -- (FIXME: Don't make assumptions like this, and if you need to do so, throw an error if the assumption is violated.) -- Avoid tagging ASCII as Hani even when it is tagged as Hani in the headword, as in [[check]]. The check for ASCII -- might need to be expanded to a check for any Latin characters and whitespace or punctuation. local display_title -- Where there are multiple headwords, use the script for the first. This assumes the first headword is similar to -- the pagename, and that headwords that are in different scripts from the pagename aren't first. This seems to be -- about the best we can do (alternatively we could potentially do script detection on the pagename). local dt_script = data.heads[1].sc local dt_script_code = dt_script:getCode() local page_non_ascii = namespace == "" and not page.pagename:find("^[%z\1-\127]+$") local unsupported_pagename, unsupported = page.full_raw_pagename:gsub("^Unsupported titles/", "") if unsupported == 1 and page.unsupported_titles[unsupported_pagename] then display_title = 'Unsupported titles/<span class="' .. dt_script_code .. '">' .. page.unsupported_titles[unsupported_pagename] .. '</span>' elseif page_non_ascii and (m_data or get_data()).toBeTagged[dt_script_code] or (dt_script_code == "Jpan" and (text_in_script(page.pagename, "Hira") or text_in_script(page.pagename, "Kana"))) or (dt_script_code == "Kore" and text_in_script(page.pagename, "Hang")) then display_title = '<span class="' .. dt_script_code .. '">' .. page.full_raw_pagename .. '</span>' -- Keep Han entries region-neutral in the display title. elseif page_non_ascii and (dt_script_code == "Hant" or dt_script_code == "Hans") then display_title = '<span class="Hani">' .. page.full_raw_pagename .. '</span>' elseif namespace == "Reconstruction" then local matched display_title, matched = ugsub( page.full_raw_pagename, "^(Reconstruction:[^/]+/)(.+)$", function(before, term) return before .. tag_text(term, data.lang, dt_script) end ) if matched == 0 then display_title = nil end end -- FIXME: Generalize this. -- If the current language uses ur-Arab (for Urdu, etc.), ku-Arab (Central Kurdish) or pa-Arab -- (Shahmukhi, for Punjabi) and there's more than one language on the page, don't set the display title -- because these three scripts display in Nastaliq and we don't want this for terms that also exist in other -- languages that don't display in Nastaliq (e.g. Arabic or Persian) to display in Nastaliq. Because the word -- "Urdu" occurs near the end of the alphabet, Urdu fonts tend to override the fonts of other languages. -- FIXME: This is checking for more than one language on the page but instead needs to check if there are any -- languages using scripts other than the ones just mentioned. if (dt_script_code == "ur-Arab" or dt_script_code == "ku-Arab" or dt_script_code == "pa-Arab") and page.L2_list.n > 1 then display_title = nil end if display_title then mw.getCurrentFrame():callParserFunction( "DISPLAYTITLE", display_title ) end ------------ 8. Insert additional categories. ------------ if data.force_cat_output then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/force cat output]] track("force cat output") end if has_redundant_head_param then if not data.no_redundant_head_cat then insert(data.categories, full_langname .. " terms with redundant head parameter") end end -- If the first head is multiword (after removing links), maybe insert into "LANG multiword terms". if not data.nomultiwordcat and any_script_has_spaces and postype == "lemma" then local no_multiword_cat = (m_data or get_data()).no_multiword_cat if not (no_multiword_cat[langcode] or no_multiword_cat[full_langcode]) then -- Check for spaces or hyphens, but exclude prefixes and suffixes. -- Use the pagename, not the head= value, because the latter may have extra -- junk in it, e.g. superscripted text that throws off the algorithm. local no_hyphen = (m_data or get_data()).hyphen_not_multiword_sep -- Exclude hyphens if the data module states that they should for this language. local checkpattern = (no_hyphen[langcode] or no_hyphen[full_langcode]) and ".[%s፡]." or ".[%s%-፡]." if umatch(page.pagename, checkpattern) then insert(data.categories, full_langname .. " multiword terms") end end end if data.sccat then for _, head in ipairs(data.heads) do insert(data.categories, full_langname .. " " .. data.pos_category .. " in " .. head.sc:getDisplayForm()) end end -- Reconstructed terms often use weird combinations of scripts and realistically aren't spelled so much as notated. if namespace ~= "Reconstruction" then -- Map from languages to a string containing the characters to ignore when considering whether a term has -- multiple written scripts in it. Typically these are Greek or Cyrillic letters used for their phonetic -- values. local characters_to_ignore = { ["aaq"] = "α", -- Penobscot ["acy"] = "δθ", -- Cypriot Arabic ["anc"] = "γ", -- Ngas ["aou"] = "χ", -- A'ou ["awg"] = "β", -- Anguthimri ["bhp"] = "β", -- Bima ["byk"] = "θ", -- Biao ["cdy"] = "θ", -- Chadong ["clm"] = "χ", -- Klallam ["col"] = "χ", -- Colombia-Wenatchi ["coo"] = "χ", -- Comox; FIXME: others? E.g. Greek theta (θ)? ["ets"] = "θ", -- Yekhee ["gmw-gts"] = "χ", -- Gottscheerish ["hur"] = "θ", -- Halkomelem ["izh"] = "ь", -- Ingrian ["kic"] = "θ", -- Kickapoo ["lil"] = "χ", -- Lillooet ["mhz"] = "β", -- Mor (Austronesian) ["neg"]= "ӡ", -- Negidal (normally in Cyrillic) ["oui"] = "γβ", -- Old Uyghur: FIXME: others? E.g. Greek delta (δ)? ["pox"] = "χ", -- Polabian ["rom"] = "Θθ", -- Romani: International Standard; two different thetas??? ["sah"] = "ь", -- Yakut (1929 - 1939 Latin spelling) ["sjw"] = "θ", -- Shawnee ["squ"] = "χ", -- Squamish ["str"] = "χθ", -- Saanich; uses two Greek letters ["twa"] = "χ", -- Twana ["yha"] = "θ", -- Baha ["za"] = "зч", -- Zhuang; 1957-1982 alphabet used two Cyrillic letters (as well as some others like -- ƃ, ƅ, ƨ, ɯ and ɵ that look like Cyrillic or Greek but are actually Latin) ["zlw-slv"] = "χђћ", -- Slovincian; FIXME: χ is Greek, the other two are Cyrillic, but I'm not sure -- the currect characters are being chosen in the entry names ["zng"] = "θ", -- Mang } -- Determine how many real scripts are found in the pagename, where we exclude symbols and such. We exclude -- scripts whose `character_category` is false as well as Zmth (mathematical notation symbols), which has a -- category of "Mathematical notation symbols". When counting scripts, we need to elide language-specific -- variants because e.g. Beng and as-Beng have slightly different characters but we don't want to consider them -- two different scripts (e.g. [[এৰ]] has two characters which are detected respectively as Beng and as-Beng). local seen_scripts = {} local num_seen_scripts = 0 local num_loops = 0 local canon_pagename = page.pagename local ch_to_ignore = characters_to_ignore[full_langcode] if ch_to_ignore then canon_pagename = ugsub(canon_pagename, "[" .. ch_to_ignore .. "]", "") end while true do if canon_pagename == "" or num_seen_scripts >= 2 or num_loops >= 10 then break end -- Make sure we don't get into a loop checking the same script over and over again; happens with e.g. [[ᠪᡳ]] num_loops = num_loops + 1 local pagename_script = find_best_script_without_lang(canon_pagename, "None only as last resort") local script_chars = pagename_script.characters if not script_chars then -- we are stuck; this happens with None break end local script_code = pagename_script:getCode() local replaced canon_pagename, replaced = ugsub(canon_pagename, "[" .. script_chars .. "]", "") if ( replaced and script_code ~= "Zmth" and (script_data or get_script_data())[script_code] and script_data[script_code].character_category ~= false ) then script_code = script_code:gsub("^.-%-", "") if not seen_scripts[script_code] then seen_scripts[script_code] = true num_seen_scripts = num_seen_scripts + 1 end end end if num_seen_scripts > 1 then insert(data.categories, full_langname .. " terms written in multiple scripts") end end -- Categorise for unusual characters. Takes into account combining characters, so that we can categorise for characters with diacritics that aren't encoded as atomic characters (e.g. U̠). These can be in two formats: single combining characters (i.e. character + diacritic(s)) or double combining characters (i.e. character + diacritic(s) + character). Each can have any number of diacritics. local standard = data.lang:getStandardCharacters() if standard then local function char_category(char) local specials = { ["#"] = "number sign", ["("] = "parentheses", [")"] = "parentheses", ["<"] = "angle brackets", [">"] = "angle brackets", ["["] = "square brackets", ["]"] = "square brackets", ["_"] = "underscore", ["{"] = "braces", ["|"] = "vertical line", ["}"] = "braces", ["ß"] = "ẞ", ["\205\133"] = "", -- this is UTF-8 for U+0345 ( ͅ) ["\239\191\189"] = "replacement character", } char = toNFD(char) :gsub(".[\128-\191]*", function(m) local new_m = specials[m] new_m = new_m or m:uupper() return new_m end) return toNFC(char) end if full_langcode ~= "hi" and full_langcode ~= "lo" then local standard_chars_scripts = {} for _, head in ipairs(data.heads) do standard_chars_scripts[head.sc:getCode()] = true end -- Iterate over the scripts, in case there is more than one (as they can have different sets of standard characters). for code in pairs(standard_chars_scripts) do local sc_standard = data.lang:getStandardCharacters(code) if sc_standard then if page.pagename_len > 1 then local explode_standard = {} local function explode(char) explode_standard[char] = true return "" end local sc_standard = ugsub(sc_standard, page.comb_chars.combined_double, explode) sc_standard = ugsub(sc_standard,page.comb_chars.combined_single, explode) :gsub(".[\128-\191]*", explode) local num_cat_inserted for char in pairs(page.explode_pagename) do if not explode_standard[char] then if char:find("[0-9]") then if not num_cat_inserted then insert(data.categories, full_langname .. " terms spelled with numbers") num_cat_inserted = true end elseif ufind(char, page.emoji_pattern) then insert(data.categories, full_langname .. " terms spelled with emoji") else local upper = char_category(char) if not explode_standard[upper] then char = upper end insert(data.categories, full_langname .. " terms spelled with " .. char) end end end end -- If a diacritic doesn't appear in any of the standard characters, also categorise for it generally. sc_standard = toNFD(sc_standard) for diacritic in ugmatch(page.decompose_pagename, page.comb_chars.diacritics_single) do if not umatch(sc_standard, diacritic) then insert(data.categories, full_langname .. " terms spelled with ◌" .. diacritic) end end for diacritic in ugmatch(page.decompose_pagename, page.comb_chars.diacritics_double) do if not umatch(sc_standard, diacritic) then insert(data.categories, full_langname .. " terms spelled with ◌" .. diacritic .. "◌") end end end end -- Ancient Greek, Hindi and Lao handled the old way for now, as their standard chars still need to be converted to the new format (because there are a lot of them). elseif ulen(page.pagename) ~= 1 then for character in ugmatch(page.pagename, "([^" .. standard .. "])") do local upper = char_category(character) if not umatch(upper, "[" .. standard .. "]") then character = upper end insert(data.categories, full_langname .. " terms spelled with " .. character) end end end if data.heads[1].sc:isSystem("alphabet") then local pagename, i = page.pagename:ulower(), 2 while umatch(pagename, "(%a)" .. ("%1"):rep(i)) do i = i + 1 insert(data.categories, full_langname .. " terms with " .. i .. " consecutive instances of the same letter") end end -- Categorise for palindromes if not data.nopalindromecat and namespace ~= "Reconstruction" and ulen(page.pagename) > 2 -- FIXME: Use of first script here seems hacky. What is the clean way of doing this in the presence of -- multiple scripts? and is_palindrome(page.pagename, data.lang, data.heads[1].sc) then insert(data.categories, full_langname .. " palindromes") end if namespace == "" and not data.lang:hasType("reconstructed") then for _, head in ipairs(data.heads) do if page.full_raw_pagename ~= get_link_page(remove_links(head.term), data.lang, head.sc) then -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch]] -- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch/LANGCODE]] track("pagename spelling mismatch", data.lang) break end end end -- Add to various maintenance categories. export.maintenance_cats(page, data.lang, data.categories, data.whole_page_categories) ------------ 9. Format and return headwords, genders, inflections and categories. ------------ -- Format and return all the gathered information. This may add more categories (e.g. gender/number categories), -- so make sure we do it before evaluating `data.categories`. local text = '<span class="headword-line">' .. format_headword(data) .. format_headword_genders(data) .. format_inflections(data) .. '</span>' -- Language-specific categories. local cats = format_categories( data.categories, data.lang, data.sort_key, page.encoded_pagename, data.force_cat_output or test_force_categories, data.heads[1].sc ) -- Language-agnostic categories. local whole_page_cats = format_categories( data.whole_page_categories, nil, "-" ) return text .. cats .. whole_page_cats end return export 8jnndvghzz4o10crky5s8chfsyef3k1 10 120 36728 358 2026-08-12T00:42:17Z Ghybu 12 ناو 36728 wikitext text/x-wiki {{head|ckb|ناو|sc=ku-Arab|sort={{{sort|}}}|head={{{head|}}}|tr={{{tr|}}}}}{{#if:{{{pl|}}}|&#32;(''plural'' '''{{l-self|ckb|accel=plural-form-of|{{{pl}}}|sc=ku-Arab}}''')}}<!-- --><noinclude>{{documentation}}</noinclude> qd9770eb69xmd70xj6t901zrgx1yowq 0 491 36737 20683 2026-08-12T01:17:28Z Ghybu 12 36737 wikitext text/x-wiki == ئینگلیزی == ===وشەڕەتناسی === * لە لاتین adumbrātus ھاتووە. === کار === {{head|en|کار}} # [[ھێما]]، [[ئاماژە]]. # کاتێک تەنھا شتە [[سەرەکی]]یەکان دەڵێیت نەک [[باسکردن]]ی شتەکان بە [[دەقیق]] و [[زانیاری]]یەوە. === سەرچاوەکان === * فەرھەنگی ڤەژین * [https://dictionary.cambridge.org/ زانکۆی کامبرێج] * وێبگەی زاراوەزانی و فەرھەنگی vocabulary d695iron6a1ygo381lnp0tu5n4eb2lb 0 2597 36720 35296 2026-08-11T22:18:53Z Ghybu 12 /* ئینگلیزی */ 36720 wikitext text/x-wiki == ئینگلیزی == [[پەڕگە:Dordogne River 05.jpg|thumb|ڕووبارێک]] === وشەڕەتناسی === لە [[ئینگلیزیی ناوەڕاست]]ەوە ''[[ryver]]'' ،[[rivere|''rivere'']] ،''river'' لە [[ئانگلۆ-نۆرمن]]ەوە ''rivere''، لە [[فەڕەنسیی کۆن]]ەوە ''[[riviere]]''، لە [[لاتینیی گشتی]]یەوە [[*rīpāria|''rīpāria*'']] («کەناری ڕووبار، کەنار، ڕووبار»)، لە [[لاتینی]]یەوە ''[[rīpārius]]'' («لە کەناری ڕووبارێک»)، لە لاتینییەوە ''[[rīpa]]'' («کەناری ڕووبار»)، لە پڕۆتۆ-ھیندی و ئەورووپییەوە [[*h₁reyp|''h₁reyp*'']] («ڕووشاندن»). ===گۆکردن=== * {{IPA|en|/ˈɹɪvɚ/|a=GA}}, {{enPR|rĭv'ər}} * {{IPA|en|/ˈɹɪvə/|a=RP}} * {{audio|en|en-us-river.ogg|a=US}} * {{audio|en|En-uk-river.ogg|a=UK}} === ناو === {{en-noun}} # [[ڕووبار]]، [[ڕۆ]]، [[چەم]] jyco87spefu272k6a4p9m181qbeuxg0 0 2827 36713 22973 2026-08-11T21:44:36Z Ghybu 12 /* تورکی */ 36713 wikitext text/x-wiki == تورکی == === وشەڕەتناسی === {{واڵا}} === ناو === {{head|tr|ناو}} # [[ئاو]] th3cxovhm5tqxcku17raopbr6manoyu 0 3130 36710 7519 2026-08-11T12:59:33Z Ghybu 12 /* ئینگلیزی */ 36710 wikitext text/x-wiki == ئینگلیزی == === ناو === {{en-noun|~}} # [[ئاو]] # [[دەریا]]، [[ڕووبار]]، [[دەریاچە]] [[پۆل:ئینگلیزی]] nopyo016zyr8glgiesly3wvz14zckoq 0 3910 36714 26091 2026-08-11T21:45:57Z Ghybu 12 /* عەرەبی */ 36714 wikitext text/x-wiki == عەرەبی == === وشەڕەتناسی === {{واڵا}} ===ناو=== {{head|fa|tr=âb|ناو}} # مانگی هەشت، [[ئاب]] 3ep4zh53tx5q6i5cyr7piopn711zndj 36715 36714 2026-08-11T21:50:54Z Ghybu 12 /* عەرەبی */ 36715 wikitext text/x-wiki == عەرەبی == === وشەڕەتناسی === {{واڵا}} ===ناو=== {{head|ar|ناو|head=آب}} # مانگی هەشت، [[ئاب]] == فارسی == === وشەڕەتناسی === {{واڵا}} === ناو === {{head|fa|tr=âb|ناو}} # [[ئاو]] 7ntklprl3fx0u9t2gfp710dc16uczc9 36716 36715 2026-08-11T21:52:04Z Ghybu 12 /* ناو */ 36716 wikitext text/x-wiki == عەرەبی == === وشەڕەتناسی === {{واڵا}} ===ناو=== {{head|ar|ناو|head=آب|g=m}} # مانگی هەشت، [[ئاب]] == فارسی == === وشەڕەتناسی === {{واڵا}} === ناو === {{head|fa|tr=âb|ناو}} # [[ئاو]] pgkjqnzec6uco7gj7bahabxv7kaa65e 0 4074 36701 9612 2026-08-11T12:29:27Z Ghybu 12 36701 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|watter}} * فەڕەنسی: {{t|fr|eau|m}} * عەرەبی: {{t|ar|ماء}} * فارسی: {{t|fa|آب|tr=âb}} * سویدی: {{t|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} bx6bqv0pccopqxl1l60vi23fbfyzu8x 36702 36701 2026-08-11T12:29:56Z Ghybu 12 /* کوردیی ناوەندی */ 36702 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|watter}} * فەڕەنسی: {{t|fr|eau|m}} * عەرەبی: {{t|ar|ماء}} * فارسی: {{t|fa|آب|tr=âb}} * سویدی: {{t|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} r1wpbezimbs67h2dkzmsnwdopcrzkjz 36703 36702 2026-08-11T12:30:16Z Ghybu 12 /* وەرگێڕانەکان */ 36703 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|watter}} * فەڕەنسی: {{t|fr|eau|f}} * عەرەبی: {{t|ar|ماء}} * فارسی: {{t|fa|آب|tr=âb}} * سویدی: {{t|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} ql2s6y53i7m5wah0l8leciurszlc5rx 36704 36703 2026-08-11T12:32:52Z Ghybu 12 /* کوردیی ناوەندی */ 36704 wikitext text/x-wiki == کوردیی ناوەندی == [[File:Water7.jpg|thumb|ئاو]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|watter}} * فەڕەنسی: {{t|fr|eau|f}} * عەرەبی: {{t|ar|ماء}} * فارسی: {{t|fa|آب|tr=âb}} * سویدی: {{t|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} 8llwnde9h3xram4zcw41kghot00n355 36705 36704 2026-08-11T12:35:47Z Ghybu 12 /* وەرگێڕانەکان */ 36705 wikitext text/x-wiki == کوردیی ناوەندی == [[File:Water7.jpg|thumb|ئاو]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|water}} * فەڕەنسی: {{t|fr|eau|f}} * عەرەبی: {{t|ar|ماء}} * فارسی: {{t|fa|آب|tr=âb}} * سویدی: {{t|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} 2hi6jtz3q2ayswut2gwwv5dmvdhqttt 36706 36705 2026-08-11T12:39:29Z Ghybu 12 /* وەرگێڕانەکان */ 36706 wikitext text/x-wiki == کوردیی ناوەندی == [[File:Water7.jpg|thumb|ئاو]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|water}} * فەڕەنسی: {{t+|fr|eau|f}} * عەرەبی: {{t+|ar|ماء}} * فارسی: {{t+|fa|آب|tr=âb}} * سویدی: {{t+|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} hhb6wmsypatj3zbrngkmse43r3aoqak 36709 36706 2026-08-11T12:57:32Z Ghybu 12 /* کوردیی ناوەندی */ 36709 wikitext text/x-wiki == کوردیی ناوەندی == [[File:Water fountain near the art museum in Milwaukee, Wisconsin 6178.jpg|thumb|ئاو]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|water}} * فەڕەنسی: {{t+|fr|eau|f}} * عەرەبی: {{t+|ar|ماء}} * فارسی: {{t+|fa|آب|tr=âb}} * سویدی: {{t+|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} m5i8lb6pnooy57rmb60i7bcrp6rexk0 36711 36709 2026-08-11T13:01:02Z Ghybu 12 /* وەرگێڕانەکان */ 36711 wikitext text/x-wiki == کوردیی ناوەندی == [[File:Water fountain near the art museum in Milwaukee, Wisconsin 6178.jpg|thumb|ئاو]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # پێکھاتووە لە شلەیەک کە لە دوو ھایدرۆجین و ئۆکسجینێک دروست بووە. # بە [[سپێرم]]ی پیاو دەڵێن ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|}} * ئینگلیزی: {{t+|en|water}} * فەڕەنسی: {{t+|fr|eau|f}} * عەرەبی: {{t+|ar|ماء}} * فارسی: {{t+|fa|آب|tr=âb}} * سویدی: {{t+|sv|vatten}} * تورکی: {{t+|tr|su}} {{وەرگێڕان-بن}} qhik50s8a3dz5wixpfmpp1lq6lp02un 0 6011 36717 23722 2026-08-11T21:54:55Z Ghybu 12 /* عەرەبی */ 36717 wikitext text/x-wiki == عەرەبی == === وشەڕەتناسی === {{واڵا}} ===ناو=== {{ar-noun|مَاء|m}} # [[ئاو]] 7kl1a7ffej86iozd40nfg2or2d8hdlf 0 6730 36718 16012 2026-08-11T22:08:06Z Ghybu 12 36718 wikitext text/x-wiki == کوردیی ناوەندی == [[پەڕگە:Lidder River 1.jpg|thumb|وێنەی ڕووبارێک.]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # ڕووبار، ڕێڕەوێکی ئاوی سروشتی فراوانە، ئاوی سازگاری تێ ئەڕژێت. ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|}} * ئینگلیزی: {{t+|en|river}} * فەڕەنسی: {{t+|fr|rivière|f}} {{وەرگێڕان-بن}} 8q8989vjkm56sxcscutlovr34w6mmv5 36719 36718 2026-08-11T22:16:15Z Ghybu 12 /* کوردیی ناوەندی */ 36719 wikitext text/x-wiki == کوردیی ناوەندی == [[پەڕگە:Lidder River 1.jpg|thumb|وێنەی ڕووبارێک.]] === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # ڕووبار، ڕێڕەوێکی ئاوی سروشتی فراوانە، ئاوی سازگاری تێ ئەڕژێت. ==== ئەمانەش ببینە ==== * [[چەم]] ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|}} * ئینگلیزی: {{t+|en|river}} * فەڕەنسی: {{t+|fr|rivière|f}} {{وەرگێڕان-بن}} l19b8ziio5whym9zd9l7cl64g9jfxby 0 7339 36694 17704 2026-08-11T12:00:22Z Ghybu 12 36694 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # کوردیی ناوەندی یان سۆرانی یەکێکە لە زارەکانی زمانی کوردی، کە لە باشووری کوردستان (کوردستانی عێراق) و ڕۆژهەڵاتی کوردستان (کوردستانی ئێران) قسەی پێ دەکرێت. ئەم زارە لە سەدەی هەژدەدا وەکوو زمانی نووسینی میرنشینی بابانەکان دەر کەوت و شاعیرانی وەکوو نالی و سالم و کوردی لە شیعرەکانیاندا بەکاریان هێنا. دواتر بوو بە زمانی ئەدەبیی دەڤەرەکە و لە سەردەمی کۆماری باشووری کوردستانی شێخ مەحموودی حەفیددا یەکەم قوتابخانەی کوردی لە سلێمانی کرایەوە کە تێیدا خوێندن بەو زارە بوو. لە ئێستا زمانی کوردی لە پاڵ زمانی عەرەبیدا زمانی فەرمی دەوڵەتی عێراقە، کە بە گشتی کوردیی ناوەندی ئەو ڕۆڵەی پێ دراوە و ڕۆڵی نیمچە ستانداردێک لە پارێزگا کوردییەکانی عێراقدا دەگێڕێت بە ناوچە کێشەلەسەرەکانیشەوە. سەرباری ئەوەش خوێندن لە پارێزگای دهۆک بە شێوەزاری بادینیی زاری کورمانجییە بەڵام بە ئەلفبێی کوردیی ناوەندی. ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|Central Kurdish}} * فەڕەنسی: {{t+|fr|kurde central}} * عەرەبی: {{t+|ar|الكُرْدِيَّة المَرْكَزِيَّة}} * فارسی: {{t|fa|کردی مرکزی|tr=kordi markazi}} * تورکی: {{t+|tr|Orta Kürtçe}} {{وەرگێڕان-بن}} jyki0mdowc1s3fgainkergbyldoj493 36696 36694 2026-08-11T12:05:52Z Ghybu 12 /* وەرگێڕانەکان */ 36696 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # کوردیی ناوەندی یان سۆرانی یەکێکە لە زارەکانی زمانی کوردی، کە لە باشووری کوردستان (کوردستانی عێراق) و ڕۆژهەڵاتی کوردستان (کوردستانی ئێران) قسەی پێ دەکرێت. ئەم زارە لە سەدەی هەژدەدا وەکوو زمانی نووسینی میرنشینی بابانەکان دەر کەوت و شاعیرانی وەکوو نالی و سالم و کوردی لە شیعرەکانیاندا بەکاریان هێنا. دواتر بوو بە زمانی ئەدەبیی دەڤەرەکە و لە سەردەمی کۆماری باشووری کوردستانی شێخ مەحموودی حەفیددا یەکەم قوتابخانەی کوردی لە سلێمانی کرایەوە کە تێیدا خوێندن بەو زارە بوو. لە ئێستا زمانی کوردی لە پاڵ زمانی عەرەبیدا زمانی فەرمی دەوڵەتی عێراقە، کە بە گشتی کوردیی ناوەندی ئەو ڕۆڵەی پێ دراوە و ڕۆڵی نیمچە ستانداردێک لە پارێزگا کوردییەکانی عێراقدا دەگێڕێت بە ناوچە کێشەلەسەرەکانیشەوە. سەرباری ئەوەش خوێندن لە پارێزگای دهۆک بە شێوەزاری بادینیی زاری کورمانجییە بەڵام بە ئەلفبێی کوردیی ناوەندی. ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|Central Kurdish}} * فەڕەنسی: {{t|fr|kurde central}} * عەرەبی: {{t|ar|الكُرْدِيَّة المَرْكَزِيَّة}} * فارسی: {{t|fa|کردی مرکزی|tr=kordi markazi}} * تورکی: {{t+|tr|Orta Kürtçe}} {{وەرگێڕان-بن}} dluem21rwkxn9c21xjfrj3afb7jm8pe 36712 36696 2026-08-11T18:03:15Z Ghybu 12 /* وەرگێڕانەکان */ 36712 wikitext text/x-wiki == کوردیی ناوەندی == === وشەڕەتناسی === {{واڵا}} === گۆکردن === * {{ckb-IPA}} === ناو === {{ckb-noun}} # کوردیی ناوەندی یان سۆرانی یەکێکە لە زارەکانی زمانی کوردی، کە لە باشووری کوردستان (کوردستانی عێراق) و ڕۆژهەڵاتی کوردستان (کوردستانی ئێران) قسەی پێ دەکرێت. ئەم زارە لە سەدەی هەژدەدا وەکوو زمانی نووسینی میرنشینی بابانەکان دەر کەوت و شاعیرانی وەکوو نالی و سالم و کوردی لە شیعرەکانیاندا بەکاریان هێنا. دواتر بوو بە زمانی ئەدەبیی دەڤەرەکە و لە سەردەمی کۆماری باشووری کوردستانی شێخ مەحموودی حەفیددا یەکەم قوتابخانەی کوردی لە سلێمانی کرایەوە کە تێیدا خوێندن بەو زارە بوو. لە ئێستا زمانی کوردی لە پاڵ زمانی عەرەبیدا زمانی فەرمی دەوڵەتی عێراقە، کە بە گشتی کوردیی ناوەندی ئەو ڕۆڵەی پێ دراوە و ڕۆڵی نیمچە ستانداردێک لە پارێزگا کوردییەکانی عێراقدا دەگێڕێت بە ناوچە کێشەلەسەرەکانیشەوە. سەرباری ئەوەش خوێندن لە پارێزگای دهۆک بە شێوەزاری بادینیی زاری کورمانجییە بەڵام بە ئەلفبێی کوردیی ناوەندی. ==== وەرگێڕانەکان ==== {{وەرگێڕان-سەر|زمان}} * ئینگلیزی: {{t+|en|Central Kurdish}} * فەڕەنسی: {{t|fr|kurde central|m}} * عەرەبی: {{t|ar|الكُرْدِيَّة المَرْكَزِيَّة}} * فارسی: {{t|fa|کردی مرکزی|tr=kordi markazi}} * تورکی: {{t+|tr|Orta Kürtçe}} {{وەرگێڕان-بن}} hc80c355uwj9vcl3ajegul7pac6sc4a 0 7341 36699 18368 2026-08-11T12:23:02Z Ghybu 12 /* ناو */ 36699 wikitext text/x-wiki == کرمانجی == === ناو === {{kmr-noun}} # [[ئاو]] [[Category:کرمانجی]] b1dojj0imr5pj5sjquypcfa5jcgsij8 36700 36699 2026-08-11T12:23:18Z Ghybu 12 /* ناو */ 36700 wikitext text/x-wiki == کرمانجی == === ناو === {{kmr-noun|f}} # [[ئاو]] [[Category:کرمانجی]] 3ppiysnrl1h42f9ycqieinnv9a75kjv 36708 36700 2026-08-11T12:45:22Z Ghybu 12 /* کرمانجی */ 36708 wikitext text/x-wiki == کرمانجی == === گۆکردن === * {{kmr-IPA}} * {{دەنگ|kmr|LL-Q36368 (kur)-Dildadil-av.wav}} * {{دەنگ|kmr|LL-Q36163 (kmr)-Ebulfîda-av.wav}} === ناو === {{kmr-noun|f}} # [[ئاو]] [[Category:کرمانجی]] rt750bv0cs5hgp6zuaynjv1ht9wqtau 0 7449 36698 17942 2026-08-11T12:22:02Z Ghybu 12 /* کرمانجی */ 36698 wikitext text/x-wiki == کرمانجی == === کار === {{kmr-verb}} # [[هەڵساندن]] [[Category:کرمانجی]] e5xf7szj844orkxzj7h5nmdofsv3iwa 0 7518 36695 18045 2026-08-11T12:02:34Z Ghybu 12 /* ناو */ 36695 wikitext text/x-wiki == کرمانجی == === ناو === {{kmr-noun|m}} # [[دێ]] [[Category:کرمانجی]] eoa1gzwp2e5fucp8gbmc5c2duwkqp1y 0 7583 36730 36569 2026-08-12T00:49:02Z Ghybu 12 /* ھاوماناکان */ 36730 wikitext text/x-wiki == کرمانجی == === گۆکردن === * {{kmr-IPA}} * {{دەنگ|kmr|LL-Q36163 (kmr)-Key Mîrza-şîn.wav}} ==== ھاوەڵناو ==== {{kmr-adj}} #[[شین]] === ناو === {{kmr-noun|f}} #[[شین]] [[Category:کرمانجی]] igr6sgq4lyeup8ijm3qmgvy6uoq45aj 0 8830 36736 33453 2026-08-12T01:12:14Z Ghybu 12 /* کوردیی ناوەندی */ 36736 wikitext text/x-wiki == کوردیی ناوەندی == ===وشەڕەتناسی === {{واڵا}} === ناو === {{ckb-proper noun}} # ناوێکی بەناوبانگی [[کوردی]]یە # 7j2rx1ee880axzl2b8jgunhaq57ktjc 10 8905 36735 20315 2026-08-12T00:52:39Z Ghybu 12 ھاوەڵناو 36735 wikitext text/x-wiki {{head|ckb|ھاوەڵناو|head={{{head|}}}|tr={{{tr|}}}}}<!-- --><noinclude>{{documentation}}</noinclude> 3y7c8gjk465pc2m7brcmf0soij5jrmu 10 9170 36729 27144 2026-08-12T00:43:20Z Ghybu 12 کار 36729 wikitext text/x-wiki {{head|ckb|کار|sort={{{sort|}}}|head={{{head|}}}<!-- -->|{{#if:{{{tr|}}}|{{#switch: {{{tr|}}}|trans = transitive|intrans = intransitive|both = transitive and intransitive}} }}<!-- -->|<!-- -->|{{#if:{{{prstem|}}}|present stem}}<!-- -->|{{{prstem|}}}<!-- -->|f2alt={{{prstem|}}}-<!-- -->|f2tr={{xlit|ckb|{{{prstem|}}}}}-<!-- -->|{{#if:{{{prstem2|}}}|or}}<!-- -->|{{{prstem2|}}}<!-- -->|f3alt={{{prstem|}}}-<!-- -->|f3tr={{xlit|ckb|{{{prstem2|}}}}}-<!-- -->}}<!-- --><noinclude>{{documentation}}</noinclude> 1zp099cx9d3ezufrnufag0ls3f0xabn 828 9176 36723 36507 2026-08-12T00:11:57Z Ghybu 12 ناو 36723 Scribunto text/plain local export = {} local pos_functions = {} local m_scripts = require("Module:scripts") local en_utilities_module = "Module:en-utilities" local lang = require("Module:languages").getByCode("kmr") local langname = lang:getCanonicalName() local ku_sc = m_scripts.getByCode("ku-Arab") local PAGENAME = mw.loadData("Module:headword/data").pagename local boolean = {type = "boolean"} local list = {list = true} local suffix_categories = { ["adjectives"] = true, ["adverbs"] = true, ["nouns"] = true, ["verbs"] = true, } local function track(page) require("Module:debug").track("kmr-headword/" .. page) return true end local function glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end local function process_arabic_spellings(spellings) local inflection = {} for _, spelling in ipairs(spellings) do table.insert(inflection, {term = spelling, sc = ku_sc}) end inflection.label = "Arabic spelling" return inflection end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local tracking_categories = {} local poscat = frame.args[1] or error("Plural part of speech e.g. 'nouns' has not been specified. Please pass parameter 1 to the module invocation.") local params = { ["head"] = list, ["tr"] = {list = true, allow_holes = true}, ["id"] = {}, ["ar"] = list, ["suff"] = boolean, ["c"] = boolean, } if pos_functions[poscat] then for key, val in pairs(pos_functions[poscat].params) do params[key] = val end end local parargs = frame:getParent().args local args = require("Module:parameters").process(parargs, params) local data = { lang = lang, pos_category = poscat, categories = {}, heads = args["head"], translits = args["tr"], genders = {}, inflections = {}, id = args["id"], categories = {} } if args["suff"] then data.pos_category = "suffixes" if suffix_categories[poscat] then local singular_poscat = poscat:gsub("s$", "") table.insert(data.categories, langname .. " " .. singular_poscat .. "-forming suffixes") else error("No category exists for suffixes forming " .. poscat .. ".") end end if pos_functions[poscat] then pos_functions[poscat].func(args, data, tracking_categories) end if #args["ar"] > 0 then table.insert(data.inflections, process_arabic_spellings(args["ar"])) end return require("Module:headword").full_headword(data) .. require("Module:utilities").format_categories(tracking_categories, lang) end pos_functions["verbs"] = { params = { [1] = {}, [2] = {}, }, func = function(args, data, tracking_categories) if args[1] then table.insert(data.inflections, {label = "third-person singular simple present", args[1], accel = {form = '3|s|pres'}}) end if args[2] then table.insert(data.inflections, {label = "past tense", args[2], accel = {form = 'past'}}) end end } pos_functions["adjectives"] = { params = { [1] = {alias_of = "comparative", list = false}, ["comparative"] = list, --comparative(s) [2] = {alias_of = "superlative", list = false}, ["superlative"] = list, --superlative(s) ["c"] = boolean, }, func = function(args, data, tracking_categories) if args.comparative[1] == "-" then table.insert(data.inflections, {label = "not comparable"}) table.insert(data.categories, langname .. " uncomparable adjectives") else if #args.comparative > 0 then args.comparative.label = glossary_link("comparative") args.comparative.accel = {form = "comparative"} table.insert(data.inflections, args.comparative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("comparative"), accel = {form = 'comparative'}, {term = PAGENAME ..'tir'}}) end end if #args.superlative > 0 then args.superlative.label = glossary_link("superlative") args.superlative.accel = {form = "superlative"} table.insert(data.inflections, args.superlative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("superlative"), accel = {form = 'superlative'}, {term = '[[herî]] ' .. PAGENAME}, {term = '[[tewrî]] ' .. PAGENAME}}) end end end end } local noun_params = { [1] = {alias_of = "g", list = false}, ["g"] = list, --gender(s) [2] = {alias_of = "pl", list = false}, ["pl"] = list, --plural(s) ["f"] = list, --feminine form(s) ["m"] = list, --masculine form(s) } local allowed_genders = { ["m"] = true, ["f"] = true, ["n"] = true, ["mf"] = true, ["mfbysense"] = true, ["m-p"] = true, ["f-p"] = true, ["n-p"] = true, } local function do_nouns(pos, args, data, tracking_categories) local genders = {} for _, g in ipairs(args.g) do if not allowed_genders[g] then error("Unrecognized gender: " .. g) end if g == "mf" then table.insert(genders, "m") table.insert(genders, "f") else table.insert(genders, g) end end if #genders > 0 then data.genders = genders else data.genders = {"?"} end local plpos = require(en_utilities_module).pluralize(pos) -- Check for special plural signals local mode = nil if args.pl[1] == "?" or args.pl[1] == "!" or args.pl[1] == "-" or args.pl[1] == "-~" or args.pl[1] == "~" or args.pl[1] == "#" then mode = args.pl[1] table.remove(args.pl, 1) -- Remove the mode parameter end if mode == "?" then -- Plural is unknown table.insert(data.categories, langname .. " " .. plpos .. " with unknown or uncertain plurals") elseif mode == "!" then -- Plural is not attested table.insert(data.inflections, {label = "plural not attested"}) table.insert(data.categories, langname .. " " .. plpos .. " with unattested plurals") return elseif mode == "-" then -- Uncountable noun; may occasionally have a plural table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = glossary_link("uncountable")}) elseif mode == "-~" then table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = "usually " .. glossary_link("uncountable")}) elseif mode == "~" then -- Mixed countable/uncountable noun, always has a plural table.insert(data.inflections, {label = glossary_link("countable") .. " and " .. glossary_link("uncountable")}) table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.categories, langname .. " countable " .. plpos) elseif mode == "#" or pos == "noun" then -- Countable nouns; the default for regular nouns but not proper nouns if mode == "#" then table.insert(data.inflections, {label = glossary_link("countable")}) end -- Not enough nouns properly use - in the second argument -- table.insert(data.categories, langname .. " countable " .. plpos) end if #args.pl > 0 then args.pl.label = "plural" args.pl.accel = {form = "p"} table.insert(data.inflections, args.pl) end if #args.f > 0 then args.f.label = "feminine" table.insert(data.inflections, args.f) end if #args.m > 0 then args.m.label = "masculine" table.insert(data.inflections, args.m) end end pos_functions["ناو"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("noun", args, data, tracking_categories) end, } pos_functions["proper nouns"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("proper noun", args, data, tracking_categories) end, } return export bujkr7jmls38wxm8y3z6ly0l073z7jj 36724 36723 2026-08-12T00:14:24Z Ghybu 12 ھاوماناکان 36724 Scribunto text/plain local export = {} local pos_functions = {} local m_scripts = require("Module:scripts") local en_utilities_module = "Module:en-utilities" local lang = require("Module:languages").getByCode("kmr") local langname = lang:getCanonicalName() local ku_sc = m_scripts.getByCode("ku-Arab") local PAGENAME = mw.loadData("Module:headword/data").pagename local boolean = {type = "boolean"} local list = {list = true} local suffix_categories = { ["adjectives"] = true, ["adverbs"] = true, ["nouns"] = true, ["verbs"] = true, } local function track(page) require("Module:debug").track("kmr-headword/" .. page) return true end local function glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end local function process_arabic_spellings(spellings) local inflection = {} for _, spelling in ipairs(spellings) do table.insert(inflection, {term = spelling, sc = ku_sc}) end inflection.label = "Arabic spelling" return inflection end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local tracking_categories = {} local poscat = frame.args[1] or error("Plural part of speech e.g. 'nouns' has not been specified. Please pass parameter 1 to the module invocation.") local params = { ["head"] = list, ["tr"] = {list = true, allow_holes = true}, ["id"] = {}, ["ar"] = list, ["suff"] = boolean, ["c"] = boolean, } if pos_functions[poscat] then for key, val in pairs(pos_functions[poscat].params) do params[key] = val end end local parargs = frame:getParent().args local args = require("Module:parameters").process(parargs, params) local data = { lang = lang, pos_category = poscat, categories = {}, heads = args["head"], translits = args["tr"], genders = {}, inflections = {}, id = args["id"], categories = {} } if args["suff"] then data.pos_category = "suffixes" if suffix_categories[poscat] then local singular_poscat = poscat:gsub("s$", "") table.insert(data.categories, langname .. " " .. singular_poscat .. "-forming suffixes") else error("No category exists for suffixes forming " .. poscat .. ".") end end if pos_functions[poscat] then pos_functions[poscat].func(args, data, tracking_categories) end if #args["ar"] > 0 then table.insert(data.inflections, process_arabic_spellings(args["ar"])) end return require("Module:headword").full_headword(data) .. require("Module:utilities").format_categories(tracking_categories, lang) end pos_functions["کار"] = { params = { [1] = {}, [2] = {}, }, func = function(args, data, tracking_categories) if args[1] then table.insert(data.inflections, {label = "third-person singular simple present", args[1], accel = {form = '3|s|pres'}}) end if args[2] then table.insert(data.inflections, {label = "past tense", args[2], accel = {form = 'past'}}) end end } pos_functions["ھاوماناکان"] = { params = { [1] = {alias_of = "comparative", list = false}, ["comparative"] = list, --comparative(s) [2] = {alias_of = "superlative", list = false}, ["superlative"] = list, --superlative(s) ["c"] = boolean, }, func = function(args, data, tracking_categories) if args.comparative[1] == "-" then table.insert(data.inflections, {label = "not comparable"}) table.insert(data.categories, langname .. " uncomparable adjectives") else if #args.comparative > 0 then args.comparative.label = glossary_link("comparative") args.comparative.accel = {form = "comparative"} table.insert(data.inflections, args.comparative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("comparative"), accel = {form = 'comparative'}, {term = PAGENAME ..'tir'}}) end end if #args.superlative > 0 then args.superlative.label = glossary_link("superlative") args.superlative.accel = {form = "superlative"} table.insert(data.inflections, args.superlative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("superlative"), accel = {form = 'superlative'}, {term = '[[herî]] ' .. PAGENAME}, {term = '[[tewrî]] ' .. PAGENAME}}) end end end end } local noun_params = { [1] = {alias_of = "g", list = false}, ["g"] = list, --gender(s) [2] = {alias_of = "pl", list = false}, ["pl"] = list, --plural(s) ["f"] = list, --feminine form(s) ["m"] = list, --masculine form(s) } local allowed_genders = { ["m"] = true, ["f"] = true, ["n"] = true, ["mf"] = true, ["mfbysense"] = true, ["m-p"] = true, ["f-p"] = true, ["n-p"] = true, } local function do_nouns(pos, args, data, tracking_categories) local genders = {} for _, g in ipairs(args.g) do if not allowed_genders[g] then error("Unrecognized gender: " .. g) end if g == "mf" then table.insert(genders, "m") table.insert(genders, "f") else table.insert(genders, g) end end if #genders > 0 then data.genders = genders else data.genders = {"?"} end local plpos = require(en_utilities_module).pluralize(pos) -- Check for special plural signals local mode = nil if args.pl[1] == "?" or args.pl[1] == "!" or args.pl[1] == "-" or args.pl[1] == "-~" or args.pl[1] == "~" or args.pl[1] == "#" then mode = args.pl[1] table.remove(args.pl, 1) -- Remove the mode parameter end if mode == "?" then -- Plural is unknown table.insert(data.categories, langname .. " " .. plpos .. " with unknown or uncertain plurals") elseif mode == "!" then -- Plural is not attested table.insert(data.inflections, {label = "plural not attested"}) table.insert(data.categories, langname .. " " .. plpos .. " with unattested plurals") return elseif mode == "-" then -- Uncountable noun; may occasionally have a plural table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = glossary_link("uncountable")}) elseif mode == "-~" then table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = "usually " .. glossary_link("uncountable")}) elseif mode == "~" then -- Mixed countable/uncountable noun, always has a plural table.insert(data.inflections, {label = glossary_link("countable") .. " and " .. glossary_link("uncountable")}) table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.categories, langname .. " countable " .. plpos) elseif mode == "#" or pos == "noun" then -- Countable nouns; the default for regular nouns but not proper nouns if mode == "#" then table.insert(data.inflections, {label = glossary_link("countable")}) end -- Not enough nouns properly use - in the second argument -- table.insert(data.categories, langname .. " countable " .. plpos) end if #args.pl > 0 then args.pl.label = "plural" args.pl.accel = {form = "p"} table.insert(data.inflections, args.pl) end if #args.f > 0 then args.f.label = "feminine" table.insert(data.inflections, args.f) end if #args.m > 0 then args.m.label = "masculine" table.insert(data.inflections, args.m) end end pos_functions["ناو"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("noun", args, data, tracking_categories) end, } pos_functions["proper nouns"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("proper noun", args, data, tracking_categories) end, } return export nv5wvrgmnrqo9wouulbvuw5ea24vckv 36732 36724 2026-08-12T00:50:24Z Ghybu 12 ھاوەڵناو 36732 Scribunto text/plain local export = {} local pos_functions = {} local m_scripts = require("Module:scripts") local en_utilities_module = "Module:en-utilities" local lang = require("Module:languages").getByCode("kmr") local langname = lang:getCanonicalName() local ku_sc = m_scripts.getByCode("ku-Arab") local PAGENAME = mw.loadData("Module:headword/data").pagename local boolean = {type = "boolean"} local list = {list = true} local suffix_categories = { ["adjectives"] = true, ["adverbs"] = true, ["nouns"] = true, ["verbs"] = true, } local function track(page) require("Module:debug").track("kmr-headword/" .. page) return true end local function glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end local function process_arabic_spellings(spellings) local inflection = {} for _, spelling in ipairs(spellings) do table.insert(inflection, {term = spelling, sc = ku_sc}) end inflection.label = "Arabic spelling" return inflection end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local tracking_categories = {} local poscat = frame.args[1] or error("Plural part of speech e.g. 'nouns' has not been specified. Please pass parameter 1 to the module invocation.") local params = { ["head"] = list, ["tr"] = {list = true, allow_holes = true}, ["id"] = {}, ["ar"] = list, ["suff"] = boolean, ["c"] = boolean, } if pos_functions[poscat] then for key, val in pairs(pos_functions[poscat].params) do params[key] = val end end local parargs = frame:getParent().args local args = require("Module:parameters").process(parargs, params) local data = { lang = lang, pos_category = poscat, categories = {}, heads = args["head"], translits = args["tr"], genders = {}, inflections = {}, id = args["id"], categories = {} } if args["suff"] then data.pos_category = "suffixes" if suffix_categories[poscat] then local singular_poscat = poscat:gsub("s$", "") table.insert(data.categories, langname .. " " .. singular_poscat .. "-forming suffixes") else error("No category exists for suffixes forming " .. poscat .. ".") end end if pos_functions[poscat] then pos_functions[poscat].func(args, data, tracking_categories) end if #args["ar"] > 0 then table.insert(data.inflections, process_arabic_spellings(args["ar"])) end return require("Module:headword").full_headword(data) .. require("Module:utilities").format_categories(tracking_categories, lang) end pos_functions["کار"] = { params = { [1] = {}, [2] = {}, }, func = function(args, data, tracking_categories) if args[1] then table.insert(data.inflections, {label = "third-person singular simple present", args[1], accel = {form = '3|s|pres'}}) end if args[2] then table.insert(data.inflections, {label = "past tense", args[2], accel = {form = 'past'}}) end end } pos_functions["ھاوەڵناو"] = { params = { [1] = {alias_of = "comparative", list = false}, ["comparative"] = list, --comparative(s) [2] = {alias_of = "superlative", list = false}, ["superlative"] = list, --superlative(s) ["c"] = boolean, }, func = function(args, data, tracking_categories) if args.comparative[1] == "-" then table.insert(data.inflections, {label = "not comparable"}) table.insert(data.categories, langname .. " uncomparable adjectives") else if #args.comparative > 0 then args.comparative.label = glossary_link("comparative") args.comparative.accel = {form = "comparative"} table.insert(data.inflections, args.comparative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("comparative"), accel = {form = 'comparative'}, {term = PAGENAME ..'tir'}}) end end if #args.superlative > 0 then args.superlative.label = glossary_link("superlative") args.superlative.accel = {form = "superlative"} table.insert(data.inflections, args.superlative) else if args["c"] then table.insert(data.inflections, {label = glossary_link("superlative"), accel = {form = 'superlative'}, {term = '[[herî]] ' .. PAGENAME}, {term = '[[tewrî]] ' .. PAGENAME}}) end end end end } local noun_params = { [1] = {alias_of = "g", list = false}, ["g"] = list, --gender(s) [2] = {alias_of = "pl", list = false}, ["pl"] = list, --plural(s) ["f"] = list, --feminine form(s) ["m"] = list, --masculine form(s) } local allowed_genders = { ["m"] = true, ["f"] = true, ["n"] = true, ["mf"] = true, ["mfbysense"] = true, ["m-p"] = true, ["f-p"] = true, ["n-p"] = true, } local function do_nouns(pos, args, data, tracking_categories) local genders = {} for _, g in ipairs(args.g) do if not allowed_genders[g] then error("Unrecognized gender: " .. g) end if g == "mf" then table.insert(genders, "m") table.insert(genders, "f") else table.insert(genders, g) end end if #genders > 0 then data.genders = genders else data.genders = {"?"} end local plpos = require(en_utilities_module).pluralize(pos) -- Check for special plural signals local mode = nil if args.pl[1] == "?" or args.pl[1] == "!" or args.pl[1] == "-" or args.pl[1] == "-~" or args.pl[1] == "~" or args.pl[1] == "#" then mode = args.pl[1] table.remove(args.pl, 1) -- Remove the mode parameter end if mode == "?" then -- Plural is unknown table.insert(data.categories, langname .. " " .. plpos .. " with unknown or uncertain plurals") elseif mode == "!" then -- Plural is not attested table.insert(data.inflections, {label = "plural not attested"}) table.insert(data.categories, langname .. " " .. plpos .. " with unattested plurals") return elseif mode == "-" then -- Uncountable noun; may occasionally have a plural table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = glossary_link("uncountable")}) elseif mode == "-~" then table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.inflections, {label = "usually " .. glossary_link("uncountable")}) elseif mode == "~" then -- Mixed countable/uncountable noun, always has a plural table.insert(data.inflections, {label = glossary_link("countable") .. " and " .. glossary_link("uncountable")}) table.insert(data.categories, langname .. " uncountable " .. plpos) table.insert(data.categories, langname .. " countable " .. plpos) elseif mode == "#" or pos == "noun" then -- Countable nouns; the default for regular nouns but not proper nouns if mode == "#" then table.insert(data.inflections, {label = glossary_link("countable")}) end -- Not enough nouns properly use - in the second argument -- table.insert(data.categories, langname .. " countable " .. plpos) end if #args.pl > 0 then args.pl.label = "plural" args.pl.accel = {form = "p"} table.insert(data.inflections, args.pl) end if #args.f > 0 then args.f.label = "feminine" table.insert(data.inflections, args.f) end if #args.m > 0 then args.m.label = "masculine" table.insert(data.inflections, args.m) end end pos_functions["ناو"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("noun", args, data, tracking_categories) end, } pos_functions["proper nouns"] = { params = noun_params, func = function(args, data, tracking_categories) return do_nouns("proper noun", args, data, tracking_categories) end, } return export 4p4ljnvkb2bqh4eceygbnka6dzsktov 10 9178 36722 27164 2026-08-12T00:10:33Z Ghybu 12 ناو 36722 wikitext text/x-wiki {{#invoke:kmr-headword|show|ناو}}<!-- --><noinclude>{{documentation}}</noinclude> 0j3o61atfczrlu2vah7epq9gxsdowc3 10 9179 36725 27166 2026-08-12T00:14:52Z Ghybu 12 ھاوماناکان 36725 wikitext text/x-wiki {{#invoke:kmr-headword|show|ھاوماناکان}}<!-- --><noinclude>{{documentation}}</noinclude> isf44st5b8nllrmrwafshvdla376udh 36731 36725 2026-08-12T00:49:39Z Ghybu 12 ھاوەڵناو 36731 wikitext text/x-wiki {{#invoke:kmr-headword|show|ھاوەڵناو}}<!-- --><noinclude>{{documentation}}</noinclude> 459g2t9glbpqlkllm7zf47sgbt4e7wu 10 9183 36726 27172 2026-08-12T00:15:51Z Ghybu 12 کار 36726 wikitext text/x-wiki {{#invoke:kmr-headword|show|کار}}<!-- --><noinclude>{{documentation}}</noinclude> l2w4s4bq2tzajiugdzsux1c616jorji 828 9311 36739 34751 2026-08-12T11:40:45Z Ghybu 12 Sorani names 36739 Scribunto text/plain local labels = {} local raw_categories = {} local handlers = {} ----------------------------------------------------------------------------- -- -- -- LABELS -- -- -- ----------------------------------------------------------------------------- local diminutive_augmentative_poses = { "adjectives", "adverbs", "interjections", "nouns", "numerals", "prefixes", "proper nouns", "pronouns", "suffixes", "verbs" } labels["لەما"] = { description = "{{{langname}}} [[Wiktionary:Lemmas|lemmas]], categorized by their part of speech.", umbrella_parents = "Fundamental", parents = {{name = "{{{langcat}}}", raw = true, sort = " "}}, } labels["abstract verbs"] = { description = "{{{langname}}} abstract verbs of motion whose motion is multidirectional (as opposed to unidirectional) or indirect, or whose action is repeated or in a series, instead of being a single, completed action. Abstract verbs are always imperfective in aspect, even with prefixes that are normally associated with the perfective aspect.", additional = "See also [[abstract verb]].", parents = {"کار"}, } labels["action nouns"] = { description = "{{{langname}}} nouns denoting action of a verb or verbal root that it is derived from.", parents = {"ناو"}, } labels["act-related adverbs"] = { description = "{{{langname}}} adverbs that indicate the motive or other background information for an action.", parents = {"adverbs"}, } labels["active verbs"] = { description = "{{{langname}}} verbs that indicate an activity", parents = {"کار"}, } labels["adjective concords"] = { description = "{{{langname}}} concords that are prefixed to adjective stems.", parents = {"concords"}, } labels["ھاوەڵناو"] = { description = "{{{langname}}} terms that give attributes to nouns, extending their definitions.", parents = {"لەما"}, } labels["adverbial accusatives"] = { description = "Accusative case-forms in {{{langname}}} used as adverbs.", parents = {"adverbs"}, } labels["adverbs"] = { description = "{{{langname}}} terms that modify clauses, sentences and phrases directly.", parents = {"لەما"}, } labels["affixes"] = { description = "Morphemes attached to existing {{{langname}}} words.", parents = {"morphemes"}, } labels["agent nouns"] = { description = "{{{langname}}} nouns that denote an agent that performs the action denoted by the verb from which the noun is derived.", parents = {"ناو"}, } labels["ambipositions"] = { description = "{{{langname}}} adpositions that can occur either before or after their objects.", parents = {"لەما"}, } labels["ambitransitive verbs"] = { description = "{{{langname}}} verbs that may or may not direct actions, occurrences or states to grammatical objects.", parents = {"verbs", "transitive verbs", "intransitive verbs"}, } labels["animal commands"] = { description = "{{{langname}}} words used to communicate with animals.", parents = {"interjections"}, } labels["articles"] = { description = "{{{langname}}} terms that indicate and specify nouns.", parents = {"determiners"}, } labels["aspect adverbs"] = { description = "{{{langname}}} adverbs that express [[w:Grammatical aspect|grammatical aspect]], describing the flow of time in relation to a statement.", parents = {"adverbs"}, } for _, pos in ipairs(diminutive_augmentative_poses) do labels["augmentative " .. pos] = { description = "{{{langname}}} " .. pos .. " that are derived from a base word to convey big size or big intensity.", parents = {pos}, } end labels["attenuative verbs"] = { description = "{{{langname}}} verbs that indicate that an action or event is performed or takes place gently, lightly, partially, perfunctorily or to an otherwise reduced extent.", parents = {"کار"}, } labels["autobenefactive verbs"] = { description = "{{{langname}}} verbs that indicate that the agent of an action is also its benefactor.", parents = {"کار"}, } labels["automative verbs"] = { description = "{{{langname}}} verbs that indicate actions directed at or a change of state of the grammatical subject.", parents = {"کار"}, } labels["auxiliary verbs"] = { description = "{{{langname}}} verbs that provide additional conjugations for other verbs.", parents = {"کار"}, } labels["biaspectual verbs"] = { description = "{{{langname}}} verbs that can be both imperfective and perfective.", parents = {"کار"}, } labels["causative verbs"] = { description = "{{{langname}}} verbs that express causing actions or states rather than performing or being them directly. Use this only for separate verbs (as opposed to causative forms that are part of the inflection of verbs).", parents = {"کار"}, } labels["circumfixes"] = { description = "Affixes attached to both the beginning and the end of {{{langname}}} words, functioning together as single units.", parents = {"morphemes"}, } labels["circumpositions"] = { description = "{{{langname}}} adpositions that appear on both sides of their objects.", parents = {"لەما"}, } labels["classifiers"] = { description = "{{{langname}}} terms that classify nouns according to their meanings.", parents = {"لەما"}, } labels["clitics"] = { description = "{{{langname}}} morphemes that function as independent words, but are always attached to another word.", parents = {"morphemes"}, } for _, pos in ipairs { "nouns", "suffixes" } do labels["collective " .. pos] = { description = "{{{langname}}} " .. pos .. " that indicate groups of related things or beings, without the need of grammatical pluralization.", parents = {pos}, } end labels["combining forms"] = { description = "Forms of {{{langname}}} words that do not occur independently, but are used when joined with other words.", parents = {"morphemes"}, } labels["comparable adjectives"] = { description = "{{{langname}}} adjectives that can be inflected to display different degrees of comparison.", parents = {"ھاوەڵناو"}, } labels["comparable adverbs"] = { description = "{{{langname}}} adverbs that can be inflected to display different degrees of comparison.", parents = {"adverbs"}, } labels["comparative-only adjectives"] = { description = "{{{langname}}} adjectives that are only used in their comparative forms.", parents = {"ھاوەڵناو"}, } labels["completive verbs"] = { description = "{{{langname}}} verbs which refer to the completion of an action which has already commenced or which has already been performed upon a subset of the entities which it affects.", parents = {"کار"}, } labels["concords"] = { description = "{{{langname}}} prefixes attached to words to show agreement with a noun or pronoun.", parents = {"prefixes"}, } labels["concrete verbs"] = { description = "{{{langname}}} concrete verbs refer to a verbal aspect in verbs of motion that is unidirectional (as opposed to multidirectional), a definitely directed motion, or a single, completed action (instead of a repeated action or series of actions). Concrete verbs may be either imperfective or perfective.", additional = "See also [[concrete verb]].", parents = {"کار"}, } labels["conjunctions"] = { description = "{{{langname}}} terms that connect words, phrases or clauses together.", parents = {"لەما"}, } labels["conjunctive adverbs"] = { description = "{{{langname}}} adverbs that connect two independent clauses together.", parents = {"adverbs"}, } labels["continuative verbs"] = { description = "{{{langname}}} verbs that express continuing action.", parents = {"کار"}, } labels["control verbs"] = { description = "{{{langname}}} verbs that take multiple arguments, one of which is another verb. One of the control verb's arguments is syntactically both an argument of the control verb and an argument of the other verb.", parents = {"کار"}, } labels["cooperative verbs"] = { description = "{{{langname}}} verbs that indicate cooperation", parents = {"کار"}, } labels["coordinating conjunctions"] = { description = "{{{langname}}} conjunctions that indicate equal syntactic importance between connected items.", parents = {"conjunctions"}, } labels["copulative verbs"] = { description = "{{{langname}}} verbs that may take adjectives as their complement.", parents = {"کار"}, } labels["ناوە ژماردەنییەکان"] = { description = "ناوە ژماردەنییە {{{langname}}}یەکان کە دەتوانرێت ڕاستەوخۆ بە ژمارەیی بپێورێت.", parents = {"ناوەکان"}, } labels["ناوە تایبەتەکان"] = { description = "ناوە تایبەتە {{{langname}}}یەکان کە دەتوانرێت ڕاستەوخۆ بە ژمارەیی بپێورێت.", parents = {"ناوەکان"}, } labels["countable numerals"] = { description = "{{{langname}}} numerals that can be quantified directly by other numerals.", parents = {"numerals"}, } labels["countable suffixes"] = { description = "{{{langname}}} suffixes that can be used to form nouns that can be quantified directly by numerals.", parents = {"numerals"}, } labels["counters"] = { description = "{{{langname}}} terms that combine with numerals to express quantity of nouns.", parents = {"لەما"}, } labels["cumulative verbs"] = { description = "{{{langname}}} verbs which indicate that an action or event gradually yields a certain or significant quantity or effect.", parents = {"کار"}, } labels["degree adverbs"] = { description = "{{{langname}}} adverbs that express a particular degree to which the word they modify applies.", parents = {"adverbs"}, } labels["delimitative verbs"] = { description = "{{{langname}}} verbs which indicate that an action or event is performed or takes place briefly or to an otherwise reduced extent.", parents = {"کار"}, } labels["demonstrative adjectives"] = { description = "{{{langname}}} adjectives that refer to nouns, comparing them to external references.", parents = {"adjectives", {name = "demonstrative pro-forms", sort = "adjectives"}}, } labels["demonstrative adverbs"] = { description = "{{{langname}}} adverbs that refer to other adverbs, comparing them to external references.", parents = {"adverbs", {name = "demonstrative pro-forms", sort = "adverbs"}}, } labels["denominal verbs"] = { -- in [[Appendix:Glossary]]; "denominative" more frequent? description = "{{{langname}}} verbs that derive from nouns.", parents = { "verbs" }, } labels["demonstrative determiners"] = { description = "{{{langname}}} determiners that refer to nouns, comparing them to external references.", parents = {"determiners", {name = "demonstrative pro-forms", sort = "determiners"}}, } labels["demonstrative pronouns"] = { description = "{{{langname}}} pronouns that refer to nouns, comparing them to external references.", parents = {"pronouns", {name = "demonstrative pro-forms", sort = "pronouns"}}, } labels["deponent verbs"] = { description = "{{{langname}}} verbs that have active meanings but are not conjugated in the active voice.", parents = {"کار"}, } labels["derivational prefixes"] = { description = "{{{langname}}} prefixes that are used to create new words.", parents = {"prefixes"}, } labels["derivational suffixes"] = { description = "{{{langname}}} suffixes that are used to create new words.", parents = {"suffixes"}, } labels["derivative verbs"] = { description = "{{{langname}}} verbs that are derived from nouns and adjectives.", parents = {"کار"}, } labels["desiderative verbs"] = { description = "{{{langname}}} verbs with the following morphology: verbal root xxx + [[desiderative]] affix, and the following semantics: to wish to do the action xxx.", parents = {"کار"}, } labels["determinatives"] = { description = "{{{langname}}} terms that indicate the general class to which the following logogram belongs.", parents = {"لەما"}, } labels["determiners"] = { description = "{{{langname}}} terms that narrow down, within the conversational context, the referent of the following noun.", parents = {"لەما"}, } labels["diminutiva tantum"] = { description = "{{{langname}}} nouns or noun senses that are mostly or exclusively used in the diminutive form.", parents = {"ناو"}, } for _, pos in ipairs(diminutive_augmentative_poses) do labels["diminutive " .. pos] = { description = "{{{langname}}} " .. pos .. " that are derived from a base word to convey endearment, small size or small intensity.", parents = {pos}, } end labels["discourse particles"] = { description = "{{{langname}}} particles that manage the flow and structure of discourse.", parents = {"particles"}, } labels["distributive verbs"] = { description = "{{{langname}}} verbs which indicate that an action or event involves multiple participants or a large quantity of an uncountable mass, usually as the grammatical subject in the case of intransitive verbs and as the grammatical object in the case of transitive verbs.", parents = {"کار"}, } labels["ditransitive verbs"] = { description = "{{{langname}}} verbs that indicate actions, occurrences or states of two grammatical objects simultaneously, one direct and one indirect.", parents = {"verbs", "transitive verbs"}, } labels["dualia tantum"] = { description = "{{{langname}}} nouns that are mostly or exclusively used in the dual form.", parents = {"ناو"}, } labels["duration adverbs"] = { description = "{{{langname}}} adverbs that express duration in time.", parents = {"time adverbs"}, } labels["ergative verbs"] = { description = "{{{langname}}} [[Appendix:Glossary#ergative|ergative verb]]s: intransitive verbs that become causatives when used transitively.", parents = {"verbs", "intransitive verbs", "transitive verbs"}, } labels["excessive verbs"] = { description = "{{{langname}}} verbs that indicate that an action is performed to an excessive extent.", parents = {"کار"}, } labels["enclitics"] = { description = "{{{langname}}} clitics that attach to the preceding word.", parents = {"clitics"}, } labels["nouns with other-gender equivalents"] = { description = "{{{langname}}} nouns that refer to gendered concepts (e.g. [[actor]] vs. [[actress]], [[king]] vs. [[queen]]) and have corresponding other-gender equivalent terms.", parents = {"ناو"}, } labels["female equivalent nouns"] = { description = "{{{langname}}} nouns that refer to female beings with the same characteristics as the base noun.", parents = {"nouns with other-gender equivalents"}, } labels["neuter equivalent nouns"] = { description = "{{{langname}}} nouns that refer to neuter beings with the same characteristics as the base noun.", parents = {"nouns with other-gender equivalents"}, } labels["female equivalent suffixes"] = { description = "{{{langname}}} suffixes that refer to female beings with the same characteristics as the base suffix.", parents = {"noun-forming suffixes"}, } labels["focus adverbs"] = { description = "{{{langname}}} adverbs that indicate [[w:Focus (linguistics)|focus]] within the sentence.", parents = {"adverbs"}, } labels["frequency adverbs"] = { description = "{{{langname}}} adverbs that express repetition with a certain frequency or interval.", parents = {"time adverbs"}, } labels["frequentative verbs"] = { description = "{{{langname}}} verbs that express repeated action.", parents = {"کار"}, } labels["general pronouns"] = { description = "{{{langname}}} pronouns that refer to all persons, things, abstract ideas and their characteristics.", parents = {"pronouns"}, } labels["generational moieties"] = { description = "{{{langname}}} moieties that alternate every generation.", parents = {"moieties"}, } labels["ideophones"] = { description = "{{{langname}}} terms that evoke an idea, especially a sensation or impression, with a sound.", parents = {"لەما"}, } labels["imperfective verbs"] = { description = "{{{langname}}} verbs that express actions considered as ongoing or continuous, as opposed to completed events.", parents = {"کار"}, } labels["impersonal verbs"] = { description = "{{{langname}}} verbs that do not indicate actions, occurrences or states of any specific grammatical subject.", parents = {"کار"}, } labels["inchoative verbs"] = { description = "{{{langname}}} verbs that indicate the beginning of an action or event.", parents = {"کار"}, } labels["indefinite adjectives"] = { description = "{{{langname}}} adjectives that refer to unspecified adjective meanings.", parents = {"adjectives", {name = "indefinite pro-forms", sort = "adjectives"}}, } labels["indefinite adverbs"] = { description = "{{{langname}}} adverbs that refer to unspecified adverbial meanings.", parents = {"adverbs", {name = "indefinite pro-forms", sort = "adverbs"}}, } labels["indefinite determiners"] = { description = "{{{langname}}} determiners that designate an unidentified noun.", parents = {"determiners", {name = "indefinite pro-forms", sort = "determiners"}}, } labels["indefinite pronouns"] = { description = "{{{langname}}} pronouns that refer to unspecified nouns.", parents = {"pronouns", {name = "indefinite pro-forms", sort = "pronouns"}}, } labels["infixes"] = { description = "Affixes inserted inside {{{langname}}} words.", parents = {"morphemes"}, } labels["inflectional prefixes"] = { description = "{{{langname}}} prefixes that are used as inflectional beginnings in noun, adjective or verb paradigms.", parents = {"prefixes"}, } labels["inflectional suffixes"] = { description = "{{{langname}}} suffixes that are used as inflectional endings in noun, adjective or verb paradigms.", parents = {"suffixes"}, } labels["intensive verbs"] = { description = "{{{langname}}} verbs which indicate that an action is performed vigorously, enthusiastically, forcefully or to an otherwise enlarged extent.", parents = {"کار"}, } labels["interfixes"] = { description = "Affixes used to join two {{{langname}}} words or morphemes together.", parents = {"morphemes"}, } labels["interjections"] = { description = "{{{langname}}} terms that express emotions, sounds, etc. as exclamations.", parents = {"لەما"}, } labels["interrogative adjectives"] = { description = "{{{langname}}} adjectives that indicate questions.", parents = {"adjectives", {name = "interrogative pro-forms", sort = "adjectives"}}, } labels["interrogative adverbs"] = { description = "{{{langname}}} adverbs that indicate questions.", parents = {"adverbs", {name = "interrogative pro-forms", sort = "adverbs"}}, } labels["interrogative determiners"] = { description = "{{{langname}}} determiners that indicate questions.", parents = {"determiners", {name = "interrogative pro-forms", sort = "determiners"}}, } labels["interrogative particles"] = { description = "{{{langname}}} particles that indicate questions.", parents = {"particles", {name = "interrogative pro-forms", sort = "particles"}}, } labels["interrogative pronouns"] = { description = "{{{langname}}} pronouns that indicate questions.", parents = {"pronouns", {name = "interrogative pro-forms", sort = "pronouns"}}, } labels["intransitive verbs"] = { description = "{{{langname}}} verbs that don't require any grammatical objects.", parents = {"کار"}, } labels["iterative verbs"] = { description = "{{{langname}}} verbs that express the repetition of an event.", parents = {"کار"}, } labels["location adverbs"] = { description = "{{{langname}}} adverbs that indicate location.", parents = {"adverbs"}, } labels["male equivalent nouns"] = { description = "{{{langname}}} nouns that refer to male beings with the same characteristics as the base noun.", parents = {"nouns with other-gender equivalents"}, } labels["manner adverbs"] = { description = "{{{langname}}} adverbs that indicate the manner, way or style in which an action is performed.", parents = {"adverbs"}, } labels["modal adverbs"] = { description = "{{{langname}}} adverbs that express [[w:Linguistic modality|linguistic modality]], indicating the mood or attitude of the speaker with respect to what is being said.", parents = {"sentence adverbs"}, } labels["modal particles"] = { description = "{{{langname}}} particles that reflect the mood or attitude of the speaker, without changing the basic meaning of the sentence.", parents = {"particles"}, } labels["modal verbs"] = { description = "{{{langname}}} verbs that indicate [[grammatical mood]].", parents = {"auxiliary verbs"}, } labels["moieties"] = { description = "{{{langname}}} pairs of abstract categories separating people and the environment.", parents = {"لەما"}, } labels["momentane verbs"] = { description = "{{{langname}}} verbs that express a sudden and brief action.", parents = {"کار"}, } labels["morphemes"] = { description = "{{{langname}}} word-elements used to form full words.", parents = {"لەما"}, } labels["multiword terms"] = { description = "{{{langname}}} lemmas that are an [[WT:CFI#Idiomaticity|idiomatic]] combination of multiple words.", parents = {"لەما"}, } labels["negative verbs"] = { description = "{{{langname}}} verbs that indicate the lack of an action.", parents = {"کار"}, } labels["negative particles"] = { description = "{{{langname}}} particles that indicate negation.", parents = {"particles"}, } labels["negative pronouns"] = { description = "{{{langname}}} pronouns that refer to negative or non-existent references.", parents = {"pronouns"}, } labels["neutral verbs"] = { description = "{{{langname}}} verbs that indicate either or both an activity or a result of an activity", parents = {"کار"}, } labels["nominalized adjectives"] = { description = "{{{langname}}} adjectives that are used as nouns.", parents = {"nouns", "adjectives"}, } labels["non-constituents"] = { description = "{{{langname}}} terms that are not grammatical [[constituent#Noun|constituents]], and therefore need to be combined with additional terms to form a complete phrase.", parents = {"phrases"}, } labels["noun prefixes"] = { description = "{{{langname}}} prefixes attached to a noun that display its noun class.", parents = {"prefixes"}, } labels["ناو"] = { description = "{{{langname}}} terms that indicate people, beings, things, places, phenomena, qualities or ideas.", parents = {"لەما"}, } labels["nouns by classifier"] = { description = "{{{langname}}} nouns organized by the classifier they are used with.", parents = {{name = "nouns", sort = "classifier"}}, } labels["numerals"] = { description = "{{{langname}}} terms that quantify nouns.", parents = {"لەما"}, } labels["object concords"] = { description = "{{{langname}}} concords used to show the grammatical object.", parents = {"concords"}, } labels["object pronouns"] = { description = "{{{langname}}} pronouns that refer to grammatical objects.", parents = {"pronouns"}, } labels["particles"] = { description = "{{{langname}}} terms that do not belong to any of the inflected grammatical word classes, often lacking their own grammatical functions and forming other parts of speech or expressing the relationship between clauses.", parents = {"لەما"}, } labels["passive verbs"] = { description = "{{{langname}}} verbs that are usually used in passive voice.", parents = {"کار"}, } labels["perfective verbs"] = { description = "{{{langname}}} verbs that express actions considered as completed events, as opposed to ongoing or continuous.", parents = {"کار"}, } labels["personal pronouns"] = { description = "{{{langname}}} pronouns that are used as substitutes for known nouns.", parents = {"pronouns"}, } labels["phrasal verbs"] = { description = "{{{langname}}} verbs accompanied by particles, such as prepositions and adverbs.", parents = {"verbs", "phrases"}, } labels["phrasal prepositions"] = { description = "{{{langname}}} prepositions formed with combinations of other terms.", parents = {"prepositions", "phrases"}, } labels["pluralia tantum"] = { description = "{{{langname}}} nouns that are mostly or exclusively used in the plural form.", parents = {"ناو"}, } labels["point-in-time adverbs"] = { description = "{{{langname}}} adverbs that reference a specific point in time, e.g. {{m|en|yesterday}}, {{m+|es|anoche||last night}} or {{m+|hu|egykor||at one o'clock}}.", parents = {"time adverbs"}, } labels["possessable nouns"] = { description = "{{{langname}}} nouns can have their possession indicated directly by possessive pronouns.", parents = {"ناو"}, umbrella = { description = "Categories with nouns that can have their possession indicated directly by possessive pronouns and, in some languages, be transformed into adjectives.", parents = {"Lemmas subcategories by language"}, breadcrumb = "Possessable nouns by language", }, } labels["possessional adjectives"] = { description = "{{{langname}}} adjectives that indicate that a noun is in possession of something.", parents = {"ھاوەڵناو"}, } labels["possessive adjectives"] = { description = "{{{langname}}} adjectives that indicate ownership.", parents = {"ھاوەڵناو"}, } labels["possessive concords"] = { description = "{{{langname}}} concords used to show possession.", parents = {"concords"}, } labels["possessive determiners"] = { description = "{{{langname}}} determiners that indicate ownership.", parents = {"determiners"}, } labels["possessive pronouns"] = { description = "{{{langname}}} pronouns that indicate ownership.", parents = {"pronouns"}, } labels["postpositional phrases"] = { description = "{{{langname}}} phrases headed by a postposition.", parents = {"phrases", "postpositions"}, } labels["postpositions"] = { description = "{{{langname}}} adpositions that are placed after their objects.", parents = {"لەما"}, } labels["predicatives"] = { description = "{{{langname}}} elements of the predicate that supplement the subject or object of a sentence via the verb.", parents = {"لەما"}, } labels["prefixes"] = { description = "Affixes attached to the beginning of {{{langname}}} words.", parents = {"morphemes"}, } labels["prepositional phrases"] = { description = "{{{langname}}} phrases headed by a preposition.", parents = {"phrases", "prepositions"}, } labels["prepositions"] = { description = "{{{langname}}} adpositions that are placed before their objects.", parents = {"لەما"}, } labels["ablative prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the ablative case.", parents = {"prepositions"}, } labels["accusative prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the accusative case.", parents = {"prepositions"}, } labels["dative prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the dative case.", parents = {"prepositions"}, } labels["genitive prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the genitive case.", parents = {"prepositions"}, } labels["instrumental prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the instrumental case.", parents = {"prepositions"}, } labels["matrilineal moieties"] = { description = "{{{langname}}} moieties inherited from an individual's mother.", parents = {"moieties"}, } labels["nominative prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the nominative case.", parents = {"prepositions"}, } labels["patrilineal moieties"] = { description = "{{{langname}}} moieties inherited from an individual's father.", parents = {"moieties"}, } labels["pejorative suffixes"] = { description = "{{{langname}}} suffixes that [[belittle]] (lessen in value).", parents = {"suffixes"}, } labels["prepositional prepositions"] = { description = "{{{langname}}} prepositions that cause the succeeding noun to be in the prepositional case.", parents = {"prepositions"}, } labels["prenouns"] = { description = "{{{langname}}} prefixes of various kinds that are attached to nouns.", parents = {"prefixes"}, } labels["preverbs"] = { description = "{{{langname}}} prefixes of various kinds that are attached to verbs.", parents = {"prefixes"}, } labels["privative verbs"] = { description = "{{{langname}}} verbs that indicate that the grammatical object is deprived of something or that something is removed from the object.", parents = {"کار"}, } labels["pronominal adverbs"] = { description = "{{{langname}}} adverbs that are formed by combining a pronoun with a preposition.", parents = {"adverbs", "prepositions", "pronouns"}, } labels["pronominal concords"] = { description = "{{{langname}}} concords that are prefixed to pronominal stems.", parents = {"concords"}, } labels["pronouns"] = { description = "{{{langname}}} terms that refer to and substitute nouns.", parents = {"لەما"}, } labels["proper nouns"] = { description = "{{{langname}}} nouns that indicate individual entities, such as names of persons, places or organizations.", parents = {"ناو"}, } labels["punctual adverbs"] = { description = "{{{langname}}} adverbs that express a single point or span in time.", parents = {"time adverbs"}, } labels["raising verbs"] = { description = "{{{langname}}} verbs that, in a matrix or main clause, take an argument from an embedded or subordinate clause; in other words, a raising verb appears with a syntactic argument that is not its semantic argument, but is rather the semantic argument of an embedded predicate.", parents = {"کار"}, } labels["reciprocal pronouns"] = { description = "{{{langname}}} pronouns that refer back to a plural subject and express an action done in two or more directions.", parents = {"pronouns", "personal pronouns"}, } labels["reciprocal verbs"] = { description = "{{{langname}}} verbs that indicate actions, occurrences or states directed from multiple subjects to each other.", parents = {"کار"}, } labels["reflexive pronouns"] = { description = "{{{langname}}} pronouns that refer back to the subject.", parents = {"pronouns", "personal pronouns"}, } labels["reflexive verbs"] = { description = "{{{langname}}} verbs that indicate actions, occurrences or states directed from the grammatical subjects to themselves.", parents = {"کار"}, } labels["relational adjectives"] = { description = "{{{langname}}} adjectives that stand in place of a noun when modifying another noun.", parents = {"ھاوەڵناو"}, } labels["relational nouns"] = { description = "{{{langname}}} nouns used to indicate a relation between other two nouns by means of possession.", parents = {"ناو"}, } labels["relative adjectives"] = { description = "{{{langname}}} adjectives used to indicate [[relative clause]]s.", parents = {"adjectives", {name = "relative pro-forms", sort = "adjectives"}}, } labels["relative adverbs"] = { description = "{{{langname}}} adverbs used to indicate [[relative clause]]s.", parents = {"adverbs", {name = "relative pro-forms", sort = "adverbs"}}, } labels["relative determiners"] = { description = "{{{langname}}} determiners used to indicate [[relative clause]]s.", parents = {"determiners", {name = "relative pro-forms", sort = "determiners"}}, } labels["relative concords"] = { description = "{{{langname}}} concords that are prefixed to relative stems.", parents = {"concords"}, } labels["relative pronouns"] = { description = "{{{langname}}} pronouns used to indicate [[relative clause]]s.", parents = {"pronouns", {name = "relative pro-forms", sort = "pronouns"}}, } labels["relatives"] = { description = "{{{langname}}} terms that give attributes to nouns, acting grammatically as relative clauses.", parents = {"لەما"}, } labels["repetitive verbs"] = { description = "{{{langname}}} verbs that indicate actions or events which are performed or occur again, anew or differently.", parents = {"کار"}, } labels["resultative verbs"] = { description = "{{{langname}}} verbs that indicate a result of some action", parents = {"کار"}, } labels["reversative verbs"] = { description = "{{{langname}}} verbs that indicate that the reversal or undoing of an action, event or state.", parents = {"کار"}, } labels["saturative verbs"] = { description = "{{{langname}}} verbs which indicate that an action is performed to the point of saturation or satisfaction.", parents = {"کار"}, } labels["semelfactive verbs"] = { description = "{{{langname}}} verbs that are punctual (instantaneous, momentive), perfective (treated as a unitary whole with no explicit internal temporal structure), and telic (having a boundary out of which the activity cannot be said to have taken place or continue).", parents = {"کار"}, } labels["sentence adverbs"] = { description = "{{{langname}}} adverbs that modify an entire clause or sentence.", parents = {"adverbs"}, } labels["sequence adverbs"] = { description = "{{{langname}}} conjunctive adverbs that express sequence in space or time.", parents = {"conjunctive adverbs"}, } labels["simulfixes"] = { description = "Affixes replacing positions in {{{langname}}} words.", parents = {"morphemes"}, } labels["singulative nouns"] = { description = "{{{langname}}} nouns that indicate a single item of a group of related things or beings.", parents = {"ناو"}, } labels["singularia tantum"] = { description = "{{{langname}}} nouns that are mostly or exclusively used in the singular form.", parents = {"ناو"}, } labels["stative verbs"] = { description = "{{{langname}}} verbs that define a state with no or insignificant internal dynamics.", parents = {"کار"}, } labels["stems"] = { description = "Morphemes from which {{{langname}}} words are formed.", parents = {"morphemes"}, } labels["subordinating conjunctions"] = { description = "{{{langname}}} conjunctions that indicate relations of syntactic dependence between connected items.", parents = {"conjunctions"}, } labels["subject concords"] = { description = "{{{langname}}} concords used to show the grammatical subject.", parents = {"concords"}, } labels["subject pronouns"] = { description = "{{{langname}}} pronouns that refer to grammatical subjects.", parents = {"pronouns"}, } labels["suffixes"] = { description = "Affixes attached to the end of {{{langname}}} words.", parents = {"morphemes"}, } labels["splitting verbs"] = { description = "{{{langname}}} bisyllabic verbs that obligatorily split around a direct object or pronoun.", parents = {"کار"}, } labels["terminative verbs"] = { description = "{{{langname}}} verbs that indicate that an action or event ceases.", parents = {"کار"}, } labels["time adverbs"] = { description = "{{{langname}}} adverbs that indicate time.", parents = {"adverbs"}, } labels["transfixes"] = { description = "Discontinuous affixes inserted within a word root.", parents = {"morphemes"}, } labels["transformative verbs"] = { description = "{{{langname}}} verbs that indicate a change of state or nature, in the subject for intransitive verbs and in the object for transitive verbs.", parents = {"کار"}, } labels["transitive verbs"] = { description = "{{{langname}}} verbs that indicate actions, occurrences or states directed to one or more grammatical objects.", parents = {"کار"}, } labels["uncomparable adjectives"] = { description = "{{{langname}}} adjectives that are not inflected to display different degrees of comparison.", parents = {"ھاوەڵناو"}, } labels["uncomparable adverbs"] = { description = "{{{langname}}} adverbs that are not inflected to display different degrees of comparison.", parents = {"adverbs"}, } labels["ناوە ژماردەنییەکان"] = { description = "{{{langname}}} nouns that indicate qualities, ideas, unbounded mass or other abstract concepts that cannot be quantified directly by numerals.", parents = {"ناوەکان"}, } labels["uncountable numerals"] = { description = "{{{langname}}} numerals that cannot be quantified directly by other numerals.", parents = {"numerals"}, } labels["uncountable proper nouns"] = { description = "{{{langname}}} proper nouns that cannot be quantified directly by numerals.", parents = {"proper nouns"}, } labels["uncountable suffixes"] = { description = "{{{langname}}} suffixes that can be used to form nouns that cannot be quantified directly by numerals.", parents = {"numerals"}, } labels["unpossessable nouns"] = { description = "{{{langname}}} nouns that cannot have their possession indicated directly by possessive pronouns.", parents = {"ناو"}, umbrella = { description = "Categories with nouns that cannot have their possession indicated directly by possessive pronouns or, in some languages, be transformed into adjectives.", parents = {"Lemmas subcategories by language"}, breadcrumb = "Unpossessable nouns by language", }, } labels["verbal nouns"] = { description = "{{{langname}}} nouns morphologically related to a verb and similar to it in meaning.", parents = {"ناو"}, } labels["verbal adjectives"] = { description = "{{{langname}}} adjectives describing the condition or state resulting from the action of the corresponding verb.", parents = {"ھاوەڵناو"}, } labels["verbs"] = { description = "{{{langname}}} terms that indicate actions, occurrences or states.", parents = {"لەما"}, } labels["verbs of movement"] = { description = "{{{langname}}} verbs that indicate physical movement of the grammatical subject across a trajectory, with a starting point and an endpoint.", parents = {"کار"}, } -- Add "POS-forming suffixes". local poses_derived_by_suffix = { "adjective", "adverb", "noun", "verb", } for _, pos in pairs(poses_derived_by_suffix) do labels[pos .. "-forming suffixes"] = { description = "{{{langname}}} suffixes that are used to derive " .. pos .. "s from other words.", parents = {"derivational suffixes"}, } end local labels2 = {} -- Add "reconstructed" subcategories; add 'umbrella_parents' key if not -- already present. for key, data in pairs(labels) do labels2[key] = data if not data.umbrella_parents then data.umbrella_parents = "Lemmas subcategories by language" end labels2["reconstructed " .. key] = { description = "{{{langname}}} " .. key .. " that have been linguistically [[Wiktionary:Reconstructed terms|reconstructed]].", umbrella_parents = "Lemmas subcategories by language", parents = {key, {name = "reconstructed terms", sort = key}} } end ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Lemmas subcategories by language"] = { description = "Umbrella categories covering topics related to lemmas.", additional = "{{{umbrella_meta_msg}}}", parents = { "Umbrella metacategories", {name = "lemmas", is_label = true, sort = " "}, }, } ----------------------------------------------------------------------------- -- -- -- HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Handler for e.g. [[:Category:English phrasal verbs with particle (around)]]. table.insert(handlers, function(data) local particle = data.label:match("^phrasal verbs with particle %((.-)%)$") if particle then local tagged_text = require("Module:script utilities").tag_text(particle, data.lang, nil, "term") local link = require("Module:links").full_link({ term = particle, lang = data.lang }, "term") return { description = "{{{langname}}} {{w|phrasal verb}}s using the particle " .. link .. ".", displaytitle = "{{{langname}}} phrasal verbs with particle (" .. tagged_text .. ")", breadcrumb = tagged_text, parents = {{ name = "phrasal verbs", sort = particle }}, umbrella = false, } end end) return {LABELS = labels2, RAW_CATEGORIES = raw_categories, HANDLERS = handlers} 58r5mwdw2z4hu8f39438irhvte40ot4 0 11120 36697 35575 2026-08-11T12:21:05Z Ghybu 12 /* کرمانجی */ 36697 wikitext text/x-wiki == کرمانجی == === ناو === {{kmr-noun|f}}| # [[مشک|مریشک]] srr8oier3apllj8xhgxbwdqoclml7pn 0 11424 36733 36650 2026-08-12T00:51:43Z Ghybu 12 /* ھاوماناکان */ 36733 wikitext text/x-wiki == کرمانجی == === گۆکردن === * {{IPA|kmr|/kʰʊɾˈdiː/}} * {{دەنگ|kmr|LL-Q36163_(kmr)-Key Mîrza-kurdî.wav}} === ناو === {{kmr-noun|m}} # [[کوردی]] ==== ھاوەڵناو ==== {{kmr-adj}} # [[کوردی]] 3z1nm7swex82ypaj6vf5zh4csz1pxwi 0 11425 36734 36651 2026-08-12T00:52:05Z Ghybu 12 /* ھاوەڵناو */ 36734 wikitext text/x-wiki == کرمانجی == === گۆکردن === {{kmr-IPA}} * {{دەنگ|kmr|LL-Q36368 (kur)-Mihemed Qers-kurmancî.wav}} * {{دەنگ|kmr|LL-Q36163 (kmr)-Ebulfîda-kurmancî.wav}} === ناو === {{kmr-noun|m}} # [[کرمانجی]] ==== ھاوەڵناو ==== {{kmr-adj}} # [[کرمانجی]] 4d57leu6y9qm9crfnzbis51tkfzbnuy 0 11427 36707 2026-08-11T12:42:04Z Ghybu 12 پەڕەی دروست کرد بە «== فەڕەنسی == === گۆکردن === * {{IPA|fr|/o/}} * {{دەنگ|fr|LL-Q150 (fra)-GrandCelinien-eau.wav}} === ناو === {{head|fr|ناو|g=f}} # [[ئاو]]»ەوە 36707 wikitext text/x-wiki == فەڕەنسی == === گۆکردن === * {{IPA|fr|/o/}} * {{دەنگ|fr|LL-Q150 (fra)-GrandCelinien-eau.wav}} === ناو === {{head|fr|ناو|g=f}} # [[ئاو]] e7ie3bmedvhlq9ofb1mckonftscrbyx 14 11428 36738 2026-08-12T11:09:41Z Ghybu 12 پەڕەی دروست کرد بە «{{auto cat}}»ەوە 36738 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 14 11429 36740 2026-08-12T11:45:50Z Ghybu 12 پەڕەی دروست کرد بە «{{auto cat}}»ەوە 36740 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx