ဝိက်ရှေန်နရဳ mnwwiktionary https://mnw.wiktionary.org/wiki/%E1%80%9D%E1%80%AD%E1%80%80%E1%80%BA%E1%80%9B%E1%80%BE%E1%80%B1%E1%80%94%E1%80%BA%E1%80%94%E1%80%9B%E1%80%B3:%E1%80%99%E1%80%AF%E1%80%80%E1%80%BA%E1%80%9C%E1%80%AD%E1%80%80%E1%80%BA%E1%80%90%E1%80%99%E1%80%BA MediaWiki 1.47.0-wmf.16 case-sensitive မဳဒဳယာ တၟေင် ဓရီုကျာ ညးလွပ် ညးလွပ် ဓရီုကျာ ဝိက်ရှေန်နရဳ ဝိက်ရှေန်နရဳ ဓရီုကျာ ဝှာင် ဝှာင် ဓရီုကျာ မဳဒဳယာဝဳကဳ မဳဒဳယာဝဳကဳ ဓရီုကျာ ထာမ်ပလိက် ထာမ်ပလိက် ဓရီုကျာ ရီု ရီု ဓရီုကျာ ကဏ္ဍ ကဏ္ဍ ဓရီုကျာ အဆက်လက္ကရဴ အဆက်လက္ကရဴ ဓရီုကျာ ကာရန် ကာရန် ဓရီုကျာ အဘိဓာန် အဘိဓာန် ဓရီုကျာ ဗီုပြၚ်သိုၚ်တၟိ ဗီုပြၚ်သိုၚ်တၟိ ဓရီုကျာ TimedText TimedText talk မဝ်ဂျူ မဝ်ဂျူ ဓရီုကျာ Event Event talk 828 705 401580 396038 2026-08-19T18:00:08Z Intobesa.bot 1035 Bot: ပွမကၠာဲစုတ်ယၟုနူဘာသာအၚ်္ဂလိက် 401580 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "ခါရှေန်-အခိုက်ကၞာ", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "အဝ်သတြေဨချေန်တေတ်-အခိုက်ကၞာ", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "အာက်ပရဝ်အဳသဳယာတေတ်-အခိုက်ကၞာ", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "အဴဂံၚ်ခဳယာန်-အခိုက်ကၞာ", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "ခါန်ဂဝ်-အာတ္တလာန်တေတ်-အခိုက်ကၞာ", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "ဨဒေခဳရိ-အခိုက်ကၞာ", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "ယိုဝ်ရုဗါအ်-အခိုက်ကၞာ", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "ယိုဝ်ရုဗေါန်-အခိုက်ကၞာ", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "အောဂျေစ်-အခိုက်ကၞာ", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "အာဒူနဳ", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "ဗေန်တဝ် ခရဳအဝ်", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "မအရေဝ်လစံက်", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "ဒဝ်တရာကဳ", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "အဳလာဲ", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "လာတ်ပဳနဳ", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "မာန်ဒဝ်လဝ်ရဳယာန်", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "နာ'ဝဳ", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "ဝါလဳရဳယာန် သၠုၚ်", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "အာက်တၜေတ်သကေၚ်-အခိုက်ကၞာ", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "ဝါယ်ဒိုဟ်သမၠုၚ်ကျာတၟိမဇ္ဇျိမ-အခိုက်ကၞာ", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "နယူနူလာန်-အခိုက်ကၞာ", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "ပါမာ-နေန်ကာန်-အခိုက်ကၞာ", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "နာဟာမ်-အခိုက်ကၞာ", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "ယူတဝ်-အာက်သတေကာန်-အခိုက်ကၞာ", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "ဗေအ်ဗေအ်-အခိုက်ကၞာ", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "ဖွဝ်ဂါဟာ", 107610173, "ber", "Latn", } m["ber-zuw"] = { "ဇျူဝါရာတ်", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "ၚုနဳ-အခိုက်ကၞာ", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "ဖူတ်တဳ", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "ဗာန်တူ-အခိုက်ကၞာ", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "ဗါတာတ်-အခိုက်ကၞာ", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "အာတ်ဟာတ်-အဗါတ်သာ-အခိုက်ကၞာ", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "အာန်ဒဳယာန်-အခိုက်ကၞာ", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "အဝါရဝ်-အာန်ဒဳယာန်-အခိုက်ကၞာ", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "သေခါတ်ဃှေန်-အခိုက်ကၞာ", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "ဒါတ်ဂွါ-အခိုက်ကၞာ", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "ခါခေန်ယှေန် သၟဝ်ကျာလ္ပာ်ဗၟံက်-အခိုက်ကၞာ", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "နေတ်-အခိုက်ကၞာ", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "ခါခေန်ယှေန် သၟဝ်ကျာလ္ပာ်ပလိုတ်-အခိုက်ကၞာ", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "သဲလ်သဳယာန်-အခိုက်ကၞာ", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "ကောတ်ဗေလဳယာန်-အခိုက်ကၞာ", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "ဂျဝ်ဂျဳယျာ-သံ-အခိုက်ကၞာ", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "ပရေတ်တိုန်နေတ်-အခိုက်ကၞာ", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "ဂဲလ်လဳအဳဃှေန်", 3094789, "cel-his", } m["cel-gau"] = { "ဂါလေတ်", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "သဲလ်တေတ်-အခိုက်ကၞာ", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "သဲလ်တေတ်-အခိုက်ကၞာ", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "မာရဳ-အခိုက်ကၞာ", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "ချေန်မါတ်-အခိုက်ကၞာ", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "မာကော ဖေန်စေံ ပဝ်တူဂြဳ", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "ရေတ်သေနိုတ်", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "အၚ်္ဂလိက် သာဝ်လုမ်ဗါလာ", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "သူဒါန် မဇ္ဇျိမ-အခိုက်ကၞာ", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "ကူဃှဳတေတ်-အခိုက်ကၞာ", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "ဗာရဳ", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", translit = { Mlym = "ml-translit", Knda = "kn-translit", }, } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "ကာန်နာဒါအဒေါဝ်", 128810572, "dra-kan", "Knda", translit = "kn-translit", } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "ကာန်နာဒါတြေံ", 15723156, "dra-kan", "Knda", translit = "kn-translit", } m["dra-ote"] = { "တေလုဂုတြေံ", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "ဒေတ်တာဗေတာံ-အခိုက်ကၞာ", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "ဒေတ်တာဗေတာံ အာဲ ဒိုဟ်သမၠုၚ်ကျာ-အခိုက်ကၞာ", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "ဒေတ်တာဗေတာံ ထူ ဒိုဟ်သမၠုၚ်ကျာ-အခိုက်ကၞာ", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "ဒေတ်တာဗေတာံ ဒိုဟ်သမၠုၚ်ကျာ-အခိုက်ကၞာ", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "ဒဳမဝ်တေတ် အဳဂျေပ်", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "ရုခါဲ-အခိုက်ကၞာ", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "အာက်သကဳမဝ်-အခိုက်ကၞာ", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "အိန်ယူအေတ်-အခိုက်ကၞာ", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "ဗက်ခ်-အခိုက်ကၞာ", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "ဂျာမာန်-အခိုက်ကၞာ", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "ခရိုၚ်မါန် ဂါပ်တေတ်", 36211, "gme", "Latn", } m["gmq-gut"] = { "ဂါတ်နေတ်", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "ဂျေန်ဒေါတ်", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "နဝ်ဝေ လဒေါဝ်", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "ဒိန်နေတ်တြေံ", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "ဂါတ်နေတ်တြေံ", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "သွဳဒေန်တြေံ", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "နဳနိုတ်-အခိုက်ကၞာ", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "သကိုန်နိယာန်", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "ဖပြၚ်ကိုဝ်နဳယာန် ဗဟဵု", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "ဂျာမာန် လ္ပာ်ဗၟံက်ဗဟဵု", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "ကတ်ချဳရေတ်", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "ဒါတ် ဂျာဇြဳ", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "သကတ် အဒေါဝ်", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "ဂျာမာန်နေတ်လက္ကရဴ-အခိုက်ကၞာ", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "ရာဲ ဖပြၚ်ကိုဝ်နဳယာန်", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "ထရေန်သဳလ်ဗေနဳယျာ သက်သိုန်", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "ဂျာမာန် သောတ်သှေ", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "ဂရိ ခလေဝ်ဗဳယာန်", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "ဂရိအဳတာလျေတ်", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "ဂရိ မာရိအုဖန်", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "ဟေဲလာန်နေတ်-အခိုက်ကၞာ", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmong", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "မဳယာန်-အခိုက်ကၞာ", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "မေန်-မဳယာန်-အခိုက်ကၞာ", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "အာမေနဳယာန်-အခိုက်ကၞာ", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "နူရေတ်သတေန်နဳ-အခိုက်ကၞာ", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "အိန်ဒဝ်-အဳရာန်-အခိုက်ကၞာ", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "အပက်ပရာန်သာ", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", Shrd = "Shrd-translit", Sidd = "Sidd-translit", }, } m["inc-ash"] = { "အခါန်ကာန် ပရာကရေတ်", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { Brah = "Brah-translit", Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "ခိုဝ်လဝ်သဳ", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "အိသ်ဇြာံမဳအဒေါဝ်", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "ဘၚ်္ဂါလဳအဒေါဝ်", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "ခုတ်ချာရေတ်လဒေါဝ်", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "အဝ်ရေဝ်ယာ လဒေါဝ်", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "အိသ်ဇြာံမဳကၠာအိုတ်", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "အဝါဒဳတြေံ", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "ဘၚ်္ဂါလဳတြေံ", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "ခုတ်ချာရေတ်တြေံ", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "ဟိန္ဒဳတြေံ", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "အဝ်ရေဝ်ယာတြေံ", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "ပါန်ချာပဳတြေံ", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "အိန်ဒဝ်-အာရိယာန်-အခိုက်ကၞာ", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "အာန်နာတဝ်လဳယာန်-အခိုက်ကၞာ", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "ဗဴတဝ်-သလာဗေတ်-အခိုက်ကၞာ", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "အိန်ဒဝ်-ယူရဝ်ပဳယာန်-အခိုက်ကၞာ", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "ထေဝ်ခါမ်ရေဝ်ယာန်-အခိုက်ကၞာ", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "မဳဒဳယာန်တြေံ", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "မဳဒဳယာန်လဒေါဝ်", 12836150, "xme", "Latn", } m["xme-ker"] = { "ခေါဝ်မာန်နေတ်", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "တေတ်တေတ်-အခိုက်ကၞာ", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "တာတဳတြေံ", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "အဳရာန်-အခိုက်ကၞာ", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "အဳရာန်-အခိုက်ကၞာ", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "သေတ်တဳယာန်-အခိုက်ကၞာ", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "သာမာတဳယာန်-အခိုက်ကၞာ", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "သကာ-ဝါကဳ-အခိုက်ကၞာ", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "သကာ-အခိုက်ကၞာ", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "သတ်ဓေတ်-အခိုက်ကၞာ", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "အခိုက်ကၞာ-မလိက်ဒစေၚ်", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "ဟာကျိကျဝ်", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "ဂျဖါန်နေတ်-အခိုက်ကၞာ", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "ရေဝ်ကယူ-အခိုက်ကၞာ", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "ကရေၚ်-အခိုက်ကၞာ", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "ခန်တဳ လ္ပာ်ဖာဗၟံက်", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "ခန်တဳ လ္ပာ်သၟဝ်ကျာ", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "ခန်တဳ-အခိုက်ကၞာ", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "ခန်တဳ ဒိုဟ်သမၠုၚ်ကျာ", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "ခဝ်-အခိုက်ကၞာ", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ခါမ်", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "ကိုဝ်ရဳယျာ ဂတာပ်ခေတ်ကၠာအိုတ်", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "ကာတ်ဒ်-အခိုက်ကၞာ", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "အာတာယျာလေတ်-အခိုက်ကၞာ", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "ဗါန်ယူမာသာန်", 33219, "map", "Latn, Java", } m["map-pro"] = { "အဝ်သတြေနဳယှေန်-အခိုက်ကၞာ", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "ဇျဲ", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "ရုဝ်ရာန်", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "တုဲဟောန်", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "တောဗါ", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "ဝူဝါန်", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "သျှာန်ပေ", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "သယောၚ်နူဝ်", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "အဝ်သလိယာန်-အခိုက်ကၞာ", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "ဗာနာရေတ်-အခိုက်ကၞာ", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "ကာထူအေတ်-အခိုက်ကၞာ", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "ခမူ-အခိုက်ကၞာ", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "ခမေန်နေတ်-အခိုက်ကၞာ", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "မန်လဒေါဝ်", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava translit = "mnw-translit", ancestors = "omx", } m["mkh-mnc-pro"] = { "မန်နေတ်-အခိုက်ကၞာ", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "ဗဳယေတ်နာမ်လဒေါဝ်", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "ပလံၚ်ဂျေတ်-အခိုက်ကၞာ", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "မန်-ခမေန်-အခိုက်ကၞာ", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "မန်သေံ", nil, "mkh-mnc", "Mymr, Thai", ancestors = "omx", translit = { Mymr = "mnw-translit", }, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ"}, }, } m["mnw-pi"] = { "ပါဠိမန်", "Mymr, Latn", "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", translit = { Mymr = "mnw-translit", }, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ"}, }, } m["mkh-vie-pro"] = { "ဗဳယေတ်ဒါသ်-အခိုက်ကၞာ", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "မာန်သဳ ဗဟဵု", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "မာန်သဳ လ္ပာ်သၟဝ်ကျာ", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "မာန်သဳ-အခိုက်ကၞာ", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "မာန်သဳ ဒိုဟ်သမၠုၚ်ကျာ", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "မုန်ဒါ-အခိုက်ကၞာ", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "မာယျာန်-အခိုက်ကၞာ", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "ဟေတ်ချေတ်တဳ", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "ဇူမာဲတဝ်ဗာဲကဲ", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "မေတ်သခါဝ်ဂျဳယာန်-အခိုက်ကၞာ", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "မေန် တထှေန်", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "ဟောတ်ကဳယာန်", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "မေန် ဟာဲဠုဟှိန်", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "မေန် လောံယေန်", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "တးကြူ", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "မေန် စေဟ်စေံ", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "မေန် သာန်ဃှဳအဟ်", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nds-de"] = { "ဂျာမာန်မသဝ်ဂျာမာန်", 25433, "gmw-lgm", "Latn", ancestors = "nds", ietf_subtag = "nds-DE", -- should we make this the actual code? wikimedia_codes = "nds", } m["nds-nl"] = { "ဒါတ် လဝ်သက်သာန်", 516137, "gmw-lgm", "Latn", ancestors = "nds", ietf_subtag = "nds-NL", -- should we make this the actual code? wikimedia_codes = "nds-nl", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "ခါန်ဂဝ်-ဗောအ်နူ-အခိုက်ကၞာ", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "နုဗဳယာန်-အခိုက်ကၞာ", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "မေတ်သတာတ်-အခိုက်ကၞာ", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 17003130, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-nha-pro"] = { "ဟာဴမာဟေရာ သၟဝ်ကျာ-အခိုက်ကၞာ", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "ဖိလေတ်ပိုၚ်-အခိုက်ကၞာ", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "မလာယဝ်-ပဝ်လဳနဳယှာ ဗဟဵု-လ္ပာ်ဖာဗၟံက်-အခိုက်ကၞာ", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "ဟဴမာဟေရာ-သေန်ဒရာဝါသဳ-အခိုက်ကၞာ", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "မာလာယဝ်-ချေန်မေတ်-အခိုက်ကၞာ", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "မာ်ခရုဝ်နဳသျှာ-အခိုက်ကၞာ", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "မလေဝ်လေတ်-အခိုက်ကၞာ", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "သာန်ပါဝါန်-မလာဲယဝ်-အခိုက်ကၞာ", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "အဝ်ဃှဳယျာနေတ်-အခိုက်ကၞာ", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "ပဝ်လဳနဳဃှေန် လ္ပာ်ဖာဗၟံက်-အခိုက်ကၞာ", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "နူကလဳယျာ ပဝ်လဳနဳဃှေန်-အခိုက်ကၞာ", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "ပဝ်လဳနဳဃှေန်-အခိုက်ကၞာ", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "မာလာယို-ပဝ်လဳနဳယျာ-အခိုက်ကၞာ", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "သူလာဝေသဳ သမၠုၚ်ကျာ-အခိုက်ကၞာ", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "သာဒါဝါတ် သၟဝ်ကျာ-အခိုက်ကၞာ", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "မာလာယဝ်-ပဝ်လဳနဳဃှေန် လ္ပာ်ဖာဗၟံက်-အခိုက်ကၞာ", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "နဳယျာပရာကရေတ်", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "ဂရေတ် အာန်ဒါမာအ်နဳ-အခိုက်ကၞာ", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "ဗါယ်-ထာၚ်-အခိုက်ကၞာ", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "ကိုဝ်ရဳယျာ-အခိုက်ကၞာ", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "ခရာပ်-အခိုက်ကၞာ", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "လာဲ-အခိုက်ကၞာ", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "ခရာပ်-ဒိုၚ်-အခိုက်ကၞာ", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "ယေနဳသဳယာန်-အခိုက်ကၞာ", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "ယူကဟဳ--အခိုက်ကၞာ", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "အာန်ဂဗေန်", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "ၜေအ်ဗွေန်နေတ်-ဗာရဳဃှေ", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "ၜေအ်ကဳယာဝ်", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "ချေန်ပေန်ဝါတ်", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "ဖရာန်အ်-ခါမ်တဝ်", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "ဂဲဠဝ်", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "လဳအဝ်နေတ်", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "ဋ္ဌဝ်ရေန်", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "ကာတ်တလာန်တြေံ", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "လဳအဝ်နေတ်တြေံ", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "ဂၠဳသဳယျာန်-ပဝ်တူဂြဳတြေံ", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "ပိုယ်တေဝေန်-သအ်တံၚ်ကာယ်သ်", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "ထာရာန်တဳနဝ်", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "ကာရေတ်ၜေန်-အခိုက်ကၞာ", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "ဆျာရာဒဝ်-အခိုက်ကၞာ", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "ဂျေမဇ္ဇျိမ-အခိုက်ကၞာ", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "ဂျေ-အခိုက်ကၞာ", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "သၟာ် လ္ပာ်သၟဝ်ကျာ-အခိုက်ကၞာ", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-otm", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "ဂျေ လ္ပာ်ဒိုဟ်သမၠုၚ်ကျာ-အခိုက်ကၞာ", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "တာရာနဝ်အာန်-အခိုက်ကၞာ", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "ယဴ (အမေရိကာန်ဒိုဟ်သမၠုၚ်ကျာ)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "ယူရူမာန်ဂဳ", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "သာလိ-အခိုက်ကၞာ", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "နယျဳမာ-အခိုက်ကၞာ", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "တမာန်-အခိုက်ကၞာ", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "သေၚ်ခုတ် လ္ပာ်သၟဝ်ကျာ", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "သေၚ်ခုတ်-အခိုက်ကၞာ", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "သေၚ်ခုတ် လ္ပာ်ဒိုဟ်သမၠုၚ်ကျာ", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "အာန်မာနေန်", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "ချာဟာ", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "ဒါဒါန်နေတ်တေတ်", 21838040, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-dum"] = { "ဒါန်မေတေတ်", 128810397, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-has"] = { "ဟာသာဲတေတ်", 3541433, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-his"] = { "ဟေတ်သမေအေတ်", 22948260, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "သဲလ်မိတိ-အခိုက်ကၞာ", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "သာဖှေက်တေတ်", 472586, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "အာရေဗဳယာန်သမၠုၚ်ကျာတြေံ", 35025, "sem-osa", "Sarb", translit = "Sarb-translit", } m["sem-tay"] = { "တေမာနဳတေတ်", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "ထာမူဒေတ်", 843030, "sem-cen", "Narb", translit = "Narb-translit", } m["sem-wes-pro"] = { "သဲလ်မိတိ လ္ပာ်ပလိုတ်-အခိုက်ကၞာ", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "သုဝေန်-အခိုက်ကၞာ", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "နာဂမဇ္ဇျိမ-အခိုက်ကၞာ", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "ဗါဲ-အခိုက်ကၞာ", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "ဗါဝ်ကာန်", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "ဂျာဖှာတ်", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "ကြုက်-တိဗိတ်-အခိုက်ကၞာ", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "သဳဒူ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "တာန်နဳ-အခိုက်ကၞာ", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "သလာဗေတ်-အခိုက်ကၞာ", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "သာမေတ်-အခိုက်ကၞာ", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "အလ်ဗနဳယာန်-အခိုက်ကၞာ", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "ကိုဝ်မာန်-အခိုက်ကၞာ", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "သာမဝ်ယေတ်ဒေတ်-အခိုက်ကၞာ", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "သေံ-အခိုက်ကၞာ", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "သေံဒိုဟ်ပလိုတ်သမၠုၚ်ကျာ-အခိုက်ကၞာ", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "ဗဝ်ဒဝ်-ဂါရဝ်-အခိုက်ကၞာ", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "ဂွာန်လံန်", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "ကူကဳ-ချေန်-အခိုက်ကၞာ", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "လာဠဝ်-အခိုက်ကၞာ", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "လာဇ်", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "လဝ်လဝ်ဗၟာ-အခိုက်ကၞာ", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "ဠဝ်ဠဝ်အေတ်-အခိုက်ကၞာ", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "မဳလာန်", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "မဝ်ရာန်", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "ၚာန်ဂါဝ်ချေန်", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "ခူခါန်", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "အဝ်ဂူဇ်တြေံဗွဲမပြဟ်", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "တူရကဳ အာန်နာတဝ်လဳယာန်တြေံ", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "တာခ်ကေတ်-အခိုက်ကၞာ", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "တူပဳ-ဂွာန်ရာနဳ-အခိုက်ကၞာ", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "တူပဳယာန်-အခိုက်ကၞာ", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "အာန်ချူကာ", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "ဗါလာ", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "ခယျာခါလာ", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "ဌာန်ဂုတ်သေတ်-အခိုက်ကၞာ", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "သဝ်လန်", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "ဖေန်နေတ်-အခိုက်ကၞာ", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "ကိုဝ်မဳတြေံ", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "ကိုဝ်မဳ-ယျတ်သဗါန်", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "ပါမေတ်ဗေတ်နေတ်-အခိုက်ကၞာ", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "ပါမေတ်-အခိုက်ကၞာ", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "ယူရာလေတ်-အခိုက်ကၞာ", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "ဥူဂရေတ်-အခိုက်ကၞာ", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "မန်ဂဝ်လဳယျာ-အခိုက်ကၞာ", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "မေန်-အခိုက်ကၞာ", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "သျှောၚ်ဂျိုထါဝ်", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "သာဲန်ချွေန်", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "ဟ္ၚိသာန်", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "နဝ်ဂိုဝ်ရဝ်ဒဳယျာတြေံ", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "ရုတဳနဳယာန်တြေံ", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "ချက်ခ်တြေံ", 593096, "zlw", "Latn", } m["zlw-opl"] = { "ပဝ်လာန်တြေံ", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "သလဝ်ဝေန်နဳယျာတြေံ", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "သဋ္ဌဝ်ဗေန်ဃှေန်", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") fhgebeicmele6tp2u3cgkjz4dg7feal 828 4904 401562 104703 2026-08-19T14:09:45Z 咽頭べさ 33 401562 Scribunto text/plain --[=[ This module implements the templates {{es-pr}} and {{es-IPA}}. Author: Benwing2 ]=] local export = {} local m_IPA = require("Module:IPA") local m_str_utils = require("Module:string utilities") local m_table = require("Module:table") local audio_module = "Module:audio" local headword_data_module = "Module:headword/data" local homophones_module = "Module:homophones" local hyphenation_module = "Module:hyphenation" local labels_module = "Module:labels" local links_module = "Module:links" local parameters_module = "Module:parameters" local parse_utilities_module = "Module:parse utilities" local pron_qualifier_module = "Module:pron qualifier" local references_module = "Module:references" local rhymes_module = "Module:rhymes" local force_cat = false -- for testing --[=[ FIXME: 1. Port latest changes to production module. [DONE] 2. Finish work on rhymes and hyphenation. [DONE] 3. Handle <hmp:...> for homophones. [DONE] 4. Don't add comma before phonetic IPA. [DONE] 5. Handle secondary stress, suffixes, etc. in syllabification. [DONE] 6. Need some changes to syllable splitting in consonant clusters. (e.g. 'cum‧min‧gto‧ni‧ta') [DONE] 7. Fix handling of references to correspond to Portuguese module. [DONE] 8. Propagate qualifiers on individual pronun terms to rhymes and hyph. 9. Support raw phonemic/phonetic pronunciations. [DONE] 10. Support overall audio. [DONE] 11. Keep th/ph/kh/gh/tz ([[Ertzaintza]]) together when syllabifying (but not bh due to [[subhumano]], [[subhistoria]], etc.). [DONE] 12. Support <q:...> and <qq:...> on audio. [DONE] 13. Support <a:...> and <aa:...> (using {{a|...}}, left and right) on terms, rhymes, hyphenation, homophones and audio. [DONE] 14. Support # instead of ; as separator between audio file and gloss and make sure it works if gloss has embedded # or ;. [DONE] 15. Use parse_inline_modifiers() in [[Module:parse utilities]]. [DONE] ]=] --[=[ About styles, dialects and isoglosses: From the standpoint of pronunciation, a given dialect is defined by isoglosses, which specify differences in the way of pronouncing certain phonemes. You can think of a dialect as a collection of isoglosses. For example, one isogloss is "distinción" (pronouncing written ''s'' and ''c/z'' differently) vs. "seseo" (pronouncing them the same). Another is "lleísmo" (pronouncing written ''ll'' and ''y'' differently) vs. "yeísmo" (pronouncing them the same). The dominant pronunciation in Spain can be described as distinción + yeísmo, while the pronunciation in rural northern Spain can be described as distinción + lléismo and the pronunciation across much of the Andes mountains, Paraguay, and the Philippines can be described as seseo + lléismo. Specifically, the following isoglosses are recognized (note, the isogloss specs as used in this module dispense with written accents): -- "distincion" = pronouncing ''s'' and ''c/z'' differently -- "seseo" = pronouncing ''s'' and ''c/z'' the same -- "lleismo" = pronouncing ''ll'' and ''y'' differently -- "yeismo" = pronouncing ''ll'' and ''y'' the same -- "rioplatense" = Rioplatense speech, i.e. seseo+yeismo with ''ll'' and ''y'' pronounced specially, and a clear distinction between initial ''hi-'' vs. initial ''ll-/y-'' -- "sheismo" = a type of Rioplatense speech, characteristic of Buenos Aires, where ''ll'' and ''y'' are pronounced as /ʃ/ -- "zheismo" = a type of Rioplatense speech, found outside of Buenos Aires, where ''ll'' and ''y'' are pronounced as /ʒ/ -- "quito" = seseo + lleismo, but pronouncing ''ll'' as /ʒ/ -- "yucatan" = seseo + yeismo, intervocalic ''y'' is pronounced ''i'' and lost in contact with ''i'' or ''e'' These isoglosses can be combined to yield one of the following eight dialects: -- "distincion-lleismo": distinción + lleísmo -- "distincion-yeismo": distinción + yeísmo -- "seseo-lleismo": seseo + lleísmo -- "seseo-yeismo": seseo + yeísmo -- "rioplatense-sheismo": Rioplatense with /ʃ/ (Buenos Aires) -- "rioplatense-zheismo": Rioplatense with /ʒ/ (non-Buenos Aires) -- "quito" -- "yucatan" A "style" here is a set of dialects that pronounce a given word in a given fashion. For example, if we are only considering the distinción/seseo and lleísmo/yeísmo isoglosses, there are four conceivable dialects (all of which in fact exist). However, for a given word, more than one dialect may pronounce it the same. For example, a word like [[paz]] has a ''z'' but no ''ll'', and so there are only two possible pronunciations for the four dialects. Here, the two styles are "Spain" and "Latin America". Correspondingly, a word like [[pollo]] with an ''ll'' but no ''z'' has two styles, which can approximately be described as "most of Spain and Latin America" vs. "rural northern Spain, Andes Mountains, Paraguay, Philippines". A "style spec" (indicated by the style= parameter to {{es-IPA}}) restricts the output to certain styles. A style spec can be one of the following: 1. An isogloss, e.g. "distincion", "rioplatense"; if specified, only styles containing this isogloss are output. 2. A negated isogloss, e.g. "-rioplatense". 3. An intersection of isoglosses ("A and B"), e.g. "distincion+lleismo". This can be used to restrict to specific dialects. 4. A union of isoglosses ("A or B"), e.g. "distincion,zheismo". If both plus and comma are used, plus takes precedence, e.g. "seseo+lleismo,zheismo" means either the "seseo+lleismo" dialect or the "rioplatense-zheismo" dialect. An example where the style= parameter might be used is with the word [[bluetooth]], which has one pronunciation in Spain/distinción (respelled "blutuz") but another in Latin America/seseo (respelled "blutud"). This might be represented using {{es-pr}} as {{es-pr|blutuz<style:distincion>|blutud<style:seseo>}}. ]=] local lang = require("Module:languages").getByCode("es") local decompose = require("Module:es-common").decompose local u = m_str_utils.char local rfind = m_str_utils.find local rsubn = m_str_utils.gsub local rsplit = m_str_utils.split local ulower = m_str_utils.lower local ulen = m_str_utils.len local unfd = mw.ustring.toNFD local unfc = mw.ustring.toNFC local AC = u(0x0301) -- acute = ́ local GR = u(0x0300) -- grave = ̀ local CFLEX = u(0x0302) -- circumflex = ̂ local TILDE = u(0x0303) -- tilde = ̃ local SYLDIV = u(0xFFF0) -- used to represent a user-specific syllable divider (.) so we won't change it local vowel = "aeiouüyAEIOUÜY" -- vowel; include y so we get single-word y correct and for syllabifying from spelling local V = "[" .. vowel .. "]" -- vowel class local accent = AC .. GR .. CFLEX local accent_c = "[" .. accent .. "]" local stress = AC .. GR local stress_c = "[" .. AC .. GR .. "]" local ipa_stress = "ˈˌ" local ipa_stress_c = "[" .. ipa_stress .. "]" local sylsep = "%-." .. SYLDIV -- hyphen included for syllabifying from spelling local sylsep_c = "[" .. sylsep .. "]" local wordsep = "# " local separator_not_wordsep = accent .. ipa_stress .. sylsep local separator = separator_not_wordsep .. wordsep local separator_c = "[" .. separator .. "]" local C = "[^" .. vowel .. separator .. "]" -- consonant class including h local C_NOT_H = "[^" .. vowel .. separator .. "h]" -- consonant class not including h local C_OR_WORDSEP = "[^" .. vowel .. separator_not_wordsep .. "]" -- consonant class including h, or word separator local T = "[^" .. vowel .. "lrɾjw" .. separator .. "]" -- obstruent or nasal local unstressed_words = m_table.listToSet({ "el", "la", "los", "las", -- definite articles "un", -- single-syllable indefinite articles "me", "te", "se", "lo", "le", "nos", "os", "les", -- unstressed object pronouns "mi", "mis", "tu", "tus", "su", "sus", -- unstressed possessive pronouns "que", "si", -- subordinating conjunctions "y", "e", "o", "u", "mas", -- coordinating conjunctions "de", "del", "a", "al", -- basic prepositions + combinations with articles "por", "en", "con", -- other prepositions }) -- version of rsubn() that discards all but the first return value local function rsub(term, foo, bar) local retval = rsubn(term, foo, bar) return retval end -- version of rsubn() that returns a 2nd argument boolean indicating whether -- a substitution was made. local function rsubb(term, foo, bar) local retval, nsubs = rsubn(term, foo, bar) return retval, nsubs > 0 end -- apply rsub() repeatedly until no change local function rsub_repeatedly(term, foo, bar) while true do local new_term = rsub(term, foo, bar) if new_term == term then return term end term = new_term end end local function split_on_comma(term) if not term then return nil end if term:find(",%s") then return require(parse_utilities_module).split_on_comma(term) elseif term:find(",") then return rsplit(term, ",") else return {term} end end -- Remove any HTML from the formatted text and resolve links, since the extra characters don't contribute to the -- displayed length. local function convert_to_raw_text(text) text = rsub(text, "<.->", "") if text:find("%[%[") then text = require(links_module).remove_links(text) end return text end -- Return the approximate displayed length in characters. local function textual_len(text) return ulen(convert_to_raw_text(text)) end local function construct_default_differences(dialect) if dialect == "distincion-lleismo" then return { distincion_different = false, lleismo_different = false, sheismo_different = false, need_rioplat = false, need_quito = false, need_yucatan = false, } end return nil end -- Main syllable-division algorithm. Can be called either directly on spelling (when hyphenating) or after -- non-trivial processing of respelling in the direction of pronunciation (when generating pronunciation). local function syllabify_from_spelling_or_pronun(text, is_spelling) -- Part 1: Divide before the last consonant in a cluster of consonants between vowels (but don't divide a VhV -- sequence; [[prohibir]] should be prohi.bir). Then move the syllable division marker leftwards over clusters that -- can form onsets. text = rsub_repeatedly(text, "(" .. V .. accent_c .. "*)(" .. C_NOT_H .. V .. ")", "%1.%2") text = rsub_repeatedly(text, "(" .. V .. accent_c .. "*" .. C .. "+)(" .. C .. V .. ")", "%1.%2") -- Puerto Rico + most of Spain divide tl as t.l. Mexico and the Canary Islands have .tl. Unclear what other regions -- do. Here we choose to go with .tl. See https://catalog.ldc.upenn.edu/docs/LDC2019S07/Syllabification_Rules_in_Spanish.pdf -- and https://www.spanishdict.com/guide/spanish-syllables-and-syllabification-rules. -- NOTE: When run on pronun, we have already eliminated c and v, but not when run on spelling. -- When run on pronun, don't include r, which at this point represents the trill. local cluster_r = is_spelling and "rɾ" or "ɾ" -- Don't divide Cl or Cr where C is a stop or fricative, except for dl. text = rsub(text, "([pbfvkctg])%.([l" .. cluster_r .. "])", ".%1%2") text = text:gsub("d%.([" .. cluster_r .. "])", ".d%1") -- Don't divide ch, sh, ph, th, dh, fh, kh or gh. Do allow bh to be divided ([[subhumano]], [[subhúmedo]], etc.). text = rsub(text, "([csptdfkg])%.h", ".%1h") -- Don't divide ll or rr. text = rsub(text, "([lr])%.%1", ".%1%1") -- Don't divide tz ([[Ertzaintza]], [[quetzal]], [[hertziano]] and other words of Basque, Nahuatl and German -- origin). text = rsub(text, "t%.z", ".tz") -- Per https://catalog.ldc.upenn.edu/docs/LDC2019S07/Syllabification_Rules_in_Spanish.pdf, tl at the end of a word -- (as in nahuatl, Popocatepetl etc.) is divided .tl from the previous vowel. if is_spelling then text = text:gsub("([^. %-])tl$", "%1.tl") text = text:gsub("([^. %-])(tl[ %-])", "%1.%2") else text = text:gsub("([^.#])tl#", "%1.tl") end -- Part 2: Divide hiatuses. Any aeo, or stressed iuüy, should be syllabically divided from a following aeo or -- stressed iuüy. Also divide ii and uu sequences ([[antiincendios]], [[shiita]], [[vacuum]]). Note that words with -- ii or uu next to a vowel (e.g. [[hawaiiano]]) will not make it to this point unchanged; the i or u adjacent to -- a vowel (or the second one if both are adjacent to vowels) will get converted to a consonant symbol (temporarily -- when syllabifying spelling). text = rsub_repeatedly(text, "([aeoAEO]" .. accent_c .. "*)(h?[aeo])", "%1.%2") text = rsub_repeatedly(text, "([aeoAEO]" .. accent_c .. "*)(h?" .. V .. stress_c .. ")", "%1.%2") text = rsub(text, "([iuüyIUÜY]" .. stress_c .. ")(h?[aeo])", "%1.%2") text = rsub_repeatedly(text, "([iuüyIUÜY]" .. stress_c .. ")(h?" .. V .. stress_c .. ")", "%1.%2") text = rsub_repeatedly(text, "([iI]" .. accent_c .. "*)(h?i)", "%1.%2") text = rsub_repeatedly(text, "([uU]" .. accent_c .. "*)(h?u)", "%1.%2") return text end local function syllabify_from_spelling(text) text = decompose(text) -- start at FFF1 because FFF0 is used for SYLDIV -- Temporary replacements for characters we want treated as default consonants. The C and related consonant regexes -- treat all unknown characters as consonants. local TEMP_I = u(0xFFF1) local TEMP_U = u(0xFFF2) local TEMP_Y_CONS = u(0xFFF3) local TEMP_QU = u(0xFFF4) local TEMP_QU_CAPS = u(0xFFF5) local TEMP_GU = u(0xFFF6) local TEMP_GU_CAPS = u(0xFFF7) local TEMP_H = u(0xFFF8) -- Change user-specified . into SYLDIV so we don't shuffle it around when dividing into syllables. text = text:gsub("%.", SYLDIV) text = rsub(text, "y(" .. V .. ")", TEMP_Y_CONS .. "%1") -- We don't want to break -sh- except in desh-, e.g. [[deshuesar]], [[deshonra]], [[deshecho]]. Normally, -sh- is -- automatically preserved, so we replace the h with a temporary symbol to avoid this. text = text:gsub("^([Dd]es)h", "%1" .. TEMP_H) text = text:gsub("([ %-][Dd]es)h", "%1" .. TEMP_H) -- qu mostly handled correctly automatically, but not in quietud text = rsub(text, "qu(" .. V .. ")", TEMP_QU .. "%1") text = rsub(text, "Qu(" .. V .. ")", TEMP_QU_CAPS .. "%1") text = rsub(text, "gu(" .. V .. ")", TEMP_GU .. "%1") text = rsub(text, "Gu(" .. V .. ")", TEMP_GU_CAPS .. "%1") local vowel_to_glide = { ["i"] = TEMP_I, ["u"] = TEMP_U } -- i and u between vowels -> consonant-like substitutions: [[paranoia]], [[baiano]], [[abreuense]], [[alauita]], -- [[Malaui]], etc.; also with h, as in [[marihuana]], [[parihuela]], [[antihielo]], [[pelluhuano]], [[náhuatl]], -- etc. When we do this we need to help the syllabification particularly of words with -hiV- and -huV- in them, -- otherwise we get e.g. 'an.tih.ie.lo' because we converted the i following the h to a consonant. Add .* at the -- beginning so we go right-to-left, in the case of [[hawaiiano]] -> ha.wai.iano. text = rsub_repeatedly(text, "(.*" .. V .. accent_c .. "*)(h?)([iu])(" .. V .. ")", function (v1, h, iu, v2) return v1 .. "." .. h .. vowel_to_glide[iu] .. v2 end ) text = syllabify_from_spelling_or_pronun(text, "is spelling") text = text:gsub(SYLDIV, ".") text = text:gsub(TEMP_I, "i") text = text:gsub(TEMP_U, "u") text = text:gsub(TEMP_Y_CONS, "y") text = text:gsub(TEMP_QU, "qu") text = text:gsub(TEMP_QU_CAPS, "Qu") text = text:gsub(TEMP_GU, "gu") text = text:gsub(TEMP_GU_CAPS, "Gu") text = text:gsub(TEMP_H, "h") text = unfc(text) -- No qualifiers from dialect tags because we assume all dialects hyphenate the same way. -- FIXME: There are region-specific ways of hyphenating -tl-. See above. We don't currently handle this properly. return text end -- Generate the IPA of a given respelling, where a respelling is the representation of the pronunciation of a given -- Spanish term using Spanish spelling conventions (augmented in a few cases with extra conventions such as 'sh' for -- /ʃ/). -- ɟ and ĉ are used internally to represent [ʝ⁓ɟ͡ʝ] and [t͡ʃ] -- function export.IPA(text, dialect, phonetic) local distincion = dialect == "distincion-lleismo" or dialect == "distincion-yeismo" local lleismo = dialect == "distincion-lleismo" or dialect == "seseo-lleismo" or dialect == "quito" local rioplat = dialect == "rioplatense-sheismo" or dialect == "rioplatense-zheismo" local sheismo = dialect == "rioplatense-sheismo" local quito = dialect == "quito" local yucatan = dialect == "yucatan" local distincion_different = false local lleismo_different = false local need_rioplat = false local need_quito = false local need_yucatan = false local initial_hi = false local sheismo_different = false -- start at FFF1 because FFF0 is used for SYLDIV local TEMP_Y = u(0xFFF1) local TEMP_W = u(0xFFF2) text = ulower(text or mw.loadData("Module:headword/data").pagename) -- decompose everything but ç, ñ and ü text = decompose(text) -- convert commas and en/en dashes to IPA foot boundaries text = rsub(text, "%s*[,–—]%s*", " | ") -- question mark or exclamation point in the middle of a sentence -> IPA foot boundary text = rsub(text, "([^%s])%s*[¡!¿?]%s*([^%s])", "%1 | %2") -- canonicalize multiple spaces and remove leading and trailing spaces local function canon_spaces(text) text = rsub(text, "%s+", " ") text = rsub(text, "^ ", "") text = rsub(text, " $", "") return text end text = canon_spaces(text) -- Make prefixes unstressed unless they have an explicit stress marker; also make certain -- monosyllabic words (e.g. [[el]], [[la]], [[de]], [[en]], etc.) without stress marks be -- unstressed. local words = rsplit(text, " ") for i, word in ipairs(words) do if rfind(word, "%-$") and not rfind(word, accent_c) or unstressed_words[word] then -- add CFLEX to the last vowel not the first one, or we will mess up 'que' by -- adding the CFLEX after the 'u' words[i] = rsub(word, "^(.*" .. V .. ")", "%1" .. CFLEX) end end text = table.concat(words, " ") -- Convert hyphens to spaces, to handle [[Austria-Hungría]], [[franco-italiano]], etc. text = rsub(text, "%-", " ") -- canonicalize multiple spaces again, which may have been introduced by hyphens text = canon_spaces(text) -- now eliminate punctuation text = rsub(text, "[¡!¿?']", "") -- put # at word beginning and end and double ## at text/foot boundary beginning/end text = rsub(text, " | ", "# | #") text = "##" .. rsub(text, " ", "# #") .. "##" --determining whether "y" is a consonant or a vowel text = rsub(text, "y(" .. V .. ")", "ɟ%1") -- not the real sound -- word-final -ay/-ey/-oy/-uy is stressed whereas word-final -ai/-ei/-oi/-ui is not; in addition, -- word-final -uy is /uj/ whereas word-final -ui is /wi/ (e.g. [[muy]] vs. [[fui]]) text = rsub(text, "([aeou])y#", "%1" .. TEMP_Y .. "#") -- a temporary symbol; replaced with i below text = rsub(text, "y", "i") -- handle certain combinations; sh handling needs to go before x handling to avoid issues with [[exhausto]] text = rsub(text, "ch", "ĉ") --not the real sound -- We want to keep desh- ([[deshuesar]]) as-is. Converting to des- won't work because we want it syllabified as -- 'des.we.saɾ' not #'de.swe.saɾ' (cf. [[desuelo]] /de.swe.lo/ from [[desolar]]). text = rsub(text, "#desh", "!") --temporary symbol text = rsub(text, "sh", "ʃ") text = rsub(text, "!", "#desh") --restore text = rsub(text, "#[ckp]([st])", "#%1") -- [[ctónico]], [[psicología]], [[pterodáctilo]] --x text = rsub(text, "#x", "#s") -- xenofobia, xilófono, etc. text = rsub(text, "x", "ks") --c, g, q text = rsub(text, "c([ie])", (distincion and "θ" or "z") .. "%1") -- not the real LatAm sound text = rsub(text, "g([ie])", "x%1") -- must happen after handling of x above text = rsub(text, "gu([ie])", "g%1") text = rsub(text, "gü([ie])", "gu%1") -- following must happen before stress assignment; [[branding]] has initial stress like 'brandin' text = rsub(text, "ng([^aeiouüwhlr])", "n%1") -- [[Bangkok]], [[ángstrom]], [[branding]] text = rsub(text, "qu([ie])", "k%1") text = rsub(text, "ü", "u") -- [[Düsseldorf]], [[hübnerita]], obsolete [[freqüentemente]], etc. text = rsub(text, "q", "k") -- [[quark]], [[Qatar]], [[burqa]], [[Iraq]], etc. text = rsub(text, "[zç]", distincion and "θ" or "z") -- not the real LatAm sound; "ç" became "z" in 1815 if rfind(text, "[θz]") then distincion_different = true end -- map various consonants to their phoneme equivalent text = rsub(text, "[cjñrv]", {["c"]="k", ["j"]="x", ["ñ"]="ɲ", ["r"]="ɾ", ["v"]="b" }) -- handle word- and syllable-initial hiV ([[hielo]], [[enhiesto]], [[deshielo]], ...) local word_initial_hi, syl_initial_hi text, word_initial_hi = rsubb(text, "#h?i(" .. V .. ")", rioplat and "#j%1" or "#ɟ%1") text, syl_initial_hi = rsubb(text, "(" .. C .. sylsep_c .. "*)hi(" .. V .. ")", rioplat and "%1j%2" or "%1ɟ%2") initial_hi = word_initial_hi or syl_initial_hi -- handle word- and syllable-initial huV ([[huevo]], [[deshuesar]]) text = rsubb(text, "(" .. C_OR_WORDSEP .. sylsep_c .. "*)hu(" .. V .. ")", "%1" .. TEMP_W .. "%2") -- handle double consonants that have a pronunciation different from their single equivalents -- double l lleismo_different = rfind(text, "ll") need_quito = lleismo_different and rfind(text, "ɟ") text = rsub(text, "ll", lleismo and "ʎ" or "ɟ") -- handle intervocalic -y- need_yucatan = rfind(text, V .. accent_c .. "*" .. sylsep_c .. "*[ʎɟ]" .. V) if yucatan then text = rsub_repeatedly(text, "([ei]" .. accent_c .. "*" .. sylsep_c .. "*)ɟ(" .. V .. ")", "%1.%2") text = rsub_repeatedly(text, "(" .. V .. accent_c .. "*" .. sylsep_c .. "*)ɟ" .. "([ei])", "%1.%2") text = rsub_repeatedly(text, "(" .. V .. accent_c .."*" .. sylsep_c .. "*)ɟ(" .. V .. ")", "%1i%2") end -- trill in #r, lr ([[alrededor]], [[malrotar]]), nr ([[enriquecer]], [[sonrisa]], etc.), sr ([[Israel]], -- [[desregular]], etc.), zr ([[Azrael]], [[cruzrojista]]), rr text = rsub(text, "ɾɾ", "r") text = rsub(text, "([#lnszθ])ɾ", "%1r") -- double n (e.g. [[[ennoblecer]]) text = rsub(text, "nn", "N") -- double b (e.g. [[subbase]]) text = rsub(text, "bb", "B") -- reduce any remaining double consonants ([[Addis Abeba]], [[cappa]], [[descender]] in Latin America ...); -- do this before handling of -nm- e.g. in [[inmigración]], which generates a double consonant, and do this -- before voicing stops before obstruents, to avoid problems with [[cappa]] and [[crackear]] text = rsub(text, "(" .. C .. ")%1", "%1") -- also reduce sz (Latin American in [[fascinante]], etc.) text = rsub(text, "sz", "s") -- restore double n, b text = rsub(text, "N", "nn") text = rsub(text, "B", "bb") -- voiceless stop to voiced before obstruent or nasal; but intercept -ts-, -tz- local voice_stop = { ["p"] = "b", ["t"] = "d", ["k"] = "g" } text = rsub(text, "t(" .. separator_c .. "*[szθ])", "!%1") -- temporary symbol text = rsub(text, "([ptk])(" .. separator_c .. "*" .. T .. ")", function(stop, after) return voice_stop[stop] .. after end) text = rsub(text, "!", "t") text = rsub(text, "n([# .]*[bpm])", "m%1") -- remove silent h before syllable division text = rsub(text, "h", "") -- convert i/u between vowels to glide local vowel_to_glide = { ["i"] = "j", ["u"] = "w" } -- i and u between vowels -> consonant-like substitutions: [[paranoia]], [[baiano]], [[abreuense]], [[alauita]], -- [[Malaui]], etc.; also with h, as in [[marihuana]], [[parihuela]], [[antihielo]], [[pelluhuano]], [[náhuatl]], -- etc. Add .* at the beginning so we go right-to-left, in the case of [[hawaiiano]] -> ha.wai.iano. text = rsub_repeatedly(text, "(.*" .. V .. accent_c .. "*h?)([iu])(" .. V .. ")", function (v1, iu, v2) return v1 .. vowel_to_glide[iu] .. v2 end ) --syllable division text = syllabify_from_spelling_or_pronun(text, false) --diphthongs; do not include TEMP_Y here text = rsub(text, "i([aeou])", "j%1") text = rsub(text, "u([aeio])", "w%1") local accent_to_stress_mark = { [AC] = "ˈ", [GR] = "ˌ", [CFLEX] = "" } local function accent_word(word, syllables) -- Now stress the word. If any accent exists in the word (including ^ indicating an unaccented word), -- put the stress mark(s) at the beginning of the indicated syllable(s). Otherwise, apply the default -- stress rule. if rfind(word, accent_c) then for i = 1, #syllables do syllables[i] = rsub(syllables[i], "^(.*)(" .. accent_c .. ")(.*)$", function(pre, accent, post) return accent_to_stress_mark[accent] .. pre .. post end ) end else -- Default stress rule. Words without vowels (e.g. IPA foot boundaries) don't get stress. if #syllables > 1 and (rfind(word, "[^" .. vowel .. "ns#]#") or rfind(word, C .. "[ns]#")) or #syllables == 1 and rfind(word, V) then syllables[#syllables] = "ˈ" .. syllables[#syllables] elseif #syllables > 1 then syllables[#syllables - 1] = "ˈ" .. syllables[#syllables - 1] end end end local words = rsplit(text, " ") for j, word in ipairs(words) do -- accentuation local syllables = rsplit(word, "%.") if rfind(word, "men%.te#") then local mente_syllables -- Words ends in -mente (converted above to ménte); add a stress to the preceding portion -- (e.g. [[agriamente]] -> 'ágriaménte') unless already stressed (e.g. [[rápidamente]]). -- It will be converted to secondary stress further below. Essentially, we rip the word apart -- into two words ('mente' and the preceding portion) and stress each one independently. mente_syllables = {} mente_syllables[2] = table.remove(syllables) mente_syllables[1] = table.remove(syllables) accent_word(table.concat(syllables, "."), syllables) accent_word(table.concat(mente_syllables, "."), mente_syllables) table.insert(syllables, mente_syllables[1]) table.insert(syllables, mente_syllables[2]) else accent_word(word, syllables) end -- Vowels are nasalized if followed by nasal in same syllable. if phonetic then for i = 1, #syllables do -- first check for two vowels (veinte) syllables[i] = rsub(syllables[i], "(" .. V .. ")(" .. V .. ")([mnɲ])", "%1" .. TILDE .. "%2" .. TILDE .. "%3") -- then for one vowel syllables[i] = rsub(syllables[i], "(" .. V .. ")([mnɲ])", "%1" .. TILDE .. "%2") end end -- Reconstruct the word. words[j] = table.concat(syllables, ".") end text = table.concat(words, " ") text = rsub(text, TEMP_Y, "i") --final -ay/-ey/-oy/-uy text = rsub(text, "z", "s") --real sound of LatAm Z -- suppress syllable mark before IPA stress indicator text = rsub(text, "%.(" .. ipa_stress_c .. ")", "%1") --make all primary stresses but the last one be secondary text = rsub_repeatedly(text, "ˈ(.+)ˈ", "ˌ%1ˈ") if (not initial_hi and rfind(text, "[ʎɟ]")) or (rfind(text, sylsep_c .. "[ʎɟ]")) then sheismo_different = true end if rioplat then if not initial_hi then if sheismo then text = rsub(text, "ɟ", "ʃ") else text = rsub(text, "ɟ", "ʒ") end else if sheismo then text = rsub(text, sylsep_c .. "(ɟ)", "ʃ") else text = rsub(text, sylsep_c .. "(ɟ)", "ʒ") end end end if quito then text = rsub(text, "ʎ", "ʒ") end --phonetic transcription if phonetic then -- θ, s, f before voiced consonants local voiced = "mnɲbdɟgʎ" .. TEMP_W local r = "ɾr" local tovoiced = { ["θ"] = "θ̬", ["s"] = "z", ["f"] = "v", } local function voice(sound, following) return tovoiced[sound] .. following end text = rsub(text, "([θs])(" .. separator_c .. "*[" .. voiced .. r .. "])", voice) text = rsub(text, "(f)(" .. separator_c .. "*[" .. voiced .. "])", voice) -- fricative vs. stop allophones; first convert stops to fricatives, then back to stops -- after nasals and sometimes after l local stop_to_fricative = {["b"] = "β", ["d"] = "ð", ["ɟ"] = "ʝ", ["g"] = "ɣ"} local fricative_to_stop = {["β"] = "b", ["ð"] = "d", ["ʝ"] = "ɟ", ["ɣ"] = "g"} text = rsub(text, "[bdɟg]", stop_to_fricative) text = rsub(text, "([mnɲ]" .. separator_c .. "*)([βɣ])", function(nasal, fricative) return nasal .. fricative_to_stop[fricative] end ) text = rsub(text, "([lʎmnɲ]" .. separator_c .. "*)([ðʝ])", function(nasal_l, fricative) return nasal_l .. fricative_to_stop[fricative] end ) text = rsub(text, "(##" .. ipa_stress_c .. "*)([βɣðʝ])", function(stress, fricative) return stress .. fricative_to_stop[fricative] end ) text = rsub(text, "[td]", {["t"] = "t̪", ["d"] = "d̪"}) -- nasal assimilation before consonants local labiodental, dentialveolar, dental, alveolopalatal, palatal, velar = "ɱ", "n̪", "n̟", "nʲ", "ɲ", "ŋ" local nasal_assimilation = { ["f"] = labiodental, ["t"] = dentialveolar, ["d"] = dentialveolar, ["θ"] = dental, ["ĉ"] = alveolopalatal, ["ʃ"] = alveolopalatal, ["ʒ"] = alveolopalatal, ["ɟ"] = palatal, ["ʎ"] = palatal, ["k"] = velar, ["x"] = velar, ["g"] = velar, } text = rsub(text, "n(" .. separator_c .. "*)(.)", function(stress, following) return (nasal_assimilation[following] or "n") .. stress .. following end ) -- lateral assimilation before consonants text = rsub(text, "l(" .. separator_c .. "*)(.)", function(stress, following) local l = "l" if following == "t" or following == "d" then -- dentialveolar l = "l̪" elseif following == "θ" then -- dental l = "l̟" elseif following == "ĉ" or following == "ʃ" then -- alveolopalatal l = "lʲ" end return l .. stress .. following end) --semivowels text = rsub(text, "([aeouãẽõũ][iĩ])", "%1̯") text = rsub(text, "([aeioãẽĩõ][uũ])", "%1̯") -- voiced fricatives are actually approximants text = rsub(text, "([βðɣ])", "%1̞") end -- convert fake symbols to real ones local final_conversions = { ["ħ"] = "h", -- fake aspirated "h" to real "h" ["ĉ"] = "t͡ʃ", -- fake "ch" to real "ch" ["ɟ"] = phonetic and "ɟ͡ʝ" or "ʝ", -- fake "y" to real "y" -- do the following at the very end so we can use regular g throughout ["g"] = "ɡ", -- U+0067 LATIN SMALL LETTER G → U+0261 LATIN SMALL LETTER SCRIPT G [TEMP_W] = "w̝", -- see https://en.wikipedia.org/wiki/Spanish_orthography for this } text = rsub(text, "[ħĉɟg" .. TEMP_W .. "]", final_conversions) -- remove # symbols at word and text boundaries text = rsub(text, "#", "") text = unfc(text) -- The values in `differences` are only accurate when the dialect is 'distincion-lleismo' -- because we look for sounds like /θ/ and /ʎ/ that are only present in that dialect. -- The calling code knows to only use this structure in conjunction with this dialect. -- but to make sure of this we set the structure to nil for other dialects. local differences = nil if dialect == "distincion-lleismo" then differences = { distincion_different = distincion_different, lleismo_different = lleismo_different, need_rioplat = initial_hi or sheismo_different, sheismo_different = sheismo_different, need_quito = need_quito, need_yucatan = need_yucatan, } end local ret = { text = text, differences = differences, } return ret end -- For bot usage; {{#invoke:es-pronunc|IPA_string|SPELLING|style=STYLE|phonetic=PHONETIC}} -- where -- -- 1. SPELLING is the word or respelling to generate pronunciation for; -- 2. required parameter style= indicates the pronunciation style to generate -- (e.g. "distincion-yeismo" for distinción+yeísmo, as is common in Spain; -- see the comment above export.IPA() above for the full list); -- 3. phonetic=1 specifies to generate the phonetic rather than phonemic pronunciation; function export.IPA_string(frame) local iparams = { [1] = {}, ["style"] = {required = true}, ["phonetic"] = {type = "boolean"}, } local iargs = require(parameters_module).process(frame.args, iparams) local retval = export.IPA(iargs[1], iargs.style, iargs.phonetic) return retval.text end -- Generate all relevant dialect pronunciations and group into styles. See the comment above about dialects and styles. -- A "pronunciation" here could be for example the IPA phonemic/phonetic representation of the term or the IPA form of -- the rhyme that the term belongs to. If `style_spec` is nil, this generates all styles for all dialects, but -- `style_spec` can also be a style spec such as "seseo" or "distincion+yeismo" (see comment above) to restrict the -- output. `dodialect` is a function of two arguments, `ret` and `dialect`, where `ret` is the return-value table (see -- below), and `dialect` is a string naming a particular dialect, such as "distincion-lleismo" or "rioplatense-sheismo". -- `dodialect` should side-effect the `ret` table by adding an entry to `ret.pronun` for the dialect in question. -- -- The return value is a table of the form -- -- { -- pronun = {DIALECT = {PRONUN, PRONUN, ...}, DIALECT = {PRONUN, PRONUN, ...}, ...}, -- expressed_styles = {STYLE_GROUP, STYLE_GROUP, ...}, -- } -- -- where: -- 1. DIALECT is a string such as "distincion-lleismo" naming a specific dialect. -- 2. PRONUN is a table describing a particular pronunciation. If the dialect is "distincion-lleismo", there should be -- a field in this table named `differences`, but where other fields may vary depending on the type of pronunciation -- (e.g. phonemic/phonetic or rhyme). See below for the form of the PRONUN table for phonemic/phonetic pronunciation -- vs. rhyme and the form of the `differences` field. -- 3. STYLE_GROUP is a table of the form {tag = "HIDDEN_TAG", styles = {INNER_STYLE, INNER_STYLE, ...}}. This describes -- a group of related styles (such as those for Latin America) that by default (the "hidden" form) are displayed as -- a single line, with an icon on the right to "open" the style group into the "shown" form, with multiple lines -- for each style in the group. The tag of the style group is the text displayed before the pronunciation in the -- default "hidden" form, such as "Spain" or "Latin America". It can have the special value of `false` to indicate -- that no tag text is to be displayed. Note that the pronunciation shown in the default "hidden" form is taken -- from the first style in the style group. -- 4. INNER_STYLE is a table of the form {tag = "SHOWN_TAG", pronun = {PRONUN, PRONUN, ...}}. This describes a single -- style (such as for the Andes Mountains and Paraguay in the case where the seseo+lleismo accent differs from all others), to -- be shown on a single line. `tag` is the text preceding the displayed pronunciation, or `false` if no tag text -- is to be displayed. PRONUN is a table as described above and describes a particular pronunciation. -- -- The PRONUN table has the following form for the full phonemic/phonetic pronunciation: -- -- { -- phonemic = "PHONEMIC", -- phonetic = "PHONETIC", -- differences = {FLAG = BOOLEAN, FLAG = BOOLEAN, ...}, -- } -- -- Here, `phonemic` is the phonemic pronunciation (displayed as /.../) and `phonetic` is the phonetic pronunciation -- (displayed as [...]). -- -- The PRONUN table has the following form for the rhyme pronunciation: -- -- { -- rhyme = "RHYME_PRONUN", -- num_syl = {NUM, NUM, ...}, -- q = nil or {QUALIFIER, QUALIFIER, ...}, -- differences = {FLAG = BOOLEAN, FLAG = BOOLEAN, ...}, -- } -- -- Here, `rhyme` is a phonemic pronunciation such as "ado" for [[abogado]] or "iʝa"/"iʎa" for [[tortilla]] (depending -- on the dialect), and `num_syl` is a list of the possible numbers of syllables for the term(s) that have this rhyme -- (e.g. {4} for [[abogado]], {3} for [[tortilla]] and {4, 5} for [[biología]], which may be syllabified as -- bio.lo.gí.a or bi.o.lo.gí.a). `num_syl` is used to generate syllable-count categories such as -- [[Category:Rhymes:Spanish/ia/4 syllables]] in addition to [[Category:Rhymes:Spanish/ia]]. `num_syl` may be nil to -- suppress the generation of syllable-count categories; this is typically the case with multiword terms. -- `q`, if non-nil, comes from the user using the syntax e.g. <rhyme:iʃa<q:Buenos Aires>>. -- -- The value of the `differences` field in the PRONUN table (which, as noted above, only needs to be present for the -- "distincion-lleismo" dialect, and otherwise should be nil) is a table containing flags indicating whether and how -- the per-dialect pronunciations differ. This is an optimization to avoid having to generate all six dialectal -- pronunciations and compare them. It has the following form: -- -- { -- distincion_different = BOOLEAN, -- lleismo_different = BOOLEAN, -- need_rioplat = BOOLEAN, -- sheismo_different = BOOLEAN, -- need_quito = BOOLEAN, -- need_yucatan = BOOLEAN, -- } -- -- where: -- 1. `distincion_different` should be `true` if the "distincion" and "seseo" pronunciations differ; -- 2. `lleismo_different` should be `true` if the "lleismo" and "yeismo" pronunciations differ; -- 3. `need_rioplat` should be `true` if the Rioplatense pronunciations differ from the seseo+yeismo pronunciation; -- 4. `sheismo_different` should be `true` if the "sheismo" and "zheismo" pronunciations differ. -- 5. `need_quito` should be `true` if the "quito" and "zheismo" pronunciations differ. -- 6. `need_yucatan` should be `true` if the "yucatan" and "yeismo" pronunciations differ; local function express_all_styles(style_spec, dodialect) local ret = { pronun = {}, expressed_styles = {}, } local need_rioplat local need_quito local need_yucatan -- Add a style object (see INNER_STYLE above) that represents a particular style to `ret.expressed_styles`. -- `hidden_tag` is the tag text to be used when the style group containing the style is in the default "hidden" -- state (e.g. "Spain", "Latin America" or false if there is only one style group and no tag text should be -- shown), while `tag` is the tag text to be used when the individual style is shown (e.g. a description such as -- "most of Spain and Latin America", "Andes Mountains and Paraguay" or "everywhere but Argentina and Uruguay"). -- `representative_dialect` is one of the dialects that this style represents, and whose pronunciation is stored in -- the style object. `matching_styles` is a hyphen separated string listing the isoglosses described by this style. -- For example, if the term has an ''ll'' but no ''c/z'', the `tag` text for the yeismo pronunciation will be -- "most of Spain and Latin America" and `matching_styles` will be "distincion-seseo-yeismo", indicating that -- it corresponds to both the "distincion" and "seseo" isoglosses as well as the "yeismo" isogloss. This is used -- when a particular style spec is given. If `matching_styles` is omitted, it takes its value from -- `representative_dialect`; this is used when the style contains only a single dialect. local function express_style(hidden_tag, tag, representative_dialect, matching_styles) matching_styles = matching_styles or representative_dialect -- If the Rioplatense pronunciation isn't distinctive, add all Rioplatense isoglosses. if not need_rioplat then matching_styles = matching_styles .. "-rioplatense-sheismo-zheismo" end -- also Quito if not need_quito then matching_styles = matching_styles .. "-quito" end -- Yucatan if not need_yucatan then matching_styles = matching_styles .. "-yucatan" end -- If style specified, make sure it matches the requested style. local style_matches if not style_spec then style_matches = true else local style_parts = rsplit(matching_styles, "%-") local or_styles = rsplit(style_spec, "%s*,%s*") for _, or_style in ipairs(or_styles) do local and_styles = rsplit(or_style, "%s*%+%s*") local and_matches = true for _, and_style in ipairs(and_styles) do local negate if and_style:find("^%-") then and_style = and_style:gsub("^%-", "") negate = true end local this_style_matches = false for _, part in ipairs(style_parts) do if part == and_style then this_style_matches = true break end end if negate then this_style_matches = not this_style_matches end if not this_style_matches then and_matches = false end end if and_matches then style_matches = true break end end end if not style_matches then return end -- Fetch the representative dialect's pronunciation if not already present. if not ret.pronun[representative_dialect] then dodialect(ret, representative_dialect) end -- Insert the new style into the style group, creating the group if necessary. local new_style = { tag = tag, pronun = ret.pronun[representative_dialect], } for _, hidden_tag_style in ipairs(ret.expressed_styles) do if hidden_tag_style.tag == hidden_tag then table.insert(hidden_tag_style.styles, new_style) return end end table.insert(ret.expressed_styles, { tag = hidden_tag, styles = {new_style}, }) end -- For each type of difference, figure out if the difference exists in any of the given respellings. We do this by -- generating the pronunciation for the dialect "distincion-lleismo", for each respelling. In the process of -- generating the pronunciation for a given respelling, it computes how the other dialects for that respelling -- differ. Then we take the union of these differences across the respellings. dodialect(ret, "distincion-lleismo") local differences = {} for _, difftype in ipairs { "distincion_different", "lleismo_different", "need_rioplat", "sheismo_different", "need_quito", "need_yucatan" } do for _, pronun in ipairs(ret.pronun["distincion-lleismo"]) do if pronun.differences[difftype] then differences[difftype] = true end end end local distincion_different = differences.distincion_different local lleismo_different = differences.lleismo_different need_rioplat = differences.need_rioplat local sheismo_different = differences.sheismo_different need_quito = differences.need_quito need_yucatan = differences.need_yucatan -- Now, based on the observed differences, figure out how to combine the individual dialects into styles and -- style groups. if not distincion_different and not lleismo_different then if not need_rioplat then if not need_yucatan then express_style(false, false, "distincion-lleismo", "distincion-seseo-lleismo-yeismo") else express_style(false, "everywhere but northern <<Mexico>>, <<Yucatán>> and <<Central America>> (except <<Panama>>)", "distincion-lleismo", "distincion-seseo-lleismo-yeismo") end else if not need_yucatan then express_style(false, "everywhere but <<{{w|Pampas}}>> and southern <<Argentina>> and <<Uruguay>>", "distincion-lleismo", "distincion-seseo-lleismo-yeismo") else express_style(false, "everywhere but <<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>, northern <<Mexico>>, <<Yucatán>> and <<Central America>> (except <<Panama>>)", "distincion-lleismo", "distincion-seseo-lleismo-yeismo") end end elseif distincion_different and not lleismo_different then express_style("<<Equatorial Guinea>>, <<Spain>>", "<<Equatorial Guinea>>, <<Spain>>", "distincion-lleismo", "distincion-lleismo-yeismo") if not need_rioplat and not need_yucatan then express_style("<<Latin America>>, <<Philippines>>", "<<Latin America>>, <<Philippines>>", "seseo-lleismo", "seseo-lleismo-yeismo") else express_style("<<Latin America>>, <<Philippines>>", "most of <<Latin America>>, <<Philippines>>", "seseo-lleismo", "seseo-lleismo-yeismo") end elseif not distincion_different and lleismo_different then express_style(false, "<<Equatorial Guinea>>, most of <<Latin America>> and <<Spain>>", "distincion-yeismo", "distincion-seseo-yeismo") express_style(false, "<<rural>> <<northern Spain>>, northern and central <<Andes>> (except central <<Ecuador>>), <<Bolivia>>, <<Paraguay>>, northeastern <<Argentina>>, <<Philippines>>", "distincion-lleismo", "distincion-seseo-lleismo") else express_style("<<Equatorial Guinea>>, <<Spain>>", "<<Equatorial Guinea>>, most of <<Spain>>", "distincion-yeismo") express_style("<<Latin America>>", "most of <<Latin America>>", "seseo-yeismo") express_style("<<Equatorial Guinea>>, <<Spain>>", "<<rural>> <<northern Spain>>", "distincion-lleismo") express_style("<<Latin America>>", "northern and central <<Andes>> (except central <<Ecuador>>), <<Bolivia>>, <<Paraguay>>, northeastern <<Argentina>>, <<Philippines>>", "seseo-lleismo") end if need_rioplat then if lleismo_different then local hidden_tag = distincion_different and "<<Latin America>>" or false if sheismo_different then if not need_quito then express_style(hidden_tag, "<<Buenos Aires>> and environs", "rioplatense-sheismo", "seseo-rioplatense-sheismo") express_style(hidden_tag, "central <<Ecuador>>, <<Santiago del Estero>> and environs, elsewhere in <<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>", "rioplatense-zheismo", "seseo-rioplatense-zheismo-quito") else express_style(hidden_tag, "central <<Ecuador>>, <<Santiago del Estero>> and environs", "quito", "seseo-quito") express_style(hidden_tag, "<<Buenos Aires>> and environs", "rioplatense-sheismo", "seseo-rioplatense-sheismo") express_style(hidden_tag, "elsewhere in <<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>", "rioplatense-zheismo", "seseo-rioplatense-zheismo") end else express_style(hidden_tag, "<<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>", "rioplatense-sheismo", "seseo-rioplatense-sheismo-zheismo") end else local hidden_tag = distincion_different and "<<Latin America>>, <<Philippines>>" or false if sheismo_different then express_style(hidden_tag, "<<Buenos Aires>> and environs", "rioplatense-sheismo", "seseo-rioplatense-sheismo") express_style(hidden_tag, "elsewhere in <<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>", "rioplatense-zheismo", "seseo-rioplatense-zheismo") else express_style(hidden_tag, "<<{{w|Pampas}}>> and southern <<Argentina>>, <<Uruguay>>", "rioplatense-sheismo", "seseo-rioplatense-sheismo-zheismo") end end end if need_yucatan then local hidden_tag = distincion_different and (lleismo_different and "<<Latin America>>" or "<<Latin America>>, <<Philippines>>") or false express_style(hidden_tag, "northern <<Mexico>>, <<Yucatán>>, <<Central America>> (except <<Panama>>)", "yucatan") end -- If only one style group, don't indicate the style. -- Not clear we want this in reality. --if #ret.expressed_styles == 1 then -- ret.expressed_styles[1].tag = false -- if #ret.expressed_styles[1].styles == 1 then -- ret.expressed_styles[1].styles[1].tag = false -- end --end return ret end local function format_all_styles(expressed_styles, format_style) for i, style_group in ipairs(expressed_styles) do if #style_group.styles == 1 then style_group.formatted, style_group.formatted_len = format_style(style_group.styles[1].tag, style_group.styles[1], i == 1) else style_group.formatted, style_group.formatted_len = format_style(style_group.tag, style_group.styles[1], i == 1) for j, style in ipairs(style_group.styles) do style.formatted, style.formatted_len = format_style(style.tag, style, i == 1 and j == 1) end end end local maxlen = 0 for i, style_group in ipairs(expressed_styles) do local this_len = style_group.formatted_len if #style_group.styles > 1 then for _, style in ipairs(style_group.styles) do this_len = math.max(this_len, style.formatted_len) end end maxlen = math.max(maxlen, this_len) end local lines = {} local need_major_hack = false for i, style_group in ipairs(expressed_styles) do if #style_group.styles == 1 then table.insert(lines, style_group.formatted) need_major_hack = false else local inline = '\n<div class="vsShow" style="display:none">\n' .. style_group.formatted .. "</div>" local full_prons = {} for _, style in ipairs(style_group.styles) do table.insert(full_prons, style.formatted) end local full = '\n<div class="vsHide">\n' .. table.concat(full_prons, "\n") .. "</div>" local em_length = math.floor(maxlen * 0.68) -- from [[Module:grc-pronunciation]] table.insert(lines, '<div class="vsSwitcher" data-toggle-category="pronunciations" style="width: ' .. em_length .. 'em; max-width:100%;"><span class="vsToggleElement" style="float: right;">&nbsp;</span>' .. inline .. full .. "</div>") need_major_hack = true end end -- major hack to get bullets working on the next line after a div box return table.concat(lines, "\n") .. (need_major_hack and "\n<span></span>" or "") end local function dodialect_pronun(args, ret, dialect) ret.pronun[dialect] = {} for i, term in ipairs(args.terms) do local phonemic, phonetic, differences if term.raw then phonemic = term.raw_phonemic phonetic = term.raw_phonetic differences = construct_default_differences(dialect) else phonemic = export.IPA(term.term, dialect, false) phonetic = export.IPA(term.term, dialect, true) differences = phonemic.differences phonemic = phonemic.text phonetic = phonetic.text end ret.pronun[dialect][i] = { raw = term.raw, phonemic = phonemic, phonetic = phonetic, refs = term.refs, q = term.q, qq = term.qq, a = term.a, aa = term.aa, differences = differences, } end end local function generate_pronun(args) local function this_dodialect_pronun(ret, dialect) dodialect_pronun(args, ret, dialect) end local ret = express_all_styles(args.style, this_dodialect_pronun) local function format_style(tag, expressed_style, is_first) local pronunciations = {} local formatted_pronuns = {} local function ins(formatted_part) table.insert(formatted_pronuns, formatted_part) end -- Loop through each pronunciation. For each one, add the phonemic and phonetic versions to `pronunciations`, -- for formatting by [[Module:IPA]], and also create an approximation of the formatted version so that we can -- compute the appropriate width of the HTML switcher div box that holds the different per-dialect variants. -- NOTE: The code below constructs the formatted approximation out-of-order in some cases but that doesn't -- currently matter because we assume all characters have the same width. If we change the width computation -- in a way that requires the correct order, we need changes to the code below. for j, pronun in ipairs(expressed_style.pronun) do -- Add tag to right accent qualifiers if last one local aas = pronun.aa if j == #expressed_style.pronun and tag then if aas then aas = m_table.deepCopy(aas) table.insert(aas, tag) else aas = {tag} end end local first_pronun = #pronunciations + 1 if not pronun.phonemic and not pronun.phonetic then error("Internal error: Saw neither phonemic nor phonetic pronunciation") end if pronun.phonemic then -- missing if 'raw:[...]' given -- don't display syllable division markers in phonemic local slash_pron = "/" .. pronun.phonemic:gsub("%.", "") .. "/" table.insert(pronunciations, { pron = slash_pron, }) ins(slash_pron) end if pronun.phonetic then -- missing if 'raw:/.../' given local bracket_pron = "[" .. pronun.phonetic .. "]" table.insert(pronunciations, { pron = bracket_pron, }) ins(bracket_pron) end local last_pronun = #pronunciations if pronun.q then pronunciations[first_pronun].q = pronun.q end if pronun.a then pronunciations[first_pronun].a = pronun.a end if j > 1 then pronunciations[first_pronun].separator = ", " ins(", ") end if pronun.qq then pronunciations[last_pronun].qq = pronun.qq end if aas then pronunciations[last_pronun].aa = aas end if pronun.q or pronun.qq or pronun.a or aas then -- Note: This inserts the actual formatted qualifier text, including HTML and such, but the later call -- to textual_len() removes all HTML and reduces links. ins(require(pron_qualifier_module).format_qualifiers { lang = lang, text = "", -- need to copy as formatting accent qualifiers destructively modifies the lists -- FIXME: we should avoid the need for this q = m_table.shallowCopy(pronun.q), qq = m_table.shallowCopy(pronun.qq), a = m_table.shallowCopy(pronun.a), aa = m_table.shallowCopy(aas), }) end if pronun.refs then pronunciations[last_pronun].refs = pronun.refs -- Approximate the reference using a footnote notation. This will be slightly inaccurate if there are -- more than nine references but that is rare. ins(string.rep("[1]", #pronun.refs)) end if first_pronun ~= last_pronun then pronunciations[last_pronun].separator = " " ins(" ") end end local bullet = string.rep("*", args.bullets) .. " " -- Here we construct the formatted line in `formatted`, and also try to construct the equivalent without HTML -- and wiki markup in `formatted_for_len`, so we can compute the approximate textual length for use in sizing -- the toggle box with the "more" button on the right. local pre = is_first and args.pre and args.pre .. " " or "" local post = is_first and args.post and " " .. args.post or "" local formatted = bullet .. pre .. m_IPA.format_IPA_full { lang = lang, items = pronunciations, separator = "" } .. post local formatted_for_len = bullet .. pre .. "IPA(key): " .. table.concat(formatted_pronuns) .. post return formatted, textual_len(formatted_for_len) end ret.text = format_all_styles(ret.expressed_styles, format_style) return ret end local function parse_respelling(respelling, pagename, parse_err) local raw_respelling = respelling:match("^raw:(.*)$") if raw_respelling then local raw_phonemic, raw_phonetic = raw_respelling:match("^/(.*)/ %[(.*)%]$") if not raw_phonemic then raw_phonemic = raw_respelling:match("^/(.*)/$") end if not raw_phonemic then raw_phonetic = raw_respelling:match("^%[(.*)%]$") end if not raw_phonemic and not raw_phonetic then parse_err(("Unable to parse raw respelling '%s', should be one of /.../, [...] or /.../ [...]") :format(raw_respelling)) end return { raw = true, raw_phonemic = raw_phonemic, raw_phonetic = raw_phonetic, } end if respelling == "+" then respelling = pagename end return {term = respelling} end -- External entry point for {{es-IPA}}. function export.show(frame) local params = { [1] = {}, ["pre"] = {}, ["post"] = {}, ["ref"] = {}, ["style"] = {}, ["bullets"] = {type = "number", default = 1}, } local parargs = frame:getParent().args local args = require(parameters_module).process(parargs, params) local text = args[1] or mw.loadData("Module:headword/data").pagename args.terms = {{term = text}} local ret = generate_pronun(args) return ret.text end -- Return the number of syllables of a phonemic representation, which should have syllable dividers in it but no -- hyphens. local function get_num_syl_from_phonemic(phonemic) -- Maybe we should just count vowels instead of the below code. phonemic = rsub(phonemic, "|", " ") -- remove IPA foot boundaries local words = rsplit(phonemic, " +") for i, word in ipairs(words) do -- IPA stress marks are syllable divisions if between characters; otherwise just remove. word = rsub(word, "(.)[ˌˈ](.)", "%1.%2") word = rsub(word, "[ˌˈ]", "") words[i] = word end -- There should be a syllable boundary between words. phonemic = table.concat(words, ".") return ulen(rsub(phonemic, "[^.]", "")) + 1 end -- Get the rhyme by truncating everything up through the last stress mark + any following consonants, and remove -- syllable boundary markers. local function convert_phonemic_to_rhyme(phonemic) -- NOTE: This works because the phonemic vowels are just [aeiou] possibly with diacritics that are separate -- Unicode chars. If we want to handle things like ɛ or ɔ we need to add them to `vowel`. return rsub(rsub(phonemic, ".*[ˌˈ]", ""), "^[^" .. vowel .. "]*", ""):gsub("%.", ""):gsub("t͡ʃ", "tʃ") end local function split_syllabified_spelling(spelling) return rsplit(spelling, "%.") end -- "Align" syllabification to original spelling by matching character-by-character, allowing for extra syllable and -- accent markers in the syllabification. If we encounter an extra syllable marker (.), we allow and keep it. If we -- encounter an extra accent marker in the syllabification, we drop it. In any other case, we return nil indicating -- the alignment failed. local function align_syllabification_to_spelling(syllab, spelling) local result = {} local syll_chars = rsplit(decompose(syllab), "") local spelling_chars = rsplit(decompose(spelling), "") local i = 1 local j = 1 while i <= #syll_chars or j <= #spelling_chars do local ci = syll_chars[i] local cj = spelling_chars[j] if ci == cj then table.insert(result, ci) i = i + 1 j = j + 1 elseif ci == "." then table.insert(result, ci) i = i + 1 elseif ci == AC or ci == GR or ci == CFLEX then -- skip character i = i + 1 else -- non-matching character return nil end end if i <= #syll_chars or j <= #spelling_chars then -- left-over characters on one side or the other return nil end return unfc(table.concat(result)) end local function generate_hyph_obj(term) return {syllabification = term, hyph = split_syllabified_spelling(term)} end -- Word should already be decomposed. local function word_has_vowels(word) return rfind(word, V) end local function all_words_have_vowels(term) local words = rsplit(decompose(term), "[ %-]") for i, word in ipairs(words) do -- Allow empty word; this occurs with prefixes and suffixes. if word ~= "" and not word_has_vowels(word) then return false end end return true end local function should_generate_rhyme_from_respelling(term) local words = rsplit(decompose(term), " +") return #words == 1 and -- no if multiple words not words[1]:find(".%-.") and -- no if word is composed of hyphenated parts (e.g. [[Austria-Hungría]]) not words[1]:find("%-$") and -- no if word is a prefix not (words[1]:find("^%-") and words[1]:find(CFLEX)) and -- no if word is an unstressed suffix word_has_vowels(words[1]) -- no if word has no vowels (e.g. a single letter) end local function should_generate_rhyme_from_ipa(ipa) return not ipa:find("%s") and word_has_vowels(decompose(ipa)) end local function dodialect_specified_rhymes(rhymes, hyphs, parsed_respellings, rhyme_ret, dialect) rhyme_ret.pronun[dialect] = {} for _, rhyme in ipairs(rhymes) do local num_syl = rhyme.num_syl local no_num_syl = false -- If user explicitly gave the rhyme but didn't explicitly specify the number of syllables, try to take it from -- the hyphenation. if not num_syl then num_syl = {} for _, hyph in ipairs(hyphs) do if should_generate_rhyme_from_respelling(hyph.syllabification) then local this_num_syl = 1 + ulen(rsub(hyph.syllabification, "[^.]", "")) m_table.insertIfNot(num_syl, this_num_syl) else no_num_syl = true break end end if no_num_syl or #num_syl == 0 then num_syl = nil end end -- If that fails and term is single-word, try to take it from the phonemic. if not no_num_syl and not num_syl then for _, parsed in ipairs(parsed_respellings) do for dialect, pronun in pairs(parsed.pronun.pronun[dialect]) do -- Check that pronun.phonemic exists (it may not if raw phonetic-only pronun is given). if pronun.phonemic then if not should_generate_rhyme_from_ipa(pronun.phonemic) then no_num_syl = true break end -- Count number of syllables by looking at syllable boundaries (including stress marks). local this_num_syl = get_num_syl_from_phonemic(pronun.phonemic) m_table.insertIfNot(num_syl, this_num_syl) end end if no_num_syl then break end end if no_num_syl or #num_syl == 0 then num_syl = nil end end table.insert(rhyme_ret.pronun[dialect], { rhyme = rhyme.rhyme, num_syl = num_syl, q = rhyme.q, qq = rhyme.qq, a = rhyme.a, aa = rhyme.aa, differences = construct_default_differences(dialect), }) end end local q_qq_inline_modifier_spec = { store = "insert-flattened", type = "qualifier", } local a_aa_inline_modifier_spec = { store = "insert-flattened", type = "labels", } local ref_inline_modifier_spec = { store = "insert-flattened", item_dest = "refs", type = "references", } -- Parse a pronunciation modifier in `arg`, the argument portion in an inline modifier (after the prefix), which -- specifies a pronunciation property such as rhyme, hyphenation/syllabification, homophones or audio. The argument -- can itself have inline modifiers, e.g. <audio:Foo.ogg<a:Colombia>>. The allowed inline modifiers are specified -- by `param_mods` (of the format expected by `parse_inline_modifiers()`); in addition to any modifiers specified -- there, the modifiers <q:...>, <qq:...>, <a:...>, <aa:...> and <ref:...> are always accepted (and can be repeated). -- `generate_obj` and `parse_err` are like in `parse_inline_modifiers()` and specify respectively a function to -- generate the object into which modifier properties are stored given the non-modifier part of the argument, and -- a function to generate an error message (given the message). Normally, a comma-separated list of pronunciation -- properties is accepted and parsed, where each element in the list can have its own inline modifiers and where -- no spaces are allowed next to the commas in order for them to be recognized as separators. If `no_split_on_comma` -- is given, only a single pronunciation property is accepted. In all cases, however, the return value is a list -- of property objects (when `no_split_on_comma` is given, the return value is a one-element list). local function parse_pron_modifier(arg, parse_err, generate_obj, param_mods, no_split_on_comma) if arg:find("<") then param_mods.q = q_qq_inline_modifier_spec param_mods.qq = q_qq_inline_modifier_spec param_mods.a = a_aa_inline_modifier_spec param_mods.aa = a_aa_inline_modifier_spec param_mods.ref = ref_inline_modifier_spec local retval = require(parse_utilities_module).parse_inline_modifiers(arg, { param_mods = param_mods, generate_obj = generate_obj, parse_err = parse_err, splitchar = not no_split_on_comma and "," or nil, }) if no_split_on_comma then retval = {retval} end return retval elseif no_split_on_comma then return {generate_obj(arg)} else local retval = {} for _, term in ipairs(split_on_comma(arg)) do table.insert(retval, generate_obj(term)) end return retval end end local function parse_rhyme(arg, parse_err) local function generate_obj(term) return {rhyme = term} end local param_mods = { s = { item_dest = "num_syl", type = "number", sublist = true, }, } return parse_pron_modifier(arg, parse_err, generate_obj, param_mods) end local function parse_hyph(arg, parse_err) -- None other than qualifiers local param_mods = {} return parse_pron_modifier(arg, parse_err, generate_hyph_obj, param_mods) end local function parse_homophone(arg, parse_err) local function generate_obj(term) return {term = term} end local param_mods = { t = { -- [[Module:links]] expects the gloss in "gloss". item_dest = "gloss", }, gloss = {}, -- No tr=, ts=, or sc=; doesn't make sense for Spanish. pos = {}, alt = {}, lit = {}, id = {}, g = { -- [[Module:links]] expects the genders in "genders". item_dest = "genders", sublist = true, }, } return parse_pron_modifier(arg, parse_err, generate_obj, param_mods) end local function generate_audio_obj(arg) local file, caption = arg:match("^(.-)%s*#%s*(.*)$") file = file or arg return {file = file, caption = caption} end local function parse_audio(arg, parse_err) local param_mods = { IPA = { sublist = true, }, text = {}, t = { item_dest = "gloss", }, -- No tr=, ts=, or sc=; doesn't make sense for Spanish. gloss = {}, pos = {}, -- No alt=; text= already goes in alt=. lit = {}, -- No id=; text= already goes in alt= and isn't normally linked. g = { item_dest = "genders", sublist = true, }, bad = {}, } -- Don't split on comma because some filenames have embedded commas not followed by a space -- (typically followed by an underscore). local retvals = parse_pron_modifier(arg, parse_err, generate_audio_obj, param_mods, "no split on comma") local retval = retvals[1] retval.lang = lang local textobj = require(audio_module).construct_audio_textobj(retval) retval.text = textobj retval.gloss = nil retval.pos = nil retval.lit = nil retval.genders = nil return retval end -- External entry point for {{es-pr}}. function export.show_pr(frame) local params = { [1] = {list = true}, ["rhyme"] = {convert = parse_rhyme}, ["hyph"] = {convert = parse_hyph}, ["hmp"] = {convert = parse_homophone}, ["audio"] = {list = true}, ["pagename"] = {}, } local parargs = frame:getParent().args local args = require(parameters_module).process(parargs, params) local pagename = args.pagename or mw.loadData(headword_data_module).pagename -- Parse the arguments. local respellings = #args[1] > 0 and args[1] or {"+"} local parsed_respellings = {} local overall_rhyme = args.rhyme local overall_hyph = args.hyph local overall_hmp = args.hmp local overall_audio if args.audio then -- We can't specify parse_audio() as a `convert` function because it needs access to `pagename` (i.e. another -- parameter). overall_audio = {} for i, audio in ipairs(args.audio) do local function parse_err(msg) error(("%s: parameter audio%s=%s"):format(msg, i == 1 and "" or i, audio)) end local parsed_audio = parse_audio(audio, parse_err, pagename) table.insert(overall_audio, parsed_audio) end end for i, respelling in ipairs(respellings) do if respelling:find("<") then local param_mods = { pre = { overall = true }, post = { overall = true }, style = { overall = true }, bullets = { overall = true, type = "number", }, rhyme = { overall = true, store = "insert-flattened", convert = parse_rhyme, }, hyph = { overall = true, store = "insert-flattened", convert = parse_hyph, }, hmp = { overall = true, store = "insert-flattened", convert = parse_homophone, }, audio = { overall = true, store = "insert", convert = function(arg, parse_err) return parse_audio(arg, parse_err, pagename) end, }, ref = ref_inline_modifier_spec, q = q_qq_inline_modifier_spec, qq = q_qq_inline_modifier_spec, a = a_aa_inline_modifier_spec, aa = a_aa_inline_modifier_spec, } local parsed = require(parse_utilities_module).parse_inline_modifiers(respelling, { paramname = i, param_mods = param_mods, generate_obj = function(term, parse_err) return parse_respelling(term, pagename, parse_err) end, splitchar = ",", outer_container = { audio = {}, rhyme = {}, hyph = {}, hmp = {} } }) if not parsed.bullets then parsed.bullets = 1 end table.insert(parsed_respellings, parsed) else local termobjs = {} local function parse_err(msg) error(msg .. ": " .. i .. "=" .. respelling) end for _, term in ipairs(split_on_comma(respelling)) do table.insert(termobjs, parse_respelling(term, pagename, parse_err)) end table.insert(parsed_respellings, { terms = termobjs, audio = {}, rhyme = {}, hyph = {}, hmp = {}, bullets = 1, }) end end if overall_hyph then local hyphs = {} for _, hyph in ipairs(overall_hyph) do if hyph.syllabification == "+" then hyph.syllabification = syllabify_from_spelling(pagename) hyph.hyph = split_syllabified_spelling(hyph.syllabification) elseif hyph.syllabification == "-" then overall_hyph = {} break end end end -- Loop over individual respellings, processing each. for _, parsed in ipairs(parsed_respellings) do parsed.pronun = generate_pronun(parsed) local no_auto_rhyme = false for _, term in ipairs(parsed.terms) do if term.raw then if not should_generate_rhyme_from_ipa(term.raw_phonemic or term.raw_phonetic) then no_auto_rhyme = true break end elseif not should_generate_rhyme_from_respelling(term.term) then no_auto_rhyme = true break end end if #parsed.hyph == 0 then if not overall_hyph and all_words_have_vowels(pagename) then for _, term in ipairs(parsed.terms) do if not term.raw then local syllabification = syllabify_from_spelling(term.term) local aligned_syll = align_syllabification_to_spelling(syllabification, pagename) if aligned_syll then m_table.insertIfNot(parsed.hyph, generate_hyph_obj(aligned_syll)) end end end end else for _, hyph in ipairs(parsed.hyph) do if hyph.syllabification == "+" then hyph.syllabification = syllabify_from_spelling(pagename) hyph.hyph = split_syllabified_spelling(hyph.syllabification) elseif hyph.syllabification == "-" then parsed.hyph = {} break end end end -- Generate the rhymes. local function dodialect_rhymes_from_pronun(rhyme_ret, dialect) rhyme_ret.pronun[dialect] = {} -- It's possible the pronunciation for a passed-in dialect was never generated. This happens e.g. with -- {{es-pr|cebolla<style:seseo>}}. The initial call to generate_pronun() fails to generate a pronunciation -- for the dialect 'distinction-yeismo' because the pronunciation of 'cebolla' differs between distincion -- and seseo and so the seseo style restriction rules out generation of pronunciation for distincion -- dialects (other than 'distincion-lleismo', which always gets generated so as to determine on which axes -- the dialects differ). However, when generating the rhyme, it is based only on -olla, whose pronunciation -- does not differ between distincion and seseo, but does differ between lleismo and yeismo, so it needs to -- generate a yeismo-specific rhyme, and 'distincion-yeismo' is the representative dialect for yeismo in the -- situation where distincion and seseo do not have distinct results (based on the following line in -- express_all_styles()): -- express_style(false, "<<Equatorial Guinea>>, most of <<Latin America>> and <<Spain>>", "distincion-yeismo", "distincion-seseo-yeismo") -- In this case we need to generate the missing overall pronunciation ourselves since we need it to generate -- the dialect-specific rhyme pronunciation. if not parsed.pronun.pronun[dialect] then dodialect_pronun(parsed, parsed.pronun, dialect) end for _, pronun in ipairs(parsed.pronun.pronun[dialect]) do -- We should have already excluded multiword terms and terms without vowels from rhyme generation (see -- `no_auto_rhyme` below). But make sure to check that pronun.phonemic exists (it may not if raw -- phonetic-only pronun is given). if pronun.phonemic then -- Count number of syllables by looking at syllable boundaries (including stress marks). local num_syl = get_num_syl_from_phonemic(pronun.phonemic) -- Get the rhyme by truncating everything up through the last stress mark + any following -- consonants, and remove syllable boundary markers. local rhyme = convert_phonemic_to_rhyme(pronun.phonemic) local saw_already = false for _, existing in ipairs(rhyme_ret.pronun[dialect]) do if existing.rhyme == rhyme then saw_already = true -- We already saw this rhyme but possibly with a different number of syllables, -- e.g. if the user specified two pronunciations 'biología' (4 syllables) and -- 'bi.ología' (5 syllables), both of which have the same rhyme /ia/. m_table.insertIfNot(existing.num_syl, num_syl) break end end if not saw_already then local rhyme_diffs = nil if dialect == "distincion-lleismo" then rhyme_diffs = {} if rhyme:find("θ") then rhyme_diffs.distincion_different = true end if rhyme:find("ʎ") then rhyme_diffs.lleismo_different = true if rhyme:find("ɟ") then rhyme_diffs.need_quito = true end end if rfind(rhyme, "[ʎɟ]") then rhyme_diffs.sheismo_different = true rhyme_diffs.need_rioplat = true if rfind(rhyme, V .. "[ʎɟ]" .. V) then rhyme_diffs.need_yucatan = true end end end table.insert(rhyme_ret.pronun[dialect], { rhyme = rhyme, num_syl = {num_syl}, differences = rhyme_diffs, }) end end end end if #parsed.rhyme == 0 then if overall_rhyme or no_auto_rhyme then parsed.rhyme = nil else parsed.rhyme = express_all_styles(parsed.style, dodialect_rhymes_from_pronun) end else local no_rhyme = false for _, rhyme in ipairs(parsed.rhyme) do if rhyme.rhyme == "-" then no_rhyme = true break end end if no_rhyme then parsed.rhyme = nil else local function this_dodialect(rhyme_ret, dialect) return dodialect_specified_rhymes(parsed.rhyme, parsed.hyph, {parsed}, rhyme_ret, dialect) end parsed.rhyme = express_all_styles(parsed.style, this_dodialect) end end end if overall_rhyme then local no_overall_rhyme = false for _, orhyme in ipairs(overall_rhyme) do if orhyme.rhyme == "-" then no_overall_rhyme = true break end end if no_overall_rhyme then overall_rhyme = nil else local all_hyphs if overall_hyph then all_hyphs = overall_hyph else all_hyphs = {} for _, parsed in ipairs(parsed_respellings) do for _, hyph in ipairs(parsed.hyph) do m_table.insertIfNot(all_hyphs, hyph) end end end local function dodialect_overall_rhyme(rhyme_ret, dialect) return dodialect_specified_rhymes(overall_rhyme, all_hyphs, parsed_respellings, rhyme_ret, dialect) end overall_rhyme = express_all_styles(parsed.style, dodialect_overall_rhyme) end end -- If all sets of pronunciations have the same rhymes, display them only once at the bottom. -- Otherwise, display rhymes beneath each set, indented. local first_rhyme_ret local all_rhyme_sets_eq = true for j, parsed in ipairs(parsed_respellings) do if j == 1 then first_rhyme_ret = parsed.rhyme elseif not m_table.deepEquals(first_rhyme_ret, parsed.rhyme) then all_rhyme_sets_eq = false break end end local function format_rhyme(rhyme_ret, num_bullets) local function format_rhyme_style(tag, expressed_style, is_first) local pronunciations = {} local rhymes = {} for _, pronun in ipairs(expressed_style.pronun) do table.insert(rhymes, pronun) end local data = { lang = lang, rhymes = rhymes, aa = tag and {tag} or nil, force_cat = force_cat, } local bullet = string.rep("*", num_bullets) .. " " local formatted = bullet .. require(rhymes_module).format_rhymes(data) local formatted_for_len_parts = {} table.insert(formatted_for_len_parts, bullet .. "ကာရန်: " .. (tag and "(" .. tag .. ") " or "")) for j, pronun in ipairs(expressed_style.pronun) do if j > 1 then table.insert(formatted_for_len_parts, ", ") end if pronun.q or pronun.qq or pronun.a or pronun.aa then -- Note: This inserts the actual formatted qualifier text, including HTML and such, but the later call -- to textual_len() removes all HTML and reduces links. table.insert(formatted_for_len_parts, require(pron_qualifier_module).format_qualifiers { lang = lang, text = "", -- need to copy as formatting accent qualifiers destructively modifies the lists -- FIXME: we should avoid the need for this q = m_table.shallowCopy(pronun.q), qq = m_table.shallowCopy(pronun.qq), a = m_table.shallowCopy(pronun.a), aa = m_table.shallowCopy(pronun.aa), }) end table.insert(formatted_for_len_parts, "-" .. pronun.rhyme) end return formatted, textual_len(table.concat(formatted_for_len_parts)) end return format_all_styles(rhyme_ret.expressed_styles, format_rhyme_style) end -- If all sets of pronunciations have the same hyphenations, display them only once at the bottom. -- Otherwise, display hyphenations beneath each set, indented. local first_hyphs local all_hyph_sets_eq = true for j, parsed in ipairs(parsed_respellings) do if j == 1 then first_hyphs = parsed.hyph elseif not m_table.deepEquals(first_hyphs, parsed.hyph) then all_hyph_sets_eq = false break end end local function format_hyphenations(hyphs, num_bullets) local hyphtext = require(hyphenation_module).format_hyphenations { lang = lang, hyphs = hyphs, caption = "Syllabification" } return string.rep("*", num_bullets) .. " " .. hyphtext end -- If all sets of pronunciations have the same homophones, display them only once at the bottom. -- Otherwise, display homophones beneath each set, indented. local first_hmps local all_hmp_sets_eq = true for j, parsed in ipairs(parsed_respellings) do if j == 1 then first_hmps = parsed.hmp elseif not m_table.deepEquals(first_hmps, parsed.hmp) then all_hmp_sets_eq = false break end end local function format_homophones(hmps, num_bullets) local hmptext = require(homophones_module).format_homophones { lang = lang, homophones = hmps } return string.rep("*", num_bullets) .. " " .. hmptext end local function format_audio(audios, num_bullets) local ret = {} for i, audio in ipairs(audios) do local text = require(audio_module).format_audio(audio) table.insert(ret, string.rep("*", num_bullets) .. " " .. text) end return table.concat(ret, "\n") end local textparts = {} local min_num_bullets = math.huge for j, parsed in ipairs(parsed_respellings) do if parsed.bullets < min_num_bullets then min_num_bullets = parsed.bullets end if j > 1 then table.insert(textparts, "\n") end table.insert(textparts, parsed.pronun.text) if #parsed.audio > 0 then table.insert(textparts, "\n") -- If only one pronunciation set, add the audio with the same number of bullets, otherwise -- indent audio by one more bullet. table.insert(textparts, format_audio(parsed.audio, #parsed_respellings == 1 and parsed.bullets or parsed.bullets + 1)) end if not all_rhyme_sets_eq and parsed.rhyme then table.insert(textparts, "\n") table.insert(textparts, format_rhyme(parsed.rhyme, parsed.bullets + 1)) end if not all_hyph_sets_eq and #parsed.hyph > 0 then table.insert(textparts, "\n") table.insert(textparts, format_hyphenations(parsed.hyph, parsed.bullets + 1)) end if not all_hmp_sets_eq and #parsed.hmp > 0 then table.insert(textparts, "\n") table.insert(textparts, format_homophones(parsed.hmp, parsed.bullets + 1)) end end if overall_audio and #overall_audio > 0 then table.insert(textparts, "\n") table.insert(textparts, format_audio(overall_audio, min_num_bullets)) end if all_rhyme_sets_eq and first_rhyme_ret then table.insert(textparts, "\n") table.insert(textparts, format_rhyme(first_rhyme_ret, min_num_bullets)) end if overall_rhyme then table.insert(textparts, "\n") table.insert(textparts, format_rhyme(overall_rhyme, min_num_bullets)) end if all_hyph_sets_eq and #first_hyphs > 0 then table.insert(textparts, "\n") table.insert(textparts, format_hyphenations(first_hyphs, min_num_bullets)) end if overall_hyph and #overall_hyph > 0 then table.insert(textparts, "\n") table.insert(textparts, format_hyphenations(overall_hyph, min_num_bullets)) end if all_hmp_sets_eq and #first_hmps > 0 then table.insert(textparts, "\n") table.insert(textparts, format_homophones(first_hmps, min_num_bullets)) end if overall_hmp and #overall_hmp > 0 then table.insert(textparts, "\n") table.insert(textparts, format_homophones(overall_hmp, min_num_bullets)) end return table.concat(textparts) end return export 79wrn9lvisekbg39t7i2kvqfh42c1gu 14 298911 401559 2026-08-19T13:45:07Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာခဝ်သဳကာန်|ခဝ်သဳကာန်]] » :ကဏ..." 401559 wikitext text/x-wiki [[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာခဝ်သဳကာန်|ခဝ်သဳကာန်]] » [[:ကဏ္ဍ:ဝေါဟာအဓိကခဝ်သဳကာန်ဂမၠိုၚ်|ဝေါဟာတံသ္ဇိုၚ်]] » [[:ကဏ္ဍ:နာမ်ခဝ်သဳကာန်ဂမၠိုၚ်|နာမ်ဂမၠိုၚ်]] » [[:ကဏ္ဍ:နာမ်ခဝ်သဳကာန်ဗက်အလိုက်လိၚ်ဂမၠိုၚ်|ဗက်အလိုက်လိၚ်ဂမၠိုၚ်]] »'''ဣတ္တိလိၚ်ဂမၠိုၚ်''' :နာမ်ခဝ်သဳကာန်မဆေၚ်စပ်ကဵုလိၚ်ဗြဴ၊ ဥပမာ ဆေၚ်စပ်ကဵုကဏ္ဍလုပ်အဝေါၚ်လိၚ်အတေံ (အကြာတၞဟ်ခြာအရာမွဲမွဲအဂှ်) မက္တဵုဒှ်ဣတ္တိလိၚ်ဂမၠိုၚ်။ [[ကဏ္ဍ:နာမ်ခဝ်သဳကာန်ဗက်အလိုက်လိၚ်ဂမၠိုၚ်|ဣ]][[ကဏ္ဍ:နာမ်ဣတ္တိလိၚ်ဗက်အလိုက်အရေဝ်ဘာသာဂမၠိုၚ်|ခ]] dq2dfwvojogeagnq2jnfxzaf2sihhqr 14 298912 401560 2026-08-19T13:47:03Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာခဝ်သဳကာန်|ခဝ်သဳကာန်]] » :ကဏ..." 401560 wikitext text/x-wiki [[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာခဝ်သဳကာန်|ခဝ်သဳကာန်]] » [[:ကဏ္ဍ:ဝေါဟာအဓိကခဝ်သဳကာန်ဂမၠိုၚ်|ဝေါဟာတံသ္ဇိုၚ်]] » [[:ကဏ္ဍ:နာမ်ခဝ်သဳကာန်ဂမၠိုၚ်|နာမ်ဂမၠိုၚ်]] »'''ဗက်အလိုက်လိၚ်ဂမၠိုၚ်''' :နာမ်ခဝ်သဳကာန်မဂကောံလဝ်နူကဵုဆေၚ်စပ်ကဵုလိၚ်ပွမတုဲဒှ်နကဵုအတေံ။ [[ကဏ္ဍ:နာမ်ခဝ်သဳကာန်ဂမၠိုၚ်]][[ကဏ္ဍ:နာမ်နူကဵုလိၚ်ဗက်အလိုက်အရေဝ်ဘာသာဂမၠိုၚ်|ခ]] fxeo42tgqwrc76h485i3ev0wstzmaxd 0 298913 401561 2026-08-19T14:03:34Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|Gallina}} ==အေက်သတဝ်ရေန်== ===နိရုတ်=== {{inh+|ast|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{ast-pr}} ===နာမ်=== {{ast-noun|f|gallines}} # စာၚ်ၝောံ။ #: {{syn|ast|pita}} ==ကာတ်တလာန်== ===ပွံၚ်နဲတၞဟ်=== * {{alt|ca|galina||Mallorca}} ===နိရုတ်=== {{inh+|ca|roa-oca|gallina}}၊ န..." 401561 wikitext text/x-wiki {{also|Gallina}} ==အေက်သတဝ်ရေန်== ===နိရုတ်=== {{inh+|ast|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{ast-pr}} ===နာမ်=== {{ast-noun|f|gallines}} # စာၚ်ၝောံ။ #: {{syn|ast|pita}} ==ကာတ်တလာန်== ===ပွံၚ်နဲတၞဟ်=== * {{alt|ca|galina||Mallorca}} ===နိရုတ်=== {{inh+|ca|roa-oca|gallina}}၊ နူကဵုဝေါဟာ {{inh|ca|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== * {{ca-IPA}} * {{audio|ca|LL-Q7026 (cat)-Unjoanqualsevol-gallina.wav|a=Catalonia}} * {{rhymes|ca|ina|s=3}} ===နာမ်=== {{ca-noun|f}} # စာၚ်ၝောံ။ ====နာမဝိသေသန==== {{ca-adj}} # ဟၟဲကဵုသတ္တိ။ ==ချာဗာကာနဝ်== ===နိရုတ်=== {{inh+|cbk|es|gallina}} ===ဗွဟ်ရမ္သာၚ်=== * {{cbk-IPA}} * {{hyph|cbk|ga|lli|na}} ===နာမ်=== {{cbk-noun}} # စာၚ်ၝောံ။ ==ခမ်နေတ်== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{der|kw|la|gallīna}} ===နာမ်=== {{kw-noun|m|gallinys}} # စာၚ်ကၠိုက်။ ==ခဝ်သဳကာန်== ===ပွံၚ်နဲတၞဟ်=== * {{alter|co|ghjaddina|ghjallina}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|co|la|gallīna}} ===နာမ်=== {{co-noun|gallin|f|a|e}} # စာၚ်ၝောံ။ ==အဳတလဳ== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|it|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{it-pr|gallìna<audio:It-una gallina.ogg>}} ===နာမ်=== {{it-noun|f|m=gallo}} # စာၚ်ၝောံ။ ==လပ်တေန်== ===ဗွဟ်ရမ္သာၚ်=== * {{la-IPA|gallīna}} ===နာမ်=== {{la-noun|gallīna<1>}} # စာၚ်ၝောံ။ ====လဟုတ်စှ်ေ==== {{la-ndecl|gallīna<1>}} ===မဒုၚ်လွဳစ=== {{top2}} ** {{desc|rup|gãljinã}} ** {{desc|ruo|gălirĕ}} ** {{desc|ruq|găľină}} ** {{desc|ro|găină}} ** {{desc|co|gallina|ghjaddina|ghjallina}} ** {{desc|dlm|galaina}} ** {{desc|it|gallina}} ** {{desc|scn|gaddina|jaddina}} ** {{desc|vec|gaƚina}} ** {{desc|fur|gjaline}} ** {{desc|lld|gialina}} ** {{desc|rm|giaglina}}, {{l|rm|gagliegna}}, {{l|rm|gaglina}} ** {{desc|lmo|gaina}} ** {{desc|ca|gallina}} ** {{desc|fro|geline}} *** {{desc|fr|géline}} *** {{desc|roa-fcm|dgelène}} *** {{desc|nrf|gelène}} *** {{desc|pcd|glinne|glaine}} ** {{desc|pro|galina|galinha}} *** {{desc|oc|galina}} ** {{desc|ast|gallina}} ** {{desc|mwl|galhina}} ** {{desctree|roa-opt|galinha}} ** {{desc|es|gallina}} ** {{desc|en|galeny|galeeny|bor=1}} {{bottom}} ==သ္ပုၚ်== ===နိရုတ်=== {{inh+|es|osp|-}}၊ နူကဵုဝေါဟာ {{inh|es|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{es-pr}} ===နာမ်=== {{es-noun|f|m=gallo}} # စာၚ်ၝောံ။ # စာၚ်။ #: {{syn|es|cagado|cagón|cagueta|cobarde}} 12ynp2hj76ndfd3egwj1ztk75ze8hjm 0 298914 401563 2026-08-19T14:13:01Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|gallina}} =={{=en=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{bor|en|it|Gallina}}၊ နူကဵုဝေါဟာ {{bor|en|scn|Gaḍḍina}}~{{m|scn|Jaḍḍina}} ===နာမ်မကိတ်ညဳ=== {{en-proper noun|s}} # {{surname|en|from=Italian}} ==အဳတလဳ== {{wp|it:+ (disambigua)}} ===နာမ်မကိတ်ညဳ=== {{it-proper noun|mfbysense}} # {{surname|it}}" 401563 wikitext text/x-wiki {{also|gallina}} =={{=en=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{bor|en|it|Gallina}}၊ နူကဵုဝေါဟာ {{bor|en|scn|Gaḍḍina}}~{{m|scn|Jaḍḍina}} ===နာမ်မကိတ်ညဳ=== {{en-proper noun|s}} # {{surname|en|from=Italian}} ==အဳတလဳ== {{wp|it:+ (disambigua)}} ===နာမ်မကိတ်ညဳ=== {{it-proper noun|mfbysense}} # {{surname|it}} ger7fq0jtjrj3m2980jf61gvyxvkwyc 401566 401563 2026-08-19T14:16:13Z 咽頭べさ 33 401566 wikitext text/x-wiki {{also|gallina}} =={{=en=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{bor|en|it|Gallina}}၊ နူကဵုဝေါဟာ {{bor|en|scn|Gaḍḍina}}~{{m|scn|Jaḍḍina}} ===နာမ်မကိတ်ညဳ=== {{en-proper noun|s}} # {{surname|en|from=Italian}} ==အဳတလဳ== {{wp|it:+ (disambigua)}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{bor|it|scn|Gaḍḍina}}~{{m|scn|Jaḍḍina}} ===နာမ်မကိတ်ညဳ=== {{it-proper noun|mfbysense}} # {{surname|it}} s83picxefzffjvtkow74nudt19e2oq5 0 298915 401564 2026-08-19T14:13:56Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|gallinas}} =={{=en=}}== ===နာမ်မကိတ်ညဳ=== {{head|en|proper noun form}} # {{plural of|en|Gallina}}" 401564 wikitext text/x-wiki {{also|gallinas}} =={{=en=}}== ===နာမ်မကိတ်ညဳ=== {{head|en|proper noun form}} # {{plural of|en|Gallina}} sbc0qex96ih3m7q3695slmq95x5r87v 0 298916 401565 2026-08-19T14:14:56Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|Gallinas}} ==လပ်တေန်== ===နာမ်=== {{head|la|noun form|head=gallīnās}} {{g|f}} # {{inflection of|la|gallīna||acc|p}} ==သ္ပုၚ်== ===နာမ်=== {{head|es|noun form|g=f-p}} # {{plural of|es|gallina}}" 401565 wikitext text/x-wiki {{also|Gallinas}} ==လပ်တေန်== ===နာမ်=== {{head|la|noun form|head=gallīnās}} {{g|f}} # {{inflection of|la|gallīna||acc|p}} ==သ္ပုၚ်== ===နာမ်=== {{head|es|noun form|g=f-p}} # {{plural of|es|gallina}} cdemcu7qxjxky1p0ev5nmrt7zdoy0lr 14 298917 401567 2026-08-19T14:16:56Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[ကဏ္ဍ:ဘာသာအဳတခ်လဳ]]" 401567 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာအဳတခ်လဳ]] gbeqdk32838i2079b24yzbewkbbcs22 14 298918 401568 2026-08-19T14:17:39Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[ကဏ္ဍ:ဘာသာအဳတခ်လဳ]]" 401568 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာအဳတခ်လဳ]] gbeqdk32838i2079b24yzbewkbbcs22 14 298919 401569 2026-08-19T14:18:34Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[ကဏ္ဍ:ဘာသာအၚ်္ဂလိက်]]" 401569 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာအၚ်္ဂလိက်]] cgthbuhht2vx8a42gqbqvafhhdb35kh 0 298920 401570 2026-08-19T14:20:43Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "==အေက်သတဝ်ရေန်== ===နာမ်=== {{head|ast|noun form}} # {{plural of|ast|gallina}} ==ကာတ်တလာန်== ===နာမ်=== {{head|ca|noun form}} # {{plural of|ca|gallina}}" 401570 wikitext text/x-wiki ==အေက်သတဝ်ရေန်== ===နာမ်=== {{head|ast|noun form}} # {{plural of|ast|gallina}} ==ကာတ်တလာန်== ===နာမ်=== {{head|ca|noun form}} # {{plural of|ca|gallina}} l4u12qawu8q6qs65loka4wmtrruhj6z 0 298921 401571 2026-08-19T14:24:27Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|galiña|Galina|Gaļina}} ==အလ်ဗနဳယာန်== ===နာမ်=== {{head|sq|noun form}} # {{infl of|sq|galinë||def|nom|s|;|indef|nom//acc|p}} ==အောက်စဳတာန်== ===ပွံၚ်နဲတၞဟ်=== * {{l|oc|garia}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|oc|pro|galina}}, {{m|pro|galinha}}၊ နူကဵုဝေါဟာ {{inh|oc|la|gallīna}..." 401571 wikitext text/x-wiki {{also|galiña|Galina|Gaļina}} ==အလ်ဗနဳယာန်== ===နာမ်=== {{head|sq|noun form}} # {{infl of|sq|galinë||def|nom|s|;|indef|nom//acc|p}} ==အောက်စဳတာန်== ===ပွံၚ်နဲတၞဟ်=== * {{l|oc|garia}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|oc|pro|galina}}, {{m|pro|galinha}}၊ နူကဵုဝေါဟာ {{inh|oc|la|gallīna}}. ===ဗွဟ်ရမ္သာၚ်=== * {{IPA|oc|[ɡaˈlino]}} * {{audio|oc|LL-Q942602-Davidgrosclaude-galina.wav|a=Languedocian}} ===နာမ်=== {{oc-noun|f}} # စာၚ်ၝောံ။ ==ဝေနေတ်== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|vec|la|gallina}} ===နာမ်=== {{head|vec|noun|g=f}} # စာၚ်ၝောံ။ 3v6mc8v74lipa3ekey5dcw7a5w68ahf 0 298922 401572 2026-08-19T17:33:01Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "==အောက်စဳတာန်== ===ပွံၚ်နဲတၞဟ်=== * {{l|oc|galina}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|oc|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== * {{audio|oc|LL-Q35735-Davidgrosclaude-garia.wav|a=Gascon}} ===နာမ်=== {{oc-noun|f}} # စာၚ်ၝောံ။" 401572 wikitext text/x-wiki ==အောက်စဳတာန်== ===ပွံၚ်နဲတၞဟ်=== * {{l|oc|galina}} ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|oc|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== * {{audio|oc|LL-Q35735-Davidgrosclaude-garia.wav|a=Gascon}} ===နာမ်=== {{oc-noun|f}} # စာၚ်ၝောံ။ eltbgebahhqxy15hafzazcaczlpubwa 0 298923 401573 2026-08-19T17:34:09Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "==အောက်စဳတာန်== ===နာမ်=== {{head|oc|noun form}} # {{plural of|oc|garia}}" 401573 wikitext text/x-wiki ==အောက်စဳတာန်== ===နာမ်=== {{head|oc|noun form}} # {{plural of|oc|garia}} q55yajsfc474ugm4fwnof47suyozr14 0 298924 401574 2026-08-19T17:35:11Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|galiñas}} ==အောက်စဳတာန်== ===နာမ်=== {{head|oc|noun form}} # {{plural of|oc|galina}}" 401574 wikitext text/x-wiki {{also|galiñas}} ==အောက်စဳတာန်== ===နာမ်=== {{head|oc|noun form}} # {{plural of|oc|galina}} jagvafl4yo8iwoq6jnjw56fbx55sbnd 0 298925 401575 2026-08-19T17:36:49Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|galinas}} ==ဂၠဳသဳယျာန်== ===နာမ်=== {{head|gl|noun form}} # {{plural of|gl|galiña}}" 401575 wikitext text/x-wiki {{also|galinas}} ==ဂၠဳသဳယျာန်== ===နာမ်=== {{head|gl|noun form}} # {{plural of|gl|galiña}} 57c4osbzu94qxuo23eajzcyzzt8hnxs 0 298926 401576 2026-08-19T17:43:30Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{also|galina|Galina|Gaļina}} ==ဂၠဳသဳယျာန်== ===ပွံၚ်နဲတၞဟ်=== * {{alt|gl|galinha||reinteg}} * {{alt|gl|galía||NE Galician}} * {{alt|gl|gallía||Galician-Asturian}} ===နိရုတ်=== {{inh+|gl|roa-opt|galinha}}၊ နကဵုအဆက်နူ {{inh|gl|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{gl-pr}} * {{hyph|gl|ga|li|ña}} ===နာမ်=== {{gl-..." 401576 wikitext text/x-wiki {{also|galina|Galina|Gaļina}} ==ဂၠဳသဳယျာန်== ===ပွံၚ်နဲတၞဟ်=== * {{alt|gl|galinha||reinteg}} * {{alt|gl|galía||NE Galician}} * {{alt|gl|gallía||Galician-Asturian}} ===နိရုတ်=== {{inh+|gl|roa-opt|galinha}}၊ နကဵုအဆက်နူ {{inh|gl|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{gl-pr}} * {{hyph|gl|ga|li|ña}} ===နာမ်=== {{gl-noun|f}} # စာၚ်ၝောံ။ #: {{syn|gl|pita}} ==ပါဲပဳယာန်မာန်တူ== [[File:Wilhelma Haushuhn 2.jpg|thumb]] ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{der|pap|pt|galinha}} ကဵု {{der|pap|kea|galinha}}၊ နကဵုမဆေၚ်စပ်ကဵုနူ {{der|pap|la|gallina}} ===နာမ်=== {{head|pap|noun}} # စာၚ်ၝောံ။ # စာၚ်။ # ကောန်ဗြဴ။ gnrspyxx980pmu9x6jk0fcxfevdgxos 14 298927 401577 2026-08-19T17:44:28Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[ကဏ္ဍ:ဘာသာပါဲပဳယာန်မာန်တူ]]" 401577 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာပါဲပဳယာန်မာန်တူ]] 47uvug4huhrqla2pkycu0r6rwrlemzq 14 298928 401578 2026-08-19T17:45:28Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[ကဏ္ဍ:ဘာသာပါဲပဳယာန်မာန်တူ]]" 401578 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာပါဲပဳယာန်မာန်တူ]] 47uvug4huhrqla2pkycu0r6rwrlemzq 14 298929 401579 2026-08-19T17:48:53Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "[[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာဂၠဳသဳယျာန်|ဂၠဳသဳယျာန်]] » :..." 401579 wikitext text/x-wiki [[:ကဏ္ဍ:ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်|ဒၞာဲလုပ်အဝေါၚ်ကဵုပၟိက်]] » [[:ကဏ္ဍ:အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်|အရေဝ်ဘာသာအိုတ်သီုဂမၠိုၚ်]] » [[:ကဏ္ဍ:ဘာသာဂၠဳသဳယျာန်|ဂၠဳသဳယျာန်]] » [[:ကဏ္ဍ:ကာရန်:ဂၠဳသဳယျာန်|ကာရန်ဂမၠိုၚ်]] » -iɲa :စရၚ်မဆေၚ်စပ်ကဵုဝေါဟာ[[:ကဏ္ဍ:ဘာသာဂၠဳသဳယျာန်|ဂၠဳသဳယျာန်]]မနွံကာရန် iɲa ဂမၠိုၚ်။ [[ကဏ္ဍ:ကာရန်:ဂၠဳသဳယျာန်|iɲa]] n8i4kya289jsxpri612nq87tox8jwve 0 298930 401581 2026-08-19T18:40:23Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကု "==ဂၠဳသဳယျာန်== ===နာမ်=== {{gl-reinteg-noun|f}} # {{gl-reinteg sp|galiña}} ==ခါၜေါအ်အဝ်ဒဳယဴနူ== ===နိရုတ်=== {{inh+|kea|pt|galinha}}၊ နကဵုအဆက်နူ {{inh|kea|roa-opt|galinha}}၊ နကဵုမဆေၚ်စပ်ကဵုနူ {{inh|kea|la|gallīna}} ===နာမ်=== {{head|kea|noun}} # စာၚ်ၝောံ။ #..." 401581 wikitext text/x-wiki ==ဂၠဳသဳယျာန်== ===နာမ်=== {{gl-reinteg-noun|f}} # {{gl-reinteg sp|galiña}} ==ခါၜေါအ်အဝ်ဒဳယဴနူ== ===နိရုတ်=== {{inh+|kea|pt|galinha}}၊ နကဵုအဆက်နူ {{inh|kea|roa-opt|galinha}}၊ နကဵုမဆေၚ်စပ်ကဵုနူ {{inh|kea|la|gallīna}} ===နာမ်=== {{head|kea|noun}} # စာၚ်ၝောံ။ # စာၚ်။ ==ဂၠဳသဳယျာန်-ပဝ်တူဂြဳတြေံ== ===ပွံၚ်နဲတၞဟ်=== * {{l|roa-opt|galỹa}}, {{l|roa-opt|galinna}} ===နိရုတ်=== {{inh+|roa-opt|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== * {{IPA|roa-opt|/ɡa.ˈli.ɲa/|/ɡa.ˈlĩ.j̃a/}} ===နာမ်=== {{roa-opt-noun|f}} # စာၚ်ၝောံ။ ===မဒုၚ်လွဳစ=== * {{desc|gl|galiña}} * {{desc|pt|galinha}} ==ပဝ်တူဂြဳ== ===နိရုတ်=== {{inh+|pt|roa-opt|galinha}}၊ နူကဵုဝေါဟာ {{inh|pt|la|gallīna}} ===ဗွဟ်ရမ္သာၚ်=== {{pt-IPA|pt=+|br=+,galhinha}} * {{rhyme|pt|iɲɐ|s=3}} * {{hyphenation|pt|ga|li|nha}} ===နာမ်=== {{pt-noun|f}} # စာၚ်ၝောံ။ # စာၚ် (ဖျုန်(။ #: {{syn|pt|frango}} # ပူဂဵုညးမမံၚ်မွဲဓဝ်ဟွံသေၚ် (ဗွဲတၟေၚ်နကဵုမၞိဟ်ဗြဴ) ။ ===မဒုၚ်လွဳစ=== * {{desc|kea|galinha}} * {{desc|pap|galiña}} ====နာမဝိသေသန==== {{pt-adj}} # ညးမဆဵုဂဗကဵုကဝေၚ်အရိုဟ်တွဵု။ icwhrubeb1pg0vtymnq3mp2dphx4gzo 10 298931 401582 2026-08-20T02:48:39Z Hiyuune 1535 ခၞံကၠောန်လဝ် မုက်လိက် နကု "{{cattoc-box | {{cattoc|lang=eo|top=Top|A|B|C:C Ĉ|D|E|F|G|H:H Ĥ|I|J:J Ĵ|K|L|M|N|O|P|R|S:S Ŝ|T|U:U Ŭ|V|Z}} }}<noinclude>{{tcat}}</noinclude>" 401582 wikitext text/x-wiki {{cattoc-box | {{cattoc|lang=eo|top=Top|A|B|C:C Ĉ|D|E|F|G|H:H Ĥ|I|J:J Ĵ|K|L|M|N|O|P|R|S:S Ŝ|T|U:U Ŭ|V|Z}} }}<noinclude>{{tcat}}</noinclude> p0gcdidvq8jv5diiluujxm3fctkus8m