Linguifex

Module:languages/data/exceptional: Difference between revisions

← Older edit
No edit summary
No edit summary
Tags: Mobile edit Mobile web edit
 
(24 intermediate revisions by 7 users not shown)
Line 274: Line 274:
"Latn",
"Latn",
type = "conlang",
type = "conlang",
}
m["cel-gal"] = {
"Modern Gallaecian",
nil,
"cel-his",
"Latn",
type = "conlang"
}
}


Line 318: Line 328:
"Latn",
"Latn",
ancestors = "wasc",
ancestors = "wasc",
type = "conlang",
}
m["xodc"] = {
"Xodec",
nil,
"wasc",
"Latn",
ancestors = "hzlc",
type = "conlang",
type = "conlang",
}
}
Line 379: Line 399:
"Latn",
"Latn",
ancestors = "slaq-pro",
ancestors = "slaq-pro",
type = "conlang",
}
m["mcb"] = {
"Macambese",
nil,
"ine, roa, roa-oil",
"Latn",
type="conlang",
}
m["naedz"] = {
"Naedzur",
nil,
"art",
"Latn",
ancestors = "naedz-old",
type = "conlang",
}
m["naedz-old"] = {
"Old Naedzur",
nil,
"art",
"Latn",
type = "conlang",
type = "conlang",
}
}
Line 396: Line 441:
"Latn",
"Latn",
ancestors = "nent-pro",
ancestors = "nent-pro",
type = "conlang",
}
m["okan"] = {
"Misa Okan",
nil,
"art",
"Latn",
type = "conlang",
}
m["popo"] = {
"Po Po",
nil,
"art",
"Latn",
type = "conlang",
type = "conlang",
}
}
Line 405: Line 466:
"Latn",
"Latn",
ancestors = "nent-pro",
ancestors = "nent-pro",
type = "conlang",
}
m["soky"] = {
"Sokya",
nil,
"wasc",
"Latn",
ancestors = "qsc",
type = "conlang",
type = "conlang",
}
}
Line 417: Line 487:
}
}


m["anktl"] = {
m["anks"] = {
"Kairitelan",
"Ankistran substrate",
nil,
"art",
"Latn",
type = "conlang",
}
 
m["anktl"] = {
"Kairitelan",
nil,
nil,
"art",
"art",
Line 607: Line 685:
"Latn",
"Latn",
ancestors = "ebur-old",
ancestors = "ebur-old",
type = "conlang",
}
m["auth"] = {
"Authish",
nil,
"gme",
"Latn",
ancestors = "auth-old",
type = "conlang",
}
m["auth-old"] = {
"Old Authish",
nil,
"gme",
"Latn, Runr",
ancestors = "gem-pro",
type = "conlang",
}
m["caim"] = {
"Caimish",
nil,
"vdnc",
"Latn",
ancestors = "caim-old, vdnc-pro",
type = "conlang",
}
m["caim-old"] = {
"Old Caimish",
nil,
"vdnc",
"Latn",
ancestors = "vdnc-pro",
type = "conlang",
}
m["vond"] = {
"Vondic",
nil,
"vdnc",
"Latn",
ancestors = "vdnc-pro",
type = "conlang",
type = "conlang",
}
}
Line 746: Line 869:
ancestors = "ine-pro",
ancestors = "ine-pro",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
}
m["vayr-old"] = {
"Old Vayri",
nil,
"vyrc",
"Latn",
ancestors = "vayr-pro",
type = "conlang",
}
m["vayr-pro"] = {
"Proto-Vayric",
nil,
"vyrc",
"Latn",
type = "conlang",
}
m["vayr"] = {
"Vayri",
nil,
"vyrc",
"Latn",
ancestors = "vayr-old",
type = "conlang",
}
}


Line 770: Line 919:
nil,
nil,
"art",
"art",
"Latn",
"Teul, Tugv",
entry_name = {
entry_name = {
from = {"‧"},
from = {"‧"},
to = {""},
to = {""},
},
},
sort_key = {
sort_key = {
Line 779: Line 928:
},
},
type = "conlang",
type = "conlang",
translit = {
Teul = "pine-translit",
},
}
}


Line 885: Line 1,037:
}
}


m["ucr"] = {
m["ucrn"] = {
"Ucrean",
"Ucrean",
nil,
nil,
Line 1,685: Line 1,837:


m["art-nav"] = {
m["art-nav"] = {
"Na'vi",
"Naʼvi",
316939,
316939,
"art",
"art",
Line 2,435: Line 2,587:
Polyt = s["Polyt-sortkey"],
Polyt = s["Polyt-sortkey"],
},
},
}
m["cel-gal"] = {
"Modern Gallaecian",
nil, --3094789,
"cel-his",
"Latn"
}
}


Line 2,513: Line 2,658:
"Latn",
"Latn",
ancestors = "kl",
ancestors = "kl",
}
m["crp-kia"] = {
"Kiautschou German Pidgin",
108314615,
"crp",
"Latn",
ancestors = "de",
}
}


Line 2,775: Line 2,928:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
}
m["ero-gsz"] = {
"Geshiza",
nil,
"ero",
"Latn",
}
m["ero-nya"] = {
"Nyagrong Minyag",
nil,
"ero",
"Latn",
}
m["ero-tau"] = {
"Stau",
nil,
"ero",
"Latn",
}
}


Line 2,820: Line 2,994:
"esx-inu",
"esx-inu",
"Latn",
"Latn",
}
m["etli"] = {
"Etlish",
nil,
"fiu, urj",
"Latn",
ancestors = "urj-fin-pro, urj-pro",
type = "conlang",
}
}


Line 2,904: Line 3,069:
1133488,
1133488,
"gmq",
"gmq",
"Latn",
"Latn, Runr",
ancestors = "non",
ancestors = "non",
}
}
Line 2,990: Line 3,155:
78079021,
78079021,
"gmw",
"gmw",
"Latn",
"Latn, Runr",
-- type = "reconstructed",
-- type = "reconstructed",
-- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added
-- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added
Line 3,111: Line 3,276:
1231805,
1231805,
"grk",
"grk",
"Latn",
"Latn, Polyt",
type = "reconstructed",
type = "reconstructed",
sort_key = {
sort_key = {Latn = {
from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ď", "ľ", "ň", "ř", "ʰ", "ʷ", c.acute, c.macron},
from = {"ʰ", "ʷ"},
to = {"a", "e", "i", "o", "u", "d", "l", "n", "r", "¯h", "¯w"}
to = {"h", "w"},
},
remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron
}},
}
}


Line 3,218: Line 3,384:
}
}


m["inc-krn-pro"] = {
m["inc-krd-pro"] = {
"Proto-Kamta",
"Proto-Kamta",
128816843,
128816843,
Line 3,397: Line 3,563:
m["ine-toc-pro"] = {
m["ine-toc-pro"] = {
"Proto-Tocharian",
"Proto-Tocharian",
37029,
104841462,
"ine-toc",
"ine-toc",
"Latn",
"Latn",
Line 3,433: Line 3,599:
129850,
129850,
"xme",
"xme",
"fa-Arab, Latn",
"fa-Arab, Latn, Hebr",
ancestors = "xme-mid",
ancestors = "xme-mid",
}
}
Line 3,640: Line 3,806:
}
}


m["jpx-hcj"] = {
m["itc-psa"] = {
"Hachijō",
"Pre-Samnite",
5637049,
7239186,
"jpx",
"itc-sbl",
"Jpan",
"Ital, Polyt, Latn",
ancestors = "ojp-eas",
translit = {
Polyt = "grc-translit",
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
Polyt = s["Polyt-sortkey"],
},
}
 
m["jpx-hcj"] = {
"Hachijō",
5637049,
"jpx",
"Jpan",
ancestors = "ojp-eas",
translit = s["jpx-translit"],
translit = s["jpx-translit"],
display_text = s["jpx-displaytext"],
display_text = s["jpx-displaytext"],
Line 3,683: Line 3,868:
translit = "kca-translit",
translit = "kca-translit",
override_translit = true,
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"} } },
}
}


Line 3,692: Line 3,879:
translit = "kca-translit",
translit = "kca-translit",
override_translit = true,
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"} } },
}
}


Line 3,764: Line 3,953:
33219,
33219,
"map",
"map",
"Latn",
"Latn, Java",
}
}


Line 3,780: Line 3,969:
"qfa-mix",
"qfa-mix",
ancestors = "nan-hbl, sou, mfa",
ancestors = "nan-hbl, sou, mfa",
}
m["mis-idn"] = {
"Idiom Neutral",
35847,
"art",
"Latn",
type = "appendix-constructed",
}
}


Line 3,838: Line 4,035:
"Hani, Latn",
"Hani, Latn",
sort_key = {Hani = "Hani-sortkey"},
sort_key = {Hani = "Hani-sortkey"},
}
m["mis-tdl"] = {
"Turdulian",
133176492,
}
m["mis-tdt"] = {
"Turdetanian",
133176461,
}
}


Line 3,876: Line 4,083:
4448647,
4448647,
"qfa-xgx",
"qfa-xgx",
"Hani, Latn",
sort_key = {Hani = "Hani-sortkey"},
}
m["mis-xnu"] = {
"Xiongnu",
10901674,
nil,
"Hani, Latn",
"Hani, Latn",
sort_key = {Hani = "Hani-sortkey"},
sort_key = {Hani = "Hani-sortkey"},
Line 4,459: Line 4,674:
ancestors = "nds",
ancestors = "nds",
ietf_subtag = "nds-NL", -- should we make this the actual code?
ietf_subtag = "nds-NL", -- should we make this the actual code?
wikimedia_codes = "nds-nl",
}
}


Line 4,925: Line 5,141:
116773279,
116773279,
"poz-ssw",
"poz-ssw",
"Latn",
type = "reconstructed",
}
m["poz-sus-pro"] = {
"Proto-Sunda-Sulawesi",
116773281,
"poz-sus",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
Line 5,119: Line 5,327:
"Latn",
"Latn",
sort_key = s["roa-oil-sortkey"],
sort_key = s["roa-oil-sortkey"],
}
m["roa-can"] = {
"Cantabrian",
917021,
"roa-asl",
"Latn",
}
}


Line 5,162: Line 5,377:
"Leonese",
"Leonese",
34108,
34108,
"roa-ibe",
"roa-asl",
"Latn",
"Latn",
ancestors = "roa-ole",
}
}


Line 5,173: Line 5,387:
"Latn",
"Latn",
sort_key = s["roa-oil-sortkey"],
sort_key = s["roa-oil-sortkey"],
}
m["roa-oan"] = {
"Navarro-Aragonese",
2736184,
"roa-ibe",
"Latn",
}
}


Line 5,187: Line 5,394:
"roa-ocr",
"roa-ocr",
"Latn",
"Latn",
sort_key = {
sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"},
from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "·"},
to = {"a", "e", "i", "o", "u", "c"}
},
}
}


Line 5,196: Line 5,400:
"Old Leonese",
"Old Leonese",
125977465,
125977465,
"roa-ibe",
"roa-asl",
"Latn",
}
 
m["roa-ona"] = {
"Old Navarro-Aragonese",
2736184,
"roa-nar",
"Latn",
"Latn",
}
}
Line 5,203: Line 5,414:
"Old Galician-Portuguese",
"Old Galician-Portuguese",
1072111,
1072111,
"roa-ibe",
"roa-gap",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ},
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ},
Line 5,227: Line 5,438:
"Tarantino",
"Tarantino",
695526,
695526,
"roa-itd",
"roa-itr",
"Latn",
"Latn",
ancestors = "nap",
wikimedia_codes = "roa-tara",
wikimedia_codes = "roa-tara",
}
}
Line 6,079: Line 6,289:
34181,
34181,
"sio",
"sio",
"Latn",
type = "reconstructed",
}
m["sit-aao-pro"] = {
"Proto-Central Naga",
nil,
"sit-aao",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
Line 6,096: Line 6,314:
"sit-hrs",
"sit-hrs",
"Latn",
"Latn",
}
m["sit-bdi-pro"] = {
"Proto-Bodish",
nil,
"sit-bdi",
"Latn",
type = "reconstructed",
}
}


Line 6,122: Line 6,348:
"sit-luu",
"sit-luu",
"Latn",
"Latn",
}
m["sit-ers-pro"] = {
"Proto-Ersuic",
nil,
"sit-ers",
"Latn",
type = "reconstructed",
}
}


Line 6,135: Line 6,369:
"Japhug",
"Japhug",
3162245,
3162245,
"sit-rgy",
"sit-egy",
"Latn",
"Latn",
}
}
Line 6,167: Line 6,401:
nil,
nil,
"sit-khw",
"sit-khw",
"Latn",
type = "reconstructed",
}
m["sit-kon-pro"] = {
"Proto-Northern Naga",
nil,
"sit-kon",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
Line 6,174: Line 6,416:
"Lizu",
"Lizu",
6660653,
6660653,
"sit-qia",
"sit-ers",
"Latn", -- and Ersu Shaba
"Latn", -- and Ersu Shaba
}
}
Line 6,196: Line 6,438:
116773783,
116773783,
"sit-luu",
"sit-luu",
"Latn",
type = "reconstructed",
}
m["sit-nas-pro"] = {
"Proto-Naish",
nil,
"sit-nas",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
Line 6,217: Line 6,467:
"Situ",
"Situ",
19840830,
19840830,
"sit-rgy",
"sit-egy",
"Latn",
"Latn",
}
}
Line 6,242: Line 6,492:
"sit-tan",
"sit-tan",
"Latn",
"Latn",
}
m["sit-tng-pro"] = {
"Proto-Tangkhulic",
nil,
"sit-tng",
"Latn",
type = "reconstructed"
}
}


Line 6,247: Line 6,505:
"Tosu",
"Tosu",
7827899,
7827899,
"sit-qia",
"sit-ers",
"Latn", -- also Ersu Shaba
"Latn", -- also Ersu Shaba
}
}
Line 6,254: Line 6,512:
"Tshobdun",
"Tshobdun",
19840950,
19840950,
"sit-rgy",
"sit-egy",
"Latn",
"Latn",
}
}
Line 6,261: Line 6,519:
"Zbu",
"Zbu",
19841106,
19841106,
"sit-rgy",
"sit-egy",
"Latn",
"Latn",
}
}
Line 6,380: Line 6,638:
"Hani",
"Hani",
sort_key = "Hani-sortkey",
sort_key = "Hani-sortkey",
}
m["tbq-brm-pro"] = {
"Proto-Burmish",
nil,
"tbq-brm",
"Latn",
type = "reconstructed",
}
}


Line 6,459: Line 6,725:
display_text = {Mong = s["Mong-displaytext"]},
display_text = {Mong = s["Mong-displaytext"]},
entry_name = {Mong = s["Mong-entryname"]},
entry_name = {Mong = s["Mong-entryname"]},
}
-- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''.
m["trk-eog"] = {
"Early Old Oghuz",
nil,
"trk-ogz",
"ota-Arab",
entry_name = {["ota-Arab"] = "ar-entryname"},
}
}


Line 6,467: Line 6,742:
"ota-Arab",
"ota-Arab",
entry_name = {["ota-Arab"] = "ar-entryname"},
entry_name = {["ota-Arab"] = "ar-entryname"},
ancestors = "trk-eog",
}
}


Line 6,475: Line 6,751:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
standardChars = {
Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron,
}
}
}


Line 6,496: Line 6,775:
10354700,
10354700,
"tup",
"tup",
"Latn",
type = "reconstructed",
}
m["tut-pro"] = {
"Proto-Altaic",
20476501,
"tut",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
Line 6,747: Line 7,034:
13211,
13211,
"zle",
"zle",
"Cyrs",
"Arab, Cyrs, Latn",
ancestors = "orv",
ancestors = "orv",
translit = "zle-ort-translit",
translit = {
Cyrs = "zle-ort-translit",
Arab = "zle-ort-Arab-translit",
},
entry_name = {
entry_name = {
remove_diacritics = s["Cyrs-entryname"].remove_diacritics,
remove_diacritics = s["Cyrs-entryname"].remove_diacritics,
remove_exceptions = {"Ї", "ї"}
remove_exceptions = {"Ї", "ї"},
Arab = "ar-entryname",
},
},
sort_key = s["Cyrs-sortkey"],
sort_key = s["Cyrs-sortkey"],
Line 6,802: Line 7,093:
"zlw-pom",
"zlw-pom",
"Latn",
"Latn",
entry_name = "zlw-slv-entryname"
entry_name = {remove_diacritics = c.macron .. c.breve},
}
 
m["carn"] = {
    "Carnian",
    nil,
    "sla",
    "Latn",
    sort_key = {
        remove_diacritics = c.grave .. c.circ,
        from = {"ċ","ġ","œ","ṡ"},
        to = {
            "c"..p[1],
            "g"..p[1],
            "o"..p[1],
            "s"..p[1]
        },
    },
    ancestors = "sla-pro, carn-old",
    type = "conlang",
}
 
m["indv"] = {                         
    "Indevroplu",                       
    nil,                         
    "ine",                       
    "Cyrs, Latn",                         
    ancestors = "ine-pro",
    type = "conlang",
    main_category = "word",
}
}


return require("Module:languages").finalizeData(m, "language")
return require("Module:languages").finalizeData(m, "language")
Retrieved from "https://duo.linguifex.com/wiki/Module:languages/data/exceptional"