Linguifex

Module:languages/data/3/c: Difference between revisions

← Older edit
m 1 revision imported
m 1 revision imported
 
(One intermediate revision by one other user not shown)
Line 101: Line 101:
"Chambri",
"Chambri",
5069707,
5069707,
"paa-lsp",
"paa-lse",
"Latn",
"Latn",
}
}
Line 123: Line 123:
35156,
35156,
"aav-nic",
"aav-nic",
"Latn",
"Latn, Deva",
}
}


Line 132: Line 132:
"Latn",
"Latn",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. "`" .. "'%-%s"},
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. "`" .. "'%-%s"},
entry_name = {
strip_diacritics = {
remove_diacritics = c.acute,
remove_diacritics = c.acute,
from = {"â", "ê", "î", "ô", "û", "ŷ"},
from = {"â", "ê", "î", "ô", "û", "ŷ"},
Line 142: Line 142:
"Tsimané",
"Tsimané",
35950,
35950,
"qfa-iso",
"qfa-dis", -- isolate or in a putative Putative Mosetan-Chonan family
"Latn",
"Latn",
}
}
Line 163: Line 163:
"Chiquitano",
"Chiquitano",
1844993,
1844993,
"qfa-iso",
"qfa-iso", -- isolate or Macro-Jê
"Latn",
"Latn",
}
}
Line 177: Line 177:
"Canichana",
"Canichana",
2936374,
2936374,
"qfa-iso",
"qfa-dis", -- isolate, unclassified or in a putative Tequiraca-Canichana family
"Latn",
"Latn",
}
}
Line 229: Line 229:
"Latn",
"Latn",
     ancestors = "es",
     ancestors = "es",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer},
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer},
sort_key = {
sort_key = {
from = {"ch", "ll", "ñ", "r"},
from = {"ch", "ll", "ñ", "r"},
to = {"c" .. p[1], "l" .. p[1], "n" .. p[1], "r" .. p[1]}
to = {"c" .. p[1], "l" .. p[1], "n" .. p[1], "r" .. p[1]}
},
},
standardChars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnÑñOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc,
standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnÑñOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc,
}
}


Line 291: Line 291:
"Candoshi-Shapra",
"Candoshi-Shapra",
642843,
642843,
"qfa-iso",
"qfa-dis", -- isolate or related to extinct Chirino; Kaufman (2007) puts it in Saparo-Yawan, Jolkesky (2016) as
  -- Macro-Arawakan
"Latn",
"Latn",
}
}
Line 334: Line 335:
"Cafundó",
"Cafundó",
3331506,
3331506,
"roa-ibe",
"roa-gap",
"Latn",
"Latn",
ancestors = "pt",
ancestors = "pt",
Line 473: Line 474:
36455,
36455,
"zhx-com",
"zhx-com",
"Hants",
"Hants, Latn",
generate_forms = "zh-generateforms",
generate_forms = "zh-generateforms",
translit = "zh-translit",
translit = "zh-translit",
Line 522: Line 523:
},
},
override_translit = true,
override_translit = true,
entry_name = {
strip_diacritics = {
Latn = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.circ
remove_diacritics = c.grave .. c.acute .. c.circ
Line 530: Line 531:
Latn = "tl-sortkey",
Latn = "tl-sortkey",
},
},
standardChars = {
standard_chars = {
Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy",
Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy",
c.punc
c.punc
Line 554: Line 555:
"Centúúm",
"Centúúm",
33608,
33608,
"qfa-iso",
"qfa-iso", -- northeastern Nigeria
"Latn",
"Latn",
}
}
Line 613: Line 614:
"Tibt",
"Tibt",
ancestors = "xct",
ancestors = "xct",
translit = "Tibt-translit",
override_translit = true,
override_translit = true,
display_text = s["Tibt-displaytext"],
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
entry_name = s["Tibt-entryname"],
sort_key = "Tibt-sortkey",
}
}


Line 642: Line 640:


m["chf"] = {
m["chf"] = {
"Tabasco Chontal",
"Chontal Maya",
35175,
35175,
"myn",
"myn",
Line 652: Line 650:
36831,
36831,
"trk-kar",
"trk-kar",
"Arab",
"Arab, Ougr",
ancestors = "zkh",
ancestors = "zkh",
entry_name = {
strip_diacritics = {
remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef,
remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef,
from = {u(0x0671)},
from = {u(0x0671)},
to  = {u(0x0627)}
to  = {u(0x0627)}
},
translit = {
Arab = "chg-translit",
Ougr = "Ougr-translit",
},
},
}
}
Line 687: Line 689:
"azc-cup",
"azc-cup",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.macron},
strip_diacritics = {remove_diacritics = c.acute .. c.macron},
}
}


Line 706: Line 708:
"Latn",
"Latn",
sort_key = {remove_diacritics = c.macronbelow .. "-"},
sort_key = {remove_diacritics = c.macronbelow .. "-"},
entry_name = {remove_diacritics = c.acute .. c.dotbelow},
strip_diacritics = {remove_diacritics = c.acute .. c.dotbelow},
}
}


Line 734: Line 736:
"Cholón",
"Cholón",
2591243,
2591243,
nil,
"qfa-unc", -- poorly attested; possibly in a Hibito-Cholon or Cholonan family
"Latn",
"Latn",
}
}
Line 758: Line 760:
"Latn",
"Latn",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.dotabove .. "-"},
sort_key = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.dotabove .. "-"},
standardChars = "AaÁáÀàĀāȦȧEeÉéÈèĒēĖėHhKkMmNnOoÓóÒòŌōȮȯPpSsŠšTtVvXx" .. c.punc, --umlaut and circumflex not allowed
standard_chars = "AaÁáÀàĀāȦȧEeÉéÈèĒēĖėHhKkMmNnOoÓóÒòŌōȮȯPpSsŠšTtVvXx" .. c.punc, --umlaut and circumflex not allowed
}
}


Line 792: Line 794:
"Chimariko",
"Chimariko",
1294251,
1294251,
"qfa-iso",
"qfa-iso", -- possibly Hokan
"Latn",
"Latn",
}
}
Line 841: Line 843:


m["cir"] = {
m["cir"] = {
"Tîrî",
"Tinrin",
7862281,
7862281,
"poz-cln",
"poz-cln",
Line 858: Line 860:
12645578,
12645578,
"cmc",
"cmc",
"Latn, Arab, Khmr", -- Western Cham script is not yet available. Also, Arabic script is missing some glyphs.
"Latn, Arab, Khmr, Cham", -- Western Cham script is not yet available. Also, Arabic script is missing some glyphs.
}
}


Line 883: Line 885:
override_translit = true,
override_translit = true,
display_text = s["cau-Cyrl-displaytext"],
display_text = s["cau-Cyrl-displaytext"],
entry_name = s["cau-Cyrl-entryname"],
strip_diacritics = s["cau-Cyrl-stripdiacritics"],
}
}


Line 903: Line 905:
"Chenapian",
"Chenapian",
5091044,
5091044,
"paa-spk",
"paa-sep",
"Latn",
"Latn",
}
}


m["cjo"] = {
m["cjo"] = {
"Ashéninka Pajonal",
"Pajonal Ashéninka",
3450481,
3450481,
"awd",
"awd",
Line 931: Line 933:
"Chuave",
"Chuave",
5115226,
5115226,
"ngf",
"ngf-sim",
"Latn",
"Latn",
}
}
Line 952: Line 954:
"ku-Arab",
"ku-Arab",
translit = "ckb-translit",
translit = "ckb-translit",
entry_name = {remove_diacritics = c.kasra .. c.sukun},
strip_diacritics = {remove_diacritics = c.kasra .. c.sukun},
}
}


Line 994: Line 996:
"Kairak",
"Kairak",
3503002,
3503002,
"paa-bng",
"paa-bai",
"Latn",
"Latn",
}
}
Line 1,011: Line 1,013:
33170,
33170,
"qfa-ckn",
"qfa-ckn",
"Cyrl",
"Cyrl, Latn", -- Latn is obsolete
entry_name = {
strip_diacritics = {
from = {"['’]"},
from = {"['’]"},
to = {"ʼ"}
to = {"ʼ"}
Line 1,077: Line 1,079:
"sem-are",
"sem-are",
"Syrc",
"Syrc",
entry_name = "Syrc-entryname",
strip_diacritics = "Syrc-stripdiacritics",
}
}


Line 1,112: Line 1,114:
"sit-gsi",
"sit-gsi",
"Tibt, Deva",
"Tibt, Deva",
translit = {
Tibt = "Tibt-translit"
},
override_translit = true,
override_translit = true,
display_text = {
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Tibt = s["Tibt-displaytext"]
},
entry_name = {
Tibt = s["Tibt-entryname"]
},
sort_key = {
Tibt = "Tibt-sortkey"
},
}
}


Line 1,149: Line 1,140:


m["clt"] = {
m["clt"] = {
"Lautu Chin",
"Lutuv",
6502107,
6502107,
"tbq-kuk",
"tbq-kuk",
Line 1,195: Line 1,186:
"xgn-cen",
"xgn-cen",
"Mong, Soyo, Zanb",
"Mong, Soyo, Zanb",
translit = {
-- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]]
Mong = "Mong-translit"
},
display_text = {
Mong = s["Mong-displaytext"]
},
entry_name = {
Mong = s["Mong-entryname"]
},
}
}


Line 1,231: Line 1,214:
9192,
9192,
"zhx-man",
"zhx-man",
"Hants, Latn, Bopo",
"Hants, Latn, Bopo, Brai",
wikimedia_codes = "zh",
wikimedia_codes = "zh",
generate_forms = "zh-generateforms",
generate_forms = "zh-generateforms",
Line 1,277: Line 1,260:
33369881,
33369881,
"mkh-ban",
"mkh-ban",
"Khmr, Latn",
}
}


Line 1,290: Line 1,274:
"ine",
"ine",
"Ital, Latn, Polyt",
"Ital, Latn, Polyt",
translit = {
-- Ital translit in [[Module:scripts/data]]
Ital = "Ital-translit",
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Polyt = "grc-translit",
},
display_text = {
Polyt = s["Polyt-displaytext"]
},
entry_name = {
Polyt = s["Polyt-entryname"]
},
sort_key = {
Polyt = s["Polyt-sortkey"]
},
}
}


Line 1,318: Line 1,291:
"sit-lab",
"sit-lab",
"Tibt",
"Tibt",
translit = "Tibt-translit",
override_translit = true,
override_translit = true,
display_text = s["Tibt-displaytext"],
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
entry_name = s["Tibt-entryname"],
sort_key = "Tibt-sortkey",
}
}


Line 1,329: Line 1,299:
12952327,
12952327,
"tbq-kuk",
"tbq-kuk",
"Latn",
}
}


Line 1,342: Line 1,313:
56559,
56559,
"sit-qia",
"sit-qia",
"Latn",
}
}


Line 1,348: Line 1,320:
3250286,
3250286,
"tbq-kuk",
"tbq-kuk",
"Latn, Mymr",
}
}


Line 1,361: Line 1,334:
56308,
56308,
"tbq-kuk",
"tbq-kuk",
"Latn",
}
}


Line 1,388: Line 1,362:
"Central Asmat",
"Central Asmat",
11732048,
11732048,
"ngf",
"ngf-asm",
"Latn",
"Latn",
}
}
Line 1,403: Line 1,377:
33276,
33276,
"ber",
"ber",
"Latn",
}
}


Line 1,528: Line 1,503:
translit = "Copt-translit",
translit = "Copt-translit",
ancestors = "egx-dem",
ancestors = "egx-dem",
entry_name = {remove_diacritics = c.grave .. c.macron .. c.overline .. c.diaer .. "ˋ"},
strip_diacritics = {remove_diacritics = c.grave .. c.macron .. c.overline .. c.diaer .. "ˋ"},
sort_key = "cop-sortkey",
sort_key = "Copt-sortkey",
}
}


Line 1,602: Line 1,577:


m["cpc"] = {
m["cpc"] = {
"Ajyíninka Apurucayali",
"Apurucayali Ashéninka",
3327405,
3327405,
"awd",
"awd",
Line 1,617: Line 1,592:
Grek = "el-translit",
Grek = "el-translit",
},
},
display_text = {
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Grek = s["Grek-displaytext"],
},
entry_name = {
Grek = s["Grek-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
},
}
}


Line 1,852: Line 1,819:
2605680,
2605680,
"aav-nic",
"aav-nic",
"Latn",
}
}


Line 1,934: Line 1,902:
12627282,
12627282,
"tbq-kuk",
"tbq-kuk",
"Latn, Mymr",
}
}


Line 1,939: Line 1,908:
"Coast Miwok",
"Coast Miwok",
2981109,
2981109,
"nai-you",
"nai-utn",
"Latn",
"Latn",
}
}
Line 1,965: Line 1,934:
"Central Sierra Miwok",
"Central Sierra Miwok",
2944443,
2944443,
"nai-you",
"nai-utn",
"Latn",
"Latn",
}
}
Line 2,009: Line 1,978:
"Southern Ohlone",
"Southern Ohlone",
25559664,
25559664,
"nai-you",
"nai-utn",
"Latn",
"Latn",
}
}
Line 2,016: Line 1,985:
"Northern Ohlone",
"Northern Ohlone",
25559666,
25559666,
"nai-you",
"nai-utn",
"Latn",
"Latn",
}
}
Line 2,032: Line 2,001:
"Latn, Cans",
"Latn, Cans",
ancestors = "cr",
ancestors = "cr",
}
m["csx"] = {
"Cambodian Sign Language",
50934287,
"sgn",
}
}


Line 2,099: Line 2,074:
"Chitimacha",
"Chitimacha",
1294227,
1294227,
"qfa-iso",
"qfa-iso", -- recently proposed to be in the Totozoquean family
"Latn",
"Latn",
}
}
Line 2,122: Line 2,097:
"omq-cha",
"omq-cha",
"Latn",
"Latn",
entry_name = {remove_diacritics = "¹²³⁴⁵"},
strip_diacritics = {remove_diacritics = "¹²³⁴⁵"},
sort_key = {remove_diacritics = c.acute},
sort_key = {remove_diacritics = c.acute},
}
}


m["cts"] = {
m["cts"] = {
"Northern Catanduanes Bicolano",
"Northern Catanduanes Bikol",
7130477,
7130477,
"phi",
"phi",
Line 2,290: Line 2,265:
47683644,
47683644,
"sit-khc",
"sit-khc",
"Tibt, Latn",
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
-- (NOTE: formerly not present, probably an accidental omission)
}
}


Line 2,380: Line 2,358:
"Hebr",
"Hebr",
ancestors = "zlw-ocs",
ancestors = "zlw-ocs",
entry_name = {remove_diacritics = u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. c.CGJ},
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Retrieved from "https://linguifex.com/wiki/Module:languages/data/3/c"