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

From Linguifex
Jump to navigation Jump to search
Ancient Greek display text.
 
m 1 revision imported
 
(2 intermediate revisions by 2 users not shown)
Line 51: Line 51:
"Gende",
"Gende",
3100425,
3100425,
"paa-kag",
"ngf-gor",
"Latn",
"Latn",
}
}
Line 79: Line 79:
"Alekano",
"Alekano",
3441595,
3441595,
"paa-kag",
"ngf-gah",
"Latn",
"Latn",
}
}
Line 86: Line 86:
"Borei",
"Borei",
6799756,
6799756,
"paa",
"paa-ott",
"Latn",
"Latn",
}
}
Line 93: Line 93:
"Gadsup",
"Gadsup",
5516467,
5516467,
"paa-kag",
"ngf-gau",
"Latn",
"Latn",
}
}
Line 100: Line 100:
"Gamkonora",
"Gamkonora",
5520226,
5520226,
"paa-nha",
"paa-sah",
"Latn",
"Latn",
}
}
Line 114: Line 114:
"Kandawo",
"Kandawo",
6361369,
6361369,
"ngf",
"ngf-jim",
"Latn",
"Latn",
}
}
Line 132: Line 132:
"Gants",
"Gants",
5521529,
5521529,
"ngf-mad",
"ngf-eso",
"Latn",
"Latn",
}
}
Line 139: Line 139:
"Gal",
"Gal",
5517742,
5517742,
"ngf-mad",
"ngf-han",
"Latn",
"Latn",
}
}
Line 147: Line 147:
3501920,
3501920,
"mun",
"mun",
"Orya",
}
}


Line 160: Line 161:
12953522,
12953522,
"inc-bhi",
"inc-bhi",
"Deva, Gujr",
ancestors = "bhb",
ancestors = "bhb",
}
}
Line 166: Line 168:
"Kenati",
"Kenati",
4219330,
4219330,
"paa-kag",
"ngf-kgo",
"Latn",
"Latn",
}
}
Line 174: Line 176:
12952433,
12952433,
"dra-pgd",
"dra-pgd",
"Telu",
}
}


Line 179: Line 182:
"Nobonob",
"Nobonob",
11732205,
11732205,
"paa",
"ngf-han",
"Latn",
"Latn",
}
}
Line 207: Line 210:
"Niksek",
"Niksek",
56375,
56375,
"paa",
"paa-sep",
"Latn",
"Latn",
}
}
Line 214: Line 217:
"Gaikundi",
"Gaikundi",
5517032,
5517032,
"paa-spk",
"paa-nnd",
"Latn",
"Latn",
}
}
Line 235: Line 238:
"Galela",
"Galela",
3094570,
3094570,
"paa-nha",
"paa-gto",
"Latn",
"Latn",
}
}
Line 279: Line 282:
"Northern Grebo",
"Northern Grebo",
11157042,
11157042,
"kro-grb",
"grb",
"Latn",
"Latn",
ancestors = "grb",
}
}


Line 350: Line 352:
"Mali",
"Mali",
6743338,
6743338,
"paa-bng",
"paa-bai",
"Latn",
"Latn",
}
}
Line 388: Line 390:
"Gaina",
"Gaina",
11732195,
11732195,
"ngf",
"ngf-gko",
"Latn",
"Latn",
}
}
Line 451: Line 453:
5515189,
5515189,
"phi",
"phi",
"Latn",
}
}


Line 491: Line 494:
"Laal",
"Laal",
33436,
33436,
nil,
"qfa-dis", -- Chad; unclassified, isolate or grouped with Adamawa or Chadic languages
"Latn",
"Latn",
}
}
Line 498: Line 501:
"Umanakaina",
"Umanakaina",
7881084,
7881084,
"ngf",
"ngf-dag",
"Latn",
"Latn",
}
}
Line 508: Line 511:
"Cyrl",
"Cyrl",
display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
entry_name = {Cyrl = s["cau-Cyrl-entryname"]},
strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]},
}
}


Line 521: Line 524:
"Wipi",
"Wipi",
8026711,
8026711,
"paa",
"paa-etf",
"Latn",
"Latn",
}
}
Line 549: Line 552:
3540922,
3540922,
"raj",
"raj",
"Deva",
}
}


Line 561: Line 565:
"Kire",
"Kire",
11129733,
11129733,
"paa",
"paa-rub",
"Latn",
"Latn",
}
}
Line 568: Line 572:
"Gboloo Grebo",
"Gboloo Grebo",
11019342,
11019342,
"kro-grb",
"grb",
"Latn",
"Latn",
ancestors = "grb",
}
}


Line 733: Line 736:
"Ganglau",
"Ganglau",
5521140,
5521140,
"ngf-mad",
"ngf-yag",
"Latn",
"Latn",
}
m["ggn"] = {
"Eastern Gurung",
12952472,
"sit-tam",
"Gukh, Deva",
}
}


Line 761: Line 757:
"Gogodala",
"Gogodala",
3512161,
3512161,
"paa-pag",
"ngf-gsu",
"Latn",
"Latn",
}
}
Line 831: Line 827:
"Guhu-Samane",
"Guhu-Samane",
11732219,
11732219,
"ngf",
"ngf-gbi",
"Latn",
"Latn",
}
}
Line 840: Line 836:
"sit-tam",
"sit-tam",
"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 904: Line 897:


m["gim"] = {
m["gim"] = {
"Gimi (Goroka)",
"Gimi (Papuan)",
11732209,
11732209,
"paa",
"ngf-fgi",
"Latn",
"Latn",
}
}
Line 917: Line 910:
translit = "gin-translit",
translit = "gin-translit",
display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
entry_name = {Cyrl = s["cau-Cyrl-entryname"]},
strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]},
}
}


Line 930: Line 923:
12953525,
12953525,
"gio",
"gio",
"Latn",
}
}


Line 948: Line 942:
3107862,
3107862,
"nai-tsi",
"nai-tsi",
"Latn",
}
}


Line 997: Line 992:
6448731,
6448731,
"aus-pam",
"aus-pam",
"Latn",
}
}


Line 1,019: Line 1,015:
"raj",
"raj",
"ur-Arab, Deva, Takr",
"ur-Arab, Deva, Takr",
entry_name = {
strip_diacritics = {
["ur-Arab"] = {
["ur-Arab"] = {
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv,
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv,
Line 1,032: Line 1,028:
"Guya",
"Guya",
11732221,
11732221,
"ngf-fin",
"ngf-war",
"Latn",
"Latn",
}
}


m["gkd"] = {
m["gkd"] = {
"Magɨ",
"Magi",
55621742,
55621742,
"ngf-mad",
"ngf-ais",
"Latn",
"Latn",
}
}
Line 1,083: Line 1,079:
"Cyrl",
"Cyrl",
translit = "gld-translit",
translit = "gld-translit",
entry_name = {remove_diacritics = c.macron},
strip_diacritics = {remove_diacritics = c.macron},
sort_key = {
sort_key = {
from = {"ё", "ӈ"},
from = {"ё", "ӈ"},
Line 1,127: Line 1,123:
5617176,
5617176,
"csu-bgr",
"csu-bgr",
"Latn",
}
}


Line 1,146: Line 1,143:
10502327,
10502327,
"aus-wor",
"aus-wor",
"Latn",
}
}


Line 1,164: Line 1,162:
"Magiyi",
"Magiyi",
16926155,
16926155,
"ngf-mad",
"ngf-sog",
"Latn",
"Latn",
}
}
Line 1,173: Line 1,171:
"gmw-hgm",
"gmw-hgm",
"Latn",
"Latn",
entry_name = {
strip_diacritics = {
remove_diacritics = c.circ .. c.macron,
remove_diacritics = c.circ .. c.macron,
from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"},
from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"},
Line 1,185: Line 1,183:
"gmw-lgm",
"gmw-lgm",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.circ .. c.macron .. c.diaer},
strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer},
}
}


Line 1,199: Line 1,197:
11016905,
11016905,
"alv-dur",
"alv-dur",
"Latn",
}
m["gmr"] = {
"Mirning",
6873793,
"aus-pam",
"Latn",
}
}


Line 1,204: Line 1,210:
"Gumalu",
"Gumalu",
5618027,
5618027,
"ngf-mad",
"ngf-gum",
"Latn",
}
}


Line 1,297: Line 1,304:
1975199,
1975199,
"khi-kal",
"khi-kal",
"Latn",
}
}


Line 1,303: Line 1,311:
4916329,
4916329,
"aus-pam",
"aus-pam",
"Latn",
}
}


Line 1,308: Line 1,317:
"Ginuman",
"Ginuman",
11732210,
11732210,
"ngf",
"ngf-dag",
"Latn",
}
}


Line 1,322: Line 1,332:
5520523,
5520523,
"poz-san",
"poz-san",
"Latn",
}
}


Line 1,328: Line 1,339:
5619998,
5619998,
"aus-pam",
"aus-pam",
"Latn",
}
}


Line 1,333: Line 1,345:
"Guntai",
"Guntai",
12952475,
12952475,
"paa",
"paa-ton",
"Latn",
}
}


Line 1,339: Line 1,352:
"Gnau",
"Gnau",
3915810,
3915810,
"qfa-tor",
"paa-trr",
"Latn",
}
}


m["gnw"] = {
m["gnw"] = {
"Western Bolivian Guaraní",
"Western Bolivian Guarani",
3775037,
3775037,
"tup-gua",
"gn",
"Latn",
"Latn",
ancestors = "gn",
}
}


Line 1,408: Line 1,421:
"gmw-hgm",
"gmw-hgm",
"Latn, Runr",
"Latn, Runr",
entry_name = {
strip_diacritics = {
remove_diacritics = c.circ .. c.macron .. c.diaer,
remove_diacritics = c.circ .. c.macron .. c.diaer,
from = {"[ƷȤ]", "[ʒȥ]"},
from = {"[ƷȤ]", "[ʒȥ]"},
Line 1,421: Line 1,434:
"Gobasi",
"Gobasi",
5575414,
5575414,
"ngf",
"ngf-est",
"Latn",
"Latn",
}
}
Line 1,437: Line 1,450:
35482,
35482,
"alv",
"alv",
"Latn, Vaii",
}
}


Line 1,443: Line 1,457:
1775361,
1775361,
"dra-gon",
"dra-gon",
"Telu, Gonm, Gong",
"Telu, Gonm, Gong, Deva, Orya",
translit = {
translit = {
Telu = "te-translit",
Telu = "te-translit",
Line 1,469: Line 1,483:
3110816,
3110816,
"crp",
"crp",
"Latn",
ancestors = "ms",
ancestors = "ms",
}
}
Line 1,486: Line 1,501:
translit = {Goth = "Goth-translit"},
translit = {Goth = "Goth-translit"},
link_tr = true,
link_tr = true,
entry_name = {Latn = {remove_diacritics = c.macron}},
strip_diacritics = {Latn = {remove_diacritics = c.macron}},
}
}


Line 1,503: Line 1,518:


m["gow"] = {
m["gow"] = {
"Gorowa",
"Gorwaa",
3437626,
3437626,
"cus-sou",
"cus-sou",
"Latn",
}
}


Line 1,531: Line 1,547:
3915352,
3915352,
"alv-ngb",
"alv-ngb",
"Latn",
}
}


Line 1,536: Line 1,553:
"Taiap",
"Taiap",
56237,
56237,
"paa",
"qfa-dis", -- Papuan; isolate in Glottolog; relationship with Torricelli proposed by Usher
"Latn",
}
}


Line 1,556: Line 1,574:
53386731,
53386731,
"awd",
"awd",
"Latn",
}
}


Line 1,562: Line 1,581:
759992,
759992,
"csu-sar",
"csu-sar",
"Latn",
}
}


Line 1,576: Line 1,596:
"Deva, Gujr",
"Deva, Gujr",
ancestors = "bhb",
ancestors = "bhb",
}
m["grb"] = {
"Grebo",
35257,
"kro-grb",
"Latn",
}
}


Line 1,591: Line 1,604:
"Polyt, Cprt",
"Polyt, Cprt",
translit = {
translit = {
Polyt = "grc-translit",
Cprt = "Cprt-translit",
Cprt = "Cprt-translit",
},
},
override_translit = true,
override_translit = true,
display_text = {
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Polyt = s["Polyt-displaytext"],
standard_chars = {
},
Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΡ̓ΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾",
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
Polyt = s["Polyt-sortkey"],
},
standardChars = {
Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾",
Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿",
Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿",
c.punc
c.punc
Line 1,621: Line 1,625:
"Madi",
"Madi",
6727664,
6727664,
"ngf-fin",
"ngf-gmo",
"Latn",
"Latn",
}
}
Line 1,642: Line 1,646:
"Southern Grebo",
"Southern Grebo",
3914444,
3914444,
"kro-grb",
"grb",
"Latn",
"Latn",
ancestors = "grb",
}
}


Line 1,663: Line 1,666:
"Gorovu",
"Gorovu",
56355,
56355,
"paa",
"paa-por",
"Latn",
"Latn",
}
}
Line 1,685: Line 1,688:
13273,
13273,
"sem-eth",
"sem-eth",
"Latn",
"Latn, Ethi",
}
}


Line 1,691: Line 1,694:
"Central Grebo",
"Central Grebo",
18385114,
18385114,
"kro-grb",
"grb",
"Latn",
"Latn",
ancestors = "grb",
}
}


Line 1,706: Line 1,708:
"Guriaso",
"Guriaso",
12631954,
12631954,
"paa-kwm",
"qfa-unc", -- no consensus; may be Kwomtari per Baron (1983) and Usher (2020), but no connections accepted by
  -- Glottolog.
"Latn",
"Latn",
}
}
Line 1,713: Line 1,716:
"Barclayville Grebo",
"Barclayville Grebo",
11157342,
11157342,
"kro-grb",
"grb",
"Latn",
"Latn",
ancestors = "grb",
}
}


Line 1,756: Line 1,758:
"Gusan",
"Gusan",
11732224,
11732224,
"ngf-fin",
"ngf-era",
"Latn",
"Latn",
}
}
Line 1,770: Line 1,772:
"Wasembo",
"Wasembo",
7971402,
7971402,
"ngf-mad",
"ngf-mad", -- placed in under Rai Coast by Glottolog (under Greater Yaganon) and Pawley-Hammarström
"Latn",
"Latn",
}
}
Line 1,792: Line 1,794:
"Guató",
"Guató",
3027940,
3027940,
"qfa-iso",
"qfa-dis", -- isolate or Macro-Jê
"Latn",
"Latn",
}
}
Line 1,846: Line 1,848:


m["gug"] = {
m["gug"] = {
"Paraguayan Guaraní",
"Paraguayan Guarani",
17478066,
17478066,
"tup-gua",
"gn",
"Latn",
"Latn",
ancestors = "gn",
wikimedia_codes = "gn",
ancestors = "gn-cls",
}
}


Line 1,861: Line 1,864:


m["gui"] = {
m["gui"] = {
"Eastern Bolivian Guaraní",
"Eastern Bolivian Guarani",
2963912,
2963912,
"tup-gua",
"gn",
"Latn",
"Latn",
ancestors = "gn",
}
}


Line 1,891: Line 1,893:


m["gun"] = {
m["gun"] = {
"Mbyá Guaraní",
"Mbya Guarani",
3915584,
3915584,
"tup-gua",
"gn",
"Latn",
"Latn",
ancestors = "gn",
}
}


Line 1,959: Line 1,960:
"alv-gbe",
"alv-gbe",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.macron},
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron},
}
}


Line 2,000: Line 2,001:
"Golin",
"Golin",
3110291,
3110291,
"ngf",
"ngf-sim",
"Latn",
"Latn",
}
}
Line 2,047: Line 2,048:


m["gvr"] = {
m["gvr"] = {
"Western Gurung",
"Gurung",
2392342,
2392342,
"sit-tam",
"sit-tam",
Line 2,086: Line 2,087:
"inc-koh",
"inc-koh",
"Arab",
"Arab",
strip_diacritics = {
["Arab"] = {
-- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
from = {"هٔ", "ۂ", "ٱ"},
to = {"ہ", "ہ", "ا"},
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef .. u(0x065e)
},
},
}
}


Line 2,092: Line 2,101:
3032135,
3032135,
"cus-eas",
"cus-eas",
"Latn, Ethi",
}
}


Line 2,105: Line 2,115:
3812403,
3812403,
"inc-koh",
"inc-koh",
"Arab",
}
}


Line 2,153: Line 2,164:
33894,
33894,
"inc-kun",
"inc-kun",
"Arab",
}
}


Line 2,193: Line 2,205:
"Garus",
"Garus",
5524492,
5524492,
"ngf-mad",
"ngf-han",
"Latn",
"Latn",
}
}

Latest revision as of 11:59, 21 April 2026


This module contains definitions and metadata for three-letter language codes starting with g. See Wiktionary:Languages for more information.

This module must not be used directly in other modules or templates. The data should be accessed through Module:languages. For the corresponding extra data, see Module:languages/data/3/g/extra.

Required values

Every entry in the table must contain the following indexed fields:

1
The "canonical" name of the language. This is the name that is used in Wiktionary entries and category names.
2
The Wikidata item ID (Q number) for the language. Must be specified as a number (a positive integer). Set to nil if not known/present. This replaces the older wikipedia_article property, which can still be used to link to specific sections or language editions.

Optional values

3
The code for the family that the language belongs to. See Wiktionary:Families.
4
A list of script codes. See Wiktionary:Scripts. These represent all the scripts (writing systems) that this language uses in the real world, as well as the ones that Wiktionary uses. The scripts that are used most often on Wiktionary should be first in the list, as this will speed up script detection.
Many templates and modules detect the script of text in a particular language using the Language:findBestScript method in Module:languages. This function goes down the list of scripts and counts how many characters in the text belong to each script. If all the characters belong to one script, that script will be returned; otherwise, the script with the most characters will be returned. Thus, script detection will be faster if the most frequently used scripts are first in the list. If none of the characters match any of the listed scripts, then the None script is returned (even if the characters would match a script not listed). Translingual (mul) and Undetermined (und) have the special value "All", which means they are treated as having every script. This value should not be set for any other language codes.
Due to the ongoing problems with Lua memory limits, this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: "Latn, Brai, Shaw, Dsrt".
type
The type of language (which affects how it is handled on Wiktionary). Possible values are:
  • regular - This value is the default, so it doesn't need to be specified. It indicates that the is attested according to WT:CFI and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the Reconstruction namespace and must be prefixed with * to indicate a reconstruction.
  • reconstructed - This language is not attested according to CFI, and therefore is allowed only in the Reconstruction namespace. All terms in this language are reconstructed, and must be prefixed with *.
  • appendix-constructed - This language is attested but does not meet the additional requirements set out for constructed languages (WT:CFI#Constructed languages). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links.
ancestors
A list of the language codes of the direct ancestors of this language. For example, the ancestor of English is listed as enm (Middle English); ang (Old English, the ancestor of Middle English), gem-pro (Proto-Germanic, the ancestor of Old English), and ine-pro (Proto-Indo-European, the ancestor of Proto-Germanic) are not listed.
For most languages, only one ancestor code should be given, but multiple ancestors can be listed for pidgins, creoles and mixed languages.
The ancestor language list should not be included if the language's direct ancestor is the proto-language of the family to which the language belongs. In such a case, if the family code has been provided, Module:languages will automatically add the proto-language as the language's ancestor. For example, Proto-Germanic (gem-pro) belongs to the Indo-European (ine) family, and its direct ancestor is Proto-Indo-European (ine-pro). Because Proto-Indo-European is the proto-language of the Indo-European languages, Proto-Germanic does not need an ancestors table; Proto-Indo-European will be automatically returned as its ancestor by the getAncestors function.
Due to the ongoing problems with Lua memory limits, this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: "cr, fr".
wikimedia_codes
A list of the Wikimedia language codes that this language maps to. This is used to translate Wiktionary codes to Wikimedia codes, which are usually the same but there are a few languages where it is different. The language codes must be valid Wikimedia codes (as determined by the wiki software), and if they are not defined in one of the language data modules, they must be defined in Module:wikimedia languages/data.
Due to the ongoing problems with Lua memory limits, this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: "en, simple".
Note that Wikimedia <-> Wiktionary language codes are currently defined in four places: the language modules (as documented here); Module:wikimedia languages/data; interwiki_langs in Module:translations/data; and the wiktprefix field of the `metadata` variable in MediaWiki:Gadget-TranslationAdder-Data.js. FIXME: Unify this data.
wikipedia_article
The name of the Wikipedia article for the language. Should normally only be supplied if the Wikidata id cannot be used.
translit
See the Substitutions section for instructions on syntax.
Defines how a language should be transliterated, which will be automatically applied to any terms in scripts that do not have their isTransliterated value set to false in Module:scripts/data. This is used by transliterate in Module:languages.
link_tr
Set this to true to link the language's transliteration in headwords. This can also be a comma-separated list of script codes, which means that links are only applied to terms using those scripts. Note that transliterations are not linked in links other than headwords (those generated using full_link() in Module:links) unless the respect_link_tr flag is set in full_link()'s data structure.
override_translit
Set this to true to make the automatic transliteration override an any given manual transliteration. Otherwise, this can be a comma-separated list of script codes, which means that the override is only applied to terms using those scripts.
display_text
See the Substitutions section for instructions on syntax.
Defines replacements to create the display form of the text, which is the form actually displayed on the page. This is occasionally necessary if there is a recurring issue of editors adding the wrong character, which is sometimes an issue when two or more characters are easy to confuse. For example, the palochka ӏ, used in Cyrillic in many Caucasian languages, is frequently entered as I, or even Latin l or I. As this is an ongoing issue (even among native speakers), the easiest way to solve the problem is to automatically correct the display form for those languages. This is used by makeDisplayText in Module:languages.
strip_diacritics
See the Substitutions section for instructions on syntax.
Defines replacements to strip diacritics from the displayed form of a term in order to get the logical pagename. This is typically used to remove certain diacritical marks according to the customs or standard practice of the language. For example, it is used to remove accent marks from Russian words (ру́сскийрусский), and macrons from Latin and Old English words (ōsos), as these are not used in the normal written form of these languages. This is used by stripDiacritics in Module:languages.
sort_key
See the Substitutions section for instructions on syntax.
Defines replacements to create a category sort key from the page name. The purpose is to:
  1. Remove any characters that should be ignored in sorting.
  2. Replace characters with other characters, if the sorting rules for that language do not distinguish them. For example, in German, the characters "ä" and "a" are considered equivalent for sorting, and are both treated as "a".
  3. Replace characters that should be sorted in different places with special characters that mimic that behaviour, (which is necessary due to MediaWiki software using the Unicode codepoint to determine sort order, which is often arbitrary). For instance, in Mongolian, the letter "ү" should be sorted after "у", but due to its codepoint it is sorted after the final letter "я" by default. As such, we can replace "ү" with "у" plus a character with a very high codepoint, which ensures that it is always sorted straight after. The data modules contain an in-built way to do this for the sake of convenience: with the above example, this would be done by using "у" .. p[1]. Another character could be inserted straight after by using "у" .. p[2] (and so on).
Note: the term is converted to lowercase before applying any substitutions, so you should not try to process capital letters (as it will not work). This is used by makeSortKey in Module:languages.
dotted_dotless_i
Set this to true for languages that distinguish between the dotted and dotless I (such as some Turkic languages).

Substitutions

translit, display_text, strip_diacritics and sort_key all use the same syntax, which is designed to be as flexible as possible:
  • If they are a string, then this is treated as the name of a dedicated module which will be used to generate the output. For example, "sa-translit" refers to Module:sa-translit.
  • If they are a table, then it can contain two kinds of keys:
    1. The keys from, to, remove_diacritics and remove_exceptions relate to text substitution (see below).
    2. Script code keys are used to specify script-specific behaviour. These, in turn, can be strings (for dedicated modules) or tables (for text substitution). In addition, a value with the key 1 can be used as a fallback, which will be used if no specific behaviour is defined for that script.
Note: if script keys and text substitution keys are given in the same table, then the text substitution will be applied after the script-specific behaviour has completed. Ensure any fallback text substitutions are given as a subtable with key 1 if you want to avoid this. It is not possible to process the output of a script-specific module with another module, however: this should be done (for example) with a tail call in the first module.
Dedicated modules must take the arguments text, lang, sc, where text is the input text (usually the page name or input by the user), lang is the language code (not the language object), and sc is the script code (not the script object). For performance reasons, they should only be used when it is not possible to achieve the desired result via text substitution.
Text substitution replaces or removes certain characters (or sets of characters) for particular contexts. There are three ways to do this:
  1. Using the from and to keys.
  2. remove_diacritics (and optionally remove_exceptions).
  3. Both of the above (in that order).
from is paired with to, and both of them must be tables that are organised pairwise: each element in from is a pattern to identify which characters in the term to replace, while the corresponding element in to defines what to replace them with (as arguments to mw.ustring.gsub).
If the replacement is not present (or if it is false or nil), then any matching characters are removed altogether. This means that the from list can be longer than the to list, and an empty replacement will be assumed for any elements in from that have no counterpart in to.
The tables can contain literal characters, or the patterns (a simplified form regular expressions) that are used by the standard Scribunto mw.ustring.gsub function. See the Scribunto reference manual for more information. Note that patterns make double substitutions a viable way to achieve more complex results. See the Latin sortkey for Mandarin (cmn) as an example of this.
remove_diacritics is a string which contains characters that will be removed after the text is decomposed. For instance, if remove_diacritics is a combining acute accent, all acute accents will be stripped, even if they are part of precomposed characters (such as á or ά). Despite the name, the characters to be stripped need not be diacritics: for instance, including an apostrophe would remove all apostrophes (though be careful with hyphens, which must be be escaped as %-).
Furthermore, if remove_diacritics is given, then it is possible to specify a remove_exceptions table, which prevents specific characters from having their diacritics stripped. For instance, if remove_diacritics is a combining diaeresis, but remove_exceptions contains "ё", then any instances of ё will remain unchanged. On the other hand, an instance of ӱ would still become у (unless "ӱ" is also added to remove_exceptions).
If no value is specified for a given field, or a table of script-specific values is given but there is no value for the script in question and no from/to or remove_diacritics fields, the script will be checked for a script-wide fallback, which uses the same data format. This is used, for example, to supply a script-wide sort key module for Ethiopic in lieu of specifying the same value for all languages that have Ethiopic as their script (or one of their scripts).

Formerly supported values

aliases, varieties, otherNames
This data is now located in the extra data modules; see Module:languages and Template:language extradata documentation.
family
Now 3.
scripts
Now 4.

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["gaa"] = {
	"Ga",
	33287,
	"alv-gda",
	"Latn",
}

m["gab"] = {
	"Gabri",
	3441237,
	"cdc-est",
	"Latn",
}

m["gac"] = {
	"Mixed Great Andamanese",
	56329630,
	"qfa-adn",
	"Latn",
}

m["gad"] = { -- not to be confused with gdk, gdg
	"Gaddang",
	3438830,
	"phi",
	"Latn",
}

m["gae"] = {
	"Warekena",
	1091095,
	"awd-nwk",
	"Latn",
}

m["gaf"] = {
	"Gende",
	3100425,
	"ngf-gor",
	"Latn",
}

m["gag"] = {
	"Gagauz",
	33457,
	"trk-ogz",
	"Latn, Cyrl",
	ancestors = "trk-oat",
	dotted_dotless_i = true,
	sort_key = {
		Latn = {
			from = {
				"i", -- Ensure "i" comes after "ı".
				"ä", "ç", "ê", "ı", "ö", "ş", "ţ", "ü"
			},
			to = {
				"i" .. p[1],
				"a" .. p[1], "c" .. p[1], "e" .. p[1], "i", "o" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1]
			}
		},
	},
}

m["gah"] = {
	"Alekano",
	3441595,
	"ngf-gah",
	"Latn",
}

m["gai"] = {
	"Borei",
	6799756,
	"paa-ott",
	"Latn",
}

m["gaj"] = {
	"Gadsup",
	5516467,
	"ngf-gau",
	"Latn",
}

m["gak"] = {
	"Gamkonora",
	5520226,
	"paa-sah",
	"Latn",
}

m["gal"] = {
	"Galoli",
	35322,
	"poz-tim",
	"Latn",
}

m["gam"] = {
	"Kandawo",
	6361369,
	"ngf-jim",
	"Latn",
}

m["gan"] = {
	"Gan",
	33475,
	"zhx",
	"Hants",
	ancestors = "ltc",
	generate_forms = "zh-generateforms",
	translit = "zh-translit",
	sort_key = "Hani-sortkey",
}

m["gao"] = {
	"Gants",
	5521529,
	"ngf-eso",
	"Latn",
}

m["gap"] = {
	"Gal",
	5517742,
	"ngf-han",
	"Latn",
}

m["gaq"] = {
	"Gata'",
	3501920,
	"mun",
	"Orya",
}

m["gar"] = {
	"Galeya",
	5518509,
	"poz-ocw",
	"Latn",
}

m["gas"] = {
	"Adiwasi Garasia",
	12953522,
	"inc-bhi",
	"Deva, Gujr",
	ancestors = "bhb",
}

m["gat"] = {
	"Kenati",
	4219330,
	"ngf-kgo",
	"Latn",
}

m["gau"] = {
	"Kondekor",
	12952433,
	"dra-pgd",
	"Telu",
}

m["gaw"] = {
	"Nobonob",
	11732205,
	"ngf-han",
	"Latn",
}

m["gay"] = {
	"Gayo",
	33286,
	"poz-nws",
	"Latn",
}

m["gbb"] = {
	"Kaytetye",
	6380709,
	"aus-rnd",
	"Latn",
}

m["gbd"] = {
	"Karadjeri",
	3913837,
	"aus-pam",
	"Latn",
}

m["gbe"] = {
	"Niksek",
	56375,
	"paa-sep",
	"Latn",
}

m["gbf"] = {
	"Gaikundi",
	5517032,
	"paa-nnd",
	"Latn",
}

m["gbg"] = {
	"Gbanziri",
	35306,
	"nic-nkg",
	"Latn",
}

m["gbh"] = {
	"Defi Gbe",
	12952446,
	"alv-gbe",
	"Latn",
}

m["gbi"] = {
	"Galela",
	3094570,
	"paa-gto",
	"Latn",
}

m["gbj"] = {
	"Bodo Gadaba",
	3347070,
	"mun",
	"Orya",
}

m["gbk"] = {
	"Gaddi",
	17455500,
	"him",
	"Deva, Takr",
	translit = {Deva = "hi-translit"},
}

m["gbl"] = {
	"Gamit",
	2731717,
	"inc-bhi",
	"Deva, Gujr",
}

m["gbm"] = {
	"Garhwali",
	33459,
	"inc-pah",
	"Deva",
	translit = "hi-translit",
}

m["gbn"] = {
	"Mo'da",
	12755683,
	"csu-bbk",
	"Latn",
}

m["gbo"] = {
	"Northern Grebo",
	11157042,
	"grb",
	"Latn",
}

m["gbp"] = {
	"Gbaya-Bossangoa",
	11011295,
	"gba-wes",
	"Latn",
}

m["gbq"] = {
	"Gbaya-Bozoum",
	4952879,
	"gba-wes",
	"Latn",
}

m["gbr"] = {
	"Gbagyi",
	11015105,
	"alv-ngb",
	"Latn",
}

m["gbs"] = {
	"Gbesi Gbe",
	12952448,
	"alv-pph",
	"Latn",
}

m["gbu"] = {
	"Gagadu",
	35677,
	"aus-arn",
	"Latn",
}

m["gbv"] = {
	"Gbanu",
	3914945,
	"gba-eas",
	"Latn",
}

m["gbw"] = {
	"Gabi",
	5515391,
	"aus-pam",
	"Latn",
}

m["gbx"] = {
	"Eastern Xwla Gbe",
	18379975,
	"alv-pph",
	"Latn",
}

m["gby"] = {
	"Gbari",
	3915451,
	"alv-ngb",
	"Latn",
}

m["gcc"] = {
	"Mali",
	6743338,
	"paa-bai",
	"Latn",
}

m["gcd"] = {
	"Ganggalida",
	3913765,
	"aus-tnk",
	"Latn",
}

m["gce"] = {
	"Galice",
	20711,
	"ath-pco",
	"Latn",
}

m["gcf"] = {
	"Antillean Creole",
	3006280,
	"crp",
	"Latn",
	ancestors = "fr",
	sort_key = s["roa-oil-sortkey"],
}

m["gcl"] = {
	"Grenadian Creole English",
	4252500,
	"crp",
	"Latn",
	ancestors = "en",
}

m["gcn"] = {
	"Gaina",
	11732195,
	"ngf-gko",
	"Latn",
}

m["gcr"] = {
	"Guianese Creole",
	1363072,
	"crp",
	"Latn",
	ancestors = "fr",
	sort_key = s["roa-oil-sortkey"],
}

m["gct"] = {
	"Colonia Tovar German",
	1138351,
	"gmw-hgm",
	"Latn",
	ancestors = "gsw",
}

m["gdb"] = {
	"Ollari",
	33906,
	"dra-pgd",
	"Orya, Telu",
	translit = {
		Telu = "te-translit"
	},
}

m["gdc"] = {
	"Gugu Badhun",
	10510360,
	"aus-pam",
	"Latn",
}

m["gdd"] = {
	"Gedaged",
	35292,
	"poz-ocw",
	"Latn",
}

m["gde"] = {
	"Gude",
	3441230,
	"cdc-cbm",
	"Latn",
}

m["gdf"] = {
	"Guduf-Gava",
	3441350,
	"cdc-cbm",
	"Latn",
}

m["gdg"] = { -- not to be confused with gad, gdk
	"Ga'dang",
	5515189,
	"phi",
	"Latn",
}

m["gdh"] = {
	"Gadjerawang",
	3913817,
	"aus-jar",
	"Latn",
}

m["gdi"] = {
	"Gundi",
	11137851,
	"nic-nkb",
	"Latn",
}

m["gdj"] = {
	"Kurtjar",
	5619931,
	"aus-pmn",
	"Latn",
}

m["gdk"] = { -- not to be confused with gad, gdg
	"Gadang",
	56256,
	"cdc-est",
	"Latn",
}

m["gdl"] = {
	"Dirasha",
	56809,
	"cus-eas",
	"Ethi",
}

m["gdm"] = {
	"Laal",
	33436,
	"qfa-dis", -- Chad; unclassified, isolate or grouped with Adamawa or Chadic languages
	"Latn",
}

m["gdn"] = {
	"Umanakaina",
	7881084,
	"ngf-dag",
	"Latn",
}

m["gdo"] = {
	"Godoberi",
	56515,
	"cau-and",
	"Cyrl",
	display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
	strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]},
}

m["gdq"] = {
	"Mehri",
	13361,
	"sem-sar",
	"Arab, Latn",
}

m["gdr"] = {
	"Wipi",
	8026711,
	"paa-etf",
	"Latn",
}

m["gds"] = {
	"Ghandruk Sign Language",
	15971577,
	"sgn",
}

m["gdt"] = {
	"Kungardutyi",
	6444517,
	"aus-kar",
	"Latn",
}

m["gdu"] = {
	"Gudu",
	3441172,
	"cdc-cbm",
	"Latn",
}

m["gdx"] = {
	"Godwari",
	3540922,
	"raj",
	"Deva",
}

m["gea"] = {
	"Geruma",
	3438789,
	"cdc-wst",
	"Latn",
}

m["geb"] = {
	"Kire",
	11129733,
	"paa-rub",
	"Latn",
}

m["gec"] = {
	"Gboloo Grebo",
	11019342,
	"grb",
	"Latn",
}

m["ged"] = {
	"Gade",
	3914459,
	"alv-nup",
	"Latn",
}

m["geg"] = {
	"Gengle",
	3438345,
	"alv-mye",
	"Latn",
	ancestors = "kow",
}

m["geh"] = {
	"Hutterisch",
	33385,
	"gmw-hgm",
	"Latn",
	ancestors = "bar",
}

m["gei"] = {
	"Gebe",
	3100032,
	"poz-hce",
	"Latn",
}

m["gej"] = {
	"Gen",
	33450,
	"alv-gbe",
	"Latn",
}

m["gek"] = {
	"Gerka",
	3441277,
	"cdc-wst",
	"Latn",
}

m["gel"] = {
	"Fakkanci",
	36627,
	"nic-knn",
	"Latn",
}

m["geq"] = {
	"Geme",
	3915851,
	"znd",
	"Latn",
}

m["ges"] = {
	"Geser-Gorom",
	5553579,
	"poz-cma",
	"Latn",
}

m["gev"] = {
	"Viya",
	7937974,
	"bnt-tso",
	"Latn",
}

m["gew"] = {
	"Gera",
	3438725,
	"cdc-wst",
	"Latn",
}

m["gex"] = {
	"Garre",
	56618,
	"cus-som",
	"Latn",
}

m["gey"] = {
	"Enya",
	5381452,
	"bnt-mbe",
	"Latn",
}

m["gez"] = {
	"Ge'ez",
	35667,
	"sem-eth",
	"Ethi",
	translit = "Ethi-translit",
}

m["gfk"] = {
	"Patpatar",
	3368846,
	"poz-ocw",
	"Latn",
}

m["gft"] = {
	"Gafat",
	56910,
	"sem-eth",
	"Ethi, Latn",
}

m["gga"] = {
	"Gao",
	3095228,
	"poz-ocw",
	"Latn",
}

m["ggb"] = {
	"Gbii",
	3914390,
	"kro-wkr",
	"Latn",
}

m["ggd"] = {
	"Gugadj",
	5615186,
	"aus-pmn",
	"Latn",
}

m["gge"] = {
	"Guragone",
	5619801,
	"aus-arn",
	"Latn",
}

m["ggg"] = {
	"Gurgula",
	5620032,
	"raj",
	"Arab",
}

m["ggk"] = {
	"Kungarakany",
	6444516,
	"aus-arn",
	"Latn",
}

m["ggl"] = {
	"Ganglau",
	5521140,
	"ngf-yag",
	"Latn",
}

m["ggt"] = {
	"Gitua",
	3107865,
	"poz-ocw",
	"Latn",
}

m["ggu"] = {
	"Gban",
	3913317,
	"dmn-nbe",
	"Latn",
}

m["ggw"] = {
	"Gogodala",
	3512161,
	"ngf-gsu",
	"Latn",
}

m["gha"] = {
	"Ghadames",
	56747,
	"ber",
	"Latn", -- and other scripts?
}

m["ghc"] = {
	"Classical Gaelic",
	5128278,
	"cel-gae",
	"Latn, Latg",
	ancestors = "mga",
}

m["ghe"] = {
	"Southern Ghale",
	12952453,
	"sit-tam",
	"Deva",
}

m["ghh"] = {
	"Northern Ghale",
	22662104,
	"sit-tam",
	"Deva",
}

m["ghk"] = {
	"Geko Karen",
	5530317,
	"kar",
}

m["ghl"] = {
	"Ghulfan",
	16885737,
	"nub-hil",
	"Latn", -- and others?
}

m["ghn"] = {
	"Ghanongga",
	3104772,
	"poz-ocw",
	"Latn",
}

m["gho"] = {
	"Ghomara",
	35315,
	"ber",
	"Tfng, Latn",
	translit = {Tfng = "Tfng-translit"},
}

m["ghr"] = {
	"Ghera",
	22808992,
	"inc-hiw",
}

m["ghs"] = {
	"Guhu-Samane",
	11732219,
	"ngf-gbi",
	"Latn",
}

m["ght"] = {
	"Kutang Ghale",
	6448337,
	"sit-tam",
	"Tibt",
	override_translit = true,
	-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}

m["gia"] = {
	"Kitja",
	1284877,
	"aus-jar",
	"Latn",
}

m["gib"] = {
	"Gibanawa",
	12953530,
	"crp",
	"Latn",
	ancestors = "ha",
}

m["gid"] = {
	"Gidar",
	35265,
	"cdc-cbm",
	"Latn",
}

m["gie"] = {
	"Guébie",
	63140714,
	"kro-did",
	"Latn",
}

m["gig"] = {
	"Goaria",
	33269,
	"raj",
	"Arab",
}

m["gih"] = {
	"Githabul",
	48987680,
	"aus-pam",
	"Latn",
}

m["gii"] = {
	"Girirra",
	5564288,
	"cus-som",
}

m["gil"] = {
	"Gilbertese",
	30898,
	"poz-mic",
	"Latn",
}

m["gim"] = {
	"Gimi (Papuan)",
	11732209,
	"ngf-fgi",
	"Latn",
}

m["gin"] = {
	"Hinukh",
	33283,
	"cau-wts",
	"Cyrl",
	translit = "gin-translit",
	display_text = {Cyrl = s["cau-Cyrl-displaytext"]},
	strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]},
}

m["gip"] = {
	"Gimi (Austronesian)",
	12952457,
	"poz-ocw",
}

m["giq"] = {
	"Green Gelao",
	12953525,
	"gio",
	"Latn",
}

m["gir"] = {
	"Red Gelao",
	3100264,
	"gio",
}

m["gis"] = {
	"North Giziga",
	3515084,
	"cdc-cbm",
}

m["git"] = {
	"Gitxsan",
	3107862,
	"nai-tsi",
	"Latn",
}

m["giu"] = {
	"Mulao",
	11092831,
	"gio",
}

m["giw"] = {
	"White Gelao",
	8843040,
	"gio",
}

m["gix"] = {
	"Gilima",
	10977716,
	"nic-nkm",
	"Latn",
}

m["giy"] = {
	"Giyug",
	5565906,
}

m["giz"] = {
	"South Giziga",
	3502232,
	"cdc-cbm",
}

m["gji"] = {
	"Geji",
	3914890,
	"cdc-wst",
	"Latn",
}

m["gjk"] = {
	"Kachi Koli",
	12953646,
	"inc-wes",
}

m["gjm"] = {
	"Gunditjmara",
	6448731,
	"aus-pam",
	"Latn",
}

m["gjn"] = {
	"Gonja",
	35267,
	"alv-gng",
	"Latn",
}

m["gjr"] = {
	"Gurindji Kriol",
	5620091,
	"qfa-mix",
	"Latn",
	ancestors = "gue, rop"
}

m["gju"] = {
	"Gojri",
	3241731,
	"raj",
	"ur-Arab, Deva, Takr",
	strip_diacritics = {
		["ur-Arab"] = {
			remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv,
			from = {"ڵ", "ݩ"},
			to = {"ل", "ن"}
		},
	},
	translit = {["ur-Arab"] = "ur-translit"},
}

m["gka"] = {
	"Guya",
	11732221,
	"ngf-war",
	"Latn",
}

m["gkd"] = {
	"Magi",
	55621742,
	"ngf-ais",
	"Latn",
}

m["gke"] = {
	"Ndai",
	6983667,
	"alv-mbm",
}

m["gkn"] = {
	"Gokana",
	3075137,
	"nic-ogo",
	"Latn",
}

m["gko"] = {
	"Kok-Nar",
	6426526,
	"aus-pmn",
	"Latn",
}

m["gkp"] = {
	"Guinea Kpelle",
	11052867,
	"dmn-msw",
	"Latn, Kpel",
	ancestors = "kpe",
}

m["glc"] = {
	"Bon Gula",
	289816,
	"alv-bua",
}

m["gld"] = {
	"Nanai",
	13303,
	"tuw-nan",
	"Cyrl",
	translit = "gld-translit",
	strip_diacritics = {remove_diacritics = c.macron},
	sort_key = {
		from = {"ё", "ӈ"},
		to = {"е" .. p[1], "н" .. p[1]}
	},
}

m["glh"] = {
	"Northwest Pashayi",
	23713532,
	"inc-pas",
	"fa-Arab",
}

m["glj"] = {
	"Kulaal",
	33360,
	"alv-bua",
}

m["glk"] = {
	"Gilaki",
	33657,
	"ira-csp",
	"fa-Arab",
}

m["glo"] = {
	"Galambu",
	2598797,
	"cdc-wst",
	"Latn",
}

m["glr"] = {
	"Glaro-Twabo",
	3915313,
	"kro-wee",
}

m["glu"] = {
	"Gula",
	5617176,
	"csu-bgr",
	"Latn",
}

m["glw"] = {
	"Glavda",
	3441285,
	"cdc-cbm",
	"Latn",
}

m["gly"] = {
	"Gule",
	3120736,
	"ssa-kom",
}

m["gma"] = {
	"Gambera",
	10502327,
	"aus-wor",
	"Latn",
}

m["gmb"] = {
	"Gula'alaa",
	3120733,
	"poz-sls",
	"Latn",
}

m["gmd"] = {
	"Mághdì",
	3914475,
	"alv-bwj",
}

m["gmg"] = {
	"Magiyi",
	16926155,
	"ngf-sog",
	"Latn",
}

m["gmh"] = {
	"Middle High German",
	837985,
	"gmw-hgm",
	"Latn",
	strip_diacritics = {
		remove_diacritics = c.circ .. c.macron,
		from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"},
		to = {"E", "e", "Z", "z"}
	},
}

m["gml"] = {
	"Middle Low German",
	505674,
	"gmw-lgm",
	"Latn",
	strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer},
}

m["gmm"] = {
	"Gbaya-Mbodomo",
	6799713,
	"gba-eas",
	"Latn",
}

m["gmn"] = {
	"Gimnime",
	11016905,
	"alv-dur",
	"Latn",
}

m["gmr"] = {
	"Mirning",
	6873793,
	"aus-pam",
	"Latn",
}

m["gmu"] = {
	"Gumalu",
	5618027,
	"ngf-gum",
	"Latn",
}

m["gmv"] = {
	"Gamo",
	16116386,
	"omv-nom",
	"Latn, Ethi",
}

m["gmx"] = {
	"Magoma",
	16939552,
	"bnt-bki",
}

m["gmy"] = {
	"Mycenaean Greek",
	668366,
	"grk",
	"Linb",
	translit = "Linb-translit",
}

m["gmz"] = {
	"Mgbo",
	6826835,
	"alv-igb",
	ancestors = "izi",
}

m["gna"] = {
	"Kaansa",
	56802,
	"nic-gur",
}

m["gnb"] = {
	"Gangte",
	12952442,
	"tbq-kuk",
}

m["gnc"] = {
	"Guanche",
	35762,
	"ber",
}

m["gnd"] = {
	"Zulgo-Gemzek",
	56800,
	"cdc-cbm",
	"Latn",
}

m["gne"] = {
	"Ganang",
	63163361,
	"nic-plc",
	ancestors = "izr",
}

m["gng"] = {
	"Ngangam",
	35888,
	"nic-grm",
}

m["gnh"] = {
	"Lere",
	3915319,
	"nic-jer",
}

m["gni"] = {
	"Gooniyandi",
	2669219,
	"aus-bub",
	"Latn",
}

m["gnj"] = {
	"Ngen of Djonkro",
	63170838,
	"dmn-nbe",
	"Latn",
}

m["gnk"] = {
	"ǁGana",
	1975199,
	"khi-kal",
	"Latn",
}

m["gnl"] = {
	"Gangulu",
	4916329,
	"aus-pam",
	"Latn",
}

m["gnm"] = {
	"Ginuman",
	11732210,
	"ngf-dag",
	"Latn",
}

m["gnn"] = {
	"Gumatj",
	10510745,
	"aus-yol",
	"Latn",
}

m["gnq"] = {
	"Gana",
	5520523,
	"poz-san",
	"Latn",
}

m["gnr"] = {
	"Gureng Gureng",
	5619998,
	"aus-pam",
	"Latn",
}

m["gnt"] = {
	"Guntai",
	12952475,
	"paa-ton",
	"Latn",
}

m["gnu"] = {
	"Gnau",
	3915810,
	"paa-trr",
	"Latn",
}

m["gnw"] = {
	"Western Bolivian Guarani",
	3775037,
	"gn",
	"Latn",
}

m["gnz"] = {
	"Ganzi",
	11137942,
	"nic-nkb",
	"Latn",
}

m["goa"] = {
	"Guro",
	35251,
	"dmn-mda",
	"Latn",
}

m["gob"] = {
	"Playero",
	3027923,
	"sai-guh",
}

m["goc"] = {
	"Gorakor",
	12952463,
	"poz-ocw",
	"Latn",
}

m["god"] = {
	"Godié",
	3914412,
	"kro-bet",
}

m["goe"] = {
	"Gongduk",
	2669221,
	"sit",
}

m["gof"] = {
	"Gofa",
	12631584,
	"omv-nom",
	"Latn, Ethi",
}

m["gog"] = {
	"Gogo",
	3272630,
	"bnt-ruv",
	"Latn",
}

m["goh"] = {
	"Old High German",
	35218,
	"gmw-hgm",
	"Latn, Runr",
	strip_diacritics = {
		remove_diacritics = c.circ .. c.macron .. c.diaer,
		from = {"[ƷȤ]", "[ʒȥ]"},
		to = {"Z", "z"}
	},
	translit = {
		Runr = "Runr-translit",
	},
}

m["goi"] = {
	"Gobasi",
	5575414,
	"ngf-est",
	"Latn",
}

m["goj"] = {
	"Gowlan",
	12953532,
	"inc-sou",
}

-- gok is a spurious language, see [[w:Spurious languages]]

m["gol"] = {
	"Gola",
	35482,
	"alv",
	"Latn, Vaii",
}

m["gon"] = {
	"Gondi",
	1775361,
	"dra-gon",
	"Telu, Gonm, Gong, Deva, Orya",
	translit = {
		Telu = "te-translit",
		Gong = "gon-Gong-translit",
		Gonm = "gon-Gonm-translit",
	},
}

m["goo"] = {
	"Gone Dau",
	3110470,
	"poz-pcc",
	"Latn",
}

m["gop"] = {
	"Yeretuar",
	8052565,
	"poz-hce",
	"Latn",
}

m["goq"] = {
	"Gorap",
	3110816,
	"crp",
	"Latn",
	ancestors = "ms",
}

m["gor"] = {
	"Gorontalo",
	2501174,
	"phi",
	"Latn",
}

m["got"] = {
	"Gothic",
	35722,
	"gme",
	"Goth, Runr, Latn",
	translit = {Goth = "Goth-translit"},
	link_tr = true,
	strip_diacritics = {Latn = {remove_diacritics = c.macron}},
}

m["gou"] = {
	"Gavar",
	3441180,
	"cdc-cbm",
}

m["gov"] = {
	"Goo",
	16927208,
	"dmn",
	"Latn",
}

m["gow"] = {
	"Gorwaa",
	3437626,
	"cus-sou",
	"Latn",
}

m["gox"] = {
	"Gobu",
	7194986,
	"bad-cnt",
}

m["goy"] = {
	"Goundo",
	317636,
	"alv-kim",
}

m["goz"] = {
	"Gozarkhani",
	5590235,
	"xme-ttc",
	ancestors = "xme-ttc-eas",
}

m["gpa"] = {
	"Gupa-Abawa",
	3915352,
	"alv-ngb",
	"Latn",
}

m["gpn"] = {
	"Taiap",
	56237,
	"qfa-dis", -- Papuan; isolate in Glottolog; relationship with Torricelli proposed by Usher
	"Latn",
}

m["gqa"] = {
	"Ga'anda",
	56245,
	"cdc-cbm",
	"Latn",
}

m["gqi"] = {
	"Guiqiong",
	3120647,
	"sit-qia",
}

m["gqn"] = { -- a variety of 'ter'
	"Kinikinao",
	53386731,
	"awd",
	"Latn",
}

m["gqr"] = {
	"Gor",
	759992,
	"csu-sar",
	"Latn",
}

m["gqu"] = {
	"Qau",
	17284874,
	"gio",
}

m["gra"] = {
	"Rajput Garasia",
	21041529,
	"inc-bhi",
	"Deva, Gujr",
	ancestors = "bhb",
}

m["grc"] = {
	"Ancient Greek",
	35497,
	"grk",
	"Polyt, Cprt",
	translit = {
		Cprt = "Cprt-translit",
	},
	override_translit = true,
	-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
	standard_chars = {
		Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΡ̓ΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾",
		Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿",
		c.punc
	},
}

m["grd"] = {
	"Guruntum",
	3441272,
	"cdc-wst",
	"Latn",
}

m["grg"] = {
	"Madi",
	6727664,
	"ngf-gmo",
	"Latn",
}

m["grh"] = {
	"Gbiri-Niragu",
	3913936,
	"nic-kau",
	"Latn",
}

m["gri"] = {
	"Ghari",
	3104782,
	"poz-sls",
	"Latn",
}

m["grj"] = {
	"Southern Grebo",
	3914444,
	"grb",
	"Latn",
}

m["grm"] = {
	"Kota Marudu Talantang",
	6433808,
	"poz-san",
	"Latn",
}

m["gro"] = {
	"Groma",
	56551,
	"sit-tib",
}

m["grq"] = {
	"Gorovu",
	56355,
	"paa-por",
	"Latn",
}

m["grs"] = {
	"Gresi",
	5607612,
	"paa-nim",
	"Latn",
}

m["grt"] = {
	"Garo",
	36137,
	"tbq-bdg",
	"Latn, Beng, Brai",
}

m["gru"] = {
	"Kistane",
	13273,
	"sem-eth",
	"Latn, Ethi",
}

m["grv"] = {
	"Central Grebo",
	18385114,
	"grb",
	"Latn",
}

m["grw"] = {
	"Gweda",
	5623387,
	"poz-ocw",
	"Latn",
}

m["grx"] = {
	"Guriaso",
	12631954,
	"qfa-unc", -- no consensus; may be Kwomtari per Baron (1983) and Usher (2020), but no connections accepted by
			   -- Glottolog.
	"Latn",
}

m["gry"] = {
	"Barclayville Grebo",
	11157342,
	"grb",
	"Latn",
}

m["grz"] = {
	"Guramalum",
	3120935,
	"poz-ocw",
	"Latn",
}

m["gse"] = {
	"Ghanaian Sign Language",
	35289,
	"sgn",
	"Latn", -- when documented
}

m["gsg"] = {
	"German Sign Language",
	33282,
	"sgn-gsl",
	"Sgnw",
}

m["gsl"] = {
	"Gusilay",
	35439,
	"alv-jol",
	"Latn",
}

m["gsm"] = {
	"Guatemalan Sign Language",
	2886781,
	"sgn",
	"Latn", -- when documented
}

m["gsn"] = {
	"Gusan",
	11732224,
	"ngf-era",
	"Latn",
}

m["gso"] = {
	"Southwest Gbaya",
	4919322,
	"gba-sou",
	"Latn",
}

m["gsp"] = {
	"Wasembo",
	7971402,
	"ngf-mad", -- placed in under Rai Coast by Glottolog (under Greater Yaganon) and Pawley-Hammarström
	"Latn",
}

m["gss"] = {
	"Greek Sign Language",
	3565084,
	"sgn",
}

m["gsw"] = {
	"Alemannic German",
	131339,
	"gmw-hgm",
	"Latn",
	wikimedia_codes = "als",
	ancestors = "gmh",
}

m["gta"] = {
	"Guató",
	3027940,
	"qfa-dis", -- isolate or Macro-Jê
	"Latn",
}

m["gtu"] = {
	"Aghu Tharrnggala",
	16825981,
	"aus-pmn",
	"Latn",
}

m["gua"] = {
	"Shiki",
	3913946,
	"nic-jrn",
	"Latn",
}

m["gub"] = {
	"Guajajára",
	7699720,
	"tup-gua",
	"Latn",
}

m["guc"] = {
	"Wayuu",
	891085,
	"awd-taa",
	"Latn",
}

m["gud"] = {
	"Yocoboué Dida",
	21074781,
	"kro-did",
	"Latn",
}

m["gue"] = {
	"Gurindji",
	10511016,
	"aus-pam",
	"Latn",
}

m["guf"] = {
	"Gupapuyngu",
	10511004,
	"aus-yol",
	"Latn",
}

m["gug"] = {
	"Paraguayan Guarani",
	17478066,
	"gn",
	"Latn",
	wikimedia_codes = "gn",
	ancestors = "gn-cls",
}

m["guh"] = {
	"Guahibo",
	2669193,
	"sai-guh",
	"Latn",
}

m["gui"] = {
	"Eastern Bolivian Guarani",
	2963912,
	"gn",
	"Latn",
}

m["guk"] = {
	"Gumuz",
	2396970,
	"ssa",
	"Latn, Ethi",
}

m["gul"] = {
	"Gullah",
	33395,
	"crp",
	"Latn",
	ancestors = "en",
}

m["gum"] = {
	"Guambiano",
	2744745,
	"sai-bar",
	"Latn",
}

m["gun"] = {
	"Mbya Guarani",
	3915584,
	"gn",
	"Latn",
}

m["guo"] = {
	"Guayabero",
	2980375,
	"sai-guh",
	"Latn",
}

m["gup"] = {
	"Gunwinggu",
	1406574,
	"aus-gun",
	"Latn",
}

m["guq"] = {
	"Aché",
	383701,
	"tup",
	"Latn",
}

m["gur"] = {
	"Farefare",
	35331,
	"nic-mre",
	"Latn",
}

m["gus"] = {
	"Guinean Sign Language",
	15983937,
	"sgn",
	"Latn", -- when documented
}

m["gut"] = {
	"Maléku Jaíka",
	3915782,
	"cba",
	"Latn",
}

m["guu"] = {
	"Yanomamö",
	8048928,
	"sai-ynm",
	"Latn",
}

m["guv"] = {
	"Gey",
	11137816,
	"alv-sav",
	"Latn",
}

m["guw"] = {
	"Gun",
	3111668,
	"alv-gbe",
	"Latn",
	strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron},
}

m["gux"] = {
	"Gourmanchéma",
	35474,
	"nic-grm",
	"Latn",
}

m["guz"] = {
	"Gusii",
	33603,
	"bnt-lok",
	"Latn",
}

m["gva"] = {
	"Kaskihá",
	3033534,
	"sai-mas",
	"Latn",
}

m["gvc"] = {
	"Guanano",
	3566001,
	"sai-tuc",
	"Latn",
}

m["gve"] = {
	"Duwet",
	5317647,
	"poz-ocw",
	"Latn",
}

m["gvf"] = {
	"Golin",
	3110291,
	"ngf-sim",
	"Latn",
}

m["gvj"] = {
	"Guajá",
	3915506,
	"tup",
	"Latn",
}

m["gvl"] = {
	"Gulay",
	641737,
	"csu-sar",
	"Latn",
}

m["gvm"] = {
	"Gurmana",
	3913363,
	"nic-shi",
	"Latn",
}

m["gvn"] = {
	"Kuku-Yalanji",
	5621973,
	"aus-pam",
	"Latn",
}

m["gvo"] = {
	"Gavião do Jiparaná",
	5528335,
	"tup",
	"Latn",
}

m["gvp"] = {
	"Pará Gavião",
	3365443,
	"sai-nje",
	"Latn",
}

m["gvr"] = {
	"Gurung",
	2392342,
	"sit-tam",
	"Gukh, Deva",
}

m["gvs"] = {
	"Gumawana",
	5618041,
	"poz-ocw",
	"Latn",
}

m["gvy"] = {
	"Guyani",
	10511230,
	"aus-pam",
	"Latn",
}

m["gwa"] = {
	"Mbato",
	3914941,
	"alv-ptn",
	"Latn",
}

m["gwb"] = {
	"Gwa",
	5623219,
	"nic-jrn",
	"Latn",
}

m["gwc"] = {
	"Kalami",
	1675961,
	"inc-koh",
	"Arab",
	strip_diacritics = {
		["Arab"] = {
			-- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
			from = {"هٔ", "ۂ", "ٱ"},
			to = {"ہ", "ہ", "ا"},
			remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef .. u(0x065e)
		},
	},
}

m["gwd"] = {
	"Gawwada",
	3032135,
	"cus-eas",
	"Latn, Ethi",
}

m["gwe"] = {
	"Gweno",
	3358211,
	"bnt-chg",
	"Latn",
}

m["gwf"] = {
	"Gowro",
	3812403,
	"inc-koh",
	"Arab",
}

m["gwg"] = {
	"Moo",
	6907057,
	"alv-bwj",
	"Latn",
}

m["gwi"] = {
	"Gwich'in",
	21057,
	"ath-nor",
	"Latn",
}

m["gwj"] = {
	"Gcwi",
	12631978,
	"khi-kal",
	"Latn",
}

m["gwm"] = {
	"Awngthim",
	4830109,
	"aus-pmn",
	"Latn",
}

m["gwn"] = {
	"Gwandara",
	56521,
	"cdc-wst",
	"Latn",
}

m["gwr"] = {
	"Gwere",
	5623559,
	"bnt-nyg",
	"Latn",
}

m["gwt"] = {
	"Gawar-Bati",
	33894,
	"inc-kun",
	"Arab",
}

m["gwu"] = {
	"Guwamu",
	10511225,
	"aus-pam",
	"Latn",
}

m["gww"] = {
	"Kwini",
	10551249,
	"aus-wor",
	"Latn",
}

m["gwx"] = {
	"Gua",
	35422,
	"alv-gng",
	"Latn",
}

m["gxx"] = {
	"Wè Southern",
	19921582,
	"kro-wee",
	"Latn",
}

m["gya"] = {
	"Northwest Gbaya",
	36594,
	"gba-wes",
	"Latn",
}

m["gyb"] = {
	"Garus",
	5524492,
	"ngf-han",
	"Latn",
}

m["gyd"] = {
	"Kayardild",
	3913770,
	"aus-tnk",
	"Latn",
}

m["gye"] = {
	"Gyem",
	5624046,
	"nic-jer",
	"Latn",
}

m["gyf"] = {
	"Gungabula",
	10510783,
	"aus-pam",
	"Latn",
}

m["gyg"] = {
	"Gbayi",
	11137618,
	"nic-ngd",
	"Latn",
}

m["gyi"] = {
	"Gyele",
	35434,
	"bnt-mnj",
	"Latn",
}

m["gyl"] = {
	"Gayil",
	5528771,
	"omv-aro",
	"Latn",
}

m["gym"] = {
	"Ngäbere",
	3915581,
	"cba",
	"Latn",
}

m["gyn"] = {
	"Guyanese Creole English",
	3305477,
	"crp",
	"Latn",
	ancestors = "en",
}

m["gyo"] = {
	"Gyalsumdo",
	53575940,
	"sit-kyk",
}

m["gyr"] = {
	"Guarayu",
	3118779,
	"tup-gua",
	"Latn",
}

m["gyy"] = {
	"Gunya",
	10511001,
	"aus-pam",
	"Latn",
}

m["gza"] = {
	"Ganza",
	5521556,
	"omv-mao",
	"Latn",
}

m["gzn"] = {
	"Gane",
	3095108,
	"poz-hce",
	"Latn",
}

return require("Module:languages").finalizeData(m, "language")