Module:languages/data/3/g: difference between revisions
< Module:languages | data
Content deleted Content added
No edit summary |
replace curly apostrophe, spacing smooth breathing, spacing coronis with straight apostrophe when generating entry names |
||
Line 16: | Line 16: | ||
local RINGBELOW = u(0x0325) |
local RINGBELOW = u(0x0325) |
||
local CEDILLA = u(0x0327) |
local CEDILLA = u(0x0327) |
||
local RSQUO = u(0x2019) |
|||
local PSILI = u(0x1FBD) |
|||
local CORONIS = u(0x1FBF) |
|||
local m = {} |
local m = {} |
||
Line 1,108: | Line 1,111: | ||
sort_key = { -- Keep this synchronized with el, cpg, pnt; compare ine-pae |
sort_key = { -- Keep this synchronized with el, cpg, pnt; compare ine-pae |
||
from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇᾱᾍ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗῑ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧῡ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧᾨ]", "ῥ", "ς"}, |
from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇᾱᾍ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗῑ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧῡ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧᾨ]", "ῥ", "ς"}, |
||
to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}}, |
to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}}, |
||
entry_name = { |
entry_name = { |
||
from = {"[ᾸᾹ]", "[ᾰᾱ]", "[ῘῙ]", "[ῐῑ]", "[ῨῩ]", "[ῠῡ]", "µ"}, |
from = {"[ᾸᾹ]", "[ᾰᾱ]", "[ῘῙ]", "[ῐῑ]", "[ῨῩ]", "[ῠῡ]", "µ", "["..RSQUO..PSILI..CORONIS.."]" }, |
||
to = {"Α", "α", "Ι", "ι", "Υ", "υ", "μ"}} |
to = {"Α", "α", "Ι", "ι", "Υ", "υ", "μ", "'"}}, |
||
} |
} |
||
Revision as of 22:19, 13 January 2017
- The following documentation is generated by Template:language data documentation. [edit]
- Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox
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.
Errors
The following errors were detected by Module:data consistency check: Lua error in Module:languages at line 1631: bad argument #1 to 'find' (string expected, got nil)
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. Can be specified as a number (a positive integer) or a string that starts with
Q
and ends with decimal digits. Set tonil
if not known/present. This replaces the olderwikipedia_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
findBestScript
function in Module:scripts. 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 theNone
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), andine-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 anancestors
table; Proto-Indo-European will be automatically returned as its ancestor by thegetAncestors
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 thewiktprefix
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 tofalse
in Module:scripts/data. This is used bytransliterate
in Module:languages. link_tr
- Set this to
true
to link the language's transliteration. For instance, Gothic has entries in Gothic script and entries for transliterations: Lua error in Module:languages at line 1631: bad argument #1 to 'find' (string expected, got nil). Otherwise, this can be a comma-separated list of script codes, which means that links are only applied to terms using those scripts. 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 asI
, or even Latinl
orI
. 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 bymakeDisplayText
in Module:languages. entry_name
- See the Substitutions section for instructions on syntax.
- Defines replacements to create the entry name from the displayed form of a term. This can be 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 (
ру́сский
→русский
), or macrons from Latin or Old English words (ōs
→os
), as these are not used in the normal written form of these languages. This is used bymakeEntryName
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:
- Remove any characters that should be ignored in sorting.
- 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".
- 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
,entry_name
andsort_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:
- The keys
from
,to
,remove_diacritics
andremove_exceptions
relate to text substitution (see below). - 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.
- The keys
- 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.
- 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,
- Dedicated modules must take the arguments
text, lang, sc
, wheretext
is the input text (usually the page name or input by the user),lang
is the language code (not the language object), andsc
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:
- Using the
from
andto
keys. remove_diacritics
(and optionallyremove_exceptions
).- Both of the above (in that order).
- Using the
from
is paired withto
, and both of them must be tables that are organised pairwise: each element infrom
is a pattern to identify which characters in the term to replace, while the corresponding element into
defines what to replace them with (as arguments tomw.ustring.gsub
).- If the replacement is not present (or if it is
false
ornil
), then any matching characters are removed altogether. This means that thefrom
list can be longer than theto
list, and an empty replacement will be assumed for any elements infrom
that have no counterpart into
. - 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, ifremove_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 aremove_exceptions
table, which prevents specific characters from having their diacritics stripped. For instance, ifremove_diacritics
is a combining diaeresis, butremove_exceptions
contains"ё"
, then any instances ofё
will remain unchanged. On the other hand, an instance ofӱ
would still becomeу
(unless"ӱ"
is also added toremove_exceptions
).
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 u = mw.ustring.char
-- UTF-8 encoded strings for some commonly-used diacritics
local GRAVE = u(0x0300)
local ACUTE = u(0x0301)
local CIRC = u(0x0302)
local TILDE = u(0x0303)
local MACRON = u(0x0304)
local BREVE = u(0x0306)
local DOTABOVE = u(0x0307)
local DIAER = u(0x0308)
local CARON = u(0x030C)
local DGRAVE = u(0x030F)
local INVBREVE = u(0x0311)
local DOTBELOW = u(0x0323)
local RINGBELOW = u(0x0325)
local CEDILLA = u(0x0327)
local RSQUO = u(0x2019)
local PSILI = u(0x1FBD)
local CORONIS = u(0x1FBF)
local m = {}
m["gaa"] = { -- test
canonicalName = "Ga",
scripts = {"Latn"},
family = "alv-kwa",
}
m["gab"] = {
canonicalName = "Gabri",
}
m["gad"] = {
canonicalName = "Gaddang",
family = "phi",
}
m["gae"] = {
canonicalName = "Warekena",
otherNames = {"Guarequena", "Arekena"},
scripts = {"Latn"},
family = "awd-nwk",
}
m["gaf"] = {
canonicalName = "Gende",
}
m["gag"] = {
canonicalName = "Gagauz",
scripts = {"Latn", "Cyrl"},
family = "trk-ogz",
}
m["gah"] = {
canonicalName = "Alekano",
otherNames = {"Gahuku"},
scripts = {"Latn"},
family = "paa-kag",
}
m["gai"] = {
canonicalName = "Borei",
family = "paa",
}
m["gaj"] = {
canonicalName = "Gadsup",
family = "paa-kag",
}
m["gak"] = {
canonicalName = "Gamkonora",
}
m["gal"] = {
canonicalName = "Galoli",
otherNames = {"Galolen", "Talur"},
}
m["gam"] = {
canonicalName = "Kandawo",
}
m["gan"] = {
canonicalName = "Gan",
scripts = {"Hani"},
family = "zhx",
ancestors = {"ltc"},
}
m["gao"] = {
canonicalName = "Gants",
}
m["gap"] = {
canonicalName = "Gal",
}
m["gaq"] = {
canonicalName = "Gata'",
family = "mun",
}
m["gar"] = {
canonicalName = "Galeya",
family = "poz-ocw",
}
m["gas"] = {
canonicalName = "Adiwasi Garasia",
family = "inc",
}
m["gat"] = {
canonicalName = "Kenati",
}
m["gau"] = {
canonicalName = "Kondekor",
otherNames = {"Gadaba", "San Gadaba", "Gadba", "Sano", "Kondekar", "Kondkor", "Konḍekor Gadaba", "Mudhili Gadaba"},
family = "dra",
}
m["gaw"] = {
canonicalName = "Nobonob",
family = "paa",
}
m["gay"] = {
canonicalName = "Gayo",
scripts = {"Latn"},
family = "poz-nws",
}
m["gba"] = {
canonicalName = "Gbaya",
}
m["gbb"] = {
canonicalName = "Kaytetye",
scripts = {"Latn"},
family = "aus-rnd",
}
m["gbd"] = {
canonicalName = "Karadjeri",
otherNames = {"Garadjari", "Karajarri"},
family = "aus-pam",
}
m["gbe"] = {
canonicalName = "Niksek",
family = "paa",
}
m["gbf"] = {
canonicalName = "Gaikundi",
family = "paa",
}
m["gbg"] = {
canonicalName = "Gbanziri",
otherNames = {"Banziri", "Gbandere", "Gbanzili"},
family = "nic-ubg",
}
m["gbh"] = {
canonicalName = "Defi Gbe",
}
m["gbi"] = {
canonicalName = "Galela",
}
m["gbj"] = {
canonicalName = "Bodo Gadaba",
otherNames = {"Gutob"},
family = "mun",
}
m["gbk"] = {
canonicalName = "Gaddi",
}
m["gbl"] = {
canonicalName = "Gamit",
family = "inc",
}
m["gbm"] = {
canonicalName = "Garhwali",
family = "inc",
}
m["gbn"] = {
canonicalName = "Mo'da",
}
m["gbo"] = {
canonicalName = "Northern Grebo",
}
m["gbp"] = {
canonicalName = "Gbaya-Bossangoa",
}
m["gbq"] = {
canonicalName = "Gbaya-Bozoum",
}
m["gbr"] = {
canonicalName = "Gbagyi",
}
m["gbs"] = {
canonicalName = "Gbesi Gbe",
}
m["gbu"] = {
canonicalName = "Gagadu",
}
m["gbv"] = {
canonicalName = "Gbanu",
}
m["gbw"] = {
canonicalName = "Gabi",
otherNames = {"Gabi-Gabi", "Gabi Gabi", "Gubbi-Gubbi", "Gubbi Gubbi"}, -- contrast xby
scripts = {"Latn"},
family = "aus-pam",
}
m["gbx"] = {
canonicalName = "Eastern Xwla Gbe",
}
m["gby"] = {
canonicalName = "Gbari",
}
m["gbz"] = {
canonicalName = "Zoroastrian Dari",
otherNames = {"Behdināni", "Gabri", "Gavrŭni", "Gabrōni"},
scripts = {"Latn"},
family = "ira",
}
m["gcc"] = {
canonicalName = "Mali",
}
m["gcd"] = {
canonicalName = "Ganggalida",
}
m["gce"] = {
canonicalName = "Galice",
family = "ath-pco",
}
m["gcf"] = {
canonicalName = "Antillean Creole",
otherNames = {"Antillean Creole French", "Guadeloupean Creole", "Guadeloupean Creole French", "Saint Lucian Creole", "Saint Lucian Creole French"},
scripts = {"Latn"},
family = "crp",
ancestors = {"fr"},
}
m["gcl"] = {
canonicalName = "Grenadian Creole English",
family = "crp",
}
m["gcn"] = {
canonicalName = "Gaina",
}
m["gcr"] = {
canonicalName = "Guianese Creole",
}
m["gct"] = {
canonicalName = "Colonia Tovar German",
otherNames = {"Alemán Coloniero"},
scripts = {"Latn"},
family = "gmw",
ancestors = {"gsw"},
}
m["gdb"] = {
canonicalName = "Ollari",
otherNames = {"Pottangi Ollar Gadaba", "Ollar Gadaba", "Ollaro", "Hallari", "Allar", "Hollar Gadbas"},
family = "dra",
}
m["gdc"] = {
canonicalName = "Gugu Badhun",
}
m["gdd"] = {
canonicalName = "Gedaged",
family = "poz-ocw",
}
m["gde"] = {
canonicalName = "Gude",
}
m["gdf"] = {
canonicalName = "Guduf-Gava",
family = "cdc-cbm",
}
m["gdg"] = {
canonicalName = "Ga'dang",
}
m["gdh"] = {
canonicalName = "Gadjerawang",
}
m["gdi"] = {
canonicalName = "Gundi",
family = "nic-ubg",
}
m["gdj"] = {
canonicalName = "Kurtjar",
otherNames = {"Gurdjar", "Kunggara"},
scripts = {"Latn"},
family = "aus-pmn",
}
m["gdk"] = {
canonicalName = "Gadang",
family = "cdc-est",
}
m["gdl"] = {
canonicalName = "Dirasha",
family = "cus",
}
m["gdm"] = {
canonicalName = "Laal",
scripts = {"Latn"},
}
m["gdn"] = {
canonicalName = "Umanakaina",
}
m["gdo"] = {
canonicalName = "Godoberi",
otherNames = {"Ghodoberi"},
scripts = {"Cyrl"},
family = "cau-ava",
}
m["gdq"] = {
canonicalName = "Mehri",
otherNames = {"Mahri"},
scripts = {"Arab"},
family = "sem-sar",
}
m["gdr"] = {
canonicalName = "Wipi",
}
m["gds"] = {
canonicalName = "Ghandruk Sign Language",
family = "sgn",
}
m["gdt"] = {
canonicalName = "Kungardutyi",
}
m["gdu"] = {
canonicalName = "Gudu",
}
m["gdx"] = {
canonicalName = "Godwari",
}
m["gea"] = {
canonicalName = "Geruma",
family = "cdc-wst",
}
m["geb"] = {
canonicalName = "Kire",
family = "paa",
}
m["gec"] = {
canonicalName = "Gboloo Grebo",
}
m["ged"] = {
canonicalName = "Gade",
}
m["geg"] = {
canonicalName = "Gengle",
}
m["geh"] = {
canonicalName = "Hutterisch",
otherNames = {"Hutterite German", "Tirolean"},
scripts = {"Latn"},
family = "gmw",
ancestors = {"bar"},
}
m["gei"] = {
canonicalName = "Gebe",
family = "poz-hce",
}
m["gej"] = {
canonicalName = "Gen",
}
m["gek"] = {
canonicalName = "Gerka",
otherNames = {"Yiwom"},
scripts = {"Latn"},
family = "cdc-wst",
}
m["gel"] = {
canonicalName = "Fakkanci",
otherNames = {"Kag-Fer-Jiir-Koor-Ror-Us-Zuksun", "ut-Ma'in", "Fakai", "Kag", "Puku", "Fakanchi", "Et-Kag", "Jiir", "Gelanchi", "Et-Jiir", "Kur", "Kere", "Kar", "Keri-Ni", "Kelli-Ni", "Kelanchi", "Kelinci", "Zuksun", "Zussun", "Et-Zuksun", "Ror", "Et-Maror", "Tudanchi", "Er-Gwar", "Fer", "Fere", "Et-Fer", "Wipsi-Ni", "Kukum", "Us", "Et-Us", "Koor", "Kulu"},
family = "nic-knj",
}
m["geq"] = {
canonicalName = "Geme",
family = "znd",
}
m["ges"] = {
canonicalName = "Geser-Gorom",
family = "plf",
}
m["gev"] = {
canonicalName = "Viya",
otherNames = {"Eviya"},
}
m["gew"] = {
canonicalName = "Gera",
family = "cdc-wst",
}
m["gex"] = {
canonicalName = "Garre",
family = "cus",
}
m["gey"] = {
canonicalName = "Enya",
}
m["gez"] = {
canonicalName = "Ge'ez",
otherNames = {"Ethiopic", "Gi'iz"},
scripts = {"Ethi"},
family = "sem-eth",
translit_module = "Ethi-translit",
}
m["gfk"] = {
canonicalName = "Patpatar",
scripts = {"Latn"},
family = "poz-ocw",
}
m["gft"] = {
canonicalName = "Gafat",
family = "sem-eth",
}
m["gga"] = {
canonicalName = "Gao",
family = "poz-ocw",
}
m["ggb"] = {
canonicalName = "Gbii",
}
m["ggd"] = {
canonicalName = "Gugadj",
}
m["gge"] = {
canonicalName = "Guragone",
family = "aus-arn",
}
m["ggg"] = {
canonicalName = "Gurgula",
scripts = {"Arab"},
family = "inc",
ancestors = {"mwr"},
}
m["ggk"] = {
canonicalName = "Kungarakany",
family = "aus-arn",
}
m["ggl"] = {
canonicalName = "Ganglau",
}
m["ggn"] = {
canonicalName = "Eastern Gurung",
}
m["ggt"] = {
canonicalName = "Gitua",
family = "poz-ocw",
}
m["ggu"] = {
canonicalName = "Gban",
}
m["ggw"] = {
canonicalName = "Gogodala",
}
m["gha"] = {
canonicalName = "Ghadames",
otherNames = {"Ghadamès"},
family = "ber",
}
m["ghe"] = {
canonicalName = "Southern Ghale",
}
m["ghh"] = {
canonicalName = "Northern Ghale",
}
m["ghk"] = {
canonicalName = "Geko Karen",
}
m["ghl"] = {
canonicalName = "Ghulfan",
}
m["ghn"] = {
canonicalName = "Ghanongga",
family = "poz-ocw",
}
m["gho"] = {
canonicalName = "Ghomara",
family = "ber",
}
m["ghr"] = {
canonicalName = "Ghera",
}
m["ghs"] = {
canonicalName = "Guhu-Samane",
}
m["ght"] = {
canonicalName = "Kutang Ghale",
}
m["gia"] = {
canonicalName = "Kitja",
}
m["gib"] = {
canonicalName = "Gibanawa",
}
m["gic"] = {
canonicalName = "Gail",
}
m["gid"] = {
canonicalName = "Gidar",
}
m["gig"] = {
canonicalName = "Goaria",
scripts = {"Arab"},
family = "inc",
ancestors = {"mwr"},
}
m["gih"] = {
canonicalName = "Githabul",
}
m["gil"] = {
canonicalName = "Gilbertese",
otherNames = {"Kiribati", "Kiribatese"},
scripts = {"Latn"},
family = "poz-mic",
}
m["gim"] = {
canonicalName = "Papuan Gimi",
otherNames = {"Gimi"},
family = "paa",
}
m["gin"] = {
canonicalName = "Hinukh",
otherNames = {"Hinuq", "Hinux", "Ginukh", "Ginux"},
family = "cau-tsz",
}
m["gio"] = {
canonicalName = "Gelao",
family = "qfa-tak",
}
m["gip"] = {
canonicalName = "Austronesian Gimi",
otherNames = {"Gimi"},
family = "poz-ocw",
}
m["giq"] = {
canonicalName = "Green Gelao",
otherNames = {"Hagei", "Hakhi"},
family = "qfa-tak",
}
m["gir"] = {
canonicalName = "Red Gelao",
otherNames = {"Vandu"},
family = "qfa-tak",
}
m["gis"] = {
canonicalName = "North Giziga",
}
m["git"] = {
canonicalName = "Gitxsan",
}
m["giu"] = {
canonicalName = "Mulao", -- a variety of Gelao
family = "qfa-tak",
}
m["giw"] = {
canonicalName = "White Gelao",
otherNames = {"Telue", "Doulou", "Tolo"},
family = "qfa-tak",
}
m["gix"] = {
canonicalName = "Gilima",
family = "nic-ubg",
}
m["giy"] = {
canonicalName = "Giyug",
}
m["giz"] = {
canonicalName = "South Giziga",
}
m["gji"] = {
canonicalName = "Geji",
}
m["gjk"] = {
canonicalName = "Kachi Koli",
}
m["gjm"] = {
canonicalName = "Gunditjmara",
}
m["gjn"] = {
canonicalName = "Gonja",
}
m["gju"] = {
canonicalName = "Gojri",
family = "inc",
ancestors = {"raj"},
}
m["gka"] = {
canonicalName = "Guya",
family = "ngf-fin",
}
m["gke"] = {
canonicalName = "Ndai",
}
m["gkn"] = {
canonicalName = "Gokana",
family = "nic-bco",
}
m["gko"] = {
canonicalName = "Kok-Nar",
scripts = {"Latn"},
family = "aus-pmn",
}
m["gkp"] = {
canonicalName = "Guinea Kpelle",
}
m["glc"] = {
canonicalName = "Bon Gula",
}
m["gld"] = {
canonicalName = "Nanai",
scripts = {"Cyrl"},
family = "tuw",
}
m["glh"] = {
canonicalName = "Northwest Pashayi",
family = "inc-dar",
}
m["gli"] = {
canonicalName = "Guliguli",
family = "poz-ocw",
}
m["glj"] = {
canonicalName = "Kulaal",
}
m["glk"] = {
canonicalName = "Gilaki",
scripts = {"fa-Arab"},
family = "ira",
}
m["glo"] = {
canonicalName = "Galambu",
family = "cdc-wst",
}
m["glr"] = {
canonicalName = "Glaro-Twabo",
}
m["glu"] = {
canonicalName = "Gula",
otherNames = {"Sara Gula"},
family = "csu",
}
m["glw"] = {
canonicalName = "Glavda",
}
m["gly"] = {
canonicalName = "Gule",
}
m["gma"] = {
canonicalName = "Gambera",
}
m["gmb"] = {
canonicalName = "Gula'alaa",
family = "poz-sls",
}
m["gmd"] = {
canonicalName = "Mághdì",
}
m["gmg"] = {
canonicalName = "Magɨyi",
family = "paa",
}
m["gmh"] = {
canonicalName = "Middle High German",
scripts = {"Latn"},
family = "gmw",
ancestors = {"goh"},
entry_name = {
from = {"[ĀÂ]", "[āâ]", "[ĒÊË]", "[ēêë]", "[ĪÎ]", "[īî]", "[ŌÔ]", "[ōô]", "[ŪÛ]", "[ūû]"},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u" },
},
}
m["gml"] = {
canonicalName = "Middle Low German",
scripts = {"Latn"},
family = "gmw",
ancestors = {"osx"},
entry_name = {
from = {"[ĀÂÄǞ]", "[āâäǟ]", "[ĒÊ]", "[ēê]", "[ĪÎ]", "[īî]", "[ŌÔÖȪ]", "[ōôöȫ]", "[ŪÛÜǕ]", "[ūûüǖ]", "[̂]"},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u" , "" },
},
}
m["gmm"] = {
canonicalName = "Gbaya-Mbodomo",
}
m["gmn"] = {
canonicalName = "Gimnime",
}
m["gmu"] = {
canonicalName = "Gumalu",
}
m["gmv"] = {
canonicalName = "Gamo",
}
m["gmx"] = {
canonicalName = "Magoma",
}
m["gmy"] = {
canonicalName = "Mycenaean Greek",
scripts = {"Linb"},
family = "grk",
translit_module = "Linb-translit",
override_translit = true,
}
m["gmz"] = {
canonicalName = "Mgbo",
otherNames = {"Mgbolizhia"},
family = "alv-von",
}
m["gna"] = {
canonicalName = "Kaansa",
}
m["gnb"] = {
canonicalName = "Gangte",
family = "tbq-kuk",
}
m["gnc"] = {
canonicalName = "Guanche",
family = "ber",
}
m["gnd"] = {
canonicalName = "Zulgo-Gemzek",
otherNames = {"Zulgo", "Gemzek", "Mineo"},
scripts = {"Latn"},
family = "cdc-cbm",
}
m["gne"] = {
canonicalName = "Ganang",
}
m["gng"] = {
canonicalName = "Ngangam",
}
m["gnh"] = {
canonicalName = "Lere",
}
m["gni"] = {
canonicalName = "Gooniyandi",
scripts = {"Latn"},
family = "aus-bub",
}
m["gnk"] = {
canonicalName = "ǁGana",
otherNames = {"Gana"},
}
m["gnl"] = {
canonicalName = "Gangulu",
}
m["gnm"] = {
canonicalName = "Ginuman",
}
m["gnn"] = {
canonicalName = "Gumatj",
family = "aus-yol",
}
m["gnq"] = {
canonicalName = "Gana",
}
m["gnr"] = {
canonicalName = "Gureng Gureng",
}
m["gnt"] = {
canonicalName = "Guntai",
}
m["gnu"] = {
canonicalName = "Gnau",
family = "qfa-tor",
}
m["gnw"] = {
canonicalName = "Western Bolivian Guaraní",
family = "tup",
}
m["gnz"] = {
canonicalName = "Ganzi",
family = "nic-ubg",
}
m["goa"] = {
canonicalName = "Guro",
}
m["gob"] = {
canonicalName = "Playero",
}
m["goc"] = {
canonicalName = "Gorakor",
family = "poz-ocw",
}
m["god"] = {
canonicalName = "Godié",
}
m["goe"] = {
canonicalName = "Gongduk",
}
m["gof"] = {
canonicalName = "Gofa",
scripts = {"Latn", "Ethi"},
family = "omv",
}
m["gog"] = {
canonicalName = "Gogo",
}
m["goh"] = {
canonicalName = "Old High German",
scripts = {"Latn"},
family = "gmw",
entry_name = {
from = {"[ĀÂ]", "[āâ]", "[ĒÊË]", "[ēêë]", "[ĪÎ]", "[īî]", "[ŌÔ]", "[ōô]", "[ŪÛ]", "[ūû]", "ʒ"},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u" , "z" }} ,
}
m["goi"] = {
canonicalName = "Gobasi",
otherNames = {"Gobosi", "Gebusi", "Bibo"},
scripts = {"Latn"},
}
m["goj"] = {
canonicalName = "Gowlan",
}
m["gok"] = {
canonicalName = "Gowli",
}
m["gol"] = {
canonicalName = "Gola",
}
m["gon"] = {
canonicalName = "Gondi",
otherNames = {"Southern Gondi", "Northern Gondi", "Aheri Gondi", "Adilabad Gondi", "Dorla Gondi", "Koya Gondi", "Maria Gondi", "Muria Gondi", "Raj Gondi"},
scripts = {"Telu"},
family = "dra",
}
m["goo"] = {
canonicalName = "Gone Dau",
family = "poz-occ",
}
m["gop"] = {
canonicalName = "Yeretuar",
family = "poz-hce",
}
m["goq"] = {
canonicalName = "Gorap",
}
m["gor"] = {
canonicalName = "Gorontalo",
scripts = {"Latn"},
family = "phi",
}
m["got"] = {
canonicalName = "Gothic",
scripts = {"Goth", "Runr"},
family = "gme",
translit_module = "Goth-translit",
link_tr = true,
entry_name = {
from = {"Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū"},
to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}} ,
}
m["gou"] = {
canonicalName = "Gavar",
}
m["gow"] = {
canonicalName = "Gorowa",
family = "cus",
}
m["gox"] = {
canonicalName = "Gobu",
}
m["goy"] = {
canonicalName = "Goundo",
}
m["goz"] = {
canonicalName = "Gozarkhani",
ancestors = {"ira-azr"},
}
m["gpa"] = {
canonicalName = "Gupa-Abawa",
}
m["gpn"] = {
canonicalName = "Taiap",
}
m["gqa"] = {
canonicalName = "Ga'anda",
}
m["gqi"] = {
canonicalName = "Guiqiong",
otherNames = {"Guìqióng", "Guichong"},
family = "sit-qia",
}
m["gqn"] = { -- a variety of 'ter'
canonicalName = "Kinikinao",
otherNames = {"Guana", "Guaná", "Guana (Brazil)", "Arawakan Guana"},
family = "awd",
}
m["gqr"] = {
canonicalName = "Gor",
}
m["gqu"] = {
canonicalName = "Qau",
otherNames = {"Gao", "Aqao", "Qau Gelao"},
family = "qfa-tak",
}
m["gra"] = {
canonicalName = "Rajput Garasia",
family = "inc",
}
m["grb"] = {
canonicalName = "Grebo",
}
m["grc"] = {
canonicalName = "Ancient Greek",
scripts = {"polytonic", "Cprt"},
family = "grk",
translit_module = "grc-translit",
override_translit = true,
sort_key = { -- Keep this synchronized with el, cpg, pnt; compare ine-pae
from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇᾱᾍ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗῑ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧῡ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧᾨ]", "ῥ", "ς"},
to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}},
entry_name = {
from = {"[ᾸᾹ]", "[ᾰᾱ]", "[ῘῙ]", "[ῐῑ]", "[ῨῩ]", "[ῠῡ]", "µ", "["..RSQUO..PSILI..CORONIS.."]" },
to = {"Α", "α", "Ι", "ι", "Υ", "υ", "μ", "'"}},
}
m["grd"] = {
canonicalName = "Guruntum",
}
m["grg"] = {
canonicalName = "Madi",
family = "ngf-fin",
}
m["grh"] = {
canonicalName = "Gbiri-Niragu",
}
m["gri"] = {
canonicalName = "Ghari",
family = "poz-sls",
}
m["grj"] = {
canonicalName = "Southern Grebo",
}
m["grm"] = {
canonicalName = "Kota Marudu Talantang",
}
m["gro"] = {
canonicalName = "Groma",
}
m["grq"] = {
canonicalName = "Gorovu",
family = "paa",
}
m["grr"] = {
canonicalName = "Taznatit",
family = "ber",
}
m["grs"] = {
canonicalName = "Gresi",
}
m["grt"] = {
canonicalName = "Garo",
}
m["gru"] = {
canonicalName = "Kistane",
otherNames = {"Soddo", "Aymälläl"},
scripts = {"Latn"},
family = "sem-eth",
}
m["grv"] = {
canonicalName = "Central Grebo",
}
m["grw"] = {
canonicalName = "Gweda",
family = "poz-ocw",
}
m["grx"] = {
canonicalName = "Guriaso",
}
m["gry"] = {
canonicalName = "Barclayville Grebo",
}
m["grz"] = {
canonicalName = "Guramalum",
family = "poz-ocw",
}
m["gse"] = {
canonicalName = "Ghanaian Sign Language",
family = "sgn",
}
m["gsg"] = {
canonicalName = "German Sign Language",
otherNames = {"Deutsche Gebärdensprache"},
scripts = {"Sgnw"},
family = "sgn-gsl",
}
m["gsl"] = {
canonicalName = "Gusilay",
}
m["gsm"] = {
canonicalName = "Guatemalan Sign Language",
family = "sgn",
}
m["gsn"] = {
canonicalName = "Gusan",
family = "ngf-fin",
}
m["gso"] = {
canonicalName = "Southwest Gbaya",
}
m["gsp"] = {
canonicalName = "Wasembo",
}
m["gss"] = {
canonicalName = "Greek Sign Language",
family = "sgn",
}
m["gsw"] = {
canonicalName = "Alemannic German",
otherNames = {"Swiss German", "Walser German", "Walserdeutsch", "Walser", "Wallisertiitsch", "Italian Walser", "Pomattertitsch", "Formazza", "Kampel", "Remmaljertittschu", "Rimella", "Chalchoufe", "Titzschu", "Alagna", "Greschóneytitsch", "Greschóney", "Greschoney", "Gressoney", "Éischemtöitschu", "Issime"},
scripts = {"Latn"},
family = "gmw",
ancestors = {"gmh"},
wikimedia_codes = {"als"},
}
m["gta"] = {
canonicalName = "Guató",
scripts = {"Latn"},
family = "qfa-iso",
}
m["gti"] = {
canonicalName = "Gbati-ri",
}
m["gtu"] = {
canonicalName = "Aghu Tharrnggala",
otherNames = {"Aghu Tharnggala", "Aghu Tharnggalu"},
scripts = {"Latn"},
family = "aus-pmn",
}
m["gua"] = {
canonicalName = "Shiki",
}
m["gub"] = {
canonicalName = "Guajajára",
}
m["guc"] = {
canonicalName = "Wayuu",
otherNames = {"Guajiro", "Goajiro", "Uagiro"},
family = "awd",
}
m["gud"] = {
canonicalName = "Yocoboué Dida",
}
m["gue"] = {
canonicalName = "Gurindji",
family = "aus-pam",
}
m["guf"] = {
canonicalName = "Gupapuyngu",
family = "aus-yol",
}
m["gug"] = {
canonicalName = "Paraguayan Guaraní",
family = "tup",
}
m["guh"] = {
canonicalName = "Guahibo",
}
m["gui"] = {
canonicalName = "Eastern Bolivian Guaraní",
family = "tup",
}
m["guk"] = {
canonicalName = "Gumuz",
}
m["gul"] = {
canonicalName = "Gullah",
otherNames = {"Geechee", "Sea Island Creole English"},
scripts = {"Latn"},
family = "crp",
ancestors = {"en"},
}
m["gum"] = {
canonicalName = "Guambiano",
}
m["gun"] = {
canonicalName = "Mbyá Guaraní",
scripts = {"Latn"},
family = "tup",
}
m["guo"] = {
canonicalName = "Guayabero",
}
m["gup"] = {
canonicalName = "Gunwinggu",
family = "aus-gun",
}
m["guq"] = {
canonicalName = "Aché",
family = "tup",
}
m["gur"] = {
canonicalName = "Farefare",
otherNames = {"Frafra", "Gurene", "Gurenɛ", "Gurenne", "Gudenne", "Gudeni", "Zuadeni", "Nankani", "Naani", "Nankanse", "Ninkare", "Booni"},
}
m["gus"] = {
canonicalName = "Guinean Sign Language",
family = "sgn",
}
m["gut"] = {
canonicalName = "Maléku Jaíka",
scripts = {"Latn"},
family = "cba",
}
m["guu"] = {
canonicalName = "Yanomamö",
}
m["guv"] = {
canonicalName = "Gey",
}
m["guw"] = {
canonicalName = "Gun",
otherNames = {"Gun-Gbe", "Gungbe"},
scripts = {"Latn"},
family = "alv-von",
}
m["gux"] = {
canonicalName = "Gourmanchéma",
}
m["guz"] = {
canonicalName = "Gusii",
scripts = {"Latn"},
family = "bnt",
}
m["gva"] = {
canonicalName = "Kaskihá",
otherNames = {"Guana", "Guaná", "Guana (Paraguay)", "Mascoian Guana"},
family = "sai-mas",
}
m["gvc"] = {
canonicalName = "Guanano",
scripts = {"Latn"},
family = "sai-tuc",
}
m["gve"] = {
canonicalName = "Duwet",
family = "poz-ocw",
}
m["gvf"] = {
canonicalName = "Golin",
scripts = {"Latn"},
family = "ngf",
}
m["gvj"] = {
canonicalName = "Guajá",
}
m["gvl"] = {
canonicalName = "Gulay",
}
m["gvm"] = {
canonicalName = "Gurmana",
}
m["gvn"] = {
canonicalName = "Kuku-Yalanji",
}
m["gvo"] = {
canonicalName = "Gavião do Jiparaná",
otherNames = {"Gavião of Jiparaná", "Digüt", "Ikolen", "Gavião do Rondônia"},
family = "tup",
}
m["gvp"] = {
canonicalName = "Pará Gavião",
}
m["gvr"] = {
canonicalName = "Western Gurung",
}
m["gvs"] = {
canonicalName = "Gumawana",
family = "poz-ocw",
}
m["gvy"] = {
canonicalName = "Guyani",
}
m["gwa"] = {
canonicalName = "Mbato",
}
m["gwb"] = {
canonicalName = "Gwa",
}
m["gwc"] = {
canonicalName = "Kalami",
scripts = {"Arab"},
family = "inc-dar",
}
m["gwd"] = {
canonicalName = "Gawwada",
family = "cus",
}
m["gwe"] = {
canonicalName = "Gweno",
scripts = {"Latn"},
family = "bnt",
}
m["gwf"] = {
canonicalName = "Gowro",
}
m["gwg"] = {
canonicalName = "Moo",
}
m["gwi"] = {
canonicalName = "Gwich'in",
otherNames = {"Gwich’in", "Kutchin", "Takudh", "Tukudh", "Loucheux"},
scripts = {"Latn"},
family = "ath",
}
m["gwj"] = {
canonicalName = "Gcwi",
otherNames = {"Gǀwi", "Gǀui"},
}
m["gwm"] = {
canonicalName = "Awngthim",
}
m["gwn"] = {
canonicalName = "Gwandara",
}
m["gwr"] = {
canonicalName = "Gwere",
family = "bnt",
}
m["gwt"] = {
canonicalName = "Gawar-Bati",
}
m["gwu"] = {
canonicalName = "Guwamu",
}
m["gww"] = {
canonicalName = "Kwini",
}
m["gwx"] = {
canonicalName = "Gua",
}
m["gxx"] = {
canonicalName = "Wè Southern",
}
m["gya"] = {
canonicalName = "Northwest Gbaya",
}
m["gyb"] = {
canonicalName = "Garus",
}
m["gyd"] = {
canonicalName = "Kayardild",
}
m["gye"] = {
canonicalName = "Gyem",
}
m["gyf"] = {
canonicalName = "Gungabula",
}
m["gyg"] = {
canonicalName = "Gbayi",
family = "nic-ubg",
}
m["gyi"] = {
canonicalName = "Gyele",
}
m["gyl"] = {
canonicalName = "Gayil",
}
m["gym"] = {
canonicalName = "Ngäbere",
}
m["gyn"] = {
canonicalName = "Guyanese Creole English",
}
m["gyr"] = {
canonicalName = "Guarayu",
}
m["gyy"] = {
canonicalName = "Gunya",
scripts = {"Latn"},
family = "aus-pam",
}
m["gza"] = {
canonicalName = "Ganza",
}
m["gzi"] = {
canonicalName = "Gazi",
scripts = {"fa-Arab"},
family = "ira",
}
m["gzn"] = {
canonicalName = "Gane",
family = "poz-hce",
}
return m