Linguifex

Module:languages/data: Difference between revisions

← Older edit
No edit summary
No edit summary
 
(One intermediate revision by the same user not shown)
Line 20: Line 20:
diaer = u(0x0308),
diaer = u(0x0308),
ringabove = u(0x030A),
ringabove = u(0x030A),
hook            = u(0x0309),
dacute = u(0x030B),
dacute = u(0x030B),
caron = u(0x030C),
caron = u(0x030C),
Line 32: Line 33:
cedilla = u(0x0327),
cedilla = u(0x0327),
ogonek = u(0x0328),
ogonek = u(0x0328),
tildebelow      = u(0x0330),
brevebelow = u(0x032E),
brevebelow = u(0x032E),
tildebelow      = u(0x0330),
macronbelow = u(0x0331),
macronbelow = u(0x0331),
perispomeni = u(0x0342),
perispomeni = u(0x0342),
Line 51: Line 52:
lowerkeraia = u(0x0375),
lowerkeraia = u(0x0375),
tonos = u(0x0384),
tonos = u(0x0384),
kamora          = u(0x0484),
palatalization = u(0x0484),
dasiapneumata   = u(0x0485),
dasiapneumata = u(0x0485),
psilipneumata   = u(0x0486),
psilipneumata = u(0x0486),
kashida = u(0x0640),
kashida = u(0x0640),
fathatan = u(0x064B),
fathatan = u(0x064B),
Line 65: Line 66:
hamzaabove = u(0x0654),
hamzaabove = u(0x0654),
nunghunna = u(0x0658),
nunghunna = u(0x0658),
zwarakay       = u(0x0659),
zwarakay = u(0x0659),
smallv = u(0x065A),
smallv = u(0x065A),
superalef = u(0x0670),
superalef = u(0x0670),
udatta = u(0x0951),
udatta = u(0x0951),
anudatta = u(0x0952),
anudatta = u(0x0952),
dottedgrave = u(0x1DC0),
dottedacute = u(0x1DC1),
coronis = u(0x1FBD),
coronis = u(0x1FBD),
psili = u(0x1FBF),
psili = u(0x1FBF),
Line 76: Line 79:
ZWJ = u(0x200D), -- zero width joiner
ZWJ = u(0x200D), -- zero width joiner
RSQuo = u(0x2019), -- right single quote
RSQuo = u(0x2019), -- right single quote
kavyka = u(0xA67C),
VS01 = u(0xFE00), -- variation selector 1
VS01 = u(0xFE00), -- variation selector 1
-- Punctuation for the standardChars field.
-- Punctuation for the standardChars field.
Line 107: Line 111:
-- These values are placed here to make it possible to synchronise a group of languages without the need for a dedicated function module.
-- These values are placed here to make it possible to synchronise a group of languages without the need for a dedicated function module.


s["cau-Cyrl-displaytext"] = {
-- cau
from = {"[IlΙІӀ]", "ᴴ"},
do
to = {"ӏ", "ᵸ"}
local cau_remove_diacritics = c.grave .. c.acute .. c.macron
}
local cau_from = {"[IlΙІӀᴴ]"}
local cau_to = {{
["l"] = "ӏ",
["Ι"] = "ӏ",
["І"] = "ӏ",
["Ӏ"] = "ӏ",
["ᴴ"] = "ᵸ",
}}
 
s["cau-Cyrl-displaytext"] = {
from = cau_from,
to = cau_to,
}
 
s["cau-Cyrl-entryname"] = {
remove_diacritics = cau_remove_diacritics,
from = cau_from,
to = cau_to,
}


s["cau-Cyrl-entryname"] = {
s["cau-Latn-entryname"] = {remove_diacritics = cau_remove_diacritics}
remove_diacritics = c.grave .. c.acute .. c.macron,
end
from = s["cau-Cyrl-displaytext"].from,
to = s["cau-Cyrl-displaytext"].to
}


s["cau-Latn-entryname"] = {remove_diacritics = c.grave .. c.acute .. c.macron}
-- Cyrs
do
local Cyrs_remove_diacritics = c.grave .. c.acute .. c.dotabove .. c.diaer .. c.invbreve .. c.palatalization .. c.dasiapneumata .. c.psilipneumata .. c.dottedgrave .. c.dottedacute .. c.kavyka


s["Cyrs-entryname"] = {remove_diacritics = c.grave .. c.acute ..  c.diaer .. c.kamora .. c.dasiapneumata .. c.psilipneumata}
s["Cyrs-entryname"] = {remove_diacritics = Cyrs_remove_diacritics}


s["Cyrs-sortkey"] = {
s["Cyrs-sortkey"] = {
from = {
remove_diacritics = Cyrs_remove_diacritics,
"ї", "оу", -- 2 chars
from = {
"ґ", "ꙣ", "є", "[ѕꙃꙅ]", "ꙁ", "[іꙇ]", "[ђꙉ]", "[ѻꙩꙫꙭꙮꚙꚛ]", "ꙋ", "[ѡѿꙍѽ]", "ꙑ", "ѣ", "ꙗ", "ѥ", "ꙕ", "[ѧꙙ]", "[ѩꙝ]", "ꙛ", "ѫ", "ѭ", "ѯ", "ѱ", "ѳ", "ѵ", "ҁ" -- 1 char
"ї", "оу", -- 2 chars
},
"[ґꙣєѕꙃꙅꙁіꙇђꙉѻꙩꙫꙭꙮꚙꚛꙋѡѿꙍѽꙑѣꙗѥꙕѧꙙѩꙝꙛѫѭѯѱѳѵҁ]"
to = {
},
"и" .. p[1], "у",
to = {
"г" .. p[1], "д" .. p[1], "е", "ж" .. p[1], "з", "и" .. p[1], "и" .. p[2], "о", "у", "х" .. p[1], "ы", "ь" .. p[1], "ь" .. p[2], "ь" .. p[3], "ю", "я", "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4], "я" .. p[5], "я" .. p[6], "я" .. p[7], "я" .. p[8], "я" .. p[9]
"и" .. p[1], "у", {
},
["ґ"] = "г" .. p[1], ["ꙣ"] = "д" .. p[1], ["є"] = "е", ["ѕ"] = "ж" .. p[1], ["ꙃ"] = "ж" .. p[1],
}
["ꙅ"] = "ж" .. p[1], ["ꙁ"] = "з", ["і"] = "и" .. p[1], ["ꙇ"] = "и" .. p[1], ["ђ"] = "и" .. p[2],
["ꙉ"] = "и" .. p[2], ["ѻ"] = "о", ["ꙩ"] = "о", ["ꙫ"] = "о", ["ꙭ"] = "о",
["ꙮ"] = "о", ["ꚙ"] = "о", ["ꚛ"] = "о", ["ꙋ"] = "у", ["ѡ"] = "х" .. p[1],
["ѿ"] = "х" .. p[1], ["ꙍ"] = "х" .. p[1], ["ѽ"] = "х" .. p[1], ["ꙑ"] = "ы", ["ѣ"] = "ь" .. p[1],
["ꙗ"] = "ь" .. p[2], ["ѥ"] = "ь" .. p[3], ["ꙕ"] = "ю", ["ѧ"] = "я", ["ꙙ"] = "я",
["ѩ"] = "я" .. p[1], ["ꙝ"] = "я" .. p[1], ["ꙛ"] = "я" .. p[2], ["ѫ"] = "я" .. p[3], ["ѭ"] = "я" .. p[4],
["ѯ"] = "я" .. p[5], ["ѱ"] = "я" .. p[6], ["ѳ"] = "я" .. p[7], ["ѵ"] = "я" .. p[8], ["ҁ"] = "я" .. p[9],
}
},
}
end


s["Grek-displaytext"] = {
s["Grek-displaytext"] = {
Line 229: Line 263:


s["Polyt-sortkey"] = s["Grek-sortkey"]
s["Polyt-sortkey"] = s["Grek-sortkey"]
-- Samr
do
s["Samr-entryname"] = {
remove_diacritics = c.CGJ .. u(0x0816) .. "-" .. u(0x082D),
}
s["Samr-sortkey"] = s["Samr-entryname"]
end


s["roa-oil-sortkey"] = {
s["roa-oil-sortkey"] = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove .. c.cedilla .. "'",
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'",
from = {"æ", "œ", "·"},
from = {"æ", "œ", "·"},
to = {"ae", "oe", " "}
to = {"ae", "oe", " "}
Line 244: Line 287:


s["wen-sortkey"] = {
s["wen-sortkey"] = {
from = {
from = {"ch", "[lłßꞩẜ]", "dz[" .. c.caron .. c.acute .. "]", "[bcefmnoprswz][" .. c.caron .. c.acute .. c.dotabove .. "]"},
"l", -- Ensure "l" comes after "ł".
"b́", "č", "ć", "dź", "ě", "f́", "ch", "ł", "ḿ", "ń", "ó", "ṕ", "ř", "ŕ", "š", "ś", "ẃ", "ž", "ż", "ź"
},
to = {
to = {
"l" .. p[1],
"h" .. p[1],
"b" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e" .. p[1], "f" .. p[1], "h" .. p[1], "l", "m" .. p[1], "n" .. p[1], "o" .. p[1], "p" .. p[1], "r" .. p[1], "r" .. p[2], "s" .. p[1], "s" .. p[2], "w" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]
{
["l"] = "l" .. p[1], ["ł"] = "l", ["ß"] = "s", ["ꞩ"] = "š", ["ẜ"] = "š",
},
{
["dz" .. c.caron] = "d" .. p[1], ["dz" .. c.acute] = "d" .. p[2]
},
{
["b" .. c.acute] = "b" .. p[1],
["c" .. c.caron] = "c" .. p[1], ["c" .. c.acute] = "c" .. p[2],
["e" .. c.caron] = "e" .. p[1], ["e" .. c.dotabove] = "e" .. p[1],
["f" .. c.acute] = "f" .. p[1],
["m" .. c.acute] = "m" .. p[1],
["n" .. c.acute] = "n" .. p[1],
["o" .. c.acute] = "o" .. p[1],
["p" .. c.acute] = "p" .. p[1],
["r" .. c.caron] = "r" .. p[1], ["r" .. c.acute] = "r" .. p[2],
["s" .. c.caron] = "s" .. p[1], ["s" .. c.acute] = "s" .. p[2],
["w" .. c.acute] = "w" .. p[1],
["z" .. c.caron] = "z" .. p[1], ["z" .. c.acute] = "z" .. p[2],
}
}
}
}
}
Line 256: Line 315:
export.shared = s
export.shared = s


-- Short-term solution to override the standard substitution process, by forcing the module to substitute the entire text in one pass. This results in any PUA characters that are used as stand-ins for formatting being handled by the language-specific substitution process, which is usually undesirable.
-- Short-term solution to override the standard substitution process, by forcing the module to substitute the entire text in one pass, if "cont" is given. This results in any PUA characters that are used as stand-ins for formatting being handled by the language-specific substitution process, which is usually undesirable. If the value is "none" then the formatting tags do not get turned into PUA characters in the first place.
-- This override is provided for languages which use formatting between strings of text which might need to interact with each other (e.g. Korean 값이 transliterates as "gaps-i", but [[값]] has the formatting '''값'''[[-이]]. The normal process would split the text at the second '''.)
-- This override is provided for languages which use formatting between strings of text which might need to interact with each other (e.g. Korean 값이 transliterates as "gaps-i", but [[값]] has the formatting '''값'''[[-이]]. The normal process would split the text at the second '''.)
export.contiguous_substitution = {
export.substitution = {
["gmy"] = "tr",
["gmy"] = "none",
["ja"] = "tr",
["ja"] = "cont",
["jje"] = "tr",
["jje"] = "cont",
["ko"] = "tr",
["ko"] = "cont",
["ko-ear"] = "tr",
["ko-ear"] = "cont",
["ru"] = "tr",
["ru"] = "cont",
["th-new"] = "tr",
["th-new"] = "cont",
["sa"] = "tr",
["sa"] = "cont",
["zkt"] = "tr",
["zkt"] = "cont",
}
}


Line 276: Line 335:
-- [[Special:WhatLinksHere/Wiktionary:Tracking/languages/RL.]] for the `RL.` alias.
-- [[Special:WhatLinksHere/Wiktionary:Tracking/languages/RL.]] for the `RL.` alias.
export.aliases = {
export.aliases = {
["CL."] = "la-cla",
["EL."] = "la-ecc",
["EL."] = "la-ecc",
["LL."] = "la-lat",
["LL."] = "la-lat",
["ML."] = "la-med",
["ML."] = "la-med",
["NL."] = "la-new",
["NL."] = "la-new",
["RL."] = "la-ren",
["VL."] = "la-vul",
["VL."] = "la-vul",
["prv"] = "oc-pro",
["nds-DE"] = "nds-de",
["nan-hnm"] = "hnm",
["nds-NL"] = "nds-nl",
["nan-luh"] = "luh",
["roa-oan"] = "roa-ona",
}
}


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