Module:languages/data - Revision history

Sware: Undo revision 493285 by Sware (talk)

2026-04-08T17:40:36Z

Undo revision 493285 by Sware (talk)

Show changes

Sware at 17:29, 8 April 2026

2026-04-08T17:29:02Z

Show changes

Sware at 14:46, 13 April 2025

2025-04-13T14:46:06Z

Show changes

Sware at 18:51, 11 January 2025

2025-01-11T18:51:46Z

← Older revision		Revision as of 18:51, 11 January 2025
Line 19:		Line 19:
	dotabove = u(0x0307),		dotabove = u(0x0307),
	diaer = u(0x0308),		diaer = u(0x0308),
			hook = u(0x0309),
	ringabove = u(0x030A),		ringabove = u(0x030A),
	dacute = u(0x030B),		dacute = u(0x030B),

Sware at 18:50, 11 January 2025

2025-01-11T18:50:16Z

← Older revision		Revision as of 18:50, 11 January 2025
Line 33:		Line 33:
	ogonek = u(0x0328),		ogonek = u(0x0328),
	brevebelow = u(0x032E),		brevebelow = u(0x032E),
			tildebelow = u(0x0330),
	macronbelow = u(0x0331),		macronbelow = u(0x0331),
	perispomeni = u(0x0342),		perispomeni = u(0x0342),

Sware at 16:08, 11 January 2025

2025-01-11T16:08:56Z

Show changes

Sware at 10:58, 6 August 2024

2024-08-06T10:58:33Z

← Older revision		Revision as of 10:58, 6 August 2024
Line 1:		Line 1:
			local m_scripts = require("Module:scripts")

	local table = table		local table = table
	local insert = table.insert		local insert = table.insert
Line 34:		Line 36:
	ypogegrammeni = u(0x0345),		ypogegrammeni = u(0x0345),
	CGJ = u(0x034F), -- combining grapheme joiner		CGJ = u(0x034F), -- combining grapheme joiner
			zigzag = u(0x035B),
	dbrevebelow = u(0x035C),		dbrevebelow = u(0x035C),
			dmacron = u(0x035E),
			dtilde = u(0x0360),
	dinvbreve = u(0x0361),		dinvbreve = u(0x0361),
			small_a = u(0x0363),
	small_e = u(0x0364),		small_e = u(0x0364),
			small_i = u(0x0365),
			small_o = u(0x0366),
			small_u = u(0x0367),
	kamora = u(0x0484),		kamora = u(0x0484),
	dasiapneumata = u(0x0485),		dasiapneumata = u(0x0485),
Line 60:		Line 69:
	VS01 = u(0xFE00), -- variation selector 1		VS01 = u(0xFE00), -- variation selector 1
	-- Punctuation for the standardChars field.		-- Punctuation for the standardChars field.
	punc = " ',%-~~–…∅~~"		-- Note: characters are literal (i.e. no magic characters).
			punc = " ',-‐‑‒–—…∅",
			-- Range covering all diacritics.
			diacritics = u(0x300) .. "-" .. u(0x34E) ..
			u(0x350) .. "-" .. u(0x36F) ..
			u(0x1AB0) .. "-" .. u(0x1ACE) ..
			u(0x1DC0) .. "-" .. u(0x1DFF) ..
			u(0x20D0) .. "-" .. u(0x20F0) ..
			u(0xFE20) .. "-" .. u(0xFE2F),
	}		}
	-- Braille characters for the standardChars field.		-- Braille characters for the standardChars field.
Line 108:		Line 125:

	s["Grek-sortkey"] = {		s["Grek-sortkey"] = {
	remove_diacritics = c.grave .. c.acute .. c.diaer .. c.caron .. c.commaabove .. c.revcommaabove .. c.diaerbelow .. c.brevebelow .. c.perispomeni .. c.ypogegrammeni,		remove_diacritics = c.grave .. c.acute .. c.diaer .. c.caron .. c.commaabove .. c.revcommaabove .. c.macron .. c.breve .. c.diaerbelow .. c.brevebelow .. c.perispomeni .. c.ypogegrammeni,
	from = {"ϝ", "ͷ", "ϛ", "ͱ", "ϻ", "ϟ", "ϙ", "ς", "ϡ", "ͳ"},		from = {"ϝ", "ͷ", "ϛ", "ͱ", "ϻ", "ϟ", "ϙ", "ς", "ϡ", "ͳ"},
	to = {"ε" .. p[1], "ε" .. p[2], "ε" .. p[3], "ζ" .. p[1], "π" .. p[1], "π" .. p[2], "π" .. p[2], "σ", "ω" .. p[1], "ω" .. p[1]}		to = {"ε" .. p[1], "ε" .. p[2], "ε" .. p[3], "ζ" .. p[1], "π" .. p[1], "π" .. p[2], "π" .. p[2], "σ", "ω" .. p[1], "ω" .. p[1]}
	}		}

	s["Jpan-sortkey"] = {		s["Jpan-standardchars"] = -- exclude ぢづヂヅ
			"ぁあぃいぅうぇえぉおかがきぎくぐけげこごさざしじすずせぜそぞただちっつてでとどなにぬねのはばぱひびぴふぶぷへべぺほぼぽまみむめもゃやゅゆょよらりるれろん" ..
			"ァアィイゥウェエォオカガキギクグケゲコゴサザシジスズセゼソゾタダチッツテデトドナニヌネノハバパヒビピフブプヘベペホボポマミムメモャヤュユョヨラリルレロン"

			local jpx_displaytext = {
			from = {"～", "＝"},
			to = {"〜", "゠"}
			}

			s["jpx-displaytext"] = {
			Jpan = jpx_displaytext,
			Hani = jpx_displaytext,
			Hrkt = jpx_displaytext,
			Hira = jpx_displaytext,
			Kana = jpx_displaytext
			-- not Latn or Brai
			}

			s["jpx-entryname"] = s["jpx-displaytext"]

			s["jpx-sortkey"] = {
	Jpan = "Jpan-sortkey",		Jpan = "Jpan-sortkey",
	Hani = "Hani-sortkey",		Hani = "Hani-sortkey",
	Hrkt = "Hira-sortkey", -- sort general kana by normalizing to Hira		Hrkt = "Hira-sortkey", -- sort general kana by normalizing to Hira
	Hira = "Hira-sortkey",		Hira = "Hira-sortkey",
	Kana = "Kana-sortkey"		Kana = "Kana-sortkey",
			Latn = {remove_diacritics = c.tilde .. c.macron .. c.diaer}
	}		}

	s["~~Jpan~~-translit"] = {		s["jpx-translit"] = {
	Hrkt = "Hrkt-translit",		Hrkt = "Hrkt-translit",
	Hira = "Hrkt-translit",		Hira = "Hrkt-translit",
Line 127:		Line 165:
	}		}

	local HaniChars = ~~require("Module:scripts")~~.getByCode("Hani"):getCharacters()		local HaniChars = m_scripts.getByCode("Hani"):getCharacters()
	-- `漢字(한자)`→`漢字`		-- `漢字(한자)`→`漢字`
	-- `가-나-다`→`가나다`		-- `가-나-다`→`가나다`, `가--나--다`→`가-나-다`
	-- `온돌(溫突/溫堗)`→`온돌` ([[ondol]])		-- `온돌(溫突/溫堗)`→`온돌` ([[ondol]])
	s["Kore-entryname"] = {		s["Kore-entryname"] = {
	remove_diacritics = u(0x302E) .. u(0x302F),		remove_diacritics = u(0x302E) .. u(0x302F),
	from = {"([" .. HaniChars .. "])%(.-%)", "(.)%-(.)", "%([" .. HaniChars .. "/]+%)"},		from = {"([" .. HaniChars .. "])%(.-%)", "^%-", "%-$", "%-(%-?)", "\1", "%([" .. HaniChars .. "/]+%)"},
	to = {"%1", "%1%2"}		to = {"%1", "\1", "\1", "%1", "-"}
	}		}

Sware at 21:28, 1 July 2024

2024-07-01T21:28:11Z

@@ Line 1: / Line 1: @@
-local u = mw.ustring.char
+local table = table
 local export = {}
 -- UTF-8 encoded strings for some commonly-used diacritics.
 local c = {
@@ Line 63: / Line 36: @@
 	dbrevebelow		= u(0x035C),
 	dinvbreve		= u(0x0361),
 	kamora          = u(0x0484),
 	dasiapneumata   = u(0x0485),
@@ Line 91: / Line 65: @@
 local braille = {}
 for i = 0x2800, 0x28FF do
-	table.insert(braille, u(i))
+	insert(braille, u(i))
 end
 c.braille = table.concat(braille)
@@ Line 135: / Line 109: @@
 s["Grek-sortkey"] = {
 	remove_diacritics = c.grave .. c.acute .. c.diaer .. c.caron .. c.commaabove .. c.revcommaabove .. c.diaerbelow .. c.brevebelow .. c.perispomeni .. c.ypogegrammeni,
-	from = {"ς"},
+	from = {"ϝ", "ͷ", "ϛ", "ͱ", "ϻ", "ϟ", "ϙ", "ς", "ϡ", "ͳ"},
-	to = {"σ"}
+	to = {"ε" .. p[1], "ε" .. p[2], "ε" .. p[3], "ζ" .. p[1], "π" .. p[1], "π" .. p[2], "π" .. p[2], "σ", "ω" .. p[1], "ω" .. p[1]}
+}
 local HaniChars = require("Module:scripts").getByCode("Hani"):getCharacters()
 s["Kore-entryname"] = {
 	remove_diacritics = u(0x302E) .. u(0x302F),
-	from = {"([" .. HaniChars .. "])%(.-%)", "(.)%-(.)", "%([" .. HaniChars .. "]+%)"},
+	from = {"([" .. HaniChars .. "])%(.-%)", "(.)%-(.)", "%([" .. HaniChars .. "/]+%)"},
 	to = {"%1", "%1%2"}
+}
 s["Mong-displaytext"] = {
-	from = {"([ᠨ-ᡂᡸ])ᠶ([ᠨ-ᡂᡸ])", "([ᠠ-ᡂᡸ])ᠸ([^ᠠ-ᠧ])", "([ᠠ-ᡂᡸ])ᠸ$"},
+	from = {"([ᠨ-ᡂᡸ])ᠶ([ᠨ-ᡂᡸ])", "([ᠠ-ᡂᡸ])ᠸ([^᠋ᠠ-ᠧ])", "([ᠠ-ᡂᡸ])ᠸ$"},
 	to = {"%1ᠢ%2", "%1ᠧ%2", "%1ᠧ"}
+}
 s["Mong-entryname"] = s["Mong-displaytext"]
 s["roa-oil-sortkey"] = {
@@ Line 185: / Line 187: @@
 	["jje"] = "tr",
 	["ko"] = "tr",
 	["ru"] = "tr",
+}
 return export

Sware: Created page with "local u = mw.ustring.char local export = {} --[=[ Here is a list of the language fields by order of frequency according to User:Erutuon/language_stuff. If the order changes, change the order here for potentially greater efficiency. local fields = { "canonical_name", "wikidata_item", "family", "scripts", "other_names", "ancestors", "type", "translit", "entry_name", "sort_key", "override_translit", "wikimedia_codes", "standard_chars", "wikipedia_article..."

2023-06-18T12:55:11Z

Created page with "local u = mw.ustring.char local export = {} --[=[ Here is a list of the language fields by order of frequency according to User:Erutuon/language_stuff. If the order changes, change the order here for potentially greater efficiency. local fields = { "canonical_name", "wikidata_item", "family", "scripts", "other_names", "ancestors", "type", "translit", "entry_name", "sort_key", "override_translit", "wikimedia_codes", "standard_chars", "wikipedia_article..."

New page

local u = mw.ustring.char
local export = {}

--[=[
Here is a list of the language fields by order of frequency according to [[User:Erutuon/language_stuff]].
If the order changes, change the order here for potentially greater efficiency.

local fields = {
"canonical_name",
"wikidata_item",
"family",
"scripts",
"other_names",
"ancestors",
"type",
"translit",
"entry_name",
"sort_key",
"override_translit",
"wikimedia_codes",
"standard_chars",
"wikipedia_article",
"link_tr",
}

--[=[
Insert the fields into the table with their values as their frequency ranking.
{export.most_common_field = 1, export.second_most_common_field = 2, ... }

for i, field in ipairs(fields) do
export[field] = i
end
]=]
-- UTF-8 encoded strings for some commonly-used diacritics.
local c = {
grave = u(0x0300),
acute = u(0x0301),
circ = u(0x0302),
tilde = u(0x0303),
macron = u(0x0304),
overline = u(0x0305),
breve = u(0x0306),
dotabove = u(0x0307),
diaer = u(0x0308),
ringabove = u(0x030A),
dacute = u(0x030B),
caron = u(0x030C),
lineabove = u(0x030D),
dgrave = u(0x030F),
invbreve = u(0x0311),
commaabove = u(0x0313),
revcommaabove = u(0x0314),
dotbelow = u(0x0323),
diaerbelow = u(0x0324),
ringbelow = u(0x0325),
cedilla = u(0x0327),
ogonek = u(0x0328),
brevebelow = u(0x032E),
macronbelow = u(0x0331),
perispomeni = u(0x0342),
ypogegrammeni = u(0x0345),
CGJ = u(0x034F), -- combining grapheme joiner
dbrevebelow = u(0x035C),
dinvbreve = u(0x0361),
kamora = u(0x0484),
dasiapneumata = u(0x0485),
psilipneumata = u(0x0486),
kashida = u(0x0640),
fathatan = u(0x064B),
dammatan = u(0x064C),
kasratan = u(0x064D),
fatha = u(0x064E),
damma = u(0x064F),
kasra = u(0x0650),
shadda = u(0x0651),
sukun = u(0x0652),
hamzaabove = u(0x0654),
nunghunna = u(0x0658),
smallv = u(0x065A),
superalef = u(0x0670),
psili = u(0x1FBD),
coronis = u(0x1FBF),
ZWNJ = u(0x200C), -- zero width non-joiner
ZWJ = u(0x200D), -- zero width joiner
RSQuo = u(0x2019), -- right single quote
VS01 = u(0xFE00), -- variation selector 1
-- Punctuation for the standardChars field.
punc = " ',%-–…∅"
}
-- Braille characters for the standardChars field.
local braille = {}
for i = 0x2800, 0x28FF do
table.insert(braille, u(i))
end
c.braille = table.concat(braille)
export.chars = c

-- PUA characters, generally used in sortkeys.
-- Note: if the limit needs to be increased, do so in powers of 2 (due to the way memory is allocated for tables).
local p = {}
for i = 1, 32 do
p[i] = u(0xF000+i-1)
end
export.puaChars = p

local s = {}
-- 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"] = {
from = {"[IlІӀ]", "ᴴ"},
to = {"ӏ", "ᵸ"}
}

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

s["cau-Latn-entryname"] = {remove_diacritics = c.grave .. c.acute .. c.macron}

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

s["Cyrs-sortkey"] = {
from = {
"ї", "оу", -- 2 chars
"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
},
to = {
"и" .. p[1], "у",
"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]
},
}

s["Grek-sortkey"] = {
remove_diacritics = c.grave .. c.acute .. c.diaer .. c.caron .. c.commaabove .. c.revcommaabove .. c.diaerbelow .. c.brevebelow .. c.perispomeni .. c.ypogegrammeni,
from = {"ς"},
to = {"σ"}
}

local HaniChars = require("Module:scripts").getByCode("Hani"):getCharacters()
s["Kore-entryname"] = {
remove_diacritics = u(0x302E) .. u(0x302F),
from = {"([" .. HaniChars .. "])%(.-%)", "(.)%-(.)", "%([" .. HaniChars .. "]+%)"},
to = {"%1", "%1%2"}
}

s["Mong-displaytext"] = {
from = {"([ᠨ-ᡂᡸ])ᠶ([ᠨ-ᡂᡸ])", "([ᠠ-ᡂᡸ])ᠸ([^ᠠ-ᠧ])", "([ᠠ-ᡂᡸ])ᠸ$"},
to = {"%1ᠢ%2", "%1ᠧ%2", "%1ᠧ"}
}

s["Mong-entryname"] = s["Mong-displaytext"]

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

s["Tibt-displaytext"] = {
from = {"ༀ", "༌", "།།", "༚༚", "༚༝", "༝༚", "༝༝", "ཷ", "ཹ", "ེེ", "ོོ"},
to = {"ཨོཾ", "་", "༎", "༛", "༟", "࿎", "༞", "ྲཱྀ", "ླཱྀ", "ཻ", "ཽ"}
}

s["Tibt-entryname"] = s["Tibt-displaytext"]

s["wen-sortkey"] = {
from = {
"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 = {
"l" .. 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]
}
}

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.
-- 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 = {
["ja"] = "tr",
["jje"] = "tr",
["ko"] = "tr",
["ru"] = "tr",
}

return export