Модул:headword/data

Аз Wiktionary

Documentation for this module may be created at Модул:headword/data/doc

local data = {}
local u = mw.ustring.char
local rsubn = mw.ustring.gsub
-- Version of rsubn() that discards all but the first return value.
local function rsub(term, foo, bar)
	return (rsubn(term, foo, bar))
end

local function track(track_id)
	local tracking_page = "headword/" .. track_id
	local m_debug_track = require("Module:debug/track")
	m_debug_track(tracking_page)
	return true
end

------ 1. Lists that will be converted into sets. ------

data.invariable = {
	"cmavo",
	"cmene",
	"fu'ivla",
	"gismu",
	"Han tu",
	"hanja",
	"hanzi",
	"jyutping",
	"kanji",
	"lujvo",
	"phrasebook",
	"pinyin",
	"rafsi",
	"romaji",
}

data.lemmas = {
	"abbreviations",
	"acronyms",
	"adjectives",
	"adnominals",
	"adpositions",
	"adverbs",
	"affixes",
	"ambipositions",
	"articles",
	"circumfixes",
	"circumpositions",
	"classifiers",
	"cmavo",
	"cmavo clusters",
	"cmene",
	"combining forms",
	"conjunctions",
	"counters",
	"determiners",
	"diacritical marks",
	"equative adjectives",
	"fu'ivla",
	"gismu",
	"Han characters",
	"Han tu",
	"hanja",
	"hanzi",
	"ideophones",
	"idioms",
	"infixes",
	"initialisms",
	"interfixes",
	"interjections",
	"kanji",
	"letters",
	"ligatures",
	"logograms",
	"lujvo",
	"morphemes",
	"non-constituents",
	"nouns",
	"numbers",
	"numeral symbols",
	"numerals",
	"particles",
	"phrases",
	"postpositions",
	"postpositional phrases",
	"predicatives",
	"prefixes",
	"prepositional phrases",
	"prepositions",
	"preverbs",
	"pronominal adverbs",
	"pronouns",
	"proper nouns",
	"proverbs",
	"punctuation marks",
	"relatives",
	"roots",
	"stems",
	"suffixes",
	"syllables",
	"symbols",
	"verbs",
}

data.nonlemmas = {
	"active participle forms",
	"active participles",
	"adjectival participles",
	"adjective forms",
	"adjective feminine forms",
	"adjective plural forms",
	"adverb forms",
	"adverbial participles",
	"agent participles",
	"article forms",
	"circumfix forms",
	"combined forms",
	"comparative adjective forms",
	"comparative adjectives",
	"comparative adverb forms",
	"comparative adverbs",
	"conjunction forms",
	"contractions",
	"converbs",
	"determiner comparative forms",
	"determiner forms",
	"determiner superlative forms",
	"diminutive nouns",
	"equative adjective forms",
	"equative adjectives",
	"future participles",
	"gerunds",
	"infinitive forms",
	"infinitives",
	"interjection forms",
	"jyutping",
	"kanji readings",
	"misspellings",
	"negative participles",
	"nominal participles",
	"noun case forms",
	"noun dual forms",
	"noun forms",
	"noun paucal forms",
	"noun plural forms",
	"noun possessive forms",
	"noun singulative forms",
	"numeral forms",
	"participles",
	"participle forms",
	"particle forms",
	"passive participles",
	"past active participles",
	"past participles",
	"past participle forms",
	"past passive participles",
	"perfect active participles",
	"perfect participles",
	"perfect passive participles",
	"pinyin",
	"plurals",
	"postposition forms",
	"prefix forms",
	"preposition contractions",
	"preposition forms",
	"prepositional pronouns",
	"present active participles",
	"present participles",
	"present passive participles",
	"pronoun forms",
	"pronoun possessive forms",
	"proper noun forms",
	"proper noun plural forms",
	"rafsi",
	"romanizations",
	"root forms",
	"singulatives",
	"suffix forms",
	"superlative adjective forms",
	"superlative adjectives",
	"superlative adverb forms",
	"superlative adverbs",
	"verb forms",
	"verbal nouns",
}

-- These langauges will not have links to separate parts of the headword.
data.no_multiword_links = {
	"zh",
}

-- These languages will not have "LANG multiword terms" categories added.
data.no_multiword_cat = {
	-------- Languages without spaces between words (sometimes spaces between phrases) --------
	"blt", -- Tai Dam
	"ja", -- Japanese
	"khb", -- Lü
	"km", -- Khmer
	"lo", -- Lao
	"mnw", -- Mon
	"my", -- Burmese
	"nan", -- Min Nan (some words in Latin script; hyphens between syllables)
	"nod", -- Northern Thai
	"ojp", -- Old Japanese
	"shn", -- Shan
	"sou", -- Southern Thai
	"tdd", -- Tai Nüa
	"th", -- Thai
	"tts", -- Isan
	"twh", -- Tai Dón
	"txg", -- Tangut
	"zh", -- Chinese (all varieties with Chinese characters)
	"zkt", -- Khitan

	-------- Languages with spaces between syllables --------
	"ahk", -- Akha
	"aou", -- A'ou
	"atb", -- Zaiwa
	"byk", -- Biao
	"cdy", -- Chadong
	--"duu", -- Drung; not sure
	--"hmx-pro", -- Proto-Hmong-Mien
	--"hnj", -- Green Hmong; not sure
	"huq", -- Tsat
	"ium", -- Iu Mien
	--"lis", -- Lisu; not sure
	"mtq", -- Muong
	--"mww", -- White Hmong; not sure
	"onb", -- Lingao
	--"sit-gkh", -- Gokhy; not sure
	--"swi", -- Sui; not sure
	"tbq-lol-pro", -- Proto-Loloish
	"tdh", -- Thulung
	"ukk", -- Muak Sa-aak
	"vi", -- Vietnamese
	"yig", -- Wusa Nasu
	"zng", -- Mang

	-------- Languages with ~ with surrounding spaces used to separate variants --------
	"mkh-ban-pro", -- Proto-Bahnaric
	"sit-pro", -- Proto-Sino-Tibetan; listed above

	-------- Other weirdnesses --------
	"mul", -- Translingual; gestures, Morse code, etc.
	"aot", -- Atong (India); bullet is a letter

	-------- All sign languages	--------
	"ads",
	"aed",
	"aen",
	"afg",
	"ase",
	"asf",
	"asp",
	"asq",
	"asw",
	"bfi",
	"bfk",
	"bog",
	"bqn",
	"bqy",
	"bvl",
	"bzs",
	"cds",
	"csc",
	"csd",
	"cse",
	"csf",
	"csg",
	"csl",
	"csn",
	"csq",
	"csr",
	"doq",
	"dse",
	"dsl",
	"ecs",
	"esl",
	"esn",
	"eso",
	"eth",
	"fcs",
	"fse",
	"fsl",
	"fss",
	"gds",
	"gse",
	"gsg",
	"gsm",
	"gss",
	"gus",
	"hab",
	"haf",
	"hds",
	"hks",
	"hos",
	"hps",
	"hsh",
	"hsl",
	"icl",
	"iks",
	"ils",
	"inl",
	"ins",
	"ise",
	"isg",
	"isr",
	"jcs",
	"jhs",
	"jls",
	"jos",
	"jsl",
	"jus",
	"kgi",
	"kvk",
	"lbs",
	"lls",
	"lsl",
	"lso",
	"lsp",
	"lst",
	"lsy",
	"lws",
	"mdl",
	"mfs",
	"mre",
	"msd",
	"msr",
	"mzc",
	"mzg",
	"mzy",
	"nbs",
	"ncs",
	"nsi",
	"nsl",
	"nsp",
	"nsr",
	"nzs",
	"okl",
	"pgz",
	"pks",
	"prl",
	"prz",
	"psc",
	"psd",
	"psg",
	"psl",
	"pso",
	"psp",
	"psr",
	"pys",
	"rms",
	"rsl",
	"rsm",
	"sdl",
	"sfb",
	"sfs",
	"sgg",
	"sgx",
	"slf",
	"sls",
	"sqk",
	"sqs",
	"ssp",
	"ssr",
	"svk",
	"swl",
	"syy",
	"tse",
	"tsm",
	"tsq",
	"tss",
	"tsy",
	"tza",
	"ugn",
	"ugy",
	"ukl",
	"uks",
	"vgt",
	"vsi",
	"vsl",
	"vsv",
	"xki",
	"xml",
	"xms",
	"ygs",
	"ysl",
	"zib",
	"zsl",
}

-- In these languages, the hyphen is not considered a word separator for the "multiword terms" category.
data.hyphen_not_multiword_sep = {
	"akk", -- Akkadian; hyphens between syllables
	"akl", -- Aklanon; hyphens for mid-word glottal stops
	"ber-pro", -- Proto-Berber; morphemes separated by hyphens
	"ceb", -- Cebuano; hyphens for mid-word glottal stops
	"cnk", -- Khumi Chin; hyphens used in single words
	"cpi", -- Chinese Pidgin English; Chinese-derived words with hyphens between syllables
	"de", -- too many false positives
	"esx-esk-pro", -- hyphen used to separate morphemes
	"fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively
	"hil", -- Hiligaynon; hyphens for mid-word glottal stops
	"ilo", -- Ilocano; hyphens for mid-word glottal stops
	"lcp", -- Western Lawa; dash as syllable joiner
	"lwl", -- Eastern Lawa; dash as syllable joiner
	"mfa", -- Pattani Malay in Thai script; dash as syllable joiner
	"mkh-vie-pro", -- Proto-Vietic; morphemes separated by hyphens
	"msb", -- Masbatenyo; too many false positives
	"tl", -- Tagalog; too many false positives
	"war", -- Waray-Waray; too many false positives
	"yo", -- Yoruba; hyphens used to show lengthened nasal vowels
}

-- These languages will not have "LANG masculine nouns" and similar categories added.
data.no_gender_cat = {
	-- Languages without gender but which use the gender field for other purposes
	"ja",
	"th",
}

data.notranslit = {
	"ams",
	"az",
	"bbc",
	"bug",
	"cia",
	"cjm",
	"cmn",
	"hak",
	"ja",
	"kzg",
	"lad",
	"lzh",
	"ms",
	"mul",
	"mvi",
	"nan",
	"oj",
	"okn",
	"ro",
	"ryn",
	"rys",
	"ryu",
	"sh",
	"tgt",
	"th",
	"tkn",
	"tly",
	"txg",
	"und",
	"vi",
	"xug",
	"yoi",
	"yox",
	"yue",
	"za",
	"zh",
}

-- Script codes for which a script-tagged display title will be added.
data.toBeTagged = {
	"Ahom",
	"Arab",
		"fa-Arab",
		"glk-Arab",
		"kk-Arab",
		"ks-Arab",
		"ku-Arab",
		"mzn-Arab",
		"ms-Arab",
		"ota-Arab",
		"pa-Arab",
		"ps-Arab",
		"sd-Arab",
		"tt-Arab",
		"ug-Arab",
		"ur-Arab",
	"Armi",
	"Armn",
	"Avst",
	"Bali",
	"Bamu",
	"Batk",
	"Beng",
		"as-Beng",
	"Bopo",
	"Brah",
	"Brai",
	"Bugi",
	"Buhd",
	"Cakm",
	"Cans",
	"Cari",
	"Cham",
	"Cher",
	"Copt",
	"Cprt",
	"Cyrl",
	"Cyrs",
	"Deva",
	"Dsrt",
	"Egyd",
	"Egyp",
	"Ethi",
	"Geok",
	"Geor",
	"Glag",
	"Goth",
	"Grek",
		"polytonic",
	"Gujr",
	"Guru",
	"Hang",
	"Hani",
	"Hano",
	"Hebr",
	"Hira",
	"Hluw",
	"Ital",
	"Java",
	"Kali",
	"Kana",
	"Khar",
	"Khmr",
	"Knda",
	"Kthi",
	"Lana",
	"Laoo",
	"Latn",
		"Latf",
		"Latg",
		"Latinx",
		"nv-Latn",
		"pjt-Latn",
	"Lepc",
	"Limb",
	"Linb",
	"Lisu",
	"Lyci",
	"Lydi",
	"Mand",
	"Mani",
	"Merc",
	"Mero",
	"Mlym",
	"Mong",
		"mnc-Mong",
		"sjo-Mong",
		"xwo-Mong",
	"Mtei",
	"Mymr",
	"Narb",
	"Nkoo",
	"Ogam",
	"Olck",
	"Orkh",
	"Orya",
	"Osma",
	"Palm",
	"Phag",
	"Phli",
	"Phlv",
	"Phnx",
	"Plrd",
	"Prti",
	"Rjng",
	"Runr",
	"Samr",
	"Sarb",
	"Saur",
	"Sgnw",
	"Shaw",
	"Shrd",
	"Sinh",
	"Sora",
	"Sund",
	"Sylo",
	"Syrc",
	"Tagb",
	"Tale",
	"Talu",
	"Taml",
	"Tang",
	"Tavt",
	"Telu",
	"Tfng",
	"Tglg",
	"Thaa",
	"Thai",
	"Tibt",
		"xzh-Tibt",
	"Ugar",
	"Vaii",
	"Xpeo",
	"Xsux",
	"Yiii",
	"Zmth",
	"Zsym",

	"IPAchar",
	"musical",
	"Ruminumerals",
}

-- Parts of speech which will not be categorised in categories like "English terms spelled with É" if
-- the term is the character in question (e.g. the letter entry for English [[é]]). This contrasts with
-- entries like the French adjective [[m̂]], which is a one-letter word spelled with the letter.
data.pos_not_spelled_with_self = {
	"diacritical marks",
	"Han characters",
	"Han tu",
	"hanja",
	"hanzi",
	"kanji",
	"letters",
	"ligatures",
	"logograms",
	"numeral symbols",
	"numerals",
	"symbols",
}

-- Convert lists into sets.
for key, list in pairs(data) do
	data[key] = {}
	for _, item in ipairs(list) do
		data[key][item] = true
	end
end

------ 2. Lists that will not be converted into sets. ------

-- Parts of speech for which categories like "German masculine nouns" or "Russian imperfective verbs"
-- will be generated if the headword is of the appropriate gender/number.
data.pos_for_gender_number_cat = {
	["nouns"] = "nouns",
	["proper nouns"] = "nouns",
	["suffixes"] = "suffixes",
	-- We include verbs because impf and pf are valid "genders".
	["verbs"] = "verbs",
}

-- Combining character data used when categorising unusual characters. These resolve into two patterns, used to find single combining characters (i.e. character + diacritic(s)) or double combining characters (i.e. character + diacritic(s) + character).
local comb_chars = {
	single = {
		{0x0300, 0x034E},
		-- Exclude combining grapheme joiner.
		{0x0350, 0x035B},
		{0x0363, 0x036F},
		{0x0483, 0x0489},
		{0x0591, 0x05BD},
		{0x05BF},
		{0x05C1, 0x05C2},
		{0x05C4, 0x05C5},
		{0x05C7},
		{0x0610, 0x061A},
		{0x064B, 0x065F},
		{0x0670},
		{0x06D6, 0x06DC},
		{0x06DF, 0x06E4},
		{0x06E7, 0x06E8},
		{0x06EA, 0x06ED},
		{0x0711},
		{0x0730, 0x074A},
		{0x07A6, 0x07B0},
		{0x07EB, 0x07F3},
		{0x07FD},
		{0x0816, 0x0819},
		{0x081B, 0x0823},
		{0x0825, 0x0827},
		{0x0829, 0x082D},
		{0x0859, 0x085B},
		{0x0898, 0x089F},
		{0x08CA, 0x08E1},
		{0x08E3, 0x0902},
		{0x093A},
		{0x093C},
		{0x0941, 0x0948},
		{0x094D},
		{0x0951, 0x0957},
		{0x0962, 0x0963},
		{0x0981},
		{0x09BC},
		{0x09C1, 0x09C4},
		{0x09CD},
		{0x09E2, 0x09E3},
		{0x09FE},
		{0x0A01, 0x0A02},
		{0x0A3C},
		{0x0A41, 0x0A42},
		{0x0A47, 0x0A48},
		{0x0A4B, 0x0A4D},
		{0x0A51},
		{0x0A70, 0x0A71},
		{0x0A75},
		{0x0A81, 0x0A82},
		{0x0ABC},
		{0x0AC1, 0x0AC5},
		{0x0AC7, 0x0AC8},
		{0x0ACD},
		{0x0AE2, 0x0AE3},
		{0x0AFA, 0x0AFF},
		{0x0B01},
		{0x0B3C},
		{0x0B3F},
		{0x0B41, 0x0B44},
		{0x0B4D},
		{0x0B55, 0x0B56},
		{0x0B62, 0x0B63},
		{0x0B82},
		{0x0BC0},
		{0x0BCD},
		{0x0C00},
		{0x0C04},
		{0x0C3C},
		{0x0C3E, 0x0C40},
		{0x0C46, 0x0C48},
		{0x0C4A, 0x0C4D},
		{0x0C55, 0x0C56},
		{0x0C62, 0x0C63},
		{0x0C81},
		{0x0CBC},
		{0x0CBF},
		{0x0CC6},
		{0x0CCC, 0x0CCD},
		{0x0CE2, 0x0CE3},
		{0x0D00, 0x0D01},
		{0x0D3B, 0x0D3C},
		{0x0D41, 0x0D44},
		{0x0D4D},
		{0x0D62, 0x0D63},
		{0x0D81},
		{0x0DCA},
		{0x0DD2, 0x0DD4},
		{0x0DD6},
		{0x0E31},
		{0x0E34, 0x0E3A},
		{0x0E47, 0x0E4E},
		{0x0EB1},
		{0x0EB4, 0x0EBC},
		{0x0EC8, 0x0ECE},
		{0x0F18, 0x0F19},
		{0x0F35},
		{0x0F37},
		{0x0F39},
		{0x0F71, 0x0F7E},
		{0x0F80, 0x0F84},
		{0x0F86, 0x0F87},
		{0x0F8D, 0x0F97},
		{0x0F99, 0x0FBC},
		{0x0FC6},
		{0x102D, 0x1030},
		{0x1032, 0x1037},
		{0x1039, 0x103A},
		{0x103D, 0x103E},
		{0x1058, 0x1059},
		{0x105E, 0x1060},
		{0x1071, 0x1074},
		{0x1082},
		{0x1085, 0x1086},
		{0x108D},
		{0x109D},
		{0x135D, 0x135F},
		{0x1712, 0x1714},
		{0x1732, 0x1733},
		{0x1752, 0x1753},
		{0x1772, 0x1773},
		{0x17B4, 0x17B5},
		{0x17B7, 0x17BD},
		{0x17C6},
		{0x17C9, 0x17D3},
		{0x17DD},
		-- Exclude Mongolian variation selectors.
		{0x1885, 0x1886},
		{0x18A9},
		{0x1920, 0x1922},
		{0x1927, 0x1928},
		{0x1932},
		{0x1939, 0x193B},
		{0x1A17, 0x1A18},
		{0x1A1B},
		{0x1A56},
		{0x1A58, 0x1A5E},
		{0x1A60},
		{0x1A62},
		{0x1A65, 0x1A6C},
		{0x1A73, 0x1A7C},
		{0x1A7F},
		{0x1AB0, 0x1ACE},
		{0x1B00, 0x1B03},
		{0x1B34},
		{0x1B36, 0x1B3A},
		{0x1B3C},
		{0x1B42},
		{0x1B6B, 0x1B73},
		{0x1B80, 0x1B81},
		{0x1BA2, 0x1BA5},
		{0x1BA8, 0x1BA9},
		{0x1BAB, 0x1BAD},
		{0x1BE6},
		{0x1BE8, 0x1BE9},
		{0x1BED},
		{0x1BEF, 0x1BF1},
		{0x1C2C, 0x1C33},
		{0x1C36, 0x1C37},
		{0x1CD0, 0x1CD2},
		{0x1CD4, 0x1CE0},
		{0x1CE2, 0x1CE8},
		{0x1CED},
		{0x1CF4},
		{0x1CF8, 0x1CF9},
		{0x1DC0, 0x1DCC},
		{0x1DCE, 0x1DFB},
		{0x1DFD, 0x1DFF},
		{0x20D0, 0x20F0},
		{0x2CEF, 0x2CF1},
		{0x2D7F},
		{0x2DE0, 0x2DFF},
		{0x302A, 0x302D},
		{0x3099, 0x309A},
		{0xA66F, 0xA672},
		{0xA674, 0xA67D},
		{0xA69E, 0xA69F},
		{0xA6F0, 0xA6F1},
		{0xA802},
		{0xA806},
		{0xA80B},
		{0xA825, 0xA826},
		{0xA82C},
		{0xA8C4, 0xA8C5},
		{0xA8E0, 0xA8F1},
		{0xA8FF},
		{0xA926, 0xA92D},
		{0xA947, 0xA951},
		{0xA980, 0xA982},
		{0xA9B3},
		{0xA9B6, 0xA9B9},
		{0xA9BC, 0xA9BD},
		{0xA9E5},
		{0xAA29, 0xAA2E},
		{0xAA31, 0xAA32},
		{0xAA35, 0xAA36},
		{0xAA43},
		{0xAA4C},
		{0xAA7C},
		{0xAAB0},
		{0xAAB2, 0xAAB4},
		{0xAAB7, 0xAAB8},
		{0xAABE, 0xAABF},
		{0xAAC1},
		{0xAAEC, 0xAAED},
		{0xAAF6},
		{0xABE5},
		{0xABE8},
		{0xABED},
		{0xFB1E},
		{0xFE20, 0xFE2F},
		{0x101FD},
		{0x102E0},
		{0x10376, 0x1037A},
		{0x10A01, 0x10A03},
		{0x10A05, 0x10A06},
		{0x10A0C, 0x10A0F},
		{0x10A38, 0x10A3A},
		{0x10A3F},
		{0x10AE5, 0x10AE6},
		{0x10D24, 0x10D27},
		{0x10EAB, 0x10EAC},
		{0x10EFD, 0x10EFF},
		{0x10F46, 0x10F50},
		{0x10F82, 0x10F85},
		{0x11001},
		{0x11038, 0x11046},
		{0x11070},
		{0x11073, 0x11074},
		{0x1107F, 0x11081},
		{0x110B3, 0x110B6},
		{0x110B9, 0x110BA},
		{0x110C2},
		{0x11100, 0x11102},
		{0x11127, 0x1112B},
		{0x1112D, 0x11134},
		{0x11173},
		{0x11180, 0x11181},
		{0x111B6, 0x111BE},
		{0x111C9, 0x111CC},
		{0x111CF},
		{0x1122F, 0x11231},
		{0x11234},
		{0x11236, 0x11237},
		{0x1123E},
		{0x11241},
		{0x112DF},
		{0x112E3, 0x112EA},
		{0x11300, 0x11301},
		{0x1133B, 0x1133C},
		{0x11340},
		{0x11366, 0x1136C},
		{0x11370, 0x11374},
		{0x11438, 0x1143F},
		{0x11442, 0x11444},
		{0x11446},
		{0x1145E},
		{0x114B3, 0x114B8},
		{0x114BA},
		{0x114BF, 0x114C0},
		{0x114C2, 0x114C3},
		{0x115B2, 0x115B5},
		{0x115BC, 0x115BD},
		{0x115BF, 0x115C0},
		{0x115DC, 0x115DD},
		{0x11633, 0x1163A},
		{0x1163D},
		{0x1163F, 0x11640},
		{0x116AB},
		{0x116AD},
		{0x116B0, 0x116B5},
		{0x116B7},
		{0x1171D, 0x1171F},
		{0x11722, 0x11725},
		{0x11727, 0x1172B},
		{0x1182F, 0x11837},
		{0x11839, 0x1183A},
		{0x1193B, 0x1193C},
		{0x1193E},
		{0x11943},
		{0x119D4, 0x119D7},
		{0x119DA, 0x119DB},
		{0x119E0},
		{0x11A01, 0x11A0A},
		{0x11A33, 0x11A38},
		{0x11A3B, 0x11A3E},
		{0x11A47},
		{0x11A51, 0x11A56},
		{0x11A59, 0x11A5B},
		{0x11A8A, 0x11A96},
		{0x11A98, 0x11A99},
		{0x11C30, 0x11C36},
		{0x11C38, 0x11C3D},
		{0x11C3F},
		{0x11C92, 0x11CA7},
		{0x11CAA, 0x11CB0},
		{0x11CB2, 0x11CB3},
		{0x11CB5, 0x11CB6},
		{0x11D31, 0x11D36},
		{0x11D3A},
		{0x11D3C, 0x11D3D},
		{0x11D3F, 0x11D45},
		{0x11D47},
		{0x11D90, 0x11D91},
		{0x11D95},
		{0x11D97},
		{0x11EF3, 0x11EF4},
		{0x11F00, 0x11F01},
		{0x11F36, 0x11F3A},
		{0x11F40},
		{0x11F42},
		{0x13440},
		{0x13447, 0x13455},
		{0x16AF0, 0x16AF4},
		{0x16B30, 0x16B36},
		{0x16F4F},
		{0x16F8F, 0x16F92},
		-- Exclude Khitan Small Script filler
		{0x1BC9D, 0x1BC9E},
		{0x1CF00, 0x1CF2D},
		{0x1CF30, 0x1CF46},
		{0x1D167, 0x1D169},
		{0x1D17B, 0x1D182},
		{0x1D185, 0x1D18B},
		{0x1D1AA, 0x1D1AD},
		{0x1D242, 0x1D244},
		{0x1DA00, 0x1DA36},
		{0x1DA3B, 0x1DA6C},
		{0x1DA75},
		{0x1DA84},
		{0x1DA9B, 0x1DA9F},
		{0x1DAA1, 0x1DAAF},
		{0x1E000, 0x1E006},
		{0x1E008, 0x1E018},
		{0x1E01B, 0x1E021},
		{0x1E023, 0x1E024},
		{0x1E026, 0x1E02A},
		{0x1E08F},
		{0x1E130, 0x1E136},
		{0x1E2AE},
		{0x1E2EC, 0x1E2EF},
		{0x1E4EC, 0x1E4EF},
		{0x1E8D0, 0x1E8D6},
		{0x1E944, 0x1E94A}
	},
	double = {
		{0x035C, 0x0362},
		{0x1DCD},
		{0x1DFC}
	}
}
for i, set in pairs(comb_chars) do
	for j, range in ipairs(set) do
		for k, char in ipairs(range) do
			range[k] = u(char)
		end
		set[j] = table.concat(range, "-")
	end
	comb_chars[i] = table.concat(set)
end
comb_chars.both = comb_chars.single .. comb_chars.double
comb_chars = {
	combined_single = "[^" .. comb_chars.both .. "][" .. comb_chars.single .. "]+%f[^" .. comb_chars.both .. "]",
	combined_double = "[^" .. comb_chars.both .. "][" .. comb_chars.single .. "]*[" .. comb_chars.double .. "]+[" .. comb_chars.both .. "]*.[" .. comb_chars.single .. "]*",
	diacritics_single = "[" .. comb_chars.single .. "]+%f[^" .. comb_chars.both .. "]",
	diacritics_double = "[" .. comb_chars.single .. "]*[" .. comb_chars.double .. "]+[" .. comb_chars.both .. "]*",
	end_of_diacritics = "%f[^" .. comb_chars.both .. "]"
}

-- Get the list of unsupported titles and invert it (so the keys are pagenames and values are canonical titles).
local unsupported_titles = {}
for k, v in pairs(require("Module:links/data").unsupported_titles) do
	unsupported_titles[v] = k
end
data.unsupported_titles = unsupported_titles

------ 3. Page-wide processing (so that it only needs to be done once per page). ------

--Get the pagename.
local pagename = mw.title.getCurrentTitle().subpageText
	:gsub("^Unsupported titles/(.*)", function(m)
		data.unsupported_title = true
		return unsupported_titles[m] or m
	end)
-- Save pagename, as local variable will be destructively modified.
data.pagename = pagename
-- Decompose the pagename in Unicode normalization form D.
data.decompose_pagename = mw.ustring.toNFD(pagename)
-- Explode the current page name into a character table, taking decomposed combining characters into account.
local explode_pagename = {}
local pagename_len = 0
local function explode(char)
	explode_pagename[char] = true
	pagename_len = pagename_len + 1
	return ""
end
pagename = rsub(pagename, comb_chars.combined_double, explode)
pagename = rsub(pagename, comb_chars.combined_single, explode)
	:gsub("[%z\1-\127\194-\244][\128-\191]*", explode)

data.comb_chars = comb_chars
data.explode_pagename = explode_pagename
data.pagename_len = pagename_len

-- Generate DEFAULTSORT.
data.encoded_pagename = mw.text.encode(data.pagename)
data.pagename_defaultsort = require("Module:languages").getByCode("mul"):makeSortKey(data.encoded_pagename)
mw.getCurrentFrame():callParserFunction(
	"DEFAULTSORT",
	data.pagename_defaultsort
)

------ 4. Parse page for maintenance categories. ------

-- Manual use of {{DEFAULTSORT:}} and aliases.
local content = mw.title.getCurrentTitle():getContent()
if content:find("{{DEFAULTC?A?T?E?G?O?R?Y?SORTK?E?Y?:") then
	data.pagename_defaultsort_conflict = true
end
-- Manual use of {{DISPLAYTITLE:}}.
if content:find("{{DISPLAYTITLE:") then
	data.pagename_displaytitle_conflict = true
end
-- Manual categories.
if content:find("%[%[Category:") then
	track("manual categories")
end
-- Manual "terms spelled with" categories.
if content:find("terms spelled with") then
	track("terms-spelled-with")
end

return data