မော်ဂျူး:headword/data/sandbox
Documentation for this module may be created at မော်ဂျူး:headword/data/sandbox/doc
local headword_page_module = "Module:headword/page/sandbox"
local list_to_set = require("Module:table").listToSet
local data = {}
------ 1. Lists which are converted into sets. ------
-- Zero-plurals (i.e. invariable plurals).
local irregular_plurals = list_to_set({
"cmavo",
"cmene",
"fu'ivla",
"gismu",
"Han tu",
"hanja",
"hanzi",
"jyutping",
"kana",
"kanji",
"lujvo",
"phrasebook",
"pinyin",
"rafsi",
}, function(_, item)
return item
end)
-- Irregular non-zero plurals AND any regular plurals where the singular ends in "s",
-- because the module assumes that inputs ending in "s" are plurals. The singular and
-- plural both need to be added, as the module will generate a default plural if
-- the input doesn't match a key in this table.
for sg, pl in next, {
mora = "morae"
} do
irregular_plurals[sg], irregular_plurals[pl] = pl, pl
end
data.irregular_plurals = irregular_plurals
data.lemmas = list_to_set{
"အကျဉ်းချုံးများ", "အကျဉ်းချုံး", -- abbreviations
"အတိုကောက်များ", "အတိုကောက်", -- acronyms
"နာမဝိသေသနများ", "နာမဝိသေသန", -- adjectives
"adnominals",
"adpositions", --adpositions
"ကြိယာဝိသေသနများ", "ကြိယာဝိသေသန", -- adverbs
"အဆက်များ", "အဆက်", -- affixes
"ambipositions",
"အညွှန်းစကားလုံးများ", "အညွှန်းစကားလုံး", -- articles
"circumfixes",
"circumpositions",
"ရေတွက်ပုံများ", "ရေတွက်ပုံ", --classifiers
"cmavo",
"cmavo clusters",
"cmene",
"ပေါင်းစပ်ပုဒ်များ", "ပေါင်းစပ်ပုဒ်", -- combining forms
"သမ္ဗန္ဓများ", "သမ္ဗန္ဓ", -- conjunctions
"counters",
"ဝါစင်္ဂများ", "ဝါစင်္ဂ", -- determiners
"အသံပြောင်းအမှတ်များ", "အသံပြောင်းအမှတ်", --diacritical marks
"ဗျည်းတွဲများ", "ဗျည်းတွဲ", --digraphs
"တူညီနှိုင်းယှဉ်နာမဝိသေသနများ", "တူညီနှိုင်းယှဉ်နာမဝိသေသန", --equative adjectives
"fu'ivla",
"gismu",
"ဟန် အက္ခရာများ", "ဟန် အက္ခရာ", -- Han characters
"ဟန်တု", -- Han tu
"ဟန်ဂျာ", -- hanja
"ဟန်ဇီ", -- hanzi
"သံပြိုင်ပုဒ်များ", "သံပြိုင်ပုဒ်", --ideophones
"အီဒီယမ်များ", "အီဒီယမ်", -- idioms
"infixes",
"အက္ခရာအတိုကောက်များ", "အက္ခရာအတိုကောက်", --initialisms
"ထပ်ဆင့်အမှတ်အသားများ", "ထပ်ဆင့်အမှတ်အသား", --iteration marks
"ပဒ်ဆက်ပစ္စည်းများ", "ပဒ်ဆက်ပစ္စည်း", --interfixes
"အာမေဍိတ်များ", "အာမေဍိတ်", -- interjections
"ခန", --kana
"ခန်းဂျီး", -- kanji
"စာလုံးများ", "စာလုံး", -- letters
"ligatures",
"လိုလိုဂရမ်များ", "လိုလိုဂရမ်", -- logograms
"lujvo",
"morae",
"ရုပ်ရင်းများ", "ရုပ်ရင်း", -- morphemes
"non-constituents",
"နာမ်များ", "နာမ်", -- nouns
"နံပါတ်များ", "နံပါတ်", -- numbers
"ကိန်းဂဏန်း သင်္ကေတများ", "ကိန်းဂဏန်း သင်္ကေတ", -- numeral symbols
"ဂဏန်းခြေများ", "ဂဏန်းခြေ", -- numerals
"ပစ္စည်းများ", "ပစ္စည်း", -- particles
"ပုဒ်စုများ", "ပုဒ်စု", -- phrases
"နာမ်ဝိဘတ်များ", "နာမ်ဝိဘတ်", --postpositions
"နာမ်ဝိဘတ်ပါသော ပုဒ်စုများ", "နာမ်ဝိဘတ်ပါသော ပုဒ်စု", -- postpositional phrases
"ကြိယာနောက်လိုက် နာမဝိသေသနများ", "ကြိယာနောက်လိုက် နာမဝိသေသန", -- predicatives
"ရှေ့ဆက်များ", "ရှေ့ဆက်", -- prefixes
"ဝိဘတ် စကားစုများ", "ဝိဘတ် စကားစု", -- prepositional phrases
"ဝိဘတ်များ", "ဝိဘတ်", -- prepositions
"ကြိယာပုဒ်ရှေ့ဆက်ပစ္စည်းများ", "ကြိယာပုဒ်ရှေ့ဆက်ပစ္စည်း", --preverbs
"နာမ်စားရင်းခံနာမဝိသေသနများ", "နာမ်စားရင်းခံနာမဝိသေသန", --pronominal adverbs
"နာမ်စားများ", "နာမ်စား", -- pronouns
"တစ်ဦးဆိုင်နာမ်များ", "တစ်ဦးဆိုင်နာမ်", -- proper nouns
"စကားပုံများ", "စကားပုံ", -- proverbs
"ပုဒ်ဖြတ်ပုဒ်ရပ်သင်္ကေတများ", "ပုဒ်ဖြတ်ပုဒ်ရပ်သင်္ကေတ", -- punctuation marks
"အညွှန်းနာမ်စားများ", "အညွှန်းနာမ်စား", -- relatives
"roots",
"stems",
"နောက်ဆက်များ", "နောက်ဆက်", -- suffixes
"ဝဏ္ဏများ", "ဝဏ္ဏ", -- syllables
"သင်္ကေတများ", "သင်္ကေတ", -- symbols
"ကြိယာများ", "ကြိယာ", -- verbs
}
data.nonlemmas = list_to_set{
"active participle forms",
"active participles",
"adjectival participles",
"adjective case forms",
"နာမဝိသေသနပုဒ်များ", "နာမဝိသေသနပုဒ်", -- adjective forms
"နာမဝိသေသန ဣတ္ထိလိင်ပုဒ်များ", "နာမဝိသေသန ဣတ္ထိလိင်ပုဒ်", -- adjective feminine forms
"နာမဝိသေသန ဗဟုဝုစ်ပုဒ်များ", "နာမဝိသေသန ဗဟုဝုစ်ပုဒ်", -- adjective plural forms
"ကြိယာဝိသေသနပုဒ်များ", "ကြိယာဝိသေသနပုဒ်", -- adverb forms
"adverbial participles",
"agent participles",
"အညွှန်းပုဒ်များ", "အညွှန်းပုဒ်", -- article forms
"circumfix forms",
"ပေါင်းစပ်ထားသောပုဒ်များ", "ပေါင်းစပ်ထားသောပုဒ်", -- combined forms
"နှိုင်းယှဉ်နိုင်သော နာမဝိသေသနပုဒ်များ", "နှိုင်းယှဉ်နိုင်သော နာမဝိသေသနပုဒ်", -- comparative adjective forms
"နှိုင်းယှဉ်နိုင်သော နာမဝိသေသနများ", "နှိုင်းယှဉ်နိုင်သော နာမဝိသေသန", -- comparative adjectives
"နှိုင်းယှဉ်နိုင်သော ကြိယာဝိသေသနပုဒ်များ", "နှိုင်းယှဉ်နိုင်သော ကြိယာဝိသေသနပုဒ်", -- comparative adverb forms
"နှိုင်းယှဉ်နိုင်သော ကြိယာဝိသေသနများ", "နှိုင်းယှဉ်နိုင်သော ကြိယာဝိသေသန", -- comparative adverbs
"သမ္ဗန္ဓပုဒ်များ", "သမ္ဗန္ဓပုဒ်", -- conjunction forms
"အတိုချုံ့စကားလုံးများ", "အတိုချုံ့စကားလုံး", -- contractions
"converbs",
"determiner comparative forms",
"ဝါစင်္ဂပုဒ်များ", "ဝါစင်္ဂပုဒ်", -- determiner forms
"determiner superlative forms",
"diminutive nouns",
"elative adjectives",
"equative adjective forms",
"equative adjectives",
"future participles",
"gerunds",
"infinitive forms",
"infinitives",
"interjection forms",
"jyutping",
"စာလုံးပေါင်းအမှားများ", "စာလုံးပေါင်းအမှား", --misspellings
"negative participles",
"nominal participles",
"noun case forms",
"noun construct forms",
"noun dual forms",
"နာမ်ပုဒ်များ", "နာမ်ပုဒ်", -- noun forms
"noun paucal forms",
"နာမ် ဗဟုဝုစ်ပုဒ်များ", "နာမ် ဗဟုဝုစ်ပုဒ်", -- noun plural forms
"noun possessive forms",
"noun singulative forms",
"ဂဏန်းခြေပုဒ်များ", "ဂဏန်းခြေပုဒ်", -- numeral forms
"ကြိယာသဏ္ဌာန်များ", "ကြိယာသဏ္ဌာန်", -- participles
"ကြိယာသဏ္ဌာန်ပုဒ်များ", "ကြိယာသဏ္ဌာန်ပုဒ်", -- participle forms
"ပစ္စည်းပုဒ်များ", "ပစ္စည်းပုဒ်", -- particle forms
"passive participles",
"past active participles",
"past adverbial participles",
"အတိတ်ကာလပြ ကြိယာသဏ္ဌာန်များ", "အတိတ်ကာလပြ ကြိယာသဏ္ဌာန်", --past participles
"အတိတ်ကာလပြ ကြိယာသဏ္ဌာန်ပုဒ်များ", "အတိတ်ကာလပြ ကြိယာသဏ္ဌာန်ပုဒ်", -- past participle forms
"past passive participles",
"perfect active participles",
"perfect participles",
"perfect passive participles",
"pinyin",
"ဗဟုဝုစ်များ", "ဗဟုဝုစ်", -- plurals
"postposition forms",
"ရှေ့ဆက်ပုဒ်များ", "ရှေ့ဆက်ပုဒ်", -- prefix forms
"preposition contractions",
"ဝိဘတ်ပုဒ်များ", "ဝိဘတ်ပုဒ်", -- preposition forms
"ဝိဘတ်နာမ်စားများ", "ဝိဘတ်နာမ်စား", -- prepositional pronouns
"present active participles",
"present adverbial participles",
"ဖြစ်ဆဲပြ ကြိယာသဏ္ဌာန်များ", "ဖြစ်ဆဲပြ ကြိယာသဏ္ဌာန်", -- present participles
"present passive participles",
"preverb forms",
"နာမ်စားပုဒ်များ", "နာမ်စားပုဒ်", -- pronoun forms
"နာမ်စားပိုင်ဆိုင်မှုပြပုဒ်များ", "နာမ်စားပိုင်ဆိုင်မှုပြပုဒ်", --pronoun possessive forms
"တစ်ဦးဆိုင်နာမ်ပုဒ်များ", "တစ်ဦးဆိုင်နာမ်ပုဒ်", -- proper noun forms
"တစ်ဦးဆိုင်နာမ် ဗဟုဝုစ်ပုဒ်များ", "တစ်ဦးဆိုင်နာမ် ဗဟုဝုစ်ပုဒ်", -- proper noun plural forms
"rafsi",
"ရောမအက္ခရာဖလှယ်ခြင်းများ", "ရောမအက္ခရာဖလှယ်ခြင်း", -- romanizations
"root forms",
"singulatives",
"နောက်ဆက်ပုဒ်များ", "နောက်ဆက်ပုဒ်", -- suffix forms
"အသာလွန်ဆုံး နာမဝိသေသနပုဒ်များ", "အသာလွန်ဆုံး နာမဝိသေသနပုဒ်", -- superlative adjective forms
"အသာလွန်ဆုံး နာမဝိသေသနများ", "အသာလွန်ဆုံး နာမဝိသေသန", -- superlative adjectives
"အသာလွန်ဆုံး ကြိယာဝိသေသနပုဒ်များ", "အသာလွန်ဆုံး ကြိယာဝိသေသနပုဒ်", -- superlative adverb forms
"အသာလွန်ဆုံး ကြိယာဝိသေသနများ", "အသာလွန်ဆုံး ကြိယာဝိသေသန", -- superlative adverbs
"ကြိယာပုဒ်များ", "ကြိယာပုဒ်", -- verb forms
"ကြိယာနာမ်များ", "ကြိယာနာမ်", -- verbal nouns
}
-- These langauges will not have links to separate parts of the headword.
data.no_multiword_links = list_to_set{
"zh",
}
-- These languages will not have "LANG multiword terms" categories added.
data.no_multiword_cat = list_to_set{
-------- 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)
"nan-hbl", -- Hokkien (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 = list_to_set{
"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
"hnn", -- Hanunoo; too many false positives
"ilo", -- Ilocano; hyphens for mid-word glottal stops
"kne", -- Kankanaey; 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 = list_to_set{
-- Languages without gender but which use the gender field for other purposes
"ja",
"th",
}
data.notranslit = list_to_set{
"ams",
"az",
"bbc",
"bug",
"cdo",
"cia",
"cjm",
"cjy",
"cmn",
"cnp",
"cpi",
"cpx",
"csp",
"czh",
"czo",
"gan",
"hak",
"hnm",
"hsn",
"ja",
"kzg",
"lad",
"ltc",
"luh",
"lzh",
"mnp",
"ms",
"mul",
"mvi",
"nan",
"nan-dat",
"nan-hbl",
"nan-hlh",
"nan-lnx",
"nan-tws",
"nan-zhe",
"nan-zsh",
"och",
"oj",
"okn",
"ryn",
"rys",
"ryu",
"sh",
"sjc",
"tgt",
"th",
"tkn",
"tly",
"txg",
"und",
"vi",
"wuu",
"xug",
"yoi",
"yox",
"yue",
"za",
"zh",
"zhx-sic",
"zhx-tai",
}
-- Script codes for which a script-tagged display title will be added.
data.toBeTagged = list_to_set{
"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",
"Polyt",
"polytonic",
"Gujr",
"Guru",
"Hang",
"Hani",
"Hano",
"Hebr",
"Hira",
"Hluw",
"Ital",
"Java",
"Kali",
"Kana",
"Khar",
"Khmr",
"Knda",
"Kthi",
"Lana",
"Laoo",
"Latn",
"Latf",
"Latg",
"Latnx",
"Latinx",
"pjt-Latn",
"Lepc",
"Limb",
"Linb",
"Lisu",
"Lyci",
"Lydi",
"Mand",
"Mani",
"Marc",
"Merc",
"Mero",
"Mlym",
"Mong",
"mnc-Mong",
"sjo-Mong",
"xwo-Mong",
"Mtei",
"Mymr",
"Narb",
"Nkoo",
"Nshu",
"Ogam",
"Olck",
"Orkh",
"Orya",
"Osma",
"Ougr",
"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",
"Ugar",
"Vaii",
"Xpeo",
"Xsux",
"Yiii",
"Zmth",
"Zsym",
"Ipach",
"Music",
"Rumin",
}
-- 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 = list_to_set{
"diacritical marks",
"Han characters",
"Han tu",
"hanja",
"hanzi",
"iteration marks",
"kana",
"kanji",
"letters",
"ligatures",
"logograms",
"morae",
"numeral symbols",
"numerals",
"punctuation marks",
"syllables",
"symbols",
}
------ 2. Lists not converted into sets. ------
-- Recognized aliases for parts of speech (param 2=). Key is the short form and value is the canonical singular (not
-- pluralized) form. It is singular so that the same table can be used in [[Module:form of]] for the p=/POS= param
-- and [[Module:links]] for the pos= param.
data.pos_aliases = {
a = "နာမဝိသေသန",
adj = "နာမဝိသေသန",
adv = "ကြိယာဝိသေသန",
art = "အညွှန်းစကားလုံး",
det = "ဝါစင်္ဂ",
compadj = "comparative adjective",
compadv = "comparative adverb",
conj = "သမ္ဗန္ဓ",
conv = "converb",
int = "အာမေဍိတ်",
interj = "အာမေဍိတ်",
intj = "အာမေဍိတ်",
n = "နာမ်",
-- the next two support Algonquian languages; see also vii/vai/vti/vta below
na = "animate noun",
ni = "inanimate noun",
num = "ဂဏန်းခြေ",
part = "participle",
pcl = "ပစ္စည်း",
phr = "စကားစု",
pn = "တစ်ဦးဆိုင်နာမ်",
postp = "postposition",
pref = "prefix",
prep = "ဝိဘတ်",
pron = "နာမ်စား",
prop = "တစ်ဦးဆိုင်နာမ်",
proper = "တစ်ဦးဆိုင်နာမ်",
propn = "တစ်ဦးဆိုင်နာမ်",
rom = "ရောမအက္ခရာဖလှယ်ခြင်း",
suf = "နောက်ဆက်",
supadj = "အသာလွန်ဆုံး နာမဝိသေသန",
supadv = "အသာလွန်ဆုံး ကြိယာဝိသေသန",
v = "ကြိယာ",
vb = "ကြိယာ",
vi = "ကံမလို ကြိယာ",
vt = "ကံလို ကြိယာများ",
-- the next four support Algonquian languages
vii = "inanimate intransitive verb",
vai = "animate intransitive verb",
vti = "ကံလိုနှင့် ကံမလို ကြိယာများ",
vta = "transitive animate verb",
}
-- 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 = {
["နာမ်"] = "နာမ်",
["တစ်ဦးဆိုင်နာမ်"] = "နာမ်",
["နောက်ဆက်"] = "နောက်ဆက်",
-- We include verbs because impf and pf are valid "genders".
["ကြိယာ"] = "ကြိယာ",
}
------ 3. Page-wide processing (so that it only needs to be done once per page). ------
data.page = require(headword_page_module).process_page()
-- Fuckme, random references to data.pagename and data.encoded_pagename are scattered throughout the codebase. FIXME!
data.pagename = data.page.pagename
data.encoded_pagename = data.page.encoded_pagename
return data