Module:User:Manishearth/zh-pron

local export = {} local m_string_utils = require("Module:string utilities")

local codepoint = mw.ustring.codepoint local find = m_string_utils.find local gsub = m_string_utils.gsub local len = m_string_utils.len local match = m_string_utils.match local u = mw.ustring.char

local langname = { ["cdo"] = "Min Dong", ["cmn"] = "Mandarin", ["cjy"] = "Jin", ["dng"] = "Dungan", ["gan"] = "Gan", ["hak"] = "Hakka", ["hsn"] = "Xiang", ["mnp"] = "Min Bei", ["nan"] = "Min Nan", ["wuu"] = "Wu", ["yue"] = "Cantonese", }

local langname_abbr = { ["m"] = "Mandarin", ["m-s"] = "Sichuanese", ["dg"] = "Dungan", ["c"] = "Cantonese", ["c-t"] = "Taishanese", ["g"] = "Gan", ["h"] = "Hakka", ["j"] = "Jin", ["mb"] = "Min Bei", ["md"] = "Min Dong", ["mn"] = "Min Nan", ["mn-t"] = "Teochew", ["w"] = "Wu", ["x"] = "Xiang", }

local pos_aliases_cat = { ["n"] = "nouns", ["noun"] = "nouns", ["pn"] = "proper nouns", ["propn"] = "proper nouns", ["proper"] = "proper nouns", ["proper noun"] = "proper nouns", ["pron"] = "pronouns", ["pronoun"] = "pronouns", ["v"] = "verbs", ["verb"] = "verbs", ["a"] = "adjectives", ["adj"] = "adjectives", ["adjective"] = "adjectives", ["adv"] = "adverbs", ["adverb"] = "adverbs", ["prep"] = "prepositions", ["pre"] = "prepositions", ["postp"] = "postpositions", ["post"] = "postpositions", ["con"] = "conjunctions", ["conj"] = "conjunctions", ["conjunction"] = "conjunctions", ["part"] = "particles", ["particle"] = "particles", ["pref"] = "prefixes", ["prefix"] = "prefixes", ["suf"] = "suffixes", ["suffix"] = "suffixes", ["infix"] = "infixes", ["prov"] = "proverbs", ["proverb"] = "proverbs", ["id"] = "idioms", ["idiom"] = "idioms", ["ch"] = "chengyu", ["cy"] = "chengyu", ["chengyu"] = "chengyu", ["ph"] = "phrases", ["phrase"] = "phrases", ["intj"] = "interjections", ["interj"] = "interjections", ["interjection"] = "interjections", ["cl"] = "classifiers", ["cls"] = "classifiers", ["classifier"] = "classifiers", ["num"] = "numerals", ["numeral"] = "numerals", ["abb"] = "abbreviations", ["abbreviation"] = "abbreviations", ["det"] = "determiners", ["deter"] = "determiners", ["determiner"] = "determiners", ["syllable"] = "syllables", }

-- if not empty local function ine(val) if val == "" then return nil end return val end

local function makeNote(text) if find(text, ": ") then text = "\n*" .. gsub(gsub(text, "\n", ".\n*"), "([:;]) ", "%1\n**") elseif find(text, "; ") then text = "\n*" .. gsub(text, '; ', ";\n*") end text = gsub(text, '“([^”]+)”', function (a) return '“' .. gsub(a, ";\n%*+", "; ") .. '”' end) return "\nNote: " .. text .. ". " end

local function ipa_format(text) local numbers = { ["1"]="¹",["2"]="²",["3"]="³",["4"]="⁴",["5"]="⁵",["0"]="⁰",["-"]="⁻",["/"]="/, /" } return gsub(text,'[0-5%-/]',numbers) end

local function Consolas(text) return '' .. text .. ' ' end

local function format_IPA(text) return ' ' .. text .. ' ' end

function export.make(frame) local args = frame:getParent.args local title = mw.title.getCurrentTitle local pagename = ine(args["pagename"]) or title.text local sortkey = (require("Module:Hani-sortkey").makeSortKey(pagename)) -- Unicode pattern for single Han character, with non-NFC characters -- inserted using mw.ustring.char because they can't be saved in a MediaWiki -- page. -- https://unicode.org/cldr/utility/regex.jsp?a=%5Cp%7BHani%7D local hanzi = "^[⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〻㐀-䶿一-鿼" .. u(0xF900) .. "-" .. u(0xFA6D) .. u(0xFA70) .. "-" .. u(0xFAD9) .. "𠀀-𪛝𪜀-𫜴𫝀-𫠝𫠠-𬺡𬺰-𮯠" .. u(0x2F800) .. "-" .. u(0x2FA1D) .. "𰀀-𱍊]$" local is_single_hanzi = find(pagename, hanzi) ~= nil local namespace = ine(args["namespace"]) or title.nsText local m_rom = ine(args["m"]) local m_s_rom = ine(args["m-s"]) local dg_rom = ine(args["dg"]) local c_rom = ine(args["c"]) local c_t_rom = ine(args["c-t"]) local g_rom = ine(args["g"]) local h_rom = ine(args["h"]) local j_rom = ine(args["j"]) local mb_rom = ine(args["mb"]) local md_rom = ine(args["md"]) local mn_rom = ine(args["mn"]) local mn_t_rom = ine(args["mn-t"]) local w_rom = ine(args["w"]) local x_rom = ine(args["x"]) local m_audio = ine(args["ma"]) local m_audio2 = ine(args["ma2"]) local m_s_audio = ine(args["m-sa"]) local dg_audio = ine(args["dga"]) local c_audio = ine(args["ca"]) local c_t_audio = ine(args["c-ta"]) local g_audio = ine(args["ga"]) local h_audio = ine(args["ha"]) local j_audio = ine(args["ja"]) local mb_audio = ine(args["mba"]) local md_audio = ine(args["mda"]) local mn_audio = ine(args["mna"]) local mn_t_audio = ine(args["mn-ta"]) local w_audio = ine(args["wa"]) local x_audio = ine(args["xa"]) local dial = ine(args["dial"]) local mc = ine(args["mc"]) or false local oc = ine(args["oc"]) or false local only_cat = args["only_cat"] == "yes" local function add_audio(text, audio, lang) -- This function has side effects if audio then if audio == "y" then audio = string.format('%s-%s.ogg', lang, mw.title.getCurrentTitle.baseText) end table.insert(text, '\n*** [[File:')           table.insert(text, audio)            table.insert(text, ']]') table.insert(text, '[[Category:')           table.insert(text, langname[lang:sub(1, 3)])            table.insert(text, ' terms with audio links|' .. sortkey .. ']]') end end local function add_audio_show(text, audio, lang) -- This function has side effects if audio then if audio == "y" then audio = string.format('%s-%s.ogg', lang, mw.title.getCurrentTitle.baseText) end table.insert(text, '\n*:: [[File:')           table.insert(text, audio)            table.insert(text, ']]') table.insert(text, '[[Category:')           table.insert(text, langname[lang:sub(1, 3)])            table.insert(text, ' terms with audio links|' .. sortkey .. ']]') end end

local text = {} --the pronunciation table if not only_cat then --The whole table consists of 4 parts --"textShow" contains Part 1, 3 and 4 local textShow = {' '} --"textHide" is Part 2 local textHide = {}

table.insert(textShow, ' \n ') --Part 1 and 2, "Pronunciation" and "Pronunciation expressed in different romanizations" if m_rom or m_s_rom or dg_rom then table.insert(textShow, '\n* Mandarin') end if m_rom or m_audio then local m_args = {} local m_pron = require("Module:cmn-pron") if m_rom then local str_analysis = m_pron.str_analysis local other_m_vars = { (m_s_rom or ""), (m_s_audio or ""), (dg_rom or ""), (dg_audio or "") } table.insert(textShow, '\n' .. str_analysis(m_rom, 'head', table.concat(other_m_vars) ~= ""))

m_args[1] = str_analysis(m_rom,'') local m_args_names = { '1n','1na','1nb','1nc','1nd','py','cap','tl','tl2','tl3','a','audio','er','ertl','ertl2','ertl3','era','eraudio', '2n','2na','2nb','2nc','2nd','2py','2cap','2tl','2tl2','2tl3','2a','2audio','2er','2ertl','2ertl2','2ertl3','2era','2eraudio', '3n','3na','3nb','3nc','3nd','3py','3cap','3tl','3tl2','3tl3','3a','3audio','3er','3ertl','3ertl2','3ertl3','3era','3eraudio', '4n','4na','4nb','4nc','4nd','4py','4cap','4tl','4tl2','4tl3','4a','4audio','4er','4ertl','4ertl2','4ertl3','4era','4eraudio', '5n','5na','5nb','5nc','5nd','5py','5cap','5tl','5tl2','5tl3','5a','5audio','5er','5ertl','5ertl2','5ertl3','5era','5eraudio', }               for _, name in ipairs(m_args_names) do                    m_args[name] = str_analysis(m_rom, name) end for i = 2, 5 do                   m_args[i] = str_analysis(m_rom, tostring(i)) end end m_args['a'] = m_audio m_args['a2'] = m_audio2 local debug = "" for code,name in pairs(m_args) do               debug = debug .. code .. ":" .. name .. ","           end table.insert(textShow, m_pron.make_audio(m_args)) table.insert(textHide, m_pron.make_args(m_args)) if args["m_note"] then table.insert(textHide, makeNote(args["m_note"])) end end if m_s_rom or m_s_audio then local m_s_pron = require("Module:cmn-sic-pron") local m_s_processed = gsub(gsub(gsub(m_s_rom, '/', ' / '), '([%d-])([%a])', '%1 %2'), '([%d-]+)', '%1') if m_s_rom then table.insert(textShow, '\n*: (Chengdu, SP) : ') table.insert(textShow, Consolas(m_s_processed)) end add_audio_show(textShow, m_s_audio, 'cmn-sic') if not (m_rom or m_audio) then table.insert(textHide, '\n* Mandarin') end table.insert(textHide, '\n** (Chengdu) ') table.insert(textHide, '\n*** Sichuanese Pinyin : ') table.insert(textHide, Consolas(m_s_processed)) local xinwenz = m_s_pron.convert(m_s_rom, 'SWZ') if xinwenz then table.insert(textHide, '\n*** Scuanxua Ladinxua Xin Wenz : ') table.insert(textHide, Consolas(m_s_pron.convert(m_s_rom, 'SWZ'))) end table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA(m_s_pron.convert(m_s_rom, 'IPA'))) if args["m-s_note"] then table.insert(textHide, makeNote(args["m-s_note"])) end end if dg_rom or dg_audio then local dg_pron = require("Module:dng-pron") local dg_processed = dg_pron.process(dg_rom) if dg_rom then table.insert(textShow, '\n*: (Dungan, Cyrillic and Wiktionary) : ') table.insert(textShow, Consolas(dg_processed)) end add_audio_show(textShow, dg_audio, 'dng') if not (m_rom or m_audio or m_s_rom or m_s_audio) then table.insert(textHide, '\n* Mandarin') end table.insert(textHide, '\n** (Dungan) ') table.insert(textHide, '\n*** Cyrillic and Wiktionary : ') table.insert(textHide, Consolas(dg_processed)) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA(dg_pron.convert(dg_rom, 'IPA')) .. '\n**: (Note: Dungan pronunciation is currently experimental and may be inaccurate.) ') if args["dg_note"] then table.insert(textHide, makeNote(args["dg_note"])) end end if c_rom or c_audio or c_t_rom or c_t_audio then local c_pron = require("Module:yue-pron") if c_rom or c_t_rom then table.insert(textShow, '\n* Cantonese') table.insert(textHide, '\n* Cantonese') if c_rom then c_rom = c_rom:gsub("%*","-") local c_processed = c_rom:gsub(',([^ ])',', %1') if len(pagename) == 1 then c_processed = c_processed:gsub('([^, ]+)','%1') c_processed = c_processed:gsub('%[%[%[%[',)                       c_processed = c_processed:gsub('%]%]%]%]',) c_processed = gsub(c_processed, '%[%[([^%]]+)%]%]', function(a)                           return  .. gsub(a, '([1-9-]+)', '%1') ..  end) else c_processed = gsub(c_processed, '([1-9-]+)', '%1') end if not c_t_rom then table.insert(textShow, ' (')                   else                        table.insert(textShow, '\n*: (Guangzhou–Hong Kong, ') end table.insert(textShow, 'Jyutping) : ' .. Consolas(c_processed))                   add_audio_show(textShow, c_audio, 'yue')                    c_rom = c_rom:gsub('[%[%]]',)                    local c_hom = mw.loadData("Module:yue-pron/hom")                    local c_hom_exists = false                    for _,c_first in ipairs(c_pron.jyutping_format(c_rom)) do                        if c_hom[c_first] then                            c_hom_exists = c_first                        end                    end                    table.insert(textHide, '\n** (Standard Cantonese, Guangzhou–Hong Kong'') ')                    if not c_hom_exists then                        table.insert(textHide, '  [')                        table.insert(textHide, tostring(mw.uri.fullUrl("Module:yue-pron/hom",{["action"]="edit"})))                        table.insert(textHide, ' +]  ') end local c_comma = gsub(c_rom,',([^ ])',', %1') table.insert(textHide, '\n*** Jyutping : ') table.insert(textHide, Consolas(tostring(gsub(c_comma, '([1-9-]+)', '%1')))) table.insert(textHide, '\n*** Yale : ') table.insert(textHide, Consolas(c_pron.jyutping_to_yale(c_rom))) table.insert(textHide, '\n*** Cantonese Pinyin : ') table.insert(textHide, Consolas(tostring(gsub(c_pron.jyutping_to_cantonese_pinyin(c_rom), '([1-9-]+)', '%1')))) table.insert(textHide, '\n*** Guangdong Romanization : ') table.insert(textHide, Consolas(tostring(gsub(c_pron.jyutping_to_guangdong(c_rom), '([1-9-]+)', '%1')))) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA('/' .. c_pron.jyutping_to_ipa(c_rom) .. '/'))                   for _,c_first in ipairs(c_pron.jyutping_format(c_rom)) do                        if c_hom_exists == c_first then local hom_textHide = {'\n*** Homophones :        ') table.insert(hom_textHide, ' [') table.insert(hom_textHide, tostring(mw.uri.fullUrl("Module:yue-pron/hom",{["action"]="edit"}))) table.insert(hom_textHide, ' edit]  edit ') local yue = require("Module:languages").getByCode("yue") for _,hom in ipairs(c_hom[c_first]) do                               table.insert(hom_text, require("Module:links").full_link( { term = hom, lang = yue, tr = "-" } )) end table.insert(hom_textHide, table.concat(hom_text, " ")) table.insert(hom_textHide, '  ') table.insert(textHide, table.concat(hom_textHide)) table.insert(textHide, '') end end if not args["c_note"] and c_rom and (find(c_rom, "^[ao]") or find(c_rom, ",[ao]")) and len(pagename) == 1 then args["c_note"] = "The zero initial " .. format_IPA("/∅-/") .. " is commonly pronounced with a ng-initial " .. format_IPA("/ŋ-/") .. " in some varieties of Cantonese, including Hong Kong Cantonese" end if args["c_note"] then table.insert(textHide, makeNote(args["c_note"])) end end if c_t_rom then local c_t_processed = c_t_rom:gsub(',([^ ])',', %1') c_t_processed = gsub(c_t_processed, '([1-9%*]%-?[1-9%*]?)', '%1') table.insert(textShow, (c_rom and '\n*:' or ) .. ' (Taishan, Wiktionary'') : ') table.insert(textShow, Consolas(c_t_processed)) add_audio_show(textShow, c_t_audio, 'yue-taishan') c_t_rom = c_t_rom:gsub('[%[%]]','') local c_t_comma = gsub(c_t_rom,',([^ ])',', %1') table.insert(textHide, '\n** (Taishanese, Taicheng) ') table.insert(textHide, '\n*** Wiktionary : ') table.insert(textHide, Consolas(tostring(gsub(c_t_comma, '([1-9%*]%-?[1-9%*]?)', '%1')))) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA(c_pron.hoisanva_to_ipa(c_t_rom))) if args["c-t_note"] then table.insert(textHide, makeNote(args["c-t_note"])) end end end end if g_rom or g_audio then local g_pron = require("Module:gan-pron") if g_rom then table.insert(textShow, '\n* Gan (Wiktionary) : ') table.insert(textShow, Consolas(g_pron.rom(g_rom))) end add_audio_show(textShow, g_audio, 'gan') table.insert(textHide, '\n* Gan') table.insert(textHide, '\n** (Nanchang) ') table.insert(textHide, '\n*** Wiktionary : ') table.insert(textHide, Consolas(g_pron.rom(g_rom))) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA('/' .. g_pron.ipa(g_rom) .. '/'))           if args["g_note"] then table.insert(textHide, makeNote(args["g_note"])) end end if h_rom and (find(h_rom, 'pfs=.') or find(h_rom, 'gd=.')) or h_audio then local h_pron = require("Module:hak-pron") if find(h_rom, "pfs=.") or find(h_rom, 'gd=.') then table.insert(textShow, '\n* Hakka') table.insert(textShow, h_pron.rom_display(h_rom,'yes')) end add_audio_show(textShow, h_audio, 'hak') table.insert(textHide, '\n* Hakka') if h_rom then table.insert(textHide, h_pron.rom_display(h_rom,'')) end if args["h_note"] then table.insert(textHide, makeNote(args["h_note"])) end end if j_rom or j_audio then local j_pron = require("Module:cjy-pron") if j_rom then table.insert(textShow, '\n* Jin (Wiktionary) : ') table.insert(textShow, Consolas(j_pron.rom(j_rom))) end add_audio_show(textShow, j_audio, 'cjy') table.insert(textHide, '\n* Jin') table.insert(textHide, '\n** (Taiyuan)+ ') if j_rom then table.insert(textHide, '\n*** Wiktionary : ') table.insert(textHide, Consolas(j_pron.rom(j_rom))) end local no_sandhi = false local roms = mw.text.split(j_rom, '/') for i = 1, table.getn(roms) do               if find(roms[i], ' [^ ]+ ') then no_sandhi = true break end end table.insert(textHide, '\n*** Sinological IPA (''old-style' .. (no_sandhi and ', no sandhi' or '') .. ''') : ')           table.insert(textHide, format_IPA('/' .. j_pron.ipa(j_rom, no_sandhi and "no_sandhi" or "") .. '/'))           if args["j_note"] then table.insert(textHide, makeNote(args["j_note"])) end end if mb_rom or mb_audio then local mb_pron = require("Module:mnp-pron") if mb_rom then table.insert(textShow, '\n* Min Bei (KCR) : ') table.insert(textShow, Consolas(mb_pron.rom(mb_rom))) end add_audio_show(textShow, mb_audio, 'mnp') table.insert(textHide, '\n* Min Bei') table.insert(textHide, "\n** (Jian'ou) ") if mb_rom then table.insert(textHide, '\n*** Kienning Colloquial Romanized : ') table.insert(textHide, Consolas(mb_pron.rom(mb_rom))) table.insert(textHide, "\n*** Sinological IPA (key) : ") table.insert(textHide, format_IPA(mb_pron.ipa(mb_rom))) end if args["mb_note"] then table.insert(textHide, makeNote(args["mb_note"])) end end if md_rom or md_audio then local md_pron = require("Module:cdo-pron") if md_rom then table.insert(textShow, '\n* Min Dong (BUC) : ') table.insert(textShow, Consolas(md_pron.rom(md_rom))) end add_audio_show(textShow, md_audio, 'cdo') table.insert(textHide, '\n* Min Dong') table.insert(textHide, '\n** (Fuzhou) ') if md_rom then table.insert(textHide, '\n*** Bàng-uâ-cê : ') table.insert(textHide, Consolas(md_pron.rom(md_rom))) if not (md_rom and find(md_rom, '([^/]*)-([^/]*)-([^/]*)-([^/]*)-([^/]*)')) then table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA('/' .. md_pron.ipa(md_rom) .. '/'))               else table.insert(textHide, '\n*** Sinological IPA (key) (no sandhi) : ') table.insert(textHide, format_IPA('/' .. md_pron.ipa(md_rom, "no_sandhi") .. '/'))               end end if args["md_note"] then table.insert(textHide, makeNote(args["md_note"])) end end if mn_rom or mn_audio or mn_t_rom or mn_t_audio then local mn_pron = require("Module:nan-pron") if mn_rom or mn_t_rom then table.insert(textShow, '\n* Min Nan') if mn_rom then table.insert(textShow, ( not mn_t_rom and " (" or "\n*: (Hokkien, ") .. 'POJ) : ')                   table.insert(textShow, Consolas(mn_pron.poj_display(mn_pron.poj_check_invalid(mn_rom))))                    add_audio_show(textShow, mn_audio, 'nan')                end                if mn_t_rom then                    table.insert(textShow, (mn_rom and '\n*:' or '') .. ' (Teochew, Peng\'im) : ')                   table.insert(textShow, Consolas(mn_pron.pengim_display(mn_t_rom)))                    add_audio_show(textShow, mn_t_audio, 'nan-teochew')                end            end            table.insert(textHide, '\n* Min Nan')            if mn_rom or mn_audio then                table.insert(textHide, mn_pron.generate_all(mn_rom))                if args["mn_note"] then table.insert(textHide, makeNote(args["mn_note"])) end            end            if mn_t_rom or mn_t_audio then                table.insert(textHide, '\n** (Teochew) ')                table.insert(textHide, '\n*** Peng\'im : ')                table.insert(textHide, Consolas(mn_pron.pengim_display(mn_t_rom)))                table.insert(textHide, '\n*** Pe̍h-ōe-jī-like : ') table.insert(textHide, Consolas(mn_pron.pengim_to_pojlike_conv(mn_t_rom))) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA(mn_pron.pengim_to_ipa_conv(mn_t_rom))) if args["mn-t_note"] then table.insert(textHide, makeNote(args["mn-t_note"])) end end end if w_rom or w_audio then local w_pron = require("Module:User:Manishearth/wuu-pron") if w_rom then table.insert(textShow, '\n* Wu') table.insert(textShow, '\n** (Shanghainese, Wiktionary) : ') table.insert(textShow, Consolas(w_pron.rom(w_rom))) table.insert(textShow, '\n** (Shanghainese, Wugniu) : ') table.insert(textShow, Consolas(w_pron.wugniu(w_rom))) end add_audio_show(textShow, w_audio, 'wuu') table.insert(textHide, '\n* Wu') table.insert(textHide, '\n** (Shanghainese) ') table.insert(textHide, '\n*** Wiktionary : ') table.insert(textHide, Consolas(w_pron.rom(w_rom))) table.insert(textHide, '\n*** Wugniu : ') table.insert(textHide, Consolas(w_pron.wugniu(w_rom))) table.insert(textHide, '\n*** Sinological IPA (key) : ') table.insert(textHide, format_IPA('/' .. w_pron.ipa_conv(w_rom) .. '/'))           -- add_audio(textHide, w_audio, 'wuu') if args["w_note"] then table.insert(textHide, makeNote(args["w_note"])) end end if x_rom or x_audio then local x_pron = require("Module:hsn-pron") if x_rom then table.insert(textShow, '\n* Xiang (Wiktionary) : ') table.insert(textShow, Consolas(x_pron.rom(x_rom))) end add_audio_show(textShow, x_audio, 'hsn') table.insert(textHide, '\n* Xiang') table.insert(textHide, '\n** (Changsha) ') if x_rom then local x_diff = x_pron.stylediff(x_rom) table.insert(textHide, '\n*** Wiktionary : ') table.insert(textHide, Consolas(x_pron.rom(x_rom))) table.insert(textHide, '\n*** Sinological IPA (key)') table.insert(textHide, x_diff and ' (old-style)' or '') table.insert(textHide, ' : ') table.insert(textHide, format_IPA('/' .. x_pron.ipa(x_rom) .. '/'))               if x_diff then table.insert(textHide, '\n*** Sinological IPA (key) (new-style) : ') table.insert(textHide, format_IPA('/' .. x_pron.ipa(x_rom, 'new') .. '/'))               end end if args["x_note"] then table.insert(textHide, makeNote(args["x_note"])) end end -- combine textShow and textHide into text text = { table.concat(textShow), '\n \n\n', table.concat(textHide), ' '        }        if not c_rom then table.insert(text, "") end

--Part 3 "Dialectal data" if dial ~= "n" and is_single_hanzi then local success, m_dial = pcall(mw.loadData, "Module:zh/data/dial-pron/" .. pagename) if success then local dialPron = {} local temporary = {} if dial and find(dial, "^[0-9\\,]+$") then for element in mw.text.gsplit(dial, ",") do                       table.insert(dialPron, m_dial[tonumber(element)]) end else for _, element in ipairs(m_dial) do                       table.insert(dialPron, element) end end for _, set in ipairs(dialPron) do                   for _, object in ipairs(set[2]) do                        table.insert(temporary, object) end end local rand = gsub("-" .. table.concat(temporary), "[^A-Za-z0-9]", codepoint('%1')) table.insert(text,                   '\n\n \n* ' ..                    ' Dialectal data ' ..                    ' \n' ..                    ' '                )

table.insert(text, '\n{| class="wikitable" ' ..                   'id="' .. rand .. '" style="width:100%; margin:0; ' ..                    'text-align:center; border-collapse: collapse; border-style: hidden;"')

local locStart = '\n|-\n!' local readingStart = table.concat({'\n!style="background:#E8ECFA; width:9em"|',               '  [', tostring(mw.uri.fullUrl("Module:zh/data/dial-pron/" .. pagename, {["action"]="edit"})), ' edit]  '}) local locEnd = ' ' local headclr = 'style="background:#E8ECFA"|' local mclr = 'style="background:#FAF5F0"|' local jclr = 'style="background:#F0F5FA"|' local wclr = 'style="background:#F4F0FA"|' local huclr = 'style="background:#FAF9F0"|' local xclr = 'style="background:#F0F2FA"|' local gclr = 'style="background:#F0FAF3"|' local haclr = 'style="background:#FAF0F6"|' local cclr = 'style="background:#F0F5FA"|' local minclr = 'style="background:#F7FAF0"|' local clrList = { mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, mclr, jclr, jclr, jclr, wclr, wclr, wclr, wclr, huclr, huclr, xclr, xclr, gclr, haclr, haclr, cclr, cclr, cclr, minclr, minclr, minclr, minclr, minclr }               local locList = { table.concat({headclr, "Variety\n!", headclr, "Location"}), table.concat({"rowspan=17 ", mclr, "Mandarin\n!", mclr, "Beijing\n|", mclr}), table.concat({mclr, "Harbin\n|", mclr}), table.concat({mclr, "Tianjin\n|", mclr}), table.concat({mclr, "Jinan\n|", mclr}), table.concat({mclr, "Qingdao\n|", mclr}), table.concat({mclr, "Zhengzhou\n|", mclr}), table.concat({mclr, "Xi'an\n|", mclr}), table.concat({mclr, "Xining\n|", mclr}), table.concat({mclr, "Yinchuan\n|", mclr}), table.concat({mclr, "Lanzhou\n|", mclr}), table.concat({mclr, "Ürümqi\n|", mclr}), table.concat({mclr, "Wuhan\n|", mclr}), table.concat({mclr, "Chengdu\n|", mclr}), table.concat({mclr, "Guiyang\n|", mclr}), table.concat({mclr, "Kunming\n|", mclr}), table.concat({mclr, "Nanjing\n|", mclr}), table.concat({mclr, "Hefei\n|", mclr}), table.concat({"rowspan=3 ", jclr, "Jin\n!", jclr, "Taiyuan\n|", jclr}), table.concat({jclr, "Pingyao\n|", jclr}), table.concat({jclr, "Hohhot\n|", jclr}), table.concat({"rowspan=4 ", wclr, "Wu\n!", wclr, "Shanghai\n|", wclr}), table.concat({wclr, "Suzhou\n|", wclr}), table.concat({wclr, "Hangzhou\n|", wclr}), table.concat({wclr, "Wenzhou\n|", wclr}), table.concat({"rowspan=2 ", huclr, "Hui\n!", huclr, "Shexian\n|", huclr}), table.concat({huclr, "Tunxi\n|", huclr}), table.concat({"rowspan=2 ", xclr, "Xiang\n!", xclr, "Changsha\n|", xclr}), table.concat({xclr, "Xiangtan\n|", xclr}), table.concat({gclr, "Gan\n!", gclr, "Nanchang\n|", gclr}), table.concat({"rowspan=2 ", haclr, "Hakka\n!", haclr, "Meixian\n|", haclr}), table.concat({haclr, "Taoyuan\n|", haclr}), table.concat({"rowspan=3 ", cclr, "Cantonese\n!", cclr, "Guangzhou\n|", cclr}), table.concat({cclr, "Nanning\n|", cclr}), table.concat({cclr, "Hong Kong\n|", cclr}), table.concat({"rowspan=5 ", minclr, "Min\n!", minclr, "Xiamen (Min Nan)\n|", minclr}), table.concat({minclr, "Fuzhou (Min Dong)\n|", minclr}), table.concat({minclr, "Jian'ou (Min Bei)\n|", minclr}), table.concat({minclr, "Shantou (Min Nan)\n|", minclr}), table.concat({minclr, "Haikou (Min Nan)\n|", minclr})}

local function ipa_correct(ipa, location) if location == 22 then return (gsub(ipa, "13", "23")) else return ipa end end

local function fmtDial(text, location) local fmttedPron = {} if text == "" then return "" end for pronunciation in mw.text.gsplit(text, "|") do                       local ipa = match(pronunciation, "^[^%(%)一-龯㐀-䶵～,]+") ipa = gsub(ipa, "([ptk])([0-5])", "%1̚%2") local environ = match(pronunciation, "[%(%)一-龯㐀-䶵～,]*$") or false table.insert(fmttedPron, " /" ..                           tostring(ipa_format(ipa_correct(ipa, location))) .. "/ " .. (environ and "  "..environ.." " or nil)) end return table.concat(fmttedPron, " ") end

for locationNo = 1, 40 do                   for readingNo = 1, #dialPron do                        if readingNo == 1 then table.insert(text, locStart) table.insert(text, locList[locationNo]) end if locationNo == 1 then local situation = dialPron[readingNo][1] table.insert(text, readingStart) table.insert(text, pagename) table.insert(text, (pagename ~= situation and " (" ..                               gsub(situation, pagename, "'''" .. pagename .. "'''") .. ")" or "")) table.insert(text, " ") else table.insert(text, (readingNo == 1 and "" or "\n|" .. clrList[locationNo-1])) table.insert(text, locEnd) table.insert(text, fmtDial(dialPron[readingNo][2][locationNo-1], locationNo)) table.insert(text, " ") end end end table.insert(text, "\n|} ") end end

--Part 4 "Middle Chinese & Old Chinese" local mc_preview, oc_preview local m_ltc_pron, m_och_pron

-- !!!       -- The following function modifies the tables generated by mod:ltc-pron and mod:och-pron, shifting them -- from using "mw-collapsible" to using "vsSwitcher", because the former -- can not collapse on the mobile site and makes Chinese entries a mess. -- It is supposed to be a temporary solution. -- !!!       local function shiftCustomtoggle2Vsswitcher(s) local result result = (s:gsub( '\n%* ]+">', '\n \n* ' ):gsub( ' ▼ (.-) \n{| class="wikitable',               ' %1\n \n{| class="wikitable' ):gsub( '{| class="wikitable mw%-collapsible mw%-collapsed" id="[^"]+"',               '{| class="wikitable"'            ):gsub(                '\n|}$',                '\n|}  '            ))            return result        end

if mc then m_ltc_pron = require("Module:ltc-pron") mc_preview = m_ltc_pron.retrieve_pron(pagename, false, mc, true) if not mc_preview then require('Module:debug').track('zh-pron/Middle Chinese data not found') mc = false end end if oc then m_och_pron = require("Module:och-pron") oc_preview = m_och_pron.generate_show(pagename, oc) if not oc_preview then require('Module:debug').track('zh-pron/Old Chinese data not found') oc = false end end if mc or oc then table.insert(text, '\n\n ') if mc then table.insert(text, shiftCustomtoggle2Vsswitcher(m_ltc_pron.ipa(mc, mc_preview))) end if oc then table.insert(text, shiftCustomtoggle2Vsswitcher(m_och_pron.ipa(oc, oc_preview))) end table.insert(text, " ") end table.insert(text, " ") if namespace == "" then if mc then table.insert(text, '') if is_single_hanzi then if mc_preview:find'k̚$' then table.insert(text, '') elseif mc_preview:find't̚$' then table.insert(text, '') elseif mc_preview:find'p̚$' then table.insert(text, '') end end end if oc then table.insert(text, '') end if not ine(args["cat"]) then table.insert(text, '') end end end

local conv_text = {} --categories if namespace == "" then local catText = args["cat"] or "" local cat_start = '[[Category:'       local cat_end = ']]' if w_rom then w_rom = gsub(w_rom, '%d', '') end local function add_cat(cat_table, name, cat) table.insert(cat_table, cat_start .. name .. cat .. "|" .. sortkey .. cat_end) end

local cats = mw.text.split(catText, ',', true) if pos_aliases_cat[cats[1]] == 'chengyu' then table.insert(cats, 2, 'idioms') end table.insert(cats, 1, "lemmas") for i = 1, #cats do           local cat = cats[i] if cat == "" then break end cat = gsub(cat, '^ +', '') if find(cat, ':') then local cat_split = mw.text.split(cat, ':', true) local lang_name = langname_abbr[cat_split[1]] local category = pos_aliases_cat[cat_split[2]] or cat add_cat(conv_text, 'Chinese ', category) table.insert(conv_text, cat_start .. lang_name .. ' ' .. category .. '|' .. sortkey .. cat_end) else cat = pos_aliases_cat[cat] or cat add_cat(conv_text, 'Chinese ', cat) if m_rom then add_cat(conv_text, 'Mandarin ', cat) end if m_s_rom or m_s_audio then add_cat(conv_text, 'Mandarin ', cat) end if dg_rom or dg_audio then add_cat(conv_text, 'Dungan ', cat) end if c_rom then add_cat(conv_text, 'Cantonese ', cat) end if c_t_rom then add_cat(conv_text, 'Taishanese ', cat) end if g_rom or g_audio then add_cat(conv_text, 'Gan ', cat) end if h_rom and (find(h_rom, 'pfs=.') or find(h_rom, 'gd=.')) or h_audio then add_cat(conv_text, 'Hakka ', cat) end if j_rom or j_audio then add_cat(conv_text, 'Jin ', cat) end if mb_rom or mb_audio then add_cat(conv_text, 'Min Bei ', cat) end if md_rom or md_audio then add_cat(conv_text, 'Min Dong ', cat) end if mn_rom or mn_audio then add_cat(conv_text, 'Min Nan ', cat) end if mn_t_rom or mn_t_audio then add_cat(conv_text, 'Teochew ', cat) end if w_rom or w_audio then add_cat(conv_text, 'Wu ', cat) end if x_rom or x_audio then add_cat(conv_text, 'Xiang ', cat) end end end if m_s_rom or m_s_audio then add_cat(conv_text, 'Sichuanese Mandarin', '') end table.insert(conv_text, cat_start .. 'Chinese terms with IPA pronunciation|' .. sortkey .. cat_end) if is_single_hanzi then table.insert(conv_text, cat_start .. 'Chinese hanzi|' .. sortkey .. cat_end) end end

local output = table.concat(text) .. table.concat(conv_text) if namespace ~= '' then output = gsub(output, "%[%[Category:[^%]]+%]%]", "") end return output end

return export