模組:Zh
The subpages of this module serve as the place of data storage for various Chinese modules and templates, in particular Module:zh and Module:zh-usex.
子页面
- Module:zh/data/ts – 繁体到简体转换
- Module:zh/data/st – 简体到繁体转换
- Module:zh/data/glosses – Character glosses
- Module:zh/data/glyph-data – 歷史字形資料
- Module:zh/data/wordlist/1, 2, 3 – 參見
{{zh-der/new}}
- Module:zh/data/dial
- Module:zh/data/dial-pron – 方言發音模組
- Module:zh/data/dial-syn – 方言同義詞模組
- Module:zh/data/ltc-pron – 中古漢語發音模組
- Module:zh/data/och-pron-BS – 上古漢語發音(白-沙)模組
- Module:zh/data/och-pron-ZS – 上古漢語發音(鄭張)模組
- Module:zh/data/cmn-pron – 官話字音
- Module:zh/data/yue-pron – 粵語字音
- Module:zh/data/yue-word
- Module:zh/data/Jyutping character
- Module:zh/data/cmn-hom – 官話同音詞資料
- Module:zh/data/cmn-tag – Mandarin regional qualifier data for characters
- Module:zh/data/nan-pron
- Module:zh/data/hak-pron
- Module:zh/data/Christian-syn
local m_str_utils = require("Module:string utilities")
local m_ts = mw.loadData("Module:zh/data/ts")
local m_st = mw.loadData("Module:zh/data/st")
local lang = require("Module:languages").getByCode("zh")
local codepoint = m_str_utils.codepoint
local find = m_str_utils.find
local len = m_str_utils.len
local split = m_str_utils.split
local sub = m_str_utils.sub
local export = {}
function export.ts_determ(f)
local text = type(f) == "table" and f.args[1] or f
local sc = lang:findBestScript(text):getCode()
return sc == "Hani" and "both" or sc == "Hant" and "trad" or "simp"
end
function export.ts(f)
local text = type(f) == "table" and f.args[1] or f
if not text then return "" end
return (text:gsub("[\194-\244][\128-\191]*", m_ts))
end
function export.st(f)
local text = type(f) == "table" and f.args[1] or f
if not text then return "" end
return (text:gsub("[\194-\244][\128-\191]*", m_st))
end
function export.py(text, comp, pos, p, is_erhua)
require("Module:debug").track("zh/py")
local m_cmn_pron = mw.loadData("Module:zh/data/cmn-pron")
if not is_erhua then is_erhua = false end
if type(text) == "table" then
text, comp, pos, p, is_erhua = text.args[1], text.args[2], text.args[3], text.args[4], text.args[5]
end
comp = comp or ''
local q = {}
local sum = 0
local length = len(text)
if is_erhua then length = length - 1 end
local textconv = text
text = ''
if comp ~= '' and comp ~= '12' and comp ~= '21' and not ((pos == 'cy' or pos == 'Idiom' or pos == 'idiom') and length == 4) and not is_erhua then
for i = 1, len(comp) do
sum = sum + tonumber(sub(comp,i,i))
q[sum] = 'y'
end
end
if not p then p={} end
local initial = true
for i = 1, length do
if p[i] and p[i] ~= '' then --pronunciation supplied
text = text .. p[i]
else
local char = sub(textconv,i,i)
char = m_cmn_pron.py[char] or m_cmn_pron.py[export.ts(char)] or char
if not is_erhua and not initial and find(char,'^[aoeāōēáóéǎǒěàòè]') then
text = text .. "'"
end
text = text .. char
initial = char == sub(textconv,i,i)
and sub(textconv,i-3,i) ~= "</b>" --checks for closing bold tag
and (i-2 == 1 or sub(textconv,i-2,i) ~= "<b>" or sub(textconv,i-3,i) == "^<b>") --checks for opening bold tag
and (i-3 == 1 or sub(textconv,i-3,i) ~= "^<b>") --checks for opening bold tag with capitalization
end
if q[i] == 'y' and i ~= length and not is_erhua then text = text .. ' ' end
end
text = text:gsub("<b>'", "'<b>") --fix bolding of apostrophe
if is_erhua then text = text .. 'r' end
if pos == 'pn' or pos == 'propn' then
local characters = split(text, ' ')
for i=1,#characters do
characters[i] = mw.language.getContentLanguage():ucfirst(characters[i])
end
text = table.concat(characters,' ')
end
return text
end
do
local function get_pron(text, startpoint, address)
local success, data = pcall(mw.loadData, ("Module:zh/data/" .. address)
:format((codepoint(text) - startpoint) / 1000)
)
return success and data[text] or false
end
function export.check_pron(text, variety, length, usex)
if type(text) == "table" then
text, variety, usex = text.args[1], text.args[2], text.args[3]
length = len(text)
usex = usex and usex ~= ""
end
if not text then
return
elseif variety == "cmn" and length == 1 then
local py = mw.loadData("Module:zh/data/cmn-pron").py
return py[text] or py[m_ts[text]] or false
elseif variety == "yue" then
if length == 1 then
return (usex and mw.loadData("Module:zh/data/yue-pron").jyutping or -- used for {{zh-x}}
mw.loadData("Module:zh/data/Jyutping character"))[text] or -- used for {{subst:zh-new}}
false
end
local result = get_pron(text, 51, "yue-word/%03d")
if result and not require("Module:yue-pron/check")(text, result) then
require("Module:debug").track("zh/yue")
require("Module:debug").track("zh/yue/"..text)
end
return result
elseif variety == "hak" then
return get_pron(text, 19968, "hak-pron/%02d")
elseif variety == "nan-hbl" or variety == "nan" then
return get_pron(text, 19968, "nan-pron/%03d")
end
return false
end
end
return export