local export = {}
local m_zh = require("Module:zh")
local sub = mw.ustring.sub
local gsub = mw.ustring.gsub
local match = mw.ustring.match
local function link(text, make_link)
return '<span lang="zh" class="Hani">' .. (make_link and ('[[' .. text .. '#漢語|' .. text .. ']]') or text) .. '</span>'
end
local function get_occurrence(content)
local _, occurrence = content:gsub("zh%-pron", "zh-see"):gsub("zh%-see", "")
return occurrence
end
function export.show(frame)
local non_lemma_type = {
['s'] = '簡化字', ['simp'] = '簡化字', ['simplified'] = '簡化字', ['簡化字'] = '簡化字', ['简化字'] = '簡化字', ['簡化'] = '簡化字', ['简化'] = '簡化字', ['簡'] = '簡化字', ['简'] = '簡化字', ['j'] = '簡化字', ['jian'] = '簡化字',
['fs'] = '一簡字（1964-1986）',
['fsv'] = '一簡字（1964-1986）和異體字',
['ss'] = '二簡字',
['ssv'] = '二簡字和異體字',
['sgs'] = '新加坡簡體字（1969–1976）',
['sgsv'] = '新加坡簡體字（1969–1976）和異體字',
['sgss'] = '新加坡簡體字（1969–1976）和二簡字',
['sgssv'] = '新加坡簡體字（1969–1976）、二簡字和異體字',
['rocs'] = '第一批簡體字表（1935–1936）', -- 中華民國教育部
['rocsv'] = '第一批簡體字表（1935–1936）和異體字',
['rocss'] = '第一批簡體字表（1935–1936）和二簡字',
['rocssv'] = '第一批簡體字表（1935–1936）、二簡字和異體字',
['rocsgs'] = '第一批簡體字表（1935–1936）和新加坡簡體字（1969–1976）',
['rocsgsv'] = '第一批簡體字表（1935–1936）、新加坡簡體字（1969–1976）和異體字',
['rocsgssv'] = '第一批簡體字表（1935–1936）、新加坡簡體字（1969–1976），二簡字和異體字',
['rocfs'] = '第一批簡體字表（1935–1936）和一簡字（1964-1986）',
['rocfsv'] = '第一批簡體字表（1935–1936）、一簡字（1964-1986）和異體字',
['rocfsgs'] = '第一批簡體字表（1935–1936）、一簡字（1964-1986）和新加坡簡體字（1969–1976）',
['rocfsgsv'] = '第一批簡體字表（1935–1936）、一簡字（1964-1986）、新加坡簡體字（1969–1976）和異體字',
['rocfsgssv'] = '第一批簡體字表（1935–1936）、一簡字（1964-1986）、新加坡簡體字（1969–1976）、二簡字和異體字',
['ds'] = '漢字簡化方案草案（1955）', -- 中華人民共和國國務院
['dsv'] = '漢字簡化方案草案（1955）和異體字',
['dss'] = '漢字簡化方案草案（1955）和二簡字',
['dssv'] = '漢字簡化方案草案（1955）、二簡字和異體字',
['dsgs'] = '漢字簡化方案草案（1955）和新加坡簡體字（1969–1976）',
['dsgsv'] = '漢字簡化方案草案（1955）、新加坡簡體字（1969–1976）和異體字',
['dsgssv'] = '漢字簡化方案草案（1955）、新加坡簡體字（1969–1976）、二簡字和異體字',
['rocds'] = '第一批簡體字表（1935–1936）和漢字簡化方案草案（1955）',
['rocdsv'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）和異體字',
['rocdss'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）和二簡字',
['rocdssv'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）、二簡字和異體字',
['rocdsgs'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）和新加坡簡體字（1969–1976）',
['rocdsgsv'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）、新加坡簡體字（1969–1976）和異體字',
['rocdsgssv'] = '第一批簡體字表（1935–1936）、漢字簡化方案草案（1955）、新加坡簡體字（1969–1976）、二簡字和異體字',
['ns'] = '非標準簡化字',
['a'] = '古字', ['ancient'] = '古字', ['古字'] = '古字', ['古'] = '古字', ['g'] = '古字', ['gu'] = '古字',
['o'] = '淘汰舊字', ['obsolete'] = '淘汰舊字',
['v'] = '異體字', ['var'] = '異體字', ['variant'] = '異體字', ['異體'] = '異體字', ['异体'] = '異體字', ['異'] = '異體字', ['异'] = '異體字', ['y'] = '異體字', ['yi'] = '異體字',
['vt'] = '傳統異體字',
['av'] = '古代異體字',
['is'] = '網路俚語異體字',
['sv'] = '簡體字和異體字',
['svt'] = '簡體字和傳統異體字',
['hv'] = '有辭書收錄過的異體字',
['hdv'] = '有辭書收錄過的異體字',
['hduo'] = '有辭書收錄過的非正體字',
['ha'] = '有辭書收錄過的古體字',
['hda'] = '有辭書收錄過的古體字',
['poj'] = '[[白話字]]',
['err'] = '訛字', ['corrupt'] = '訛字', ['c'] = '訛字', ['訛'] = '訛字', ['讹'] = '訛字', ['e'] = '訛字',
['l'] = '借字',
['all'] = '簡體字、異體字、淘汰舊字或異體字',
}
local args = frame:getParent().args
local title = args[1]
local curr_title = mw.title.getCurrentTitle().subpageText
local content = mw.title.new(title):getContent()
local title_exists = content ~= nil
local simp = args["simp"] or false
local non_lemma_abbrev = args[2] or ""
local categories = ''
if title == curr_title then
return error("The soft-directed item is the same as the page title.")
end
if content then
if not match(content, "==漢語==") then
categories = categories .. '[[Category:漢語紅鏈/zh-see]]'
elseif not match(content, "zh%-pron") and not match(content, "zh%-see") then
require('Module:debug').track('zh-see/unidirectional reference to variant')
elseif not match(content, curr_title) then
require('Module:debug').track('zh-see/unidirectional reference variant→orthodox')
end
occurrence = get_occurrence(content)
if match(content, "zh%-see") and occurrence == 1 then
new_title = match(content, "zh%-see%|([^%|%}]+)")
if non_lemma_abbrev == "" and occurrence == 1 and match(content, "zh%-see%|([^%|%}]+)%|v") then
chain = true
end
content = mw.title.new(new_title):getContent()
end
end
if content then
content = gsub(content, "zh%-forms", "Ѭ")
content = gsub(content, "zh%-pron", "Ꙁ")
if non_lemma_abbrev == "" then
template = mw.ustring.match(content, "{{Ѭ[^}]*}}") or false
if template then
for forms_template in mw.ustring.gmatch(content, "{{Ѭ[^}]*}}") do
if match(forms_template, curr_title) then
if match(forms_template, "|s[0-9]*=" .. curr_title) then
non_lemma_abbrev = non_lemma_abbrev .. "s"
end
if match(forms_template, "|t[0-9]*=" .. curr_title) then
non_lemma_abbrev = non_lemma_abbrev .. "vt"
end
if match(forms_template, "|alt=[^|}\n]*" .. curr_title) then
non_lemma_abbrev = non_lemma_abbrev .. "v"
end
break
end
end
end
end
end
local non_lemma_cat = non_lemma_type[non_lemma_abbrev ~= "" and non_lemma_abbrev or 's'] or '簡體字'
local note = (content or mw.title.getCurrentTitle().nsText ~= "") and "" or '[[Category:未有頁面的漢字]]'
local gloss_text = args[3] or (content and require("Module:zh/extract").extract_gloss(gsub(content, "Ѭ", "zh%-forms"), true) or "")
local box =
'{| class="wikitable' .. (match(non_lemma_cat, '簡') and ' mw-collapsible mw-collapsed' or '') ..
'" style="border:1px solid #797979; margin-left: 1px; text-align:left; min-width:' .. (chain and 80 or 70) .. '%"' ..
'\n|-\n| style="background-color: #eeeeee; padding-left: 0.5em" | \'\'\'關於「\'\'\'' .. (non_lemma_abbrev=="poj" and curr_title or link(mw.ustring.gsub(curr_title, '(.)', '-{[[%1#漢語|%1]]}-'), false)) ..
'\'\'\'」的發音和釋義，請看<span style="font-size:120%">「-{' .. link(title, true) .. '}-」</span>' .. (gloss_text ~= "" and ('（「' .. gloss_text .. '」）') or '') .. '。\'\'\'' ..
'<br>此' .. (mw.ustring.len(title) == 1 and '字' or '詞' ) .. '「-{' .. link(curr_title) .. '}-」是「-{' .. link(title) .. '}-」的' .. non_lemma_cat ..'。'..
(match(non_lemma_cat, '簡') and [=[
|-
| class="mw-collapsible-content" style="background-color: #F5DEB3; font-size: smaller" | <b>註解：</b>
* [[w:簡體中文|簡體字]]主要在中國大陸、馬來西亞和新加坡使用。
* [[w:繁體中文|繁體字]]主要在香港、澳門和臺灣使用。]=] or '') ..
'\n|}' .. note
local cat = { "variant", "simplified", "obsolete" }
local m_cat = require("Module:zh-cat")
for _, word in ipairs(cat) do
if match(non_lemma_cat, word) then
categories = categories .. m_cat.categorize(word)
end
end
if content then
local part_a, part_b, part_c = '{{Ѭ[^%}]+' .. curr_title .. '[^%}]*}}', '[^ѬꙀ]+', '({{Ꙁ.+\n%|cat%=[^\n]*\n?}})'
local match_group = mw.ustring.len(gsub(content, "[^Ѭ]", "")) == 1
and mw.ustring.gmatch(content, '{{Ꙁ[^Ꙁ]+%|cat%=[^\n]*\n?}}')
or (match(content, part_a)
and (match(content, part_a .. part_b .. part_c)
and mw.ustring.gmatch(content, part_a .. part_b .. part_c)
or mw.ustring.gmatch(content, part_c .. part_b .. part_a))
or mw.ustring.gmatch(content, part_c))
for match_result in match_group do
local function find_pron(variety)
return match(match_result, '|' .. variety .. '=([^|}\n]*)') or ''
end
if non_lemma_abbrev == "poj" then
categories = categories .. frame:expandTemplate{
title = "Template:zh-pron",
args = {
['mn'] = find_pron('mn'),
['cat'] = find_pron('cat'),
['only_cat'] = 'yes',
}
}
else
categories = categories .. frame:expandTemplate{
title = "Template:zh-pron",
args = {
['m'] = find_pron('m'),
['c'] = find_pron('c'),
['c-t'] = find_pron('c%-t'),
['dg'] = find_pron('dg'),
['g'] = find_pron('g'),
['h'] = find_pron('h'),
['j'] = find_pron('j'),
['mb'] = find_pron('mb'),
['md'] = find_pron('md'),
['mn'] = find_pron('mn'),
['mn-t'] = find_pron('mn%-t'),
['w'] = find_pron('w'),
['x'] = find_pron('x'),
['cat'] = find_pron('cat'),
['only_cat'] = 'yes',
}
}
end
end
if non_lemma_abbrev ~= "poj" then
local match_cat = mw.ustring.match(content, "{{zh%-cat%|([^}]+)}}") or nil
if match_cat then
match_cat_group = mw.text.split(match_cat, "|")
categories = categories .. frame:expandTemplate{
title = "Template:zh-cat",
args = match_cat_group
}
end
--local match_label = mw.ustring.gmatch(content, "{{lb%|zh%|([^}]+)}}") or nil
--if match_label then
-- local lang = require("Module:languages").getByCode("zh")
-- for match_label_item in match_label do
-- local match_label_group = mw.text.split(match_label_item, "|")
-- local label_text = require("Module:labels").show_labels(match_label_group, lang)
-- categories = categories .. (mw.ustring.match(label_text, "%[%[Category:[^%]]+%]%]") or "")
-- end
--end
local match_char_comp = mw.ustring.match(content, "{{zh%-character component%|") or nil
--mw.log(match_char_comp)
if match_char_comp then
categories = categories .. frame:expandTemplate{
title = "Template:zh-cat",
args = { "漢字部件" }
}
end
else
categories = categories .. "[[Category:閩南語白話字]]"
end
end
return box .. categories
end
return export
