模組:Character info
這個模板為{{character info/new}}自動產生內容。
local m_unicode = require('Module:Unicode data')
local char_to_script = require('Module:scripts').charToScript
local export = {}
local dingbat_scripts = {
["Zsym"] = true;
["Zmth"] = true;
["Zyyy"] = true;
}
local function page_exists(title)
local ok, title_obj = pcall(mw.title.new, title)
if ok and title_obj then
local ok, exists = pcall(function() return title_obj.exists end)
return ok and exists
else
return false
end
end
function export.exotic_symbol_warning(frame)
local title = mw.title.getCurrentTitle()
if title.exists then
return ""
end
if mw.ustring.len(title.fullText) ~= 1 then
return ""
end
local codepoint = mw.ustring.codepoint(title.fullText)
local script_code = char_to_script(codepoint)
if dingbat_scripts[script_code] then
return frame:expandTemplate { title = "editnotice-exotic symbols" }
end
return ""
end
local function get_codepoint(codepoint, param_name)
if codepoint then
codepoint = mw.text.trim(codepoint)
codepoint = tonumber(codepoint) or mw.text.decode(codepoint)
if (type(codepoint) == "string") and (mw.ustring.len(codepoint) == 1) then
codepoint = mw.ustring.codepoint(codepoint)
elseif type(codepoint) ~= "number" then
error("Unrecognised string given for the " .. param_name
.. " parameter")
end
end
return codepoint
end
function export._show(args, parent_title)
local codepoint = args.codepoint or args[1] or "";
local image
local title = mw.title.getCurrentTitle()
local to_boolean = require('Module:yesno')
local namespace = mw.title.getCurrentTitle().nsText
if codepoint ~= "" then
codepoint = get_codepoint(codepoint, "codepoint")
else
if title.fullText == parent_title then
codepoint = 0xfffd
elseif mw.ustring.len(title.fullText) == 1 then
codepoint = mw.ustring.codepoint(title.fullText)
else
if title.nsText == "Template" then return "" end
error("頁名非單一Unicode字元")
end
end
args.image = args.image and mw.text.trim(args.image)
if args.image == "" then
image = nil
else
image = args.image or m_unicode.lookup_image(codepoint)
end
local table_markup = {}
table.insert(table_markup,
'{| class="wikitable floatright" style="width:25em;"\n')
if image then
if not image:match("\127") then -- <hiero> tags generate these; pass them through
if image:match("^%[?%[?[Ff]ile:") or image:match("^%[?%[?[Ii]mage:") then
image = image:gsub("^%[%[", ""):gsub("^[Ff]ile:", ""):gsub("^[Ii]mage:", ""):gsub("|.*", ""):gsub("]]", "")
end
local category = "[[Category:有圖像的字元框|*" .. string.format("%010d", codepoint) .. "]]"
image = "[[File:" .. image .. "|120x140px]]"
if namespace == "" then
image = image .. category
end
end
table.insert(table_markup,
('|-\n| colspan="2" style="text-align: center;" | %s<br/>%s\n'):format(
image, args.caption or ""
)
)
elseif args.caption then
table.insert(table_markup,
('|-\n| colspan="2" style="text-align: center;" | %s\n'):format(
args.caption
)
)
end
local script_code = args.sc or char_to_script(codepoint)
local script_data = mw.loadData("Module:scripts/data")[script_code]
or error("No data for script code " .. script_code .. ".")
local script_name = script_data.canonicalName
local NAMESPACE = title.namespace
local cat_name
if not args.nocat and ((NAMESPACE == 0) or (NAMESPACE == 100)) then -- main and Appendix
if script_data.character_category ~= nil then
-- false means no category, overriding the default below
cat_name = script_data.character_category or nil
elseif script_name then
cat_name = script_name .. "字元"
end
end
local block_name = mw.text.encode(args.block or m_unicode.lookup_block(codepoint))
local aliases
if args.aliases == "" then
aliases = nil
else
aliases = mw.loadData('Module:Unicode data/aliases')[codepoint]
end
local function parse_aliases(aliases)
local result = {}
if aliases then
local classif = {}
for i, alias in ipairs(aliases) do
if not classif[alias[1]] then
classif[alias[1]] = {}
end
table.insert(classif[alias[1]], mw.text.encode(alias[2]))
end
if classif.correction then
for i, name in ipairs(classif.correction) do
local category = '[[Category:有正確名稱的字元框]]'
if namespace == "" then
table.insert(result,
('[[Category:有正確名稱的字元框]]正確名稱：%s'):format(
name
)
)
else
table.insert(result,
('正確名稱：%s'):format(
name
)
)
end
end
end
if classif.alternate then
for i, name in ipairs(classif.alternate) do
local category = '[[Category:有替代名稱的字元框]]'
if namespace == "" then
table.insert(result,
('[[Category:有替代名稱的字元框]]替代名稱：%s'):format(
name
)
)
else
table.insert(result,
('替代名稱：%s'):format(
name
)
)
end
end
end
if classif.abbreviation then
local category = '[[Category:有縮寫的字元框]]'
if namespace == "" then
table.insert(result,
('[[Category:有縮寫的字元框]]縮寫：%s'):format(
table.concat(classif.abbreviation, ", ")
)
)
else
table.insert(result,
('縮寫：%s'):format(
table.concat(classif.abbreviation, ", ")
)
)
end
end
local parsed_result = table.concat(result, ", ")
return '<div>(' .. parsed_result .. ')</div>'
end
return ""
end
local li, vi, ti = nil, nil, nil
if block_name == "Hangul Syllables" then
local m_Kore = require('Module:ko-hangul')
li, vi, ti = m_Kore.syllable2JamoIndices(codepoint)
end
local initial_to_letter = { [0] =
0x3131, 0x3132, 0x3134, 0x3137, 0x3138, 0x3139, 0x3141, 0x3142,
0x3143, 0x3145, 0x3146, 0x3147, 0x3148, 0x3149, 0x314A, 0x314B,
0x314C, 0x314D, 0x314E,
}
local vowel_to_letter = { [0] =
0x314F, 0x3150, 0x3151, 0x3152, 0x3153, 0x3154, 0x3155, 0x3156,
0x3157, 0x3158, 0x3159, 0x315A, 0x315B, 0x315C, 0x315D, 0x315E,
0x315F, 0x3160, 0x3161, 0x3162, 0x3163,
}
local final_to_letter = {
0x3131, 0x3132, 0x3133, 0x3134, 0x3135, 0x3136, 0x3137, 0x3139,
0x313A, 0x313B, 0x313C, 0x313D, 0x313E, 0x313F, 0x3140, 0x3141,
0x3142, 0x3144, 0x3145, 0x3146, 0x3147, 0x3148, 0x314A, 0x314B,
0x314C, 0x314D, 0x314E, -- KIYEOK-RIEUL = ???
}
local function parse_composition()
local result = nil
if block_name == "Hangul Syllables" then
result = ((ti ~= 0) and
'<big class="Kore" lang="">[[&#%u;]] + [[&#%u;]] + [[&#%u;]]</big>' or
'<big class="Kore" lang="">[[&#%u;]] + [[&#%u;]]</big>'):format(
initial_to_letter[li],
vowel_to_letter[vi],
final_to_letter[ti]
)
else
local nfd = mw.ustring.toNFD(mw.ustring.char(codepoint))
if mw.ustring.len(nfd) ~= 1 then
local compo = {}
for nfdcp in mw.ustring.gcodepoint(nfd) do
local dotted_circle = (m_unicode.is_combining(nfdcp) and "◌" or "")
local link_target = m_unicode.get_entry_title(nfdcp)
if not link_target or not page_exists(link_target) then
link_target = nil
end
local script = char_to_script(nfdcp)
local character_text =
link_target and ('[[&#%u;|<span class="%s">%s&#%u;</span> [U+%04X]]]')
:format(nfdcp, script, dotted_circle, nfdcp, nfdcp)
or ('<span class="%s">%s&#%u;</span> [U+%04X]')
:format(script, dotted_circle, nfdcp, nfdcp)
table.insert(compo, '<span class="character-sample-secondary">' .. character_text .. '</span> ')
end
result = table.concat(compo, " + ")
end
end
if result then
return "組成", result, "[[Category:由多個字符組成的字元框]]"
end
return nil
end
-- [[ Egyptian Hieroglyphs
local function parse_gardiner()
local result = nil
if args.gardiner then
result =
(
'[http://vincent.euverte.free.fr/Rosette/Rosette_410.php?Hiero=%s&Lang=E %s]\n'):format(
args.gardiner, args.gardiner
)
return "加汀納編號", result, "[[Category:有添加資訊的埃及聖書體字元框]]"
end
return nil
end
local function parse_mdc()
local result = nil
if args.mdc then
result = args.mdc
return "Manuel de Codage", result, "[[Category:Character boxes with additional information for Egyptian Hieroglyphs]]"
end
return nil
end
local function parse_egpz()
local result = nil
if args.egpz then
result = args.egpz
return "EGPZ 1.0", result, "[[Category:Character boxes with additional information for Egyptian Hieroglyphs]]"
end
return nil
end
-- ]]
local function middle_part()
local rows = {}
local function insert_row(row_title, row_contents, row_category)
if row_contents then
table.insert(rows,
('<tr><td style="text-align: left">%s:</td><td>%s%s</td></tr>'):format(row_title, row_contents, row_category))
end
end
insert_row(parse_composition())
insert_row(parse_gardiner())
insert_row(parse_egpz())
insert_row(parse_mdc())
if rows[1] then
return ('<table style="margin: 0 auto;">%s</table>')
:format(table.concat(rows, ""))
end
return ""
end
local function present_codepoint(codepoint, np, script, combining, name, printable, title)
local display
local link_target
if combining then
combining = to_boolean(combining)
else
combining = m_unicode.is_combining(codepoint)
end
if printable then
printable = to_boolean(printable)
else
printable = m_unicode.is_printable(codepoint)
end
local char = mw.ustring.char(codepoint)
mw.log(char)
if title == "self" or page_exists(char) then
link_target = char
elseif title ~= "" then
link_target = m_unicode.get_entry_title(codepoint)
end
if printable then
display = ('<span class="character-sample-secondary %s">%s&#x%04X;</span>'):format(
script or char_to_script(codepoint),
combining and "◌" or "", codepoint
)
end
local arrow_and_maybe_char
if np then
arrow_and_maybe_char = (display or "") .. ' →'
else
arrow_and_maybe_char = '← ' .. (display or "")
end
local text = ('<span title="%s">%s<br><small>[U+%04X]</small></span>')
:format(mw.text.encode(name or m_unicode.lookup_name(codepoint)),
arrow_and_maybe_char, codepoint)
if link_target then
return ('[[' .. link_target .. '|' .. text .. ']]')
else
return text
end
end
local function get_next(codepoint, step)
-- Skip past noncharacters and reserved characters (Cn), private-use
-- characters (Co), surrogates (Cs), and control characters (Cc), all
-- of which have a label beginning in "<" rather than a proper name.
if step < 0 and 0 < codepoint or step > 0 and codepoint < 0x10FFFF then
repeat
codepoint = codepoint + step
until m_unicode.lookup_name(codepoint):sub(1, 1) ~= "<"
or not (0 < codepoint and codepoint < 0x10FFFF)
end
return codepoint
end
local previous_codepoint =
get_codepoint(args.previous_codepoint, "previous_codepoint")
and tonumber(args.previous_codepoint, 16) or get_next(codepoint, -1)
local next_codepoint = get_codepoint(args.next_codepoint, "next_codepoint")
and tonumber(args.next_codepoint, 16) or get_next(codepoint, 1)
local combining
if args.combining then
combining = to_boolean(args.combining)
else
combining = m_unicode.is_combining(codepoint)
end
table.insert(table_markup,
'|-\n| style="width: 70px;" colspan="2" | ' ..
'<table>' ..
'<tr>' ..
'<td>' ..
('<span class="character-sample-primary %s">%s&#%u;</span>')
:format(script_code, combining and "◌" or "", codepoint) ..
'</td>' ..
'<td>' ..
(' [https://util.unicode.org/UnicodeJsps/character.jsp?a=%.4X U+%.4X]'):format(codepoint, codepoint) ..
', [[w:XML与HTML字符实体引用列表|&#' .. codepoint .. ';]]\n' ..
'<div class="character-sample-name">' ..
mw.text.encode(args.name or m_unicode.lookup_name(codepoint)) ..
'</div>' ..
parse_aliases(aliases) ..
'</td>' ..
'</tr>' ..
'</table>'
)
table.insert(table_markup,
middle_part()
)
local previous_unassigned_first = previous_codepoint + 1
local previous_unassigned_last = codepoint - 1
local next_unassigned_first = codepoint + 1
local next_unassigned_last = next_codepoint - 1
local left_unassigned_text
local right_unassigned_text
if previous_codepoint == 0 then
previous_unassigned_first = 0
end
if previous_unassigned_first <= previous_unassigned_last or next_unassigned_first <= next_unassigned_last then
if previous_unassigned_first < previous_unassigned_last then
left_unassigned_text = ('[未分配：U+%.4X–U+%.4X]'):format(previous_unassigned_first, previous_unassigned_last)
elseif previous_unassigned_first == previous_unassigned_last then
left_unassigned_text = ('[未分配：U+%.4X]'):format(previous_unassigned_first)
end
if next_unassigned_first < next_unassigned_last then
right_unassigned_text = ('[未分配：U+%.4X–U+%.4X]'):format(next_unassigned_first, next_unassigned_last)
elseif next_unassigned_first == next_unassigned_last then
right_unassigned_text = ('[未分配：U+%.4X]'):format(next_unassigned_first)
end
end
local unassignedsRow =
mw.html.create('table'):css('width', '100%'):css('font-size', '80%'):css('white-space', 'nowrap')
:tag('tr')
:tag('td'):css('width', '50%'):css('text-align', 'left'):wikitext(left_unassigned_text or ''):done()
:tag('td'):css('width', '50%'):css('text-align', 'right'):wikitext(right_unassigned_text or ''):done()
:allDone()
table.insert(table_markup, tostring(unassignedsRow) ..'\n')
local previous_codepoint_text = ""
local next_codepoint_text = ('%s\n')
:format(present_codepoint(next_codepoint, true,
args.next_codepoint_sc, args.next_codepoint_combining,
args.next_codepoint_name, args.next_codepoint_printable,
args.next_codepoint_title))
if previous_codepoint > 0 then
previous_codepoint_text = ('%s\n')
:format(present_codepoint(previous_codepoint, false,
args.previous_codepoint_sc, args.previous_codepoint_combining,
args.previous_codepoint_name, args.previous_codepoint_printable,
args.previous_codepoint_title))
end
local block_name_text = ('[[Appendix:Unicode/%s|%s]]')
:format(block_name, block_name)
if namespace == "" then
block_name_text = block_name_text .. ('[[Category:%s區段|*%010d]]\n')
:format(block_name, codepoint)
else
block_name_text = block_name_text .. '\n'
end
local lastRow =
mw.html.create('table'):css('width', '100%'):css('text-align', 'center')
:tag('tr')
:tag('td'):css('width', '20%'):wikitext(previous_codepoint_text):done()
--:tag('td'):css('width', '15%')
-- :tag('span'):wikitext(left_unassigned_text and "'''...'''" or ""):attr('title', left_unassigned_text or ""):done():done()
:tag('td'):css('width', '60%'):css('font-size', '110%'):css('font-weight', 'bold'):wikitext(block_name_text)
--:tag('td'):css('width', '15%')
-- :tag('span'):wikitext(right_unassigned_text and "'''...'''" or ""):attr('title', right_unassigned_text or ""):done():done()
:tag('td'):css('width', '20%'):wikitext(next_codepoint_text):done()
:allDone()
table.insert(table_markup, tostring(lastRow) ..'\n')
table.insert(table_markup, '|}')
if cat_name and namespace == "" then
table.insert(table_markup, "[[Category:" .. cat_name .. "| " .. mw.ustring.char(codepoint) .. "]]")
end
table.insert(table_markup, require("Module:TemplateStyles")("Template:character info/style.css"))
return table.concat(table_markup)
end
function export.show(frame)
local parent_frame = frame:getParent()
return export._show(parent_frame.args, parent_frame:getTitle())
end
return export