Zoran: Pywikibot 6.4.0

2021-07-15T20:55:57Z

Pywikibot 6.4.0

New page

local p = {}
local unicode_convert = require('Module:Unicode convert')
local numcr2namecr = mw.loadData('Module:Numcr2namecr')
local yesno = require('Module:Yesno')
local GB18030_cache = {}

-- Input e.g. " A B FF ", output "10 11 255"
local function hex2dec_words(s)
local x = mw.text.split(mw.text.trim(s or ''), '%s+')
if #x == 1 and x[1] == '' then return '' end
for i = 1, #x do
x[i] = tonumber(x[i], 16) or 0
end
return table.concat(x, ' ')
end

-- Wrapper to let us replace Template:UTF-8 and Template:UTF-16
local function template(title, args)
if title == 'UTF-8' then
return unicode_convert.getUTF8{ args = args }
elseif title == 'UTF-16' then
return unicode_convert.getUTF16{ args = args }
elseif title == 'hex2dec' then
return tostring(tonumber(args[1], 16))
elseif title == 'charmap/numcharref' then
local format = args['base'] == 'dec' and '&#%d;<wbr>' or '&#x%02X;<wbr>'
return format:format(tonumber(args[1], 16))
elseif title == 'charmap/showchar' then
return '&#x' .. mw.text.trim(args[1]) .. ';'
elseif title == 'GB18030' then
if GB18030_cache[args[1]] then
if args['base'] == 'dec' then
return mw.getCurrentFrame():expandTemplate{
title = 'GB18030/decimal', args = { GB18030_cache[args[1]] }}
else return GB18030_cache[args[1]] end
elseif os.clock() > 7 then
return "''currently unavailable''"
else
GB18030_cache[args[1]] = mw.getCurrentFrame():expandTemplate{title = 'GB18030', args = {args[1]}}
if args['base'] == 'dec' then
return hex2dec_words(GB18030_cache[args[1]])
else return GB18030_cache[args[1]] end
end
else
return mw.getCurrentFrame():expandTemplate{ title = title, args = args }
end
end

local function _multiUTF(args)
local code = args[1] or ''
local encoding = args[2] or 'UTF-8'
local output = ''
local pstp_sep = encoding:sub(1, 8) == 'charmap/' and '' or ' '
local words = mw.text.split(mw.text.trim(code), '%s')

if not (encoding == 'charmap/showchar' or encoding == 'hex2dec') then
output = '|| '
for i = 1, #words do
output = output .. template(encoding, {words[i], base = 'dec'})
if i == 4 then break end
output = output .. pstp_sep
end
output = output .. '|| '
end

for i = 1, #words do
output = output .. template(encoding, {words[i]})
if i == 4 then break end
output = output .. pstp_sep
end

return output
end

p.multiUTF = function(frame) -- temporary
return _multiUTF(frame.args)
end

local function paramCoalesce(args, arg1, arg2)
if args[arg1] ~= nil and args[arg1] ~= '' then return args[arg1] end
if arg2 ~= nil and args[arg2] ~= nil and args[arg2] ~= '' then return args[arg2] end
return nil
end

p.alt = function(frame, n)
n = n or frame.args[1]
local args = frame:getParent().args
if args['map' .. n] == '' or args['map' .. n] == nil then return '' end

local output = '|-\n| style="text-align:left;" | ' .. args['map' .. n]
local codes = {}
for i = 1, 10 do
if args['name' .. i] and args['name' .. i] ~= '' then
local x = args['map' .. n .. 'char' .. i] or ''
output = output .. ' || ' .. hex2dec_words(x) .. ' || ' .. frame:callParserFunction('uc', x)
end
end
return output .. '\n'
end

p.head = function(frame)
local output = '|- style="text-align:center;"\n'
codes = {} -- May contain nils if bad input
infos = {} -- boolean array
names = {} -- string array
args = frame:getParent().args
for i = 1, 10 do
if args['name' .. i] and args['name' .. i] ~= '' then
-- The parser function uc: preserves strip markers.
codes[1 + #names] = frame:callParserFunction('uc', mw.text.trim(args[i]))
infos[1 + #names] = paramCoalesce(args, 'Info' .. i, 'Info') == 'yes'
names[1 + #names] = frame:callParserFunction('uc', args['name' .. i])
end
end

if #names > 0 then
output = output .. "| align=\"center\" | '''" .. frame:preprocess('<templatestyles src="smallcaps/styles.css"/>') ..
(next(codes) == nil and 'Character' or 'Unicode') .. " name''' "
for i, n in ipairs(names) do
-- Display the character in smallcaps
output = output .. '|| colspan=2 | <span class="smallcaps smallcaps-smaller">' .. n .. '</span>'
end
end

output = output .. '\n|-\n! style="text-align:left;" | Encodings' ..
string.rep('|| decimal || hex', #names) ..
'\n|-\n| style="text-align:left;" | [[Unicode]]'
for i, n in ipairs(names) do
local code = codes[i] or '';
-- padleft, get to form U+XXXX or U+XXXX+XXXX.
code = (#code >= 4) and code:gsub(' ', '+') or ('0000' .. (code or '')):sub(-4)
output = output .. ' || ' .. _multiUTF{codes[i] or '0', 'hex2dec'} .. ' || ' ..
(infos[i] and '[http://www.fileformat.info/info/unicode/char/%s/index.htm U+%s]' or 'U+%s'):format(code, code)
end

output = output .. '\n|-\n| style="text-align:left;" | [[UTF-8]]'
for i, n in ipairs(names) do
output = output .. _multiUTF{codes[i]}
end

local outsideBMP = false -- Do we need to show surrogate pairs?
for i, n in ipairs(names) do
if (tonumber(codes[i] or '', 16) or 0) > 0xFFFF then
outsideBMP = true
break
end
end

if outsideBMP then
output = output .. '\n|-\n| style="text-align:left;" | [[UTF-16]]'
for i, n in ipairs(names) do
output = output .. _multiUTF{codes[i], 'UTF-16'}
end
end

if yesno(args['IncludeGB']) then
output = output .. '\n|-\n| style="text-align:left;" | [[GB 18030]]'
for i, n in ipairs(names) do
output = output .. _multiUTF{codes[i], 'GB18030'}
end
end

output = output .. '\n|-\n| style="text-align:left;" | [[Numeric character reference]]'
for i, n in ipairs(names) do
output = output .. _multiUTF{codes[i], 'charmap/numcharref'}
end

return output
end

p.named = function(frame, n)
n = n or frame.args[1]
local args = frame:getParent().args
local refchars = {}
local empty = true;
local namedref = (n == 'html') and '[[List of XML and HTML character entity references|Named character reference]]' or
args['namedref' .. n] or '';
for i = 1, 10 do
if args['name' .. i] and args['name' .. i] ~= '' then
local x = (n == 'html') and
(numcr2namecr[tonumber(args[i], 16)] or '') or
args['ref' .. n .. 'char' .. i] or ''
empty = empty and #x == 0
refchars[1 + #refchars] = x
end
end
if empty then return '' end
return '|- style="text-align:center"\n| style="text-align:left" | ' .. namedref ..
(' || colspan="2" | %s'):rep(#refchars):format(unpack(refchars)) .. '\n'
end

p.main = function(frame)
-- text-align:center: ''
local output = {'{| class="wikitable template-charmap" style="text-align:right"\n',
'|+Character information\n',
'|- style="text-align:center"\n', -- Otherwise mobile site tries aligning preview cells right
'! scope="row" | Preview'}
local args = frame:getParent().args
for i = 1, 10 do
-- Header row with the symbol in a large font or an image
if args['name' .. i] and args['name' .. i] ~= '' then
output[1 + #output] = ' || colspan="2" style="font-size:' .. (paramCoalesce(args, 'size' .. i, 'size') or '150%') ..
'" | ' .. (paramCoalesce(args, 'image' .. i) or _multiUTF{args[i] or '20', 'charmap/showchar'})
end
end
output[1 + #output] = '\n' .. p.head(frame) .. '\n' .. p.named(frame, 'html')
for i = 1, 10 do
output[1 + #output] = p.alt(frame, i)
end
for i = 1, 5 do
output[1 + #output] = p.named(frame, i)
end
return table.concat(output) .. '|}'
end

return p

Module:Charmap - Revision history

Zoran: Pywikibot 6.4.0