Module:Sandbox/Erutuon: Difference between revisions

Revision as of 18:24, 4 July 2018

Revision as of 18:28, 4 July 2018

Line 1:

local p = {}

local Unicode_data = require '"Module:Unicode data/sandbox'"

local function errorf(level, ...)

Line 36:

local Latn_pattern = table.concat {

'"['",

'"\n\32-\127'",

'"\194\160-\194\172'",

'"\195\128-\195\191'",

'"\196\128-\197\191'",

'"\198\128-\201\143'",

'"\225\184\128-\225\187\191'",

'"\226\177\160-\226\177\191'",

'"\234\156\160-\234\159\191'",

'"\234\172\176-\234\173\175'",

'"\239\172\128-\239\172\134'",

'"\239\188\129-\239\188\188'",

'"–'",

'"—'",

'"«'", '"»'",

'"]'",

};

Line 134:

function p.show(frame)

local expanded_pattern = Latn_pattern

:gsub('"%[(.-)%]'", '"%1'")

:gsub( -- Find two UTF-8-encoded characters separated by hyphen-minus.

'"([%z\1-\127\194-\244][\128-\191]*)%-([%z\1-\127\194-\244][\128-\191]*)'",

function (char1, char2)

return expand_range(char1, char2)

Line 143:

return ('* <div style="overflow-wrap: break-word;">%s</div><br>%s')

:format(expanded_pattern

:gsub('"^%s*'", ''""), -- Remove initial '"\n '" to avoid creating unwanted pre element.

show_scripts(mw.ustring.gcodepoint(expanded_pattern)))

end

Line 173:

local function link_block_name(block_name)

if block_name:find '" '" then

return ("[[%s]]"):format(block_name)

else

Line 213:

or codepoint <= 0x1F)) then

if self[script_code].n == 0x20 then

local period = ('".'"):byte()

for _ = 1, 3 do

self[script_code].n = self[script_code].n + 1

Line 340:

local language_codes = {}

for lang_template in content:gmatch '"{{lang[^}]+'" do

local template_name = lang_template:match('"{{([^|}]+)'")

local language_code

if template_name == '"lang'" then

language_code = lang_template:match '"{{lang|([^|}]+)'"

elseif template_name:find '"^lang-'" then

language_code = lang_template:match '"{{lang-([^|}]+)'"

end

if language_code then

Line 353:

end

return table.concat(m_table.keysToList(language_codes), '", '")

end

Line 421:

-- Language tags probably only contain ASCII alphabetic and numerical

-- characters and hyphen-minus.

if not tag:find '"^[A-Za-z0-9-]+$'" then

mw.log(tag, tag:find '[^A-Za-z0-9-]')

return parsed_subtags:throw(

"invalid characters",

fun.indexOf(

function (tag)

return tag:find '"[^A-Za-z0-9-]'"

end,

potential_subtags))