Article snapshot taken from Wikipedia with creative commons attribution-sharealike license.
Give it a read and then ask your questions in the chat.
We can research this topic together.
languageCode, subtags.script, subtags.region, subtags.variant, subtags.private, errorText = langM.get_ietf_parts (codes) -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})
mw.log("--new code--")
mw.log(languageCode)
local scriptCode
if require("Module:Unicode data").is_Latin (word2 or word1) then
This module is rated as beta, and is ready for widespread use. It is still new and should be used with some caution to ensure the results are as expected.
This module is used by {{Wikt-lang}}. It is inspired by the templates {{m}} and {{l}} and their associated modules on Wiktionary. It has a Wiktionary link function that links to the correct section of the Wiktionary entry, and applies correct language formatting and italics. The language-tagging function does most of what {{Lang}} does, except that italics can't be customized and categories aren't added.
The module uses Module:Wikt-lang/data to retrieve the language name for a language code, and to perform the necessary entry-name replacements (for instance, removing macrons from Latin entry names). These are unfortunately not automatically retrieved from Wiktionary's Wikt-lang data modules. For language codes that do not have a name value in this module, the language name is fetched with mw.language.fetchLanguage. When mw.language.fetchLanguage does not fetch the correct language name (or any language name at all), please add it to Module:Wikt-lang/data, and similarly when the correct entry name is not generated, please add the entry name replacements to the module.
require('strict')
local m_data = mw.loadData("Module:Wikt-lang/data")
local langData = m_data.languages or m_data
local p = {}
local error_mesages = {
= "The function makeEntryName requires a string argument",
= "Name for the language code $1 could not be retrieved with mw.language.fetchLanguageName, so it should be added to ]",
= "Language name is empty",
= "linkToWiktionary needs a Wiktionary entry or link text, or both",
= "The function wiktlang generated nothing",
= "<code>$1</code> is not a valid language or script code.",
= "<code>$1</code> is not a valid script code.",
}
local cfg = {
wiki_language = "en",
appendix = "Appendix:$1/$2",
reconstruction = "Reconstruction:$1/$2",
types = {
appendix = "appendix",
reconstructed = "reconstructed",
}
}
local function ifNotEmpty(value)
if value == "" then
return nil
else
return value
end
end
local function makeEntryName(word, languageCode)
local data = langData
local ugsub = mw.ustring.gsub
word = tostring(word)
if word == nil then
error(error_mesages.makeEntryName)
elseif word == "" then
return ""
else
-- Remove bold and italics, so that words that contain bolding or emphasis can be linked without piping.
word = word:gsub("\'\'\'", "")
word = word:gsub("\'\'", "")
if data == nil then
return word
else
local replacements = data and data
if replacements == nil then
return word
else
-- Decompose so that the diacritics of characters such
-- as á can be removed in one go.
-- No need to compose at the end, because the MediaWiki software
-- will handle that.
if replacements.decompose then
word = mw.ustring.toNFD(word)
for i, from in ipairs(replacements.from) do
word = ugsub(
word,
from,
replacements.to and replacements.to or "")
end
else
for regex, replacement in pairs(replacements) do
word = ugsub(word, regex, replacement)
end
end
return word
end
end
end
end
local function fixScriptCode(firstLetter, threeLetters)
return string.upper(firstLetter) .. string.lower(threeLetters)
end
local function getCodes(codes, text)
local languageCode, scriptCode, invalidCode
local errorText
if codes == nil or codes == "" then
errorText = 'no language or script code provided'
elseif codes:find("^%a%a%a?$") or codes:find("^%a%a%a?%-%a%a%a%a$") then
-- A three- or two-letter lowercase sequence at beginning of first parameter
languageCode =
codes:find("^%a%a%a?") and (
codes:match("^(%l%l%l?)")
or codes:match("^(%a%a%a?)")
:gsub("(%a%a%a?)", string.lower, 1)
)
-- One uppercase and three lowercase letters at the end of the first parameter
scriptCode =
codes:find("%a%a%a%a$") and (
codes:match("(%u%l%l%l)$")
or gsub(
codes:match("(%a%a%a%a)$"),
"(%a)(%a%a%a)",
fixScriptCode,
1
)
)
elseif codes:find("^%a%a%a?%-%a%a%a?$")
or codes:find("^%a%a%a%-%a%a%a%-%a%a%a$") then
languageCode = codes
-- Private-use subtag: x followed by one or more sequences of 1-8 lowercase
-- letters separated by hyphens. This only allows for one sequence, as it is
-- needed for proto-languages such as ine-x-proto (Proto-Indo-European).
elseif codes:find("^%a%a%a?%-x%-%a%a?%a?%a?%a?%a?%a?%a?$") then
languageCode, scriptCode =
codes:match("^(%a%a%a%-x%-%a%a?%a?%a?%a?%a?%a?%a?)%-?(.*)$")
if not languageCode then
errorText = '<code>'..codes..'</code> is not a valid language or script code.'
elseif scriptCode ~= "" and not scriptCode:find("%a%a%a%a") then
errorText = '<code>'..scriptCode..'</code> is not a valid script code.'
else
scriptCode = scriptCode:gsub(
"(%a)(%a%a%a)",
fixScriptCode,
1
)
end
elseif codes:find("^%a%a%a?") then
languageCode, invalidCode = codes:match("^(%a%a%a?)%-?(.*)")
languageCode = string.lower(languageCode)
errorText = '<code>'..invalidCode..'</code> is not a valid script code.'
elseif codes:find("%-?%a%a%a%a$") then
invalidCode, scriptCode = codes:match("(.*)%-?(%a%a%a%a)$")
scriptCode = gsub(
scriptCode,
"(%a)(%a%a%a)",
fixScriptCode
)
errorText = '<code>'..invalidCode..'</code> is not a valid language code.'
else
errorText = '<code>'..codes..'</code> is not a valid language or script code.'
end
if not scriptCode or scriptCode == "" then
scriptCode = require("Module:Unicode data").is_Latin(text) and "Latn" or "unknown"
end
if errorText then
errorText = ' <span style="font-size: smaller;"></span>'
else
errorText = ""
end
languageCode = m_data.redirects or languageCode
return languageCode, scriptCode, errorText
end
local function tag(text, languageCode, script, italics)
local data = langData
-- Use Misplaced Pages code if it has been given: for instance,
-- Proto-Indo-European has the Wiktionary code "ine-pro" but the Misplaced Pages
-- code "ine-x-proto".
languageCode = data and data.Wikipedia_code or languageCode
local italicize = script == "Latn" and italics
if not text then text = "" end
local textDirectionMarkers = {"", "", ""}
if data and data == "rtl" then
textDirectionMarkers = {' dir="rtl"', '‏', '‎'}
end
local out = {textDirectionMarkers}
if italicize then
table.insert(out, "<i lang=\"" .. languageCode .. "\"" .. textDirectionMarkers .. ">" .. text .. "</i>")
else
table.insert(out, "<span lang=\"" .. languageCode .. "\"" .. textDirectionMarkers .. ">" .. text .. "</span>")
end
table.insert(out, textDirectionMarkers)
return table.concat(out)
end
local function linkToWiktionary(entry, linkText, languageCode)
local data = langData
local name
if languageCode then
if data and data.name then
name = data.name
else
-- On other languages' wikis, use mw.getContentLanguage():getCode(),
-- or replace 'en' with that wiki's language code.
name = mw.language.fetchLanguageName(languageCode, cfg.wiki_language)
if name == "" then
error("Name for the language code " .. ("%q"):format(languageCode or nil)
.. " could not be retrieved with mw.language.fetchLanguageName, "
.. "so it should be added to ]")
end
end
if entry:sub(1, 1) == "*" then
if name ~= "" then
entry = "Reconstruction:" .. name .. "/" .. entry:sub(2)
else
error(error_mesages.empty_language_name)
end
elseif data and data.type == cfg.types.reconstructed then
mw.log("Reconstructed language without asterisk:", languageCode, name, entry)
local frame = mw.getCurrentFrame()
-- Track reconstructed entries with no asterisk by transcluding
-- a nonexistent template. This technique is used in Wiktionary:
-- see ].
-- ]
pcall(frame.expandTemplate, frame,
{ title = 'tracking/wikt-lang/reconstructed with no asterisk' })
if name ~= "" then
entry = "Reconstruction:" .. name .. "/" .. entry
else
error(error_mesages.empty_language_name)
end
elseif data and data.type == cfg.types.appendix then
if name ~= "" then
entry = "Appendix:" .. name .. "/" .. entry
else
error(error_mesages.empty_language_name)
end
end
if entry and linkText then
return "]"
else
error(error_mesages.no_text)
end
else
return "]"
end
end
function p.wiktlang(frame)
local parent = frame:getParent()
local args = parent.args and parent.args or frame.args
local codes = args and mw.text.trim(args)
local word1 = ifNotEmpty(args)
local word2 = ifNotEmpty(args)
if not args or '' == args then
return '<span style="color: #d33;"> Parameter 2 is required</span>';
end
--local languageCode, scriptCode, errorText = getCodes(codes, word2 or word1)
local languageCode
local scriptCode
local subtags = {}
local errorText
local langM = require("Module:Lang/sandbox")
languageCode, subtags.script, subtags.region, subtags.variant, subtags.private, errorText = langM.get_ietf_parts (codes) -- |script=, |region=, |variant= not supported because they should be part of args.code ({{{1}}} in {{lang}})
mw.log("--new code--")
mw.log(languageCode)
local scriptCode
if require("Module:Unicode data").is_Latin (word2 or word1) then
scriptCode = "Latn"
else
scriptCode = "unknown"
end
mw.log(scriptCode)
local italics = args.italics or args.i or args.italic
italics = not (italics == "n" or italics == "-" or italics == "no")
local entry, linkText
if word2 and word1 then
entry = makeEntryName(word1, languageCode)
linkText = word2
elseif word1 then
entry = makeEntryName(word1, languageCode)
linkText = word1
end
local out
if languageCode and entry and linkText then
out = tag(linkToWiktionary(entry, linkText, languageCode), languageCode, scriptCode, italics)
elseif entry and linkText then
out = linkToWiktionary(entry, linkText)
else
out = '<span style="font-size: smaller;"></span>'
end
mw.log(out)
if errorText then
return errorText or error(error_mesages.no_result)
else
return out
end
end
return p
Module documentation[view] [edit] [history] [purge]
