Module:Languages and Module:Languages/sandbox: Difference between pages

(Difference between pages)
Jump to navigation Jump to search
Page 1
Page 2
No edit summary
 
(Created page with "local export = {} --[=[ This function checks for things that could plausibly be a language code: two or three lowercase letters, two or three groups of three lowercase le...")
 
Line 1: Line 1:
local export = {}
local export = {}


local function track(page, code)
--[=[ This function checks for things that could plausibly be a language code:
local tracking_page = "languages/" .. page
two or three lowercase letters, two or three groups of three lowercase
if code then
letters with hyphens between them. If such a pattern is not found,
require("Module:debug/track"){tracking_page, tracking_page .. "/" .. code}
it is likely the editor simply forgot to enter a language code. ]=]
else
require("Module:debug/track")(tracking_page)
end
return true
end
 
local checkObject = require("Module:utilities").check_object


local function make_language(code, data, useRequire)
function export.err(langCode, param, text, template_tag)
local function conditionalRequire(modulename)
local ordinals = {
if useRequire then
"first", "second", "third", "fourth", "fifth", "sixth",
return require(modulename)
"seventh", "eighth", "ninth", "tenth", "eleventh", "twelfth",
else
"thirteenth", "fourteenth", "fifteenth", "sixteenth", "seventeenth",
return mw.loadData(modulename)
"eighteenth", "nineteenth", "twentieth"
end
}
end
-- Temporarily convert various formatting characters to PUA to prevent them from being disrupted by the substitution process.
if not template_tag then
local function doTempSubstitutions(text, subbedChars, keepCarets, noTrim)
template_tag = ""
-- Clone so that we don't insert any extra patterns into the table in package.loaded. For some reason, using require seems to keep memory use down; probably because the table is always cloned.
else
local patterns = require("Module:table").shallowcopy(require("Module:languages/data/patterns"))
if type(template_tag) ~= "string" then
if keepCarets then
template_tag = template_tag()
table.insert(patterns, "((\\+)%^)")
table.insert(patterns, "((%^))")
end
-- Ensure any whitespace at the beginning and end is temp substituted, to prevent it from being accidentally trimmed. We only want to trim any final spaces added during the substitution process (e.g. by a module), which means we only do this during the first round of temp substitutions.
if not noTrim then
table.insert(patterns, "^([\128-\191\244]*(%s+))")
table.insert(patterns, "((%s+)[\128-\191\244]*)$")
end
-- Pre-substitution, of "[[" and "]]", which makes pattern matching more accurate.
text = text
:gsub("%f[%[]%[%[", "\1")
:gsub("%f[%]]%]%]", "\2")
local i, pe = #subbedChars, require("Module:utilities").pattern_escape
for j, pattern in ipairs(patterns) do
-- Patterns ending in \0 stand are for things like "[[" or "]]"), so the inserted PUA are treated as breaks between terms by modules that scrape info from pages.
local term_divider
pattern = pattern:gsub("%z$", function(divider)
term_divider = divider == "\0"
return ""
end)
text = text:gsub(pattern, function(...)
local m = {...}
local m1New = m[1]
for k = 2, #m do
local n = i + k - 1
subbedChars[n] = m[k]
local byte2 = math.floor(n / 4096) % 64 + (term_divider and 128 or 136)
local byte3 = math.floor(n / 64) % 64 + 128
local byte4 = n % 64 + 128
m1New = m1New:gsub(pe(m[k]), "\244" .. string.char(byte2) .. string.char(byte3) .. string.char(byte4), 1)
end
i = i + #m - 1
return m1New
end)
end
end
text = text
template_tag = " (Original template: " .. template_tag .. ")"
:gsub("\1", "%[%[")
:gsub("\2", "%]%]")
return text, subbedChars
end
end
local paramType = type(param)
-- Reinsert any formatting that was temporarily substituted.
if paramType == "number" then
local function undoTempSubstitutions(text, subbedChars)
ordinal = ordinals[param]
local pe = require("Module:utilities").pattern_escape
param = ordinal .. ' parameter'
for i = 1, #subbedChars do
elseif paramType == "string" then
local byte2 = math.floor(i / 4096) % 64 + 128
param = 'parameter "' .. param .. '"'
local byte3 = math.floor(i / 64) % 64 + 128
else
local byte4 = i % 64 + 128
error("The parameter name is "
text = text:gsub("\244[" .. string.char(byte2) .. string.char(byte2+8) .. "]" .. string.char(byte3) .. string.char(byte4), pe(subbedChars[i]))
.. (paramType == "table" and "a table" or tostring(param))
end
.. ", but it should be a number or a string." .. template_tag, 2)
text = text
:gsub("\1", "%[%[")
:gsub("\2", "%]%]")
return text
end
end
-- Convert any HTML entities.
-- Can use string.find because language codes only contain ASCII.
local function noEntities(text)
if not langCode or langCode == "" then
if text:match("&[^;]+;") then
error("The " .. param .. " (" .. (text or "language code") .. ") is missing." .. template_tag, 2)
return require("Module:utilities").get_entities(text)
elseif langCode:find("^%l%l%l?$")
else
or langCode:find("^%l%l%l%-%l%l%l$")
return text
or langCode:find("^%l%l%l%-%l%l%l%-%l%l%l$") then
end
error("The language code \"" .. langCode .. "\" is not valid." .. template_tag, 2)
else
error("Please enter a " .. (text or "language code") .. " in the " .. param .. "." .. template_tag, 2)
end
end
end
-- Check if the raw text is an unsupported title, and if so return that. Otherwise, remove HTML entities. We do the pre-conversion to avoid loading the unsupported title list unnecessarily.
 
local function checkNoEntities(text)
local function do_entry_name_or_sort_key_replacements(text, replacements)
local textNoEnc = noEntities(text)
if replacements.from then
if textNoEnc ~= text and conditionalRequire("Module:links/data").unsupported_titles[text] then
for i, from in ipairs(replacements.from) do
return text
local to = replacements.to[i] or ""
else
text = mw.ustring.gsub(text, from, to)
return textNoEnc
end
end
-- If no script object is provided (or if it's invalid or None), get one.
local function checkScript(text, self, sc)
if not checkObject("script", true, sc) or sc:getCode() == "None" then
return self:findBestScript(text)
else
return sc
end
end
end
end
local function normalize(text, sc)
if replacements.remove_diacritics then
text = sc:fixDiscouragedSequences(text)
text = mw.ustring.toNFD(text)
return sc:toFixedNFD(text)
text = mw.ustring.gsub(text,
'[' .. replacements.remove_diacritics .. ']',
'')
text = mw.ustring.toNFC(text)
end
end
-- Split the text into sections, based on the presence of temporarily substituted formatting characters, then iterate over each one to apply substitutions. This avoids putting PUA characters through language-specific modules, which may be unequipped for them.
return text
local function iterateSectionSubstitutions(text, subbedChars, keepCarets, self, sc, substitution_data, function_name)
end
local pe = require("Module:utilities").pattern_escape
 
local fail, cats, sections = nil, {}
local Language = {}
-- See [[Module:languages/data]].
 
if not text:match("\244") or conditionalRequire("Module:languages/data").contiguous_substitution[self:getCode()] then
function Language:getCode()
sections = {text}
return self._code
else
end
sections = mw.text.split(text, "[􀀀-􏿽]")
 
end
 
for i, section in ipairs(sections) do
function Language:getCanonicalName()
-- Don't bother processing empty strings or whitespace (which may also not be handled well by dedicated modules).
return self._rawData[1] or self._rawData.canonicalName
if section:gsub("%s", "") ~= "" then
end
local sub, sub_fail, sub_cats = require("Module:languages/doSubstitutions")(section, self, sc, substitution_data, function_name)
 
-- Second round of temporary substitutions, in case any formatting was added by the main substitution process. However, don't do this if the section contains formatting already (as it would have had to have been escaped to reach this stage, and therefore should be given as raw text).
 
if sub and subbedChars then
function Language:getOtherNames()
local noSub
return self._rawData.otherNames or {}
for _, pattern in ipairs(require("Module:languages/data/patterns")) do
end
if section:match(pattern .. "%z?") then
 
noSub = true
 
end
function Language:getType()
end
return self._rawData.type or "regular"
if not noSub then
end
sub, subbedChars = doTempSubstitutions(sub, subbedChars, keepCarets, true)
 
end
 
end
function Language:getWikimediaLanguages()
if (not sub) or sub_fail then
if not self._wikimediaLanguageObjects then
text = sub
local m_wikimedia_languages = require("Module:wikimedia languages")
fail = sub_fail
self._wikimediaLanguageObjects = {}
cats = sub_cats or {}
local wikimedia_codes = self._rawData.wikimedia_codes or { self._code }
break
end
text = sub and text:gsub(pe(section), pe(sub), 1) or text
if type(sub_cats) == "table" then
for _, cat in ipairs(sub_cats) do
table.insert(cats, cat)
end
end
end
end
-- Trim, unless there are only spacing characters, while ignoring any final formatting characters.
text = text and text
:gsub("^([\128-\191\244]*)%s+(%S)", "%1%2")
:gsub("(%S)%s+([\128-\191\244]*)$", "%1%2")
-- Remove duplicate categories.
for _, wlangcode in ipairs(wikimedia_codes) do
if #cats > 1 then
table.insert(self._wikimediaLanguageObjects, m_wikimedia_languages.getByCode(wlangcode))
cats = require("Module:table").removeDuplicates(cats)
end
end
return text, fail, cats, subbedChars
end
end
-- Process carets (and any escapes). Default to simple removal, if no pattern/replacement is given.
return self._wikimediaLanguageObjects
local function processCarets(text, pattern, repl)
end
local rep
repeat
text, rep = text:gsub("\\\\(\\*^)", "\3%1")
until rep == 0
return text
:gsub("\\^", "\4")
:gsub(pattern or "%^", repl or "")
:gsub("\3", "\\")
:gsub("\4", "^")
end
-- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped).
local function removeCarets(text, sc)
if not sc:hasCapitalization() and sc:isTransliterated() and text:match("%^") then
return processCarets(text)
else
return text
end
end
local Language = {}
--[==[Returns the language code of the language. Example: {{code|lua|"fr"}} for French.]==]
function Language:getCode()
return self._code
end
--[==[Returns the canonical name of the language. This is the name used to represent that language on Wiktionary, and is guaranteed to be unique to that language alone. Example: {{code|lua|"French"}} for French.]==]
function Language:getCanonicalName()
return self._rawData[1]
end
--[==[Returns the display form of the language. The display form of a language, family or script is the form it takes when appearing as the ''SOURCE'' in categories such as <code>English terms derived from ''SOURCE''</code> or <code>English given names from ''SOURCE''</code>, and is also the displayed text in <code>:makeCategoryLink</code> links. For regular and etymology languages, this is the same as the canonical name, but for families, it reads "NAME languages" (e.g. {{code|lua|"Indo-Iranian languages"}}), and for scripts, it reads "NAME script" (e.g. {{code|lua|"Arabic script"}}).]==]
function Language:getDisplayForm()
if not self._displayForm then
local form = self:getCanonicalName()
-- Add article and " substrate" if a substrate that lacks them.
if self:getFamilyCode() == "qfa-sub" then
if not (form:find("^[Tt]he ") or form:find("^[Aa] ")) then
form = "a " .. form
end
if not form:find("[Ss]ubstrate") then
form = form .. " substrate"
end
end
self._displayForm = form
end
return self._displayForm
end
--[==[Returns a table of the "other names" that the language is known by, excluding the canonical name. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: {{code|lua|{"Manx Gaelic", "Northern Manx", "Southern Manx"} }} for [[:Category:Manx language|Manx]]. If <code>onlyOtherNames</code> is given and is non-{{code|lua|nil}}, only names explicitly listed in the <code>otherNames</code> field are returned; otherwise, names listed under <code>otherNames</code>, <code>aliases</code> and <code>varieties</code> are combined together and returned. For example, for Manx, Manx Gaelic is listed as an alias, while Northern Manx and Southern Manx are listed as varieties. It should be noted that the <code>otherNames</code> field itself is deprecated, and entries listed there should eventually be moved to either <code>aliases</code> or <code>varieties</code>.]==]
function Language:getOtherNames(onlyOtherNames)
if #self._stack == 1 then
self:loadInExtraData()
end
return require("Module:language-like").getOtherNames(self, onlyOtherNames)
end
--[==[Returns a table of the aliases that the language is known by, excluding the canonical name. Aliases are synonyms for the language in question. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: {{code|lua|{"High German", "New High German", "Deutsch"} }} for [[:Category:German language|German]].]==]
function Language:getAliases()
if #self._stack == 1 then
self:loadInExtraData()
end
return self._rawData.aliases or (self._extraData and self._extraData.aliases) or {}
end
--[==[Returns a table of the known subvarieties of a given language, excluding subvarieties that have been given explicit etymology language codes. The names are not guaranteed to be unique, in that sometimes a given name refers to a subvariety of more than one language. Example: {{code|lua|{"Southern Aymara", "Central Aymara"} }} for [[:Category:Aymara language|Aymara]]. Note that the returned value can have nested tables in it, when a subvariety goes by more than one name. Example: {{code|lua|{"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor"} }} for [[:Category:Azerbaijani language|Azerbaijani]]. Here, for example, Afshar, Afshari, Afshar Azerbaijani and Afchar all refer to the same subvariety, whose preferred name is Afshar (the one listed first). To avoid a return value with nested tables in it, specify a non-{{code|lua|nil}} value for the <code>flatten</code> parameter; in that case, the return value would be {{code|lua|{"North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"} }}.]==]
function Language:getVarieties(flatten)
if #self._stack == 1 then
self:loadInExtraData()
end
return require("Module:language-like").getVarieties(self, flatten)
end
--[==[Given a list of types as strings, returns true if the language has all of them.


The possible types are
function Language:getWikipediaArticle()
* {language}: This is a language, either full or etymology-only.
if self._rawData.wikipedia_article then
* {full}: This is a "full" (not etymology-only) language, i.e. the union of {regular}, {reconstructed} and
return self._rawData.wikipedia_article  
  {appendix-constructed}. Note that the types {full} and {etymology-only} also exist for families, so if you
elseif self._wikipedia_article then
  want to check specifically for a full language and you have an object that might be a family, you should
  use {{lua|hasType("language", "full")}} and not simply {{lua|hasType("full")}}.
* {etymology-only}: This is an etymology-only (not full) language, whose parent is another etymology-only
language or a full language. Note that the types {full} and {etymology-only} also exist for
families, so if you want to check specifically for an etymology-only language and you have an
object that might be a family, you should use {{lua|hasType("language", "etymology-only")}}
and not simply {{lua|hasType("etymology-only")}}.
* {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted
in the main namespace. There may also be reconstructed terms for the language, which are placed in
the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full
languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto
and Volapük, among others) are also allowed in the mainspace and considered regular languages.
* {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the
  {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed
  with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category.
* {appendix-constructed}: This language is attested but does not meet the additional requirements set out for
  constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore
  be in the Appendix namespace, but they are not reconstructed and therefore should
  not have * prefixed in links.
]==]
function Language:hasType(...)
if not self._type then
self._type = {language = true}
if self:getNonEtymologicalCode() == self:getCode() then
self._type.full = true
else
self._type["etymology-only"] = true
end
for _, type in ipairs(mw.text.split(self._rawData.type, "%s*,%s*")) do
self._type[type] = true
end
end
for _, type in ipairs{...} do
if not self._type[type] then
return false
end
end
return true
end
--[==[Returns a table containing <code>WikimediaLanguage</code> objects (see [[Module:wikimedia languages]]), which represent languages and their codes as they are used in Wikimedia projects for interwiki linking and such. More than one object may be returned, as a single Wiktionary language may correspond to multiple Wikimedia languages. For example, Wiktionary's single code <code>sh</code> (Serbo-Croatian) maps to four Wikimedia codes: <code>sh</code> (Serbo-Croatian), <code>bs</code> (Bosnian), <code>hr</code> (Croatian) and <code>sr</code> (Serbian).
The code for the Wikimedia language is retrieved from the <code>wikimedia_codes</code> property in the data modules. If that property is not present, the code of the current language is used. If none of the available codes is actually a valid Wikimedia code, an empty table is returned.]==]
function Language:getWikimediaLanguages()
if not self._wikimediaLanguageObjects then
local m_wikimedia_languages = require("Module:wikimedia languages")
self._wikimediaLanguageObjects = {}
local wikimedia_codes = self:getWikimediaLanguageCodes()
for _, wlangcode in ipairs(wikimedia_codes) do
table.insert(self._wikimediaLanguageObjects, m_wikimedia_languages.getByCode(wlangcode))
end
end
return self._wikimediaLanguageObjects
end
function Language:getWikimediaLanguageCodes()
if not self._wikimediaLanguageCodes then
self._wikimediaLanguageCodes = self._rawData.wikimedia_codes or {self:getCode()}
end
return self._wikimediaLanguageCodes
end
--[==[Returns the name of the Wikipedia article for the language. If the property <code>wikipedia_article</code> is present in the data module it will be used first, otherwise a sitelink will be generated from <code>:getWikidataItem</code> (if set). Otherwise <code>:getCategoryName</code> is used as fallback.]==]
function Language:getWikipediaArticle()
if not self._wikipedia_article then
if self._rawData.wikipedia_article then
self._wikipedia_article = self._rawData.wikipedia_article
elseif self:getWikidataItem() and mw.wikibase then
self._wikipedia_article = mw.wikibase.sitelink(self:getWikidataItem(), 'enwiki')
end
if not self._wikipedia_article then
self._wikipedia_article = self:getCategoryName():gsub("Creole language", "Creole")
end
end
return self._wikipedia_article
return self._wikipedia_article
elseif self:getWikidataItem() and mw.wikibase then
self._wikipedia_article = mw.wikibase.sitelink(self:getWikidataItem(), 'enwiki')
end
end
if not self._wikipedia_article then
function Language:makeWikipediaLink()
self._wikipedia_article = mw.ustring.gsub(self:getCategoryName(), "Creole language", "Creole")
return "[[w:" .. self:getWikipediaArticle() .. "|" .. self:getCanonicalName() .. "]]"
end
end
return self._wikipedia_article
--[==[Returns the Wikidata item id for the language or <code>nil</code>. This corresponds to the the second field in the data modules.]==]
end
function Language:getWikidataItem()
 
if not self._WikidataItem then
function Language:makeWikipediaLink()
local item = self._rawData[2]
return "[[w:" .. self:getWikipediaArticle() .. "|" .. self:getCanonicalName() .. "]]"
if type(item) == "number" then
end
self._WikidataItem = "Q" .. item
 
else
function Language:getWikidataItem()
self._WikidataItem = item
return self._rawData[2] or self._rawData.wikidata_item
end
end
 
function Language:getScripts()
if not self._scriptObjects then
local m_scripts = require("Module:scripts")
self._scriptObjects = {}
for _, sc in ipairs(self._rawData.scripts or { "None" }) do
table.insert(self._scriptObjects, m_scripts.getByCode(sc))
end
end
return self._WikidataItem
end
end
--[==[Returns a table of <code>Script</code> objects for all scripts that the language is written in. See [[Module:scripts]].]==]
return self._scriptObjects
function Language:getScripts()
end
if not self._scriptObjects then
 
self._scriptObjects = {}
function Language:getScriptCodes()
if self:getScriptCodes()[1] == "All" then
return self._rawData.scripts or { "None" }
self._scriptObjects = conditionalRequire("Module:scripts/data")
end
else
 
for _, sc in ipairs(self:getScriptCodes()) do
function Language:getFamily()
table.insert(self._scriptObjects, require("Module:scripts").getByCode(sc, nil, nil, useRequire))
if self._familyObject then
end
return self._familyObject
end
end
return self._scriptObjects
end
end
--[==[Returns the table of script codes in the language's data file.]==]
local family = self._rawData[3] or self._rawData.family
function Language:getScriptCodes()
if family then
if not self._scriptCodes then
self._familyObject = require("Module:families").getByCode(family)
self._scriptCodes = self._rawData[4] or {"None"}
end
return self._scriptCodes
end
end
--[==[Given some text, this function iterates through the scripts of a given language and tries to find the script that best matches the text. It returns a {{code|lua|Script}} object representing the script. If no match is found at all, it returns the {{code|lua|None}} script object.]==]
return self._familyObject
function Language:findBestScript(text, forceDetect)
end
if (not text) or text == "" or text == "-" then
 
return require("Module:scripts").getByCode("None", nil, nil, useRequire)
 
end
function Language:getAncestors()
if not self._ancestorObjects then
if table.concat(self:getScriptCodes()) == "All" then
self._ancestorObjects = {}
return require("Module:scripts").findBestScriptWithoutLang(text)
end
local scripts = self:getScripts()
if not scripts[2] and not forceDetect then
if self._rawData.ancestors then
-- Necessary, because Hani covers the entire Han range (while the Hant & Hans lists don't list shared characters).
for _, ancestor in ipairs(self._rawData.ancestors) do
if scripts[1]:getCode():match("^Han") and require("Module:scripts").getByCode("Hani", nil, nil, useRequire):countCharacters(text) > 0 then
table.insert(self._ancestorObjects, export.getByCode(ancestor) or require("Module:etymology languages").getByCode(ancestor))
return scripts[1]
elseif scripts[1]:countCharacters(text) > 0 then
return scripts[1]
else
return require("Module:scripts").getByCode("None", nil, nil, useRequire)
end
end
end
else
local fam = self:getFamily()
return require("Module:languages/findBestScript")(export, self, text, scripts, forceDetect, useRequire)
local protoLang = fam and fam:getProtoLanguage() or nil
end
-- For the case where the current language is the proto-language
--[==[Returns a <code>Family</code> object for the language family that the language belongs to. See [[Module:families]].]==]
-- of its family, we need to step up a level higher right from the start.
function Language:getFamily()
if protoLang and protoLang:getCode() == self:getCode() then
if self._familyObject == nil then
fam = fam:getFamily()
local familyCode = self:getFamilyCode()
protoLang = fam and fam:getProtoLanguage() or nil
if familyCode then
self._familyObject = require("Module:families").getByCode(familyCode, useRequire)
-- Still memoize a nil result.
else
self._familyObject = false
end
end
end
return self._familyObject or nil
while not protoLang and not (not fam or fam:getCode() == "qfa-not") do
end
fam = fam:getFamily()
protoLang = fam and fam:getProtoLanguage() or nil
--[==[Returns the family code in the language's data file.]==]
function Language:getFamilyCode()
if not self._familyCode then
self._familyCode = self._rawData[3]
end
return self._familyCode
end
function Language:getFamilyName()
if self._familyName == nil then
local family = self:getFamily()
if family then
self._familyName = family:getCanonicalName()
else
self._familyName = false
end
end
table.insert(self._ancestorObjects, protoLang)
end
end
return self._familyName or nil
end
end
--[==[Check whether the language belongs to `family` (which can be a family code or object). A list of objects can be given in place of `family`; in that case, return true if the language belongs to any of the specified families. Note that some languages (in particular, certain creoles) can have multiple immediate ancestors potentially belonging to different families; in that case, return true if the language belongs to any of the specified families.]==]
return self._ancestorObjects
function Language:inFamily(...)
end
--checkObject("family", nil, ...)
 
for _, family in ipairs{...} do
local function iterateOverAncestorTree(node, func)
if type(family) == "table" then
for _, ancestor in ipairs(node:getAncestors()) do
family = family:getCode()
if ancestor then
end
local ret = func(ancestor) or iterateOverAncestorTree(ancestor, func)
if not self:getFamilyCode() then
if ret then
return false
return ret
elseif self:getFamilyCode() == family or self:getFamily():inFamily(family) then
return true
else
local ancestors = self:getAncestors()
for _, ancestor in ipairs(ancestors) do
if ancestor:inFamily(family) then
return true
end
end
end
end
end
end
return false
end
end
end
function Language:getParent()
 
if self._parentObject == nil then
function Language:getAncestorChain()
local parentCode = self:getParentCode()
if not self._ancestorChain then
if parentCode then
self._ancestorChain = {}
self._parentObject = export.getByCode(parentCode, nil, true, true, useRequire)
local step = #self:getAncestors() == 1 and self:getAncestors()[1] or nil
else
self._parentObject = false
while step do
end
table.insert(self._ancestorChain, 1, step)
step = #step:getAncestors() == 1 and step:getAncestors()[1] or nil
end
end
return self._parentObject or nil
end
end
function Language:getParentCode()
return self._ancestorChain
if not self._parentCode then
end
self._parentCode = self._rawData[5]
 
end
 
return self._parentCode
function Language:hasAncestor(otherlang)
local function compare(ancestor)
return ancestor:getCode() == otherlang:getCode()
end
end
function Language:getParentName()
return iterateOverAncestorTree(self, compare) or false
if self._parentName == nil then
end
local parent = self:getParent()
 
if parent then
 
self._parentName = parent:getCanonicalName()
function Language:getCategoryName()
else
local name = self:getCanonicalName()
self._parentName = false
end
end
return self._parentName or nil
end
function Language:getParentChain()
-- If the name already has "language" in it, don't add it.
if not self._parentChain then
if name:find("[Ll]anguage$") then
self._parentChain = {}
return name
local parent = self:getParent()
else
while parent do
return name .. " language"
table.insert(self._parentChain, parent)
parent = parent:getParent()
end
end
return self._parentChain
end
end
end
function Language:getStandardCharacters()
return self._rawData.standardChars
end
function Language:makeEntryName(text)
text = mw.ustring.match(text, "^[¿¡](.-[^%s%p].-)[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]$") or text
function Language:hasParent(...)
if self:getCode() == "ar" then
--checkObject("language", nil, ...)
local U = mw.ustring.char
for _, otherlang in ipairs{...} do
local taTwiil = U(0x640)
for _, parent in ipairs(self:getParentChain()) do
local waSla = U(0x671)
if type(otherlang) == "string" then
-- diacritics ordinarily removed by entry_name replacements
if otherlang == parent:getCode() then return true end
local Arabic_diacritics = U(0x64B, 0x64C, 0x64D, 0x64E, 0x64F, 0x650, 0x651, 0x652, 0x670)
else
if otherlang:getCode() == parent:getCode() then return true end
if text == waSla or mw.ustring.find(text, "^" .. taTwiil .. "?[" .. Arabic_diacritics .. "]" .. "$") then
end
return text
end
end
end
return false
end
end
--[==[If the language is an etymology language, this iterates through parents until a regular language or family is found, and the corresponding object is returned. If the language is a regular language, then it simply returns the language.]==]
if type(self._rawData.entry_name) == "table" then
function Language:getNonEtymological()
text = do_entry_name_or_sort_key_replacements(text, self._rawData.entry_name)
if not self._nonEtymologicalObject then
local nonEtymologicalCode = self:getNonEtymologicalCode()
if nonEtymologicalCode ~= self:getCode() then
self._nonEtymologicalObject = export.getByCode(nonEtymologicalCode, nil, nil, nil, useRequire)
else
self._nonEtymologicalObject = self
end
end
return self._nonEtymologicalObject
end
end
function Language:getNonEtymologicalCode()
return text
return self._nonEtymologicalCode or self:getCode()
end
 
 
-- Add to data tables?
local has_dotted_undotted_i = {
["az"] = true,
["crh"] = true,
["gag"] = true,
["kaa"] = true,
["tt"] = true,
["tr"] = true,
["zza"] = true,
}
 
function Language:makeSortKey(name, sc)
if has_dotted_undotted_i[self:getCode()] then
name = name:gsub("I", "ı")
end
end
function Language:getNonEtymologicalName()
name = mw.ustring.lower(name)
if self._nonEtymologicalName == nil then
local nonEtymological = self:getNonEtymological()
if nonEtymological then
self._nonEtymologicalName = nonEtymological:getCanonicalName()
else
self._nonEtymologicalName = false
end
end
return self._nonEtymologicalName or nil
end
--[==[Returns a table of <code class="nf">Language</code> objects for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors.]==]
-- Remove initial hyphens and *
function Language:getAncestors()
local hyphens_regex = "^[-־ـ*]+(.)"
if not self._ancestorObjects then
name = mw.ustring.gsub(name, hyphens_regex, "%1")
self._ancestorObjects = {}
local ancestors = require("Module:table").shallowcopy(self:getAncestorCodes())
if #ancestors > 0 then
for _, ancestor in ipairs(ancestors) do
table.insert(self._ancestorObjects, export.getByCode(ancestor, nil, true, nil, useRequire))
end
else
local fam = self:getFamily()
local protoLang = fam and fam:getProtoLanguage() or nil
-- For the cases where the current language is the proto-language
-- of its family, or an etymology language that is ancestral to that
-- proto-language, we need to step up a level higher right from the
-- start.
if protoLang and (
protoLang:getCode() == self:getCode() or
(self:hasType("etymology-only") and protoLang:hasAncestor(self))
) then
fam = fam:getFamily()
protoLang = fam and fam:getProtoLanguage() or nil
end
while not protoLang and not (not fam or fam:getCode() == "qfa-not") do
fam = fam:getFamily()
protoLang = fam and fam:getProtoLanguage() or nil
end
table.insert(self._ancestorObjects, protoLang)
end
end
return self._ancestorObjects
end
function Language:getAncestorCodes()
-- If there are language-specific rules to generate the key, use those
if not self._ancestorCodes then
if type(self._rawData.sort_key) == "table" then
local function get_codes(lang)
name = do_entry_name_or_sort_key_replacements(name, self._rawData.sort_key)
return lang._rawData.ancestors or {}
elseif type(self._rawData.sort_key) == "string" then
end
name = require("Module:" .. self._rawData.sort_key).makeSortKey(name, self:getCode(), sc and sc:getCode())
local codes = get_codes(self)
-- Avoid a language being its own ancestor via class inheritance. We only need to check for this if the language has inherited an ancestor table from its parent, because we never want to drop ancestors that have been explicitly set in the data.
-- Recursively iterate over ancestors until we find a loop/run out. If a loop is found that involves the language, drop that ancestor.
if #codes > 0 and #self._stack > 1 and not self._stack[#self._stack].ancestors then
local function check_ancestor(i, code, seen)
if seen[code] then
if code == self:getCode() then
table.remove(codes, i)
end
else
seen[code] = true
local ancestor = export.getByCode(code, nil, true, nil, useRequire)
for _, ancestorCode in ipairs(get_codes(ancestor)) do
check_ancestor(i, ancestorCode, seen)
end
end
end
for i, ancestorCode in ipairs(codes) do
local seen = {[self:getCode()] = true}
check_ancestor(i, ancestorCode, seen)
end
end
self._ancestorCodes = codes
end
return self._ancestorCodes
end
end
--[==[Given a list of language objects or codes, returns true if at least one of them is an ancestor. This includes any etymology-only children of that ancestor. If the language's ancestor(s) are etymology-only languages, it will also return true for those language parent(s) (e.g. if Vulgar Latin is the ancestor, it will also return true for its parent, Latin). However, a parent is excluded from this if the ancestor is also ancestral to that parent (e.g. if Classical Persian is the ancestor, Persian would return false, because Classical Persian is also ancestral to Persian).]==]
-- Remove parentheses, as long as they are either preceded or followed by something
function Language:hasAncestor(...)
name = mw.ustring.gsub(name, "(.)[()]+", "%1")
--checkObject("language", nil, ...)
name = mw.ustring.gsub(name, "[()]+(.)", "%1")
local function iterateOverAncestorTree(node, func, parent_check)
local ancestors = node:getAncestors()
local ancestorsParents = {}
for _, ancestor in ipairs(ancestors) do
local ret = func(ancestor) or iterateOverAncestorTree(ancestor, func, parent_check)
if ret then return ret end
end
-- Check the parents of any ancestors. We don't do this if checking the parents of the other language, so that we exclude any etymology-only children of those parents that are not directly related (e.g. if the ancestor is Vulgar Latin and we are checking New Latin, we want it to return false because they are on different ancestral branches. As such, if we're already checking the parent of New Latin (Latin) we don't want to compare it to the parent of the ancestor (Latin), as this would be a false positive; it should be one or the other).
if not parent_check then
return nil
end
for _, ancestor in ipairs(ancestors) do
local ancestorParents = ancestor:getParentChain()
for _, ancestorParent in ipairs(ancestorParents) do
if ancestorParent:getCode() == self:getCode() or ancestorParent:hasAncestor(ancestor) then
break
else
table.insert(ancestorsParents, ancestorParent)
end
end
end
for _, ancestorParent in ipairs(ancestorsParents) do
local ret = func(ancestorParent)
if ret then return ret end
end
end
local parent_check = true
for _, otherlang in ipairs{...} do
repeat
if iterateOverAncestorTree(
self,
function(ancestor)
if type(otherlang) == "string" then
return ancestor:getCode() == otherlang
else
return ancestor:getCode() == otherlang:getCode()
end
end,
parent_check
) then
return true
elseif type(otherlang) == "string" then
otherlang = export.getByCode(otherlang, nil, true, nil, useRequire)
end
otherlang = otherlang:getParent()
parent_check = false
until not otherlang
end
return false
end
function Language:getAncestorChain()
if has_dotted_undotted_i[self:getCode()] then
if not self._ancestorChain then
name = name:gsub("i", "İ")
self._ancestorChain = {}
local step = self
while true do
local ancestors = step:getAncestors()
step = #ancestors == 1 and ancestors[1] or nil
if not step then break end
table.insert(self._ancestorChain, 1, step)
end
end
return self._ancestorChain
end
end
local function fetch_descendants(self, format)
return mw.ustring.upper(name)
local languages = require("Module:languages/code to canonical name")
end
local etymology_languages = require("Module:etymology languages/code to canonical name")
 
local families = require("Module:families/code to canonical name")
function Language:overrideManualTranslit()
local descendants = {}
if self._rawData.override_translit then
local family = self:getFamily()
return true
-- Iterate over all three datasets.
else
for _, data in ipairs{languages, etymology_languages, families} do
for code in pairs(data) do
local lang = export.getByCode(code, nil, true, true, useRequire)
-- Test for a descendant. Earlier tests weed out most candidates, while the more intensive tests are only used sparingly.
if (
( -- Not an alias code.
(not lang._rawData.main_code) or
lang._rawData.main_code == code
) and
code ~= self:getCode() and -- Not self.
lang:inFamily(family) and -- In the same family.
(
family:getProtoLanguageCode() == self:getCode() or -- Self is the protolanguage.
self:hasDescendant(lang) or -- Full hasDescendant check.
(lang:getNonEtymologicalCode() == self:getCode() and not self:hasAncestor(lang)) -- Etymology-only child which isn't an ancestor.
)
) then
if format == "object" then
table.insert(descendants, lang)
elseif format == "code" then
table.insert(descendants, code)
elseif format == "name" then
table.insert(descendants, lang:getCanonicalName())
end
end
end
end
return descendants
end
function Language:getDescendants()
if not self._descendantObjects then
self._descendantObjects = fetch_descendants(self, "object")
end
return self._descendantObjects
end
function Language:getDescendantCodes()
if not self._descendantCodes then
self._descendantCodes = fetch_descendants(self, "code")
end
return self._descendantCodes
end
function Language:getDescendantNames()
if not self._descendantNames then
self._descendantNames = fetch_descendants(self, "name")
end
return self._descendantNames
end
function Language:hasDescendant(...)
for _, lang in ipairs{...} do
if type(lang) == "string" then
lang = export.getByCode(lang, nil, true, nil, useRequire)
end
if lang:hasAncestor(self) then
return true
end
end
return false
return false
end
end
end
--[==[Returns the name of the main category of that language. Example: {{code|lua|"French language"}} for French, whose category is at [[:Category:French language]]. Unless optional argument <code>nocap</code> is given, the language name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the language name is lowercase and the returned value of this function is used in the middle of a sentence.]==]
 
function Language:getCategoryName(nocap)
 
if not self._categoryName then
function Language:transliterate(text, sc, module_override)
local name = self:getCanonicalName()
if not ((module_override or self._rawData.translit_module) and text) then
-- Only add " language" if a regular language.
return nil
if #self._stack == 1 then
-- If the name already has "language" in it, don't add it.
if not name:match("[Ll]anguage$") then
name = name .. " language"
end
end
self._categoryName = name
end
if nocap then
return self._categoryName
else
return mw.getContentLanguage():ucfirst(self._categoryName)
end
end
end
--[==[Creates a link to the category; the link text is the canonical name.]==]
if module_override then
function Language:makeCategoryLink()
require("Module:debug").track("module_override")
return "[[:Category:" .. self:getCategoryName() .. "|" .. self:getDisplayForm() .. "]]"
end
end
function Language:getStandardCharacters(sc)
return require("Module:" .. (module_override or self._rawData.translit_module)).tr(text, self:getCode(), sc and sc:getCode() or nil)
if type(self._rawData.standardChars) ~= "table" then
end
return self._rawData.standardChars
 
else
function Language:hasTranslit()
if sc and type(sc) ~= "string" then
return self._rawData.translit_module and true or false
checkObject("script", nil, sc)
end
sc = sc:getCode()
 
end
 
if (not sc) or sc == "None" then
function Language:link_tr()
local scripts = {}
return self._rawData.link_tr and true or false
for _, script in pairs(self._rawData.standardChars) do
end
table.insert(scripts, script)
 
end
 
return table.concat(scripts)
function Language:toJSON()
end
local entryNamePatterns = nil
if self._rawData.standardChars[sc] then
local entryNameRemoveDiacritics = nil
return self._rawData.standardChars[sc] .. (self._rawData.standardChars[1] or "")
end
end
end
--[==[Make the entry name (i.e. the correct page name).]==]
function Language:makeEntryName(text, sc)
if (not text) or text == "" then
return text, nil, {}
end
-- Set `unsupported` as true if certain conditions are met.
local unsupported
-- Check if there's an unsupported character. \239\191\189 is the replacement character U+FFFD, which can't be typed directly here due to an abuse filter. Unix-style dot-slash notation is also unsupported, as it is used for relative paths in links, as are 3 or more consecutive tildes.
if (
text:find("[#<>%[%]_{|}]") or
text:find("\239\191\189") or
text:find("%f[^%z/]%.%.?%f[%z/]") or
text:find("~~~")
) then
unsupported = true
-- If it looks like an interwiki link.
elseif text:find(":") then
local m_utildata = conditionalRequire("Module:utilities/data")
local prefix = text:gsub("^:*(.-):.*", string.ulower)
if m_utildata.interwikis[prefix] or m_utildata.namespaces[prefix] then
unsupported = true
end
end
-- Check if the text is a listed unsupported title.
local unsupportedTitles = conditionalRequire("Module:links/data").unsupported_titles
if unsupportedTitles[text] then
return "Unsupported titles/" .. unsupportedTitles[text], nil, {}
end
sc = checkScript(text, self, sc)
local fail, cats
text = normalize(text, sc)
text, fail, cats = iterateSectionSubstitutions(text, nil, nil, self, sc, self._rawData.entry_name, "makeEntryName")
text = mw.ustring.gsub(text, "^[¿¡]?([^%s%p]+)%s*[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]?$", "%1") or text
-- Escape unsupported characters so they can be used in titles. ` is used as a delimiter for this, so a raw use of it in an unsupported title is also escaped here to prevent interference; this is only done with unsupported titles, though, so inclusion won't in itself mean a title is treated as unsupported (which is why it's excluded from the earlier test).
if unsupported then
local unsupported_characters = conditionalRequire("Module:links/data").unsupported_characters
text = text
:gsub("[#<>%[%]_`{|}\239]\191?\189?", unsupported_characters)
:gsub("%f[^%z/]%.%.?%f[%z/]", function(m)
return m:gsub("%.", "`period`")
end)
:gsub("~~~+", function(m)
return m:gsub("~", "`tilde`")
end)
text = "Unsupported titles/" .. text
end
return text, fail, cats
end
--[==[Generates alternative forms using a specified method, and returns them as a table. If no method is specified, returns a table containing only the input term.]==]
function Language:generateForms(text, sc)
if self._rawData.generate_forms then
sc = checkScript(text, self, sc)
return require("Module:" .. self._rawData.generate_forms).generateForms(text, self:getCode(), sc:getCode())
else
return {text}
end
end
--[==[Creates a sort key for the given entry name, following the rules appropriate for the language. This removes diacritical marks from the entry name if they are not considered significant for sorting, and may perform some other changes. Any initial hyphen is also removed, and anything parentheses is removed as well.
The <code>sort_key</code> setting for each language in the data modules defines the replacements made by this function, or it gives the name of the module that takes the entry name and returns a sortkey.]==]
function Language:makeSortKey(text, sc)
if (not text) or text == "" then
return text, nil, {}
end
if text:find("<[^<>]+>") then
track("track HTML tag")
end
-- Remove soft hyphens, strip markers and HTML tags.
text = text:gsub("­", "")
text = mw.text.unstrip(text)
:gsub("<[^<>]+>", "")
text = mw.uri.decode(text, "PATH")
text = checkNoEntities(text)
-- Remove initial hyphens and * unless the term only consists of spacing + punctuation characters.
text = mw.ustring.gsub(text, "^([􀀀-􏿽]*)[-־ـ᠊*]+([􀀀-􏿽]*)(.*[^%s%p].*)", "%1%2%3")
sc = checkScript(text, self, sc)
text = normalize(text, sc)
text = removeCarets(text, sc)
-- For languages with dotted dotless i, ensure that "İ" is sorted as "i", and "I" is sorted as "ı".
if self:hasDottedDotlessI() then
text = text
:gsub(mw.ustring.toNFD("İ"), "i")
:gsub("I", "ı")
text = sc:toFixedNFD(text)
end
-- Convert to lowercase, make the sortkey, then convert to uppercase. Where the language has dotted dotless i, it is usually not necessary to convert "i" to "İ" and "ı" to "I" first, because "I" will always be interpreted as conventional "I" (not dotless "İ") by any sorting algorithms, which will have been taken into account by the sortkey substitutions themselves. However, if no sortkey substitutions have been specified, then conversion is necessary so as to prevent "i" and "ı" both being sorted as "I".
-- An exception is made for scripts that (sometimes) sort by scraping page content, as that means they are sensitive to changes in capitalization (as it changes the target page).
local fail, cats
if not sc:sortByScraping() then
text = text:ulower()
end
text, fail, cats = iterateSectionSubstitutions(text, nil, nil, self, sc, self._rawData.sort_key, "makeSortKey")
if not sc:sortByScraping() then
if self:hasDottedDotlessI() and not self._rawData.sort_key then
text = text
:gsub("ı", "I")
:gsub("i", "İ")
text = sc:toFixedNFC(text)
end
text = text:uupper()
end
-- Remove parentheses, as long as they are either preceded or followed by something.
text = text
:gsub("(.)[()]+", "%1")
:gsub("[()]+(.)", "%1")
text = require("Module:string utilities").escape_risky_characters(text)
return text, fail, cats
end
--[==[Create the form used as as a basis for display text and transliteration.]==]
if self._rawData.entry_name then
local function processDisplayText(text, self, sc, keepCarets, keepPrefixes)
entryNameRemoveDiacritics = self._rawData.entry_name.remove_diacritics
local subbedChars = {}
if self._rawData.entry_name.from then
text, subbedChars = doTempSubstitutions(text, subbedChars, keepCarets)
entryNamePatterns = {}
for i, from in ipairs(self._rawData.entry_name.from) do
text = mw.uri.decode(text, "PATH")
local to = self._rawData.entry_name.to[i] or ""
text = checkNoEntities(text)
table.insert(entryNamePatterns, { from = from, to = to })
sc = checkScript(text, self, sc)
local fail, cats
text = normalize(text, sc)
text, fail, cats, subbedChars = iterateSectionSubstitutions(text, subbedChars, keepCarets, self, sc, self._rawData.display_text, "makeDisplayText")
text = removeCarets(text, sc)
-- Remove any interwiki link prefixes (unless they have been escaped or this has been disabled).
if text:match(":") and not keepPrefixes then
local m_utildata, rep = conditionalRequire("Module:utilities/data")
repeat
text, rep = text:gsub("\\\\(\\*:)", "\3%1")
until rep == 0
text = text
:gsub("\\:", "\4")
while true do
local prefix = text:gsub("^(.-):.+", function(m1)
return m1:gsub("\244[\128-\191]*", "")
end)
if not prefix or prefix == text then
break
end
local lower_prefix = prefix:ulower()
if not (m_utildata.interwikis[lower_prefix] or prefix == "") then
break
end
text = text:gsub("^(.-):(.*)", function(m1, m2)
local ret = {}
for subbedChar in m1:gmatch("\244[\128-\191]*") do
table.insert(ret, subbedChar)
end
return table.concat(ret) .. m2
end)
end
end
text = text
:gsub("\3", "\\")
:gsub("\4", ":")
end
end
return text, fail, cats, subbedChars
end
end
--[==[Make the display text (i.e. what is displayed on the page).]==]
local ret = {
function Language:makeDisplayText(text, sc, keepPrefixes)
ancestors = self._rawData.ancestors,
if (not text) or text == "" then
canonicalName = self:getCanonicalName(),
return text, nil, {}
categoryName = self:getCategoryName(),
end
code = self._code,
entryNamePatterns = entryNamePatterns,
local fail, cats, subbedChars
family = self._rawData[3] or self._rawData.family,
text, fail, cats, subbedChars = processDisplayText(text, self, sc, nil, keepPrefixes)
otherNames = self:getOtherNames(),
scripts = self._rawData.scripts,
text = require("Module:string utilities").escape_risky_characters(text)
type = self:getType(),
return undoTempSubstitutions(text, subbedChars), fail, cats
wikimediaLanguages = self._rawData.wikimedia_codes,
end
wikidataItem = self:getWikidataItem(),
}
--[==[Transliterates the text from the given script into the Latin script (see [[Wiktionary:Transliteration and romanization]]). The language must have the <code>translit</code> property for this to work; if it is not present, {{code|lua|nil}} is returned.
return require("Module:JSON").toJSON(ret)
Returns three values:
end
# The transliteration.
 
# A boolean which indicates whether the transliteration failed for an unexpected reason. If {{code|lua|false}}, then the transliteration either succeeded, or the module is returning nothing in a controlled way (e.g. the input was {{code|lua|"-"}}). Generally, this means that no maintenance action is required. If {{code|lua|true}}, then the transliteration is {{code|lua|nil}} because either the input or output was defective in some way (e.g. [[Module:ar-translit]] will not transliterate non-vocalised inputs, and this module will fail partially-completed transliterations in all languages). Note that this value can be manually set by the transliteration module, so make sure to cross-check to ensure it is accurate.
# A table of categories selected by the transliteration module, which should be in the format expected by {{code|lua|format_categories}} in [[Module:utilities]].
The <code>sc</code> parameter is handled by the transliteration module, and how it is handled is specific to that module. Some transliteration modules may tolerate {{code|lua|nil}} as the script, others require it to be one of the possible scripts that the module can transliterate, and will show an error if it's not one of them. For this reason, the <code>sc</code> parameter should always be provided when writing non-language-specific code.
The <code>module_override</code> parameter is used to override the default module that is used to provide the transliteration. This is useful in cases where you need to demonstrate a particular module in use, but there is no default module yet, or you want to demonstrate an alternative version of a transliteration module before making it official. It should not be used in real modules or templates, only for testing. All uses of this parameter are tracked by [[Template:tracking/module_override]].
'''Known bugs''':
* This function assumes {tr(s1) .. tr(s2) == tr(s1 .. s2)}. When this assertion fails, wikitext markups like <nowiki>'''</nowiki> can cause wrong transliterations.
* HTML entities like <code>&amp;apos;</code>, often used to escape wikitext markups, do not work.]==]
function Language:transliterate(text, sc, module_override)
-- If there is no text, or the language doesn't have transliteration data and there's no override, return nil.
if not (self._rawData.translit or module_override) then
return nil, false, {}
elseif (not text) or text == "" or text == "-" then
return text, false, {}
end
-- If the script is not transliteratable (and no override is given), return nil.
sc = checkScript(text, self, sc)
if not (sc:isTransliterated() or module_override) then
return nil, true, {}
end
-- Remove any strip markers.
text = mw.text.unstrip(text)
-- Get the display text with the keepCarets flag set.
local fail, cats, subbedChars
text, fail, cats, subbedChars = processDisplayText(text, self, sc, true)
-- Transliterate (using the module override if applicable).
text, fail, cats, subbedChars = iterateSectionSubstitutions(text, subbedChars, true, self, sc, module_override or self._rawData.translit, "tr")
-- Incomplete transliterations return nil.
if text then
if sc:countCharacters(text) > 0 then
-- Remove any characters in (extended) Latin, which includes Latin characters also included in other scripts (as these are false positives). Anything remaining should only be script code "None" (e.g. numerals).
local check_text = mw.ustring.gsub(text, "[" .. require("Module:scripts").getByCode("Latnx"):getCharacters() .. "]", "")
if require("Module:scripts").findBestScriptWithoutLang(check_text) ~= "None" then
return nil, true, cats
end
end
else
return nil, true, cats
end
text = require("Module:string utilities").escape_risky_characters(text)
text = undoTempSubstitutions(text, subbedChars)
-- If the script does not use capitalization, then capitalize any letters of the transliteration which are immediately preceded by a caret (and remove the caret).
if text and not sc:hasCapitalization() and text:match("%^") then
text = processCarets(text, "%^([\128-\191\244]*%*?)([^\128-\191\244][\128-\191]*)", function(m1, m2)
return m1 .. m2:uupper()
end)
end
-- Track module overrides.
if module_override ~= nil then
track("module_override")
end
fail = text == nil and (not not fail) or false
return text, fail, cats
end
function Language:overrideManualTranslit()
return not not self._rawData.override_translit
end
--[==[Returns {{code|lua|true}} if the language has a transliteration module, or {{code|lua|false}} if it doesn't.]==]
function Language:hasTranslit()
return not not self._rawData.translit
end
function Language:link_tr()
return not not self._rawData.link_tr
end
--[==[Returns {{code|lua|true}} if the language uses the letters I/ı and İ/i, or {{code|lua|false}} if it doesn't.]==]
function Language:hasDottedDotlessI()
return not not self._rawData.dotted_dotless_i
end
function Language:toJSON(returnTable)
local entryNamePatterns = nil
local entryNameRemoveDiacritics = nil
if self._rawData.entry_name then
entryNameRemoveDiacritics = self._rawData.entry_name.remove_diacritics
if self._rawData.entry_name.from then
entryNamePatterns = {}
for i, from in ipairs(self._rawData.entry_name.from) do
table.insert(entryNamePatterns, {from = from, to = self._rawData.entry_name.to[i] or ""})
end
end
end
if not self._type then
self:hasType()
end
local types = {}
for type in pairs(self._type) do
table.insert(types, type)
end
local ret = {
ancestors = self:getAncestorCodes(),
canonicalName = self:getCanonicalName(),
categoryName = self:getCategoryName("nocap"),
code = self:getCode(),
entryNamePatterns = entryNamePatterns,
entryNameRemoveDiacritics = entryNameRemoveDiacritics,
family = self:getFamilyCode(),
otherNames = self:getOtherNames(true),
aliases = self:getAliases(),
varieties = self:getVarieties(),
scripts = self:getScriptCodes(),
parent = self._parentCode or nil,
nonEtymological = self._nonEtymologicalCode or nil,
type = types,
wikimediaLanguages = self:getWikimediaLanguageCodes(),
wikidataItem = self:getWikidataItem(),
}
ret = require("Module:table").deepcopy(ret)
if returnTable then
return ret
else
return require("Module:JSON").toJSON(ret)
end
end
--[==[
<span style="color: #BA0000">This function is not for use in entries or other content pages.</span>
Returns a blob of data about the language. The format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes.
-- Do NOT use these methods!
-- All uses should be pre-approved on the talk page!
]==]
function Language:getRawData()
local rawData = {}
for _, element in ipairs(self._stack) do
for k, v in pairs(element) do
rawData[k] = v
end
end
return rawData
end
--[==[<span style="color: #BA0000">This function is not for use in entries or other content pages.</span>
Returns a blob of data about the language that contains the "extra data". Much like with getRawData, the format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes.]==]
function Language:getRawExtraData()
if #self._stack == 1 then
self:loadInExtraData()
end
return self._extraData
end
local function getRawExtraLanguageData(code)
local modulename = export.getExtraDataModuleName(code)
return modulename and conditionalRequire("Module:" .. modulename)[code] or nil
end


function Language:loadInExtraData()
-- Do NOT use this method!
if not self._extraData then
-- All uses should be pre-approved on the talk page!
-- load extra data from module and assign to _extraData field
function Language:getRawData()
-- use empty table as a fallback if extra data is nil
return self._rawData
self._extraData = getRawExtraLanguageData(self:getCode()) or {}
end
end
return Language
end
end


local function make_stack(code, data, parent, useRequire)
Language.__index = Language
parent.__index = parent
 
local lang = {_code = code}
-- Full language.
if not parent._stack then
-- Create stack, accessed with rawData metamethod.
lang._stack = parent._rawData and {parent._rawData, data} or {data}
lang._rawData = setmetatable({}, {
__index = function(t, k)
-- Data that isn't inherited from the parent.
local function no_inherit(lang, t, k)
if (
k == "aliases" or
k == "varieties" or
k == "otherNames"
) then
return lang._stack[#lang._stack][k]
end
end
-- Data that is appended by each generation.
local function append_data(lang, t, k)
if k == "type" then
local parts = {}
for i = 1, #lang._stack do
table.insert(parts, lang._stack[i][k])
end
if type(parts[1]) == "string" then
return table.concat(parts, ", ")
end
end
end
-- Otherwise, iterate down the stack, looking for a match.
local function inherit_data(lang, t, k)
local i = #lang._stack
while not lang._stack[i][k] and i > 1 do
i = i - 1
end
return lang._stack[i][k]
end
local ret = no_inherit(lang, t, k) or
append_data(lang, t, k) or
inherit_data(lang, t, k)
if (
k == 4 or
k == "ancestors" or
k == "wikimedia_codes"
) then
if type(ret) == "table" then
return ret
elseif type(ret) == "string" then
return mw.text.split(ret, "%s*,%s*")
end
else
return ret
end
end,
-- Retain immutability (as writing to rawData will break functionality).
__newindex = function()
error("not allowed to edit rawData")
end
})
-- Non-etymological code is the parent code.
lang._nonEtymologicalCode = parent._code or code
-- Etymology-only.
else
-- Copy over rawData and stack to the new object, and add new layer to stack.
lang._rawData = parent._rawData
lang._stack = parent._stack
table.insert(lang._stack, data)
-- Copy non-etymological code.
lang._nonEtymologicalCode = parent._nonEtymologicalCode
end
return setmetatable(lang, parent)
end


-- Edits for DJP WIKI - added support for DJP's four character codes
function export.getDataModuleName(code)
function export.getDataModuleName(code)
if code:match("^%l%l$") then
if code:find("^%l%l$") then
return "languages/data/2"
return "languages/data2"
elseif code:match("^%l%l%l$") then
elseif code:find("^%l%l%l$") then
local prefix = code:sub(1, 1)
local prefix = code:sub(1, 1)
return "languages/data/3/" .. prefix
return "languages/data3/" .. prefix
elseif code:match("^%l%l%l%l$") then
elseif code:find("^[%l-]+$") then
return "languages/data/djp"
return "languages/datax"
elseif code:match("^[%l-]+$") then
return "languages/data/exceptional"
else
else
return nil
return nil
Line 1,247: Line 386:
end
end


function export.getExtraDataModuleName(code)
 
local dataModule = export.getDataModuleName(code)
local function getRawLanguageData(code)
return dataModule and dataModule .. "/extra" or nil
local modulename = export.getDataModuleName(code)
return modulename and mw.loadData("Module:" .. modulename)[code] or nil
end
end


function export.makeObject(code, data, useRequire)
 
if not data then
function export.makeObject(code, data)
return nil
if data and data.deprecated then
require("Module:debug").track {
"languages/deprecated",
"languages/deprecated/" .. code
}
end
end
code = data.main_code or code
return data and setmetatable({ _rawData = data, _code = code }, Language) or nil
if data.type:find("family") and not data[5] then
return require("Module:families").makeObject(code, data, useRequire)
else
local parent
if data[5] then
parent = export.getByCode(data[5], nil, true, true, useRequire)
else
parent = make_language(code, data, useRequire)
end
return make_stack(code, data, parent, useRequire)
end
end
end


--[==[Finds the language whose code matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">paramForError</code> is {{code|lua|true}}, a generic error message mentioning the bad code is generated; otherwise <code class="n">paramForError</code> should be a string or number specifying the parameter that the code came from, and this parameter will be mentioned in the error message along with the bad code. If <code class="n">allowEtymLang</code> is specified, etymology language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes.]==]
 
function export.getByCode(code, paramForError, allowEtymLang, allowFamily, useRequire)
function export.getByCode(code)
if type(code) ~= "string" then
if type(code) ~= "string" then
local typ
error("The function getByCode expects a string as its first argument, but received " .. (code == nil and "nil" or "a " .. type(code)) .. ".")
if not code then
typ = "nil"
elseif checkObject("language", true, code) then
typ = "a language object"
elseif checkObject("family", true, code) then
typ = "a family object"
else
typ = "a " .. type(code)
end
error("The function getByCode expects a string as its first argument, but received " .. typ .. ".")
end
local function conditionalRequire(modulename)
if useRequire then
return require(modulename)
else
return mw.loadData(modulename)
end
end
local modulename = export.getDataModuleName(code)
local data = modulename and
conditionalRequire("Module:" .. modulename)[code] or
(allowEtymLang and require("Module:etymology languages/track-bad-etym-code")(code) and conditionalRequire("Module:etymology languages/data")[code]) or
(allowFamily and conditionalRequire("Module:families/data")[code]) or
(allowEtymLang and allowFamily and conditionalRequire("Module:families/data/etymology")[code])
local retval = code and data and export.makeObject(code, data, useRequire)
if not retval and paramForError then
require("Module:languages/errorGetBy").code(code, paramForError, allowEtymLang, allowFamily)
end
end
return retval
return export.makeObject(code, getRawLanguageData(code))
end
end


--[==[Like {{code|lua|getByCanonicalName()}}, except it also looks at the <code class="n">otherNames</code> listed in the non-etymology language data modules, and does not (currently) have options to look up etymology languages and families.]==]
 
function export.getByName(name, errorIfInvalid)
function export.getByName(name)
local byName = mw.loadData("Module:languages/by name")
local byName = mw.loadData("Module:languages/by name")
local code = byName.all and byName.all[name] or byName[name]
local code = byName.all and byName.all[name] or byName[name]
if not code then
if not code then
if errorIfInvalid then
return nil
error("The language name \"" .. name .. "\" is not valid. See [[Wiktionary:List of languages]].")
else
return nil
end
end
end
return export.getByCode(code)
return export.makeObject(code, getRawLanguageData(code))
end
end


--[==[Finds the language whose canonical name (the name used to represent that language on Wiktionary) or other name matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">allowEtymLang</code> is specified, etymology language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes.
 
The canonical name of languages should always be unique (it is an error for two languages on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result.
function export.getByCanonicalName(name)
This function is powered by [[Module:languages/canonical names]], which contains a pre-generated mapping of non-etymology-language canonical names to codes. It is generated by going through the [[:Category:Language data modules]] for non-etymology languages. When <code class="n">allowEtymLang</code> is specified for the above function, [[Module:etymology languages/canonical names]] may also be used, and when <code class="n">allowFamily</code> is specified for the above function, [[Module:families/canonical names]] may also be used.]==]
local byName = mw.loadData("Module:languages/canonical names")
function export.getByCanonicalName(name, errorIfInvalid, allowEtymLang, allowFamily, useRequire)
local function conditionalRequire(modulename)
if useRequire then
return require(modulename)
else
return mw.loadData(modulename)
end
end
local byName = conditionalRequire("Module:languages/canonical names")
local code = byName and byName[name]
local code = byName and byName[name]
if not code and allowEtymLang then
if not code then
byName = conditionalRequire("Module:etymology languages/canonical names")
return nil
code = byName and byName[name] or
byName[name:gsub(" [Ss]ubstrate$", "")] or
byName[name:gsub("^a ", "")] or
byName[name:gsub("^a ", ""):gsub(" [Ss]ubstrate$", "")] or
-- For etymology families like "ira-pro".
-- FIXME: This is not ideal, as it allows " languages" to be appended to any etymology-only language, too.
byName[name:match("^(.*) languages$")]
end
if not code and allowFamily then
byName = conditionalRequire("Module:families/canonical names")
code = byName and byName[name] or
byName[name:match("^(.*) languages$")]
end
local retval = code and export.getByCode(code, errorIfInvalid, allowEtymLang, allowFamily, useRequire)
if not retval and errorIfInvalid then
require("Module:languages/errorGetBy").canonicalName(name, allowEtymLang, allowFamily)
end
end
return retval
return export.makeObject(code, getRawLanguageData(code))
end
end


--[==[Used by [[Module:languages/data/2]] (et al.) to add default types to the entities returned.]==]
 
function export.addDefaultTypes(data, regular, ...)
function export.iterateAll()
for _, entity in pairs(data) do
mw.incrementExpensiveFunctionCount()
-- "regular" encompasses everything that doesn't have another type already assigned.
local m_data = mw.loadData("Module:languages/alldata")
if regular then
local func, t, var = pairs(m_data)
entity.type = entity.type or "regular"
end
return function()
local types = table.concat({...}, ", ")
local code, data = func(t, var)
if #types > 0 then
return export.makeObject(code, data)
entity.type =  types .. (entity.type and (", " .. entity.type) or "")
end
end
end
return data
end
end


--[==[Used by [[Module:etymology languages/data]] and [[Module:families/data/etymology]] to finalize the data into the format that is actually returned.]==]
--[[ If language is an etymology language, iterates through parent languages
function export.finalizeEtymologyData(data)
until it finds a non-etymology language. ]]
local aliases = {}
function export.getNonEtymological(lang)
for code, entity in pairs(data) do
while lang:getType() == "etymology language" do
-- Move parent to 5 and family to 3.
local parentCode = lang:getParentCode()
data[code][5] = data[code][3]
lang = export.getByCode(parentCode)
data[code][3] = data[code].family
or require("Module:etymology languages").getByCode(parentCode)
data[code].family = nil
or require("Module:families").getByCode(parentCode)
-- Assign any alias codes listed in alias_codes. The main_code field is used to make sure objects always use that to identify themselves, which means all aliases are fungible with their counterparts.
if entity.alias_codes then
entity.main_code = code
for _, alias in ipairs(entity.alias_codes) do
aliases[alias] = entity
end
entity.alias_codes = nil
end
end
end
for code, alias in pairs(aliases) do
data[code] = alias
return lang
end
return data
end
 
--[==[For backwards compatibility only; modules should require the /error themselves.]==]
function export.err(lang_code, param, code_desc, template_tag, not_real_lang)
return require("Module:languages/error")(lang_code, param, code_desc, template_tag, not_real_lang)
end
end


return export
return export
Retrieved from "https://wiki.languageinvention.com/index.php?title=Special:ComparePages"