Module:script utilities: Difference between revisions

Jump to navigation Jump to search

Module:script utilities (view source)

Revision as of 18:12, 11 January 2025

5,012 bytes added ,  11 January
no edit summary
No edit summary
No edit summary
 
Line 1: Line 1:
local export = {}
local export = {}
local anchors_module = "Module:anchors"
local links_module = "Module:links"
local munge_text_module = "Module:munge text"
local parameters_module = "Module:parameters"
local scripts_module = "Module:scripts"
local string_utilities_module = "Module:string utilities"
local utilities_module = "Module:utilities"
local concat = table.concat
local insert = table.insert
local require = require
local toNFD = mw.ustring.toNFD
--[==[
Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==]
local function embedded_language_links(...)
embedded_language_links = require(links_module).embedded_language_links
return embedded_language_links(...)
end
local function format_categories(...)
format_categories = require(utilities_module).format_categories
return format_categories(...)
end
local function get_script(...)
get_script = require(scripts_module).getByCode
return get_script(...)
end
local function language_anchor(...)
language_anchor = require(anchors_module).language_anchor
return language_anchor(...)
end
local function munge_text(...)
munge_text = require(munge_text_module)
return munge_text(...)
end
local function process_params(...)
process_params = require(parameters_module).process
return process_params(...)
end
local function u(...)
u = require(string_utilities_module).char
return u(...)
end
local function ugsub(...)
ugsub = require(string_utilities_module).gsub
return ugsub(...)
end
local function umatch(...)
umatch = require(string_utilities_module).match
return umatch(...)
end
--[==[
Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==]
local m_data
local function get_data()
m_data, get_data = mw.loadData("Module:script utilities/data"), nil
return m_data
end


--[=[
--[=[
Line 5: Line 73:
[[Module:script utilities/data]]
[[Module:script utilities/data]]
[[Module:scripts]]
[[Module:scripts]]
[[Module:senseid]] (only when id's present)
[[Module:anchors]] (only when IDs present)
[[Module:string utilities]] (only when hyphens in Korean text or spaces in vertical text)
[[Module:string utilities]] (only when hyphens in Korean text or spaces in vertical text)
[[Module:languages]]
[[Module:languages]]
[[Module:parameters]]
[[Module:parameters]]
[[Module:utilities/format_categories]]
[[Module:utilities]]
]=]
]=]


function export.is_Latin_script(sc)
function export.is_Latin_script(sc)
-- Latn, Latf, Latinx, pjt-Latn
-- Latn, Latf, Latg, pjt-Latn
return sc:getCode():find("Lat") and true or false
return sc:getCode():find("Lat") and true or false
end
end


-- Used by [[Template:lang]]
--[==[{{temp|#invoke:script utilities|lang_t}}
function export.lang_t(frame)
This is used by {{temp|lang}} to wrap portions of text in a language tag. See there for more information.]==]
params = {
do
[1] = {},
local function get_args(frame)
[2] = { allow_empty = true, default = "" },
return process_params(frame:getParent().args, {
["sc"] = {},
[1] = {required = true, type = "language", default = "und"},
["face"] = {},
[2] = {required = true, allow_empty = true, default = ""},
["class"] = {},
["sc"] = {type = "script"},
}
["face"] = true,
["class"] = true,
})
end
local args = require("Module:parameters").process(frame:getParent().args, params)
function export.lang_t(frame)
local NAMESPACE = mw.title.getCurrentTitle().nsText
local args = get_args(frame)
local lang = args[1] or (NAMESPACE == "Template" and "und") or error("Language code has not been specified. Please pass parameter 1 to the template.")
local lang = args[1]
lang = require("Module:languages").getByCode(lang) or require("Module:languages").err(lang, 1)
local sc = args["sc"]
local text = args[2]
local text = args[2]
local cats = {}
local sc = args["sc"]
if sc then
sc = (sc and (require("Module:scripts").getByCode(sc) or error("The script code \"" .. sc .. "\" is not valid.")) or nil)
else
sc = lang:findBestScript(text)
local face = args["face"]
end
if (face == "term_i" or face == "usex") and not export.is_Latin_script(sc) then
text = embedded_language_links{
face = nil
term = text,
lang = lang,
sc = sc
}
cats = #cats > 0 and format_categories(cats, lang, "-", nil, nil, sc) or ""
local face = args["face"]
local class = args["class"]
return export.tag_text(text, lang, sc, face, class) .. cats
end
end
return export.tag_text(text, lang, sc, face, class)
end
end


-- Wrap text in the appropriate HTML tags with language and script class.
--[==[Wraps the given text in HTML tags with appropriate CSS classes (see [[WT:CSS]]) for the [[Module:languages#Language objects|language]] and script. This is required for all non-English text on Wiktionary.
The actual tags and CSS classes that are added are determined by the <code>face</code> parameter. It can be one of the following:
; {{code|lua|"term"}}
: The text is wrapped in {{code|html|2=<i class="(sc) mention" lang="(lang)">...</i>}}.
; {{code|lua|"head"}}
: The text is wrapped in {{code|html|2=<strong class="(sc) headword" lang="(lang)">...</strong>}}.
; {{code|lua|"hypothetical"}}
: The text is wrapped in {{code|html|2=<span class="hypothetical-star">*</span><i class="(sc) hypothetical" lang="(lang)">...</i>}}.
; {{code|lua|"bold"}}
: The text is wrapped in {{code|html|2=<b class="(sc)" lang="(lang)">...</b>}}.
; {{code|lua|nil}}
: The text is wrapped in {{code|html|2=<span class="(sc)" lang="(lang)">...</span>}}.
The optional <code>class</code> parameter can be used to specify an additional CSS class to be added to the tag.]==]
function export.tag_text(text, lang, sc, face, class, id)
function export.tag_text(text, lang, sc, face, class, id)
if not sc then
if not sc then
sc = require("Module:scripts").findBestScript(text, lang)
sc = lang:findBestScript(text)
end
end
-- Replace space characters with newlines in Mongolian-script text, which is written top-to-bottom.
-- Replace space characters with newlines in Mongolian-script text, which is written top-to-bottom.
--[[if sc:getDirection() == "down" and text:find(" ") then
if sc:getDirection():match("vertical") and text:find(" ") then
text = require("Module:munge_text")(text, function(txt)
text = munge_text(text, function(txt)
-- having extra parentheses makes sure only the first return value gets through
-- having extra parentheses makes sure only the first return value gets through
return (txt:gsub(" +", "<br>"))
return (txt:gsub(" +", "<br>"))
end)
end)
end]]
end


-- Hack Korean script text to remove hyphens.
-- Hack Korean script text to remove hyphens.
-- XXX: This should be handled in a more general fashion, but needs to
-- FIXME: This should be handled in a more general fashion, but needs to
-- be efficient by not doing anything if no hyphens are present, and currently this is the only
-- be efficient by not doing anything if no hyphens are present, and currently this is the only
-- language needing such processing.
-- language needing such processing.
-- 20220221: Also convert 漢字(한자) to ruby, instead of needing [[Template:Ruby]].
-- 20220221: Also convert 漢字(한자) to ruby, instead of needing [[Template:Ruby]].
if sc:getCode() == "Kore" and (text:find("%-") or text:find("[()]")) then
if sc:getCode() == "Kore" and (text:find("-", 1, true) or text:find("[()]")) then
text = require("Module:munge_text")(text, function(txt)
text = munge_text(text, function(txt)
-- Hani/Hang regex is a reasonable subset of Hani/Hang from [[Module:scripts/data]],
txt = txt:gsub("%-(%-?)", "%1")
-- last checked on 20220221
txt = ugsub(txt, "([%-".. get_script("Hani"):getCharacters() .. "]+)%(([%-" .. get_script("Hang"):getCharacters() .. "]+)%)", "<ruby>%1<rp>(</rp><rt>%2</rt><rp>)</rp></ruby>")
txt = txt:gsub("%-", "")
txt = mw.ustring.gsub(txt, "([一-鿿㐀-䶿𠀀-𮯯𰀀-𱍏]+)%(([가-힣ᄀ-ᇿꥠ-ꥼힰ-ퟻ]+)%)", "<ruby>%1<rp>(</rp><rt>%2</rt><rp>)</rp></ruby>")
return txt
return txt
end)
end)
end
end
if sc:getCode() == "Imag" then
if sc:getCode() == "Image" then
face = nil
face = nil
end
end
 
if (face == "term_i" or face == "usex") and not export.is_Latin_script(sc) then
face = nil
end
local function class_attr(classes)
local function class_attr(classes)
table.insert(classes, 1, sc:getCode())
-- if the script code is hyphenated (i.e. language code-script code, add the last component as a class as well)
-- e.g. ota-Arab adds both Arab and ota-Arab as classes
if sc:getCode():find("-", 1, true) then
insert(classes, 1, (ugsub(sc:getCode(), ".+%-", "")))
insert(classes, 2, sc:getCode())
else
insert(classes, 1, sc:getCode())
end
if class and class ~= '' then
if class and class ~= '' then
table.insert(classes, class)
insert(classes, class)
end
end
return 'class="' .. table.concat(classes, ' ') .. '"'
return 'class="' .. concat(classes, ' ') .. '"'
end
end
Line 95: Line 187:
local output = {}
local output = {}
if id then
if id then
table.insert(output, 'id="' .. require("Module:senseid").anchor(lang, id) .. '"')
insert(output, 'id="' .. language_anchor(lang, id) .. '"')
end
end
table.insert(output, class_attr({...}) )
insert(output, class_attr({...}) )
if lang then
if lang then
table.insert(output, 'lang="' .. lang:getCode() .. '"')
-- FIXME: Is it OK to insert the etymology-only lang code and have it fall back to the first part of the
-- lang code (by chopping off the '-...' part)? It seems the :lang() selector does this; not sure about
-- [lang=...] attributes.
insert(output, 'lang="' .. lang:getFullCode() .. '"')
end
end
return table.concat(output, " ")
return concat(output, " ")
end
end
local data = mw.loadData("Module:script utilities/data").faces[face or "nil"]
local data = (m_data or get_data()).faces[face or "plain"]
local post = ""
if sc:getDirection() == "rtl" and (face == "translation" or mw.ustring.find(text, "%p$")) then
post = "&lrm;"
end
-- Add a script wrapper
-- Add a script wrapper
if data then
if data then
return ( data.prefix or "" ) .. '<' .. data.tag .. ' ' .. tag_attr(data.class) .. '>' .. text .. '</' .. data.tag .. '>' .. post
return ( data.prefix or "" ) .. '<' .. data.tag .. ' ' .. tag_attr(data.class) .. '>' .. text .. '</' .. data.tag .. '>'
else
else
error('Invalid script face "' .. face .. '".')
error('Invalid script face "' .. face .. '".')
Line 122: Line 212:
end
end


--[==[Tags the transliteration for given text {translit} and language {lang}. It will add the language, script subtag (as defined in [https://www.rfc-editor.org/rfc/bcp/bcp47.txt BCP 47 2.2.3]) and [https://developer.mozilla.org/en-US/docs/Web/HTML/Global_attributes/dir dir] (directional) attributes as needed.
The optional <code>kind</code> parameter can be one of the following:
; {{code|lua|"term"}}
: tag transliteration for {{temp|mention}}
; {{code|lua|"usex"}}
: tag transliteration for {{temp|usex}}
; {{code|lua|"head"}}
: tag transliteration for {{temp|head}}
; {{code|lua|"default"}}
: default
The optional <code>attributes</code> parameter is used to specify additional HTML attributes for the tag.]==]
function export.tag_translit(translit, lang, kind, attributes, is_manual)
function export.tag_translit(translit, lang, kind, attributes, is_manual)
if type(lang) == "table" then
if type(lang) == "table" then
lang = lang.getCode and lang:getCode()
-- FIXME: Do better support for etym languages; see https://www.rfc-editor.org/rfc/bcp/bcp47.txt
lang = lang.getFullCode and lang:getFullCode()
or error("Second argument to tag_translit should be a language code or language object.")
or error("Second argument to tag_translit should be a language code or language object.")
end
end
local data = mw.loadData("Module:script utilities/data").translit[kind or "default"]
local data = (m_data or get_data()).translit[kind or "default"]
local opening_tag = {}
local opening_tag = {}
table.insert(opening_tag, data.tag)
insert(opening_tag, data.tag)
if lang == "ja" then
if lang == "ja" then
table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr"')
insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr"')
else
else
table.insert(opening_tag, 'lang="' .. lang .. '-Latn"')
insert(opening_tag, 'lang="' .. lang .. '-Latn"')
table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr Latn"')
insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr Latn"')
end
end
if data.dir then
if data.dir then
table.insert(opening_tag, 'dir="' .. data.dir .. '"')
insert(opening_tag, 'dir="' .. data.dir .. '"')
end
end
table.insert(opening_tag, attributes)
insert(opening_tag, attributes)
return "<" .. table.concat(opening_tag, " ") .. ">" .. translit .. "</" .. data.tag .. ">"
return "<" .. concat(opening_tag, " ") .. ">" .. translit .. "</" .. data.tag .. ">"
end
end


function export.tag_transcription(transcription, lang, kind, attributes)
function export.tag_transcription(transcription, lang, kind, attributes)
if type(lang) == "table" then
if type(lang) == "table" then
lang = lang.getCode and lang:getCode()
-- FIXME: Do better support for etym languages; see https://www.rfc-editor.org/rfc/bcp/bcp47.txt
or error("Third argument to tag_translit should be a language code or language object.")
lang = lang.getFullCode and lang:getFullCode()
or error("Second argument to tag_transcription should be a language code or language object.")
end
end
local data = mw.loadData("Module:script utilities/data").transcription[kind or "default"]
local data = (m_data or get_data()).transcription[kind or "default"]
local opening_tag = {}
local opening_tag = {}
table.insert(opening_tag, data.tag)
insert(opening_tag, data.tag)
if lang == "ja" then
if lang == "ja" then
table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts"')
insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts"')
else
else
table.insert(opening_tag, 'lang="' .. lang .. '-Latn"')
insert(opening_tag, 'lang="' .. lang .. '-Latn"')
table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts Latn"')
insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts Latn"')
end
end
if data.dir then
if data.dir then
table.insert(opening_tag, 'dir="' .. data.dir .. '"')
insert(opening_tag, 'dir="' .. data.dir .. '"')
end
end
table.insert(opening_tag, attributes)
insert(opening_tag, attributes)
return "<" .. table.concat(opening_tag, " ") .. ">" .. transcription .. "</" .. data.tag .. ">"
return "<" .. concat(opening_tag, " ") .. ">" .. transcription .. "</" .. data.tag .. ">"
end
end


-- Add a notice to request the native script of a word
--[==[Generates a request to provide a term in its native script, if it is missing. This is used by the {{temp|rfscript}} template as well as by the functions in [[Module:links]].
The function will add entries to one of the subcategories of [[:Category:Requests for native script by language]], and do several checks on the given language and script. In particular:
* If the script was given, a subcategory named "Requests for (script) script" is added, but only if the language has more than one script. Otherwise, the main "Requests for native script" category is used.
* Nothing is added at all if the language has no scripts other than Latin and its varieties.]==]
function export.request_script(lang, sc, usex, nocat, sort_key)
function export.request_script(lang, sc, usex, nocat, sort_key)
local scripts = lang.getScripts and lang:getScripts() or error('The language "' .. lang:getCode() .. '" does not have the method getScripts. It may be unwritten.')
local scripts = lang.getScripts and lang:getScripts() or error('The language "' .. lang:getCode() .. '" does not have the method getScripts. It may be unwritten.')
Line 190: Line 296:
-- Is the script known?
-- Is the script known?
if sc then
if sc and sc:getCode() ~= "None" then
-- If the script is Latin, return nothing.
-- If the script is Latin, return nothing.
if export.is_Latin_script(sc) then
if export.is_Latin_script(sc) then
Line 196: Line 302:
end
end
if sc:getCode() ~= scripts[1]:getCode() then
if (not scripts[1]) or sc:getCode() ~= scripts[1]:getCode() then
disp_script = sc:getCanonicalName()
disp_script = sc:getCanonicalName()
end
end
-- The category needs to be specific to script only if there is chance
-- The category needs to be specific to script only if there is chance of ambiguity. This occurs when when the language has multiple scripts (or with codes such as "und").
-- of ambiguity. This occurs when lang=und, or when the language has
if (not scripts[1]) or scripts[2] then
-- multiple scripts.
if lang:getCode() == "und" or scripts[2] then
cat_script = sc:getCanonicalName()
cat_script = sc:getCanonicalName()
end
end
Line 211: Line 315:
local has_nonlatin = false
local has_nonlatin = false
for i, val in ipairs(scripts) do
for _, val in ipairs(scripts) do
if not export.is_Latin_script(val) then
if not export.is_Latin_script(val) then
has_nonlatin = true
has_nonlatin = true
Line 223: Line 327:
end
end
end
end
-- Etymology languages have their own categories, whose parents are the regular language.
local category
return "<small>[" .. disp_script .. " needed]</small>" .. (nocat and "" or
format_categories("Requests for " .. cat_script .. " script " ..
if usex then
(usex and "in" or "for") .. " " .. lang:getCanonicalName() .. " " ..
category = "Requests for " .. cat_script .. " script in " .. lang:getCanonicalName() .. " usage examples"
(usex == "quote" and "quotations" or usex and "usage examples" or "terms"),
else
lang, sort_key
category = "Requests for " .. cat_script .. " script for " .. lang:getCanonicalName() .. " terms"
)
end
)
return "<small>[" .. disp_script .. " needed]</small>" ..
(nocat and "" or require("Module:utilities/format_categories")({category}, lang, sort_key))
end
end


function export.template_rfscript(frame)
--[==[This is used by {{temp|rfscript}}. See there for more information.]==]
params = {
do
[1] = { required = true, default = "und" },
local function get_args(frame)
["sc"] = {},
local boolean = {type = "boolean"}
["usex"] = { type = "boolean" },
return process_params(frame:getParent().args, {
["nocat"] = { type = "boolean" },
[1] = {required = true, type = "language", default = "und"},
["sort"] = {},
["sc"] = {type = "script"},
}
["usex"] = boolean,
["quote"] = boolean,
["nocat"] = boolean,
["sort"] = true,
})
end
local args = require("Module:parameters").process(frame:getParent().args, params)
function export.template_rfscript(frame)
local args = get_args(frame)
local lang = require("Module:languages").getByCode(args[1], 1)
local sc = args.sc and require("Module:scripts").getByCode(args.sc, true)
local ret = export.request_script(args[1], args["sc"], args.quote and "quote" or args.usex, args.nocat, args.sort)
 
local ret = export.request_script(lang, sc, args.usex, args.nocat, args.sort)
if ret == "" then
error("This language is written in the Latin alphabet. It does not need a native script.")
if ret == "" then
else
error("This language is written in the Latin alphabet. It does not need a native script.")
return ret
else
end
return ret
end
end
end
end


function export.checkScript(text, scriptCode, result)
function export.checkScript(text, scriptCode, result)
local scriptObject = require("Module:scripts").getByCode(scriptCode)
local scriptObject = get_script(scriptCode)
if not scriptObject then
if not scriptObject then
Line 269: Line 374:
-- Remove non-letter characters.
-- Remove non-letter characters.
text = mw.ustring.gsub(text, "[%A]", "")
text = ugsub(text, "%A+", "")
-- Remove all characters of the script in question.
-- Remove all characters of the script in question.
text = mw.ustring.gsub(text, "[" .. scriptObject:getCharacters() .. "]", "")
text = ugsub(text, "[" .. scriptObject:getCharacters() .. "]+", "")
if text ~= "" then
if text ~= "" then
Retrieved from "https://linguifex.com/wiki/Special:MobileDiff/423948"

Navigation menu