Module:String2 - Revision history

imported>Gonnym: fix

2025-02-19T12:24:59Z

fix

@@ Line 12: / Line 12: @@
 end
-p.ucfirst = function (frame )
+p.ucfirst = function (frame)
 	local s = frame.args[1];
 	if not s or '' == s or s:match ('^%s+$') then								-- when <s> is nil, empty, or only whitespace
@@ Line 87: / Line 87: @@
-p.title = function (frame )
+p.title = function (frame)
 	-- http://grammar.yourdictionary.com/capitalization/rules-for-capitalization-in-titles.html
 	-- recommended by The U.S. Government Printing Office Style Manual:
@@ Line 389: / Line 389: @@
 	end
 	return boolean and 0 or ''
 end
 return p

imported>Ahecht: add p.isnumeric, which is a more WP:PEIS-efficient implementation of Template:Isnumeric

2024-09-20T15:35:27Z

add p.isnumeric, which is a more WP:PEIS-efficient implementation of Template:Isnumeric

← Older revision		Revision as of 15:35, 20 September 2024
Line 379:		Line 379:
	function p.startswith(frame)		function p.startswith(frame)
	return (frame.args[1]:sub(1, frame.args[2]:len()) == frame.args[2]) and 'yes' or ''		return (frame.args[1]:sub(1, frame.args[2]:len()) == frame.args[2]) and 'yes' or ''
			end

			-- Implements [[Template:Isnumeric]]
			function p.isnumeric(frame)
			local s = frame.args[1] or frame:getParent().args[1]
			local boolean = (frame.args.boolean or frame:getParent().args.boolean) == 'true'
			if type(s) == 'string' and mw.getContentLanguage():parseFormattedNumber( s ) then
			return boolean and 1 or s
			end
			return boolean and 0 or ''
	end		end

	return p		return p

imported>Trappist the monk: better;

2024-03-10T18:46:48Z

better;

← Older revision		Revision as of 18:46, 10 March 2024
Line 1:		Line 1:
			require ('strict');
	local p = {}		local p = {}

Line 12:		Line 13:

	p.ucfirst = function (frame )		p.ucfirst = function (frame )
	local s = mw.text.trim( frame.args[1] or "" )		local s = frame.args[1];
			if not s or '' == s or s:match ('^%s+$') then -- when <s> is nil, empty, or only whitespace
			return s; -- abandon because nothing to do
			end

			s = mw.text.trim( frame.args[1] or "" )
	local s1 = ""		local s1 = ""
	-- ~~if it~~'s a list ~~chop off and~~ (~~store as s1~~) ~~everything up to the first~~ <li>
	local ~~lipos~~ = ~~mw.ustring.find~~(s, "<li>~~" )~~		local prefix_patterns_t = { -- sequence of prefix patterns
	if ~~lipos~~ then		'^\127[^\127]UNIQ%-%-%a+%-%x+%-QINU[^\127]\127', -- stripmarker
	s1 = ~~mw.ustring~~.~~sub~~(s, ~~1, lipos + 3~~)		'^([%*;:#]+)', -- various list markup
	s = ~~mw.ustring.~~sub(s, ~~lipos + 4)~~		'^(\'\'\'*)', -- bold / italic markup
			'^(%b<>)', -- html-like tags because some templates render these
			'^(&%a+;)', -- html character entities because some templates render these
			'^(&#%d+;)', -- html numeric (decimal) entities because some templates render these
			'^(&#x%x+;)', -- html numeric (hexadecimal) entities because some templates render these
			'^(%s+)', -- any whitespace characters
			'^([%(%)%-%+%?%.%%!~!@%$%^&_={}/`,‘’„“”ʻ\|\"\'\\]+)', -- miscellaneous punctuation
			}

			local prefixes_t = {}; -- list, bold/italic, and html-like markup, & whitespace saved here

			local function prefix_strip (s) -- local function to strip prefixes from <s>
			for _, pattern in ipairs (prefix_patterns_t) do -- spin through <prefix_patterns_t>
			if s:match (pattern) then -- when there is a match
			local prefix = s:match (pattern); -- get a copy of the matched prefix
			table.insert (prefixes_t, prefix); -- save it
			s = s:sub (prefix:len() + 1); -- remove the prefix from <s>
			return s, true; -- return <s> without prefix and flag; force restart at top of sequence because misc punct removal can break stripmarker
			end
			end
			return s; -- no prefix found; return <s> with nil flag
	end		end
	-- ~~s1 is either "" or the first part of the~~ list markup, ~~so we can continue~~
	-- ~~and prepend~~ s1 to the ~~returned~~ string		local prefix_removed; -- flag; boolean true as long as prefix_strip() finds and removes a prefix
	local ~~letterpos~~
	if mw.ustring.~~find~~(s, "^%[%[[^\|]+\|[^%]]+%]%]") then		repeat -- one by one remove list, bold/italic, html-like markup, whitespace, etc from start of <s>
	-- ~~this~~ is a piped ~~wikilink~~, ~~so we capitalise the text~~, ~~not the pipe~~		s, prefix_removed = prefix_strip (s);
	~~local _~~		until (not prefix_removed); -- until <prefix_removed> is nil
	~~_, letterpos~~ = mw.ustring.~~find~~(s, "\|%W*%w") -- ~~find the~~ first letter ~~after the pipe~~
	~~else~~		s1 = table.concat (prefixes_t); -- recreate the prefix string for later reattachment
	~~letterpos~~ = mw.ustring.~~find~~(s, '%w')
	end		local first_text = mw.ustring.match (s, '^%[%[[^%]]+%]%]'); -- extract wikilink at start of string if present; TODO: this can be string.match()?
	if ~~letterpos then~~
	~~local first~~ = mw.ustring.~~sub~~(s, ~~1, letterpos~~ - 1)		local upcased;
	~~local letter~~ = mw.ustring.~~sub~~(~~s, letterpos, letterpos~~)		if first_text then
	~~local rest~~ = mw.ustring.~~sub~~(s, ~~letterpos~~ + 1)		if first_text:match ('^%[%[[^\|]+\|[^%]]+%]%]') then -- if <first_text> is a piped link
	return s1 .. ~~first~~ .. mw.ustring.upper(letter~~) .. rest~~		upcased = mw.ustring.match (s, '^%[%[[^\|]+\|%W*(%w)'); -- get first letter character
	~~else~~		upcased = mw.ustring.upper (upcased); -- upcase first letter character
	~~return s1~~ .. s		s = mw.ustring.gsub (s, '^(%[%[[^\|]+\|%W*)%w', '%1' .. upcased); -- replace
			else -- here when <first_text> is a wikilink but not a piped link
			upcased = mw.ustring.match (s, '^%[%[%W*%w'); -- get '[[' and first letter
			upcased = mw.ustring.upper (upcased); -- upcase first letter character
			s = mw.ustring.gsub (s, '^%[%[%W*%w', upcased); -- replace; no capture needed here
			end

			elseif s:match ('^%[%S+%s+[^%]]+%]') then -- if <s> is a ext link of some sort; must have label text
			upcased = mw.ustring.match (s, '^%[%S+%s+%W*(%w)'); -- get first letter character
			upcased = mw.ustring.upper (upcased); -- upcase first letter character
			s = mw.ustring.gsub (s, '^(%[%S+%s+%W*)%w', '%1' .. upcased); -- replace

			elseif s:match ('^%[%S+%s*%]') then -- if <s> is a ext link without label text; nothing to do
			return s1 .. s; -- reattach prefix string (if present) and done

			else -- <s> is not a wikilink or ext link; assume plain text
			upcased = mw.ustring.match (s, '^%W*%w'); -- get the first letter character
			upcased = mw.ustring.upper (upcased); -- upcase first letter character
			s = mw.ustring.gsub (s, '^%W*%w', upcased); -- replace; no capture needed here
	end		end

			return s1 .. s; -- reattach prefix string (if present) and done
	end		end


	p.title = function (frame )		p.title = function (frame )
Line 204:		Line 251:

	-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String		-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String
	function p._escapePattern( pattern_str)		function p._escapePattern( pattern_str )
	return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )		return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )
	end		end

imported>Trappist the monk: Undo revision 1213019104 by Trappist the monk (talk) that didna work;

2024-03-10T18:28:06Z

Undo revision 1213019104 by Trappist the monk (talk) that didna work;

Show changes

imported>Trappist the monk: sync from sandbox;

2024-03-10T18:22:14Z

sync from sandbox;

Show changes

imported>GKFX: Copy changes by User:Tholme from Module:String2/sandbox per edit request.

2022-05-14T12:03:50Z

Copy changes by User:Tholme from Module:String2/sandbox per edit request.

← Older revision		Revision as of 12:03, 14 May 2022
Line 26:		Line 26:
	-- this is a piped wikilink, so we capitalise the text, not the pipe		-- this is a piped wikilink, so we capitalise the text, not the pipe
	local _		local _
	_, letterpos = mw.ustring.find(s, "\|%A*%a") -- find the first letter after the pipe		_, letterpos = mw.ustring.find(s, "\|%W*%w") -- find the first letter after the pipe
	else		else
	letterpos = mw.ustring.find(s, '%a')		letterpos = mw.ustring.find(s, '%w')
	end		end
	if letterpos then		if letterpos then

imported>Plastikspork: Per TfD outcome

2022-01-07T16:14:43Z

Per TfD outcome

@@ Line 94: / Line 94: @@
 	local str = mw.text.trim(frame.args[1] or "")
 	return mw.text.nowiki(str)
 end

imported>GKFX: Add startswith, analogous to endswith

2021-11-18T20:15:10Z

Add startswith, analogous to endswith

← Older revision		Revision as of 20:15, 18 November 2021
Line 350:		Line 350:

	return p.hyphen_to_dash(str, spacing)		return p.hyphen_to_dash(str, spacing)
			end

			-- Similar to [[Module:String#endswith]]
			function p.startswith(frame)
			return (frame.args[1]:sub(1, frame.args[2]:len()) == frame.args[2]) and 'yes' or ''
	end		end

	return p		return p

imported>Johnuniq: update from Module:String2/sandbox: tweaks + findpagetext won't fail if given an invalid or nonexistent page title

2021-10-28T06:32:57Z

update from Module:String2/sandbox: tweaks + findpagetext won't fail if given an invalid or nonexistent page title

imported>Matthiaspaul: add optional spacing parameter to hyphen2dash for improved support in templates r/rp/ran. Default is a normal space after the separating comma.

2021-09-13T18:48:42Z

add optional spacing parameter to hyphen2dash for improved support in templates r/rp/ran. Default is a normal space after the separating comma.

← Older revision		Revision as of 18:48, 13 September 2021
Line 308:		Line 308:

	]]		]]
	function p.hyphen_to_dash( str )		function p.hyphen_to_dash( str, spacing )
	if (str == nil or str == '') then		if (str == nil or str == '') then
	return str;		return str;
Line 337:		Line 337:
	end		end

	local temp_str = table.concat (out, ', '); -- concatenate the output table into a comma separated string		local temp_str = table.concat (out, ',' .. spacing); -- concatenate the output table into a comma separated string
	temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of concatenated out		temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of concatenated out
	if accept ~= 0 then		if accept ~= 0 then
Line 349:		Line 349:
	function p.hyphen2dash( frame )		function p.hyphen2dash( frame )
	local str = frame.args[1] or ''		local str = frame.args[1] or ''
	return p.hyphen_to_dash(str)		local spacing = frame.args[2] or ' ' -- space is part of the standard separator for normal spacing (but in conjunction with templates r/rp/ran we may need a narrower spacing

			return p.hyphen_to_dash(str, spacing)
	end		end

	return p		return p

← Older revision		Revision as of 06:32, 28 October 2021
Line 189:		Line 189:
	if plain:sub(1, 1) == "f" then plain = false else plain = true end		if plain:sub(1, 1) == "f" then plain = false else plain = true end
	-- get the page content and look for 'text' - return position or nomatch		-- get the page content and look for 'text' - return position or nomatch
	local content = titleobj:getContent()		local content = titleobj and titleobj:getContent()
	return mw.ustring.find(content, text, 1, plain) or nomatch ~~-- returns multiple values~~		return content and mw.ustring.find(content, text, 1, plain) or nomatch
	end		end
	p.findpagetext = function(frame)		p.findpagetext = function(frame)
Line 228:		Line 228:
	-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String		-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String
	function p._escapePattern( pattern_str)		function p._escapePattern( pattern_str)
	return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );		return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )
	end		end

Line 251:		Line 251:
	function p.strip( frame )		function p.strip( frame )
	local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} )		local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} )
	local source_str = new_args['source'] or '';		local source_str = new_args['source'] or ''
	local chars = new_args['chars'] or '' or 'characters';		local chars = new_args['chars'] or '' or 'characters'
	source_str = mw.text.trim(source_str);		source_str = mw.text.trim(source_str)
	if source_str == '' or chars == '' then		if source_str == '' or chars == '' then
	return source_str;		return source_str
	end		end
	local l_plain = p._getBoolean( new_args['plain'] or true );		local l_plain = p._getBoolean( new_args['plain'] or true )
	if l_plain then		if l_plain then
	chars = p._escapePattern( chars );		chars = p._escapePattern( chars )
	end		end
	local result;		local result
	result = mw.ustring.gsub(source_str, "["..chars.."]", '')		result = mw.ustring.gsub(source_str, "["..chars.."]", '')
	return result;		return result
	end		end

Line 310:		Line 310:
	function p.hyphen_to_dash( str, spacing )		function p.hyphen_to_dash( str, spacing )
	if (str == nil or str == '') then		if (str == nil or str == '') then
	return str;		return str
	end		end

	local accept;		local accept

	str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split		str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split

	local out = {};		local out = {}
	local list = mw.text.split (str, '%s[,;]%s'); -- split str at comma or semicolon separators if there are any		local list = mw.text.split (str, '%s[,;]%s') -- split str at comma or semicolon separators if there are any

	for _, item in ipairs (list) do -- for each item in the list		for _, item in ipairs (list) do -- for each item in the list
	item = mw.text.trim(item) -- trim whitespace		item = mw.text.trim(item) -- trim whitespace
	item, accept = item:gsub ('^%(%((.+)%)%)$', '%1');		item, accept = item:gsub ('^%(%((.+)%)%)$', '%1')
	if accept == 0 and mw.ustring.match (item, '^%w[%.%-]?%w+%s[%-–—]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators		if accept == 0 and mw.ustring.match (item, '^%w[%.%-]?%w+%s[%-–—]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
	if item:match ('^%a+[%.%-]?%d+%s%-%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)		if item:match ('^%a+[%.%-]?%d+%s%-%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
Line 329:		Line 329:
	item:match ('^%d+%s%-%s%d+$') or -- digit hyphen digit		item:match ('^%d+%s%-%s%d+$') or -- digit hyphen digit
	item:match ('^%a+%s%-%s%a+$') then -- letter hyphen letter		item:match ('^%a+%s%-%s%a+$') then -- letter hyphen letter
	item = item:gsub ('(%w[%.%-]?%w+)%s%-%s(%w[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters		item = item:gsub ('(%w[%.%-]?%w+)%s%-%s(%w[%.%-]?%w+)', '%1–%2') -- replace hyphen, remove extraneous space characters
	else		else
	item = mw.ustring.gsub (item, '%s[–—]%s', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace		item = mw.ustring.gsub (item, '%s[–—]%s', '–') -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace
	end		end
	end		end
	table.insert (out, item); -- add the (possibly modified) item to the output table		table.insert (out, item) -- add the (possibly modified) item to the output table
	end		end

	local temp_str = table.concat (out, ',' .. spacing); -- concatenate the output table into a comma separated string		local temp_str = table.concat (out, ',' .. spacing) -- concatenate the output table into a comma separated string
	temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of concatenated out		temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1') -- remove accept-this-as-written markup when it wraps all of concatenated out
	if accept ~= 0 then		if accept ~= 0 then
	temp_str = str:gsub ('^%(%((.+)%)%)$', '%1'); -- when global markup removed, return original str; do it this way to suppress boolean second return value		temp_str = str:gsub ('^%(%((.+)%)%)$', '%1') -- when global markup removed, return original str; do it this way to suppress boolean second return value
	~~return temp_str;~~
	~~else~~
	~~return temp_str; -- else, return assembled temp_str~~
	end		end
			return temp_str
	end		end

Line 350:		Line 348:
	local str = frame.args[1] or ''		local str = frame.args[1] or ''
	local spacing = frame.args[2] or ' ' -- space is part of the standard separator for normal spacing (but in conjunction with templates r/rp/ran we may need a narrower spacing		local spacing = frame.args[2] or ' ' -- space is part of the standard separator for normal spacing (but in conjunction with templates r/rp/ran we may need a narrower spacing

	return p.hyphen_to_dash(str, spacing)		return p.hyphen_to_dash(str, spacing)
	end		end

	return p		return p