Module:String2 - Revision history

>QuebbingtonBear: 60 revisions imported from :wikipedia:Module:String2

2022-10-28T07:38:30Z

60 revisions imported from wikipedia:Module:String2

← Older revision	Revision as of 07:38, 28 October 2022
(No difference)

wikipedia>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

>QuebbingtonBear: 1 revision imported

2022-01-18T15:03:46Z

1 revision imported

← Older revision	Revision as of 15:03, 18 January 2022
(No difference)

[[wikipedia:]]>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

wikipedia>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

wikipedia>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

wikipedia>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

>Ahecht: revert encoding output of hyphen2dash

2021-09-02T15:19:52Z

revert encoding output of hyphen2dash

← Older revision		Revision as of 15:19, 2 September 2021
Line 334:		Line 334:
	end		end
	end		end
	table.insert (out, ~~mw.text.encode(~~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

>Ahecht: implement has_accept_as_written for hyphen2dash

2021-09-02T02:23:54Z

implement has_accept_as_written for hyphen2dash

← Older revision		Revision as of 02:23, 2 September 2021
Line 309:		Line 309:
	]]		]]
	function p.hyphen_to_dash( str )		function p.hyphen_to_dash( str )
			if (str == nil or str == '') then
			return str;
			end

			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

Line 316:		Line 322:
	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
	if mw.ustring.match (item, '^%w[%.%-]?%w+%s[%-–—]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators		item, accept = item:gsub ('^%(%((.+)%)%)$', '%1');
			if accept == 0 and mw.ustring.match (item, '^%w[%.%-]?%w+%s[%-–—]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
	if item:match ('^%a+[%.%-]?%d+%s%-%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)		if item:match ('^%a+[%.%-]?%d+%s%-%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
	item:match ('^%d+[%.%-]?%a+%s%-%s%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)		item:match ('^%d+[%.%-]?%a+%s%-%s%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
Line 327:		Line 334:
	end		end
	end		end
	table.insert (out, mw.text.encode(item) ); -- add the (possibly modified) item to the output table		table.insert (out, mw.text.encode(item) ); -- add the (possibly modified) item to the output table
	end		end

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

>Ahecht: Use mw.text.decode/mw.text.encode in hyphen_to_dash

2021-09-02T01:37:58Z

Use mw.text.decode/mw.text.encode in hyphen_to_dash

← Older revision		Revision as of 01:37, 2 September 2021
Line 309:		Line 309:
	]]		]]
	function p.hyphen_to_dash( str )		function p.hyphen_to_dash( str )
			str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split
	str = str~~:gsub ('&[nm]dash;'~~, ~~{['–'] = '–', ['—'] = '—'}~~); -- replace ~~— and –~~ entities with their characters; semicolon mucks up the text.split
	~~str = str:gsub ('-', '-'); -- replace HTML numeric entity with hyphen character~~

	~~str = str:gsub (' ', ' '); -- replace   entity with generic keyboard space character~~

	local out = {};		local out = {};
Line 331:		Line 327:
	end		end
	end		end
	table.insert (out, item); -- add the (possibly modified) item to the output table		table.insert (out, mw.text.encode(item) ); -- add the (possibly modified) item to the output table
	end		end

← 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