Module:Citation/CS1/Utilities - Revision history

Sushoff: Created page with "local z = { error_cats_t = {}; -- for categorizing citations that contain errors error_ids_t = {}; -- list of error identifiers; used to prevent duplication of certain errors; local to this module error_msgs_t = {}; -- sequence table of error messages maint_cats_t = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work prop_cats_t = {}; -- for categorizing cit..."

2025-02-01T12:38:35Z

Created page with "local z = { error_cats_t = {}; -- for categorizing citations that contain errors error_ids_t = {}; -- list of error identifiers; used to prevent duplication of certain errors; local to this module error_msgs_t = {}; -- sequence table of error messages maint_cats_t = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work prop_cats_t = {}; -- for categorizing cit..."

← Older revision	Revision as of 12:38, 1 February 2025
(No difference)

imported>Trappist the monk: sync from sandbox;

2024-12-28T15:31:46Z

sync from sandbox;

← Older revision		Revision as of 15:31, 28 December 2024
Line 98:		Line 98:
	--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------		--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------

	Converts a hyphen to ~~a dash~~ under certain conditions. The hyphen must separate		Converts a hyphen, endash, emdash to endash under certain conditions. The hyphen/en/em must separate
	like items; unlike items are returned unmodified. These forms are modified:		like items; unlike items are returned unmodified. These forms are modified:
	letter - letter (A - B)		letter - letter (A-B)
	digit - digit (4-5)		digit - digit (4-5)
	digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)		digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
	letterdigit - letterdigit (A1-A5) (an optional separator between letter and		letterdigit - letterdigit (A1-A5) (an optional separator between letter and
	digit is supported – a.1-a.5 or a-1-a-5)		digit is supported – a.1-a.5 or a-1-a-5)
	digitletter - digitletter (5a - 5d) (an optional separator between letter and		digitletter - digitletter (5a-5d) (an optional separator between letter and
	digit is supported – 5.a-5.d or 5-a-5-d)		digit is supported – 5.a-5.d or 5-a-5-d)

	any other forms are returned unmodified.		any other forms are returned unmodified.

	str may be a comma- or semicolon-separated list		str may be a comma- or semicolon-separated list of page ranges with/without single pages

	]]		]]
Line 118:		Line 118:
	return str;		return str;
	end		end

	~~local accept; -- boolean~~

	str = str:gsub ("(%(%(.-%)%))", function(m) return m:gsub(",", "，"):gsub(";", "；") end) -- replace commas and semicolons in accept-as-written markup with similar unicode characters so they'll be ignored during the split		str = str:gsub ("(%(%(.-%)%))", function(m) return m:gsub(",", "，"):gsub(";", "；") end) -- replace commas and semicolons in accept-as-written markup with similar unicode characters so they'll be ignored during the split
	str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – 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 HTML numeric entity with hyphen character
	str = str:gsub (' ', ' '); -- replace   entity with generic keyboard space character		str = str:gsub (' ', ' '); -- replace   entity with generic keyboard space character

	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

			local accept; -- boolean

	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, accept = has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item		item, accept = has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
	if not accept and mw.ustring.match (item, '^%w[%.%-]?%w+%s[%-–—]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators		if not accept and mw.ustring.match (item, '^%w[%.%-]?%w+%s[—–-]%s%w[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
	if ~~item:~~match ('^%a+[%.%-]?%d+%s%-%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)		if mw.ustring.match (item, '^%a+[%.%-]?%d+%s[—–-]%s%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
	~~item:~~match ('^%d+[%.%-]?%a+%s%-%s%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)		mw.ustring.match (item, '^%d+[%.%-]?%a+%s[—–-]%s%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
	~~item:~~match ('^%d+[%.%-]%d+%s%-%s%d+[%.%-]%d+$') or -- digit separator digit hyphen digit separator digit		mw.ustring.match (item, '^%d+[%.%-]%d+%s[—–-]%s%d+[%.%-]%d+$') then -- digit separator digit hyphen digit separator digit
	item:match ('^%d+%s%-%s%d+$') or -- digit hyphen digit		item = mw.ustring.gsub (item, '(%w[%.%-]?%w+)%s[—–-]%s(%w[%.%-]?%w+)', '<span class="nowrap">%1 –</span> <span class="nowrap">%2</span>'); -- replace hyphen/dash, with spaced endash
	~~item:~~match ('^%a+%s%-%s%a+$') then -- letter hyphen letter
	item = ~~item:~~gsub ('(~~%w[%.%-]?~~%w+)%s%-%s(~~%w[%.%-]?~~%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters		elseif mw.ustring.match (item, '^%d+%s[—–-]%s%d+$') or -- digit hyphen digit
			mw.ustring.match (item, '^%a+%s[—–-]%s%a+$') then -- letter hyphen letter
			item = mw.ustring.gsub (item, '(%w+)%s[—–-]%s(%w+)', '<span class="nowrap">%1–</span>%2'); -- replace hyphen/emdash with endash, 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', '–'); -- disabled; here when 'unlike' items so return <item> as is
	end		end
	end		end

imported>Trappist the monk: update per RfC;

2022-01-22T14:11:16Z

update per RfC;

Show changes

imported>Trappist the monk: sync from sandbox;

2021-01-09T14:11:11Z

sync from sandbox;

Show changes

imported>Trappist the monk: sync from sandbox;

2020-10-10T13:22:53Z

sync from sandbox;

Show changes

imported>Trappist the monk: sync from sandbox;

2020-01-11T12:32:44Z

sync from sandbox;

← Older revision		Revision as of 12:32, 11 January 2020
Line 334:		Line 334:
	local wl_type = 2; -- assume that str is a complex wikilink [[L\|D]]		local wl_type = 2; -- assume that str is a complex wikilink [[L\|D]]

			if not str:match ('^%[%[[^%]]+%]%]$') then -- is str some sort of a wikilink (must have some sort of content)
			return 0, str, ''; -- not a wililink; return wl_type as 0, str as D, and empty string as L
			end

	L, D = str:match ('^%[%[([^\|]+)\|([^%]]+)%]%]$'); -- get L and D from [[L\|D]]		L, D = str:match ('^%[%[([^\|]+)\|([^%]]+)%]%]$'); -- get L and D from [[L\|D]]

	if not is_set (D) then -- if no separate ~~link~~		if not is_set (D) then -- if no separate display
	D = str:match ('^%[%[([^%]])\|%]%]$'); -- get D from [[D]]		D = str:match ('^%[%[([^%]])\|%]%]$'); -- get D from [[D]] or [[D\|]]
	wl_type = 1;		wl_type = 1;
	~~end~~

	~~if not is_set (D) then -- no wikilink markup~~
	~~D = str; -- return the string as D~~
	~~wl_type = 0; -- but say that it is not a wikilink~~
	end		end

	D = mw.text.trim (D, '%s\|'); -- trim white space and pipe characters		D = mw.text.trim (D, '%s\|'); -- trim white space and pipe characters
	L = L and mw.text.trim (L, '%s\|');		-- L = L and mw.text.trim (L, '%s\|');

	return wl_type, D, L or '';		return wl_type, D, L or '';
	end		end

imported>Trappist the monk: undo brute force hiding of deprecated parameter and missing periodical error messages;

2019-09-04T14:45:24Z

undo brute force hiding of deprecated parameter and missing periodical error messages;

← Older revision		Revision as of 14:45, 4 September 2019
Line 108:		Line 108:

	local message = substitute( error_state.message, arguments );		local message = substitute( error_state.message, arguments );

	~~if error_state.hidden then -- hack to hide error message that are being problematic~~
	~~return; -- without this hidden=true isn't working; don't know why~~
	~~end~~

	message = table.concat (		message = table.concat (

imported>Trappist the monk: hide deprecated parameters error messages and hide missing periodical error messages;

2019-09-03T22:05:11Z

hide deprecated parameters error messages and hide missing periodical error messages;

← Older revision		Revision as of 22:05, 3 September 2019
Line 108:		Line 108:

	local message = substitute( error_state.message, arguments );		local message = substitute( error_state.message, arguments );

			if error_state.hidden then -- hack to hide error message that are being problematic
			return; -- without this hidden=true isn't working; don't know why
			end

	message = table.concat (		message = table.concat (

imported>Trappist the monk: sync from sandbox;

2019-09-03T11:05:52Z

sync from sandbox;

@@ Line 124: / Line 124: @@
 		});
 	z.error_ids[ error_id ] = true;
 	if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } )
@@ Line 340: / Line 334: @@
 	local wl_type = 2;															-- assume that str is a complex wikilink [[L|D]]
-	L, D = str:match ('%[%[([^|]+)|([^%]]+)%]%]');								-- get L and D from [[L|D]]
+	L, D = str:match ('^%[%[([^|]+)|([^%]]+)%]%]$');							-- get L and D from [[L|D]]
 	if not is_set (D) then														-- if no separate link
-		D = str:match ('%[%[([^%]]*)|*%]%]');									-- get D from [[D]]
+		D = str:match ('^%[%[([^%]]*)|*%]%]$');									-- get D from [[D]]
 		wl_type = 1;
 	end
@@ Line 356: / Line 350: @@
 	return wl_type, D, L or '';
 end
@@ Line 388: / Line 422: @@
 	make_wikilink = make_wikilink,
 	set_selected_modules = set_selected_modules,
 	z = z,																		-- exported table
+	}

imported>Trappist the monk: sync from sandbox;

2019-04-20T13:20:10Z

sync from sandbox;

← Older revision		Revision as of 13:20, 20 April 2019
Line 1:		Line 1:
	~~local u = {}~~

	local z = {		local z = {
Line 372:		Line 371:


			--[[--------------------------< E X P O R T S >----------------------------------------------------------------
			]]

	return { ~~-- return exported functions and tables~~		return {
	is_set = is_set,		is_set = is_set, -- exported functions
	in_array = in_array,		in_array = in_array,
	substitute = substitute,		substitute = substitute,
Line 387:		Line 388:
	make_wikilink = make_wikilink,		make_wikilink = make_wikilink,
	set_selected_modules = set_selected_modules,		set_selected_modules = set_selected_modules,
	z = z,		z = z, -- exported table
	}		}