Module:Citation/CS1 and Module:Citation/CS1/sandbox: Difference between pages

Content deleted Content added

@@ Line 1: / Line 1: @@
+--[[
+History of changes since last sync: 2025-04-12
+-05-10: maint cat to track {{cite journal}} templates misusing |page= for |article-number=; see Help_talk:Citation_Style_1#|page=_same_value_as_last_n-digits_of_|doi=
+]]
 require ('strict');
@@ Line 2,721: / Line 2,728: @@
 			utilities.set_message ('maint_publisher_location');					-- set a maint message
 			return;																-- and done
+		end
+	end
+end
+--[[--------------------------< I S _ P A G E _ A R T _ N U M >------------------------------------------------
+compare the trailing (rightmost) characters of the |doi= value against the whole value assigned to |page(s)=.
+return boolean true when:
+	|page(s)= has exactly 8 digits and a dot between the fourth and fifth digits matches the trailing 9 characters
+		of the |doi= value: |page=12345678 → |page=1234.5678 matches |doi=10.xxxx/yyyy1234.5678
+	|page(s)= is 5 or more characters and matches |doi= values's trailing characters
+	|page(s)= begins with a lowercase 'e' and |page(s)= without the 'e' matches |doi= values's trailing
+		characters: |page=e12345 → |page=12345 matches |doi=10.xxxx/yyyy12345
+	|page(s)= begins with a uppercase 'CD' followed by (typically) six digits matches |doi= values that ends with
+		'CDxxxxxx.pubx' (where 'x' is any single digit)
+return nil when |page(s)= values:
+	are ranges separated by underscore, hyphen, emdash, endash, figure dash, or minus character
+	are comma- or semicolon-separated lists of pages
+	have external urls (has text 'http')
+	are digit-only values less than 10000
+	do not match |doi= values's trailing characters
+]]
+local function is_page_art_num (page, doi)
+	if not (utilities.is_set (page) and utilities.is_set (doi)) then			-- both required
+		return;																	-- abandon; nothing to do
+	end
+	if page:match ('[,;_−–—‒%-]') then											-- when |page(s)= might be a page range or a separated list of pages
+		return;																	-- abandon
+	end
+	page = page:lower();														-- because doi names are case insensitive
+	doi = doi:lower();															-- force these to lowercase for testing
+	if page:match ('http') then													-- when |page(s)= appears to hold a url
+		return;																	-- abandon
+	end
+	if tonumber (page) then														-- is |page(s)= digits only
+		if 10000 > tonumber (page) then											-- when |page(s)= less than 10000
+			return;																-- abandon
+		end
+		if doi:match (page .. '$') then											-- digits only page number match the last digits in |doi=?
+			return true;
+		end
+		if 8 == page:len() then													-- special case when |page(s)= is exactly 8 digits
+			local dot_page = page:gsub ('(%d%d%d%d)(%d%d%d%d)', '%1.%2');		-- make a |page=xxxx.yyyy version commonly used in |doi=
+			if doi:match (dot_page .. '$') then									-- 8-digit dotted page number match the last characters in |doi=?
+				return true;
+			end
+		end
+	else																		-- here when |page(s)= is alpha-numeric
+		if 4 < page:len() then													-- when |page(s)= is five or more characters
+			if doi:match (page .. '$') then										-- alpha-numeric page match the last characters in |doi=?
+				return true;
+			end
+			local epage = page:match ('^e([%w]+)$');							-- if first character of |page= is 'e', remove it
+			if epage and doi:match (epage .. '$') then							-- page number match the last characters in |doi=?
+				return true;
+			end
+			local cdpage = page:match ('^cd%d+$');								-- if first characters of |page= are 'CD' and last characters are digits (typically 6 digits)
+			if cdpage and doi:match (cdpage .. '%.pub%d$') then					-- page number matches doi 'CDxxxxxx.pubx' where 'x' is a digit
+				return true;
+			end
 		end
 	end
@@ Line 3,460: / Line 3,541: @@
 				Title = '';														-- set title to empty string
 				utilities.set_message ('maint_untitled');						-- add maint cat
+	end
+	if 'journal' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then
+		if is_page_art_num (Page or Pages, ID_list_coins['DOI']) then			-- does |page(s)= look like it holds an article number
+			utilities.set_message ('maint_page_art_num');						-- add maint cat
+		end
 	end
@@ Line 4,373: / Line 4,460: @@
 		_, value, _ = utilities.is_wikilink (value);							-- extract label portion from wikilink
 	end
 	return value;
 end
@@ Line 4,474: / Line 4,562: @@
 	frame – from template call (citation()); may be nil when called from another module
-	args – table of all cs1|2 parameters in the template (the template frame)
+	args_t – table of all cs1|2 parameters in the template (the parent frame)
-	config – table of template-supplied parameter (the #invoke frame)
+	config_t – table of template-supplied parameter (the #invoke frame)
 ]]
-local function _citation (frame, args, config)									-- save a copy in case we need to display an error message in preview mode
+local function _citation (frame, args_t, config_t)								-- save a copy in case we need to display an error message in preview mode
 	if not frame then
 		frame = mw.getCurrentFrame();											-- if called from another module, get a frame for frame-provided functions
 	end
 																				-- i18n: set the name that your wiki uses to identify sandbox subpages from sandbox template invoke (or can be set here)
-	local sandbox = ((config.SandboxPath and '' ~= config.SandboxPath) and config.SandboxPath) or '/sandbox';	-- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}}
+	local sandbox = ((config_t.SandboxPath and '' ~= config_t.SandboxPath) and config_t.SandboxPath) or '/sandbox';	-- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}}
 	is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true);		-- is this invoke the sandbox module?
 	sandbox = is_sandbox and sandbox or '';										-- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else
@@ Line 4,501: / Line 4,589: @@
 	z = utilities.z;															-- table of error and category tables in Module:Citation/CS1/Utilities
+	local cite_args_t = {};														-- because args_t is the parent (template) frame args (which cannot be modified); params and their values will be placed here
 	is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}'));
@@ Line 4,509: / Line 4,598: @@
 	local capture;																-- the single supported capture when matching unknown parameters using patterns
 	local empty_unknowns = {};													-- sequence table to hold empty unknown params for error message listing
-	for k, v in pairs( args ) do												-- get parameters from the parent (template) frame
+	for k, v in pairs (args_t) do												-- get parameters from the parent (template) frame
 		v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1');							-- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
 		if v ~= '' then
@@ Line 4,515: / Line 4,604: @@
 				k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits);		-- for enumerated parameters, translate 'local' digits to Western 0-9
 			end
-			if not validate( k, config.CitationClass ) then
+			if not validate( k, config_t.CitationClass ) then
 				if type (k) ~= 'string' then									-- exclude empty numbered parameters
 					if v:match("%S+") ~= nil then
 						error_text = utilities.set_message ('err_text_ignored', {v});
 					end
-				elseif validate (k:lower(), config.CitationClass) then
+				elseif validate (k:lower(), config_t.CitationClass) then
 					error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, k:lower()});	-- suggest the lowercase version of the parameter
 				else
@@ Line 4,530: / Line 4,619: @@
 						if capture then											-- if the pattern matches
 							param = utilities.substitute (param, capture);		-- add the capture to the suggested parameter (typically the enumerator)
-							if validate (param, config.CitationClass) then		-- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
+							if validate (param, config_t.CitationClass) then		-- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
 								error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param});	-- set the suggestion error message
 							else
@@ Line 4,539: / Line 4,628: @@
 					end
 					if not utilities.is_set (error_text) then					-- couldn't match with a pattern, is there an explicit suggestion?
-						if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
+						if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config_t.CitationClass) then
 							utilities.set_message ('err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]});
 						else
@@ Line 4,549: / Line 4,638: @@
 			end
-			args[k] = v;														-- save this parameter and its value
+			cite_args_t[k] = v;													-- save this parameter and its value
 		elseif not utilities.is_set (v) then									-- for empty parameters
-			if not validate (k, config.CitationClass, true) then				-- is this empty parameter a valid parameter
+			if not validate (k, config_t.CitationClass, true) then				-- is this empty parameter a valid parameter
 				k = ('' == k) and '(empty string)' or k;						-- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
 				table.insert (empty_unknowns, utilities.wrap_style ('parameter', k));	-- format for error message and add to the list
 			end
+		end
-																				-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
-	--	elseif args[k] ~= nil or (k == 'postscript') then						-- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
-	--		args[k] = v;														-- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
-		end																		-- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
 	end
@@ Line 4,572: / Line 4,658: @@
 	local url_param_t = {};														-- table of url-holding paramters and their values
-	for k, v in pairs( args ) do
+	for k, v in pairs (cite_args_t) do
 		if 'string' == type (k) then											-- don't evaluate positional parameters
 			has_invisible_chars (k, v);											-- look for invisible characters
@@ Line 4,578: / Line 4,665: @@
 		has_extraneous_punc (k, v);												-- look for extraneous terminal punctuation in parameter values
 		missing_pipe_check (k, v);												-- do we think that there is a parameter that is missing a pipe?
-		args[k] = inter_wiki_check (k, v);										-- when language interwiki-linked parameter missing leading colon replace with wiki-link label
+		cite_args_t[k] = inter_wiki_check (k, v);								-- when language interwiki-linked parameter missing leading colon replace with wiki-link label
 		if 'string' == type (k) then											-- when parameter k is not positional
@@ Line 4,591: / Line 4,678: @@
 	has_extraneous_url (non_url_param_t);										-- look for url in parameter values where a url does not belong
 	if has_twl_url (url_param_t) then												-- look for url-holding parameters that hold a The Wikipedia Library url
-		args['url-access'] = 'subscription';
+		cite_args_t['url-access'] = 'subscription';
 	end
 	return table.concat ({
 		frame:extensionTag ('templatestyles', '', {src='Module:Citation/CS1' .. sandbox .. '/styles.css'}),
-		citation0( config, args)
+		citation0 (config_t, cite_args_t)
 	});
 end