Module:Citation/CS1/Identifiers - Revision history

Trappist the monk at 14:06, 12 April 2025

2025-04-12T14:06:45Z

← Previous revision		Revision as of 14:06, 12 April 2025
Line 733:		Line 733:
	if year and not ignore_invalid then --		if year and not ignore_invalid then --
	year = year:match ('%d%d%d%d?'); -- strip disambiguator if present		year = year:match ('%d%d%d%d?'); -- strip disambiguator if present
	if 1965 > tonumber(year) then		if year and (1965 > tonumber(year)) then
	set_message ('err_invalid_isbn_date'); -- set an error message		set_message ('err_invalid_isbn_date'); -- set an error message
	return internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect,		return internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect,

Trappist the monk at 13:55, 12 April 2025

2025-04-12T13:55:44Z

← Previous revision		Revision as of 13:55, 12 April 2025
Line 732:		Line 732:

	if year and not ignore_invalid then --		if year and not ignore_invalid then --
	year = year:match ('%d%d%d%d'); -- strip disambiguator if present		year = year:match ('%d%d%d%d?'); -- strip disambiguator if present
	if 1965 > tonumber(year) then		if 1965 > tonumber(year) then
	set_message ('err_invalid_isbn_date'); -- set an error message		set_message ('err_invalid_isbn_date'); -- set an error message

Trappist the monk: sync from sandbox;

2025-04-12T13:48:49Z

sync from sandbox;

← Previous revision		Revision as of 13:48, 12 April 2025
Line 291:		Line 291:

	return lccn;		return lccn;
	end		end


Line 710:		Line 710:
	]]		]]

	local function isbn (~~options~~)		local function isbn (options_t)
	local isbn_str = ~~options~~.id;		local isbn_str = options_t.id;
	local ignore_invalid = ~~options~~.accept;		local ignore_invalid = options_t.accept;
	local handler = ~~options~~.handler;		local handler = options_t.handler;
			local year = options_t.Year; -- when set, valid anchor_year; may have a disambiguator which must be removed

	local function return_result (check, err_type) -- local function to handle the various returns		local function return_result (check, err_type) -- local function to handle the various returns
Line 722:		Line 723:
	else -- here when not ignoring		else -- here when not ignoring
	if not check then -- and there is an error		if not check then -- and there is an error
	~~options~~.coins_list_t['ISBN'] = nil; -- when error, unset so not included in COinS		options_t.coins_list_t['ISBN'] = nil; -- when error, unset so not included in COinS
	set_message ('err_bad_isbn', err_type); -- set an error message		set_message ('err_bad_isbn', err_type); -- set an error message
	return ISBN; -- return id text		return ISBN; -- return id text
Line 728:		Line 729:
	end		end
	return ISBN; -- return id text		return ISBN; -- return id text
			end

			if year and not ignore_invalid then --
			year = year:match ('%d%d%d%d'); -- strip disambiguator if present
			if 1965 > tonumber(year) then
			set_message ('err_invalid_isbn_date'); -- set an error message
			return internal_link_id ({link = handler.link, label = handler.label, redirect = handler.redirect,
			prefix = handler.prefix, id = isbn_str, separator = handler.separator});
			end
	end		end

Trappist the monk: sync from sandbox;

2024-12-28T15:31:47Z

sync from sandbox;

← Previous revision		Revision as of 15:31, 28 December 2024
Line 555:		Line 555:
	local err_flag;		local err_flag;

	local function is_extended_free (registrant, id) -- local function to check those few registrants that are mixed; identifiable by the doi suffix <incipit>		local function is_extended_free (registrant, suffix) -- local function to check those few registrants that are mixed; identifiable by the doi suffix <incipit>
	if cfg.extended_registrants_t[registrant] then -- if this registrant has known free-to-read extentions		if cfg.extended_registrants_t[registrant] then -- if this registrant has known free-to-read extentions
	for _, incipit in ipairs (cfg.extended_registrants_t[registrant]) do -- loop through the registrant's incipits		for _, incipit in ipairs (cfg.extended_registrants_t[registrant]) do -- loop through the registrant's incipits
	if ~~string~~.find (id, ~~incipit,~~ 1, ~~true~~) then -- if found		if mw.ustring.find (suffix, '^' .. incipit) then -- if found
	return true;		return true;
	end		end
Line 590:		Line 590:
	end		end

			local suffix;
	local registrant = mw.ustring.match (id, '^10%.([^/]+)/[^%s–]-[^%.,]$'); -- registrant set when DOI has the proper basic form		local registrant, suffix = mw.ustring.match (id, '^10%.([^/]+)/([^%s–]-[^%.,])$'); -- registrant and suffix set when DOI has the proper basic form

	local registrant_err_patterns = { -- these patterns are for code ranges that are not supported		local registrant_err_patterns = { -- these patterns are for code ranges that are not supported
	'^[^1-3]%d%d%d%d%.%d+$', -- 5 digits with subcode (0xxxx, 40000+); accepts: 10000–39999		'^[^1-3]%d%d%d%d%.%d+$', -- 5 digits with subcode (0xxxx, 40000+); accepts: 10000–39999
	'^[^1-6]%d%d%d%d$', -- 5 digits without subcode (0xxxx, 60000+); accepts: 10000–69999		'^[^1-7]%d%d%d%d$', -- 5 digits without subcode (0xxxx, 60000+); accepts: 10000–69999
	'^[^1-9]%d%d%d%.%d+$', -- 4 digits with subcode (0xxx); accepts: 1000–9999		'^[^1-9]%d%d%d%.%d+$', -- 4 digits with subcode (0xxx); accepts: 1000–9999
	'^[^1-9]%d%d%d$', -- 4 digits without subcode (0xxx); accepts: 1000–9999		'^[^1-9]%d%d%d$', -- 4 digits without subcode (0xxx); accepts: 1000–9999
Line 622:		Line 623:
	options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS		options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS
	else		else
	if not access and (cfg.known_free_doi_registrants_t[registrant] or is_extended_free (registrant, id)) then -- \|doi-access=free not set and <registrant> is known to be free		if not access and (cfg.known_free_doi_registrants_t[registrant] or is_extended_free (registrant, suffix)) then -- \|doi-access=free not set and <registrant> is known to be free
	set_message ('maint_doi_unflagged_free'); -- set a maint cat		set_message ('maint_doi_unflagged_free'); -- set a maint cat
	end		end

Trappist the monk: sync from sandbox;

2024-08-17T18:39:06Z

sync from sandbox;

← Previous revision		Revision as of 18:39, 17 August 2024
Line 554:		Line 554:
	local handler = options.handler;		local handler = options.handler;
	local err_flag;		local err_flag;

			local function is_extended_free (registrant, id) -- local function to check those few registrants that are mixed; identifiable by the doi suffix <incipit>
			if cfg.extended_registrants_t[registrant] then -- if this registrant has known free-to-read extentions
			for _, incipit in ipairs (cfg.extended_registrants_t[registrant]) do -- loop through the registrant's incipits
			if string.find (id, incipit, 1, true) then -- if found
			return true;
			end
			end
			end
			end

	local text;		local text;
Line 612:		Line 622:
	options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS		options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS
	else		else
	if not access and cfg.known_free_doi_registrants_t[registrant] then -- \|doi-access=free not set and <registrant> is known to be free		if not access and (cfg.known_free_doi_registrants_t[registrant] or is_extended_free (registrant, id)) then -- \|doi-access=free not set and <registrant> is known to be free
	set_message ('maint_doi_unflagged_free'); -- set a maint cat		set_message ('maint_doi_unflagged_free'); -- set a maint cat
	end		end

Trappist the monk: sync from sandbox;

2023-11-25T16:42:08Z

sync from sandbox;

← Previous revision		Revision as of 16:42, 25 November 2023
Line 611:		Line 611:
	if err_flag then		if err_flag then
	options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS		options.coins_list_t['DOI'] = nil; -- when error, unset so not included in COinS
			else
			if not access and cfg.known_free_doi_registrants_t[registrant] then -- \|doi-access=free not set and <registrant> is known to be free
			set_message ('maint_doi_unflagged_free'); -- set a maint cat
			end
	end		end

Trappist the monk: tweak to support new oclc limit;

2023-09-20T15:12:36Z

tweak to support new oclc limit;

← Previous revision		Revision as of 15:12, 20 September 2023
Line 1,131:		Line 1,131:
	elseif id:match('^%d+$') then -- no prefix		elseif id:match('^%d+$') then -- no prefix
	number = id; -- get the number		number = id; -- get the number
	if 10 ~~< number:len~~() then		if tonumber (id) > handler.id_limit then
	number = nil; -- ~~constrain~~ to ~~1 to 10 digits; change this when~~ ~~OCLC~~ ~~issues~~ ~~11-digit~~ ~~numbers~~		number = nil; -- unset when id value exceeds the limit
	end		end
	end		end

Trappist the monk: rare 8-digit medrxiv without date;

2023-08-12T22:15:16Z

rare 8-digit medrxiv without date;

← Previous revision		Revision as of 22:15, 12 August 2023
Line 1,043:		Line 1,043:

	local patterns = {		local patterns = {
			'%d%d%d%d%d%d%d%d$', -- simple 8-digit identifier; these should be relatively rare
	'^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%dv%d+$', -- y.m.d. date + 8-digit identifier + version (2020-01-01 and later)		'^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%dv%d+$', -- y.m.d. date + 8-digit identifier + version (2020-01-01 and later)
	'^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%d$', -- y.m.d. date + 8-digit identifier (2020-01-01 and later)		'^10%.1101/(20%d%d)%.(%d%d)%.(%d%d)%.%d%d%d%d%d%d%d%d$', -- y.m.d. date + 8-digit identifier (2020-01-01 and later)
Line 1,048:		Line 1,049:

	for _, pattern in ipairs (patterns) do -- spin through the patterns looking for a match		for _, pattern in ipairs (patterns) do -- spin through the patterns looking for a match
	local y, m, d = id:match (pattern); -- attempt to get year, month and date from the identifier		if id:match (pattern) then
			local y, m, d = id:match (pattern); -- found a match, attempt to get year, month and date from the identifier

	if m then -- m is nil when no ~~match~~		if m then -- m is nil when id is the 8-digit form
	if not is_valid_rxiv_date (y, m, d, 'm') then -- validate the encoded date; 'm' for medrxiv limit		if not is_valid_rxiv_date (y, m, d, 'b') then -- validate the encoded date; 'b' for medrxiv limit
	break; -- date fail; break out early so we don't unset the ~~err_msg_flag~~		break; -- date fail; break out early so we don't unset the error message
			end
	end		end
			err_msg_flag = nil; -- we found a match so unset the error message
		⚫	break; -- and done
	end		end
	~~err_msg_flag = nil;~~ -- we ~~found~~ a ~~match~~ ~~and~~ ~~date~~ ~~is valid so unset the err_msg_flag~~		end -- <err_msg_flag> remains set here when no match
⚫	break; -- and done
	end -- err_msg flag remains set here when no match

	if err_msg_flag then		if err_msg_flag then

Trappist the monk: sync from sandbox;

2023-08-12T19:19:04Z

sync from sandbox;

Show changes

Trappist the monk: sync from sandbox;

2023-01-14T14:43:38Z

sync from sandbox;

← Previous revision		Revision as of 14:43, 14 January 2023
Line 250:		Line 250:
	--[[--------------------------< N O R M A L I Z E _ L C C N >--------------------------------------------------		--[[--------------------------< N O R M A L I Z E _ L C C N >--------------------------------------------------

	LCCN normalization (~~http~~://www.loc.gov/marc/lccn-namespace.html#normalization)		LCCN normalization (https://www.loc.gov/marc/lccn-namespace.html#normalization)
	1. Remove all blanks.		1. Remove all blanks.
	2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.		2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
Line 287:		Line 287:
	--[[--------------------------< A R X I V >--------------------------------------------------------------------		--[[--------------------------< A R X I V >--------------------------------------------------------------------

	See: ~~http~~://arxiv.org/help/arxiv_identifier		See: https://arxiv.org/help/arxiv_identifier

	format and error check arXiv identifier. There are three valid forms of the identifier:		format and error check arXiv identifier. There are three valid forms of the identifier:
Line 381:		Line 381:
	Validates (sort of) and formats a bibcode ID.		Validates (sort of) and formats a bibcode ID.

	Format for bibcodes is specified here: ~~http~~://adsabs.harvard.edu/abs_doc/help_pages/data.html#bibcodes		Format for bibcodes is specified here: https://adsabs.harvard.edu/abs_doc/help_pages/data.html#bibcodes

	But, this: 2015arXiv151206696F is apparently valid so apparently, the only things that really matter are length, 19 characters		But, this: 2015arXiv151206696F is apparently valid so apparently, the only things that really matter are length, 19 characters
Line 527:		Line 527:
	and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely		and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely
	if ever used in DOI names.		if ever used in DOI names.

			https://www.doi.org/doi_handbook/2_Numbering.html -- 2.2 Syntax of a DOI name
			https://www.doi.org/doi_handbook/2_Numbering.html#2.2.2 -- 2.2.2 DOI prefix

	]]		]]
Line 573:		Line 576:
	'^[^1-9]%d%d%d$', -- 4 digits without subcode (0xxx); accepts: 1000–9999		'^[^1-9]%d%d%d$', -- 4 digits without subcode (0xxx); accepts: 1000–9999
	'^%d%d%d%d%d%d+', -- 6 or more digits		'^%d%d%d%d%d%d+', -- 6 or more digits
	'^%d%d?%d?$', -- less than 4 digits without subcode (with subcode is legitimate)		'^%d%d?%d?$', -- less than 4 digits without subcode (3 digits with subcode is legitimate)
			'^%d%d?%.[%d%.]+', -- 1 or 2 digits with subcode
	'^5555$', -- test registrant will never resolve		'^5555$', -- test registrant will never resolve
	'[^%d%.]', -- any character that isn't a digit or a dot		'[^%d%.]', -- any character that isn't a digit or a dot
Line 621:		Line 625:
	if ever used in HDLs.		if ever used in HDLs.

	Query string parameters are named here: ~~http~~://www.handle.net/proxy_servlet.html. query strings are not displayed		Query string parameters are named here: https://www.handle.net/proxy_servlet.html. query strings are not displayed
	but since '?' is an allowed character in an HDL, '?' followed by one of the query parameters is the only way we		but since '?' is an allowed character in an HDL, '?' followed by one of the query parameters is the only way we
	have to detect the query string so that it isn't URL-encoded with the rest of the identifier.		have to detect the query string so that it isn't URL-encoded with the rest of the identifier.
Line 631:		Line 635:
	local access = options.access;		local access = options.access;
	local handler = options.handler;		local handler = options.handler;
	local query_params = { -- list of known query parameters from ~~http~~://www.handle.net/proxy_servlet.html		local query_params = { -- list of known query parameters from https://www.handle.net/proxy_servlet.html
	'noredirect',		'noredirect',
	'ignore_aliases',		'ignore_aliases',
Line 800:		Line 804:

	Determines whether an ISMN string is valid. Similar to ISBN-13, ISMN is 13 digits beginning 979-0-... and uses the		Determines whether an ISMN string is valid. Similar to ISBN-13, ISMN is 13 digits beginning 979-0-... and uses the
	same check digit calculations. See ~~http~~://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf		same check digit calculations. See https://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
	section 2, pages 9–12.		section 2, pages 9–12.

Line 849:		Line 853:
	like this:		like this:

	\|issn=0819 4327 gives: [~~http~~://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link		\|issn=0819 4327 gives: [https://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link

	This code now prevents that by inserting a hyphen at the ISSN midpoint. It also validates the ISSN for length		This code now prevents that by inserting a hyphen at the ISSN midpoint. It also validates the ISSN for length
Line 953:		Line 957:
	Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of		Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of
	the LCCN dictates the character type of the first 1-3 characters; the rightmost eight are always digits.		the LCCN dictates the character type of the first 1-3 characters; the rightmost eight are always digits.
			https://oclc-research.github.io/infoURI-Frozen/info-uri.info/info:lccn/reg.html
	http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/

	length = 8 then all digits		length = 8 then all digits