Module:Citation/CS1: Difference between revisions

Content deleted Content added
m 1 revision imported
m deprecated enumerated parameter error message fix;
Line 1:
 
require('Module:No globals');
 
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
 
each of these counts against the Lua upvalue limit
local dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation
date_name_xlate
 
]]
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink,
strip_apostrophe_markup;
 
local z ={}; -- tables in Module:Citation/CS1/Utilities
 
local extract_ids, extract_id_access_levels, build_id_list, is_embargoedvalidation; -- functions in Module:Citation/CS1/IdentifiersDate_validation
 
local make_coins_title, get_coins_pages, COinSutilities; -- functions in Module:Citation/CS1/COinSUtilities
local z ={}; -- table of tables in Module:Citation/CS1/Utilities
 
local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
local metadata; -- functions in Module:Citation/CS1/COinS
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
Line 26 ⟶ 25:
]]
 
local added_deprecated_cat; -- booleanBoolean flag so that the category is added only once
local added_prop_cats = {}added_vanc_errs; -- listBoolean flag ofso propertywe categoriesonly thatemit haveone beenVancouver addederror to/ z.properties_catscategory
local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category
 
local Frame; -- holds the module's frame table
Line 47 ⟶ 45:
local i = 1;
while i <= count do -- loop through all items in list
if utilities.is_set( list[i] ) then
return list[i]; -- return the first set list member
end
i = i + 1; -- point to next
end
end
 
 
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
 
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
 
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages
may be categorized but multiples of the same language are not categorized.
 
added_prop_cats is a table declared in page scope variables above
 
]]
 
local function add_prop_cat (key, arguments)
if not added_prop_cats [key] then
added_prop_cats [key] = true; -- note that we've added this category
key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?[%a%-]*', '%1'); -- strip lang code from keyname
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
Line 80 ⟶ 58:
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
 
added_vanc_errs is a booleanBoolean declared in page scope variables above
 
]]
Line 87 ⟶ 65:
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_errorutilities.set_message ( 'vancouvererr_vancouver', {source}, true ) } );
end
end
Line 94 ⟶ 72:
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
 
does this thing that purports to be a uriURI scheme seem to be a valid scheme? The scheme is checked to see if it
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
Scheme names consist of a sequence of characters beginning with a
Line 117 ⟶ 95:
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
see also [[Single-letter second-level domain]]
list of tldsTLDs: https://www.iana.org/domains/root/db
 
rfc952RFC 952 (modified by rfcRFC 1123) requires the first and last character of a hostname to be a letter or a digit. Between
the first and last characters the name may use letters, digits, and the hyphen.
 
Also allowed are IPv4 addresses. IPv6 not supported
 
domain is expected to be stripped of any path so that the last character in the last character of the tldTLD. tld
is two or more alpha characters. Any preceding '//' (from splitting a urlURL with a scheme) will be stripped
here. Perhaps not necessary but retained incasein case it is necessary for IPv4 dot decimal.
 
There are several tests:
the first character of the whole domain name including subdomains must be a letter or a digit
internationalized domain name (asciiASCII characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the tldTLD) see https://tools.ietf.org/html/rfc3490
single-letter/digit second-level domains in the .org, .cash, and .today TLDs
q, x, and z SL domains in the .com TLD
Line 139 ⟶ 117:
IPv4 dot-decimal address format; TLD not allowed
 
returns true if domain appears to be a proper name and tldTLD or IPv4 address, else false
 
]=]
Line 154 ⟶ 132:
end
 
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at wikisourceWikisource
return false;
end
 
local patterns = { -- patterns that look like urlsURLs
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
'%f[%w][%w]%.%a%a$', -- one character hostname and cctldccTLD (2 chars)
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and tldTLD
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}
Line 170 ⟶ 148:
for _, pattern in ipairs (patterns) do -- loop through the patterns list
if domain:match (pattern) then
return true; -- if a match then we think that this thing that purports to be a urlURL is a urlURL
end
end
Line 185 ⟶ 163:
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
 
returns true if the scheme and domain parts of a urlURL appear to be a valid urlURL; else false.
 
This function is the last step in the validation process. This function is separate because there are cases that
Line 194 ⟶ 172:
 
local function is_url (scheme, domain)
if utilities.is_set (scheme) then -- if scheme is set check it and domain
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when urlURL is protocol -relative
end
end
Line 204 ⟶ 182:
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
 
Split a urlURL into a scheme, authority indicator, and domain.
 
First remove Fully Qualified Domain Name terminator (a dot following tldTLD) (if any) and any path(/), query(?) or fragment(#).
 
If protocol -relative urlURL, return nil scheme and domain else return nil for both scheme and domain.
 
When not protocol -relative, get scheme, authority indicator, and domain. If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
 
Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes
like news: that don't use authority indicator?
 
Strip off any port and path;
Line 222 ⟶ 203:
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
 
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol -relative urlURL
domain = url_str:match ('^//(%S*)')
elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
if utilities.is_set (authority) then
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
if authority = is_set(authority):gsub then ('//', '', 1); -- ifreplace anythingplace left (1 orpair 3+of '/' where authority should be)with thennothing;
if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
return scheme; -- return scheme only making domain nil which will cause an error message
return scheme; -- return scheme only making domain nil which will cause an error message
end
else
if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test?
return scheme; -- return scheme only making domain nil which will cause an error message
end
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
Line 239 ⟶ 226:
--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
 
checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no urlsURLs
 
Link parameters are to hold the title of a wikipediaWikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
# < > [ ] | { } _
except the underscore which is used as a space in wiki urlsURLs and # which is used for section links
 
returns false when the value contains any of these characters.
 
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid urlURL (the
|<param>-link= parameter is ok); else false when value appears to be a valid urlURL (the |<param>-link= parameter is NOT ok).
 
]]
Line 258 ⟶ 245:
end
 
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from urlURL;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid urlURL
end
 
Line 267 ⟶ 254:
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
 
|<title>= may be wikilinkedwiki-linked but not when |<param>-link= has a value. This function emits an error message when
that condition exists
 
check <link> for inter-language interwiki-link prefix. prefix must be a MediaWiki-recognized language
code and must begin with a colon.
 
]]
Line 274 ⟶ 264:
local function link_title_ok (link, lorig, title, torig)
local orig;
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value
 
if is_set (link) then -- don't bother if <param>-link doesn't have a value
if not link_param_ok (link) then -- check |<param>-link= markup
orig = lorig; -- identify the failing link parameter
elseif title:find ('%[%[') then -- check |title= for wikilink markup
orig = torig; -- identify the failing |title= parameter
elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki
local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix
 
if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon
orig = lorig; -- flag as error
end
end
end
 
if utilities.is_set (orig) then
link = ''; -- unset
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=;
table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)}); -- URL or wikilink in |title= with |title-link=;
end
return link; -- link if ok, empty string else
end
 
Line 293 ⟶ 291:
Determines whether a URL string appears to be valid.
 
First we test for space characters. If any are found, return false. Then split the urlURL into scheme and domain
portions, or for protocol -relative (//example.com) urlsURLs, just the domain. Use is_url() to validate the two
portions of the urlURL. If both are valid, or for protocol -relative if domain is valid, return true, else false.
 
Because it is different from a standard urlURL, and because this module used external_link() to make external links
that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
Line 304 ⟶ 302:
 
local function check_url( url_str )
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper urlURL
return false;
end
local scheme, domain;
 
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from urlURL;
if 'news:' == scheme then -- special case for newsgroups
Line 315 ⟶ 313:
end
return is_url (scheme, domain); -- return true if value appears to be a valid urlURL
end
 
Line 322 ⟶ 320:
 
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
non-space characters following the opening bracket appear to be a urlURL. The test will also find external wikilinks
that use protocol -relative urlsURLs. Also finds bare urlsURLs.
 
The frontier pattern prevents a match on interwiki -links which are similar to scheme:path urlsURLs. The tests that
find bracketed urlsURLs are required because the parameters that call this test (currently |title=, |chapter=, |work=,
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
is possible as might be [[en://Hus]].
Line 335 ⟶ 333:
local scheme, domain;
 
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol -relative ext. wikilink: [//yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
elseif value:match ('%a%S*:%S+') then -- if bare urlURL with scheme; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
elseif value:match ('//%S+') then -- if protocol -relative bare urlURL: //yyyyy.zzz; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a urlURL
end
 
return is_url (scheme, domain); -- return true if value appears to be a valid urlURL
end
 
Line 360 ⟶ 358:
local error_message = '';
for k, v in pairs (parameter_list) do -- for each parameter in the list
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a urlURL add an error message
if utilities.is_set(error_message) then -- once we've added the first portion of the error message ...
error_message = error_message .. ", "; -- ... add a comma space separator
end
error_message = error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
if utilities.is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_errorutilities.set_message ( 'param_has_ext_linkerr_param_has_ext_link', {error_message}, true ) } );
end
end
Line 381 ⟶ 379:
local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then
table.insert( z.message_tail, { set_errorutilities.set_message ( 'wikilink_in_urlerr_wikilink_in_url', {}, true ) } );
end
Line 403 ⟶ 401:
local base_url;
 
if not utilities.is_set ( label ) then
label = URL;
if utilities.is_set ( source ) then
error_str = set_errorutilities.set_message ( 'bare_url_missing_titleerr_bare_url_missing_title', { utilities.wrap_style ('parameter', source) }, false, " " );
else
error( cfg.messages["bare_url_no_origin"] );
Line 412 ⟶ 410:
end
if not check_url( URL ) then
error_str = set_errorutilities.set_message ( 'bad_urlerr_bad_url', {utilities.wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the urlURL into scheme plus domain and path
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent -encoded values
URL = table.concat ({domain, path}); -- and reassemble
end
 
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkupwiki-markup urlURL
 
if utilities.is_set (access) then -- access level (subscription, registration, limited)
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
end
Line 437 ⟶ 435:
parameters in the citation.
 
added_deprecated_cat is a booleanBoolean declared in page scope variables above
 
]]
Line 444 ⟶ 442:
if not added_deprecated_cat then
added_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, { set_errorutilities.set_message ( 'deprecated_paramserr_deprecated_params', {name}, true ) } ); -- add error message
end
end
Line 451 ⟶ 449:
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
Apply kerning to open the space between the quote mark provided by the Modulemodule and a leading or trailing quote
mark contained in a |title= or |chapter= parameter's value.
 
Line 457 ⟶ 455:
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkupwiki-markup) are not kerned.
 
Replaces unicodeUnicode quotemarksquote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
 
Call this function for chapter titles, for website titles, etc.; not for book titles.
 
]=]
 
local function kern_quotes (str)
local cap = '';
local cap2 = '';
local wl_type, label, link;
 
wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
 
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
Line 508 ⟶ 506:
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
 
|script-title= holds title parameters that are not written in Latin -based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.
 
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtlRTL languages from the English left to right.
 
|script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639ISO 639-1 language code and a colon:
|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
Line 522 ⟶ 520:
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
 
The prefix is checked for validity. If it is a valid ISO639ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
is not added. At this time there is no error message for this condition.
Line 535 ⟶ 533:
if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix
lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not utilities.is_set (lang) then
table.insert( z.message_tail, { set_errorutilities.set_message ( 'script_parametererr_script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
return ''; -- script_value was just the prefix so return empty string
end
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if utilities.in_array (lang, cfg.script_lang_codes) then
utilities.add_prop_cat ('script_with_name', {name, lang})
else
table.insert( z.message_tail, { set_errorutilities.set_message ( 'script_parametererr_script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
table.insert( z.message_tail, { set_errorutilities.set_message ( 'script_parametererr_script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
end
else
table.insert( z.message_tail, { set_errorutilities.set_message ( 'script_parametererr_script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
end
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtlRTL
 
return script_value;
Line 570 ⟶ 568:
 
local function script_concatenate (title, script, script_param)
if utilities.is_set (script) then
script = format_script_value (script, script_param); -- <bdi> tags, lang atributeattribute, categorization, etc.; returns empty string on error
if utilities.is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
Line 589 ⟶ 587:
 
local function wrap_msg (key, str, lower)
if not utilities.is_set ( str ) then
return "";
end
Line 595 ⟶ 593:
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return utilities.substitute ( msg, str ); -- including template text
else
return utilities.substitute ( cfg.messages[key], str );
end
end
Line 604 ⟶ 602:
--[[--------------------------< W I K I S O U R C E _ U R L _ M A K E >----------------------------------------
 
makesMakes a wikisourceWikisource urlURL from wikisourceWikisource interwiki -link. returnsReturns the urlURL and appropriate label; nil else.
 
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
Line 615 ⟶ 613:
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
 
wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
 
if 0 == wl_type then -- not a wikilink; might be from |title-link=
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if utilities.is_set (str) then
ws_url = table.concat ({ -- build a wikisourceWikisource urlURL
wikisource_prefix, -- prefix
str, -- article title
});
ws_label = str; -- label for the urlURL
end
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if utilities.is_set (str) then
ws_url = table.concat ({ -- build a wikisourceWikisource urlURL
wikisource_prefix, -- prefix
str, -- article title
});
ws_label = str; -- label for the urlURL
end
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if utilities.is_set (str) then
ws_label = D; -- get ws article name from display portion of interwiki link
ws_url = table.concat ({ -- build a wikisourceWikisource urlURL
wikisource_prefix, -- prefix
str, -- article title without namespace from link portion of wikilink
Line 647 ⟶ 645:
if ws_url then
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable urlURL
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of fragment marker
end
 
return ws_url, ws_label, L or D; -- return proper urlURL or nil and a label or nil
end
 
Line 665 ⟶ 663:
local periodical_error = '';
 
if not utilities.is_set (periodical) then
periodical = ''; -- to be safe for concatenation
else
periodical = utilities.wrap_style ('italic-title', periodical); -- style
end
 
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
 
if utilities.is_set (trans_periodical) then
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
if utilities.is_set (periodical) then
periodical = periodical .. ' ' .. trans_periodical;
else -- here when trans-periodical without periodical or script-periodical
periodical = trans_periodical;
periodical_error = ' ' .. set_errorutilities.set_message ('trans_missing_titleerr_trans_missing_title', {'periodical'});
end
end
Line 689 ⟶ 687:
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
 
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapterchapter meta-
parameter (chapter_url_source used for error messages).
 
Line 697 ⟶ 695:
local chapter_error = '';
 
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource urlURL and label from a wikisource interwiki link
if ws_url then
ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters
Line 703 ⟶ 701:
end
 
if not utilities.is_set (chapter) then
chapter = ''; -- to be safe for concatenation
else
if false == no_quotes then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Modulemodule provided quote marks
chapter = utilities.wrap_style ('quoted-title', chapter);
end
end
 
chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
 
if utilities.is_set (chapter_url) then
chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
elseif ws_url then
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
 
if utilities.is_set (trans_chapter) then
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter);
if utilities.is_set (chapter) then
chapter = chapter .. ' ' .. trans_chapter;
else -- here when trans_chapter without chapter or script-chapter
chapter = trans_chapter;
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>
chapter_error = ' ' .. set_errorutilities.set_message ('trans_missing_titleerr_trans_missing_title', {chapter_source});
end
end
Line 738 ⟶ 736:
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
This function searches a parameter's value for nonprintablenon-printable or invisible characters. The search stops at the
first match.
 
This function will detect the visible replacement character when it is part of the wikisourceWikisource.
 
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)
Line 756 ⟶ 754:
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
local capture; -- used by stripmarker detection to hold name of the stripmarker
local i = 1;
local stripmarker, apostrophe;
capture = string.match (v, '[%w%p ]*'); -- Testtest for values that are simple ASCII text and bypass other tests if true
if capture == v then -- if same there are no unicodeUnicode characters
return;
end
 
while cfg.invisible_chars[i] do
local char = cfg.invisible_chars[i][1] -- the character or group name
local pattern = cfg.invisible_chars[i][2] -- the pattern used to find it
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position and (char == 'zero width joiner') then -- if we found a zero -width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- itsit's ok if one of the indicIndic scripts
position = nil; -- unset position
end
Line 777 ⟶ 775:
if position then
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
stripmarker = true; -- set a flag
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
Line 789 ⟶ 787:
end
 
table.insert( z.message_tail, { set_errorutilities.set_message ( 'invisible_charerr_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true ) } ); -- add error message
return; -- and done with this parameter
end
end
i = i+1; -- bump our index
end
end
Line 805 ⟶ 803:
]]
 
local function argument_wrapper ( args )
local origin = {};
return setmetatable({
ORIGIN = function ( self, k )
local dummy = self[k]; --force the variable to be loaded.
return origin[k];
Line 823 ⟶ 821:
if type( list ) == 'table' then
v, origin[k] = utilities.select_one ( args, list, 'redundant_parameterserr_redundant_parameters' );
if origin[k] == nil then
origin[k] = ''; -- Empty string, not nil
Line 837 ⟶ 835:
-- Empty strings, not nil;
if v == nil then
-- v = cfg.defaults[k] or '';
v = '';
origin[k] = '';
Line 859 ⟶ 856:
 
local function nowrap_date (date)
local cap = '';
local cap2 = '';
 
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
date = utilities.substitute (cfg.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2});
end
Line 882 ⟶ 879:
 
local function set_titletype (cite_class, title_type)
if utilities.is_set (title_type) then
if 'none' == cfg.keywords_xlate[title_type] then
title_type = ''; -- if |type=none then type parameter not displayed
Line 910 ⟶ 907:
 
local function hyphen_to_dash( str )
if not utilities.is_set (str) then
return str;
end
 
local accept; -- Boolean
str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str
str, accept = utilities.has_accept_as_written (str); -- remove accept-this-as-written markup when it wraps all of str
if 0 ~= count then -- non-zero when markup removed; zero else
if accept then
return str; -- nothing to do, we're done
return str; -- when markup removed, nothing to do, we're done
end
 
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities with their characters; semicolon mucks up the text.split
str = str:gsub ('&#45;', '-'); -- replace htmlHTML numeric entity with hyphen character
str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character
Line 935 ⟶ 933:
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white spacewhitespace
end
end
item = item:gsubutilities.has_accept_as_written ('^%(%((.+)%)%)$', '%1'item); -- remove the accept-this-as-written markup when it wraps all of str
table.insert (out, item); -- add the (possibly modified) item to the output table
end
Line 953 ⟶ 951:
 
local function safe_join( tbl, duplicate_char )
local f = {}; -- create a function table appropriate to type of 'dupicateduplicate character'
if 1 == #duplicate_char then -- for single byte asciiASCII characters use the string library functions
f.gsub = string.gsub
f.match = string.match
f.sub = string.sub
else -- for multi-byte characters use the ustring library functions
f.gsub = mw.ustring.gsub
f.match = mw.ustring.match
f.sub = mw.ustring.sub
end
 
Line 974 ⟶ 972:
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1, 1) == '<' then -- Specialspecial case of values enclosed in spans and other markup.
comp = value:gsub( "%b<>", "" ); -- remove htmlHTML markup (<span>string</span> -> string)
else
comp = value;
end
-- typically duplicate_char is sepc
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
-- Because individual string segments often (always?) begin with terminal punct for the
-- preceding segment: 'First element' .. 'sepc next element' .. etc.?
trim = false;
end_chr = f.sub(str, -1, -1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
str = f.sub(str, 1, -2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkupwiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be wikimarkupwiki-markup
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
trim = true;
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link
trim = true;
elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = f.sub(str, 1, -3); -- remove them both
end
end
 
if trim then
if value ~= comp then -- value does not equal comp when value contains htmlHTML markup
local dup2 = duplicate_char;
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows htmlHTML markup
else
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
Line 1,032 ⟶ 1,030:
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
 
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–91–9. Puncutation not allowed.
 
]]
 
local function is_suffix (suffix)
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
Line 1,046 ⟶ 1,044:
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
 
For Vancouver Stylestyle, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
Line 1,062 ⟶ 1,060:
This original test:
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
was written ousideoutside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.
The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicodeUnicode characters so that it is not necessary
to use an external editor to maintain this code.
 
Line 1,080 ⟶ 1,078:
end
end
if utilities.is_set (suffix) then
if not is_suffix (suffix) then
add_vanc_error (cfg.err_msg_supl.suffix);
Line 1,089 ⟶ 1,087:
nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then
add_vanc_error (cfg.err_msg_supl['non-Latin char']);
return false; -- not a string of latinLatin characters; Vancouver requires Romanization
end;
return true;
Line 1,097 ⟶ 1,095:
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
 
Attempts to convert names to initials in support of |name-list-formatstyle=vanc.
 
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
 
Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
 
This function uses ustring functions because firstname initials may be any of the unicodeUnicode Latin characters accepted by is_good_vanc_name ().
 
]]
Line 1,112 ⟶ 1,110:
 
if not name then -- if not initials and a suffix
name = mw.ustring.match(first, "^(%u+)$"); -- is it just intialsinitials?
end
 
Line 1,144 ⟶ 1,142:
end
if 3 > i then
table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the intialinitial at end of initials table
end
i = i+1; -- bump the counter
Line 1,153 ⟶ 1,151:
 
 
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
 
Formats a list of people (e.g. authors, /contributors, editors, interviewers, translators)
 
names in the list will be linked when
|<name>-link= has a value
|<name>-mask- does NOT have a value; masked names are presumed to have been rendered previously so should have been linked there
 
when |<name>-mask=0, the associated name is not rendered
 
]]
 
local function list_people (control, people, etal)
local sep;
local namesep;
local format = control.format;
local maximum = control.maximum;
local lastauthoramp = control.lastauthoramp; -- TODO: delete after deprecation
local textname_list = {};
 
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between authorsnames is a comma
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
lastauthoramp = nil; -- TODO: delete after deprecation -- unset because isn't used by Vancouver style
else
sep = cfg.presentation['sep_nl']; -- name-list separator between authorsnames is a semicolon
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
end
if sep:sub (-1, -1) ~= " " then sep = sep .. " " end
if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authorsother names
for i, person in ipairs (people) do
if utilities.is_set (person.last) then
local mask = person.mask;
local one;
local sep_one = sep;
 
if is_set (maximum) and i > maximum then
if utilities.is_set (maximum) and i > maximum then
etal = true;
break;
end
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil)mask then
local n = tonumber (mask); -- convert to a number if it can be converted; nil else
one = string.rep("&mdash;",n)
if n then
one = 0 ~= n and string.rep("&mdash;",n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
else
one = mask; -- replace name with mask text (must include name-list separator)
one = mask;
sep_one = " "; -- modify name-list separator
end
else
one = person.last; -- get surname
local first = person.first -- get given name
if utilities.is_set (first) then
if ( "vanc" == format ) then -- if vancouverVancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials (first); -- attempt to convert first name(s) to initials
end
end
Line 1,208 ⟶ 1,216:
end
end
if utilities.is_set (person.link) then
one = utilities.make_wikilink (person.link, one); -- link author/editor
end
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
table.insert (name_list, one); -- add it to the list of names
table.insert (name_list, sep_one); -- add the proper name-list separator
end
table.insert (text, one)
table.insert (text, sep_one)
end
end
 
local count = #textname_list / 2; -- (number of names + number of separators) divided by 2
if count0 >< 0count then
if count > 1 and< is_set(lastauthoramp)count and not etal then
if 'amp' == format or utilities.is_set (lastauthoramp) then -- TODO: delete lastauthoramp after deprecation
text[#text-2] = " & "; -- replace last separator with ampersand text
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
elseif 'and' == format then
if 2 == count then
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
else
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
end
end
end
textname_list[#textname_list] = nil; -- erase the last separator
end
 
local result = table.concat (textname_list) ; -- construct list
if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've gogot a last-first list and etal so add et al.
end
return result, count; -- return name-list string and count of number of names (count used for editor names only)
return result, count
end
 
Line 1,249 ⟶ 1,267:
table.insert (names, year); -- add the year at the end
local id = table.concat(names); -- concatenate names and year for CITEREF id
if utilities.is_set (id) then -- if concatenation is not an empty string
return "CITEREF" .. id; -- add the CITEREF portion
else
Line 1,259 ⟶ 1,277:
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
 
Evaluates the content of name parameters (author, editor, etc.) for variations on the theme of et al. If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
 
Line 1,269 ⟶ 1,287:
local function name_has_etal (name, etal, nocat, param)
 
if utilities.is_set (name) then -- name can be nil in which case just return
local patterns = cfg.et_al_patterns; --get patterns from configuration
Line 1,277 ⟶ 1,295:
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
if not nocat then -- no categorization for |vauthors=
table.insert( z.message_tail, {set_errorutilities.set_message ('etalerr_etal', {param})}); -- and set an error if not added
end
end
Line 1,283 ⟶ 1,301:
end
 
return name, etal; --
end
 
Line 1,297 ⟶ 1,315:
 
local function name_is_numeric (name, list_name)
if utilities.is_set (name) then
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
add_maint_catutilities.set_message ('numeric_namesmaint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
end
end
Line 1,307 ⟶ 1,325:
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
 
Evaluates the content of author and editor parameters for extraniousextraneous editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
Line 1,318 ⟶ 1,336:
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
 
if utilities.is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
add_maint_catutilities.set_message ('extra_text_namesmaint_extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
Line 1,331 ⟶ 1,349:
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
 
Evaluates the content of author and editorlast/surname (surnamesauthors onlyetc.) parameters for multiple names. Multiple names are indicated
indicated if there is more than one comma and or semicolonany semicolons. If found, the function adds the multiple name maintenance category.
(author or editor) maintenance category.
 
returns nothing
Line 1,340 ⟶ 1,357:
 
local function name_has_mult_names (name, list_name)
local _, countcommas, semicolons;
if utilities.is_set (name) then
_, countcommas = name:gsub ('[;,]', ''); -- count the number of separator-like characterscommas
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
if 1 < commas or 0 < semicolons then
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable
add_maint_catutilities.set_message ('mult_namesmaint_mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this templatemessage
end
end
Line 1,359 ⟶ 1,377:
 
local function name_checks (last, first, list_name)
local accept_name;
if is_set (last) then
 
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
if utilities.is_set (last) then
last = last:match ('^%(%((.*)%)%)$'); -- strip parens
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
else
if not accept_name then -- <last> not wrapped in accept-as-written markup
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
Line 1,368 ⟶ 1,388:
end
end
 
if is_set (first) then
if utilities.is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
 
else
if not accept_name then -- <first> not wrapped in accept-as-written markup
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
name_is_numeric (first, list_name); -- check for names that are compsed of digits and punctuation
end
end
 
return last, first; -- done
end
 
 
Line 1,397 ⟶ 1,419:
 
local function extract_names(args, list_name)
local names = {}; -- table of names
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
local etal = false; -- return value set to true when we find some form of et al. in an author parameter
 
local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging
while true do
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameterserr_redundant_parameters', i ); -- search through args for name components beginning at 1
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'redundant_parameterserr_redundant_parameters', i );
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameterserr_redundant_parameters', i );
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameterserr_redundant_parameters', i );
 
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last, first = name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks
if first and not last then -- if there is a firstn without a matching lastn
table.insert(local z.message_tail,alias {= set_error( 'first_missing_last', {first_alias,:find first_alias:gsub('firstgiven', 'last')}1, true ) }and )'given' or 'first'; -- addget first or given form thisof errorthe messagealias
table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', {
first_alias, -- param name of alias missing its mate
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
Line 1,426 ⟶ 1,452:
end
else -- we have last with or without a first
local result;
link_title_ok (link, link_alias, last, last_alias); -- check for improper wikimarkup
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
if first then
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wikimarkupwiki-markup
end
 
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { set_errorutilities.set_message ( 'missing_nameerr_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}, true ) } ); -- add this error message
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
Line 1,441 ⟶ 1,468:
end
return names, etal; -- all done, return our list of names and the etal flag
end
 
Line 1,477 ⟶ 1,504:
end
 
local ietf_code; -- because some languages have both ietfIETF-like codes and isoISO 639-like codes
local ietf_name;
local langlc = mw.ustring.lower (lang); -- lower-case version for comparisons
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
 
for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower (name) then
if 2 == #code:len() or 3 == #code:len() then -- two- or three-character codes only; IETF extensions not supported
return name, code; -- so return the name and the code
end
ietf_code = code; -- remember that we found an ietfIETF-like code and save its name
ietf_name = name; -- but keep looking for a 2- or 3-char code
end
end
-- didn't find name with 2- or 3-char code; if ietfIETF-like code found return
return ietf_code and ietf_name or lang; -- associated name; return original language text else
end
Line 1,521 ⟶ 1,546:
local names_table = {}; -- table made from the value assigned to |language=
 
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
 
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
Line 1,529 ⟶ 1,554:
 
if name then -- there was a remapped code so
if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private ietfIETF tag
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietfIETF tags from code
end
else
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any ietfIETF-like tags from code
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
Line 1,539 ⟶ 1,564:
end
 
if utilities.is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if utilities.is_set (code) then -- only 2- or 3-character codes
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
 
if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if 2 == code:len() then -- and is a two-character code
utilities.add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character code)
utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support multiple three-character code categories per cs1|2 template
end
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled
utilities.add_prop_cat ('local_lang_source', {name, code}); -- categorize it
end
else
add_maint_catutilities.set_message ('unknown_langmaint_unknown_lang'); -- add maint category if not already added
end
Line 1,564 ⟶ 1,589:
name = ''; -- so we can reuse it
end
name = utilities.make_sep_list (#language_list, language_list);
code = #language_list -- reuse code as number of languages in the list
 
if 2 >= code then
name = table.concat (language_list, cfg.messages['parameter-pair-separator']) -- insert '<space>and<space>' between two language names
elseif 2 < code then
name = table.concat (language_list, cfg.messages['parameter-separator'], 1, code-1); -- concatenate all but last
name = table.concat ({name, language_list[code]}, cfg.messages['parameter-final-separator']); -- concatenate last with final separator
end
if this_wiki_name == name then
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
Line 1,592 ⟶ 1,612:
 
local function set_cs1_style (ps)
if not utilities.is_set (ps) then -- unless explicitly set to something
ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation
end
Line 1,609 ⟶ 1,629:
 
local function set_cs2_style (ps, ref)
if not utilities.is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation
end
if not utilities.is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
Line 1,665 ⟶ 1,685:
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
 
Determines if a urlURL has the file extension that is one of the pdfPDF file extensions used by [[MediaWiki:Common.css]] when
applying the pdfPDF icon to external links.
 
returns true if file extension is one of the recognized extensions, else false
Line 1,681 ⟶ 1,701:
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
 
Applies cssCSS style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does
not have a matching urlURL parameter. If the format parameter is not set and the urlURL contains a file extension that
is recognized as a pdfPDF document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.
 
Line 1,689 ⟶ 1,709:
 
local function style_format (format, url, fmt_param, url_param)
if utilities.is_set (format) then
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
if not utilities.is_set (url) then
format = format .. set_error' ' .. utilities.set_message ( 'format_missing_urlerr_format_missing_url', {fmt_param, url_param} ); -- add an error message
end
elseif is_pdf (url) then -- format is not set so if urlURL is a pdfPDF file then
format = utilities.wrap_style ('format', 'PDF'); -- set format to pdfPDF
else
format = ''; -- empty string for concatenation
Line 1,705 ⟶ 1,725:
--[[--------------------------< G E T _ D I S P L A Y _ N A M E S >--------------------------------------------
 
Returns a number that defines the number of names displayed for author and editor name lists and a booleanBoolean flag
to indicate when et al. should be appended to the name list.
 
Line 1,727 ⟶ 1,747:
 
local function get_display_names (max, count, list_name, etal)
if utilities.is_set (max) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
max = count + 1; -- number of authors + 1 so display all author name plus et al.
Line 1,734 ⟶ 1,754:
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cattable.insert( z.message_tail, {utilities.set_message ('disp_nameerr_disp_name', {cfg.special_case_translation [list_name], max}, true)}); -- add error message
max = nil;
end
else -- not a valid keyword or number
table.insert( z.message_tail, {utilities.set_message set_error( 'invalid_param_valerr_disp_name', {'display-' .cfg.special_case_translation [list_name], max}, true ) } ); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
Line 1,762 ⟶ 1,783:
 
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
utilities.set_message ('maint_extra_text'); -- add maint cat;
add_maint_cat ('extra_text');
end
end
Line 1,770 ⟶ 1,791:
 
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled parnethesesparentheses were included in the
rendered citation and in the metadata. Individual author names may be wikilinked
 
Line 1,784 ⟶ 1,805:
while name_table[i] do
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parensparentheses
local name = name_table[i];
i = i + 1; -- bump indexer to next segment
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parensparentheses
break; -- and done reassembling so
end
i = i + 1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
Line 1,805 ⟶ 1,826:
end
end
i = i + 1;
end
return output_table;
Line 1,818 ⟶ 1,839:
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled paranetheseparentheses ((corporate name)) to suppress the format tests.
 
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
 
This function sets the vancouverVancouver error when a reqiredrequired comma is missing and when there is a space between an author's initials.
 
]]
Line 1,839 ⟶ 1,860:
for i, v_name in ipairs(v_name_table) do
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
local accept_name;
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
 
-- if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to suppress vanc formatting and error detection
-- last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parentheses
if accept_name then
last = v_name;
corporate = true; -- flag used in list_people()
elseif string.find(v_name, "%s") then
Line 1,848 ⟶ 1,874:
local lastfirstTable = {}
lastfirstTable = mw.text.split(v_name, "%s+")
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be intialsinitials or generational suffix
 
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-latinLatin characters
suffix = first; -- not initials so assume that whatever we got is a generational suffix
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end
last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
if not utilities.is_set (last) then
first = ''; -- unset
last = v_name; -- last empty because something wrong with first
Line 1,864 ⟶ 1,890:
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error (cfg.err_msg_supl.name); -- matches a space between two intiialsinitials
end
else
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
if utilities.is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error (cfg.err_msg_supl.initials); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first, suffix); -- check first and last before restoring the suffix which may have a non-Latin digit
if utilities.is_set (suffix) then
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
suffix = ''; -- unset so we don't add this suffix to all subsequent names
Line 1,885 ⟶ 1,911:
end
 
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameterserr_redundant_parameters', i ) or v_link_table[i];
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameterserr_redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list
end
return names, etal; -- all done, return our list of names
Line 1,913 ⟶ 1,939:
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local lastfirst = false;
if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incasein case we have a |first1= without a |last1=; this ...
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
lastfirst = true;
end
 
if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
(utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
(true == lastfirst and utilities.is_set (xxxxors)) then
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
Line 1,929 ⟶ 1,955:
err_name = 'editor';
end
table.insert( z.message_tail, { set_errorutilities.set_message ( 'redundant_parameterserr_redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
 
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if utilities.is_set (vxxxxors) then return 2 end;
if utilities.is_set (xxxxors) then return 3 end;
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
end
Line 1,943 ⟶ 1,969:
 
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, live, dead, etc.). When the parameter value has not been assigned a value (missing
or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one
of the list of allowed values returns the translated value; else, emits an error message and returns the value
Line 1,951 ⟶ 1,977:
 
local function is_valid_parameter_value (value, name, possible, ret_val)
if not utilities.is_set (value) then
return ret_val; -- an empty parameter is ok
elseif utilities.in_array (value, possible) then
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
else
table.insert( z.message_tail, { set_errorutilities.set_message ( 'invalid_param_valerr_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return ret_val;
end
Line 1,972 ⟶ 1,998:
 
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
return name_list; -- just return the name list
elseif (string.sub (name_list, -1, -1) == sepc) or (string.sub (name_list, -3, -1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
else
return name_list .. sepc .. ' '; -- otherwise terninateterminate the name list
end
end
Line 1,990 ⟶ 2,016:
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not utilities.is_set (volume) and not utilities.is_set (issue) then
return '';
end
if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
Line 2,004 ⟶ 2,030:
end
 
if 'podcast' == cite_class and utilities.is_set (issue) then
return wrap_msg ('issue', {sepc, issue}, lower);
end
Line 2,010 ⟶ 2,036:
local vol = ''; -- here for all cites except magazine
if utilities.is_set (volume) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase romanRoman numerals
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face
elseif (4 < mw.ustring.len(volume)) then -- not all digits or romanRoman numerals and longer than 4 characters
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold
utilities.add_prop_cat ('long_vol');
else -- four or less characters
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold
end
end
if utilities.is_set (issue) then
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
end
return vol;
Line 2,039 ⟶ 2,065:
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if utilities.is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
Line 2,045 ⟶ 2,071:
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif utilities.is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
Line 2,054 ⟶ 2,080:
end
 
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
if utilities.is_set (page) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif utilities.is_set (pages) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
Line 2,084 ⟶ 2,110:
returns one of the in-source locators: page, pages, or at.
 
If any of these are interwiki links to wikisourceWikisource, returns the label portion of the interwikilinkinterwiki-link as plain text
for use in COinS. This COinS thing is done because here we convert an interwiki -link to and external link and
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?
 
Line 2,096 ⟶ 2,122:
 
local function insource_loc_get (page, pages, at)
local ws_url, ws_label, coins_pages, L; -- for wikisourceWikisource interwikilinksinterwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
 
if utilities.is_set (page) then
if utilities.is_set (pages) or utilities.is_set (at) then
pages = ''; -- unset the others
at = '';
Line 2,105 ⟶ 2,131:
extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
 
ws_url, ws_label, L = wikisource_url_make (page); -- make ws urlURL from |page= interwiki link; link portion L becomes tool tiptooltip label
if ws_url then
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
coins_pages = ws_label;
end
elseif utilities.is_set (pages) then
if utilities.is_set (at) then
at = ''; -- unset
end
extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
 
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws urlURL from |pages= interwiki link; link portion L becomes tool tiptooltip label
if ws_url then
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
coins_pages = ws_label;
end
elseif utilities.is_set (at) then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws urlURL from |at= interwiki link; link portion L becomes tool tiptooltip label
if ws_url then
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
Line 2,138 ⟶ 2,164:
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
 
Check archive.org urlsURLs to make sure they at least look like they are pointing at valid archives and not to the
save snapshot urlURL or to calendar pages. When the archive urlURL is 'https://web.archive.org/save/' (or http://...)
archive.org saves a snapshot of the target page in the urlURL. That is something that Wikipedia should not allow
unwitting readers to do.
 
When the archive.org urlURL does not have a complete timestamp, archive.org chooses a snapshot according to its own
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
 
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
|archive-date= and an error message when:
|archive-url= holds an archive.org save command urlURL
|archive-url= is an archive.org urlURL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
correct place
otherwise returns |archive-url= and |archive-date=
 
There are two mostly compatible archive.org urlsURLs:
//web.archive.org/<timestamp>... -- the old form
//web.archive.org/web/<timestamp>... -- the new form
Line 2,161 ⟶ 2,187:
we don't check for these specific flags but we do check the form.
 
This function supports a preview mode. When the article is rendered in preview mode, this functfunction may return a modified
archive urlURL:
for save command errors, return undated wildcard (/*/)
for timestamp errors when the timestamp has a wildcard, return the urlURL unmodified
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
 
Line 2,171 ⟶ 2,197:
local function archive_url_check (url, date)
local err_msg = ''; -- start with the error message empty
local path, timestamp, flag; -- portions of the archive.ororg urlURL
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine urlURL
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
end
 
if url:match('//web%.archive%.org/save/') then -- if a save command urlURL, we don't want to allow saving of the target page
err_msg = cfg.err_msg_supl.save;
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
Line 2,183 ⟶ 2,209:
err_msg = cfg.err_msg_supl.liveweb;
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the urlURL parts for evaluation
if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = cfg.err_msg_supl.timestamp;
if '*' ~= flag then
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif utilities.is_set (path) and 'web/' ~= path then -- older archive urlsURLs do not have the extra 'web/' path element
err_msg = cfg.err_msg_supl.path;
elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form urlURL (without the 'web/' path element)
err_msg = cfg.err_msg_supl.flag;
elseif utilities.is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = cfg.err_msg_supl.flag;
else
Line 2,201 ⟶ 2,227:
end
-- if here, something not right so
table.insert( z.message_tail, { set_errorutilities.set_message ( 'archive_urlerr_archive_url', {err_msg}, true ) } ); -- add error message and
if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
else
Line 2,213 ⟶ 2,239:
 
check |place=, |publication-place=, |location= to see if these params include digits. This function added because
many editors mis-usemisuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
 
returns the original parameter value without modification; added maint cat when parameter value contains digits
Line 2,220 ⟶ 2,246:
 
local function place_check (param_val)
if not utilities.is_set (param_val) then -- parameter empty or omitted
return param_val; -- return that empty state
end
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
add_maint_catutilities.set_message ('locationmaint_location'); -- yep, add maint cat
end
return param_val; -- and done
end
 
 
--[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------
 
compares |title= value against list of known generic title patterns. Returns true when pattern matches; nil else
 
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
index [1]. index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so
that we don't run out of processing time on very large articles.
 
]]
 
local function is_generic_title (title)
title = mw.ustring.lower(title); -- switch title to lower case
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do --spin through the list of known generic title fragments
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
return true; -- found English generic title so done
elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script
return true; -- found local generic title so done
end
end
end
end
 
 
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
 
compares |title= to 'Archived copy' (place holder added by bots that can't find proper title); if matches, return true; nil else
 
]]
 
local function is_archived_copy (title)
title = mw.ustring.lower(title); -- switch title to lower case
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
return true;
elseif cfg.special_case_translation.archived_copy['local'] then
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
return true;
end
end
end
 
Line 2,243 ⟶ 2,313:
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
]]
local A = argument_wrapper ( args );
local i
 
Line 2,255 ⟶ 2,325:
local Authors;
 
local NameListFormatNameListStyle = is_valid_parameter_value (A['NameListFormatNameListStyle'], A:ORIGIN('NameListFormatNameListStyle'), cfg.keywords_lists['name-list-formatstyle'], '');
local Collaboration = A['Collaboration'];
 
Line 2,263 ⟶ 2,333:
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
NameListFormatNameListStyle = 'vanc'; -- override whatever |name-list-formatstyle= might be
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
add_maint_catutilities.set_message ('authorsmaint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
end
if utilities.is_set (Collaboration) then
author_etal = true; -- so that |display-authors=etal not required
end
Line 2,287 ⟶ 2,357:
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
elseif 2 == selected then
NameListFormatNameListStyle = 'vanc'; -- override whatever |name-list-formatstyle= might be
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged
end
end
Line 2,316 ⟶ 2,385:
end
 
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
if 0 < #c then
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
table.insert( z.message_tail, { set_errorutilities.set_message ( 'contributor_missing_required_paramerr_contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
table.insert( z.message_tail, { set_errorutilities.set_message ( 'contributor_missing_required_paramerr_contributor_missing_required_param', 'author')}); -- add missing author error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
end
else -- if not a book cite
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameterserr_redundant_parameters', 1 ) then -- are there contributor name list parameters?
table.insert( z.message_tail, { set_errorutilities.set_message ( 'contributor_ignorederr_contributor_ignored')}); -- add contributor ignored error message
end
Contribution = nil; -- unset
end
 
if utilities.is_set (Others) then
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
add_maint_catutilities.set_message ('othersmaint_others');
end
end
Line 2,344 ⟶ 2,413:
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local OrigYearOrigDate = A['OrigYearOrigDate'];
local Date = A['Date'];
local LayDate = A['LayDate'];
Line 2,356 ⟶ 2,425:
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
 
local auto_select = ''; -- default is auto
local Section = ''; -- {{cite map}} only; preset to empty string for concatnation if not used
local accept_link;
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
auto_select = TitleLink; -- remember selection for later
TitleLink = ''; -- treat as if |title-link= would have been empty
end
 
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
 
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
if 'map' == config.CitationClass and 'section' == A:ORIGIN ('Chapter') then
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
Line 2,366 ⟶ 2,444:
local ScriptChapter = A['ScriptChapter'];
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TransChapter_origin = A:ORIGIN ('TransChapter');
Line 2,380 ⟶ 2,458:
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
 
 
local URL = A['URL']
Line 2,392 ⟶ 2,469:
local Periodical = A['Periodical'];
local Periodical_origin = '';
if utilities.is_set (Periodical) then
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local i;
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip appostropheapostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_errorutilities.set_message ('apostrophe_markuperr_apostrophe_markup', {Periodical_origin}, true)});
end
end
end
 
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error
table.insert( z.message_tail, {utilities.set_message set_error('redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
end
 
Line 2,410 ⟶ 2,487:
end
 
 
 
local ScriptPeriodical = A['ScriptPeriodical'];
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
 
-- web and news not tested for now because of
-- web and news not tested for now because of
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
if not (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
if p[config.CitationClass] then
table.insert( z.message_tail, {set_error ('missing_periodical', {config.CitationClass,if p[config.CitationClass]}, true)}); then
table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
end
end
end
 
local TransPeriodical = A['TransPeriodical'];
Line 2,437 ⟶ 2,512:
 
if 'citation' == config.CitationClass then
if utilities.is_set (Periodical) then
if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif utilities.is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
Line 2,448 ⟶ 2,523:
Volume = A['Volume']; -- and does for non-'periodical' cites
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
Volume = A['Volume'];
end
 
if 'citation' == config.CitationClass then
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
Issue = hyphen_to_dash (A['Issue']);
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
Issue = hyphen_to_dash (A['Issue']);
end
Line 2,464 ⟶ 2,539:
 
local Position = '';
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = hyphen_to_dash (A['Pages']);
Line 2,476 ⟶ 2,551:
local PublisherName = A['PublisherName'];
local PublisherName_origin = A:ORIGIN('PublisherName');
if utilities.is_set (PublisherName) then
local i = 0;
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip appostropheapostrophe markup so that metadata isn't contaminated; publisher is never italicized
if i then -- non-zero when markup was stripped so emit an error message
 
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_error ('apostrophe_markup', {PublisherName_origin}, true)});
end
end
end
 
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
Line 2,489 ⟶ 2,563:
 
if 'newsgroup' == config.CitationClass then
if utilities.is_set (PublisherName) then -- general use parmeterparameter |publisher= not allowed in cite newsgroup
local error_text, error_state = set_errorutilities.set_message ('parameter_ignorederr_parameter_ignored', {PublisherName_origin}, true);
if utilities.is_set (error_text) then
table.insert( z.message_tail, {error_text, error_state} );
end
Line 2,500 ⟶ 2,574:
 
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
UrlAccess = nil;
table.insert( z.message_tail, { set_errorutilities.set_message ( 'param_access_requires_paramerr_param_access_requires_param', {'url'}, true ) } );
end
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
ChapterUrlAccess = nil;
table.insert( z.message_tail, { set_errorutilities.set_message ( 'param_access_requires_paramerr_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
end
 
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
MapUrlAccess = nil;
table.insert( z.message_tail, { set_errorutilities.set_message ( 'param_access_requires_paramerr_param_access_requires_param', {'map-url'}, true ) } );
end
 
local Via = A['Via'];
Line 2,530 ⟶ 2,604:
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
 
local ID_list = extract_ids( args );
if is_set (DoiBroken) and not ID_list['DOI'] then
table.insert( z.message_tail, { set_error( 'doibroken_missing_doi', A:ORIGIN('DoiBroken'))});
end
local ID_access_levels = extract_id_access_levels( args, ID_list );
 
local Quote = A['Quote'];
local QuotePage = A['QuotePage'];
local QuotePages = A['QuotePages'];
local ScriptQuote = A['ScriptQuote'];
local TransQuote = A['TransQuote'];
 
local LayFormat = A['LayFormat'];
Line 2,550 ⟶ 2,622:
 
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
if 'nocat' == A:ORIGIN('NoTracking') then
 
utilities.set_message ('maint_nocat'); -- this one so that we get the message; see main categorization at end of citation0()
end
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
Line 2,558 ⟶ 2,633:
 
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
if not utilities.is_set (DF) then
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
end
 
Line 2,566 ⟶ 2,641:
local Ref = A['Ref'];
if 'harv' == Ref then
add_maint_catutilities.set_message ('ref_harvmaint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value
elseif not utilities.is_set (Ref) then
Ref = 'harv'; -- set as default when not set externally
end
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], Ref, config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
 
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
Line 2,587 ⟶ 2,662:
end
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameterserr_redundant_parameters'); -- this is a dummy call simply to get the error message and category
 
local coins_pages;
Line 2,595 ⟶ 2,670:
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
 
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
if PublicationPlace == Place then
Place = ''; -- unset; don't need both if they are the same
end
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
Line 2,609 ⟶ 2,684:
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title=
|encyclopedia= and |article= then map |encyclopedia= to |title=
 
|trans-title= maps to |trans-chapter= when |title= is re-mapped
|url= maps to |chapterurlchapter-url= when |title= is remapped
All other combinations of |encyclopedia=, |title=, and |article= are not modified
]]
Line 2,621 ⟶ 2,696:
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
 
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
table.insert (z.message_tail, {set_errorutilities.set_message ('parameter_ignorederr_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
Encyclopedia = nil; -- unset because not supported by this template
end
end
 
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error
table.insert (z.message_tail, {set_errorutilities.set_message ('redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
end
 
if utilities.is_set (Encyclopedia) then
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
Periodical_origin = A:ORIGIN ('Encyclopedia');
end
 
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
if not utilities.is_set (Chapter) then
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle')
Line 2,650 ⟶ 2,725:
ChapterUrlAccess = UrlAccess;
 
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
Chapter = utilities.make_wikilink (TitleLink, Chapter);
end
Title = Periodical;
Line 2,662 ⟶ 2,737:
ScriptTitle = '';
end
elseif utilities.is_set (Chapter) then -- |title= not set
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
Periodical = ''; -- redundant so unset
end
Line 2,669 ⟶ 2,744:
end
 
-- Specialspecial case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
if not utilities.is_set (ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
table.insert( z.message_tail, { set_errorutilities.set_message ('redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
end
end
Line 2,682 ⟶ 2,757:
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if 'conference' == config.CitationClass then
if utilities.is_set (BookTitle) then
Chapter = Title;
Chapter_origin = 'title';
-- ChapterLink = TitleLink; -- |chapterlinkchapter-link= is deprecated
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
Line 2,709 ⟶ 2,784:
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
if utilities.is_set (Chapter) then
table.insert( z.message_tail, { set_errorutilities.set_message ( 'redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
end
Chapter = A['Map'];
Line 2,724 ⟶ 2,799:
 
Cartography = A['Cartography'];
if utilities.is_set ( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
Scale = A['Scale'];
if utilities.is_set ( Scale ) then
Scale = sepc .. " " .. Scale;
end
Line 2,737 ⟶ 2,812:
local SeriesLink = A['SeriesLink'];
 
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkupwiki-markup in |series-link= or wikimarkupwiki-markup in |series= when |series-link= is set
 
local Network = A['Network'];
Line 2,743 ⟶ 2,818:
local s, n = {}, {};
-- do common parameters first
if utilities.is_set (Network) then table.insert(n, Network); end
if utilities.is_set (Station) then table.insert(n, Station); end
ID = table.concat(n, sepc .. ' ');
Line 2,751 ⟶ 2,826:
local SeriesNumber = A['SeriesNumber'];
 
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
table.insert( z.message_tail, { set_errorutilities.set_message ( 'redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Line 2,764 ⟶ 2,839:
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
ChapterLink = TitleLink; -- alias episodelink|episode-link=
TransChapter = TransTitle;
ChapterURL = URL;
Line 2,774 ⟶ 2,849:
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
 
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
Series = utilities.make_wikilink (ChapterLink, Series);
end
URL = ''; -- unset
Line 2,786 ⟶ 2,861:
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
Series = utilities.make_wikilink (SeriesLink, Series);
end
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
end
end
-- end of {{cite episode}} stuff
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
do
if in_array (config.CitationClass, whitelist.preprint_template_list) then
if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message
end
 
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
end
end
 
-- handle type parameter for those CS1 citations that have default values
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
end
end
 
if utilities.is_set (TitleType) then -- if type parameter is specified
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
-- TODO: Hack on TitleType to fix bunched parentheses problem
end
Line 2,821 ⟶ 2,885:
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
 
if not utilities.is_set (Date) then
Date = Year; -- promote Year to Date
Year = nil; -- make nil so Year as empty string isn't used for CITEREF
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
Line 2,847 ⟶ 2,911:
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
['date'] = {val = Date, name = Date_origin},
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')},
['lay-date'] = {val = LayDate, name = A:ORIGIN ('LayDate')},
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')},
['year'] = {val = Year, name = A:ORIGIN ('Year')},
};
 
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
local error_list = {};
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
 
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
utilities.add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
 
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
local mismatch = validation.year_date_check (Year, Date);
if 0 == mismatch then -- |year= does not match a year-value in |date=
table.insert (error_list, '<code class="cs1-code">&#124;year= / &#124;date= mismatch</code>');
if is_set (error_message) then -- if there is already an error message
error_message = error_message .. ', '; -- tack on this additional message
end
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
elseif 1 == mismatch then -- |year= matches year-value in |date=
utilities.set_message ('maint_date_year'); -- add a maint cat
add_maint_cat ('date_year');
end
end
if not0 is_set(error_message)== #error_list then -- error free dates only; 0 when error_list is empty
local modified = false; -- flag
if utilities.is_set (DF) then -- if we need to reformat dates
modified = validation.reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
end
 
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
modified = true;
add_maint_catutilities.set_message ('date_formatmaint_date_format'); -- hyphens were converted so add maint category
end
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment thesethe next three lines. Not supported by en.wiki (for obvious reasons)
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
-- if validation.date_name_xlate (date_parameters_list, false) then
-- modified = true;
-- end
Line 2,904 ⟶ 2,967:
end
else
table.insert( (z.message_tail, {utilities.set_message set_error( 'bad_dateerr_bad_date', {error_messageutilities.make_sep_list (#error_list, error_list)}, true ) } ); -- add this error message
end
end -- end of do
 
local ID_list_coins = identifiers.extract_ids (args); -- gets identifiers and their values from args; this list used for COinS and source for build_id_list()
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
if utilities.is_set (DoiBroken) and not ID_list_coins['DOI'] then
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
table.insert (z.message_tail, {utilities.set_message ('err_doibroken_missing_doi', A:ORIGIN('DoiBroken'))});
Embargo = is_embargoed (Embargo);
end
local ID_access_levels = identifiers.extract_id_access_levels (args, ID_list_coins);
local ID_list = identifiers.build_id_list (ID_list_coins, {IdAccessLevels = ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo = Embargo, Class = Class}); -- render identifiers
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
if config.CitationClass == "journal" and not is_set(URL) and not is_set(TitleLink) then
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then
if is_set(ID_list['PMC']) and not is_set (Embargo) then -- if not embargoed or embargo has expired
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- add error message
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif is_set(ID_list['DOI']) and ID_access_levels['DOI'] == "free" then
URL=cfg.id_handlers['DOI'].prefix .. ID_list['DOI'];
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
 
if is_set(URL) and is_set(AccessDate) then -- access date requires |url=; pmc or doi created url is not |url=
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
end
AccessDate = ''; -- unset
 
-- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
 
if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled
if identifiers.auto_link_urls[auto_select] then -- manual selection
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
URL = identifiers.auto_link_urls['doi'];
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
end
 
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url=
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message
AccessDate = ''; -- unset
end
end
Line 2,928 ⟶ 3,011:
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
-- Test if citation has no title
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
table.insert( z.message_tail, { set_errorutilities.set_message ( 'citation_missing_titleerr_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
end
 
if utilities.in_array (cfg.keywords_xlate[Title], =={'off', 'none'}) and
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Title = ''; -- set title to empty string
utilities.set_message ('maint_untitled'); -- add maint cat
add_maint_cat ('untitled');
end
 
Line 2,954 ⟶ 3,037:
local coins_chapter = Chapter; -- default assuming that remapping not required
local coins_title = Title; -- et tu
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then
coins_chapter = Title; -- remap
coins_title = Periodical;
Line 2,964 ⟶ 3,047:
coins_author = c; -- use that instead
end
 
-- this is the function call to COinS()
local OCinSoutput = metadata.COinS({
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkupwiki-markup
['Degree'] = Degree; -- cite thesis only
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkupwiki-markup
['PublicationPlace'] = PublicationPlace,
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
Line 2,980 ⟶ 3,063:
['Volume'] = Volume,
['Issue'] = Issue,
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['ID_list'] = ID_listID_list_coins,
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
 
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
end
 
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
end
 
Line 3,006 ⟶ 3,089:
local last_first_list;
local control = {
format = NameListFormatNameListStyle, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
Line 3,016 ⟶ 3,099:
last_first_list, EditorCount = list_people(control, e, editor_etal);
 
if utilities.is_set (Editors) then
Editors, editor_etal = name_has_etal (Editors, editor_etal, false, 'editors'); -- find and remove variations on et al.
if editor_etal then
Line 3,047 ⟶ 3,130:
last_first_list = list_people(control, a, author_etal);
 
if utilities.is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
Line 3,057 ⟶ 3,140:
end -- end of do
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
end
Line 3,064 ⟶ 3,147:
 
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated urlURL is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Line 3,072 ⟶ 3,155:
 
-- special case for chapter format so no error message or cat when chapter not supported
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
 
if not utilities.is_set (URL) then
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
table.insert( z.message_tail, { set_errorutilities.set_message ( 'cite_web_urlerr_cite_web_url', {}, true ) } );
end
-- do we have |accessdate= without either |url= or |chapter-url=?
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set;
table.insert( z.message_tail, { set_errorutilities.set_message ( 'accessdate_missing_urlerr_accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
Line 3,092 ⟶ 3,175:
local OriginalURL, OriginalURL_origin, OriginalFormat, OriginalAccess;
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
if utilities.is_set ( ArchiveURL ) then
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
OriginalFormat = ChapterFormat; -- and original |chapter-format=
 
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's urlURL
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urlsURLs
end
elseif utilities.is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURL_origin = URL_origin; -- name of urlURL parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
 
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
URL = ArchiveURL -- swap-in the archive's urlURL
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive urlURL parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived urlsURLs
end
end
end
 
if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
local chap_param;
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
chap_param = A:ORIGIN ('Chapter')
elseif utilities.is_set (TransChapter) then
chap_param = A:ORIGIN ('TransChapter')
elseif utilities.is_set (ChapterURL) then
chap_param = A:ORIGIN ('ChapterURL')
elseif utilities.is_set (ScriptChapter) then
chap_param = ScriptChapter_origin;
else utilities.is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
 
if utilities.is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { set_errorutilities.set_message ( 'chapter_ignorederr_chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
Line 3,144 ⟶ 3,227:
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
Line 3,151 ⟶ 3,234:
 
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
if utilities.is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
if 'map' == config.CitationClass and utilities.is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
end
Chapter = Chapter .. sepc .. ' ';
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
Line 3,163 ⟶ 3,246:
 
-- Format main title
local plain_title = false;
if is_set (ArchiveURL) and
local accept_title;
(mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation.archived_copy.en) or -- if title is 'Archived copy' (place holder added by bots that can't find proper title)
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation.archived_copy['local'])) then -- local-wiki's form
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title
Title = cfg.messages['notitle']; -- replace by predefined "No title" message
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
ScriptTitle = ''; -- just mute for now
TransTitle = ''; -- just mute for now
plain_title = true; -- suppress text decoration for descriptive title
utilities.set_message ('maint_untitled'); -- add maint cat
end
 
if Title:matchnot ('^%(%(.*%)%)$')accept_title then -- if<Title> keepnot aswrapped in accept-as-written markup:
Titleif '...' == Title:gsubsub ('^%(%((.*-3)%)%)$', '%1')then -- removeif ellipsis is the markuplast three characters of |title=
else
if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title=
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
 
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
end
 
if is_generic_title (Title) then
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message
end
end
 
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Modulemodule provided quote marks
Title = utilities.wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
Title = utilities.wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
end
 
local TransError = "";
if utilities.is_set (TransTitle) then
if utilities.is_set (Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. set_errorutilities.set_message ( 'trans_missing_titleerr_trans_missing_title', {'title'} );
end
end
 
if utilities.is_set (Title) then -- TODO: is this the right place to be making wikisourceWikisource urlsURLs?
if utilities.is_set (TitleLink) and utilities.is_set (URL) then
table.insert( z.message_tail, { set_errorutilities.set_message ( 'wikilink_in_urlerr_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both
TitleLink = ''; -- unset
end
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format;
URL = ''; -- unset these because no longer needed
Format = "";
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
ws_url, ws_label, L = wikisource_url_make (Title:gsub('[\'"](.-)[\'"]', '%1')); -- make ws urlURL from |title= interwiki link (strip italic or quote markup); link portion L becomes tool tiptooltip label
if ws_url then
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Line 3,241 ⟶ 3,336:
end
 
if utilities.is_set (Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
 
if utilities.is_set (Conference) then
if utilities.is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif utilities.is_set (ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil );
end
 
if not utilities.is_set (Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
 
if utilities.is_set (Minutes) then
if utilities.is_set (Time) then
table.insert( z.message_tail, { set_errorutilities.set_message ( 'redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if utilities.is_set (Time) then
local TimeCaption = A['TimeCaption']
if not utilities.is_set (TimeCaption) then
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
Line 3,282 ⟶ 3,377:
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
 
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
local Inset = A['Inset'];
if utilities.is_set ( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
 
if utilities.is_set ( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif utilities.is_set ( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
Line 3,300 ⟶ 3,395:
end
 
if utilities.is_set (Language) then
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
else
Language=""; -- language not specified so make sure this is an empty string;
Line 3,309 ⟶ 3,404:
end
 
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
if utilities.is_set (Translators) then
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
end
if utilities.is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if utilities.is_set (Edition) then
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
add_maint_catutilities.set_message ('extra_textmaint_extra_text', 'edition'); -- add maint cat
end
Edition = " " .. wrap_msg ('edition', Edition);
Line 3,328 ⟶ 3,423:
end
 
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
OrigYearOrigDate = utilities.is_set (OrigYearOrigDate) and wrap_msg ('origyearorigdate', OrigYearOrigDate) or '';
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
 
------------------------------------ totally unrelated data
Via = utilities.is_set (Via) and wrap_msg ('via', Via) or '';
 
if utilities.is_set (AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
 
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text
 
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
if "thesis" == config.CitationClass and utilities.is_set (Docket) then
ID = sepc .. " Docket " .. Docket .. ID;
end
if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
 
if utilities.is_set (URL) then
ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
 
if is_set(URL) then
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
end
 
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
 
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
if utilities.is_set (Quote) then
Quote = Quote:sub(2,-2); -- strip them off
if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks
Quote = Quote:sub(2, -2); -- strip them off
end
end
 
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
if utilities.is_set (ScriptQuote) then
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
end
 
if utilities.is_set (TransQuote) then
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
TransQuote = TransQuote:sub(2, -2); -- strip them off
end
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
end
 
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
local quote_prefix = '';
if utilities.is_set (QuotePage) then
if not NoPP then
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
end
elseif utilities.is_set (QuotePages) then
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', '';
elseif not NoPP then
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', '';
else
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', '';
end
end
Quote = quote_prefix .. ": " .. Quote;
else
Quote = sepc .. " " .. Quote;
end
 
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set
end
local Archived
if utilities.is_set (ArchiveURL) then
local arch_text;
if not utilities.is_set (ArchiveDate) then
ArchiveDate = set_errorutilities.set_message ('archive_missing_dateerr_archive_missing_date');
end
if "live" == UrlStatus then
arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not utilities.is_set (OriginalURL) then
Archived = Archived .. " " .. set_errorutilities.set_message ('archive_missing_urlerr_archive_missing_url');
end
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
arch_text = cfg.messages['archived-unfit'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
if 'bot: unknown' == UrlStatus then
add_maint_catutilities.set_message ('bot:_unknownmaint_bot_unknown'); -- and add a category if not already added
else
add_maint_catutilities.set_message ('unfitmaint_unfit'); -- and add a category if not already added
end
else -- UrlStatus is empty, 'dead'
arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
Line 3,401 ⟶ 3,533:
arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ set_errorutilities.set_message ('archive_missing_urlerr_archive_missing_url'), ArchiveDate } );
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Line 3,411 ⟶ 3,543:
local Lay = '';
if utilities.is_set (LayURL) then
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
if utilities.is_set (LaySource) then
LaySource = " &ndash; ''" .. utilities.safe_for_italics (LaySource) .. "''";
else
LaySource = "";
Line 3,423 ⟶ 3,555:
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
elseif utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
end
 
if utilities.is_set (Transcript) then
if utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif utilities.is_set (TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil );
end
 
local Publisher;
if utilities.is_set (PublicationDate) then
PublicationDate = wrap_msg ('published', PublicationDate);
end
if utilities.is_set (PublisherName) then
if utilities.is_set (PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate;
end
elseif utilities.is_set (PublicationPlace) then
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else
Line 3,453 ⟶ 3,585:
-- Several of the above rely upon detecting this as nil, so do it last.
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then
if utilities.is_set (Title) or utilities.is_set (TitleNote) then
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
else
Line 3,467 ⟶ 3,599:
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
if utilities.is_set (Conference) then -- and if |event= is set
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
Line 3,481 ⟶ 3,613:
local tcommon2; -- used for book cite when |contributor= is set
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Line 3,493 ⟶ 3,625:
 
elseif 'map' == config.CitationClass then -- special cases for cite map
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif utilities.is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
Line 3,525 ⟶ 3,657:
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 
if utilities.is_set (Date) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date .. ")" .. OrigYearOrigDate .. sepc .. " "; -- in paranethesesparentheses
else -- neither of authors and editors set
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
Date = " " .. Date .. OrigYearOrigDate; -- Date does not begin with sepc
else
Date = sepc .. " " .. Date .. OrigYearOrigDate; -- Date begins with sepc
end
end
end
if utilities.is_set (Authors) then
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
if utilities.is_set (Editors) then
local in_text = " ";
local post_text = "";
if utilities.is_set (Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then
Line 3,556 ⟶ 3,688:
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
Line 3,570 ⟶ 3,702:
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif utilities.is_set (Editors) then
if utilities.is_set (Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
Line 3,586 ⟶ 3,718:
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
Line 3,593 ⟶ 3,725:
end
if utilities.is_set (PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1, -sepc:len() - 1);
end
Line 3,603 ⟶ 3,735:
local options = {};
if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref=
else
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2');
end
if utilities.is_set (Ref) and 'none' ~= cfg.keywords_xlate[Ref:lower()] then
local id = Ref
if ('harv' == Ref ) then
Line 3,631 ⟶ 3,763:
end
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then -- remove <span> tags and other htmlHTML-like markup; then get length of what remains
z.error_categories = {};
text = set_errorutilities.set_message ('empty_citationerr_empty_citation');
z.message_tail = {};
end
Line 3,639 ⟶ 3,771:
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
 
if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
 
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
 
if 0 ~= #z.message_tail then
table.insert (render, ' ');
for i,v in ipairs( z.message_tail ) do
if utilities.is_set (v[1]) then
if i == #z.message_tail then
table.insert (render, utilities.error_comment ( v[1], v[2] ));
else
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
end
end
Line 3,666 ⟶ 3,798:
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint, utilities.make_wikilink (':Category:' .. v, 'link')); -- add the link
table.insert (maint, ')'); -- and close it
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
end
table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
end
if not no_tracking_cats then
for _, v in ipairs( z.error_categories ) do
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
for _, v in ipairs( z.properties_cats ) do -- append properties categories
table.insert (render, utilities.make_wikilink ('Category:' .. v));
end
elseif 'nocat' == A:ORIGIN('NoTracking') then -- peculiar special case; can't track nocat without tracking nocat
table.insert (render, utilities.make_wikilink ('Category:CS1 maint: nocat')); -- hand-set this category because it is supposed to be temporary
end
 
Line 3,700 ⟶ 3,834:
]]
 
local function validate (name, cite_class, empty)
local name = tostring (name);
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
local state;
local function state_test (state, name) -- local function to do testing of state values
if true == state then return true; end -- valid actively supported parameter
if false == state then
if empty then return nil; end -- deprecated empty parameters are treated as unknowns
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
Line 3,716 ⟶ 3,852:
end
 
if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[name];
if true == state_test (state, name) then return true; end
Line 3,724 ⟶ 3,860:
 
-- limited enumerated parameters list
nameenum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[nameenum_name];
if true == state_test (state, name) then return true; end
 
Line 3,731 ⟶ 3,867:
end -- end limited parameter-set templates
 
if utilities.in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list
state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
if true == state_test (state, name) then return true; end
Line 3,740 ⟶ 3,876:
 
-- all enumerated parameters allowed
nameenum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.numbered_arguments[nameenum_name];
if true == state_test (state, name) then return true; end
 
return false; -- not supported because not found or name is set to nil
end
 
 
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
 
check <value> for inter-language interwiki-link markup. <prefix> must be a MediaWiki-recognized language
code. when these values have the form (without leading colon):
[[<prefix>:link|label]] return label as plain-text
[[<prefix>:link]] return <prefix>:link as plain-text
 
return value as is else
 
]=]
 
local function inter_wiki_check (parameter, value)
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
local _;
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
end
return value;
end
 
Line 3,754 ⟶ 3,913:
parameter that is missing its pipe. There are two tests made:
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by mediawikiMediaWiki)
cs1|2 shares some parameter names with xmlXML/htmlHTML atributesattributes: class=, title=, etc. To prevent false positives xmlXML/htmlHTML
tags are removed before the search.
 
Line 3,764 ⟶ 3,923:
local function missing_pipe_check (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xmlXML/htmlHTML tags because attributes: class=, title=, etc .
 
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {set_errorutilities.set_message ('missing_pipeerr_missing_pipe', parameter)});
end
end
Line 3,790 ⟶ 3,949:
if value:match ('[,;:]$') then
add_maint_catutilities.set_message ('extra_punctmaint_extra_punct'); -- has extraneous punctuation; add maint cat
end
end
Line 3,802 ⟶ 3,961:
 
local function citation(frame)
Frame = frame; -- save a copy incasein case we need to display an error message in preview mode
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata, styles;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
Line 3,823 ⟶ 3,982:
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
 
end
 
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
 
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation
year_date_check = validation.year_date_check;
reformat_dates = validation.reformat_dates;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
date_name_xlate = validation.date_name_xlate;
 
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
in_array = utilities.in_array;
substitute = utilities.substitute;
error_comment = utilities.error_comment;
set_error = utilities.set_error;
select_one = utilities.select_one;
add_maint_cat = utilities.add_maint_cat;
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
is_wikilink = utilities.is_wikilink;
make_wikilink = utilities.make_wikilink;
strip_apostrophe_markup = utilities.strip_apostrophe_markup;
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
extract_id_access_levels = identifiers.extract_id_access_levels;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
get_coins_pages = metadata.get_coins_pages;
COinS = metadata.COinS;
 
local args = {}; -- table where we store all of the template's arguments
Line 3,872 ⟶ 4,002:
 
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( pframe.args ) 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
if ('string' == type (k)) then
Line 3,880 ⟶ 4,012:
error_text = "";
if type( k ) ~= 'string' then
-- Excludeexclude empty numbered parameters
if v:match("%S+") ~= nil then
error_text, error_state = set_errorutilities.set_message ( 'text_ignorederr_text_ignored', {v}, true );
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state = set_errorutilities.set_message ( 'parameter_ignored_suggesterr_parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
Line 3,895 ⟶ 4,027:
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
capture = k:match (pattern); -- the whole match if no caputrecapture in pattern else the capture if a match
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)
error_text, error_state = set_errorutilities.set_message ('parameter_ignored_suggesterr_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = set_errorutilities.set_message ( 'parameter_ignorederr_parameter_ignored', {param}, true ); -- suggested param not supported by this template
v = ''; -- unset
end
end
end
if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion?
if suggestions.suggestions[ k:lower() ] ~= nil then
error_text, error_state = set_errorutilities.set_message ( 'parameter_ignored_suggesterr_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
else
error_text, error_state = set_errorutilities.set_message ( 'parameter_ignorederr_parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
Line 3,922 ⟶ 4,054:
args[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
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
-- 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)
Line 3,927 ⟶ 4,064:
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
end
 
if 0 ~= #empty_unknowns then -- create empty unknown error message
table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
}, true )});
end
 
for k, v in pairs( args ) do
Line 3,934 ⟶ 4,078:
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
end