Module:Citation/CS1: Difference between revisions

m
1 revision imported
m (1 revision imported)
m (1 revision imported)
 
(5 intermediate revisions by 4 users not shown)
Line 1:
require('strict');
 
local cs1 ={};
 
--[[--------------------------< 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
 
]]
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, remove_wiki_link;
 
local z ={}validation; -- tablesfunctions in Module:Citation/CS1/UtilitiesDate_validation
 
local extract_ids, extract_id_access_levels, build_id_list, is_embargoedutilities; -- functions in Module:Citation/CS1/IdentifiersUtilities
local z = {}; -- table of tables in Module:Citation/CS1/Utilities
 
local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS
 
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
 
 
--[[--------------------------< P A G E S C O P E V A R I A B L E S >--------------------------------------
 
delaredeclare variables here that have page-wide scope that are not brought in from other modules; thatare created here
other modules; that are created here and used here
 
]]
 
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_errsadded_generic_name_errs; -- booleanBoolean flag so we only emit one Vancouvergeneric name error / category and stop testing names once an error is encountered
 
local Frame; -- holds the module's frame table
local is_preview_mode; -- true when article is in preview mode; false when using 'Preview page with this template' (previewing the module)
local is_sandbox; -- true when using sandbox modules to render citation
 
 
Line 48 ⟶ 47:
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
Line 55 ⟶ 54:
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.
 
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
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
 
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Line 75 ⟶ 60:
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
 
]]
 
local function add_vanc_error (source, position)
if not added_vanc_errs then return end
added_vanc_errs = true; -- note that we've added this category
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } );
utilities.set_message ('err_vancouver', {source, position});
end
end
 
Line 89 ⟶ 74:
--[[--------------------------< 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 112 ⟶ 97:
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, TLD.cash, and .today TLDs
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
Line 134 ⟶ 119:
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 145 ⟶ 130:
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if not domain:match ('^[%a%dw]') then -- first character must be letter or digit
return false;
end
 
-- Do most common case first
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a^%a+$:') then -- threehack to detect things that look like s:Page:Title orwhere morePage: characteris hostname.hostnamenamespace orat hostname.tldWikisource
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
return true;
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
return true;
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
return true;
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
return true;
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
end
 
local patterns = { -- patterns that look like URLs
'%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$', -- one character hostname and ccTLD (2 chars)
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}
 
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 URL is a URL
end
end
 
for _, d in ipairs (cfg.single_letter_2nd_lvl_domains_t) do -- look for single letter second level domain names for these top level domains
if domain:match ('%f[%w][%w]%.' .. d) then
return true
end
end
return false; -- no matches, we don't know what this thing is
end
 
Line 173 ⟶ 165:
--[[--------------------------< 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 182 ⟶ 174:
 
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 192 ⟶ 184:
--[[--------------------------< 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 210 ⟶ 205:
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 227 ⟶ 228:
--[[--------------------------< 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 246 ⟶ 247:
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
 
 
--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
Line 254 ⟶ 256:
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.
 
]]
 
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=;
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 280 ⟶ 293:
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 291 ⟶ 304:
 
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 302 ⟶ 315:
end
return is_url (scheme, domain); -- return true if value appears to be a valid urlURL
end
 
Line 309 ⟶ 322:
 
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 322 ⟶ 335:
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 344 ⟶ 357:
]]
 
local function check_for_url (parameter_list, error_list)
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
table.insert (error_list, utilities.wrap_style ('parameter', k));
if 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 is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
end
end
Line 368 ⟶ 374:
local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then
utilities.set_message ('err_wikilink_in_url', {});
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } );
end
Line 376 ⟶ 382:
['\n'] = ' ' } );
end
 
 
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
Line 383 ⟶ 390:
]]
 
local function external_link( (URL, label, source, access)
local error_strerr_msg = ""'';
local domain;
local path;
local base_url;
 
if not utilities.is_set ( label ) then
label = URL;
if utilities.is_set ( source ) then
error_strutilities.set_message = set_error( 'bare_url_missing_titleerr_bare_url_missing_title', { utilities.wrap_style ('parameter', source) }, false, " " );
else
error( (cfg.messages["bare_url_no_origin"] ); -- programmer error; valid parameter name does not have matching meta-parameter
end
end
if not check_url ( URL ) then
error_str =utilities.set_message set_error( '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
if is_set (access) then -- access level (subscription, registration, limited)
local label_head = '';
local label_tail;
local markup = ''; -- can't start a span inside italic markup and end it outside the italic markup
 
base_url = table.concat ({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL
label = safe_for_url (label); -- replace square brackets and newlines (is this necessary? already done above?)
if label:match ("(.*)%s+(.+)('''?)$") then -- for italicized titles (cite book, etc)
label_head, label_tail, markup = label:match ("(.*)%s+(.+)('''?)$"); -- split the label at the right-most space; separate the markup
elseif label:match ("(.*)%s+(.+)$") then -- for upright titles (journal, news, magazine, etc)
label_head, label_tail = label:match ("(.*)%s+(.+)$"); -- split the label at the right-most space; no markup
elseif label:match ("(.+)('''?)$") then -- single word label with markup
label_tail, markup = label:match ("(.+)('''?)$"); -- save label text as label tail; separate the markup
else
label_tail = label;
end
 
if utilities.is_set (access) then -- access level (subscription, registration, limited)
base_url = table.concat (
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
{
'<span class="plainlinks">[', -- opening css
URL, -- the url
' ', -- the required space
label_head, -- all but the last word of the label
' <span class="nowrap">', -- nowrap css for the last word and the signal icon
label_tail, -- last (or only) word of the label inside the span
'<span style="padding-left:0.15em">', -- signal spacing css
cfg.presentation[access], -- the appropriate icon
'</span></span>', -- close signal spacing and nowrap spans
markup, -- insert italic markup if any
']</span>' -- close the plain links span
});
else
base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" }); -- no signal markup
end
 
return table.concat({ base_url, error_str });
end
 
Line 451 ⟶ 430:
parameters in the citation.
 
added_deprecated_cat is a booleanBoolean declared in page scope variables above
 
]]
Line 458 ⟶ 437:
if not added_deprecated_cat then
added_deprecated_cat = true; -- note that we've added this category
tableutilities.insert( z.message_tail, {set_message set_error( 'deprecated_paramserr_deprecated_params', {name}, true ) } ); -- add error message
end
end
 
--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
 
Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote
mark contained in a |title= or |chapter= parameter's value.
 
This function will positive kern either single or double quotes:
"'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 Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
Replaces unicode quotemarks with typewriter quote marks regardless of the need for kerning.
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=''wl_type, label, link;
 
-- TODO: move this elswhere so that all title-holding elements get these quote marks replaced?
wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
str= mw.ustring.gsub (str, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
str= mw.ustring.gsub (str, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
cap,if cap21 == str:matchwl_type ("^([\"\'])([^\'].+)");then -- match[[D]] leadingsimple doublewikilink with or singlewithout quote but not double single quotesmarks
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
if is_set (cap) then
str = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2}str);
str = utilities.substitute (cfg.presentation['kern-right'], str);
end
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = utilities.substitute (cfg.presentation['kern-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = utilities.substitute (cfg.presentation['kern-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
if is_set (cap) then
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
 
cap = 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);
end
cap = 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);
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
return str;
end
 
 
--[[--------------------------< 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 511 ⟶ 515:
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.
 
Supports |script-title= and, |script-chapter=, |script-<periodical>=
 
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
 
local function format_script_value (script_value, script_param)
local lang=''; -- initialize to empty string
local name;
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
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing title part']}); -- 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, "en"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%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_namescript', {name, lang})
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['unknown language code']}); -- unknown script-language; add error message
add_prop_cat ('script')
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['invalid language code']}); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
end
else
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing prefix']}); -- 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;
end
 
 
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
 
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
value has been wrapped in <bdi> tags.
 
]]
 
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 574 ⟶ 583:
 
local function wrap_msg (key, str, lower)
if not utilities.is_set ( str ) then
return "";
end
Line 580 ⟶ 589:
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
 
 
--[[--------------------------< FW OI RK MI AS TO _U R C HE A_ PU TR E RL _ TM IA T LK E >--------------------------------------
 
Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
label; nil else.
parameter (chapter_url_source used for error messages).
 
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
 
]]
 
local function wikisource_url_make (str)
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local chapter_errorwl_type, =D, ''L;
local ws_url, ws_label;
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
if not is_set (chapter) then
 
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 Wikisource URL
wikisource_prefix, -- prefix
str, -- article title
});
ws_label = str; -- label for the URL
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 Wikisource URL
wikisource_prefix, -- prefix
str, -- article title
});
ws_label = str; -- label for the URL
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 Wikisource URL
wikisource_prefix, -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
 
if ws_url then
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker
end
 
return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil
end
 
 
--[[----------------< F O R M A T _ P E R I O D I C A L >-----------------------
 
Format the three periodical parameters: |script-<periodical>=, |<periodical>=,
and |trans-<periodical>= into a single Periodical meta-parameter.
 
]]
 
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
 
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 attribute, 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;
utilities.set_message ('err_trans_missing_title', {'periodical'});
end
end
 
return periodical;
end
 
 
--[[------------------< 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 chapter meta- parameter (chapter_url_source used
for error messages).
 
]]
 
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access)
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link
if ws_url then
ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters
chapter = ws_label;
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, scriptchapterscript_chapter, script_chapter_source) ; -- <bdi> tags, lang atributeattribute, categorization, etc.; must be done after title is wrapped
 
if utilities.is_set (transchapterchapter_url) then
chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
transchapter = wrap_style ('trans-quoted-title', transchapter);
if elseif is_set (chapter)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 = chapter .. ' ' .. transchapter;
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end
 
if utilities.is_set (chapterurltrans_chapter) then
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter);
chapter = external_link (chapterurl, chapter, chapter_url_source, nil); -- adds bare_url_missing_title error if appropriate
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>
utilities.set_message ('err_trans_missing_title', {chapter_source});
end
end
 
return chapter .. chapter_error;
end
 
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
--[[----------------< 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 nonprintable or invisible characters. The search stops at the
first match.
 
This function searches a parameter's value for non-printable or invisible characters.
This function will detect the visible replacement character when it is part of the wikisource.
The search stops at the first match.
 
This function will detect the visible replacement character when it is part of the Wikisource.
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)
and identifies them with a slightly different error message. See also coins_cleanup().
 
Detects but ignores thenowiki characterand patternmath thatstripmarkers. results fromAlso thedetects transclusionother ofnamed {{'}} templates.stripmarkers
(gallery, math, pre, ref) and identifies them with a slightly different error message.
See also coins_cleanup().
 
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
Unicode group, or the stripmarker that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
for multi-byte characters, the position of its first byte) in the parameter value.
parameter value.
 
]]
Line 645 ⟶ 748:
local function has_invisible_chars (param, v)
local position = ''; -- position of invisible char or starting position of stripmarker
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 stripmarker; -- boolean set true when a stripmarker is found
local i=1;
 
local stripmarker, apostrophe;
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
if capture == string.match (v, '[%w%p ]*');then -- Testif forsame values thatthere are simpleno ASCII text and bypass other tests ifUnicode truecharacters
if capture == v then -- if same there are no unicode characters
return;
end
 
whilefor _, invisible_char in ipairs (cfg.invisible_chars[i]) do
local charchar_name =cfg.invisible_chars[i] invisible_char[1]; -- the character or group name
local pattern =cfg.invisible_chars[i] invisible_char[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 (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
position = nil; -- unset position
elseif cfg.emoji_t[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
position = nil; -- unset position
end
end
if position then
if 'nowiki' == capture or 'math' == capture then or -- nowiki, and math stripmarkerstripmarkers (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
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
elseif true == stripmarker and cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
position = nil; -- unset
else
local err_msg;
if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
if capture then
err_msg = capture .. ' ' .. charchar_name;
else
err_msg = charchar_name .. ' ' .. 'character';
end
 
tableutilities.insert(set_message z.message_tail, { set_error( '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
 
 
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
 
Argument wrapper. This function provides support for argument mapping defined in the configuration file so that
in the configuration file so that multiple names can be transparently aliased to single internal variable.
single internal variable.
 
]]
 
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];
end
Line 707 ⟶ 817:
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
end
elseif list ~= nil then
Line 716 ⟶ 826:
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
end
-- Empty strings, not nil;
if v == nil then
v = cfg.defaults[k] or '';
origin[k] = '';
end
Line 731 ⟶ 841:
end
 
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
 
--[[--------------------------< N O W R A P _ D A T E >-------------------------
Looks for a parameter's name in one of several whitelists.
 
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
Parameters in the whitelist can have three values:
When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
true - active, supported parameters
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
false - deprecated, supported parameters
nil - unsupported parameters
]]
 
--local function validate( name )
local function validate( name, cite_class )
local name = tostring( name );
local state;
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
if 'arxiv' == cite_class then -- basic parameters unique to these templates
state = whitelist.arxiv_basic_arguments[name];
end
if 'biorxiv' == cite_class then
state = whitelist.biorxiv_basic_arguments[name];
end
if 'citeseerx' == cite_class then
state = whitelist.citeseerx_basic_arguments[name];
end
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- limited enumerated parameters list
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#)
state = whitelist.limited_numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
state = whitelist.basic_arguments[ name ]; -- all other templates; all normal parameters allowed
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- all enumerated parameters allowed
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- not supported because not found or name is set to nil
end
 
 
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
 
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
 
DOES NOT yet support MMMM YYYY or any of the date ranges.
Line 813 ⟶ 853:
 
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 827 ⟶ 867:
end
 
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
 
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------
This function sets default title types (equivalent to the citation including |type=<default value>) for those templates that have defaults.
 
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
This function sets default title types (equivalent to the citation including
|type=<default value>) for those templates that have defaults. Also handles the
special case where it is desirable to omit the title type from the rendered citation
(|type=none).
 
]]
 
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
end
return title_type; -- if |type= has been set to any other value use that value
Line 846 ⟶ 889:
 
 
--[[--------------------------< HS YA P HF E N _ TJ O _I D A S HN >--------------------------------------------------
 
Converts a hyphen to a dash
 
]]
 
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
return str;
end
return str:gsub( '-', '–' );
end
 
 
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
 
Joins a sequence of strings together while checking for duplicate separation characters.
Line 867 ⟶ 896:
 
local function safe_join( tbl, duplicate_char )
local f = {}; -- create a function table appropriate to type of 'duplicate character'
--[[
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
Note: we use string functions here, rather than ustring functions.
f.gsub = string.gsub
f.match = string.match
This has considerably faster performance and should work correctly as
f.sub = string.sub
long as the duplicate_char is strict ASCII. The strings
else -- for multi-byte characters use the ustring library functions
in tbl may be ASCII or UTF8.
f.gsub = mw.ustring.gsub
]]
f.match = mw.ustring.match
f.sub = mw.ustring.sub
end
 
local str = ''; -- the output string
local comp = ''; -- what does 'comp' mean?
Line 885 ⟶ 917:
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 comp:f.sub(comp, 1, 1) == duplicate_char then -- is first charactiercharacter same as duplicate_char? why test first character?
-- Because individual string segments often (always?) begin with terminal punct for ththe
-- preceding segment: 'First element' .. 'sepc next element' .. etc.?
trim = false;
end_chr = str: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 = str:f.sub(str, 1, -2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkupwiki-markup
if str:f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc''
str = str:f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif str: 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 str: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 str: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 str: f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif str: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 str:f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = 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 dup2:f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows htmlHTML markup
else
value = value:f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
str = str .. value; -- add it to the output string
end
end
return str;
end
 
 
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
 
returns true isif suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed1–9.
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 952 ⟶ 987:
end
 
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
 
--[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
For Vancouver Style, 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.
For Vancouver style, author/editor names are supposed to be rendered in Latin
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
(read ASCII) characters. When a name uses characters that contain diacritical
These things are not currently possible in this module so are left to the editor to do.
marks, those characters are to be 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. The module doesn't do this
so editors may/must.
 
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
in the four Unicode Latin character sets
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
Line 965 ⟶ 1,004:
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
 
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
 
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
or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then
was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.
was written outside of the code editor and pasted here because the code editor
The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary
gets confused between character insertion point and cursor position. The test has
to use an external editor to maintain this code.
been rewritten to use decimal character escape sequence for the individual bytes
of the Unicode characters so that it is not necessary to use an external editor
to maintain this code.
 
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
Line 981 ⟶ 1,024:
]]
 
local function is_good_vanc_name (last, first, suffix, position)
if not suffix then
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
 
first = first:match ('(.-)[,%s]+'); -- get name/initials
if is_set (suffix) then
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
end
end
if utilities.is_set (suffix) then
if not is_suffix (suffix) then
add_vanc_error ('cfg.err_msg_supl.suffix', position);
return false; -- not a name with an appropriate suffix
end
Line 992 ⟶ 1,039:
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
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 characterchar'], position);
return false; -- not a string of latinLatin characters; Vancouver requires Romanization
end;
return true;
end
 
 
--[[--------------------------< 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/.
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/.
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 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 unicode Latin characters accepted by is_good_vanc_name ().
Unicode Latin characters accepted by is_good_vanc_name ().
 
]]
 
local function reduce_to_initials(first, position)
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
 
if not name then -- if not initials and a suffix
name = mw.ustring.match(first, "^(%u+)$"); -- is it just intialsinitials?
end
 
Line 1,024 ⟶ 1,076:
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error ('cfg.err_msg_supl.suffix', position); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
Line 1,032 ⟶ 1,084:
end
end -- if here then name has 3 or more uppercase letters so treat them as a word
 
 
local initials, names = {}, {}; -- tables to hold name parts and initials
Line 1,048 ⟶ 1,099:
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
end
Line 1,056 ⟶ 1,107:
end
 
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
 
--[[--------------------------< I N T E R W I K I _ P R E F I X E N _ G E T >----------------------------------
Formats a list of people (e.g. authors / editors)
 
extract interwiki prefixen from <value>. Returns two one or two values:
false – no prefixen
nil – prefix exists but not recognized
project prefix, language prefix – when value has either of:
:<project>:<language>:<article>
:<language>:<project>:<article>
project prefix, nil – when <value> has only a known single-letter prefix
nil, language prefix – when <value> has only a known language prefix
 
accepts single-letter project prefixen: 'd' (wikidata), 's' (wikisource), and 'w' (wikipedia) prefixes; at this
writing, the other single-letter prefixen (b (wikibook), c (commons), m (meta), n (wikinews), q (wikiquote), and
v (wikiversity)) are not supported.
 
]]
 
local function interwiki_prefixen_get (value, is_link)
if not value:find (':%l+:') then -- if no prefix
return false; -- abandon; boolean here to distinguish from nil fail returns later
end
 
local prefix_patterns_linked_t = { -- sequence of valid interwiki and inter project prefixen
'^%[%[:([dsw]):(%l%l+):', -- wikilinked; project and language prefixes
'^%[%[:(%l%l+):([dsw]):', -- wikilinked; language and project prefixes
'^%[%[:([dsw]):', -- wikilinked; project prefix
'^%[%[:(%l%l+):', -- wikilinked; language prefix
}
local prefix_patterns_unlinked_t = { -- sequence of valid interwiki and inter project prefixen
'^:([dsw]):(%l%l+):', -- project and language prefixes
'^:(%l%l+):([dsw]):', -- language and project prefixes
'^:([dsw]):', -- project prefix
'^:(%l%l+):', -- language prefix
}
local cap1, cap2;
for _, pattern in ipairs ((is_link and prefix_patterns_linked_t) or prefix_patterns_unlinked_t) do
cap1, cap2 = value:match (pattern);
if cap1 then
break; -- found a match so stop looking
end
end
if cap1 and cap2 then -- when both then :project:language: or :language:project: (both forms allowed)
if 1 == #cap1 then -- length == 1 then :project:language:
if cfg.inter_wiki_map[cap2] then -- is language prefix in the interwiki map?
return cap1, cap2; -- return interwiki project and interwiki language
end
else -- here when :language:project:
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map?
return cap2, cap1; -- return interwiki project and interwiki language
end
end
return nil; -- unknown interwiki language
elseif not (cap1 or cap2) then -- both are nil?
return nil; -- we got something that looks like a project prefix but isn't; return fail
elseif 1 == #cap1 then -- here when one capture
return cap1, nil; -- length is 1 so return project, nil language
else -- here when one capture and its length it more than 1
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map?
return nil, cap1; -- return nil project, language
end
end
end
 
 
--[[--------------------------< L I S T _ P E O P L E >--------------------------
 
Formats a list of people (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 lastauthorampname_list = control.lastauthoramp{};
local text = {}
 
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
elseif 'mla' == control.mode then
sep = ','; -- name-list separator between authors is a comma
namesep = ', ' -- last/first separator is <comma><space>
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 'mla'("vanc" == control.modeformat) then -- if Vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if i == 1 then -- for mla
if not person.corporate and is_good_vanc_name (one, first, nil, i) then -- and name is all Latin characters; corporate authors not tested
one = one .. namesep .. first; -- first name last, first
first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials
else -- all other names
one = first .. ' ' .. one; -- first last
end
else
if ( "vanc" == format ) then -- if vancouver 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
one = one .. namesep .. first;
end
one = one .. namesep .. first;
end
end
if is_set(person.link) and person.link ~= control.page_name then
if utilities.is_set (person.link) then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
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)
local proj, tag = interwiki_prefixen_get (one, true); -- get the interwiki prefixen if present
 
if 'w' == proj and ('Wikipedia' == mw.site.namespaces.Project['name']) then
proj = nil; -- for stuff like :w:de:<article>, :w is unnecessary TODO: maint cat?
end
if proj then
proj = ({['d'] = 'Wikidata', ['s'] = 'Wikisource', ['w'] = 'Wikipedia'})[proj]; -- :w (wikipedia) for linking from a non-wikipedia project
if proj then
one = one .. utilities.wrap_style ('interproj', proj); -- add resized leading space, brackets, static text, language name
tag = nil; -- unset; don't do both project and language
end
end
if tag == cfg.this_wiki_code then
tag = nil; -- stuff like :en:<article> at en.wiki is pointless TODO: maint cat?
end
if tag then
local lang = cfg.lang_code_remap[tag] or cfg.mw_languages_by_tag_t[tag];
if lang then -- error messaging done in extract_names() where we know parameter names
one = one .. utilities.wrap_style ('interwiki', lang); -- add resized leading space, brackets, static text, language name
end
end
 
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 'mlaamp' == control.modeformat then
textname_list[#textname_list-2] = ", and& "; -- replace last separator with ', and 'ampersand text
elseif 'and' == format then
else
if 2 == count then
text[#text-2] = " & "; -- replace last separator with ampersand text
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
 
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
 
--[[--------------------< M A K E _ C I T E R E F _ I D >-----------------------
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
 
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
returns an empty string.
 
namelist is one of the contributor-, author-, or editor-name lists chosen in that
order. year is Year or anchor_year.
 
]]
 
local function anchor_id (namelist, year)
local function make_citeref_id (namelist, year)
local names={}; -- a table for the one to four names and year
forlocal i,v in ipairs (namelist) do names={}; -- loopa throughtable for the list and take upone to thefour firstnames fourand last namesyear
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
names[i] = v.last
names[i] = v.last
if i == 4 then break end -- if four then done
if i == 4 then break end -- if four then done
end
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
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end
 
 
--[[--------------------------< NC AI MT E _ HC L A S _S E_A T T R I B U T E _M A LK E >----------------------------------------------------
 
construct <cite> tag class attribute for this citation.
Evaluates the content of author and editor name parameters 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.
 
<cite_class> – config.CitationClass from calling template
This function never sets the flag to false but returns it's previous state because it may have been set by
<mode> – value from |mode= parameter
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
 
]]
 
local function name_has_etalcite_class_attribute_make (namecite_class, etal, nocatmode)
local class_t = {};
table.insert (class_t, 'citation'); -- required for blue highlight
if 'citation' ~= cite_class then
table.insert (class_t, cite_class); -- identify this template for user css
table.insert (class_t, utilities.is_set (mode) and mode or 'cs1'); -- identify the citation style for user css or javascript
else
table.insert (class_t, utilities.is_set (mode) and mode or 'cs2'); -- identify the citation style for user css or javascript
end
for _, prop_key in ipairs (z.prop_keys_t) do
table.insert (class_t, prop_key); -- identify various properties for user css or javascript
end
 
ifreturn is_settable.concat (nameclass_t, ' ') then ; -- namemake cana bebig nilstring inand which case just returndone
end
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
 
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
 
--[[---------------------< 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.
 
This function never sets the flag to false but returns its previous state because
it may have been set by previous passes through this function or by the associated
|display-<names>=etal parameter
 
]]
 
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
iffor name:match_, pattern in ipairs (etal_patternpatterns) then do -- variantsloop through all onof etthe al.patterns
name =if name:gsubmatch (etal_pattern, ''pattern); then -- if this 'et al' pattern is found, removein name
name = name:gsub (pattern, ''); -- remove the offending text
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if etal not nocat= thentrue; -- noset categorizationflag for(may have been set previously here or by |vauthorsdisplay-<names>=etal)
add_maint_catif ('etal');not nocat then -- andno add a category if notcategorization alreadyfor added|vauthors=
utilities.set_message ('err_etal', {param}); -- and set an error if not added
end
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
 
return name, etal; --
return name, etal;
end
 
 
--[[--------------------------< N A M E _ H AI S _ EN D _U M AE R K UI PC >------------------------------------------
 
Add maint cat when name parameter value does not contain letters. Does not catch
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
current version of this test but |first=(1888) is caught.
adds the editor markup maintenance category.
 
returns nothing
 
]]
 
local function name_has_ed_markupname_is_numeric (name, list_name)
if utilities.is_set (name) then
local _, pattern;
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
local patterns = { -- these patterns match annotations at end of name
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'
end
'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)
end
'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'
end
'[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive
 
 
--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
 
Evaluates the content of last/surname (authors etc.) parameters for multiple names.
Multiple names are indicated if there is more than one comma or any "unescaped"
semicolons. Escaped semicolons are ones used as part of selected HTML entities.
If the condition is met, the function adds the multiple name maintenance category.
 
returns nothing
 
]]
 
local function name_has_mult_names (name, list_name)
local _, commas, semicolons, nbsps;
if utilities.is_set (name) then
_, commas = name:gsub (',', ''); -- count the number of commas
_, semicolons = name:gsub (';', ''); -- count the number of semicolons
-- nbsps probably should be its own separate count rather than merged in
-- some way with semicolons because Lua patterns do not support the
-- grouping operator that regex does, which means there is no way to add
-- more entities to escape except by adding more counts with the new
-- entities
_, nbsps = name:gsub ('&nbsp;',''); -- count nbsps
-- There is exactly 1 semicolon per &nbsp; entity, so subtract nbsps
-- these patterns match annotations at beginning of name
-- from semicolons to 'escape' them. If additional entities are added,
'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.'
-- they also can be subtracted.
'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'
if 1 < commas or 0 < (semicolons - nbsps) then
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's'
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets
end
end
end
 
 
--[=[-------------------------< I S _ G E N E R I C >----------------------------------------------------------
 
Compares values assigned to various parameters according to the string provided as <item> in the function call.
<item> can have on of two values:
'generic_names' – for name-holding parameters: |last=, |first=, |editor-last=, etc
'generic_titles' – for |title=
 
There are two types of generic tests. The 'accept' tests look for a pattern that should not be rejected by the
'reject' test. For example,
|author=[[John Smith (author)|Smith, John]]
would be rejected by the 'author' reject test. But piped wikilinks with 'author' disambiguation should not be
rejected so the 'accept' test prevents that from happening. Accept tests are always performed before reject
tests.
 
Each of the 'accept' and 'reject' sequence tables hold tables for en.wiki (['en']) and local.wiki (['local'])
that each can hold a test sequence table The sequence table holds, at index [1], a test pattern, and, at index
[2], a boolean control value. The control value 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.
 
Returns
true when a reject test finds the pattern or string
false when an accept test finds the pattern or string
nil else
 
]=]
 
local function is_generic (item, value, wiki)
local test_val;
local str_lower = { -- use string.lower() for en.wiki (['en']) and use mw.ustring.lower() or local.wiki (['local'])
['en'] = string.lower,
['local'] = mw.ustring.lower,
}
local str_find = { -- use string.find() for en.wiki (['en']) and use mw.ustring.find() or local.wiki (['local'])
['en'] = string.find,
['local'] = mw.ustring.find,
}
 
local function test (val, test_t, wiki) -- local function to do the testing; <wiki> selects lower() and find() functions
if is_set (name) then
val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value
for _, pattern in ipairs (patterns) do -- spin through patterns table and
return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched
if name:match (pattern) then
end
add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
local test_types_t = {'accept', 'reject'}; -- test accept patterns first, then reject patterns
local wikis_t = {'en', 'local'}; -- do tests for each of these keys; en.wiki first, local.wiki second
 
for _, test_type in ipairs (test_types_t) do -- for each test type
for _, generic_value in pairs (cfg.special_case_translation[item][test_type]) do -- spin through the list of generic value fragments to accept or reject
for _, wiki in ipairs (wikis_t) do
if generic_value[wiki] then
if test (value, generic_value[wiki], wiki) then -- go do the test
return ('reject' == test_type); -- param value rejected, return true; false else
end
end
end
end
end
return name; -- and done
end
 
 
--[[--------------------------< N A M E _ H AI S _ MG U L T _E N AE MR EI SC >------------------------------------------------
 
calls is_generic() to determine if <name> is a 'generic name' listed in cfg.generic_names; <name_alias> is the
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are
parameter name used in error messaging
indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name
(author or editor) maintenance category.
 
]]
 
local function name_has_mult_namesname_is_generic (name, list_namename_alias)
if not added_generic_name_errs and is_generic ('generic_names', name) then
local count, _;
utilities.set_message ('err_generic_name', name_alias); -- set an error message
if is_set (name) then
added_generic_name_errs = true;
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
end
end
return name; -- and done
end
 
 
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
 
This function calls various name checking functions used to validate the content of the various name-holding
This function calls various name checking functions used to validate the content of the various name-holding parameters.
parameters.
 
]]
 
local function name_checks (last, first, list_name, last_alias, first_alias)
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
 
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
if not accept_name then -- <last> not wrapped in accept-as-written markup
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
name_is_generic (last, last_alias); -- check for names found in the generic names list
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
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
name_is_generic (first, first_alias); -- check for names found in the generic names list
end
local wl_type, D = utilities.is_wikilink (first);
if 0 ~= wl_type then
first = D;
utilities.set_message ('err_bad_paramlink', first_alias);
end
end
 
return last, first; -- done
end
 
 
--[[----------------------< E X T R A C T _ N A M E S >-------------------------
 
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments
 
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
(or their aliases), and their matching link and mask parameters. Stops searching
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't
when both |lastn= and |firstn= are not found in args after two sequential attempts:
find |last4= and |last5= then the search is done.
found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the
search is done.
 
This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=
|lastn=. When there are 'holes' in the list of last names, |last1= and |last3=
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
are present but |last2= is missing, an error message is emitted. |lastn= is not
required to have a matching |firstn=.
 
When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned
is stripped from the parameter and a flag (etal) returned that will cause list_people()
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the
to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps
template's metadata. When this occurs, the page is added to a maintenance category.
'et al.' out of the template's metadata. When this occurs, an error is emitted.
 
]]
 
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
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
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 );
 
if last then -- error check |lastn= alias for unknown interwiki link prefix; done here because this is where we have the parameter name
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
local project, language = interwiki_prefixen_get (last, true); -- true because we expect interwiki links in |lastn= to be wikilinked
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
if nil == project and nil == language then -- when both are nil
last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks
utilities.set_message ('err_bad_paramlink', last_alias); -- not known, emit an error message -- TODO: err_bad_interwiki?
last = utilities.remove_wiki_link (last); -- remove wikilink markup; show display value only
end
end
if link then -- error check |linkn= alias for unknown interwiki link prefix
local project, language = interwiki_prefixen_get (link, false); -- false because wiki links in |author-linkn= is an error
if nil == project and nil == language then -- when both are nil
utilities.set_message ('err_bad_paramlink', link_alias); -- not known, emit an error message -- TODO: err_bad_interwiki?
link = nil; -- unset so we don't link
link_alias = nil;
end
end
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, last_alias, first_alias); -- multiple names, extraneous annotation, etc. checks
 
if first and not last then -- if there is a firstn without a matching lastn
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
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
}); -- 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 1,335 ⟶ 1,618:
end
else -- we have last with or without a first
local result;
link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
 
if first then
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only)
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-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
tableutilities.insert(set_message z.message_tail, { set_error( 'missing_nameerr_missing_name', {err_msg_list_namelist_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 1,347 ⟶ 1,635:
end
return names, etal; -- all done, return our list of names and the etal flag
end
 
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
 
--[[--------------------------< N A M E _ T A G _ G E T >------------------------------------------------------
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
 
attempt to decode |language=<lang_param> and return language name and matching tag; nil else.
Returns the language name and associated two- or three-character code. Because case of the source may be incorrect
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we
return the original language name string.
 
This function looks for:
mw.language.fetchLanguageNames(<local wiki language>, 'all') return a list of languages that in some cases may include
<lang_param> as a tag in cfg.lang_code_remap{}
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
<lang_param> as a name in cfg.lang_name_remap{}
code 'cbk' or name 'Chavacano'.
<lang_param> as a name in cfg.mw_languages_by_name_t
<lang_param> as a tag in cfg.mw_languages_by_tag_t
when those fail, presume that <lang_param> is an IETF-like tag that MediaWiki does not recognize. Strip all
script, region, variant, whatever subtags from <lang_param> to leave just a two or three character language tag
and look for the new <lang_param> in cfg.mw_languages_by_tag_t{}
 
on success, returns name (in properly capitalized form) and matching tag (in lowercase); on failure returns nil
Names but that are included in the list will be found if that name is provided in the |language= parameter. For example,
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found
and the associated code is not two or three characters, this function returns only the Wikimedia language name.
 
Adapted from code taken from Module:Check ISO 639-1.
 
]]
 
local function get_iso639_codename_tag_get (lang, this_wiki_codelang_param)
local lang_param_lc = mw.ustring.lower (lang_param); -- use lowercase as an index into the various tables
if 'bangla' == lang:lower() then -- special case related to Wikimedia remap of code 'bn' at mw:Extension:CLDR
local name;
return 'Bengali', 'bn'; -- make sure rendered version is properly capitalized
local tag;
 
name = cfg.lang_code_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name
if name then -- when <name>, <lang_param> is a tag for a remapped language name
return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc>
end
 
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
name = cfg.lang_code_remap[tag]; -- attempt to get remapped language name with language subtag only
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
localif langlcname = mw.ustring.lower(lang);then -- lowerwhen case<name>, version<tag> is a tag for comparisonsa remapped language name
return name, tag; -- so return <name> from remap and <tag>
end
 
if cfg.lang_name_remap[lang_param_lc] then -- not a tag, assume <lang_param_lc> is a name; attempt to get remapped language tag
return cfg.lang_name_remap[lang_param_lc][1], cfg.lang_name_remap[lang_param_lc][2]; -- for this <lang_param_lc>, return a (possibly) new name and appropriate tag
end
 
tag = cfg.mw_languages_by_name_t[lang_param_lc]; -- assume that <lang_param_lc> is a language name; attempt to get its matching tag
if tag then
for code, name in pairs(languages) do -- scan the list to see if we can find our language
return cfg.mw_languages_by_tag_t[tag], tag; -- <lang_param_lc> is a name so return the name from the table and <tag>
if langlc == mw.ustring.lower(name) then
end
if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported
 
return name; -- so return the name but not the code
name = cfg.mw_languages_by_tag_t[lang_param_lc]; -- assume that <lang_param_lc> is a tag; attempt to get its matching language name
end
return name, code; -- found it, return name to ensure proper capitalization and the the code
if name then
return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name>
end
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- is <lang_param_lc> an IETF-like tag that MediaWiki doesn't recognize? <tag> gets the language subtag; nil else
 
if tag then
name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag>
if name then
return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag
end
end
return lang; -- not valid language; return language in original case and nil for the code
end
 
 
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
 
Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki,
is recognized by MediaWiki, use the returned name; if not, then use the value that was provided with the language parameter.
was provided with the language parameter.
 
When |language= contains a recognized language (either code or name), the page is assigned to the category for
assigned to the category for that code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assigned
For valid three-character code languages, the page is assigned to the single category
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources.
for '639-2' codes: Category:CS1 ISO 639-2 language sources.
 
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character
not recognize three-character equivalents of two-character codes: code 'ar' is recognized bit code 'ara' is not.
recognized but code 'ara' is not.
 
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are
where the language names or codes are separated from each other by commas. with
optional space characters.
 
]]
 
local function language_parameter (lang)
local codetag; -- thesome two-form orof threeIETF-characterlike language codetag; language subtag with optional region, sript, vatiant, etc subtags
local lang_subtag; -- ve populates |language= with mostly unecessary region subtags the MediaWiki does not recognize; this is the base language subtag
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_tablenames_t = {}; -- table made from the value assigned to |language=
 
local this_wikithis_wiki_name = mw.getContentLanguagelanguage.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get athis wiki's language object for this wikiname
local this_wiki_code = this_wiki:getCode() -- get this wiki's language code
local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name
 
names_tablenames_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
 
for _, lang in ipairs (names_tablenames_t) do -- reuse lang here because we don't yet know if lang is a language name or a language tag
name, tag = name_tag_get (lang); -- attempt to get name/tag pair for <lang>; <name> has proper capitalization; <tag> is lowercase
 
if utilities.is_set (tag) then
if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag?
langlang_subtag = langtag:matchgsub ('^(%a%a%a?)%-.*', '%1') ; -- keepfor onlycategorization, 639-1strip codeany portionIETF-like totags lang;from TODO:language do something with 3166 alpha 2 country code?tag
 
end
if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
if 2 == lang_subtag:len() then -- and is a two-character tag
name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
end
else -- or is a recognized language (but has a three-character tag)
utilities.add_prop_cat ('foreign-lang-source-2', {lang_subtag}, lang_subtag); -- categorize it differently TODO: support multiple three-character tag categories per cs1|2 template?
if is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if is_set (code) then -- only 2- or 3-character codes
if 'bn' == code then name = 'Bengali' end; -- override wikimedia when code is 'bn'
if 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
add_prop_cat ('foreign_lang_source', {name, code}) -- categorize it
else -- or is a recognized language (but has a three-character code)
add_prop_cat ('foreign_lang_source_2', {code}) -- categorize it differently TODO: support mutliple 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, lang_subtag}); -- categorize it
end
else
add_maint_catname ('unknown_lang')= lang; -- addreturn whatever <lang> mainthas categoryso ifthat notwe alreadyshow addedsomething
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added
end
Line 1,452 ⟶ 1,755:
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 (1 == #language_list) and (lang_subtag == cfg.this_wiki_code) then -- when only one language, find lang name in this wiki lang name; for |language=en-us, 'English' in 'American English'
if 2 >= code then
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
elseif 2 < code then
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
if this_wiki_name == name then
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
end
Line 1,469 ⟶ 1,766:
end
 
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
 
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
Set style settings for CS1 citation templates. Returns separator and postscript settings
 
Gets the default CS style configuration for the given mode.
Returns default separator and either postscript as passed in or the default.
In CS1, the default postscript and separator are '.'.
In CS2, the default postscript is the empty string and the default separator is ','.
 
]]
 
local function set_cs1_styleset_cs_style (pspostscript, mode)
if utilities.is_set(postscript) then
if not is_set (ps) then -- unless explicitely set to something
-- emit a maintenance message if user postscript is the default cs1 postscript
ps = '.'; -- terminate the rendered citation with a period
-- we catch the opposite case for cs2 in set_style
if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then
utilities.set_message ('maint_postscript');
end
else
postscript = cfg.presentation['ps_' .. mode];
end
return cfg.presentation['sep_' .. mode], postscript;
return '.', ps; -- separator is a full stop
end
 
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
 
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
 
]]
 
local function set_cs2_style (ps, ref)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = ''; -- make sure it isn't nil
end
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
end
return ',', ps, ref; -- separator is a comma
end
 
--[[--------------------------< GS E T _ S E T TY I N G S _ F R O M _ C I TL E _ C L A S S >-----------------------------
 
Sets the separator and postscript styles. Checks the |mode= first and the
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish
#invoke CitationClass second. Removes the postscript if postscript == none.
rendered style.
 
]]
 
local function get_settings_from_cite_classset_style (psmode, refpostscript, cite_class)
local sep;
if 'cs2' == mode then
if (cite_class == "citation") then -- for citation templates (CS2)
sep, ps, refpostscript = set_cs2_styleset_cs_style (pspostscript, ref'cs2');
elseif 'cs1' == mode then
else -- not a citation template so CS1
sep, pspostscript = set_cs1_styleset_cs_style (pspostscript, 'cs1');
elseif 'citation' == cite_class then
sep, postscript = set_cs_style (postscript, 'cs2');
else
sep, postscript = set_cs_style (postscript, 'cs1');
end
 
if cfg.keywords_xlate[postscript:lower()] == 'none' then
return sep, ps, ref -- return them all
-- emit a maintenance message if user postscript is the default cs2 postscript
end
-- we catch the opposite case for cs1 in set_cs_style
 
if 'cs2' == mode or 'citation' == cite_class then
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
utilities.set_message ('maint_postscript');
 
end
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
postscript = '';
config.CitationClass from the template's #invoke: to establish style.
 
]]
 
local function set_style (mode, ps, ref, cite_class)
local sep;
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style
sep, ps, ref = set_cs2_style (ps, ref);
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
sep, ps = set_cs1_style (ps);
elseif 'mla' == mode then -- if this template is to be rendered in mla style use cs1 for bot cs1 & cs2 templates
sep, ps = set_cs1_style (ps);
else -- anything but cs1 or cs2
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
if 'none' == ps:lower() then -- if assigned value is 'none' then
ps = ''; -- set to empty string
end
return sep, ps, refpostscript
end
 
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
 
--[=[-------------------------< I S _ P D F >-----------------------------------
Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
applying the pdf icon to external links.
 
returns trueDetermines if a URL has the file extension that is one of the recognizedPDF extension, elsefile falseextensions
used by [[MediaWiki:Common.css]] when applying the PDF icon to external links.
 
returns true if file extension is one of the recognized extensions, else false
 
]=]
 
local function is_pdf (url)
return url:match ('%.pdf[%?#]?$') or url:match ('%.PDF[%?#]?$'); or
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end
 
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
 
--[[--------------------------< S T Y L E _ F O R M A T >-----------------------
Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does
 
not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
if the format parameter does not have a matching URL parameter. If the format parameter
is not set and the URL contains a file extension that is recognized as a PDF document
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
the appropriate styling.
 
Line 1,564 ⟶ 1,849:
 
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, parenthasesparentheses, resize
if not utilities.is_set (url) then
format = format .utilities.set_message set_error( '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 1,577 ⟶ 1,862:
end
 
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
 
--[[---------------------< 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 boolean flag
to indicate when et al. should be appended to the name list.
 
Returns a number that defines the number of names displayed for author and editor
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and
thename previouslists stateand ofa the 'etal'Boolean flag (falseto byindicate defaultwhen butet mayal. haveshould beenbe setappended to true if the name list contains.
some variant of the text 'et al.').
 
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number thatgreater isthan oneor greaterequal thanto thezero,
numberreturn ofthe authorsnumber inand the listprevious andstate setof the 'etal' flag true. This will cause the list_people()false toby display all ofdefault
thebut namesmay inhave been set to true if the name list followedcontains bysome variant of the text 'et al.').
 
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number
that is one greater than the number of authors in the list and set the 'etal' flag true.
This will cause the list_people() to display all of the names in the name list followed by 'et al.'
 
In all other cases, returns nil and the previous state of the 'etal' flag.
Line 1,600 ⟶ 1,886:
]]
 
local function get_display_authors_editorsget_display_names (max, count, list_name, etal, param)
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 1,608 ⟶ 1,894:
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
utilities.set_message ('err_disp_name', {param, max}); -- add error message
add_maint_cat ('disp_auth_ed', cfg.special_case_translation [list_name]);
max = nil;
end
else -- not a valid keyword or number
tableutilities.insert( z.message_tail, {set_message set_error( 'invalid_param_valerr_disp_name', {'display-' .. list_nameparam, max}, true ) } ); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
Line 1,619 ⟶ 1,906:
end
 
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
 
--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
abbreviation in the first characters of the parameter content.
 
Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
some form of p. or pp. abbreviation in the first characters of the parameter content.
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
 
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value:
good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px
where x and X are letters and # is a digit
bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG
 
]]
 
local function extra_text_in_page_check (pageval, name)
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
-- local good_pattern = '^P[^%.P%l]';
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
if val:match (pattern) then -- when a match, error so
-- local bad_pattern = '^[Pp][Pp]';
utilities.set_message ('err_extra_text_pages', name); -- add error message
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
return; -- and done
end
end
end
end
 
 
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
add_maint_cat ('extra_text');
 
Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
 
For |volume=:
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
are allowed.
 
For |issue=:
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
parameter content (all case insensitive).
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
<val> is |volume= or |issue= parameter value
<name> is |volume= or |issue= parameter name for error message
<selector> is 'v' for |volume=, 'i' for |issue=
 
sets error message on failure; returns nothing
 
]]
 
local function extra_text_in_vol_iss_check (val, name, selector)
if not utilities.is_set (val) then
return;
end
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns;
 
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
val = val:lower(); -- force parameter value to lower case
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
if val:match (pattern) then -- when a match, error so
utilities.set_message (handler, name); -- add error message
return; -- and done
end
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
end
 
--[[--------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
 
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
split apart a |vautthors= 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 parnetheses were included in the
rendered citation and in the metadata.
 
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
|vauthors=Jones AB, White EB, ((Black, Brown, and Co.))
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
rendered citation and in the metadata. Individual author names may be wikilinked
 
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
This code is experimental and may not be retained.
 
]=]
 
local function get_v_name_table (vparam, output_table)
local function get_v_name_table (vparam, output_table, output_link_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local wl_type, label, link; -- wl_type not used here; just a placeholder
local i = 1;
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, name_table[i]); -- add this name
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
end
i = i + 1;
end
return output_table;
end
 
 
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
Line 1,688 ⟶ 2,024:
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 1,699 ⟶ 2,035:
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local v_link_table = {}; -- when name is wikilinked, targets go in this table
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
Line 1,704 ⟶ 2,041:
 
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ('wikilink');
end
v_name_table = get_v_name_table (vparam, v_name_table); -- names are separated by commas
 
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
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
local accept_name;
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
 
if accept_name then
last = v_name;
corporate = true; -- flag used in list_people()
elseif string.find(v_name, "%s") then
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
add_vanc_error ('cfg.err_msg_supl.punctuation', i);
end
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 authorinitials intialsor generational suffix
 
if is_suffix (first) then -- if a valid suffix
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
suffix = first -- save it as a suffix and
suffix = first; -- not initials so assume that whatever we got is a generational suffix
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end
end -- no suffix error message here because letter combination may be result of Romanization; check for digits?
last = table.concat(lastfirstTable, "' "') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
if not utilities.is_set (last) then
first = ''; -- unset
last = v_name; -- last empty because something wrong with first
add_vanc_error (cfg.err_msg_supl.name, i);
end
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error ('name'cfg.err_msg_supl.initials, i); -- matches a space between two intiialsinitials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
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', i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first, suffix, i); -- 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 1,748 ⟶ 2,090:
else
if not corporate then
is_good_vanc_name (last, '', nil, i);
end
end
 
-- this from extract_names ()
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 1,763 ⟶ 2,105:
 
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
 
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and;
similarly, |editorn= (and aliases) highest and |editorsveditors= lowest (support for |editors= withdrawn)
 
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
Line 1,774 ⟶ 2,116:
Emits an error message when more than one xxxxor name source is provided.
 
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
 
]]
 
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 1,796 ⟶ 2,138:
err_name = 'editor';
end
utilities.set_message ('err_redundant_parameters', err_name .. '-name-list parameters'); -- add error message
table.insert( z.message_tail, { set_error( '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 1,810 ⟶ 2,151:
 
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, nolive, dead, etc.). When the parameter value has not been assigned a value (missing or empty
or empty in the source template) the function refurnsreturns truethe value specified by ret_val. If the parameter value is one of the list of allowed values returns
trueof the list of allowed values returns the translated value; else, emits an error message and returns false.the value
specified by ret_val.
 
TODO: explain <invert>
 
]]
 
local function is_valid_parameter_value (value, name, possible, cite_classret_val, invert)
if not utilities.is_set (value) then
-- begin hack to limit |mode=mla to a specific set of templates
return ret_val; -- an empty parameter is ok
if ('mode' == name) and ('mla' == value) and not in_array (cite_class, {'book', 'journal', 'news'}) then
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
end
-- end hack
 
if (not invert and utilities.in_array (value, possible)) then -- normal; <value> is in <possible> table
if not is_set (value) then
return truecfg.keywords_xlate[value]; -- anreturn emptytranslation of parameter is okkeyword
elseif invert and not utilities.in_array (value:lower(), possible) then -- invert; <value> is not in <possible> table
return value; -- return <value> as it is
return true;
else
tableutilities.insert( z.message_tail, {set_message set_error( 'invalid_param_valerr_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return falseret_val;
end
end
Line 1,845 ⟶ 2,186:
 
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
 
 
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >-----------------------------------------
 
returns the concatenation of the formatted volume and issue parameters(or asjournal aarticle singlenumber) string;parameters oras formatteda volumesingle
string; or formatted volume or formatted issue, or an empty string if neither are set.
 
]]
local function format_volume_issue (volume, issue, article, cite_class, origin, sepc, lower, mode)
if not utilities.is_set (volume) and not utilities.is_set (issue) and not utilities.is_set (article) then
return '';
end
 
-- same condition as in format_pages_sheets()
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
 
local is_numeric_vol = volume and (volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')); -- is only uppercase roman numerals or only digits?
local is_long_vol = volume and (4 < mw.ustring.len(volume)); -- is |volume= value longer than 4 characters?
if volume and (not is_numeric_vol and is_long_vol) then -- when not all digits or Roman numerals, is |volume= longer than 4 characters?
if ('mla' == mode) and ('journal' == cite_class) then -- same as cs1 for magazines
utilities.add_prop_cat ('long-vol'); -- yes, add properties cat
lower = true; -- mla 8th edition; force these to lower case
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return '';
end
end
 
if is_journal then -- journal-style formatting
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
local vol = '';
if is_set (volume) and is_set (issue) then
 
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseifif utilities.is_set (volume) then
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals?
return wrap_msg ('vol', {sepc, volume}, lower);
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
else
elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters?
return wrap_msg ('issue', {sepc, issue}, lower);
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, utilities.hyphen_to_dash (volume)}); -- not bold
else -- four or fewer characters
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, utilities.hyphen_to_dash (volume)}); -- bold
end
end
vol = vol .. (utilities.is_set (issue) and utilities.substitute (cfg.messages['j-issue'], issue) or '')
vol = vol .. (utilities.is_set (article) and utilities.substitute (cfg.messages['j-article-num'], article) or '')
return vol;
end
 
if 'podcast' == cite_class and utilities.is_set (issue) then
local vol = '';
return wrap_msg ('issue', {sepc, issue}, lower);
end
if is_set (volume) then
if (4 < mw.ustring.len(volume)) then
if 'conference' == cite_class and utilities.is_set (article) then -- |article-number= supported only in journal and conference cites
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
if utilities.is_set (volume) and utilities.is_set (article) then -- both volume and article number
else
volreturn = substitutewrap_msg (cfg.presentation['vol-boldart'], {sepc, utilities.hyphen_to_dash (volume), article}, lower);
elseif utilities.is_set (article) then -- article number alone; when volume alone, handled below
return wrap_msg ('art', {sepc, article}, lower);
end
end
 
if is_set (issue) then
-- all other types of citation
return vol .. substitute (cfg.messages['j-issue'], issue);
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, utilities.hyphen_to_dash (volume), issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, utilities.hyphen_to_dash (volume)}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
return vol;
end
 
 
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
 
not currently used
 
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
returns list unchanged if there are no commas else strips whitespace and then reformats the list
 
]]
--[[
local function normalize_page_list (list)
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
list = table.concat (list, ', '); -- and now make a normalized list
return list;
end
]]
 
 
Line 1,933 ⟶ 2,268:
]]
 
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower, mode)
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 1,941 ⟶ 2,276:
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 1,950 ⟶ 2,285:
end
 
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
if is_journalutilities.is_set and 'mla' == mode(page) then
is_journal = false; -- mla always uses p & pp
end
 
if 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
return '', '', '', ''; -- return empty strings
end
 
 
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
 
returns one of the in-source locators: page, pages, or at.
 
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
for use in COinS. This COinS thing is done because here we convert an interwiki-link to an external link and
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?
 
TODO: add support for sheet and sheets?; streamline;
 
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
to a new name)?
 
]]
 
local function insource_loc_get (page, page_orig, pages, pages_orig, at)
local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-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 = '';
end
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
 
ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip 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, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
 
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip 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 URL from |at= interwiki link; link portion L becomes tooltip 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
end
return page, pages, at, coins_pages;
end
 
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
 
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value
 
]]
 
local function is_unique_archive_url (archive, url, c_url, source, date)
if utilities.is_set (archive) then
if archive == url or archive == c_url then
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); -- add error message
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
end
end
 
return archive, date;
end
 
Line 1,982 ⟶ 2,386:
--[=[-------------------------< 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 2,005 ⟶ 2,409:
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 2,015 ⟶ 2,419:
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 command';
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
elseif url:match('//liveweb%.archive%.org/') then
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 path then -- malformed in some way; pattern did not match
err_msg = cfg.err_msg_supl.timestamp;
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = 'timestamp';
err_msg = cfg.err_msg_supl.timestamp;
if '*' ~= flag then
urllocal replacement =url timestamp:gsubmatch ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*',) or timestamp:match ('^%1*d%d%d%d', 1); -- forget preview,the modifyfirst ts6 to(YYYYMM) beor yearmo*first max (0-64 digits plus splat(YYYY)
if replacement then -- nil if there aren't at least 4 digits (year)
replacement = replacement .. string.rep ('0', 14 - replacement:len()); -- year or yearmo (4 or 6 digits) zero-fill to make 14-digit timestamp
url=url:gsub ('(//web%.archive%.org/[^%d]*)%d[^/]*', '%1' .. replacement .. '*', 1) -- for preview, modify ts to 14 digits plus splat for calendar display
end
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
return url, date; -- return archiveURLArchiveURL and ArchiveDate
end
end
-- if here, something not right so
tableutilities.insert( z.message_tail, {set_message set_error( 'archive_urlerr_archive_url', {err_msg}, true ) } ); -- add error message and
 
if is_set (Frame:preprocess('{{REVISIONID}}')) then
if is_preview_mode then
return '', ''; -- return empty strings for archiveURL and ArchiveDate
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
else
return url'', date''; -- previewreturn modeempty sostrings returnfor archiveURLArchiveURL and ArchiveDate
end
end
 
 
--[[--------------------------< MP IL SA S I N G _ P I PC E _ C H E C K >--------------------------------------------------------
 
check |place=, |publication-place=, |location= to see if these params include digits. This function added because
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a
parameter that is missing its pipe:
{{cite ... |title=Title access-date=2016-03-17}}
 
returns the original parameter value without modification; added maint cat when parameter value contains digits
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 
]]
 
local function missing_pipe_checkplace_check (valueparam_val)
if not utilities.is_set (param_val) then -- parameter empty or omitted
local capture;
return param_val; -- return that empty state
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
end
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
utilities.set_message ('maint_location'); -- yep, add maint cat
end
return param_val; -- and done
end
 
 
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
if capture and validate (capture) then -- if the capture is a valid parameter name
 
add_maint_cat ('missing_pipe');
compares |title= to 'Archived copy' (placeholder 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 2,085 ⟶ 2,510:
]]
 
local function citation0( config, args )
--[[
Load Input Parameters
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable.
]]
local A = argument_wrapper ( args );
local i
 
-- Pick out the relevant fields from the arguments. Different citation templates
-- define different field names for the same underlying things.
 
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode'], config.CitationClass) then
Mode = '';
end
 
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
local Authors;
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
local NameListFormat = A['NameListFormat'];
local Collaboration = A['Collaboration'];
 
Line 2,113 ⟶ 2,532:
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
end
 
local Others = A['Others'];
 
local editor_etal;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
local Editors;
 
do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'], A['Editors']nil, args, 'EditorList'); -- support for |editors= withdrawn
if 1 == selected then
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
 
local tChapter = {}A['Chapter']; -- translatorsdone listhere fromso that we have access to |translator-lastncontribution= /from translator-firstn|chapter= pairsaliases
local Chapter_origin = A:ORIGIN ('Chapter');
local Translators; -- assembled translators name list
local Contribution; -- because contribution is required for contributor(s)
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
if 'contribution' == Chapter_origin then
Contribution = Chapter; -- get the name of the contribution
end
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
 
local interviewers_list = {};
local Interviewers = A['Interviewers']
if is_set (Interviewers) then -- add a maint cat if the |interviewers= is used
add_maint_cat ('interviewers'); -- because use of this parameter is discouraged
else
interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters
end
 
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local Contributors; -- assembled contributors name list
local Contribution = A['Contribution'];
if in_array(config.CitationClass, {"book","citation"}) and not 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=
tableutilities.insert(set_message z.message_tail, { set_error( '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=
tableutilities.insert(set_message z.message_tail, { set_error( '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?
tableutilities.insert(set_message z.message_tail, { set_error( 'contributor_ignorederr_contributor_ignored')}); -- add contributor ignored error message
end
Contribution = nil; -- unset
end
 
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
NameListFormat = ''; -- anything else, set to empty string
end
 
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local Date = A['Date'];
local LayDate = A['LayDate'];
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
local TransTitle = A['TransTitle'];
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 Chapterauto_select = A['Chapter']; -- default is auto
local accept_link;
local ScriptChapter = A['ScriptChapter'];
TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
local TransChapter = A['TransChapter'];
auto_select = TitleLink; -- remember selection for later
local TitleType = A['TitleType'];
TitleLink = ''; -- treat as if |title-link= would have been empty
local Degree = A['Degree'];
end
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
 
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 ArchiveDate;
local ArchiveURL;
 
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
if 'map' == config.CitationClass and 'section' == Chapter_origin then
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
local DeadURL = A['DeadURL']
Chapter = ''; -- unset for now; will be reset later from |map= if present
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
end
DeadURL = ''; -- anything else, set to empty string
end
 
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local ChapterURL = A['ChapterURL'];
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
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 apostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
utilities.set_message ('err_apostrophe_markup', {Periodical_origin});
end
end
 
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
local Series = A['Series'];
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error TODO: make a function for this and similar?
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'mailinglist')});
end
 
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
Periodical_origin = A:ORIGIN('MailingList');
end
 
local ScriptPeriodical = A['ScriptPeriodical'];
 
-- 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?
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'}; -- for error message
if p[config.CitationClass] then
utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]});
end
end
local Volume;
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
if 'citation' == config.CitationClass then
if utilities.is_set (Periodical) then
if not utilities.in_array (Periodical_origin, cfg.citation_no_volume_t) then -- {{citation}} does not render |volume= when these parameters are used
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'
end
else
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
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v');
 
local Issue;
if 'citation' == config.CitationClass then
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, cfg.citation_issue_t) then -- {{citation}} may render |issue= when these parameters are used
Issue = utilities.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 = utilities.hyphen_to_dash (A['Issue']);
end
end
local ArticleNumber;
 
if utilities.in_array (config.CitationClass, {'journal', 'conference'}) or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then
ArticleNumber = A['ArticleNumber'];
end
 
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
 
local Page;
local Pages;
local At;
local QuotePage;
-- previously conference books did not support volume
local QuotePages;
-- if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
if not utilities.in_array (config.CitationClass, cfg.templates_using_volumetemplates_not_using_page) then -- TODO: rewrite to emit ignored parameter error message?
Volume = A['Volume'];
end
-- conference & map books do not support issue
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = A['Issue'];
end
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = utilities.hyphen_to_dash ( A['Pages'] );
At = A['At'];
QuotePage = A['QuotePage'];
QuotePages = utilities.hyphen_to_dash (A['QuotePages']);
end
 
local Edition = A['Edition'];
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
local Place = place_check (A['Place'], A:ORIGIN('Place'));
local PublisherName = A['PublisherName'];
local RegistrationRequiredPublisherName_origin = A[:ORIGIN('RegistrationRequiredPublisherName']);
if utilities.is_set (PublisherName) then
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
local i = 0;
RegistrationRequired=nil;
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
end
if i then -- non-zero when markup was stripped so emit an error message
local SubscriptionRequired = A['SubscriptionRequired'];
utilities.set_message ('err_apostrophe_markup', {PublisherName_origin});
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end
local UrlAccess = A['UrlAccess'];
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
UrlAccess = nil;
end
if not is_set(URL) and is_set(UrlAccess) then
UrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } );
end
end
 
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set
local Newsgroup_origin = A:ORIGIN('Newsgroup');
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription=
end
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message
RegistrationRequired = nil; -- unset; prefer |access= over |registration=
end
 
if 'newsgroup' == config.CitationClass then
 
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
local Via = A['Via'];
utilities.set_message ('err_parameter_ignored', {PublisherName_origin});
local AccessDate = A['AccessDate'];
local Agency = A['Agency'];
 
local Language = A['Language'];
local Format = A['Format'];
local ChapterFormat = A['ChapterFormat'];
local DoiBroken = A['DoiBroken'];
local ID = A['ID'];
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
IgnoreISBN = nil; -- anything else, set to empty string
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
 
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
local ID_list = extract_ids( args );
end
local ID_access_levels = extract_id_access_levels( args, ID_list );
 
local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL?
local Quote = A['Quote'];
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;
utilities.set_message ('err_param_access_requires_param', 'url');
end
local ChapterURL = A['ChapterURL'];
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;
utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')});
end
 
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
local LayFormat = A['LayFormat'];
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
local LayURL = A['LayURL'];
MapUrlAccess = nil;
local LaySource = A['LaySource'];
utilities.set_message ('err_param_access_requires_param', {'map-url'});
local Transcript = A['Transcript'];
end
local TranscriptFormat = A['TranscriptFormat'];
local TranscriptURL = A['TranscriptURL']
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
 
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
end
if 'mla' == Mode then
LastAuthorAmp = 'yes'; -- replaces last author/editor separator with ' and ' text
end
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
no_tracking_cats = nil; -- set to empty string
end
 
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
local anchor_year; -- used in the CITEREF identifier
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
 
local DF = A['DF']; -- date format set in cs1|2 template
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
DF = ''; -- not valid, set to empty string
end
 
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['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 in_array (this_page.nsText, cfg.uncategorized_namespaces)[this_page.namespace] then -- is this page's namespace id one of the uncategorized namespace ids?
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 2,355 ⟶ 2,749:
end
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'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category
 
local coins_pages;
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
 
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
NoPP = true;
else
NoPP = nil; -- unset, used as a flag later
end
 
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
if is_set(Page) then
utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
if is_set(Pages) or is_set(At) then
if PublicationPlace == Place then
Pages = ''; -- unset the others
Place = ''; -- unset; don't need both if they are the same
At = '';
end
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
elseif is_set(Pages) then
if 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.
end
 
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
 
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
local ScriptChapter = A['ScriptChapter'];
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
local Format = A['Format'];
local ChapterFormat = A['ChapterFormat'];
local TransChapter = A['TransChapter'];
local TransChapter_origin = A:ORIGIN ('TransChapter');
local TransTitle = A['TransTitle'];
local ScriptTitle = A['ScriptTitle'];
--[[
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=
|encyclopedia then map |encyclopedia to |title
 
|trans_titletrans-title= maps to |trans_chaptertrans-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
]]
 
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS
All other combinations of |encyclopedia, |title, and |article are not modified
 
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
utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')});
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
local Encyclopedia = A['Encyclopedia'];
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error TODO: make a function for this and similar?
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Periodical_origin)});
end
 
if ( configutilities.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set( Periodical) then = Encyclopedia; -- Periodicalerror isor no, set whenPeriodical |encyclopediato isEncyclopedia; setallow periodical without encyclopedia
Periodical_origin = A:ORIGIN ('Encyclopedia');
if is_set(Title) or is_set (ScriptTitle) then
end
if not is_set(Chapter) then
 
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
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')
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL_origin = URL_origin;
if not is_set (ChapterURL) and is_set (TitleLink) then
 
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
ChapterUrlAccess = UrlAccess;
 
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
Chapter = utilities.make_wikilink (TitleLink, Chapter);
end
Title = Periodical;
Line 2,422 ⟶ 2,836:
ScriptTitle = '';
end
else elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set
Title = Periodical; -- |encyclopedia= set and |article set or not= set so map |encyclopedia= to |title=
Periodical = ''; -- redundant so unset
end
Line 2,429 ⟶ 2,843:
end
 
-- Specialspecial case for cite techreport.
local ID = A['ID'];
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
tableutilities.insert( z.message_tail, {set_message set_error('redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. cfg.presentation[' and sep_list_pair'] .. utilities.wrap_style ('parameter', 'number')}, true )});
end
end
end
 
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
-- special case for cite mailing list
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
if (config.CitationClass == "mailinglist") then
Periodical local Conference = A ['MailingListConference'];
local BookTitle = A['BookTitle'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
local TransTitle_origin = A:ORIGIN ('TransTitle');
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
 
-- 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; -- |chapterlink= is deprecated
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
ChapterURL = URL;
ChapterURLoriginChapterUrlAccess = URLoriginUrlAccess;
URLoriginChapterURL_origin = ''URL_origin;
URL_origin = '';
ChapterFormat = Format;
TransChapter = TransTitle;
TransChapter_origin = TransTitle_origin;
Title = BookTitle;
Format = '';
-- TitleLink = '';
TransTitle = '';
URL = '';
Line 2,466 ⟶ 2,881:
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
 
-- CS1/2 mode
-- cite map oddities
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
-- separator character and postscript
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
-- controls capitalization of certain static text
local use_lowercase = ( sepc == ',' );
-- cite map oddities
local Cartography = "";
local Scale = "";
Line 2,473 ⟶ 2,895:
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
if utilities.is_set (Chapter) then --TODO: make a function for this and similar?
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Chapter_origin)}); -- add error message
end
Chapter = A['Map'];
Chapter_origin = A:ORIGIN('Map');
ChapterURL = A['MapURL'];
ChapterURL_origin = A:ORIGIN('MapURL');
TransChapter = A['TransMap'];
ScriptChapter = A['ScriptMap']
ChapterURLorigin = A:ORIGIN('MapURL');
ScriptChapter_origin = A:ORIGIN('ScriptMap')
 
ChapterUrlAccess = MapUrlAccess;
ChapterFormat = A['MapFormat'];
 
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
end
 
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
local Series = A['Series'];
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
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 2,500 ⟶ 2,930:
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 .. ' ');
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date
Date = AirDate;
end
 
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
local Season = A['Season'];
local SeriesNumber = A['SeriesNumber'];
 
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set TODO: make a function for this and similar?
tableutilities.insert(set_message z.message_tail, { set_error( 'redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. cfg.presentation[' and sep_list_pair'] .. 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 ('seriesseriesnum', 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
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
ChapterLink = TitleLink; -- alias episodelink
ChapterLink = TitleLink; -- alias |episode-link=
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURLorigin = A:ORIGIN('URL');
ChapterURL_origin = URL_origin;
ChapterFormat = Format;
 
Title = Series; -- promote series to title
TitleLink = SeriesLink;
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 .. ']]'); -- ok to wikilink
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' .utilities.make_wikilink (ChapterLink .. '|' .., Series .. ']]'); -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
end
URL = ''; -- unset
TransTitle = '';
ScriptTitle = '';
Format = '';
else -- now oddities that are cite serial
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
 
-- handle type parameter for those CS1 citations that have default values
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data.
local TitleType = A['TitleType'];
do
local Degree = A['Degree'];
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then
if utilities.in_array (config.CitationClass, {'AV-media-notes', 'interview', 'mailinglist', 'map', 'podcast', 'pressrelease', 'report', 'speech', 'techreport', 'thesis'}) 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
if 'arxiv' == config.CitationClass then
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
if 'biorxiv' == config.CitationClass then
Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string
end
if 'citeseerx' == config.CitationClass then
Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string
end
end
end
 
-- handle type parameter for those CS1 citations that have default values
if 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
 
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
iflocal notDate is_set= (A['Date) then'];
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
local PublicationDate = A['PublicationDate'];
local Year = A['Year'];
 
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
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
else
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
end
else
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
end
 
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
 
--[[
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
we get the date used in the metadata.
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
 
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
Date validation supporting code is in Module:Citation/CS1/Date_validation
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
 
local ArchiveURL;
local ArchiveDate;
local ArchiveFormat = A['ArchiveFormat'];
 
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL
 
local AccessDate = A['AccessDate'];
local LayDate = A['LayDate'];
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
local DoiBroken = A['DoiBroken'];
local Embargo = A['Embargo'];
local anchor_year; -- used in the CITEREF identifier
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};
['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')},
};
 
local error_list = {};
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
 
-- start temporary Julian / Gregorian calendar uncertainty categorization
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
if COinS_date.inter_cal_cat then
local mismatch = year_date_check (Year, Date)
utilities.add_prop_cat ('jul-greg-uncertainty');
if 0 == mismatch then -- |year= does not match a year-value in |date=
end
if is_set (error_message) then -- if there is already an error message
-- end temporary Julian / Gregorian calendar uncertainty categorization
error_message = error_message .. ', '; -- tack on this additional message
 
end
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed;
error_message = error_message .. '&#124;year= / &#124;date= mismatch';
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
elseif 1 == mismatch then -- |year= matches year-value in |date=
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 is_set (DF) then -- if we need to reformat dates
if utilities.is_set (DF) then -- if we need to reformat dates
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
modified = validation.reformat_dates (date_parameters_list, DF); -- 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; not supported at en.wiki
if cfg.date_name_auto_xlate_enable and validation.date_name_xlate (date_parameters_list, cfg.date_digit_auto_xlate_enable ) then
utilities.set_message ('maint_date_auto_xlated'); -- add maint cat
modified = true;
end
 
if modified then -- if the date_parameters_list values were modified
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
ArchiveDate = date_parameters_list['archive-date'].val;
Date = date_parameters_list['date'].val;
DoiBroken = date_parameters_list['doi-broken-date'].val;
LayDate = date_parameters_list['lay-date'].val;
PublicationDate = date_parameters_list['publication-date'].val;
end
else
tableutilities.insert( z.message_tail, {set_message set_error( 'bad_dateerr_bad_date', {error_message}utilities.make_sep_list (#error_list, true error_list) } ); -- add this error message
end
end -- end of do
 
local ID_list = {}; -- sequence table of rendered identifiers
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS.
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
-- 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
Embargolocal =Class is_embargoed= (Embargo)A['Class']; -- arxiv class identifier
local ID_support = {
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')},
}
 
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
 
if not is_set (Embargo) then -- if not embargoed or embargo has expired
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv=, |citeseerx=, |ssrn= required for their templates
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
if not (args[cfg.id_handlers[config.CitationClass:upper()].parameters[1]] or -- can't use ID_list_coins k/v table here because invalid parameters omitted
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
args[cfg.id_handlers[config.CitationClass:upper()].parameters[2]]) then -- which causes unexpected parameter missing error message
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message
end
 
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
end
 
-- 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) then -- set when using an identifier-created URL
if utilities.is_set (AccessDate) then -- |access-date= requires |url=; identifier-created URL is not |url=
utilities.set_message ('err_accessdate_missing_url'); -- add an error message
AccessDate = ''; -- unset
end
 
if utilities.is_set (ArchiveURL) then -- |archive-url= requires |url=; identifier-created URL is not |url=
utilities.set_message ('err_archive_missing_url'); -- add an error message
ArchiveURL = ''; -- unset
end
end
end
 
-- 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
if not is_set(Title) and
utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'});
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
end
end
 
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
Title = ''; -- set title to empty string
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
add_maint_cat ('untitled');
('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
end
 
check_for_url ({ -- add error message when any of these parameters contains a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[A:ORIGIN('PublisherName')] = PublisherName
});
 
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
Line 2,694 ⟶ 3,178:
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 2,704 ⟶ 3,188:
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 wikimarkup/ accept-as-written markup
['Degree'] = Degree; -- cite thesis only
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup/ accept-as-written markup
['PublicationPlace'] = PublicationPlace,
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
['Season'] = COinS_date.rftssn,
['Quarter'] = COinS_date.rftquarter,
['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
['Series'] = Series,
['Volume'] = Volume,
['Issue'] = Issue,
['ArticleNumber'] = ArticleNumber,
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- 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 'arxiv' ==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
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX 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 ));
if is_set (PublisherName) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil ));
end
end
 
local Editors;
 
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
 
local Contributors; -- assembled contributors name list
local contributor_etal;
local Translators; -- assembled translators name list
local translator_etal;
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
local Interviewers;
local interviewers_list = {};
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
local interviewer_etal;
-- Now perform various field substitutions.
-- We also add leading spaces and surrounding markup and punctuation to the
-- various parts of the citation, but only when they are non-nil.
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
do
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,
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn
mode = Mode
};
 
do -- do editor name list first because the now unsupported coauthors used to modify control table
control.maximum , editor_etal = get_display_authors_editorsget_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
last_first_listEditors, EditorCount = list_people (control, e, editor_etal);
 
if is_set (Editors) then
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else
Editors = last_first_list; -- either an author name list or an empty string
end
 
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
Line 2,777 ⟶ 3,257:
end
do -- now do interviewers
control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list; --, number'interviewers', ofinterviewer_etal, interviewerssA:ORIGIN ('DisplayInterviewers'));
Interviewers = list_people (control, interviewers_list, falseinterviewer_etal); -- et al not currently supported
end
do -- now do translators
control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators'));
control.maximum = #t; -- number of translators
Translators = list_people (control, t, falsetranslator_etal); -- et al not currently supported
end
do -- now do contributors
control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
control.maximum = #c; -- number of contributors
Contributors = list_people (control, c, falsecontributor_etal); -- et al not currently supported
end
do -- now do authors
control.maximum , author_etal = get_display_authors_editorsget_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));
 
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
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Line 2,803 ⟶ 3,283:
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 2,809 ⟶ 3,289:
end
 
local ConferenceFormat = A['ConferenceFormat'];
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
local ConferenceURL = A['ConferenceURL'];
-- an error message if the associated url 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');
Format = style_format (Format, URL, 'format', 'url');
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
 
-- 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"}) thenor -- |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_error( 'cite_web_url', {}, true ) } );
utilities.set_message ('err_cite_web_url');
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;
utilities.set_message ('err_accessdate_missing_url');
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
end
end
 
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess;
local OriginalURL
DeadURL = DeadURL:lower(); -- used later when assembling archived text
local OriginalURL_origin
if is_set( ArchiveURL ) then
local OriginalFormat
if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
local 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
OriginalURLoriginOriginalURL_origin = ChapterURLoriginChapterURL_origin; -- name of |chapter-url= parameter for error messages
OriginalFormat = ChapterFormat; -- and original |chapter-format=
 
if 'no' ~= DeadURL then
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURLoriginChapterURL = A:ORIGIN('ArchiveURL') -- name of archiveswap-urlin parameterthe for errorarchive's messagesURL
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 URLs
end
elseif utilities.is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURLoriginOriginalURL_origin = URLoriginURL_origin; -- name of urlURL parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
 
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
URLif 'live' ~= ArchiveURL UrlStatus then -- swap-inif theURL archive'sset then |archive-url= applies to it
URLoriginURL = A:ORIGIN('ArchiveURL') -- nameswap-in ofthe archive's url parameter for error messagesURL
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL 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
elseif utilities.is_set (UrlStatus) then -- if |url-status= is set when |archive-url= is not set
utilities.set_message ('maint_url_status'); -- add maint cat
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 = A:ORIGIN ('ScriptChapter')ScriptChapter_origin;
else utilities.is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
 
if utilities.is_set (chap_param) then -- if we found one
tableutilities.insert( z.message_tail, {set_message set_error( 'chapter_ignorederr_chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
Line 2,886 ⟶ 3,373:
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.keywordskeywords_lists.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
 
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURLoriginChapterURL_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
end
 
-- Format main title.
local plain_title = false;
if is_set(TitleLink) and is_set(Title) then
local accept_title;
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title>
if accept_title and ('' == Title) then -- only support forced empty for now "(())"
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 not accept_title then -- <Title> not wrapped in accept-as-written markup
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title=
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = wrap_style ('quoted-title', Title);
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
end
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
 
elseif 'report' == config.CitationClass then -- no styling for cite report
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
end
 
if is_generic ('generic_titles', Title) then
utilities.set_message ('err_generic_title'); -- 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 module provided quote marks
Title = utilities.wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, 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 attribute, 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
 
if utilities.is_set (TransTitle) then
local TransError = "";
if utilities.is_set (TransTitleTitle) then
if is_set(Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .utilities.set_message set_error( 'trans_missing_titleerr_trans_missing_title', {'title'} );
end
end
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format;
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive
-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available
-- local err_msg
-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message
-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this
-- Title = Title .. (err_msg or '');
-- end
-- else
-- Title = temp_title;
-- end
 
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
if utilities.is_set (TitleLink) and utilities.is_set (URL) then
utilities.set_message ('err_wikilink_in_url'); -- 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 .. 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;
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle;
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)
Title = Title .. TransTitle .. TransError;
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip 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;
else
Title = Title .. TransTitle;
end
end
else
Title = TransTitle;
end
 
if utilities.is_set (Place) then
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
end
 
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
if is_set (Conference) then
if utilities.is_set (ConferenceURLConference) then
if utilities.is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil );
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, ConferenceURLoriginConferenceURL_origin, nil );
end
 
iflocal not is_set(Position) then= '';
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 --TODO: make a function for this and similar?
tableutilities.insert(set_message z.message_tail, { set_error( 'redundant_parameterserr_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. cfg.presentation[' and sep_list_pair'] .. 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 2,996 ⟶ 3,522:
end
 
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase, Mode);
 
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 Section = A['Section'];
local Sections = A['Sections'];
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 3,017 ⟶ 3,542:
end
 
local Others = A['Others'];
if is_set (Language) then
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc
if config.CitationClass == "AV-media-notes"
else
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now
Language=""; -- language not specified so make sure this is an empty string;
utilities.set_message ('maint_others_avm')
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
 
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then
if 'mla' == Mode then
Others = sepc .. ' Trans. ' .. Translators .. Others;
else
utilities.set_message ('maint_others');
Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;
end
end
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
if is_set (Interviewers) then
Others = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others;
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
local TitleNote = is_set(A['TitleNote) and (sepc .. " " .. TitleNote) or ""'];
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (Edition) then
if Edition:matchutilities.is_set ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
add_maint_cat ('extra_text', 'edition');
utilities.set_message ('err_extra_text_edition'); -- add error message
end
if 'mla' == Mode then
Edition = '. ' .. Edition .. ' ed.';
else
Edition = " " .. wrap_msg ('edition', Edition);
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
 
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc .. " " .., Series}) or ""; -- not the same as SeriesNum
local Agency = A['Agency'];
if 'mla' == Mode then -- not in brackets for mla
OrigYear Agency = utilities.is_set (OrigYearAgency) and wrap_msg (".'agency', " ..{sepc, OrigYearAgency}) or "";
Volume = format_volume_issue (Volume, Issue, ArticleNumber, config.CitationClass, Periodical_origin, sepc, use_lowercase);
else
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
end
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase, Mode);
 
if utilities.is_set (AccessDate) then
------------------------------------ totally unrelated data
if is_set(Via) then
Via = " " .. wrap_msg ('via', Via);
end
 
--[[
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.
 
]]
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif is_set (RegistrationRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
end
 
if 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
if 'mla' == Mode then -- retrieved text not used in mla
AccessDate = ' ' .utilities.substitute (retrv_text, AccessDate); -- add retrieved text
 
else
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
end
AccessDate = 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 is_set(Docket) then
ID = sepc .." local Docket "..= A['Docket .. ID'];
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} );
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
 
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin, UrlAccess );
end
 
iflocal is_set(Quote) then= A['Quote'];
local TransQuote = A['TransQuote'];
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
local ScriptQuote = A['ScriptQuote'];
Quote = Quote:sub(2,-2); -- strip them off
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
 
if utilities.is_set (Quote) then
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 = kern_quotes (Quote); -- kern if needed
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
extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc.
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
extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc.
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
-- We check length of PostScript here because it will have been nuked by
local Archived
-- the quote parameters. We'd otherwise emit a message even if there wasn't
if is_set(ArchiveURL) then
-- a displayed postscript.
if not is_set(ArchiveDate) then
-- TODO: Should the max size (1) be configurable?
ArchiveDate = set_error('archive_missing_date');
-- TODO: Should we check a specific pattern?
if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then
utilities.set_message ('maint_postscript')
end
local Archived;
if utilities.is_set (ArchiveURL) then
local arch_text;
if not utilities.is_set (ArchiveDate) then
utilities.set_message ('err_archive_missing_date');
ArchiveDate = ''; -- empty string for concatenation
end
if "nolive" == DeadURLUrlStatus then
local arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
if utilities.is_set (ArchiveDate) then
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
{external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
else
Archived = Archived .. " " .. set_error('archive_missing_url');
Archived = '';
end
elseif if not utilities.is_set (OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
utilities.set_message ('err_archive_missing_url');
local arch_text = cfg.messages['archived-dead'];
Archived = ''; -- empty string for concatenation
if sepc ~= "." then arch_text = arch_text:lower() end
end
if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown' == DeadURL}) then
arch_text = cfg.messages['archived-unfit'];
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. ' ' .. arch_text .. ArchiveDate; -- format already styled
if 'bot: unknown' == UrlStatus then
utilities.set_message ('maint_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
if utilities.is_set (ArchiveDate) then
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
else
Archived = ''; -- unset for concatenation
end
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else -- OriginalUrl not set
else
local arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
utilities.set_message ('err_archive_missing_url');
Archived = sepc .. " " .. substitute( arch_text,
Archived = ''; -- empty string for concatenation
{ set_error('archive_missing_url'), ArchiveDate } );
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Archived = ""'';
end
local Lay = '';
local LaySource = A['LaySource'];
if is_set(LayURL) then
local LayURL = A['LayURL'];
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
local LayFormat = A['LayFormat'];
if is_set(LaySource) then
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
LaySource = " &ndash; ''" .. safe_for_italics(LaySource) .. "''";
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 3,168 ⟶ 3,731:
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
 
local TranscriptURL = A['TranscriptURL']
if is_set(Transcript) then
local TranscriptFormat = A['TranscriptFormat'];
if is_set(TranscriptURL) then
Transcript TranscriptFormat = external_linkstyle_format (TranscriptFormat, TranscriptURL, Transcript'transcript-format', TranscriptURLorigin, nil 'transcripturl');
local Transcript = A['Transcript'];
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL
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, TranscriptURLoriginTranscriptURL_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 3,197 ⟶ 3,765:
end
local TransPeriodical = A['TransPeriodical'];
local TransPeriodical_origin = A:ORIGIN ('TransPeriodical');
-- 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 .. " " .. wrap_styleformat_periodical ('italic-title'ScriptPeriodical, ScriptPeriodical_origin, Periodical), TransPeriodical, TransPeriodical_origin);
else
Periodical = wrap_styleformat_periodical ('italic-title'ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
end
end
local Language = A['Language'];
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;
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
 
--[[
Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"TitleType; -- annotatemove TitleType to TitleNote so that it renders ahead theof citation|event=
TitleType = ''; -- and unset
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
 
if is_set (Conference) then -- and if |event= is set
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
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
end
Line 3,226 ⟶ 3,808:
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 not (utilities.is_set (Authors) or utilities.is_set (Editors)) then
if is_set(Others) then Others = Others .. sepc .. " " end
Others = Others:gsub ('^' .. sepc .. ' ', ''); -- when no authors and no editors, strip leading sepc and space
if 'mla' == Mode then
end
tcommon = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
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?
else
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
Language, Edition, Publisher, Agency, Volume}, sepc );
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc.
end
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
if 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 );
if 'mla' == Mode then
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Edition, Publisher, Agency}, sepc );
else
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
end
elseif 'mla' == Mode then
tcommon = safe_join( {TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Publisher, Agency}, sepc );
else
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Line 3,249 ⟶ 3,823:
 
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 3,258 ⟶ 3,832:
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
 
elseif ('news' == config.CitationClass) and ('mla' == Mode) then -- special case for cite news in MLA mode
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, Edition, Agency}, sepc );
 
elseif ('web' == config.CitationClass) and ('mla' == Mode) then -- special case for cite web in MLA mode
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language,
Edition, Publisher, Agency}, sepc );
 
else -- all other CS1 templates
Line 3,278 ⟶ 3,845:
end
local Via = A['Via'];
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
Via = utilities.is_set (Via) and wrap_msg ('via', Via) or '';
local idcommon;
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc );
else
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
end
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
 
local OrigDate = A['OrigDate'];
if is_set(Date) then
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
if ('mla' == Mode) then
if utilities.is_set (Date) then
if in_array (config.CitationClass, {'book', 'news', 'web'}) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
Date = ', ' .. Date; -- origyear follows title in mla
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
elseif 'journal' == config.CitationClass then
Date = ', (' .. Date .. ')';
end
elseif is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
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)) or ('mla' == Mode) 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 and 'mla' ~= Mode then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
in_text = in_text:lower() -- lowercase for cs2
elseif is_set(Chapter) and 'mla' == Mode then
if EditorCount <= 1 then
in_text = '. Ed. ';
else
in_text = '. Eds. ';
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
post_text = " (" .. cfg.messages['editors'] .. ")";
if EditorCount <= 1 then
end
post_text = ", " .. cfg.messages['editor'];
else
post_text = ", " .. cfg.messages['editors'];
end
end
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) and ('mla' ~= Mode) 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)) or ('mla' == Mode) 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
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
if 'mla' == Mode then
text = safe_join( {Contributors, Chapter, tcommon, OrigYear, Authors, Place, Others, Editors, tcommon2, Date, pgtext, idcommon }, sepc );
else
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
end
elseif 'mla' == Mode then
tcommon = tcommon .. Date; -- hack to avoid duplicate separators
text = safe_join( {Authors, Chapter, Title, OrigYear, Others, Editors, Edition, Place, tcommon, pgtext, idcommon }, sepc );
else
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.presentation['sep_name'] .. cfg.messages['editor'];
else
Editors = Editors .. ", "cfg.presentation['sep_name'] .. cfg.messages['editors'];
end
else
Line 3,359 ⟶ 3,918:
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
if 'mla' == Mode then
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
text = safe_join( {Editors, Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Editors, Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
else
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
end
elseif 'mla' == Mode then
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
text = safe_join( {Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
text = safe_join( {Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
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 3,382 ⟶ 3,927:
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
text = safe_join( {text, PostScript}, sepc );
 
-- Now enclose the whole thing in a <cite/> element
local optionsoptions_t = {};
options_t.class = cite_class_attribute_make (config.CitationClass, Mode);
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
options.class = config.CitationClass;
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
else
options.class = "citation";
end
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
if ('harv' == Ref ) then
local namelist = {}; -- holds selected contributor, author, editor name list
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
 
local Ref = is_valid_parameter_value (A['Ref'], A:ORIGIN('Ref'), cfg.keywords_lists['ref'], nil, true); -- nil when |ref=harv; A['Ref'] else
if #c > 0 then -- if there is a contributor list
 
namelist = c; -- select it
if 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then
elseif #a > 0 then -- or an author list
local namelist_t = {}; -- holds selected contributor, author, editor name list
namelist = a;
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
elseif #e > 0 then -- or an editor list
 
namelist = e;
if #c > 0 then -- if there is a contributor list
end
ifnamelist_t #namelist= > 0 thenc; -- if there are names inselect namelistit
idelseif =#a anchor_id> (namelist,0 year);then -- go makeor thean CITEREFauthor anchorlist
namelist_t = a;
else
idelseif =#e '';> 0 then -- unsetor an editor list
namelist_t = e;
end
local citeref_id;
if #namelist_t > 0 then -- if there are names in namelist_t
citeref_id = make_citeref_id (namelist_t, year); -- go make the CITEREF anchor
if mw.uri.anchorEncode (citeref_id) == ((Ref and mw.uri.anchorEncode (Ref)) or '') then -- Ref may already be encoded (by {{sfnref}}) so citeref_id must be encoded before comparison
utilities.set_message ('maint_ref_duplicates_default');
end
else
citeref_id = ''; -- unset
end
optionsoptions_t.id = idRef or citeref_id;
end
 
if string.len (text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("'%b<>"',"" '')) <= 2 then -- remove <span> tagshtml and other html-like markuptags; then get length of what remains;
z.error_cats_t = {}; -- blank the categories list
z.error_categories = {};
z.error_msgs_t = {}; -- blank the error messages list
text = set_error('empty_citation');
OCinSoutput = nil; -- blank the metadata string
z.message_tail = {};
text = ''; -- blank the the citation
utilities.set_message ('err_empty_citation'); -- set empty citation message and category
end
iflocal is_set(options.id)render_t then= {}; -- here we wrapcollect the renderedfinal citationbits infor <citeconcatenation ...>...</cite>into tagsthe rendered citation
 
text = substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text}); -- when |ref= is set
if utilities.is_set (options_t.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
table.insert (render_t, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options_t.id), mw.text.nowiki(options_t.class), text})); -- when |ref= is set or when there is a namelist
else
texttable.insert =(render_t, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(optionsoptions_t.class), text})); -- allwhen |ref=none or when namelist_t empty and |ref= is missing or otheris casesempty
end
 
if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span
text = text .. substitute (cfg.presentation['ocins'], {OCinSoutput}); -- append metadata to the citation
table.insert (render_t, utilities.substitute (cfg.presentation['ocins'], OCinSoutput)); -- format and append metadata to the citation
end
if #z.message_tail ~= 0 then
 
text = text .. " ";
local template_name = ('citation' == config.CitationClass) and 'citation' or 'cite ' .. (cfg.citation_class_map_t[config.CitationClass] or config.CitationClass);
for i,v in ipairs( z.message_tail ) do
local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]';
if is_set(v[1]) then
local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: ';
if i == #z.message_tail then
 
text = text .. error_comment( v[1], v[2] );
if 0 ~= #z.error_msgs_t then
else
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, template_link));
text = text .. error_comment( v[1] .. "; ", v[2] );
 
end
table.insert (render_t, ' '); -- insert a space between citation and its error messages
table.sort (z.error_msgs_t); -- sort the error messages list; sorting includes wrapping <span> and <code> tags; hidden-error sorts ahead of visible-error
 
local hidden = true; -- presume that the only error messages emited by this template are hidden
for _, v in ipairs (z.error_msgs_t) do -- spin through the list of error messages
if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name
hidden = false; -- found one; so don't hide the error message prefix
break; -- and done because no need to look further
end
end
 
z.error_msgs_t[1] = table.concat ({utilities.error_comment (msg_prefix, hidden), z.error_msgs_t[1]}); -- add error message prefix to first error message to prevent extraneous punctuation
table.insert (render_t, table.concat (z.error_msgs_t, '; ')); -- make a big string of error messages and add it to the rendering
end
 
if #z.maintenance_cats0 ~= 0#z.maint_cats_t then
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, template_link));
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33; margin-left:0.3em">';
 
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
table.sort (z.maint_cats_t); -- sort the maintenance messages list
text = text .. v .. ' ([[:Category:' .. v ..'|link]])';
 
local maint_msgs_t = {}; -- here we collect all of the maint messages
 
if 0 == #z.error_msgs_t then -- if no error messages
table.insert (maint_msgs_t, msg_prefix); -- insert message prefix in maint message livery
end
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
for _, v in ipairs( z.maint_cats_t ) do -- append maintenance categories
table.insert (maint_msgs_t, -- assemble new maint message and add it to the maint_msgs_t table
table.concat ({v, ' (', utilities.substitute (cfg.messages[':cat wikilink'], v), ')'})
);
end
table.insert (render_t, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs_t, ' '))); -- wrap the group of maint messages with proper presentation and save
end
 
no_tracking_catsif =not no_tracking_cats:lower(); then
for _, v in ipairs (z.error_cats_t) do -- append error categories
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs ( z.maintenance_cats maint_cats_t) do -- append maintenance categories
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( (z.properties_cats prop_cats_t) do -- append maintenanceproperties categories
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v));
text = text .. '[[Category:' .. v ..']]';
end
end
 
return table.concat (render_t); -- make a big string and done
return text
end
 
 
--[[--------------------------< CV SA 1 . CL I TD A T I O NE >--------------------------------------------------------------
 
Looks for a parameter's name in one of several whitelists.
This is used by templates such as {{cite book}} to create the actual citation text.
 
Parameters in the whitelist can have three values:
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
 
local function cs1.citationvalidate (framename, cite_class, empty)
local name = tostring (name);
Frame = frame; -- save a copy incase we need to display an error message in preview mode
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
local pframe = frame:getParent()
local state;
local validation, utilities, identifiers, metadata;
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 nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
if false == state then
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
if empty then return nil; end -- empty deprecated parameters are treated as unknowns
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
deprecated_parameter (name); -- parameter is deprecated but still supported
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
return true;
validation = require ('Module:Citation/CS1/Date_validation/sandbox');
end
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
if 'tracked' == state then
metadata = require ('Module:Citation/CS1/COinS/sandbox');
local base_name = name:gsub ('%d', ''); -- strip enumerators from parameter names that have them to get the base name
utilities.add_prop_cat ('tracked-param', {base_name}, base_name); -- add a properties category; <base_name> modifies <key>
return true;
end
return nil;
end
 
if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
return nil;
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
 
state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
if true == state_test (state, name) then return true; end
 
-- limited enumerated parameters list
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[enum_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 -- 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
end -- if here, fall into general validation
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
else -- otherwise
if true == state_test (state, name) then return true; end
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
 
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
-- all enumerated parameters allowed
utilities = require ('Module:Citation/CS1/Utilities');
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
validation = require ('Module:Citation/CS1/Date_validation');
state = whitelist.numbered_arguments[enum_name];
identifiers = require ('Module:Citation/CS1/Identifiers');
if true == state_test (state, name) then return true; end
metadata = require ('Module:Citation/CS1/COinS');
 
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
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
 
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the 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 (utilities); -- so that functions in Date validataion can see 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
 
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation
 
year_date_check = validation.year_date_check;
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
reformat_dates = validation.reformat_dates;
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a
date_hyphen_to_dash = validation.date_hyphen_to_dash;
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 MediaWiki)
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc. To prevent false positives XML/HTML
tags are removed before the search.
 
If a missing pipe is detected, this function adds the missing pipe maintenance category.
 
]]
 
local function missing_pipe_check (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove XML/HTML 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
utilities.set_message ('err_missing_pipe', parameter);
end
end
 
 
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
 
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
 
]]
 
local function has_extraneous_punc (param, value)
if 'number' == type (param) then
return;
end
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
if cfg.punct_skip[param] then
in_array = utilities.in_array;
return; -- parameter name found in the skip table so done
substitute = utilities.substitute;
end
error_comment = utilities.error_comment;
set_error = utilities.set_error;
if value:match ('[,;:]$') then
select_one = utilities.select_one;
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
add_maint_cat = utilities.add_maint_cat;
end
wrap_style = utilities.wrap_style;
if value:match ('^=') then -- sometimes an extraneous '=' character appears ...
safe_for_italics = utilities.safe_for_italics;
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat
remove_wiki_link = utilities.remove_wiki_link;
end
end
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 
--[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers
 
build_id_list = identifiers.build_id_list;
look for extraneous url parameter values; parameters listed in skip table are not checked
is_embargoed = identifiers.is_embargoed;
 
extract_id_access_levels = identifiers.extract_id_access_levels;
]]
 
local function has_extraneous_url (url_param_t)
local url_error_t = {};
check_for_url (url_param_t, url_error_t); -- extraneous url check
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
if 0 ~= #url_error_t then -- non-zero when there are errors
get_coins_pages = metadata.get_coins_pages;
table.sort (url_error_t);
COinS = metadata.COinS;
utilities.set_message ('err_param_has_ext_link', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message
end
end
 
 
local args = {}; -- table where we store all of the template's arguments
--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
local suggestions = {}; -- table where we store suggestions if we need to loadData them
 
local error_text, error_state;
This is used by templates such as {{cite book}} to create the actual citation text.
 
]]
 
local function citation(frame)
Frame = frame; -- save a copy in case we need to display an error message in preview mode
 
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame
config[k] = v;
-- args[k] = v; -- crude debug toolsupport that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep?
end
-- i18n: set the name that your wiki uses to identify sandbox subpages from sandbox template invoke (or can be set here)
local sandbox = ((config.SandboxPath and '' ~= config.SandboxPath) and config.SandboxPath) or '/sandbox'; -- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}}
is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true); -- is this invoke the sandbox module?
sandbox = is_sandbox and sandbox or ''; -- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else
 
local pframe = frame:getParent()
local styles;
cfg = mw.loadData ('Module:Citation/CS1/Configuration' .. sandbox); -- load sandbox versions of support modules when {{#invoke:Citation/CS1/sandbox|...}}; live modules else
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist' .. sandbox);
utilities = require ('Module:Citation/CS1/Utilities' .. sandbox);
validation = require ('Module:Citation/CS1/Date_validation' .. sandbox);
identifiers = require ('Module:Citation/CS1/Identifiers' .. sandbox);
metadata = require ('Module:Citation/CS1/COinS' .. sandbox);
styles = 'Module:Citation/CS1' .. sandbox .. '/styles.css';
 
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
 
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
 
is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}'));
 
local args = {}; -- table where we store all of the template's arguments
local suggestions = {}; -- table where we store suggestions if we need to loadData them
local error_text; -- used as a flag
 
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
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
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
end
if not validate( k, config.CitationClass ) then
if type (k) ~= 'string' then -- exclude empty numbered parameters
error_text = "";
if type( k ) ~= 'string' then
-- Exclude 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_error(utilities.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
suggestions = mw.loadData ('Module:Citation/CS1/Suggestions' .. sandbox); --load sandbox version of suggestion module when {{#invoke:Citation/CS1/sandbox|...}}; live module else
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
else
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
end
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_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message
else
error_text = utilities.set_message ('err_parameter_ignored', {k}); -- 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 expicitexplicit suggestion?
if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
error_text, error_state =utilities.set_message set_error( 'parameter_ignored_suggesterr_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
else
error_text, error_state =utilities.set_message set_error( 'parameter_ignorederr_parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end
if error_text ~= '' then
table.insert( z.message_tail, {error_text, error_state} );
end
end
 
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe?
args[k] = v; -- save this parameter and its value
 
args[k] = v;
elseif not utilities.is_set (v) then -- for empty parameters
elseif args[k] ~= nil or (k == 'postscript') then
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
args[k] = v;
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
end
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)
-- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact?
end
 
if 0 ~= #empty_unknowns then -- create empty unknown error message
utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
});
end
 
local url_param_t = {};
 
for k, v in pairs( args ) do
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v); -- look for invisible characters
end
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
 
if 'string' == type (k) and not cfg.url_skip[k] then -- when parameter k is not positional and not in url skip table
url_param_t[k] = v; -- make a parameter/value list for extraneous url check
end
end
 
return citation0( config, args)
has_extraneous_url (url_param_t); -- look for url in parameter values where a url does not belong
 
return table.concat ({
frame:extensionTag ('templatestyles', '', {src=styles}),
citation0( config, args)
});
end
 
 
return cs1;
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
 
return {citation = citation};