Modul:Citation/CS1: razlika između inačica
Izbrisani sadržaj Dodani sadržaj
rev Oznaka: uklanjanje ručnim načinom |
m test |
||
Redak 1:
require('Module:No globals');
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
each of these counts against the Lua upvalue limit
]]
local
local
local z ={}; -- table of tables in Module:Citation/CS1/Utilities
local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
local metadata; -- functions in Module:Citation/CS1/COinS
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
--[[------------------< P A G E S C O P E V A R I A B L E S >---------------
declare variables here that have page-wide scope that are not brought in from
other modules; that are created here and used here
]]
local added_deprecated_cat; -- Boolean flag so that the category is added only once
local
local
local Frame; -- holds the module's frame table
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Line 48 ⟶ 39:
local i = 1;
while i <= count do -- loop through all items in list
if utilities.is_set( list[i] ) then
return list[i]; -- return the first set list member
end
i = i + 1; -- point to next
end
end
Line 81 ⟶ 52:
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
added_vanc_errs is a
]]
local function add_vanc_error (source, position)
if
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source, position}, true ) } );
end
Line 95 ⟶ 66:
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
does this thing that purports to be a
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 118 ⟶ 89:
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
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
is two or more alpha characters. Any preceding '//' (from splitting a
here. Perhaps not necessary but retained
There are several tests:
the first character of the whole domain name including subdomains must be a letter or a digit
internationalized domain name (
single-letter/digit second-level domains in the .org, .cash, and .today TLDs
q, x, and z SL domains in the .com TLD
Line 140 ⟶ 111:
IPv4 dot-decimal address format; TLD not allowed
returns true if domain appears to be a proper name and
]=]
Line 155 ⟶ 126:
end
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at
return false;
end
local patterns = { -- patterns that look like
'%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$', -- one character hostname and
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}
Line 171 ⟶ 142:
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
end
end
Line 186 ⟶ 157:
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
returns true if the scheme and domain parts of a
This function is the last step in the validation process. This function is separate because there are cases that
Line 195 ⟶ 166:
local function is_url (scheme, domain)
if utilities.is_set (scheme) then
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when
end
end
Line 205 ⟶ 176:
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
Split a
First remove Fully Qualified Domain Name terminator (a dot following
If protocol
When not protocol
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 223 ⟶ 197:
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
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); if utilities.is_set(authority) then
return scheme;
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 240 ⟶ 220:
--[[--------------------------< 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
Link parameters are to hold the title of a
# < > [ ] | { } _
except the underscore which is used as a space in wiki
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
|<param>-link= parameter is ok); else false when value appears to be a valid
]]
Line 259 ⟶ 239:
end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid
end
Line 268 ⟶ 248:
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
|<title>= may be
that condition exists
check <link> for inter-language interwiki-link prefix. prefix must be a MediaWiki-recognized language
code and must begin with a colon.
]]
Line 275 ⟶ 258:
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 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, { 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 294 ⟶ 285:
Determines whether a URL string appears to be valid.
First we test for space characters. If any are found, return false. Then split the
portions, or for protocol
portions of the
Because it is different from a standard
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 305 ⟶ 296:
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
return false;
end
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from
if 'news:' == scheme then -- special case for newsgroups
Line 316 ⟶ 307:
end
return is_url (scheme, domain); -- return true if value appears to be a valid
end
Line 323 ⟶ 314:
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
that use protocol
The frontier pattern prevents a match on interwiki
find bracketed
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 336 ⟶ 327:
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
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
elseif value:match ('%a%S*:%S+') then -- if bare
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
elseif value:match ('//%S+') then -- if protocol
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
end
return is_url (scheme, domain); -- return true if value appears to be a valid
end
Line 361 ⟶ 352:
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
if utilities.is_set(error_message) then
error_message = error_message .. ", "; -- ... add a comma space separator
end
error_message = error_message .. "|" .. k .. "="; -- add the failed parameter
end
end
if utilities.is_set (error_message) then
table.insert( z.message_tail, {
end
end
Line 382 ⟶ 373:
local function safe_for_url( str )
if str:match( "%[%[.-%]%]" ) ~= nil then
table.insert( z.message_tail, {
end
Line 404 ⟶ 395:
local base_url;
if not utilities.is_set ( label ) then
label = URL;
if utilities.is_set ( source ) then
error_str =
else
error( cfg.messages["bare_url_no_origin"] );
Line 413 ⟶ 404:
end
if not check_url( URL ) then
error_str =
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'});
URL = table.concat ({domain, path}); -- and reassemble
end
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a
if utilities.is_set (access) then
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
end
Line 438 ⟶ 429:
parameters in the citation.
added_deprecated_cat is a
]]
Line 445 ⟶ 436:
if not added_deprecated_cat then
added_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, {
end
end
--[[--------------------------< D I S C O U R A G E D _ P A R A M E T E R >------------------------------------
Categorize and emit an maintenance message when the citation contains one or more discouraged parameters. Only
one error message is emitted regardless of the number of discouraged parameters in the citation.
added_discouraged_cat is a Boolean declared in page scope variables above
]]
local function discouraged_parameter(name)
if not added_discouraged_cat then
added_discouraged_cat = true; -- note that we've added this category
table.insert( z.message_tail, { utilities.set_message ( 'maint_discouraged', {name}, true ) } ); -- add maint message
end
end
Line 452 ⟶ 460:
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
Apply kerning to open the space between the quote mark provided by the
mark contained in a |title= or |chapter= parameter's value.
Line 458 ⟶ 466:
"'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
Replaces
quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
Call this function for chapter titles, for website titles, etc.; not for book titles.
]=]
local function kern_quotes (str)
local cap = '';
local cap2 = '';
local wl_type, label, link;
wl_type, label, link = utilities.is_wikilink (str);
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
str = utilities.substitute (cfg.presentation['kern-wl-both'], str);
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = utilities.substitute (cfg.presentation['kern-wl-right'], str);
end
else -- plain text or [[L|D]]; text in label variable
label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if utilities.is_set (cap) then
label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = utilities.make_wikilink (link, label);
else
str = label;
Line 509 ⟶ 517:
--[[--------------------------< 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
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
|script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character
|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 523 ⟶ 531:
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
The prefix is checked for validity. If it is a valid
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
is not added. At this time there is no error message for this condition.
Line 534 ⟶ 542:
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
table.insert( z.message_tail, {
return ''; -- script_value was just the prefix so return empty string
end
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
if utilities.is_set (name) then
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if utilities.in_array (lang, cfg.script_lang_codes) then
utilities.add_prop_cat ('script_with_name', {name, lang})
else
table.insert( z.message_tail, {
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
table.insert( z.message_tail, {
lang = ''; -- invalid so set lang to empty string
end
else
table.insert( z.message_tail, {
end
script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is
return script_value;
Line 574 ⟶ 579:
local function script_concatenate (title, script, script_param)
if utilities.is_set (script) then
script = format_script_value (script, script_param); -- <bdi> tags, lang
if utilities.is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
Line 593 ⟶ 598:
local function wrap_msg (key, str, lower)
if not utilities.is_set ( str ) then
return "";
end
Line 599 ⟶ 604:
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
return utilities.substitute ( msg, str );
else
return utilities.substitute ( cfg.messages[key], str );
end
end
--[[
label; nil else. str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
Line 617 ⟶ 623:
local wl_type, D, L;
local ws_url, ws_label;
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
wl_type, D, L = utilities.is_wikilink (str);
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
str, -- article title
});
ws_label = str; -- label for the
end
elseif 1 == wl_type then
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
str, -- article title
});
ws_label = str; -- label for the
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
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
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent
end
return ws_url, ws_label, L or D; -- return proper
end
--[[
Format the
and |trans-<periodical>= into a single Periodical meta-parameter. ]]
Line 668 ⟶ 675:
local periodical_error = '';
if not utilities.is_set (periodical) then
periodical = ''; -- to be safe for concatenation
else
periodical = utilities.wrap_style ('italic-title', periodical);
end
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang
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 ..
else -- here when
periodical = trans_periodical;
periodical_error = ' ' ..
end
end
Line 690 ⟶ 697:
--[[
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
and |chapter-url= into a single ]]
local function format_chapter_title (
local chapter_error = '';
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource
if ws_url then
ws_label = ws_label:gsub ('_', ' ');
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
chapter = utilities.wrap_style ('quoted-title', chapter);
end
end
chapter = script_concatenate (chapter,
if utilities.is_set (
chapter = external_link (
elseif ws_url then
chapter = external_link (ws_url, chapter .. ' ', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
if utilities.is_set (
if utilities.is_set (chapter) then
chapter = chapter ..
else -- here when
chapter =
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>
chapter_error = ' ' .. utilities.set_message ('err_trans_missing_title', {chapter_source});
end
end
return chapter .. chapter_error;
Line 742 ⟶ 747:
--[[
This function searches a parameter's value for
The search stops at the first match. This function will detect the visible replacement character when it is part of the
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(). Output of this function is an error message that identifies the character or the
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 parameter value. ]]
Line 760 ⟶ 766:
local function has_invisible_chars (param, v)
local position = ''; -- position of invisible char or starting position of stripmarker
local capture; -- used by stripmarker detection to hold name of the stripmarker
local stripmarker; -- boolean set true when a stripmarker is found
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
if capture ==
return;
end
local
local pattern =
position,
if position and (
if mw.ustring.find (v, cfg.indic_script) then --
position = nil; -- unset position
elseif cfg.emoji[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
position = nil; -- unset position
end
Line 783 ⟶ 789:
if position then
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
stripmarker = true; -- set a flag
elseif true == stripmarker and
position = nil; -- unset
else
local err_msg;
if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
err_msg = capture .. ' ' ..
else
err_msg =
end
table.insert
return; -- and done with this parameter
end
end
end
end
--[[
Argument wrapper. This function provides support for argument mapping defined
in the configuration file so that multiple names can be transparently aliased to
single internal variable. ]]
local function argument_wrapper ( args )
local origin = {};
return setmetatable({
ORIGIN = function ( self, k )
local dummy = self[k];
return origin[k];
end
Line 829 ⟶ 835:
if type( list ) == 'table' then
v, origin[k] = utilities.select_one ( args, list, '
if origin[k] == nil then
origin[k] = '';
end
elseif list ~= nil then
Line 843 ⟶ 849:
-- Empty strings, not nil;
if v == nil then
v =
origin[k] = '';
end
Line 854 ⟶ 860:
--[[--------------------------< 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: DOES NOT yet support MMMM YYYY or any of the date ranges.
Line 864 ⟶ 871:
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 879 ⟶ 886:
--[[--------------------------< 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 (|type=none). ]]
local function set_titletype (cite_class, title_type)
if utilities.is_set (title_type) then
if
title_type =
end
return title_type; -- if |type= has been set to any other value use that value
Line 900 ⟶ 909:
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
Converts a hyphen to a dash under certain conditions. The hyphen must separate
like items; unlike items are returned unmodified. These forms are modified:
letter - letter (A - B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and
digit is supported – a.1-a.5 or a-1-a-5) digitletter - digitletter (5a - 5d) (an optional separator between letter and
digit is supported – 5.a-5.d or 5-a-5-d) any other forms are returned unmodified.
Line 915 ⟶ 926:
local function hyphen_to_dash( str )
if not utilities.is_set (str) then
return str;
end
local accept; -- Boolean
str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split
str = str:gsub ('-', '-'); -- replace HTML numeric entity with hyphen character
str = str:gsub ('&
local out = {};
Line 931 ⟶ 941:
for _, item in ipairs (list) do -- for each item in the list
item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter)
Line 939 ⟶ 950:
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous
end
end
table.insert (out, item); -- add the (possibly modified) item to the output table
end
temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out
if accept then
temp_str = utilities.has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value
return temp_str;
else
return temp_str; -- else, return assembled temp_str
end
end
--[[--------------------------< S A F E _ J O I N >
Joins a sequence of strings together while checking for duplicate separation characters.
Line 957 ⟶ 974:
local function safe_join( tbl, duplicate_char )
local f = {}; -- create a function table appropriate to type of '
if 1 == #duplicate_char then -- for single byte
f.gsub = string.gsub
f.match = string.match
f.sub = string.sub
else -- for multi-byte characters use the ustring library functions
f.gsub = mw.ustring.gsub
f.match = mw.ustring.match
f.sub = mw.ustring.sub
end
Line 978 ⟶ 995:
str = value; -- assign value to it (first time through the loop)
elseif value ~= '' then
if value:sub(1, 1) == '<' then --
comp = value:gsub( "%b<>", "" ); -- remove
else
comp = value;
end
-- typically duplicate_char is sepc
if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
-- Because individual string segments often (always?) begin with terminal punct for the
-- preceding segment: 'First element' .. 'sepc next element' .. etc.?
trim = false;
end_chr = f.sub(str, -1, -1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr .. ")"
if end_chr == duplicate_char then -- if same as separator
str = f.sub(str, 1, -2);
elseif end_chr == "'" then -- if it might be
if f.sub(str, -3, -1) == duplicate_char .. "''" then
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''
trim = true; -- why? why do this and next differently from previous?
elseif f.sub(str, -4, -1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''
trim = true; -- same question
end
elseif end_chr == "]" then -- if it might be
if f.sub(str, -3, -1) == duplicate_char .. "]]" then
trim = true;
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then
trim = true;
elseif f.sub(str, -2, -1) == duplicate_char .. "]" then
trim = true;
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
end
elseif end_chr == " " then -- if last char of output string is a space
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = f.sub(str, 1, -3);
end
end
if trim then
if value ~= comp then -- value does not equal comp when value contains
local dup2 = duplicate_char;
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows
else
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
Line 1.027 ⟶ 1.044:
end
end
str = str .. value;
end
end
Line 1.034 ⟶ 1.051:
--[[--------------------------< I S _ S U F F I X >
returns true is suffix is properly formed Jr, Sr, or ordinal in the range
Puncutation not allowed. ]]
local function is_suffix (suffix)
if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
Line 1.048 ⟶ 1.066:
--[[
For Vancouver
(read ASCII) characters. When a name uses characters that contain diacritical 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 [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 1.061 ⟶ 1.082:
[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/) |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 was written
gets confused between character insertion point and cursor position. The test has of the \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
Line 1.077 ⟶ 1.102:
]]
local function is_good_vanc_name (last, first, suffix, position)
if not suffix then
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
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
end
end
if utilities.is_set (suffix) then
if not is_suffix (suffix) then
add_vanc_error (
return false; -- not a name with an appropriate suffix
end
Line 1.088 ⟶ 1.117:
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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%'%.]*$") then
add_vanc_error (cfg.err_msg_supl['non-Latin
return false; -- not a string of
end;
return true;
Line 1.097 ⟶ 1.126:
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period.
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered
as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. This code only accepts and understands generational suffix in the Vancouver format
because Roman numerals look like, and can be mistaken for, initials. This function uses ustring functions because firstname initials may be any of the
Unicode Latin characters accepted by is_good_vanc_name (). ]]
local function reduce_to_initials(first, position)
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
if not name then -- if not initials and a suffix
name = mw.ustring.match(first, "^(%u+)$"); -- is it just
end
Line 1.121 ⟶ 1.154:
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error (
return first; -- and return first unmolested
end
Line 1.129 ⟶ 1.162:
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 1.145 ⟶ 1.177:
end
if 3 > i then
table.insert (initials, mw.ustring.sub(names[i], 1, 1));
end
i = i + 1; -- bump the counter
end
Line 1.154 ⟶ 1.186:
--[[--------------------------< L I S T
Formats a list of people (
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
if 'vanc' == format then -- Vancouver-like
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
else
sep = cfg.presentation['sep_nl']; -- name-list separator between
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
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 utilities.is_set (maximum) and i > maximum then
etal = true;
break;
end
local n = tonumber (mask); -- convert to a number if it can be converted; nil else
if n then
one = 0 ~= n and string.rep("—", 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)
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 (
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, nil, i) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials (first, i)
end
end
one = one .. namesep .. first;
end
end
if utilities.is_set (person.link) then
one = utilities.make_wikilink (person.link, one); -- link author/editor
end
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
table.insert (name_list, one); -- add it to the list of names
table.insert (name_list, sep_one); -- add the proper name-list separator
end
end
end
local count = #
if
if
if 'amp' == format then
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
elseif 'and' == format then
if 2 == count then
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
else
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
end
end
end
end
local result = table.concat (
if etal and utilities.is_set (result) then
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've
end
return result, count; -- return name-list string and count of number of names (count used for editor names only)
end
--[[--------------------< 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.
namelist is one of the contributor-, author-, or editor-name lists chosen in that
order. year is Year or anchor_year.
]]
local function make_citeref_id (namelist, year)
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
names[i] = v.last
if i == 4 then break end -- if four then done
end
table.insert (names, year);
local id = table.concat(names);
if utilities.is_set (id) then
return "CITEREF" .. id;
else
return '';
end
end
--[[
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
it may have been set by previous passes through this function or by the associated
|display-<names>=etal parameter ]]
Line 1.269 ⟶ 1.324:
local function name_has_etal (name, etal, nocat, param)
if utilities.is_set (name) then
local patterns = cfg.et_al_patterns; -- get patterns from configuration
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
Line 1.277 ⟶ 1.332:
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
if not nocat then -- no categorization for |vauthors=
table.insert( z.message_tail, {
end
end
Line 1.283 ⟶ 1.338:
end
return name, etal;
end
--[[
Add maint cat when name parameter value does not contain letters. Does not catch
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
current version of this test but |first=(1888) is caught.
returns nothing
]]
local function name_is_numeric (name, list_name)
if utilities.is_set (name) then
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
end
end
end
--[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------
Evaluates the content of author and editor parameters for extraneous editor annotations:
ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and
are redundant in editor parameters. If found, the function adds the editor markup
maintenance category.
returns nothing
]]
local function name_has_ed_markup (name, list_name)
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
if utilities.is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
break;
end
end
end
end
--[[
Evaluates the content of
Multiple names are indicated if there is more than one comma
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
if utilities.is_set (name) then
_,
_, 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 (' ',''); -- count nbsps
-- There is exactly 1 semicolon per entity, so subtract nbsps
-- from semicolons to 'escape' them. If additional entities are added,
-- they also can be subtracted.
if 1 < commas or 0 < (semicolons - nbsps) then
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
end
end
end
--[[
This function calls various name checking functions used to validate the content
of the various name-holding parameters.
]]
local function name_checks (last, first, list_name)
local accept_name;
if utilities.is_set (last) then
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
if not accept_name then -- <last> not wrapped in accept-as-written markup
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
end
end
if utilities.is_set (first) then
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
if not accept_name then -- <first> not wrapped in accept-as-written markup
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
end
end
return last, first; -- done
--[[
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. Stops searching found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the 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= 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 that will cause list_people() 'et al.' out of the template's metadata. When this occurs,
]]
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;
while true do
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], '
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], '
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], '
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], '
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last, first = name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks
if first and not last then -- if there is a firstn without a matching lastn
table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', {
first_alias, -- param name of alias missing its mate
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
count = count + 1; -- number of times we haven't found last and first
Line 1.404 ⟶ 1.507:
end
else -- we have last with or without a first
local result;
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
if first then
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper 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
table.insert( z.message_tail, {
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
Line 1.416 ⟶ 1.523:
end
return names, etal; -- all done, return our list of names and the etal flag
end
--[[
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
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, match, we return the original language name string.
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of
languages that in some cases may include extensions. For example, code 'cbk-zam' code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a
'language' codes per se, rather they are used as sub-domain names: cbk-zam.wikipedia.org.
A list of language names and codes supported by fetchLanguageNames() can be found Names 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 WikiMedia language name. Some language names have multiple entries under different codes:
Line 1.452 ⟶ 1.564:
end
local ietf_code; -- because some languages have both
local ietf_name;
local langlc = mw.ustring.lower (lang); -- lower-case version for comparisons
for code, name in pairs (cfg.languages) do
if langlc == mw.ustring.lower (name) then
if 2 == #code
return name, code; -- so return the name and the code
end
ietf_code = code; -- remember that we found an
ietf_name = name; -- but keep looking for a 2- or 3-char code
end
end
-- didn't find name with 2- or 3-char code; if
return ietf_code and ietf_name or lang; -- associated name; return original language text else
end
--[[
Gets language name from a provided two- or three-character ISO 639 code. If a code
is recognized by MediaWiki, use the returned name; if not, then use the value that
was provided with the language parameter. When |language= contains a recognized language (either code or name), the page is
assigned to the category for that code: Category:Norwegian-language sources (no).
For valid three-character code languages, the page is assigned to the single category Languages that are the same as the local wiki are not categorized. MediaWiki does
not recognize three-character equivalents of two-character codes: code 'ar' is
recognized This function supports multiple languages in the form |language=nb, French, th
where the language names or codes are separated from each other by commas with optional space characters.
]]
Line 1.496 ⟶ 1.610:
local names_table = {}; -- table made from the value assigned to |language=
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
Line 1.504 ⟶ 1.618:
if name then -- there was a remapped code so
if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip
end
else
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
Line 1.516 ⟶ 1.628:
end
if utilities.is_set (name) then
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, cfg.this_wiki_code);
end
if utilities.is_set (code) then
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if 2 == code:len() then -- and is a two-character code
utilities.add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character code)
utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support
end
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled
utilities.add_prop_cat ('local_lang_source', {name, code});
end
else
end
Line 1.541 ⟶ 1.653:
name = ''; -- so we can reuse it
end
name = utilities.make_sep_list (#language_list, language_list);
if this_wiki_name == name then
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
Line 1.558 ⟶ 1.665:
end
--[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
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_cs_style (postscript, mode)
if utilities.is_set(postscript) then
-- emit a maintenance message if user postscript is the default cs1 postscript
-- 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['
end
--[[--------------------------< S E T _ S T Y L E >-----------------------------
Sets the separator and postscript styles. Checks the |mode= first and the
#invoke CitationClass second. Removes the postscript if postscript == none.
]]
local function set_style (mode, postscript, cite_class)
local sep;
if 'cs2' == mode then
sep,
elseif 'cs1' == mode then
sep,
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
-- emit a maintenance message if user postscript is the default cs2 postscript
-- we catch the opposite case for cs1 in set_cs_style
if 'cs2' == mode or 'citation' == cite_class then
utilities.set_message ('maint_postscript');
end
postscript = '';
end
return sep,
end
--[=[-------------------------< 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 true if file extension is one of the recognized extensions, else false
Line 1.655 ⟶ 1.728:
--[[--------------------------< S T Y L E _ F O R M A T >
Applies
if the format parameter does not have a matching
is not set and the the appropriate styling.
Line 1.665 ⟶ 1.739:
local function style_format (format, url, fmt_param, url_param)
if utilities.is_set (format) then
format = utilities.wrap_style ('format', format);
if not utilities.is_set (url) then
format = format ..
end
elseif is_pdf (url) then -- format is not set so if
format = utilities.wrap_style ('format', 'PDF');
else
format = ''; -- empty string for concatenation
Line 1.679 ⟶ 1.753:
--[[
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.
When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
return the number and the previous state of the 'etal' flag (false by default
but may have been set 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
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 1.702 ⟶ 1.776:
]]
local function get_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 1.710 ⟶ 1.784:
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
max = nil;
end
else -- not a valid keyword or number
table.insert( z.message_tail, {utilities.set_message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
Line 1.722 ⟶ 1.797:
--[[
Adds
some form of p. or pp. abbreviation in the first characters of the parameter content.
check
good pattern: '^P[^%.P%l]' matches when
where x and X are letters and # is a bad pattern: '^[Pp][
]]
local function extra_text_in_page_check (
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
if val:match (pattern) then -- when a match, error so
table.insert (z.message_tail, {utilities.set_message ('err_extra_text_pages', {name}, true)}); -- add error message
return; -- and done
end
end
end
end
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
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
table.insert (z.message_tail, {utilities.set_message (handler, {name}, true)}); -- add error message
return; -- and done
end
end
end
Line 1.746 ⟶ 1.866:
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled
rendered citation and in the metadata. Individual author names may be wikilinked
Line 1.755 ⟶ 1.875:
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
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
local name = name_table[i];
i = i + 1;
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled
break; -- and done reassembling so
end
i = i + 1;
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = utilities.is_wikilink (name_table[i]);
table.insert (output_table, label); -- add this name
if 1 == wl_type then
Line 1.781 ⟶ 1.901:
end
end
i = i + 1;
end
return output_table;
Line 1.794 ⟶ 1.914:
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
tests, are wrapped in doubled
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the
]]
Line 1.814 ⟶ 1.934:
for i, v_name in ipairs(v_name_table) do
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
local accept_name;
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
if accept_name then
last = v_name;
corporate = true; -- flag used in list_people()
elseif string.find(v_name, "%s") then
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
add_vanc_error (
end
local lastfirstTable = {}
lastfirstTable = mw.text.split(v_name, "%s+")
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
suffix = first; -- not initials so assume that whatever we got is a generational suffix
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end
last = table.concat(lastfirstTable,
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);
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error (
end
else
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
if utilities.is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error (
end
is_good_vanc_name (last, first, suffix, i);
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 1.852 ⟶ 1.980:
else
if not corporate then
is_good_vanc_name (last, '', nil, i);
end
end
link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], '
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], '
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 1.867 ⟶ 1.995:
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
Line 1.878 ⟶ 2.006:
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors
]]
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
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
(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 1.900 ⟶ 2.028:
err_name = 'editor';
end
table.insert( z.message_tail, {
{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 1.914 ⟶ 2.042:
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
of allowable values (yes, y, true, live, dead, etc.). When the parameter value has not been assigned a value (missing
or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one
of the list of allowed values returns the translated value; else, emits an error message and returns the value
Line 1.922 ⟶ 2.050:
local function is_valid_parameter_value (value, name, possible, ret_val)
if not utilities.is_set (value) then
return ret_val; -- an empty parameter is ok
elseif utilities.in_array (value, possible) then
return cfg.keywords_xlate[value]; -- return translation of parameter keyword
else
table.insert( z.message_tail, {
return ret_val;
end
Line 1.943 ⟶ 2.071:
local function terminate_name_list (name_list, sepc)
if (string.sub (name_list, -3, -1) == sepc .. '. ') then
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
end
end
Line 1.961 ⟶ 2.089:
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not utilities.is_set (volume) and not utilities.is_set (issue) then
return '';
end
if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if utilities.is_set (volume) and utilities.is_set (issue) then
return wrap_msg ('vol-no', {sepc, hyphen_to_dash (volume), issue}, lower);
elseif utilities.is_set (volume) then
return wrap_msg ('vol', {sepc, hyphen_to_dash (volume)}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
Line 1.975 ⟶ 2.103:
end
if 'podcast' == cite_class and utilities.is_set (issue) then
return wrap_msg ('issue', {sepc, issue}, lower);
end
Line 1.981 ⟶ 2.109:
local vol = ''; -- here for all cites except magazine
if utilities.is_set (volume) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc,
elseif (4 < mw.ustring.len(volume)) then -- not all digits or
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)});
utilities.add_prop_cat ('long_vol');
else -- four or less characters
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold
end
end
if utilities.is_set (issue) then
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
end
return vol;
Line 2.010 ⟶ 2.138:
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
if utilities.is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
Line 2.016 ⟶ 2.144:
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif utilities.is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
Line 2.025 ⟶ 2.153:
end
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
if utilities.is_set (page) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif utilities.is_set (pages) then
if is_journal then
return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', '';
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
Line 2.055 ⟶ 2.183:
returns one of the in-source locators: page, pages, or at.
If any of these are interwiki links to
for use in COinS. This COinS thing is done because here we convert an interwiki
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it?
Line 2.066 ⟶ 2.194:
]]
local function insource_loc_get (page, page_orig, pages, pages_orig, at)
local ws_url, ws_label, coins_pages, L; -- for
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);
ws_url, ws_label, L = wikisource_url_make (page); -- make ws
if ws_url then
page = external_link (ws_url, ws_label .. ' ', '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);
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws
if ws_url then
pages = external_link (ws_url, ws_label .. ' ', '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
if ws_url then
at = external_link (ws_url, ws_label .. ' ', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
Line 2.106 ⟶ 2.234:
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
table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)}); -- add error message
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
end
end
return archive, date;
end
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
Check archive.org
save snapshot
archive.org saves a snapshot of the target page in the
unwitting readers to do.
When the archive.org
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
|archive-url= is an archive.org
correct place
otherwise returns |archive-url= and |archive-date=
There are two mostly compatible archive.org
//web.archive.org/<timestamp>... -- the old form
//web.archive.org/web/<timestamp>... -- the new form
Line 2.133 ⟶ 2.277:
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
archive
for save command errors, return undated wildcard (/*/)
for timestamp errors when the timestamp has a wildcard, return the
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
Line 2.143 ⟶ 2.287:
local function archive_url_check (url, date)
local err_msg = ''; -- start with the error message empty
local path, timestamp, flag; -- portions of the archive.
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine
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
err_msg =
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
elseif url:match('//liveweb%.archive%.org/') then
err_msg =
else
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the
if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then
err_msg =
if '*' ~= flag then
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif utilities.is_set (path) and 'web/' ~= path then
err_msg =
elseif utilities.is_set (flag) and not utilities.is_set (path) then
err_msg =
elseif utilities.is_set (flag) and not flag:match ('%a%a_') then
err_msg =
else
return url, date; -- return
end
end
-- if here, something not right so
table.insert( z.message_tail, {
if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for
else
return url, date; -- preview mode so return
end
end
Line 2.185 ⟶ 2.329:
check |place=, |publication-place=, |location= to see if these params include digits. This function added because
many editors
returns the original parameter value without modification; added maint cat when parameter value contains digits
Line 2.192 ⟶ 2.336:
local function place_check (param_val)
if not utilities.is_set (param_val) then
return param_val; -- return that empty state
end
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value
end
return param_val; -- and done
end
--[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------
compares |title= value against list of known generic title patterns. Returns true when pattern matches; nil else
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
index [1]. index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so
that we don't run out of processing time on very large articles.
]]
local function is_generic_title (title)
title = mw.ustring.lower(title); -- switch title to lower case
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then
return true; -- found English generic title so done
elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script
return true; -- found local generic title so done
end
end
end
end
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
compares |title= to 'Archived copy' (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 2.210 ⟶ 2.398:
]]
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.
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 Collaboration = A['Collaboration'];
Line 2.235 ⟶ 2.420:
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
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=
end
end
if utilities.is_set (Collaboration) then
author_etal = true; -- so that |display-authors=etal not required
end
end
local editor_etal;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'],
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
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
end
end
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
local Chapter_origin = A:ORIGIN ('Chapter');
local
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
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
table.insert( z.message_tail, {
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
table.insert( z.message_tail, {
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'], '
table.insert( z.message_tail, {
end
Contribution = nil; -- unset
end
local Title = A['Title'];
local TitleLink = A['TitleLink'];
local
local accept_link;
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords
auto_select = TitleLink; -- remember selection for later
TitleLink = ''; -- treat as if |title-link= would have been empty
end
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used
if 'map' == config.CitationClass and 'section' == Chapter_origin then
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}}
Chapter = ''; -- unset for now; will be reset later from |map= if present
end
local Periodical = A['Periodical'];
local Periodical_origin = '';
end
end
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}}
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error
table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
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
-- 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
table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
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, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif utilities.is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
Line 2.392 ⟶ 2.539:
Volume = A['Volume']; -- and does for non-'periodical' cites
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then
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, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
Issue = hyphen_to_dash (A['Issue']);
end
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
Issue = hyphen_to_dash (A['Issue']);
end
end
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
local
local Pages;
local At;
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Pages = hyphen_to_dash (A['Pages']);
Line 2.420 ⟶ 2.572:
local PublisherName = A['PublisherName'];
local PublisherName_origin = A:ORIGIN('PublisherName');
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)});
end
end
local Newsgroup_origin = A:ORIGIN('Newsgroup');
if 'newsgroup' == config.CitationClass then
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
if utilities.is_set (error_text) then
table.insert( z.message_tail, {error_text, error_state} );
end
end
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
end
local URL = A['URL']
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then
UrlAccess = nil;
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
end
local ChapterURL = A['ChapterURL'];
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
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);
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
no_tracking_cats = "true"; -- set no_tracking_cats
end
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
if this_page.text:match (v) then -- test page name against each pattern
no_tracking_cats = "true"; -- set no_tracking_cats
Line 2.510 ⟶ 2.630:
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;
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 utilities.is_set (PublicationPlace) and utilities.is_set (Place) then
utilities.add_prop_cat ('location test');
if PublicationPlace == Place then
Place = ''; -- unset; don't need both if they are the same
end
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then
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
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=
|trans-title= maps to |trans-chapter= when |title= is re-mapped
|url= maps to |
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
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
Encyclopedia = nil; -- unset because not supported by this template
end
end
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error
table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
end
if utilities.is_set (Encyclopedia) then
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
Periodical_origin = A:ORIGIN ('Encyclopedia');
end
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then
if not utilities.is_set (Chapter) then
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title=
ScriptChapter = ScriptTitle;
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL_origin = URL_origin;
ChapterUrlAccess = UrlAccess;
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
Chapter = utilities.make_wikilink (TitleLink, Chapter);
end
Title = Periodical;
Line 2.573 ⟶ 2.717:
ScriptTitle = '';
end
elseif utilities.is_set (Chapter) then
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title=
Periodical = ''; -- redundant so unset
end
Line 2.580 ⟶ 2.724:
end
--
local ID = A['ID'];
if (config.CitationClass == "techreport") then -- special case for cite techreport
if utilities.is_set (A['Number']) then
if not utilities.is_set (ID) then
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
table.insert( z.message_tail, {
end
end
end
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local Conference = A['Conference'];
local BookTitle = A['BookTitle'];
local TransTitle_origin = A:ORIGIN ('TransTitle');
if 'conference' == config.CitationClass then
if utilities.is_set (BookTitle) then
Chapter = Title;
Chapter_origin = 'title';
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterFormat = Format;
TransChapter = TransTitle;
TransChapter_origin = TransTitle_origin;
Title = BookTitle;
Format = '';
--
TransTitle = '';
URL = '';
Line 2.618 ⟶ 2.762:
Conference = ''; -- not cite conference or cite speech so make sure this is empty string
end
-- CS1/2 mode
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 = "";
Line 2.625 ⟶ 2.776:
local Sheets = A['Sheets'] or '';
if config.CitationClass == "map" then
if utilities.is_set (Chapter) then
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
end
Chapter = A['Map'];
Chapter_origin = A:ORIGIN('Map');
ChapterURL = A['MapURL'];
TransChapter = A['TransMap'];
ScriptChapter = A['ScriptMap']
ChapterUrlAccess = MapUrlAccess;
Line 2.636 ⟶ 2.791:
Cartography = A['Cartography'];
if utilities.is_set ( Cartography ) then
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
end
Scale = A['Scale'];
if utilities.is_set ( Scale ) then
Scale = sepc .. " " .. Scale;
end
Line 2.646 ⟶ 2.801:
-- 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 SeriesLink = A['SeriesLink'];
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for
local Network = A['Network'];
Line 2.656 ⟶ 2.811:
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 '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
table.insert( z.message_tail, {
SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
end
-- assemble a table of parts concatenated later into Series
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ScriptChapter_origin = A:ORIGIN('ScriptTitle');
ChapterLink = TitleLink; -- alias |episode-link=
TransChapter = TransTitle;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURL_origin = URL_origin;
Title = Series; -- promote series to title
Line 2.692 ⟶ 2.842:
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
Chapter = utilities.make_wikilink (ChapterLink, Chapter);
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then
Series = utilities.make_wikilink (ChapterLink, Series);
end
URL = ''; -- unset
Line 2.704 ⟶ 2.854:
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);
end
end
-- end of {{cite episode}} stuff
-- handle type parameter for those CS1 citations that have default values
local TitleType = A['TitleType'];
local Degree = A['Degree'];
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
if utilities.is_set (Degree) and "Thesis" == TitleType then
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
end
end
if utilities.is_set (TitleType) then
TitleType = utilities.substitute ( cfg.messages['type'], TitleType);
-- TODO: Hack on TitleType to fix bunched parentheses problem
end
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
local Date = A['Date'];
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
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
Line 2.761 ⟶ 2.905:
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'], '');
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'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')},
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
['date'] = {val = Date, name = Date_origin},
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')},
['lay-date'] = {val = LayDate, name = A:ORIGIN ('LayDate')},
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')},
['year'] = {val = Year, name = A:ORIGIN ('Year')},
};
local error_list = {};
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
utilities.add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization
if utilities.is_set (Year) and utilities.is_set (Date) then
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
end
if
local modified = false; -- flag
if
modified = true;
end
if utilities.is_set (DF) then -- if we need to reformat dates
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
modified = true;
end
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
--
--
--
if modified then -- if the date_parameters_list values were modified
Line 2.822 ⟶ 2.986:
end
else
table.insert
end
end -- end of do
local ID_list = {}; -- sequence table of rendered identifiers
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
local Class = 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);
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- 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 (
if
if identifiers.auto_link_urls[auto_select] then -- manual selection
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
URL = identifiers.auto_link_urls['doi'];
URL_origin = cfg.id_handlers['DOI'].parameters[1];
end
end
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url=
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message
AccessDate = ''; -- unset
end
end
Line 2.844 ⟶ 3.035:
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
-- Test if citation has no title
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
end
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Title = ''; -- set title to empty string
utilities.set_message ('maint_untitled'); -- add maint cat
end
check_for_url ({ -- add error message when any of these parameters hold a URL
['title'] = Title,
[A:ORIGIN('Chapter')] = Chapter,
[Periodical_origin] = Periodical,
[PublisherName_origin] = PublisherName
Line 2.876 ⟶ 3.061:
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 2.886 ⟶ 3.071:
coins_author = c; -- use that instead
end
local QuotePage = A['QuotePage'];
local QuotePages = hyphen_to_dash (A['QuotePages']);
-- this is the function call to COinS()
local OCinSoutput = metadata.COinS({
['Periodical'] = utilities.strip_apostrophe_markup (Periodical),
['Encyclopedia'] =
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter),
['Degree'] = Degree; -- cite thesis only
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle),
['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,
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages},
['Edition'] = Edition,
['PublisherName'] = PublisherName or Newsgroup,
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['ID_list'] =
['RawPage'] = this_page.prefixedText,
}, config.CitationClass);
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
if utilities.in_array (config.CitationClass,
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
end
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
end
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.
do
local last_first_list;
local control = {
format =
maximum = nil, -- as if display-authors or display-editors not set
mode = Mode
};
do -- do editor name list first because the now unsupported coauthors used to modify control table
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
Line 2.957 ⟶ 3.142:
end
do -- now do interviewers
control.maximum
Interviewers = list_people (control, interviewers_list, interviewer_etal);
end
do -- now do translators
control.maximum
Translators = list_people (control, t, translator_etal);
end
do -- now do contributors
control.maximum
Contributors = list_people (control, c, contributor_etal);
end
do -- now do authors
control.maximum
last_first_list = list_people (control, a, author_etal);
if utilities.is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
Line 2.983 ⟶ 3.168:
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 2.989 ⟶ 3.174:
end
local ConferenceFormat = A['ConferenceFormat'];
local ConferenceURL = A['ConferenceURL'];
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', 'url');
-- special case for chapter format so no error message or cat when chapter not supported
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
if not utilities.is_set (URL) then
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
table.insert( z.message_tail, {
end
-- do we have |accessdate= without either |url= or |chapter-url=?
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then
table.insert( z.message_tail, {
AccessDate = '';
end
end
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], '');
local OriginalURL
local OriginalURL_origin
local OriginalFormat
local OriginalAccess;
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
if utilities.is_set ( ArchiveURL ) then
if utilities.is_set (ChapterURL) then
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalFormat = ChapterFormat; -- and original |chapter-format=
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived
end
elseif utilities.is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalFormat = Format; -- and original |format=
OriginalAccess = UrlAccess;
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
URL = ArchiveURL -- swap-in the archive's
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived
end
end
end
if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
local chap_param;
if utilities.is_set (Chapter) then
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 =
else utilities.is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
if utilities.is_set (chap_param) then
table.insert( z.message_tail, {
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
Line 3.070 ⟶ 3.256:
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 utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
Chapter = format_chapter_title (ScriptChapter,
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 = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
-- Format main title
local plain_title = false;
local accept_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
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', '');
end
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
end
if is_generic_title (Title) then
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message
end
end
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from
Title = utilities.wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang
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
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
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle);
end
local TransError = "";
if utilities.is_set (TransTitle) then
if utilities.is_set (Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " ..
end
end
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
if
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both
TitleLink = ''; -- unset
end
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format;
URL = ''; -- unset these because no longer needed
Format = "";
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. ' ', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink)
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1'));
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 .. ' ', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Line 3.160 ⟶ 3.365:
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 utilities.is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif utilities.is_set (ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil,
end
if not utilities.is_set (Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
if utilities.is_set (Minutes) then
if utilities.is_set (Time) then
table.insert( z.message_tail, {
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if utilities.is_set (Time) then
local TimeCaption = A['TimeCaption']
if not utilities.is_set (TimeCaption) then
TimeCaption = cfg.messages['event'];
if sepc ~= '.' then
Line 3.201 ⟶ 3.408:
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
At = utilities.is_set (At) and (sepc .. " " .. At) or "";
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or "";
if config.CitationClass == 'map' then
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier
local Inset = A['Inset'];
if utilities.is_set ( Inset ) then
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
end
if utilities.is_set ( Sections ) then
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
elseif utilities.is_set ( Section ) then
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
end
Line 3.220 ⟶ 3.426:
end
local Others = A['Others'];
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
if config.CitationClass == "AV-media-notes"
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now
utilities.set_message ('maint_others_avm')
else
utilities.set_message ('maint_others');
end
end
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or "";
if utilities.is_set (Translators) then
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
end
if utilities.is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
local TitleNote =
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_edition')}); -- add error
end
Edition = " " .. wrap_msg ('edition', Edition);
Line 3.248 ⟶ 3.455:
end
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or "";
local Agency = A['Agency'];
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
if utilities.is_set (AccessDate) then
local retrv_text = " " .. cfg.messages['retrieved']
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = utilities.substitute (retrv_text, AccessDate);
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end
if "thesis" == config.CitationClass and utilities.is_set (Docket) then
ID = sepc .. " Docket " .. Docket .. ID;
end
if "report" == config.CitationClass and utilities.is_set (Docket) then
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set
end
if utilities.is_set (URL) then
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess );
end
local TransQuote = A['TransQuote'];
local ScriptQuote = A['ScriptQuote'];
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 = 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
-- the quote parameters. We'd otherwise emit a message even if there wasn't
-- a displayed postscript.
-- TODO: Should the max size (1) be configurable?
-- 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
ArchiveDate =
end
if "live" == UrlStatus then
arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not utilities.is_set (OriginalURL) then
Archived = Archived .. " " ..
end
elseif utilities.is_set (OriginalURL) then
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
arch_text = cfg.messages['archived-unfit'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
if 'bot: unknown' == UrlStatus then
else
end
else -- UrlStatus is empty, 'dead'
arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{ external_link( OriginalURL, cfg.messages['original'],
end
else -- OriginalUrl not set
arch_text = cfg.messages['archived-missing'];
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. utilities.substitute ( arch_text,
{
end
elseif utilities.is_set (ArchiveFormat) then
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
else
Line 3.331 ⟶ 3.588:
local Lay = '';
local LaySource = A['LaySource'];
local LayURL = A['LayURL'];
local LayFormat = A['LayFormat'];
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
if utilities.is_set (LayURL) then
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end
if utilities.is_set (LaySource) then
LaySource = " – ''" .. utilities.safe_for_italics (LaySource) .. "''";
else
LaySource = "";
Line 3.343 ⟶ 3.604:
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
elseif utilities.is_set (LayFormat) then
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message
end
local TranscriptURL = A['TranscriptURL']
local TranscriptFormat = A['TranscriptFormat'];
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,
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 3.372 ⟶ 3.638:
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 .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin);
else
Periodical = format_periodical (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
Line 3.387 ⟶ 3.665:
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
if utilities.is_set (Periodical) then
if utilities.is_set (Conference) then
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
Line 3.401 ⟶ 3.679:
local tcommon2; -- used for book cite when |contributor= is set
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
if utilities.is_set (Contributors) then
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Line 3.413 ⟶ 3.691:
elseif 'map' == config.CitationClass then -- special cases for cite map
if utilities.is_set (Chapter) then
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif utilities.is_set (Periodical) then
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
else -- a sheet or stand-alone map
Line 3.435 ⟶ 3.713:
end
local Via = A['Via'];
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
Line 3.445 ⟶ 3.725:
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
local OrigDate = A['OrigDate'];
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
if utilities.is_set (Date) then
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses
else -- neither of authors and editors set
if (string.sub(tcommon, -1, -1) == sepc) then
Date = " " .. Date ..
else
Date = sepc .. " " .. Date ..
end
end
end
if utilities.is_set (Authors) then
if (not utilities.is_set (Date)) then
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
if utilities.is_set (Editors) then
local in_text = " ";
local post_text = "";
if utilities.is_set (Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then
Line 3.476 ⟶ 3.758:
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
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
if utilities.is_set (Editors) and utilities.is_set (Date) then
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if (not utilities.is_set (Date)) then
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
Line 3.490 ⟶ 3.772:
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif utilities.is_set (Editors) then
if utilities.is_set (Date) then
if EditorCount <= 1 then
Editors = Editors .. ", " .. cfg.messages['editor'];
Line 3.506 ⟶ 3.788:
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc );
else
Line 3.513 ⟶ 3.795:
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
local options = {};
if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref=
else
options.class =
end
local Ref = A['Ref'];
if 'harv' == Ref then -- need to check this before setting to default
utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value
elseif not utilities.is_set (Ref) then
Ref = 'harv'; -- set as default when not set externally
end
if 'none' ~= cfg.keywords_xlate[Ref:lower()] then
local id = Ref
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 citeref_id
citeref_id = make_citeref_id (namelist, year); -- go make the CITEREF anchor
else
citeref_id = ''; -- unset
end
if citeref_id == Ref then
utilities.set_message ('maint_ref_duplicates_default');
end
if 'harv' == Ref then
id = citeref_id
end
options.id = id;
end
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then -- remove <span> tags and other
z.error_categories = {};
text =
z.message_tail = {};
end
Line 3.560 ⟶ 3.852:
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if utilities.is_set (options.id) then
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
if 0 ~= #z.message_tail then
table.insert (render, ' ');
for i,v in ipairs( z.message_tail ) do
if utilities.is_set (v[1]) then
if i == #z.message_tail then
table.insert (render, utilities.error_comment ( v[1], v[2] ));
else
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] ));
end
end
Line 3.587 ⟶ 3.879:
table.insert (maint, v); -- maint msg is the category name
table.insert (maint, ' ('); -- open the link text
table.insert (maint,
table.insert (maint, ')'); -- and close it
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
end
table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
end
if not no_tracking_cats then
for _, v in ipairs( z.error_categories ) do -- append error categories
table.insert (render,
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
table.insert (render,
end
for _, v in ipairs( z.properties_cats ) do -- append properties categories
table.insert (render,
end
end
Line 3.623 ⟶ 3.913:
]]
local function validate (name, cite_class, empty)
local name = tostring (name);
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#'
local state;
local function state_test (state, name) -- local function to do testing of state values
if true == state then return true; end -- valid actively supported parameter
if false == state then
if empty then return nil; end -- empty deprecated parameters are treated as unknowns
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
if 'discouraged' == state then
discouraged_parameter (name); -- parameter is discouraged but still supported
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
state = whitelist.limited_numbered_arguments[
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
if true == state_test (state, name) then return true; end
-- all enumerated parameters allowed
state = whitelist.numbered_arguments[
if true == state_test (state, name) then return true; end
return false; -- not supported because not found or name is set to nil
end
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
check <value> for inter-language interwiki-link markup. <prefix> must be a MediaWiki-recognized language
code. when these values have the form (without leading colon):
[[<prefix>:link|label]] return label as plain-text
[[<prefix>:link]] return <prefix>:link as plain-text
return value as is else
]=]
local function inter_wiki_check (parameter, value)
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
local _;
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
end
return value;
end
Line 3.679 ⟶ 3.994:
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
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. 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
tags are removed before the search.
Line 3.691 ⟶ 4.006:
local function missing_pipe_check (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {
end
end
Line 3.707 ⟶ 4.022:
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
if cfg.punct_skip[param] then
return; -- parameter name found in the skip table so done
Line 3.712 ⟶ 4.032:
if value:match ('[,;:]$') then
end
end
Line 3.724 ⟶ 4.044:
local function citation(frame)
Frame = frame; -- save a copy
local pframe = frame:getParent()
local
if nil ~= string.find (frame:getTitle(), 'igralište', 1, true) then -- did the {{#invoke:}} use sandbox version?
Line 3.745 ⟶ 4.065:
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
end
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
local args = {}; -- table where we store all of the template's arguments
Line 3.788 ⟶ 4.079:
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;
--
end
local capture; -- the single supported capture when matching unknown parameters using patterns
local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing
for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame
v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
if v ~= '' then
if ('string' == type (k)) then
Line 3.802 ⟶ 4.095:
error_text = "";
if type( k ) ~= 'string' then
--
if v:match("%S+") ~= nil then
error_text, error_state =
end
elseif validate( k:lower(), config.CitationClass ) then
error_text, error_state =
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
Line 3.817 ⟶ 4.110:
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
if capture then -- if the pattern matches
param = utilities.substitute (param, capture);
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 =
else
error_text, error_state =
v = ''; -- unset
end
end
end
if not utilities.is_set (error_text) then
if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
error_text, error_state =
else
error_text, error_state =
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
Line 3.841 ⟶ 4.134:
end
end
elseif
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list
end
-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
-- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
-- 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
table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
1 == #empty_unknowns and '' or 's',
utilities.make_sep_list (#empty_unknowns, empty_unknowns)
}, true )});
end
for k, v in pairs( args ) do
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
end
return table.concat ({
frame:extensionTag ('templatestyles', '', {src=styles}) citation0( config, args)
});
end
|