Anonymous user
Module:Citation/CS1: Difference between revisions
try again; vauthors generational suffix fix;
m (1 revision imported: Math) |
(try again; vauthors generational suffix fix;) |
||
Line 1:
local
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
local
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
add_maint_cat, wrap_style, safe_for_italics, remove_wiki_link;
local z ={}; -- tables in Module:Citation/CS1/Utilities
local extract_ids, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
local make_coins_title, get_coins_pages, COinS; -- 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 >--------------------------------------
delare variables here that have page-wide scope
]]
local Preview_mode = false; -- flag indicating that we are rendering a preview page (Show preview button)
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Locates and returns the first set value in a table of values where the order established in the table,
left-to-right (or top-to-bottom), is the order in which the values are evaluated. Returns nil if none are set.
This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs. With the pairs
version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate
the for-loop before it reached the actual end of the list.
]]
local function first_set (
local
while i <= count do -- loop through all items in list
if is_set(
return list[i]; -- return the first set list member
end
i = i + 1; -- point to next
end
end
--[[--------------------------<
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
]]
local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
local function add_prop_cat (key, arguments)
if not added_prop_cats [key] then
added_prop_cats [key] = true; -- note that we've added this category
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
--[[--------------------------<
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
]]
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
local function add_vanc_error (source)
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } );
end
end
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it
is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
Scheme names consist of a sequence of characters beginning with a
letter and followed by any combination of letters, digits, plus
("+"), period ("."), or hyphen ("-").
returns true if it does, else false
]]
local function is_scheme (scheme)
return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
end
--[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
Does this thing that purports to be a domain name seem to be a valid domain name?
Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5
BNF defined here: https://tools.ietf.org/html/rfc4234
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 tlds: https://www.iana.org/domains/root/db
rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between
the first and last characters the name may use letters, digits, and the hyphen.
Also allowed are IPv4 addresses. IPv6 not supported
domain is expected to be stripped of any path so that the last character in the last character of the tld. tld
is two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be stripped
here. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.
There are several tests:
the first character of the whole domain name including subdomains must be a letter or a digit
internationalized domain name (ascii characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the tld) see https://tools.ietf.org/html/rfc3490
single-letter/digit second-level domains in the .org TLD
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
single-letter SL domains in the ccTLDs (where the ccTLD is two letters)
two-character SL domains in gTLDs (where the gTLD is two or more letters)
three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)
IPv4 dot-decimal address format; TLD not allowed
returns true if domain appears to be a proper name and tld or IPv4 address, else false
]=]
local function is_domain_name (domain)
if not domain then
return false; -- if not set, abandon
end
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
return false;
end
-- Do most common case first
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
return true;
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
return true;
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
return true;
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
return true;
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
end
end
--[[--------------------------< I S _ U R L >------------------------------------------------------------------
returns true if the scheme and domain parts of a url appear to be a valid url; else false.
This function is the last step in the validation process. This function is separate because there are cases that
are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
wikilinks.
]]
local function is_url (scheme, domain)
if is_set (scheme) then -- if scheme is set check it and domain
return is_scheme (scheme) and is_domain_name (domain);
else
return is_domain_name (domain); -- scheme not set when url is protocol relative
end
end
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------
Split a url into a scheme, authority indicator, and domain.
First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#).
If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.
When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one
or more '/' characters immediately following the scheme's colon), make sure that there are only 2.
Strip off any port and path;
]]
local function split_url (url_str)
local scheme, authority, domain;
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url
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
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then
return scheme; -- return scheme only making domain nil which will cause an error message
end
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present
end
return scheme, domain;
end
--[[--------------------------< 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 urls
Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
# < > [ ] | { } _
except the underscore which is used as a space in wiki urls and # which is used for section links
returns false when the value contains any of these characters.
When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
|<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok).
]]
local function
local scheme, domain;
if value:find ('[<>%[%]|{}]') then -- if any prohibited characters
return false;
end
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
--[[--------------------------<
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
|<title>= may be wikilinked but not when |<param>-link= has a value. This function emits an error message when
that condition exists
]]
local function
local orig;
if is_set (link) then -- don't bother if <param>-link doesn't have a value
if not link_param_ok (link) then -- check |<param>-link= markup
orig = lorig; -- identify the failing link parameter
elseif title:find ('%[%[') then -- check |title= for wikilink markup
orig = torig; -- identify the failing |title= parameter
end
end
if is_set (orig) then
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=;
end
end
--[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
Determines whether a URL string
First we test for space characters. If any are found, return false. Then split the url into scheme and domain
portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two
portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false.
Because it is different from a standard url, and because this module used external_link() to make external links
that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name
is at https://tools.ietf.org/html/rfc5536#section-3.1.4
]]
local function check_url( url_str )
return false;
end
local scheme, domain;
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url;
if 'news:' == scheme then -- special case for newsgroups
return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
end
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
--[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
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 url. The test will also find external wikilinks
that use protocol relative urls. Also finds bare urls.
The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests that
find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=,
and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]
is possible as might be [[en://Hus]].
]=]
local function is_parameter_ext_wikilink (value)
local scheme, domain;
if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz]
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
elseif value:match ('//%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
else
return false; -- didn't find anything that is obviously a url
end
return is_url (scheme, domain); -- return true if value appears to be a valid url
end
--[[-------------------------< C H E C K _ F O R _ U R L >-----------------------------------------------------
loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
]]
local function check_for_url (parameter_list)
local error_message = '';
for k, v in pairs (parameter_list) do -- for each parameter in the list
if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message
if is_set(error_message) then -- once we've added the first portion of the error message ...
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "|" .. k .. "="; -- add the failed parameter
end
end
if is_set (error_message) then -- done looping, if there is an error message, display it
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } );
end
end
--[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
Line 186 ⟶ 367:
[']'] = ']',
['\n'] = ' ' } );
end
Line 214 ⟶ 377:
local function external_link( URL, label, source )
local error_str = "";
local domain;
local path;
if not is_set( label ) then
label = URL;
Line 223 ⟶ 389:
end
if not check_url( URL ) then
error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str;
end
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
URL=domain..path; -- and reassemble
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
end
--[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >--------------------------------------
Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the
offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated
parameters in the citation.
]]
local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local function deprecated_parameter(name)
if not page_in_deprecated_cat then
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
Line 306 ⟶ 466:
is not added. At this time there is no error message for this condition.
Supports |script-title= and |script-chapter=
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
Line 324 ⟶ 484:
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
-- is prefix one of these language codes?
if in_array (lang, cfg.script_lang_codes) then
add_prop_cat ('script_with_name', {name, lang})
else
Line 371 ⟶ 531:
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before
else
return substitute( cfg.messages[key],
end
end
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
parameter (chapter_url_source used for error messages).
]]
local function
local
if not is_set (chapter) then
chapter = ''; -- to be safe for concatenation
else
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
end
end
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
if is_set (transchapter) then
transchapter = wrap_style ('trans-quoted-title', transchapter);
if is_set (chapter) then
chapter = chapter .. ' ' .. transchapter;
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
end
end
if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
end
return chapter .. chapter_error;
end
--[[--------------------------<
This function searches a parameter's value for nonprintable or invisible characters. The search stops at the
first match.
This function will detect the visible replacement character when it is part of the wikisource.
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref)
and identifies them with a slightly different error message. See also coins_cleanup().
Detects but ignores the character pattern that results from the transclusion of {{'}} templates.
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.
]]
local function
local position = ''; -- position of invisible char or starting position of stripmarker
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
local capture; -- used by stripmarker detection to hold name of the stripmarker
local i=1;
local stripmarker, apostrophe;
capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true
return;
end
while cfg.invisible_chars[i] do
local char=cfg.invisible_chars[i][1] -- the character or group name
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position then
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
stripmarker = true; -- set a flag
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
position = nil; -- unset
else
local err_msg;
if
err_msg = capture .. ' ' .. char;
else
err_msg = char .. ' ' .. 'character';
end
table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message
return; -- and done with this parameter
end
end
i=i+1; -- bump our index
end
end
--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
Argument wrapper. This function provides support for argument mapping defined in the configuration file so that
multiple names can be transparently aliased to single internal variable.
]]
Line 521 ⟶ 682:
end
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.
Line 528 ⟶ 689:
false - deprecated, supported parameters
nil - unsupported parameters
]]
Line 551 ⟶ 713:
return false; -- Not supported because not found or name is set to nil
end
Line 580 ⟶ 732:
date = substitute (cfg.presentation['nowrap1'], date);
elseif date:match("^%a+%s*%d%d?,%s
cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
date = substitute (cfg.presentation['nowrap2'], {cap, cap2});
Line 586 ⟶ 738:
return date;
end
Line 1,075 ⟶ 758:
end
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
Converts a hyphen to a dash
]]
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
Line 1,186 ⟶ 771:
return str:gsub( '-', '–' );
end
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
Line 1,264 ⟶ 850:
return str;
end
--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed.
]]
local function is_suffix (suffix)
if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then
return true;
end
return false;
end
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
Line 1,281 ⟶ 881:
|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 ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position.
The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary
to use an external editor to maintain this code.
\195\128-\195\150 – À-Ö
\195\152-\195\182 – Ø-ö
\195\184-\198\191 – ø-ƿ
\199\132-\201\143 – DŽ-ɏ%
]]
local function is_good_vanc_name (last, first)
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it
if is_set (suffix) then
if not is_suffix (suffix) then
add_vanc_error ('suffix');
return false; -- not a name with an appropriate suffix
end
end
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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%'%.]*$") then
add_vanc_error ('non-Latin character');
return false; -- not a string of latin characters; Vancouver requires Romanization
end;
return true;
Line 1,303 ⟶ 917:
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc.
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
Line 1,311 ⟶ 925:
local function reduce_to_initials(first)
end
if name then -- if first is initials with or without suffix
if 3 > name:len() then -- if one or two initials
if suffix then -- if there is a suffix
if is_suffix (suffix) then -- is it legitimate?
return first; -- one or two initials and a valid suffix so nothing to do
else
add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message
return first; -- and return first unmolested
end
else
return first; -- one or two initials without suffix; nothing to do
end
end
end -- if here then name has 3 or more uppercase letters so treat them as a word
local initials, names = {}, {}; -- tables to hold name parts and initials
local i = 1; -- counter for number of initials
names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
while names[i] do -- loop through the table
if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
if is_suffix (names[i]) then -- if a legitimate suffix
table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
break; -- and done because suffix must fall at the end of a name
end -- no error message if not a suffix; possibly because of Romanization
end
if 3 > i then
table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table
end
i = i+1; -- bump the counter
end
-- for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
-- table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
-- i = i + 1; -- bump the counter
-- if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
-- end
return table.concat(initials) -- Vancouver format does not include spaces.
end
Line 1,369 ⟶ 1,021:
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first)
end
end
Line 1,376 ⟶ 1,028:
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
end
table.insert( text, one )
Line 1,387 ⟶ 1,036:
end
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
local result = table.concat(text)
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
end
Line 1,407 ⟶ 1,055:
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 anchor_id (namelist, year)
local names={}; -- a table for the one to four names and year
names[i] = v.last
if i == 4 then break end -- if four then done
end
table.insert (names, year); -- add the year at the end
local id = table.concat(names); -- concatenate names and year for CITEREF id
if is_set (id) then -- if concatenation is not an empty string
return "CITEREF" .. id; -- add the CITEREF portion
Line 1,417 ⟶ 1,072:
return ''; -- return an empty string; no reason to include CITEREF id in this citation
end
end
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
This function never sets the flag to false but returns it's previous state because it may have been set by
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
]]
local function name_has_etal (name, etal, nocat)
if is_set (name) then -- name can be nil in which case just return
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
if name:match (etal_pattern) then -- variants on et al.
name = name:gsub (etal_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
name = name:gsub (others_pattern, ''); -- if found, remove
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
if not nocat then -- no categorization for |vauthors=
add_maint_cat ('etal'); -- and add a category if not already added
end
end
end
return name, etal; --
end
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are
indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name
(author or editor) maintenance category.
]]
local function name_has_mult_names (name, list_name)
local count, _;
if is_set (name) then
if name:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, ignore
name = name:match ('^%(%((.*)%)%)$'); -- strip parens
else
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
if 1 < count then -- param could be |author= or |editor= so one separactor character is acceptable
add_maint_cat ('mult_names', list_name:lower()); -- more than one separator indicates multiple names so add a maint cat for this template
end
end
end
return name; -- and done
end
Line 1,445 ⟶ 1,158:
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 err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
Line 1,455 ⟶ 1,166:
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, 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
if 2
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup
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
Line 1,484 ⟶ 1,190:
end
return names, etal; -- all done, return our list of names
end
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
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, the name comparisons are done in lower case and when a match is
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we
return the original language name string.
mw.language.fetchLanguageNames(<local wiki language>, 'all') return a list of languages that in some cases may include
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
code 'cbk' or name 'Chavacano'.
Names but that are included in the list will be found if that name is provided in the |language= parameter. For example,
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found
and the associated code is not two or three characters, this function returns only the Wikimedia language name.
Adapted from code taken from Module:Check ISO 639-1.
Line 1,667 ⟶ 1,214:
]]
local function get_iso639_code (lang, this_wiki_code)
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
Line 1,678 ⟶ 1,221:
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() and 3 ~= code:len() then
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the
end
end
return lang; -- not valid language; return language in original case and nil for
end
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
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 for '639-2' codes: Category:CS1 ISO 639-2 language sources.
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character
equivalents of two-character codes: code 'ar' is recognized bit code 'ara' is not.
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.
]]
local function language_parameter (lang
local code; -- the
local name; -- the language name
local language_list = {}; -- table of language names to be rendered
local names_table = {}; -- table made from the value assigned to |language=
local this_wiki = mw.getContentLanguage(); -- get a language object for this wiki
local this_wiki_code = this_wiki:getCode() -- get this wiki's language code
local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
for _, lang in ipairs (names_table) do -- reuse lang
if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag?
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
end
if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code
end
if is_set (name) then -- if
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang, this_wiki_code);
end
if is_set (code) then -- only 2- or 3-character codes
if
if
add_prop_cat ('foreign_lang_source', {name, code}) -- categorize it
else -- or is a recognized language (but has a three-character code)
add_prop_cat ('foreign_lang_source_2', {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
end
end
else
end
Line 1,752 ⟶ 1,297:
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
end
if this_wiki_name == name then
return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
end
Line 1,816 ⟶ 1,364:
sep, ps = set_cs1_style (ps);
else -- anything but cs1 or cs2
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass
end
Line 1,830 ⟶ 1,375:
--[=[-------------------------< 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.
Line 1,852 ⟶ 1,397:
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
format = wrap_style ('format', format
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
Line 1,866 ⟶ 1,411:
--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
Returns a number that
to indicate when et al. should be appended to the name list.
When the value assigned to |display-
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-
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.
inputs:
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
count: #a or #e
list_name: 'authors' or 'editors'
etal: author_etal or editor_etal
]]
Line 1,887 ⟶ 1,439:
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
if max >= count
add_maint_cat ('disp_auth_ed', list_name);
end
else -- not a valid keyword or number
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message
max = nil; -- unset; as if |display-xxxxors= had not been set
end
end
return max, etal;
end
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
abbreviation in the first characters of the parameter content.
check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
]]
local function extra_text_in_page_check (page)
-- local good_pattern = '^P[^%.P%l]';
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg?
-- local bad_pattern = '^[Pp][Pp]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
add_maint_cat ('extra_text');
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
-- add_maint_cat ('extra_text');
-- end
end
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
|xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
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 paranethese ((corporate name)) to suppress the format tests.
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
]]
local function parse_vauthors_veditors (args, vparam, list_name)
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
local corporate = false;
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names
add_vanc_error ('wikilink');
end
v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas
for i, v_name in ipairs(v_name_table) do
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses
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 ('punctuation');
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 author intials
if is_suffix (first) then -- if a valid suffix
suffix = first -- save it as a suffix and
first = table.remove(lastfirstTable); -- get what should be the initials from the table
end -- no suffix error message here because letter combination may be result of Romanization; check for digits?
last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing
end
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
add_vanc_error ('name'); -- matches a space between two intiials
end
else
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
end
if is_set (first) then
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
end
is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit
if 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
end
else
is_good_vanc_name (last, '');
end
-- this from extract_names ()
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
end
return names, etal; -- all done, return our list of names
end
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
similarly, |editorn= (and aliases) highest and |editors= lowest
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better
way to do this, I just haven't discovered what that way is.
Emits an error message when more than one xxxxor name source is provided.
In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
]]
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local lastfirst = false;
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
lastfirst=true;
end
if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
(is_set (vxxxxors) and is_set (xxxxors)) or
(true == lastfirst and is_set (xxxxors)) then
local err_name;
if 'AuthorList' == list_name then -- figure out which name should be used in error message
err_name = 'author';
else
err_name = 'editor';
end
table.insert( z.message_tail, { set_error( 'redundant_parameters',
{err_name .. '-name-list parameters'}, true ) } ); -- add error message
end
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
if is_set (vxxxxors) then return 2 end;
if 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
--[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
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, no, etc). When the parameter value has not been assigned a value (missing or empty
in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.
]]
local function is_valid_parameter_value (value, name, possible)
if not is_set (value) then
return true; -- an empty parameter is ok
elseif in_array(value:lower(), possible) then
return true;
else
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
return false
end
end
--[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
when the last character is not a sepc character or when the last three characters are not sepc followed by two
closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
single space character.
]]
local function terminate_name_list (name_list, sepc)
if (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 terninate the name list
end
end
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
or formatted issue, or an empty string if neither are set.
]]
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
if not is_set (volume) and not is_set (issue) then
return '';
end
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
if is_set (volume) and is_set (issue) then
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
elseif is_set (volume) then
return wrap_msg ('vol', {sepc, volume}, lower);
else
return wrap_msg ('issue', {sepc, issue}, lower);
end
end
local vol = '';
if is_set (volume) then
if (4 < mw.ustring.len(volume)) then
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
else
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
end
end
if is_set (issue) then
return vol .. substitute (cfg.messages['j-issue'], issue);
end
return vol;
end
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
not currently used
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
returns list unchanged if there are no commas else strips whitespace and then reformats the list
]]
--[[
local function normalize_page_list (list)
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
list = table.concat (list, ', '); -- and now make a normalized list
return list;
end
]]
--[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
The return order is:
page, pages, sheet, sheets
Singular has priority over plural when both are provided.
]]
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 is_set (sheet) then
if 'journal' == origin then
return '', '', wrap_msg ('j-sheet', sheet, lower), '';
else
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
end
elseif is_set (sheets) then
if 'journal' == origin then
return '', '', '', wrap_msg ('j-sheets', sheets, lower);
else
return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
end
end
end
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
if is_set (page) then
if is_journal then
return substitute (cfg.messages['j-page(s)'], page), '', '', '';
elseif not nopp then
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
else
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
end
elseif is_set(pages) then
if is_journal then
return 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 '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
else
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', '';
end
end
return '', '', '', ''; -- return empty strings
end
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the
save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...)
archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allow
unwitting readers to do.
When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own
algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
|archive-date= and an error message when:
|archive-url= holds an archive.org save command url
|archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
correct place
otherwise returns |archive-url= and |archive-date=
There are two mostly compatible archive.org urls:
//web.archive.org/<timestamp>... -- the old form
//web.archive.org/web/<timestamp>... -- the new form
The old form does not support or map to the new form when it contains a display flag. There are four identified flags
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
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 funct may return a modified
archive url:
for save command errors, return undated wildcard (/*/)
for timestamp errors when the timestamp has a wildcard, return the url unmodified
for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
]=]
local function archive_url_check (url, date)
local err_msg = ''; -- start with the error message empty
local path, timestamp, flag; -- portions of the archive.or url
if not url:match('//web%.archive%.org/') then
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 url, we don't want to allow saving of the target page
table.insert( z.message_tail, { set_error( 'archive_url', {'save command'}, true ) } ); -- add error message
if Preview_mode then
return url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1), date; -- preview mode: modify and return ArchiveURL and ArchiveDate
else
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
end
-- if url:match('//web%.archive%.org/web/%*/') or url:match('//web%.archive%.org/%*/') then -- wildcard with or without 'web/' path element
-- table.insert( z.message_tail, { set_error( 'archive_url', {'wildcard'}, true ) } ); -- add error message and
-- return '', ''; -- return empty strings for archiveURL and ArchiveDate
-- end
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
err_msg = 'timestamp';
if '*' ~= flag then
url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
end
elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element
err_msg = 'path';
elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element)
err_msg = 'flag';
elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
err_msg = 'flag';
else
return url, date; -- return archiveURL and ArchiveDate
end
-- if here something not right so
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
if Preview_mode then
return url, date; -- preview mode so return archiveURL and ArchiveDate
else
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
end
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
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:
{{cite ... |title=Title access-date=2016-03-17}}
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html
tags are removed before the search.
If a missing pipe is detected, this function adds the missing pipe maintenance category.
]]
local function missing_pipe_check (value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
add_maint_cat ('missing_pipe');
end
end
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
This is the main function doing the majority of the citation formatting.
]]
Line 1,911 ⟶ 1,868:
--[[
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 NameListFormat = A['NameListFormat'];
local Collaboration = A['Collaboration'];
do -- to limit scope of selected
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
if 1 == selected then
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
elseif 2 == selected then
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
end
if is_set (Collaboration) then
author_etal = true; -- so that |display-authors=etal not required
end
end
local Coauthors = A['Coauthors'];
local Others = A['Others'];
local editor_etal;
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
local Editors;
do -- to limit scope of selected
local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
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
NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
end
end
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local Translators; -- assembled translators name list
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local Contributors; -- assembled contributors name list
local Contribution = A['Contribution'];
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
if 0 < #c then
if not is_set (Contribution) then -- |contributor= requires |contribution=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
if 0 == #a then -- |contributor= requires |author=
table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message
c = {}; -- blank the contributors' table; it is used as a flag later
end
end
else -- if not a book cite
if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters?
table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message
end
Contribution = nil; -- unset
end
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc'
NameListFormat = ''; -- anything else, set to empty string
end
Line 1,952 ⟶ 1,959:
local TitleNote = A['TitleNote'];
local TitleLink = A['TitleLink'];
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set
local Chapter = A['Chapter'];
local
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TitleType = A['TitleType'];
Line 1,959 ⟶ 1,969:
local Docket = A['Docket'];
local ArchiveFormat = A['ArchiveFormat'];
local ArchiveDate;
local ArchiveURL;
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
local DeadURL = A['DeadURL']
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
DeadURL = ''; -- anything else, set to empty string
end
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
Line 1,968 ⟶ 1,988:
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local Series = A['Series'];
local
local Issue;
local Page;
local Pages;
local At;
if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
Volume = A['Volume'];
end
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
Issue = A['Issue'];
end
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
At = A['At'];
end
local Edition = A['Edition'];
Line 1,983 ⟶ 2,017:
local PublisherName = A['PublisherName'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
end
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
SubscriptionRequired=nil;
end
local Via = A['Via'];
local AccessDate = A['AccessDate'];
local Agency = A['Agency'];
local Language = A['Language'];
local Format = A['Format'];
Line 1,996 ⟶ 2,036:
local ASINTLD = A['ASINTLD'];
local IgnoreISBN = A['IgnoreISBN'];
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
IgnoreISBN = nil; -- anything else, set to empty string
end
local Embargo = A['Embargo'];
local Class = A['Class']; -- arxiv class identifier
Line 2,012 ⟶ 2,055:
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
end
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
no_tracking_cats = nil; -- set to empty string
end
--these are used by cite interview
Line 2,020 ⟶ 2,069:
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local anchor_year; -- used in the CITEREF identifier
local COinS_date = {}; --
local DF = A['DF']; -- date format set in cs1|2 template
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
DF = ''; -- not valid, set to empty string
end
-- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
local PostScript;
local Ref;
sepc, PostScript, Ref = set_style (
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
Line 2,045 ⟶ 2,103:
end
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category
local NoPP = A['NoPP']
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
NoPP = true;
else
NoPP = nil; -- unset, used as a flag later
end
if is_set(Page) then
if is_set(Pages) or is_set(At) then
Pages = ''; -- unset the others
At = '';
end
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
elseif is_set(Pages) then
if is_set(At) then
At = ''; -- unset
end
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
end
Line 2,077 ⟶ 2,144:
All other combinations of |encyclopedia, |title, and |article are not modified
]]
Line 2,083 ⟶ 2,150:
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
if is_set(Title) or is_set (ScriptTitle) then
if not 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;
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
end
Title = Periodical;
ChapterFormat = Format;
Periodical = ''; -- redundant so unset
TransTitle = '';
URL = '';
Format = '';
TitleLink = '';
ScriptTitle = '';
end
else -- |title not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Periodical = ''; -- redundant so unset
end
end
Line 2,104 ⟶ 2,177:
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if is_set(
if not is_set(ID) then -- can we use ID for the "number"?
ID =
else -- ID has a value so emit error message
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
end
end
Line 2,150 ⟶ 2,222:
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
Line 2,197 ⟶ 2,271:
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local SeriesLink = A['SeriesLink'];
link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set
local Network = A['Network'];
local Station = A['Station'];
local s, n = {}, {};
-- do common parameters first
if is_set(Network) then table.insert(n, Network); end
Line 2,209 ⟶ 2,283:
ID = table.concat(n, sepc .. ' ');
if not is_set (Date) and is_set (AirDate) then
end
Line 2,236 ⟶ 2,302:
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
Line 2,251 ⟶ 2,318:
end
URL = ''; -- unset
TransTitle = '';
ScriptTitle = '';
else -- now oddities that are cite serial
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
Line 2,268 ⟶ 2,336:
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
elseif is_set (Series) then -- series is an alias of version
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
Series = ''; -- unset
deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
end
if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'],
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message
Line 2,286 ⟶ 2,359:
-- handle type parameter for those CS1 citations that have default values
if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
Line 2,295 ⟶ 2,367:
if is_set(TitleType) then -- if type parameter is specified
end
-- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set.
if not 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 is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
end
end
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
--[[
Line 2,321 ⟶ 2,388:
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
do -- create defined block to contain local variables error_message,
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
['embargo']=Embargo, ['
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;
Line 2,338 ⟶ 2,407:
end
end
if not is_set(error_message) then -- error free dates only
local modified = false; -- flag
if is_set (DF) then -- if we need to reformat dates
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
end
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
modified = true;
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
end
if modified then -- if the date_parameters_list values were modified
AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with modified values
ArchiveDate = date_parameters_list['archive-date'];
Date = date_parameters_list['date'];
DoiBroken = date_parameters_list['doi-broken-date'];
LayDate = date_parameters_list['lay-date'];
PublicationDate = date_parameters_list['publication-date'];
end
else
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
-- if is_set(error_message) then
-- table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
-- elseif is_set (DF) then
-- if reformat_dates (date_parameters_list, DF, false) then -- reformat to DF format, use long month names if appropriate
-- AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with reformatted values
-- ArchiveDate = date_parameters_list['archive-date'];
-- Date = date_parameters_list['date'];
-- DoiBroken = date_parameters_list['doi-broken-date'];
-- LayDate = date_parameters_list['lay-date'];
-- PublicationDate = date_parameters_list['publication-date'];
-- end
-- end
end -- end of do
Line 2,360 ⟶ 2,461:
not is_set(TransTitle) and
not is_set(ScriptTitle) then
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this?
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
else
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
end
end
if 'none' == Title and
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
check_for_url ({ -- add error message when any of these parameters contains a URL
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[A:ORIGIN('PublisherName')] = PublisherName
});
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
Line 2,381 ⟶ 2,493:
end
end
local coins_author = a; -- default for coins rft.au
if 0 < #c then -- but if contributor list
coins_author = c; -- use that instead
end
-- this is the function call to COinS()
local OCinSoutput = COinS({
['Periodical'] = Periodical,
['Encyclopedia'] = Encyclopedia,
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
['Degree'] = Degree; -- cite thesis only
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
['PublicationPlace'] = PublicationPlace,
['Date'] =
['Season'] = COinS_date.rftssn,
['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'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['URL'] = first_set ({ChapterURL, URL},
['Authors'] =
['ID_list'] = ID_list,
['RawPage'] = this_page.prefixedText,
Line 2,409 ⟶ 2,529:
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
PublisherName =
end
end
Line 2,418 ⟶ 2,538:
-- 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
-- local maximum;
local control = {
format = NameListFormat, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via
};
do -- do editor name list first because coauthors can modify control table
control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
last_first_list, EditorCount = list_people(control, e, editor_etal);
if is_set (Editors) then
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
else
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation
end
else
Editors = last_first_list; -- either an author name list or an empty string
end
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
do -- now do translators
control.maximum = #t; -- number of translators
Translators = list_people(control, t, false); -- et al not currently supported
end
do -- now do contributors
control.maximum = #c; -- number of contributors
Contributors = list_people(control, c, false); -- et al not currently supported
end
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal);
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
end
else
Authors = last_first_list; -- either an author name list or an empty string
end
end -- end of do
if is_set (Authors) and is_set (Collaboration) then
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
end
if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified
table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
end
end
Line 2,482 ⟶ 2,608:
-- an error message if the associated url is not set, or an empty string for concatenation
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Format = style_format (Format, URL, 'format', 'url');
Line 2,488 ⟶ 2,613:
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
-- special case for chapter format so no error message or cat when chapter not supported
if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
if not is_set(URL) then
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- |url= required for cite web, cite podcast, and cite mailinglist
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
--
if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = '';
Line 2,505 ⟶ 2,631:
end
local OriginalURL, OriginalURLorigin, OriginalFormat;
DeadURL = DeadURL:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
if is_set (ChapterURL) then -- swapped -- URL not set so if chapter-url is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalFormat = ChapterFormat; -- and original |format=
if 'no' ~= DeadURL then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
end
elseif is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalFormat = Format; -- and original |format=
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
Line 2,516 ⟶ 2,652:
Format = ArchiveFormat or ''; -- swap in archive's format
end
end
end
if in_array(config.CitationClass, {
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
local chap_param;
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
chap_param = A:ORIGIN ('Chapter')
elseif is_set (TransChapter) then
chap_param = A:ORIGIN ('TransChapter')
elseif is_set (ChapterURL) then
chap_param = A:ORIGIN ('ChapterURL')
elseif is_set (ScriptChapter) then
chap_param = A:ORIGIN ('ScriptChapter')
else is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
end
if is_set (chap_param) then -- if we found one
table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
Chapter = ''; -- and set them to empty string to be safe with concatenation
TransChapter = '';
ChapterURL = '';
ScriptChapter = '';
ChapterFormat = '';
end
else -- otherwise, format chapter / article title
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title
no_quotes = true; -- then render it unquoted
end
end
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
if is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
if 'map' == config.CitationClass and is_set (TitleType) then
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
end
Chapter = Chapter
elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
end
end
Line 2,550 ⟶ 2,703:
end
if in_array(config.CitationClass, {
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Line 2,567 ⟶ 2,720:
end
local TransError = "";
if is_set(TransTitle) then
if is_set(Title) then
TransTitle = " " .. TransTitle;
else
TransError = " " .. set_error( 'trans_missing_title', {'title'} );
end
end
Line 2,579 ⟶ 2,732:
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive
-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available
-- local err_msg
-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message
-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this
-- Title = Title .. (err_msg or '');
-- end
-- else
-- Title = temp_title;
-- end
URL = ''; -- unset these because no longer needed
Format = "";
else
Line 2,594 ⟶ 2,759:
if is_set (Conference) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
Line 2,603 ⟶ 2,768:
if not is_set(Position) then
local Minutes = A['Minutes'];
local Time = A['Time'];
if is_set(Minutes) then
if is_set (Time) then
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
end
Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
else
if is_set(Time) then
local TimeCaption = A['TimeCaption']
Line 2,621 ⟶ 2,790:
Position = " " .. Position;
At = '';
end
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
At = is_set(At) and (sepc .. " " .. At) or "";
Line 2,695 ⟶ 2,814:
if is_set (Language) then
Language = language_parameter (Language
else
Language=""; -- language not specified so make sure this is an empty string;
Line 2,701 ⟶ 2,820:
Others = is_set(Others) and (sepc .. " " .. Others) or "";
if is_set (Translators) then
-- Others = sepc .. ' Translated by ' .. Translators .. Others;
Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;
end
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
add_maint_cat ('extra_text', 'edition');
end
Edition = " " .. wrap_msg ('edition', Edition);
else
Edition = '';
end
Series = is_set(Series) and (sepc .. " " .. Series) or "";
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
------------------------------------ totally unrelated data
Line 2,726 ⟶ 2,852:
]]
if
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
elseif
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
else
Line 2,759 ⟶ 2,885:
if 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
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
PostScript = ""; --
end
Line 2,775 ⟶ 2,901:
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if in_array (DeadURL, {'unfit', 'usurped'}) then
else -- DeadURL is empty, 'yes', 'true', or 'y'
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
else
local arch_text = cfg.messages['archived-missing'];
Line 2,805 ⟶ 2,935:
end
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Line 2,815 ⟶ 2,945:
if is_set(Transcript) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
Line 2,889 ⟶ 3,019:
-- not to keep reassigning to the same string variable over and over.
local tcommon;
local tcommon2; -- used for book cite when |contributor= is set
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
Language, Edition, Publisher, Agency, Volume
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
else
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
end
elseif 'map' == config.CitationClass then -- special cases for cite map
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
elseif is_set (Periodical) then -- map in a periodical
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume
else -- a sheet or stand-alone map
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
Line 2,908 ⟶ 3,048:
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,
Volume
end
Line 2,919 ⟶ 3,059:
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
if is_set(Date) then
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
else -- neither of authors and editors set
if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
else
Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
end
end
end
if is_set(Authors) then
if is_set(Coauthors) then
if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
Authors = Authors .. ', ' .. Coauthors;
else
Authors = Authors .. '; ' .. Coauthors;
end
end
if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
if is_set(Editors) then
local in_text = " ";
local post_text = "";
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
else
if EditorCount <= 1 then
Line 2,948 ⟶ 3,096:
end
end
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
else
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
end
elseif is_set(Editors) then
if is_set(Date) then
Line 2,965 ⟶ 3,119:
Editors = Editors .. ", " .. cfg.messages['editors'];
end
else
if EditorCount <= 1 then
Line 2,973 ⟶ 3,126:
end
end
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
else
if in_array(config.CitationClass, {"journal","citation"}) and is_set(
else
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc );
end
end
Line 2,998 ⟶ 3,142:
text = safe_join( {text, PostScript}, sepc );
-- Now enclose the whole thing in a <
local options = {};
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
options.class =
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref=
else
options.class = "citation";
end
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate
local id = Ref
if (
local
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
if #c > 0 then -- if there is a contributor list
elseif #a > 0 then -- or an author list
elseif #e > 0 then -- or an editor list
end
if #namelist > 0 then -- if there are names in namelist
id = anchor_id (namelist, year); -- go make the CITEREF anchor
else
id = ''; -- unset
end
end
options.id = id;
Line 3,034 ⟶ 3,180:
end
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
text =
else
text =
end
text = text .. substitute (cfg.presentation['ocins'], {OCinSoutput}); -- append metadata to the citation
if #z.message_tail ~= 0 then
Line 3,060 ⟶ 3,202:
if #z.maintenance_cats ~= 0 then
text = text .. '
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
end
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
Line 3,083 ⟶ 3,225:
end
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
This is used by templates such as {{cite book}} to create the actual citation text.
]]
function cs1.citation(frame)
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
validation = require ('Module:Citation/CS1/Date_validation/sandbox');
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
else -- otherwise
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
validation = require ('Module:Citation/CS1/Date_validation');
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
end
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
validation.set_selected_modules (utilities); -- so that functions in Date validataion can see the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation
year_date_check = validation.year_date_check;
reformat_dates = validation.reformat_dates;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
in_array = utilities.in_array;
substitute = utilities.substitute;
error_comment = utilities.error_comment;
set_error = utilities.set_error;
select_one = utilities.select_one;
add_maint_cat = utilities.add_maint_cat;
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
remove_wiki_link = utilities.remove_wiki_link;
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Utilities
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
get_coins_pages = metadata.get_coins_pages;
COinS = metadata.COinS;
Preview_mode = frame:preprocess('{{REVISIONID}}'); -- use magic word to get revision id
if is_set (Preview_mode) then -- if there is a value then this is not a preiview
Preview_mode = false;
else
Preview_mode = true; -- no value (nil or empty string) so this is a preview
end
local args = {};
local suggestions = {};
Line 3,112 ⟶ 3,301:
end
local capture; -- the single supported capture when matching unknown parameters using patterns
for k, v in pairs( pframe.args ) do
if v ~= '' then
Line 3,124 ⟶ 3,314:
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
else
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
end
end
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter
capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match
if capture then -- if the pattern matches
param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message
end
end
if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion?
if suggestions.suggestions[ k:lower() ] ~= nil then
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
end
end
end
Line 3,137 ⟶ 3,340:
end
end
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe?
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then
Line 3,142 ⟶ 3,347:
end
end
for k, v in pairs( args ) do
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v);
end
end
return citation0( config, args)
end
return
| |||