Module:Citation/CS1: Difference between revisions

From Chalo Chatu, Zambia online encyclopedia

Module:Citation/CS1 (view source)

Revision as of 15:27, 23 September 2019

32,336 bytes added ,  23 September 2019
m
1 revision imported
(Created page with " local cs1 ={}; --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local dates, year_date_check, reformat_dat...")
 
m (1 revision imported)
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
local cs1 ={};


--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
]]
]]


local dates, year_date_check, reformat_dates, date_hyphen_to_dash -- functions in Module:Citation/CS1/Date_validation
local dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation
date_name_xlate


local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities
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;
add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink,
strip_apostrophe_markup;


local z ={}; -- tables in Module:Citation/CS1/Utilities
local z ={}; -- tables in Module:Citation/CS1/Utilities


local extract_ids, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers
local extract_ids, extract_id_access_levels, 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 make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS
Line 22: Line 22:
--[[--------------------------< P A G E  S C O P E  V A R I A B L E S >--------------------------------------
--[[--------------------------< 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
delare variables here that have page-wide scope that are not brought in from other modules; thatare created here
and used here


]]
]]


local Preview_mode = false; -- flag indicating that we are rendering a preview page (Show preview button)
local added_deprecated_cat; -- boolean flag so that the category is added only once
local added_prop_cats = {}; -- list of property categories that have been added to z.properties_cats
local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category
 
local Frame; -- holds the module's frame table
 


--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
Line 48: Line 54:
end
end
end
end


--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------
--[[--------------------------< A D D _ P R O P _ C A T >--------------------------------------------------------


Adds a category to z.properties_cats using names from the configuration file with additional text if any.
Adds a category to z.properties_cats using names from the configuration file with additional text if any.
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages
may be categorized but multiples of the same language are not categorized.
added_prop_cats is a table declared in page scope variables above


]]
]]


local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
local function add_prop_cat (key, arguments)
local function add_prop_cat (key, arguments)
if not added_prop_cats [key] then
if not added_prop_cats [key] then
added_prop_cats [key] = true; -- note that we've added this category
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
key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
end
end
end
end


--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Line 67: Line 80:
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
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.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
added_vanc_errs is a boolean declared in page scope variables above


]]
]]


local added_vanc_errs; -- flag so we only emit one Vancouver error / category
local function add_vanc_error (source)
local function add_vanc_error (source)
if not added_vanc_errs then
if not added_vanc_errs then
Line 118: Line 132:
the first character of the whole domain name including subdomains must be a letter or a digit
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
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
single-letter/digit second-level domains in the .org, .cash, and .today TLDs
q, x, and z SL domains in the .com TLD
q, x, and z SL domains in the .com TLD
i and q SL domains in the .net TLD
i and q SL domains in the .net TLD
Line 137: Line 151:
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once
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
if not domain:match ('^[%w]') then -- first character must be letter or digit
return false;
return false;
end
end
-- Do most common case first
 
if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at wikisource
return true;
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') 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+$') then -- two character hostname and tld
return true;
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address
return true;
else
return false;
return false;
end
end
local patterns = { -- patterns that look like urls
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)
'%f[%w][%w]%.%a%a$', -- one character hostname and cctld (2 chars)
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and tld
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address
}
for _, pattern in ipairs (patterns) do -- loop through the patterns list
if domain:match (pattern) then
return true; -- if a match then we think that this thing that purports to be a url is a url
end
end
for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
if domain:match ('%f[%w][%w]%.' .. d) then
return true
end
end
return false; -- no matches, we don't know what this thing is
end
end


Line 241: Line 262:
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url
end
end


--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
--[[--------------------------< L I N K _ T I T L E _ O K >---------------------------------------------------
Line 368: Line 390:
['\n'] = ' ' } );
['\n'] = ' ' } );
end
end


--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
--[[--------------------------< E X T E R N A L _ L I N K >----------------------------------------------------
Line 375: Line 398:
]]
]]


local function external_link( URL, label, source )
local function external_link( URL, label, source, access)
local error_str = "";
local error_str = "";
local domain;
local domain;
local path;
local path;
local base_url;
 
if not is_set( label ) then
if not is_set( label ) then
label = URL;
label = URL;
Line 395: Line 419:
if path then -- if there is a path portion
if path then -- if there is a path portion
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values
URL=domain..path; -- and reassemble
URL = table.concat ({domain, path}); -- and reassemble
end
 
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url
 
if is_set (access) then -- access level (subscription, registration, limited)
base_url = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon
end
end
return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str });
return table.concat ({base_url, error_str});
end
end


Line 407: Line 437:
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
offending parameter name to the error message.  Only one error message is emitted regardless of the number of deprecated
parameters in the citation.
parameters in the citation.
added_deprecated_cat is a boolean declared in page scope variables above


]]
]]


local page_in_deprecated_cat; -- sticky flag so that the category is added only once
local function deprecated_parameter(name)
local function deprecated_parameter(name)
if not page_in_deprecated_cat then
if not added_deprecated_cat then
page_in_deprecated_cat = true; -- note that we've added this category
added_deprecated_cat = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message
end
end
end
end


--[[--------------------------< K E R N _ Q U O T E S >--------------------------------------------------------


Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value.
--[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
 
Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote
mark contained in a |title= or |chapter= parameter's value.
 
This function will positive kern either single or double quotes:
This function will positive kern either single or double quotes:
"'Unkerned title with leading and trailing single quote marks'"
"'Unkerned title with leading and trailing single quote marks'"
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)
Double single quotes (italic or bold wikimarkup) are not kerned.
Double single quotes (italic or bold wikimarkup) are not kerned.
Replaces unicode quotemarks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
quote marks regardless of the need for kerning.  Unicode quote marks are not replaced in simple [[D]] wikilinks.


Call this function for chapter titles, for website titles, etc; not for book titles.
Call this function for chapter titles, for website titles, etc; not for book titles.


]]
]=]


local function kern_quotes (str)
local function kern_quotes (str)
local cap='';
local cap='';
local cap2='';
local cap2='';
local wl_type, label, link;
wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks
if is_set (cap) then
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks
str = substitute (cfg.presentation['kern-left'], {cap, cap2});
str = substitute (cfg.presentation['kern-wl-both'], str);
end
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
str = substitute (cfg.presentation['kern-wl-left'], str);
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks
str = substitute (cfg.presentation['kern-wl-right'], str);
end
 
else -- plain text or [[L|D]]; text in label variable
label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)


cap, cap2 = str:match ("^(.+[^\'])([\"\'])$")
cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
if is_set (cap) then
str = substitute (cfg.presentation['kern-right'], {cap, cap2});
label = substitute (cfg.presentation['kern-left'], {cap, cap2});
end
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)
if is_set (cap) then
label = substitute (cfg.presentation['kern-right'], {cap, cap2});
end
if 2 == wl_type then
str = make_wikilink (link, label); -- reassemble the wikilink
else
str = label;
end
end
end
return str;
return str;
end
end


--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
Line 466: Line 527:
is not added.  At this time there is no error message for this condition.
is not added.  At this time there is no error message for this condition.


Supports |script-title= and |script-chapter=
Supports |script-title=, |script-chapter=, |script-<periodical>=


TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
]]


local function format_script_value (script_value)
local function format_script_value (script_value, script_param)
local lang=''; -- initialize to empty string
local lang=''; -- initialize to empty string
local name;
local name;
Line 477: Line 537:
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not is_set (lang) then
if not is_set (lang) then
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message
return ''; -- script_value was just the prefix so return empty string
return ''; -- script_value was just the prefix so return empty string
end
end
-- if we get this far we have prefix and script
-- if we get this far we have prefix and script
name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
if is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script
Line 487: Line 548:
add_prop_cat ('script_with_name', {name, lang})
add_prop_cat ('script_with_name', {name, lang})
else
else
add_prop_cat ('script')
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
end
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
else
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
lang = ''; -- invalid so set lang to empty string
lang = ''; -- invalid so set lang to empty string
end
end
else
table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
end
end
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl
Line 498: Line 562:
return script_value;
return script_value;
end
end


--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Line 505: Line 570:
]]
]]


local function script_concatenate (title, script)
local function script_concatenate (title, script, script_param)
if is_set (script) then
if is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
script = format_script_value (script, script_param); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set (script) then
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
title = title .. ' ' .. script; -- concatenate title and script title
Line 531: Line 596:
local msg;
local msg;
msg = cfg.messages[key]:lower(); -- set the message to lower case before  
msg = cfg.messages[key]:lower(); -- set the message to lower case before  
return substitute( msg, str ); -- including template text
return substitute( msg, str ); -- including template text
else
else
return substitute( cfg.messages[key], str );
return substitute( cfg.messages[key], str );
Line 538: Line 603:




--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
--[[--------------------------< W I K I S O U R C E _ U R L _ M A K E >----------------------------------------
 
makes a wikisource url from wikisource interwiki link.  returns the url and appropriate label; nil else.


Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
parameter (chapter_url_source used for error messages).


]]
]]


local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes)
local function wikisource_url_make (str)
local chapter_error = '';
local wl_type, D, L;
local ws_url, ws_label;
 
wl_type, D, L = is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink)
 
if 0 == wl_type then -- not a wikilink; might be from |title-link=
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]]
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title
});
ws_label = str; -- label for the url
end
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]])
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace
if is_set (str) then
ws_label = D; -- get ws article name from display portion of interwiki link
ws_url = table.concat ({ -- build a wikisource url
'https://en.wikisource.org/wiki/', -- prefix
str, -- article title without namespace from link portion of wikilink
});
end
end
if not is_set (chapter) then
if ws_url then
chapter = ''; -- to be safe for concatenation
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable url
else
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of anchor
if false == no_quotes then
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
chapter = wrap_style ('quoted-title', chapter);
end
end
end


chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
return ws_url, ws_label, L or D; -- return proper url or nil and a label or nil
end
 


if is_set (transchapter) then
--[[--------------------------< F O R M A T _ P E R I O D I C A L >--------------------------------------------
transchapter = wrap_style ('trans-quoted-title', transchapter);
 
if is_set (chapter) then
Format the four periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta-
chapter = chapter ..  ' ' .. transchapter;
parameter.
 
]]
 
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
local periodical_error = '';
 
if not is_set (periodical) then
periodical = ''; -- to be safe for concatenation
else
periodical = wrap_style ('italic-title', periodical); -- style
end
 
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 
if is_set (trans_periodical) then
trans_periodical = wrap_style ('trans-italic-title', trans_periodical);
if is_set (periodical) then
periodical = periodical ..  ' ' .. trans_periodical;
else -- here when transchapter without chapter or script-chapter
else -- here when transchapter without chapter or script-chapter
chapter = transchapter; --
periodical = trans_periodical;
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'});
periodical_error = ' ' .. set_error ('trans_missing_title', {'periodical'});
end
end
end
end


if is_set (chapterurl) then
return periodical .. periodical_error;
chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
end
 
return chapter .. chapter_error;
end
end


--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------


This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
first match.


This function will detect the visible replacement character when it is part of the wikisource.
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).


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.
local function format_chapter_title (scriptchapter, script_chapter_source, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access)
local chapter_error = '';


Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource url and label from a wikisource interwiki link
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
if ws_url then
parameter value.
ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters
chapter = ws_label;
end


]]
if not is_set (chapter) then
 
chapter = ''; -- to be safe for concatenation
local function has_invisible_chars (param, v)
else
local position = ''; -- position of invisible char or starting position of stripmarker
if false == no_quotes then
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned
chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
local capture; -- used by stripmarker detection to hold name of the stripmarker
chapter = wrap_style ('quoted-title', chapter);
local i=1;
end
local stripmarker, apostrophe;
capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true
if capture == v then -- if same there are no unicode characters
return;
end
end


while cfg.invisible_chars[i] do
chapter = script_concatenate (chapter, scriptchapter, script_chapter_source); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
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 capture then
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
if is_set (chapterurl) then
return; -- and done with this parameter
chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
end
elseif ws_url then
end
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
i=i+1; -- bump our index
chapter = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
end
end
end


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, access); -- adds bare_url_missing_title error if appropriate
-- end
return chapter .. chapter_error;
end
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
This function searches a parameter's value for nonprintable or invisible characters.  The search stops at the
first match.
This function will detect the visible replacement character when it is part of the wikisource.


--[[--------------------------< A R G U M E N T _ W R A P P E R >----------------------------------------------
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().


Argument wrapper.  This function provides support for argument mapping defined in the configuration file so that
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker
multiple names can be transparently aliased to single internal variable.
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the
parameter value.


]]
]]


local function argument_wrapper( args )
local function has_invisible_chars (param, v)
local origin = {};
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;
return setmetatable({
capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true
ORIGIN = function( self, k )
if capture == v then -- if same there are no unicode characters
local dummy = self[k]; --force the variable to be loaded.
return;
return origin[k];
end
 
while cfg.invisible_chars[i] do
local char=cfg.invisible_chars[i][1] -- the character or group name
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern
if position and (char == 'zero width joiner') then -- if we found a zero width joiner character
if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts
position = nil; -- unset position
end
end
end
},
{
if position then
__index = function ( tbl, k )
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
if origin[k] ~= nil then
('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
return nil;
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 capture then
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
end
local args, list, v = args, cfg.aliases[k];
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.
 
]]
 
local function argument_wrapper( args )
local origin = {};
return setmetatable({
ORIGIN = function( self, k )
local dummy = self[k]; --force the variable to be loaded.
return origin[k];
end
},
{
__index = function ( tbl, k )
if origin[k] ~= nil then
return nil;
end
local args, list, v = args, cfg.aliases[k];
if type( list ) == 'table' then
if type( list ) == 'table' then
Line 667: Line 835:
-- maybe let through instead of raising an error?
-- maybe let through instead of raising an error?
-- v, origin[k] = args[k], k;
-- v, origin[k] = args[k], k;
error( cfg.messages['unknown_argument_map'] );
error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
end
end
Line 682: Line 850:
end
end


--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
Looks for a parameter's name in the whitelist.


Parameters in the whitelist can have three values:
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
true - active, supported parameters
 
false - deprecated, supported parameters
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
nil - unsupported parameters
]]
 
local function validate( name )
local name = tostring( name );
local state = whitelist.basic_arguments[ name ];
-- Normal arguments
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- Arguments with numbers in them
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
state = whitelist.numbered_arguments[ name ];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- Not supported because not found or name is set to nil
end
 
 
--[[--------------------------< N O W R A P _ D A T E >--------------------------------------------------------
 
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.  When date is DD MMMM YYYY or is
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY


Line 739: Line 874:
return date;
return date;
end
end


--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
--[[--------------------------< S E T _ T I T L E T Y P E >----------------------------------------------------
Line 761: Line 897:
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
--[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------


Converts a hyphen to a dash
Converts a hyphen to a dash under certain conditions.  The hyphen must separate like items; unlike items are
returned unmodified.  These forms are modified:
letter - letter (A - B)
digit - digit (4-5)
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5)
letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5)
digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d)
 
any other forms are returned unmodified.
 
str may be a comma- or semicolon-separated list


]]
]]


local function hyphen_to_dash( str )
local function hyphen_to_dash( str )
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
if not is_set (str) then
return str;
return str;
end
end
return str:gsub( '-', '–' );
str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str
if 0 ~= count then -- non-zero when markup removed; zero else
return str; -- nothing to do, we're done
end
str = str:gsub ('&[nm]dash;', {['&ndash;'] = '–', ['&mdash;'] = '—'}); -- replace &mdash; and &ndash; entities  with their characters; semicolon mucks up the text.split
local out = {};
local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any
 
for _, item in ipairs (list) do -- for each item in the list
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators
if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or -- letterdigit hyphen letterdigit (optional separator between letter and digit)
item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or -- digitletter hyphen digitletter (optional separator between digit and letter)
item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or -- digit separator digit hyphen digit separator digit
item:match ('%d+%s*%-%s*%d+') or -- digit hyphen digit
item:match ('%a+%s*%-%s*%a+') then -- letter hyphen letter
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space
end
end
item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup
table.insert (out, item); -- add the (possibly modified) item to the output table
end
 
return table.concat (out, ', '); -- concatenate the output table into a comma separated string
end
end


Line 780: Line 953:


local function safe_join( tbl, duplicate_char )
local function safe_join( tbl, duplicate_char )
--[[
local f = {}; -- create a function table appropriate to type of 'dupicate character'
Note: we use string functions here, rather than ustring functions.
if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions
f.gsub=string.gsub
This has considerably faster performance and should work correctly as
f.match=string.match
long as the duplicate_char is strict ASCII. The strings
f.sub=string.sub
in tbl may be ASCII or UTF8.
else -- for multi-byte characters use the ustring library functions
]]
f.gsub=mw.ustring.gsub
f.match=mw.ustring.match
f.sub=mw.ustring.sub
end
 
local str = ''; -- the output string
local str = ''; -- the output string
local comp = ''; -- what does 'comp' mean?
local comp = ''; -- what does 'comp' mean?
Line 804: Line 980:
end
end
-- typically duplicate_char is sepc
-- typically duplicate_char is sepc
if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
if f.sub(comp, 1,1) == duplicate_char then -- is first character same as duplicate_char? why test first character?
--  Because individual string segments often (always?) begin with terminal punct for th
--  Because individual string segments often (always?) begin with terminal punct for the
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
--  preceding segment: 'First element' .. 'sepc next element' .. etc?
trim = false;
trim = false;
end_chr = str:sub(-1,-1); -- get the last character of the output string
end_chr = f.sub(str, -1,-1); -- get the last character of the output string
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff?
if end_chr == duplicate_char then -- if same as separator
if end_chr == duplicate_char then -- if same as separator
str = str:sub(1,-2); -- remove it
str = f.sub(str, 1,-2); -- remove it
elseif end_chr == "'" then -- if it might be wikimarkup
elseif end_chr == "'" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''  
if f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc''  
str = str:sub(1, -4) .. "''"; -- remove them and add back ''
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''
elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''  
elseif f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]''  
trim = true; -- why? why do this and next differently from previous?
trim = true; -- why? why do this and next differently from previous?
elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''  
elseif f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]''  
trim = true; -- same question
trim = true; -- same question
end
end
elseif end_chr == "]" then -- if it might be wikimarkup
elseif end_chr == "]" then -- if it might be wikimarkup
if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink  
if f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink  
trim = true;
trim = true;
elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
elseif f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link  
trim = true;
trim = true;
elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
elseif f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link
trim = true;
elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.
trim = true;
trim = true;
end
end
elseif end_chr == " " then -- if last char of output string is a space
elseif end_chr == " " then -- if last char of output string is a space
if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
if f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space>
str = str:sub(1,-3); -- remove them both
str = f.sub(str, 1,-3); -- remove them both
end
end
end
end
Line 837: Line 1,015:
if value ~= comp then -- value does not equal comp when value contains html markup
if value ~= comp then -- value does not equal comp when value contains html markup
local dup2 = duplicate_char;
local dup2 = duplicate_char;
if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it
value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup
else
else
value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character
end
end
end
end
Line 849: Line 1,027:
end
end
return str;
return str;
end
end




Line 864: Line 1,042:
return false;
return false;
end
end


--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
Line 887: Line 1,066:
to use an external editor to maintain this code.
to use an external editor to maintain this code.


\195\128-\195\150 – À-Ö
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
\195\152-\195\182 – Ø-ö
\195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
\195\184-\198\191 – ø-ƿ
\195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
\199\132-\201\143 – DŽ-ɏ%
\199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)


]]
]]


local function is_good_vanc_name (last, first)
local function is_good_vanc_name (last, first)
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it


if is_set (suffix) then
if is_set (suffix) then
Line 910: Line 1,089:
return true;
return true;
end
end


--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Line 932: Line 1,112:


if name then -- if first is initials with or without suffix
if name then -- if first is initials with or without suffix
if 3 > name:len() then -- if one or two initials
if 3 > mw.ustring.len (name) then -- if one or two initials
if suffix then -- if there is a suffix
if suffix then -- if there is a suffix
if is_suffix (suffix) then -- is it legitimate?
if is_suffix (suffix) then -- is it legitimate?
Line 966: Line 1,146:
end
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.
return table.concat(initials) -- Vancouver format does not include spaces.
end
end


--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
--[[--------------------------< L I S T  _ P E O P L E >-------------------------------------------------------
Line 989: Line 1,165:


if 'vanc' == format then -- Vancouver-like author/editor name styling?
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = ','; -- name-list separator between authors is a comma
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between authors is a comma
namesep = ' '; -- last/first separator is a space
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
else
else
sep = ';' -- name-list separator between authors is a semicolon
sep = cfg.presentation['sep_nl']; -- name-list separator between authors is a semicolon
namesep = ', ' -- last/first separator is <comma><space>
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
end
end
Line 1,018: Line 1,194:
one = person.last
one = person.last
local first = person.first
local first = person.first
if is_set(first) then  
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
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
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
end
end
one = one .. namesep .. first  
one = one .. namesep .. first;
end
end
if is_set(person.link) and person.link ~= control.page_name then
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
one = make_wikilink (person.link, one); -- link author/editor if this page is not the author's/editor's page
end
end
end
end
Line 1,051: Line 1,227:
return result, count
return result, count
end
end


--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
Line 1,077: Line 1,254:
--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------
--[[--------------------------< 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,
Evaluates the content of name parameters (author, editor, etc) for variations on the theme of et al.  If found,
the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
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
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
previous passes through this function or by the associated |display-<names>=etal parameter


]]
]]


local function name_has_etal (name, etal, nocat)
local function name_has_etal (name, etal, nocat, param)


if is_set (name) then -- name can be nil in which case just return
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 patterns = cfg.et_al_patterns; --get patterns from configuration
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
if name:match (etal_pattern) then -- variants on et al.
for _, pattern in ipairs (patterns) do -- loop through all of the patterns
name = name:gsub (etal_pattern, ''); -- if found, remove
if name:match (pattern) then -- if this 'et al' pattern is found in name
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
name = name:gsub (pattern, ''); -- remove the offending text
if not nocat then -- no categorization for |vauthors=
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
add_maint_cat ('etal'); -- and add a category if not already added
if not nocat then -- no categorization for |vauthors=
table.insert( z.message_tail, {set_error ('etal', {param})}); -- and set an error if not added
end
end
end
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'?
end
name = name:gsub (others_pattern, ''); -- if found, remove
end
etal = true; -- set flag (may have been set previously here or by |display-authors=etal)
 
if not nocat then -- no categorization for |vauthors=
return name, etal; --
add_maint_cat ('etal'); -- and add a category if not already added
end
 
 
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
 
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc.
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function
adds the editor markup maintenance category.
 
]]
 
local function name_has_ed_markup (name, list_name)
local _, pattern;
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
 
if is_set (name) then
for _, pattern in ipairs (patterns) do -- spin through patterns table and
if name:match (pattern) then
add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
break;
end
end
end
end
end
end
return name, etal; --  
return name; -- and done
end
end


--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------
Line 1,119: Line 1,317:
local count, _;
local count, _;
if is_set (name) then
if is_set (name) then
if name:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, ignore
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
name = name:match ('^%(%((.*)%)%)$'); -- strip parens
else
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
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
end
end
Line 1,132: Line 1,326:
end
end


--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
 
Gets name list from the input arguments
--[[--------------------------< N A M E _ C H E C K S >--------------------------------------------------------
This function calls various name checking functions used to validate the content of the various name-holding
parameters.
 
]]
 
local function name_checks (last, first, list_name)
if is_set (last) then
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
last = last:match ('^%(%((.*)%)%)$'); -- strip parens
else
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation
end
end
if is_set (first) then
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written
first = first:match ('^%(%((.*)%)%)$'); -- strip parens
else
first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
end
end
return last, first; -- done
end
 
 
--[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
Gets name list from the input arguments


Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters.
Line 1,159: Line 1,380:
local etal=false; -- return value set to true when we find some form of et al. in an author parameter
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
local last_alias, first_alias; -- selected parameter aliases used in error messaging
while true do
while true do
last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
last, last_alias = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1
first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
first, first_alias = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i );
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.
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
last = name_has_mult_names (last, err_msg_list_name); -- check for multiple names in last and its aliases
last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks
if first and not last then -- if there is a firstn without a matching lastn
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
table.insert( z.message_tail, { set_error( 'first_missing_last', {first_alias, first_alias:gsub('first', 'last')}, true ) } ); -- add this error message
elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
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
count = count + 1; -- number of times we haven't found last and first
Line 1,183: Line 1,404:
n = n + 1; -- point to next location in the names table
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
table.insert( z.message_tail, { set_error( 'missing_name', {list_name:match ("(%w+)List"):lower(), i-1}, true ) } ); -- add this error message
end
end
count = 0; -- reset the counter, we're looking for two consecutive missing names
count = 0; -- reset the counter, we're looking for two consecutive missing names
Line 1,192: Line 1,413:
return names, etal; -- all done, return our list of names
return names, etal; -- all done, return our list of names
end
end


--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Line 1,202: Line 1,424:
return the original language name string.
return the original language name string.


mw.language.fetchLanguageNames(<local wiki language>, 'all') return a list of languages that in some cases may include
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns 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
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support
code 'cbk' or name 'Chavacano'.
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they
are used as sub-domain names: cbk-zam.wikipedia.org.  A list of language names and codes supported by fetchLanguageNames()
can be found at Template:Citation Style documentation/language/doc


Names but that are included in the list will be found if that name is provided in the |language= parameter.  For example,
Names that are included in the list will be found if that name is provided in the |language= parameter.  For example,
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'.  When names are found
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.
and the associated code is not two or three characters, this function returns only the WikiMedia language name.
 
Some language names have multiple entries under different codes:
Aromanian has code rup and code roa-rup
When this occurs, this function returns the language name and the 2- or 3-character code


Adapted from code taken from Module:Check ISO 639-1.
Adapted from code taken from Module:Check ISO 639-1.
Line 1,215: Line 1,443:


local function get_iso639_code (lang, this_wiki_code)
local function get_iso639_code (lang, this_wiki_code)
if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
end
local ietf_code; -- because some languages have both ietf-like codes and iso 639-like codes
local ietf_name;
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia
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)
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
 
for code, name in pairs(languages) do -- scan the list to see if we can find our language
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 langlc == mw.ustring.lower(name) then
if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported
if 2 == code:len() or 3 == code:len() then -- two- or three-character codes only; extensions not supported
return name; -- so return the name but not the code
return name, code; -- so return the name and the code
end
end
return name, code; -- found it, return name to ensure proper capitalization and the the code
ietf_code = code; -- remember that we found an ietf-like code and save its name
ietf_name = name; -- but keep looking for a 2- or 3-char code
end
end
end
end
return lang; -- not valid language; return language in original case and nil for the code
-- didn't find name with 2- or 3-char code; if ietf-like code found return
return ietf_code and ietf_name or lang; -- associated name; return original language text else
end
end


--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Line 1,260: Line 1,498:


for _, lang in ipairs (names_table) do -- reuse lang
for _, lang in ipairs (names_table) do -- reuse lang
name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap


if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag?
if name then -- there was a remapped code so
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code?
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietf tags from code
else
if lang:match ('^%a%a%-') then -- strip ietf 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
end
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 |language= specified a valid code
if is_set (name) then -- if |language= specified a valid code
code = lang:lower(); -- save it
code = lang:lower(); -- save it
Line 1,275: Line 1,518:
if is_set (code) then -- only 2- or 3-character codes
if is_set (code) then -- only 2- or 3-character codes
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language
if 2 == code:len() then -- and is a two-character code
if 2 == code:len() then -- and is a two-character code
add_prop_cat ('foreign_lang_source', {name, code}) -- categorize it
add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it
else -- or is a recognized language (but has a three-character code)
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
add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template
end
end
end
end
Line 1,292: Line 1,537:
code = #language_list -- reuse code as number of languages in the list
code = #language_list -- reuse code as number of languages in the list
if 2 >= code then
if 2 >= code then
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names
name = table.concat (language_list, cfg.messages['parameter-pair-separator']) -- insert '<space>and<space>' between two language names
elseif 2 < code then
elseif 2 < code then
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>'
name = table.concat (language_list, ', '); -- and concatenate with '<comma><space>' separators
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators
name = name:gsub (', ([^,]+)$', cfg.messages['parameter-final-separator'] .. '%1'); -- replace last '<comma><space>' separator with '<comma><space>and<space>' separator
end
end
if this_wiki_name == name then
if this_wiki_name == name then
Line 1,301: Line 1,546:
end
end
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
--[[ TODO: should only return blank or name rather than full list
so we can clean up the bunched parenthetical elements Language, Type, Format
]]
end
end


--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
--[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------


Set style settings for CS1 citation templates. Returns separator and postscript settings
Set style settings for CS1 citation templates. Returns separator and postscript settings
At en.wiki, for cs1:
ps gets: '.'
sep gets: '.'


]]
]]
Line 1,311: Line 1,563:
local function set_cs1_style (ps)
local function set_cs1_style (ps)
if not is_set (ps) then -- unless explicitely set to something
if not is_set (ps) then -- unless explicitely set to something
ps = '.'; -- terminate the rendered citation with a period
ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation
end
end
return '.', ps; -- separator is a full stop
return cfg.presentation['sep_cs1'], ps; -- element separator
end
end


--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
--[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------


Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
At en.wiki, for cs2:
ps gets: '' (empty string - no terminal punctuation)
sep gets: ','


]]
]]
Line 1,324: Line 1,580:
local function set_cs2_style (ps, ref)
local function set_cs2_style (ps, ref)
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default
ps = ''; -- make sure it isn't nil
ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation
end
end
if not is_set (ref) then -- if |ref= is not set
if not is_set (ref) then -- if |ref= is not set
ref = "harv"; -- set default |ref=harv
ref = "harv"; -- set default |ref=harv
end
end
return ',', ps, ref; -- separator is a comma
return cfg.presentation['sep_cs2'], ps, ref; -- element separator
end
end


--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >----------------------
Line 1,349: Line 1,606:
return sep, ps, ref -- return them all
return sep, ps, ref -- return them all
end
end


--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
Line 1,372: Line 1,630:
return sep, ps, ref
return sep, ps, ref
end
end


--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Line 1,378: Line 1,637:
applying the pdf icon to external links.
applying the pdf icon to external links.


returns true if file extension is one of the recognized extension, else false
returns true if file extension is one of the recognized extensions, else false


]=]
]=]


local function is_pdf (url)
local function is_pdf (url)
return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?');
return url:match ('%.pdf$') or url:match ('%.PDF$') or
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
url:match ('%.PDF&#035') or url:match ('%.pdf&#035');
end
end


--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
Line 1,397: Line 1,659:
local function style_format (format, url, fmt_param, url_param)
local function style_format (format, url, fmt_param, url_param)
if is_set (format) then
if is_set (format) then
format = wrap_style ('format', format); -- add leading space, parenthases, resize
format = wrap_style ('format', format); -- add leading space, parentheses, resize
if not is_set (url) then
if not is_set (url) then
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message
Line 1,409: Line 1,671:
end
end


--[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
 
--[[--------------------------< G E T _ D I S P L A Y _ N A M E S >--------------------------------------------


Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag
Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag
Line 1,432: Line 1,695:
]]
]]


local function get_display_authors_editors (max, count, list_name, etal)
local function get_display_names (max, count, list_name, etal)
if is_set (max) then
if is_set (max) then
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
Line 1,440: Line 1,703:
max = tonumber (max); -- make it a number
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
add_maint_cat ('disp_auth_ed', list_name);
add_maint_cat ('disp_name', cfg.special_case_translation [list_name]);
end
end
else -- not a valid keyword or number
else -- not a valid keyword or number
Line 1,450: Line 1,713:
return max, etal;
return max, etal;
end
end


--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
Line 1,463: Line 1,727:


local function extra_text_in_page_check (page)
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 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]';
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]';


Line 1,471: Line 1,733:
add_maint_cat ('extra_text');
add_maint_cat ('extra_text');
end
end
-- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or  Page:match ('^[Pp]ages?[ %d]') or
end
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
 
-- add_maint_cat ('extra_text');
 
-- end
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
 
split apart a |vauthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the
rendered citation and in the metadata.  Individual author names may be wikilinked
 
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
 
]=]
 
local function get_v_name_table (vparam, output_table, output_link_table)
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
local wl_type, label, link; -- wl_type not used here; just a place holder
local i = 1;
while name_table[i] do
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens
local name = name_table[i];
i=i+1; -- bump indexer to next segment
while name_table[i] do
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens
break; -- and done reassembling so
end
i=i+1; -- bump indexer
end
table.insert (output_table, name); -- and add corporate name to the output table
table.insert (output_link_table, ''); -- no wikilink
else
wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
table.insert (output_table, label); -- add this name
if 1 == wl_type then
table.insert (output_link_table, label); -- simple wikilink [[D]]
else
table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
end
end
i = i+1;
end
return output_table;
end
end


Line 1,496: Line 1,798:
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
local v_name_table = {};
local v_name_table = {};
local v_link_table = {}; -- when name is wikilinked, targets go in this table
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
local last, first, link, mask, suffix;
local last, first, link, mask, suffix;
Line 1,501: Line 1,804:


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)
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
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
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
for i, v_name in ipairs(v_name_table) do
Line 1,544: Line 1,844:
end
end
else
else
is_good_vanc_name (last, '');
if not corporate then
is_good_vanc_name (last, '');
end
end
end
 
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[i];
-- 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 );
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
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list
Line 1,555: Line 1,855:
return names, etal; -- all done, return our list of names
return names, etal; -- all done, return our list of names
end
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 >------------------------
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
Line 1,576: Line 1,877:
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
local lastfirst = false;
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
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a |first1= without a |last1=; this ...
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
lastfirst=true;
lastfirst=true;
end
end
Line 1,605: Line 1,908:
This function is used to validate a parameter's assigned value for those parameters that have only a limited number
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
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
in the source template) the function returns true.  If the parameter value is one of the list of allowed values returns
true; else, emits an error message and returns false.
true; else, emits an error message and returns false.


Line 1,613: Line 1,916:
if not is_set (value) then
if not is_set (value) then
return true; -- an empty parameter is ok
return true; -- an empty parameter is ok
elseif in_array(value:lower(), possible) then
elseif in_array (value, possible) then
return true;
return true;
else
else
Line 1,632: Line 1,935:


local function terminate_name_list (name_list, sepc)
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
if (string.sub (name_list,-3,-1) == sepc .. '. ') then -- if already properly terminated
return name_list; -- just return the name list
elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char
return name_list .. " "; -- don't add another
return name_list .. " "; -- don't add another
else
else
Line 1,661: Line 1,966:
end
end
end
end
 
local vol = '';
local vol = ''; -- here for all cites except magazine
if is_set (volume) then
if is_set (volume) then
if (4 < mw.ustring.len(volume)) then
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals
vol = substitute (cfg.messages['j-vol'], {sepc, volume});
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face
else
elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters
vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
vol = substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold
add_prop_cat ('long_vol');
else -- four or less characters
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold
end
end
end
end
Line 1,678: Line 1,986:




--[[-------------------------< 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.


 
]]
--[[-------------------------< 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)
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
Line 1,727: Line 2,013:
end
end


local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
 
if is_set (page) then
if is_set (page) then
if is_journal then
if is_journal then
Line 1,740: Line 2,026:
if is_journal then
if is_journal then
return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
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
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}), '', '';
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
elseif not nopp then
elseif not nopp then
Line 1,753: Line 2,039:




--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
--[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------


Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the  
returns one of the in-source locators: page, pages, or at.  
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
If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain text
algorithm or provides a calendar 'search' result.  [[WP:ELNO]] discourages links to search results.
for use in COinS. This COinS thing is done because here we convert an interwiki link to and external link and
add an icon span around that; get_coins_pages() doesn't know about the span.  TODO: should it? 


This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
TODO: add support for sheet and sheets?; streamline;
|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:
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
//web.archive.org/<timestamp>... -- the old form
to a new name)?
//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
local function insource_loc_get (page, pages, at)
archive url:
local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
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*/)


]=]
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.


local function archive_url_check (url, date)
ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label
local err_msg = ''; -- start with the error message empty
if ws_url then
local path, timestamp, flag; -- portions of the archive.or url
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
if not url:match('//web%.archive%.org/') then
coins_pages = ws_label;
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
end
end
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.


if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label
table.insert( z.message_tail, { set_error( 'archive_url', {'save command'}, true ) } ); -- add error message
if ws_url then
if Preview_mode then
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
return url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1), date; -- preview mode: modify and return ArchiveURL and ArchiveDate
pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
else
coins_pages = ws_label;
return '', ''; -- return empty strings for archiveURL and ArchiveDate
end
elseif is_set (at) then
ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label
if ws_url then
at = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
at = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
coins_pages = ws_label;
end
end
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
return page, pages, at, coins_pages;
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
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
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
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
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the
tags are removed before the search.
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.


If a missing pipe is detected, this function adds the missing pipe maintenance category.
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=


local function missing_pipe_check (value)
There are two mostly compatible archive.org urls:
local capture;
//web.archive.org/<timestamp>... -- the old form
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
//web.archive.org/web/<timestamp>... -- the new form


capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
The old form does not support or map to the new form when it contains a display flag.  There are four identified flags
if capture and validate (capture) then -- if the capture is a valid parameter name
('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
add_maint_cat ('missing_pipe');
we don't check for these specific flags but we do check the form.
end
 
end
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/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url
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
err_msg = 'save command';
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
elseif url:match('//liveweb%.archive%.org/') then
err_msg = 'liveweb';
else
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
end
-- if here, something not right so
table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and
if is_set (Frame:preprocess('{{REVISIONID}}')) then
return '', ''; -- return empty strings for archiveURL and ArchiveDate
else
return url, date; -- preview mode so return archiveURL and ArchiveDate
end
end




Line 1,875: Line 2,186:
-- Pick out the relevant fields from the arguments.  Different citation templates
-- Pick out the relevant fields from the arguments.  Different citation templates
-- define different field names for the same underlying things.
-- define different field names for the same underlying things.
-- set default parameter values defined by |mode= parameter.
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
Mode = '';
end
local author_etal;
local author_etal;
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
Line 1,890: Line 2,208:
elseif 3 == selected then
elseif 3 == selected then
Authors = A['Authors']; -- use content of |authors=
Authors = A['Authors']; -- use content of |authors=
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
end
end
end
if is_set (Collaboration) then
if is_set (Collaboration) then
Line 1,896: Line 2,217:
end
end


local Coauthors = A['Coauthors'];
local Others = A['Others'];
local Others = A['Others'];


Line 1,912: Line 2,232:
elseif 3 == selected then
elseif 3 == selected then
Editors = A['Editors']; -- use content of |editors=
Editors = A['Editors']; -- use content of |editors=
add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged
end
end
end
end


local translator_etal;
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
local Translators; -- assembled translators name list
local Translators; -- assembled translators name list
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
 
local interviewer_etal;
local interviewers_list = {};
local Interviewers; -- used later
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
 
local contributor_etal;
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
local Contributors; -- assembled contributors name list
local Contributors; -- assembled contributors name list
Line 1,942: Line 2,270:
end
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'
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
NameListFormat = ''; -- anything else, set to empty string
end
end


local Year = A['Year'];
if is_set (Others) then
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor=
add_maint_cat ('others');
end
end
 
local Year = A['Year'];
local PublicationDate = A['PublicationDate'];
local PublicationDate = A['PublicationDate'];
local OrigYear = A['OrigYear'];
local OrigYear = A['OrigYear'];
Line 1,963: Line 2,297:
local Chapter = A['Chapter'];
local Chapter = A['Chapter'];
local ScriptChapter = A['ScriptChapter'];
local ScriptChapter = A['ScriptChapter'];
local ScriptChapterOrigin = A:ORIGIN ('ScriptChapter');
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
local TransChapter = A['TransChapter'];
local TransChapter = A['TransChapter'];
Line 1,975: Line 2,310:
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
local DeadURL = A['DeadURL']
local UrlStatus = A['UrlStatus'];
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes'
if 'url-status' == A:ORIGIN ('UrlStatus') then -- interim: TODO: this line goes away
DeadURL = ''; -- anything else, set to empty string
if not is_valid_parameter_value (UrlStatus, 'url-status', cfg.keywords ['url-status']) then -- set in config.defaults to 'dead'
end
UrlStatus = ''; -- anything else, set to empty string
 
end -- interim: TODO: this line goes away
elseif is_set (A:ORIGIN ('UrlStatus')) then -- interim: while both |dead-url= and |url-status= allowed use separate keyword lists; TODO: remove this section
if not is_valid_parameter_value (UrlStatus, A:ORIGIN ('UrlStatus'), cfg.keywords ['deadurl']) then -- interim: assume |dead-url=; use those keywords; TODO: this line goes away
UrlStatus = ''; -- anything else, set to empty string; interim: TODO: this line goes away
end -- interim: TODO: this line goes away
end -- interim: TODO: this line goes away
if in_array (UrlStatus, {'yes', 'true', 'y'}) then -- TODO: remove this whole thing when |dead-url=[yes|no] parameters removed from articles
UrlStatus = 'dead';
elseif 'no' == UrlStatus then
UrlStatus = 'live';
end
local URL = A['URL']
local URL = A['URL']
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
Line 1,988: Line 2,335:
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
local Periodical = A['Periodical'];
local Periodical = A['Periodical'];
local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local Periodical_origin = '';
if is_set (Periodical) then
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
local i;
Periodical, i = strip_apostrophe_markup (Periodical); -- strip appostrophe markup so that metadata isn't contaminated
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_error ('apostrophe_markup', {Periodical_origin}, true)});
end
end
 
local ScriptPeriodical = A['ScriptPeriodical'];
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
-- web and news not tested for now because of
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
if not (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter
-- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
if p[config.CitationClass]  then
table.insert( z.message_tail, {set_error ('missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)});
end
end
 
local TransPeriodical =  A['TransPeriodical'];


local Series = A['Series'];
local Series = A['Series'];
Line 1,998: Line 2,367:
local At;
local At;


if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
if 'citation' == config.CitationClass then
if is_set (Periodical) then
if not in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
Volume = A['Volume']; -- but does for all other 'periodicals'
end
elseif is_set (ScriptPeriodical) then
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
Volume = A['Volume']; -- but does for all other 'periodicals'
end
else
Volume = A['Volume']; -- and does for non-'periodical' cites
end
elseif in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
Volume = A['Volume'];
Volume = A['Volume'];
end
if 'citation' == config.CitationClass then
if is_set (Periodical) and in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
is_set (ScriptPeriodical) and in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals'
Issue = hyphen_to_dash (A['Issue']);
end
elseif in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
if not (in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (is_set (Periodical) or is_set (ScriptPeriodical))) then
Issue = hyphen_to_dash (A['Issue']);
end
end
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 = '';
local Position = '';
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
if not in_array (config.CitationClass, cfg.templates_not_using_page) then
Page = A['Page'];
Page = A['Page'];
Pages = hyphen_to_dash( A['Pages'] );
Pages = hyphen_to_dash (A['Pages']);
At = A['At'];
At = A['At'];
end
end
Line 2,016: Line 2,406:
local PublisherName = A['PublisherName'];
local PublisherName = A['PublisherName'];
local PublisherName_origin = A:ORIGIN('PublisherName');
if is_set (PublisherName) then
local i=0;
PublisherName, i = strip_apostrophe_markup (PublisherName); -- strip appostrophe markup so that metadata isn't contaminated; publisher is never italicized
if i then -- non-zero when markup was stripped so emit an error message
table.insert( z.message_tail, {set_error ('apostrophe_markup', {PublisherName_origin}, true)});
end
end
local RegistrationRequired = A['RegistrationRequired'];
local RegistrationRequired = A['RegistrationRequired'];
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then
RegistrationRequired=nil;
RegistrationRequired=nil;
end
end
local SubscriptionRequired = A['SubscriptionRequired'];
local SubscriptionRequired = A['SubscriptionRequired'];
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then
Line 2,025: Line 2,426:
end
end


local Via = A['Via'];
local UrlAccess = A['UrlAccess'];
local AccessDate = A['AccessDate'];
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
local Agency = A['Agency'];
UrlAccess = nil;
end
if not is_set(URL) and is_set(UrlAccess) then
UrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } );
end
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription=
end
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message
RegistrationRequired = nil; -- unset; prefer |access= over |registration=
end
 
local ChapterUrlAccess = A['ChapterUrlAccess'];
if not is_valid_parameter_value (ChapterUrlAccess, A:ORIGIN('ChapterUrlAccess'), cfg.keywords ['url-access']) then -- same as url-access
ChapterUrlAccess = nil;
end
if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then
ChapterUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
end
 
local MapUrlAccess = A['MapUrlAccess'];
if not is_valid_parameter_value (MapUrlAccess, 'map-url-access', cfg.keywords ['url-access']) then
MapUrlAccess = nil;
end
if not is_set(A['MapURL']) and is_set(MapUrlAccess) then
MapUrlAccess = nil;
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'map-url'}, true ) } );
end
 
local Via = A['Via'];
local AccessDate = A['AccessDate'];
local Agency = A['Agency'];


local Language = A['Language'];
local Language = A['Language'];
Line 2,043: Line 2,480:


local ID_list = extract_ids( args );
local ID_list = extract_ids( args );
if is_set (DoiBroken) and not ID_list['DOI'] then
table.insert( z.message_tail, { set_error( 'doibroken_missing_doi', A:ORIGIN('DoiBroken'))});
end
local ID_access_levels = extract_id_access_levels( args, ID_list );


local Quote = A['Quote'];
local Quote = A['Quote'];
Line 2,056: Line 2,497:
local LastAuthorAmp = A['LastAuthorAmp'];
local LastAuthorAmp = A['LastAuthorAmp'];
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
LastAuthorAmp = nil; -- set to empty string
LastAuthorAmp = nil; -- set to empty string
end
end
local no_tracking_cats = A['NoTracking'];
local no_tracking_cats = A['NoTracking'];
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then
Line 2,063: Line 2,505:
end
end


--these are used by cite interview
--local variables that are not cs1 parameters
local Callsign = A['Callsign'];
local City = A['City'];
local Program = A['Program'];
 
--local variables that are not cs1 parameters
local use_lowercase; -- controls capitalization of certain static text
local use_lowercase; -- controls capitalization of certain static text
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
Line 2,077: Line 2,514:
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword
DF = ''; -- not valid, set to empty string
DF = ''; -- not valid, set to empty string
end
if not is_set (DF) then
DF = cfg.global_df;
end
end


-- set default parameter values defined by |mode= parameter.  If |mode= is empty or omitted, use CitationClass to set these values
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma
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 PostScript;
local Ref;
local Ref;
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass);
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text


--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then
Line 2,103: Line 2,538:
end
end


-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
-- 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
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 coins_pages;
Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);


local NoPP = A['NoPP']  
local NoPP = A['NoPP']  
Line 2,113: Line 2,552:
end
end


if is_set(Page) then
if not is_set(PublicationPlace) and is_set(Place) then -- both |publication-place= and |place= (|location=) allowed if different
if is_set(Pages) or is_set(At) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
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
 
-- both |publication-place= and |place= (|location=) allowed if different
if not is_set(PublicationPlace) and is_set(Place) then
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
end
end
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
--[[
--[[
Parameter remapping for cite encyclopedia:
Parameter remapping for cite encyclopedia:
When the citation has these parameters:
When the citation has these parameters:
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |title then map |title to |article and |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia and |article then map |encyclopedia to |title
|encyclopedia then map |encyclopedia to |title


|trans_title maps to |trans_chapter when |title is re-mapped
|trans-title maps to |trans-chapter when |title is re-mapped
|url maps to |chapterurl when |title is remapped
|url maps to |chapterurl when |title is remapped
 
All other combinations of |encyclopedia, |title, and |article are not modified
All other combinations of |encyclopedia, |title, and |article are not modified
 
]]
]]


local Encyclopedia = A['Encyclopedia'];
local Encyclopedia = A['Encyclopedia'];


if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation
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 (Periodical) then -- Periodical is set when |encyclopedia is set
if is_set(Title) or is_set (ScriptTitle) then
if is_set(Title) or is_set (ScriptTitle) then
if not is_set(Chapter) then
if not is_set(Chapter) then
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
ScriptChapter = ScriptTitle;
ScriptChapter = ScriptTitle;
ScriptChapterOrigin = 'title';
TransChapter = TransTitle;
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
if not is_set (ChapterURL) and is_set (TitleLink) then
if not is_set (ChapterURL) and is_set (TitleLink) then
Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
Chapter = make_wikilink (TitleLink, Chapter);
end
end
Title = Periodical;
Title = Periodical;
Line 2,169: Line 2,596:
ScriptTitle = '';
ScriptTitle = '';
end
end
else -- |title not set
elseif is_set (Chapter) then -- |title not set
Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title
Title = Periodical; -- |encyclopedia set and |article set so map |encyclopedia to |title
Periodical = ''; -- redundant so unset
Periodical = ''; -- redundant so unset
end
end
Line 2,176: Line 2,603:
end
end


-- Special case for cite techreport.
-- Special case for cite techreport.
if (config.CitationClass == "techreport") then -- special case for cite techreport
if (config.CitationClass == "techreport") then -- special case for cite techreport
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue'
if not is_set(ID) then -- can we use ID for the "number"?
if not is_set(ID) then -- can we use ID for the "number"?
ID = A['Number']; -- yes, use it
ID = A['Number']; -- yes, use it
else -- ID has a value so emit error message
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 )});
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
Line 2,187: Line 2,614:
end
end


-- special case for cite interview
-- special case for cite mailing list
if (config.CitationClass == "interview") then
if (config.CitationClass == "mailinglist") then
if is_set(Program) then
ID = ' ' .. Program;
end
if is_set(Callsign) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. Callsign;
else
ID = ' ' .. Callsign;
end
end
if is_set(City) then
if is_set(ID) then
ID = ID .. sepc .. ' ' .. City;
else
ID = ' ' .. City;
end
end
 
if is_set(Others) then
if is_set(TitleType) then
Others = ' ' .. TitleType .. ' with ' .. Others;
TitleType = '';
else
Others = ' ' .. 'Interview with ' .. Others;
end
else
Others = '(Interview)';
end
end
 
-- special case for cite mailing list
if (config.CitationClass == "mailinglist") then
Periodical = A ['MailingList'];
Periodical = A ['MailingList'];
elseif 'mailinglist' == A:ORIGIN('Periodical') then
elseif 'mailinglist' == Periodical_origin then
Periodical = ''; -- unset because mailing list is only used for cite mailing list
Periodical = ''; -- unset because mailing list is only used for cite mailing list
end
end


-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
-- Account for the oddity that is {{cite conference}}, before generation of COinS data.
if 'conference' == config.CitationClass then
if 'conference' == config.CitationClass then
if is_set(BookTitle) then
if is_set(BookTitle) then
Line 2,232: Line 2,627:
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
ChapterURL = URL;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURLorigin = URLorigin;
ChapterURLorigin = URLorigin;
URLorigin = '';
URLorigin = '';
Line 2,246: Line 2,642:
end
end


-- cite map oddities
-- cite map oddities
local Cartography = "";
local Cartography = "";
local Scale = "";
local Scale = "";
Line 2,254: Line 2,650:
Chapter = A['Map'];
Chapter = A['Map'];
ChapterURL = A['MapURL'];
ChapterURL = A['MapURL'];
ChapterUrlAccess = MapUrlAccess;
TransChapter = A['TransMap'];
TransChapter = A['TransMap'];
ChapterURLorigin = A:ORIGIN('MapURL');
ChapterURLorigin = A:ORIGIN('MapURL');
Line 2,268: Line 2,665:
end
end


-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
local AirDate = A['AirDate'];
local AirDate = A['AirDate'];
Line 2,297: Line 2,694:
-- assemble a table of parts concatenated later into Series
-- assemble a table of parts concatenated later into Series
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end
if is_set(SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
Issue = ''; -- unset because this is not a unique parameter
Issue = ''; -- unset because this is not a unique parameter
Line 2,303: Line 2,700:
Chapter = Title; -- promote title parameters to chapter
Chapter = Title; -- promote title parameters to chapter
ScriptChapter = ScriptTitle;
ScriptChapter = ScriptTitle;
ScriptChapterOrigin = 'title';
ChapterLink = TitleLink; -- alias episodelink
ChapterLink = TitleLink; -- alias episodelink
TransChapter = TransTitle;
TransChapter = TransTitle;
ChapterURL = URL;
ChapterURL = URL;
ChapterUrlAccess = UrlAccess;
ChapterURLorigin = A:ORIGIN('URL');
ChapterURLorigin = A:ORIGIN('URL');
Line 2,313: Line 2,712:


if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL
Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink
Chapter = make_wikilink (ChapterLink, Chapter);
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode;
Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly
Series = make_wikilink (ChapterLink, Series);
end
end
URL = ''; -- unset
URL = ''; -- unset
Line 2,325: Line 2,724:
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
if is_set (Series) and is_set (SeriesLink) then
if is_set (Series) and is_set (SeriesLink) then
Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
Series = make_wikilink (SeriesLink, Series);
end
end
Series = wrap_style ('italic-title', Series); -- series is italicized
Series = wrap_style ('italic-title', Series); -- series is italicized
end
end
end
end
-- end of {{cite episode}} stuff
-- end of {{cite episode}} stuff


-- Account for the oddities that are {{cite arxiv}}, before generation of COinS data.
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
if 'arxiv' == config.CitationClass then
do
if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then
table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
elseif is_set (Series) then -- series is an alias of version
table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message
ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
end
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


AccessDate= ''; -- set these to empty string; not supported in cite arXiv
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = bioRxiv, ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
Chapter = '';
URL = '';
Format = '';
Page = ''; Pages = ''; At = '';
end
end
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
end
end


-- handle type parameter for those CS1 citations that have default values
-- 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
if in_array(config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
TitleType = set_titletype (config.CitationClass, TitleType);
TitleType = set_titletype (config.CitationClass, TitleType);
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis
TitleType = Degree .. " thesis";
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower();
end
end
end
end


if is_set(TitleType) then -- if type parameter is specified
if is_set(TitleType) then -- if type parameter is specified
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
-- TODO: Hack on TitleType to fix bunched parentheses problem
end
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.
-- legacy: promote PublicationDate to Date if neither Date nor Year are set.
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
 
if not is_set (Date) then
if not is_set (Date) then
Date = Year; -- promote Year to Date
Date = Year; -- promote Year to Date
Line 2,377: Line 2,764:
Date = PublicationDate; -- promote PublicationDate to Date
Date = PublicationDate; -- promote PublicationDate to Date
PublicationDate = ''; -- unset, no longer needed
PublicationDate = ''; -- unset, no longer needed
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter
else
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter
end
end
else
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging
end
end


if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation


--[[
--[[
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
we get the date used in the metadata.
we get the date used in the metadata.
 
Date validation supporting code is in Module:Citation/CS1/Date_validation
Date validation supporting code is in Module:Citation/CS1/Date_validation
]]
]]
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
local error_message = '';
local error_message = '';
-- AirDate has been promoted to Date so not necessary to check it
-- AirDate has been promoted to Date so not necessary to check it
local date_parameters_list = {['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken,
local date_parameters_list = {
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};
['access-date'] = {val=AccessDate, name=A:ORIGIN ('AccessDate')},
['archive-date'] = {val=ArchiveDate, name=A:ORIGIN ('ArchiveDate')},
['date'] = {val=Date, name=Date_origin},
['doi-broken-date'] = {val=DoiBroken, name=A:ORIGIN ('DoiBroken')},
['embargo'] = {val=Embargo, name=A:ORIGIN ('Embargo')},
['lay-date'] = {val=LayDate, name=A:ORIGIN ('LayDate')},
['publication-date'] ={val=PublicationDate, name=A:ORIGIN ('PublicationDate')},
['year'] = {val=Year, name=A:ORIGIN ('Year')},
};
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);


anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date);
-- start temporary Julian / Gregorian calendar uncertainty categorization
if COinS_date.inter_cal_cat then
add_prop_cat ('jul_greg_uncertainty');
end
-- end temporary Julian / Gregorian calendar uncertainty categorization


if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;  
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed;  
Line 2,410: Line 2,815:
if not is_set(error_message) then -- error free dates only
if not is_set(error_message) then -- error free dates only
local modified = false; -- flag
local modified = false; -- flag
if is_set (DF) then -- if we need to reformat dates
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
modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate
end
end


if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
modified = true;
modified = true;
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
add_maint_cat ('date_format'); -- hyphens were converted so add maint category
end
end
-- for those wikis that can and want to have English date names translated to the local language,
-- uncomment these three lines.  Not supported by en.wiki (for obvious reasons)
-- set date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
-- if date_name_xlate (date_parameters_list, false) then
-- modified = true;
-- end
if modified then -- if the date_parameters_list values were modified
if modified then -- if the date_parameters_list values were modified
AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with modified values
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values
ArchiveDate = date_parameters_list['archive-date'];
ArchiveDate = date_parameters_list['archive-date'].val;
Date = date_parameters_list['date'];
Date = date_parameters_list['date'].val;
DoiBroken = date_parameters_list['doi-broken-date'];
DoiBroken = date_parameters_list['doi-broken-date'].val;
LayDate = date_parameters_list['lay-date'];
LayDate = date_parameters_list['lay-date'].val;
PublicationDate = date_parameters_list['publication-date'];
PublicationDate = date_parameters_list['publication-date'].val;
end
end
else
else
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message
end
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
end -- end of do


-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set.  Do this after date check but before COInS.
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date
Embargo = is_embargoed (Embargo); --
Embargo = is_embargoed (Embargo);


if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then
Line 2,453: Line 2,853:
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url=
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } );
AccessDate = ''; -- unset
end
end
end
end
end


-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- At this point fields may be nil if they weren't specified in the template use.  We can use that fact.
-- Test if citation has no title
-- Test if citation has no title
if not is_set(Title) and
if not is_set(Title) and
Line 2,467: Line 2,872:
end
end
end
end
 
if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites
if 'none' == Title and
Title = ''; -- set title to empty string
in_array (config.CitationClass, {'journal', 'citation'}) and
add_maint_cat ('untitled');
(is_set (Periodical) or is_set (ScriptPeriodical)) and
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
Title = ''; -- set title to empty string
add_maint_cat ('untitled');
end
end


check_for_url ({ -- add error message when any of these parameters contains a URL
check_for_url ({ -- add error message when any of these parameters hold a URL
['title']=Title,
['title']=Title,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Chapter')]=Chapter,
[A:ORIGIN('Periodical')]=Periodical,
[Periodical_origin] = Periodical,
[A:ORIGIN('PublisherName')] = PublisherName
[PublisherName_origin] = PublisherName
});
});


Line 2,500: Line 2,908:
-- this is the function call to COinS()
-- this is the function call to COinS()
local OCinSoutput = COinS({
local OCinSoutput = COinS({
['Periodical'] = Periodical,
['Periodical'] = strip_apostrophe_markup (Periodical), -- no markup in the metadata
['Encyclopedia'] = Encyclopedia,
['Encyclopedia'] = strip_apostrophe_markup (Encyclopedia),
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup
['Degree'] = Degree; -- cite thesis only
['Degree'] = Degree; -- cite thesis only
Line 2,512: Line 2,920:
['Volume'] = Volume,
['Volume'] = Volume,
['Issue'] = Issue,
['Issue'] = Issue,
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Pages'] = coins_pages or get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
['Edition'] = Edition,
['Edition'] = Edition,
['PublisherName'] = PublisherName,
['PublisherName'] = PublisherName, -- any apostrophe markup already removed
['URL'] = first_set ({ChapterURL, URL}, 2),
['URL'] = first_set ({ChapterURL, URL}, 2),
['Authors'] = coins_author,
['Authors'] = coins_author,
Line 2,521: Line 2,929:
}, config.CitationClass);
}, config.CitationClass);


-- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data.
if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal
Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal
end
end


-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
-- special case for cite newsgroup.  Do this after COinS because we are modifying Publishername to include some static text
if 'newsgroup' == config.CitationClass then
if 'newsgroup' == config.CitationClass then
if is_set (PublisherName) then
if is_set (PublisherName) then
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') ));
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, PublisherName_origin, nil ));
end
end
end
end


-- Now perform various field substitutions.
-- Now perform various field substitutions.
Line 2,541: Line 2,947:
do
do
local last_first_list;
local last_first_list;
-- local maximum;
local control = {  
local control = {  
format = NameListFormat, -- empty string or 'vanc'
format = NameListFormat, -- empty string or 'vanc'
maximum = nil, -- as if display-authors or display-editors not set
maximum = nil, -- as if display-authors or display-editors not set
lastauthoramp = LastAuthorAmp,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn
mode = Mode
};
};


do -- do editor name list first because coauthors can modify control table
do -- do editor name list first because the now unsupported coauthors used to modify control table
control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal);
last_first_list, EditorCount = list_people(control, e, editor_etal);
last_first_list, EditorCount = list_people(control, e, editor_etal);


if is_set (Editors) then
if is_set (Editors) then
Editors, editor_etal = name_has_etal (Editors, editor_etal, false, 'editors'); -- find and remove variations on et al.
if editor_etal then
if editor_etal then
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
Line 2,567: Line 2,974:
EditorCount = 2; -- spoof to display (eds.) annotation
EditorCount = 2; -- spoof to display (eds.) annotation
end
end
end
do -- now do interviewers
control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal);
Interviewers = list_people (control, interviewers_list, interviewer_etal);
end
end
do -- now do translators
do -- now do translators
control.maximum = #t; -- number of translators
control.maximum , translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal);
Translators = list_people(control, t, false); -- et al not currently supported
Translators = list_people (control, t, translator_etal);
end
end
do -- now do contributors
do -- now do contributors
control.maximum = #c; -- number of contributors
control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal);
Contributors = list_people(control, c, false); -- et al not currently supported
Contributors = list_people (control, c, contributor_etal);
end
end
do -- now do authors
do -- now do authors
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
control.maximum , author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal);


if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting.
control.lastauthoramp = nil;
control.maximum = #a + 1;
end
last_first_list = list_people(control, a, author_etal);
last_first_list = list_people(control, a, author_etal);


if is_set (Authors) then
if is_set (Authors) then
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
if author_etal then
if author_etal then
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
Line 2,600: Line 3,006:
end
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
end


-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
-- an error message if the associated url is not set, or an empty string for concatenation
-- 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');
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
Line 2,613: Line 3,016:
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');


-- special case for chapter format so no error message or cat when chapter not supported
-- 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
if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia))) then
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
end
end


if not is_set(URL) then
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
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website=
table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } );
end
end
Line 2,631: Line 3,035:
end
end


local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess;
DeadURL = DeadURL:lower(); -- used later when assembling archived text
-- DeadURL = DeadURL:lower(); -- used later when assembling archived text
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
if is_set( ArchiveURL ) then
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
if is_set (ChapterURL) then -- if chapter-url is set apply archive url to it
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
OriginalFormat = ChapterFormat; -- and original |format=
OriginalFormat = ChapterFormat; -- and original |chapter-format=
if 'no' ~= DeadURL then
-- if 'no' ~= DeadURL then
if 'live' ~= UrlStatus then
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURL = ArchiveURL -- swap-in the archive's url
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls
end
end
elseif is_set (URL) then
elseif is_set (URL) then
OriginalURL = URL; -- save copy of original source URL
OriginalURL = URL; -- save copy of original source URL
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalURLorigin = URLorigin; -- name of url parameter for error messages
OriginalFormat = Format; -- and original |format=
OriginalFormat = Format; -- and original |format=
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
OriginalAccess = UrlAccess;
-- if 'no' ~= DeadURL then -- if URL set then archive-url applies to it
if 'live' ~= UrlStatus then -- if URL set then archive-url applies to it
URL = ArchiveURL -- swap-in the archive's url
URL = ArchiveURL -- swap-in the archive's url
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages
Format = ArchiveFormat or ''; -- swap in archive's format
Format = ArchiveFormat or ''; -- swap in archive's format
UrlAccess = nil; -- restricted access levels do not make sense for archived urls
end
end
  end
  end
end
end


if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) then
local chap_param;
local chap_param;
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
Line 2,665: Line 3,075:
chap_param = A:ORIGIN ('ChapterURL')
chap_param = A:ORIGIN ('ChapterURL')
elseif is_set (ScriptChapter) then
elseif is_set (ScriptChapter) then
chap_param = A:ORIGIN ('ScriptChapter')
chap_param = ScriptChapterOrigin;
else is_set (ChapterFormat)
else is_set (ChapterFormat)
chap_param = A:ORIGIN ('ChapterFormat')
chap_param = A:ORIGIN ('ChapterFormat')
Line 2,686: Line 3,096:
end
end


Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
Chapter = format_chapter_title (ScriptChapter, ScriptChapterOrigin, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
if is_set (Chapter) then
if is_set (Chapter) then
Chapter = Chapter .. ChapterFormat ;
Chapter = Chapter .. ChapterFormat ;
Line 2,699: Line 3,109:


-- Format main title.
-- Format main title.
if is_set(TitleLink) and is_set(Title) then
if is_set (ArchiveURL) and mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation['archived_copy']) then -- if title is 'Archived copy' (place holder added by bots that can't find proper title)
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title
end
end


if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or
if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup:
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
else
if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title=
Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three
elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ...
not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.)
Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
end
end
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) or
('map' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical))) then -- special case for cite map when the map is in a periodical treat as an article
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap_style ('quoted-title', Title);
Title = wrap_style ('quoted-title', Title);
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
TransTitle= wrap_style ('trans-quoted-title', TransTitle );
elseif 'report' == config.CitationClass then -- no styling for cite report
elseif 'report' == config.CitationClass then -- no styling for cite report
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
else
else
Title = wrap_style ('italic-title', Title);
Title = wrap_style ('italic-title', Title);
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = wrap_style ('trans-italic-title', TransTitle);
TransTitle = wrap_style ('trans-italic-title', TransTitle);
end
end
Line 2,728: Line 3,148:
end
end
end
end
 
Title = Title .. TransTitle;
if is_set(Title) then
if is_set(Title) then
if not is_set(TitleLink) and is_set(URL) then
if not is_set (TitleLink) and is_set (URL) then
Title = external_link( URL, Title, URLorigin ) .. TransError .. Format;
Title = external_link (URL, Title, URLorigin, UrlAccess) .. TransTitle .. TransError .. Format;
-- this experiment hidden 2016-04-10; see Help_talk:Citation_Style_1#Recycled_urls
-- local temp_title = external_link( URL, Title, URLorigin ) .. TransError .. Format; -- do this so we get error message even if url is usurped no archive
-- if in_array (DeadURL, {'unfit no archive', 'usurped no archive'}) then -- when url links to inappropriate location and there is no archive of original source available
-- local err_msg
-- if temp_title:match ('%[%S+%s+(.+)%](<.+)') then -- if there is an error message
-- Title, err_msg = temp_title:match ('%[%S+%s+(.+)%](<.+)'); -- strip off external link; TODO: find a better to do this
-- Title = Title .. (err_msg or '');
-- end
-- else
-- Title = temp_title;
-- end
 
URL = ''; -- unset these because no longer needed
URL = ''; -- unset these because no longer needed
Format = "";
Format = "";
elseif is_set (TitleLink) and not is_set (URL) then
local ws_url;
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here
if ws_url then
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
Title = Title .. TransTitle .. TransError;
else
Title = make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
end
else
else
Title = Title .. TransError;
local ws_url, ws_label;
ws_url, ws_label, L = wikisource_url_make (Title); -- make ws url from |title= interwiki link; link portion L becomes tool tip label
if ws_url then
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup
Title = external_link (ws_url, Title .. '&nbsp;', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this?
Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
Title = Title .. TransTitle .. TransError;
else
Title = Title .. TransTitle .. TransError;
end
end
end
else
Title = TransTitle .. TransError;
end
end


Line 2,759: Line 3,186:
if is_set (Conference) then
if is_set (Conference) then
if is_set (ConferenceURL) then
if is_set (ConferenceURL) then
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin );
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil );
end
end
Conference = sepc .. " " .. Conference .. ConferenceFormat;
Conference = sepc .. " " .. Conference .. ConferenceFormat;
elseif is_set(ConferenceURL) then
elseif is_set(ConferenceURL) then
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin );
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil );
end
end


Line 2,817: Line 3,244:
else
else
Language=""; -- language not specified so make sure this is an empty string;
Language=""; -- language not specified so make sure this is an empty string;
--[[ TODO: need to extract the wrap_msg from language_parameter
so that we can solve parentheses bunching problem with Format/Language/TitleType
]]
end
end


Line 2,822: Line 3,252:
if is_set (Translators) then
if is_set (Translators) then
-- Others = sepc .. ' Translated by ' .. Translators .. Others;  
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;  
end
if is_set (Interviewers) then
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
end
end
 
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or "";
if is_set (Edition) then
if is_set (Edition) then
Line 2,836: Line 3,268:
end
end


Series = is_set(Series) and (sepc .. " " .. Series) or "";
Series = is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
OrigYear = is_set (OrigYear) and wrap_msg ('origyear', OrigYear) or '';
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
Agency = is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
 
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);


------------------------------------ totally unrelated data
------------------------------------ totally unrelated data
if is_set(Via) then
Via = is_set (Via) and  wrap_msg ('via', Via) or '';
Via = " " .. wrap_msg ('via', Via);
end


--[[
--[[
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
Subscription implies paywall; Registration does not.  If both are used in a citation, the subscription required link
note is displayed. There are no error messages for this condition.
note is displayed. There are no error messages for this condition.
 
]]
]]
if is_set (SubscriptionRequired) then
if is_set (SubscriptionRequired) then
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
Line 2,864: Line 3,293:


AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
-- neither of these work; don't know why; it seems that substitute() isn't being called
 
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
end
end
Line 2,878: Line 3,307:
end
end


ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );


if is_set(URL) then
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin );
URL = " " .. external_link( URL, nil, URLorigin, UrlAccess );
end
end


Line 2,897: Line 3,326:
ArchiveDate = set_error('archive_missing_date');
ArchiveDate = set_error('archive_missing_date');
end
end
if "no" == DeadURL then
if "live" == UrlStatus then
local arch_text = cfg.messages['archived'];
local arch_text = cfg.messages['archived'];
if sepc ~= "." then arch_text = arch_text:lower() end
if sepc ~= "." then arch_text = arch_text:lower() end
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
Archived = sepc .. " " .. substitute( cfg.messages['archived-live'],
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } );
if not is_set(OriginalURL) then
if not is_set(OriginalURL) then
Archived = Archived .. " " .. set_error('archive_missing_url');    
Archived = Archived .. " " .. set_error('archive_missing_url');    
end
end
elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
elseif is_set(OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown'
local arch_text = cfg.messages['archived-dead'];
local arch_text = cfg.messages['archived-dead'];
if sepc ~= "." then arch_text = arch_text:lower() end
if sepc ~= "." then arch_text = arch_text:lower() end
if in_array (DeadURL, {'unfit', 'usurped'}) then
if in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled
else -- DeadURL is empty, 'yes', 'true', or 'y'
if 'bot: unknown' == UrlStatus then
add_maint_cat ('bot:_unknown'); -- and add a category if not already added
else
add_maint_cat ('unfit'); -- and add a category if not already added
end
else -- UrlStatus is empty, 'dead'
Archived = sepc .. " " .. substitute( arch_text,
Archived = sepc .. " " .. substitute( arch_text,
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
end
end
else
else
Line 2,935: Line 3,369:
end
end
if sepc == '.' then
if sepc == '.' then
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
else
else
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate
end
end
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
Line 2,945: Line 3,379:
if is_set(Transcript) then
if is_set(Transcript) then
if is_set(TranscriptURL) then
if is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil );
end
end
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
elseif is_set(TranscriptURL) then
elseif is_set(TranscriptURL) then
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil );
end
end


local Publisher;
local Publisher;
if is_set(Periodical) and
if is_set(PublicationDate) then
not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
PublicationDate = wrap_msg ('published', PublicationDate);
if is_set(PublisherName) then
end
if is_set(PublicationPlace) then
if is_set(PublisherName) then
Publisher = PublicationPlace .. ": " .. PublisherName;
if is_set(PublicationPlace) then
else
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
Publisher = PublisherName; 
else
end
Publisher = sepc .. " " .. PublisherName .. PublicationDate;   
elseif is_set(PublicationPlace) then
end
Publisher= PublicationPlace;
elseif is_set(PublicationPlace) then  
else
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
Publisher = "";
else  
end
Publisher = PublicationDate;
if is_set(PublicationDate) then
if is_set(Publisher) then
Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate);
else
Publisher = PublicationDate;
end
end
if is_set(Publisher) then
Publisher = " (" .. Publisher .. ")";
end
else
if is_set(PublicationDate) then
PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")";
end
if is_set(PublisherName) then
if is_set(PublicationPlace) then
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
else
Publisher = sepc .. " " .. PublisherName .. PublicationDate;   
end
elseif is_set(PublicationPlace) then  
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
else  
Publisher = PublicationDate;
end
end
end
-- Several of the above rely upon detecting this as nil, so do it last.
-- Several of the above rely upon detecting this as nil, so do it last.
if is_set(Periodical) then
if (is_set (Periodical) or is_set (ScriptPeriodical) or is_set (TransPeriodical)) then
if is_set(Title) or is_set(TitleNote) then  
if is_set(Title) or is_set(TitleNote) then  
Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)  
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical);
else  
else  
Periodical = wrap_style ('italic-title', Periodical)
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical);
end
end
end
end


--[[
--[[
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
Handle the oddity that is cite speech.  This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
]]
]]
if "speech" == config.CitationClass then -- cite speech only
if "speech" == config.CitationClass then -- cite speech only
TitleNote = " (Speech)"; -- annotate the citation
TitleNote = " (Speech)"; -- annotate the citation
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter  
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter  
if is_set (Conference) then -- and if |event= is set
if is_set (Conference) then -- and if |event= is set
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
end
end
end
end
Line 3,023: Line 3,432:
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
if is_set(Others) then Others = Others .. sepc .. " " end
if is_set(Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,  
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
Language, Edition, Publisher, Agency, Volume}, sepc );
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites
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
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
Line 3,045: Line 3,452:
elseif 'episode' == config.CitationClass then -- special case for cite episode
elseif 'episode' == config.CitationClass then -- special case for cite episode
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
 
else -- all other CS1 templates
else -- all other CS1 templates
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language,  
Line 3,057: Line 3,465:
end
end
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
local idcommon;
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
else
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
end
local text;
local text;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
Line 3,073: Line 3,487:
end
end
if is_set(Authors) then
if is_set(Authors) then
if is_set(Coauthors) then
if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
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
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
end
end
Line 3,088: Line 3,495:
if is_set(Chapter) and 0 == #c then
if is_set(Chapter) and 0 == #c then
in_text = in_text .. cfg.messages['in'] .. " "
in_text = in_text .. cfg.messages['in'] .. " "
if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2
if (sepc ~= '.') then
in_text = in_text:lower() -- lowercase for cs2
end
end
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
else
else
if EditorCount <= 1 then
post_text = " (" .. cfg.messages['editors'] .. ")";
post_text = ", " .. cfg.messages['editor'];
end
else
post_text = ", " .. cfg.messages['editors'];
end
end  
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
end
end
Line 3,102: Line 3,510:
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
Authors = by_text .. Authors; -- author follows title so tweak it here
Authors = by_text .. Authors; -- author follows title so tweak it here
if is_set (Editors) then -- when Editors make sure that Authors gets terminated
if is_set (Editors) and is_set (Date) then -- when Editors make sure that Authors gets terminated
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
end
end
if not is_set (Date) then -- when date is set it's in parentheses; no Contributors termination
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
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
end
end
Line 3,136: Line 3,544:
if is_set(PostScript) and PostScript ~= sepc then
if is_set(PostScript) and PostScript ~= sepc then
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
text = text:sub(1,-sepc:len()-1);
text = text:sub(1,-sepc:len()-1);
end
end
Line 3,174: Line 3,582:
end
end
if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>","")) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains
z.error_categories = {};
z.error_categories = {};
text = set_error('empty_citation');
text = set_error('empty_citation');
Line 3,180: Line 3,588:
end
end
local render = {}; -- here we collect the final bits for concatenation into the rendered citation
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags
text = substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text}); -- when |ref= is set
table.insert (render, substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set
else
else
text = substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text}); -- all other cases
table.insert (render, substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases
end
end


text = text .. substitute (cfg.presentation['ocins'], {OCinSoutput}); -- append metadata to the citation
table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation
 
if #z.message_tail ~= 0 then
if 0 ~= #z.message_tail then
text = text .. " ";
table.insert (render, ' ');
for i,v in ipairs( z.message_tail ) do
for i,v in ipairs( z.message_tail ) do
if is_set(v[1]) then
if is_set(v[1]) then
if i == #z.message_tail then
if i == #z.message_tail then
text = text .. error_comment( v[1], v[2] );
table.insert (render, error_comment( v[1], v[2] ));
else
else
text = text .. error_comment( v[1] .. "; ", v[2] );
table.insert (render, error_comment( v[1] .. "; ", v[2] ));
end
end
end
end
end
end
end
end
 
 
if #z.maintenance_cats ~= 0 then
if 0 ~= #z.maintenance_cats then
text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">';
local maint_msgs = {}; -- here we collect all of the maint messages
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])';
local maint = {}; -- here we assemble a maintenence message
end
table.insert (maint, v); -- maint msg is the category name
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
table.insert (maint, ' ('); -- open the link text
end
table.insert (maint, make_wikilink (':Category:' .. v, 'link')); -- add the link
table.insert (maint, ')'); -- and close it
no_tracking_cats = no_tracking_cats:lower();
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
end
for _, v in ipairs( z.error_categories ) do
table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
text = text .. '[[Category:' .. v ..']]';
end
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
no_tracking_cats = no_tracking_cats:lower();
text = text .. '[[Category:' .. v ..']]';
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
end
for _, v in ipairs( z.error_categories ) do
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
table.insert (render, make_wikilink ('Category:' .. v));
text = text .. '[[Category:' .. v ..']]';
end
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
end
table.insert (render, make_wikilink ('Category:' .. v));
end
return text
for _, v in ipairs( z.properties_cats ) do -- append properties categories
end
table.insert (render, make_wikilink ('Category:' .. v));
 
end
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
end
 
 
This is used by templates such as {{cite book}} to create the actual citation text.
return table.concat (render);
 
end
]]
 
 
 
function cs1.citation(frame)
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
local pframe = frame:getParent()
 
local validation, utilities, identifiers, metadata;
Looks for a parameter's name in one of several whitelists.
 
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
Parameters in the whitelist can have three values:
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
true - active, supported parameters
false - deprecated, supported parameters
nil - unsupported parameters
]]
 
local function validate (name, cite_class)
local name = tostring (name);
local state;
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) then -- limited parameter sets allowed for these templates
state = whitelist.limited_basic_arguments[name];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
state = whitelist[cite_class .. '_basic_arguments'][name]; -- look in the parameter-list for the template identified by cite_class
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- limited enumerated parameters list
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.limited_numbered_arguments[name];
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
 
return false; -- not supported because not found or name is set to nil
end -- end limited parameter-set templates
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
-- all enumerated parameters allowed
name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
state = whitelist.numbered_arguments[name];
 
if true == state then return true; end -- valid actively supported parameter
if false == state then
deprecated_parameter (name); -- parameter is deprecated but still supported
return true;
end
return false; -- not supported because not found or name is set to nil
end
 
 
--[[--------------------------< 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 (parameter, value)
local capture;
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
 
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
if capture and validate (capture) then -- if the capture is a valid parameter name
table.insert( z.message_tail, {set_error ('missing_pipe',parameter)});
end
end
 
 
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
 
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
 
]]
 
local function has_extraneous_punc (param, value)
if cfg.punct_skip[param] then
return; -- parameter name found in the skip table so done
end
if value:match ('[,;:]$') then
add_maint_cat ('extra_punct'); -- has extraneous punctuation; add maint cat
end
end
 
 
--[[--------------------------< C I T A T I O N >--------------------------------------------------------------
 
This is used by templates such as {{cite book}} to create the actual citation text.
 
]]
 
local function citation(frame)
Frame = frame; -- save a copy incase we need to display an error message in preview mode
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata, styles;
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
utilities = require ('Module:Citation/CS1/Utilities/sandbox');
Line 3,242: Line 3,764:
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
metadata = require ('Module:Citation/CS1/COinS/sandbox');
styles = 'Module:Citation/CS1/sandbox/styles.css';
else -- otherwise
else -- otherwise
Line 3,250: Line 3,773:
identifiers = require ('Module:Citation/CS1/Identifiers');
identifiers = require ('Module:Citation/CS1/Identifiers');
metadata = require ('Module:Citation/CS1/COinS');
metadata = require ('Module:Citation/CS1/COinS');
styles = 'Module:Citation/CS1/styles.css';
end
end


utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
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
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module


Line 3,261: Line 3,786:
reformat_dates = validation.reformat_dates;
reformat_dates = validation.reformat_dates;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
date_hyphen_to_dash = validation.date_hyphen_to_dash;
date_name_xlate = validation.date_name_xlate;
 
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities
in_array = utilities.in_array;
in_array = utilities.in_array;
Line 3,271: Line 3,797:
wrap_style = utilities.wrap_style;
wrap_style = utilities.wrap_style;
safe_for_italics = utilities.safe_for_italics;
safe_for_italics = utilities.safe_for_italics;
remove_wiki_link = utilities.remove_wiki_link;
is_wikilink = utilities.is_wikilink;
make_wikilink = utilities.make_wikilink;
strip_apostrophe_markup = utilities.strip_apostrophe_markup;


z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
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
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers
build_id_list = identifiers.build_id_list;
build_id_list = identifiers.build_id_list;
is_embargoed = identifiers.is_embargoed;
is_embargoed = identifiers.is_embargoed;
extract_id_access_levels = identifiers.extract_id_access_levels;
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS
Line 3,283: Line 3,812:
COinS = metadata.COinS;
COinS = metadata.COinS;


local args = {}; -- table where we store all of the template's arguments
Preview_mode = frame:preprocess('{{REVISIONID}}'); -- use magic word to get revision id
local suggestions = {}; -- table where we store suggestions if we need to loadData them
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 = {};
local error_text, error_state;
local error_text, error_state;


local config = {};
local config = {}; -- table to store parameters from the module {{#invoke:}}
for k, v in pairs( frame.args ) do
for k, v in pairs( frame.args ) do
config[k] = v;
config[k] = v;
args[k] = v;  
-- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}}
end
end


Line 3,304: Line 3,825:
for k, v in pairs( pframe.args ) do
for k, v in pairs( pframe.args ) do
if v ~= '' then
if v ~= '' then
if not validate( k ) then
if ('string' == type (k)) then
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
end
if not validate( k, config.CitationClass ) then
error_text = "";
error_text = "";
if type( k ) ~= 'string' then
if type( k ) ~= 'string' then
Line 3,311: Line 3,835:
error_text, error_state = set_error( 'text_ignored', {v}, true );
error_text, error_state = set_error( 'text_ignored', {v}, true );
end
end
elseif validate( k:lower() ) then  
elseif validate( k:lower(), config.CitationClass ) then  
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true );
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter
else
else
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
if nil == suggestions.suggestions then -- if this table is nil then we need to load it
Line 3,324: Line 3,848:
capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match
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  
if capture then -- if the pattern matches  
param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)
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
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists)
error_text, error_state = set_error ('parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
else
error_text, error_state = set_error( 'parameter_ignored', {param}, true ); -- suggested param not supported by this template
end
end
end
end
end
Line 3,333: Line 3,861:
else
else
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
error_text, error_state = set_error( 'parameter_ignored', {k}, true );
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
end
end
end
end
Line 3,340: Line 3,869:
end
end
end
end
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe?
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
-- TODO: is this the best place for this translation?
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then
args[k] = v;
args[k] = v;
elseif args[k] ~= nil or (k == 'postscript') then -- here when v is empty string
args[k] = v; -- why do we do this?  we don't support 'empty' parameters
end
end
end
end
Line 3,351: Line 3,880:
if 'string' == type (k) then -- don't evaluate positional parameters
if 'string' == type (k) then -- don't evaluate positional parameters
has_invisible_chars (k, v);
has_invisible_chars (k, v);
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
end
end
end
end
return citation0( config, args)
return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})});
end
end


return cs1;
--[[--------------------------< E X P O R T E D  F U N C T I O N S >------------------------------------------
]]
 
return {citation = citation};
Icem4k
Administrators, upwizcampeditors
0

edits

Retrieved from "http://www.chalochatu.org/Special:MobileDiff/1832...21186"