Changes

Jump to navigation Jump to search
16,716 bytes added ,  10:35, 11 February 2019
m
1 revision imported
Line 5: Line 5:  
]]
 
]]
   −
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;
    
local z ={}; -- tables in Module:Citation/CS1/Utilities
 
local z ={}; -- tables in Module:Citation/CS1/Utilities
   −
local extract_ids, extract_id_access_levels, 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 54: Line 55:  
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
 
added_prop_cats is a table declared in page scope variables above
Line 66: Line 71:  
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
 +
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
 
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 126: Line 133:  
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 and .cash 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 146: Line 153:  
 
 
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
 
if not domain:match ('^[%a%d]') then -- first character must be letter or digit
 +
return false;
 +
end
 +
 +
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at wikisource
 
return false;
 
return false;
 
end
 
end
Line 153: Line 164:  
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
 
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix
 
return true;
 
return true;
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname
+
elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname
 +
return true;
 +
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/digit .org hostname
 
return true;
 
return true;
 
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
 
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)
Line 249: 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 376: 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 388: Line 403:  
local path;
 
local path;
 
local base_url;
 
local base_url;
+
 
 
if not is_set( label ) then
 
if not is_set( label ) then
 
label = URL;
 
label = URL;
Line 404: 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
 
end
+
 
base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" });
+
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url
+
 
if is_set(access) then -- access level (free, paywalled, ...)
+
if is_set (access) then -- access level (subscription, registration, limited)
base_url = substitute(cfg.presentation[access], base_url);
+
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({ base_url, error_str });
+
return table.concat ({base_url, error_str});
 
end
 
end
   Line 434: Line 449:  
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'"
Line 442: Line 460:  
Double single quotes (italic or bold wikimarkup) are not kerned.
 
Double single quotes (italic or bold wikimarkup) are not kerned.
   −
Replaces unicode quotemarks with typewriter quote marks regardless of the need for kerning.
+
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='';
-- TODO: move this elswhere so that all title-holding elements get these quote marks replaced?
+
local wl_type, label, link;
str= mw.ustring.gsub (str, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark)
+
 
str= mw.ustring.gsub (str, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
+
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 501: Line 541:  
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 519: Line 559:  
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 559: Line 600:       −
--[[--------------------------< 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 ws_url then
 +
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable url
 +
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of anchor
 +
end
 +
 +
return ws_url, ws_label, L or D; -- return proper url or nil and a label or nil
 +
end
 +
 +
 +
--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
 +
 +
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
 +
parameter (chapter_url_source used for error messages).
 +
 +
]]
 +
 +
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access)
 +
local chapter_error = '';
 +
 +
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource url and label from a wikisource interwiki link
 +
if ws_url then
 +
ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters
 +
chapter = ws_label;
 +
end
 +
 
if not is_set (chapter) then
 
if not is_set (chapter) then
 
chapter = ''; -- to be safe for concatenation
 
chapter = ''; -- to be safe for concatenation
 
else
 
else
 
if false == no_quotes then
 
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 = 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);
 
chapter = wrap_style ('quoted-title', chapter);
 
end
 
end
Line 579: Line 678:     
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 
chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
 +
 +
if is_set (chapterurl) then
 +
chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
 +
elseif ws_url then
 +
chapter = external_link (ws_url, chapter .. '&nbsp;', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this?
 +
chapter = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
 +
end
    
if is_set (transchapter) then
 
if is_set (transchapter) then
Line 590: Line 696:  
end
 
end
   −
if is_set (chapterurl) then
+
-- if is_set (chapterurl) then
chapter = external_link (chapterurl, chapter, chapter_url_source, nil); -- adds bare_url_missing_title error if appropriate
+
-- chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate
end
+
-- end
    
return chapter .. chapter_error;
 
return chapter .. chapter_error;
 
end
 
end
 +
    
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
 
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
Line 631: Line 738:  
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it
 
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
 
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
 
 
 
if position then
 
if position then
if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition)
+
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
stripmarker = true; -- set a flag
+
('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
 +
stripmarker = true; -- set a flag
 
elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
 
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
 
position = nil; -- unset
Line 703: Line 817:  
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 760: Line 841:  
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 782: Line 864:  
--[[--------------------------< 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 801: Line 920:     
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 825: Line 947:  
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 858: Line 982:  
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 870: Line 994:  
end
 
end
 
return str;
 
return str;
end
+
end
      Line 885: Line 1,009:  
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 931: Line 1,056:  
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 953: Line 1,079:     
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 989: Line 1,115:  
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 1,005: Line 1,132:     
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
elseif 'mla' == control.mode then
  −
sep = ','; -- name-list separator between authors is a comma
  −
namesep = ', ' -- last/first separator is <comma><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 1,038: Line 1,162:  
local first = person.first
 
local first = person.first
 
if is_set(first) then
 
if is_set(first) then
if 'mla' == control.mode then  
+
if ( "vanc" == format ) then -- if vancouver format
if i == 1 then -- for mla
+
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
one = one .. namesep .. first; -- first name last, first
+
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
else -- all other names
+
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
one = first .. ' ' .. one; -- first last
   
end
 
end
else
  −
if ( "vanc" == format ) then -- if vancouver format
  −
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
  −
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
  −
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
  −
end
  −
end
  −
one = one .. namesep .. first;
   
end
 
end
 +
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 1,066: Line 1,182:  
if count > 0 then  
 
if count > 0 then  
 
if count > 1 and is_set(lastauthoramp) and not etal then
 
if count > 1 and is_set(lastauthoramp) and not etal then
if 'mla' == control.mode then
+
text[#text-2] = " & "; -- replace last separator with ampersand text
text[#text-2] = ", and "; -- replace last separator with ', and ' text
  −
else
  −
text[#text-2] = " & "; -- replace last separator with ampersand text
  −
end
   
end
 
end
 
text[#text] = nil; -- erase the last separator
 
text[#text] = nil; -- erase the last separator
Line 1,082: Line 1,194:  
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 1,138: Line 1,251:  
return name, etal; --  
 
return name, etal; --  
 
end
 
end
 +
 +
 +
--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------
 +
 +
Evaluates the content of author and editor parameters for 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 = { -- these patterns match annotations at end of name
 +
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')'
 +
'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name)
 +
'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')'
 +
'[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive
 +
 +
-- these patterns match annotations at beginning of name
 +
'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.'
 +
'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.'
 +
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's'
 +
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets
 +
}
 +
 +
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
 +
return name; -- and done
 +
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 1,150: Line 1,299:  
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', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template
  −
end
   
end
 
end
 
end
 
end
Line 1,163: Line 1,308:  
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 1,199: Line 1,371:  
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al.
 
last, etal = name_has_etal (last, etal, false); -- 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); -- 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
last = name_has_mult_names (last, list_name); -- check for multiple names in last and its aliases
   
 
 
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
Line 1,224: Line 1,395:  
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 1,234: Line 1,406:  
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 1,247: Line 1,425:     
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 1,292: Line 1,480:     
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 1,307: Line 1,500:  
 
 
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 1,324: Line 1,519:  
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 1,337: Line 1,532:  
]]
 
]]
 
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 1,346: Line 1,545:  
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 1,359: Line 1,562:  
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 1,384: Line 1,588:  
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 1,397: Line 1,602:  
sep, ps, ref = set_cs2_style (ps, ref);
 
sep, ps, ref = set_cs2_style (ps, ref);
 
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
 
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
sep, ps = set_cs1_style (ps);
  −
elseif 'mla' == mode then -- if this template is to be rendered in mla style use cs1 for bot cs1 & cs2 templates
   
sep, ps = set_cs1_style (ps);
 
sep, ps = set_cs1_style (ps);
 
else -- anything but cs1 or cs2
 
else -- anything but cs1 or cs2
Line 1,409: Line 1,612:  
return sep, ps, ref
 
return sep, ps, ref
 
end
 
end
 +
    
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
 
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------
Line 1,415: Line 1,619:  
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[%?#]');
 
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 1,434: Line 1,639:  
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 1,445: Line 1,650:  
return format;
 
return format;
 
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 _ A U T H O R S _ E D I T O R S >------------------------
Line 1,487: Line 1,693:  
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 1,500: Line 1,707:     
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 1,508: Line 1,713:  
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
  −
-- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or  Pages:match ('^[Pp]ages?[ %d]') then
  −
-- add_maint_cat ('extra_text');
  −
-- end
   
end
 
end
   −
--[[--------------------------< G E T _ V _ N A M E _ T A B L E >----------------------------------------------
     −
split apart a |vautthors= or |veditors= parameter.  This function allows for corporate names, wrapped in doubled
+
--[=[-------------------------< 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
 
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.
+
rendered citation and in the metadata. Individual author names may be wikilinked
   −
|vauthors=Jones AB, White EB, ((Black, Brown, and Co.))
+
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
   −
This code is experimental and may not be retained.
+
]=]
   −
]]
+
local function get_v_name_table (vparam, output_table, output_link_table)
local function get_v_name_table (vparam, output_table)
   
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas
 
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;
 
local i = 1;
Line 1,542: Line 1,744:  
end
 
end
 
table.insert (output_table, name); -- and add corporate name to the output table
 
table.insert (output_table, name); -- and add corporate name to the output table
 +
table.insert (output_link_table, ''); -- no wikilink
 
else
 
else
table.insert (output_table, name_table[i]); -- add this name
+
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
 
end
 
i = i+1;
 
i = i+1;
Line 1,549: Line 1,758:  
return output_table;
 
return output_table;
 
end
 
end
 +
    
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
 
--[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
Line 1,568: Line 1,778:  
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 1,573: Line 1,784:     
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 = get_v_name_table (vparam, v_name_table); -- 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 1,620: Line 1,828:  
end
 
end
 
end
 
end
-- this from extract_names ()
+
 
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i );
+
link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[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 1,680: Line 1,888:  
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.
    
]]
 
]]
   −
local function is_valid_parameter_value (value, name, possible, cite_class)
+
local function is_valid_parameter_value (value, name, possible)
-- begin hack to limit |mode=mla to a specific set of templates
  −
if ('mode' == name) and ('mla' == value) and not in_array (cite_class, {'book', 'journal', 'news'}) then
  −
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
  −
return false
  −
end
  −
-- end hack
  −
 
   
if not is_set (value) then
 
if not is_set (value) then
 
return true; -- an empty parameter is ok
 
return true; -- an empty parameter is ok
Line 1,714: Line 1,915:     
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 1,729: Line 1,932:  
]]
 
]]
 
 
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower, mode)
+
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
 
if not is_set (volume) and not is_set (issue) then
 
if not is_set (volume) and not is_set (issue) then
 
return '';
 
return '';
 
end
 
end
 
 
if ('mla' == mode) and ('journal' == cite_class) then -- same as cs1 for magazines
  −
lower = true; -- mla 8th edition; force these to lower case
  −
if is_set (volume) and is_set (issue) then
  −
return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
  −
elseif is_set (volume) then
  −
return wrap_msg ('vol', {sepc, volume}, lower);
  −
else
  −
return '';
  −
end
  −
end
  −
   
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
 
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
 
if is_set (volume) and is_set (issue) then
 
if is_set (volume) and is_set (issue) then
Line 1,755: Line 1,947:  
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 = substitute (cfg.presentation['vol-bold'], {sepc, 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 1,769: Line 1,964:  
return vol;
 
return vol;
 
end
 
end
  −
  −
--[[-------------------------< N O R M A L I Z E _ P A G E _ L I S T >-----------------------------------------
  −
  −
not currently used
  −
  −
normalizes a comma, ampersand, and/or space separated list to be '<value>, <value>, ..., <value>'
  −
returns list unchanged if there are no commas else strips whitespace and then reformats the list
  −
  −
]]
  −
--[[
  −
local function normalize_page_list (list)
  −
if not list:find ('[,& ]') then return list end -- if list is not delimited with commas, ampersands, or spaces; done
  −
  −
list = mw.text.split (list, '[,&%s]+'); -- make a table of values
  −
list = table.concat (list, ', '); -- and now make a normalized list
  −
return list;
  −
end
  −
]]
        Line 1,800: Line 1,976:  
]]
 
]]
   −
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower, mode)
+
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
 
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
 
if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
 
if is_set (sheet) then
 
if is_set (sheet) then
Line 1,817: Line 1,993:  
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_journal and 'mla' == mode then
  −
is_journal = false; -- mla always uses p & pp
  −
end
  −
   
if is_set (page) then
 
if is_set (page) then
 
if is_journal then
 
if is_journal then
Line 1,847: Line 2,019:       −
--[=[-------------------------< 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 >----------------------------------------------
 +
 
 +
returns one of the in-source locators: page, pages, or at.
   −
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the  
+
If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain text
 +
for use in COinS.  This COinS thing is done because here we convert an interwiki link to and external link and
 +
add an icon span around that; get_coins_pages() doesn't know about the span.  TODO: should it? 
 +
 
 +
TODO: add support for sheet and sheets?; streamline;
 +
 
 +
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned
 +
to a new name)?
 +
 
 +
]]
 +
 
 +
local function insource_loc_get (page, pages, at)
 +
local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
 +
 
 +
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.
 +
 
 +
ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label
 +
if ws_url then
 +
page = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
 +
coins_pages = ws_label;
 +
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.
 +
 
 +
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label
 +
if ws_url then
 +
pages = external_link (ws_url, ws_label .. '&nbsp;', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this?
 +
pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
 +
coins_pages = ws_label;
 +
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
 +
 +
return page, pages, at, coins_pages;
 +
end
 +
 
 +
 
 +
 
 +
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
 +
 
 +
Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the  
 
save snapshot url or to calendar pages.  When the archive url is 'https://web.archive.org/save/' (or http://...)
 
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
 
archive.org saves a snapshot of the target page in the url.  That is something that Wikipedia should not allow
Line 1,884: Line 2,113:  
local path, timestamp, flag; -- portions of the archive.or url
 
local path, timestamp, flag; -- portions of the archive.or url
 
 
if not url:match('//web%.archive%.org/') then
+
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
 
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
 
end
 
end
Line 1,891: Line 2,120:  
err_msg = 'save command';
 
err_msg = 'save command';
 
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL
 
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
 
else
 
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
 
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation
Line 1,919: Line 2,150:       −
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------
+
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
   −
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal
+
This is the main function doing the majority of the citation formatting.
sign, compare the alphanumeric string to the list of cs1|2 parameters.  If found, then the string is possibly a
  −
parameter that is missing its pipe:
  −
{{cite ... |title=Title access-date=2016-03-17}}
  −
 
  −
cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc.  To prevent false positives xml/html
  −
tags are removed before the search.
  −
 
  −
If a missing pipe is detected, this function adds the missing pipe maintenance category.
      
]]
 
]]
   −
local function missing_pipe_check (value)
+
local function citation0( config, args)
local capture;
  −
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
  −
 
  −
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
  −
if capture and validate (capture) then -- if the capture is a valid parameter name
  −
add_maint_cat ('missing_pipe');
  −
end
  −
end
  −
 
  −
 
  −
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
  −
 
  −
This is the main function doing the majority of the citation formatting.
  −
 
  −
]]
  −
 
  −
local function citation0( config, args)
   
--[[  
 
--[[  
 
Load Input Parameters
 
Load Input Parameters
Line 1,961: Line 2,167:  
-- 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. If |mode= is empty or omitted, use CitationClass to set these values
+
-- set default parameter values defined by |mode= parameter.
 
local Mode = A['Mode'];
 
local Mode = A['Mode'];
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode'], config.CitationClass) then
+
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
 
Mode = '';
 
Mode = '';
 
end
 
end
Line 1,991: Line 2,197:  
end
 
end
   −
local Coauthors = A['Coauthors'];
   
local Others = A['Others'];
 
local Others = A['Others'];
   Line 2,014: Line 2,219:  
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 Interviewers = A['Interviewers']
+
local interviewers_list = {};
+
local Interviewers; -- used later
 +
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
 +
 
 
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 2,095: Line 2,302:  
local Pages;
 
local Pages;
 
local At;
 
local At;
-- previously conference books did not support volume
+
 
-- if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then
   
if in_array (config.CitationClass, cfg.templates_using_volume) then
 
if in_array (config.CitationClass, cfg.templates_using_volume) then
 
Volume = A['Volume'];
 
Volume = A['Volume'];
Line 2,102: Line 2,308:  
-- conference & map books do not support issue
 
-- conference & map books do not support issue
 
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then
 
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'];
+
Issue = hyphen_to_dash (A['Issue']);
 
end
 
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 2,120: Line 2,326:  
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
 
SubscriptionRequired=nil;
 
SubscriptionRequired=nil;
 
end
 
end
 +
 
local UrlAccess = A['UrlAccess'];
 
local UrlAccess = A['UrlAccess'];
 
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
 
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then
Line 2,142: Line 2,350:  
end
 
end
    +
local ChapterUrlAccess = A['ChapterUrlAccess'];
 +
if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', 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', {'chapter-url'}, true ) } );
 +
end
    
local Via = A['Via'];
 
local Via = A['Via'];
Line 2,177: Line 2,393:  
LastAuthorAmp = nil; -- set to empty string
 
LastAuthorAmp = nil; -- set to empty string
 
end
 
end
if 'mla' == Mode then
+
 
LastAuthorAmp = 'yes'; -- replaces last author/editor separator with ' and ' text
  −
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 2,185: Line 2,399:  
end
 
end
   −
--these deprecated parameters 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 2,207: Line 2,416:  
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 2,220: Line 2,429:  
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 2,230: Line 2,443:  
end
 
end
   −
if is_set(Page) then
+
-- both |publication-place= and |place= (|location=) allowed if different
if is_set(Pages) or is_set(At) then
  −
Pages = ''; -- unset the others
  −
At = '';
  −
end
  −
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
  −
elseif is_set(Pages) then
  −
if is_set(At) then
  −
At = ''; -- unset
  −
end
  −
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.
  −
end
  −
 
  −
-- both |publication-place= and |place= (|location=) allowed if different
   
if not is_set(PublicationPlace) and is_set(Place) then
 
if not is_set(PublicationPlace) and is_set(Place) then
 
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
 
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
Line 2,250: Line 2,450:  
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
+
|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'];
Line 2,274: Line 2,474:  
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 2,293: Line 2,495:  
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'
Line 2,304: Line 2,506:  
end
 
end
   −
-- special case for cite interview
+
-- special case for cite mailing list
-- TODO: make cite interview not need any special cases
  −
--[[
  −
Program, Callsign, City deprecated, so avoid using /Configuration
  −
for reassignment, which would allow these parameters' use outside interview
  −
]]
  −
if (config.CitationClass == "interview") then
  −
if is_set(Program) then
  −
if not is_set(Periodical) then
  −
Periodical = Program;
  −
end
  −
end
  −
if is_set(Callsign) then
  −
if not is_set(PublisherName) then
  −
PublisherName = Callsign;
  −
end
  −
end
  −
if is_set(City) then
  −
if not is_set(PublicationPlace) then
  −
PublicationPlace = City;
  −
end
  −
end
  −
end
  −
 
  −
-- special case for cite mailing list
   
if (config.CitationClass == "mailinglist") then
 
if (config.CitationClass == "mailinglist") then
 
Periodical = A ['MailingList'];
 
Periodical = A ['MailingList'];
Line 2,335: Line 2,513:  
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 2,341: Line 2,519:  
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
 
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated
 
ChapterURL = URL;
 
ChapterURL = URL;
 +
ChapterUrlAccess = UrlAccess;
 
ChapterURLorigin = URLorigin;
 
ChapterURLorigin = URLorigin;
 
URLorigin = '';
 
URLorigin = '';
Line 2,355: Line 2,534:  
end
 
end
   −
-- cite map oddities
+
-- cite map oddities
 
local Cartography = "";
 
local Cartography = "";
 
local Scale = "";
 
local Scale = "";
Line 2,363: Line 2,542:  
Chapter = A['Map'];
 
Chapter = A['Map'];
 
ChapterURL = A['MapURL'];
 
ChapterURL = A['MapURL'];
 +
ChapterUrlAccess = UrlAccess;
 
TransChapter = A['TransMap'];
 
TransChapter = A['TransMap'];
 
ChapterURLorigin = A:ORIGIN('MapURL');
 
ChapterURLorigin = A:ORIGIN('MapURL');
Line 2,377: Line 2,557:  
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 2,415: Line 2,595:  
TransChapter = TransTitle;
 
TransChapter = TransTitle;
 
ChapterURL = URL;
 
ChapterURL = URL;
 +
ChapterUrlAccess = UrlAccess;
 
ChapterURLorigin = A:ORIGIN('URL');
 
ChapterURLorigin = A:ORIGIN('URL');
 
 
Line 2,422: Line 2,603:     
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 2,434: Line 2,615:  
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}}, 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'}) 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
+
if 'arxiv' == config.CitationClass then
end
+
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
+
end
if first_set ({AccessDate, At, Authors, 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'], -- TODO: find a better way to do this
+
if 'biorxiv' == config.CitationClass then
ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'],
+
Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string
ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then
+
end
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
+
if 'citeseerx' == config.CitationClass then
Authors = '';
+
Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string
PublisherName = ''; -- (if the article has been published, use cite journal, or other)
+
end
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", "interview", "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);
Line 2,481: Line 2,656:  
end
 
end
   −
-- legacy: 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 2,488: Line 2,665:  
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 2,521: Line 2,716:  
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
Line 2,543: Line 2,746:  
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 2,559: Line 2,762:  
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 2,615: Line 2,818:  
['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,
Line 2,624: Line 2,827:  
}, 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}}, and {{cite citeseerx}} 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'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed
Periodical = ''; -- periodical not allowed in 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
Line 2,652: Line 2,855:  
};
 
};
   −
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_authors_editors (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);
Line 2,670: Line 2,873:  
EditorCount = 2; -- spoof to display (eds.) annotation
 
EditorCount = 2; -- spoof to display (eds.) annotation
 
end
 
end
 +
end
 +
do -- now do interviewers
 +
control.maximum = #interviewers_list; -- number of interviewerss
 +
Interviewers = list_people(control, interviewers_list, false); -- et al not currently supported
 
end
 
end
 
do -- now do translators
 
do -- now do translators
Line 2,682: Line 2,889:  
control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal);
 
control.maximum , author_etal = get_display_authors_editors (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);
   Line 2,703: Line 2,905:  
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 2,716: Line 2,915:  
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'}) or
 
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
 
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then
 
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
 
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
Line 2,737: Line 2,936:  
DeadURL = DeadURL:lower(); -- used later when assembling archived text
 
DeadURL = DeadURL:lower(); -- used later when assembling archived text
 
if is_set( ArchiveURL ) then
 
if is_set( ArchiveURL ) then
if is_set (ChapterURL) then -- 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
 
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
Line 2,760: Line 2,960:  
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'}) 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) and not is_set (Encyclopedia)) then
 
local chap_param;
 
local chap_param;
Line 2,791: Line 2,991:  
end
 
end
   −
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter
+
Chapter = format_chapter_title (ScriptChapter, 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 2,804: Line 3,004:     
-- 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', 'interview'}) or
+
if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup:
 +
Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup
 +
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'}) or
 
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
 
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or
 
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
 
('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article
Line 2,832: Line 3,043:  
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, UrlAccess) .. TransTitle .. TransError .. Format;
Title = external_link( URL, Title, URLorigin, UrlAccess ) .. 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 2,897: Line 3,114:  
end
 
end
   −
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase, Mode);
+
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
    
At = is_set(At) and (sepc .. " " .. At) or "";
 
At = is_set(At) and (sepc .. " " .. At) or "";
Line 2,930: Line 3,147:  
 
 
if is_set (Translators) then
 
if is_set (Translators) then
if 'mla' == Mode then
+
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
Others = sepc .. ' Trans. ' .. Translators .. Others;
  −
else
  −
Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;
  −
end
   
end
 
end
 
if is_set (Interviewers) then
 
if is_set (Interviewers) then
Others = sepc .. ' ' .. wrap_msg ('interview', Interviewers, use_lowercase) .. Others;
+
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc);
 
end
 
end
 
 
Line 2,945: Line 3,158:  
add_maint_cat ('extra_text', 'edition');
 
add_maint_cat ('extra_text', 'edition');
 
end
 
end
if 'mla' == Mode then
+
Edition = " " .. wrap_msg ('edition', Edition);
Edition = '. ' .. Edition .. ' ed.';
  −
else
  −
Edition = " " .. wrap_msg ('edition', Edition);
  −
end
   
else
 
else
 
Edition = '';
 
Edition = '';
Line 2,955: Line 3,164:     
Series = is_set(Series) and (sepc .. " " .. Series) or "";
 
Series = is_set(Series) and (sepc .. " " .. Series) or "";
if 'mla' == Mode then -- not in brackets for mla
+
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; -- TODO: presentation
OrigYear = is_set(OrigYear) and (". " .. OrigYear) or "";
+
 
else
  −
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
  −
end
   
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
 
Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
   −
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase, Mode);
+
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase);
    
------------------------------------ totally unrelated data
 
------------------------------------ totally unrelated data
Line 2,969: Line 3,175:  
end
 
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 2,986: Line 3,192:     
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 'mla' == Mode then -- retrieved text not used in mla
+
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
AccessDate = ' ' .. AccessDate;
+
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
else
+
 
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case
  −
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
  −
end
   
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
 
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
 
end
 
end
Line 3,006: Line 3,209:     
if is_set(URL) then
 
if is_set(URL) then
URL = " " .. external_link( URL, nil, URLorigin, Access );
+
URL = " " .. external_link( URL, nil, URLorigin, UrlAccess );
 
end
 
end
   Line 3,107: Line 3,310:  
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
Line 3,128: Line 3,331:  
 
 
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?
if 'mla' == Mode then
+
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
tcommon = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
  −
else
  −
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,  
  −
Language, Edition, Publisher, Agency, Volume}, sepc );
  −
end
   
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
 
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
 
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
if 'mla' == Mode then
+
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Edition, Publisher, Agency}, sepc );
  −
else
  −
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
  −
end
  −
elseif 'mla' == Mode then
  −
tcommon = safe_join( {TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Publisher, Agency}, sepc );
   
else
 
else
 
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
 
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
Line 3,160: Line 3,352:  
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, Transcript, Language, Edition, Publisher}, sepc );
  −
elseif ('news' == config.CitationClass) and ('mla' == Mode) then -- special case for cite news in MLA mode
  −
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language, Edition, Agency}, sepc );
  −
  −
elseif ('web' == config.CitationClass) and ('mla' == Mode) then -- special case for cite web in MLA mode
  −
tcommon = safe_join( {Periodical, Format, TitleType, Series, Language,
  −
Edition, Publisher, Agency}, sepc );
      
else -- all other CS1 templates
 
else -- all other CS1 templates
Line 3,184: Line 3,369:     
if is_set(Date) then
 
if is_set(Date) then
if ('mla' == Mode) then
+
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
if in_array (config.CitationClass, {'book', 'news', 'web'}) then
  −
Date = ', ' .. Date; -- origyear follows title in mla
  −
elseif 'journal' == config.CitationClass then
  −
Date = ', (' .. Date .. ')';
  −
end
  −
elseif is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
   
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
 
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
 
else -- neither of authors and editors set
 
else -- neither of authors and editors set
Line 3,201: Line 3,380:  
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)) or ('mla' == Mode) then -- when date is set it's in parentheses; no Authors termination
   
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
 
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
 
end
 
end
Line 3,214: Line 3,386:  
local in_text = " ";
 
local in_text = " ";
 
local post_text = "";
 
local post_text = "";
if is_set(Chapter) and 0 == #c and 'mla' ~= Mode 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
elseif is_set(Chapter) and 'mla' == Mode then
+
in_text = in_text:lower() -- lowercase for cs2
if EditorCount <= 1 then
+
end
in_text = '. Ed. ';
  −
else
  −
in_text = '. Eds. ';
  −
end
   
else
 
else
 
if EditorCount <= 1 then
 
if EditorCount <= 1 then
Line 3,236: Line 3,404:  
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) and ('mla' ~= Mode)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)) or ('mla' == Mode) 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
if 'mla' == Mode then
+
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
text = safe_join( {Contributors, Chapter, tcommon, OrigYear, Authors, Place, Others, Editors, tcommon2, Date, pgtext, idcommon }, sepc );
  −
else
  −
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
  −
end
  −
elseif 'mla' == Mode then
  −
tcommon = tcommon .. Date; -- hack to avoid duplicate separators
  −
text = safe_join( {Authors, Chapter, Title, OrigYear, Others, Editors, Edition, Place, tcommon, pgtext, idcommon }, sepc );
   
else
 
else
 
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
 
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
Line 3,267: Line 3,428:  
end
 
end
 
end
 
end
if 'mla' == Mode then
+
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
  −
text = safe_join( {Editors, Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
  −
else
  −
text = safe_join( {Editors, Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
  −
end
  −
else
  −
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc );
  −
end
  −
elseif 'mla' == Mode then
  −
if in_array(config.CitationClass, {'journal', 'news', 'web'}) and is_set(Periodical) then
  −
text = safe_join( {Title, Place, tcommon, pgtext, Date, idcommon}, sepc );
  −
else
  −
text = safe_join( {Chapter, Title, Place, tcommon, Date, pgtext, idcommon}, sepc );
  −
end
   
else
 
else
 
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
 
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
Line 3,335: Line 3,482:  
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
Line 3,356: Line 3,505:  
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
 +
table.insert (maint, v); -- maint msg is the category name
 +
table.insert (maint, ' ('); -- open the link text
 +
table.insert (maint, make_wikilink (':Category:' .. v, 'link')); -- add the link
 +
table.insert (maint, ')'); -- and close it
 +
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table
 
end
 
end
text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now)
+
table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
 
end
 
end
 
 
Line 3,367: Line 3,521:  
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
 
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then
 
for _, v in ipairs( z.error_categories ) do
 
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
+
table.insert (render, make_wikilink ('Category:' .. v));
 
end
 
end
 
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
 
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
+
table.insert (render, make_wikilink ('Category:' .. v));
 
end
 
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
+
for _, v in ipairs( z.properties_cats ) do -- append properties categories
text = text .. '[[Category:' .. v ..']]';
+
table.insert (render, make_wikilink ('Category:' .. v));
 
end
 
end
 
end
 
end
+
 
return text
+
return table.concat (render);
 
end
 
end
   −
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
     −
This is used by templates such as {{cite book}} to create the actual citation text.
+
--[[--------------------------< V A L I D A T E >--------------------------------------------------------------
   −
]]
+
Looks for a parameter's name in one of several whitelists.
   −
function cs1.citation(frame)
+
Parameters in the whitelist can have three values:
Frame = frame; -- save a copy incase we need to display an error message in preview mode
+
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'}) 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 (value)
 +
local capture;
 +
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc
 +
 
 +
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes
 +
if capture and validate (capture) then -- if the capture is a valid parameter name
 +
add_maint_cat ('missing_pipe');
 +
end
 +
end
 +
 
 +
 
 +
--[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------
 +
 
 +
This is used by templates such as {{cite book}} to create the actual citation text.
 +
 
 +
]]
 +
 
 +
function cs1.citation(frame)
 +
Frame = frame; -- save a copy incase we need to display an error message in preview mode
 
local pframe = frame:getParent()
 
local pframe = frame:getParent()
local validation, utilities, identifiers, metadata;
+
local validation, utilities, identifiers, metadata, styles;
 
 
 
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
 
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
Line 3,398: Line 3,641:  
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 3,406: Line 3,650:  
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 3,417: Line 3,663:  
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 3,427: Line 3,674:  
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;
    
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;
Line 3,440: Line 3,688:  
COinS = metadata.COinS;
 
COinS = metadata.COinS;
   −
local args = {};
+
local args = {}; -- table where we store all of the template's arguments
local suggestions = {};
+
local suggestions = {}; -- table where we store suggestions if we need to loadData them
 
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 3,453: Line 3,701:  
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 3,460: Line 3,711:  
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 3,473: Line 3,724:  
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 3,482: Line 3,737:  
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 3,490: Line 3,746:  
end
 
end
 
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe?
 
missing_pipe_check (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 3,502: Line 3,758:  
end
 
end
 
end
 
end
return citation0( config, args)
+
return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})});
 
end
 
end
    
return cs1;
 
return cs1;
Bureaucrats, private-view, public-view, Administrators
97,692

edits

Navigation menu