Module:Citation/CS1: திருத்தங்களுக்கு இடையிலான வேறுபாடு
உள்ளடக்கம் நீக்கப்பட்டது உள்ளடக்கம் சேர்க்கப்பட்டது
சி Changed protection level of Module:Citation/CS1: Remove cascading, doesn't work like as you would expect for Modules/Templates ([Edit=Allow only administrators] (indefinite) [Move=Allow only administrators] (indefinite)) |
Synch from sandbox; |
||
வரிசை 1:
local z = {
error_categories = {}; -- for categorizing citations that contain errors
error_ids = {};
message_tail = {};
maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work
properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance
}
வரி 41 ⟶ 44:
if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a
Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once
table.insert( z.message_tail, { seterror( 'deprecated_params', {}, true ) } ); -- add error message
end
வரி 69 ⟶ 71:
end
return str;
end
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped
in italic markup.
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right.
|script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon:
|script-title=ja:*** *** (where * represents a Japanese character)
Spaces between the two-character code and the colon and the colon and the first script character are allowed:
|script-title=ja : *** ***
|script-title=ja: *** ***
|script-title=ja :*** ***
Spaces preceding the prefix are allowed: |script-title = ja:*** ***
The prefix is checked for validity. If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute
is not added. At this time there is no error message for this condition.
At this writing, only |script-title= is supported. It is anticipated that additional parameters will be created to use this function.
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script;
]]
function format_script_value (script_value)
local lang=''; -- initialize to empty string
local name;
if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script
if not is_set (lang) then
return ''; -- script_value was just the prefix so return empty string
end
-- 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
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
if inArray (lang, {'ar', 'ja', 'ko', 'he', 'zh'}) then -- is prefix one of these language codes?
table.insert( z.properties_cats, 'CS1 uses ' .. name .. '-language script ('..lang..')'); -- categorize in language-specific categories
else
table.insert( z.properties_cats, 'CS1 uses foreign language script'); -- use this category as a catchall until language-specific category is available
end
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
else
lang = ''; -- invalid so set lang to empty string
end
end
script_value = '<bdi' .. lang .. '>' .. script_value .. '</bdi>'; -- isolate incase script is rlt
return script_value;
end
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
wrapped in <bdi> tags.
]]
function script_concatenate (title, script)
if is_set (script) then
script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error
if is_set (script) then
title = title .. ' ' .. script; -- concatenate title and script title
end
end
return title;
end
வரி 246 ⟶ 316:
-- Formats a link to Amazon
function amazon(id, domain)
if checkisbn( id ) then -- see if asin value is a 10-digit isbn
table.insert( z.maintenance_cats, "CS1 maint: ASIN uses ISBN"); -- add to maint category so a bot or awb script can replace |asin= with |isbn=
end
if not is_set(domain) then
domain = "com";
elseif inArray (domain,
domain = "co." .. domain;
elseif inArray (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
domain = "com." .. domain;
end
local handler = cfg.id_handlers['ASIN'];
வரி 347 ⟶ 422:
length = 8 then all digits
length = 9 then lccn[1] is lower case alpha
length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits
length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits
length = 12 then lccn[1] and lccn[2] are both lower case alpha
]]
வரி 366 ⟶ 441:
end
elseif 9 == len then -- LCCN should be adddddddd
if nil == id:match("%
err_cat = ' ' .. seterror( 'bad_lccn' ); -- set an error message
end
elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
if nil == id:match("^%
err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message
end
end
elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd
if not (id:match("^%
err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message
end
elseif 12 == len then -- LCCN should be aadddddddddd
if not id:match("^%
err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message
end
வரி 510 ⟶ 585:
-- Formats an OpenLibrary link, and checks for associated errors.
function openlibrary(id)
local code = id:
local handler = cfg.id_handlers['OL'];
if ( code == "A" ) then
return externallinkid({link=handler.link, label=handler.label,
வரி 618 ⟶ 694:
function cleanisbn( isbn_str )
return isbn_str:gsub( "[^-0-9X]", "" );
end
--[[
Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata
This function strips common patterns of apostrophe markup. We presume that editors who have taken the time to
markup a title have, as a result, provided valid markup.
]]
function strip_apostrophe_markup (argument)
local pattern, c1, c2;
if not is_set (argument) then return argument; end
while true do -- look for and remove all 5-apostrophe (bold and italic) markup
if argument:match ("%'%'%'%'%'") then -- is there an instance of bold-italic?
if argument:match ("%'%'%'%'%'.*%'%'%'%'%'") then -- 5, 5
pattern, c1 = argument:match ("(%'%'%'%'%'(.*)%'%'%'%'%')");
c2 = ""; -- set to empty string so we do only one replacement at end
elseif argument:match ("%'%'%'%'%'.*%'%'%'.*%'%'") then -- bold italic followed by italic (5, 3, 2)
pattern, c1, c2 = argument:match ("(%'%'%'%'%'(.*)%'%'%'(.*)%'%')");
elseif argument:match ("%'%'%'%'%'.*%'%'.*%'%'%'") then -- bold italic followed by bold (5, 2, 3)
pattern, c1, c2 = argument:match ("(%'%'%'%'%'(.*)%'%'(.*)%'%'%')");
elseif argument:match ("%'%'%'.*%'%'.*%'%'%'%'%'") then -- bold italic followed by italic (3, 2, 5)
pattern, c1, c2 = argument:match ("(%'%'%'(.*)%'%'(.*)%'%'%'%'%')");
elseif argument:match ("%'%'.*%'%'%'.*%'%'%'%'%'") then -- italic followed by bold (2, 3, 5)
pattern, c1, c2 = argument:match ("(%'%'(.*)%'%'%'(.*)%'%'%'%'%')");
end
argument=argument:gsub(pattern, c1..c2); -- remove the markup
else
break; -- none or no more 5-apostrophe matches
end
end
while true do -- look for and remove all 3-apostrophe (bold) markup
if argument:match ("%'%'%'.*%'%'%'") then -- is there an instance of bold?
pattern, c1 = argument:match ("(%'%'%'(.*)%'%'%')")
argument=argument:gsub(pattern, c1); -- remove the markup
else
break; -- none or no more 3 matches
end
end
while true do -- look for and remove all 2-apostrophe (italic) markup
if argument:match ("%'%'.*%'%'") then -- is there an instance of italic?
pattern, c1 = argument:match ("(%'%'(.*)%'%')")
argument=argument:gsub(pattern, c1); -- remove the markup
else
break; -- none or no more 2 matches
end
end
return argument; -- done
end
--[[--------------------------< M A K E _ C O I N S _ T I T L E >----------------------------------------------
Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
of %27%27...
]]
function make_coins_title (title, script)
if is_set (title) then
title = strip_apostrophe_markup (title); -- strip any apostrophe markup
else
title=''; -- if not set, make sure title is an empty string
end
if is_set (script) then
script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string)
script = strip_apostrophe_markup (script); -- strip any apostrophe markup
else
script=''; -- if not set, make sure script is an empty string
end
if is_set (title) and is_set (script) then
script = ' ' .. script; -- add a space before we concatenate
end
return title .. script; -- return the concatenation
end
-- Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
function get_coins_pages (pages)
local pattern;
if not is_set (pages) then return pages; end -- if no page numbers then we're done
வரி 851 ⟶ 1,000:
one = one .. namesep .. first
end
if is_set(person.link)
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
if is_set(person.link) and nil ~= person.link:find("//") then one = one .. " " .. seterror( 'bad_authorlink' ) end -- check for url in author link;
end
வரி 895 ⟶ 1,047:
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
]]
function extractnames(args, list_name)
local names = {}; -- table of names
local last; -- individual name components
local first;
local link;
local mask;
local i = 1; -- loop counter/indexer
local n = 1; -- output table indexer
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors)
வரி 927 ⟶ 1,060:
while true do
first = selectone( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i );
if first and not last then -- if there is a firstn without a matching lastn
table.insert( z.message_tail, { seterror( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
count = count + 1; -- number of times we haven't found last and first
if 2 == count then -- two missing names and we give up
break; -- normal exit or there is a two-name hole in the list; can't tell which
end
else -- we have last with or without a first
names[n] = {last = last, first = first, link = link, mask = mask}; -- add this name to our names list
n = n + 1; -- point to next location in the names table
if 1 == count then -- if the previous name was missing
table.insert( z.message_tail, { seterror( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message
வரி 949 ⟶ 1,080:
count = 0; -- reset the counter, we're looking for two consecutive missing names
end
i = i + 1; --
end
return names; -- all done, return our list of names
end
-- Populates ID table from arguments using configuration settings
வரி 1,159 ⟶ 1,287:
end
--[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------
Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian where
ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia
uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along
with the code. When there is no match, we return the original language name string.
mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included
in the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan Aramaic, that name will be
found with the associated code 'sam', not an ISO639-1 code. When names are found and the associated code is not two characters, this function
returns only the Wikimedia language name.
Adapted from code taken from Module:Check ISO 639-1.
]]
function get_iso639_code (lang)
if 'Norwegian' == lang then
return lang, 'no'; -- special case related to Wikimedia remap of code 'no' at Extension:CLDR
end
local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa)
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons
for code, name in pairs(languages) do -- scan the list to see if we can find our language
if langlc == mw.ustring.lower(name) then
if 2 ~= code:len() then -- ISO639-1 codes only
return name; -- so return the name but not the code
end
return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
end
end
return lang; -- not valid language; return language in original case and nil for ISO639-1 code
end
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
Get language name from ISO639-1 code value provided. If a code is valid use the returned name; if not, then use the value that was provided with the language parameter.
There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and
Norwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appears
that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links.
Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and
return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them.
See Help talk:Citation Style_1#An ISO 639-1 language name test
When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
the page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way.
TODO: Error message when language or language code is not ISO639-1?
]]
function language_parameter (lang, namespace)
local code; -- the ISO639-1 two character code
local name; -- the language name
local test='';
if 0 == namespace and (('en' == lang:lower()) or ('english' == lang:lower())) then
table.insert (z.maintenance_cats, 'CS1 maint: English language specified'); -- add maintenance category if |language=English or |language=en in article space
end
if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code
end
if is_set (name) then -- if Language specified a valid ISO639-1 code
code = lang:lower(); -- save it
else
name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
end
if is_set (code) then
if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no'
if 0 == namespace and 'en' ~= code then -- is this page main / article space and English not the language?
table.insert( z.properties_cats, 'CS1 ' .. name .. '-language sources (' .. code .. ')'); -- in main space and not English: categorize
end
end
return (" " .. wrap( 'language', name)); -- wrap with '(in ...)'
end
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------
This is the main function doing the majority of the citation
formatting.
வரி 1,193 ⟶ 1,409:
------------------------------------------------- Get title data
local Title = A['Title'];
local ScriptTitle = A['ScriptTitle'];
local BookTitle = A['BookTitle'];
local Conference = A['Conference'];
வரி 1,291 ⟶ 1,508:
--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
no_tracking_cats = "true"; -- set no_tracking_cats
end
end
வரி 1,500 ⟶ 1,714:
-- COinS metadata (see <http://ocoins.info/>) for
-- automated parsing of citation information.
-- this is the function call to COinS()
local OCinSoutput = COinS{
['Periodical'] = Periodical,
['Chapter'] = strip_apostrophe_markup (Chapter), -- Chapter stripped of bold / italic wikimarkup
['Title'] = make_coins_title (Title, ScriptTitle), -- strip_apostrophe_markup (Title), -- Title stripped of bold / italic wikimarkup
['PublicationPlace'] = PublicationPlace,
['Date'] = first_set(COinS_date, Date), -- COinS_date has correctly formatted date if Date is valid; any reason to keep Date here? Should we be including invalid dates in metadata?
வரி 1,517 ⟶ 1,732:
['RawPage'] = this_page.prefixedText,
};
--[[Why is this here? Why are we mapping Title to Chapter when Periodical is set?
if is_set(Periodical) and not is_set(Chapter) and is_set(Title) then
Chapter = Title;
வரி 1,526 ⟶ 1,741:
TransTitle = '';
end
]]
--[[ Hide unfinished cite newsgroup code so that long delayed update can take place
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername and ID
வரி 1,555 ⟶ 1,771:
format = A["AuthorFormat"],
maximum = Maximum,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via authorlinkn
};
வரி 1,587 ⟶ 1,804:
format = A['EditorFormat'],
maximum = Maximum,
lastauthoramp = LastAuthorAmp,
page_name = this_page.text -- get current page name so that we don't wikilink to it via authorlinkn
};
வரி 1,636 ⟶ 1,854:
-- Test if citation has no title
if
not is_set(Periodical) and
not is_set(Conference) and
not is_set(TransTitle) and
not is_set(
table.insert( z.message_tail, { seterror( 'citation_missing_title', {}, true ) } );
end
வரி 1,660 ⟶ 1,877:
Chapter = "[[" .. ChapterLink .. "|" .. Chapter .. "]]";
end
Chapter = kern_quotes (Chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
TransChapter = wrap( 'trans-quoted-title', TransChapter );
local TransError = ""
if is_set(TransChapter) then
வரி 1,710 ⟶ 1,923:
Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
end
if inArray(config.CitationClass, {"web","news","journal","pressrelease","conference","podcast"}) then
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
Title = wrap( 'quoted-title', Title );
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = wrap( 'trans-quoted-title', TransTitle );
Chapter = ''; -- chapter not allowed
else
Title = wrap( 'italic-title', Title );
Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped
TransTitle = wrap( 'trans-italic-title', TransTitle );
end
TransError = "";
if is_set(TransTitle) then
if
TransTitle = " " .. TransTitle;
else
TransError = " " .. seterror( 'trans_missing_title' );
end
end
வரி 1,828 ⟶ 2,037:
end
if is_set (Language) then
Language = language_parameter (Language, this_page.namespace); -- format, categories (article namespace only), name from ISO639-1, etc
else
Language=""; -- language not specified so make sure this is an empty string;
end
வரி 2,207 ⟶ 2,401:
if inArray(no_tracking_cats, {"", "no", "false", "n"}) then
for _, v in ipairs( z.error_categories ) do
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
for _, v in ipairs( z.properties_cats ) do -- append maintenance categories
text = text .. '[[Category:' .. v ..']]';
end
| |||