Module:Citation/CS1: Difference between revisions

Line 153:

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;

end

Line 399:

Line 403:

local path;

local base_url;

if not is_set( label ) then

label = URL;

Line 415:

Line 419:

if path then -- if there is a path portion

path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values

URL=domain..path; -- and reassemble

URL = table.concat ({domain, path}); -- and reassemble

end

base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url

if is_set (access) then -- access level (subscription, registration, limited)

base_url = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon

label = safe_for_url (label); -- replace square brackets and newlines

base_url = table.concat ( -- assemble external link with access signal

{

'[', -- opening css and url markup

URL, -- the url

' ', -- the required space

label,

'', -- signal spacing css

cfg.presentation[access], -- the appropriate icon

'', -- close signal spacing span

']' -- close url markup and plain links span

});

else

base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" }); -- no signal markup

end

return table.concat({ base_url, error_str });

return table.concat ({base_url, error_str});

end

Line 549:

Line 541:

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

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?

script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script

Line 605:

Line 597:

return substitute( cfg.messages[key], str );

end

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

str is the value assigned to |chapter= (or aliases) or |title= or |title-link=

]]

local function wikisource_url_make (str)

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

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

Line 617:

Line 661:

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

chapter = ''; -- to be safe for concatenation

Line 628:

Line 678:

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 .. ' ', '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

Line 639:

Line 696:

end

if is_set (chapterurl) then

-- if is_set (chapterurl) then

chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- 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;

Line 689:

Line 746:

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)

('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

position = nil; -- unset

Line 757:

Line 815:

end,

});

end

--[[--------------------------< V A L I D A T E >--------------------------------------------------------------

Looks for a parameter's name in one of several whitelists.

Parameters in the whitelist can have three values:

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

if 'arxiv' == cite_class then -- basic parameters unique to these templates

state = whitelist.arxiv_basic_arguments[name];

end

if 'biorxiv' == cite_class then

state = whitelist.biorxiv_basic_arguments[name];

end

if 'citeseerx' == cite_class then

state = whitelist.citeseerx_basic_arguments[name];

end

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#)

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#

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

Line 877:

Line 864:

--[[--------------------------< 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 )

if not is_set(str) ~~or str:match( "[%[%]{}<>]" ) ~= nil~~ then

if not is_set (str) then

return str;

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;', {['–'] = '–', ['—'] = '—'}); -- replace — and – 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

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

Line 896:

Line 920:

local function safe_join( tbl, duplicate_char )

local f = {}; -- create a function table appropriate to type of 'dupicate character'

--[[

if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions

Note: we use string functions here, rather than ustring functions.

f.gsub=string.gsub

f.match=string.match

This has considerably faster performance and should work correctly as

f.sub=string.sub

long as the duplicate_char is strict ASCII. The strings

else -- for multi-byte characters use the ustring library functions

in tbl may be ASCII or UTF8.

f.gsub=mw.ustring.gsub

]]

f.match=mw.ustring.match

f.sub=mw.ustring.sub

end

local str = ''; -- the output string

local comp = ''; -- what does 'comp' mean?

Line 920:

Line 947:

end

-- 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?

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?

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

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?

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

end

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;

elseif ~~str:~~sub(-3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link

elseif f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link

trim = true;

elseif ~~str:~~sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link

elseif f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link

trim = true;

elseif ~~str:~~sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.

elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title.

trim = true;

end

elseif end_chr == " " then -- if last char of output string is a space

if ~~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

Line 955:

Line 982:

if value ~= comp then -- value does not equal comp when value contains html markup

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

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

Line 967:

Line 994:

end

return str;

end

Line 1,105:

Line 1,132:

if 'vanc' == format then -- Vancouver-like author/editor name styling?

sep = ','; -- name-list separator between authors is a comma

sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between authors is a comma

namesep = ' '; -- last/first separator is a space

namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space

else

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

Line 1,379:

Line 1,406:

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

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

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.

Line 1,392:

Line 1,425:

local function get_iso639_code (lang, this_wiki_code)

if ~~'bangla' ==~~ lang:lower() then -- ~~special~~ ~~case~~ ~~related~~ to ~~Wikimedia~~ ~~remap~~ of ~~code~~ '~~bn'~~ at ~~mw:Extension:CLDR~~

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

return 'Bengali', 'bn'; -- make sure rendered version is properly capitalized

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

-- ('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() ~~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

~~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

~~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

Line 1,442:

Line 1,480:

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

~~end~~

else

if ~~2 ==~~ lang:~~len() or~~ ~~3 == lang:len~~() then -- if ~~two-or~~ ~~three-character~~ code

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?

name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code

end

if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code

name = mw.language.fetchLanguageName (lang:lower(), this_wiki_code); -- get language name if |language= is a proper code

end

if is_set (name) then -- if |language= specified a valid code

code = lang:lower(); -- save it

Line 1,457:

Line 1,500:

if is_set (code) then -- only 2- or 3-character codes

if ~~'bn' =~~= code ~~then~~ name ~~= 'Bengali' end~~; -- override wikimedia when ~~code~~ is ~~'bn'~~

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 2 == code:len() then -- and is a two-character code

add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it

else -- or is a recognized language (but has a three-character code)

add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template

end

Line 1,475:

Line 1,519:

code = #language_list -- reuse code as number of languages in the list

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

~~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

if this_wiki_name == name then

Line 1,493:

Line 1,537:

Set style settings for CS1 citation templates. Returns separator and postscript settings

At en.wiki, for cs1:

ps gets: '.'

sep gets: '.'

]]

Line 1,498:

Line 1,545:

local function set_cs1_style (ps)

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

return '.', ps; -- separator ~~is a full stop~~

return cfg.presentation['sep_cs1'], ps; -- element separator

end

Line 1,507:

Line 1,554:

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 1,512:

Line 1,562:

local function set_cs2_style (ps, ref)

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

if not is_set (ref) then -- if |ref= is not set

ref = "harv"; -- set default |ref=harv

end

return ',', ps, ref; -- separator ~~is a comma~~

return cfg.presentation['sep_cs2'], ps, ref; -- element separator

end

Line 1,897:

Line 1,947:

end

local vol = '';

local vol = ''; -- here for all cites except magazine

if is_set (volume) then

if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals

if (4 < mw.ustring.len(volume)) then

vol = substitute (cfg.~~messages~~['j-vol'], {sepc, volume});

vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- render in bold face

elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters

else

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

Line 1,940:

Line 1,993:

end

local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin);

local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);

if is_set (page) then

Line 1,964:

Line 2,017:

return '', '', '', ''; -- return empty strings

end

--[[------------------------------------------------------------------------

returns one of the in-source locators: page, pages, or at.

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 .. ' ', '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 .. ' ', '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 .. ' ', '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

return page, pages, at, coins_pages;

end

Line 2,036:

Line 2,146:

else

return url, date; -- preview mode so return archiveURL and ArchiveDate

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:

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

Line 2,135:

Line 2,220:

t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=

local interviewers_list = {};

local Interviewers = ~~A['Interviewers']~~

local Interviewers; -- used later

interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters

if is_set (Interviewers) then -- add a maint cat if the |interviewers= is used

add_maint_cat ('interviewers'); -- because use of this parameter is discouraged

else

interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters

end

local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs

Line 2,227:

Line 2,308:

-- 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

Issue = A['Issue'];

Issue = hyphen_to_dash (A['Issue']);

end

local Position = '';

if not in_array (config.CitationClass, cfg.templates_not_using_page) then

Page = A['Page'];

Pages = hyphen_to_dash( A['Pages'] );

Pages = hyphen_to_dash (A['Pages']);

At = A['At'];

end

Line 2,350:

Line 2,431:

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

select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category

local coins_pages;

Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At);

local NoPP = A['NoPP']

Line 2,357:

Line 2,442:

NoPP = nil; -- unset, used as a flag later

end

if is_set(Page) then

if is_set(Pages) or is_set(At) then

Pages = ''; -- unset the others

At = '';

end

extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.

elseif is_set(Pages) then

if is_set(At) then

At = ''; -- unset

end

extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp.

end

-- both |publication-place= and |place= (|location=) allowed if different

Line 2,385:

Line 2,457:

|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

Line 2,585:

Line 2,657:

-- 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

Date = Year; -- promote Year to Date

Line 2,591:

Line 2,665:

Date = PublicationDate; -- promote PublicationDate to Date

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

else

Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging

end

Line 2,605:

Line 2,684:

local error_message = '';

-- 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 = {

['access-date'] = {val=AccessDate, name=A:ORIGIN ('AccessDate')},

['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year};

['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);

-- 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;

Line 2,636:

Line 2,728:

-- 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) then

-- if date_name_xlate (date_parameters_list, false) then

-- modified = true;

-- end

if modified then -- if the date_parameters_list values were modified

AccessDate = date_parameters_list['access-date']; -- overwrite date holding parameters with modified values

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

else

Line 2,725:

Line 2,818:

['Volume'] = Volume,

['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,

['PublisherName'] = PublisherName,

Line 2,843:

Line 2,936:

DeadURL = DeadURL:lower(); -- used later when assembling archived text

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

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

ChapterURL = ArchiveURL -- swap-in the archive's url

ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages

ChapterFormat = ArchiveFormat or ''; -- swap in archive's format

ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls

end

elseif is_set (URL) then

Line 2,910:

Line 3,004:

-- Format main title.

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 = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character

add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title

if is_set(TitleLink) and is_set(Title) then

Title = make_wikilink (TitleLink, Title);

end

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

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

Line 2,939:

Line 3,043:

end

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 ) .. TransTitle .. TransError .. Format;

URL = ''; -- unset these because no longer needed

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 .. ' ', '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

local ws_url, ws_label;

Title = Title .. TransTitle .. TransError;

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 .. ' ', '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

else

Line 3,025:

Line 3,147:

if is_set (Translators) then

Others = sepc .. ' ' .. wrap_msg ('translated', Translators, use_lowercase) .. Others;

Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);

end

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

Line 3,209:

Line 3,331:

if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then

if is_set(Others) then Others = Others .. sepc .. " " end

if is_set(Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here?

tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );

elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites

Line 3,370:

Line 3,492:

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

table.insert (render, ' ');

for i,v in ipairs( z.message_tail ) do

Line 3,383:

Line 3,505:

end

if ~~#z.maintenance_cats~~ ~= 0 then

if 0 ~= #z.maintenance_cats then

local maint_msgs = {}; -- here we collect all of the maint messages

table.insert (render, '');

for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories

local maint = {}; -- here we assemble a maintenence message

table.insert (render, v);

table.insert (~~render~~, ~~' ('~~);

table.insert (maint, v); -- maint msg is the category name

table.insert (~~render~~, ~~make_wikilink~~ ('~~:Category:'~~ .. v, 'link~~'));~~

table.insert (maint, ' ('); -- open the link text

table.insert (~~render~~, ') ');

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

table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save

table.insert (render, '');

end

Line 3,408:

Line 3,532:

return table.concat (render);

end

--[[--------------------------< V A L I D A T E >--------------------------------------------------------------

Looks for a parameter's name in one of several whitelists.

Parameters in the whitelist can have three values:

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:

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

Line 3,420:

Line 3,632:

Frame = frame; -- save a copy incase we need to display an error message in preview mode

local pframe = frame:getParent()

local validation, utilities, identifiers, metadata;

local validation, utilities, identifiers, metadata, styles;

if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?

Line 3,429:

Line 3,641:

identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');

metadata = require ('Module:Citation/CS1/COinS/sandbox');

styles = 'Module:Citation/CS1/sandbox/styles.css';

else -- otherwise

Line 3,437:

Line 3,650:

identifiers = require ('Module:Citation/CS1/Identifiers');

metadata = require ('Module:Citation/CS1/COinS');

styles = 'Module:Citation/CS1/styles.css';

end

Line 3,486:

Line 3,701:

for k, v in pairs( pframe.args ) do

if v ~= '' 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 = "";

Line 3,494:

Line 3,712:

end

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

if nil == suggestions.suggestions then -- if this table is nil then we need to load it

Line 3,506:

Line 3,724:

capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match

if capture then -- if the pattern matches

param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator)

param = substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator)

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 error message

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

Line 3,524:

Line 3,746:

end

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;

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

Line 3,536:

Line 3,758:

end

return citation0( config, args)

return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})});

end