Module:Citation/CS1: Difference between revisions

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

local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration

local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist

]]

local Frame; -- holds the module's frame table

local i = 1;

while i <= count do -- loop through all items in list

return list[i]; -- return the first set list member

end

i = i + 1; -- point to next

end

end

To prevent duplication, added_vanc_errs is nil until an error message is emitted.

]]

if not added_vanc_errs then

added_vanc_errs = true; -- note that we've added this category

end

end

--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------

is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:

Scheme names consist of a sequence of characters beginning with a

Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;

see also [[Single-letter second-level domain]]

the first and last characters the name may use letters, digits, and the hyphen.

Also allowed are IPv4 addresses. IPv6 not supported

There are several tests:

the first character of the whole domain name including subdomains must be a letter or a digit

single-letter/digit second-level domains in the .org, .cash, and .today TLDs

q, x, and z SL domains in the .com TLD

IPv4 dot-decimal address format; TLD not allowed

]=]

end

return false;

end

'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld

'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix

'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10)

'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10)

'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address

}

for _, pattern in ipairs (patterns) do -- loop through the patterns list

if domain:match (pattern) then

end

end

--[[--------------------------< I S _ U R L >------------------------------------------------------------------

This function is the last step in the validation process.  This function is separate because there are cases that

local function is_url (scheme, domain)

return is_scheme (scheme) and is_domain_name (domain);

else

end

end

--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------

or more '/' characters immediately following the scheme's colon), make sure that there are only 2.

Strip off any port and path;

url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')

domain = url_str:match ('^//(%S*)')

elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name

scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions

end

domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present

--[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------

# < > [ ] | { } _

returns false when the value contains any of these characters.

]]

end

end

Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.

that condition exists

]]

local function link_title_ok (link, lorig, title, torig)

local orig;

if not link_param_ok (link) then -- check |<param>-link= markup

orig = lorig; -- identify the failing link parameter

elseif title:find ('%[%[') then -- check |title= for wikilink markup

orig = torig; -- identify the failing |title= parameter

end

end

end

end

Determines whether a URL string appears to be valid.

that work for standard and news: links, we validate newsgroup names here.  The specification for a newsgroup name

is at https://tools.ietf.org/html/rfc5536#section-3.1.4

local function check_url( url_str )

return false;

end

local scheme, domain;

if 'news:' == scheme then -- special case for newsgroups

end

end

Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first

and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]]

is possible as might be [[en://Hus]].

local scheme, domain;

scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));

scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));

scheme, domain = split_url (value:match ('(%a%S*:%S+)'));

scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain

else

end

end

local error_message = '';

for k, v in pairs (parameter_list) do -- for each parameter in the list

end

end

end

end

end

local function safe_for_url( str )

if str:match( "%[%[.-%]%]" ) ~= nil then  

end

local base_url;

label = URL;

else

error( cfg.messages["bare_url_no_origin"] );

end

if not check_url( URL ) then

end

if path then -- if there is a path portion

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

end

end

parameters in the citation.

]]

if not added_deprecated_cat then

added_deprecated_cat = true; -- note that we've added this category

end

end

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

mark contained in a |title= or |chapter= parameter's value.

"'Unkerned title with leading and trailing single quote marks'"

" 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example)

quote marks regardless of the need for kerning.  Unicode quote marks are not replaced in simple [[D]] wikilinks.

]=]

local function kern_quotes (str)

local wl_type, label, link;

if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks

if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks

elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks

elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks

end

else -- plain text or [[L|D]]; text in label variable

cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)

end

cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup)

end

if 2 == wl_type then

else

str = label;

--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------

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.

|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:

Spaces preceding the prefix are allowed: |script-title = ja:*** ***

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.

if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix

lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script

return ''; -- script_value was just the prefix so return empty string

end

-- if we get this far we have prefix and script

name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize

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

-- is prefix one of these language codes?

else

end

lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute

else

lang = ''; -- invalid so set lang to empty string

end

else

end

return script_value;

local function script_concatenate (title, script, script_param)

title = title .. ' ' .. script; -- concatenate title and script title

end

local function wrap_msg (key, str, lower)

return "";

end

local msg;

msg = cfg.messages[key]:lower(); -- set the message to lower case before  

else

end

end

--[[--------------------------< W I K I S O U R C E _ U R L _ M A K E >----------------------------------------

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

local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});

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

wikisource_prefix, -- prefix

str, -- article title

});

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

wikisource_prefix, -- prefix

str, -- article title

});

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

ws_label = D; -- get ws article name from display portion of interwiki link

wikisource_prefix, -- prefix

str, -- article title without namespace from link portion of wikilink

if ws_url then

ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of fragment marker

end

end

local periodical_error = '';

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

else

end

else -- here when trans-periodical without periodical or script-periodical

periodical = trans_periodical;

end

end

--[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------

parameter (chapter_url_source used for error messages).

local chapter_error = '';

if ws_url then

ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters

end

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

else

if false == no_quotes then

end

end

chapter = external_link (chapter_url, 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?

end

else -- here when trans_chapter without chapter or script-chapter

chapter = trans_chapter;

chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param>

end

end

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

first match.

Detects but ignores nowiki and math stripmarkers.  Also detects other named stripmarkers (gallery, math, pre, ref)

local dummy; -- end of matching string; not used but required to hold end position when a capture is returned

local capture; -- used by stripmarker detection to hold name of the stripmarker

local stripmarker, apostrophe;

return;

end

while cfg.invisible_chars[i] do

position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern

position = nil; -- unset position

end

if position then

if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)

stripmarker = true; -- set a flag

elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker

end

return; -- and done with this parameter

end

end

end

end

]]

local origin = {};

return setmetatable({

local dummy = self[k]; --force the variable to be loaded.

return origin[k];

if type( list ) == 'table' then

if origin[k] == nil then

origin[k] = ''; -- Empty string, not nil

-- Empty strings, not nil;

if v == nil then

v = '';

origin[k] = '';

local function nowrap_date (date)

if date:match("^%d%d%d%d%-%d%d%-%d%d$") then

elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then

cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");

end

local function set_titletype (cite_class, title_type)

if 'none' == cfg.keywords_xlate[title_type] then

title_type = ''; -- if |type=none then type parameter not displayed

local function hyphen_to_dash( str )

return str;

end

end

str = str:gsub ('&nbsp;', ' '); -- replace &nbsp; entity with generic keyboard space character

item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters

else

end

end

table.insert (out, item); -- add the (possibly modified) item to the output table

end

local function safe_join( tbl, duplicate_char )

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

end

str = value; -- assign value to it (first time through the loop)

elseif value ~= '' then

else

comp = value;

end

-- typically duplicate_char is sepc

--  Because individual string segments often (always?) begin with terminal punct for the

trim = false;

if end_chr == duplicate_char then -- if same as separator

str = f.sub(str, 1, -4) .. "''"; -- remove them and add back ''

trim = true; -- why? why do this and next differently from previous?

trim = true; -- same question

end

trim = true;

trim = true;

trim = true;

trim = true;

end

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

end

end

if trim then

local dup2 = duplicate_char;

if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it

else

value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character

--[[--------------------------< I S _ S U F F I X >------------------------------------------------------------

]]

local function is_suffix (suffix)

return true;

end

--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------

uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.

When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.

This original test:

if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then

to use an external editor to maintain this code.

end

end

if not is_suffix (suffix) then

add_vanc_error (cfg.err_msg_supl.suffix);

nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then

add_vanc_error (cfg.err_msg_supl['non-Latin char']);

end;

return true;

--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------

Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.

This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials.

]]

if not name then -- if not initials and a suffix

end

end

if 3 > i then

end

i = i+1; -- bump the counter

]]

local sep;

local namesep;

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

else

namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>

end

local sep_one = sep;

etal = true;

break;

else

end

else

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

end

end

end

end

end

end

end

end

end

end

end

table.insert (names, year); -- add the year at the end

local id = table.concat(names); -- concatenate names and year for CITEREF id

return "CITEREF" .. id; -- add the CITEREF portion

else

--[[--------------------------< N A M E _ H A S _ E T A L >----------------------------------------------------

the et al. is removed, a flag is set to true and the function returns the modified name and the flag.

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

local patterns = cfg.et_al_patterns; --get patterns from configuration

etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)

if not nocat then -- no categorization for |vauthors=

end

end

end

end

local function name_is_numeric (name, list_name)

if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters

end

end

--[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------

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 patterns = cfg.editor_markup_patterns; -- get patterns from configuration

for _, pattern in ipairs (patterns) do -- spin through patterns table and

if name:match (pattern) then

break;

end

--[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >----------------------------------------

returns nothing

local function name_has_mult_names (name, list_name)

end

end

local function name_checks (last, first, list_name)

name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)

name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation

end

end

name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation

name_is_numeric (first, list_name); -- check for names that are compsed of digits and punctuation

end

end

return last, first; -- done

local function extract_names(args, list_name)

local first;

local link;

local mask;

local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging

while true do

last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.

first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.

if first and not last then -- if there is a firstn without a matching lastn

elseif not first and not last then -- if both firstn and lastn aren't found, are we done?

count = count + 1; -- number of times we haven't found last and first

end

else -- we have last with or without a first

if first then

end

n = n + 1; -- point to next location in the names table

if 1 == count then -- if the previous name was missing

end

count = 0; -- reset the counter, we're looking for two consecutive missing names

end

end

end

local ietf_name;

return name, code; -- so return the name and the code

end

ietf_name = name; -- but keep looking for a 2- or 3-char code

end

end

return ietf_code and ietf_name or lang; -- associated name; return original language text else

end

local names_table = {}; -- table made from the value assigned to |language=

names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list