local cs1 ={};

]]

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

add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink;

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 make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS

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

delare variables here that have page-wide scope that are not brought in from other modules; thatare created here

and used here

]]

local added_deprecated_cat; -- boolean flag so that the category is added only once

local added_prop_cats = {}; -- list of property categories that have been added to z.properties_cats

local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category

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

Locates and returns the first set value in a table of values where the order established in the table,

left-to-right (or top-to-bottom), is the order in which the values are evaluated. Returns nil if none are set.

This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs. With the pairs

version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate

the for-loop before it reached the actual end of the list.

]]

local function first_set (list, count)

local i = 1;

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

if is_set( list[i] ) then

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

end

i = i + 1; -- point to next

end

end

Adds a category to z.properties_cats using names from the configuration file with additional text if any.

foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages

may be categorized but multiples of the same language are not categorized.

added_prop_cats is a table declared in page scope variables above

]]

local function add_prop_cat (key, arguments)

if not added_prop_cats [key] then

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

end

end

Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.

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

added_vanc_errs is a boolean declared in page scope variables above

]]

local function add_vanc_error (source)

if not added_vanc_errs then

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

table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } );

end

end

does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it

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

   letter and followed by any combination of letters, digits, plus   ("+"), period ("."), or hyphen ("-").

returns true if it does, else false

]]

local function is_scheme (scheme)

return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern

end

Does this thing that purports to be a domain name seem to be a valid domain name?

Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5

BNF defined here: https://tools.ietf.org/html/rfc4234

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

list of tlds: https://www.iana.org/domains/root/db

rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between

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

Also allowed are IPv4 addresses. IPv6 not supported

domain is expected to be stripped of any path so that the last character in the last character of the tld. tld

is two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be stripped

here. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal.

There are several tests:

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

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

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

i and q SL domains in the .net TLD

single-letter SL domains in the ccTLDs (where the ccTLD is two letters)

two-character SL domains in gTLDs (where the gTLD is two or more letters)

three-plus-character SL domains in gTLDs (where the gTLD is two or more letters)

IPv4 dot-decimal address format; TLD not allowed

returns true if domain appears to be a proper name and tld or IPv4 address, else false

]=]

local function is_domain_name (domain)

if not domain then

return false; -- if not set, abandon

end

domain = domain:gsub ('^//', ); -- strip '//' from domain name if present; done here so we only have to do it once

if not domain:match ('^[%a%d]') then -- first character must be letter or digit

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

-- Do most common case first

if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld

return true;

elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix

return true;

elseif domain:match ('%f[%a%d][%a%d]%.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;

elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10)

return true;

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

return true;

elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars)

return true;

elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld

return true;

elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address

return true;

else

return false;

end

end

returns true if the scheme and domain parts of a url appear to be a valid url; else false.

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

are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external

wikilinks.

]]

local function is_url (scheme, domain)

if is_set (scheme) then -- if scheme is set check it and domain

return is_scheme (scheme) and is_domain_name (domain);

else

return is_domain_name (domain); -- scheme not set when url is protocol relative

end

end

Split a url into a scheme, authority indicator, and domain.

First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#).

If protocol relative url, return nil scheme and domain else return nil for both scheme and domain.

When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one

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

Strip off any port and path;

]]

local function split_url (url_str)

local scheme, authority, domain;

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

if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url

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

authority = authority:gsub ('//', , 1); -- replace place 1 pair of '/' with nothing;

if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then

return scheme; -- return scheme only making domain nil which will cause an error message

end

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

end

return scheme, domain;

end

checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls

Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:

# < > | { } _

except the underscore which is used as a space in wiki urls and # which is used for section links

returns false when the value contains any of these characters.

When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the

]]

local function link_param_ok (value)

local scheme, domain;

if value:find ('[<>%[%]|{}]') then -- if any prohibited characters

return false;

end

scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url;

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

end

Use link_param_ok() to validate |-link= value and its matching |