Latest revision |
Your text |
Line 1: |
Line 1: |
| | local z = { |
| | error_categories = {}; |
| | error_ids = {}; |
| | message_tail = {}; |
| | } |
|
| |
|
| require('Module:No globals');
| | -- Whether variable is set or not |
| | | function is_set( var ) |
| --[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
| | return not (var == nil or var == ''); |
| each of these counts against the Lua upvalue limit
| | end |
| ]]
| |
| | |
| local validation; -- functions in Module:Citation/CS1/Date_validation
| |
| | |
| local utilities; -- functions in Module:Citation/CS1/Utilities
| |
| local z ={}; -- table of tables in Module:Citation/CS1/Utilities
| |
| | |
| local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
| |
| local metadata; -- 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
| |
| | |
| --[[------------------< P A G E S C O P E V A R I A B L E S >---------------
| |
| declare variables here that have page-wide scope that are not brought in from
| |
| other modules; that are created here and used here
| |
| ]]
| |
| local added_deprecated_cat; -- Boolean flag so that the category is added only once
| |
| local added_discouraged_cat; -- Boolean flag so that the category is added only once
| |
| local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category
| |
| local Frame; -- holds the module's frame table
| |
| | |
| --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------
| |
| | |
| 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
| | -- First set variable or nil if none |
| version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate
| | function first_set(...) |
| the for-loop before it reached the actual end of the list.
| | local list = {...}; |
| | | for _, var in pairs(list) do |
| ]]
| | if is_set( var ) then |
| | | return var; |
| local function first_set (list, count)
| |
| local i = 1; | |
| while i <= count do -- loop through all items in list | |
| if utilities.is_set( list[i] ) then | |
| return list[i]; -- return the first set list member | |
| end | | end |
| i = i + 1; -- point to next
| |
| end | | end |
| end | | end |
|
| |
|
| | | -- Whether needle is in haystack |
| --[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
| | function inArray( needle, haystack ) |
| | | if needle == nil then |
| 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, position)
| |
| if added_vanc_errs then return end
| |
|
| |
| added_vanc_errs = true; -- note that we've added this category
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source, position}, true ) } );
| |
| end
| |
| | |
| | |
| --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------
| |
| | |
| 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
| |
| | |
| | |
| --[=[-------------------------< I S _ D O M A I N _ N A M E >--------------------------------------------------
| |
| | |
| 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
| |
| | |
| RFC 952 (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 in case 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, .cash, and .today 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 ('^[%w]') then -- first character must be letter or digit
| |
| return false; | | return false; |
| end | | end |
| | | for n,v in ipairs( haystack ) do |
| if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource
| | if v == needle then |
| return false;
| | return n; |
| end
| |
| | |
| local patterns = { -- patterns that look like URLs
| |
| '%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)
| |
| '%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars)
| |
| '%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD
| |
| '^%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 | |
| return true; -- if a match then we think that this thing that purports to be a URL is a URL | |
| end | | end |
| end | | end |
| | | return false; |
| for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
| |
| if domain:match ('%f[%w][%w]%.' .. d) then
| |
| return true
| |
| end
| |
| end
| |
| return false; -- no matches, we don't know what this thing is | |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< I S _ U R L >------------------------------------------------------------------ | | Categorize and emit an error message when the citation contains one or more deprecated parameters. Because deprecated parameters (currently |day=, |month=, |
| | | |coauthor=, and |coauthors=) aren't related to each other and because these parameters may be concatenated into the variables used by |date= and |author#= (and aliases) |
| returns true if the scheme and domain parts of a URL appear to be a valid URL; else false.
| | details of which parameter caused the error message are not provided. Only one error message is emitted regardless of the number of deprecated parameters in the citation. |
| | |
| 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.
| |
| | |
| ]] | | ]] |
| | | function deprecated_parameter() |
| local function is_url (scheme, domain)
| | if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a |
| if utilities.is_set (scheme) then -- if scheme is set check it and domain | | Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once |
| return is_scheme (scheme) and is_domain_name (domain); | | -- table.insert( z.message_tail, { seterror( 'deprecated_params', {error_message}, true ) } ); -- add error message |
| else | | table.insert( z.message_tail, { seterror( 'deprecated_params', {}, true ) } ); -- add error message |
| return is_domain_name (domain); -- scheme not set when URL is protocol-relative | |
| end | | end |
| end | | end |
|
| |
|
| | -- Populates numbered arguments in a message string using an argument table. |
| | function substitute( msg, args ) |
| | -- return args and tostring( mw.message.newRawMessage( msg, args ) ) or msg; |
| | return args and mw.message.newRawMessage( msg, args ):plain() or msg; |
| | end |
|
| |
|
| --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ | | --[[ |
| | | Apply kerning to open the space between the quote mark provided by the Module and a leading or trailing quote mark contained in a |title= or |chapter= parameter's value. |
| Split a URL into a scheme, authority indicator, and domain.
| | This function will positive kern either single or double quotes: |
| | | "'Unkerned title with leading and trailing single quote marks'" |
| First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#).
| | " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example) |
| | |
| 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. | |
| | |
| Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes
| |
| like news: that don't use authority indicator?
| |
| | |
| Strip off any port and path;
| |
| | |
| ]] | | ]] |
| | | function kern_quotes (str) |
| local function split_url (url_str)
| | local left='<span style="padding-left:0.2em;">%1</span>'; -- spacing to use when title contains leading single or double quote mark |
| local scheme, authority, domain; | | local right='<span style="padding-right:0.2em;">%1</span>'; -- spacing to use when title contains trailing single or double quote mark |
| | | |
| url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//')
| | if str:match ("^[\"\'][^\']") then |
| | | str = string.gsub( str, "^[\"\']", left, 1 ); -- replace (captured) leading single or double quote with left-side <span> |
| if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL | | end |
| domain = url_str:match ('^//(%S*)')
| | if str:match ("[^\'][\"\']$") then |
| elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
| | str = string.gsub( str, "[\"\']$", right, 1 ); -- replace (captured) trailing single or double quote with right-side <span> |
| scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions | |
| if utilities.is_set (authority) then
| |
| authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing;
| |
| if utilities.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
| |
| else
| |
| if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test?
| |
| return scheme; -- return scheme only making domain nil which will cause an error message
| |
| end
| |
| end
| |
| domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present | |
| end | | end |
|
| | return str; |
| return scheme, domain; | |
| end | | end |
|
| |
|
| | | -- Wraps a string using a message_list configuration taking one argument |
| --[[--------------------------< L I N K _ P A R A M _ O K >---------------------------------------------------
| | function wrap( key, str, lower ) |
| | | if not is_set( str ) then |
| checks the content of |title-link=, |series-link=, |author-link=, etc. for properly formatted content: no wikilinks, no URLs
| | return ""; |
| | | elseif inArray( key, { 'italic-title', 'trans-italic-title' } ) then |
| Link parameters are to hold the title of a Wikipedia article, so none of the WP:TITLESPECIALCHARACTERS are allowed:
| | str = safeforitalics( str ); |
| # < > [ ] | { } _
| |
| 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
| |
| |<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok).
| |
| | |
| ]]
| |
| | |
| local function link_param_ok (value)
| |
| local scheme, domain;
| |
| if value:find ('[<>%[%]|{}]') then -- if any prohibited characters | |
| return false; | |
| end | | end |
| | | if lower == true then |
| scheme, domain = split_url (value); -- get scheme or nil and domain or nil from URL; | | return substitute( cfg.messages[key]:lower(), {str} ); |
| return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL | | else |
| | return substitute( cfg.messages[key], {str} ); |
| | end |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< L I N K _ T I T L E _ O K >--------------------------------------------------- | | Argument wrapper. This function provides support for argument |
| | | mapping defined in the configuration file so that multiple names |
| Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value.
| | can be transparently aliased to single internal variable. |
| | |
| |<title>= may be wiki-linked but not when |<param>-link= has a value. This function emits an error message when
| |
| that condition exists | |
| | |
| check <link> for inter-language interwiki-link prefix. prefix must be a MediaWiki-recognized language
| |
| code and must begin with a colon.
| |
| | |
| ]] | | ]] |
| | | function argument_wrapper( args ) |
| local function link_title_ok (link, lorig, title, torig)
| | local origin = {}; |
| local orig; | | |
| if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value | | return setmetatable({ |
| if not link_param_ok (link) then -- check |<param>-link= markup | | ORIGIN = function( self, k ) |
| orig = lorig; -- identify the failing link parameter | | local dummy = self[k]; --force the variable to be loaded. |
| elseif title:find ('%[%[') then -- check |title= for wikilink markup
| | return origin[k]; |
| orig = torig; -- identify the failing |title= parameter
| | end |
| elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki
| | }, |
| local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix
| | { |
| | | __index = function ( tbl, k ) |
| if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon | | if origin[k] ~= nil then |
| orig = lorig; -- flag as error | | return nil; |
| | end |
| | |
| | local args, list, v = args, cfg.aliases[k]; |
| | |
| | if type( list ) == 'table' then |
| | v, origin[k] = selectone( args, list, 'redundant_parameters' ); |
| | if origin[k] == nil then |
| | origin[k] = ''; -- Empty string, not nil |
| | end |
| | elseif list ~= nil then |
| | v, origin[k] = args[list], list; |
| | else |
| | -- maybe let through instead of raising an error? |
| | -- v, origin[k] = args[k], k; |
| | error( cfg.messages['unknown_argument_map'] ); |
| | end |
| | |
| | -- Empty strings, not nil; |
| | if v == nil then |
| | v = cfg.defaults[k] or ''; |
| | origin[k] = ''; |
| end | | end |
| end
| | |
| end
| | tbl = rawset( tbl, k, v ); |
| | | return v; |
| if utilities.is_set (orig) then
| | end, |
| link = ''; -- unset
| | }); |
| table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)}); -- URL or wikilink in |title= with |title-link=;
| |
| end
| |
| | |
| return link; -- link if ok, empty string else
| |
| end | | end |
|
| |
|
| | --[[ |
| | Looks for a parameter's name in the whitelist. |
|
| |
|
| --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
| | Parameters in the whitelist can have three values: |
| | | true - active, supported parameters |
| Determines whether a URL string appears to be valid.
| | false - deprecated, supported parameters |
| | | nil - unsupported parameters |
| First we test for space characters. If any are found, return false. Then split the URL into scheme and domain
| |
| portions, or for protocol-relative (//example.com) URLs, just the domain. Use is_url() to validate the two
| |
| portions of the URL. If both are valid, or for protocol-relative if domain is valid, return true, else false.
| |
| | |
| Because it is different from a standard URL, and because this module used external_link() to make external links
| |
| 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
| |
| | |
| ]] | | ]] |
| | | function validate( name ) |
| local function check_url( url_str ) | | local name = tostring( name ); |
| if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL | | local state = whitelist.basic_arguments[ name ]; |
| return false; | | |
| | -- Normal arguments |
| | if true == state then return true; end -- valid actively supported parameter |
| | if false == state then |
| | deprecated_parameter (); -- parameter is deprecated but still supported |
| | return true; |
| end | | end |
| local scheme, domain;
| |
|
| |
| scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL;
| |
| | | |
| if 'news:' == scheme then -- special case for newsgroups | | -- Arguments with numbers in them |
| return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$');
| | 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 (); -- parameter is deprecated but still supported |
| | return true; |
| end | | end |
| | | |
| return is_url (scheme, domain); -- return true if value appears to be a valid URL | | return false; -- Not supported because not found or name is set to nil |
| end | | end |
|
| |
|
| | | -- Formats a comment for error trapping |
| --[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >----------------------------
| | function errorcomment( content, hidden ) |
| | | return wrap( hidden and 'hidden-error' or 'visible-error', content ); |
| Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first
| |
| non-space characters following the opening bracket appear to be a URL. The test will also find external wikilinks
| |
| that use protocol-relative URLs. Also finds bare URLs.
| |
| | |
| The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs. The tests that
| |
| find bracketed URLs are required because the parameters that call this test (currently |title=, |chapter=, |work=,
| |
| 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 function is_parameter_ext_wikilink (value)
| |
| local scheme, domain;
| |
| | |
| if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext. wikilink with scheme and domain: [xxxx://yyyyy.zzz] | |
| scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]'));
| |
| elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz]
| |
| scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]'));
| |
| elseif value:match ('%a%S*:%S+') then -- if bare URL with scheme; may have leading or trailing plain text
| |
| scheme, domain = split_url (value:match ('(%a%S*:%S+)'));
| |
| elseif value:match ('//%S+') then -- if protocol-relative bare URL: //yyyyy.zzz; may have leading or trailing plain text
| |
| scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain
| |
| else
| |
| return false; -- didn't find anything that is obviously a URL
| |
| end
| |
| | |
| return is_url (scheme, domain); -- return true if value appears to be a valid URL
| |
| end | | end |
|
| |
|
| | | --[[ |
| --[[-------------------------< C H E C K _ F O R _ U R L >----------------------------------------------------- | | Sets an error condition and returns the appropriate error message. The actual placement |
| | | of the error message in the output is the responsibility of the calling function. |
| loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message.
| |
| | |
| ]] | | ]] |
| | | function seterror( error_id, arguments, raw, prefix, suffix ) |
| local function check_for_url (parameter_list)
| | local error_state = cfg.error_conditions[ error_id ]; |
| local error_message = ''; | | |
| for k, v in pairs (parameter_list) do -- for each parameter in the list | | prefix = prefix or ""; |
| if is_parameter_ext_wikilink (v) then -- look at the value; if there is a URL add an error message
| | suffix = suffix or ""; |
| if utilities.is_set(error_message) then -- once we've added the first portion of the error message ...
| | |
| error_message = error_message .. ", "; -- ... add a comma space separator
| | if error_state == nil then |
| end
| | error( cfg.messages['undefined_error'] ); |
| error_message = error_message .. "|" .. k .. "="; -- add the failed parameter
| | elseif is_set( error_state.category ) then |
| end
| | table.insert( z.error_categories, error_state.category ); |
| end | | end |
| if utilities.is_set (error_message) then -- done looping, if there is an error message, display it | | |
| table.insert( z.message_tail, { utilities.set_message ( 'err_param_has_ext_link', {error_message}, true ) } ); | | local message = substitute( error_state.message, arguments ); |
| | |
| | message = message .. " ([[" .. cfg.messages['help page link'] .. |
| | "#" .. error_state.anchor .. "|" .. |
| | cfg.messages['help page label'] .. "]])"; |
| | |
| | z.error_ids[ error_id ] = true; |
| | if inArray( error_id, { 'bare_url_missing_title', 'trans_missing_title' } ) |
| | and z.error_ids['citation_missing_title'] then |
| | return '', false; |
| end | | end |
| | |
| | message = table.concat({ prefix, message, suffix }); |
| | |
| | if raw == true then |
| | return message, error_state.hidden; |
| | end |
| | |
| | return errorcomment( message, error_state.hidden ); |
| end | | end |
|
| |
|
| | | -- Formats a wiki style external link |
| --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------
| | function externallinkid(options) |
| | | local url_string = options.id; |
| Escape sequences for content that will be used for URL descriptions
| | if options.encode == true or options.encode == nil then |
| | | url_string = mw.uri.encode( url_string ); |
| ]]
| |
| | |
| local function safe_for_url( str )
| |
| if str:match( "%[%[.-%]%]" ) ~= nil then | |
| table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); | |
| end | | end |
|
| | return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]', |
| return str:gsub( '[%[%]\n]', { | | options.link, options.label, options.separator or " ", |
| ['['] = '[', | | options.prefix, url_string, options.suffix or "", |
| [']'] = ']', | | mw.text.nowiki(options.id) |
| ['\n'] = ' ' } ); | | ); |
| end | | end |
|
| |
|
| | -- Formats a wiki style internal link |
| | function internallinkid(options) |
| | return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]', |
| | options.link, options.label, options.separator or " ", |
| | options.prefix, options.id, options.suffix or "", |
| | mw.text.nowiki(options.id) |
| | ); |
| | end |
|
| |
|
| --[[--------------------------< E X T E R N A L _ L I N K >---------------------------------------------------- | | -- Format an external link with error checking |
| | | function externallink( URL, label, source ) |
| Format an external link with error checking | |
| | |
| ]]
| |
| | |
| local function external_link( URL, label, source, access)
| |
| local error_str = ""; | | local error_str = ""; |
| local domain;
| | if not is_set( label ) then |
| local path;
| |
| local base_url;
| |
| | |
| if not utilities.is_set ( label ) then | |
| label = URL; | | label = URL; |
| if utilities.is_set ( source ) then | | if is_set( source ) then |
| error_str = utilities.set_message ( 'err_bare_url_missing_title', { utilities.wrap_style ('parameter', source) }, false, " " ); | | error_str = seterror( 'bare_url_missing_title', { wrap( 'parameter', source ) }, false, " " ); |
| else | | else |
| error( cfg.messages["bare_url_no_origin"] ); | | error( cfg.messages["bare_url_no_origin"] ); |
| end | | end |
| end | | end |
| if not check_url( URL ) then | | if not checkurl( URL ) then |
| error_str = utilities.set_message ( 'err_bad_url', {utilities.wrap_style ('parameter', source)}, false, " " ) .. error_str; | | error_str = seterror( 'bad_url', {}, false, " " ) .. error_str; |
| end | | end |
| | | return table.concat({ "[", URL, " ", safeforurl( label ), "]", error_str }); |
| domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path
| | end |
| if path then -- if there is a path portion
| |
| path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values
| |
| URL = table.concat ({domain, path}); -- and reassemble
| |
| end
| |
| | |
| base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL
| |
|
| |
|
| if utilities.is_set (access) then -- access level (subscription, registration, limited) | | -- Formats a link to Amazon |
| base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon | | function amazon(id, domain) |
| | if not is_set(domain) then |
| | domain = "com" |
| | elseif ( "jp" == domain or "uk" == domain ) then |
| | domain = "co." .. domain |
| end | | end |
| | | local handler = cfg.id_handlers['ASIN']; |
| return table.concat ({base_url, error_str}); | | return externallinkid({link = handler.link, |
| | label=handler.label , prefix="//www.amazon."..domain.."/dp/",id=id, |
| | encode=handler.encode, separator = handler.separator}) |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >-------------------------------------- | | format and error check arXiv identifier. There are two valid forms of the identifier: |
| | | the first form, valid only between date codes 9108 and 0703 is: |
| Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the
| | arXiv:<archive>.<class>/<date code><number> |
| offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated
| | where: |
| parameters in the citation.
| | <archive> is a string of alpha characters - may be hyphenated; no other punctuation |
| | | <class> is a string of alpha characters - may be hyphenated; no other punctuation |
| added_deprecated_cat is a Boolean declared in page scope variables above
| | <date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01 |
| | | first digit of YY for this form can only 9 and 0 |
| | <number> is a three-digit number |
| | |
| | the second form, valid from April 2007 is: |
| | arXiv:<date code>.<number><version> |
| | where: |
| | <date code> is four digits in the form YYMM where YY is the last two digits of the four-digit year and MM is the month number January = 01 |
| | <number> is a four-digit number |
| | <version> is a 1 or more digit number preceded with a lowercase v; no spaces |
| ]] | | ]] |
|
| |
|
| local function deprecated_parameter(name) | | function arxiv (id) |
| if not added_deprecated_cat then | | local handler = cfg.id_handlers['ARXIV']; |
| added_deprecated_cat = true; -- note that we've added this category | | local year, month, version; |
| table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } ); -- add error message | | local err_cat = "" |
| | |
| | year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d$"); -- test for the 9108-0703 format |
| | if not year then -- arXiv id is not proper 9108-0703 form |
| | year, month, version = id:match("^(%d%d)([01]%d)%.%d%d%d%d([v%d]*)$"); -- test for the 0704- format |
| | if not year then |
| | err_cat = ' ' .. seterror( 'bad_arxiv' ); -- arXiv id doesn't match either format |
| | else -- id is the 0704- format |
| | year = tonumber(year); |
| | month = tonumber(month); |
| | if ((7 > year) or (1 > month and 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years) |
| | ((7 == year) and (4 > month)) or -- when year is 07, is month invalid (before April)? |
| | is_set (version) and nil == version:match("v%d+") then -- is version proper format of single 'v' followed by digits? |
| | err_cat = ' ' .. seterror( 'bad_arxiv' ); -- set error message |
| | end |
| | end |
| | else -- id is the 9108-0703 format; are the date values ok |
| | year = tonumber(year); |
| | month = tonumber(month); |
| | if ((91 > year and 7 < year) or (1 > month and 12 < month)) or -- if invalid year or invalid month |
| | ((91 == year and 8 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok? |
| | err_cat = ' ' .. seterror( 'bad_arxiv' ); -- set error message |
| | end |
| end | | end |
| | |
| | return externallinkid({link = handler.link, label = handler.label, |
| | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| end | | end |
|
| |
|
| | --[[ |
| | lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization) |
| | 1. Remove all blanks. |
| | 2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash. |
| | 3. If there is a hyphen in the string: |
| | a. Remove it. |
| | b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out): |
| | 1. All these characters should be digits, and there should be six or less. (not done in this function) |
| | 2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six. |
|
| |
|
| --[[--------------------------< D I S C O U R A G E D _ P A R A M E T E R >------------------------------------
| | Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function. |
| | ]] |
|
| |
|
| Categorize and emit an maintenance message when the citation contains one or more discouraged parameters. Only
| | function normalize_lccn (lccn) |
| one error message is emitted regardless of the number of discouraged parameters in the citation.
| | lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace |
|
| |
|
| added_discouraged_cat is a Boolean declared in page scope variables above
| | if nil ~= string.find (lccn,'/') then |
| | lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it |
| | end |
|
| |
|
| ]]
| | local prefix |
| | local suffix |
| | prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix |
|
| |
|
| local function discouraged_parameter(name)
| | if nil ~= suffix then -- if there was a hyphen |
| if not added_discouraged_cat then | | suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6 |
| added_discouraged_cat = true; -- note that we've added this category
| | lccn=prefix..suffix; -- reassemble the lccn |
| table.insert( z.message_tail, { utilities.set_message ( 'maint_discouraged', {name}, true ) } ); -- add maint message | | end |
| | |
| | return lccn; |
| end | | end |
| end
| |
|
| |
|
| | --[[ |
| | Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the |
| | rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/ |
|
| |
|
| --[=[-------------------------< K E R N _ Q U O T E S >--------------------------------------------------------
| | length = 8 then all digits |
| | length = 9 then lccn[1] is alpha |
| | length = 10 then lccn[1] and lccn[2] are both alpha or both digits |
| | length = 11 then lccn[1] is alpha, lccn[2] and lccn[3] are both alpha or both digits |
| | length = 12 then lccn[1] and lccn[2] are both alpha |
|
| |
|
| Apply kerning to open the space between the quote mark provided by the module and a leading or trailing quote
| | ]] |
| mark contained in a |title= or |chapter= parameter's value.
| | function lccn(lccn) |
| | | local handler = cfg.id_handlers['LCCN']; |
| This function will positive kern either single or double quotes:
| | local err_cat = ''; -- presume that LCCN is valid |
| "'Unkerned title with leading and trailing single quote marks'" | | local id = lccn; -- local copy of the lccn |
| " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example) | |
| Double single quotes (italic or bold wiki-markup) are not kerned.
| |
|
| |
|
| Replaces Unicode quote marks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter
| | id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) |
| quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks.
| | local len = id:len(); -- get the length of the lccn |
|
| |
|
| Call this function for chapter titles, for website titles, etc.; not for book titles.
| | if 8 == len then |
| | | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) |
| ]=]
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- set an error message |
| | | end |
| local function kern_quotes (str)
| | elseif 9 == len then -- LCCN should be adddddddd |
| local cap = '';
| | if nil == id:match("%a%d%d%d%d%d%d%d%d") then -- does it match our pattern? |
| local cap2 = '';
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- set an error message |
| local wl_type, label, link;
| |
| | |
| wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
| |
|
| |
| if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks | |
| if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks | |
| str = utilities.substitute (cfg.presentation['kern-wl-both'], str); | |
| elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks
| |
| str = utilities.substitute (cfg.presentation['kern-wl-left'], str);
| |
| elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks | |
| str = utilities.substitute (cfg.presentation['kern-wl-right'], str); | |
| end | | end |
| | | elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd |
| else -- plain text or [[L|D]]; text in label variable | | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... |
| label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) | | if nil == id:match("^%a%a%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern |
| label = mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark)
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message |
| | | end |
| cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup)
| |
| if utilities.is_set (cap) then
| |
| label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2});
| |
| end | | end |
| | | elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd |
| cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) | | if not (id:match("^%a%a%a%d%d%d%d%d%d%d%d") or id:match("^%a%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns |
| if utilities.is_set (cap) then
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message |
| label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2}); | |
| end | | end |
|
| | elseif 12 == len then -- LCCN should be aadddddddddd |
| if 2 == wl_type then | | if not id:match("^%a%a%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern |
| str = utilities.make_wikilink (link, label); -- reassemble the wikilink | | err_cat = ' ' .. seterror( 'bad_lccn' ); -- no match, set an error message |
| else
| |
| str = label;
| |
| end | | end |
| | else |
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- wrong length, set an error message |
| end | | end |
| return str;
| |
| end
| |
|
| |
|
| | if not is_set (err_cat) and nil ~= lccn:find ('%s') then |
| | err_cat = ' ' .. seterror( 'bad_lccn' ); -- lccn contains a space, set an error message |
| | end |
|
| |
|
| --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >----------------------------------------
| | return externallinkid({link = handler.link, label = handler.label, |
| | | prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| |script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should
| | end |
| 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 ISO 639-1 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 ISO 639-1 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.
| |
| | |
| Supports |script-title=, |script-chapter=, |script-<periodical>=
| |
|
| |
|
| | --[[ |
| | Format PMID and do simple error checking. PMIDs are sequential numbers beginning at 1 and counting up. This code checks the PMID to see that it |
| | contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued. |
| ]] | | ]] |
| | | function pmid(id) |
| local function format_script_value (script_value, script_param)
| | local test_limit = 30000000; -- update this value as PMIDs approach |
| local lang=''; -- initialize to empty string | | local handler = cfg.id_handlers['PMID']; |
| local name; | | local err_cat = ''; -- presume that PMID is valid |
| 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 | | if id:match("[^%d]") then -- if PMID has anything but digits |
| if not utilities.is_set (lang) then | | err_cat = ' ' .. seterror( 'bad_pmid' ); -- set an error message |
| table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message | | else -- PMID is only digits |
| return ''; -- script_value was just the prefix so return empty string
| | local id_num = tonumber(id); -- convert id to a number for range testing |
| | if 1 > id_num or test_limit < id_num then -- if PMID is outside test limit boundaries |
| | err_cat = ' ' .. seterror( 'bad_pmid' ); -- set an error message |
| end | | 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
| |
| if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
| |
| script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
| |
| -- is prefix one of these language codes?
| |
| if utilities.in_array (lang, cfg.script_lang_codes) then
| |
| utilities.add_prop_cat ('script_with_name', {name, lang})
| |
| else
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message
| |
| end
| |
| lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute
| |
| else
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message
| |
| lang = ''; -- invalid so set lang to empty string
| |
| end
| |
| else
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message
| |
| end | | end |
| script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL | | |
| | | return externallinkid({link = handler.link, label = handler.label, |
| return script_value;
| | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ | | Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is |
| | | in the future, returns true; otherwise, returns false because the embargo has expired or |embargo= not set in this cite. |
| Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been
| |
| wrapped in <bdi> tags.
| |
| ]] | | ]] |
| | | function is_embargoed(embargo) |
| local function script_concatenate (title, script, script_param)
| | if is_set(embargo) then |
| if utilities.is_set (script) then | | local lang = mw.getContentLanguage(); |
| script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error | | local good1, embargo_date, good2, todays_date; |
| if utilities.is_set (script) then | | good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo ); |
| title = title .. ' ' .. script; -- concatenate title and script title | | good2, todays_date = pcall( lang.formatDate, lang, 'U' ); |
| | |
| | if good1 and good2 and tonumber( embargo_date ) >= tonumber( todays_date ) then --is embargo date is in the future? |
| | return true; -- still embargoed |
| end | | end |
| end | | end |
| return title; | | return false; -- embargo expired or |embargo= not set |
| end | | end |
|
| |
|
| | --[[ |
| | Format a PMC, do simple error checking, and check for embargoed articles. |
|
| |
|
| --[[--------------------------< W R A P _ M S G >--------------------------------------------------------------
| | The embargo parameter takes a date for a value. If the embargo date is in the future |
| | | the PMC identifier will not be linked to the article. If the embargo specifies a date in the past, or if it is empty or omitted, then |
| Applies additional message text to various parameter values. Supplied string is wrapped using a message_list
| | the PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix. |
| configuration taking one argument. Supports lower case text for {{citation}} templates. Additional text taken
| |
| from citation_config.messages - the reason this function is similar to but separate from wrap_style().
| |
|
| |
|
| | PMCs are sequential numbers beginning at 1 and counting up. This code checks the PMC to see that it contains only digits and is less |
| | than test_limit; the value in local variable test_limit will need to be updated periodically as more PMCs are issued. |
| ]] | | ]] |
| | function pmc(id, embargo) |
| | local test_limit = 5000000; -- update this value as PMCs approach |
| | local handler = cfg.id_handlers['PMC']; |
| | local err_cat = ''; -- presume that PMC is valid |
| | |
| | local text; |
|
| |
|
| local function wrap_msg (key, str, lower) | | if id:match("[^%d]") then -- if PMC has anything but digits |
| if not utilities.is_set ( str ) then | | err_cat = ' ' .. seterror( 'bad_pmc' ); -- set an error message |
| return ""; | | else -- PMC is only digits |
| | local id_num = tonumber(id); -- convert id to a number for range testing |
| | if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries |
| | err_cat = ' ' .. seterror( 'bad_pmc' ); -- set an error message |
| | end |
| end | | end |
| if true == lower then | | |
| local msg; | | if is_embargoed(embargo) then |
| msg = cfg.messages[key]:lower(); -- set the message to lower case before
| | text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; --still embargoed so no external link |
| return utilities.substitute ( msg, str ); -- including template text
| |
| else | | else |
| return utilities.substitute ( cfg.messages[key], str ); | | text = externallinkid({link = handler.link, label = handler.label, --no embargo date, ok to link to article |
| end | | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| | end |
| | return text; |
| end | | end |
|
| |
|
| | -- Formats a DOI and checks for DOI errors. |
|
| |
|
| --[[----------------< W I K I S O U R C E _ U R L _ M A K E >------------------- | | -- DOI names contain two parts: prefix and suffix separated by a forward slash. |
| | -- Prefix: directory indicator '10.' followed by a registrant code |
| | -- Suffix: character string of any length chosen by the registrant |
|
| |
|
| Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate
| | -- This function checks a DOI name for: prefix/suffix. If the doi name contains spaces or endashes, |
| label; nil else.
| | -- or, if it ends with a period or a comma, this function will emit a bad_doi error message. |
|
| |
|
| str is the value assigned to |chapter= (or aliases) or |title= or |title-link=
| | -- DOI names are case-insensitive and can incorporate any printable Unicode characters so the test for spaces, endash, |
| | -- and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in doi names. |
|
| |
|
| ]]
| | function doi(id, inactive) |
| | | local cat = "" |
| local function wikisource_url_make (str)
| | local handler = cfg.id_handlers['DOI']; |
| local wl_type, D, L; | | |
| local ws_url, ws_label; | | local text; |
| local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'});
| | if is_set(inactive) then |
| | | local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date |
| wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink) | | text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id; |
| | | if is_set(inactive_year) then |
| if 0 == wl_type then -- not a wikilink; might be from |title-link= | | table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year ); |
| str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace | | else |
| if utilities.is_set (str) then
| | table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year |
| ws_url = table.concat ({ -- build a Wikisource URL
| |
| wikisource_prefix, -- 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 utilities.is_set (str) then | |
| ws_url = table.concat ({ -- build a Wikisource URL | |
| wikisource_prefix, -- 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 utilities.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
| |
| wikisource_prefix, -- prefix
| |
| str, -- article title without namespace from link portion of wikilink
| |
| });
| |
| end | | end |
| | inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")" |
| | else |
| | text = externallinkid({link = handler.link, label = handler.label, |
| | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| | inactive = "" |
| end | | end |
|
| |
|
| if ws_url then | | if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma |
| ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL
| | cat = ' ' .. seterror( 'bad_doi' ); |
| ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker | |
| end | | end |
| | | return text .. inactive .. cat |
| return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil | |
| end | | end |
|
| |
|
| | | -- Formats an OpenLibrary link, and checks for associated errors. |
| --[[----------------< F O R M A T _ P E R I O D I C A L >----------------------- | | function openlibrary(id) |
| | | local code = id:sub(-1,-1) |
| Format the three periodical parameters: |script-<periodical>=, |<periodical>=,
| | local handler = cfg.id_handlers['OL']; |
| and |trans-<periodical>= into a single Periodical meta-parameter.
| | if ( code == "A" ) then |
| | | return externallinkid({link=handler.link, label=handler.label, |
| ]]
| | prefix="http://openlibrary.org/authors/OL",id=id, separator=handler.separator, |
| | | encode = handler.encode}) |
| local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical)
| | elseif ( code == "M" ) then |
| local periodical_error = '';
| | return externallinkid({link=handler.link, label=handler.label, |
| | | prefix="http://openlibrary.org/books/OL",id=id, separator=handler.separator, |
| if not utilities.is_set (periodical) then | | encode = handler.encode}) |
| periodical = ''; -- to be safe for concatenation | | elseif ( code == "W" ) then |
| | return externallinkid({link=handler.link, label=handler.label, |
| | prefix= "http://openlibrary.org/works/OL",id=id, separator=handler.separator, |
| | encode = handler.encode}) |
| else | | else |
| periodical = utilities.wrap_style ('italic-title', periodical); -- style | | return externallinkid({link=handler.link, label=handler.label, |
| end
| | prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator, |
| | | encode = handler.encode}) .. |
| periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
| | ' ' .. seterror( 'bad_ol' ); |
| | |
| if utilities.is_set (trans_periodical) then
| |
| trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical);
| |
| if utilities.is_set (periodical) then
| |
| periodical = periodical .. ' ' .. trans_periodical; | |
| else -- here when trans-periodical without periodical or script-periodical
| |
| periodical = trans_periodical; | |
| periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'});
| |
| end
| |
| end | | end |
|
| |
| return periodical .. periodical_error;
| |
| end | | end |
|
| |
|
| | --[[ |
| | Validate and format an issn. This code fixes the case where an editor has included an ISSN in the citation but has separated the two groups of four |
| | digits with a space. When that condition occurred, the resulting link looked like this: |
|
| |
|
| --[[------------------< F O R M A T _ C H A P T E R _ T I T L E >---------------
| | |issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link |
| | | |
| Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=,
| | This code now prevents that by inserting a hyphen at the issn midpoint. It also validates the issn for length and makes sure that the checkdigit agrees |
| and |chapter-url= into a single chapter meta- parameter (chapter_url_source used
| | with the calculated value. Incorrect length (8 digits), characters other than 0-9 and X, or checkdigit / calculated value mismatch will all cause a check issn |
| for error messages).
| | error message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits. |
| | |
| ]] | | ]] |
| | function issn(id) |
| | local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate |
| | local handler = cfg.id_handlers['ISSN']; |
| | local text; |
| | local valid_issn = true; |
|
| |
|
| local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access)
| | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn |
| 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 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position |
| if ws_url then | | valid_issn=false; -- wrong length or improper character |
| ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters | | else |
| chapter = ws_label;
| | valid_issn=is_valid_isxn(id, 8); -- validate issn |
| end | | end |
|
| |
|
| if not utilities.is_set (chapter) then | | if true == valid_issn then |
| chapter = ''; -- to be safe for concatenation | | id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version |
| else | | else |
| if false == no_quotes then | | id = issn_copy; -- if not valid, use the show the invalid issn with error message |
| chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from module provided quote marks
| |
| chapter = utilities.wrap_style ('quoted-title', chapter);
| |
| end
| |
| end | | end |
| | | |
| chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | | text = externallinkid({link = handler.link, label = handler.label, |
| | | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| if utilities.is_set (chapter_url) then
| | |
| chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate | | if false == valid_issn then |
| elseif ws_url then
| | text = text .. ' ' .. seterror( 'bad_issn' ) -- add an error message if the issn is invalid |
| 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?
| | end |
| chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter});
| | |
| end
| | return text |
| | |
| if utilities.is_set (trans_chapter) then | |
| trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter); | |
| if utilities.is_set (chapter) then
| |
| chapter = chapter .. ' ' .. trans_chapter;
| |
| 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>
| |
| chapter_error = ' ' .. utilities.set_message ('err_trans_missing_title', {chapter_source});
| |
| end
| |
| end | |
| | |
| return chapter .. chapter_error; | |
| end | | end |
|
| |
|
| | | --[[ |
| --[[----------------< H A S _ I N V I S I B L E _ C H A R S >------------------- | | This function sets default title types (equivalent to the citation including |type=<default value>) for those citations that have defaults. |
| | | Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none). |
| This function searches a parameter's value for non-printable or invisible characters. | |
| The search stops at the first match.
| |
| | |
| This function will detect the visible replacement character when it is part of the Wikisource.
| |
| | |
| Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers
| |
| (gallery, math, pre, ref) and identifies them with a slightly different error message.
| |
| See also coins_cleanup().
| |
| | |
| Output of this function is an error message that identifies the character or the
| |
| Unicode group, or the stripmarker that was detected along with its position (or,
| |
| for multi-byte characters, the position of its first byte) in the parameter value.
| |
| | |
| ]] | | ]] |
| | | function set_titletype(cite_class, title_type) |
| local function has_invisible_chars (param, v)
| | if is_set(title_type) then |
| local position = ''; -- position of invisible char or starting position of stripmarker | | if "none" == title_type then |
| local capture; -- used by stripmarker detection to hold name of the stripmarker
| | title_type = ""; -- if |type=none then type parameter not displayed |
| local stripmarker; -- boolean set true when a stripmarker is found
| |
| | |
| capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true
| |
| if capture == v then -- if same there are no Unicode characters
| |
| return;
| |
| end
| |
| | |
| for _, invisible_char in ipairs (cfg.invisible_chars) do
| |
| local char_name = invisible_char[1]; -- the character or group name | |
| local pattern = invisible_char[2]; -- the pattern used to find it
| |
| position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern
| |
|
| |
| if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character
| |
| if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts | |
| position = nil; -- unset position
| |
| elseif cfg.emoji[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
| |
| position = nil; -- unset position | |
| end
| |
| end
| |
|
| |
| if position then
| |
| if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition)
| |
| ('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters
| |
| stripmarker = true; -- set a flag
| |
| elseif true == stripmarker and cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker
| |
| position = nil; -- unset
| |
| else
| |
| local err_msg;
| |
| if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then
| |
| err_msg = capture .. ' ' .. char_name;
| |
| else
| |
| err_msg = char_name .. ' ' .. 'character';
| |
| end
| |
| | |
| table.insert (z.message_tail, {utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true)}); -- add error message
| |
| return; -- and done with this parameter
| |
| end
| |
| end | | end |
| | return title_type; -- if |type= has been set to any other value use that value |
| end | | end |
| end
| |
|
| |
|
| |
|
| --[[-------------------< A R G U M E N T _ W R A P P E R >---------------------- | | if "AV-media-notes" == cite_class or "DVD-notes" == cite_class then -- if this citation is cite AV media notes or cite DVD notes |
| | return "Media notes"; -- display AV media notes / DVD media notes annotation |
|
| |
|
| Argument wrapper. This function provides support for argument mapping defined
| | elseif "podcast" == cite_class then -- if this citation is cite podcast |
| in the configuration file so that multiple names can be transparently aliased to
| | return "Podcast"; -- display podcast annotation |
| single internal variable.
| |
|
| |
|
| ]]
| | elseif "pressrelease" == cite_class then -- if this citation is cite press release |
| | return "Press release"; -- display press release annotation |
|
| |
|
| local function argument_wrapper ( args )
| | elseif "techreport" == cite_class then -- if this citation is cite techreport |
| local origin = {}; | | return "Technical report"; -- display techreport annotation |
| | | |
| return setmetatable({ | | elseif "thesis" == cite_class then -- if this citation is cite thesis (degree option handled after this function returns) |
| ORIGIN = function ( self, k )
| | return "Thesis"; -- display simple thesis annotation (without |degree= modification) |
| local dummy = self[k]; -- force the variable to be loaded.
| | end |
| return origin[k];
| |
| end
| |
| },
| |
| {
| |
| __index = function ( tbl, k )
| |
| if origin[k] ~= nil then | |
| return nil;
| |
| end
| |
|
| |
| local args, list, v = args, cfg.aliases[k];
| |
|
| |
| if type( list ) == 'table' then
| |
| v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' ); | |
| if origin[k] == nil then
| |
| origin[k] = ''; -- Empty string, not nil
| |
| end
| |
| elseif list ~= nil then
| |
| v, origin[k] = args[list], list;
| |
| else
| |
| -- maybe let through instead of raising an error?
| |
| -- v, origin[k] = args[k], k;
| |
| error( cfg.messages['unknown_argument_map'] .. ': ' .. k);
| |
| end
| |
|
| |
| -- Empty strings, not nil;
| |
| if v == nil then
| |
| v = '';
| |
| origin[k] = '';
| |
| end
| |
|
| |
| tbl = rawset( tbl, k, v );
| |
| return v;
| |
| end,
| |
| });
| |
| end | | end |
|
| |
|
| | --[[ |
| | Determines whether a URL string is valid |
|
| |
|
| --[[--------------------------< N O W R A P _ D A T E >-------------------------
| | At present the only check is whether the string appears to |
| | | be prefixed with a URI scheme. It is not determined whether |
| When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>.
| | the URI scheme is valid or whether the URL is otherwise well |
| When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span:
| | formed. |
| <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY
| |
| | |
| DOES NOT yet support MMMM YYYY or any of the date ranges.
| |
| | |
| ]] | | ]] |
| | function checkurl( url_str ) |
| | -- Protocol-relative or URL scheme |
| | return url_str:sub(1,2) == "//" or url_str:match( "^[^/]*:" ) ~= nil; |
| | end |
|
| |
|
| local function nowrap_date (date)
| | -- Removes irrelevant text and dashes from ISBN number |
| local cap = ''; | | -- Similar to that used for Special:BookSources |
| local cap2 = '';
| | function cleanisbn( isbn_str ) |
| | return isbn_str:gsub( "[^-0-9X]", "" ); |
| | end |
|
| |
|
| if date:match("^%d%d%d%d%-%d%d%-%d%d$") then
| | -- Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS. |
| date = utilities.substitute (cfg.presentation['nowrap1'], date);
| | --TODO: Fix so this code supports urls like this: |
| | -- http://www.history.navy.mil/download/va125153.pdf#page=13 %w/:\. |
| | function get_coins_pages (pages) |
| | if not is_set (pages) then return pages; end -- if no page numbers then we're done |
| | | |
| 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 | | while true do |
| cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$");
| | pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url " |
| date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2}); | | if nil == pattern then break; end -- no more urls |
| | pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible |
| end | | end |
| | | pages = pages:gsub("[%[%]]", ""); -- remove the brackets |
| return date; | | pages = pages:gsub("–", "-" ); -- replace endashes with hyphens |
| | pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like? |
| | return pages; |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< S E T _ T I T L E T Y P E >--------------------- | | ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in checkisbn(). |
| | | If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes, |
| This function sets default title types (equivalent to the citation including
| | spaces and other non-isxn characters. |
| |type=<default value>) for those templates that have defaults. Also handles the
| |
| special case where it is desirable to omit the title type from the rendered citation
| |
| (|type=none).
| |
| | |
| ]] | | ]] |
| | | function is_valid_isxn (isxn_str, len) |
| local function set_titletype (cite_class, title_type) | | local temp = 0; |
| if utilities.is_set (title_type) then | | isxn_str = { isxn_str:byte(1, len) }; -- make a table of bytes |
| if 'none' == cfg.keywords_xlate[title_type] then | | len = len+1; -- adjust to be a loop counter |
| title_type = ''; -- if |type=none then type parameter not displayed | | for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum |
| | if v == string.byte( "X" ) then -- if checkdigit is X |
| | temp = temp + 10*( len - i ); -- it represents 10 decimal |
| | else |
| | temp = temp + tonumber( string.char(v) )*(len-i); |
| end | | end |
| return title_type; -- if |type= has been set to any other value use that value
| |
| end | | end |
| | | return temp % 11 == 0; -- returns true if calculation result is zero |
| return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation | |
| end | | end |
|
| |
|
| | -- Determines whether an ISBN string is valid |
| | function checkisbn( isbn_str ) |
| | if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X |
| | isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces |
| | local len = isbn_str:len(); |
| | |
| | if len ~= 10 and len ~= 13 then |
| | return false; |
| | end |
|
| |
|
| --[[--------------------------< H Y P H E N _ T O _ D A S H >--------------------------------------------------
| | if len == 10 then |
| | if isbn_str:match( "^%d*X?$" ) == nil then return false; end |
| | return is_valid_isxn(isbn_str, 10); |
| | else |
| | local temp = 0; |
| | if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979 |
| | isbn_str = { isbn_str:byte(1, len) }; |
| | for i, v in ipairs( isbn_str ) do |
| | temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); |
| | end |
| | return temp % 10 == 0; |
| | end |
| | end |
|
| |
|
| Converts a hyphen to a dash under certain conditions. The hyphen must separate
| | -- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B |
| like items; unlike items are returned unmodified. These forms are modified: | | function removewikilink( str ) |
| letter - letter (A - B)
| | return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l) |
| digit - digit (4-5)
| | return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1"); |
| digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) | | end)); |
| letterdigit - letterdigit (A1-A5) (an optional separator between letter and
| | end |
| 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.
| | -- Escape sequences for content that will be used for URL descriptions |
| | function safeforurl( str ) |
| | if str:match( "%[%[.-%]%]" ) ~= nil then |
| | table.insert( z.message_tail, { seterror( 'wikilink_in_url', {}, true ) } ); |
| | end |
| | |
| | return str:gsub( '[%[%]\n]', { |
| | ['['] = '[', |
| | [']'] = ']', |
| | ['\n'] = ' ' } ); |
| | end |
|
| |
|
| str may be a comma- or semicolon-separated list
| | -- Converts a hyphen to a dash |
| | | function hyphentodash( str ) |
| ]]
| | if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then |
| | |
| local function hyphen_to_dash( str )
| |
| if not utilities.is_set (str) then | |
| return str; | | return str; |
| end | | end |
| | return str:gsub( '-', '–' ); |
| | end |
|
| |
|
| local accept; -- Boolean
| | -- Protects a string that will be wrapped in wiki italic markup '' ... '' |
| | | function safeforitalics( str ) |
| str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split
| | --[[ Note: We cannot use <i> for italics, as the expected behavior for |
| str = str:gsub ('-', '-'); -- replace HTML numeric entity with hyphen character | | italics specified by ''...'' in the title is that they will be inverted |
| | | (i.e. unitalicized) in the resulting references. In addition, <i> and '' |
| str = str:gsub (' ', ' '); -- replace entity with generic keyboard space character | | tend to interact poorly under Mediawiki's HTML tidy. ]] |
| | | |
| local out = {}; | | if not is_set(str) then |
| local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any
| | return str; |
| | |
| for _, item in ipairs (list) do -- for each item in the list
| |
| item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item
| |
| if not accept and 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 whitespace
| |
| end
| |
| end
| |
| table.insert (out, item); -- add the (possibly modified) item to the output table
| |
| end
| |
| | |
| local temp_str = ''; -- concatenate the output table into a comma separated string
| |
| temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out
| |
| if accept then
| |
| temp_str = utilities.has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value | |
| return temp_str;
| |
| else | | else |
| return temp_str; -- else, return assembled temp_str | | if str:sub(1,1) == "'" then str = "<span />" .. str; end |
| | if str:sub(-1,-1) == "'" then str = str .. "<span />"; end |
| | |
| | -- Remove newlines as they break italics. |
| | return str:gsub( '\n', ' ' ); |
| end | | end |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< S A F E _ J O I N >----------------------------- | |
| | |
| Joins a sequence of strings together while checking for duplicate separation characters. | | Joins a sequence of strings together while checking for duplicate separation characters. |
|
| |
|
| | TODO: safejoin() has a flaw where it won't remove the duplicate character from a |title= / |url= combination. |
| | This is because by the time we get here, |title=http://somesite.com and |title=Document Title. have been combined: |
| | [http://somesite.com and ''Document Title.''] |
| | so that now, the last character is not sepc but is ] (unless sepc == ']' which breaks the external link) |
| ]] | | ]] |
| | | function safejoin( tbl, duplicate_char ) |
| local function safe_join( tbl, duplicate_char )
| | --[[ |
| local f = {}; -- create a function table appropriate to type of 'duplicate character' | | Note: we use string functions here, rather than ustring functions. |
| if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions
| | |
| f.gsub = string.gsub
| | This has considerably faster performance and should work correctly as |
| f.match = string.match
| | long as the duplicate_char is strict ASCII. The strings |
| f.sub = string.sub
| | in tbl may be ASCII or UTF8. |
| else -- for multi-byte characters use the ustring library functions
| | ]] |
| f.gsub = mw.ustring.gsub
| | |
| f.match = mw.ustring.match
| | local str = ''; |
| f.sub = mw.ustring.sub
| | local comp = ''; |
| end
| |
| | |
| local str = ''; -- the output string | |
| local comp = ''; -- what does 'comp' mean? | |
| local end_chr = ''; | | local end_chr = ''; |
| local trim; | | local trim; |
Line 992: |
Line 747: |
| if value == nil then value = ''; end | | if value == nil then value = ''; end |
| | | |
| if str == '' then -- if output string is empty | | if str == '' then |
| str = value; -- assign value to it (first time through the loop) | | str = value; |
| elseif value ~= '' then | | elseif value ~= '' then |
| if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup. | | if value:sub(1,1) == '<' then |
| comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string) | | -- Special case of values enclosed in spans and other markup. |
| | comp = value:gsub( "%b<>", "" ); |
| else | | else |
| comp = value; | | comp = value; |
| end | | end |
| -- typically duplicate_char is sepc
| | |
| if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character? | | if comp:sub(1,1) == duplicate_char then |
| -- Because individual string segments often (always?) begin with terminal punct for the
| |
| -- preceding segment: 'First element' .. 'sepc next element' .. etc.?
| |
| trim = false; | | trim = false; |
| end_chr = f.sub(str, -1, -1); -- get the last character of the output string | | end_chr = str:sub(-1,-1); |
| -- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff? | | -- str = str .. "<HERE(enchr=" .. end_chr.. ")" |
| if end_chr == duplicate_char then -- if same as separator | | if end_chr == duplicate_char then |
| str = f.sub(str, 1, -2); -- remove it | | str = str:sub(1,-2); |
| elseif end_chr == "'" then -- if it might be wiki-markup | | elseif end_chr == "'" then |
| if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' | | if str:sub(-3,-1) == duplicate_char .. "''" then |
| str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' | | str = str:sub(1, -4) .. "''"; |
| elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' | | elseif str:sub(-5,-1) == duplicate_char .. "]]''" then |
| trim = true; -- why? why do this and next differently from previous?
| |
| 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 wiki-markup
| |
| if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink
| |
| trim = true; | | trim = true; |
| elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link | | elseif str:sub(-4,-1) == duplicate_char .. "]''" then |
| trim = true; | | trim = true; |
| elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link | | end |
| | elseif end_chr == "]" then |
| | if str:sub(-3,-1) == duplicate_char .. "]]" then |
| trim = true; | | trim = true; |
| elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. | | elseif str:sub(-2,-1) == duplicate_char .. "]" then |
| trim = true; | | trim = true; |
| end | | end |
| elseif end_chr == " " then -- if last char of output string is a space | | elseif end_chr == " " then |
| if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> | | if str:sub(-2,-1) == duplicate_char .. " " then |
| str = f.sub(str, 1, -3); -- remove them both | | str = str:sub(1,-3); |
| end | | end |
| end | | end |
|
| |
|
| if trim then | | if trim then |
| if value ~= comp then -- value does not equal comp when value contains HTML markup | | if value ~= comp then |
| local dup2 = duplicate_char; | | local dup2 = duplicate_char; |
| if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it | | if dup2:match( "%A" ) then dup2 = "%" .. dup2; end |
| | | |
| value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup | | value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) |
| else | | else |
| value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character | | value = value:sub( 2, -1 ); |
| end | | end |
| end | | end |
| end | | end |
| str = str .. value; -- add it to the output string | | str = str .. value; |
| end | | end |
| end | | end |
| return str; | | return str; |
| end | | end |
| | |
| | |
| --[[--------------------------< I S _ S U F F I X >-----------------------------
| |
| | |
| returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9.
| |
| Puncutation not allowed.
| |
| | |
| ]]
| |
| | |
| local function is_suffix (suffix)
| |
| if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then
| |
| return true;
| |
| end
| |
| return false;
| |
| end
| |
| | |
| | |
| --[[--------------------< I S _ G O O D _ V A N C _ N A M E >-------------------
| |
| | |
| For Vancouver style, author/editor names are supposed to be rendered in Latin
| |
| (read ASCII) characters. When a name uses characters that contain diacritical
| |
| marks, those characters are to be 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. The module doesn't do this
| |
| so editors may/must.
| |
| | |
| This test allows |first= and |last= names to contain any of the letters defined
| |
| in the four Unicode Latin character sets
| |
| [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
| |
| [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
| |
| [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
| |
| [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
| |
| | |
| |lastn= also allowed to contain hyphens, spaces, and apostrophes.
| |
| (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
| |
| |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
| |
| | |
| 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
| |
| was written outside of the code editor and pasted here because the code editor
| |
| gets confused between character insertion point and cursor position. The test has
| |
| been rewritten to use decimal character escape sequence for the individual bytes
| |
| of the Unicode characters so that it is not necessary to use an external editor
| |
| to maintain this code.
| |
| | |
| \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls)
| |
| \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls)
| |
| \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B)
| |
| \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B)
| |
| | |
| ]]
| |
| | |
| local function is_good_vanc_name (last, first, suffix, position)
| |
| if not suffix then
| |
| if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix
| |
| first = first:match ('(.-)[,%s]+'); -- get name/initials
| |
| suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix
| |
| end
| |
| end
| |
| if utilities.is_set (suffix) then
| |
| if not is_suffix (suffix) then
| |
| add_vanc_error (cfg.err_msg_supl.suffix, position);
| |
| return false; -- not a name with an appropriate suffix
| |
| end
| |
| end
| |
| if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or
| |
| 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%'%.]*$") then
| |
| add_vanc_error (cfg.err_msg_supl['non-Latin char'], position);
| |
| return false; -- not a string of Latin characters; Vancouver requires Romanization
| |
| end;
| |
| return true;
| |
| end
| |
| | |
| | |
| --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
| |
| | |
| Attempts to convert names to initials in support of |name-list-style=vanc.
| |
| | |
| Names in |firstn= may be separated by spaces or hyphens, or for initials, a period.
| |
| See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
| |
| | |
| Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered
| |
| as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
| |
| This code only accepts and understands generational suffix in the Vancouver format
| |
| because Roman numerals look like, and can be mistaken for, initials.
| |
| | |
| This function uses ustring functions because firstname initials may be any of the
| |
| Unicode Latin characters accepted by is_good_vanc_name ().
| |
| | |
| ]]
| |
| | |
| local function reduce_to_initials(first, position)
| |
| local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$");
| |
| | |
| if not name then -- if not initials and a suffix
| |
| name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials?
| |
| end
| |
| | |
| if name then -- if first is initials with or without suffix
| |
| if 3 > mw.ustring.len (name) then -- if one or two initials
| |
| if suffix then -- if there is a suffix
| |
| if is_suffix (suffix) then -- is it legitimate?
| |
| return first; -- one or two initials and a valid suffix so nothing to do
| |
| else
| |
| add_vanc_error (cfg.err_msg_supl.suffix, position); -- one or two initials with invalid suffix so error message
| |
| return first; -- and return first unmolested
| |
| end
| |
| else
| |
| return first; -- one or two initials without suffix; nothing to do
| |
| end
| |
| end
| |
| end -- if here then name has 3 or more uppercase letters so treat them as a word
| |
| | |
| local initials, names = {}, {}; -- tables to hold name parts and initials
| |
| local i = 1; -- counter for number of initials
| |
| | |
| names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix
| |
|
| |
|
| while names[i] do -- loop through the table
| | -- Attempts to convert names to initials. |
| if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot)
| | function reducetoinitials(first) |
| names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present
| | local initials = {} |
| if is_suffix (names[i]) then -- if a legitimate suffix
| | local i = 0; -- counter for number of initials |
| table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table
| | for word in string.gmatch(first, "%S+") do |
| break; -- and done because suffix must fall at the end of a name
| | table.insert(initials, string.sub(word,1,1)) -- Vancouver format does not include full stops. |
| end -- no error message if not a suffix; possibly because of Romanization
| | i = i + 1; -- bump the counter |
| end
| | if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit |
| if 3 > i then | |
| table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table
| |
| end
| |
| i = i + 1; -- bump the counter | |
| end | | end |
|
| | return table.concat(initials) -- Vancouver format does not include spaces. |
| return table.concat(initials) -- Vancouver format does not include spaces. | |
| end | | end |
|
| |
|
| | | -- Formats a list of people (e.g. authors / editors) |
| --[[--------------------------< L I S T _ P E O P L E >--------------------------
| | function listpeople(control, people) |
| | | local sep = control.sep; |
| Formats a list of people (authors, contributors, editors, interviewers, translators) | | local namesep = control.namesep |
| | | local format = control.format |
| names in the list will be linked when
| | local maximum = control.maximum |
| |<name>-link= has a value
| | local lastauthoramp = control.lastauthoramp; |
| |<name>-mask- does NOT have a value; masked names are presumed to have been
| | local text = {} |
| rendered previously so should have been linked there
| | local etal = false; |
| | |
| when |<name>-mask=0, the associated name is not rendered
| |
| | |
| ]]
| |
| | |
| local function list_people (control, people, etal)
| |
| local sep; | |
| local namesep; | |
| local format = control.format; | |
| local maximum = control.maximum; | |
| local name_list = {}; | |
| | |
| if 'vanc' == format then -- Vancouver-like name styling? | |
| sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma
| |
| namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space
| |
| else | |
| sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon
| |
| namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space>
| |
| end
| |
| | | |
| if sep:sub (-1, -1) ~= " " then sep = sep .. " " end | | if sep:sub(-1,-1) ~= " " then sep = sep .. " " end |
| if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names | | if maximum ~= nil and maximum < 1 then return "", 0; end |
| | | |
| for i, person in ipairs (people) do | | for i,person in ipairs(people) do |
| if utilities.is_set (person.last) then | | if is_set(person.last) then |
| local mask = person.mask; | | local mask = person.mask |
| local one; | | local one |
| local sep_one = sep; | | local sep_one = sep; |
| | | if maximum ~= nil and i > maximum then |
| if utilities.is_set (maximum) and i > maximum then | |
| etal = true; | | etal = true; |
| break; | | break; |
| end | | elseif (mask ~= nil) then |
|
| | local n = tonumber(mask) |
| if mask then
| | if (n ~= nil) then |
| local n = tonumber (mask); -- convert to a number if it can be converted; nil else | | one = string.rep("—",n) |
| if n then | |
| one = 0 ~= n and string.rep("—", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name | |
| person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil
| |
| else | | else |
| one = mask; -- replace name with mask text (must include name-list separator) | | one = mask; |
| sep_one = " "; -- modify name-list separator | | sep_one = " "; |
| end | | end |
| else | | else |
| one = person.last; -- get surname | | one = person.last |
| local first = person.first -- get given name | | local first = person.first |
| if utilities.is_set (first) then | | if is_set(first) then |
| if ("vanc" == format) then -- if Vancouver format | | if ( "vanc" == format ) then first = reducetoinitials(first) end |
| one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
| | one = one .. namesep .. first |
| if not person.corporate and is_good_vanc_name (one, first, nil, i) then -- and name is all Latin characters; corporate authors not tested
| |
| first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials
| |
| end
| |
| end
| |
| one = one .. namesep .. first; | |
| end | | end |
| | if is_set(person.link) then one = "[[" .. person.link .. "|" .. one .. "]]" 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 | | end |
| if utilities.is_set (person.link) then | | table.insert( text, one ) |
| one = utilities.make_wikilink (person.link, one); -- link author/editor
| | table.insert( text, sep_one ) |
| end
| |
| if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
| |
| table.insert (name_list, one); -- add it to the list of names
| |
| table.insert (name_list, sep_one); -- add the proper name-list separator
| |
| end
| |
| end | | end |
| end | | end |
|
| |
|
| local count = #name_list / 2; -- (number of names + number of separators) divided by 2 | | local count = #text / 2; |
| if 0 < count then | | if count > 0 then |
| if 1 < count and not etal then | | if count > 1 and is_set(lastauthoramp) and not etal then |
| if 'amp' == format then | | text[#text-2] = " & "; |
| name_list[#name_list-2] = " & "; -- replace last separator with ampersand text
| |
| elseif 'and' == format then
| |
| if 2 == count then
| |
| name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text
| |
| else
| |
| name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text
| |
| end
| |
| end
| |
| end | | end |
| name_list[#name_list] = nil; -- erase the last separator | | text[#text] = nil; |
| end | | end |
| | | |
| local result = table.concat (name_list); -- construct list | | local result = table.concat(text) -- construct list |
| if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list | | if etal then |
| result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al. | | local etal_text = cfg.messages['et al']; |
| | result = result .. " " .. etal_text; |
| end | | end |
| | | |
| return result, count; -- return name-list string and count of number of names (count used for editor names only) | | -- if necessary wrap result in <span> tag to format in Small Caps |
| | if ( "scap" == format ) then result = |
| | '<span class="smallcaps" style="font-variant:small-caps">' .. result .. '</span>'; |
| | end |
| | return result, count |
| end | | end |
|
| |
|
| --[[--------------------< M A K E _ C I T E R E F _ I D >----------------------- | | -- Generates a CITEREF anchor ID. |
| | | function anchorid( options ) |
| Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise | | return "CITEREF" .. table.concat( options ); |
| returns an empty string.
| |
| | |
| namelist is one of the contributor-, author-, or editor-name lists chosen in that
| |
| order. year is Year or anchor_year.
| |
| | |
| ]]
| |
| | |
| local function make_citeref_id (namelist, year)
| |
| local names={}; -- a table for the one to four names and year | |
| for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
| |
| names[i] = v.last
| |
| if i == 4 then break end -- if four then done
| |
| end
| |
| table.insert (names, year); -- add the year at the end
| |
| local id = table.concat(names); -- concatenate names and year for CITEREF id
| |
| if utilities.is_set (id) then -- if concatenation is not an empty string
| |
| return "CITEREF" .. id; -- add the CITEREF portion
| |
| else
| |
| return ''; -- return an empty string; no reason to include CITEREF id in this citation
| |
| end
| |
| end | | end |
|
| |
|
| | | --[[ |
| --[[---------------------< N A M E _ H A S _ E T A L >-------------------------- | |
| | |
| Evaluates the content of name parameters (author, editor, etc.) for variations on
| |
| the theme of et al. If found, the et al. is removed, a flag is set to true and
| |
| the function returns the modified name and the flag.
| |
| | |
| This function never sets the flag to false but returns its previous state because
| |
| it may have been set by previous passes through this function or by the associated
| |
| |display-<names>=etal parameter
| |
| | |
| ]]
| |
| | |
| local function name_has_etal (name, etal, nocat, param)
| |
| | |
| if utilities.is_set (name) then -- name can be nil in which case just return
| |
| local patterns = cfg.et_al_patterns; -- get patterns from configuration
| |
|
| |
| for _, pattern in ipairs (patterns) do -- loop through all of the patterns
| |
| if name:match (pattern) then -- if this 'et al' pattern is found in name
| |
| name = name:gsub (pattern, ''); -- remove the offending text
| |
| etal = true; -- set flag (may have been set previously here or by |display-<names>=etal)
| |
| if not nocat then -- no categorization for |vauthors=
| |
| table.insert( z.message_tail, {utilities.set_message ('err_etal', {param})}); -- and set an error if not added
| |
| end
| |
| end
| |
| end
| |
| end
| |
| | |
| return name, etal;
| |
| end
| |
| | |
| | |
| --[[---------------------< N A M E _ I S _ N U M E R I C >----------------------
| |
| | |
| Add maint cat when name parameter value does not contain letters. Does not catch
| |
| mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the
| |
| current version of this test but |first=(1888) is caught.
| |
| | |
| returns nothing
| |
| | |
| ]]
| |
| | |
| local function name_is_numeric (name, list_name)
| |
| if utilities.is_set (name) then
| |
| if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters
| |
| utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
| |
| end
| |
| end
| |
| end
| |
| | |
| | |
| --[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------
| |
| | |
| Evaluates the content of author and editor parameters for extraneous editor annotations:
| |
| ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and
| |
| are redundant in editor parameters. If found, the function adds the editor markup
| |
| maintenance category.
| |
| | |
| returns nothing
| |
| | |
| ]]
| |
| | |
| local function name_has_ed_markup (name, list_name)
| |
| local patterns = cfg.editor_markup_patterns; -- get patterns from configuration
| |
| | |
| if utilities.is_set (name) then
| |
| for _, pattern in ipairs (patterns) do -- spin through patterns table and
| |
| if name:match (pattern) then
| |
| utilities.set_message ('maint_extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template
| |
| break;
| |
| end
| |
| end
| |
| end
| |
| end
| |
| | |
| | |
| --[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------
| |
| | |
| Evaluates the content of last/surname (authors etc.) parameters for multiple names.
| |
| Multiple names are indicated if there is more than one comma or any "unescaped"
| |
| semicolons. Escaped semicolons are ones used as part of selected HTML entities.
| |
| If the condition is met, the function adds the multiple name maintenance category.
| |
| | |
| returns nothing
| |
| | |
| ]]
| |
| | |
| local function name_has_mult_names (name, list_name)
| |
| local _, commas, semicolons, nbsps;
| |
| if utilities.is_set (name) then
| |
| _, commas = name:gsub (',', ''); -- count the number of commas
| |
| _, semicolons = name:gsub (';', ''); -- count the number of semicolons
| |
| -- nbsps probably should be its own separate count rather than merged in
| |
| -- some way with semicolons because Lua patterns do not support the
| |
| -- grouping operator that regex does, which means there is no way to add
| |
| -- more entities to escape except by adding more counts with the new
| |
| -- entities
| |
| _, nbsps = name:gsub (' ',''); -- count nbsps
| |
|
| |
| -- There is exactly 1 semicolon per entity, so subtract nbsps
| |
| -- from semicolons to 'escape' them. If additional entities are added,
| |
| -- they also can be subtracted.
| |
| if 1 < commas or 0 < (semicolons - nbsps) then
| |
| utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
| |
| end
| |
| end
| |
| end
| |
| | |
| | |
| --[[------------------------< N A M E _ C H E C K S >---------------------------
| |
| | |
| This function calls various name checking functions used to validate the content
| |
| of the various name-holding parameters.
| |
| | |
| ]]
| |
| | |
| local function name_checks (last, first, list_name)
| |
| local accept_name;
| |
| | |
| if utilities.is_set (last) then
| |
| last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last>
| |
|
| |
| if not accept_name then -- <last> not wrapped in accept-as-written markup
| |
| 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
| |
| name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
| |
| end
| |
| end
| |
| | |
| if utilities.is_set (first) then
| |
| first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first>
| |
| | |
| if not accept_name then -- <first> not wrapped in accept-as-written markup
| |
| name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation
| |
| name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
| |
| end
| |
| end
| |
| | |
| return last, first; -- done
| |
| end
| |
| | |
| | |
| --[[----------------------< E X T R A C T _ N A M E S >-------------------------
| |
| Gets name list from the input arguments | | Gets name list from the input arguments |
|
| |
|
| Searches through args in sequential order to find |lastn= and |firstn= parameters | | Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. |
| (or their aliases), and their matching link and mask parameters. Stops searching | | Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't |
| when both |lastn= and |firstn= are not found in args after two sequential attempts: | | find |last4= and |last5= then the search is done. |
| found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the | |
| search is done. | |
| | |
| This function emits an error message when there is a |firstn= without a matching
| |
| |lastn=. When there are 'holes' in the list of last names, |last1= and |last3=
| |
| are present but |last2= is missing, an error message is emitted. |lastn= is not
| |
| required to have a matching |firstn=.
| |
| | |
| When an author or editor parameter contains some form of 'et al.', the 'et al.'
| |
| is stripped from the parameter and a flag (etal) returned that will cause list_people()
| |
| to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps
| |
| 'et al.' out of the template's metadata. When this occurs, an error is emitted.
| |
|
| |
|
| | This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3= |
| | 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 i = 1; -- loop counter/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) |
| | |
| | local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary |
|
| |
|
| local function extract_names(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)
| |
| local etal = false; -- return value set to true when we find some form of et al. in an author parameter
| |
|
| |
| local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging
| |
| while true do | | while true do |
| last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1 | | names[i] = -- search through args for name components beginning at 1 |
| first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i );
| | { |
| link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
| | last = selectone( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ), |
| mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
| | first = selectone( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ), |
| | | link = selectone( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ), |
| last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
| | mask = selectone( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ) |
| first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
| | }; |
| last, first = name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc. checks | | if names[i].first and not names[i].last then -- if there is a firstn without a matching lastn |
|
| | names[i].first = nil; -- set first to nil so we don't confuse the implicit et al message code |
| 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 |
| local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias | | break; -- and done because lastn not found |
| table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', { | | elseif not names[i].first and not names[i].last then -- if both firstn and lastn aren't found, are we done? |
| first_alias, -- param name of alias missing its mate
| |
| first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form
| |
| }, true ) } ); -- add this error message
| |
| 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 | | count = count + 1; -- number of times we haven't found last and first |
| if 2 <= count then -- two missing names and we give up | | 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 | | break; -- normal exit or there is a two-name hole in the list; can't tell which |
| end | | end |
| else -- we have last with or without a first | | else -- last with or without a first |
| local result;
| |
| link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup
| |
| if first then
| |
| link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup
| |
| end
| |
| | |
| names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only)
| |
| n = n + 1; -- point to next location in the names table
| |
| if 1 == count then -- if the previous name was missing | | if 1 == count then -- if the previous name was missing |
| table.insert( z.message_tail, { utilities.set_message ( 'err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}, true ) } ); -- add this error message | | table.insert( z.message_tail, { seterror( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message |
| end | | end |
| count = 0; -- reset the counter, we're looking for two consecutive missing names | | count = 0; -- reset the counter, we're looking for two consecutive missing names |
| end | | end |
| i = i + 1; -- point to next args location | | |
| | i = i + 1; -- bump to the next name |
| end | | end |
|
| | return names; -- all done, return our list of names |
| return names, etal; -- all done, return our list of names and the etal flag | |
| end | | end |
|
| |
|
| | | -- Populates ID table from arguments using configuration settings |
| --[[---------------------< G E T _ I S O 6 3 9 _ C O D E >----------------------
| | function extractids( args ) |
| | | local id_list = {}; |
| Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code.
| | for k, v in pairs( cfg.id_handlers ) do |
| | | v = selectone( args, v.parameters, 'redundant_parameters' ); |
| Returns the language name and associated two- or three-character code. Because
| | if is_set(v) then id_list[k] = v; end |
| 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(<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'. 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 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.
| |
| | |
| 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.
| |
| | |
| ]]
| |
| | |
| local function get_iso639_code (lang, this_wiki_code)
| |
| if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct)
| |
| return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code
| |
| end | | end |
| | return id_list; |
| | end |
|
| |
|
| local ietf_code; -- because some languages have both IETF-like codes and ISO 639-like codes
| | -- Takes a table of IDs and turns it into a table of formatted ID outputs. |
| local ietf_name; | | function buildidlist( id_list, options ) |
| | local new_list, handler = {}; |
| | | |
| local langlc = mw.ustring.lower (lang); -- lower-case version for comparisons | | function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end; |
| | |
| for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language
| |
| if langlc == mw.ustring.lower (name) then
| |
| if 2 == #code or 3 == #code then -- two- or three-character codes only; IETF extensions not supported
| |
| return name, code; -- so return the name and the code
| |
| end
| |
| ietf_code = code; -- remember that we found an IETF-like code and save its name
| |
| ietf_name = name; -- but keep looking for a 2- or 3-char code
| |
| end
| |
| end
| |
| -- 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
| |
| | |
| | |
| --[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------
| |
| | |
| Gets language name from a provided two- or three-character ISO 639 code. If a code
| |
| is recognized by MediaWiki, use the returned name; if not, then use the value that
| |
| was provided with the language parameter.
| |
| | |
| When |language= contains a recognized language (either code or name), the page is
| |
| assigned to the category for that code: Category:Norwegian-language sources (no).
| |
| For valid three-character code languages, the page is assigned to the single category
| |
| for '639-2' codes: Category:CS1 ISO 639-2 language sources.
| |
| | |
| Languages that are the same as the local wiki are not categorized. MediaWiki does
| |
| not recognize three-character equivalents of two-character codes: code 'ar' is
| |
| recognized but code 'ara' is not.
| |
| | |
| This function supports multiple languages in the form |language=nb, French, th
| |
| where the language names or codes are separated from each other by commas with
| |
| optional space characters.
| |
| | |
| ]]
| |
| | |
| local function language_parameter (lang)
| |
| local code; -- the two- or three-character language code
| |
| local name; -- the language name
| |
| local language_list = {}; -- table of language names to be rendered
| |
| local names_table = {}; -- table made from the value assigned to |language=
| |
| | |
| local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name
| |
| | |
| names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list
| |
| | |
| 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 name then -- there was a remapped code so
| |
| if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private IETF tag
| |
| lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip IETF tags from code
| |
| end
| |
| else
| |
| lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any IETF-like tags from code
| |
| if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code
| |
| name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code
| |
| end
| |
| end
| |
| | |
| if utilities.is_set (name) then -- if |language= specified a valid code
| |
| code = lang:lower(); -- save it
| |
| else
| |
| name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization)
| |
| end
| |
| | | |
| if utilities.is_set (code) then -- only 2- or 3-character codes | | for k, v in pairs( id_list ) do |
| name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names | | -- fallback to read-only cfg |
| | | handler = setmetatable( { ['id'] = v }, fallback(k) ); |
| if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language | | |
| if 2 == code:len() then -- and is a two-character code
| | if handler.mode == 'external' then |
| utilities.add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization
| | table.insert( new_list, {handler.label, externallinkid( handler ) } ); |
| else -- or is a recognized language (but has a three-character code)
| | elseif handler.mode == 'internal' then |
| utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support multiple three-character code categories per cs1|2 template
| | table.insert( new_list, {handler.label, internallinkid( handler ) } ); |
| end
| | elseif handler.mode ~= 'manual' then |
| elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled | | error( cfg.messages['unknown_ID_mode'] ); |
| utilities.add_prop_cat ('local_lang_source', {name, code}); -- categorize it | | elseif k == 'DOI' then |
| | table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } ); |
| | elseif k == 'ARXIV' then |
| | table.insert( new_list, {handler.label, arxiv( v ) } ); |
| | elseif k == 'ASIN' then |
| | table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } ); |
| | elseif k == 'LCCN' then |
| | table.insert( new_list, {handler.label, lccn( v ) } ); |
| | elseif k == 'OL' then |
| | table.insert( new_list, {handler.label, openlibrary( v ) } ); |
| | elseif k == 'PMC' then |
| | table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } ); |
| | elseif k == 'PMID' then |
| | table.insert( new_list, {handler.label, pmid( v ) } ); |
| | elseif k == 'ISSN' then |
| | table.insert( new_list, {handler.label, issn( v ) } ); |
| | elseif k == 'ISBN' then |
| | local ISBN = internallinkid( handler ); |
| | if not checkisbn( v ) and not is_set(options.IgnoreISBN) then |
| | ISBN = ISBN .. seterror( 'bad_isbn', {}, false, " ", "" ); |
| end | | end |
| | table.insert( new_list, {handler.label, ISBN } ); |
| else | | else |
| utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added | | error( cfg.messages['unknown_manual_ID'] ); |
| end
| |
|
| |
| table.insert (language_list, name);
| |
| name = ''; -- so we can reuse it
| |
| end
| |
|
| |
| name = utilities.make_sep_list (#language_list, language_list);
| |
| | |
| if this_wiki_name == name then
| |
| return ''; -- if one language and that language is this wiki's return an empty string (no annotation)
| |
| end
| |
| return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)'
| |
| --[[ TODO: should only return blank or name rather than full list
| |
| so we can clean up the bunched parenthetical elements Language, Type, Format
| |
| ]]
| |
| end
| |
| | |
| --[[-----------------------< S E T _ C S _ S T Y L E >--------------------------
| |
| Gets the default CS style configuration for the given mode.
| |
| Returns default separator and either postscript as passed in or the default.
| |
| In CS1, the default postscript and separator are '.'.
| |
| In CS2, the default postscript is the empty string and the default separator is ','.
| |
| ]]
| |
| local function set_cs_style (postscript, mode)
| |
| if utilities.is_set(postscript) then
| |
| -- emit a maintenance message if user postscript is the default cs1 postscript
| |
| -- we catch the opposite case for cs2 in set_style
| |
| if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then
| |
| utilities.set_message ('maint_postscript');
| |
| end
| |
| else
| |
| postscript = cfg.presentation['ps_' .. mode];
| |
| end
| |
| return cfg.presentation['sep_' .. mode], postscript;
| |
| end
| |
| | |
| --[[--------------------------< S E T _ S T Y L E >-----------------------------
| |
| Sets the separator and postscript styles. Checks the |mode= first and the
| |
| #invoke CitationClass second. Removes the postscript if postscript == none.
| |
| ]]
| |
| local function set_style (mode, postscript, cite_class)
| |
| local sep;
| |
| if 'cs2' == mode then
| |
| sep, postscript = set_cs_style (postscript, 'cs2');
| |
| elseif 'cs1' == mode then
| |
| sep, postscript = set_cs_style (postscript, 'cs1');
| |
| elseif 'citation' == cite_class then
| |
| sep, postscript = set_cs_style (postscript, 'cs2');
| |
| else
| |
| sep, postscript = set_cs_style (postscript, 'cs1');
| |
| end
| |
| | |
| if cfg.keywords_xlate[postscript:lower()] == 'none' then
| |
| -- emit a maintenance message if user postscript is the default cs2 postscript
| |
| -- we catch the opposite case for cs1 in set_cs_style
| |
| if 'cs2' == mode or 'citation' == cite_class then
| |
| utilities.set_message ('maint_postscript');
| |
| end | | end |
| postscript = '';
| |
| end | | end |
| | | |
| return sep, postscript | | function comp( a, b ) -- used in following table.sort() |
| end
| | return a[1] < b[1]; |
| | |
| --[=[-------------------------< I S _ P D F >-----------------------------------
| |
| | |
| Determines if a URL has the file extension that is one of the PDF file extensions
| |
| used by [[MediaWiki:Common.css]] when applying the PDF icon to external links.
| |
| | |
| returns true if file extension is one of the recognized extensions, else false
| |
| | |
| ]=]
| |
| | |
| local function is_pdf (url)
| |
| return url:match ('%.pdf$') or url:match ('%.PDF$') or
| |
| url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or
| |
| url:match ('%.PDF#') or url:match ('%.pdf#');
| |
| end
| |
| | |
| | |
| --[[--------------------------< S T Y L E _ F O R M A T >-----------------------
| |
| | |
| Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message
| |
| if the format parameter does not have a matching URL parameter. If the format parameter
| |
| is not set and the URL contains a file extension that is recognized as a PDF document
| |
| by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
| |
| the appropriate styling.
| |
| | |
| ]]
| |
| | |
| local function style_format (format, url, fmt_param, url_param)
| |
| if utilities.is_set (format) then
| |
| format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize
| |
| if not utilities.is_set (url) then
| |
| format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} ); -- add an error message
| |
| end
| |
| elseif is_pdf (url) then -- format is not set so if URL is a PDF file then
| |
| format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF
| |
| else
| |
| format = ''; -- empty string for concatenation | |
| end
| |
| return format;
| |
| end
| |
| | |
| | |
| --[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------
| |
| | |
| Returns a number that defines the number of names displayed for author and editor
| |
| name lists and a Boolean flag to indicate when et al. should be appended to the name list.
| |
| | |
| When the value assigned to |display-xxxxors= is a number greater than or equal to zero,
| |
| return the number and the previous state of the 'etal' flag (false by default
| |
| but may have been set to true if the name list contains some variant of the text 'et al.').
| |
| | |
| When the value assigned to |display-xxxxors= is the keyword 'etal', return a number
| |
| that is one greater than the number of authors in the list and set the 'etal' flag true.
| |
| This will cause the list_people() to display all of the names in the name list followed by 'et al.'
| |
| | |
| In all other cases, returns nil and the previous state of the 'etal' flag.
| |
| | |
| inputs:
| |
| max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
| |
| count: #a or #e
| |
| list_name: 'authors' or 'editors'
| |
| etal: author_etal or editor_etal
| |
| | |
| ]]
| |
| | |
| local function get_display_names (max, count, list_name, etal, param)
| |
| if utilities.is_set (max) then
| |
| if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
| |
| max = count + 1; -- number of authors + 1 so display all author name plus et al.
| |
| etal = true; -- overrides value set by extract_names()
| |
| elseif max:match ('^%d+$') then -- if is a string of numbers
| |
| max = tonumber (max); -- make it a number
| |
| if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
| |
| table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
| |
| max = nil;
| |
| end
| |
| else -- not a valid keyword or number
| |
| table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message
| |
| max = nil; -- unset; as if |display-xxxxors= had not been set
| |
| end
| |
| end | | end |
| | | |
| return max, etal; | | table.sort( new_list, comp ); |
| end
| | for k, v in ipairs( new_list ) do |
| | | new_list[k] = v[2]; |
| | |
| --[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >---------------
| |
| | |
| Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be
| |
| some form of p. or pp. abbreviation in the first characters of the parameter content.
| |
| | |
| check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value:
| |
| good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px
| |
| where x and X are letters and # is a digit
| |
| bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG
| |
| | |
| ]]
| |
| | |
| local function extra_text_in_page_check (val, name)
| |
| if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then | |
| for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns
| |
| if val:match (pattern) then -- when a match, error so
| |
| table.insert (z.message_tail, {utilities.set_message ('err_extra_text_pages', {name}, true)}); -- add error message
| |
| return; -- and done
| |
| end
| |
| end | |
| end
| |
| end
| |
| | |
| | |
| --[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------
| |
| | |
| Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator.
| |
| | |
| For |volume=:
| |
| 'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter
| |
| content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so
| |
| are allowed.
| |
| | |
| For |issue=:
| |
| 'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the
| |
| parameter content (all case insensitive).
| |
|
| |
| Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or
| |
| whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module.
| |
|
| |
| <val> is |volume= or |issue= parameter value
| |
| <name> is |volume= or |issue= parameter name for error message
| |
| <selector> is 'v' for |volume=, 'i' for |issue=
| |
| | |
| sets error message on failure; returns nothing
| |
| | |
| ]] | |
| | |
| local function extra_text_in_vol_iss_check (val, name, selector)
| |
| if not utilities.is_set (val) then
| |
| return;
| |
| end | | end |
| | | |
| local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns; | | return new_list; |
| | |
| local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue';
| |
| val = val:lower(); -- force parameter value to lower case
| |
| for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns
| |
| if val:match (pattern) then -- when a match, error so
| |
| table.insert (z.message_tail, {utilities.set_message (handler, {name}, true)}); -- add error message
| |
| return; -- and done
| |
| end
| |
| end
| |
| end | | end |
| | | |
| | | -- Chooses one matching parameter from a list of parameters to consider |
| --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- | | -- Generates an error if more than one match is present. |
| | | function selectone( args, possible, error_condition, index ) |
| split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled
| | local value = nil; |
| parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the
| | local selected = ''; |
| rendered citation and in the metadata. Individual author names may be wikilinked
| | local error_list = {}; |
| | |
| |vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.))
| |
| | |
| ]=]
| |
| | |
| local function get_v_name_table (vparam, output_table, output_link_table)
| |
| local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas | |
| local wl_type, label, link; -- wl_type not used here; just a placeholder | |
| | | |
| local i = 1; | | if index ~= nil then index = tostring(index); end |
| | | |
| while name_table[i] do | | -- Handle special case of "#" replaced by empty string |
| if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses
| | if index == '1' then |
| local name = name_table[i];
| | for _, v in ipairs( possible ) do |
| i = i + 1; -- bump indexer to next segment | | v = v:gsub( "#", "" ); |
| while name_table[i] do | | if is_set(args[v]) then |
| name = name .. ', ' .. name_table[i]; -- concatenate with previous segments | | if value ~= nil and selected ~= v then |
| if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses | | table.insert( error_list, v ); |
| break; -- and done reassembling so | | else |
| | value = args[v]; |
| | selected = v; |
| end | | end |
| i = i + 1; -- bump indexer
| |
| end | | end |
| table.insert (output_table, name); -- and add corporate name to the output table
| | end |
| table.insert (output_link_table, ''); -- no wikilink
| |
| else | |
| wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]]
| |
| table.insert (output_table, label); -- add this name
| |
| if 1 == wl_type then
| |
| table.insert (output_link_table, label); -- simple wikilink [[D]]
| |
| else
| |
| table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string
| |
| end
| |
| end
| |
| i = i + 1;
| |
| end
| |
| return output_table;
| |
| end
| |
| | |
| | |
| --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
| |
| | |
| This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
| |
| |xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
| |
| | |
| Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
| |
| may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
| |
| tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests.
| |
| | |
| Supports generational suffixes Jr, 2nd, 3rd, 4th–6th.
| |
| | |
| This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials.
| |
| | |
| ]]
| |
| | |
| local function parse_vauthors_veditors (args, vparam, list_name)
| |
| local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
| |
| local v_name_table = {};
| |
| local v_link_table = {}; -- when name is wikilinked, targets go in this table
| |
| local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
| |
| local last, first, link, mask, suffix;
| |
| local corporate = false;
| |
| | |
| vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period)
| |
| v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas
| |
| | |
| for i, v_name in ipairs(v_name_table) do
| |
| first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
| |
| local accept_name;
| |
| v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name>
| |
| | |
| if accept_name then
| |
| last = v_name;
| |
| corporate = true; -- flag used in list_people()
| |
| elseif string.find(v_name, "%s") then
| |
| if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters;
| |
| add_vanc_error (cfg.err_msg_supl.punctuation, i);
| |
| end
| |
| local lastfirstTable = {}
| |
| lastfirstTable = mw.text.split(v_name, "%s+")
| |
| first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix
| |
| | |
| if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters
| |
| suffix = first; -- not initials so assume that whatever we got is a generational suffix
| |
| first = table.remove(lastfirstTable); -- get what should be the initials from the table
| |
| end
| |
| last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix
| |
| if not utilities.is_set (last) then
| |
| first = ''; -- unset
| |
| last = v_name; -- last empty because something wrong with first
| |
| add_vanc_error (cfg.err_msg_supl.name, i);
| |
| end
| |
| if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then
| |
| add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing
| |
| end
| |
| if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test
| |
| add_vanc_error (cfg.err_msg_supl.initials, i); -- matches a space between two initials
| |
| end
| |
| else
| |
| last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this?
| |
| end
| |
|
| |
| if utilities.is_set (first) then
| |
| if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else
| |
| add_vanc_error (cfg.err_msg_supl.initials, i); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials
| |
| end
| |
| is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit
| |
| if utilities.is_set (suffix) then
| |
| first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials
| |
| suffix = ''; -- unset so we don't add this suffix to all subsequent names
| |
| end
| |
| else
| |
| if not corporate then
| |
| is_good_vanc_name (last, '', nil, i);
| |
| end
| |
| end
| |
| | |
| link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i];
| |
| mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
| |
| names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list
| |
| end | | end |
| return names, etal; -- all done, return our list of names
| |
| end
| |
|
| |
|
| |
| --[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------
| |
|
| |
| Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
| |
| select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
| |
|
| |
| Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest;
| |
| |editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn)
| |
|
| |
| When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
| |
| test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better
| |
| way to do this, I just haven't discovered what that way is.
| |
|
| |
| Emits an error message when more than one xxxxor name source is provided.
| |
|
| |
| In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate.
| |
|
| |
| ]]
| |
|
| |
| local function select_author_editor_source (vxxxxors, xxxxors, args, list_name)
| |
| local lastfirst = false;
| |
| if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ...
| |
| utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors=
| |
| utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or
| |
| utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then
| |
| lastfirst = true;
| |
| end
| |
|
| |
| if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions
| |
| (utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or
| |
| (true == lastfirst and utilities.is_set (xxxxors)) then
| |
| local err_name;
| |
| if 'AuthorList' == list_name then -- figure out which name should be used in error message
| |
| err_name = 'author';
| |
| else
| |
| err_name = 'editor';
| |
| end
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters',
| |
| {err_name .. '-name-list parameters'}, true ) } ); -- add error message
| |
| end
| |
|
| |
| if true == lastfirst then return 1 end; -- return a number indicating which author name source to use
| |
| if utilities.is_set (vxxxxors) then return 2 end;
| |
| if utilities.is_set (xxxxors) then return 3 end;
| |
| return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
| |
| end
| |
|
| |
|
| |
| --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
| |
|
| |
| This function is used to validate a parameter's assigned value for those parameters that have only a limited number
| |
| of allowable values (yes, y, true, live, dead, etc.). When the parameter value has not been assigned a value (missing
| |
| or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one
| |
| of the list of allowed values returns the translated value; else, emits an error message and returns the value
| |
| specified by ret_val.
| |
|
| |
| ]]
| |
|
| |
| local function is_valid_parameter_value (value, name, possible, ret_val)
| |
| if not utilities.is_set (value) then
| |
| return ret_val; -- an empty parameter is ok
| |
| elseif utilities.in_array (value, possible) then
| |
| return cfg.keywords_xlate[value]; -- return translation of parameter keyword
| |
| else
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
| |
| return ret_val;
| |
| end
| |
| end
| |
|
| |
|
| |
| --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >----------------------------------------
| |
|
| |
| This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
| |
| when the last character is not a sepc character or when the last three characters are not sepc followed by two
| |
| closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
| |
| single space character.
| |
|
| |
| ]]
| |
|
| |
| local function terminate_name_list (name_list, sepc)
| |
| if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated
| |
| return name_list; -- just return the name list
| |
| elseif (string.sub (name_list, -1, -1) == sepc) or (string.sub (name_list, -3, -1) == sepc .. ']]') then -- if last name in list ends with sepc char
| |
| return name_list .. " "; -- don't add another
| |
| else
| |
| return name_list .. sepc .. ' '; -- otherwise terminate the name list
| |
| end
| |
| end
| |
|
| |
|
| |
| --[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------
| |
|
| |
| returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
| |
| or formatted issue, or an empty string if neither are set.
| |
|
| |
| ]]
| |
| | | |
| local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
| | for _, v in ipairs( possible ) do |
| if not utilities.is_set (volume) and not utilities.is_set (issue) then
| | if index ~= nil then |
| return ''; | | v = v:gsub( "#", index ); |
| end
| |
|
| |
| if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
| |
| if utilities.is_set (volume) and utilities.is_set (issue) then
| |
| return wrap_msg ('vol-no', {sepc, hyphen_to_dash (volume), issue}, lower); | |
| elseif utilities.is_set (volume) then
| |
| return wrap_msg ('vol', {sepc, hyphen_to_dash (volume)}, lower);
| |
| else
| |
| return wrap_msg ('issue', {sepc, issue}, lower);
| |
| end | | end |
| end
| | if is_set(args[v]) then |
| | | if value ~= nil and selected ~= v then |
| if 'podcast' == cite_class and utilities.is_set (issue) then
| | table.insert( error_list, v ); |
| return wrap_msg ('issue', {sepc, issue}, lower); | |
| end
| |
| | |
| local vol = ''; -- here for all cites except magazine
| |
|
| |
| if utilities.is_set (volume) then
| |
| if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals
| |
| vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face
| |
| elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters
| |
| vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)}); -- not bold | |
| utilities.add_prop_cat ('long_vol');
| |
| else -- four or less characters
| |
| vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold
| |
| end
| |
| end
| |
| if utilities.is_set (issue) then
| |
| return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
| |
| end
| |
| return vol;
| |
| end
| |
| | |
| | |
| --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
| |
| | |
| adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings.
| |
| The return order is:
| |
| page, pages, sheet, sheets
| |
| | |
| Singular has priority over plural when both are provided.
| |
| | |
| ]]
| |
| | |
| local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower)
| |
| if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
| |
| if utilities.is_set (sheet) then
| |
| if 'journal' == origin then
| |
| return '', '', wrap_msg ('j-sheet', sheet, lower), '';
| |
| else | | else |
| return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; | | value = args[v]; |
| end
| | selected = v; |
| elseif utilities.is_set (sheets) then
| |
| if 'journal' == origin then
| |
| return '', '', '', wrap_msg ('j-sheets', sheets, lower);
| |
| else
| |
| return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower); | |
| end | | end |
| end | | end |
| end | | end |
|
| |
| local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin);
| |
| | | |
| if utilities.is_set (page) then | | if #error_list > 0 then |
| if is_journal then | | local error_str = ""; |
| return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', '';
| | for _, k in ipairs( error_list ) do |
| elseif not nopp then
| | if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end |
| return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
| | error_str = error_str .. wrap( 'parameter', k ); |
| else
| |
| return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; | |
| end | | end |
| elseif utilities.is_set (pages) then
| | if #error_list > 1 then |
| if is_journal then | | error_str = error_str .. cfg.messages['parameter-final-separator']; |
| return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', ''; | |
| elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
| |
| return '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
| |
| elseif not nopp then
| |
| return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
| |
| else | | else |
| return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; | | error_str = error_str .. cfg.messages['parameter-pair-separator']; |
| end | | end |
| | error_str = error_str .. wrap( 'parameter', selected ); |
| | table.insert( z.message_tail, { seterror( error_condition, {error_str}, true ) } ); |
| end | | end |
| | | |
| return '', '', '', ''; -- return empty strings | | return value, selected; |
| end | | end |
|
| |
|
| | | -- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse |
| --[[--------------------------< I N S O U R C E _ L O C _ G E T >----------------------------------------------
| | -- the citation information. |
| | | function COinS(data) |
| returns one of the in-source locators: page, pages, or at.
| | if 'table' ~= type(data) or nil == next(data) then |
| | | return ''; |
| If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text
| |
| for use in COinS. This COinS thing is done because here we convert an interwiki-link to an 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, page_orig, pages, pages_orig, at)
| |
| local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?)
| |
| | |
| if utilities.is_set (page) then
| |
| if utilities.is_set (pages) or utilities.is_set (at) then
| |
| pages = ''; -- unset the others
| |
| at = '';
| |
| end
| |
| extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
| |
| | |
| ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page});
| |
| coins_pages = ws_label;
| |
| end
| |
| elseif utilities.is_set (pages) then | |
| if utilities.is_set (at) then
| |
| at = ''; -- unset
| |
| end
| |
| extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc.
| |
| | |
| ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages});
| |
| coins_pages = ws_label;
| |
| end
| |
| elseif utilities.is_set (at) then
| |
| ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at});
| |
| coins_pages = ws_label;
| |
| end
| |
| end | | end |
| | | |
| return page, pages, at, coins_pages; | | local ctx_ver = "Z39.88-2004"; |
| end
| |
| | |
| --[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------
| |
| | |
| add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value
| |
| | |
| ]]
| |
| | |
| local function is_unique_archive_url (archive, url, c_url, source, date) | |
| if utilities.is_set (archive) then
| |
| if archive == url or archive == c_url then
| |
| table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)}); -- add error message
| |
| return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url=
| |
| end
| |
| end
| |
| | |
| return archive, date;
| |
| end
| |
| | |
| | |
| --[=[-------------------------< A R C H I V E _ U R L _ C H E C K >--------------------------------------------
| |
| | |
| Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the
| |
| save snapshot URL or to calendar pages. When the archive URL is 'https://web.archive.org/save/' (or http://...)
| |
| archive.org saves a snapshot of the target page in the URL. That is something that Wikipedia should not allow
| |
| unwitting readers to do.
| |
| | |
| When the archive.org URL does not have a complete timestamp, archive.org chooses a snapshot according to its own
| |
| algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results.
| |
| | |
| This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and
| |
| |archive-date= and an error message when:
| |
| |archive-url= holds an archive.org save command URL
| |
| |archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the
| |
| correct place
| |
| otherwise returns |archive-url= and |archive-date=
| |
| | |
| There are two mostly compatible archive.org URLs:
| |
| //web.archive.org/<timestamp>... -- the old form
| |
| //web.archive.org/web/<timestamp>... -- the new form
| |
| | |
| The old form does not support or map to the new form when it contains a display flag. There are four identified flags
| |
| ('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore)
| |
| we don't check for these specific flags but we do check the form.
| |
| | |
| This function supports a preview mode. When the article is rendered in preview mode, this function may return a modified
| |
| archive URL:
| |
| for save command errors, return undated wildcard (/*/)
| |
| for timestamp errors when the timestamp has a wildcard, return the URL unmodified
| |
| for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/)
| |
| | |
| ]=]
| |
| | |
| local function archive_url_check (url, date)
| |
| local err_msg = ''; -- start with the error message empty
| |
| local path, timestamp, flag; -- portions of the archive.org URL
| |
| | | |
| if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
| | -- treat table strictly as an array with only set values. |
| return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
| | local OCinSoutput = setmetatable( {}, { |
| end | | __newindex = function(self, key, value) |
| | | if is_set(value) then |
| if url:match('//web%.archive%.org/save/') then -- if a save command URL, we don't want to allow saving of the target page
| | rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( removewikilink( value ) ) } ); |
| err_msg = cfg.err_msg_supl.save;
| |
| url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL | |
| elseif url:match('//liveweb%.archive%.org/') then
| |
| err_msg = cfg.err_msg_supl.liveweb;
| |
| else
| |
| path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation
| |
|
| |
| if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here
| |
| err_msg = cfg.err_msg_supl.timestamp;
| |
| if '*' ~= flag then
| |
| url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat)
| |
| end | | end |
| elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element
| |
| err_msg = cfg.err_msg_supl.path;
| |
| elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element)
| |
| err_msg = cfg.err_msg_supl.flag;
| |
| elseif utilities.is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element)
| |
| err_msg = cfg.err_msg_supl.flag;
| |
| else
| |
| return url, date; -- return ArchiveURL and ArchiveDate
| |
| end | | end |
| end | | }); |
| -- if here, something not right so
| | |
| table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } ); -- add error message and
| | if is_set(data.Chapter) then |
| if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then | | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; |
| return '', ''; -- return empty strings for ArchiveURL and ArchiveDate | | OCinSoutput["rft.genre"] = "bookitem"; |
| | OCinSoutput["rft.btitle"] = data.Chapter; |
| | OCinSoutput["rft.atitle"] = data.Title; |
| | elseif is_set(data.Periodical) then |
| | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; |
| | OCinSoutput["rft.genre"] = "article"; |
| | OCinSoutput["rft.jtitle"] = data.Periodical; |
| | OCinSoutput["rft.atitle"] = data.Title; |
| else | | else |
| return url, date; -- preview mode so return ArchiveURL and ArchiveDate | | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; |
| end
| | OCinSoutput["rft.genre"] = "book" |
| end
| | OCinSoutput["rft.btitle"] = data.Title; |
| | |
| | |
| --[[--------------------------< P L A C E _ C H E C K >--------------------------------------------------------
| |
| | |
| check |place=, |publication-place=, |location= to see if these params include digits. This function added because
| |
| many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that)
| |
| | |
| returns the original parameter value without modification; added maint cat when parameter value contains digits
| |
| | |
| ]] | |
| | |
| local function place_check (param_val)
| |
| if not utilities.is_set (param_val) then -- parameter empty or omitted
| |
| return param_val; -- return that empty state
| |
| end | | end |
| | | |
| if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value | | OCinSoutput["rft.place"] = data.PublicationPlace; |
| utilities.set_message ('maint_location'); -- yep, add maint cat | | OCinSoutput["rft.date"] = data.Date; |
| | OCinSoutput["rft.series"] = data.Series; |
| | OCinSoutput["rft.volume"] = data.Volume; |
| | OCinSoutput["rft.issue"] = data.Issue; |
| | OCinSoutput["rft.pages"] = data.Pages; |
| | OCinSoutput["rft.edition"] = data.Edition; |
| | OCinSoutput["rft.pub"] = data.PublisherName; |
| | |
| | for k, v in pairs( data.ID_list ) do |
| | local id, value = cfg.id_handlers[k].COinS; |
| | if k == 'ISBN' then value = cleanisbn( v ); else value = v; end |
| | if string.sub( id or "", 1, 4 ) == 'info' then |
| | OCinSoutput["rft_id"] = table.concat{ id, "/", v }; |
| | else |
| | OCinSoutput[ id ] = value; |
| | end |
| end | | end |
| | | |
| return param_val; -- and done | | local last, first; |
| end
| | for k, v in ipairs( data.Authors ) do |
| | | last, first = v.last, v.first; |
| | | if k == 1 then |
| --[[--------------------------< I S _ G E N E R I C _ T I T L E >----------------------------------------------
| | if is_set(last) then |
| | | OCinSoutput["rft.aulast"] = last; |
| compares |title= value against list of known generic title patterns. Returns true when pattern matches; nil else
| | end |
| | | if is_set(first) then |
| the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language
| | OCinSoutput["rft.aufirst"] = first; |
| Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in
| |
| index [1]. index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true)
| |
| or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so
| |
| that we don't run out of processing time on very large articles.
| |
| | |
| ]]
| |
| | |
| local function is_generic_title (title)
| |
| title = mw.ustring.lower(title); -- switch title to lower case
| |
| for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments
| |
| if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then | |
| return true; -- found English generic title so done | |
| elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title
| |
| if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script | |
| return true; -- found local generic title so done | |
| end | | end |
| end | | end |
| end
| | if is_set(last) and is_set(first) then |
| end
| | OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; |
| | | elseif is_set(last) then |
| | | OCinSoutput["rft.au"] = last; |
| --[[--------------------------< I S _ A R C H I V E D _ C O P Y >----------------------------------------------
| |
| | |
| compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else
| |
| | |
| ]]
| |
| | |
| local function is_archived_copy (title)
| |
| title = mw.ustring.lower(title); -- switch title to lower case
| |
| if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy'
| |
| return true;
| |
| elseif cfg.special_case_translation.archived_copy['local'] then
| |
| if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script
| |
| return true;
| |
| end | | end |
| end | | end |
| | |
| | OCinSoutput.rft_id = data.URL; |
| | OCinSoutput.rfr_id = table.concat{ "info:sid/", mw.site.server:match( "[^/]*$" ), ":", data.RawPage }; |
| | OCinSoutput = setmetatable( OCinSoutput, nil ); |
| | |
| | -- sort with version string always first, and combine. |
| | table.sort( OCinSoutput ); |
| | table.insert( OCinSoutput, 1, "ctx_ver=" .. ctx_ver ); -- such as "Z39.88-2004" |
| | return table.concat(OCinSoutput, "&"); |
| end | | end |
|
| |
|
| | | --[[ |
| --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ | | This is the main function doing the majority of the citation |
| | | formatting. |
| This is the main function doing the majority of the citation formatting. | |
| | |
| ]] | | ]] |
| | | function citation0( config, args) |
| local function citation0( config, args )
| |
| --[[ | | --[[ |
| Load Input Parameters | | Load Input Parameters |
| The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. | | The argument_wrapper facilitates the mapping of multiple |
| | aliases to single internal variable. |
| ]] | | ]] |
| local A = argument_wrapper ( args ); | | local A = argument_wrapper( args ); |
| | |
| local i | | local i |
| | | local PPrefix = A['PPrefix'] |
| | local PPPrefix = A['PPPrefix'] |
| | if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end |
| | |
| -- Pick out the relevant fields from the arguments. Different citation templates | | -- Pick out the relevant fields from the arguments. Different citation templates |
| -- define different field names for the same underlying things. | | -- define different field names for the same underlying things. |
| | local Authors = A['Authors']; |
| | local a = extractnames( args, 'AuthorList' ); |
|
| |
|
| local author_etal; | | local Coauthors = A['Coauthors']; |
| local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors=
| | local Others = A['Others']; |
| local Authors;
| | local Editors = A['Editors']; |
| local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], '');
| | local e = extractnames( args, 'EditorList' ); |
| local Collaboration = A['Collaboration']; | |
| | |
| do -- to limit scope of selected | |
| local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList');
| |
| if 1 == selected then
| |
| a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
| |
| elseif 2 == selected then
| |
| NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
| |
| a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
| |
| elseif 3 == selected then
| |
| Authors = A['Authors']; -- use content of |authors=
| |
| if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors=
| |
| utilities.set_message ('maint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO:
| |
| end
| |
| end
| |
| if utilities.is_set (Collaboration) then
| |
| author_etal = true; -- so that |display-authors=etal not required
| |
| end
| |
| end
| |
| | |
| local editor_etal;
| |
| local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
| |
| | |
| do -- to limit scope of selected | |
| local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn
| |
| if 1 == selected then
| |
| e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
| |
| elseif 2 == selected then
| |
| NameListStyle = 'vanc'; -- override whatever |name-list-style= might be
| |
| e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
| |
| end
| |
| end
| |
|
| |
| local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases
| |
| local Chapter_origin = A:ORIGIN ('Chapter');
| |
| local Contribution; -- because contribution is required for contributor(s)
| |
| if 'contribution' == Chapter_origin then
| |
| Contribution = Chapter; -- get the name of the contribution
| |
| end
| |
| local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
| |
|
| |
| if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites
| |
| c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
| |
|
| |
| if 0 < #c then
| |
| if not utilities.is_set (Contribution) then -- |contributor= requires |contribution=
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'contribution')}); -- add missing contribution error message
| |
| c = {}; -- blank the contributors' table; it is used as a flag later
| |
| end
| |
| if 0 == #a then -- |contributor= requires |author=
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'author')}); -- add missing author error message
| |
| c = {}; -- blank the contributors' table; it is used as a flag later
| |
| end
| |
| end
| |
| else -- if not a book cite
| |
| if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters?
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_ignored')}); -- add contributor ignored error message
| |
| end
| |
| Contribution = nil; -- unset
| |
| end
| |
|
| |
|
| | local Year = A['Year']; |
| | local PublicationDate = A['PublicationDate']; |
| | local OrigYear = A['OrigYear']; |
| | local Date = A['Date']; |
| | local LayDate = A['LayDate']; |
| | ------------------------------------------------- Get title data |
| local Title = A['Title']; | | local Title = A['Title']; |
| | local BookTitle = A['BookTitle']; |
| | local Conference = A['Conference']; |
| | local TransTitle = A['TransTitle']; |
| | local TitleNote = A['TitleNote']; |
| local TitleLink = A['TitleLink']; | | local TitleLink = A['TitleLink']; |
| | local Chapter = A['Chapter']; |
| | local ChapterLink = A['ChapterLink']; |
| | local TransChapter = A['TransChapter']; |
| | local TitleType = A['TitleType']; |
| | local Degree = A['Degree']; |
| | local Docket = A['Docket']; |
| | local ArchiveURL = A['ArchiveURL']; |
| | local URL = A['URL'] |
| | local URLorigin = A:ORIGIN('URL'); |
| | local ChapterURL = A['ChapterURL']; |
| | local ChapterURLorigin = A:ORIGIN('ChapterURL'); |
| | local ConferenceURL = A['ConferenceURL']; |
| | local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); |
| | local Periodical = A['Periodical']; |
|
| |
|
| local auto_select = ''; -- default is auto | | local Series = A['Series']; |
| local accept_link; | | local Volume = A['Volume']; |
| TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup | | local Issue = A['Issue']; |
| if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords | | local Position = ''; |
| auto_select = TitleLink; -- remember selection for later
| | local Page = A['Page']; |
| TitleLink = ''; -- treat as if |title-link= would have been empty
| | local Pages = hyphentodash( A['Pages'] ); |
| end
| | local At = A['At']; |
|
| |
|
| TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set | | local Edition = A['Edition']; |
| | local PublicationPlace = A['PublicationPlace'] |
| | local Place = A['Place']; |
| | |
| | local PublisherName = A['PublisherName']; |
| | local RegistrationRequired = A['RegistrationRequired']; |
| | local SubscriptionRequired = A['SubscriptionRequired']; |
| | local Via = A['Via']; |
| | local AccessDate = A['AccessDate']; |
| | local ArchiveDate = A['ArchiveDate']; |
| | local Agency = A['Agency']; |
| | local DeadURL = A['DeadURL'] |
| | local Language = A['Language']; |
| | local Format = A['Format']; |
| | local Ref = A['Ref']; |
| | local DoiBroken = A['DoiBroken']; |
| | local ID = A['ID']; |
| | local ASINTLD = A['ASINTLD']; |
| | local IgnoreISBN = A['IgnoreISBN']; |
| | local Embargo = A['Embargo']; |
|
| |
|
| local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used | | local ID_list = extractids( args ); |
| if 'map' == config.CitationClass and 'section' == Chapter_origin then | | --[[ Hide unfinished cite newsgroup code so that long delayed update can take place |
| Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}} | | -- special case for cite newsgroup which uses |id= for a usenet article or post id |
| Chapter = ''; -- unset for now; will be reset later from |map= if present | | -- |id= is not included in COinS so here we convert it to an ID that will be included in COinS |
| | if ('newsgroup' == config.CitationClass) and (is_set (ID)) then |
| | ID_list['USENETID']=ID; -- add this new 'id' to the list of IDs |
| | ID = ''; -- and unset |
| end | | end |
| | ]] |
| | local Quote = A['Quote']; |
| | local PostScript = A['PostScript']; |
|
| |
|
| local Periodical = A['Periodical']; | | local LayURL = A['LayURL']; |
| local Periodical_origin = ''; | | local LaySource = A['LaySource']; |
| if utilities.is_set (Periodical) then | | local Transcript = A['Transcript']; |
| Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
| | local TranscriptURL = A['TranscriptURL'] |
| local i;
| | local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); |
| Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated
| | local sepc = A['Separator']; |
| if i then -- non-zero when markup was stripped so emit an error message
| |
| table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {Periodical_origin}, true)});
| |
| end
| |
| end | |
|
| |
|
| if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} | | local LastAuthorAmp = A['LastAuthorAmp']; |
| if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error
| | local no_tracking_cats = A['NoTracking']; |
| table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )});
| |
| end
| |
|
| |
|
| Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}}
| | --these are used by cite interview |
| Periodical_origin = A:ORIGIN('MailingList');
| | local Callsign = A['Callsign']; |
| end | | local City = A['City']; |
| | local Cointerviewers = A['Cointerviewers']; -- deprecated |
| | local Interviewer = A['Interviewer']; -- deprecated |
| | local Program = A['Program']; |
|
| |
|
| local ScriptPeriodical = A['ScriptPeriodical']; | | --local variables that are not cs1 parameters |
| | local page_type; -- is this needed? Doesn't appear to be used anywhere; |
| | local use_lowercase = ( sepc ~= '.' ); |
| | local this_page = mw.title.getCurrentTitle(); --Also used for COinS and for language |
| | local anchor_year; -- used in the CITEREF identifier |
| | local COinS_date; -- used in the COinS metadata |
|
| |
|
| -- web and news not tested for now because of
| | -- Set postscript default. |
| -- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors?
| | if not is_set (PostScript) then -- if |postscript= has not been set (Postscript is nil which is the default for {{citation}}) and |
| if not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter | | if (config.CitationClass ~= "citation") then -- this template is not a citation template |
| -- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message
| | PostScript = '.'; -- must be a cite xxx template so set postscript to default (period) |
| local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message
| |
| if p[config.CitationClass] then | |
| table.insert( z.message_tail, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)}); | |
| end | | end |
| end | | else |
|
| | if PostScript:lower() == 'none' then -- if |postscript=none then |
| local Volume;
| | PostScript = ''; -- no postscript |
| local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical');
| |
| if 'citation' == config.CitationClass then
| |
| if utilities.is_set (Periodical) then
| |
| if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals'
| |
| Volume = A['Volume']; -- but does for all other 'periodicals'
| |
| end
| |
| elseif utilities.is_set (ScriptPeriodical) then
| |
| if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website=
| |
| Volume = A['Volume']; -- but does for all other 'periodicals'
| |
| end
| |
| else
| |
| Volume = A['Volume']; -- and does for non-'periodical' cites
| |
| end
| |
| elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings
| |
| Volume = A['Volume'];
| |
| end
| |
| extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v');
| |
| | |
| local Issue;
| |
| if 'citation' == config.CitationClass then
| |
| if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals'
| |
| utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals' | |
| Issue = hyphen_to_dash (A['Issue']);
| |
| end
| |
| elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table
| |
| if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then
| |
| Issue = hyphen_to_dash (A['Issue']);
| |
| end | | end |
| end | | end |
| extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i');
| |
|
| |
|
| local Page;
| | --check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories. |
| local Pages;
| | if not is_set(no_tracking_cats) then -- ignore if we are already not going to categorize this page |
| local At;
| | for k, v in pairs( cfg.uncategorized_namespaces ) do -- otherwise, spin through the list of namespaces we don't include in error categories |
| if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then | | if this_page.nsText == v then -- if we find one |
| Page = A['Page']; | | no_tracking_cats = "true"; -- set no_tracking_cats |
| Pages = hyphen_to_dash (A['Pages']);
| | break; -- and we're done |
| At = A['At'];
| | end |
| end
| |
| | |
| local Edition = A['Edition'];
| |
| local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace'));
| |
| local Place = place_check (A['Place'], A:ORIGIN('Place'));
| |
|
| |
| local PublisherName = A['PublisherName'];
| |
| local PublisherName_origin = A:ORIGIN('PublisherName');
| |
| if utilities.is_set (PublisherName) then
| |
| local i = 0;
| |
| PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized
| |
| if i then -- non-zero when markup was stripped so emit an error message
| |
| table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)}); | |
| end | | end |
| end | | end |
|
| |
|
| local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup?
| | -- check for extra |page=, |pages= or |at= parameters. |
| local Newsgroup_origin = A:ORIGIN('Newsgroup');
| | if is_set(Page) then |
| | | if is_set(Pages) or is_set(At) then |
| if 'newsgroup' == config.CitationClass then
| | Page = Page .. " " .. seterror('extra_pages'); -- add error message |
| if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup
| | Pages = ''; -- unset the others |
| local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true);
| | At = ''; |
| if utilities.is_set (error_text) then
| |
| table.insert( z.message_tail, {error_text, error_state} );
| |
| end
| |
| end
| |
| | |
| PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS
| |
| end
| |
| | |
| local URL = A['URL']
| |
| local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil);
| |
|
| |
| if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then | |
| UrlAccess = nil; | |
| table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } );
| |
| end
| |
|
| |
| local ChapterURL = A['ChapterURL'];
| |
| local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil);
| |
| if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then
| |
| ChapterUrlAccess = nil;
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } );
| |
| end
| |
| | |
| local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil);
| |
| if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then
| |
| MapUrlAccess = nil;
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'map-url'}, true ) } );
| |
| end
| |
| | |
| local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language
| |
| local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil);
| |
| | |
| -- 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 utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page
| |
| if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then
| |
| no_tracking_cats = "true"; -- set no_tracking_cats | |
| end | | end |
| for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns
| | elseif is_set(Pages) then |
| if this_page.text:match (v) then -- test page name against each pattern
| | if is_set(At) then |
| no_tracking_cats = "true"; -- set no_tracking_cats
| | Pages = Pages .. " " .. seterror('extra_pages'); -- add error messages |
| break; -- bail out if one is found
| | At = ''; -- unset |
| end
| |
| end | | end |
| end | | end |
| -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it)
| |
| utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_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, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At);
| |
| | |
| local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil);
| |
|
| |
|
| if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different
| | -- both |publication-place= and |place= (|location=) allowed if different |
| utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together
| | if not is_set(PublicationPlace) and is_set(Place) then |
| if PublicationPlace == Place then
| | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
| Place = ''; -- unset; don't need both if they are the same
| |
| end
| |
| elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ...
| |
| PublicationPlace = Place; -- promote |place= (|location=) to |publication-place | |
| end | | end |
|
| |
| if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
| |
|
| |
| local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL
| |
| local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
| |
| local ScriptChapter = A['ScriptChapter'];
| |
| local ScriptChapter_origin = A:ORIGIN ('ScriptChapter');
| |
| local Format = A['Format'];
| |
| local ChapterFormat = A['ChapterFormat'];
| |
| local TransChapter = A['TransChapter'];
| |
| local TransChapter_origin = A:ORIGIN ('TransChapter');
| |
| local TransTitle = A['TransTitle'];
| |
| local ScriptTitle = A['ScriptTitle'];
| |
|
| |
| --[[
| |
| Parameter remapping for cite encyclopedia:
| |
| When the citation has these parameters:
| |
| |encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title=
| |
| |encyclopedia= and |article= then map |encyclopedia= to |title=
| |
|
| |
| |trans-title= maps to |trans-chapter= when |title= is re-mapped
| |
| |url= maps to |chapter-url= when |title= is remapped
| |
| | | |
| All other combinations of |encyclopedia=, |title=, and |article= are not modified | | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
| | | |
| ]] | | --[[ |
| | Parameter remapping for cite encyclopedia: |
| | When the citation has these parameters: |
| | |encyclopedia and |title then map |title to |article and |encyclopedia to |title |
| | |encyclopedia and |article then map |encyclopedia to |title |
| | |encyclopedia then map |encyclopedia to |title |
|
| |
|
| local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS | | |trans_title maps to |trans_chapter when |title is re-mapped |
|
| |
|
| if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}}
| | All other combinations of |encyclopedia, |title, and |article are not modified |
| if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then
| | ]] |
| table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)});
| | if ( config.CitationClass == "encyclopaedia" ) then |
| Encyclopedia = nil; -- unset because not supported by this template
| | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set |
| end
| | if is_set(Title) then |
| end
| | if not is_set(Chapter) then |
| | | Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
| if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then | |
| if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error | |
| table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )});
| |
| end
| |
| | |
| if utilities.is_set (Encyclopedia) then
| |
| Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia
| |
| Periodical_origin = A:ORIGIN ('Encyclopedia');
| |
| end
| |
| | |
| if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set
| |
| if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then | |
| if not utilities.is_set (Chapter) then | |
| Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title= | |
| ScriptChapter = ScriptTitle;
| |
| ScriptChapter_origin = A:ORIGIN('ScriptTitle')
| |
| TransChapter = TransTitle; | | TransChapter = TransTitle; |
| ChapterURL = URL;
| |
| ChapterURL_origin = URL_origin;
| |
|
| |
| ChapterUrlAccess = UrlAccess;
| |
|
| |
| if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then
| |
| Chapter = utilities.make_wikilink (TitleLink, Chapter);
| |
| end
| |
| Title = Periodical; | | Title = Periodical; |
| ChapterFormat = Format;
| | Periodical = ''; -- redundant so unset |
| Periodical = ''; -- redundant so unset | | TransTitle = ''; -- redundant so unset |
| TransTitle = ''; | |
| URL = '';
| |
| Format = '';
| |
| TitleLink = '';
| |
| ScriptTitle = '';
| |
| end | | end |
| elseif utilities.is_set (Chapter) then -- |title= not set | | else -- |title not set |
| Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= | | Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title |
| Periodical = ''; -- redundant so unset | | Periodical = ''; -- redundant so unset |
| end | | end |
| end | | end |
| end | | end |
|
| |
|
| -- special case for cite techreport.
| | --special cases for citation. |
| local ID = A['ID'];
| | if (config.CitationClass == "citation") then -- for citation templates |
| if (config.CitationClass == "techreport") then -- special case for cite techreport | | if not is_set (Ref) then -- if |ref= is not set |
| if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' | | Ref = "harv"; -- set default |ref=harv |
| if not utilities.is_set (ID) then -- can we use ID for the "number"?
| |
| ID = A['Number']; -- yes, use it
| |
| else -- ID has a value so emit error message
| |
| table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )});
| |
| end
| |
| end
| |
| end
| |
| | |
| -- Account for the oddity that is {{cite conference}}, before generation of COinS data.
| |
| local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode
| |
| local Conference = A['Conference'];
| |
| local BookTitle = A['BookTitle'];
| |
| local TransTitle_origin = A:ORIGIN ('TransTitle');
| |
| if 'conference' == config.CitationClass then
| |
| if utilities.is_set (BookTitle) then
| |
| Chapter = Title;
| |
| Chapter_origin = 'title';
| |
| -- ChapterLink = TitleLink; -- |chapter-link= is deprecated
| |
| ChapterURL = URL; | |
| ChapterUrlAccess = UrlAccess;
| |
| ChapterURL_origin = URL_origin;
| |
| URL_origin = '';
| |
| ChapterFormat = Format;
| |
| TransChapter = TransTitle;
| |
| TransChapter_origin = TransTitle_origin;
| |
| Title = BookTitle;
| |
| Format = '';
| |
| -- TitleLink = '';
| |
| TransTitle = '';
| |
| URL = '';
| |
| end | | end |
| elseif 'speech' ~= config.CitationClass then
| | if not is_set (sepc) then -- if |separator= is not set |
| Conference = ''; -- not cite conference or cite speech so make sure this is empty string | | sepc = ','; -- set citation separator to its default (comma) |
| end
| |
|
| |
| -- CS1/2 mode
| |
| local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], '');
| |
| -- separator character and postscript
| |
| local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass);
| |
| -- controls capitalization of certain static text
| |
| local use_lowercase = ( sepc == ',' );
| |
|
| |
| -- cite map oddities
| |
| local Cartography = "";
| |
| local Scale = "";
| |
| local Sheet = A['Sheet'] or '';
| |
| local Sheets = A['Sheets'] or '';
| |
| if config.CitationClass == "map" then
| |
| if utilities.is_set (Chapter) then
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message
| |
| end | | end |
| Chapter = A['Map'];
| | else -- not a citation template |
| Chapter_origin = A:ORIGIN('Map');
| | if not is_set (sepc) then -- if |separator= has not been set |
| ChapterURL = A['MapURL'];
| | sepc = '.'; -- set cite xxx separator to its default (period) |
| ChapterURL_origin = A:ORIGIN('MapURL');
| |
| TransChapter = A['TransMap'];
| |
| ScriptChapter = A['ScriptMap']
| |
| ScriptChapter_origin = A:ORIGIN('ScriptMap')
| |
| | |
| ChapterUrlAccess = MapUrlAccess;
| |
| ChapterFormat = A['MapFormat'];
| |
| | |
| Cartography = A['Cartography'];
| |
| if utilities.is_set ( Cartography ) then | |
| Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); | |
| end
| |
| Scale = A['Scale'];
| |
| if utilities.is_set ( Scale ) then
| |
| Scale = sepc .. " " .. Scale;
| |
| end | | end |
| end | | end |
|
| |
|
| -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data.
| | -- check for special case where |separator=none |
| local Series = A['Series'];
| | if 'none' == sepc:lower() then -- if |separator=none |
| if 'episode' == config.CitationClass or 'serial' == config.CitationClass then | | sepc = ''; -- then set it to an empty string |
| local SeriesLink = A['SeriesLink'];
| | end |
| | |
| SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set
| |
| | |
| local Network = A['Network']; | |
| local Station = A['Station'];
| |
| local s, n = {}, {};
| |
| -- do common parameters first
| |
| if utilities.is_set (Network) then table.insert(n, Network); end
| |
| if utilities.is_set (Station) then table.insert(n, Station); end
| |
| ID = table.concat(n, sepc .. ' ');
| |
|
| |
| if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
| |
| local Season = A['Season'];
| |
| local SeriesNumber = A['SeriesNumber'];
| |
| | |
| if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message
| |
| SeriesNumber = ''; -- unset; prefer |season= over |seriesno=
| |
| end
| |
| -- assemble a table of parts concatenated later into Series
| |
| if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end
| |
| if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end
| |
| if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end
| |
| Issue = ''; -- unset because this is not a unique parameter
| |
|
| |
| Chapter = Title; -- promote title parameters to chapter
| |
| ScriptChapter = ScriptTitle;
| |
| ScriptChapter_origin = A:ORIGIN('ScriptTitle');
| |
| ChapterLink = TitleLink; -- alias |episode-link=
| |
| TransChapter = TransTitle;
| |
| ChapterURL = URL;
| |
| ChapterUrlAccess = UrlAccess;
| |
| ChapterURL_origin = URL_origin;
| |
|
| |
| Title = Series; -- promote series to title
| |
| TitleLink = SeriesLink;
| |
| Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number
| |
|
| |
|
| if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL
| | -- Special case for cite techreport. |
| Chapter = utilities.make_wikilink (ChapterLink, Chapter);
| | if (config.CitationClass == "techreport") then -- special case for cite techreport |
| elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode;
| | if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue' |
| Series = utilities.make_wikilink (ChapterLink, Series);
| | if not is_set(ID) then -- can we use ID for the "number"? |
| end
| | ID = Issue; -- yes, use it |
| URL = ''; -- unset
| | Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata |
| TransTitle = '';
| | else -- can't use ID so emit error message |
| ScriptTitle = '';
| | ID = ID .. " " .. seterror('redundant_parameters', '<code>|id=</code> and <code>|number=</code>'); |
|
| |
| else -- now oddities that are cite serial
| |
| Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
| |
| Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? | |
| if utilities.is_set (Series) and utilities.is_set (SeriesLink) then
| |
| Series = utilities.make_wikilink (SeriesLink, Series);
| |
| end | | end |
| Series = utilities.wrap_style ('italic-title', Series); -- series is italicized
| |
| end | | end |
| end | | end |
| -- end of {{cite episode}} stuff
| |
|
| |
|
| -- handle type parameter for those CS1 citations that have default values
| | -- special case for cite interview |
| local TitleType = A['TitleType'];
| | if (config.CitationClass == "interview") then |
| local Degree = A['Degree'];
| | if is_set(Program) then |
| if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then | | ID = ' ' .. Program; |
| TitleType = set_titletype (config.CitationClass, TitleType);
| |
| if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis | |
| TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower(); | |
| end | | end |
| end
| | if is_set(Callsign) then |
| | | if is_set(ID) then |
| if utilities.is_set (TitleType) then -- if type parameter is specified
| | ID = ID .. sepc .. ' ' .. Callsign; |
| TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses
| | else |
| -- TODO: Hack on TitleType to fix bunched parentheses problem
| | ID = ' ' .. Callsign; |
| end
| | end |
| | |
| -- legacy: promote PublicationDate to Date if neither Date nor Year are set.
| |
| local Date = A['Date'];
| |
| local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging
| |
| local PublicationDate = A['PublicationDate'];
| |
| local Year = A['Year'];
| |
| | |
| if not utilities.is_set (Date) then
| |
| Date = Year; -- promote Year to Date
| |
| Year = nil; -- make nil so Year as empty string isn't used for CITEREF
| |
| if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set
| |
| 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 | | end |
| else
| | if is_set(City) then |
| Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging | | if is_set(ID) then |
| end
| | ID = ID .. sepc .. ' ' .. City; |
| | | else |
| if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation
| | ID = ' ' .. City; |
| | | end |
| --[[
| |
| Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
| |
| we get the date used in the metadata.
| |
|
| |
| Date validation supporting code is in Module:Citation/CS1/Date_validation
| |
| ]]
| |
| | |
| local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], '');
| |
| if not utilities.is_set (DF) then
| |
| DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template
| |
| end
| |
| | |
| local ArchiveURL;
| |
| local ArchiveDate;
| |
| local ArchiveFormat = A['ArchiveFormat'];
| |
| | |
| ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate'])
| |
| ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url');
| |
|
| |
| ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL
| |
| | |
|
| |
| local AccessDate = A['AccessDate'];
| |
| local LayDate = A['LayDate'];
| |
| local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification
| |
| local DoiBroken = A['DoiBroken'];
| |
| local Embargo = A['Embargo'];
| |
| local anchor_year; -- used in the CITEREF identifier
| |
| do -- create defined block to contain local variables error_message, date_parameters_list, mismatch
| |
| local error_message = '';
| |
| -- AirDate has been promoted to Date so not necessary to check it
| |
| local date_parameters_list = {
| |
| ['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')}, | |
| ['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')},
| |
| ['date'] = {val = Date, name = Date_origin},
| |
| ['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')},
| |
| ['pmc-embargo-date'] = {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')},
| |
| };
| |
| | |
| local error_list = {};
| |
| anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list);
| |
| | |
| -- start temporary Julian / Gregorian calendar uncertainty categorization
| |
| if COinS_date.inter_cal_cat then
| |
| utilities.add_prop_cat ('jul_greg_uncertainty'); | |
| end | | end |
| -- end temporary Julian / Gregorian calendar uncertainty categorization
| |
|
| |
|
| if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed; | | if is_set(Interviewer) then |
| validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list);
| | if is_set(TitleType) then |
| end
| | Others = ' ' .. TitleType .. ' with ' .. Interviewer; |
|
| | TitleType = ''; |
| if 0 == #error_list then -- error free dates only; 0 when error_list is empty
| | else |
| local modified = false; -- flag
| | Others = ' ' .. 'Interview with ' .. Interviewer; |
|
| |
| if validation.edtf_transform (date_parameters_list) then -- edtf dates to MOS compliant format
| |
| modified = true; | |
| end | |
| | |
| if utilities.is_set (DF) then -- if we need to reformat dates
| |
| modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate | |
| end
| |
| | |
| if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate
| |
| modified = true;
| |
| utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category
| |
| end | | end |
| | | if is_set(Cointerviewers) then |
| -- for those wikis that can and want to have English date names translated to the local language,
| | Others = Others .. sepc .. ' ' .. Cointerviewers; |
| -- uncomment the next three lines. Not supported by en.wiki (for obvious reasons)
| |
| -- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates)
| |
| -- if validation.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'].val; -- overwrite date holding parameters with modified values | |
| ArchiveDate = date_parameters_list['archive-date'].val;
| |
| Date = date_parameters_list['date'].val;
| |
| DoiBroken = date_parameters_list['doi-broken-date'].val;
| |
| LayDate = date_parameters_list['lay-date'].val;
| |
| PublicationDate = date_parameters_list['publication-date'].val;
| |
| end | | end |
| else | | else |
| table.insert (z.message_tail, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)}); -- add this error message | | Others = '(Interview)'; |
| end | | end |
| end -- end of do | | end |
|
| |
|
| local ID_list = {}; -- sequence table of rendered identifiers
| | --Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set |
| local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key
| | if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
| local Class = A['Class']; -- arxiv class identifier | | if not is_embargoed(Embargo) then |
|
| | URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed |
| local ID_support = {
| | URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title= |
| {A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')},
| |
| {DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')},
| |
| {Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')}, | |
| }
| |
| | |
| ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support);
| |
| | |
| -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data.
| |
| if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then
| |
| if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates
| |
| table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- add error message | |
| end | | end |
| | end |
|
| |
|
| Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass];
| | -- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
| | --TODO: if this is only for {{cite conference}}, shouldn't we be checking? (if config.CitationClass=='conference' then ...) |
| | if is_set(BookTitle) then |
| | Chapter = Title; |
| | ChapterLink = TitleLink; |
| | TransChapter = TransTitle; |
| | Title = BookTitle; |
| | TitleLink = ''; |
| | TransTitle = ''; |
| end | | end |
|
| |
|
| -- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free
| | -- Account for the oddity that is {{cite episode}}, before generation of COinS data. |
| | --[[ -- {{cite episode}} is not currently supported by this module |
| | if config.CitationClass == "episode" then |
| | local AirDate = A['AirDate']; |
| | local SeriesLink = A['SeriesLink']; |
| | local Season = A['Season']; |
| | local SeriesNumber = A['SeriesNumber']; |
| | local Network = A['Network']; |
| | local Station = A['Station']; |
| | local s, n = {}, {}; |
| | local Sep = (first_set(A["SeriesSeparator"], A["Separator"]) or "") .. " "; |
| | |
| | if is_set(Issue) then table.insert(s, cfg.messages["episode"] .. " " .. Issue); Issue = ''; end |
| | if is_set(Season) then table.insert(s, cfg.messages["season"] .. " " .. Season); end |
| | if is_set(SeriesNumber) then table.insert(s, cfg.messages["series"] .. " " .. SeriesNumber); end |
| | if is_set(Network) then table.insert(n, Network); end |
| | if is_set(Station) then table.insert(n, Station); end |
| | |
| | Date = Date or AirDate; |
| | Chapter = Title; |
| | ChapterLink = TitleLink; |
| | TransChapter = TransTitle; |
| | Title = Series; |
| | TitleLink = SeriesLink; |
| | TransTitle = ''; |
| | |
| | Series = table.concat(s, Sep); |
| | ID = table.concat(n, Sep); |
| | end |
| | -- end of {{cite episode}} stuff]] |
|
| |
|
| if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead
| | -- legacy: promote concatenation of |day=, |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set. |
| if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled | | if not is_set(Date) then |
| if identifiers.auto_link_urls[auto_select] then -- manual selection
| | Date = Year; -- promote Year to Date |
| URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link
| | Year = nil; -- make nil so Year as empty string isn't used for CITEREF |
| URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title=
| | if is_set(Date) then |
| elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC | | local Month = A['Month']; |
| URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed
| | if is_set(Month) then |
| URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title= | | Date = Month .. " " .. Date; |
| elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI
| | local Day = A['Day'] |
| URL = identifiers.auto_link_urls['doi']; | | if is_set(Day) then Date = Day .. " " .. Date end |
| URL_origin = cfg.id_handlers['DOI'].parameters[1]; | |
| end | | end |
| end
| | elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set |
| | | Date = PublicationDate; -- promote PublicationDate to Date |
| if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url= | | PublicationDate = ''; -- unset, no longer needed |
| table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message | |
| AccessDate = ''; -- unset | |
| end | | end |
| end | | end |
|
| |
|
| -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. | | if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation |
| -- Test if citation has no title
| |
| if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } );
| |
| end
| |
|
| |
|
| if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and
| |
| utilities.in_array (config.CitationClass, {'journal', 'citation'}) and
| |
| (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and
| |
| ('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites
| |
| Title = ''; -- set title to empty string
| |
| utilities.set_message ('maint_untitled'); -- add maint cat
| |
| end
| |
|
| |
|
| check_for_url ({ -- add error message when any of these parameters hold a URL
| | --[[ |
| ['title'] = Title,
| | Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where |
| [A:ORIGIN('Chapter')] = Chapter,
| | we get the date used in the metadata. |
| [Periodical_origin] = Periodical,
| |
| [PublisherName_origin] = PublisherName
| |
| });
| |
|
| |
|
| -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
| | Date validation supporting code is in Module:Citation/CS1/Date_validation |
| -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
| | ]] |
| -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title | | anchor_year, COinS_date, error_message = dates({['accessdate']=AccessDate, ['airdate']=AirDate, ['archivedate']=ArchiveDate, ['date']=Date, ['doi_brokendate']=DoiBroken, |
| -- is the article title, and Chapter is a section within the article. So, we remap
| | ['embargo']=Embargo, ['laydate']=LayDate, ['publicationdate']=PublicationDate, ['year']=Year}); |
|
| | if is_set(error_message) then |
| local coins_chapter = Chapter; -- default assuming that remapping not required
| | table.insert( z.message_tail, { seterror( 'bad_date', {error_message}, true ) } ); -- add this error message |
| local coins_title = Title; -- et tu
| |
| if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then
| |
| if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then | |
| coins_chapter = Title; -- remap
| |
| coins_title = Periodical;
| |
| end
| |
| end | | end |
| local coins_author = a; -- default for coins rft.au
| |
| if 0 < #c then -- but if contributor list
| |
| coins_author = c; -- use that instead
| |
| end
| |
|
| |
| local QuotePage = A['QuotePage'];
| |
| local QuotePages = hyphen_to_dash (A['QuotePages']);
| |
|
| |
|
| -- this is the function call to COinS()
| | -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. |
| local OCinSoutput = metadata.COinS({ | | |
| ['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata | | -- COinS metadata (see <http://ocoins.info/>) for |
| ['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS | | -- automated parsing of citation information. |
| ['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wiki-markup
| | local OCinSoutput = COinS{ |
| ['Degree'] = Degree; -- cite thesis only | | ['Periodical'] = Periodical, |
| ['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wiki-markup
| | ['Chapter'] = Chapter, |
| | ['Title'] = Title, |
| ['PublicationPlace'] = PublicationPlace, | | ['PublicationPlace'] = PublicationPlace, |
| ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; | | ['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? |
| ['Season'] = COinS_date.rftssn,
| |
| ['Quarter'] = COinS_date.rftquarter,
| |
| ['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit?
| |
| ['Series'] = Series, | | ['Series'] = Series, |
| ['Volume'] = Volume, | | ['Volume'] = Volume, |
| ['Issue'] = Issue, | | ['Issue'] = Issue, |
| ['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links | | ['Pages'] = get_coins_pages (first_set(Page, Pages, At)), -- pages stripped of external links |
| ['Edition'] = Edition, | | ['Edition'] = Edition, |
| ['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName | | ['PublisherName'] = PublisherName, |
| ['URL'] = first_set ({ChapterURL, URL}, 2), | | ['URL'] = first_set( URL, ChapterURL ), |
| ['Authors'] = coins_author, | | ['Authors'] = a, |
| ['ID_list'] = ID_list_coins, | | ['ID_list'] = ID_list, |
| ['RawPage'] = this_page.prefixedText, | | ['RawPage'] = this_page.prefixedText, |
| }, config.CitationClass); | | }; |
|
| |
|
| -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data. | | if is_set(Periodical) and not is_set(Chapter) and is_set(Title) then |
| if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed
| | Chapter = Title; |
| Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal | | ChapterLink = TitleLink; |
| | TransChapter = TransTitle; |
| | Title = ''; |
| | TitleLink = ''; |
| | TransTitle = ''; |
| end | | 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 |
| | if 'newsgroup' == config.CitationClass then |
| | if is_set (PublisherName) then |
| | PublisherName = '[Newsgroup]: ' .. externallink( 'news:' .. PublisherName, PublisherName ); |
| | end |
| | end |
| | ]] |
|
| |
|
| -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
| |
| if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then
| |
| PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil ));
| |
| end
| |
|
| |
|
| local Editors;
| |
| local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
| |
| local Contributors; -- assembled contributors name list
| |
| local contributor_etal;
| |
| local Translators; -- assembled translators name list
| |
| local translator_etal;
| |
| local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs
| |
| t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
| |
| local Interviewers;
| |
| local interviewers_list = {};
| |
| interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters
| |
| local interviewer_etal;
| |
|
| |
| -- Now perform various field substitutions. | | -- Now perform various field substitutions. |
| -- We also add leading spaces and surrounding markup and punctuation to the | | -- We also add leading spaces and surrounding markup and punctuation to the |
| -- various parts of the citation, but only when they are non-nil. | | -- various parts of the citation, but only when they are non-nil. |
| do | | if not is_set(Authors) then |
| local last_first_list; | | local Maximum = tonumber( A['DisplayAuthors'] ); |
| | |
| | -- Preserve old-style implicit et al. |
| | if not is_set(Maximum) and #a == 9 then |
| | Maximum = 8; |
| | table.insert( z.message_tail, { seterror('implict_etal_author', {}, true ) } ); |
| | elseif not is_set(Maximum) then |
| | Maximum = #a + 1; |
| | end |
| | |
| local control = { | | local control = { |
| format = NameListStyle, -- empty string or 'vanc' | | sep = A["AuthorSeparator"] .. " ", |
| maximum = nil, -- as if display-authors or display-editors not set | | namesep = (first_set(A["AuthorNameSeparator"], A["NameSeparator"]) or "") .. " ", |
| mode = Mode | | format = A["AuthorFormat"], |
| | maximum = Maximum, |
| | lastauthoramp = LastAuthorAmp |
| }; | | }; |
| | |
| | -- If the coauthor field is also used, prevent ampersand and et al. formatting. |
| | if is_set(Coauthors) then |
| | control.lastauthoramp = nil; |
| | control.maximum = #a + 1; |
| | end |
| | |
| | Authors = listpeople(control, a) |
| | end |
|
| |
|
| do -- do editor name list first because the now unsupported coauthors used to modify control table
| | if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified |
| control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors'));
| | table.insert( z.message_tail, { seterror('coauthors_missing_author', {}, true) } ); -- emit error message |
| Editors, EditorCount = list_people (control, e, editor_etal);
| | end |
|
| |
|
| if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then
| | local EditorCount |
| EditorCount = 2; -- spoof to display (eds.) annotation
| | if not is_set(Editors) then |
| end
| | local Maximum = tonumber( A['DisplayEditors'] ); |
| end | | -- Preserve old-style implicit et al. |
| do -- now do interviewers
| | if not is_set(Maximum) and #e == 4 then |
| control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal, A:ORIGIN ('DisplayInterviewers'));
| | Maximum = 3; |
| Interviewers = list_people (control, interviewers_list, interviewer_etal); | | table.insert( z.message_tail, { seterror('implict_etal_editor', {}, true) } ); |
| end
| | elseif not is_set(Maximum) then |
| do -- now do translators
| | Maximum = #e + 1; |
| control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators')); | |
| Translators = list_people (control, t, translator_etal); | |
| end | | end |
| do -- now do contributors
| |
| control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors'));
| |
| Contributors = list_people (control, c, contributor_etal);
| |
| end
| |
| do -- now do authors
| |
| control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors'));
| |
|
| |
|
| last_first_list = list_people (control, a, author_etal); | | local control = { |
| | | sep = A["EditorSeparator"] .. " ", |
| if utilities.is_set (Authors) then | | namesep = (first_set(A["EditorNameSeparator"], A["NameSeparator"]) or "") .. " ", |
| Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al.
| | format = A['EditorFormat'], |
| if author_etal then
| | maximum = Maximum, |
| Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter
| | lastauthoramp = LastAuthorAmp |
| end
| | }; |
| else | |
| Authors = last_first_list; -- either an author name list or an empty string
| |
| end | |
| end -- end of do
| |
|
| |
| if utilities.is_set (Authors) and utilities.is_set (Collaboration) then | |
| Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al.
| |
| end
| |
|
| |
|
| | Editors, EditorCount = listpeople(control, e); |
| | else |
| | EditorCount = 1; |
| end | | end |
|
| |
|
| local ConferenceFormat = A['ConferenceFormat']; | | local Cartography = ""; |
| local ConferenceURL = A['ConferenceURL']; | | local Scale = ""; |
| ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); | | if config.CitationClass == "map" then |
| Format = style_format (Format, URL, 'format', 'url');
| | if not is_set( Authors ) and is_set( PublisherName ) then |
| | | Authors = PublisherName; |
| -- special case for chapter format so no error message or cat when chapter not supported
| | PublisherName = ""; |
| if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or
| | end |
| ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then | | Cartography = A['Cartography']; |
| ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); | | if is_set( Cartography ) then |
| | Cartography = sepc .. " " .. wrap( 'cartography', Cartography, use_lowercase ); |
| | end |
| | Scale = A['Scale']; |
| | if is_set( Scale ) then |
| | Scale = sepc .. " " .. Scale; |
| | end |
| end | | end |
| | | |
| if not utilities.is_set (URL) then | | if not is_set(URL) and |
| if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist | | not is_set(ChapterURL) and |
| ('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website= | | not is_set(ArchiveURL) and |
| table.insert( z.message_tail, { utilities.set_message ( 'err_cite_web_url', {}, true ) } );
| | not is_set(ConferenceURL) and |
| | not is_set(TranscriptURL) then |
| | |
| | -- Test if cite web or cite podcast |url= is missing or empty |
| | if inArray(config.CitationClass, {"web","podcast"}) then |
| | table.insert( z.message_tail, { seterror( 'cite_web_url', {}, true ) } ); |
| end | | end |
| | | |
| -- do we have |accessdate= without either |url= or |chapter-url=? | | -- Test if accessdate is given without giving a URL |
| if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set; | | if is_set(AccessDate) then |
| table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); | | table.insert( z.message_tail, { seterror( 'accessdate_missing_url', {}, true ) } ); |
| AccessDate = ''; | | AccessDate = ''; |
| | end |
| | |
| | -- Test if format is given without giving a URL |
| | if is_set(Format) then |
| | Format = Format .. seterror( 'format_missing_url' ); |
| end | | end |
| end | | end |
| | | |
| local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); | | -- Test if citation has no title |
| local OriginalURL | | if not is_set(Chapter) and |
| local OriginalURL_origin
| | not is_set(Title) and |
| local OriginalFormat
| | not is_set(Periodical) and |
| local OriginalAccess;
| | not is_set(Conference) and |
| UrlStatus = UrlStatus:lower(); -- used later when assembling archived text
| | not is_set(TransTitle) and |
| if utilities.is_set ( ArchiveURL ) then | | not is_set(TransChapter) then |
| if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it | | table.insert( z.message_tail, { seterror( 'citation_missing_title', {}, true ) } ); |
| OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
| |
| OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages
| |
| OriginalFormat = ChapterFormat; -- and original |chapter-format=
| |
| | |
| if 'live' ~= UrlStatus then
| |
| ChapterURL = ArchiveURL -- swap-in the archive's URL
| |
| ChapterURL_origin = 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 utilities.is_set (URL) then | |
| OriginalURL = URL; -- save copy of original source URL
| |
| OriginalURL_origin = URL_origin; -- name of URL parameter for error messages
| |
| OriginalFormat = Format; -- and original |format=
| |
| OriginalAccess = UrlAccess;
| |
| | |
| if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it
| |
| URL = ArchiveURL -- swap-in the archive's URL
| |
| URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages
| |
| Format = ArchiveFormat or ''; -- swap in archive's format
| |
| UrlAccess = nil; -- restricted access levels do not make sense for archived URLs
| |
| end
| |
| end
| |
| end | | end |
| | | |
| if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia | | Format = is_set(Format) and " (" .. Format .. ")" or ""; |
| ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then
| | |
| local chap_param;
| | local OriginalURL = URL |
| if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
| | DeadURL = DeadURL:lower(); |
| chap_param = A:ORIGIN ('Chapter')
| | if is_set( ArchiveURL ) then |
| elseif utilities.is_set (TransChapter) then
| | if ( DeadURL ~= "no" ) then |
| chap_param = A:ORIGIN ('TransChapter')
| | URL = ArchiveURL |
| elseif utilities.is_set (ChapterURL) then
| | URLorigin = A:ORIGIN('ArchiveURL') |
| chap_param = A:ORIGIN ('ChapterURL')
| |
| elseif utilities.is_set (ScriptChapter) then
| |
| chap_param = ScriptChapter_origin;
| |
| else utilities.is_set (ChapterFormat)
| |
| chap_param = A:ORIGIN ('ChapterFormat')
| |
| end
| |
| | |
| if utilities.is_set (chap_param) then -- if we found one
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } ); -- add error message
| |
| Chapter = ''; -- and set them to empty string to be safe with concatenation
| |
| TransChapter = '';
| |
| ChapterURL = '';
| |
| ScriptChapter = '';
| |
| ChapterFormat = '';
| |
| end
| |
| else -- otherwise, format chapter / article title | |
| local no_quotes = false; -- default assume that we will be quoting the chapter parameter value
| |
| if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s)
| |
| if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title
| |
| no_quotes = true; -- then render it unquoted
| |
| end
| |
| end
| |
| | |
| Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter
| |
| if utilities.is_set (Chapter) then
| |
| Chapter = Chapter .. ChapterFormat ;
| |
| if 'map' == config.CitationClass and utilities.is_set (TitleType) then
| |
| Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title
| |
| end
| |
| Chapter = Chapter .. sepc .. ' '; | |
| elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ...
| |
| Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it
| |
| end | | end |
| end | | end |
| | | |
| -- Format main title | | -- Format chapter / article title |
| local plain_title = false; | | if is_set(Chapter) and is_set(ChapterLink) then |
| local accept_title; | | Chapter = "[[" .. ChapterLink .. "|" .. Chapter .. "]]"; |
| Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title> | | end |
| if accept_title and ('' == Title) then -- only support forced empty for now "(())"
| | if is_set(Periodical) and is_set(Title) then |
| Title = cfg.messages['notitle']; -- replace by predefined "No title" message | | Chapter = wrap( 'italic-title', Chapter ); |
| -- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting
| | TransChapter = wrap( 'trans-italic-title', TransChapter ); |
| ScriptTitle = ''; -- just mute for now
| | else |
| TransTitle = ''; -- just mute for now
| | Chapter = kern_quotes (Chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks |
| plain_title = true; -- suppress text decoration for descriptive title
| | Chapter = wrap( 'quoted-title', Chapter ); |
| utilities.set_message ('maint_untitled'); -- add maint cat | | TransChapter = wrap( 'trans-quoted-title', TransChapter ); |
| end | | end |
| | | |
| if not accept_title then -- <Title> not wrapped in accept-as-written markup | | local TransError = "" |
| if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title= | | if is_set(TransChapter) then |
| Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three | | if not is_set(Chapter) then |
| elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ... | | TransError = " " .. seterror( 'trans_missing_chapter' ); |
| not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.) | | else |
| Title = mw.ustring.gsub(Title, '%' .. sepc .. '$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters
| | TransChapter = " " .. TransChapter; |
| end | | end |
| | | end |
| if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then | | |
| utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title
| | Chapter = Chapter .. TransChapter; |
| end
| | |
| | | if is_set(Chapter) then |
| if is_generic_title (Title) then | | if not is_set(ChapterLink) then |
| table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message | | if is_set(ChapterURL) then |
| | Chapter = externallink( ChapterURL, Chapter ) .. TransError; |
| | if not is_set(URL) then |
| | Chapter = Chapter .. Format; |
| | Format = ""; |
| | end |
| | elseif is_set(URL) then |
| | Chapter = externallink( URL, Chapter ) .. TransError .. Format; |
| | URL = ""; |
| | Format = ""; |
| | else |
| | Chapter = Chapter .. TransError; |
| | end |
| | elseif is_set(ChapterURL) then |
| | Chapter = Chapter .. " " .. externallink( ChapterURL, nil, ChapterURLorigin ) .. |
| | TransError; |
| | else |
| | Chapter = Chapter .. TransError; |
| end | | end |
| | Chapter = Chapter .. sepc .. " " -- with end-space |
| | elseif is_set(ChapterURL) then |
| | Chapter = " " .. externallink( ChapterURL, nil, ChapterURLorigin ) .. sepc .. " "; |
| | end |
| | |
| | -- Format main title. |
| | if is_set(TitleLink) and is_set(Title) then |
| | Title = "[[" .. TitleLink .. "|" .. Title .. "]]" |
| end | | end |
| | | |
| if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or | | if is_set(Periodical) then |
| ('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or
| | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks |
| ('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article | | Title = wrap( 'quoted-title', Title ); |
| Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks
| | TransTitle = wrap( 'trans-quoted-title', TransTitle ); |
| Title = utilities.wrap_style ('quoted-title', Title);
| | --[[ Hide unfinished cite newsgroup code so that long delayed update can take place |
| Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
| | elseif inArray(config.CitationClass, {"web","news","pressrelease","conference","podcast","newsgroup"}) and |
| TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle );
| | ]] elseif inArray(config.CitationClass, {"web","news","pressrelease","conference","podcast"}) and |
| elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above)
| | not is_set(Chapter) then |
| Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks |
| TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title | | Title = wrap( 'quoted-title', Title ); |
| | TransTitle = wrap( 'trans-quoted-title', TransTitle ); |
| else | | else |
| Title = utilities.wrap_style ('italic-title', Title); | | Title = wrap( 'italic-title', Title ); |
| Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped
| | TransTitle = wrap( 'trans-italic-title', TransTitle ); |
| TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle); | |
| end | | end |
| | | |
| local TransError = ""; | | TransError = ""; |
| if utilities.is_set (TransTitle) then | | if is_set(TransTitle) then |
| if utilities.is_set (Title) then | | if not is_set(Title) then |
| | TransError = " " .. seterror( 'trans_missing_title' ); |
| | else |
| TransTitle = " " .. TransTitle; | | TransTitle = " " .. TransTitle; |
| else
| |
| TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} );
| |
| end | | end |
| end | | end |
|
| |
| if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs?
| |
| if utilities.is_set (TitleLink) and utilities.is_set (URL) then
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both
| |
| TitleLink = ''; -- unset
| |
| end
| |
| | | |
| if not utilities.is_set (TitleLink) and utilities.is_set (URL) then | | Title = Title .. TransTitle; |
| Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format; | | |
| URL = ''; -- unset these because no longer needed | | if is_set(Title) then |
| | if not is_set(TitleLink) and is_set(URL) then |
| | Title = externallink( URL, Title ) .. TransError .. Format |
| | URL = ""; |
| Format = ""; | | Format = ""; |
| elseif utilities.is_set (TitleLink) and not utilities.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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title});
| |
| Title = Title .. TransTitle .. TransError;
| |
| else
| |
| Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError;
| |
| end
| |
| else | | else |
| local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink) | | Title = Title .. TransError; |
| ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title});
| |
| Title = Title .. TransTitle .. TransError;
| |
| else
| |
| Title = Title .. TransTitle .. TransError;
| |
| end
| |
| end | | end |
| else
| |
| Title = TransTitle .. TransError;
| |
| end | | end |
| | | |
| if utilities.is_set (Place) then | | if is_set(Place) then |
| Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; | | Place = " " .. wrap( 'written', Place, use_lowercase ) .. sepc .. " "; |
| end | | end |
| | | |
| local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL | | if is_set(Conference) then |
| if utilities.is_set (Conference) then | | if is_set(ConferenceURL) then |
| if utilities.is_set (ConferenceURL) then | | Conference = externallink( ConferenceURL, Conference ); |
| Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil ); | |
| end | | end |
| Conference = sepc .. " " .. Conference .. ConferenceFormat; | | Conference = sepc .. " " .. Conference |
| elseif utilities.is_set (ConferenceURL) then | | elseif is_set(ConferenceURL) then |
| Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil ); | | Conference = sepc .. " " .. externallink( ConferenceURL, nil, ConferenceURLorigin ); |
| end | | end |
| | | |
| local Position = ''; | | if not is_set(Position) then |
| if not utilities.is_set (Position) then | |
| local Minutes = A['Minutes']; | | local Minutes = A['Minutes']; |
| local Time = A['Time'];
| | if is_set(Minutes) then |
| | |
| if utilities.is_set (Minutes) then | |
| if utilities.is_set (Time) then
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } );
| |
| end
| |
| Position = " " .. Minutes .. " " .. cfg.messages['minutes']; | | Position = " " .. Minutes .. " " .. cfg.messages['minutes']; |
| else | | else |
| if utilities.is_set (Time) then | | local Time = A['Time']; |
| | if is_set(Time) then |
| local TimeCaption = A['TimeCaption'] | | local TimeCaption = A['TimeCaption'] |
| if not utilities.is_set (TimeCaption) then | | if not is_set(TimeCaption) then |
| TimeCaption = cfg.messages['event']; | | TimeCaption = cfg.messages['event']; |
| if sepc ~= '.' then | | if sepc ~= '.' then |
Line 3,405: |
Line 1,753: |
| At = ''; | | At = ''; |
| end | | end |
| | | |
| Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); | | if not is_set(Page) then |
| | | if is_set(Pages) then |
| At = utilities.is_set (At) and (sepc .. " " .. At) or ""; | | if is_set(Periodical) and |
| Position = utilities.is_set (Position) and (sepc .. " " .. Position) or ""; | | not inArray(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then |
| | Pages = ": " .. Pages; |
| | elseif tonumber(Pages) ~= nil then |
| | Pages = sepc .." " .. PPrefix .. Pages; |
| | else |
| | Pages = sepc .." " .. PPPrefix .. Pages; |
| | end |
| | end |
| | else |
| | if is_set(Periodical) and |
| | not inArray(config.CitationClass, {"encyclopaedia","web","book","news","podcast"}) then |
| | Page = ": " .. Page; |
| | else |
| | Page = sepc .." " .. PPrefix .. Page; |
| | end |
| | end |
| | |
| | At = is_set(At) and (sepc .. " " .. At) or ""; |
| | Position = is_set(Position) and (sepc .. " " .. Position) or ""; |
| if config.CitationClass == 'map' then | | if config.CitationClass == 'map' then |
| local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier | | local Section = A['Section']; |
| local Inset = A['Inset']; | | local Inset = A['Inset']; |
| | | if first_set( Pages, Page, At ) ~= nil or sepc ~= '.' then |
| if utilities.is_set ( Inset ) then | | if is_set( Section ) then |
| Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); | | Section = ", " .. wrap( 'section', Section, true ); |
| | end |
| | if is_set( Inset ) then |
| | Inset = ", " .. wrap( 'inset', Inset, true ); |
| | end |
| | else |
| | if is_set( Section ) then |
| | Section = sepc .. " " .. wrap( 'section', Section, use_lowercase ); |
| | if is_set( Inset ) then |
| | Inset = ", " .. wrap( 'inset', Inset, true ); |
| | end |
| | elseif is_set( Inset ) then |
| | Inset = sepc .. " " .. wrap( 'inset', Inset, use_lowercase ); |
| | end |
| end | | end |
| | | At = At .. Section .. Inset; |
| if utilities.is_set ( Sections ) then | |
| Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase);
| |
| elseif utilities.is_set ( Section ) then
| |
| Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase);
| |
| end
| |
| At = At .. Inset .. Section;
| |
| end | | end |
|
| |
|
| local Others = A['Others']; | | --[[Look in the list of iso639-1 language codes to see if the value provided in the language parameter matches one of them. If a match is found, |
| if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= | | use that value; if not, then use the value that was provided with the language parameter. |
| if config.CitationClass == "AV-media-notes" | | |
| or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now | | Categories are assigned in a manner similar to the {{xx icon}} templates - categorizes only mainspace citations and only when the language code is not 'en' (English). |
| utilities.set_message ('maint_others_avm') | | ]] |
| | if is_set (Language) then |
| | -- local name = mw.language.fetchLanguageName( Language:lower(), "en" ); -- experiment: this seems to return correct ISO 639-1 language names |
| | local name = cfg.iso639_1[Language:lower()]; -- get the language name if Language parameter has a valid iso 639-1 code |
| | if nil == name then |
| | Language=" " .. wrap( 'language', Language ); -- no match, use parameter's value |
| else | | else |
| utilities.set_message ('maint_others'); | | if 0 == this_page.namespace and 'en' ~= Language:lower() then --found a match; is this page main / article space and English not the language? |
| | Language=" " .. wrap( 'language', name .. '[[Category:Articles with ' .. name .. '-language external links]]' ); -- in main space and not English: categorize |
| | else |
| | Language=" " .. wrap( 'language', name ); --not in mainspace or language is English so don't categorize |
| | end |
| end | | end |
| | else |
| | Language=""; -- language not specified so make sure this is an empty string; |
| end | | end |
| Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | | |
|
| | Others = is_set(Others) and (sepc .. " " .. Others) or ""; |
| if utilities.is_set (Translators) then | | |
| Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc);
| | -- handle type parameter for those CS1 citations that have default values |
| end
| | |
| if utilities.is_set (Interviewers) then
| | if inArray(config.CitationClass, {"AV-media-notes", "DVD-notes", "podcast", "pressrelease", "techreport", "thesis"}) then |
| Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc); | | TitleType = set_titletype (config.CitationClass, TitleType); |
| end
| | if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis |
|
| | TitleType = Degree .. " thesis"; |
| local TitleNote = A['TitleNote'];
| |
| TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or "";
| |
| if utilities.is_set (Edition) then
| |
| if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn.
| |
| table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_edition')}); -- add error | |
| end | | end |
| Edition = " " .. wrap_msg ('edition', Edition);
| |
| else
| |
| Edition = '';
| |
| end | | end |
|
| |
|
| Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum | | if is_set(TitleType) then -- if type parameter is specified |
| local Agency = A['Agency'];
| | TitleType = " (" .. TitleType .. ")"; -- display it in parentheses |
| Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or "";
| | end |
| Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); | |
|
| |
|
| if utilities.is_set (AccessDate) then | | TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; |
| local retrv_text = " " .. cfg.messages['retrieved']
| | Edition = is_set(Edition) and (" " .. wrap( 'edition', Edition )) or ""; |
| | Issue = is_set(Issue) and (" (" .. Issue .. ")") or ""; |
| | Series = is_set(Series) and (sepc .. " " .. Series) or ""; |
| | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; |
| | Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; |
|
| |
|
| AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
| | if is_set(Volume) then |
| if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case | | if ( mw.ustring.len(Volume) > 4 ) |
| AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text
| | then Volume = sepc .." " .. Volume; |
| | else Volume = " <b>" .. hyphentodash(Volume) .. "</b>"; |
| | end |
| | end |
|
| |
|
| AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates | | --[[ This code commented out while discussion continues until after week of 2014-03-23 live module update; |
| | if is_set(Volume) then |
| | if ( mw.ustring.len(Volume) > 4 ) |
| | then Volume = sepc .. " " .. Volume; |
| | else |
| | Volume = " <b>" .. hyphentodash(Volume) .. "</b>"; |
| | if is_set(Series) then Volume = sepc .. Volume; |
| | end |
| | end |
| end | | end |
| | ]] |
| | ------------------------------------ totally unrelated data |
| | --[[ Loosely mimic {{subscription required}} template; Via parameter identifies a delivery source that is not the publisher; these sources often, but not always, exist |
| | behind a registration or paywall. So here, we've chosen to decouple via from subscription (via has never been part of the registration required template). |
| | | |
| if utilities.is_set (ID) then ID = sepc .. " " .. ID; end | | Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link note is displayed. There are no error messages for this condition. |
| | | ]] |
| local Docket = A['Docket']; | | if is_set(Via) then |
| if "thesis" == config.CitationClass and utilities.is_set (Docket) then
| | Via = " " .. wrap( 'via', Via ); |
| ID = sepc .. " Docket " .. Docket .. ID; | |
| end | | end |
| if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set
| | |
| ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set | | if is_set(SubscriptionRequired) then |
| | SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; --here when 'via' parameter not used but 'subscription' is |
| | elseif is_set(RegistrationRequired) then |
| | SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; --here when 'via' and 'subscription' parameters not used but 'registration' is |
| end | | end |
|
| |
|
| if utilities.is_set (URL) then | | if is_set(AccessDate) then |
| URL = " " .. external_link( URL, nil, URL_origin, UrlAccess ); | | local retrv_text = " " .. cfg.messages['retrieved'] |
| | if (sepc ~= ".") then retrv_text = retrv_text:lower() end |
| | AccessDate = '<span class="reference-accessdate">' .. sepc |
| | .. substitute( retrv_text, {AccessDate} ) .. '</span>' |
| | end |
| | |
| | if is_set(ID) then ID = sepc .." ".. ID; end |
| | if "thesis" == config.CitationClass and is_set(Docket) then |
| | ID = sepc .." Docket ".. Docket .. ID; |
| end | | end |
|
| |
|
| local Quote = A['Quote'];
| |
| local TransQuote = A['TransQuote'];
| |
| local ScriptQuote = A['ScriptQuote'];
| |
| if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then
| |
|
| |
| if utilities.is_set (Quote) then
| |
| if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks
| |
| Quote = Quote:sub(2, -2); -- strip them off
| |
| end
| |
| end
| |
|
| |
| Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags
| |
| | | |
| if utilities.is_set (ScriptQuote) then
| | ID_list = buildidlist( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo} ); |
| Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped
| |
| end
| |
|
| |
|
| if utilities.is_set (TransQuote) then
| | if is_set(URL) then |
| if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks
| | URL = " " .. externallink( URL, nil, URLorigin ); |
| TransQuote = TransQuote:sub(2, -2); -- strip them off
| | end |
| end
| |
| Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote );
| |
| end
| |
|
| |
|
| if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix
| | if is_set(Quote) then |
| local quote_prefix = '';
| | if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then |
| if utilities.is_set (QuotePage) then
| | Quote = Quote:sub(2,-2); |
| extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc.
| |
| if not NoPP then
| |
| quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', '';
| |
| else
| |
| quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', '';
| |
| end
| |
| elseif utilities.is_set (QuotePages) then
| |
| extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc.
| |
| if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page
| |
| quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', '';
| |
| elseif not NoPP then
| |
| quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', '';
| |
| else
| |
| quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', '';
| |
| end
| |
| end
| |
|
| |
| Quote = quote_prefix .. ": " .. Quote;
| |
| else
| |
| Quote = sepc .. " " .. Quote;
| |
| end | | end |
| | | Quote = sepc .." " .. wrap( 'quoted-text', Quote ); |
| PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set | | PostScript = ""; -- CS1 does not supply terminal punctuation when |quote= is set |
| end
| |
|
| |
| -- We check length of PostScript here because it will have been nuked by
| |
| -- the quote parameters. We'd otherwise emit a message even if there wasn't
| |
| -- a displayed postscript.
| |
| -- TODO: Should the max size (1) be configurable?
| |
| -- TODO: Should we check a specific pattern?
| |
| if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then
| |
| utilities.set_message('maint_postscript')
| |
| end | | end |
| | | |
| local Archived | | local Archived |
| if utilities.is_set (ArchiveURL) then | | if is_set(ArchiveURL) then |
| local arch_text;
| | if not is_set(ArchiveDate) then |
| if not utilities.is_set (ArchiveDate) then | | ArchiveDate = seterror('archive_missing_date'); |
| ArchiveDate = utilities.set_message ('err_archive_missing_date'); | |
| end | | end |
| if "live" == UrlStatus then | | if "no" == DeadURL then |
| arch_text = cfg.messages['archived']; | | local arch_text = cfg.messages['archived']; |
| if sepc ~= "." then arch_text = arch_text:lower() end | | if sepc ~= "." then arch_text = arch_text:lower() end |
| Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'], | | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], |
| { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } ); | | { externallink( ArchiveURL, arch_text ), ArchiveDate } ); |
| if not utilities.is_set (OriginalURL) then | | if not is_set(OriginalURL) then |
| Archived = Archived .. " " .. utilities.set_message ('err_archive_missing_url'); | | Archived = Archived .. " " .. seterror('archive_missing_url'); |
| end | | end |
| elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' | | elseif is_set(OriginalURL) then |
| if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then | | local arch_text = cfg.messages['archived-dead']; |
| arch_text = cfg.messages['archived-unfit'];
| | if sepc ~= "." then arch_text = arch_text:lower() end |
| if sepc ~= "." then arch_text = arch_text:lower() end
| | Archived = sepc .. " " .. substitute( arch_text, |
| Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled
| | { externallink( OriginalURL, cfg.messages['original'] ), ArchiveDate } ); |
| if 'bot: unknown' == UrlStatus then
| | else |
| utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added
| | local arch_text = cfg.messages['archived-missing']; |
| else
| |
| utilities.set_message ('maint_unfit'); -- and add a category if not already added
| |
| end
| |
| else -- UrlStatus is empty, 'dead'
| |
| arch_text = cfg.messages['archived-dead'];
| |
| if sepc ~= "." then arch_text = arch_text:lower() end
| |
| Archived = sepc .. " " .. utilities.substitute ( arch_text,
| |
| { external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled
| |
| end
| |
| else -- OriginalUrl not set | |
| arch_text = cfg.messages['archived-missing']; | |
| if sepc ~= "." then arch_text = arch_text:lower() end | | if sepc ~= "." then arch_text = arch_text:lower() end |
| Archived = sepc .. " " .. utilities.substitute ( arch_text, | | Archived = sepc .. " " .. substitute( arch_text, |
| { utilities.set_message ('err_archive_missing_url'), ArchiveDate } ); | | { seterror('archive_missing_url'), ArchiveDate } ); |
| end | | end |
| elseif utilities.is_set (ArchiveFormat) then
| |
| Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
| |
| else | | else |
| Archived = "" | | Archived = "" |
| end | | end |
| | | |
| local Lay = ''; | | local Lay |
| local LaySource = A['LaySource'];
| | if is_set(LayURL) then |
| local LayURL = A['LayURL'];
| | if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end |
| local LayFormat = A['LayFormat'];
| | if is_set(LaySource) then |
| LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
| | LaySource = " – ''" .. safeforitalics(LaySource) .. "''"; |
| if utilities.is_set (LayURL) then | |
| if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end | |
| if utilities.is_set (LaySource) then | |
| LaySource = " – ''" .. utilities.safe_for_italics (LaySource) .. "''"; | |
| else | | else |
| LaySource = ""; | | LaySource = ""; |
| end | | end |
| if sepc == '.' then | | if sepc == '.' then |
| Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate | | Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary'] ) .. LaySource .. LayDate |
| else | | else |
| Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate | | Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary']:lower() ) .. LaySource .. LayDate |
| end | | end |
| elseif utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= | | else |
| Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message | | Lay = ""; |
| end | | end |
| | | |
| local TranscriptURL = A['TranscriptURL']
| | if is_set(Transcript) then |
| local TranscriptFormat = A['TranscriptFormat'];
| | if is_set(TranscriptURL) then Transcript = externallink( TranscriptURL, Transcript ); end |
| TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
| | elseif is_set(TranscriptURL) then |
| local Transcript = A['Transcript'];
| | Transcript = externallink( TranscriptURL, nil, TranscriptURLorigin ); |
| local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL | |
| if utilities.is_set (Transcript) then | |
| if utilities.is_set (TranscriptURL) then | |
| Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil );
| |
| end
| |
| Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
| |
| elseif utilities.is_set (TranscriptURL) then | |
| Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil ); | |
| end | | end |
| | | |
| local Publisher; | | local Publisher; |
| if utilities.is_set (PublicationDate) then | | if is_set(Periodical) and |
| PublicationDate = wrap_msg ('published', PublicationDate); | | not inArray(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then |
| end
| | if is_set(PublisherName) then |
| if utilities.is_set (PublisherName) then | | if is_set(PublicationPlace) then |
| if utilities.is_set (PublicationPlace) then
| | Publisher = PublicationPlace .. ": " .. PublisherName; |
| Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate;
| | else |
| else
| | Publisher = PublisherName; |
| Publisher = sepc .. " " .. PublisherName .. PublicationDate;
| | end |
| end
| | elseif is_set(PublicationPlace) then |
| elseif utilities.is_set (PublicationPlace) then
| | Publisher= PublicationPlace; |
| Publisher= sepc .. " " .. PublicationPlace .. PublicationDate;
| | else |
| else
| | Publisher = ""; |
| Publisher = PublicationDate;
| | end |
| | if is_set(PublicationDate) then |
| | if is_set(Publisher) then |
| | Publisher = Publisher .. ", " .. wrap( 'published', PublicationDate ); |
| | else |
| | Publisher = PublicationDate; |
| | end |
| | end |
| | if is_set(Publisher) then |
| | Publisher = " (" .. Publisher .. ")"; |
| | end |
| | else |
| | if is_set(PublicationDate) then |
| | PublicationDate = " (" .. wrap( 'published', PublicationDate ) .. ")"; |
| | end |
| | if is_set(PublisherName) then |
| | if is_set(PublicationPlace) then |
| | Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
| | else |
| | Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
| | end |
| | elseif is_set(PublicationPlace) then |
| | Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
| | else |
| | Publisher = PublicationDate; |
| | end |
| end | | end |
| | | |
| local TransPeriodical = A['TransPeriodical'];
| |
| local TransPeriodical_origin = A:ORIGIN ('TransPeriodical');
| |
| -- Several of the above rely upon detecting this as nil, so do it last. | | -- Several of the above rely upon detecting this as nil, so do it last. |
| if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then | | if is_set(Periodical) then |
| if utilities.is_set (Title) or utilities.is_set (TitleNote) then | | if is_set(Title) or is_set(TitleNote) then |
| Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); | | Periodical = sepc .. " " .. wrap( 'italic-title', Periodical ) |
| else | | else |
| Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); | | Periodical = wrap( 'italic-title', Periodical ) |
| end | | end |
| end
| |
|
| |
| local Language = A['Language'];
| |
| if utilities.is_set (Language) then
| |
| Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc.
| |
| else
| |
| Language=''; -- language not specified so make sure this is an empty string;
| |
| --[[ TODO: need to extract the wrap_msg from language_parameter
| |
| so that we can solve parentheses bunching problem with Format/Language/TitleType
| |
| ]]
| |
| end | | end |
|
| |
|
| --[[
| | --[[ |
| Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
| | Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that |
| the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
| | the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). |
| ]]
| | ]] |
| if "speech" == config.CitationClass then -- cite speech only | | if "speech" == config.CitationClass then -- cite speech only |
| TitleNote = " (Speech)"; -- annotate the citation | | TitleNote = " (Speech)"; -- annotate the citation |
| if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter | | if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter |
| if utilities.is_set (Conference) then -- and if |event= is set | | if is_set (Conference) then -- and if |event= is set |
| Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering | | Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering |
| end | | end |
| end | | end |
Line 3,676: |
Line 2,021: |
| -- not to keep reassigning to the same string variable over and over. | | -- not to keep reassigning to the same string variable over and over. |
|
| |
|
| local tcommon; | | local tcommon |
| local tcommon2; -- used for book cite when |contributor= is set
| | if inArray(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
|
| | if is_set(Others) then Others = Others .. sepc .. " " end |
| if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then | | tcommon = safejoin( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series, |
| if utilities.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? | | Language, Cartography, Edition, Publisher, Agency, Volume, Issue}, sepc ); |
| tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc );
| | else |
| elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites
| | tcommon = safejoin( {Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series, Language, |
| if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc. | | Volume, Issue, Others, Cartography, Edition, Publisher, Agency}, sepc ); |
| tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
| |
| tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
| |
| else
| |
| tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
| |
| end
| |
| | |
| elseif 'map' == config.CitationClass then -- special cases for cite map
| |
| if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter
| |
| tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
| |
| elseif utilities.is_set (Periodical) then -- map in a periodical
| |
| tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); | |
| else -- a sheet or stand-alone map
| |
| tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
| |
| end
| |
|
| |
| elseif 'episode' == config.CitationClass then -- special case for cite episode
| |
| tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc );
| |
| | |
| else -- all other CS1 templates | |
| tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, | |
| Volume, Others, Edition, Publisher, Agency}, sepc ); | |
| end | | end |
| | | |
| if #ID_list > 0 then | | if #ID_list > 0 then |
| ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); | | ID_list = safejoin( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); |
| else | | else |
| ID_list = ID; | | ID_list = ID; |
| end | | end |
| | | |
| local Via = A['Via']; | | local idcommon = safejoin( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); |
| Via = utilities.is_set (Via) and wrap_msg ('via', Via) or '';
| | local text; |
| local idcommon;
| | local pgtext = Position .. Page .. Pages .. At; |
| if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript
| |
| idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc );
| |
| else | |
| idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc );
| |
| end
| |
| | | |
| local text;
| | if is_set(Authors) then |
| local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
| | if is_set(Coauthors) then |
| | | Authors = Authors .. A['AuthorSeparator'] .. " " .. Coauthors |
| local OrigDate = A['OrigDate'];
| |
| OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or '';
| |
| if utilities.is_set (Date) then | |
| if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set | |
| Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses | |
| else -- neither of authors and editors set
| |
| if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc
| |
| Date = " " .. Date .. OrigDate; -- Date does not begin with sepc
| |
| else
| |
| Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc
| |
| end
| |
| end | | end |
| end
| | if is_set(Date) then |
| if utilities.is_set (Authors) then
| | Date = " ("..Date..")" .. OrigYear .. sepc .. " " |
| if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Authors termination
| | elseif string.sub(Authors,-1,-1) == sepc then |
| Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space | | Authors = Authors .. " " |
| | else |
| | Authors = Authors .. sepc .. " " |
| end | | end |
| if utilities.is_set (Editors) then | | if is_set(Editors) then |
| local in_text = " "; | | local in_text = " "; |
| local post_text = ""; | | local post_text = ""; |
| if utilities.is_set (Chapter) and 0 == #c then | | if is_set(Chapter) then |
| in_text = in_text .. cfg.messages['in'] .. " " | | in_text = in_text .. cfg.messages['in'] .. " " |
| if (sepc ~= '.') then | | else |
| in_text = in_text:lower() -- lowercase for cs2 | | if EditorCount <= 1 then |
| | post_text = ", " .. cfg.messages['editor']; |
| | else |
| | post_text = ", " .. cfg.messages['editors']; |
| end | | end |
| | end |
| | if (sepc ~= '.') then in_text = in_text:lower() end |
| | Editors = in_text .. Editors .. post_text; |
| | if (string.sub(Editors,-1,-1) == sepc) |
| | then Editors = Editors .. " " |
| | else Editors = Editors .. sepc .. " " |
| end | | end |
| if EditorCount <= 1 then
| |
| post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case
| |
| else
| |
| post_text = " (" .. cfg.messages['editors'] .. ")";
| |
| end
| |
| Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space
| |
| end
| |
| if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc.
| |
| local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' ';
| |
| if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2
| |
| Authors = by_text .. Authors; -- author follows title so tweak it here
| |
| if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated
| |
| Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space
| |
| end
| |
| if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination
| |
| Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space
| |
| end
| |
| text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc );
| |
| else
| |
| text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc );
| |
| end | | end |
| elseif utilities.is_set (Editors) then | | text = safejoin( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc ); |
| if utilities.is_set (Date) then | | text = safejoin( {text, pgtext, idcommon}, sepc ); |
| | elseif is_set(Editors) then |
| | if is_set(Date) then |
| if EditorCount <= 1 then | | if EditorCount <= 1 then |
| Editors = Editors .. ", " .. cfg.messages['editor']; | | Editors = Editors .. ", " .. cfg.messages['editor']; |
Line 3,779: |
Line 2,080: |
| Editors = Editors .. ", " .. cfg.messages['editors']; | | Editors = Editors .. ", " .. cfg.messages['editors']; |
| end | | end |
| | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " " |
| else | | else |
| if EditorCount <= 1 then | | if EditorCount <= 1 then |
Line 3,786: |
Line 2,088: |
| end | | end |
| end | | end |
| text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); | | text = safejoin( {Editors, Date, Chapter, Place, tcommon}, sepc ); |
| | text = safejoin( {text, pgtext, idcommon}, sepc ); |
| else | | else |
| if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then | | if is_set(Date) then |
| text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); | | if ( string.sub(tcommon,-1,-1) ~= sepc ) |
| | then Date = sepc .." " .. Date .. OrigYear |
| | else Date = " " .. Date .. OrigYear |
| | end |
| | end |
| | if config.CitationClass=="journal" and is_set(Periodical) then |
| | text = safejoin( {Chapter, Place, tcommon}, sepc ); |
| | text = safejoin( {text, pgtext, Date, idcommon}, sepc ); |
| else | | else |
| text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc ); | | text = safejoin( {Chapter, Place, tcommon, Date}, sepc ); |
| | text = safejoin( {text, pgtext, idcommon}, sepc ); |
| end | | end |
| end | | end |
| | | |
| if utilities.is_set (PostScript) and PostScript ~= sepc then | | if is_set(PostScript) and PostScript ~= sepc then |
| text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc. | | text = safejoin( {text, sepc}, sepc ); --Deals with italics, spaces, etc. |
| text = text:sub(1, -sepc:len() - 1); | | text = text:sub(1,-sepc:len()-1); |
| | -- text = text:sub(1,-2); --Remove final separator (assumes that sepc is only one character) |
| end | | end |
| | | |
| text = safe_join( {text, PostScript}, sepc ); | | text = safejoin( {text, PostScript}, sepc ); |
|
| |
|
| -- Now enclose the whole thing in a <cite> element | | -- Now enclose the whole thing in a <span/> element |
| local options = {}; | | local options = {}; |
| | | |
| if utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then | | if is_set(config.CitationClass) and config.CitationClass ~= "citation" then |
| options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref= | | options.class = "citation " .. config.CitationClass; |
| else | | else |
| options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2'); | | options.class = "citation"; |
| end | | end |
| | | |
| local Ref = A['Ref']; | | if is_set(Ref) and Ref:lower() ~= "none" then |
| if 'harv' == Ref then -- need to check this before setting to default | |
| utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value
| |
| elseif not utilities.is_set (Ref) then
| |
| Ref = 'harv'; -- set as default when not set externally
| |
| end
| |
| if 'none' ~= cfg.keywords_xlate[Ref:lower()] then
| |
| local id = Ref | | local id = Ref |
| local namelist = {}; -- holds selected contributor, author, editor name list | | if ( "harv" == Ref ) then |
| local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation
| | local names = {} --table of last names & year |
| | | if #a > 0 then |
| if #c > 0 then -- if there is a contributor list
| | for i,v in ipairs(a) do |
| namelist = c; -- select it
| | names[i] = v.last |
| elseif #a > 0 then -- or an author list
| | if i == 4 then break end |
| namelist = a; | | end |
| elseif #e > 0 then -- or an editor list
| | elseif #e > 0 then |
| namelist = e; | | for i,v in ipairs(e) do |
| end
| | names[i] = v.last |
| local citeref_id
| | if i == 4 then break end |
| if #namelist > 0 then -- if there are names in namelist
| | end |
| citeref_id = make_citeref_id (namelist, year); -- go make the CITEREF anchor
| | end |
| else
| | names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations |
| citeref_id = ''; -- unset | | id = anchorid(names) |
| end
| |
| if citeref_id == Ref then
| |
| utilities.set_message ('maint_ref_duplicates_default');
| |
| end
| |
| if 'harv' == Ref then
| |
| id = citeref_id
| |
| end | | end |
| options.id = id; | | options.id = id; |
| end | | end |
| | | |
| if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then -- remove <span> tags and other HTML-like markup; then get length of what remains | | if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then |
| z.error_categories = {}; | | z.error_categories = {}; |
| text = utilities.set_message ('err_empty_citation'); | | text = seterror('empty_citation'); |
| z.message_tail = {}; | | z.message_tail = {}; |
| end | | end |
| | | |
| local render = {}; -- here we collect the final bits for concatenation into the rendered citation
| | if is_set(options.id) then |
| | | text = '<span id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>"; |
| if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags | |
| table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set | |
| else | | else |
| table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases | | text = '<span class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>"; |
| end | | end |
|
| |
|
| table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation | | local empty_span = '<span style="display:none;"> </span>'; |
| | | |
| if 0 ~= #z.message_tail then | | -- Note: Using display: none on then COinS span breaks some clients. |
| table.insert (render, ' '); | | local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>'; |
| | text = text .. OCinS; |
| | |
| | if #z.message_tail ~= 0 then |
| | text = text .. " "; |
| for i,v in ipairs( z.message_tail ) do | | for i,v in ipairs( z.message_tail ) do |
| if utilities.is_set (v[1]) then | | if is_set(v[1]) then |
| if i == #z.message_tail then | | if i == #z.message_tail then |
| table.insert (render, utilities.error_comment ( v[1], v[2] )); | | text = text .. errorcomment( v[1], v[2] ); |
| else | | else |
| table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] )); | | text = text .. errorcomment( v[1] .. "; ", v[2] ); |
| end | | end |
| end | | end |
| end | | end |
| end | | end |
|
| |
| if 0 ~= #z.maintenance_cats then
| |
| local maint_msgs = {}; -- here we collect all of the maint messages
| |
| for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
| |
| local maint = {}; -- here we assemble a maintenence message
| |
| table.insert (maint, v); -- maint msg is the category name
| |
| table.insert (maint, ' ('); -- open the link text
| |
| table.insert (maint, utilities.substitute (cfg.messages[':cat wikilink'], {v})); -- 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, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save
| |
| end
| |
|
| |
| if not no_tracking_cats then
| |
| for _, v in ipairs( z.error_categories ) do -- append error categories
| |
| table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
| |
| end
| |
| for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories
| |
| table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
| |
| end
| |
| for _, v in ipairs( z.properties_cats ) do -- append properties categories
| |
| table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v}));
| |
| end
| |
| end
| |
|
| |
| 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
| |
| | | |
| ]]
| | no_tracking_cats = no_tracking_cats:lower(); |
| | | if inArray(no_tracking_cats, {"", "no", "false", "n"}) then |
| local function validate (name, cite_class, empty)
| | for _, v in ipairs( z.error_categories ) do |
| local name = tostring (name); | | text = text .. '[[Category:' .. v ..']]'; |
| local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#' | |
| local state;
| |
| local function state_test (state, name) -- local function to do testing of state values
| |
| if true == state then return true; end -- valid actively supported parameter
| |
| if false == state then | |
| if empty then return nil; end -- empty deprecated parameters are treated as unknowns
| |
| deprecated_parameter (name); -- parameter is deprecated but still supported
| |
| return true; | |
| end | | end |
| if 'discouraged' == state then
| |
| discouraged_parameter (name); -- parameter is discouraged but still supported
| |
| return true;
| |
| end
| |
| return nil;
| |
| end
| |
|
| |
| if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted
| |
| return nil;
| |
| end | | end |
|
| |
| if utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates
| |
| state = whitelist.limited_basic_arguments[name];
| |
| if true == state_test (state, name) then return true; end
| |
|
| |
| state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class
| |
| if true == state_test (state, name) then return true; end
| |
|
| |
| -- limited enumerated parameters list
| |
| enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
| |
| state = whitelist.limited_numbered_arguments[enum_name];
| |
| if true == state_test (state, name) then return true; end
| |
|
| |
| return false; -- not supported because not found or name is set to nil
| |
| end -- end limited parameter-set templates
| |
|
| |
| if utilities.in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list
| |
| state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class
| |
| if true == state_test (state, name) then return true; end
| |
| end -- if here, fall into general validation
| |
|
| |
| state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed
| |
| if true == state_test (state, name) then return true; end
| |
|
| |
| -- all enumerated parameters allowed
| |
| enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits)
| |
| state = whitelist.numbered_arguments[enum_name];
| |
| if true == state_test (state, name) then return true; end
| |
|
| |
| return false; -- not supported because not found or name is set to nil
| |
| end
| |
|
| |
|
| |
| --[=[-------------------------< I N T E R _ W I K I _ C H E C K >----------------------------------------------
| |
|
| |
| check <value> for inter-language interwiki-link markup. <prefix> must be a MediaWiki-recognized language
| |
| code. when these values have the form (without leading colon):
| |
| [[<prefix>:link|label]] return label as plain-text
| |
| [[<prefix>:link]] return <prefix>:link as plain-text
| |
|
| |
| return value as is else
| |
|
| |
| ]=]
| |
|
| |
| local function inter_wiki_check (parameter, value)
| |
| local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists
| |
| local _;
| |
| | | |
| if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so
| | return text |
| table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message
| |
| _, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink
| |
| end
| |
| return value; | |
| end | | end |
|
| |
|
| | | -- This is used by templates such as {{cite book}} to create the actual citation text. |
| --[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ | | function z.citation(frame) |
| | | local pframe = frame:getParent() |
| 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. There are two tests made:
| |
| {{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name
| |
| {{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki)
| |
| cs1|2 shares some parameter names with XML/HTML attributes: 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 (parameter, value)
| |
| local capture;
| |
| value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc.
| |
| | |
| capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes
| |
| if capture and validate (capture) then -- if the capture is a valid parameter name
| |
| table.insert( z.message_tail, {utilities.set_message ('err_missing_pipe', parameter)});
| |
| end | |
| end
| |
| | |
| | |
| --[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >--------------------------------------
| |
| | |
| look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked
| |
| | |
| ]]
| |
| | |
| local function has_extraneous_punc (param, value) | |
| if 'number' == type (param) then
| |
| return;
| |
| end
| |
|
| |
| param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize
| |
| if cfg.punct_skip[param] then
| |
| return; -- parameter name found in the skip table so done
| |
| end
| |
| | | |
| if value:match ('[,;:]$') then | | if nil ~= string.find( frame:getTitle(), 'sandbox', 1, true ) then -- did the {{#invoke:}} use sandbox version? |
| utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat | | cfg = mw.loadData( 'Module:Citation/CS1/Configuration/sandbox' ); -- load sandbox versions of Configuration and Whitelist and ... |
| | whitelist = mw.loadData( 'Module:Citation/CS1/Whitelist/sandbox' ); |
| | dates = require('Module:Citation/CS1/Date_validation/sandbox').dates -- ... sandbox version of date validation code |
| | else -- otherwise |
| | cfg = mw.loadData( 'Module:Citation/CS1/Configuration' ); -- load live versions of Configuration and Whitelist and ... |
| | whitelist = mw.loadData( 'Module:Citation/CS1/Whitelist' ); |
| | dates = require('Module:Citation/CS1/Date_validation').dates -- ... live version of date validation code |
| end | | end |
| end
| |
|
| |
|
| |
| --[[--------------------------< C I T A T I O N >--------------------------------------------------------------
| |
|
| |
| This is used by templates such as {{cite book}} to create the actual citation text.
| |
|
| |
| ]]
| |
|
| |
| local function citation(frame)
| |
| Frame = frame; -- save a copy in case we need to display an error message in preview mode
| |
| local pframe = frame:getParent()
| |
| local styles;
| |
| | | |
| if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
| | local args = {}; |
| cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules
| | local suggestions = {}; |
| whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox');
| |
| utilities = require ('Module:Citation/CS1/Utilities/sandbox');
| |
| validation = require ('Module:Citation/CS1/Date_validation/sandbox');
| |
| identifiers = require ('Module:Citation/CS1/Identifiers/sandbox');
| |
| metadata = require ('Module:Citation/CS1/COinS/sandbox');
| |
| styles = 'Module:Citation/CS1/sandbox/styles.css';
| |
|
| |
| else -- otherwise
| |
| cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules
| |
| whitelist = mw.loadData ('Module:Citation/CS1/Whitelist');
| |
| utilities = require ('Module:Citation/CS1/Utilities');
| |
| validation = require ('Module:Citation/CS1/Date_validation');
| |
| identifiers = require ('Module:Citation/CS1/Identifiers');
| |
| metadata = require ('Module:Citation/CS1/COinS');
| |
| styles = 'Module:Citation/CS1/styles.css';
| |
| end
| |
| | |
| utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables
| |
| identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module
| |
| validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module
| |
| metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module
| |
| | |
| z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities
| |
| | |
| local args = {}; -- table where we store all of the template's arguments | |
| local suggestions = {}; -- table where we store suggestions if we need to loadData them | |
| local error_text, error_state; | | local error_text, error_state; |
|
| |
|
| local config = {}; -- table to store parameters from the module {{#invoke:}} | | local config = {}; |
| for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame | | for k, v in pairs( frame.args ) do |
| config[k] = v; | | config[k] = v; |
| -- args[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep?
| | args[k] = v; |
| end | | end |
|
| |
|
| local capture; -- the single supported capture when matching unknown parameters using patterns
| | for k, v in pairs( pframe.args ) do |
| local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing
| |
| for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame | |
| v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string
| |
| if v ~= '' then | | if v ~= '' then |
| if ('string' == type (k)) then
| | if not validate( k ) then |
| k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9
| |
| end
| |
| if not validate( k, config.CitationClass ) then | |
| error_text = ""; | | error_text = ""; |
| if type( k ) ~= 'string' then | | if type( k ) ~= 'string' then |
| -- exclude empty numbered parameters | | -- Exclude empty numbered parameters |
| if v:match("%S+") ~= nil then | | if v:match("%S+") ~= nil then |
| error_text, error_state = utilities.set_message ( 'err_text_ignored', {v}, true ); | | error_text, error_state = seterror( 'text_ignored', {v}, true ); |
| end | | end |
| elseif validate( k:lower(), config.CitationClass ) then | | elseif validate( k:lower() ) then |
| error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter | | error_text, error_state = seterror( 'parameter_ignored_suggest', {k, k:lower()}, true ); |
| else | | else |
| if nil == suggestions.suggestions then -- if this table is nil then we need to load it | | if #suggestions == 0 then |
| if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
| | suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); |
| suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version
| |
| else | |
| suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version
| |
| end
| |
| end | | end |
| for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter | | if suggestions[ k:lower() ] ~= nil then |
| capture = k:match (pattern); -- the whole match if no capture in pattern else the capture if a match
| | error_text, error_state = seterror( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true ); |
| if capture then -- if the pattern matches
| | else |
| param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator)
| | error_text, error_state = seterror( 'parameter_ignored', {k}, true ); |
| 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 = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message
| |
| else
| |
| error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true ); -- suggested param not supported by this template
| |
| v = ''; -- unset
| |
| end
| |
| end
| |
| end
| |
| if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an explicit suggestion?
| |
| if (suggestions.suggestions[ k:lower() ] ~= nil) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then
| |
| error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true );
| |
| else
| |
| error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true );
| |
| v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists)
| |
| end
| |
| end | | end |
| end | | end |
Line 4,134: |
Line 2,234: |
| end | | end |
| end | | end |
| | | args[k] = v; |
| args[k] = v; -- save this parameter and its value | | elseif args[k] ~= nil or (k == 'postscript') then |
| | | args[k] = v; |
| elseif not utilities.is_set (v) then -- for empty parameters | | end |
| if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter
| |
| k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text
| |
| table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list
| |
| end
| |
| -- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep?
| |
| -- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that)
| |
| -- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here
| |
| end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact? | |
| end | | end |
| | | |
| if 0 ~= #empty_unknowns then -- create empty unknown error message
| | return citation0( config, args) |
| table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', {
| |
| 1 == #empty_unknowns and '' or 's',
| |
| utilities.make_sep_list (#empty_unknowns, empty_unknowns)
| |
| }, true )});
| |
| end
| |
| | |
| for k, v in pairs( args ) do
| |
| if 'string' == type (k) then -- don't evaluate positional parameters
| |
| has_invisible_chars (k, v); -- look for invisible characters
| |
| end
| |
| has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values
| |
| missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe?
| |
| args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label
| |
| end | |
| | |
| return table.concat ({ | |
| frame:extensionTag ('templatestyles', '', {src=styles}),
| |
| citation0( config, args)
| |
| });
| |
| end | | end |
|
| |
|
| --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
| | return z |
| ]]
| |
| | |
| return {citation = citation}; | |