Line 1: |
Line 1: |
| + | |
| local z = { | | local z = { |
− | error_categories = {};
| + | error_categories = {}; -- for categorizing citations that contain errors |
− | error_ids = {};
| + | error_ids = {}; |
− | message_tail = {};
| + | message_tail = {}; |
| + | maintenance_cats = {}; -- for categorizing citations that aren't erroneous per se, but could use a little work |
| + | properties_cats = {}; -- for categorizing citations based on certain properties, language of source for instance |
| } | | } |
| | | |
− | -- Include translation message hooks, ID and error handling configuration settings. | + | --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- |
− | local cfg = mw.loadData( 'Module:Citation/CS1/Configuration' ); | + | ]] |
| + | local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation |
| + | |
| + | 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 |
| + | |
| + | --[[--------------------------< I S _ S E T >------------------------------------------------------------------ |
| | | |
− | -- Contains a list of all recognized parameters
| + | Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. |
− | local whitelist = mw.loadData( 'Module:Citation/CS1/Whitelist' );
| + | This function is global because it is called from both this module and from Date validation |
| | | |
− | -- Whether variable is set or not
| + | ]] |
| function is_set( var ) | | function is_set( var ) |
− | return not (var == nil or var == '');
| + | return not (var == nil or var == ''); |
| + | end |
| + | |
| + | --[[--------------------------< 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 |
| + | version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate |
| + | the for-loop before it reached the actual end of the list. |
| + | |
| + | ]] |
| + | |
| + | local function first_set (list, count) |
| + | local i = 1; |
| + | while i <= count do -- loop through all items in list |
| + | if is_set( list[i] ) then |
| + | return list[i]; -- return the first set list member |
| + | end |
| + | i = i + 1; -- point to next |
| + | end |
| + | end |
| + | |
| + | --[[--------------------------< I N _ A R R A Y >-------------------------------------------------------------- |
| + | |
| + | Whether needle is in haystack |
| + | |
| + | ]] |
| + | |
| + | local function in_array( needle, haystack ) |
| + | if needle == nil then |
| + | return false; |
| + | end |
| + | for n,v in ipairs( haystack ) do |
| + | if v == needle then |
| + | return n; |
| + | end |
| + | end |
| + | return false; |
| + | end |
| + | |
| + | --[[--------------------------< S U B S T I T U T E >---------------------------------------------------------- |
| + | |
| + | Populates numbered arguments in a message string using an argument table. |
| + | |
| + | ]] |
| + | |
| + | local function substitute( msg, args ) |
| + | return args and mw.message.newRawMessage( msg, args ):plain() or msg; |
| + | end |
| + | |
| + | --[[--------------------------< E R R O R _ C O M M E N T >---------------------------------------------------- |
| + | |
| + | Wraps error messages with css markup according to the state of hidden. |
| + | |
| + | ]] |
| + | local function error_comment( content, hidden ) |
| + | return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content ); |
| + | end |
| + | |
| + | --[[--------------------------< S E T _ E R R O R >-------------------------------------------------------------- |
| + | |
| + | 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. |
| + | |
| + | ]] |
| + | local function set_error( error_id, arguments, raw, prefix, suffix ) |
| + | local error_state = cfg.error_conditions[ error_id ]; |
| + | |
| + | prefix = prefix or ""; |
| + | suffix = suffix or ""; |
| + | |
| + | if error_state == nil then |
| + | error( cfg.messages['undefined_error'] ); |
| + | elseif is_set( error_state.category ) then |
| + | table.insert( z.error_categories, error_state.category ); |
| + | end |
| + | |
| + | 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 in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } ) |
| + | and z.error_ids['citation_missing_title'] then |
| + | return '', false; |
| + | end |
| + | |
| + | message = table.concat({ prefix, message, suffix }); |
| + | |
| + | if raw == true then |
| + | return message, error_state.hidden; |
| + | end |
| + | |
| + | return error_comment( message, error_state.hidden ); |
| + | end |
| + | |
| + | --[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------ |
| + | |
| + | Adds a category to z.maintenance_cats using names from the configuration file with additional text if any. |
| + | To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats. |
| + | |
| + | ]] |
| + | |
| + | local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats |
| + | local function add_maint_cat (key, arguments) |
| + | if not added_maint_cats [key] then |
| + | added_maint_cats [key] = true; -- note that we've added this category |
| + | table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table |
| + | end |
| + | end |
| + | |
| + | --[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- |
| + | |
| + | Adds a category to z.properties_cats using names from the configuration file with additional text if any. |
| + | |
| + | ]] |
| + | |
| + | local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats |
| + | local function add_prop_cat (key, arguments) |
| + | if not added_prop_cats [key] then |
| + | added_prop_cats [key] = true; -- note that we've added this category |
| + | table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table |
| + | end |
| + | end |
| + | |
| + | --[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- |
| + | |
| + | 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. |
| + | |
| + | ]] |
| + | |
| + | local added_vanc_errs; -- flag so we only emit one Vancouver error / category |
| + | local function add_vanc_error () |
| + | if not added_vanc_errs then |
| + | added_vanc_errs = true; -- note that we've added this category |
| + | table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } ); |
| + | end |
| + | 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 |
| + | |
| + | rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between |
| + | the first and last characters the name may use letters, digits, and the hyphen. |
| + | |
| + | Also allowed are IPv4 addresses. IPv6 not supported |
| + | |
| + | domain is expected to be stripped of any path so that the last character in the last character of the tld. tld |
| + | is two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be stripped |
| + | here. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal. |
| + | |
| + | There are several tests: |
| + | the first character of the whole domain name including subdomains must be a letter or a digit |
| + | single-letter/digit second-level domains in the .org TLD |
| + | q, x, and z SL domains in the .com TLD |
| + | i and q SL domains in the .net TLD |
| + | single-letter SL domains in the ccTLDs (where the ccTLD is two letters) |
| + | two-character SL domains in gTLDs (where the gTLD is two or more letters) |
| + | three-plus-character SL domains in gTLDs (where the gTLD is two or more letters) |
| + | IPv4 dot-decimal address format; TLD not allowed |
| + | |
| + | returns true if domain appears to be a proper name and tld or IPv4 address, else false |
| + | |
| + | ]=] |
| + | |
| + | local function is_domain_name (domain) |
| + | if not domain then |
| + | return false; -- if not set, abandon |
| + | end |
| + | |
| + | domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once |
| + | |
| + | if not domain:match ('^[%a%d]') then -- first character must be letter or digit |
| + | return false; |
| + | end |
| + | |
| + | if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname |
| + | return true; |
| + | elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) |
| + | return true; |
| + | elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld |
| + | return true; |
| + | elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address |
| + | return true; |
| + | else |
| + | return false; |
| + | end |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< I S _ U R L >------------------------------------------------------------------ |
| + | |
| + | returns true if the scheme and domain parts of a url appear to be a valid url; else false. |
| + | |
| + | This function is the last step in the validation process. This function is separate because there are cases that |
| + | are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external |
| + | wikilinks. |
| + | |
| + | ]] |
| + | |
| + | local function is_url (scheme, domain) |
| + | if is_set (scheme) then -- if scheme is set check it and domain |
| + | return is_scheme (scheme) and is_domain_name (domain); |
| + | else |
| + | return is_domain_name (domain); -- scheme not set when url is protocol relative |
| + | end |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ |
| + | |
| + | Split a url into a scheme, authority indicator, and domain. |
| + | 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 following the scheme's colon), make sure that there are only 2. |
| + | |
| + | ]] |
| + | |
| + | local function split_url (url_str) |
| + | local scheme, authority, domain; |
| + | |
| + | url_str = url_str:gsub ('(%a)/.*', '%1'); -- strip path information (the capture prevents false replacement of '//') |
| + | |
| + | if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url |
| + | domain = url_str:match ('^//(%S*)') |
| + | elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name |
| + | scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions |
| + | authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; |
| + | if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then |
| + | domain = nil; -- set to nil which will cause an error message |
| + | end |
| + | end |
| + | |
| + | return scheme, domain; |
| end | | end |
| | | |
− | -- First set variable or nil if none | + | |
− | function first_set(...) | + | --[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- |
− | local list = {...};
| + | |
− | for _, var in pairs(list) do
| + | checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls |
− | if is_set( var ) then
| + | |
− | return var;
| + | Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed: |
− | end
| + | # < > [ ] | { } _ |
− | end
| + | 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 |
| + | |
| + | scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url; |
| + | return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------ |
| + | |
| + | Determines whether a URL string appears to be valid. |
| + | |
| + | 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. |
| + | |
| + | ]] |
| + | |
| + | local function check_url( url_str ) |
| + | if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url |
| + | return false; |
| + | end |
| + | local scheme, domain; |
| + | |
| + | scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url; |
| + | return is_url (scheme, domain); -- return true if value appears to be a valid url |
| end | | end |
| | | |
− | -- Whether needle is in haystack | + | |
− | function inArray( needle, haystack ) | + | --[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >---------------------------- |
− | if needle == nil then
| + | |
− | return false;
| + | Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first |
− | end
| + | non-space characters following the opening bracket appear to be a url. The test will also find external wikilinks |
− | for n,v in ipairs( haystack ) do
| + | that use protocol relative urls. Also finds bare urls. |
− | if v == needle then
| + | |
− | return n;
| + | The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests that |
− | end
| + | find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=, |
− | end
| + | and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]] |
− | return false;
| + | is possible as might be [[en://Hus]]. |
| + | |
| + | ]=] |
| + | |
| + | local function is_parameter_ext_wikilink (value) |
| + | local scheme, domain; |
| + | |
| + | value = value:gsub ('([^%s/])/[%a%d].*', '%1'); -- strip path information (the capture prevents false replacement of '//') |
| + | |
| + | if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz] |
| + | scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S+).*%]') |
| + | elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] |
| + | domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]'); |
| + | elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text |
| + | scheme, domain = value:match ('(%a%S*:)(%S+)'); |
| + | elseif value:match ('//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text |
| + | domain = value:match ('//(%S*%.%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 |
| | | |
− | --[[ | + | |
− | Categorize and emit an error message when the citation contains one or more deprecated parameters. Because deprecated parameters (currently |day=, |month=,
| + | --[[-------------------------< C H E C K _ F O R _ U R L >----------------------------------------------------- |
− | |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)
| + | |
− | details of which parameter caused the error message are not provided. Only one error message is emitted regarless of the number of deprecated parameters in the citation.
| + | loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message. |
| + | |
| + | ]] |
| + | |
| + | local function check_for_url (parameter_list) |
| + | local error_message = ''; |
| + | for k, v in pairs (parameter_list) do -- for each parameter in the list |
| + | if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message |
| + | if 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 |
| + | end |
| + | error_message=error_message .. "|" .. k .. "="; -- add the failed parameter |
| + | end |
| + | end |
| + | if is_set (error_message) then -- done looping, if there is an error message, display it |
| + | table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } ); |
| + | end |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< S A F E _ F O R _ I T A L I C S >---------------------------------------------- |
| + | |
| + | Protects a string that will be wrapped in wiki italic markup '' ... '' |
| + | |
| + | Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that |
| + | they will be inverted (i.e. unitalicized) in the resulting references. In addition, <i> and '' tend to interact |
| + | poorly under Mediawiki's HTML tidy. |
| + | |
| + | ]] |
| + | |
| + | local function safe_for_italics( str ) |
| + | if not is_set(str) then |
| + | return str; |
| + | else |
| + | 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 |
| + | |
| + | --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------ |
| + | |
| + | Escape sequences for content that will be used for URL descriptions |
| + | |
| + | ]] |
| + | |
| + | local function safe_for_url( str ) |
| + | if str:match( "%[%[.-%]%]" ) ~= nil then |
| + | table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } ); |
| + | end |
| + | |
| + | return str:gsub( '[%[%]\n]', { |
| + | ['['] = '[', |
| + | [']'] = ']', |
| + | ['\n'] = ' ' } ); |
| + | end |
| + | |
| + | --[[--------------------------< W R A P _ S T Y L E >---------------------------------------------------------- |
| + | |
| + | Applies styling to various parameters. Supplied string is wrapped using a message_list configuration taking one |
| + | argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason |
| + | this function is similar to but separate from wrap_msg(). |
| + | |
| + | ]] |
| + | |
| + | local function wrap_style (key, str) |
| + | if not is_set( str ) then |
| + | return ""; |
| + | elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then |
| + | str = safe_for_italics( str ); |
| + | end |
| + | |
| + | return substitute( cfg.presentation[key], {str} ); |
| + | end |
| + | |
| + | --[[--------------------------< E X T E R N A L _ L I N K >---------------------------------------------------- |
| + | |
| + | Format an external link with error checking |
| + | |
| + | ]] |
| + | |
| + | local function external_link( URL, label, source ) |
| + | local error_str = ""; |
| + | if not is_set( label ) then |
| + | label = URL; |
| + | if is_set( source ) then |
| + | error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " ); |
| + | else |
| + | error( cfg.messages["bare_url_no_origin"] ); |
| + | end |
| + | end |
| + | if not check_url( URL ) then |
| + | error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str; |
| + | end |
| + | return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str }); |
| + | end |
| + | |
| + | --[[--------------------------< E X T E R N A L _ L I N K _ I D >---------------------------------------------- |
| + | |
| + | Formats a wiki style external link |
| + | |
| ]] | | ]] |
− | function deprecated_parameter() | + | |
− | if true ~= Page_in_deprecated_cat then -- if we haven't been here before then set a | + | local function external_link_id(options) |
− | Page_in_deprecated_cat=true; -- sticky flag so that if there are more than one deprecated parameter the category is added only once | + | local url_string = options.id; |
− | table.insert( z.message_tail, { seterror( 'deprecated_params', {error_message}, true ) } ); -- add error message
| + | if options.encode == true or options.encode == nil then |
| + | url_string = mw.uri.encode( url_string ); |
| end | | end |
| + | return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]', |
| + | options.link, options.label, options.separator or " ", |
| + | options.prefix, url_string, options.suffix or "", |
| + | mw.text.nowiki(options.id) |
| + | ); |
| end | | end |
| | | |
− | -- Populates numbered arguments in a message string using an argument table. | + | --[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >-------------------------------------- |
− | function substitute( msg, args ) | + | |
− | -- return args and tostring( mw.message.newRawMessage( msg, args ) ) or msg; | + | Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the |
− | return args and mw.message.newRawMessage( msg, args ):plain() or msg; | + | offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated |
| + | parameters in the citation. |
| + | |
| + | ]] |
| + | |
| + | local page_in_deprecated_cat; -- sticky flag so that the category is added only once |
| + | local function deprecated_parameter(name) |
| + | if not page_in_deprecated_cat then |
| + | page_in_deprecated_cat = true; -- note that we've added this category |
| + | table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message |
| + | end |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< K E R N _ Q U O T E S >-------------------------------------------------------- |
| + | |
| 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. | | 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. |
− | This function will positive kern either single or double quotes: | + | This function will positive kern either single or double quotes: |
| "'Unkerned title with leading and trailing single quote marks'" | | "'Unkerned title with leading and trailing single quote marks'" |
| " 'Kerned title with leading and trailing single quote marks' " (in real life the kerning isn't as wide as this example) | | " '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 wikimarkup) are not kerned. |
| + | |
| + | Call this function for chapter titles, for website titles, etc; not for book titles. |
| + | |
| ]] | | ]] |
− | function kern_quotes (str) | + | |
− | local left='<span style="padding-left:0.2em;">%1</span>'; -- spacing to use when title contains leading single or double quote mark | + | local function kern_quotes (str) |
− | local right='<span style="padding-right:0.2em;">%1</span>'; -- spacing to use when title contains trailing single or double quote mark | + | local cap=''; |
| + | local cap2=''; |
| | | |
− | if str:match ("^[\"\'][^\']") then | + | cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes |
− | str = string.gsub( str, "^[\"\']", left, 1 ); -- replace (captured) leading single or double quote with left-side <span> | + | if is_set (cap) then |
| + | str = substitute (cfg.presentation['kern-left'], {cap, cap2}); |
| end | | end |
− | if str:match ("[^\'][\"\']$") then | + | |
− | str = string.gsub( str, "[\"\']$", right, 1 ); -- replace (captured) trailing single or double quote with right-side <span> | + | cap, cap2 = str:match ("^(.+[^\'])([\"\'])$") |
| + | if is_set (cap) then |
| + | str = substitute (cfg.presentation['kern-right'], {cap, cap2}); |
| end | | end |
| return str; | | return str; |
| end | | end |
| | | |
− | -- Wraps a string using a message_list configuration taking one argument | + | --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- |
− | function wrap( key, str, lower )
| + | |
− | if not is_set( str ) then
| + | |script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should |
− | return "";
| + | 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 |
− | elseif inArray( key, { 'italic-title', 'trans-italic-title' } ) then
| + | in italic markup. |
− | str = safeforitalics( str );
| + | |
− | end
| + | 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. |
− | if lower == true then
| + | |
− | return substitute( cfg.messages[key]:lower(), {str} );
| + | |script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon: |
− | else
| + | |script-title=ja:*** *** (where * represents a Japanese character) |
− | return substitute( cfg.messages[key], {str} );
| + | Spaces between the two-character code and the colon and the colon and the first script character are allowed: |
− | end
| + | |script-title=ja : *** *** |
| + | |script-title=ja: *** *** |
| + | |script-title=ja :*** *** |
| + | Spaces preceding the prefix are allowed: |script-title = ja:*** *** |
| + | |
| + | The prefix is checked for validity. If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can |
| + | know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute |
| + | is not added. At this time there is no error message for this condition. |
| + | |
| + | Supports |script-title= and |script-chapter= |
| + | |
| + | TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script; |
| + | ]] |
| + | |
| + | local function format_script_value (script_value) |
| + | local lang=''; -- initialize to empty string |
| + | local name; |
| + | if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix |
| + | lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script |
| + | if not is_set (lang) then |
| + | return ''; -- script_value was just the prefix so return empty string |
| + | end |
| + | -- if we get this far we have prefix and script |
| + | name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize |
| + | if is_set (name) then -- is prefix a proper ISO 639-1 language code? |
| + | script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script |
| + | -- is prefix one of these language codes? |
| + | if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then |
| + | add_prop_cat ('script_with_name', {name, lang}) |
| + | else |
| + | add_prop_cat ('script') |
| + | end |
| + | lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute |
| + | else |
| + | lang = ''; -- invalid so set lang to empty string |
| + | end |
| + | end |
| + | script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl |
| + | |
| + | return script_value; |
| + | end |
| + | |
| + | --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ |
| + | |
| + | Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been |
| + | wrapped in <bdi> tags. |
| + | ]] |
| + | |
| + | local function script_concatenate (title, script) |
| + | if is_set (script) then |
| + | script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error |
| + | if is_set (script) then |
| + | title = title .. ' ' .. script; -- concatenate title and script title |
| + | end |
| + | end |
| + | return title; |
| end | | end |
| | | |
− | --[[ | + | |
− | Argument wrapper. This function provides support for argument | + | --[[--------------------------< W R A P _ M S G >-------------------------------------------------------------- |
− | mapping defined in the configuration file so that multiple names | + | |
− | can be transparently aliased to single internal variable. | + | Applies additional message text to various parameter values. Supplied string is wrapped using a message_list |
| + | 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(). |
| + | |
| + | ]] |
| + | |
| + | local function wrap_msg (key, str, lower) |
| + | if not is_set( str ) then |
| + | return ""; |
| + | end |
| + | if true == lower then |
| + | local msg; |
| + | msg = cfg.messages[key]:lower(); -- set the message to lower case before |
| + | return substitute( msg, str ); -- including template text |
| + | else |
| + | return substitute( cfg.messages[key], str ); |
| + | end |
| + | end |
| + | |
| + | |
| + | --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- |
| + | |
| + | This function is used by select_one() to determine if one of a list of alias parameters is in the argument list |
| + | provided by the template. |
| + | |
| + | Input: |
| + | args – pointer to the arguments table from calling template |
| + | alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration |
| + | index – for enumerated parameters, identifies which one |
| + | enumerated – true/false flag used choose how enumerated aliases are examined |
| + | value – value associated with an alias that has previously been selected; nil if not yet selected |
| + | selected – the alias that has previously been selected; nil if not yet selected |
| + | error_list – list of aliases that are duplicates of the alias already selected |
| + | |
| + | Returns: |
| + | value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected |
| + | selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected |
| + | |
| + | ]] |
| + | |
| + | local function is_alias_used (args, alias, index, enumerated, value, selected, error_list) |
| + | if enumerated then -- is this a test for an enumerated parameters? |
| + | alias = alias:gsub ('#', index); -- replace '#' with the value in index |
| + | else |
| + | alias = alias:gsub ('#', ''); -- remove '#' if it exists |
| + | end |
| + | |
| + | if is_set(args[alias]) then -- alias is in the template's argument list |
| + | if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases |
| + | local skip; |
| + | for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias |
| + | if v == alias then |
| + | skip = true; |
| + | break; -- has been added so stop looking |
| + | end |
| + | end |
| + | if not skip then -- has not been added so |
| + | table.insert( error_list, alias ); -- add error alias to the error list |
| + | end |
| + | else |
| + | value = args[alias]; -- not yet selected an alias, so select this one |
| + | selected = alias; |
| + | end |
| + | end |
| + | return value, selected; -- return newly selected alias, or previously selected alias |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- |
| + | |
| + | Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just |
| + | names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified |
| + | by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'. |
| + | |
| + | Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities. |
| + | |
| + | |
| + | Generates an error if more than one match is present. |
| + | |
| + | ]] |
| + | |
| + | local function select_one( args, aliases_list, error_condition, index ) |
| + | local value = nil; -- the value assigned to the selected parameter |
| + | local selected = ''; -- the name of the parameter we have chosen |
| + | local error_list = {}; |
| + | |
| + | if index ~= nil then index = tostring(index); end |
| + | |
| + | for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list |
| + | if alias:match ('#') then -- if this alias can be enumerated |
| + | if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases |
| + | value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias |
| + | end |
| + | value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias |
| + | else |
| + | value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias |
| + | end |
| + | end |
| + | |
| + | if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names() |
| + | local error_str = ""; |
| + | for _, k in ipairs( error_list ) do |
| + | if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end |
| + | error_str = error_str .. wrap_style ('parameter', k); |
| + | end |
| + | if #error_list > 1 then |
| + | error_str = error_str .. cfg.messages['parameter-final-separator']; |
| + | else |
| + | error_str = error_str .. cfg.messages['parameter-pair-separator']; |
| + | end |
| + | error_str = error_str .. wrap_style ('parameter', selected); |
| + | table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } ); |
| + | end |
| + | |
| + | return value, selected; |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >-------------------------------------- |
| + | |
| + | Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta- |
| + | parameter (chapter_url_source used for error messages). |
| + | |
| + | ]] |
| + | |
| + | local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) |
| + | local chapter_error = ''; |
| + | |
| + | if not is_set (chapter) then |
| + | chapter = ''; -- to be safe for concatenation |
| + | else |
| + | if false == no_quotes then |
| + | chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks |
| + | chapter = wrap_style ('quoted-title', chapter); |
| + | end |
| + | end |
| + | |
| + | chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
| + | |
| + | if is_set (transchapter) then |
| + | transchapter = wrap_style ('trans-quoted-title', transchapter); |
| + | if is_set (chapter) then |
| + | chapter = chapter .. ' ' .. transchapter; |
| + | else -- here when transchapter without chapter or script-chapter |
| + | chapter = transchapter; -- |
| + | chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); |
| + | end |
| + | end |
| + | |
| + | if is_set (chapterurl) then |
| + | chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate |
| + | end |
| + | |
| + | return chapter .. chapter_error; |
| + | end |
| + | |
| + | --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- |
| + | |
| + | This function searches a parameter's value for nonprintable 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(). |
| + | |
| + | Detects but ignores the character pattern that results from the transclusion of {{'}} templates. |
| + | |
| + | 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. |
| + | |
| + | ]] |
| + | |
| + | local function has_invisible_chars (param, v) |
| + | local position = ''; -- position of invisible char or starting position of stripmarker |
| + | local dummy; -- end of matching string; not used but required to hold end position when a capture is returned |
| + | local capture; -- used by stripmarker detection to hold name of the stripmarker |
| + | local i=1; |
| + | local stripmarker, apostrophe; |
| + | |
| + | while cfg.invisible_chars[i] do |
| + | local char=cfg.invisible_chars[i][1] -- the character or group name |
| + | local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it |
| + | position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern |
| + | |
| + | if position then |
| + | -- if 'nowiki' == capture or 'math' == capture or ('ref' == capture and 'quote' == param) then -- nowiki, math, or quote param and ref stripmarker (not an error condition) |
| + | if 'nowiki' == capture or 'math' == capture then -- nowiki, math stripmarker (not an error condition) |
| + | stripmarker = true; -- set a flag |
| + | elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker |
| + | position = nil; -- unset |
| + | elseif 'apostrophe' == char then -- apostrophe template uses ‍, hair space and zero-width space |
| + | apostrophe = true; |
| + | elseif true == apostrophe and in_array (char, {'zero width joiner', 'zero width space', 'hair space'}) then |
| + | position = nil; -- unset |
| + | else |
| + | local err_msg; |
| + | if capture then |
| + | err_msg = capture .. ' ' .. char; |
| + | else |
| + | err_msg = char .. ' ' .. 'character'; |
| + | end |
| + | |
| + | table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message |
| + | return; -- and done with this parameter |
| + | end |
| + | end |
| + | i=i+1; -- bump our index |
| + | end |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< A R G U M E N T _ W R A P P E R >---------------------------------------------- |
| + | |
| + | Argument wrapper. This function provides support for argument mapping defined in the configuration file so that |
| + | multiple names can be transparently aliased to single internal variable. |
| + | |
| ]] | | ]] |
− | function argument_wrapper( args ) | + | |
− | local origin = {};
| + | local function argument_wrapper( args ) |
− |
| + | local origin = {}; |
− | return setmetatable({
| + | |
− | ORIGIN = function( self, k )
| + | return setmetatable({ |
− | local dummy = self[k]; --force the variable to be loaded.
| + | ORIGIN = function( self, k ) |
− | return origin[k];
| + | local dummy = self[k]; --force the variable to be loaded. |
− | end
| + | return origin[k]; |
− | },
| + | end |
− | {
| + | }, |
− | __index = function ( tbl, k )
| + | { |
− | if origin[k] ~= nil then
| + | __index = function ( tbl, k ) |
− | return nil;
| + | if origin[k] ~= nil then |
− | end
| + | return nil; |
− |
| + | end |
− | local args, list, v = args, cfg.aliases[k];
| + | |
− |
| + | local args, list, v = args, cfg.aliases[k]; |
− | if type( list ) == 'table' then
| + | |
− | v, origin[k] = selectone( args, list, 'redundant_parameters' );
| + | if type( list ) == 'table' then |
− | if origin[k] == nil then
| + | v, origin[k] = select_one( args, list, 'redundant_parameters' ); |
− | origin[k] = ''; -- Empty string, not nil
| + | if origin[k] == nil then |
− | end
| + | origin[k] = ''; -- Empty string, not nil |
− | elseif list ~= nil then
| + | end |
− | v, origin[k] = args[list], list;
| + | elseif list ~= nil then |
− | else
| + | v, origin[k] = args[list], list; |
− | -- maybe let through instead of raising an error?
| + | else |
− | -- v, origin[k] = args[k], k;
| + | -- maybe let through instead of raising an error? |
− | error( cfg.messages['unknown_argument_map'] );
| + | -- v, origin[k] = args[k], k; |
− | end
| + | error( cfg.messages['unknown_argument_map'] ); |
− |
| + | end |
− | -- Empty strings, not nil;
| + | |
− | if v == nil then
| + | -- Empty strings, not nil; |
− | v = cfg.defaults[k] or '';
| + | if v == nil then |
− | origin[k] = '';
| + | v = cfg.defaults[k] or ''; |
− | end
| + | origin[k] = ''; |
− |
| + | end |
− | tbl = rawset( tbl, k, v );
| + | |
− | return v;
| + | tbl = rawset( tbl, k, v ); |
− | end,
| + | return v; |
− | });
| + | end, |
| + | }); |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< V A L I D A T E >-------------------------------------------------------------- |
| Looks for a parameter's name in the whitelist. | | Looks for a parameter's name in the whitelist. |
| | | |
Line 144: |
Line 881: |
| false - deprecated, supported parameters | | false - deprecated, supported parameters |
| nil - unsupported parameters | | nil - unsupported parameters |
| + | |
| ]] | | ]] |
− | function validate( name ) | + | |
| + | local function validate( name ) |
| local name = tostring( name ); | | local name = tostring( name ); |
| local state = whitelist.basic_arguments[ name ]; | | local state = whitelist.basic_arguments[ name ]; |
Line 152: |
Line 891: |
| if true == state then return true; end -- valid actively supported parameter | | if true == state then return true; end -- valid actively supported parameter |
| if false == state then | | if false == state then |
− | deprecated_parameter (); -- parameter is deprecated but still supported | + | deprecated_parameter (name); -- parameter is deprecated but still supported |
| return true; | | return true; |
| end | | end |
Line 161: |
Line 900: |
| if true == state then return true; end -- valid actively supported parameter | | if true == state then return true; end -- valid actively supported parameter |
| if false == state then | | if false == state then |
− | deprecated_parameter (); -- parameter is deprecated but still supported | + | deprecated_parameter (name); -- parameter is deprecated but still supported |
| return true; | | return true; |
| end | | end |
Line 168: |
Line 907: |
| end | | end |
| | | |
− | -- Formats a comment for error trapping | + | |
− | function errorcomment( content, hidden ) | + | -- Formats a wiki style internal link |
− | return wrap( hidden and 'hidden-error' or 'visible-error', content );
| + | local function internal_link_id(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 |
| + | |
| + | |
| + | --[[--------------------------< N O W R A P _ D A T E >-------------------------------------------------------- |
| + | |
| + | When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is |
| + | MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY |
| + | |
| + | DOES NOT yet support MMMM YYYY or any of the date ranges. |
| + | |
| + | ]] |
| + | |
| + | local function nowrap_date (date) |
| + | local cap=''; |
| + | local cap2=''; |
| + | |
| + | if date:match("^%d%d%d%d%-%d%d%-%d%d$") then |
| + | date = substitute (cfg.presentation['nowrap1'], date); |
| + | |
| + | elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then |
| + | cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$"); |
| + | date = substitute (cfg.presentation['nowrap2'], {cap, cap2}); |
| + | end |
| + | |
| + | return date; |
| + | end |
| + | |
| + | --[[--------------------------< IS _ V A L I D _ I S X N >----------------------------------------------------- |
| + | |
| + | ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn(). |
| + | 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, |
| + | spaces and other non-isxn characters. |
| + | |
| + | ]] |
| + | |
| + | local function is_valid_isxn (isxn_str, len) |
| + | local temp = 0; |
| + | isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58 |
| + | len = len+1; -- adjust to be a loop counter |
| + | 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 (compares the byte value of 'X' which is 0x58) |
| + | temp = temp + 10*( len - i ); -- it represents 10 decimal |
| + | else |
| + | temp = temp + tonumber( string.char(v) )*(len-i); |
| + | end |
| + | end |
| + | return temp % 11 == 0; -- returns true if calculation result is zero |
| end | | end |
| | | |
− | --[[ | + | |
− | Sets an error condition and returns the appropriate error message. The actual placement
| + | --[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >---------------------------------------------- |
− | of the error message in the output is the responsibility of the calling function.
| + | |
| + | ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit. |
| + | If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length |
| + | and stripped of dashes, spaces and other non-isxn-13 characters. |
| + | |
| ]] | | ]] |
− | function seterror( error_id, arguments, raw, prefix, suffix ) | + | |
− | local error_state = cfg.error_conditions[ error_id ];
| + | local function is_valid_isxn_13 (isxn_str) |
− |
| + | local temp=0; |
− | prefix = prefix or "";
| + | |
− | suffix = suffix or "";
| + | isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39 |
− |
| + | for i, v in ipairs( isxn_str ) do |
− | if error_state == nil then
| + | temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) ); -- multiply odd index digits by 1, even index digits by 3 and sum; includes check digit |
− | error( cfg.messages['undefined_error'] );
| + | end |
− | elseif is_set( error_state.category ) then
| + | return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct |
− | table.insert( z.error_categories, error_state.category );
| |
− | end
| |
− |
| |
− | 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
| |
− |
| |
− | 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 | + | --[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------ |
− | function externallinkid(options) | + | |
− | local url_string = options.id;
| + | Determines whether an ISBN string is valid |
− | if options.encode == true or options.encode == nil then
| + | |
− | url_string = mw.uri.encode( url_string );
| + | ]] |
− | end
| + | |
− | return mw.ustring.format( '[[%s|%s]]%s[%s%s%s %s]',
| + | local function check_isbn( isbn_str ) |
− | options.link, options.label, options.separator or " ",
| + | 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 |
− | options.prefix, url_string, options.suffix or "",
| + | isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces |
− | mw.text.nowiki(options.id)
| + | local len = isbn_str:len(); |
− | );
| + | |
| + | if len ~= 10 and len ~= 13 then |
| + | return false; |
| + | end |
| + | |
| + | 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; ismn begins with 979 |
| + | return is_valid_isxn_13 (isbn_str); |
| + | end |
| end | | end |
| | | |
− | -- Formats a wiki style internal link | + | --[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------ |
− | function internallinkid(options) | + | |
− | return mw.ustring.format( '[[%s|%s]]%s[[%s%s%s|%s]]',
| + | Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the |
− | options.link, options.label, options.separator or " ",
| + | same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf |
− | options.prefix, options.id, options.suffix or "",
| + | section 2, pages 9–12. |
− | mw.text.nowiki(options.id)
| + | |
− | );
| + | ]] |
| + | |
| + | local function ismn (id) |
| + | local handler = cfg.id_handlers['ISMN']; |
| + | local text; |
| + | local valid_ismn = true; |
| + | |
| + | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn |
| + | |
| + | if 13 ~= id:len() or id:match( "^9790%d*$" ) == nil then -- ismn must be 13 digits and begin 9790 |
| + | valid_ismn = false; |
| + | else |
| + | valid_ismn=is_valid_isxn_13 (id); -- validate ismn |
| + | end |
| + | |
| + | -- text = internal_link_id({link = handler.link, label = handler.label, -- use this (or external version) when there is some place to link to |
| + | -- prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| + | |
| + | text="[[" .. handler.link .. "|" .. handler.label .. "]]" .. handler.separator .. id; -- because no place to link to yet |
| + | |
| + | if false == valid_ismn then |
| + | text = text .. ' ' .. set_error( 'bad_ismn' ) -- add an error message if the issn is invalid |
| + | end |
| + | |
| + | return text; |
| + | end |
| + | |
| + | --[[--------------------------< I S S N >---------------------------------------------------------------------- |
| + | |
| + | 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: |
| + | |
| + | |issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link |
| + | |
| + | 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 |
| + | 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 |
| + | error message. The issn is always displayed with a hyphen, even if the issn was given as a single group of 8 digits. |
| + | |
| + | ]] |
| + | |
| + | local 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; |
| + | |
| + | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn |
| + | |
| + | 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 |
| + | valid_issn=false; -- wrong length or improper character |
| + | else |
| + | valid_issn=is_valid_isxn(id, 8); -- validate issn |
| + | end |
| + | |
| + | if true == valid_issn then |
| + | id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version |
| + | else |
| + | id = issn_copy; -- if not valid, use the show the invalid issn with error message |
| + | end |
| + | |
| + | text = external_link_id({link = handler.link, label = handler.label, |
| + | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| + | |
| + | if false == valid_issn then |
| + | text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid |
| + | end |
| + | |
| + | return text |
| end | | end |
| | | |
− | -- Format an external link with error checking | + | --[[--------------------------< A M A Z O N >------------------------------------------------------------------ |
− | function externallink( URL, label, source ) | + | |
− | local error_str = "";
| + | Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha |
− | if not is_set( label ) then
| + | characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit |
− | label = URL;
| + | isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=. |
− | if is_set( source ) then
| + | Error message if not 10 characters, if not isbn10, if mixed and first character is a digit. |
− | error_str = seterror( 'bare_url_missing_title', { wrap( 'parameter', source ) }, false, " " );
| + | |
− | else
| + | ]] |
− | error( cfg.messages["bare_url_no_origin"] );
| + | |
− | end
| + | local function amazon(id, domain) |
− | end
| + | local err_cat = "" |
− | if not checkurl( URL ) then
| + | |
− | error_str = seterror( 'bad_url', {}, false, " " ) .. error_str;
| + | if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then |
− | end
| + | err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters |
− | return table.concat({ "[", URL, " ", safeforurl( label ), "]", error_str });
| + | else |
| + | if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") then -- if 10-digit numeric (or 9 digits with terminal X) |
| + | if check_isbn( id ) then -- see if asin value is isbn10 |
| + | add_maint_cat ('ASIN'); |
| + | elseif not is_set (err_cat) then |
| + | err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10 |
| + | end |
| + | elseif not id:match("^%u[%d%u]+$") then |
| + | err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha |
| + | end |
| + | end |
| + | if not is_set(domain) then |
| + | domain = "com"; |
| + | elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom |
| + | domain = "co." .. domain; |
| + | elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico |
| + | domain = "com." .. domain; |
| + | end |
| + | local handler = cfg.id_handlers['ASIN']; |
| + | return external_link_id({link=handler.link, |
| + | label=handler.label, prefix=handler.prefix .. domain .. "/dp/", |
| + | id=id, encode=handler.encode, separator = handler.separator}) .. err_cat; |
| end | | end |
| | | |
− | -- Formats a link to Amazon | + | --[[--------------------------< A R X I V >-------------------------------------------------------------------- |
− | function amazon(id, domain) | + | |
− | if not is_set(domain) then
| + | See: http://arxiv.org/help/arxiv_identifier |
− | domain = "com"
| + | |
− | elseif ( "jp" == domain or "uk" == domain ) then
| + | format and error check arXiv identifier. There are three valid forms of the identifier: |
− | domain = "co." .. domain
| + | the first form, valid only between date codes 9108 and 0703 is: |
− | end
| + | arXiv:<archive>.<class>/<date code><number><version> |
− | local handler = cfg.id_handlers['ASIN'];
| + | where: |
− | return externallinkid({link = handler.link,
| + | <archive> is a string of alpha characters - may be hyphenated; no other punctuation |
− | label=handler.label , prefix="//www.amazon."..domain.."/dp/",id=id,
| + | <class> is a string of alpha characters - may be hyphenated; no other punctuation |
− | encode=handler.encode, separator = handler.separator})
| + | <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 |
| + | <version> is a 1 or more digit number preceded with a lowercase v; no spaces (undocumented) |
| + | |
| + | the second form, valid from April 2007 through December 2014 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 |
| + | |
| + | the third form, valid from January 2015 is: |
| + | arXiv:<date code>.<number><version> |
| + | where: |
| + | <date code> and <version> are as defined for 0704-1412 |
| + | <number> is a five-digit number |
| + | ]] |
| + | |
| + | local function arxiv (id, class) |
| + | local handler = cfg.id_handlers['ARXIV']; |
| + | local year, month, version; |
| + | local err_cat = ''; |
| + | local text; |
| + | |
| + | if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version |
| + | year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$"); |
| + | year = tonumber(year); |
| + | month = tonumber(month); |
| + | if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month |
| + | ((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok? |
| + | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
| + | end |
| + | elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version |
| + | year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); |
| + | year = tonumber(year); |
| + | month = tonumber(month); |
| + | if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years) |
| + | ((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)? |
| + | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
| + | end |
| + | elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version |
| + | year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); |
| + | year = tonumber(year); |
| + | month = tonumber(month); |
| + | if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years) |
| + | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
| + | end |
| + | else |
| + | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format |
| + | end |
| + | |
| + | text = external_link_id({link = handler.link, label = handler.label, |
| + | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| + | |
| + | if is_set (class) then |
| + | class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink |
| + | else |
| + | class = ''; -- empty string for concatenation |
| + | end |
| + | |
| + | return text .. class; |
| + | 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. |
| + | |
| + | Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function. |
| + | ]] |
| + | |
| + | local function normalize_lccn (lccn) |
| + | lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace |
| + | |
| + | 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 |
| + | |
| + | if nil ~= suffix then -- if there was a hyphen |
| + | suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6 |
| + | lccn=prefix..suffix; -- reassemble the lccn |
| + | end |
| + | |
| + | return lccn; |
| + | 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/ |
| + | |
| + | length = 8 then all digits |
| + | length = 9 then lccn[1] is lower case alpha |
| + | length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits |
| + | length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits |
| + | length = 12 then lccn[1] and lccn[2] are both lower case alpha |
| + | |
| + | ]] |
| + | |
| + | local function lccn(lccn) |
| + | local handler = cfg.id_handlers['LCCN']; |
| + | local err_cat = ''; -- presume that LCCN is valid |
| + | local id = lccn; -- local copy of the lccn |
| + | |
| + | id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) |
| + | local len = id:len(); -- get the length of the lccn |
| + | |
| + | if 8 == len then |
| + | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message |
| + | end |
| + | elseif 9 == len then -- LCCN should be adddddddd |
| + | if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern? |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message |
| + | end |
| + | elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd |
| + | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... |
| + | if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
| + | end |
| + | end |
| + | elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd |
| + | if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
| + | end |
| + | elseif 12 == len then -- LCCN should be aadddddddddd |
| + | if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
| + | end |
| + | else |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message |
| + | end |
| + | |
| + | if not is_set (err_cat) and nil ~= lccn:find ('%s') then |
| + | err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message |
| + | end |
| + | |
| + | return external_link_id({link = handler.link, label = handler.label, |
| + | prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| end | | end |
| | | |
Line 266: |
Line 1,286: |
| 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. | | 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 pmid(id) |
| local test_limit = 30000000; -- update this value as PMIDs approach | | local test_limit = 30000000; -- update this value as PMIDs approach |
| local handler = cfg.id_handlers['PMID']; | | local handler = cfg.id_handlers['PMID']; |
Line 272: |
Line 1,293: |
| | | |
| if id:match("[^%d]") then -- if PMID has anything but digits | | if id:match("[^%d]") then -- if PMID has anything but digits |
− | err_cat = ' ' .. seterror( 'bad_pmid' ); -- set an error message | + | err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message |
| else -- PMID is only digits | | else -- PMID is only digits |
| local id_num = tonumber(id); -- convert id to a number for range testing | | 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 | | 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 | + | err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message |
| end | | end |
| end | | end |
| | | |
− | return externallinkid({link = handler.link, label = handler.label, | + | return external_link_id({link = handler.link, label = handler.label, |
| prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; | | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< I S _ E M B A R G O E D >------------------------------------------------------ |
| + | |
| Determines if a PMC identifier's online version is embargoed. Compares the date in |embargo= against today's date. If embargo date is | | 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; otherwse, returns false because the embargo has expired or |embargo= not set in this cite. | + | in the future, returns the content of |embargo=; otherwise, returns and empty string because the embargo has expired or because |
| + | |embargo= was not set in this cite. |
| + | |
| ]] | | ]] |
− | function is_embargoed(embargo) | + | |
− | if is_set(embargo) then | + | local function is_embargoed (embargo) |
| + | if is_set (embargo) then |
| local lang = mw.getContentLanguage(); | | local lang = mw.getContentLanguage(); |
| local good1, embargo_date, good2, todays_date; | | local good1, embargo_date, good2, todays_date; |
Line 295: |
Line 1,320: |
| good2, todays_date = pcall( lang.formatDate, lang, 'U' ); | | 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? | + | if good1 and good2 then -- if embargo date and today's date are good dates |
− | return true; -- still embargoed
| + | if tonumber( embargo_date ) >= tonumber( todays_date ) then -- is embargo date is in the future? |
| + | return embargo; -- still embargoed |
| + | else |
| + | add_maint_cat ('embargo') |
| + | return ''; -- unset because embargo has expired |
| + | end |
| end | | end |
| end | | end |
− | return false; -- embargo expired or |embargo= not set | + | return ''; -- |embargo= not set return empty string |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< P M C >------------------------------------------------------------------------ |
− | Formats a PMC and checks for embargoed articles. 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 | + | Format a PMC, do simple error checking, and check for embargoed articles. |
− | the PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix.
| + | |
| + | 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 date is today or in the past, or if it is empty or omitted, then the |
| + | PMC identifier is linked to the article through the link at cfg.id_handlers['PMC'].prefix. |
| + | |
| + | PMC embargo date testing is done in function is_embargoed () which is called earlier because when the citation |
| + | has |pmc=<value> but does not have a |url= then |title= is linked with the PMC link. Function is_embargoed () |
| + | returns the embargo date if the PMC article is still embargoed, otherwise it returns an empty string. |
| + | |
| + | 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 function pmc(id, embargo) |
| + | local test_limit = 5000000; -- update this value as PMCs approach |
| local handler = cfg.id_handlers['PMC']; | | local handler = cfg.id_handlers['PMC']; |
− |
| + | local err_cat = ''; -- presume that PMC is valid |
| + | |
| local text; | | local text; |
| | | |
− | if is_embargoed(embargo) then | + | if id:match("[^%d]") then -- if PMC has anything but digits |
− | text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id; --still embargoed so no external link | + | err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message |
| + | 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 = ' ' .. set_error( 'bad_pmc' ); -- set an error message |
| + | end |
| + | end |
| + | |
| + | if is_set (embargo) then -- is PMC is still embargoed? |
| + | text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link |
| else | | else |
− | text = externallinkid({link = handler.link, label = handler.label, --no embargo date, ok to link to article | + | text = external_link_id({link = handler.link, label = handler.label, -- no embargo date or embargo has expired, ok to link to article |
− | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) | + | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
| end | | end |
| return text; | | return text; |
Line 322: |
Line 1,375: |
| | | |
| -- Formats a DOI and checks for DOI errors. | | -- Formats a DOI and checks for DOI errors. |
− | function doi(id, inactive) | + | |
− | local cat = ""
| + | -- DOI names contain two parts: prefix and suffix separated by a forward slash. |
− | local handler = cfg.id_handlers['DOI'];
| + | -- Prefix: directory indicator '10.' followed by a registrant code |
− |
| + | -- Suffix: character string of any length chosen by the registrant |
− | local text;
| + | |
| + | -- This function checks a DOI name for: prefix/suffix. If the doi name contains spaces or endashes, |
| + | -- or, if it ends with a period or a comma, this function will emit a bad_doi error message. |
| + | |
| + | -- 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. |
| + | |
| + | local function doi(id, inactive) |
| + | local cat = "" |
| + | local handler = cfg.id_handlers['DOI']; |
| + | |
| + | local text; |
| if is_set(inactive) then | | 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 | | local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date |
Line 337: |
Line 1,401: |
| inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")" | | inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")" |
| else | | else |
− | text = externallinkid({link = handler.link, label = handler.label, | + | text = external_link_id({link = handler.link, label = handler.label, |
| prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) | | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| inactive = "" | | inactive = "" |
| end | | end |
| | | |
− | if nil == id:match("^10%.[^%s–]-[^%.,]$") then -- doi must begin with '10.', must not contain spaces or endashes, and must not end with period or comma | + | if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") 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 |
− | cat = ' ' .. seterror( 'bad_doi' ); | + | cat = ' ' .. set_error( 'bad_doi' ); |
| end | | end |
| return text .. inactive .. cat | | return text .. inactive .. cat |
| end | | end |
| | | |
− | -- Formats an OpenLibrary link, and checks for associated errors.
| |
− | function openlibrary(id)
| |
− | local code = id:sub(-1,-1)
| |
− | local handler = cfg.id_handlers['OL'];
| |
− | 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})
| |
− | elseif ( code == "M" ) then
| |
− | return externallinkid({link=handler.link, label=handler.label,
| |
− | prefix="http://openlibrary.org/books/OL",id=id, separator=handler.separator,
| |
− | encode = handler.encode})
| |
− | 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
| |
− | return externallinkid({link=handler.link, label=handler.label,
| |
− | prefix= "http://openlibrary.org/OL",id=id, separator=handler.separator,
| |
− | encode = handler.encode}) ..
| |
− | ' ' .. seterror( 'bad_ol' );
| |
− | end
| |
− | end
| |
| | | |
− | --[[ | + | --[[--------------------------< O P E N L I B R A R Y >-------------------------------------------------------- |
− | 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:
| + | Formats an OpenLibrary link, and checks for associated errors. |
| | | |
− | |issn=0819 4327 gives: [http://www.worldcat.org/issn/0819 4327 0819 4327] -- can't have spaces in an external link
| |
− |
| |
− | 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
| |
− | 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
| |
− | 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 function openlibrary(id) |
− | local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate | + | local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W' |
− | local handler = cfg.id_handlers['ISSN']; | + | local handler = cfg.id_handlers['OL']; |
− | local text;
| |
− | local valid_issn = true;
| |
− | | |
− | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and ndashes from the issn
| |
| | | |
− | if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 didgits long, containing only 0-9 or X in the last position | + | if ( code == "A" ) then |
− | valid_issn=false; -- wrong length or improper character
| + | return external_link_id({link=handler.link, label=handler.label, |
| + | prefix=handler.prefix .. 'authors/OL', |
| + | id=id, separator=handler.separator, encode = handler.encode}) |
| + | elseif ( code == "M" ) then |
| + | return external_link_id({link=handler.link, label=handler.label, |
| + | prefix=handler.prefix .. 'books/OL', |
| + | id=id, separator=handler.separator, encode = handler.encode}) |
| + | elseif ( code == "W" ) then |
| + | return external_link_id({link=handler.link, label=handler.label, |
| + | prefix=handler.prefix .. 'works/OL', |
| + | id=id, separator=handler.separator, encode = handler.encode}) |
| else | | else |
− | valid_issn=is_valid_isxn(id, 8); -- validate issn | + | return external_link_id({link=handler.link, label=handler.label, |
| + | prefix=handler.prefix .. 'OL', |
| + | id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' ); |
| end | | end |
| + | end |
| | | |
− | if true == valid_issn then
| + | |
− | id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
| + | --[[--------------------------< M E S S A G E _ I D >---------------------------------------------------------- |
− | else | + | |
− | id = issn_copy; -- if not valid, use the show the invalid issn with error message
| + | Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in |
− | end
| + | '<' and/or '>' angle brackets. |
− |
| + | |
− | text = externallinkid({link = handler.link, label = handler.label, | + | ]] |
| + | |
| + | local function message_id (id) |
| + | local handler = cfg.id_handlers['USENETID']; |
| + | |
| + | text = external_link_id({link = handler.link, label = handler.label, |
| prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) | | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
| | | |
− | if false == valid_issn then | + | if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>' |
− | text = text .. ' ' .. seterror( 'bad_issn' ) -- add an error message if the issn is invalid | + | text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid |
| end | | end |
| | | |
Line 412: |
Line 1,462: |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- |
− | 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 desireable to omit the title type from the rendered citation (|type=none). | + | This function sets default title types (equivalent to the citation including |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 set_titletype(cite_class, title_type) | + | |
| + | local function set_titletype (cite_class, title_type) |
| if is_set(title_type) then | | if is_set(title_type) then |
| if "none" == title_type then | | if "none" == title_type then |
− | title_type = ""; -- if |type=none then type parameter not displayed | + | title_type = ""; -- if |type=none then type parameter not displayed |
| end | | end |
− | return title_type; -- if |type= has been set to any other value use that value | + | return title_type; -- if |type= has been set to any other value use that value |
| end | | end |
| | | |
− | if "podcast" == cite_class then -- if this citation is cite podcast | + | return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation |
− | return "Podcast"; -- display podcast annotation | + | end |
| + | |
| + | --[[--------------------------< C L E A N _ I S B N >---------------------------------------------------------- |
| + | |
| + | Removes irrelevant text and dashes from ISBN number |
| + | Similar to that used for Special:BookSources |
| + | |
| + | ]] |
| + | |
| + | local function clean_isbn( isbn_str ) |
| + | return isbn_str:gsub( "[^-0-9X]", "" ); |
| + | end |
| + | |
| + | --[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >---------------------------------- |
| + | |
| + | Returns a string where all of lua's magic characters have been escaped. This is important because functions like |
| + | string.gsub() treat their pattern and replace strings as patterns, not literal strings. |
| + | ]] |
| + | local function escape_lua_magic_chars (argument) |
| + | argument = argument:gsub("%%", "%%%%"); -- replace % with %% |
| + | argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters |
| + | return argument; |
| + | end |
| + | |
| + | --[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >-------------------------------- |
| + | |
| + | Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata. |
| + | This function strips common patterns of apostrophe markup. We presume that editors who have taken the time to |
| + | markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind. |
| + | |
| + | ]] |
| + | |
| + | local function strip_apostrophe_markup (argument) |
| + | if not is_set (argument) then return argument; end |
| + | |
| + | while true do |
| + | if argument:match ("%'%'%'%'%'") then -- bold italic (5) |
| + | argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it |
| + | elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4) |
| + | argument=argument:gsub("%'%'%'%'", ""); |
| + | elseif argument:match ("%'%'%'") then -- bold (3) |
| + | argument=argument:gsub("%'%'%'", ""); |
| + | elseif argument:match ("%'%'") then -- italic (2) |
| + | argument=argument:gsub("%'%'", ""); |
| + | else |
| + | break; |
| + | end |
| + | end |
| + | return argument; -- done |
| + | end |
| + | |
| + | --[[--------------------------< M A K E _ C O I N S _ T I T L E >---------------------------------------------- |
| | | |
− | elseif "pressrelease" == cite_class then -- if this citation is cite press release
| + | Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs) |
− | return "Press release"; -- display press release annotation
| + | |
| + | Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings |
| + | of %27%27... |
| + | ]] |
| | | |
− | elseif "techreport" == cite_class then -- if this citation is cite techreport | + | local function make_coins_title (title, script) |
− | return "Technical report"; -- display techreport annotation | + | if is_set (title) then |
| + | title = strip_apostrophe_markup (title); -- strip any apostrophe markup |
| + | else |
| + | title=''; -- if not set, make sure title is an empty string |
| + | end |
| + | if is_set (script) then |
| + | script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string) |
| + | script = strip_apostrophe_markup (script); -- strip any apostrophe markup |
| + | else |
| + | script=''; -- if not set, make sure script is an empty string |
| + | end |
| + | if is_set (title) and is_set (script) then |
| + | script = ' ' .. script; -- add a space before we concatenate |
| + | end |
| + | return title .. script; -- return the concatenation |
| + | end |
| + | |
| + | --[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------ |
| + | |
| + | Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS. |
| + | |
| + | ]] |
| + | |
| + | local function get_coins_pages (pages) |
| + | local pattern; |
| + | if not is_set (pages) then return pages; end -- if no page numbers then we're done |
| | | |
− | elseif "thesis" == cite_class then -- if this citation is cite thesis (degree option handled after this function returns) | + | while true do |
− | return "Thesis"; -- display simple thesis annotation (without |degree= modification)
| + | pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url " |
| + | if nil == pattern then break; end -- no more urls |
| + | pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters |
| + | pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible |
| end | | end |
| + | pages = pages:gsub("[%[%]]", ""); -- remove the brackets |
| + | 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 |
| | | |
− | -- returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct. If not a valid month, returns 0 | + | -- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B |
− | function get_month_number (month)
| + | local function remove_wiki_link( str ) |
− | local long_months = {['January']=1, ['February']=2, ['March']=3, ['April']=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12};
| + | return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l) |
− | local short_months = {['Jan']=1, ['Feb']=2, ['Mar']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12}; | + | return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1"); |
− | local temp;
| + | end)); |
− | temp=long_months[month];
| |
− | if temp then return temp; end -- if month is the long-form name | |
− | temp=short_months[month];
| |
− | if temp then return temp; end -- if month is the short-form name
| |
− | return 0; -- misspelled, improper case, or not a month name
| |
| end | | end |
| | | |
− | -- returns a number according to the sequence of seasons in a year: 1 for Winter, etc. Capitalization and spelling must be correct. If not a valid season, returns 0 | + | -- Converts a hyphen to a dash |
− | function get_season_number (season) | + | local function hyphen_to_dash( str ) |
− | local season_list = {['Winter']=1, ['Spring']=2, ['Summer']=3, ['Fall']=4, ['Autumn']=4}
| + | if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then |
− | local temp;
| + | return str; |
− | temp=season_list[season]; | + | end |
− | if temp then return temp; end -- if season is a valid name return its number
| + | return str:gsub( '-', '–' ); |
− | return 0; -- misspelled, improper case, or not a season name | |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< S A F E _ J O I N >------------------------------------------------------------ |
− | Returns true if day is less than or equal to the number of days in month; else returns false.
| + | |
| + | Joins a sequence of strings together while checking for duplicate separation characters. |
| | | |
− | Assumes Julian calendar prior to year 1582 and Gregorian calendar thereafter. Accounts for Julian calendar leap years before 1582 and Gregorian leap years after 1582.
| |
− | Where the two calendars overlap (1582 to approximately 1923) dates are assumed to be Gregorian.
| |
| ]] | | ]] |
− | function is_valid_date (year, month, day) | + | |
− | local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31}; | + | local function safe_join( tbl, duplicate_char ) |
− | local month_length; | + | --[[ |
− | if (2==month) then -- if February | + | Note: we use string functions here, rather than ustring functions. |
− | month_length = 28; -- then 28 days unless
| + | |
− | if 1582 > tonumber(year) then -- Julian calendar
| + | This has considerably faster performance and should work correctly as |
− | if 0==(year%4) then
| + | long as the duplicate_char is strict ASCII. The strings |
− | month_length = 29; | + | in tbl may be ASCII or UTF8. |
| + | ]] |
| + | |
| + | local str = ''; -- the output string |
| + | local comp = ''; -- what does 'comp' mean? |
| + | local end_chr = ''; |
| + | local trim; |
| + | for _, value in ipairs( tbl ) do |
| + | if value == nil then value = ''; end |
| + | |
| + | if str == '' then -- if output string is empty |
| + | str = value; -- assign value to it (first time through the loop) |
| + | elseif value ~= '' then |
| + | if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup. |
| + | comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string) |
| + | else |
| + | comp = value; |
| end | | end |
− | else -- Gregorian calendar
| + | -- typically duplicate_char is sepc |
− | if (0==(year%4) and (0~=(year%100) or 0==(year%400))) then -- is a leap year? | + | if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character? |
− | month_length = 29; -- if leap year then 29 days in February | + | -- Because individual string segments often (always?) begin with terminal punct for th |
| + | -- preceding segment: 'First element' .. 'sepc next element' .. etc? |
| + | trim = false; |
| + | end_chr = str:sub(-1,-1); -- get the last character of the output string |
| + | -- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? |
| + | if end_chr == duplicate_char then -- if same as separator |
| + | str = str:sub(1,-2); -- remove it |
| + | elseif end_chr == "'" then -- if it might be wikimarkup |
| + | if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' |
| + | str = str:sub(1, -4) .. "''"; -- remove them and add back '' |
| + | elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' |
| + | trim = true; -- why? why do this and next differently from previous? |
| + | elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' |
| + | trim = true; -- same question |
| + | end |
| + | elseif end_chr == "]" then -- if it might be wikimarkup |
| + | if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink |
| + | trim = true; |
| + | elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link |
| + | trim = true; |
| + | elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. |
| + | trim = true; |
| + | end |
| + | elseif end_chr == " " then -- if last char of output string is a space |
| + | if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> |
| + | str = str:sub(1,-3); -- remove them both |
| + | end |
| + | end |
| + | |
| + | if trim then |
| + | if value ~= comp then -- value does not equal comp when value contains html markup |
| + | local dup2 = duplicate_char; |
| + | if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it |
| + | |
| + | value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup |
| + | else |
| + | value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character |
| + | end |
| + | end |
| end | | end |
| + | str = str .. value; --add it to the output string |
| end | | end |
− | else
| |
− | month_length=days_in_month[month];
| |
| end | | end |
| + | return str; |
| + | end |
| | | |
− | if tonumber (day) > month_length then | + | --[[--------------------------< I S _ G O O D _ V A N C _ N A M E >-------------------------------------------- |
− | return false; | + | |
| + | 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 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. |
| + | These things are not currently possible in this module so are left to the editor to do. |
| + | |
| + | 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 |
| + | |
| + | At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here |
| + | because the code editor gets confused between character insertion point and cursor position. |
| + | |
| + | ]] |
| + | |
| + | local function is_good_vanc_name (last, first) |
| + | 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%'%.]*$") then |
| + | add_vanc_error (); |
| + | return false; -- not a string of latin characters; Vancouver required Romanization |
| + | end; |
| + | return true; |
| + | end |
| + | |
| + | --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
| + | |
| + | Attempts to convert names to initials in support of |name-list-format=vanc. |
| + | |
| + | Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. |
| + | |
| + | Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not |
| + | currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. |
| + | |
| + | This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (). |
| + | |
| + | ]] |
| + | |
| + | local function reduce_to_initials(first) |
| + | if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do |
| + | local initials = {} |
| + | local i = 0; -- counter for number of initials |
| + | for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods |
| + | table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops. |
| + | i = i + 1; -- bump the counter |
| + | if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit |
| end | | end |
− | return true; | + | return table.concat(initials) -- Vancouver format does not include spaces. |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< L I S T _ P E O P L E >------------------------------------------------------- |
− | Check a pair of months or seasons to see if both are valid members of a month or season pair.
| + | |
| + | Formats a list of people (e.g. authors / editors) |
| | | |
− | Month pairs are expected to be left to right, earliest to latest in time. Similarly, seasons are also left to right, earliest to latest in time. There is
| |
− | an oddity with seasons. Winter is assigned a value of 1, spring 2, ..., fall and autumn 4. Because winter can follow fall/autumn at the end of a calender year, a special test
| |
− | is made to see if |date=Fall-Winter yyyy (4-1) is the date.
| |
| ]] | | ]] |
| | | |
− | function is_valid_month_season_range(range_start, range_end) | + | local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function |
− | local range_start_number = get_month_number (range_start); | + | local sep; |
| + | local namesep; |
| + | local format = control.format |
| + | local maximum = control.maximum |
| + | local lastauthoramp = control.lastauthoramp; |
| + | local text = {} |
| + | |
| + | if 'vanc' == format then -- Vancouver-like author/editor name styling? |
| + | sep = ','; -- name-list separator between authors is a comma |
| + | namesep = ' '; -- last/first separator is a space |
| + | else |
| + | sep = ';' -- name-list separator between authors is a semicolon |
| + | namesep = ', ' -- last/first separator is <comma><space> |
| + | end |
| | | |
− | if 0 == range_start_number then -- is this a month range? | + | if sep:sub(-1,-1) ~= " " then sep = sep .. " " end |
− | local range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number | + | if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors |
− | local range_end_number = get_season_number (range_end); -- get end season number
| + | |
− | | + | for i,person in ipairs(people) do |
− | if 0 ~= range_start_number then -- is start of range a season?
| + | if is_set(person.last) then |
− | if range_start_number < range_end_number then -- range_start is a season
| + | local mask = person.mask |
− | return true; -- return true when range_end is also a season and follows start season; else false | + | local one |
− | end
| + | local sep_one = sep; |
− | if 4 == range_start_number and 1 == range_end_number then -- special case when range is Fall-Winter or Autumn-Winter
| + | if is_set (maximum) and i > maximum then |
− | return true; | + | etal = true; |
| + | break; |
| + | elseif (mask ~= nil) then |
| + | local n = tonumber(mask) |
| + | if (n ~= nil) then |
| + | one = string.rep("—",n) |
| + | else |
| + | one = mask; |
| + | sep_one = " "; |
| + | end |
| + | else |
| + | one = person.last |
| + | local first = person.first |
| + | if is_set(first) then |
| + | if ( "vanc" == format ) then -- if vancouver format |
| + | one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |
| + | if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested |
| + | first = reduce_to_initials(first) -- attempt to convert first name(s) to initials |
| + | end |
| + | end |
| + | one = one .. namesep .. first |
| + | end |
| + | if is_set(person.link) and person.link ~= control.page_name then |
| + | one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page |
| + | end |
| end | | end |
| + | table.insert( text, one ) |
| + | table.insert( text, sep_one ) |
| end | | end |
− | return false; -- range_start is not a month or a season; or range_start is a season and range_end is not; or improper season sequence
| |
| end | | end |
| | | |
− | local range_end_number = get_month_number (range_end); -- get end month number | + | local count = #text / 2; -- (number of names + number of separators) divided by 2 |
− | if range_start_number < range_end_number then -- range_start is a month; does range_start precede range_end? | + | if count > 0 then |
− | return true; -- if yes, return true | + | if count > 1 and is_set(lastauthoramp) and not etal then |
| + | text[#text-2] = " & "; -- replace last separator with ampersand text |
| + | end |
| + | text[#text] = nil; -- erase the last separator |
| + | end |
| + | |
| + | local result = table.concat(text) -- construct list |
| + | if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list |
| + | result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al. |
| end | | end |
− | return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month | + | |
| + | return result, count |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< A N C H O R _ I D >------------------------------------------------------------ |
− | Check date format to see that it is one of the formats approved by MOS:DATE: MMMM D, YYYY; D MMMM YYYY; MMMM YYYY; YYYY-MM-DD; YYYY.
| |
− | Additionally, check the date to see that it is a real date: no 31 in 30-day months; no 29 February when not a leap year. Months, both long-form and three
| |
− | character abbreviations, and seasons must be spelled correctly.
| |
| | | |
− | If the date fails the fomat tests, this function returns false but does not return values for anchor_year and COinS_date. When this happens, the date parameter is
| + | Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string. |
− | used in the COinS metadata and the CITEREF identifier gets its year from the year parameter if present.
| |
| | | |
− | Inputs:
| + | namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year. |
− | date_string - date string from date-holding parameters (date, year, accessdate, embargo, archivedate, etc)
| |
| | | |
− | Returns:
| |
− | false if date string is not a real date; else
| |
− | true, anchor_year, COinS_date
| |
− | anchor_year can be used in CITEREF anchors
| |
− | COinS_date is date_string without anchor_year disambiguator if any
| |
| ]] | | ]] |
− | function check_date (date_string) | + | local function anchor_id (namelist, year) |
− | local year; | + | local names={}; -- a table for the one to four names and year |
− | local month=0; -- assume that month and day are not used; if either is zero then final year/month/day validation is not necessary | + | for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names |
− | local day=0;
| + | names[i] = v.last |
− | local day2=0; -- second day in a day range | + | if i == 4 then break end -- if four then done |
− | local anchor_year; | + | end |
− | local coins_date;
| + | table.insert (names, year); -- add the year at the end |
| + | local id = table.concat(names); -- concatenate names and year for CITEREF id |
| + | if 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 |
| | | |
− | if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- Year-initial numerical year month day format
| |
− | year, month, day=string.match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)");
| |
− | month=tonumber(month);
| |
− | if 12 < month or 1 > month or 1583 > tonumber(year) then return false; end -- month number not valid or not Gregorian calendar
| |
− | anchor_year = year;
| |
| | | |
− | elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial: month day, year
| + | --[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- |
− | month, day, anchor_year, year=string.match(date_string, "(%a+)%s*(%d%d?),%s*((%d%d%d%d)%a?)");
| |
− | month = get_month_number (month);
| |
− | if 0 == month then return false; end -- return false if month text isn't one of the twelve months
| |
− |
| |
− | elseif date_string:match("^%a+ +[1-9]%d?–[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash
| |
− | month, day, day2, anchor_year, year=string.match(date_string, "(%a+) +(%d%d?)–(%d%d?), +((%d%d%d%d)%a?)");
| |
− | if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
| |
− | month = get_month_number (month);
| |
− | if 0 == month then return false; end -- return false if month text isn't one of the twelve months
| |
| | | |
− | elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-initial: day month year
| + | Evaluates the content of author and editor name parameters for variations on the theme of et al. If found, |
− | day, month, anchor_year, year=string.match(date_string, "(%d%d*)%s*(%a+)%s*((%d%d%d%d)%a?)");
| + | the et al. is removed, a flag is set to true and the function returns the modified name and the flag. |
− | month = get_month_number (month);
| |
− | if 0 == month then return false; end -- return false if month text isn't one of the twelve months
| |
| | | |
− | elseif date_string:match("^[1-9]%d?–[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash
| + | This function never sets the flag to false but returns it's previous state because it may have been set by |
− | day, day2, month, anchor_year, year=string.match(date_string, "(%d%d?)–(%d%d?) +(%a+) +((%d%d%d%d)%a?)");
| + | previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal |
− | if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
| |
− | month = get_month_number (month);
| |
− | if 0 == month then return false; end -- return false if month text isn't one of the twelve months
| |
| | | |
− | elseif mw.ustring.match (date_string, "^%a+–%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash | + | ]] |
− | local month2 | + | |
− | month, month2, anchor_year, year=mw.ustring.match (date_string, "(%a+)[%-/–](%a+)%s*((%d%d%d%d)%a?)"); | + | local function name_has_etal (name, etal, nocat) |
− | if false == is_valid_month_season_range(month, month2) then
| + | |
− | return false; | + | if is_set (name) then -- name can be nil in which case just return |
| + | local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme |
| + | local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. |
| + | |
| + | if name:match (etal_pattern) then -- variants on et al. |
| + | name = name:gsub (etal_pattern, ''); -- if found, remove |
| + | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
| + | if not nocat then -- no categorization for |vauthors= |
| + | add_maint_cat ('etal'); -- and add a category if not already added |
| + | end |
| + | elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? |
| + | name = name:gsub (others_pattern, ''); -- if found, remove |
| + | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
| + | if not nocat then -- no categorization for |vauthors= |
| + | add_maint_cat ('etal'); -- and add a category if not already added |
| + | end |
| end | | end |
− |
| + | end |
− | elseif date_string:match("^%a+ +%d%d%d%d%a?$") then -- month/season year | + | return name, etal; -- |
− | month, anchor_year, year=string.match(date_string, "(%a+)%s*((%d%d%d%d)%a?)"); | + | end |
− | if 0 == get_month_number (month) then -- if month text isn't one of the twelve months, might be a season | + | |
− | if 0 == get_season_number (month) then -- not a month, is it a season? | + | --[[--------------------------< E X T R A C T _ N A M E S >---------------------------------------------------- |
− | return false; -- return false not a month or one of the five seasons | + | Gets name list from the input arguments |
| + | |
| + | Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. |
| + | Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: 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, the page is added to a maintenance category. |
| + | |
| + | ]] |
| + | |
| + | 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 err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary |
| + | while true do |
| + | last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 |
| + | first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ); |
| + | link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); |
| + | mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); |
| + | |
| + | last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al. |
| + | first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al. |
| + | |
| + | if first and not last then -- if there is a firstn without a matching lastn |
| + | table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, 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 |
| + | if 2 <= count then -- two missing names and we give up |
| + | break; -- normal exit or there is a two-name hole in the list; can't tell which |
| + | end |
| + | else -- we have last with or without a first |
| + | if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last |
| + | table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link; |
| + | 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 |
| + | table.insert( z.message_tail, { set_error( '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 |
| end | | end |
| + | i = i + 1; -- point to next args location |
| + | end |
| + | |
| + | return names, etal; -- all done, return our list of names |
| + | end |
| + | |
| + | --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- |
| + | |
| + | Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for |
| + | any of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value to |
| + | the identifier list. Emits redundant error message is more than one alias exists in args |
| | | |
− | elseif date_string:match("^[1-9]%d%d%d?%a?$") then -- year; here accept either YYY or YYYY
| + | ]] |
− | anchor_year, year=string.match(date_string, "((%d%d%d%d?)%a?)");
| |
| | | |
− | else | + | local function extract_ids( args ) |
− | return false; -- date format not one of the MOS:DATE approved formats | + | local id_list = {}; -- list of identifiers found in args |
| + | for k, v in pairs( cfg.id_handlers ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table |
| + | v = select_one( args, v.parameters, 'redundant_parameters' ); -- v.parameters is a table of aliases for k; here we pick one from args if present |
| + | if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list |
| end | | end |
| + | return id_list; |
| + | end |
| + | |
| + | --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- |
| + | |
| + | Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs. |
| + | |
| + | inputs: |
| + | id_list – table of identifiers built by extract_ids() |
| + | options – table of various template parameter values used to modify some manually handled identifiers |
| + | |
| + | ]] |
| + | |
| + | local function build_id_list( id_list, options ) |
| + | local new_list, handler = {}; |
| | | |
− | if 0~=month and 0~=day then -- check year month day dates for validity | + | function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end; |
− | if 0~=day2 then -- If there is a second day (d–d Mmm YYYY or Mmm d–d, YYYY) test the second date | + | |
− | if false==is_valid_date(year,month,day2) then | + | for k, v in pairs( id_list ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table |
− | return false; -- second date in date range string is not a real date return false; unset anchor_year and coins_date
| + | -- fallback to read-only cfg |
− | end -- if second date range string is valid, fall through to test the first date range | + | handler = setmetatable( { ['id'] = v }, fallback(k) ); |
− | end | + | |
− | if false==is_valid_date(year,month,day) then | + | if handler.mode == 'external' then |
− | return false; -- date string is not a real date return false; unset anchor_year and coins_date | + | table.insert( new_list, {handler.label, external_link_id( handler ) } ); |
| + | elseif handler.mode == 'internal' then |
| + | table.insert( new_list, {handler.label, internal_link_id( handler ) } ); |
| + | elseif handler.mode ~= 'manual' then |
| + | error( cfg.messages['unknown_ID_mode'] ); |
| + | 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, options.Class ) } ); |
| + | 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' or k == 'OLA' 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 == 'ISMN' then |
| + | table.insert( new_list, {handler.label, ismn( v ) } ); |
| + | elseif k == 'ISSN' then |
| + | table.insert( new_list, {handler.label, issn( v ) } ); |
| + | elseif k == 'ISBN' then |
| + | local ISBN = internal_link_id( handler ); |
| + | if not check_isbn( v ) and not is_set(options.IgnoreISBN) then |
| + | ISBN = ISBN .. set_error( 'bad_isbn', {}, false, " ", "" ); |
| + | end |
| + | table.insert( new_list, {handler.label, ISBN } ); |
| + | elseif k == 'USENETID' then |
| + | table.insert( new_list, {handler.label, message_id( v ) } ); |
| + | else |
| + | error( cfg.messages['unknown_manual_ID'] ); |
| end | | end |
| end | | end |
| + | |
| + | function comp( a, b ) -- used in following table.sort() |
| + | return a[1] < b[1]; |
| + | end |
| + | |
| + | table.sort( new_list, comp ); |
| + | for k, v in ipairs( new_list ) do |
| + | new_list[k] = v[2]; |
| + | end |
| + | |
| + | return new_list; |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< C O I N S _ C L E A N U P >---------------------------------------------------- |
| + | |
| + | Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities. |
| + | |
| + | 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate content |
| + | when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 |
| + | |
| + | TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible |
| + | characters table? |
| + | ]] |
| + | |
| + | local function coins_cleanup (value) |
| + | value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content |
| + | value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s |
| + | value = value:gsub ('‍\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe |
| + | value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11) |
| + | value = value:gsub (' ', ' '); -- replace entity with plain space |
| + | value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space |
| + | value = value:gsub ('‍', ''); -- remove ‍ entities |
| + | value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space |
| + | value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space |
| + | return value; |
| + | end |
| + | |
| | | |
− | coins_date= mw.ustring.gsub( date_string, "–", "-" ); -- if here, then date_string is valid; set coins_date and replace any ndash with a hyphen
| + | --[[--------------------------< C O I N S >-------------------------------------------------------------------- |
− |
| |
− | return true, anchor_year, coins_date; -- format is good and date string represents a real date
| |
− | end
| |
| | | |
− | --[[
| + | COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information. |
− | Cycle the date-holding parameters in passed table date_parameters_list through check_date() to check compliance with MOS:DATE. For all valid dates, check_date() returns
| |
− | true and values for anchor_year (used in CITEREF identifiers) and COinS_date (used in the COinS metadata). The |date= parameter test is unique. This function only
| |
− | accepts anchor_year and COinS_date results from the |date= parameter test and |date= is the only date-holding parameter that is allowed to contain the no-date keywords
| |
− | "n.d." or "nd" (without quotes).
| |
| | | |
− | Unlike most error messages created in this module, only one error message is created by this function. Because all of the date holding parameters are processed serially,
| |
− | a single error message is created as the dates are tested.
| |
| ]] | | ]] |
| | | |
− | function dates(date_parameters_list) | + | local function COinS(data, class) |
− | local anchor_year; -- will return as nil if the date being tested is not |date= | + | if 'table' ~= type(data) or nil == next(data) then |
− | local COinS_date; -- will return as nil if the date being tested is not |date=
| + | return ''; |
− | local error_message =""; | + | end |
− | local good_date=false;
| + | |
| + | for k, v in pairs (data) do -- spin through all of the metadata parameter values |
| + | if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) |
| + | data[k] = coins_cleanup (v); |
| + | end |
| + | end |
| + | |
| + | local ctx_ver = "Z39.88-2004"; |
| | | |
− | for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list | + | -- treat table strictly as an array with only set values. |
− | if is_set(v) then -- if the parameter has a value
| + | local OCinSoutput = setmetatable( {}, { |
− | if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year= | + | __newindex = function(self, key, value) |
− | if 'date'==k then
| + | if is_set(value) then |
− | good_date, anchor_year, COinS_date = true, v:match("((c%. [1-9]d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
| + | rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } ); |
− | elseif 'year'==k then
| + | end |
− | good_date = true;
| + | end |
− | end
| + | }); |
− | elseif 'year'==k then -- if the parameter is |year= (but not c. year) | + | |
− | if v:match("^[1-9]%d%d%d?%a?$") then -- year with or without CITEREF disambiguator | + | if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or |
− | good_date = true;
| + | ('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then |
− | end
| + | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier |
− | elseif 'date'==k then -- if the parameter is |date= | + | if 'arxiv' == class then -- set genre according to the type of citation template we are rendering |
− | if v:match("n%.d%.%a?") then -- if |date=n.d. with or without a CITEREF disambiguator | + | OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv |
− | good_date, anchor_year, COinS_date = true, v:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
| + | elseif 'conference' == class then |
− | elseif v:match("nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator
| + | OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set) |
− | good_date, anchor_year, COinS_date = true, v:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
| + | elseif 'web' == class then |
| + | OCinSoutput["rft.genre"] = "unknown"; -- cite web (when Periodical set) |
| + | else |
| + | OCinSoutput["rft.genre"] = "article"; -- journal and other 'periodical' articles |
| + | end |
| + | OCinSoutput["rft.jtitle"] = data.Periodical; -- journal only |
| + | if is_set (data.Map) then |
| + | OCinSoutput["rft.atitle"] = data.Map; -- for a map in a periodical |
| + | else |
| + | OCinSoutput["rft.atitle"] = data.Title; -- all other 'periodical' article titles |
| + | end |
| + | -- these used onlu for periodicals |
| + | OCinSoutput["rft.ssn"] = data.Season; -- keywords: winter, spring, summer, fall |
| + | OCinSoutput["rft.chron"] = data.Chron; -- free-form date components |
| + | OCinSoutput["rft.volume"] = data.Volume; -- does not apply to books |
| + | OCinSoutput["rft.issue"] = data.Issue; |
| + | OCinSoutput["rft.pages"] = data.Pages; -- also used in book metadata |
| + | |
| + | elseif 'thesis' ~= class then -- all others except cite thesis are treated as 'book' metadata; genre distinguishes |
| + | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book"; -- book metadata identifier |
| + | if 'report' == class or 'techreport' == class then -- cite report and cite techreport |
| + | OCinSoutput["rft.genre"] = "report"; |
| + | elseif 'conference' == class then -- cite conference when Periodical not set |
| + | OCinSoutput["rft.genre"] = "conference"; |
| + | elseif in_array (class, {'book', 'citation', 'encyclopaedia', 'interview', 'map'}) then |
| + | if is_set (data.Chapter) then |
| + | OCinSoutput["rft.genre"] = "bookitem"; |
| + | OCinSoutput["rft.atitle"] = data.Chapter; -- book chapter, encyclopedia article, interview in a book, or map title |
| + | else |
| + | if 'map' == class or 'interview' == class then |
| + | OCinSoutput["rft.genre"] = 'unknown'; -- standalone map or interview |
| else | | else |
− | good_date, anchor_year, COinS_date = check_date (v); -- go test the date | + | OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia |
| end | | end |
− | else -- any other date-holding parameter
| |
− | good_date = check_date (v); -- go test the date
| |
| end | | end |
− | if false==good_date then -- assemble one error message so we don't add the tracking category multiple times | + | else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'} |
− | if is_set(error_message) then -- once we've added the first portion of the error message ...
| + | OCinSoutput["rft.genre"] = "unknown"; |
− | error_message=error_message .. ", "; -- ... add a comma space separator
| + | end |
− | end
| + | OCinSoutput["rft.btitle"] = data.Title; -- book only |
− | error_message=error_message .. "|" .. k .. "="; -- add the failed parameter
| + | OCinSoutput["rft.place"] = data.PublicationPlace; -- book only |
| + | OCinSoutput["rft.series"] = data.Series; -- book only |
| + | OCinSoutput["rft.pages"] = data.Pages; -- book, journal |
| + | OCinSoutput["rft.edition"] = data.Edition; -- book only |
| + | OCinSoutput["rft.pub"] = data.PublisherName; -- book and dissertation |
| + | |
| + | else -- cite thesis |
| + | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:dissertation"; -- dissertation metadata identifier |
| + | OCinSoutput["rft.title"] = data.Title; -- dissertation (also patent but that is not yet supported) |
| + | OCinSoutput["rft.degree"] = data.Degree; -- dissertation only |
| + | OCinSoutput['rft.inst'] = data.PublisherName; -- book and dissertation |
| + | end |
| + | -- and now common parameters (as much as possible) |
| + | OCinSoutput["rft.date"] = data.Date; -- book, journal, dissertation |
| + | |
| + | for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? |
| + | if k == 'ISBN' then v = clean_isbn( v ) end |
| + | local id = cfg.id_handlers[k].COinS; |
| + | if string.sub( id or "", 1, 4 ) == 'info' then -- for ids that are in the info:registry |
| + | OCinSoutput["rft_id"] = table.concat{ id, "/", v }; |
| + | elseif string.sub (id or "", 1, 3 ) == 'rft' then -- for isbn, issn, eissn, etc that have defined COinS keywords |
| + | OCinSoutput[ id ] = v; |
| + | elseif id then -- when cfg.id_handlers[k].COinS is not nil |
| + | OCinSoutput["rft_id"] = table.concat{ cfg.id_handlers[k].prefix, v }; -- others; provide a url |
| + | end |
| + | end |
| + | |
| + | --[[ |
| + | for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? |
| + | local id, value = cfg.id_handlers[k].COinS; |
| + | if k == 'ISBN' then value = clean_isbn( 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 |
| + | ]] |
| + | local last, first; |
| + | for k, v in ipairs( data.Authors ) do |
| + | last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers |
| + | if k == 1 then -- for the first author name only |
| + | if is_set(last) and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name |
| + | OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation |
| + | OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation |
| + | elseif is_set(last) then |
| + | OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name |
| + | end |
| + | else -- for all other authors |
| + | if is_set(last) and is_set(first) then |
| + | OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation |
| + | elseif is_set(last) then |
| + | OCinSoutput["rft.au"] = last; -- book, journal, dissertation |
| end | | end |
| end | | end |
− | end
| |
− | if is_set(error_message) then
| |
− | table.insert( z.message_tail, { seterror( 'bad_date', {error_message}, true ) } ); -- add this error message
| |
| end | | end |
| | | |
− | return anchor_year, COinS_date; -- and done | + | 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 |
| | | |
− | --[[
| |
− | Determines whether a URL string is valid
| |
| | | |
− | At present the only check is whether the string appears to
| + | --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ |
− | be prefixed with a URI scheme. It is not determined whether
| + | |
− | the URI scheme is valid or whether the URL is otherwise well | + | Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian where |
− | formed.
| + | ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR. |
| + | |
| + | Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia |
| + | uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along |
| + | with the code. When there is no match, we return the original language name string. |
| + | |
| + | mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included |
| + | in the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan Aramaic, that name will be |
| + | found with the associated code 'sam', not an ISO639-1 code. When names are found and the associated code is not two characters, this function |
| + | returns only the Wikimedia language name. |
| + | |
| + | Adapted from code taken from Module:Check ISO 639-1. |
| + | |
| ]] | | ]] |
− | function checkurl( url_str ) | + | |
− | -- Protocol-relative or URL scheme
| + | local function get_iso639_code (lang) |
− | return url_str:sub(1,2) == "//" or url_str:match( "^[^/]*:" ) ~= nil;
| + | if 'norwegian' == lang:lower() then -- special case related to Wikimedia remap of code 'no' at Extension:CLDR |
| + | return 'Norwegian', 'no'; -- Make sure rendered version is properly capitalized |
| + | end |
| + | |
| + | local languages = mw.language.fetchLanguageNames('en', 'all') -- get a list of language names known to Wikimedia |
| + | -- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) |
| + | local langlc = mw.ustring.lower(lang); -- lower case version for comparisons |
| + | |
| + | for code, name in pairs(languages) do -- scan the list to see if we can find our language |
| + | if langlc == mw.ustring.lower(name) then |
| + | if 2 ~= code:len() then -- ISO639-1 codes only |
| + | return name; -- so return the name but not the code |
| + | end |
| + | return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code |
| + | end |
| + | end |
| + | return lang; -- not valid language; return language in original case and nil for ISO639-1 code |
| end | | end |
| | | |
− | -- Removes irrelevant text and dashes from ISBN number | + | --[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------ |
− | -- Similar to that used for Special:BookSources | + | |
− | function cleanisbn( isbn_str )
| + | Get language name from ISO639-1 code value provided. If a code is valid use the returned name; if not, then use the value that was provided with the language parameter. |
− | return isbn_str:gsub( "[^-0-9X]", "" );
| + | |
− | end
| + | There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and |
| + | Norwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appears |
| + | that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links. |
| + | |
| + | Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and |
| + | return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them. |
| + | |
| + | See Help talk:Citation Style_1#An ISO 639-1 language name test |
| + | |
| + | When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if |
| + | the page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way. |
| + | |
| + | 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. |
| | | |
− | --[[
| |
− | 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,
| |
− | spaces and other non-isxn characters.
| |
| ]] | | ]] |
− | function is_valid_isxn (isxn_str, len) | + | |
− | local temp = 0; | + | local function language_parameter (lang) |
− | isxn_str = { isxn_str:byte(1, len) }; -- make a table of bytes | + | local code; -- the ISO639-1 two character code |
− | len = len+1; -- adjust to be a loop counter | + | local name; -- the language name |
− | for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum | + | local language_list = {}; -- table of language names to be rendered |
− | if v == string.byte( "X" ) then -- if checkdigit is X | + | local names_table = {}; -- table made from the value assigned to |language= |
− | temp = temp + 10*( len - i ); -- it represents 10 decimal | + | |
| + | names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
| + | |
| + | for _, lang in ipairs (names_table) do -- reuse lang |
| + | |
| + | if lang:match ('^%a%a%-') then -- strip ietf language tags from code |
| + | lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? |
| + | end |
| + | if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes) |
| + | name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code |
| + | end |
| + | |
| + | if is_set (name) then -- if Language specified a valid ISO639-1 code |
| + | code = lang:lower(); -- save it |
| + | else |
| + | name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) |
| + | end |
| + | |
| + | if is_set (code) then |
| + | if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no' |
| + | if 'en' ~= code then -- English not the language |
| + | add_prop_cat ('foreign_lang_source', {name, code}) |
| + | end |
| else | | else |
− | temp = temp + tonumber( string.char(v) )*(len-i); | + | add_maint_cat ('unknown_lang'); -- add maint category if not already added |
| end | | end |
| + | |
| + | table.insert (language_list, name); |
| + | name = ''; -- so we can reuse it |
| + | end |
| + | |
| + | code = #language_list -- reuse code as number of languages in the list |
| + | if 2 >= code then |
| + | name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names |
| + | elseif 2 < code then |
| + | language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>' |
| + | name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators |
| + | end |
| + | if 'English' == name then |
| + | return ''; -- if one language and that language is English return an empty string (no annotation) |
| + | end |
| + | return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' |
| + | end |
| + | |
| + | --[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- |
| + | |
| + | Set style settings for CS1 citation templates. Returns separator and postscript settings |
| + | |
| + | ]] |
| + | |
| + | local function set_cs1_style (ps) |
| + | if not is_set (ps) then -- unless explicitely set to something |
| + | ps = '.'; -- terminate the rendered citation with a period |
| end | | end |
− | return temp % 11 == 0; -- returns true if calculation result is zero | + | return '.', ps; -- separator is a full stop |
| end | | end |
| | | |
− | -- Determines whether an ISBN string is valid | + | --[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- |
− | 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 | + | Set style settings for CS2 citation templates. Returns separator, postscript, ref settings |
− | isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
| + | |
− | local len = isbn_str:len(); | + | ]] |
− |
| + | |
− | if len ~= 10 and len ~= 13 then
| + | local function set_cs2_style (ps, ref) |
− | return false; | + | if not is_set (ps) then -- if |postscript= has not been set, set cs2 default |
| + | ps = ''; -- make sure it isn't nil |
| + | end |
| + | if not is_set (ref) then -- if |ref= is not set |
| + | ref = "harv"; -- set default |ref=harv |
| end | | end |
| + | return ',', ps, ref; -- separator is a comma |
| + | end |
| + | |
| + | --[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- |
| + | |
| + | When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish |
| + | rendered style. |
| | | |
− | if len == 10 then
| + | ]] |
− | if isbn_str:match( "^%d*X?$" ) == nil then return false; end
| + | |
− | return is_valid_isxn(isbn_str, 10);
| + | local function get_settings_from_cite_class (ps, ref, cite_class) |
− | else | + | local sep; |
− | local temp = 0;
| + | if (cite_class == "citation") then -- for citation templates (CS2) |
− | if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979
| + | sep, ps, ref = set_cs2_style (ps, ref); |
− | isbn_str = { isbn_str:byte(1, len) }; | + | else -- not a citation template so CS1 |
− | for i, v in ipairs( isbn_str ) do | + | sep, ps = set_cs1_style (ps); |
− | temp = temp + (3 - 2*(i % 2)) * tonumber( string.char(v) );
| |
− | end
| |
− | return temp % 10 == 0;
| |
| end | | end |
| + | |
| + | return sep, ps, ref -- return them all |
| end | | end |
| | | |
− | -- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B | + | --[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ |
− | function removewikilink( str ) | + | |
− | return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
| + | Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses |
− | return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
| + | config.CitationClass from the template's #invoke: to establish style. |
− | end));
| + | |
| + | ]] |
| + | |
| + | local function set_style (mode, ps, ref, cite_class) |
| + | local sep; |
| + | if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style |
| + | sep, ps, ref = set_cs2_style (ps, ref); |
| + | elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style |
| + | sep, ps = set_cs1_style (ps); |
| + | else -- anything but cs1 or cs2 |
| + | sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass |
| + | end |
| + | if 'none' == ps:lower() then -- if assigned value is 'none' then |
| + | ps = ''; -- set to empty string |
| + | end |
| + | |
| + | return sep, ps, ref |
| end | | end |
| | | |
− | -- Escape sequences for content that will be used for URL descriptions | + | --[=[-------------------------< I S _ P D F >------------------------------------------------------------------ |
− | function safeforurl( str )
| + | |
− | if str:match( "%[%[.-%]%]" ) ~= nil then
| + | Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when |
− | table.insert( z.message_tail, { seterror( 'wikilink_in_url', {}, true ) } );
| + | applying the pdf icon to external links. |
− | end
| + | |
− |
| + | returns true if file extension is one of the recognized extension, else false |
− | return str:gsub( '[%[%]\n]', {
| + | |
− | ['['] = '[',
| + | ]=] |
− | [']'] = ']',
| + | |
− | ['\n'] = ' ' } );
| + | local function is_pdf (url) |
| + | return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?'); |
| end | | end |
| | | |
− | -- Converts a hyphen to a dash | + | --[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ |
− | function hyphentodash( str ) | + | |
− | if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
| + | Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does |
− | return str;
| + | not have a matching url parameter. If the format parameter is not set and the url contains a file extension that |
− | end
| + | is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with |
− | return str:gsub( '-', '–' );
| + | the appropriate styling. |
| + | |
| + | ]] |
| + | |
| + | local function style_format (format, url, fmt_param, url_param) |
| + | if is_set (format) then |
| + | format = wrap_style ('format', format); -- add leading space, parenthases, resize |
| + | if not is_set (url) then |
| + | format = format .. set_error( '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 = wrap_style ('format', 'PDF'); -- set format to pdf |
| + | else |
| + | format = ''; -- empty string for concatenation |
| + | end |
| + | return format; |
| end | | end |
| | | |
− | -- Protects a string that will be wrapped in wiki italic markup '' ... '' | + | --[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------ |
− | function safeforitalics( str )
| + | |
− | --[[ Note: We can not use <i> for italics, as the expected behavior for
| + | Returns a number that may or may not limit the length of the author or editor name lists. |
− | italics specified by ''...'' in the title is that they will be inverted
| + | |
− | (i.e. unitalicized) in the resulting references. In addition, <i> and ''
| + | When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and |
− | tend to interact poorly under Mediawiki's HTML tidy. ]]
| + | 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.'). |
− | if not is_set(str) then
| + | |
− | return str;
| + | When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the |
− | else
| + | number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of |
− | if str:sub(1,1) == "'" then str = "<span />" .. str; end
| + | the names in the name list followed by 'et al.' |
− | if str:sub(-1,-1) == "'" then str = str .. "<span />"; end
| + | |
− |
| + | In all other cases, returns nil and the previous state of the 'etal' flag. |
− | -- Remove newlines as they break italics.
| + | |
− | return str:gsub( '\n', ' ' );
| + | ]] |
− | end
| + | |
| + | local function get_display_authors_editors (max, count, list_name, etal) |
| + | if 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 and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors |
| + | add_maint_cat ('disp_auth_ed', list_name); |
| + | end |
| + | else -- not a valid keyword or number |
| + | table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message |
| + | max = nil; -- unset |
| + | end |
| + | elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category |
| + | max = count + 1; -- number of authors + 1 |
| + | end |
| + | |
| + | return max, etal; |
| end | | end |
| | | |
− | --[[ | + | --[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------ |
− | Joins a sequence of strings together while checking for duplicate separation
| + | |
− | characters.
| + | Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp. |
| + | abbreviation in the first characters of the parameter content. |
| + | |
| + | check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: |
| + | good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit |
| + | bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP |
| + | |
| ]] | | ]] |
− | function safejoin( tbl, duplicate_char )
| |
− | --[[
| |
− | Note: we use string functions here, rather than ustring functions.
| |
− |
| |
− | This has considerably faster performance and should work correctly as
| |
− | long as the duplicate_char is strict ASCII. The strings
| |
− | in tbl may be ASCII or UTF8.
| |
− | ]]
| |
− |
| |
− | local str = '';
| |
− | local comp = '';
| |
− | local end_chr = '';
| |
− | local trim;
| |
− | for _, value in ipairs( tbl ) do
| |
− | if value == nil then value = ''; end
| |
− |
| |
− | if str == '' then
| |
− | str = value;
| |
− | elseif value ~= '' then
| |
− | if value:sub(1,1) == '<' then
| |
− | -- Special case of values enclosed in spans and other markup.
| |
− | comp = value:gsub( "%b<>", "" );
| |
− | else
| |
− | comp = value;
| |
− | end
| |
− |
| |
− | if comp:sub(1,1) == duplicate_char then
| |
− | trim = false;
| |
− | end_chr = str:sub(-1,-1);
| |
− | -- str = str .. "<HERE(enchr=" .. end_chr.. ")"
| |
− | if end_chr == duplicate_char then
| |
− | str = str:sub(1,-2);
| |
− | elseif end_chr == "'" then
| |
− | if str:sub(-3,-1) == duplicate_char .. "''" then
| |
− | str = str:sub(1, -4) .. "''";
| |
− | elseif str:sub(-5,-1) == duplicate_char .. "]]''" then
| |
− | trim = true;
| |
− | elseif str:sub(-4,-1) == duplicate_char .. "]''" then
| |
− | trim = true;
| |
− | end
| |
− | elseif end_chr == "]" then
| |
− | if str:sub(-3,-1) == duplicate_char .. "]]" then
| |
− | trim = true;
| |
− | elseif str:sub(-2,-1) == duplicate_char .. "]" then
| |
− | trim = true;
| |
− | end
| |
− | elseif end_chr == " " then
| |
− | if str:sub(-2,-1) == duplicate_char .. " " then
| |
− | str = str:sub(1,-3);
| |
− | end
| |
− | end
| |
| | | |
− | if trim then
| + | local function extra_text_in_page_check (page) |
− | if value ~= comp then
| + | -- local good_pattern = '^P[^%.P%l]'; |
− | local dup2 = duplicate_char;
| + | local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg? |
− | if dup2:match( "%A" ) then dup2 = "%" .. dup2; end
| + | -- local bad_pattern = '^[Pp][Pp]'; |
− |
| + | local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; |
− | value = value:gsub( "(%b<>)" .. dup2, "%1", 1 )
| |
− | else
| |
− | value = value:sub( 2, -1 );
| |
− | end
| |
− | end
| |
− | end
| |
− | str = str .. value;
| |
− | end
| |
− | end
| |
− | return str;
| |
− | end
| |
| | | |
− | -- Attempts to convert names to initials.
| + | if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then |
− | function reducetoinitials(first)
| + | add_maint_cat ('extra_text'); |
− | local initials = {}
| + | end |
− | for word in string.gmatch(first, "%S+") do
| + | -- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or |
− | table.insert(initials, string.sub(word,1,1)) -- Vancouver format does not include full stops.
| + | -- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then |
− | end
| + | -- add_maint_cat ('extra_text'); |
− | return table.concat(initials) -- Vancouver format does not include spaces.
| + | -- end |
| end | | end |
| | | |
− | -- Formats a list of people (e.g. authors / editors)
| |
− | function listpeople(control, people)
| |
− | local sep = control.sep;
| |
− | local namesep = control.namesep
| |
− | local format = control.format
| |
− | local maximum = control.maximum
| |
− | local lastauthoramp = control.lastauthoramp;
| |
− | local text = {}
| |
− | local etal = false;
| |
− |
| |
− | if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
| |
− | if maximum ~= nil and maximum < 1 then return "", 0; end
| |
− |
| |
− | for i,person in ipairs(people) do
| |
− | if is_set(person.last) then
| |
− | local mask = person.mask
| |
− | local one
| |
− | local sep_one = sep;
| |
− | if maximum ~= nil and i > maximum then
| |
− | etal = true;
| |
− | break;
| |
− | elseif (mask ~= nil) then
| |
− | local n = tonumber(mask)
| |
− | if (n ~= nil) then
| |
− | one = string.rep("—",n)
| |
− | else
| |
− | one = mask;
| |
− | sep_one = " ";
| |
− | end
| |
− | else
| |
− | one = person.last
| |
− | local first = person.first
| |
− | if is_set(first) then
| |
− | if ( "vanc" == format ) then first = reducetoinitials(first) end
| |
− | one = one .. namesep .. first
| |
− | end
| |
− | if is_set(person.link) then one = "[[" .. person.link .. "|" .. one .. "]]" end
| |
− | end
| |
− | table.insert( text, one )
| |
− | table.insert( text, sep_one )
| |
− | end
| |
− | end
| |
| | | |
− | local count = #text / 2;
| + | --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >-------------------------------- |
− | if count > 0 then
| + | |
− | if count > 1 and is_set(lastauthoramp) and not etal then
| + | This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and |
− | text[#text-2] = " & ";
| + | |xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does. |
− | end
| + | |
− | text[#text] = nil;
| + | Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names |
− | end
| + | 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 paranethese ((corporate name)) to suppress the format tests. |
− | local result = table.concat(text) -- construct list
| + | |
− | if etal then
| + | This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials. |
− | local etal_text = cfg.messages['et al'];
| + | |
− | result = result .. " " .. etal_text;
| + | ]] |
− | end
| + | |
− |
| + | local function parse_vauthors_veditors (args, vparam, list_name) |
− | -- if necessary wrap result in <span> tag to format in Small Caps
| + | local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= |
− | if ( "scap" == format ) then result =
| + | local v_name_table = {}; |
− | '<span class="smallcaps" style="font-variant:small-caps">' .. result .. '</span>';
| + | local etal = false; -- return value set to true when we find some form of et al. vauthors parameter |
− | end
| + | local last, first, link, mask; |
− | return result, count
| + | 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) |
| + | if vparam:find ('%[%[') or vparam:find ('%]%]') then -- no wikilinking vauthors names |
| + | add_vanc_error (); |
| + | end |
| + | v_name_table = mw.text.split(vparam, "%s*,%s*") -- names are separated by commas |
| + | |
| + | for i, v_name in ipairs(v_name_table) do |
| + | if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection |
| + | first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
| + | last = v_name:match ('^%(%((.+)%)%)$') |
| + | corporate = true; |
| + | elseif string.find(v_name, "%s") then |
| + | lastfirstTable = {} |
| + | lastfirstTable = mw.text.split(v_name, "%s") |
| + | first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials |
| + | last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials |
| + | if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then |
| + | add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials |
| + | end |
| + | else |
| + | first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
| + | last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? |
| + | end |
| + | |
| + | if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else |
| + | add_vanc_error (); |
| + | end |
| + | -- this from extract_names () |
| + | link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); |
| + | mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); |
| + | names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list |
| + | end |
| + | return names, etal; -- all done, return our list of names |
| end | | end |
| | | |
− | -- Generates a CITEREF anchor ID. | + | --[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ |
− | function anchorid( options ) | + | |
− | return "CITEREF" .. table.concat( options );
| + | Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or |
| + | select one of |editors=, |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 and |
| + | similarly, |editorn= (and aliases) highest and |editors= lowest |
| + | |
| + | 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 or editors as appropriate. |
| + | |
| + | ]] |
| + | |
| + | local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) |
| + | local lastfirst = false; |
| + | if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1 |
| + | select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then |
| + | lastfirst=true; |
| + | end |
| + | |
| + | if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions |
| + | (is_set (vxxxxors) and is_set (xxxxors)) or |
| + | (true == lastfirst and 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, { set_error( '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 is_set (vxxxxors) then return 2 end; |
| + | if 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 | | end |
| | | |
− | -- Gets name list from the input arguments | + | |
− | function extractnames(args, list_name) | + | --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------ |
− | local names = {};
| + | |
− | local i = 1;
| + | This function is used to validate a parameter's assigned value for those parameters that have only a limited number |
− | local last;
| + | of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty |
− |
| + | in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns |
− | while true do
| + | true; else, emits an error message and returns false. |
− | last = selectone( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i );
| + | |
− | if not is_set(last) then
| + | ]] |
− | -- just in case someone passed in an empty parameter
| + | |
− | break;
| + | local function is_valid_parameter_value (value, name, possible) |
− | end
| + | if not is_set (value) then |
− | names[i] = {
| + | return true; -- an empty parameter is ok |
− | last = last,
| + | elseif in_array(value:lower(), possible) then |
− | first = selectone( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ),
| + | return true; |
− | link = selectone( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ),
| + | else |
− | mask = selectone( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i )
| + | table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message |
− | };
| + | return false |
− | i = i + 1;
| + | end |
− | end
| |
− | return names;
| |
| end | | end |
| | | |
− | -- Populates ID table from arguments using configuration settings | + | |
− | function extractids( args ) | + | --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- |
− | local id_list = {};
| + | |
− | for k, v in pairs( cfg.id_handlers ) do
| + | This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space |
− | v = selectone( args, v.parameters, 'redundant_parameters' );
| + | when the last character is not a sepc character or when the last three characters are not sepc followed by two |
− | if is_set(v) then id_list[k] = v; end
| + | closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a |
− | end
| + | single space character. |
− | return id_list;
| + | |
| + | ]] |
| + | |
| + | local function terminate_name_list (name_list, sepc) |
| + | if (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 terninate the name list |
| + | end |
| end | | end |
| | | |
− | -- Takes a table of IDs and turns it into a table of formatted ID outputs. | + | |
− | function buildidlist( id_list, options )
| + | --[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- |
− | local new_list, handler = {};
| + | |
− |
| + | returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume |
− | function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
| + | or formatted issue, or an empty string if neither are set. |
− |
| + | |
− | for k, v in pairs( id_list ) do
| + | ]] |
− | -- fallback to read-only cfg
| + | |
− | handler = setmetatable( { ['id'] = v }, fallback(k) );
| + | local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) |
− |
| + | if not is_set (volume) and not is_set (issue) then |
− | if handler.mode == 'external' then
| + | return ''; |
− | table.insert( new_list, {handler.label, externallinkid( handler ) } );
| + | end |
− | elseif handler.mode == 'internal' then
| + | |
− | table.insert( new_list, {handler.label, internallinkid( handler ) } );
| + | if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then |
− | elseif handler.mode ~= 'manual' then
| + | if is_set (volume) and is_set (issue) then |
− | error( cfg.messages['unknown_ID_mode'] );
| + | return wrap_msg ('vol-no', {sepc, volume, issue}, lower); |
− | elseif k == 'DOI' then
| + | elseif is_set (volume) then |
− | table.insert( new_list, {handler.label, doi( v, options.DoiBroken ) } );
| + | return wrap_msg ('vol', {sepc, volume}, lower); |
− | elseif k == 'ASIN' then
| + | else |
− | table.insert( new_list, {handler.label, amazon( v, options.ASINTLD ) } );
| + | return wrap_msg ('issue', {sepc, issue}, lower); |
− | elseif k == 'OL' then
| + | end |
− | table.insert( new_list, {handler.label, openlibrary( v ) } );
| + | end |
− | elseif k == 'PMC' then
| + | |
− | table.insert( new_list, {handler.label, pmc( v, options.Embargo ) } );
| + | local vol = ''; |
− | elseif k == 'PMID' then
| + | |
− | table.insert( new_list, {handler.label, pmid( v ) } );
| + | if is_set (volume) then |
− | elseif k == 'ISSN' then
| + | if (4 < mw.ustring.len(volume)) then |
− | table.insert( new_list, {handler.label, issn( v ) } );
| + | vol = substitute (cfg.messages['j-vol'], {sepc, volume}); |
− | elseif k == 'ISBN' then
| + | else |
− | local ISBN = internallinkid( handler );
| + | vol = wrap_style ('vol-bold', hyphen_to_dash(volume)); |
− | if not checkisbn( v ) and not is_set(options.IgnoreISBN) then
| + | end |
− | ISBN = ISBN .. seterror( 'bad_isbn', {}, false, " ", "" );
| + | end |
− | end
| + | if is_set (issue) then |
− | table.insert( new_list, {handler.label, ISBN } );
| + | return vol .. substitute (cfg.messages['j-issue'], issue); |
− | else
| + | end |
− | error( cfg.messages['unknown_manual_ID'] );
| + | return vol; |
− | end
| |
− | end
| |
− |
| |
− | function comp( a, b ) -- used in following table.sort()
| |
− | return a[1] < b[1];
| |
− | end
| |
− |
| |
− | table.sort( new_list, comp );
| |
− | for k, v in ipairs( new_list ) do
| |
− | new_list[k] = v[2];
| |
− | end
| |
− |
| |
− | return new_list;
| |
| end | | end |
− |
| + | |
− | -- Chooses one matching parameter from a list of parameters to consider | + | |
− | -- Generates an error if more than one match is present.
| + | --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- |
− | function selectone( args, possible, error_condition, index ) | + | |
− | local value = nil;
| + | adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings. |
− | local selected = '';
| + | The return order is: |
− | local error_list = {};
| + | page, pages, sheet, sheets |
− |
| + | |
− | if index ~= nil then index = tostring(index); end
| + | Singular has priority over plural when both are provided. |
− |
| + | |
− | -- Handle special case of "#" replaced by empty string
| + | ]] |
− | if index == '1' then
| + | |
− | for _, v in ipairs( possible ) do
| + | local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) |
− | v = v:gsub( "#", "" );
| + | if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators |
− | if is_set(args[v]) then
| + | if is_set (sheet) then |
− | if value ~= nil and selected ~= v then
| + | if 'journal' == origin then |
− | table.insert( error_list, v );
| + | return '', '', wrap_msg ('j-sheet', sheet, lower), ''; |
− | else
| + | else |
− | value = args[v];
| + | return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; |
− | selected = v;
| + | end |
− | end
| + | elseif is_set (sheets) then |
− | end
| + | if 'journal' == origin then |
− | end
| + | return '', '', '', wrap_msg ('j-sheets', sheets, lower); |
− | end
| + | else |
− |
| + | return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower); |
− | for _, v in ipairs( possible ) do
| + | end |
− | if index ~= nil then
| + | end |
− | v = v:gsub( "#", index );
| + | end |
− | end
| + | |
− | if is_set(args[v]) then
| + | local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin); |
− | if value ~= nil and selected ~= v then
| + | |
− | table.insert( error_list, v );
| + | if is_set (page) then |
− | else
| + | if is_journal then |
− | value = args[v];
| + | return substitute (cfg.messages['j-page(s)'], page), '', '', ''; |
− | selected = v;
| + | elseif not nopp then |
− | end
| + | return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; |
− | end
| + | else |
− | end
| + | return substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; |
− |
| + | end |
− | if #error_list > 0 then
| + | elseif is_set(pages) then |
− | local error_str = "";
| + | if is_journal then |
− | for _, k in ipairs( error_list ) do
| + | return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; |
− | if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end
| + | elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number |
− | error_str = error_str .. wrap( 'parameter', k );
| + | return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; |
− | end
| + | elseif not nopp then |
− | if #error_list > 1 then
| + | return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; |
− | error_str = error_str .. cfg.messages['parameter-final-separator'];
| + | else |
− | else
| + | return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; |
− | error_str = error_str .. cfg.messages['parameter-pair-separator'];
| + | end |
− | end
| + | end |
− | error_str = error_str .. wrap( 'parameter', selected );
| + | |
− | table.insert( z.message_tail, { seterror( error_condition, {error_str}, true ) } );
| + | return '', '', '', ''; -- return empty strings |
− | end
| |
− |
| |
− | return value, selected;
| |
| end | | end |
| | | |
− | -- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse | + | --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ |
− | -- the citation information. | + | |
− | function COinS(data)
| + | This is the main function doing the majority of the citation formatting. |
− | if 'table' ~= type(data) or nil == next(data) then
| |
− | return '';
| |
− | end
| |
− |
| |
− | local ctx_ver = "Z39.88-2004";
| |
− |
| |
− | -- treat table strictly as an array with only set values.
| |
− | local OCinSoutput = setmetatable( {}, {
| |
− | __newindex = function(self, key, value)
| |
− | if is_set(value) then
| |
− | rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( removewikilink( value ) ) } );
| |
− | end
| |
− | end
| |
− | });
| |
− |
| |
− | if is_set(data.Chapter) then
| |
− | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
| |
− | 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
| |
− | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:book";
| |
− | OCinSoutput["rft.genre"] = "book"
| |
− | OCinSoutput["rft.btitle"] = data.Title;
| |
− | end
| |
− |
| |
− | OCinSoutput["rft.place"] = data.PublicationPlace;
| |
− | 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
| |
− |
| |
− | local last, first;
| |
− | for k, v in ipairs( data.Authors ) do
| |
− | last, first = v.last, v.first;
| |
− | if k == 1 then
| |
− | if is_set(last) then
| |
− | OCinSoutput["rft.aulast"] = last;
| |
− | end
| |
− | if is_set(first) then
| |
− | OCinSoutput["rft.aufirst"] = first;
| |
− | end
| |
− | end
| |
− | if is_set(last) and is_set(first) then
| |
− | OCinSoutput["rft.au"] = table.concat{ last, ", ", first };
| |
− | elseif is_set(last) then
| |
− | OCinSoutput["rft.au"] = last;
| |
− | 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
| |
| | | |
− | --[[
| |
− | This is the main function doing the majority of the citation
| |
− | formatting.
| |
| ]] | | ]] |
− | function citation0( config, args)
| |
− | --[[
| |
− | Load Input Parameters
| |
− | The argment_wrapper facillitates the mapping of multiple
| |
− | aliases to single internal variable.
| |
− | ]]
| |
− | local A = argument_wrapper( args );
| |
| | | |
− | local i
| + | local function citation0( config, args) |
− | local PPrefix = A['PPrefix']
| + | --[[ |
− | local PPPrefix = A['PPPrefix']
| + | Load Input Parameters |
− | if is_set( A['NoPP'] ) then PPPrefix = "" PPrefix = "" end
| + | The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. |
− |
| + | ]] |
− | -- Pick out the relevant fields from the arguments. Different citation templates
| + | local A = argument_wrapper( args ); |
− | -- define different field names for the same underlying things.
| + | local i |
− | local Authors = A['Authors'];
| + | |
− | local a = extractnames( args, 'AuthorList' );
| + | -- Pick out the relevant fields from the arguments. Different citation templates |
| + | -- define different field names for the same underlying things. |
| + | local author_etal; |
| + | local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
| + | local Authors; |
| + | local NameListFormat = A['NameListFormat']; |
| + | |
| + | 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 |
| + | NameListFormat = 'vanc'; -- override whatever |name-list-format= 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= |
| + | end |
| + | end |
| | | |
− | local Coauthors = A['Coauthors'];
| + | local Coauthors = A['Coauthors']; |
− | local Others = A['Others'];
| + | local Others = A['Others']; |
− | local Editors = A['Editors'];
| |
− | local e = extractnames( args, 'EditorList' );
| |
| | | |
− | local Year = A['Year'];
| + | local editor_etal; |
− | local PublicationDate = A['PublicationDate'];
| + | local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= |
− | local OrigYear = A['OrigYear'];
| + | local Editors; |
− | local Date = A['Date'];
| |
− | local LayDate = A['LayDate'];
| |
− | ------------------------------------------------- Get title data
| |
− | 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 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'];
| |
| | | |
| + | do -- to limit scope of selected |
| + | local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList'); |
| + | 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 |
| + | NameListFormat = 'vanc'; -- override whatever |name-list-format= might be |
| + | e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= |
| + | elseif 3 == selected then |
| + | Editors = A['Editors']; -- use content of |editors= |
| + | end |
| + | end |
| + | |
| + | local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs |
| + | local Translators; -- assembled translators name list |
| + | t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
| + | |
| + | local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
| + | local Contributors; -- assembled contributors name list |
| + | local Contribution = A['Contribution']; |
| + | if in_array(config.CitationClass, {"book","citation"}) and not 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 is_set (Contribution) then -- |contributor= requires |contribution= |
| + | table.insert( z.message_tail, { set_error( '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, { set_error( '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 select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters? |
| + | table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message |
| + | end |
| + | Contribution = nil; -- unset |
| + | end |
| + | |
| + | if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc' |
| + | NameListFormat = ''; -- anything else, set to empty string |
| + | 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 ScriptTitle = A['ScriptTitle']; |
| + | local BookTitle = A['BookTitle']; |
| + | local Conference = A['Conference']; |
| + | local TransTitle = A['TransTitle']; |
| + | local TitleNote = A['TitleNote']; |
| + | local TitleLink = A['TitleLink']; |
| + | if is_set (TitleLink) and false == link_param_ok (TitleLink) then |
| + | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=; |
| + | end |
| + | |
| + | local Chapter = A['Chapter']; |
| + | local ScriptChapter = A['ScriptChapter']; |
| + | local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode |
| + | local TransChapter = A['TransChapter']; |
| + | local TitleType = A['TitleType']; |
| + | local Degree = A['Degree']; |
| + | local Docket = A['Docket']; |
| + | local ArchiveFormat = A['ArchiveFormat']; |
| + | local ArchiveURL = A['ArchiveURL']; |
| + | local URL = A['URL'] |
| + | local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL |
| + | local ChapterURL = A['ChapterURL']; |
| + | local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL |
| + | local ConferenceFormat = A['ConferenceFormat']; |
| + | local ConferenceURL = A['ConferenceURL']; |
| + | local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL |
| + | local Periodical = A['Periodical']; |
| + | local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter |
| + | |
| + | local Series = A['Series']; |
| + | |
| + | local Volume; |
| + | local Issue; |
| + | local Page; |
| + | local Pages; |
| + | local At; |
| + | |
| + | if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then |
| + | Volume = A['Volume']; |
| + | end |
| + | if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then |
| + | Issue = A['Issue']; |
| + | end |
| + | local Position = ''; |
| + | if not in_array (config.CitationClass, cfg.templates_not_using_page) then |
| + | Page = A['Page']; |
| + | Pages = hyphen_to_dash( A['Pages'] ); |
| + | At = A['At']; |
| + | end |
| + | |
| + | local Edition = A['Edition']; |
| + | local PublicationPlace = A['PublicationPlace'] |
| + | local Place = A['Place']; |
| + | |
| + | local PublisherName = A['PublisherName']; |
| + | local RegistrationRequired = A['RegistrationRequired']; |
| + | if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then |
| + | RegistrationRequired=nil; |
| + | end |
| + | local SubscriptionRequired = A['SubscriptionRequired']; |
| + | if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then |
| + | SubscriptionRequired=nil; |
| + | end |
| + | |
| + | local Via = A['Via']; |
| + | local AccessDate = A['AccessDate']; |
| + | local ArchiveDate = A['ArchiveDate']; |
| + | local Agency = A['Agency']; |
| + | local DeadURL = A['DeadURL'] |
| + | if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' |
| + | DeadURL = ''; -- anything else, set to empty string |
| + | end |
| + | |
| + | local Language = A['Language']; |
| + | local Format = A['Format']; |
| + | local ChapterFormat = A['ChapterFormat']; |
| + | local DoiBroken = A['DoiBroken']; |
| + | local ID = A['ID']; |
| + | local ASINTLD = A['ASINTLD']; |
| + | local IgnoreISBN = A['IgnoreISBN']; |
| + | if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then |
| + | IgnoreISBN = nil; -- anything else, set to empty string |
| + | end |
| + | local Embargo = A['Embargo']; |
| + | local Class = A['Class']; -- arxiv class identifier |
| + | |
| + | local ID_list = extract_ids( args ); |
| + | |
| + | local Quote = A['Quote']; |
| + | |
| + | local LayFormat = A['LayFormat']; |
| + | local LayURL = A['LayURL']; |
| + | local LaySource = A['LaySource']; |
| + | local Transcript = A['Transcript']; |
| + | local TranscriptFormat = A['TranscriptFormat']; |
| + | local TranscriptURL = A['TranscriptURL'] |
| + | local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL |
| + | |
| + | local LastAuthorAmp = A['LastAuthorAmp']; |
| + | if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then |
| + | LastAuthorAmp = nil; -- set to empty string |
| + | end |
| + | local no_tracking_cats = A['NoTracking']; |
| + | if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then |
| + | no_tracking_cats = nil; -- set to empty string |
| + | end |
| + | |
| + | --these are used by cite interview |
| + | local Callsign = A['Callsign']; |
| + | local City = A['City']; |
| + | local Program = A['Program']; |
| + | |
| + | --local variables that are not cs1 parameters |
| + | local use_lowercase; -- controls capitalization of certain static text |
| + | local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language |
| + | local anchor_year; -- used in the CITEREF identifier |
| + | local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification |
| + | |
| + | -- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values |
| + | local Mode = A['Mode']; |
| + | if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then |
| + | Mode = ''; |
| + | end |
| + | local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma |
| + | local PostScript; |
| + | local Ref; |
| + | sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass); |
| + | use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text |
| + | |
| + | --check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories |
| + | if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page |
| + | if in_array (this_page.nsText, cfg.uncategorized_namespaces) then |
| + | no_tracking_cats = "true"; -- set no_tracking_cats |
| + | end |
| + | for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns |
| + | if this_page.text:match (v) then -- test page name against each pattern |
| + | no_tracking_cats = "true"; -- set no_tracking_cats |
| + | break; -- bail out if one is found |
| + | end |
| + | end |
| + | end |
| + | |
| + | -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) |
| + | select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category |
| + | |
| + | local NoPP = A['NoPP'] |
| + | if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then |
| + | NoPP = true; |
| + | else |
| + | NoPP = nil; -- unset, used as a flag later |
| + | end |
| + | |
| + | if is_set(Page) then |
| + | if is_set(Pages) or is_set(At) then |
| + | Pages = ''; -- unset the others |
| + | At = ''; |
| + | end |
| + | extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp. |
| + | elseif is_set(Pages) then |
| + | if is_set(At) then |
| + | At = ''; -- unset |
| + | end |
| + | extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. |
| + | end |
| + | |
| + | -- both |publication-place= and |place= (|location=) allowed if different |
| + | if not is_set(PublicationPlace) and is_set(Place) then |
| + | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
| + | end |
| + | |
| + | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
| + | |
| --[[ | | --[[ |
| Parameter remapping for cite encyclopedia: | | Parameter remapping for cite encyclopedia: |
Line 1,208: |
Line 2,948: |
| | | |
| |trans_title maps to |trans_chapter when |title is re-mapped | | |trans_title maps to |trans_chapter when |title is re-mapped |
| + | |url maps to |chapterurl when |title is remapped |
| | | |
| All other combinations of |encyclopedia, |title, and |article are not modified | | All other combinations of |encyclopedia, |title, and |article are not modified |
| + | |
| ]] | | ]] |
− | if ( config.CitationClass == "encyclopaedia" ) then | + | |
− | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set | + | local Encyclopedia = A['Encyclopedia']; |
− | if is_set(Title) then | + | |
| + | if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation |
| + | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set |
| + | if is_set(Title) or is_set (ScriptTitle) then |
| if not is_set(Chapter) then | | if not is_set(Chapter) then |
− | Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title | + | Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
| + | ScriptChapter = ScriptTitle; |
| TransChapter = TransTitle; | | TransChapter = TransTitle; |
| + | ChapterURL = URL; |
| + | if not is_set (ChapterURL) and is_set (TitleLink) then |
| + | Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]'; |
| + | end |
| Title = Periodical; | | Title = Periodical; |
− | Periodical = ''; -- redundant so unset | + | ChapterFormat = Format; |
− | TransTitle = ''; -- redundant so unset | + | Periodical = ''; -- redundant so unset |
| + | TransTitle = ''; |
| + | URL = ''; |
| + | Format = ''; |
| + | TitleLink = ''; |
| + | ScriptTitle = ''; |
| end | | end |
− | else -- |title not set | + | else -- |title not set |
− | Title = Periodical; -- |encyclopedia set and |article set or not 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 |
| | | |
− | local Series = A['Series'];
| |
− | local Volume = A['Volume'];
| |
− | local Issue = A['Issue'];
| |
− | local Position = '';
| |
− | local Page, Pages, At, page_type;
| |
− |
| |
− | Page = A['Page'];
| |
− | Pages = hyphentodash( A['Pages'] );
| |
− | At = A['At'];
| |
− |
| |
− | if is_set(Page) then
| |
− | if is_set(Pages) or is_set(At) then
| |
− | Page = Page .. " " .. seterror('extra_pages');
| |
− | Pages = '';
| |
− | At = '';
| |
− | end
| |
− | elseif is_set(Pages) then
| |
− | if is_set(At) then
| |
− | Pages = Pages .. " " .. seterror('extra_pages');
| |
− | At = '';
| |
− | end
| |
− | end
| |
− |
| |
− | local Edition = A['Edition'];
| |
− | local PublicationPlace = A['PublicationPlace']
| |
− | local Place = A['Place'];
| |
− |
| |
− | if not is_set(PublicationPlace) and is_set(Place) then
| |
− | PublicationPlace = Place;
| |
− | end
| |
− |
| |
− | if PublicationPlace == Place then Place = ''; end
| |
− |
| |
− | 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'];
| |
− |
| |
| -- Special case for cite techreport. | | -- Special case for cite techreport. |
− | local ID = A['ID'];
| + | if (config.CitationClass == "techreport") then -- special case for cite techreport |
− | if (config.CitationClass == "techreport") then -- special case for cite techreport | + | if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' |
− | if is_set(Issue) then -- cite techreport uses 'number', which other citations aliase to 'issue' | + | if not is_set(ID) then -- can we use ID for the "number"? |
− | if not is_set(ID) then -- can we use ID for the "number"? | + | ID = A['Number']; -- yes, use it |
− | ID = Issue; -- yes, use it | + | else -- ID has a value so emit error message |
− | Issue = ""; -- unset Issue so that "number" isn't duplicated in the rendered citation or COinS metadata
| + | table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )}); |
− | else -- can't use ID so emit error message | |
− | ID = ID .. " " .. seterror('redundant_parameters', '<code>|id=</code> and <code>|number=</code>'); | |
| end | | end |
| end | | end |
− | end | + | end |
| + | |
| + | -- special case for cite interview |
| + | if (config.CitationClass == "interview") then |
| + | if is_set(Program) then |
| + | ID = ' ' .. Program; |
| + | end |
| + | if is_set(Callsign) then |
| + | if is_set(ID) then |
| + | ID = ID .. sepc .. ' ' .. Callsign; |
| + | else |
| + | ID = ' ' .. Callsign; |
| + | end |
| + | end |
| + | if is_set(City) then |
| + | if is_set(ID) then |
| + | ID = ID .. sepc .. ' ' .. City; |
| + | else |
| + | ID = ' ' .. City; |
| + | end |
| + | end |
| + | |
| + | if is_set(Others) then |
| + | if is_set(TitleType) then |
| + | Others = ' ' .. TitleType .. ' with ' .. Others; |
| + | TitleType = ''; |
| + | else |
| + | Others = ' ' .. 'Interview with ' .. Others; |
| + | end |
| + | else |
| + | Others = '(Interview)'; |
| + | end |
| + | end |
| + | |
| + | -- special case for cite mailing list |
| + | if (config.CitationClass == "mailinglist") then |
| + | Periodical = A ['MailingList']; |
| + | elseif 'mailinglist' == A:ORIGIN('Periodical') then |
| + | Periodical = ''; -- unset because mailing list is only used for cite mailing list |
| + | end |
| + | |
| + | -- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
| + | if 'conference' == config.CitationClass then |
| + | if is_set(BookTitle) then |
| + | Chapter = Title; |
| + | -- ChapterLink = TitleLink; -- |chapterlink= is deprecated |
| + | ChapterURL = URL; |
| + | ChapterURLorigin = URLorigin; |
| + | URLorigin = ''; |
| + | ChapterFormat = Format; |
| + | TransChapter = TransTitle; |
| + | Title = BookTitle; |
| + | Format = ''; |
| + | -- TitleLink = ''; |
| + | TransTitle = ''; |
| + | URL = ''; |
| + | end |
| + | elseif 'speech' ~= config.CitationClass then |
| + | Conference = ''; -- not cite conference or cite speech so make sure this is empty string |
| + | end |
| + | |
| + | -- cite map oddities |
| + | local Cartography = ""; |
| + | local Scale = ""; |
| + | local Sheet = A['Sheet'] or ''; |
| + | local Sheets = A['Sheets'] or ''; |
| + | if config.CitationClass == "map" then |
| + | Chapter = A['Map']; |
| + | ChapterURL = A['MapURL']; |
| + | TransChapter = A['TransMap']; |
| + | ChapterURLorigin = A:ORIGIN('MapURL'); |
| + | ChapterFormat = A['MapFormat']; |
| + | |
| + | Cartography = A['Cartography']; |
| + | if is_set( Cartography ) then |
| + | Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); |
| + | end |
| + | Scale = A['Scale']; |
| + | if is_set( Scale ) then |
| + | Scale = sepc .. " " .. Scale; |
| + | end |
| + | end |
| + | |
| + | -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. |
| + | if 'episode' == config.CitationClass or 'serial' == config.CitationClass then |
| + | local AirDate = A['AirDate']; |
| + | local SeriesLink = A['SeriesLink']; |
| + | if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then |
| + | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))}); |
| + | end |
| + | local Network = A['Network']; |
| + | local Station = A['Station']; |
| + | local s, n = {}, {}; |
| + | -- do common parameters first |
| + | if is_set(Network) then table.insert(n, Network); end |
| + | if is_set(Station) then table.insert(n, Station); end |
| + | ID = table.concat(n, sepc .. ' '); |
| + | |
| + | if not is_set (Date) and is_set (AirDate) then -- promote airdate to date |
| + | Date = AirDate; |
| + | end |
| + | |
| + | if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
| + | local Season = A['Season']; |
| + | local SeriesNumber = A['SeriesNumber']; |
| + | |
| + | if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set |
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. 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 is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
| + | if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end |
| + | if 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; |
| + | ChapterLink = TitleLink; -- alias episodelink |
| + | TransChapter = TransTitle; |
| + | ChapterURL = URL; |
| + | ChapterURLorigin = A:ORIGIN('URL'); |
| + | |
| + | Title = Series; -- promote series to title |
| + | TitleLink = SeriesLink; |
| + | Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number |
| + | |
| + | if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL |
| + | Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink |
| + | elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; |
| + | Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly |
| + | end |
| + | URL = ''; -- unset |
| + | TransTitle = ''; |
| + | ScriptTitle = ''; |
| | | |
− | local ASINTLD = A['ASINTLD'];
| + | else -- now oddities that are cite serial |
− | local IgnoreISBN = A['IgnoreISBN'];
| + | Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial |
− | local Embargo = A['Embargo'];
| + | Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? |
| + | if is_set (Series) and is_set (SeriesLink) then |
| + | Series = '[[' .. SeriesLink .. '|' .. Series .. ']]'; |
| + | end |
| + | Series = wrap_style ('italic-title', Series); -- series is italicized |
| + | end |
| + | end |
| + | -- end of {{cite episode}} stuff |
| | | |
− | local ID_list = extractids( args );
| + | -- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. |
− |
| + | if 'arxiv' == config.CitationClass then |
− | local Quote = A['Quote'];
| + | if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv |
− | local PostScript = A['PostScript'];
| + | table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message |
− | local LayURL = A['LayURL'];
| + | elseif is_set (Series) then -- series is an alias of version |
− | local LaySource = A['LaySource'];
| + | ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier |
− | local Transcript = A['Transcript'];
| + | Series = ''; -- unset |
− | local TranscriptURL = A['TranscriptURL']
| + | deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv |
− | local TranscriptURLorigin = A:ORIGIN('TranscriptURL');
| + | end |
− | local sepc = A['Separator'];
| + | |
− | local LastAuthorAmp = A['LastAuthorAmp'];
| + | if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv |
− | local no_tracking_cats = A['NoTracking'];
| + | ID_list['ASIN'], ID_list['BIBCODE'], ID_list['DOI'], ID_list['ISBN'], ID_list['ISSN'], |
| + | ID_list['JFM'], ID_list['JSTOR'], ID_list['LCCN'], ID_list['MR'], ID_list['OCLC'], ID_list['OL'], |
| + | ID_list['OSTI'], ID_list['PMC'], ID_list['PMID'], ID_list['RFC'], ID_list['SSRN'], ID_list['USENETID'], ID_list['ZBL']},27) then |
| + | table.insert( z.message_tail, { set_error( 'arxiv_params_not_supported', {}, true ) } ); -- add error message |
| | | |
− | local use_lowercase = ( sepc ~= '.' );
| + | AccessDate= ''; -- set these to empty string; not supported in cite arXiv |
− | local this_page = mw.title.getCurrentTitle(); --Also used for COinS and for language
| + | PublisherName = ''; -- (if the article has been published, use cite journal, or other) |
− |
| + | Chapter = ''; |
− | if not is_set(no_tracking_cats) then
| + | URL = ''; |
− | for k, v in pairs( cfg.uncategorized_namespaces ) do
| + | Format = ''; |
− | if this_page.nsText == v then
| + | Page = ''; Pages = ''; At = ''; |
− | no_tracking_cats = "true";
| + | end |
− | break;
| + | Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string |
− | end
| + | end |
− | end
| |
− | end
| |
| | | |
− | local anchor_year; -- used in the CITEREF identifier | + | -- handle type parameter for those CS1 citations that have default values |
− | local COinS_date; -- used in the COinS metadata
| + | if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then |
| + | TitleType = set_titletype (config.CitationClass, TitleType); |
| + | if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis |
| + | TitleType = Degree .. " thesis"; |
| + | end |
| + | end |
| | | |
− | -- 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 is_set(TitleType) then -- if type parameter is specified |
− | if not is_set(Date) then | + | TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses |
− | Date = Year; -- promote Year to Date | + | end |
− | Year = nil; -- make nil so Year as empty string isn't used for CITEREF | + | |
− | if is_set(Date) then | + | -- legacy: promote concatenation of |month=, and |year= to Date if Date not set; or, promote PublicationDate to Date if neither Date nor Year are set. |
− | local Month = A['Month']; | + | if not is_set (Date) then |
− | if is_set(Month) then
| + | Date = Year; -- promote Year to Date |
− | Date = Month .. " " .. Date; | + | Year = nil; -- make nil so Year as empty string isn't used for CITEREF |
− | local Day = A['Day']
| + | if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set |
− | if is_set(Day) then Date = Day .. " " .. Date end | + | Date = PublicationDate; -- promote PublicationDate to Date |
| + | PublicationDate = ''; -- unset, no longer needed |
| + | end |
| + | end |
| + | |
| + | if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation |
| + | |
| + | --[[ |
| + | 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 |
| + | ]] |
| + | do -- create defined block to contain local variables error_message and mismatch |
| + | local error_message = ''; |
| + | -- AirDate has been promoted to Date so not necessary to check it |
| + | anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, |
| + | ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date); |
| + | |
| + | if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; |
| + | local mismatch = year_date_check (Year, Date) |
| + | if 0 == mismatch then -- |year= does not match a year-value in |date= |
| + | if is_set (error_message) then -- if there is already an error message |
| + | error_message = error_message .. ', '; -- tack on this additional message |
| + | end |
| + | error_message = error_message .. '|year= / |date= mismatch'; |
| + | elseif 1 == mismatch then -- |year= matches year-value in |date= |
| + | add_maint_cat ('date_year'); |
| end | | end |
− | elseif is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set | + | end |
− | Date = PublicationDate; -- promonte PublicationDate to Date | + | |
− | PublicationDate = ''; -- unset, no longer needed | + | if is_set(error_message) then |
| + | table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message |
| + | end |
| + | end -- end of do |
| + | |
| + | -- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS. |
| + | -- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date |
| + | Embargo = is_embargoed (Embargo); -- |
| + | |
| + | if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
| + | if not is_set (Embargo) then -- if not embargoed or embargo has expired |
| + | URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed |
| + | URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title= |
| end | | end |
| end | | end |
| | | |
− | if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation | + | -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. |
| + | -- Test if citation has no title |
| + | if not is_set(Title) and |
| + | not is_set(TransTitle) and |
| + | not is_set(ScriptTitle) then |
| + | if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? |
| + | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); |
| + | else |
| + | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); |
| + | end |
| + | end |
| + | |
| + | if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites |
| + | Title = ''; -- set title to empty string |
| + | add_maint_cat ('untitled'); |
| + | end |
| + | |
| + | check_for_url ({ -- add error message when any of these parameters contains a URL |
| + | ['title']=Title, |
| + | [A:ORIGIN('Chapter')]=Chapter, |
| + | [A:ORIGIN('Periodical')]=Periodical, |
| + | [A:ORIGIN('PublisherName')] = PublisherName, |
| + | }); |
| + | |
| + | -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. |
| + | -- 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 |
| + | -- is the article title, and Chapter is a section within the article. So, we remap |
| + | |
| + | local coins_chapter = Chapter; -- default assuming that remapping not required |
| + | local coins_title = Title; -- et tu |
| + | if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then |
| + | if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then |
| + | coins_chapter = Title; -- remap |
| + | coins_title = Periodical; |
| + | 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 |
| | | |
− | -- Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. | + | -- this is the function call to COinS() |
− | -- TODO: 2013-10-27: AirDate is nil when dates() is called because it hasn't been set yet. Move the call to dates() or set AirDate earlier. | + | local OCinSoutput = COinS({ |
− | anchor_year, COinS_date = dates({['accessdate']=AccessDate, ['airdate']=AirDate, ['archivedate']=ArchiveDate, ['date']=Date, ['doi_brokendate']=DoiBroken,
| + | ['Periodical'] = Periodical, |
− | ['embargo']=Embargo, ['laydate']=LayDate, ['publicationdate']=PublicationDate, ['year']=Year}); | + | ['Encyclopedia'] = Encyclopedia, |
| + | ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup |
| + | ['Map'] = Map, |
| + | ['Degree'] = Degree; -- cite thesis only |
| + | ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup |
| + | ['PublicationPlace'] = PublicationPlace, |
| + | ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; |
| + | ['Season'] = COinS_date.rftssn, |
| + | ['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, |
| + | ['Volume'] = Volume, |
| + | ['Issue'] = Issue, |
| + | ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links |
| + | ['Edition'] = Edition, |
| + | ['PublisherName'] = PublisherName, |
| + | ['URL'] = first_set ({ChapterURL, URL}, 2), |
| + | ['Authors'] = coins_author, |
| + | ['ID_list'] = ID_list, |
| + | ['RawPage'] = this_page.prefixedText, |
| + | }, config.CitationClass); |
| | | |
− | -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. | + | -- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data. |
| + | if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed |
| + | Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal |
| + | end |
| | | |
− | --Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set
| + | -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text |
− | if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then | + | if 'newsgroup' == config.CitationClass then |
− | if not is_embargoed(Embargo) then | + | if is_set (PublisherName) then |
− | URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed | + | PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') )); |
− | URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title=
| |
| end | | end |
| end | | end |
| | | |
− | -- Account for the oddity that is {{cite conference}}, before generation of COinS data.
| |
− | if is_set(BookTitle) then
| |
− | Chapter = Title;
| |
− | ChapterLink = TitleLink;
| |
− | TransChapter = TransTitle;
| |
− | Title = BookTitle;
| |
− | TitleLink = '';
| |
− | TransTitle = '';
| |
− | end
| |
− | -- Account for the oddity that is {{cite episode}}, before generation of COinS data.
| |
− | 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
| |
− |
| |
− | -- COinS metadata (see <http://ocoins.info/>) for
| |
− | -- automated parsing of citation information.
| |
− | local OCinSoutput = COinS{
| |
− | ['Periodical'] = Periodical,
| |
− | ['Chapter'] = Chapter,
| |
− | ['Title'] = Title,
| |
− | ['PublicationPlace'] = PublicationPlace,
| |
− | ['Date'] = first_set(COinS_date, Date), -- COinS_date has correctly formatted date if Date is valid; any reason to keep Date here? Should we be including invalid dates in metadata?
| |
− | ['Series'] = Series,
| |
− | ['Volume'] = Volume,
| |
− | ['Issue'] = Issue,
| |
− | ['Pages'] = first_set(Page, Pages, At),
| |
− | ['Edition'] = Edition,
| |
− | ['PublisherName'] = PublisherName,
| |
− | ['URL'] = first_set( URL, ChapterURL ),
| |
− | ['Authors'] = a,
| |
− | ['ID_list'] = ID_list,
| |
− | ['RawPage'] = this_page.prefixedText,
| |
− | };
| |
| | | |
− | if is_set(Periodical) and not is_set(Chapter) and is_set(Title) then
| |
− | Chapter = Title;
| |
− | ChapterLink = TitleLink;
| |
− | TransChapter = TransTitle;
| |
− | Title = '';
| |
− | TitleLink = '';
| |
− | TransTitle = '';
| |
− | end
| |
| | | |
− | -- 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. |
− | if not is_set(Authors) then
| + | local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list |
− | local Maximum = tonumber( A['DisplayAuthors'] );
| + | do |
− |
| + | local last_first_list; |
− | -- Preserve old-style implicit et al.
| + | local maximum; |
− | if not is_set(Maximum) and #a == 9 then
| + | local control = { |
− | Maximum = 8;
| + | format = NameListFormat, -- empty string or 'vanc' |
− | table.insert( z.message_tail, { seterror('implict_etal_author', {}, true ) } );
| + | maximum = nil, -- as if display-authors or display-editors not set |
− | elseif not is_set(Maximum) then
| + | lastauthoramp = LastAuthorAmp, |
− | Maximum = #a + 1;
| + | page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn |
− | end
| + | }; |
− |
| + | |
− | local control = {
| + | do -- do editor name list first because coauthors can modify control table |
− | sep = A["AuthorSeparator"] .. " ",
| + | maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal); |
− | namesep = (first_set(A["AuthorNameSeparator"], A["NameSeparator"]) or "") .. " ",
| + | -- Preserve old-style implicit et al. |
− | format = A["AuthorFormat"],
| + | if not is_set(maximum) and #e == 4 then |
− | maximum = Maximum,
| + | maximum = 3; |
− | lastauthoramp = LastAuthorAmp
| + | table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } ); |
− | };
| + | end |
− |
| |
− | -- 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
| |
| | | |
− | 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 = maximum; |
− | table.insert( z.message_tail, { seterror('coauthors_missing_author', {}, true) } ); -- emit error message
| + | |
| + | last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor'); |
| + | |
| + | if is_set (Editors) then |
| + | if editor_etal then |
| + | Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal |
| + | EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation |
| + | else |
| + | EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation |
| + | end |
| + | else |
| + | Editors = last_first_list; -- either an author name list or an empty string |
| + | end |
| + | |
| + | if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then |
| + | EditorCount = 2; -- spoof to display (eds.) annotation |
| + | end |
| + | end |
| + | do -- now do translators |
| + | control.maximum = #t; -- number of translators |
| + | Translators = list_people(control, t, false, 'translator'); -- et al not currently supported |
| + | end |
| + | do -- now do contributors |
| + | control.maximum = #c; -- number of contributors |
| + | Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported |
| + | end |
| + | do -- now do authors |
| + | control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal); |
| + | |
| + | if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting. |
| + | control.lastauthoramp = nil; |
| + | control.maximum = #a + 1; |
| + | end |
| + | |
| + | last_first_list = list_people(control, a, author_etal, 'author'); |
| + | |
| + | if is_set (Authors) then |
| + | Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. |
| + | if author_etal then |
| + | Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter |
| + | end |
| + | else |
| + | Authors = last_first_list; -- either an author name list or an empty string |
| + | end |
| + | end -- end of do |
| + | |
| + | if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified |
| + | table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message |
| + | end |
| end | | end |
| | | |
− | local EditorCount
| + | -- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation, |
− | if not is_set(Editors) then
| + | -- an error message if the associated url is not set, or an empty string for concatenation |
− | local Maximum = tonumber( A['DisplayEditors'] );
| + | ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); |
− | -- Preserve old-style implicit et al.
| + | ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); |
− | if not is_set(Maximum) and #e == 4 then
| + | Format = style_format (Format, URL, 'format', 'url'); |
− | Maximum = 3;
| + | LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); |
− | table.insert( z.message_tail, { seterror('implict_etal_editor', {}, true) } );
| + | TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); |
− | elseif not is_set(Maximum) then
| |
− | Maximum = #e + 1;
| |
− | end
| |
| | | |
− | local control = {
| + | -- special case for chapter format so no error message or cat when chapter not supported |
− | sep = A["EditorSeparator"] .. " ",
| + | if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or |
− | namesep = (first_set(A["EditorNameSeparator"], A["NameSeparator"]) or "") .. " ",
| + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then |
− | format = A['EditorFormat'],
| + | ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); |
− | maximum = Maximum,
| + | end |
− | lastauthoramp = LastAuthorAmp
| |
− | };
| |
| | | |
− | Editors, EditorCount = listpeople(control, e);
| + | if not is_set(URL) then --and |
− | else
| + | if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty |
− | EditorCount = 1;
| + | table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); |
− | end
| + | end |
| + | |
| + | -- Test if accessdate is given without giving a URL |
| + | if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test? |
| + | table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
| + | AccessDate = ''; |
| + | end |
| + | end |
| | | |
− | local Cartography = "";
| + | local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set? |
− | local Scale = "";
| + | DeadURL = DeadURL:lower(); -- used later when assembling archived text |
− | if config.CitationClass == "map" then
| + | if is_set( ArchiveURL ) then |
− | if not is_set( Authors ) and is_set( PublisherName ) then
| + | if is_set (URL) then |
− | Authors = PublisherName;
| + | OriginalURL = URL; -- save copy of original source URL |
− | PublisherName = "";
| + | OriginalURLorigin = URLorigin; -- name of url parameter for error messages |
− | end
| + | OriginalFormat = Format; -- and original |format= |
− | Cartography = A['Cartography'];
| + | if 'no' ~= DeadURL then -- if URL set then archive-url applies to it |
− | if is_set( Cartography ) then
| + | URL = ArchiveURL -- swap-in the archive's url |
− | Cartography = sepc .. " " .. wrap( 'cartography', Cartography, use_lowercase );
| + | URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages |
− | end
| + | Format = ArchiveFormat or ''; -- swap in archive's format |
− | Scale = A['Scale'];
| + | end |
− | if is_set( Scale ) then
| + | elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it |
− | Scale = sepc .. " " .. Scale;
| + | OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text |
− | end
| + | OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages |
− | end
| + | OriginalFormat = ChapterFormat; -- and original |format= |
− |
| + | if 'no' ~= DeadURL then |
− | if not is_set(URL) and
| + | ChapterURL = ArchiveURL -- swap-in the archive's url |
− | not is_set(ChapterURL) and
| + | ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages |
− | not is_set(ArchiveURL) and
| + | ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
− | not is_set(ConferenceURL) and
| + | end |
− | 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 |
− |
| + | end |
− | -- Test if accessdate is given without giving a URL
| |
− | if is_set(AccessDate) then
| |
− | table.insert( z.message_tail, { seterror( 'accessdate_missing_url', {}, true ) } );
| |
− | AccessDate = '';
| |
− | end
| |
− |
| |
− | -- Test if format is given without giving a URL
| |
− | if is_set(Format) then
| |
− | Format = Format .. seterror( 'format_missing_url' );
| |
− | end
| |
− | end
| |
− |
| |
− | -- Test if citation has no title
| |
− | if not is_set(Chapter) and
| |
− | not is_set(Title) and
| |
− | not is_set(Periodical) and
| |
− | not is_set(Conference) and
| |
− | not is_set(TransTitle) and
| |
− | not is_set(TransChapter) then
| |
− | table.insert( z.message_tail, { seterror( 'citation_missing_title', {}, true ) } );
| |
− | end
| |
− |
| |
− | Format = is_set(Format) and " (" .. Format .. ")" or "";
| |
− |
| |
− | local OriginalURL = URL
| |
− | DeadURL = DeadURL:lower();
| |
− | if is_set( ArchiveURL ) then
| |
− | if ( DeadURL ~= "no" ) then
| |
− | URL = ArchiveURL
| |
− | URLorigin = A:ORIGIN('ArchiveURL')
| |
− | end
| |
− | end
| |
− |
| |
− | -- Format chapter / article title
| |
− | if is_set(Chapter) and is_set(ChapterLink) then
| |
− | Chapter = "[[" .. ChapterLink .. "|" .. Chapter .. "]]";
| |
− | end
| |
− | if is_set(Periodical) and is_set(Title) then
| |
− | Chapter = wrap( 'italic-title', Chapter );
| |
− | TransChapter = wrap( 'trans-italic-title', TransChapter );
| |
− | else
| |
− | Chapter = kern_quotes (Chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks
| |
− | Chapter = wrap( 'quoted-title', Chapter );
| |
− | TransChapter = wrap( 'trans-quoted-title', TransChapter );
| |
− | end
| |
− |
| |
− | local TransError = ""
| |
− | if is_set(TransChapter) then
| |
− | if not is_set(Chapter) then
| |
− | TransError = " " .. seterror( 'trans_missing_chapter' );
| |
− | else
| |
− | TransChapter = " " .. TransChapter;
| |
− | end
| |
− | end
| |
− |
| |
− | Chapter = Chapter .. TransChapter;
| |
− |
| |
− | if is_set(Chapter) then
| |
− | if not is_set(ChapterLink) then
| |
− | 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
| |
− | 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
| |
− |
| |
− | if is_set(Periodical) then
| |
− | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
| |
− | Title = wrap( 'quoted-title', Title );
| |
− | TransTitle = wrap( 'trans-quoted-title', TransTitle );
| |
− | elseif inArray(config.CitationClass, {"web","news","pressrelease","conference","podcast"}) and
| |
− | not is_set(Chapter) then
| |
− | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks
| |
− | Title = wrap( 'quoted-title', Title );
| |
− | TransTitle = wrap( 'trans-quoted-title', TransTitle );
| |
− | else
| |
− | Title = wrap( 'italic-title', Title );
| |
− | TransTitle = wrap( 'trans-italic-title', TransTitle );
| |
− | end
| |
− |
| |
− | TransError = "";
| |
− | if is_set(TransTitle) then
| |
− | if not is_set(Title) then
| |
− | TransError = " " .. seterror( 'trans_missing_title' );
| |
− | else
| |
− | TransTitle = " " .. TransTitle;
| |
− | end
| |
− | end
| |
− |
| |
− | Title = Title .. TransTitle;
| |
− |
| |
− | if is_set(Title) then
| |
− | if not is_set(TitleLink) and is_set(URL) then
| |
− | Title = externallink( URL, Title ) .. TransError .. Format
| |
− | URL = "";
| |
− | Format = "";
| |
− | else
| |
− | Title = Title .. TransError;
| |
− | end
| |
− | end
| |
− |
| |
− | if is_set(Place) then
| |
− | Place = " " .. wrap( 'written', Place, use_lowercase ) .. sepc .. " ";
| |
− | end
| |
− |
| |
− | if is_set(Conference) then
| |
− | if is_set(ConferenceURL) then
| |
− | Conference = externallink( ConferenceURL, Conference );
| |
− | end
| |
− | Conference = sepc .. " " .. Conference
| |
− | elseif is_set(ConferenceURL) then
| |
− | Conference = sepc .. " " .. externallink( ConferenceURL, nil, ConferenceURLorigin );
| |
− | end
| |
− |
| |
− | if not is_set(Position) then
| |
− | local Minutes = A['Minutes'];
| |
− | if is_set(Minutes) then
| |
− | Position = " " .. Minutes .. " " .. cfg.messages['minutes'];
| |
− | else
| |
− | local Time = A['Time'];
| |
− | if is_set(Time) then
| |
− | local TimeCaption = A['TimeCaption']
| |
− | if not is_set(TimeCaption) then
| |
− | TimeCaption = cfg.messages['event'];
| |
− | if sepc ~= '.' then
| |
− | TimeCaption = TimeCaption:lower();
| |
− | end
| |
− | end
| |
− | Position = " " .. TimeCaption .. " " .. Time;
| |
− | end
| |
− | end
| |
− | else
| |
− | Position = " " .. Position;
| |
− | At = '';
| |
− | end
| |
− |
| |
− | if not is_set(Page) then
| |
− | if is_set(Pages) then
| |
− | if is_set(Periodical) and
| |
− | 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
| |
− | local Section = A['Section'];
| |
− | local Inset = A['Inset'];
| |
− | if first_set( Pages, Page, At ) ~= nil or sepc ~= '.' then
| |
− | if is_set( Section ) then
| |
− | 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
| |
− | At = At .. Section .. Inset;
| |
− | end
| |
| | | |
− | --[[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 in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia |
− | use that value; if not, then use the value that was provided with the language parameter. | + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then |
| + | local chap_param; |
| + | if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters |
| + | chap_param = A:ORIGIN ('Chapter') |
| + | elseif is_set (TransChapter) then |
| + | chap_param = A:ORIGIN ('TransChapter') |
| + | elseif is_set (ChapterURL) then |
| + | chap_param = A:ORIGIN ('ChapterURL') |
| + | elseif is_set (ScriptChapter) then |
| + | chap_param = A:ORIGIN ('ScriptChapter') |
| + | else is_set (ChapterFormat) |
| + | chap_param = A:ORIGIN ('ChapterFormat') |
| + | end |
| + | |
| + | if is_set (chap_param) then -- if we found one |
| + | table.insert( z.message_tail, { set_error( '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 is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) |
| + | if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title |
| + | no_quotes = true; -- then render it unquoted |
| + | end |
| + | end |
| + | |
| + | Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter |
| + | if is_set (Chapter) then |
| + | if 'map' == config.CitationClass and is_set (TitleType) then |
| + | Chapter = Chapter .. ' ' .. TitleType; |
| + | end |
| + | Chapter = Chapter .. ChapterFormat .. sepc .. ' '; |
| + | elseif 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 |
| + | |
| + | -- Format main title. |
| + | if is_set(TitleLink) and is_set(Title) then |
| + | Title = "[[" .. TitleLink .. "|" .. Title .. "]]" |
| + | end |
| + | |
| + | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or |
| + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or |
| + | ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article |
| + | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks |
| + | Title = wrap_style ('quoted-title', Title); |
| + | |
| + | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
| + | TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
| + | elseif 'report' == config.CitationClass then -- no styling for cite report |
| + | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
| + | TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title |
| + | else |
| + | Title = wrap_style ('italic-title', Title); |
| + | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
| + | TransTitle = wrap_style ('trans-italic-title', TransTitle); |
| + | end |
| + | |
| + | TransError = ""; |
| + | if is_set(TransTitle) then |
| + | if is_set(Title) then |
| + | TransTitle = " " .. TransTitle; |
| + | else |
| + | TransError = " " .. set_error( 'trans_missing_title', {'title'} ); |
| + | end |
| + | end |
| + | |
| + | Title = Title .. TransTitle; |
| | | |
− | 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). | + | if is_set(Title) then |
− | ]] | + | if not is_set(TitleLink) and is_set(URL) then |
− | if is_set (Language) then | + | Title = external_link( URL, Title, URLorigin ) .. TransError .. Format; |
− | -- local name = mw.language.fetchLanguageName( Language:lower(), "en" ); -- experiment: this seems to return correct ISO 639-1 language names
| + | URL = ""; |
− | local name = cfg.iso639_1[Language:lower()]; -- get the language name if Language parameter has a valid iso 639-1 code | + | Format = ""; |
− | if nil == name then | + | else |
− | Language=" " .. wrap( 'language', Language ); -- no match, use parameter's value | + | Title = Title .. TransError; |
| + | end |
| + | end |
| + | |
| + | if is_set(Place) then |
| + | Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; |
| + | end |
| + | |
| + | if is_set (Conference) then |
| + | if is_set (ConferenceURL) then |
| + | Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin ); |
| + | end |
| + | Conference = sepc .. " " .. Conference .. ConferenceFormat; |
| + | elseif is_set(ConferenceURL) then |
| + | Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin ); |
| + | end |
| + | |
| + | if not is_set(Position) then |
| + | local Minutes = A['Minutes']; |
| + | local Time = A['Time']; |
| + | |
| + | if is_set(Minutes) then |
| + | if is_set (Time) then |
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } ); |
| + | end |
| + | Position = " " .. Minutes .. " " .. cfg.messages['minutes']; |
| else | | else |
− | if 0 == this_page.namespace and 'en' ~= Language:lower() then --found a match; is this page main / article space and English not the language? | + | if is_set(Time) then |
− | Language=" " .. wrap( 'language', name .. '[[Category:Articles with ' .. name .. '-language external links]]' ); -- in main space and not English: categorize | + | local TimeCaption = A['TimeCaption'] |
− | else
| + | if not is_set(TimeCaption) then |
− | Language=" " .. wrap( 'language', name ); --not in mainspace or language is English so don't categorize
| + | TimeCaption = cfg.messages['event']; |
| + | if sepc ~= '.' then |
| + | TimeCaption = TimeCaption:lower(); |
| + | end |
| + | end |
| + | Position = " " .. TimeCaption .. " " .. Time; |
| end | | end |
| end | | end |
| else | | else |
− | Language=""; -- language not specified so make sure this is an empty string; | + | Position = " " .. Position; |
| + | At = ''; |
| end | | end |
| | | |
− | Others = is_set(Others) and (sepc .. " " .. Others) or ""; | + | Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); |
| | | |
− | -- handle type parameter for those CS1 citations that have default values
| + | At = is_set(At) and (sepc .. " " .. At) or ""; |
| + | Position = is_set(Position) and (sepc .. " " .. Position) or ""; |
| + | if config.CitationClass == 'map' then |
| + | local Section = A['Section']; |
| + | local Sections = A['Sections']; |
| + | local Inset = A['Inset']; |
| + | |
| + | if is_set( Inset ) then |
| + | Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); |
| + | end |
| | | |
− | if inArray(config.CitationClass, {"podcast","pressrelease","techreport","thesis"}) then
| + | if is_set( Sections ) then |
− | TitleType = set_titletype (config.CitationClass, TitleType);
| + | Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); |
− | if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis | + | elseif is_set( Section ) then |
− | TitleType = Degree .. " thesis"; | + | Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); |
| end | | end |
| + | At = At .. Inset .. Section; |
| + | end |
| + | |
| + | if 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; |
| end | | end |
| | | |
− | if is_set(TitleType) then -- if type parameter is specified | + | Others = is_set(Others) and (sepc .. " " .. Others) or ""; |
− | TitleType = " (" .. TitleType .. ")"; -- display it in parentheses | + | |
| + | if is_set (Translators) then |
| + | Others = sepc .. ' Translated by ' .. Translators .. Others; |
| end | | end |
| | | |
| TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; | | TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; |
− | Edition = is_set(Edition) and (" " .. wrap( 'edition', Edition )) or "";
| + | if is_set (Edition) then |
− | Issue = is_set(Issue) and (" (" .. Issue .. ")") or "";
| + | if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then |
− | Series = is_set(Series) and (sepc .. " " .. Series) or "";
| + | add_maint_cat ('extra_text', 'edition'); |
− | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
| + | end |
− | Agency = is_set(Agency) and (sepc .. " " .. Agency) or "";
| + | Edition = " " .. wrap_msg ('edition', Edition); |
− |
| + | else |
− | if is_set(Volume) then
| + | Edition = ''; |
− | if ( mw.ustring.len(Volume) > 4 )
| + | end |
− | then Volume = sepc .." " .. Volume;
| + | |
− | else Volume = " <b>" .. hyphentodash(Volume) .. "</b>";
| + | Series = is_set(Series) and (sepc .. " " .. Series) or ""; |
− | end
| + | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; |
− | end
| + | Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; |
− |
| + | |
− | ------------------------------------ totally unrelated data
| + | Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
− | --[[ 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).
| + | ------------------------------------ totally unrelated data |
− |
| + | if is_set(Via) then |
− | 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.
| + | Via = " " .. wrap_msg ('via', Via); |
− | ]]
| + | end |
− | if is_set(Via) then
| |
− | Via = " " .. wrap( 'via', Via );
| |
− | end
| |
| | | |
− | if is_set(SubscriptionRequired) then
| + | --[[ |
− | SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; --here when 'via' parameter not used but 'subscription' is
| + | Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link |
− | elseif is_set(RegistrationRequired) then
| + | note is displayed. There are no error messages for this condition. |
− | SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; --here when 'via' and 'subscription' parameters not used but 'registration' is
| |
− | end
| |
| | | |
− | if is_set(AccessDate) then
| + | ]] |
− | local retrv_text = " " .. cfg.messages['retrieved']
| + | if is_set (SubscriptionRequired) then |
− | if (sepc ~= ".") then retrv_text = retrv_text:lower() end
| + | SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message |
− | AccessDate = '<span class="reference-accessdate">' .. sepc
| + | elseif is_set (RegistrationRequired) then |
− | .. substitute( retrv_text, {AccessDate} ) .. '</span>'
| + | SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message |
− | end
| + | else |
− |
| + | SubscriptionRequired = ''; -- either or both might be set to something other than yes true y |
− | if is_set(ID) then ID = sepc .." ".. ID; end
| + | end |
| + | |
| + | if is_set(AccessDate) then |
| + | local retrv_text = " " .. cfg.messages['retrieved'] |
| + | |
| + | AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
| + | if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case |
| + | AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text |
| + | -- neither of these work; don't know why; it seems that substitute() isn't being called |
| + | AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
| + | end |
| + | |
| + | if is_set(ID) then ID = sepc .." ".. ID; end |
| if "thesis" == config.CitationClass and is_set(Docket) then | | if "thesis" == config.CitationClass and is_set(Docket) then |
| ID = sepc .." Docket ".. Docket .. ID; | | ID = sepc .." Docket ".. Docket .. ID; |
| + | end |
| + | if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set |
| + | ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set |
| end | | end |
| | | |
− |
| + | ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); |
− | ID_list = buildidlist( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo} );
| + | |
| + | if is_set(URL) then |
| + | URL = " " .. external_link( URL, nil, URLorigin ); |
| + | end |
| + | |
| + | if 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 |
| + | Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags |
| + | PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set |
| + | end |
| + | |
| + | local Archived |
| + | if is_set(ArchiveURL) then |
| + | if not is_set(ArchiveDate) then |
| + | ArchiveDate = set_error('archive_missing_date'); |
| + | end |
| + | if "no" == DeadURL then |
| + | local arch_text = cfg.messages['archived']; |
| + | if sepc ~= "." then arch_text = arch_text:lower() end |
| + | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], |
| + | { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } ); |
| + | if not is_set(OriginalURL) then |
| + | Archived = Archived .. " " .. set_error('archive_missing_url'); |
| + | end |
| + | elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' |
| + | local arch_text = cfg.messages['archived-dead']; |
| + | if sepc ~= "." then arch_text = arch_text:lower() end |
| + | if in_array (DeadURL, {'unfit', 'usurped'}) then |
| + | Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled |
| + | else -- DeadURL is empty, 'yes', 'true', or 'y' |
| + | Archived = sepc .. " " .. substitute( arch_text, |
| + | { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled |
| + | end |
| + | else |
| + | local arch_text = cfg.messages['archived-missing']; |
| + | if sepc ~= "." then arch_text = arch_text:lower() end |
| + | Archived = sepc .. " " .. substitute( arch_text, |
| + | { set_error('archive_missing_url'), ArchiveDate } ); |
| + | end |
| + | elseif is_set (ArchiveFormat) then |
| + | Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message |
| + | else |
| + | Archived = "" |
| + | end |
| + | |
| + | local Lay = ''; |
| + | if is_set(LayURL) then |
| + | if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end |
| + | if is_set(LaySource) then |
| + | LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; |
| + | else |
| + | LaySource = ""; |
| + | end |
| + | if sepc == '.' then |
| + | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate |
| + | else |
| + | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate |
| + | end |
| + | elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= |
| + | Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message |
| + | end |
| | | |
− | if is_set(URL) then
| + | if is_set(Transcript) then |
− | URL = " " .. externallink( URL, nil, URLorigin );
| + | if is_set(TranscriptURL) then |
− | end
| + | Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin ); |
| + | end |
| + | Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
| + | elseif is_set(TranscriptURL) then |
| + | Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin ); |
| + | end |
| | | |
− | if is_set(Quote) then
| + | local Publisher; |
− | if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then
| + | if is_set(Periodical) and |
− | Quote = Quote:sub(2,-2);
| + | not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then |
− | end
| + | if is_set(PublisherName) then |
− | Quote = sepc .." " .. wrap( 'quoted-text', Quote );
| + | if is_set(PublicationPlace) then |
− | PostScript = "";
| + | Publisher = PublicationPlace .. ": " .. PublisherName; |
− | elseif PostScript:lower() == "none" then
| + | else |
− | PostScript = "";
| + | Publisher = PublisherName; |
− | end
| + | end |
− |
| + | elseif is_set(PublicationPlace) then |
− | local Archived
| + | Publisher= PublicationPlace; |
− | if is_set(ArchiveURL) then
| + | else |
− | if not is_set(ArchiveDate) then
| + | Publisher = ""; |
− | ArchiveDate = seterror('archive_missing_date');
| + | end |
− | end
| + | if is_set(PublicationDate) then |
− | if "no" == DeadURL then
| + | if is_set(Publisher) then |
− | local arch_text = cfg.messages['archived'];
| + | Publisher = Publisher .. ", " .. wrap_msg ('published', PublicationDate); |
− | if sepc ~= "." then arch_text = arch_text:lower() end
| + | else |
− | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
| + | Publisher = PublicationDate; |
− | { externallink( ArchiveURL, arch_text ), ArchiveDate } );
| + | end |
− | if not is_set(OriginalURL) then
| + | end |
− | Archived = Archived .. " " .. seterror('archive_missing_url');
| + | if is_set(Publisher) then |
− | end
| + | Publisher = " (" .. Publisher .. ")"; |
− | elseif is_set(OriginalURL) then
| + | end |
− | local arch_text = cfg.messages['archived-dead'];
| + | else |
− | if sepc ~= "." then arch_text = arch_text:lower() end
| + | if is_set(PublicationDate) then |
− | Archived = sepc .. " " .. substitute( arch_text,
| + | PublicationDate = " (" .. wrap_msg ('published', PublicationDate) .. ")"; |
− | { externallink( OriginalURL, cfg.messages['original'] ), ArchiveDate } );
| + | end |
− | else
| + | if is_set(PublisherName) then |
− | local arch_text = cfg.messages['archived-missing'];
| + | if is_set(PublicationPlace) then |
− | if sepc ~= "." then arch_text = arch_text:lower() end
| + | Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
− | Archived = sepc .. " " .. substitute( arch_text,
| + | else |
− | { seterror('archive_missing_url'), ArchiveDate } );
| + | Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
− | end
| + | end |
− | else
| + | elseif is_set(PublicationPlace) then |
− | Archived = ""
| + | Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
− | end
| + | else |
− |
| + | Publisher = PublicationDate; |
− | local Lay
| + | end |
− | if is_set(LayURL) then
| + | end |
− | if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end
| + | |
− | if is_set(LaySource) then
| + | -- Several of the above rely upon detecting this as nil, so do it last. |
− | LaySource = " – ''" .. safeforitalics(LaySource) .. "''";
| + | if is_set(Periodical) then |
− | else
| + | if is_set(Title) or is_set(TitleNote) then |
− | LaySource = "";
| + | Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical) |
− | end
| + | else |
− | if sepc == '.' then
| + | Periodical = wrap_style ('italic-title', Periodical) |
− | Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary'] ) .. LaySource .. LayDate
| + | end |
− | else
| + | end |
− | Lay = sepc .. " " .. externallink( LayURL, cfg.messages['lay summary']:lower() ) .. LaySource .. LayDate
| |
− | end
| |
− | else
| |
− | Lay = "";
| |
− | end
| |
− |
| |
− | if is_set(Transcript) then
| |
− | if is_set(TranscriptURL) then Transcript = externallink( TranscriptURL, Transcript ); end
| |
− | elseif is_set(TranscriptURL) then
| |
− | Transcript = externallink( TranscriptURL, nil, TranscriptURLorigin );
| |
− | end
| |
− |
| |
− | local Publisher;
| |
− | if is_set(Periodical) and
| |
− | not inArray(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
| |
− | if is_set(PublisherName) then
| |
− | if is_set(PublicationPlace) then
| |
− | Publisher = PublicationPlace .. ": " .. PublisherName;
| |
− | else
| |
− | Publisher = PublisherName;
| |
− | end
| |
− | elseif is_set(PublicationPlace) then
| |
− | Publisher= PublicationPlace;
| |
− | else
| |
− | Publisher = "";
| |
− | 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
| |
− |
| |
− | -- Several of the above rely upon detecting this as nil, so do it last.
| |
− | if is_set(Periodical) then
| |
− | if is_set(Title) or is_set(TitleNote) then
| |
− | Periodical = sepc .. " " .. wrap( 'italic-title', Periodical )
| |
− | else
| |
− | Periodical = wrap( 'italic-title', Periodical )
| |
− | end
| |
− | end
| |
| | | |
| --[[ | | --[[ |
Line 1,920: |
Line 3,779: |
| end | | end |
| | | |
− | -- Piece all bits together at last. Here, all should be non-nil.
| + | -- Piece all bits together at last. Here, all should be non-nil. |
− | -- We build things this way because it is more efficient in LUA
| + | -- We build things this way because it is more efficient in LUA |
− | -- 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; |
− | if inArray(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
| + | local tcommon2; -- used for book cite when |contributor= is set |
− | if is_set(Others) then Others = Others .. sepc .. " " end
| + | |
− | tcommon = safejoin( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series,
| + | if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
− | Language, Cartography, Edition, Publisher, Agency, Volume, Issue}, sepc );
| + | if is_set(Others) then Others = Others .. sepc .. " " end |
− | else
| + | tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, |
− | tcommon = safejoin( {Title, TitleNote, Conference, Periodical, Format, TitleType, Scale, Series, Language,
| + | Language, Edition, Publisher, Agency, Volume}, sepc ); |
− | Volume, Issue, Others, Cartography, Edition, Publisher, Agency}, sepc );
| + | |
− | end
| + | elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites |
− |
| + | if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc |
− | if #ID_list > 0 then
| + | tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2 |
− | ID_list = safejoin( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
| + | tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); |
− | else
| + | else |
− | ID_list = ID;
| + | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); |
− | end
| + | end |
− |
| |
− | local idcommon = safejoin( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
| |
− | local text;
| |
− | local pgtext = Position .. Page .. Pages .. At;
| |
− |
| |
− | if is_set(Authors) then
| |
− | if is_set(Coauthors) then
| |
− | Authors = Authors .. A['AuthorSeparator'] .. " " .. Coauthors
| |
− | end
| |
− | if is_set(Date) then
| |
− | Date = " ("..Date..")" .. OrigYear .. sepc .. " "
| |
− | elseif string.sub(Authors,-1,-1) == sepc then
| |
− | Authors = Authors .. " "
| |
− | else
| |
− | Authors = Authors .. sepc .. " "
| |
− | end
| |
− | if is_set(Editors) then
| |
− | local in_text = " ";
| |
− | local post_text = "";
| |
− | if is_set(Chapter) then
| |
− | in_text = in_text .. cfg.messages['in'] .. " "
| |
− | else
| |
− | if EditorCount <= 1 then
| |
− | post_text = ", " .. cfg.messages['editor'];
| |
− | else
| |
− | post_text = ", " .. cfg.messages['editors'];
| |
− | 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
| |
− | text = safejoin( {Authors, Date, Chapter, Place, Editors, tcommon }, sepc );
| |
− | text = safejoin( {text, pgtext, idcommon}, sepc );
| |
− | elseif is_set(Editors) then
| |
− | if is_set(Date) then
| |
− | if EditorCount <= 1 then
| |
− | Editors = Editors .. ", " .. cfg.messages['editor'];
| |
− | else
| |
− | Editors = Editors .. ", " .. cfg.messages['editors'];
| |
− | end
| |
− | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "
| |
− | else
| |
− | if EditorCount <= 1 then
| |
− | Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " "
| |
− | else
| |
− | Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " "
| |
− | end
| |
− | end
| |
− | text = safejoin( {Editors, Date, Chapter, Place, tcommon}, sepc );
| |
− | text = safejoin( {text, pgtext, idcommon}, sepc );
| |
− | else
| |
− | if is_set(Date) then
| |
− | 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
| |
− | text = safejoin( {Chapter, Place, tcommon, Date}, sepc );
| |
− | text = safejoin( {text, pgtext, idcommon}, sepc );
| |
− | end
| |
− | end
| |
− |
| |
− | if is_set(PostScript) and PostScript ~= sepc then
| |
− | text = safejoin( {text, sepc}, sepc ); --Deals with italics, spaces, etc.
| |
− | text = text:sub(1,-2); --Remove final seperator
| |
− | end
| |
− |
| |
− | text = safejoin( {text, PostScript}, sepc );
| |
| | | |
− | -- Now enclose the whole thing in a <span/> element
| + | elseif 'map' == config.CitationClass then -- special cases for cite map |
− | local options = {};
| + | if 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 ); |
− | if is_set(config.CitationClass) and config.CitationClass ~= "citation" then
| + | elseif is_set (Periodical) then -- map in a periodical |
− | options.class = "citation " .. config.CitationClass;
| + | tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); |
− | else
| + | else -- a sheet or stand-alone map |
− | options.class = "citation";
| + | tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc ); |
− | end
| + | end |
− |
| + | |
− | if is_set(Ref) and Ref:lower() ~= "none" then
| + | elseif 'episode' == config.CitationClass then -- special case for cite episode |
− | local id = Ref
| + | tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc ); |
− | if ( "harv" == Ref ) then
| + | else -- all other CS1 templates |
− | local names = {} --table of last names & year
| + | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, |
− | if #a > 0 then
| + | Volume, Others, Edition, Publisher, Agency}, sepc ); |
− | for i,v in ipairs(a) do
| + | end |
− | names[i] = v.last
| + | |
− | if i == 4 then break end
| + | if #ID_list > 0 then |
− | end
| + | ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); |
− | elseif #e > 0 then
| + | else |
− | for i,v in ipairs(e) do
| + | ID_list = ID; |
− | names[i] = v.last
| + | end |
− | if i == 4 then break end
| + | |
− | end
| + | local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); |
− | end
| + | local text; |
− | names[ #names + 1 ] = first_set(Year, anchor_year); -- Year first for legacy citations
| + | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
− | id = anchorid(names)
| |
− | end
| |
− | options.id = id;
| |
− | end
| |
− |
| |
− | if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then
| |
− | z.error_categories = {};
| |
− | text = seterror('empty_citation');
| |
− | z.message_tail = {};
| |
− | end
| |
− |
| |
− | if is_set(options.id) then
| |
− | text = '<span id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
| |
− | else
| |
− | text = '<span class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</span>";
| |
− | end
| |
| | | |
− | local empty_span = '<span style="display:none;"> </span>';
| + | if is_set(Date) then |
− |
| + | if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set |
− | -- Note: Using display: none on then COinS span breaks some clients.
| + | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses |
− | local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>';
| + | else -- neither of authors and editors set |
− | text = text .. OCinS;
| + | if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc |
− |
| + | Date = " " .. Date .. OrigYear; -- Date does not begin with sepc |
− | if #z.message_tail ~= 0 then
| + | else |
− | text = text .. " ";
| + | Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc |
− | for i,v in ipairs( z.message_tail ) do
| + | end |
− | if is_set(v[1]) then
| + | end |
− | if i == #z.message_tail then
| + | end |
− | text = text .. errorcomment( v[1], v[2] );
| + | if is_set(Authors) then |
− | else
| + | if is_set(Coauthors) then |
− | text = text .. errorcomment( v[1] .. "; ", v[2] );
| + | if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator |
− | end
| + | Authors = Authors .. ', ' .. Coauthors; |
− | end
| + | else |
− | end
| + | Authors = Authors .. '; ' .. Coauthors; |
− | end
| + | end |
− |
| + | end |
− | no_tracking_cats = no_tracking_cats:lower();
| + | if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination |
− | if inArray(no_tracking_cats, {"", "no", "false", "n"}) then
| + | Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space |
− | for _, v in ipairs( z.error_categories ) do
| + | end |
− | text = text .. '[[Category:' .. v ..']]';
| + | if is_set(Editors) then |
− | end
| + | local in_text = " "; |
− | end
| + | local post_text = ""; |
− |
| + | if is_set(Chapter) and 0 == #c then |
− | return text
| + | in_text = in_text .. cfg.messages['in'] .. " " |
| + | if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2 |
| + | else |
| + | if EditorCount <= 1 then |
| + | post_text = ", " .. cfg.messages['editor']; |
| + | else |
| + | post_text = ", " .. cfg.messages['editors']; |
| + | end |
| + | end |
| + | Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
| + | end |
| + | if 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 is_set (Editors) 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 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 |
| + | elseif is_set(Editors) then |
| + | if is_set(Date) then |
| + | if EditorCount <= 1 then |
| + | Editors = Editors .. ", " .. cfg.messages['editor']; |
| + | else |
| + | Editors = Editors .. ", " .. cfg.messages['editors']; |
| + | end |
| + | else |
| + | if EditorCount <= 1 then |
| + | Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " |
| + | else |
| + | Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " |
| + | end |
| + | end |
| + | text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
| + | else |
| + | if config.CitationClass=="journal" and is_set(Periodical) then |
| + | text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); |
| + | else |
| + | text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc ); |
| + | end |
| + | end |
| + | |
| + | if is_set(PostScript) and PostScript ~= sepc then |
| + | text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc. |
| + | text = text:sub(1,-sepc:len()-1); |
| + | end |
| + | |
| + | text = safe_join( {text, PostScript}, sepc ); |
| + | |
| + | -- Now enclose the whole thing in a <cite/> element |
| + | local options = {}; |
| + | |
| + | if is_set(config.CitationClass) and config.CitationClass ~= "citation" then |
| + | options.class = config.CitationClass; |
| + | options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref= |
| + | else |
| + | options.class = "citation"; |
| + | end |
| + | |
| + | if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate |
| + | local id = Ref |
| + | if ('harv' == Ref ) then |
| + | local namelist = {}; -- holds selected contributor, author, editor name list |
| + | -- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation |
| + | local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation |
| + | |
| + | if #c > 0 then -- if there is a contributor list |
| + | namelist = c; -- select it |
| + | elseif #a > 0 then -- or an author list |
| + | namelist = a; |
| + | elseif #e > 0 then -- or an editor list |
| + | namelist = e; |
| + | end |
| + | id = anchor_id (namelist, year); -- go make the CITEREF anchor |
| + | end |
| + | options.id = id; |
| + | end |
| + | |
| + | if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then |
| + | z.error_categories = {}; |
| + | text = set_error('empty_citation'); |
| + | z.message_tail = {}; |
| + | end |
| + | |
| + | if is_set(options.id) then |
| + | text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; |
| + | else |
| + | text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; |
| + | end |
| + | |
| + | local empty_span = '<span style="display:none;"> </span>'; |
| + | |
| + | -- Note: Using display: none on the COinS span breaks some clients. |
| + | 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 |
| + | if is_set(v[1]) then |
| + | if i == #z.message_tail then |
| + | text = text .. error_comment( v[1], v[2] ); |
| + | else |
| + | text = text .. error_comment( v[1] .. "; ", v[2] ); |
| + | end |
| + | end |
| + | end |
| + | end |
| + | |
| + | if #z.maintenance_cats ~= 0 then |
| + | text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">'; |
| + | for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
| + | text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])'; |
| + | end |
| + | text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now) |
| + | end |
| + | |
| + | no_tracking_cats = no_tracking_cats:lower(); |
| + | if in_array(no_tracking_cats, {"", "no", "false", "n"}) then |
| + | for _, v in ipairs( z.error_categories ) do |
| + | text = text .. '[[Category:' .. v ..']]'; |
| + | end |
| + | for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
| + | text = text .. '[[Category:' .. v ..']]'; |
| + | end |
| + | for _, v in ipairs( z.properties_cats ) do -- append maintenance categories |
| + | text = text .. '[[Category:' .. v ..']]'; |
| + | end |
| + | end |
| + | |
| + | return text |
| end | | end |
| | | |
− | -- This is used by templates such as {{cite book}} to create the actual citation text. | + | --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- |
| + | |
| + | This function searches a parameter's value for nonprintable or invisible characters. The search stops at the first match. |
| + | |
| + | Sometime after this module is done with rendering a citation, some C0 control characters are replaced with the |
| + | replacement character. That replacement character is not detected by this test though it is visible to readers |
| + | of the rendered citation. This function will detect the replacement character when it is part of the wikisource. |
| + | |
| + | Output of this function is an error message that identifies the character or the Unicode group that the character |
| + | belongs to along with its position in the parameter value. |
| + | |
| + | ]] |
| + | --[[ |
| + | local function has_invisible_chars (param, v) |
| + | local position = ''; |
| + | local i=1; |
| + | |
| + | while cfg.invisible_chars[i] do |
| + | local char=cfg.invisible_chars[i][1] -- the character or group name |
| + | local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it |
| + | v = mw.text.unstripNoWiki( v ); -- remove nowiki stripmarkers |
| + | position = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern |
| + | if position then |
| + | table.insert( z.message_tail, { set_error( 'invisible_char', {char, wrap_style ('parameter', param), position}, true ) } ); -- add error message |
| + | return; -- and done with this parameter |
| + | end |
| + | i=i+1; -- bump our index |
| + | end |
| + | end |
| + | ]] |
| + | |
| + | --[[--------------------------< Z . C I T A T I O N >---------------------------------------------------------- |
| + | |
| + | This is used by templates such as {{cite book}} to create the actual citation text. |
| + | |
| + | ]] |
| + | |
| function z.citation(frame) | | function z.citation(frame) |
− | local pframe = frame:getParent()
| + | local pframe = frame:getParent() |
− |
| + | local validation; |
− | local args = {};
| + | |
− | local suggestions = {};
| + | if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
− | local error_text, error_state;
| + | cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ... |
| + | whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); |
| + | validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... 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'); |
| + | validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code |
| + | end |
| + | |
| + | dates = validation.dates; -- imported functions |
| + | year_date_check = validation.year_date_check; |
| + | |
| + | local args = {}; |
| + | local suggestions = {}; |
| + | local error_text, error_state; |
| + | |
| + | local config = {}; |
| + | for k, v in pairs( frame.args ) do |
| + | config[k] = v; |
| + | args[k] = v; |
| + | end |
| | | |
− | local config = {};
| + | local capture; -- the single supported capture when matching unknown parameters using patterns |
− | for k, v in pairs( frame.args ) do
| + | for k, v in pairs( pframe.args ) do |
− | config[k] = v;
| + | if v ~= '' then |
− | args[k] = v;
| + | if not validate( k ) then |
− | end
| + | error_text = ""; |
| + | if type( k ) ~= 'string' then |
| + | -- Exclude empty numbered parameters |
| + | if v:match("%S+") ~= nil then |
| + | error_text, error_state = set_error( 'text_ignored', {v}, true ); |
| + | end |
| + | elseif validate( k:lower() ) then |
| + | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); |
| + | else |
| + | if nil == suggestions.suggestions then -- if this table is nil then we need to load it |
| + | if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
| + | 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 |
| + | for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter |
| + | capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match |
| + | if capture then -- if the pattern matches |
| + | param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator) |
| + | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message |
| + | end |
| + | end |
| + | if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion? |
| + | if suggestions.suggestions[ k:lower() ] ~= nil then |
| + | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); |
| + | else |
| + | error_text, error_state = set_error( 'parameter_ignored', {k}, true ); |
| + | end |
| + | end |
| + | end |
| + | if error_text ~= '' then |
| + | table.insert( z.message_tail, {error_text, error_state} ); |
| + | end |
| + | end |
| + | args[k] = v; |
| + | elseif args[k] ~= nil or (k == 'postscript') then |
| + | args[k] = v; |
| + | end |
| + | end |
| | | |
− | for k, v in pairs( pframe.args ) do
| + | for k, v in pairs( args ) do |
− | if v ~= '' then
| + | if 'string' == type (k) then -- don't evaluate positional parameters |
− | if not validate( k ) then
| + | has_invisible_chars (k, v); |
− | error_text = "";
| + | end |
− | if type( k ) ~= 'string' then
| + | end |
− | -- Exclude empty numbered parameters
| + | return citation0( config, args) |
− | if v:match("%S+") ~= nil then
| |
− | error_text, error_state = seterror( 'text_ignored', {v}, true );
| |
− | end
| |
− | elseif validate( k:lower() ) then
| |
− | error_text, error_state = seterror( 'parameter_ignored_suggest', {k, k:lower()}, true );
| |
− | else
| |
− | if #suggestions == 0 then
| |
− | suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' );
| |
− | end
| |
− | if suggestions[ k:lower() ] ~= nil then
| |
− | error_text, error_state = seterror( 'parameter_ignored_suggest', {k, suggestions[ k:lower() ]}, true );
| |
− | else
| |
− | error_text, error_state = seterror( 'parameter_ignored', {k}, true );
| |
− | end
| |
− | end
| |
− | if error_text ~= '' then
| |
− | table.insert( z.message_tail, {error_text, error_state} );
| |
− | end
| |
− | end
| |
− | args[k] = v;
| |
− | elseif args[k] ~= nil or (k == 'postscript') then
| |
− | args[k] = v;
| |
− | end
| |
− | end
| |
− |
| |
− | return citation0( config, args)
| |
| end | | end |
| | | |
| return z | | return z |