Line 1: |
Line 1: |
| | | |
− | local z = { | + | local cs1 ={}; |
− | error_categories = {}; -- for categorizing citations that contain errors
| |
− | error_ids = {};
| |
− | 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
| |
− | }
| |
| | | |
| --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- | | --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- |
| ]] | | ]] |
− | 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 dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation |
− | local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist
| + | date_name_xlate |
| | | |
− | --[[--------------------------< I S _ S E T >------------------------------------------------------------------ | + | local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities |
| + | add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink; |
| | | |
− | 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 z ={}; -- tables in Module:Citation/CS1/Utilities |
− | This function is global because it is called from both this module and from Date validation
| + | |
| + | local extract_ids, extract_id_access_levels, build_id_list, is_embargoed; -- functions in Module:Citation/CS1/Identifiers |
| + | |
| + | local make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS |
| + | |
| + | local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration |
| + | local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist |
| + | |
| + | |
| + | --[[--------------------------< P A G E S C O P E V A R I A B L E S >-------------------------------------- |
| + | |
| + | delare variables here that have page-wide scope that are not brought in from other modules; thatare created here |
| + | and used here |
| | | |
| ]] | | ]] |
− | function is_set( var )
| + | |
− | return not (var == nil or var == '');
| + | local added_deprecated_cat; -- boolean flag so that the category is added only once |
− | end
| + | local added_prop_cats = {}; -- list of property categories that have been added to z.properties_cats |
| + | local added_vanc_errs; -- boolean flag so we only emit one Vancouver error / category |
| + | |
| + | local Frame; -- holds the module's frame table |
| + | |
| | | |
| --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ | | --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ |
Line 46: |
Line 56: |
| end | | end |
| | | |
− | --[[--------------------------< I N _ A R R A Y >--------------------------------------------------------------
| |
| | | |
− | Whether needle is in haystack
| + | --[[--------------------------< 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. |
| + | |
| + | foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages |
| + | may be categorized but multiples of the same language are not categorized. |
| + | |
| + | added_prop_cats is a table declared in page scope variables above |
| | | |
| ]] | | ]] |
| | | |
− | local function in_array( needle, haystack ) | + | local function add_prop_cat (key, arguments) |
− | if needle == nil then | + | if not added_prop_cats [key] then |
− | return false; | + | added_prop_cats [key] = true; -- note that we've added this category |
| + | key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname |
| + | table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table |
| end | | end |
− | for n,v in ipairs( haystack ) do
| |
− | if v == needle then
| |
− | return n;
| |
− | end
| |
− | end
| |
− | return false;
| |
| end | | end |
| | | |
− | --[[--------------------------< S U B S T I T U T E >----------------------------------------------------------
| |
| | | |
− | Populates numbered arguments in a message string using an argument table.
| + | --[[--------------------------< 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 function substitute( msg, args )
| + | added_vanc_errs is a boolean declared in page scope variables above |
− | 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 add_vanc_error (source) |
− | | + | if not added_vanc_errs then |
− | ]]
| + | added_vanc_errs = true; -- note that we've added this category |
− | local function error_comment( content, hidden ) | + | table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } ); |
− | return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content ); | + | end |
| end | | 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
| + | --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ |
− | the responsibility of the calling function.
| |
| | | |
− | ]]
| + | does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it |
− | local function set_error( error_id, arguments, raw, prefix, suffix )
| + | is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says: |
− | local error_state = cfg.error_conditions[ error_id ];
| + | Scheme names consist of a sequence of characters beginning with a |
− |
| + | letter and followed by any combination of letters, digits, plus |
− | prefix = prefix or "";
| + | ("+"), period ("."), or hyphen ("-"). |
− | 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 >------------------------------------------------------
| + | returns true if it does, else false |
− | | |
− | 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 is_scheme (scheme) |
− | local function add_maint_cat (key, arguments) | + | return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern |
− | 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 | | 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.
| + | --[=[-------------------------< 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? |
| | | |
− | local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats
| + | Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5 |
− | local function add_prop_cat (key, arguments)
| + | BNF defined here: https://tools.ietf.org/html/rfc4234 |
− | if not added_prop_cats [key] then | + | Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; |
− | added_prop_cats [key] = true; -- note that we've added this category
| + | see also [[Single-letter second-level domain]] |
− | table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table
| + | list of tlds: https://www.iana.org/domains/root/db |
− | end
| |
− | end
| |
| | | |
− | --[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
| + | 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. |
| | | |
− | Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
| + | Also allowed are IPv4 addresses. IPv6 not supported |
− | To prevent duplication, added_vanc_errs is nil until an error message is emitted.
| |
| | | |
− | ]]
| + | 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. |
| | | |
− | local added_vanc_errs; -- flag so we only emit one Vancouver error / category
| + | There are several tests: |
− | local function add_vanc_error ()
| + | the first character of the whole domain name including subdomains must be a letter or a digit |
− | if not added_vanc_errs then | + | internationalized domain name (ascii characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the tld) see https://tools.ietf.org/html/rfc3490 |
− | added_vanc_errs = true; -- note that we've added this category
| + | single-letter/digit second-level domains in the .org and .cash TLDs |
− | table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
| + | q, x, and z SL domains in the .com TLD |
− | end | + | i and q SL domains in the .net TLD |
− | end
| + | 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 |
| | | |
− | --[[--------------------------< 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
| + | local function is_domain_name (domain) |
− | is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says:
| + | if not domain then |
− | Scheme names consist of a sequence of characters beginning with a | + | return false; -- if not set, abandon |
− | letter and followed by any combination of letters, digits, plus
| + | end |
− | ("+"), period ("."), or hyphen ("-").
| + | |
| + | 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 |
| + | -- Do most common case first |
| + | if domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/digit .org hostname |
| + | return true; |
| + | elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) |
| + | return true; |
| + | elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) |
| + | return true; |
| + | elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld |
| + | return true; |
| + | elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address |
| + | return true; |
| + | else |
| + | return false; |
| + | end |
| + | end |
| | | |
− | returns true if it does, else false
| |
| | | |
− | ]]
| + | --[[--------------------------< I S _ U R L >------------------------------------------------------------------ |
| | | |
− | local function is_scheme (scheme)
| + | returns true if the scheme and domain parts of a url appear to be a valid url; else false. |
− | return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern
| |
− | end
| |
| | | |
| + | 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. |
| | | |
− | --[=[-------------------------< 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
| + | local function is_url (scheme, domain) |
− | BNF defined here: https://tools.ietf.org/html/rfc4234
| + | if is_set (scheme) then -- if scheme is set check it and domain |
− | Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15;
| + | return is_scheme (scheme) and is_domain_name (domain); |
− | see also [[Single-letter second-level domain]] | + | else |
− | list of tlds: https://www.iana.org/domains/root/db
| + | return is_domain_name (domain); -- scheme not set when url is protocol relative |
| + | end |
| + | end |
| | | |
− | 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
| + | --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ |
| | | |
− | domain is expected to be stripped of any path so that the last character in the last character of the tld. tld
| + | Split a url into a scheme, authority indicator, and domain. |
− | 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:
| + | First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#). |
− | 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
| + | If protocol relative url, return nil scheme and domain else return nil for both scheme and domain. |
| + | |
| + | When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one |
| + | or more '/' characters immediately following the scheme's colon), make sure that there are only 2. |
| + | |
| + | Strip off any port and path; |
| | | |
− | ]=] | + | ]] |
| | | |
− | local function is_domain_name (domain) | + | local function split_url (url_str) |
− | if not domain then | + | local scheme, authority, domain; |
− | 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 | + | url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') |
− |
| + | |
− | if not domain:match ('^[%a%d]') then -- first character must be letter or digit | + | if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url |
− | return false; | + | domain = url_str:match ('^//(%S*)') |
| + | elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name |
| + | scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions |
| + | authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; |
| + | if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then |
| + | return scheme; -- return scheme only making domain nil which will cause an error message |
| + | end |
| + | domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present |
| end | | end |
| | | |
− | if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname | + | return scheme, domain; |
− | return true;
| + | end |
− | 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)
| + | --[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- |
− | 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
| |
| | | |
| + | checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls |
| | | |
− | --[[--------------------------< I S _ U R L >------------------------------------------------------------------
| + | Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed: |
| + | # < > [ ] | { } _ |
| + | except the underscore which is used as a space in wiki urls and # which is used for section links |
| | | |
− | returns true if the scheme and domain parts of a url appear to be a valid url; else false. | + | returns false when the value contains any of these characters. |
| | | |
− | This function is the last step in the validation process. This function is separate because there are cases that
| + | When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the |
− | are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external
| + | |<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok). |
− | wikilinks.
| |
| | | |
| ]] | | ]] |
| | | |
− | local function is_url (scheme, domain) | + | local function link_param_ok (value) |
− | if is_set (scheme) then -- if scheme is set check it and domain | + | local scheme, domain; |
− | return is_scheme (scheme) and is_domain_name (domain);
| + | if value:find ('[<>%[%]|{}]') then -- if any prohibited characters |
− | else
| + | return false; |
− | return is_domain_name (domain); -- scheme not set when url is protocol relative | |
| end | | 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 | | end |
| | | |
| | | |
− | --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ | + | --[[--------------------------< L I N K _ T I T L E _ O K >--------------------------------------------------- |
| | | |
− | Split a url into a scheme, authority indicator, and domain.
| + | Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value. |
− | 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
| + | |<title>= may be wikilinked but not when |<param>-link= has a value. This function emits an error message when |
− | or more '/' characters following the scheme's colon), make sure that there are only 2.
| + | that condition exists |
| | | |
| ]] | | ]] |
| | | |
− | local function split_url (url_str) | + | local function link_title_ok (link, lorig, title, torig) |
− | local scheme, authority, domain;
| + | local orig; |
− |
| |
− | 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 | + | if is_set (link) then -- don't bother if <param>-link doesn't have a value |
− | domain = url_str:match ('^//(%S*)') | + | if not link_param_ok (link) then -- check |<param>-link= markup |
− | elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name
| + | orig = lorig; -- identify the failing link parameter |
− | scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions
| + | elseif title:find ('%[%[') then -- check |title= for wikilink markup |
− | authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; | + | orig = torig; -- identify the failing |title= parameter |
− | 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 |
| end | | end |
− | | + | |
− | return scheme, domain;
| + | if is_set (orig) then |
| + | table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=; |
| + | end |
| end | | end |
| | | |
| | | |
− | --[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- | + | --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------ |
| | | |
− | checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls
| + | Determines whether a URL string appears to be valid. |
| | | |
− | Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed:
| + | 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 |
− | except the underscore which is used as a space in wiki urls and # which is used for section links
| + | portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false. |
| | | |
− | returns false when the value contains any of these characters.
| + | Because it is different from a standard url, and because this module used external_link() to make external links |
− | | + | that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name |
− | When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the
| + | is at https://tools.ietf.org/html/rfc5536#section-3.1.4 |
− | |<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 function check_url( url_str ) |
− | local scheme, domain;
| + | if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url |
− | if value:find ('[<>%[%]|{}]') then -- if any prohibited characters | |
| return false; | | return false; |
| end | | end |
| + | local scheme, domain; |
| | | |
− | scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url; | + | scheme, domain = split_url (url_str); -- 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
| + | if 'news:' == scheme then -- special case for newsgroups |
− | | + | return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$'); |
− | | |
− | --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------
| |
− | | |
− | Determines whether a URL string appears to be valid.
| |
− | | |
− | First we test for space characters. If any are found, return false. Then split the url into scheme and domain
| |
− | portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two
| |
− | portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false.
| |
− | | |
− | ]] | |
− | | |
− | local function check_url( url_str )
| |
− | if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url
| |
− | return false;
| |
| end | | 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 | | return is_url (scheme, domain); -- return true if value appears to be a valid url |
| end | | end |
Line 358: |
Line 331: |
| local function is_parameter_ext_wikilink (value) | | local function is_parameter_ext_wikilink (value) |
| local scheme, domain; | | 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] | | 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+).*%]') | + | scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); |
− | elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] | + | elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] |
− | domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]'); | + | scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]')); |
| elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text | | 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+)'); | + | scheme, domain = split_url (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 | + | elseif value:match ('//%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 | + | scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain |
| else | | else |
| return false; -- didn't find anything that is obviously a url | | return false; -- didn't find anything that is obviously a url |
Line 398: |
Line 369: |
| 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 >------------------------------------------------------ | | --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------ |
Line 438: |
Line 387: |
| end | | 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 >---------------------------------------------------- | | --[[--------------------------< E X T E R N A L _ L I N K >---------------------------------------------------- |
Line 462: |
Line 394: |
| ]] | | ]] |
| | | |
− | local function external_link( URL, label, source ) | + | local function external_link( URL, label, source, access) |
| local error_str = ""; | | local error_str = ""; |
| + | local domain; |
| + | local path; |
| + | local base_url; |
| + | |
| if not is_set( label ) then | | if not is_set( label ) then |
| label = URL; | | label = URL; |
Line 475: |
Line 411: |
| error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str; | | error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str; |
| end | | end |
− | return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str }); | + | |
− | end | + | domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the url into scheme plus domain and path |
| + | if path then -- if there is a path portion |
| + | path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values |
| + | URL = table.concat ({domain, path}); -- and reassemble |
| + | end |
| | | |
− | --[[--------------------------< E X T E R N A L _ L I N K _ I D >----------------------------------------------
| + | base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url |
− | | + | |
− | Formats a wiki style external link
| + | if is_set (access) then -- access level (subscription, registration, limited) |
− | | + | base_url = substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon |
− | ]]
| |
− | | |
− | local function external_link_id(options)
| |
− | local url_string = options.id;
| |
− | 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 " ",
| + | return table.concat ({base_url, error_str}); |
− | options.prefix, url_string, options.suffix or "",
| |
− | mw.text.nowiki(options.id)
| |
− | );
| |
| end | | end |
| + | |
| | | |
| --[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >-------------------------------------- | | --[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >-------------------------------------- |
Line 501: |
Line 433: |
| offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated | | offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated |
| parameters in the citation. | | parameters in the citation. |
| + | |
| + | added_deprecated_cat is a boolean declared in page scope variables above |
| | | |
| ]] | | ]] |
| | | |
− | local page_in_deprecated_cat; -- sticky flag so that the category is added only once
| |
| local function deprecated_parameter(name) | | local function deprecated_parameter(name) |
− | if not page_in_deprecated_cat then | + | if not added_deprecated_cat then |
− | page_in_deprecated_cat = true; -- note that we've added this category | + | added_deprecated_cat = true; -- note that we've added this category |
| table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message | | table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message |
| end | | 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. | + | --[=[-------------------------< 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. |
| + | |
| 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. | | Double single quotes (italic or bold wikimarkup) are not kerned. |
| + | |
| + | Replaces unicode quotemarks in plain text or in the label portion of a [[L|D]] style wikilink with typewriter |
| + | quote marks regardless of the need for kerning. Unicode quote marks are not replaced in simple [[D]] wikilinks. |
| | | |
| Call this function for chapter titles, for website titles, etc; not for book titles. | | Call this function for chapter titles, for website titles, etc; not for book titles. |
| | | |
− | ]] | + | ]=] |
| | | |
| local function kern_quotes (str) | | local function kern_quotes (str) |
| local cap=''; | | local cap=''; |
| local cap2=''; | | local cap2=''; |
| + | local wl_type, label, link; |
| + | |
| + | wl_type, label, link = is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] |
| | | |
− | cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes | + | if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks |
− | if is_set (cap) then
| + | if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks |
− | str = substitute (cfg.presentation['kern-left'], {cap, cap2});
| + | str = substitute (cfg.presentation['kern-wl-both'], str); |
− | end
| + | elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks |
| + | str = substitute (cfg.presentation['kern-wl-left'], str); |
| + | elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks |
| + | str = substitute (cfg.presentation['kern-wl-right'], str); |
| + | end |
| | | |
− | cap, cap2 = str:match ("^(.+[^\'])([\"\'])$") | + | else -- plain text or [[L|D]]; text in label variable |
− | if is_set (cap) then
| + | label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) |
− | str = substitute (cfg.presentation['kern-right'], {cap, cap2}); | + | label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark) |
− | end
| |
− | return str;
| |
− | end
| |
| | | |
− | --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- | + | cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) |
| + | if is_set (cap) then |
| + | label = substitute (cfg.presentation['kern-left'], {cap, cap2}); |
| + | end |
| + | |
| + | cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) |
| + | if is_set (cap) then |
| + | label = substitute (cfg.presentation['kern-right'], {cap, cap2}); |
| + | end |
| + | |
| + | if 2 == wl_type then |
| + | str = make_wikilink (link, label); -- reassemble the wikilink |
| + | else |
| + | str = label; |
| + | end |
| + | end |
| + | return str; |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- |
| | | |
| |script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should | | |script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should |
Line 574: |
Line 537: |
| end | | end |
| -- if we get this far we have prefix and script | | -- if we get this far we have prefix and script |
− | name = mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize | + | name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, "en" ); -- get language name so that we can use it to categorize |
| if is_set (name) then -- is prefix a proper ISO 639-1 language code? | | 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 | | script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script |
| -- is prefix one of these language codes? | | -- 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 | + | if in_array (lang, cfg.script_lang_codes) then |
| add_prop_cat ('script_with_name', {name, lang}) | | add_prop_cat ('script_with_name', {name, lang}) |
| else | | else |
Line 592: |
Line 555: |
| return script_value; | | return script_value; |
| end | | end |
| + | |
| | | |
| --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ | | --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ |
Line 632: |
Line 596: |
| | | |
| | | |
− | --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- | + | --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >-------------------------------------- |
| | | |
− | This function is used by select_one() to determine if one of a list of alias parameters is in the argument list
| + | Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta- |
− | provided by the template.
| + | parameter (chapter_url_source used for error messages). |
− | | |
− | 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) | + | local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access) |
− | if enumerated then -- is this a test for an enumerated parameters? | + | local chapter_error = ''; |
− | alias = alias:gsub ('#', index); -- replace '#' with the value in index | + | |
| + | if not is_set (chapter) then |
| + | chapter = ''; -- to be safe for concatenation |
| else | | else |
− | alias = alias:gsub ('#', ''); -- remove '#' if it exists
| + | if false == no_quotes then |
− | end
| + | 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); |
− | 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 |
| end | | end |
− | return value, selected; -- return newly selected alias, or previously selected alias
| |
− | end
| |
| | | |
| + | chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
| | | |
− | --[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- | + | if is_set (chapterurl) then |
| + | chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate |
| + | end |
| | | |
− | Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just
| + | if is_set (transchapter) then |
− | names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified
| + | transchapter = wrap_style ('trans-quoted-title', transchapter); |
− | by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'.
| + | if is_set (chapter) then |
− | | + | chapter = chapter .. ' ' .. transchapter; |
− | Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities.
| + | 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, access); -- adds bare_url_missing_title error if appropriate |
| + | -- end |
| | | |
− | Generates an error if more than one match is present.
| + | return chapter .. chapter_error; |
| + | end |
| | | |
− | ]]
| |
| | | |
− | local function select_one( args, aliases_list, error_condition, index )
| + | --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- |
− | 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
| + | This function searches a parameter's value for nonprintable or invisible characters. The search stops at the |
| + | first match. |
| | | |
− | for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list
| + | This function will detect the visible replacement character when it is part of the wikisource. |
− | 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()
| + | Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref) |
− | local error_str = "";
| + | and identifies them with a slightly different error message. See also coins_cleanup(). |
− | 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
| |
| | | |
| + | Detects but ignores the character pattern that results from the transclusion of {{'}} templates. |
| | | |
− | --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------------------------------
| + | 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 |
− | Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta-
| + | parameter value. |
− | parameter (chapter_url_source used for error messages). | |
| | | |
| ]] | | ]] |
| | | |
− | local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) | + | local function has_invisible_chars (param, v) |
− | local chapter_error = ''; | + | 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; |
| | | |
− | if not is_set (chapter) then | + | capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true |
− | chapter = ''; -- to be safe for concatenation
| + | if capture == v then -- if same there are no unicode characters |
− | else | + | return; |
− | 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 | | end |
| | | |
− | chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped | + | while cfg.invisible_chars[i] do |
− | | + | local char=cfg.invisible_chars[i][1] -- the character or group name |
− | if is_set (transchapter) then
| + | local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it |
− | transchapter = wrap_style ('trans-quoted-title', transchapter); | + | position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern |
− | if is_set (chapter) then | + | |
− | chapter = chapter .. ' ' .. transchapter; | + | if position and (char == 'zero width joiner') then -- if we found a zero width joiner character |
− | else -- here when transchapter without chapter or script-chapter
| + | if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts |
− | chapter = transchapter; --
| + | position = nil; -- unset position |
− | chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); | + | end |
| end | | end |
− | end
| + | |
| + | if position then |
| + | if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) |
| + | ('templatestyles' == capture and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters |
| + | stripmarker = true; -- set a flag |
| + | elseif true == stripmarker and 'delete' == char then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker |
| + | position = nil; -- unset |
| + | else |
| + | local err_msg; |
| + | if capture then |
| + | err_msg = capture .. ' ' .. char; |
| + | else |
| + | err_msg = char .. ' ' .. 'character'; |
| + | end |
| | | |
− | if is_set (chapterurl) then
| + | table.insert( z.message_tail, { set_error( 'invisible_char', {err_msg, wrap_style ('parameter', param), position}, true ) } ); -- add error message |
− | chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate
| + | return; -- and done with this parameter |
| + | end |
| + | end |
| + | i=i+1; -- bump our index |
| end | | end |
− |
| |
− | return chapter .. chapter_error;
| |
| end | | end |
| | | |
− | --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >----------------------------------------
| |
| | | |
− | This function searches a parameter's value for nonprintable or invisible characters. The search stops at the
| + | --[[--------------------------< A R G U M E N T _ W R A P P E R >---------------------------------------------- |
− | first match.
| |
| | | |
− | This function will detect the visible replacement character when it is part of the wikisource.
| + | 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. |
− | 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 function argument_wrapper( args ) |
− | local position = ''; -- position of invisible char or starting position of stripmarker
| + | local origin = {}; |
− | 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
| + | return setmetatable({ |
− | local i=1;
| + | ORIGIN = function( self, k ) |
− | local stripmarker, apostrophe;
| + | local dummy = self[k]; --force the variable to be loaded. |
− | | + | return origin[k]; |
− | while cfg.invisible_chars[i] do
| + | end |
− | 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
| + | __index = function ( tbl, k ) |
− |
| + | if origin[k] ~= nil then |
− | if position then
| + | return nil; |
− | -- 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.
| |
− | | |
− | ]]
| |
− | | |
− | local function argument_wrapper( args ) | |
− | local origin = {}; | |
− | | |
− | return setmetatable({ | |
− | ORIGIN = function( self, k ) | |
− | local dummy = self[k]; --force the variable to be loaded. | |
− | return origin[k]; | |
− | end | |
− | }, | |
− | { | |
− | __index = function ( tbl, k ) | |
− | if origin[k] ~= nil then | |
− | return nil; | |
| end | | end |
| | | |
Line 874: |
Line 752: |
| end | | end |
| | | |
− | --[[--------------------------< V A L I D A T E >--------------------------------------------------------------
| |
− | Looks for a parameter's name in the whitelist.
| |
| | | |
− | Parameters in the whitelist can have three values:
| + | --[[--------------------------< N O W R A P _ D A T E >-------------------------------------------------------- |
− | true - active, supported parameters
| |
− | false - deprecated, supported parameters
| |
− | nil - unsupported parameters
| |
− |
| |
− | ]]
| |
− | | |
− | local function validate( name )
| |
− | local name = tostring( name );
| |
− | local state = whitelist.basic_arguments[ name ];
| |
− |
| |
− | -- Normal arguments
| |
− | if true == state then return true; end -- valid actively supported parameter
| |
− | if false == state then
| |
− | deprecated_parameter (name); -- parameter is deprecated but still supported
| |
− | return true;
| |
− | end
| |
− |
| |
− | -- Arguments with numbers in them
| |
− | name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#
| |
− | state = whitelist.numbered_arguments[ name ];
| |
− | if true == state then return true; end -- valid actively supported parameter
| |
− | if false == state then
| |
− | deprecated_parameter (name); -- parameter is deprecated but still supported
| |
− | return true;
| |
− | end
| |
− |
| |
− | return false; -- Not supported because not found or name is set to nil
| |
− | end
| |
| | | |
− | | + | When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is |
− | -- Formats a wiki style internal link
| + | MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY |
− | 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. | | DOES NOT yet support MMMM YYYY or any of the date ranges. |
Line 942: |
Line 777: |
| end | | 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().
| + | --[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- |
− | 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.
| + | 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). |
| | | |
| ]] | | ]] |
| | | |
− | local function is_valid_isxn (isxn_str, len) | + | local function set_titletype (cite_class, title_type) |
− | local temp = 0; | + | if is_set(title_type) then |
− | isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58
| + | if "none" == title_type then |
− | len = len+1; -- adjust to be a loop counter
| + | title_type = ""; -- if |type=none then type parameter not displayed |
− | for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum
| |
− | if v == string.byte( "X" ) then -- if checkdigit is X (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 title_type; -- if |type= has been set to any other value use that value |
| end | | end |
− | return temp % 11 == 0; -- returns true if calculation result is zero | + | |
| + | return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation |
| end | | end |
| | | |
| | | |
− | --[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >---------------------------------------------- | + | --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- |
| + | |
| + | Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items are |
| + | returned unmodified. These forms are modified: |
| + | letter - letter (A - B) |
| + | digit - digit (4-5) |
| + | digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) |
| + | letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5) |
| + | digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d) |
| + | |
| + | any other forms are returned unmodified. |
| | | |
− | ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit.
| + | str may be a comma- or semicolon-separated list |
− | 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.
| |
| | | |
| ]] | | ]] |
| | | |
− | local function is_valid_isxn_13 (isxn_str) | + | local function hyphen_to_dash( str ) |
− | local temp=0; | + | if not is_set (str) then |
| + | return str; |
| + | end |
| | | |
− | isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39 | + | str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str |
− | for i, v in ipairs( isxn_str ) do | + | if 0 ~= count then -- non-zero when markup removed; zero else |
− | 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 | + | return str; -- nothing to do, we're done |
| end | | end |
− | return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct | + | |
− | end
| + | local out = {}; |
| + | local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any |
| | | |
− | --[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------ | + | for _, item in ipairs (list) do -- for each item in the list |
− | | + | if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators |
− | Determines whether an ISBN string is valid
| + | if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) |
− | | + | item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or -- digitletter hyphen digitletter (optional separator between digit and letter) |
− | ]]
| + | item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or -- digit separator digit hyphen digit separator digit |
− | | + | item:match ('%d+%s*%-%s*%d+') or -- digit hyphen digit |
− | local function check_isbn( isbn_str )
| + | item:match ('%a+%s*%-%s*%a+') then -- letter hyphen letter |
− | if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X
| + | item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters |
− | isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces
| + | else |
− | local len = isbn_str:len();
| + | item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space |
− |
| + | end |
− | if len ~= 10 and len ~= 13 then
| + | end |
− | return false; | + | item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup |
| + | table.insert (out, item); -- add the (possibly modified) item to the output table |
| end | | end |
| | | |
− | if len == 10 then | + | return table.concat (out, ', '); -- concatenate the output table into a comma separated string |
− | 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 |
| | | |
− | --[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------
| |
| | | |
− | Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the
| + | --[[--------------------------< S A F E _ J O I N >------------------------------------------------------------ |
− | same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf
| |
− | section 2, pages 9–12.
| |
| | | |
− | ]]
| + | Joins a sequence of strings together while checking for duplicate separation characters. |
− | | |
− | 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 function safe_join( tbl, duplicate_char ) |
− | local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate | + | local f = {}; -- create a function table appropriate to type of 'dupicate character' |
− | local handler = cfg.id_handlers['ISSN'];
| + | if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions |
− | local text;
| + | f.gsub=string.gsub |
− | local valid_issn = true;
| + | f.match=string.match |
| + | f.sub=string.sub |
| + | else -- for multi-byte characters use the ustring library functions |
| + | f.gsub=mw.ustring.gsub |
| + | f.match=mw.ustring.match |
| + | f.sub=mw.ustring.sub |
| + | end |
| | | |
− | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn | + | local str = ''; -- the output string |
− | | + | local comp = ''; -- what does 'comp' mean? |
− | 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 | + | local end_chr = ''; |
− | valid_issn=false; -- wrong length or improper character
| + | local trim; |
− | else | + | for _, value in ipairs( tbl ) do |
− | valid_issn=is_valid_isxn(id, 8); -- validate issn
| + | if value == nil then value = ''; end |
− | end | + | |
− | | + | if str == '' then -- if output string is empty |
− | if true == valid_issn then | + | str = value; -- assign value to it (first time through the loop) |
− | id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version
| + | elseif value ~= '' then |
− | else
| + | if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup. |
− | id = issn_copy; -- if not valid, use the show the invalid issn with error message | + | comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string) |
− | end
| + | else |
− |
| + | comp = value; |
− | 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
| |
− | | |
− | --[[--------------------------< A M A Z O N >------------------------------------------------------------------ | |
− | | |
− | Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha
| |
− | characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit
| |
− | isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=.
| |
− | Error message if not 10 characters, if not isbn10, if mixed and first character is a digit.
| |
− | | |
− | ]]
| |
− | | |
− | local function amazon(id, domain)
| |
− | local err_cat = ""
| |
− | | |
− | if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") then
| |
− | err_cat = ' ' .. set_error ('bad_asin'); -- asin is not a mix of 10 uppercase alpha and numeric characters
| |
− | else
| |
− | if id:match("^%d%d%d%d%d%d%d%d%d[%dX]$") 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 | | end |
− | elseif not id:match("^%u[%d%u]+$") then
| + | -- typically duplicate_char is sepc |
− | err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha
| + | if f.sub(comp, 1,1) == duplicate_char then -- is first character same as duplicate_char? why test first character? |
− | end
| + | -- Because individual string segments often (always?) begin with terminal punct for the |
− | end
| + | -- preceding segment: 'First element' .. 'sepc next element' .. etc? |
− | if not is_set(domain) then
| + | trim = false; |
− | domain = "com";
| + | end_chr = f.sub(str, -1,-1); -- get the last character of the output string |
− | elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom
| + | -- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? |
− | domain = "co." .. domain;
| + | if end_chr == duplicate_char then -- if same as separator |
− | elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico
| + | str = f.sub(str, 1,-2); -- remove it |
− | domain = "com." .. domain;
| + | elseif end_chr == "'" then -- if it might be wikimarkup |
| + | if f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' |
| + | str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' |
| + | elseif f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' |
| + | trim = true; -- why? why do this and next differently from previous? |
| + | elseif f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' |
| + | trim = true; -- same question |
| + | end |
| + | elseif end_chr == "]" then -- if it might be wikimarkup |
| + | if f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink |
| + | trim = true; |
| + | elseif f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link |
| + | trim = true; |
| + | elseif f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link |
| + | trim = true; |
| + | elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. |
| + | trim = true; |
| + | end |
| + | elseif end_chr == " " then -- if last char of output string is a space |
| + | if f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> |
| + | str = f.sub(str, 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 f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it |
| + | |
| + | value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup |
| + | else |
| + | value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character |
| + | end |
| + | end |
| + | end |
| + | str = str .. value; --add it to the output string |
| + | end |
| end | | end |
− | local handler = cfg.id_handlers['ASIN'];
| + | return str; |
− | 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 |
| | | |
− | --[[--------------------------< A R X I V >--------------------------------------------------------------------
| |
| | | |
− | See: http://arxiv.org/help/arxiv_identifier
| + | --[[--------------------------< I S _ S U F F I X >------------------------------------------------------------ |
| | | |
− | format and error check arXiv identifier. There are three valid forms of the identifier:
| + | returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed. |
− | the first form, valid only between date codes 9108 and 0703 is:
| |
− | arXiv:<archive>.<class>/<date code><number><version>
| |
− | where:
| |
− | <archive> is a string of alpha characters - may be hyphenated; no other punctuation
| |
− | <class> is a string of alpha characters - may be hyphenated; no other punctuation
| |
− | <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 function is_suffix (suffix) |
− | local handler = cfg.id_handlers['ARXIV'];
| + | if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then |
− | local year, month, version;
| + | return true; |
− | 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 | | end |
| + | return false; |
| + | 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
| + | --[[--------------------------< I S _ G O O D _ V A N C _ N A M E >-------------------------------------------- |
− | class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink
| + | |
− | else | + | For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name |
− | class = ''; -- empty string for concatenation
| + | uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character. |
− | end
| + | 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. |
− | return text .. class;
| + | |
− | end
| + | This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets |
| + | [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A |
| + | [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF |
| + | [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F |
| + | [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F |
| + | |
| + | |lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |
| + | |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods |
| + | |
| + | This original test: |
| + | if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then |
| + | was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position. |
| + | The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary |
| + | to use an external editor to maintain this code. |
| | | |
− | --[[ | + | \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) |
− | lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization)
| + | \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls) |
− | 1. Remove all blanks.
| + | \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B) |
− | 2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash.
| + | \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B) |
− | 3. If there is a hyphen in the string:
| |
− | a. Remove it. | |
− | b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out):
| |
− | 1. All these characters should be digits, and there should be six or less. (not done in this function)
| |
− | 2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six.
| |
| | | |
− | Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function.
| |
| ]] | | ]] |
| | | |
− | local function normalize_lccn (lccn) | + | local function is_good_vanc_name (last, first) |
− | lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace | + | local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it |
| | | |
− | if nil ~= string.find (lccn,'/') then | + | if is_set (suffix) then |
− | lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it | + | if not is_suffix (suffix) then |
| + | add_vanc_error ('suffix'); |
| + | return false; -- not a name with an appropriate suffix |
| + | end |
| end | | end |
| + | if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or |
| + | nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then |
| + | add_vanc_error ('non-Latin character'); |
| + | return false; -- not a string of latin characters; Vancouver requires Romanization |
| + | end; |
| + | return true; |
| + | end |
| + | |
| | | |
− | local prefix
| + | --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
− | 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
| + | Attempts to convert names to initials in support of |name-list-format=vanc. |
− | 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
| + | 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/. |
− | end
| |
− |
| |
− | return lccn;
| |
− | end
| |
| | | |
− | --[[
| + | Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. |
− | 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
| + | This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. |
− | rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/
| |
| | | |
− | length = 8 then all digits
| + | This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (). |
− | 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 function reduce_to_initials(first) |
− | local handler = cfg.id_handlers['LCCN']; | + | local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$"); |
− | local err_cat = ''; -- presume that LCCN is valid
| |
− | local id = lccn; -- local copy of the lccn
| |
| | | |
− | id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) | + | if not name then -- if not initials and a suffix |
− | local len = id:len(); -- get the length of the lccn
| + | name = mw.ustring.match(first, "^(%u+)$"); -- is it just intials? |
| + | end |
| | | |
− | if 8 == len then | + | if name then -- if first is initials with or without suffix |
− | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) | + | if 3 > mw.ustring.len (name) then -- if one or two initials |
− | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message | + | if suffix then -- if there is a suffix |
− | end
| + | if is_suffix (suffix) then -- is it legitimate? |
− | elseif 9 == len then -- LCCN should be adddddddd
| + | return first; -- one or two initials and a valid suffix so nothing to do |
− | if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern?
| + | else |
− | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message
| + | add_vanc_error ('suffix'); -- one or two initials with invalid suffix so error message |
− | end
| + | return first; -- and return first unmolested |
− | elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd
| + | end |
− | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ...
| + | else |
− | if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern | + | return first; -- one or two initials without suffix; nothing to do |
− | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message | |
| end | | end |
| end | | end |
− | elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd | + | end -- if here then name has 3 or more uppercase letters so treat them as a word |
− | 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, | + | local initials, names = {}, {}; -- tables to hold name parts and initials |
− | prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat;
| + | local i = 1; -- counter for number of initials |
− | end
| |
| | | |
− | --[[ | + | names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix |
− | Format PMID and do simple error checking. PMIDs are sequential numbers beginning at 1 and counting up. This code checks the PMID to see that it
| |
− | contains only digits and is less than test_limit; the value in local variable test_limit will need to be updated periodically as more PMIDs are issued.
| |
− | ]]
| |
| | | |
− | local function pmid(id)
| + | while names[i] do -- loop through the table |
− | local test_limit = 30000000; -- update this value as PMIDs approach | + | if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot) |
− | local handler = cfg.id_handlers['PMID'];
| + | names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present |
− | local err_cat = ''; -- presume that PMID is valid
| + | if is_suffix (names[i]) then -- if a legitimate suffix |
− |
| + | table.insert (initials, ' ' .. names[i]); -- add a separator space, insert at end of initials table |
− | if id:match("[^%d]") then -- if PMID has anything but digits
| + | break; -- and done because suffix must fall at the end of a name |
− | err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message
| + | end -- no error message if not a suffix; possibly because of Romanization |
− | else -- PMID 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 PMID is outside test limit boundaries
| |
− | err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message | |
| end | | end |
− | end
| + | if 3 > i then |
− |
| + | table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table |
− | return external_link_id({link = handler.link, label = handler.label,
| |
− | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; | |
− | 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
| |
− | 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.
| |
− | | |
− | ]]
| |
− | | |
− | local function is_embargoed (embargo)
| |
− | if is_set (embargo) then
| |
− | local lang = mw.getContentLanguage();
| |
− | local good1, embargo_date, good2, todays_date;
| |
− | good1, embargo_date = pcall( lang.formatDate, lang, 'U', embargo );
| |
− | good2, todays_date = pcall( lang.formatDate, lang, 'U' );
| |
− |
| |
− | if good1 and good2 then -- if embargo date and today's date are good dates
| |
− | 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 |
| + | i = i+1; -- bump the counter |
| end | | end |
− | return ''; -- |embargo= not set return empty string | + | |
| + | return table.concat(initials) -- Vancouver format does not include spaces. |
| end | | end |
| | | |
− | --[[--------------------------< P M C >------------------------------------------------------------------------
| |
| | | |
− | Format a PMC, do simple error checking, and check for embargoed articles.
| + | --[[--------------------------< L I S T _ P E O P L E >------------------------------------------------------- |
| | | |
− | The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not
| + | Formats a list of people (e.g. authors / editors) |
− | 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.
| |
| | | |
| ]] | | ]] |
| | | |
− | local function pmc(id, embargo) | + | local function list_people(control, people, etal) |
− | local test_limit = 5000000; -- update this value as PMCs approach | + | local sep; |
− | local handler = cfg.id_handlers['PMC']; | + | local namesep; |
− | local err_cat = ''; -- presume that PMC is valid | + | local format = control.format |
− | | + | local maximum = control.maximum |
− | local text; | + | local lastauthoramp = control.lastauthoramp; |
| + | local text = {} |
| | | |
− | if id:match("[^%d]") then -- if PMC has anything but digits | + | if 'vanc' == format then -- Vancouver-like author/editor name styling? |
− | err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message | + | sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between authors is a comma |
− | else -- PMC is only digits
| + | namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space |
− | local id_num = tonumber(id); -- convert id to a number for range testing | + | else |
− | if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries | + | sep = cfg.presentation['sep_nl']; -- name-list separator between authors is a semicolon |
− | err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message
| + | namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space> |
− | end
| |
| end | | end |
| | | |
− | if is_set (embargo) then -- is PMC is still embargoed? | + | if sep:sub(-1,-1) ~= " " then sep = sep .. " " end |
− | text="[[" .. handler.link .. "|" .. handler.label .. "]]:" .. handler.separator .. id .. err_cat; -- still embargoed so no external link
| + | if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors |
− | else | |
− | 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}) .. err_cat;
| |
− | end
| |
− | return text;
| |
− | end | |
− | | |
− | -- Formats a DOI and checks for DOI errors. | |
− | | |
− | -- DOI names contain two parts: prefix and suffix separated by a forward slash.
| |
− | -- Prefix: directory indicator '10.' followed by a registrant code
| |
− | -- Suffix: character string of any length chosen by the registrant
| |
− | | |
− | -- 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; | + | for i,person in ipairs(people) do |
− | if is_set(inactive) then
| + | if is_set(person.last) then |
− | local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date
| + | local mask = person.mask |
− | text = "[[" .. handler.link .. "|" .. handler.label .. "]]:" .. id;
| + | local one |
− | if is_set(inactive_year) then
| + | local sep_one = sep; |
− | table.insert( z.error_categories, "Pages with DOIs inactive since " .. inactive_year );
| + | if is_set (maximum) and i > maximum then |
− | else
| + | etal = true; |
− | table.insert( z.error_categories, "Pages with inactive DOIs" ); -- when inactive doesn't contain a recognizable year | + | break; |
− | end
| + | elseif (mask ~= nil) then |
− | inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")"
| + | local n = tonumber(mask) |
− | else
| + | if (n ~= nil) then |
− | text = external_link_id({link = handler.link, label = handler.label,
| + | one = string.rep("—",n) |
− | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode})
| + | else |
− | inactive = ""
| + | one = mask; |
− | end
| + | sep_one = " "; |
− | | + | end |
− | 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
| + | else |
− | cat = ' ' .. set_error( 'bad_doi' );
| + | one = person.last |
− | end
| + | local first = person.first |
− | return text .. inactive .. cat
| + | if is_set(first) then |
− | end
| + | 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 |
− | --[[--------------------------< O P E N L I B R A R Y >-------------------------------------------------------- | + | first = reduce_to_initials(first) -- attempt to convert first name(s) to initials |
− | | + | end |
− | Formats an OpenLibrary link, and checks for associated errors.
| + | end |
− | | + | one = one .. namesep .. first; |
− | ]]
| + | end |
− | local function openlibrary(id)
| + | if is_set(person.link) and person.link ~= control.page_name then |
− | local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W'
| + | one = make_wikilink (person.link, one); -- link author/editor if this page is not the author's/editor's page |
− | local handler = cfg.id_handlers['OL'];
| + | end |
− | | + | end |
− | if ( code == "A" ) then
| + | table.insert( text, one ) |
− | return external_link_id({link=handler.link, label=handler.label,
| + | table.insert( text, sep_one ) |
− | prefix=handler.prefix .. 'authors/OL',
| + | end |
− | 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
| |
− | 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
| |
| | | |
− | | + | local count = #text / 2; -- (number of names + number of separators) divided by 2 |
− | --[[--------------------------< M E S S A G E _ I D >----------------------------------------------------------
| + | if count > 0 then |
− | | + | if count > 1 and is_set(lastauthoramp) and not etal then |
− | Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in
| + | text[#text-2] = " & "; -- replace last separator with ampersand text |
− | '<' and/or '>' angle brackets.
| + | end |
− | | + | text[#text] = nil; -- erase the last separator |
− | ]]
| + | end |
− | | |
− | 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}) | |
− |
| |
− | if not id:match('^.+@.+$') or not id:match('^[^<].*[^>]$')then -- doesn't have '@' or has one or first or last character is '< or '>'
| |
− | text = text .. ' ' .. set_error( 'bad_message_id' ) -- add an error message if the message id is invalid | |
− | end | |
| | | |
− | return text | + | local result = table.concat(text) -- construct list |
− | end
| + | 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. |
− | --[[--------------------------< 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 templates that have defaults.
| |
− | Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none).
| |
− | | |
− | ]]
| |
− | | |
− | local function set_titletype (cite_class, title_type)
| |
− | if is_set(title_type) then | |
− | if "none" == title_type then
| |
− | title_type = ""; -- if |type=none then type parameter not displayed
| |
− | end | |
− | return title_type; -- if |type= has been set to any other value use that value
| |
| end | | end |
− | | + | |
− | return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation | + | return result, count |
| end | | end |
| | | |
− | --[[--------------------------< C L E A N _ I S B N >----------------------------------------------------------
| |
| | | |
− | Removes irrelevant text and dashes from ISBN number
| + | --[[--------------------------< A N C H O R _ I D >------------------------------------------------------------ |
− | Similar to that used for Special:BookSources
| |
| | | |
− | ]]
| + | Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string. |
| | | |
− | local function clean_isbn( isbn_str )
| + | namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year. |
− | 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) | + | local function anchor_id (namelist, year) |
− | argument = argument:gsub("%%", "%%%%"); -- replace % with %% | + | local names={}; -- a table for the one to four names and year |
− | argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters | + | for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names |
− | return argument; | + | names[i] = v.last |
| + | if i == 4 then break end -- if four then done |
| + | end |
| + | table.insert (names, year); -- add the year at the end |
| + | local id = table.concat(names); -- concatenate names and year for CITEREF id |
| + | if is_set (id) then -- if concatenation is not an empty string |
| + | return "CITEREF" .. id; -- add the CITEREF portion |
| + | else |
| + | return ''; -- return an empty string; no reason to include CITEREF id in this citation |
| + | end |
| end | | end |
| | | |
− | --[[--------------------------< 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.
| + | --[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- |
− | 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.
| |
| | | |
− | ]]
| + | Evaluates the content of author and editor name parameters for variations on the theme of et al. If found, |
| + | the et al. is removed, a flag is set to true and the function returns the modified name and the flag. |
| | | |
− | local function strip_apostrophe_markup (argument)
| + | This function never sets the flag to false but returns it's previous state because it may have been set by |
− | if not is_set (argument) then return argument; end
| + | previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal |
| | | |
− | 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 >----------------------------------------------
| |
− |
| |
− | Makes a title for COinS from Title and / or ScriptTitle (or any other name-script pairs)
| |
− |
| |
− | Apostrophe markup (bold, italics) is stripped from each value so that the COinS metadata isn't correupted with strings
| |
− | of %27%27...
| |
| ]] | | ]] |
| | | |
− | local function make_coins_title (title, script) | + | local function name_has_etal (name, etal, nocat) |
− | 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 >------------------------------------------------ | + | if is_set (name) then -- name can be nil in which case just return |
| + | local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme |
| + | local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. |
| + | |
| + | if name:match (etal_pattern) then -- variants on et al. |
| + | name = name:gsub (etal_pattern, ''); -- if found, remove |
| + | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
| + | if not nocat then -- no categorization for |vauthors= |
| + | add_maint_cat ('etal'); -- and add a category if not already added |
| + | end |
| + | elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? |
| + | name = name:gsub (others_pattern, ''); -- if found, remove |
| + | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
| + | if not nocat then -- no categorization for |vauthors= |
| + | add_maint_cat ('etal'); -- and add a category if not already added |
| + | end |
| + | end |
| + | end |
| + | return name, etal; -- |
| + | end |
| | | |
− | Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS.
| + | |
| + | --[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------ |
| + | |
| + | Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc. |
| + | These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function |
| + | adds the editor markup maintenance category. |
| | | |
| ]] | | ]] |
| | | |
− | local function get_coins_pages (pages) | + | local function name_has_ed_markup (name, list_name) |
− | local pattern; | + | local _, pattern; |
− | if not is_set (pages) then return pages; end -- if no page numbers then we're done | + | local patterns = { -- these patterns match annotations at end of name |
− |
| + | '%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')' |
− | while true do
| + | '[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name) |
− | pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url " | + | '%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')' |
− | if nil == pattern then break; end -- no more urls | + | '[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive |
− | pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters | + | |
− | pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible
| + | -- these patterns match annotations at beginning of name |
| + | '^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.' |
| + | '^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.' |
| + | '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's' |
| + | '^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets |
| + | } |
| + | |
| + | if is_set (name) then |
| + | for _, pattern in ipairs (patterns) do -- spin through patterns table and |
| + | if name:match (pattern) then |
| + | add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template |
| + | break; |
| + | end |
| + | end |
| end | | end |
− | pages = pages:gsub("[%[%]]", ""); -- remove the brackets | + | return name; -- and done |
− | pages = pages:gsub("–", "-" ); -- replace endashes with hyphens
| |
− | pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like?
| |
− | return pages;
| |
| end | | end |
| | | |
− | -- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B
| |
− | local function remove_wiki_link( str )
| |
− | return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l)
| |
− | return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1");
| |
− | end));
| |
− | end
| |
| | | |
− | -- Converts a hyphen to a dash | + | --[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >---------------------------------------- |
− | local function hyphen_to_dash( str )
| |
− | if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then
| |
− | return str;
| |
− | end
| |
− | return str:gsub( '-', '–' );
| |
− | end
| |
| | | |
− | --[[--------------------------< S A F E _ J O I N >------------------------------------------------------------
| + | Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are |
| + | indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name |
| + | (author or editor) maintenance category. |
| | | |
− | Joins a sequence of strings together while checking for duplicate separation characters.
| + | ]] |
| + | |
| + | local function name_has_mult_names (name, list_name) |
| + | local count, _; |
| + | if is_set (name) then |
| + | _, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters |
| + | |
| + | if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable |
| + | add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template |
| + | end |
| + | end |
| + | return name; -- and done |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< N A M E _ C H E C K S >-------------------------------------------------------- |
| + | This function calls various name checking functions used to validate the content of the various name-holding |
| + | parameters. |
| | | |
| ]] | | ]] |
| | | |
− | local function safe_join( tbl, duplicate_char ) | + | local function name_checks (last, first, list_name) |
− | --[[ | + | if is_set (last) then |
− | Note: we use string functions here, rather than ustring functions.
| + | if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
− |
| + | last = last:match ('^%(%((.*)%)%)$'); -- strip parens |
− | This has considerably faster performance and should work correctly as
| + | else |
− | long as the duplicate_char is strict ASCII. The strings
| + | last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) |
− | in tbl may be ASCII or UTF8.
| + | last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation |
− | ]]
| + | end |
− |
| + | end |
− | local str = ''; -- the output string
| + | if is_set (first) then |
− | local comp = ''; -- what does 'comp' mean?
| + | if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
− | local end_chr = '';
| + | first = first:match ('^%(%((.*)%)%)$'); -- strip parens |
− | local trim; | + | else |
− | for _, value in ipairs( tbl ) do | + | first = name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation |
− | if value == nil then value = ''; end
| + | end |
− |
| + | end |
− | if str == '' then -- if output string is empty | + | return last, first; -- done |
− | str = value; -- assign value to it (first time through the loop) | + | end |
− | 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)
| + | --[[--------------------------< E X T R A C T _ N A M E S >---------------------------------------------------- |
− | else
| + | Gets name list from the input arguments |
− | comp = value;
| + | |
− | end
| + | Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. |
− | -- typically duplicate_char is sepc
| + | Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't |
− | if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character?
| + | find |last4= and |last5= then the search is done. |
− | -- Because individual string segments often (always?) begin with terminal punct for th
| + | |
− | -- preceding segment: 'First element' .. 'sepc next element' .. etc?
| + | 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= |
− | trim = false;
| + | are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. |
− | 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
| + | 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 |
− | if value ~= comp then -- value does not equal comp when value contains html markup
| + | that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the |
− | local dup2 = duplicate_char;
| + | template's metadata. When this occurs, the page is added to a maintenance category. |
− | 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
| |
− | str = str .. value; --add it to the output string
| |
− | end
| |
− | end
| |
− | return str;
| |
− | end
| |
| | | |
− | --[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
| + | ]] |
| | | |
− | For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
| + | local function extract_names(args, list_name) |
− | uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
| + | local names = {}; -- table of names |
− | When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
| + | local last; -- individual name components |
− | These things are not currently possible in this module so are left to the editor to do.
| + | 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 |
| | | |
− | This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
| + | local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary |
− | [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A | + | while true do |
− | [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
| + | last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 |
− | [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
| + | first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ); |
− | [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
| + | link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); |
| + | mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); |
| | | |
− | |lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
| + | last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al. |
− | |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
| + | first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al. |
| + | last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks |
| + | |
| + | 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 |
| + | link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup |
| | | |
− | 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
| + | names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) |
− | because the code editor gets confused between character insertion point and cursor position.
| + | 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 |
| + | count = 0; -- reset the counter, we're looking for two consecutive missing names |
| + | end |
| + | i = i + 1; -- point to next args location |
| + | end |
| + | |
| + | return names, etal; -- all done, return our list of names |
| + | end |
| | | |
− | ]]
| |
| | | |
− | local function is_good_vanc_name (last, first)
| + | --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ |
− | 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 >------------------------------------------ | + | Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. |
| | | |
− | Attempts to convert names to initials in support of |name-list-format=vanc.
| + | Returns the language name and associated two- or three-character 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. |
| | | |
− | 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/.
| + | mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include |
| + | extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support |
| + | code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they |
| + | are used as sub-domain names: cbk-zam.wikipedia.org. These names can be found (for the time being) at |
| + | https://phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEn.php |
| | | |
− | Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not
| + | Names but that are included in the list will be found if that name is provided in the |language= parameter. For example, |
− | 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/.
| + | if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found |
| + | and the associated code is not two or three characters, this function returns only the Wikimedia language name. |
| | | |
− | This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
| + | Adapted from code taken from Module:Check ISO 639-1. |
| | | |
| ]] | | ]] |
| | | |
− | local function reduce_to_initials(first) | + | local function get_iso639_code (lang, this_wiki_code) |
− | if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do | + | if cfg.lang_name_remap[lang:lower()] then -- if there is a remapped name (because MediaWiki uses something that we don't think is correct) |
− | local initials = {}
| + | return cfg.lang_name_remap[lang:lower()][1], cfg.lang_name_remap[lang:lower()][2]; -- for this language 'name', return a possibly new name and appropriate code |
− | 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 table.concat(initials) -- Vancouver format does not include spaces. | + | |
| + | local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia |
| + | -- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) |
| + | local langlc = mw.ustring.lower(lang); -- lower case version for comparisons |
| + | |
| + | for code, name in pairs(languages) do -- scan the list to see if we can find our language |
| + | if langlc == mw.ustring.lower(name) then |
| + | if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported |
| + | return name; -- so return the name but not the code |
| + | end |
| + | return name, code; -- found it, return name to ensure proper capitalization and the the code |
| + | end |
| + | end |
| + | return lang; -- not valid language; return language in original case and nil for the code |
| end | | end |
| | | |
− | --[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
| |
| | | |
− | Formats a list of people (e.g. authors / editors)
| + | --[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------ |
| + | |
| + | Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki, |
| + | use the returned name; if not, then use the value that was provided with the language parameter. |
| + | |
| + | When |language= contains a recognized language (either code or name), the page is assigned to the category for |
| + | that code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assigned |
| + | to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. |
| + | |
| + | Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character |
| + | equivalents of two-character codes: code 'ar' is recognized bit code 'ara' is not. |
| + | |
| + | This function supports multiple languages in the form |language=nb, French, th where the language names or codes are |
| + | separated from each other by commas. |
| | | |
| ]] | | ]] |
| | | |
− | local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function | + | local function language_parameter (lang) |
− | local sep; | + | local code; -- the two- or three-character language code |
− | local namesep; | + | local name; -- the language name |
− | local format = control.format | + | local language_list = {}; -- table of language names to be rendered |
− | local maximum = control.maximum | + | local names_table = {}; -- table made from the value assigned to |language= |
− | local lastauthoramp = control.lastauthoramp; | + | |
− | local text = {} | + | local this_wiki = mw.getContentLanguage(); -- get a language object for this wiki |
| + | local this_wiki_code = this_wiki:getCode() -- get this wiki's language code |
| + | local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name |
| + | |
| + | names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
| | | |
− | if 'vanc' == format then -- Vancouver-like author/editor name styling? | + | for _, lang in ipairs (names_table) do -- reuse lang |
− | sep = ','; -- name-list separator between authors is a comma
| + | |
− | namesep = ' '; -- last/first separator is a space | + | if lang:match ('^%a%a%-') then -- strip ietf language tags from code; TODO: is there a need to support 3-char with tag? |
− | else
| + | lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? |
− | sep = ';' -- name-list separator between authors is a semicolon
| + | end |
− | namesep = ', ' -- last/first separator is <comma><space>
| + | if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code |
− | end
| + | name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code |
| + | if not is_set (name) then |
| + | name = cfg.lang_code_remap[lang]; -- not supported by MediaWiki; is it in remap? |
| + | end |
| + | end |
| | | |
− | if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
| + | if is_set (name) then -- if |language= specified a valid code |
− | if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
| + | code = lang:lower(); -- save it |
| + | else |
| + | name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) |
| + | end |
| | | |
− | for i,person in ipairs(people) do
| + | if is_set (code) then -- only 2- or 3-character codes |
− | if is_set(person.last) then | + | name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names |
− | local mask = person.mask | + | |
− | local one
| + | if this_wiki_code ~= code then -- when the language is not the same as this wiki's language |
− | local sep_one = sep; | + | if 2 == code:len() then -- and is a two-character code |
− | if is_set (maximum) and i > maximum then
| + | add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it |
− | etal = true; | + | else -- or is a recognized language (but has a three-character code) |
− | break;
| + | add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template |
− | elseif (mask ~= nil) then
| |
− | local n = tonumber(mask)
| |
− | if (n ~= nil) then | |
− | one = string.rep("—",n) | |
− | else
| |
− | one = mask;
| |
− | sep_one = " ";
| |
| end | | end |
− | else | + | end |
− | one = person.last
| + | else |
− | local first = person.first
| + | add_maint_cat ('unknown_lang'); -- add maint category if not already added |
− | if is_set(first) then
| + | end |
− | if ( "vanc" == format ) then -- if vancouver format
| + | |
− | one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
| + | table.insert (language_list, name); |
− | if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
| + | name = ''; -- so we can reuse it |
− | 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
| |
− | table.insert( text, one )
| |
− | table.insert( text, sep_one )
| |
− | end | |
| end | | end |
− | | + | |
− | local count = #text / 2; -- (number of names + number of separators) divided by 2 | + | code = #language_list -- reuse code as number of languages in the list |
− | if count > 0 then | + | if 2 >= code then |
− | if count > 1 and is_set(lastauthoramp) and not etal then | + | name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names |
− | text[#text-2] = " & "; -- replace last separator with ampersand text
| + | elseif 2 < code then |
− | end
| + | language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>' |
− | text[#text] = nil; -- erase the last separator | + | name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators |
| end | | end |
− | | + | if this_wiki_name == name then |
− | local result = table.concat(text) -- construct list
| + | return ''; -- if one language and that language is this wiki's return an empty string (no annotation) |
− | 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 (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' |
− | return result, count | + | --[[ TODO: should only return blank or name rather than full list |
| + | so we can clean up the bunched parenthetical elements Language, Type, Format |
| + | ]] |
| end | | end |
| | | |
− | --[[--------------------------< A N C H O R _ I D >------------------------------------------------------------
| |
| | | |
− | Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise returns an empty string.
| + | --[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- |
| | | |
− | namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year.
| + | Set style settings for CS1 citation templates. Returns separator and postscript settings |
| + | At en.wiki, for cs1: |
| + | ps gets: '.' |
| + | sep gets: '.' |
| | | |
| ]] | | ]] |
− | local function anchor_id (namelist, year) | + | |
− | local names={}; -- a table for the one to four names and year
| + | local function set_cs1_style (ps) |
− | for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names
| + | if not is_set (ps) then -- unless explicitely set to something |
− | names[i] = v.last
| + | ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation |
− | if i == 4 then break end -- if four then done
| |
− | end
| |
− | table.insert (names, year); -- add the year at the end
| |
− | local id = table.concat(names); -- concatenate names and year for CITEREF id
| |
− | if 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 |
| + | return cfg.presentation['sep_cs1'], ps; -- element separator |
| end | | end |
| | | |
| | | |
− | --[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- | + | --[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- |
| | | |
− | Evaluates the content of author and editor name parameters for variations on the theme of et al. If found,
| + | Set style settings for CS2 citation templates. Returns separator, postscript, ref settings |
− | the et al. is removed, a flag is set to true and the function returns the modified name and the flag.
| + | At en.wiki, for cs2: |
− | | + | ps gets: '' (empty string - no terminal punctuation) |
− | This function never sets the flag to false but returns it's previous state because it may have been set by
| + | sep gets: ',' |
− | previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal
| |
| | | |
| ]] | | ]] |
| | | |
− | local function name_has_etal (name, etal, nocat) | + | local function set_cs2_style (ps, ref) |
− | | + | if not is_set (ps) then -- if |postscript= has not been set, set cs2 default |
− | if is_set (name) then -- name can be nil in which case just return | + | ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation |
− | local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme | + | end |
− | local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al.
| + | if not is_set (ref) then -- if |ref= is not set |
− |
| + | ref = "harv"; -- set default |ref=harv |
− | 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 |
− | return name, etal; -- | + | return cfg.presentation['sep_cs2'], ps, ref; -- element separator |
| end | | end |
| | | |
− | --[[--------------------------< E X T R A C T _ N A M E S >----------------------------------------------------
| |
− | 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.
| + | --[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- |
− | 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=
| + | When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish |
− | are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=.
| + | rendered style. |
− | | |
− | 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 function get_settings_from_cite_class (ps, ref, cite_class) |
− | local names = {}; -- table of names | + | local sep; |
− | local last; -- individual name components | + | if (cite_class == "citation") then -- for citation templates (CS2) |
− | local first;
| + | sep, ps, ref = set_cs2_style (ps, ref); |
− | local link; | + | else -- not a citation template so CS1 |
− | local mask;
| + | sep, ps = set_cs1_style (ps); |
− | local i = 1; -- loop counter/indexer | + | end |
− | 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)
| + | return sep, ps, ref -- return them all |
− | local etal=false; -- return value set to true when we find some form of et al. in an author parameter
| + | end |
| + | |
| + | |
| + | --[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ |
| | | |
− | local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary
| + | Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses |
− | while true do
| + | config.CitationClass from the template's #invoke: to establish style. |
− | 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
| + | local function set_style (mode, ps, ref, cite_class) |
− | table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message
| + | local sep; |
− | elseif not first and not last then -- if both firstn and lastn aren't found, are we done?
| + | if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style |
− | count = count + 1; -- number of times we haven't found last and first
| + | sep, ps, ref = set_cs2_style (ps, ref); |
− | if 2 <= count then -- two missing names and we give up
| + | elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style |
− | break; -- normal exit or there is a two-name hole in the list; can't tell which
| + | sep, ps = set_cs1_style (ps); |
− | end
| + | else -- anything but cs1 or cs2 |
− | else -- we have last with or without a first | + | sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass |
− | if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last
| + | end |
− | table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link;
| + | if 'none' == ps:lower() then -- if assigned value is 'none' then |
− | end
| + | ps = ''; -- set to empty string |
− | 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
| |
− | count = 0; -- reset the counter, we're looking for two consecutive missing names
| |
− | end
| |
− | i = i + 1; -- point to next args location
| |
| end | | end |
| | | |
− | return names, etal; -- all done, return our list of names | + | return sep, ps, ref |
| end | | 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
| + | --[=[-------------------------< I S _ P D F >------------------------------------------------------------------ |
− | 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
| |
| | | |
− | ]] | + | Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when |
| + | applying the pdf icon to external links. |
| + | |
| + | returns true if file extension is one of the recognized extensions, else false |
| + | |
| + | ]=] |
| | | |
− | local function extract_ids( args ) | + | local function is_pdf (url) |
− | local id_list = {}; -- list of identifiers found in args | + | return url:match ('%.pdf$') or url:match ('%.PDF$') or url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]'); |
− | 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
| |
− | return id_list;
| |
| end | | 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.
| + | --[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ |
| | | |
− | inputs:
| + | Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does |
− | id_list – table of identifiers built by extract_ids()
| + | not have a matching url parameter. If the format parameter is not set and the url contains a file extension that |
− | options – table of various template parameter values used to modify some manually handled identifiers
| + | is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with |
| + | the appropriate styling. |
| | | |
| ]] | | ]] |
| | | |
− | local function build_id_list( id_list, options ) | + | local function style_format (format, url, fmt_param, url_param) |
− | local new_list, handler = {};
| + | if is_set (format) then |
− | | + | format = wrap_style ('format', format); -- add leading space, parentheses, resize |
− | function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end;
| + | if not is_set (url) then |
− | | + | format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message |
− | 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
| |
− | -- fallback to read-only cfg
| |
− | handler = setmetatable( { ['id'] = v }, fallback(k) );
| |
− |
| |
− | if handler.mode == 'external' then
| |
− | 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 |
| + | 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 | | end |
− | | + | return format; |
− | 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 |
− |
| |
| | | |
− | --[[--------------------------< 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.
| + | --[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------ |
| | | |
− | 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate content
| + | Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag |
− | when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 | + | to indicate when et al. should be appended to the name list. |
| | | |
− | TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible
| + | When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and |
− | characters table?
| + | 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.'). |
| | | |
− | local function coins_cleanup (value)
| + | When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the |
− | value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content
| + | number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of |
− | value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s
| + | the names in the name list followed by 'et al.' |
− | 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
| |
| | | |
| + | In all other cases, returns nil and the previous state of the 'etal' flag. |
| | | |
− | --[[--------------------------< C O I N S >--------------------------------------------------------------------
| + | inputs: |
− | | + | max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal |
− | COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information.
| + | count: #a or #e |
| + | list_name: 'authors' or 'editors' |
| + | etal: author_etal or editor_etal |
| | | |
| ]] | | ]] |
| | | |
− | local function COinS(data, class) | + | local function get_display_authors_editors (max, count, list_name, etal) |
− | if 'table' ~= type(data) or nil == next(data) then | + | if is_set (max) then |
− | return ''; | + | if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings |
− | end
| + | max = count + 1; -- number of authors + 1 so display all author name plus et al. |
− | | + | etal = true; -- overrides value set by extract_names() |
− | for k, v in pairs (data) do -- spin through all of the metadata parameter values
| + | elseif max:match ('^%d+$') then -- if is a string of numbers |
− | if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed)
| + | max = tonumber (max); -- make it a number |
− | data[k] = coins_cleanup (v); | + | if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors |
| + | add_maint_cat ('disp_auth_ed', cfg.special_case_translation [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; as if |display-xxxxors= had not been set |
| end | | end |
| end | | end |
− |
| |
− | local ctx_ver = "Z39.88-2004";
| |
| | | |
− | -- treat table strictly as an array with only set values. | + | return max, etal; |
− | local OCinSoutput = setmetatable( {}, {
| + | end |
− | __newindex = function(self, key, value)
| |
− | if is_set(value) then
| |
− | rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( remove_wiki_link( value ) ) } );
| |
− | end
| |
− | end
| |
− | });
| |
− |
| |
− | if in_array (class, {'arxiv', 'journal', 'news'}) or (in_array (class, {'conference', 'interview', 'map', 'press release', 'web'}) and is_set(data.Periodical)) or
| |
− | ('citation' == class and is_set(data.Periodical) and not is_set (data.Encyclopedia)) then
| |
− | OCinSoutput.rft_val_fmt = "info:ofi/fmt:kev:mtx:journal"; -- journal metadata identifier
| |
− | if 'arxiv' == class then -- set genre according to the type of citation template we are rendering
| |
− | OCinSoutput["rft.genre"] = "preprint"; -- cite arxiv
| |
− | elseif 'conference' == class then
| |
− | OCinSoutput["rft.genre"] = "conference"; -- cite conference (when Periodical set)
| |
− | 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
| |
− | OCinSoutput["rft.genre"] = 'book'; -- book and encyclopedia
| |
− | end
| |
− | end
| |
− | else --{'audio-visual', 'AV-media-notes', 'DVD-notes', 'episode', 'interview', 'mailinglist', 'map', 'newsgroup', 'podcast', 'press release', 'serial', 'sign', 'speech', 'web'}
| |
− | OCinSoutput["rft.genre"] = "unknown";
| |
− | end
| |
− | OCinSoutput["rft.btitle"] = data.Title; -- book only
| |
− | 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
| |
| | | |
− | --[[ | + | --[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------ |
− | 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;
| + | Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp. |
− | if k == 'ISBN' then value = clean_isbn( v ); else value = v; end
| + | abbreviation in the first characters of the parameter content. |
− | if string.sub( id or "", 1, 4 ) == 'info' then
| + | |
− | OCinSoutput["rft_id"] = table.concat{ id, "/", v };
| + | check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: |
− | else
| + | 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 |
− | OCinSoutput[ id ] = value;
| + | bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP |
− | end
| + | |
− | end
| |
| ]] | | ]] |
− | local last, first;
| + | |
− | for k, v in ipairs( data.Authors ) do
| + | local function extra_text_in_page_check (page) |
− | last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers
| + | 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 k == 1 then -- for the first author name only
| + | local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; |
− | 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
| + | if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then |
− | OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation
| + | add_maint_cat ('extra_text'); |
− | 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 |
− |
| |
− | 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 |
| | | |
| | | |
− | --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ | + | --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- |
| | | |
− | Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian where
| + | split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled |
− | ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR.
| + | parentheses to also have commas; in the old version of the code, the doubled parnetheses were included in the |
| + | rendered citation and in the metadata. Individual author names may be wikilinked |
| | | |
− | Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia
| + | |vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.)) |
− | 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.
| + | local function get_v_name_table (vparam, output_table, output_link_table) |
− | | + | local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas |
− | ]]
| + | local wl_type, label, link; -- wl_type not used here; just a place holder |
− | | |
− | local function get_iso639_code (lang) | |
− | 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 | + | local i = 1; |
− | -- ('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 | + | while name_table[i] do |
− | if langlc == mw.ustring.lower(name) then
| + | if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens |
− | if 2 ~= code:len() then -- ISO639-1 codes only | + | local name = name_table[i]; |
− | return name; -- so return the name but not the code | + | i=i+1; -- bump indexer to next segment |
| + | while name_table[i] do |
| + | name = name .. ', ' .. name_table[i]; -- concatenate with previous segments |
| + | if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parens |
| + | break; -- and done reassembling so |
| + | end |
| + | i=i+1; -- bump indexer |
| + | end |
| + | table.insert (output_table, name); -- and add corporate name to the output table |
| + | table.insert (output_link_table, ''); -- no wikilink |
| + | else |
| + | wl_type, label, link = is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] |
| + | table.insert (output_table, label); -- add this name |
| + | if 1 == wl_type then |
| + | table.insert (output_link_table, label); -- simple wikilink [[D]] |
| + | else |
| + | table.insert (output_link_table, link); -- no wikilink or [[L|D]]; add this link if there is one, else empty string |
| end | | end |
− | return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code
| |
| end | | end |
− | end | + | i = i+1; |
− | return lang; -- not valid language; return language in original case and nil for ISO639-1 code | + | end |
| + | return output_table; |
| end | | end |
| | | |
− | --[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------
| |
| | | |
− | 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.
| + | --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >-------------------------------- |
| | | |
− | There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and
| + | This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= 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
| + | |xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does. |
− | 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
| + | Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names |
− | return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them.
| + | 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. |
| | | |
− | See Help talk:Citation Style_1#An ISO 639-1 language name test
| + | Supports generational suffixes Jr, 2nd, 3rd, 4th–6th. |
| | | |
− | When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if
| + | This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials. |
− | 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.
| |
| | | |
| ]] | | ]] |
| | | |
− | local function language_parameter (lang) | + | local function parse_vauthors_veditors (args, vparam, list_name) |
− | local code; -- the ISO639-1 two character code | + | local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= |
− | local name; -- the language name | + | local v_name_table = {}; |
− | local language_list = {}; -- table of language names to be rendered | + | local v_link_table = {}; -- when name is wikilinked, targets go in this table |
− | local names_table = {}; -- table made from the value assigned to |language= | + | local etal = false; -- return value set to true when we find some form of et al. vauthors parameter |
| + | local last, first, link, mask, suffix; |
| + | local corporate = false; |
| | | |
− | names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list | + | vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) |
| + | v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas |
| | | |
− | for _, lang in ipairs (names_table) do -- reuse lang | + | for i, v_name in ipairs(v_name_table) do |
− | | + | if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection |
− | if lang:match ('^%a%a%-') then -- strip ietf language tags from code | + | first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
− | lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? | + | last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses |
− | end | + | corporate = true; -- flag used in list_people() |
− | if 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes)
| + | elseif string.find(v_name, "%s") then |
− | name = mw.language.fetchLanguageName( lang:lower(), "en" ); -- get ISO 639-1 language name if Language is a proper code | + | if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; |
− | end
| + | add_vanc_error ('punctuation'); |
− |
| + | end |
− | if is_set (name) then -- if Language specified a valid ISO639-1 code
| + | local lastfirstTable = {} |
− | code = lang:lower(); -- save it | + | lastfirstTable = mw.text.split(v_name, "%s") |
| + | first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials |
| + | if is_suffix (first) then -- if a valid suffix |
| + | suffix = first -- save it as a suffix and |
| + | first = table.remove(lastfirstTable); -- get what should be the initials from the table |
| + | end -- no suffix error message here because letter combination may be result of Romanization; check for digits? |
| + | last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials |
| + | if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then |
| + | add_vanc_error ('missing comma'); -- matches last II last; the case when a comma is missing |
| + | end |
| + | if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test |
| + | add_vanc_error ('name'); -- matches a space between two intiials |
| + | end |
| else | | else |
− | name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) | + | 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 | | end |
− |
| + | |
− | if is_set (code) then | + | if is_set (first) then |
− | if 'no' == code then name = 'Norwegian' end; -- override wikimedia when code is 'no' | + | if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else |
− | if 'en' ~= code then -- English not the language | + | add_vanc_error ('initials'); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials |
− | add_prop_cat ('foreign_lang_source', {name, code}) | + | end |
| + | is_good_vanc_name (last, first); -- check first and last before restoring the suffix which may have a non-Latin digit |
| + | if is_set (suffix) then |
| + | first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials |
| + | suffix = ''; -- unset so we don't add this suffix to all subsequent names |
| end | | end |
| else | | else |
− | add_maint_cat ('unknown_lang'); -- add maint category if not already added | + | if not corporate then |
| + | is_good_vanc_name (last, ''); |
| + | end |
| end | | end |
− |
| + | |
− | table.insert (language_list, name); | + | link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ) or v_link_table[i]; |
− | name = ''; -- so we can reuse it | + | 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 | | end |
− | | + | return names, etal; -- all done, return our list of names |
− | 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 | | end |
| | | |
− | --[[--------------------------< S E T _ C S 1 _ S T Y L E >----------------------------------------------------
| |
| | | |
− | Set style settings for CS1 citation templates. Returns separator and postscript settings
| + | --[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ |
| | | |
− | ]]
| + | Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or |
| + | select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list. |
| | | |
− | local function set_cs1_style (ps)
| + | Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and |
− | if not is_set (ps) then -- unless explicitely set to something
| + | similarly, |editorn= (and aliases) highest and |editors= lowest |
− | ps = '.'; -- terminate the rendered citation with a period
| + | |
− | end
| + | When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second |
− | return '.', ps; -- separator is a full stop
| + | test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better |
− | end
| + | way to do this, I just haven't discovered what that way is. |
| | | |
− | --[[--------------------------< S E T _ C S 2 _ S T Y L E >----------------------------------------------------
| + | Emits an error message when more than one xxxxor name source is provided. |
| | | |
− | Set style settings for CS2 citation templates. Returns separator, postscript, ref settings
| + | In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate. |
| | | |
| ]] | | ]] |
| | | |
− | local function set_cs2_style (ps, ref) | + | local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) |
− | if not is_set (ps) then -- if |postscript= has not been set, set cs2 default | + | local lastfirst = false; |
− | ps = ''; -- make sure it isn't nil | + | if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a |first1= without a |last1=; this ... |
| + | select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors= |
| + | select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or |
| + | select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then |
| + | lastfirst=true; |
| end | | end |
− | if not is_set (ref) then -- if |ref= is not set | + | |
− | ref = "harv"; -- set default |ref=harv
| + | 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 | | 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 >---------------------- | + | 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; |
− | When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish | + | if is_set (xxxxors) then return 3 end; |
− | rendered style.
| + | return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last |
| + | end |
| + | |
| + | |
| + | --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------ |
| + | |
| + | This function is used to validate a parameter's assigned value for those parameters that have only a limited number |
| + | of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty |
| + | in the source template) the function returns true. If the parameter value is one of the list of allowed values returns |
| + | true; else, emits an error message and returns false. |
| | | |
| ]] | | ]] |
| | | |
− | local function get_settings_from_cite_class (ps, ref, cite_class) | + | local function is_valid_parameter_value (value, name, possible) |
− | local sep;
| + | if not is_set (value) then |
− | if (cite_class == "citation") then -- for citation templates (CS2) | + | return true; -- an empty parameter is ok |
− | sep, ps, ref = set_cs2_style (ps, ref); | + | elseif in_array(value:lower(), possible) then |
− | else -- not a citation template so CS1
| + | return true; |
− | sep, ps = set_cs1_style (ps); | + | else |
| + | table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message |
| + | return false |
| end | | end |
− |
| |
− | return sep, ps, ref -- return them all
| |
| end | | end |
| | | |
− | --[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------
| |
| | | |
− | Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses
| + | --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- |
− | config.CitationClass from the template's #invoke: to establish style.
| |
| | | |
− | ]]
| + | This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space |
| + | when the last character is not a sepc character or when the last three characters are not sepc followed by two |
| + | closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a |
| + | single space character. |
| | | |
− | local function set_style (mode, ps, ref, cite_class) | + | ]] |
− | local sep;
| + | |
− | if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style | + | local function terminate_name_list (name_list, sepc) |
− | sep, ps, ref = set_cs2_style (ps, ref); | + | if (string.sub (name_list,-3,-1) == sepc .. '. ') then -- if already properly terminated |
− | elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style
| + | return name_list; -- just return the name list |
− | sep, ps = set_cs1_style (ps); | + | elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char |
− | else -- anything but cs1 or cs2 | + | return name_list .. " "; -- don't add another |
− | sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass | + | else |
| + | return name_list .. sepc .. ' '; -- otherwise terninate the name list |
| end | | end |
− | if 'none' == ps:lower() then -- if assigned value is 'none' then
| |
− | ps = ''; -- set to empty string
| |
− | end
| |
− |
| |
− | return sep, ps, ref
| |
| end | | end |
| | | |
− | --[=[-------------------------< I S _ P D F >------------------------------------------------------------------
| |
| | | |
− | Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when
| + | --[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- |
− | applying the pdf icon to external links.
| |
| | | |
− | returns true if file extension is one of the recognized extension, else false | + | returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume |
| + | or formatted issue, or an empty string if neither are set. |
| | | |
− | ]=] | + | ]] |
− | | + | |
− | local function is_pdf (url) | + | local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) |
− | return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?'); | + | if not is_set (volume) and not is_set (issue) then |
| + | return ''; |
| + | end |
| + | |
| + | if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then |
| + | if is_set (volume) and is_set (issue) then |
| + | return wrap_msg ('vol-no', {sepc, volume, issue}, lower); |
| + | elseif is_set (volume) then |
| + | return wrap_msg ('vol', {sepc, volume}, lower); |
| + | else |
| + | return wrap_msg ('issue', {sepc, issue}, lower); |
| + | end |
| + | end |
| + | |
| + | local vol = ''; |
| + | |
| + | if is_set (volume) then |
| + | if (4 < mw.ustring.len(volume)) then |
| + | vol = substitute (cfg.messages['j-vol'], {sepc, volume}); |
| + | else |
| + | vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); |
| + | end |
| + | end |
| + | if is_set (issue) then |
| + | return vol .. substitute (cfg.messages['j-issue'], issue); |
| + | end |
| + | return vol; |
| end | | end |
| | | |
− | --[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------
| |
| | | |
− | Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does
| + | --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- |
− | not have a matching url parameter. If the format parameter is not set and the url contains a file extension that
| |
− | is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with
| |
− | the appropriate styling.
| |
| | | |
− | ]]
| + | adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings. |
| + | The return order is: |
| + | page, pages, sheet, sheets |
| | | |
− | local function style_format (format, url, fmt_param, url_param)
| + | Singular has priority over plural when both are provided. |
− | 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
| |
− | | |
− | --[[--------------------------< G E T _ D I S P L A Y _ A U T H O R S _ E D I T O R S >------------------------
| |
− | | |
− | Returns a number that may or may not limit the length of the author or editor name lists.
| |
− | | |
− | When the value assigned to |display-authors= is a number greater than or equal to zero, return the number and
| |
− | the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains
| |
− | some variant of the text 'et al.').
| |
− | | |
− | When the value assigned to |display-authors= is the keyword 'etal', return a number that is one greater than the
| |
− | number of authors in the list and set the 'etal' flag true. This will cause the list_people() to display all of
| |
− | the names in the name list followed by 'et al.'
| |
− | | |
− | In all other cases, returns nil and the previous state of the 'etal' flag.
| |
| | | |
| ]] | | ]] |
| | | |
− | local function get_display_authors_editors (max, count, list_name, etal) | + | local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) |
− | if is_set (max) then | + | if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators |
− | if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings
| + | if is_set (sheet) then |
− | max = count + 1; -- number of authors + 1 so display all author name plus et al.
| + | if 'journal' == origin then |
− | etal = true; -- overrides value set by extract_names() | + | return '', '', wrap_msg ('j-sheet', sheet, lower), ''; |
− | elseif max:match ('^%d+$') then -- if is a string of numbers
| + | else |
− | max = tonumber (max); -- make it a number | + | return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; |
− | if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors | + | end |
− | add_maint_cat ('disp_auth_ed', list_name); | + | elseif is_set (sheets) then |
| + | if 'journal' == origin then |
| + | return '', '', '', wrap_msg ('j-sheets', sheets, lower); |
| + | else |
| + | return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower); |
| end | | end |
− | 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 | | end |
− | elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category | + | end |
− | max = count + 1; -- number of authors + 1 | + | |
| + | local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); |
| + | |
| + | if is_set (page) then |
| + | if is_journal then |
| + | return substitute (cfg.messages['j-page(s)'], page), '', '', ''; |
| + | elseif not nopp then |
| + | return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; |
| + | else |
| + | return substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; |
| + | end |
| + | elseif is_set(pages) then |
| + | if is_journal then |
| + | return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; |
| + | elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number |
| + | return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; |
| + | elseif not nopp then |
| + | return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; |
| + | else |
| + | return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; |
| + | end |
| end | | end |
| | | |
− | return max, etal; | + | return '', '', '', ''; -- return empty strings |
| end | | end |
| | | |
− | --[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------
| |
| | | |
− | Adds page to Category:CS1 maint: extra text if |page= or |pages= has what appears to be some form of p. or pp.
| + | --[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- |
− | abbreviation in the first characters of the parameter content.
| + | |
| + | Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the |
| + | save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...) |
| + | archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allow |
| + | unwitting readers to do. |
| | | |
− | check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value:
| + | When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own |
− | 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
| + | algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results. |
− | bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP
| |
| | | |
− | ]]
| + | This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and |
| + | |archive-date= and an error message when: |
| + | |archive-url= holds an archive.org save command url |
| + | |archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the |
| + | correct place |
| + | otherwise returns |archive-url= and |archive-date= |
| | | |
− | local function extra_text_in_page_check (page)
| + | There are two mostly compatible archive.org urls: |
− | -- local good_pattern = '^P[^%.P%l]';
| + | //web.archive.org/<timestamp>... -- the old form |
− | 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? | + | //web.archive.org/web/<timestamp>... -- the new form |
− | -- local bad_pattern = '^[Pp][Pp]'; | |
− | local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; | |
| | | |
− | if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then
| + | The old form does not support or map to the new form when it contains a display flag. There are four identified flags |
− | add_maint_cat ('extra_text');
| + | ('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore) |
− | end
| + | we don't check for these specific flags but we do check the form. |
− | -- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or
| |
− | -- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then
| |
− | -- add_maint_cat ('extra_text');
| |
− | -- end
| |
− | end
| |
| | | |
| + | This function supports a preview mode. When the article is rendered in preview mode, this funct may return a modified |
| + | archive url: |
| + | for save command errors, return undated wildcard (/*/) |
| + | for timestamp errors when the timestamp has a wildcard, return the url unmodified |
| + | for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/) |
| | | |
− | --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >--------------------------------
| + | ]=] |
| | | |
− | This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and
| + | local function archive_url_check (url, date) |
− | |xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does.
| + | local err_msg = ''; -- start with the error message empty |
| + | local path, timestamp, flag; -- portions of the archive.or url |
| + | |
| + | if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine url |
| + | return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate |
| + | end |
| | | |
− | Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names
| + | if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page |
− | may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance
| + | err_msg = 'save command'; |
− | tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests.
| + | url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL |
| + | elseif url:match('//liveweb%.archive%.org/') then |
| + | err_msg = 'liveweb'; |
| + | else |
| + | path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation |
| + | |
| + | if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here |
| + | err_msg = 'timestamp'; |
| + | if '*' ~= flag then |
| + | url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat) |
| + | end |
| + | elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element |
| + | err_msg = 'path'; |
| + | elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element) |
| + | err_msg = 'flag'; |
| + | elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element) |
| + | err_msg = 'flag'; |
| + | else |
| + | return url, date; -- return archiveURL and ArchiveDate |
| + | end |
| + | end |
| + | -- if here, something not right so |
| + | table.insert( z.message_tail, { set_error( 'archive_url', {err_msg}, true ) } ); -- add error message and |
| + | if is_set (Frame:preprocess('{{REVISIONID}}')) then |
| + | return '', ''; -- return empty strings for archiveURL and ArchiveDate |
| + | else |
| + | return url, date; -- preview mode so return archiveURL and ArchiveDate |
| + | end |
| + | end |
| | | |
− | This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials.
| |
| | | |
− | ]]
| + | --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ |
| | | |
− | local function parse_vauthors_veditors (args, vparam, list_name)
| + | This is the main function doing the majority of the citation formatting. |
− | local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn=
| |
− | local v_name_table = {};
| |
− | local etal = false; -- return value set to true when we find some form of et al. vauthors parameter
| |
− | local last, first, link, mask;
| |
− | 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
| + | local function citation0( config, args) |
− | if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection
| + | --[[ |
− | first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor
| + | Load Input Parameters |
− | last = v_name:match ('^%(%((.+)%)%)$')
| + | The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. |
− | corporate = true;
| + | ]] |
− | elseif string.find(v_name, "%s") then
| + | local A = argument_wrapper( args ); |
− | lastfirstTable = {}
| + | local i |
− | 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
| |
| | | |
− | --[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ | + | -- Pick out the relevant fields from the arguments. Different citation templates |
| + | -- define different field names for the same underlying things. |
| | | |
− | Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or
| + | -- set default parameter values defined by |mode= parameter. |
− | select one of |editors=, |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list.
| + | local Mode = A['Mode']; |
| + | if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then |
| + | Mode = ''; |
| + | end |
| | | |
− | Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and
| + | local author_etal; |
− | similarly, |editorn= (and aliases) highest and |editors= lowest
| + | local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
| + | local Authors; |
| + | local NameListFormat = A['NameListFormat']; |
| + | local Collaboration = A['Collaboration']; |
| | | |
− | When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second
| + | do -- to limit scope of selected |
− | test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better
| + | local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList'); |
− | way to do this, I just haven't discovered what that way is.
| + | 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= |
| + | if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors= |
| + | add_maint_cat ('authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO: |
| + | end |
| + | end |
| + | if is_set (Collaboration) then |
| + | author_etal = true; -- so that |display-authors=etal not required |
| + | end |
| + | end |
| | | |
− | Emits an error message when more than one xxxxor name source is provided.
| + | local Others = A['Others']; |
| | | |
− | In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate.
| + | local editor_etal; |
| + | local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= |
| + | local Editors; |
| | | |
− | ]] | + | 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= |
| + | add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged |
| + | end |
| + | end |
| | | |
− | local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) | + | local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs |
− | local lastfirst = false; | + | local Translators; -- assembled translators name list |
− | if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1 | + | t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
− | 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 | + | local interviewers_list = {}; |
− | (is_set (vxxxxors) and is_set (xxxxors)) or | + | local Interviewers = A['Interviewers'] |
− | (true == lastfirst and is_set (xxxxors)) then
| + | if is_set (Interviewers) then -- add a maint cat if the |interviewers= is used |
− | local err_name;
| + | add_maint_cat ('interviewers'); -- because use of this parameter is discouraged |
− | if 'AuthorList' == list_name then -- figure out which name should be used in error message
| + | else |
− | err_name = 'author';
| + | interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters |
− | else
| |
− | err_name = 'editor';
| |
− | end
| |
− | table.insert( z.message_tail, { set_error( 'redundant_parameters',
| |
− | {err_name .. '-name-list parameters'}, true ) } ); -- add error message
| |
| end | | end |
| | | |
− | if true == lastfirst then return 1 end; -- return a number indicating which author name source to use | + | local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
− | if is_set (vxxxxors) then return 2 end; | + | local Contributors; -- assembled contributors name list |
− | if is_set (xxxxors) then return 3 end;
| + | local Contribution = A['Contribution']; |
− | return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last
| + | if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites |
− | end | + | 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 |
| | | |
− | --[[--------------------------< I S _ V A L I D _ P A R A M E T E R _ V A L U E >------------------------------
| + | local Year = A['Year']; |
− | | + | local PublicationDate = A['PublicationDate']; |
− | This function is used to validate a parameter's assigned value for those parameters that have only a limited number
| + | local OrigYear = A['OrigYear']; |
− | of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty
| + | local Date = A['Date']; |
− | in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns | + | local LayDate = A['LayDate']; |
− | true; else, emits an error message and returns false.
| + | ------------------------------------------------- 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']; |
| + | link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set |
| | | |
− | ]] | + | 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 function is_valid_parameter_value (value, name, possible) | + | local ArchiveDate; |
− | if not is_set (value) then
| + | local ArchiveURL; |
− | return true; -- an empty parameter is ok
| |
− | elseif in_array(value:lower(), possible) then | |
− | return true;
| |
− | else
| |
− | table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message
| |
− | return false
| |
− | end
| |
− | end
| |
| | | |
| + | ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) |
| + | |
| + | 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 |
| | | |
− | --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- | + | 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 |
| | | |
− | This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space
| + | local Series = A['Series']; |
− | when the last character is not a sepc character or when the last three characters are not sepc followed by two
| + | |
− | closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a
| + | local Volume; |
− | single space character.
| + | local Issue; |
| + | local Page; |
| + | local Pages; |
| + | local At; |
| | | |
− | ]] | + | if in_array (config.CitationClass, cfg.templates_using_volume) then |
− | | + | Volume = A['Volume']; |
− | local function terminate_name_list (name_list, sepc)
| + | end |
− | 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 | + | -- conference & map books do not support issue |
− | return name_list .. " "; -- don't add another | + | if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then |
− | else
| + | Issue = hyphen_to_dash (A['Issue']); |
− | return name_list .. sepc .. ' '; -- otherwise terninate the name list | + | 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 | | end |
− | 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 |
| | | |
− | --[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- | + | local UrlAccess = A['UrlAccess']; |
− | | + | if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then |
− | returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume
| + | UrlAccess = nil; |
− | or formatted issue, or an empty string if neither are set.
| + | end |
| + | if not is_set(URL) and is_set(UrlAccess) then |
| + | UrlAccess = nil; |
| + | table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } ); |
| + | end |
| | | |
− | ]]
| + | if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set |
− |
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message |
− | local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower)
| + | SubscriptionRequired = nil; -- unset; prefer |access= over |subscription= |
− | if not is_set (volume) and not is_set (issue) then
| |
− | return ''; | |
− | end
| |
− |
| |
− | if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then
| |
− | if is_set (volume) and is_set (issue) then
| |
− | return wrap_msg ('vol-no', {sepc, volume, issue}, lower);
| |
− | elseif is_set (volume) then
| |
− | return wrap_msg ('vol', {sepc, volume}, lower);
| |
− | else
| |
− | return wrap_msg ('issue', {sepc, issue}, lower); | |
| end | | end |
− | end
| + | if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set |
− |
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message |
− | local vol = '';
| + | RegistrationRequired = nil; -- unset; prefer |access= over |registration= |
− | | |
− | if is_set (volume) then
| |
− | if (4 < mw.ustring.len(volume)) then | |
− | vol = substitute (cfg.messages['j-vol'], {sepc, volume}); | |
− | else
| |
− | vol = wrap_style ('vol-bold', hyphen_to_dash(volume));
| |
| end | | end |
− | end
| |
− | if is_set (issue) then
| |
− | return vol .. substitute (cfg.messages['j-issue'], issue);
| |
− | end
| |
− | return vol;
| |
− | end
| |
| | | |
| + | local ChapterUrlAccess = A['ChapterUrlAccess']; |
| + | if not is_valid_parameter_value (ChapterUrlAccess, 'chapter-url-access', cfg.keywords ['url-access']) then -- same as url-access |
| + | ChapterUrlAccess = nil; |
| + | end |
| + | if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then |
| + | ChapterUrlAccess = nil; |
| + | table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'chapter-url'}, true ) } ); |
| + | end |
| | | |
− | --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >-----------------------------------------
| + | local Via = A['Via']; |
| + | local AccessDate = A['AccessDate']; |
| + | local Agency = A['Agency']; |
| | | |
− | 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 Language = A['Language']; |
− | The return order is:
| + | local Format = A['Format']; |
− | page, pages, sheet, sheets | + | 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 |
| | | |
− | Singular has priority over plural when both are provided.
| + | local ID_list = extract_ids( args ); |
| + | local ID_access_levels = extract_id_access_levels( args, ID_list ); |
| | | |
− | ]] | + | 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 function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) | + | local LastAuthorAmp = A['LastAuthorAmp']; |
− | if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators
| + | if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then |
− | if is_set (sheet) then | + | LastAuthorAmp = nil; -- set to empty string |
− | if 'journal' == origin then
| |
− | return '', '', wrap_msg ('j-sheet', sheet, lower), '';
| |
− | else
| |
− | return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), '';
| |
− | end
| |
− | elseif is_set (sheets) then
| |
− | if 'journal' == origin then | |
− | return '', '', '', wrap_msg ('j-sheets', sheets, lower);
| |
− | else
| |
− | return '', '', '', wrap_msg ('sheets', {sepc, sheets}, lower);
| |
− | end
| |
| end | | end |
− | end
| |
| | | |
− | local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin); | + | 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 |
| | | |
− | if is_set (page) then | + | --local variables that are not cs1 parameters |
− | if is_journal then
| + | local use_lowercase; -- controls capitalization of certain static text |
− | return substitute (cfg.messages['j-page(s)'], page), '', '', '';
| + | local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language |
− | elseif not nopp then
| + | local anchor_year; -- used in the CITEREF identifier |
− | return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', '';
| + | local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification |
− | else | + | |
− | return substitute (cfg.messages['nopp'], {sepc, page}), '', '', '';
| + | local DF = A['DF']; -- date format set in cs1|2 template |
| + | if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword |
| + | DF = ''; -- not valid, set to empty string |
| + | 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 | | end |
− | elseif is_set(pages) then
| + | for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns |
− | if is_journal then | + | if this_page.text:match (v) then -- test page name against each pattern |
− | return substitute (cfg.messages['j-page(s)'], pages), '', '', '';
| + | no_tracking_cats = "true"; -- set no_tracking_cats |
− | elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number
| + | break; -- bail out if one is found |
− | return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', '';
| + | end |
− | elseif not nopp then
| |
− | return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', '';
| |
− | else
| |
− | return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; | |
| end | | end |
| end | | end |
− |
| |
− | return '', '', '', ''; -- return empty strings
| |
− | end
| |
| | | |
− | --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ | + | -- 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 |
| | | |
− | This is the main function doing the majority of the citation formatting.
| + | 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 |
| | | |
− | local function citation0( config, args)
| + | -- both |publication-place= and |place= (|location=) allowed if different |
− | --[[ | + | if not is_set(PublicationPlace) and is_set(Place) then |
− | Load Input Parameters | + | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
− | The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. | + | end |
− | ]] | + | |
− | local A = argument_wrapper( args ); | + | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
− | local i | + | |
| + | --[[ |
| + | Parameter remapping for cite encyclopedia: |
| + | When the citation has these parameters: |
| + | |encyclopedia and |title then map |title to |article and |encyclopedia to |title |
| + | |encyclopedia and |article then map |encyclopedia to |title |
| + | |encyclopedia then map |encyclopedia to |title |
| + | |
| + | |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 |
| + | |
| + | ]] |
| | | |
− | -- Pick out the relevant fields from the arguments. Different citation templates
| + | local Encyclopedia = A['Encyclopedia']; |
− | -- 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 | + | if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation |
− | local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList'); | + | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set |
− | if 1 == selected then
| + | if is_set(Title) or is_set (ScriptTitle) then |
− | a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn=
| + | if not is_set(Chapter) then |
− | elseif 2 == selected then
| + | Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
− | NameListFormat = 'vanc'; -- override whatever |name-list-format= might be
| + | ScriptChapter = ScriptTitle; |
− | a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn=
| + | TransChapter = TransTitle; |
− | elseif 3 == selected then
| + | ChapterURL = URL; |
− | Authors = A['Authors']; -- use content of |authors=
| + | ChapterUrlAccess = UrlAccess; |
− | end
| |
− | end
| |
| | | |
− | local Coauthors = A['Coauthors'];
| + | if not is_set (ChapterURL) and is_set (TitleLink) then |
− | local Others = A['Others'];
| + | Chapter = make_wikilink (TitleLink, Chapter); |
− | | + | end |
− | local editor_etal;
| + | Title = Periodical; |
− | local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors=
| + | ChapterFormat = Format; |
− | local Editors;
| + | Periodical = ''; -- redundant so unset |
− | | + | TransTitle = ''; |
− | do -- to limit scope of selected
| + | URL = ''; |
− | local selected = select_author_editor_source (A['Veditors'], A['Editors'], args, 'EditorList');
| + | Format = ''; |
− | if 1 == selected then
| + | TitleLink = ''; |
− | e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn=
| + | ScriptTitle = ''; |
− | elseif 2 == selected then
| + | end |
− | NameListFormat = 'vanc'; -- override whatever |name-list-format= might be | + | else -- |title not set |
− | e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn=
| + | Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title |
− | elseif 3 == selected then
| + | Periodical = ''; -- redundant so unset |
− | Editors = A['Editors']; -- use content of |editors=
| + | end |
| end | | end |
| end | | end |
| | | |
− | local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs | + | -- Special case for cite techreport. |
− | local Translators; -- assembled translators name list
| + | if (config.CitationClass == "techreport") then -- special case for cite techreport |
− | t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn=
| + | if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' |
− |
| + | if not is_set(ID) then -- can we use ID for the "number"? |
− | local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs
| + | ID = A['Number']; -- yes, use it |
− | local Contributors; -- assembled contributors name list
| + | else -- ID has a value so emit error message |
− | local Contribution = A['Contribution'];
| + | table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )}); |
− | if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites | + | end |
− | c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn=
| + | end |
− |
| |
− | 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 | | 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' | + | -- special case for cite mailing list |
− | NameListFormat = ''; -- anything else, set to empty string | + | 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 | | end |
| | | |
− | local Year = A['Year']; | + | -- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
− | local PublicationDate = A['PublicationDate']; | + | if 'conference' == config.CitationClass then |
− | local OrigYear = A['OrigYear'];
| + | if is_set(BookTitle) then |
− | local Date = A['Date'];
| + | Chapter = Title; |
− | local LayDate = A['LayDate'];
| + | -- ChapterLink = TitleLink; -- |chapterlink= is deprecated |
− | ------------------------------------------------- Get title data
| + | ChapterURL = URL; |
− | local Title = A['Title'];
| + | ChapterUrlAccess = UrlAccess; |
− | local ScriptTitle = A['ScriptTitle'];
| + | ChapterURLorigin = URLorigin; |
− | local BookTitle = A['BookTitle'];
| + | URLorigin = ''; |
− | local Conference = A['Conference'];
| + | ChapterFormat = Format; |
− | local TransTitle = A['TransTitle'];
| + | TransChapter = TransTitle; |
− | local TitleNote = A['TitleNote'];
| + | Title = BookTitle; |
− | local TitleLink = A['TitleLink'];
| + | Format = ''; |
− | if is_set (TitleLink) and false == link_param_ok (TitleLink) then | + | -- TitleLink = ''; |
− | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=; | + | TransTitle = ''; |
| + | URL = ''; |
| end | | end |
| + | elseif 'speech' ~= config.CitationClass then |
| + | Conference = ''; -- not cite conference or cite speech so make sure this is empty string |
| + | end |
| | | |
− | local Chapter = A['Chapter']; | + | -- cite map oddities |
− | local ScriptChapter = A['ScriptChapter']; | + | local Cartography = ""; |
− | local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode | + | local Scale = ""; |
− | local TransChapter = A['TransChapter']; | + | local Sheet = A['Sheet'] or ''; |
− | local TitleType = A['TitleType'];
| + | local Sheets = A['Sheets'] or ''; |
− | local Degree = A['Degree']; | + | if config.CitationClass == "map" then |
− | local Docket = A['Docket'];
| + | Chapter = A['Map']; |
− | local ArchiveFormat = A['ArchiveFormat']; | + | ChapterURL = A['MapURL']; |
− | local ArchiveURL = A['ArchiveURL'];
| + | ChapterUrlAccess = UrlAccess; |
− | local URL = A['URL']
| + | TransChapter = A['TransMap']; |
− | local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL
| + | ChapterURLorigin = A:ORIGIN('MapURL'); |
− | local ChapterURL = A['ChapterURL'];
| + | ChapterFormat = A['MapFormat']; |
− | local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL
| + | |
− | local ConferenceFormat = A['ConferenceFormat'];
| + | Cartography = A['Cartography']; |
− | local ConferenceURL = A['ConferenceURL'];
| + | if is_set( Cartography ) then |
− | local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL
| + | Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); |
− | local Periodical = A['Periodical']; | + | end |
− | local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter
| + | Scale = A['Scale']; |
| + | if is_set( Scale ) then |
| + | Scale = sepc .. " " .. Scale; |
| + | end |
| + | end |
| | | |
− | local Series = A['Series']; | + | -- 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 Volume;
| + | local AirDate = A['AirDate']; |
− | local Issue;
| + | local SeriesLink = A['SeriesLink']; |
− | 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
| + | link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set |
− | 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 Network = A['Network']; |
− | local PublicationPlace = A['PublicationPlace']
| + | local Station = A['Station']; |
− | local Place = A['Place'];
| + | local s, n = {}, {}; |
− |
| + | -- do common parameters first |
− | local PublisherName = A['PublisherName'];
| + | if is_set(Network) then table.insert(n, Network); end |
− | local RegistrationRequired = A['RegistrationRequired'];
| + | if is_set(Station) then table.insert(n, Station); end |
− | if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then | + | ID = table.concat(n, sepc .. ' '); |
− | RegistrationRequired=nil;
| + | |
− | end | + | if not is_set (Date) and is_set (AirDate) then -- promote airdate to date |
− | local SubscriptionRequired = A['SubscriptionRequired'];
| + | Date = AirDate; |
− | if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then | |
− | SubscriptionRequired=nil; | |
| end | | end |
| | | |
− | local Via = A['Via'];
| + | if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
− | local AccessDate = A['AccessDate'];
| + | local Season = A['Season']; |
− | local ArchiveDate = A['ArchiveDate'];
| + | local SeriesNumber = A['SeriesNumber']; |
− | 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'];
| + | if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set |
− | local Format = A['Format'];
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message |
− | local ChapterFormat = A['ChapterFormat'];
| + | SeriesNumber = ''; -- unset; prefer |season= over |seriesno= |
− | local DoiBroken = A['DoiBroken'];
| + | end |
− | local ID = A['ID'];
| + | -- assemble a table of parts concatenated later into Series |
− | local ASINTLD = A['ASINTLD'];
| + | if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
− | local IgnoreISBN = A['IgnoreISBN'];
| + | if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end |
− | if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then
| + | if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end |
− | IgnoreISBN = nil; -- anything else, set to empty string | + | Issue = ''; -- unset because this is not a unique parameter |
− | end
| + | |
− | local Embargo = A['Embargo'];
| + | Chapter = Title; -- promote title parameters to chapter |
− | local Class = A['Class']; -- arxiv class identifier
| + | ScriptChapter = ScriptTitle; |
− | | + | ChapterLink = TitleLink; -- alias episodelink |
− | local ID_list = extract_ids( args );
| + | TransChapter = TransTitle; |
| + | ChapterURL = URL; |
| + | ChapterUrlAccess = UrlAccess; |
| + | 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 |
| | | |
− | local Quote = A['Quote'];
| + | if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL |
| + | Chapter = make_wikilink (ChapterLink, Chapter); |
| + | elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; |
| + | Series = make_wikilink (ChapterLink, Series); |
| + | end |
| + | URL = ''; -- unset |
| + | TransTitle = ''; |
| + | ScriptTitle = ''; |
| + | |
| + | else -- now oddities that are cite serial |
| + | Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial |
| + | Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? |
| + | if is_set (Series) and is_set (SeriesLink) then |
| + | Series = make_wikilink (SeriesLink, Series); |
| + | end |
| + | Series = wrap_style ('italic-title', Series); -- series is italicized |
| + | end |
| + | end |
| + | -- end of {{cite episode}} stuff |
| + | |
| + | -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. |
| + | do |
| + | if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then |
| + | if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates |
| + | table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message |
| + | end |
| + | |
| + | if 'arxiv' == config.CitationClass then |
| + | Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string |
| + | end |
| | | |
− | local LayFormat = A['LayFormat'];
| + | if 'biorxiv' == config.CitationClass then |
− | local LayURL = A['LayURL'];
| + | Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string |
− | local LaySource = A['LaySource'];
| + | end |
− | 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 'citeseerx' == config.CitationClass then |
− | if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then
| + | Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string |
− | LastAuthorAmp = nil; -- set to empty string
| + | end |
| end | | end |
− | local no_tracking_cats = A['NoTracking']; | + | end |
− | 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
| + | -- handle type parameter for those CS1 citations that have default values |
| + | if in_array(config.CitationClass, {"AV-media-notes", "interview", "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 .. ' ' .. cfg.title_types ['thesis']:lower(); |
| end | | end |
| + | end |
| | | |
− | --these are used by cite interview | + | if is_set(TitleType) then -- if type parameter is specified |
− | local Callsign = A['Callsign'];
| + | TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses |
− | local City = A['City']; | + | -- TODO: Hack on TitleType to fix bunched parentheses problem |
− | local Program = A['Program']; | + | end |
| | | |
− | --local variables that are not cs1 parameters | + | -- legacy: promote PublicationDate to Date if neither Date nor Year are set. |
− | local use_lowercase; -- controls capitalization of certain static text
| + | local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging |
− | 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 | + | if not is_set (Date) then |
− | local Mode = A['Mode'];
| + | Date = Year; -- promote Year to Date |
− | if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then
| + | Year = nil; -- make nil so Year as empty string isn't used for CITEREF |
− | Mode = ''; | + | if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set |
| + | Date = PublicationDate; -- promote PublicationDate to Date |
| + | PublicationDate = ''; -- unset, no longer needed |
| + | Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter |
| + | else |
| + | Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter |
| + | end |
| + | else |
| + | Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging |
| end | | 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 PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation |
− | 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 | + | 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, date_parameters_list, mismatch |
| + | local error_message = ''; |
| + | -- AirDate has been promoted to Date so not necessary to check it |
| + | local date_parameters_list = { |
| + | ['access-date'] = {val=AccessDate, name=A:ORIGIN ('AccessDate')}, |
| + | ['archive-date'] = {val=ArchiveDate, name=A:ORIGIN ('ArchiveDate')}, |
| + | ['date'] = {val=Date, name=Date_origin}, |
| + | ['doi-broken-date'] = {val=DoiBroken, name=A:ORIGIN ('DoiBroken')}, |
| + | ['embargo'] = {val=Embargo, name=A:ORIGIN ('Embargo')}, |
| + | ['lay-date'] = {val=LayDate, name=A:ORIGIN ('LayDate')}, |
| + | ['publication-date'] ={val=PublicationDate, name=A:ORIGIN ('PublicationDate')}, |
| + | ['year'] = {val=Year, name=A:ORIGIN ('Year')}, |
| + | }; |
| + | anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date); |
| + | |
| + | -- start temporary Julian / Gregorian calendar uncertainty categorization |
| + | if COinS_date.inter_cal_cat then |
| + | add_prop_cat ('jul_greg_uncertainty'); |
| end | | end |
− | for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns | + | -- end temporary Julian / Gregorian calendar uncertainty categorization |
− | if this_page.text:match (v) then -- test page name against each pattern | + | |
− | no_tracking_cats = "true"; -- set no_tracking_cats
| + | if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; |
− | break; -- bail out if one is found | + | 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 |
| end | | end |
− | end
| + | |
| + | if not is_set(error_message) then -- error free dates only |
| + | local modified = false; -- flag |
| + | |
| + | if is_set (DF) then -- if we need to reformat dates |
| + | modified = reformat_dates (date_parameters_list, DF, false); -- reformat to DF format, use long month names if appropriate |
| + | end |
| | | |
− | -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) | + | if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate |
− | 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 | + | modified = true; |
| + | add_maint_cat ('date_format'); -- hyphens were converted so add maint category |
| + | end |
| + | |
| + | -- for those wikis that can and want to have English date names translated to the local language, |
| + | -- uncomment these three lines. Not supported by en.wiki (for obvious reasons) |
| + | -- set date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates) |
| + | -- if date_name_xlate (date_parameters_list, false) then |
| + | -- modified = true; |
| + | -- end |
| | | |
− | local NoPP = A['NoPP']
| + | if modified then -- if the date_parameters_list values were modified |
− | if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then
| + | AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values |
− | NoPP = true;
| + | ArchiveDate = date_parameters_list['archive-date'].val; |
− | else
| + | Date = date_parameters_list['date'].val; |
− | NoPP = nil; -- unset, used as a flag later
| + | DoiBroken = date_parameters_list['doi-broken-date'].val; |
− | end
| + | LayDate = date_parameters_list['lay-date'].val; |
− | | + | PublicationDate = date_parameters_list['publication-date'].val; |
− | if is_set(Page) then
| + | end |
− | if is_set(Pages) or is_set(At) then
| + | else |
− | Pages = ''; -- unset the others
| + | table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message |
− | At = '';
| |
| end | | end |
− | extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp.
| + | end -- end of do |
− | 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 | + | -- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS. |
− | if not is_set(PublicationPlace) and is_set(Place) then | + | -- 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 |
− | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place
| + | Embargo = is_embargoed (Embargo); |
− | end
| |
− |
| |
− | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same
| |
− |
| |
− | --[[
| |
− | Parameter remapping for cite encyclopedia:
| |
− | When the citation has these parameters:
| |
− | |encyclopedia and |title then map |title to |article and |encyclopedia to |title | |
− | |encyclopedia and |article then map |encyclopedia to |title
| |
− | |encyclopedia then map |encyclopedia to |title
| |
| | | |
− | |trans_title maps to |trans_chapter when |title is re-mapped | + | if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
− | |url maps to |chapterurl when |title is remapped
| + | 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= |
| + | if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url= |
| + | table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
| + | AccessDate = ''; -- unset |
| + | end |
| | | |
− | All other combinations of |encyclopedia, |title, and |article are not modified
| + | end |
| + | end |
| | | |
− | ]]
| + | -- 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 |
− | local Encyclopedia = A['Encyclopedia'];
| + | if not is_set(Title) and |
− | | + | not is_set(TransTitle) and |
− | if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation | + | not is_set(ScriptTitle) then |
− | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set
| + | if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? |
− | if is_set(Title) or is_set (ScriptTitle) then
| + | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); |
− | if not is_set(Chapter) then
| + | else |
− | Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title
| + | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); |
− | ScriptChapter = ScriptTitle;
| |
− | TransChapter = TransTitle;
| |
− | ChapterURL = URL;
| |
− | if not is_set (ChapterURL) and is_set (TitleLink) then
| |
− | Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]';
| |
− | end
| |
− | Title = Periodical;
| |
− | ChapterFormat = Format;
| |
− | Periodical = ''; -- redundant so unset
| |
− | TransTitle = '';
| |
− | URL = '';
| |
− | Format = '';
| |
− | TitleLink = '';
| |
− | ScriptTitle = '';
| |
− | end
| |
− | else -- |title not set | |
− | Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title | |
− | Periodical = ''; -- redundant so unset
| |
| end | | end |
− | 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 | | end |
| | | |
− | -- Special case for cite techreport.
| + | check_for_url ({ -- add error message when any of these parameters contains a URL |
− | if (config.CitationClass == "techreport") then -- special case for cite techreport | + | ['title']=Title, |
− | if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' | + | [A:ORIGIN('Chapter')]=Chapter, |
− | if not is_set(ID) then -- can we use ID for the "number"?
| + | [A:ORIGIN('Periodical')]=Periodical, |
− | ID = A['Number']; -- yes, use it
| + | [A:ORIGIN('PublisherName')] = PublisherName |
− | else -- ID has a value so emit error message
| + | }); |
− | table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )});
| |
− | end
| |
− | end
| |
− | end
| |
| | | |
− | -- special case for cite interview | + | -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. |
− | if (config.CitationClass == "interview") then | + | -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that |
− | if is_set(Program) then
| + | -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title |
− | ID = ' ' .. Program;
| + | -- is the article title, and Chapter is a section within the article. So, we remap |
− | end
| + | |
− | if is_set(Callsign) then
| + | local coins_chapter = Chapter; -- default assuming that remapping not required |
− | if is_set(ID) then
| + | local coins_title = Title; -- et tu |
− | ID = ID .. sepc .. ' ' .. Callsign;
| + | if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then |
− | else
| + | if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then |
− | ID = ' ' .. Callsign;
| + | coins_chapter = Title; -- remap |
− | end
| + | coins_title = Periodical; |
− | end
| |
− | if is_set(City) then
| |
− | if is_set(ID) then
| |
− | ID = ID .. sepc .. ' ' .. City;
| |
− | else | |
− | ID = ' ' .. City;
| |
− | end
| |
| end | | end |
| + | end |
| + | local coins_author = a; -- default for coins rft.au |
| + | if 0 < #c then -- but if contributor list |
| + | coins_author = c; -- use that instead |
| + | end |
| | | |
− | if is_set(Others) then | + | -- this is the function call to COinS() |
− | if is_set(TitleType) then
| + | local OCinSoutput = COinS({ |
− | Others = ' ' .. TitleType .. ' with ' .. Others;
| + | ['Periodical'] = Periodical, |
− | TitleType = '';
| + | ['Encyclopedia'] = Encyclopedia, |
− | else | + | ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup |
− | Others = ' ' .. 'Interview with ' .. Others;
| + | ['Degree'] = Degree; -- cite thesis only |
− | end
| + | ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup |
− | else | + | ['PublicationPlace'] = PublicationPlace, |
− | Others = '(Interview)'; | + | ['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); |
| + | |
| + | -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite citeseerx}} AFTER generation of COinS data. |
| + | if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, or CiteSeerX now unset so it isn't displayed |
| + | Periodical = ''; -- periodical not allowed in these templates; if article has been published, use cite journal |
| + | end |
| + | |
| + | -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text |
| + | if 'newsgroup' == config.CitationClass then |
| + | if is_set (PublisherName) then |
| + | PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil )); |
| end | | end |
| 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 | + | -- Now perform various field substitutions. |
− | local Cartography = ""; | + | -- We also add leading spaces and surrounding markup and punctuation to the |
− | local Scale = ""; | + | -- various parts of the citation, but only when they are non-nil. |
− | local Sheet = A['Sheet'] or '';
| + | local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list |
− | local Sheets = A['Sheets'] or '';
| + | do |
− | if config.CitationClass == "map" then
| + | local last_first_list; |
− | Chapter = A['Map'];
| + | local control = { |
− | ChapterURL = A['MapURL'];
| + | format = NameListFormat, -- empty string or 'vanc' |
− | TransChapter = A['TransMap'];
| + | maximum = nil, -- as if display-authors or display-editors not set |
− | ChapterURLorigin = A:ORIGIN('MapURL'); | + | lastauthoramp = LastAuthorAmp, |
− | ChapterFormat = A['MapFormat'];
| + | page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn |
− | | + | mode = Mode |
− | Cartography = A['Cartography'];
| + | }; |
− | if is_set( Cartography ) then
| + | |
− | Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase);
| + | do -- do editor name list first because the now unsupported coauthors used to modify control table |
− | end
| + | control.maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal); |
− | Scale = A['Scale'];
| + | last_first_list, EditorCount = list_people(control, e, editor_etal); |
− | 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 is_set (Editors) then |
− | if 'episode' == config.CitationClass or 'serial' == config.CitationClass then
| + | if editor_etal then |
− | local AirDate = A['AirDate'];
| + | Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal |
− | local SeriesLink = A['SeriesLink']; | + | EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation |
− | if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then
| + | else |
− | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))}); | + | 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 | | end |
− | local Network = A['Network'];
| + | |
− | local Station = A['Station'];
| + | if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then |
− | local s, n = {}, {}; | + | EditorCount = 2; -- spoof to display (eds.) annotation |
− | -- do common parameters first
| + | end |
− | if is_set(Network) then table.insert(n, Network); end
| + | end |
− | if is_set(Station) then table.insert(n, Station); end | + | do -- now do interviewers |
− | ID = table.concat(n, sepc .. ' ');
| + | control.maximum = #interviewers_list; -- number of interviewerss |
− | | + | Interviewers = list_people(control, interviewers_list, false); -- et al not currently supported |
− | if not is_set (Date) and is_set (AirDate) then -- promote airdate to date | + | end |
− | Date = AirDate; | + | do -- now do translators |
| + | control.maximum = #t; -- number of translators |
| + | Translators = list_people(control, t, false); -- et al not currently supported |
| + | end |
| + | do -- now do contributors |
| + | control.maximum = #c; -- number of contributors |
| + | Contributors = list_people(control, c, false); -- et al not currently supported |
| end | | end |
| + | do -- now do authors |
| + | control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal); |
| | | |
− | if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}}
| + | last_first_list = list_people(control, a, author_etal); |
− | 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 | + | if is_set (Authors) then |
− | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message | + | Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. |
− | SeriesNumber = ''; -- unset; prefer |season= over |seriesno= | + | 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 |
− | -- assemble a table of parts concatenated later into Series
| + | end -- end of do |
− | 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
| + | if is_set (Authors) and is_set (Collaboration) then |
− | ScriptChapter = ScriptTitle;
| + | Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. |
− | ChapterLink = TitleLink; -- alias episodelink
| + | end |
− | 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 = '';
| |
− |
| |
− | else -- now oddities that are cite serial
| |
− | Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial
| |
− | Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday?
| |
− | if is_set (Series) and is_set (SeriesLink) then
| |
− | Series = '[[' .. SeriesLink .. '|' .. Series .. ']]';
| |
− | end
| |
− | Series = wrap_style ('italic-title', Series); -- series is italicized
| |
− | end
| |
| end | | end |
− | -- end of {{cite episode}} stuff
| |
| | | |
− | -- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. | + | -- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation, |
− | if 'arxiv' == config.CitationClass then
| + | -- an error message if the associated url is not set, or an empty string for concatenation |
− | if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv
| + | ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); |
− | table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message
| + | ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); |
− | elseif is_set (Series) then -- series is an alias of version
| + | Format = style_format (Format, URL, 'format', 'url'); |
− | ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier
| + | LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); |
− | Series = ''; -- unset
| + | TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); |
− | deprecated_parameter ('version'); -- deprecated parameter but only for cite arxiv
| |
− | end
| |
− |
| |
− | if first_set ({AccessDate, At, Chapter, Format, Page, Pages, Periodical, PublisherName, URL, -- a crude list of parameters that are not supported by cite arxiv
| |
− | 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
| |
| | | |
− | AccessDate= ''; -- set these to empty string; not supported in cite arXiv
| + | -- special case for chapter format so no error message or cat when chapter not supported |
− | PublisherName = ''; -- (if the article has been published, use cite journal, or other)
| + | if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or |
− | Chapter = '';
| + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then |
− | URL = '';
| + | ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); |
− | Format = '';
| |
− | Page = ''; Pages = ''; At = '';
| |
− | end | |
− | Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string
| |
| end | | end |
| | | |
− | -- handle type parameter for those CS1 citations that have default values
| + | if not is_set(URL) then |
− | if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then
| + | if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- |url= required for cite web, cite podcast, and cite mailinglist |
− | TitleType = set_titletype (config.CitationClass, TitleType); | + | table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); |
− | if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis | + | end |
− | TitleType = Degree .. " thesis"; | + | |
| + | -- do we have |accessdate= without either |url= or |chapter-url=? |
| + | if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when URL is not set; |
| + | table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
| + | AccessDate = ''; |
| end | | end |
| end | | end |
| | | |
− | if is_set(TitleType) then -- if type parameter is specified | + | local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; |
− | TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses
| + | DeadURL = DeadURL:lower(); -- used later when assembling archived text |
| + | if is_set( ArchiveURL ) then |
| + | if is_set (ChapterURL) then -- if chapter-url is set apply archive url to it |
| + | OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text |
| + | OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages |
| + | OriginalFormat = ChapterFormat; -- and original |chapter-format= |
| + | if 'no' ~= DeadURL then |
| + | ChapterURL = ArchiveURL -- swap-in the archive's url |
| + | ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages |
| + | ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
| + | ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls |
| + | end |
| + | elseif is_set (URL) then |
| + | OriginalURL = URL; -- save copy of original source URL |
| + | OriginalURLorigin = URLorigin; -- name of url parameter for error messages |
| + | OriginalFormat = Format; -- and original |format= |
| + | OriginalAccess = UrlAccess; |
| + | if 'no' ~= DeadURL then -- if URL set then archive-url applies to it |
| + | URL = ArchiveURL -- swap-in the archive's url |
| + | URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages |
| + | Format = ArchiveFormat or ''; -- swap in archive's format |
| + | UrlAccess = nil; -- restricted access levels do not make sense for archived urls |
| + | end |
| + | end |
| end | | end |
| | | |
− | -- 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. | + | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or -- if any of the 'periodical' cites except encyclopedia |
− | if not is_set (Date) then
| + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then |
− | Date = Year; -- promote Year to Date
| + | local chap_param; |
− | Year = nil; -- make nil so Year as empty string isn't used for CITEREF | + | if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters |
− | if not is_set (Date) and is_set(PublicationDate) then -- use PublicationDate when |date= and |year= are not set | + | chap_param = A:ORIGIN ('Chapter') |
− | Date = PublicationDate; -- promote PublicationDate to Date | + | elseif is_set (TransChapter) then |
− | PublicationDate = ''; -- unset, no longer needed | + | 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, ChapterUrlAccess); -- Contribution is also in Chapter |
| + | if is_set (Chapter) then |
| + | Chapter = Chapter .. ChapterFormat ; |
| + | if 'map' == config.CitationClass and is_set (TitleType) then |
| + | Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title |
| + | end |
| + | Chapter = Chapter.. 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 |
| end | | end |
| | | |
− | if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation | + | -- Format main title. |
| + | if is_set (ArchiveURL) and mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation['archived_copy']) then -- if title is 'Archived copy' (place holder added by bots that can't find proper title) |
| + | add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title |
| + | end |
| | | |
− | --[[
| + | if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup: |
− | Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where
| + | Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup |
− | we get the date used in the metadata.
| + | else |
− | | + | if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title= |
− | Date validation supporting code is in Module:Citation/CS1/Date_validation
| + | Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three |
− | ]]
| + | elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ... |
− | do -- create defined block to contain local variables error_message and mismatch
| + | not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.) |
− | local error_message = ''; | + | Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters |
− | -- AirDate has been promoted to Date so not necessary to check it
| + | end |
− | anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, | + | end |
− | ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date); | + | |
− | | + | if is_set(TitleLink) and is_set(Title) then |
− | if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; | + | Title = make_wikilink (TitleLink, Title); |
− | 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
| |
− | | |
− | 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 |
| | | |
− | -- At this point fields may be nil if they weren't specified in the template use. We can use that fact.
| + | if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or |
− | -- Test if citation has no title
| + | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or |
− | if not is_set(Title) and
| + | ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article |
− | not is_set(TransTitle) and
| + | Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks |
− | not is_set(ScriptTitle) then | + | Title = wrap_style ('quoted-title', Title); |
− | if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? | + | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
− | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } );
| + | TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
− | else
| + | elseif 'report' == config.CitationClass then -- no styling for cite report |
− | table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } );
| + | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
− | end
| + | 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 |
| + | |
| + | local TransError = ""; |
| + | if is_set(TransTitle) then |
| + | if is_set(Title) then |
| + | TransTitle = " " .. TransTitle; |
| + | else |
| + | TransError = " " .. set_error( 'trans_missing_title', {'title'} ); |
| + | end |
| 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 | + | if is_set(Title) then |
− | Title = ''; -- set title to empty string | + | if not is_set(TitleLink) and is_set(URL) then |
− | add_maint_cat ('untitled'); | + | |
| + | Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format; |
| + | URL = ''; -- unset these because no longer needed |
| + | Format = ""; |
| + | else |
| + | Title = Title .. TransTitle .. TransError; |
| + | end |
| + | else |
| + | Title = TransTitle .. TransError; |
| end | | end |
| | | |
− | check_for_url ({ -- add error message when any of these parameters contains a URL | + | if is_set(Place) then |
− | ['title']=Title, | + | Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; |
− | [A:ORIGIN('Chapter')]=Chapter,
| + | end |
− | [A:ORIGIN('Periodical')]=Periodical,
| |
− | [A:ORIGIN('PublisherName')] = PublisherName,
| |
− | });
| |
| | | |
− | -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information.
| + | if is_set (Conference) then |
− | -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that
| + | if is_set (ConferenceURL) then |
− | -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title
| + | Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil ); |
− | -- 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 |
| + | Conference = sepc .. " " .. Conference .. ConferenceFormat; |
| + | elseif is_set(ConferenceURL) then |
| + | Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin, nil ); |
| 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
| |
| | | |
− | -- this is the function call to COinS() | + | if not is_set(Position) then |
− | local OCinSoutput = COinS({
| + | local Minutes = A['Minutes']; |
− | ['Periodical'] = Periodical,
| + | local Time = A['Time']; |
− | ['Encyclopedia'] = Encyclopedia, | + | |
− | ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup | + | if is_set(Minutes) then |
− | ['Map'] = Map,
| + | if is_set (Time) then |
− | ['Degree'] = Degree; -- cite thesis only
| + | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } ); |
− | ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup
| + | end |
− | ['PublicationPlace'] = PublicationPlace,
| + | Position = " " .. Minutes .. " " .. cfg.messages['minutes']; |
− | ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid;
| + | else |
− | ['Season'] = COinS_date.rftssn,
| + | if is_set(Time) then |
− | ['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?
| + | local TimeCaption = A['TimeCaption'] |
− | ['Series'] = Series,
| + | if not is_set(TimeCaption) then |
− | ['Volume'] = Volume,
| + | TimeCaption = cfg.messages['event']; |
− | ['Issue'] = Issue, | + | if sepc ~= '.' then |
− | ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links
| + | TimeCaption = TimeCaption:lower(); |
− | ['Edition'] = Edition,
| + | end |
− | ['PublisherName'] = PublisherName,
| + | end |
− | ['URL'] = first_set ({ChapterURL, URL}, 2),
| + | Position = " " .. TimeCaption .. " " .. Time; |
− | ['Authors'] = coins_author, | + | end |
− | ['ID_list'] = ID_list, | + | end |
− | ['RawPage'] = this_page.prefixedText, | + | else |
− | }, config.CitationClass); | + | Position = " " .. Position; |
| + | At = ''; |
| + | end |
| | | |
− | -- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data.
| + | Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); |
− | 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 | + | At = is_set(At) and (sepc .. " " .. At) or ""; |
− | end
| + | 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 |
| | | |
− | -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text
| + | if is_set( Sections ) then |
− | if 'newsgroup' == config.CitationClass then
| + | Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); |
− | if is_set (PublisherName) then | + | elseif is_set( Section ) then |
− | PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') )); | + | 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; |
| + | --[[ TODO: need to extract the wrap_msg from language_parameter |
| + | so that we can solve parentheses bunching problem with Format/Language/TitleType |
| + | ]] |
| end | | end |
| | | |
| + | Others = is_set(Others) and (sepc .. " " .. Others) or ""; |
| + | |
| + | if is_set (Translators) then |
| + | Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc); |
| + | end |
| + | if is_set (Interviewers) then |
| + | Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc); |
| + | end |
| + | |
| + | TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; |
| + | if is_set (Edition) then |
| + | if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then |
| + | add_maint_cat ('extra_text', 'edition'); |
| + | end |
| + | Edition = " " .. wrap_msg ('edition', Edition); |
| + | else |
| + | Edition = ''; |
| + | end |
| + | |
| + | Series = is_set(Series) and (sepc .. " " .. Series) or ""; |
| + | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; -- TODO: presentation |
| | | |
| + | Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; |
| | | |
− | -- Now perform various field substitutions. | + | Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
− | -- We also add leading spaces and surrounding markup and punctuation to the
| |
− | -- various parts of the citation, but only when they are non-nil.
| |
− | local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list
| |
− | do
| |
− | local last_first_list;
| |
− | local maximum;
| |
− | local control = {
| |
− | format = NameListFormat, -- empty string or 'vanc'
| |
− | maximum = nil, -- as if display-authors or display-editors not set
| |
− | lastauthoramp = LastAuthorAmp,
| |
− | page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn
| |
− | };
| |
− | | |
− | do -- do editor name list first because coauthors can modify control table
| |
− | maximum , editor_etal = get_display_authors_editors (A['DisplayEditors'], #e, 'editors', editor_etal);
| |
− | -- Preserve old-style implicit et al.
| |
− | if not is_set(maximum) and #e == 4 then
| |
− | maximum = 3;
| |
− | table.insert( z.message_tail, { set_error('implict_etal_editor', {}, true) } );
| |
− | end
| |
− | | |
− | control.maximum = maximum;
| |
− |
| |
− | last_first_list, EditorCount = list_people(control, e, editor_etal, 'editor');
| |
| | | |
− | if is_set (Editors) then
| + | ------------------------------------ totally unrelated data |
− | if editor_etal then
| + | if is_set(Via) then |
− | Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal
| + | Via = " " .. wrap_msg ('via', Via); |
− | EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation
| + | end |
− | 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
| + | Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link |
− | end
| + | note is displayed. There are no error messages for this condition. |
− | end
| + | |
− | do -- now do translators
| + | ]] |
− | control.maximum = #t; -- number of translators
| + | if is_set (SubscriptionRequired) then |
− | Translators = list_people(control, t, false, 'translator'); -- et al not currently supported
| + | SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message |
− | end
| + | elseif is_set (RegistrationRequired) then |
− | do -- now do contributors | + | SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message |
− | control.maximum = #c; -- number of contributors
| + | else |
− | Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported
| + | SubscriptionRequired = ''; -- either or both might be set to something other than yes true y |
− | end
| + | 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.
| + | if is_set(AccessDate) then |
− | control.lastauthoramp = nil;
| + | local retrv_text = " " .. cfg.messages['retrieved'] |
− | control.maximum = #a + 1;
| |
− | end
| |
− |
| |
− | last_first_list = list_people(control, a, author_etal, 'author');
| |
| | | |
− | if is_set (Authors) then
| + | AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
− | Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al.
| + | if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case |
− | if author_etal then
| + | AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text |
− | 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 | + | AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
− | table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message
| + | end |
− | end
| + | |
| + | if is_set(ID) then ID = sepc .." ".. ID; end |
| + | if "thesis" == config.CitationClass and is_set(Docket) then |
| + | ID = sepc .." Docket ".. Docket .. ID; |
| + | end |
| + | 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 |
| | | |
− | -- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation,
| + | ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); |
− | -- an error message if the associated url is not set, or an empty string for concatenation
| |
− | ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); | |
− | ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url');
| |
− | Format = style_format (Format, URL, 'format', 'url');
| |
− | LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url');
| |
− | TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl');
| |
| | | |
− | -- special case for chapter format so no error message or cat when chapter not supported
| + | if is_set(URL) then |
− | if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or | + | URL = " " .. external_link( URL, nil, URLorigin, UrlAccess ); |
− | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then | |
− | ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url');
| |
| end | | end |
| | | |
− | if not is_set(URL) then --and | + | if is_set(Quote) then |
− | if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty | + | if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks |
− | table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); | + | Quote = Quote:sub(2,-2); -- strip them off |
| end | | end |
− | | + | Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags |
− | -- Test if accessdate is given without giving a URL | + | PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set |
− | 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?
| + | end |
− | table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); | + | |
− | AccessDate = '';
| + | local Archived |
| + | if is_set(ArchiveURL) then |
| + | if not is_set(ArchiveDate) then |
| + | ArchiveDate = set_error('archive_missing_date'); |
| end | | end |
− | end
| + | if "no" == DeadURL then |
− | | + | local arch_text = cfg.messages['archived']; |
− | local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set?
| + | if sepc ~= "." then arch_text = arch_text:lower() end |
− | DeadURL = DeadURL:lower(); -- used later when assembling archived text
| + | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], |
− | if is_set( ArchiveURL ) then
| + | { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } ); |
− | if is_set (URL) then
| + | if not is_set(OriginalURL) then |
− | OriginalURL = URL; -- save copy of original source URL | + | Archived = Archived .. " " .. set_error('archive_missing_url'); |
− | OriginalURLorigin = URLorigin; -- name of url parameter for error messages
| |
− | OriginalFormat = Format; -- and original |format=
| |
− | if 'no' ~= DeadURL then -- if URL set then archive-url applies to it | |
− | URL = ArchiveURL -- swap-in the archive's url
| |
− | URLorigin = A:ORIGIN('ArchiveURL') -- name of archive url parameter for error messages | |
− | Format = ArchiveFormat or ''; -- swap in archive's format
| |
− | end | |
− | elseif is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it
| |
− | OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text
| |
− | OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages
| |
− | OriginalFormat = ChapterFormat; -- and original |format=
| |
− | if 'no' ~= DeadURL then
| |
− | ChapterURL = ArchiveURL -- swap-in the archive's url
| |
− | ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages | |
− | ChapterFormat = ArchiveFormat or ''; -- swap in archive's format
| |
| end | | 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', 'bot: unknown'}) then |
| + | Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled |
| + | if 'bot: unknown' == DeadURL then |
| + | add_maint_cat ('bot:_unknown'); -- and add a category if not already added |
| + | else |
| + | add_maint_cat ('unfit'); -- and add a category if not already added |
| + | end |
| + | else -- DeadURL is empty, 'yes', 'true', or 'y' |
| + | Archived = sepc .. " " .. substitute( arch_text, |
| + | { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. 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 | | end |
| + | if sepc == '.' then |
| + | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate |
| + | else |
| + | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. 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 | | end |
| | | |
− | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia | + | if is_set(Transcript) then |
− | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then
| + | if is_set(TranscriptURL) then |
− | local chap_param;
| + | Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin, nil ); |
− | if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters
| + | end |
− | chap_param = A:ORIGIN ('Chapter')
| + | Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
− | elseif is_set (TransChapter) then | + | elseif is_set(TranscriptURL) then |
− | chap_param = A:ORIGIN ('TransChapter')
| + | Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin, nil ); |
− | elseif is_set (ChapterURL) then
| + | end |
− | 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
| + | local Publisher; |
− | table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message
| + | if is_set(PublicationDate) then |
− | Chapter = ''; -- and set them to empty string to be safe with concatenation
| + | PublicationDate = wrap_msg ('published', PublicationDate); |
− | 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 | | end |
− | | + | if is_set(PublisherName) then |
− | -- Format main title.
| + | if is_set(PublicationPlace) then |
− | if is_set(TitleLink) and is_set(Title) then | + | Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
− | Title = "[[" .. TitleLink .. "|" .. Title .. "]]"
| + | else |
| + | Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
| + | end |
| + | elseif is_set(PublicationPlace) then |
| + | Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
| + | else |
| + | Publisher = PublicationDate; |
| end | | 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
| + | -- Several of the above rely upon detecting this as nil, so do it last. |
− | TransTitle= wrap_style ('trans-quoted-title', TransTitle );
| + | if is_set(Periodical) then |
− | elseif 'report' == config.CitationClass then -- no styling for cite report
| + | if is_set(Title) or is_set(TitleNote) then |
− | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped | + | Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical) |
− | TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title
| + | else |
− | else
| + | Periodical = wrap_style ('italic-title', Periodical) |
− | Title = wrap_style ('italic-title', Title);
| + | end |
− | 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 | | end |
| | | |
− | TransError = ""; | + | --[[ |
− | if is_set(TransTitle) then
| + | Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that |
− | if is_set(Title) then
| + | the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). |
− | TransTitle = " " .. TransTitle;
| + | ]] |
− | else
| + | if "speech" == config.CitationClass then -- cite speech only |
− | TransError = " " .. set_error( 'trans_missing_title', {'title'} ); | + | TitleNote = " (Speech)"; -- annotate the citation |
| + | if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter |
| + | if is_set (Conference) then -- and if |event= is set |
| + | Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering |
| + | end |
| end | | end |
| end | | end |
| + | |
| + | -- Piece all bits together at last. Here, all should be non-nil. |
| + | -- We build things this way because it is more efficient in LUA |
| + | -- not to keep reassigning to the same string variable over and over. |
| + | |
| + | local tcommon; |
| + | local tcommon2; -- used for book cite when |contributor= is set |
| | | |
− | Title = Title .. TransTitle; | + | if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
− |
| + | if is_set(Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here? |
− | if is_set(Title) then | + | tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); |
− | if not is_set(TitleLink) and is_set(URL) then | + | elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites |
− | Title = external_link( URL, Title, URLorigin ) .. TransError .. Format; | + | if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc |
− | URL = ""; | + | tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2 |
− | Format = "";
| + | tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); |
| else | | else |
− | Title = Title .. TransError; | + | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); |
| end | | end |
− | end
| |
| | | |
− | if is_set(Place) then | + | elseif 'map' == config.CitationClass then -- special cases for cite map |
− | Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " ";
| + | if is_set (Chapter) then -- map in a book; TitleType is part of Chapter |
− | end
| + | tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); |
− | | + | elseif is_set (Periodical) then -- map in a periodical |
− | if is_set (Conference) then
| + | tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); |
− | if is_set (ConferenceURL) then
| + | else -- a sheet or stand-alone map |
− | Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin ); | + | tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc ); |
| end | | end |
− | Conference = sepc .. " " .. Conference .. ConferenceFormat; | + | |
− | elseif is_set(ConferenceURL) then | + | elseif 'episode' == config.CitationClass then -- special case for cite episode |
− | Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin ); | + | tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc ); |
| + | |
| + | else -- all other CS1 templates |
| + | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, |
| + | Volume, Others, Edition, Publisher, Agency}, sepc ); |
| + | end |
| + | |
| + | if #ID_list > 0 then |
| + | ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); |
| + | else |
| + | ID_list = ID; |
| end | | end |
| + | |
| + | local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); |
| + | local text; |
| + | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
| | | |
− | if not is_set(Position) then | + | if is_set(Date) then |
− | local Minutes = A['Minutes'];
| + | if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set |
− | local Time = A['Time'];
| + | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses |
− | | + | else -- neither of authors and editors set |
− | if is_set(Minutes) then | + | if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc |
− | if is_set (Time) then
| + | Date = " " .. Date .. OrigYear; -- Date does not begin with sepc |
− | table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } );
| + | else |
| + | Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc |
| end | | end |
− | Position = " " .. Minutes .. " " .. cfg.messages['minutes']; | + | end |
− | else | + | end |
− | if is_set(Time) then
| + | if is_set(Authors) then |
− | local TimeCaption = A['TimeCaption']
| + | if (not is_set (Date)) then -- when date is set it's in parentheses; no Authors termination |
− | if not is_set(TimeCaption) then
| + | Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space |
− | TimeCaption = cfg.messages['event'];
| + | end |
− | if sepc ~= '.' then
| + | if is_set(Editors) then |
− | TimeCaption = TimeCaption:lower();
| + | local in_text = " "; |
− | end | + | local post_text = ""; |
| + | if is_set(Chapter) and 0 == #c then |
| + | in_text = in_text .. cfg.messages['in'] .. " " |
| + | if (sepc ~= '.') then |
| + | in_text = in_text:lower() -- lowercase for cs2 |
| + | end |
| + | else |
| + | if EditorCount <= 1 then |
| + | post_text = ", " .. cfg.messages['editor']; |
| + | else |
| + | post_text = ", " .. cfg.messages['editors']; |
| end | | end |
− | Position = " " .. TimeCaption .. " " .. Time;
| + | end |
− | end
| + | Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
| end | | end |
− | else
| + | if is_set (Contributors) then -- book cite and we're citing the intro, preface, etc |
− | Position = " " .. Position; | + | local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; |
− | At = '';
| + | if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 |
− | end
| + | Authors = by_text .. Authors; -- author follows title so tweak it here |
− | | + | if is_set (Editors) and is_set (Date) then -- when Editors make sure that Authors gets terminated |
− | Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase);
| + | Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space |
− | | + | end |
− | At = is_set(At) and (sepc .. " " .. At) or "";
| + | if (not is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination |
− | Position = is_set(Position) and (sepc .. " " .. Position) or "";
| + | Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space |
− | if config.CitationClass == 'map' then
| + | end |
− | local Section = A['Section'];
| + | text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); |
− | local Sections = A['Sections'];
| + | else |
− | local Inset = A['Inset'];
| + | text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); |
− |
| |
− | if is_set( Inset ) then
| |
− | Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase);
| |
− | end
| |
− | | |
− | if is_set( Sections ) then
| |
− | Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); | |
− | elseif is_set( Section ) then | |
− | Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); | |
| end | | end |
− | At = At .. Inset .. Section; | + | elseif is_set(Editors) then |
− | end
| + | if is_set(Date) then |
− | | + | if EditorCount <= 1 then |
− | if is_set (Language) then
| + | Editors = Editors .. ", " .. cfg.messages['editor']; |
− | Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc | + | 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 | | else |
− | Language=""; -- language not specified so make sure this is an empty string; | + | if in_array(config.CitationClass, {"journal","citation"}) 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 | | 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 ); |
| | | |
− | Others = is_set(Others) and (sepc .. " " .. Others) or ""; | + | -- Now enclose the whole thing in a <cite/> element |
| + | local options = {}; |
| | | |
− | if is_set (Translators) then | + | if is_set(config.CitationClass) and config.CitationClass ~= "citation" then |
− | Others = sepc .. ' Translated by ' .. Translators .. Others; | + | options.class = config.CitationClass; |
| + | options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref= |
| + | else |
| + | options.class = "citation"; |
| end | | end |
− | | + | |
− | TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; | + | if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate |
− | if is_set (Edition) then
| + | local id = Ref |
− | if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') then
| + | if ('harv' == Ref ) then |
− | add_maint_cat ('extra_text', 'edition'); | + | local namelist = {}; -- holds selected contributor, author, editor name list |
| + | 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 |
| + | if #namelist > 0 then -- if there are names in namelist |
| + | id = anchor_id (namelist, year); -- go make the CITEREF anchor |
| + | else |
| + | id = ''; -- unset |
| + | end |
| end | | end |
− | Edition = " " .. wrap_msg ('edition', Edition); | + | options.id = id; |
− | else
| + | end |
− | Edition = ''; | + | |
| + | if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>","")) <= 2 then -- remove <span> tags and other html-like markup; then get length of what remains |
| + | z.error_categories = {}; |
| + | text = set_error('empty_citation'); |
| + | z.message_tail = {}; |
| end | | end |
| + | |
| + | local render = {}; -- here we collect the final bits for concatenation into the rendered citation |
| | | |
− | Series = is_set(Series) and (sepc .. " " .. Series) or ""; | + | if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags |
− | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or "";
| + | table.insert (render, substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set |
− | Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; | + | else |
| + | table.insert (render, substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases |
| + | end |
| | | |
− | Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); | + | table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation |
| | | |
− | ------------------------------------ totally unrelated data | + | if #z.message_tail ~= 0 then |
− | if is_set(Via) then | + | table.insert (render, ' '); |
− | Via = " " .. wrap_msg ('via', Via); | + | for i,v in ipairs( z.message_tail ) do |
| + | if is_set(v[1]) then |
| + | if i == #z.message_tail then |
| + | table.insert (render, error_comment( v[1], v[2] )); |
| + | else |
| + | table.insert (render, error_comment( v[1] .. "; ", v[2] )); |
| + | end |
| + | end |
| + | end |
| + | end |
| + | |
| + | if #z.maintenance_cats ~= 0 then |
| + | table.insert (render, '<span class="citation-comment" style="display:none; color:#33aa33; margin-left:0.3em">'); |
| + | for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
| + | table.insert (render, v); |
| + | table.insert (render, ' ('); |
| + | table.insert (render, make_wikilink (':Category:' .. v, 'link')); |
| + | table.insert (render, ') '); |
| + | end |
| + | table.insert (render, '</span>'); |
| + | 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 |
| + | table.insert (render, make_wikilink ('Category:' .. v)); |
| + | end |
| + | for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
| + | table.insert (render, make_wikilink ('Category:' .. v)); |
| + | end |
| + | for _, v in ipairs( z.properties_cats ) do -- append properties categories |
| + | table.insert (render, make_wikilink ('Category:' .. v)); |
| + | end |
| end | | end |
| | | |
− | --[[
| + | return table.concat (render); |
− | Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link
| + | end |
− | note is displayed. There are no error messages for this condition.
| |
| | | |
− | ]]
| |
− | if is_set (SubscriptionRequired) then
| |
− | SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message
| |
− | elseif is_set (RegistrationRequired) then
| |
− | SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message
| |
− | else
| |
− | SubscriptionRequired = ''; -- either or both might be set to something other than yes true y
| |
− | end
| |
| | | |
− | if is_set(AccessDate) then
| + | --[[--------------------------< V A L I D A T E >-------------------------------------------------------------- |
− | local retrv_text = " " .. cfg.messages['retrieved']
| |
| | | |
− | AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format
| + | Looks for a parameter's name in one of several whitelists. |
− | if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case
| + | |
− | AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text
| + | Parameters in the whitelist can have three values: |
− | -- neither of these work; don't know why; it seems that substitute() isn't being called
| + | true - active, supported parameters |
− | AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates
| + | false - deprecated, supported parameters |
− | end | + | nil - unsupported parameters |
| + | |
| + | ]] |
| + | |
| + | local function validate (name, cite_class) |
| + | local name = tostring (name); |
| + | local state; |
| | | |
− | if is_set(ID) then ID = sepc .." ".. ID; end | + | if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- limited parameter sets allowed for these templates |
− | if "thesis" == config.CitationClass and is_set(Docket) then
| + | state = whitelist.limited_basic_arguments[name]; |
− | ID = sepc .." Docket ".. Docket .. ID;
| + | if true == state then return true; end -- valid actively supported parameter |
− | end
| + | if false == state then |
− | if "report" == config.CitationClass and is_set(Docket) then -- for cite report when |docket= is set
| + | deprecated_parameter (name); -- parameter is deprecated but still supported |
− | ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set | + | return true; |
− | end
| + | end |
| + | |
| + | state = whitelist[cite_class .. '_basic_arguments'][name]; -- look in the parameter-list for the template identified by cite_class |
| | | |
− | ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} );
| + | if true == state then return true; end -- valid actively supported parameter |
| + | if false == state then |
| + | deprecated_parameter (name); -- parameter is deprecated but still supported |
| + | return true; |
| + | end |
| + | -- limited enumerated parameters list |
| + | name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) |
| + | state = whitelist.limited_numbered_arguments[name]; |
| + | if true == state then return true; end -- valid actively supported parameter |
| + | if false == state then |
| + | deprecated_parameter (name); -- parameter is deprecated but still supported |
| + | return true; |
| + | end |
| | | |
− | if is_set(URL) then | + | return false; -- not supported because not found or name is set to nil |
− | URL = " " .. external_link( URL, nil, URLorigin ); | + | end -- end limited parameter-set templates |
| + | |
| + | state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed |
| + | |
| + | if true == state then return true; end -- valid actively supported parameter |
| + | if false == state then |
| + | deprecated_parameter (name); -- parameter is deprecated but still supported |
| + | return true; |
| end | | end |
| + | -- all enumerated parameters allowed |
| + | name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) |
| + | state = whitelist.numbered_arguments[name]; |
| | | |
− | if is_set(Quote) then | + | if true == state then return true; end -- valid actively supported parameter |
− | if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks
| + | if false == state then |
− | Quote = Quote:sub(2,-2); -- strip them off
| + | deprecated_parameter (name); -- parameter is deprecated but still supported |
− | end
| + | return true; |
− | 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 | | end |
| | | |
− | local Archived | + | return false; -- not supported because not found or name is set to nil |
− | if is_set(ArchiveURL) then
| + | end |
− | if not is_set(ArchiveDate) then
| + | |
− | ArchiveDate = set_error('archive_missing_date');
| + | |
− | end
| + | --[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ |
− | if "no" == DeadURL then
| + | |
− | local arch_text = cfg.messages['archived'];
| + | Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal |
− | if sepc ~= "." then arch_text = arch_text:lower() end
| + | sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a |
− | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'],
| + | parameter that is missing its pipe: |
− | { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } );
| + | {{cite ... |title=Title access-date=2016-03-17}} |
− | if not is_set(OriginalURL) then
| + | |
− | Archived = Archived .. " " .. set_error('archive_missing_url');
| + | cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html |
− | end
| + | tags are removed before the search. |
− | elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped'
| + | |
− | local arch_text = cfg.messages['archived-dead'];
| + | If a missing pipe is detected, this function adds the missing pipe maintenance category. |
− | 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'
| + | local function missing_pipe_check (value) |
− | Archived = sepc .. " " .. substitute( arch_text,
| + | local capture; |
− | { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled
| + | value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc |
− | end
| + | |
− | else
| + | capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes |
− | local arch_text = cfg.messages['archived-missing'];
| + | if capture and validate (capture) then -- if the capture is a valid parameter name |
− | if sepc ~= "." then arch_text = arch_text:lower() end
| + | add_maint_cat ('missing_pipe'); |
− | Archived = sepc .. " " .. substitute( arch_text,
| + | end |
− | { set_error('archive_missing_url'), ArchiveDate } );
| + | end |
− | end
| + | |
− | elseif is_set (ArchiveFormat) then
| + | |
− | Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message
| + | --[[--------------------------< C S 1 . C I T A T I O N >------------------------------------------------------ |
− | else | + | |
− | Archived = ""
| + | This is used by templates such as {{cite book}} to create the actual citation text. |
− | end | + | |
| + | ]] |
| + | |
| + | function cs1.citation(frame) |
| + | Frame = frame; -- save a copy incase we need to display an error message in preview mode |
| + | local pframe = frame:getParent() |
| + | local validation, utilities, identifiers, metadata, styles; |
| | | |
− | local Lay = ''; | + | if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
− | if is_set(LayURL) then
| + | cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules |
− | if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end | + | whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); |
− | if is_set(LaySource) then | + | utilities = require ('Module:Citation/CS1/Utilities/sandbox'); |
− | LaySource = " – ''" .. safe_for_italics(LaySource) .. "''";
| + | validation = require ('Module:Citation/CS1/Date_validation/sandbox'); |
− | else | + | identifiers = require ('Module:Citation/CS1/Identifiers/sandbox'); |
− | LaySource = "";
| + | metadata = require ('Module:Citation/CS1/COinS/sandbox'); |
− | end | + | styles = 'Module:Citation/CS1/sandbox/styles.css'; |
− | if sepc == '.' then | + | |
− | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
| + | else -- otherwise |
− | else | + | cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules |
− | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate
| + | whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); |
− | end | + | utilities = require ('Module:Citation/CS1/Utilities'); |
− | elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url=
| + | validation = require ('Module:Citation/CS1/Date_validation'); |
− | Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message | + | identifiers = require ('Module:Citation/CS1/Identifiers'); |
| + | metadata = require ('Module:Citation/CS1/COinS'); |
| + | styles = 'Module:Citation/CS1/styles.css'; |
| + | |
| end | | end |
| | | |
− | if is_set(Transcript) then | + | utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables |
− | if is_set(TranscriptURL) then
| + | identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module |
− | Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin );
| + | validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module |
− | end
| + | metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module |
− | Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat;
| + | |
− | elseif is_set(TranscriptURL) then | + | dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation |
− | Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin );
| + | year_date_check = validation.year_date_check; |
− | end | + | reformat_dates = validation.reformat_dates; |
| + | date_hyphen_to_dash = validation.date_hyphen_to_dash; |
| + | date_name_xlate = validation.date_name_xlate; |
| + | |
| + | is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities |
| + | in_array = utilities.in_array; |
| + | substitute = utilities.substitute; |
| + | error_comment = utilities.error_comment; |
| + | set_error = utilities.set_error; |
| + | select_one = utilities.select_one; |
| + | add_maint_cat = utilities.add_maint_cat; |
| + | wrap_style = utilities.wrap_style; |
| + | safe_for_italics = utilities.safe_for_italics; |
| + | is_wikilink = utilities.is_wikilink; |
| + | make_wikilink = utilities.make_wikilink; |
| + | |
| + | z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities |
| | | |
− | local Publisher; | + | extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers |
− | if is_set(Periodical) and
| + | build_id_list = identifiers.build_id_list; |
− | not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then
| + | is_embargoed = identifiers.is_embargoed; |
− | if is_set(PublisherName) then
| + | extract_id_access_levels = identifiers.extract_id_access_levels; |
− | 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_msg ('published', PublicationDate);
| |
− | else
| |
− | Publisher = PublicationDate;
| |
− | end
| |
− | end
| |
− | if is_set(Publisher) then
| |
− | Publisher = " (" .. Publisher .. ")";
| |
− | end
| |
− | else | |
− | if is_set(PublicationDate) then
| |
− | PublicationDate = " (" .. wrap_msg ('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. | + | make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS |
− | if is_set(Periodical) then | + | get_coins_pages = metadata.get_coins_pages; |
− | if is_set(Title) or is_set(TitleNote) then
| + | COinS = metadata.COinS; |
− | Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical)
| + | |
− | else
| + | local args = {}; -- table where we store all of the template's arguments |
− | Periodical = wrap_style ('italic-title', Periodical)
| + | local suggestions = {}; -- table where we store suggestions if we need to loadData them |
− | end
| + | local error_text, error_state; |
− | end | |
| | | |
− | --[[ | + | local config = {}; -- table to store parameters from the module {{#invoke:}} |
− | Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that
| + | for k, v in pairs( frame.args ) do |
− | the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided).
| + | config[k] = v; |
− | ]] | + | -- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}} |
− | if "speech" == config.CitationClass then -- cite speech only
| + | end |
− | TitleNote = " (Speech)"; -- annotate the citation
| |
− | if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter
| |
− | if is_set (Conference) then -- and if |event= is set
| |
− | Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering
| |
− | end
| |
− | end
| |
− | end | |
| | | |
− | -- Piece all bits together at last. Here, all should be non-nil.
| + | local capture; -- the single supported capture when matching unknown parameters using patterns |
− | -- We build things this way because it is more efficient in LUA
| + | for k, v in pairs( pframe.args ) do |
− | -- not to keep reassigning to the same string variable over and over.
| + | if v ~= '' then |
− | | + | if ('string' == type (k)) then |
− | local tcommon;
| + | k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9 |
− | local tcommon2; -- used for book cite when |contributor= is set | |
− |
| |
− | if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then
| |
− | if is_set(Others) then Others = Others .. sepc .. " " end
| |
− | tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series,
| |
− | Language, Edition, Publisher, Agency, Volume}, sepc );
| |
− |
| |
− | elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites | |
− | if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc
| |
− | tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2
| |
− | tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
| |
− | else
| |
− | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc );
| |
− | end
| |
− | | |
− | elseif 'map' == config.CitationClass then -- special cases for cite map
| |
− | if is_set (Chapter) then -- map in a book; TitleType is part of Chapter
| |
− | tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
| |
− | elseif is_set (Periodical) then -- map in a periodical
| |
− | tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc );
| |
− | else -- a sheet or stand-alone map
| |
− | tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc );
| |
− | end
| |
− |
| |
− | elseif 'episode' == config.CitationClass then -- special case for cite episode
| |
− | tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Language, Edition, Publisher}, sepc );
| |
− | else -- all other CS1 templates
| |
− | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, | |
− | Volume, Others, Edition, Publisher, Agency}, sepc );
| |
− | end
| |
− |
| |
− | if #ID_list > 0 then
| |
− | ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc );
| |
− | else
| |
− | ID_list = ID;
| |
− | end
| |
− |
| |
− | local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc );
| |
− | local text;
| |
− | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At;
| |
− | | |
− | if is_set(Date) then
| |
− | if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set
| |
− | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses
| |
− | else -- neither of authors and editors set
| |
− | if (string.sub(tcommon,-1,-1) == sepc) then -- if the last character of tcommon is sepc
| |
− | Date = " " .. Date .. OrigYear; -- Date does not begin with sepc
| |
− | else
| |
− | Date = sepc .. " " .. Date .. OrigYear; -- Date begins with sepc
| |
− | end
| |
− | end
| |
− | end
| |
− | if is_set(Authors) then
| |
− | if is_set(Coauthors) then
| |
− | if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator
| |
− | Authors = Authors .. ', ' .. Coauthors;
| |
− | else | |
− | Authors = Authors .. '; ' .. Coauthors;
| |
− | end
| |
− | end
| |
− | if not is_set (Date) then -- when date is set it's in parentheses; no Authors termination
| |
− | Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space
| |
− | end
| |
− | if is_set(Editors) then
| |
− | local in_text = " ";
| |
− | local post_text = "";
| |
− | if is_set(Chapter) and 0 == #c then
| |
− | 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 not validate( k, config.CitationClass ) then |
− | 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
| |
− | | |
− | --[[--------------------------< 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)
| |
− | local pframe = frame:getParent()
| |
− | local validation;
| |
− |
| |
− | if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version?
| |
− | 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 capture; -- the single supported capture when matching unknown parameters using patterns
| |
− | for k, v in pairs( pframe.args ) do
| |
− | if v ~= '' then
| |
− | if not validate( k ) then
| |
| error_text = ""; | | error_text = ""; |
| if type( k ) ~= 'string' then | | if type( k ) ~= 'string' then |
Line 4,065: |
Line 3,570: |
| error_text, error_state = set_error( 'text_ignored', {v}, true ); | | error_text, error_state = set_error( 'text_ignored', {v}, true ); |
| end | | end |
− | elseif validate( k:lower() ) then | + | elseif validate( k:lower(), config.CitationClass ) then |
− | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); | + | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter |
| else | | else |
| if nil == suggestions.suggestions then -- if this table is nil then we need to load it | | if nil == suggestions.suggestions then -- if this table is nil then we need to load it |
Line 4,078: |
Line 3,583: |
| capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match | | 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 | | if capture then -- if the pattern matches |
− | param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator) | + | param = substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator) |
− | error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message | + | if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists) |
| + | error_text, error_state = set_error ('parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message |
| + | else |
| + | error_text, error_state = set_error( 'parameter_ignored', {param}, true ); -- suggested param not supported by this template |
| + | end |
| end | | end |
| end | | end |
Line 4,087: |
Line 3,596: |
| else | | else |
| error_text, error_state = set_error( 'parameter_ignored', {k}, true ); | | error_text, error_state = set_error( 'parameter_ignored', {k}, true ); |
| + | v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists) |
| end | | end |
| end | | end |
Line 4,094: |
Line 3,604: |
| end | | end |
| end | | end |
| + | missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe? |
| + | -- TODO: is this the best place for this translation? |
| args[k] = v; | | args[k] = v; |
− | elseif args[k] ~= nil or (k == 'postscript') then | + | elseif args[k] ~= nil or (k == 'postscript') then -- here when v is empty string |
− | args[k] = v; | + | args[k] = v; -- why do we do this? we don't support 'empty' parameters |
| end | | end |
| end | | end |
Line 4,105: |
Line 3,617: |
| end | | end |
| end | | end |
− | return citation0( config, args) | + | return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})}); |
| end | | end |
| | | |
− | return z | + | return cs1; |