Mosquitopang(留言墙 | 貢獻) 无编辑摘要 |
Mosquitopang(留言墙 | 貢獻) 无编辑摘要 |
||
第1行: | 第1行: | ||
+ | |||
+ | local z = { |
||
+ | 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 |
+ | 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 |
||
− | 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, |
||
− | strip_apostrophe_markup; |
||
+ | 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 >------------------------------------------------------------ |
||
第55行: | 第46行: | ||
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. |
||
+ | local function in_array( needle, haystack ) |
||
− | foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages |
||
+ | if needle == nil then |
||
− | may be categorized but multiples of the same language are not categorized. |
||
+ | return false; |
||
+ | end |
||
+ | for n,v in ipairs( haystack ) do |
||
+ | if v == needle then |
||
+ | return n; |
||
+ | end |
||
+ | end |
||
+ | return false; |
||
+ | end |
||
+ | --[[--------------------------< S U B S T I T U T E >---------------------------------------------------------- |
||
− | added_prop_cats is a table declared in page scope variables above |
||
+ | |||
+ | Populates numbered arguments in a message string using an argument table. |
||
]] |
]] |
||
+ | local function substitute( msg, args ) |
||
+ | return args and mw.message.newRawMessage( msg, args ):plain() or msg; |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< E R R O R _ C O M M E N T >---------------------------------------------------- |
||
+ | |||
+ | Wraps error messages with css markup according to the state of hidden. |
||
+ | |||
+ | ]] |
||
+ | local function error_comment( content, hidden ) |
||
+ | return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content ); |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< S E T _ E R R O R >-------------------------------------------------------------- |
||
+ | |||
+ | Sets an error condition and returns the appropriate error message. The actual placement of the error message in the output is |
||
+ | the responsibility of the calling function. |
||
+ | |||
+ | ]] |
||
+ | local function set_error( error_id, arguments, raw, prefix, suffix ) |
||
+ | local error_state = cfg.error_conditions[ error_id ]; |
||
+ | |||
+ | prefix = prefix or ""; |
||
+ | suffix = suffix or ""; |
||
+ | |||
+ | if error_state == nil then |
||
+ | error( cfg.messages['undefined_error'] ); |
||
+ | elseif is_set( error_state.category ) then |
||
+ | table.insert( z.error_categories, error_state.category ); |
||
+ | end |
||
+ | |||
+ | local message = substitute( error_state.message, arguments ); |
||
+ | |||
+ | message = message .. " ([[" .. cfg.messages['help page link'] .. |
||
+ | "#" .. error_state.anchor .. "|" .. |
||
+ | cfg.messages['help page label'] .. "]])"; |
||
+ | |||
+ | z.error_ids[ error_id ] = true; |
||
+ | if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } ) |
||
+ | and z.error_ids['citation_missing_title'] then |
||
+ | return '', false; |
||
+ | end |
||
+ | |||
+ | message = table.concat({ prefix, message, suffix }); |
||
+ | |||
+ | if raw == true then |
||
+ | return message, error_state.hidden; |
||
+ | end |
||
+ | |||
+ | return error_comment( message, error_state.hidden ); |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------ |
||
+ | |||
+ | Adds a category to z.maintenance_cats using names from the configuration file with additional text if any. |
||
+ | To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats |
||
+ | local function add_maint_cat (key, arguments) |
||
+ | if not added_maint_cats [key] then |
||
+ | added_maint_cats [key] = true; -- note that we've added this category |
||
+ | table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table |
||
+ | end |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- |
||
+ | |||
+ | Adds a category to z.properties_cats using names from the configuration file with additional text if any. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats |
||
local function add_prop_cat (key, arguments) |
local function add_prop_cat (key, arguments) |
||
if not added_prop_cats [key] then |
if not added_prop_cats [key] then |
||
added_prop_cats [key] = true; -- note that we've added this category |
added_prop_cats [key] = true; -- note that we've added this category |
||
+ | table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table |
||
− | key = key:gsub ('(foreign_lang_source_?2?)%a%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 |
||
end |
end |
||
− | |||
--[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- |
--[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- |
||
第80行: | 第155行: | ||
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist. |
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. |
To prevent duplication, added_vanc_errs is nil until an error message is emitted. |
||
− | |||
− | added_vanc_errs is a boolean declared in page scope variables above |
||
]] |
]] |
||
+ | local added_vanc_errs; -- flag so we only emit one Vancouver error / category |
||
− | local function add_vanc_error (source) |
||
+ | local function add_vanc_error () |
||
if not added_vanc_errs then |
if not added_vanc_errs then |
||
added_vanc_errs = true; -- note that we've added this category |
added_vanc_errs = true; -- note that we've added this category |
||
− | table.insert( z.message_tail, { set_error( 'vancouver', { |
+ | table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } ); |
end |
end |
||
end |
end |
||
第131行: | 第205行: | ||
There are several tests: |
There are several tests: |
||
the first character of the whole domain name including subdomains must be a letter or a digit |
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 |
||
− | internationalized domain name (ascii characters with .xn-- ASCII Compatible Encoding (ACE) prefix xn-- in the tld) see https://tools.ietf.org/html/rfc3490 |
||
− | single-letter/digit second-level domains in the .org, .cash, and .today TLDs |
||
q, x, and z SL domains in the .com TLD |
q, x, and z SL domains in the .com TLD |
||
i and q SL domains in the .net TLD |
i and q SL domains in the .net TLD |
||
第151行: | 第224行: | ||
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once |
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once |
||
− | if not domain:match ('^[% |
+ | if not domain:match ('^[%a%d]') then -- first character must be letter or digit |
return false; |
return false; |
||
end |
end |
||
+ | |||
− | |||
− | if domain:match (' |
+ | if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname |
+ | return true; |
||
+ | elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) |
||
+ | return true; |
||
+ | elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
||
+ | return true; |
||
+ | elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix |
||
+ | return true; |
||
+ | elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname |
||
+ | return true; |
||
+ | elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') 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; |
return false; |
||
end |
end |
||
− | |||
− | local patterns = { -- patterns that look like urls |
||
− | '%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld |
||
− | '%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix |
||
− | '%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10) |
||
− | '%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
||
− | '%f[%w][%w]%.%a%a$', -- one character hostname and cctld (2 chars) |
||
− | '%f[%w][%w][%w]%.%a%a+$', -- two character hostname and tld |
||
− | '^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address |
||
− | } |
||
− | |||
− | for _, pattern in ipairs (patterns) do -- loop through the patterns list |
||
− | if domain:match (pattern) then |
||
− | return true; -- if a match then we think that this thing that purports to be a url is a url |
||
− | end |
||
− | end |
||
− | |||
− | for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains |
||
− | if domain:match ('%f[%w][%w]%.' .. d) then |
||
− | return true |
||
− | end |
||
− | end |
||
− | return false; -- no matches, we don't know what this thing is |
||
end |
end |
||
第206行: | 第274行: | ||
Split a url into a scheme, authority indicator, and domain. |
Split a url into a scheme, authority indicator, and domain. |
||
− | |||
− | First remove Fully Qualified Domain Name terminator (a dot following tld) (if any) and any path(/), query(?) or fragment(#). |
||
− | |||
If protocol relative url, return nil scheme and domain else return nil for both scheme and domain. |
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 |
When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one |
||
− | or more '/' characters |
+ | or more '/' characters following the scheme's colon), make sure that there are only 2. |
− | |||
− | Strip off any port and path; |
||
]] |
]] |
||
第261行: | 第324行: | ||
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url; |
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 |
return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url |
||
− | end |
||
− | |||
− | |||
− | --[[--------------------------< L I N K _ T I T L E _ O K >--------------------------------------------------- |
||
− | |||
− | Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value. |
||
− | |||
− | |<title>= may be wikilinked but not when |<param>-link= has a value. This function emits an error message when |
||
− | that condition exists |
||
− | |||
− | ]] |
||
− | |||
− | local function link_title_ok (link, lorig, title, torig) |
||
− | local orig; |
||
− | |||
− | if is_set (link) then -- don't bother if <param>-link doesn't have a value |
||
− | if not link_param_ok (link) then -- check |<param>-link= markup |
||
− | orig = lorig; -- identify the failing link parameter |
||
− | elseif title:find ('%[%[') then -- check |title= for wikilink markup |
||
− | orig = torig; -- identify the failing |title= parameter |
||
− | end |
||
− | end |
||
− | |||
− | 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 |
||
第297行: | 第334行: | ||
portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two |
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. |
portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false. |
||
− | |||
− | Because it is different from a standard url, and because this module used external_link() to make external links |
||
− | that work for standard and news: links, we validate newsgroup names here. The specification for a newsgroup name |
||
− | is at https://tools.ietf.org/html/rfc5536#section-3.1.4 |
||
]] |
]] |
||
第310行: | 第343行: | ||
local scheme, domain; |
local scheme, domain; |
||
− | scheme, domain = split_url (url_str); -- 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; |
− | |||
− | if 'news:' == scheme then -- special case for newsgroups |
||
− | return domain:match('^[%a%d%+%-_]+%.[%a%d%+%-_%.]*[%a%d%+%-_]$'); |
||
− | end |
||
− | |||
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 |
||
第335行: | 第363行: | ||
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 = |
+ | scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S+).*%]') |
− | elseif value:match ('%f[%[]%[//%S+.*%]') then |
+ | elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] |
− | + | domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]'); |
|
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text |
elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text |
||
− | scheme, domain = |
+ | scheme, domain = value:match ('(%a%S*:)(%S+)'); |
− | elseif value:match ('//%S+') then |
+ | elseif value:match ('//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text |
− | + | domain = value:match ('//(%S*%.%S+)'); -- what is left should be the domain |
|
else |
else |
||
return false; -- didn't find anything that is obviously a url |
return false; -- didn't find anything that is obviously a url |
||
第373行: | 第403行: | ||
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></span>" .. str; end |
||
+ | if str:sub(-1,-1) == "'" then str = str .. "<span></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 >------------------------------------------------------ |
||
第391行: | 第443行: | ||
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 >---------------------------------------------------- |
||
第398行: | 第467行: | ||
]] |
]] |
||
− | local function external_link( URL, label, source |
+ | local function external_link( URL, label, source ) |
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; |
||
第415行: | 第480行: | ||
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 |
||
+ | --[[--------------------------< E X T E R N A L _ L I N K _ I D >---------------------------------------------- |
||
− | path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values |
||
− | URL = table.concat ({domain, path}); -- and reassemble |
||
− | end |
||
+ | Formats a wiki style external link |
||
− | base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wikimarkup url |
||
+ | ]] |
||
− | 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 \<span title\=\"%s\"\>%s%s%s\<\/span\>]', |
||
− | |||
+ | options.prefix, url_string, options.suffix or "", |
||
− | return table.concat ({base_url, error_str}); |
||
+ | options.link, options.label, options.separator 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 >-------------------------------------- |
||
第437行: | 第506行: | ||
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 |
+ | if not page_in_deprecated_cat then |
− | + | page_in_deprecated_cat = true; -- note that we've added this category |
|
− | table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message |
+ | 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 is_set (cap) then |
||
− | if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks |
||
− | + | str = substitute (cfg.presentation['kern-left'], {cap, cap2}); |
|
+ | 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 ("^(.+[^\'])([\"\'])$") |
||
− | else -- plain text or [[L|D]]; text in label variable |
||
+ | if is_set (cap) then |
||
− | label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) |
||
+ | str = substitute (cfg.presentation['kern-right'], {cap, cap2}); |
||
− | label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark) |
||
− | |||
− | cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) |
||
− | if is_set (cap) then |
||
− | label = substitute (cfg.presentation['kern-left'], {cap, cap2}); |
||
− | end |
||
− | |||
− | cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- 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 |
end |
||
return str; |
return str; |
||
end |
end |
||
− | |||
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- |
--[[--------------------------< F O R M A T _ S C R I P T _ V A L U E >---------------------------------------- |
||
第527行: | 第565行: | ||
is not added. At this time there is no error message for this condition. |
is not added. At this time there is no error message for this condition. |
||
− | Supports |script-title= |
+ | Supports |script-title= and |script-chapter= |
+ | TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script; |
||
]] |
]] |
||
− | local function format_script_value (script_value |
+ | local function format_script_value (script_value) |
local lang=''; -- initialize to empty string |
local lang=''; -- initialize to empty string |
||
local name; |
local name; |
||
− | if script_value:match('^%l%l |
+ | if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix |
− | lang = script_value:match('^(%l%l |
+ | lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script |
if not is_set (lang) then |
if not is_set (lang) then |
||
− | table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing title part'}, true ) } ); -- prefix without 'title'; add error message |
||
return ''; -- script_value was just the prefix so return empty string |
return ''; -- script_value was just the prefix so return empty string |
||
end |
end |
||
-- if we get this far we have prefix and script |
-- if we get this far we have prefix and script |
||
− | name = |
+ | name = mw.language.fetchLanguageName( lang, mw.getContentLanguage():getCode() ); -- 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 |
+ | 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 |
||
+ | add_prop_cat ('script') |
||
− | table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'unknown language code'}, true ) } ); -- unknown script-language; add error message |
||
end |
end |
||
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute |
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute |
||
else |
else |
||
− | table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message |
||
lang = ''; -- invalid so set lang to empty string |
lang = ''; -- invalid so set lang to empty string |
||
end |
end |
||
+ | end |
||
− | else |
||
+ | if is_set(script_value) then |
||
− | table.insert( z.message_tail, { set_error( 'script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message |
||
+ | script_value = '-{R|' .. script_value .. '}-'; |
||
end |
end |
||
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl |
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl |
||
第562行: | 第600行: | ||
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 >------------------------------------------ |
||
第570行: | 第607行: | ||
]] |
]] |
||
− | local function script_concatenate (title, script |
+ | local function script_concatenate (title, script) |
+ | if is_set(title) then |
||
+ | title = '-{zh;zh-hans;zh-hant|' .. title .. '}-'; |
||
+ | end |
||
if is_set (script) then |
if is_set (script) then |
||
− | script = format_script_value (script |
+ | script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error |
if is_set (script) then |
if is_set (script) then |
||
title = title .. ' ' .. script; -- concatenate title and script title |
title = title .. ' ' .. script; -- concatenate title and script title |
||
第596行: | 第636行: | ||
local msg; |
local msg; |
||
msg = cfg.messages[key]:lower(); -- set the message to lower case before |
msg = cfg.messages[key]:lower(); -- set the message to lower case before |
||
− | return substitute( msg, str ); |
+ | return substitute( msg, str ); -- including template text |
else |
else |
||
return substitute( cfg.messages[key], str ); |
return substitute( cfg.messages[key], str ); |
||
第603行: | 第643行: | ||
− | --[[ |
+ | --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- |
+ | This function is used by select_one() to determine if one of a list of alias parameters is in the argument list |
||
− | makes a wikisource url from wikisource interwiki link. returns the url and appropriate label; nil else. |
||
+ | provided by the template. |
||
+ | Input: |
||
− | str is the value assigned to |chapter= (or aliases) or |title= or |title-link= |
||
+ | 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 wikisource_url_make (str) |
||
+ | if enumerated then -- is this a test for an enumerated parameters? |
||
− | local wl_type, D, L; |
||
+ | alias = alias:gsub ('#', index); -- replace '#' with the value in index |
||
− | local ws_url, ws_label; |
||
+ | else |
||
− | local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'}); |
||
+ | alias = alias:gsub ('#', ''); -- remove '#' if it exists |
||
+ | end |
||
+ | if is_set(args[alias]) then -- alias is in the template's argument list |
||
− | wl_type, D, L = is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink) |
||
+ | if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases |
||
− | |||
+ | local skip; |
||
− | if 0 == wl_type then -- not a wikilink; might be from |title-link= |
||
+ | for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias |
||
− | str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
||
− | if |
+ | if v == alias then |
+ | skip = true; |
||
− | ws_url = table.concat ({ -- build a wikisource url |
||
− | + | break; -- has been added so stop looking |
|
+ | end |
||
− | str, -- article title |
||
− | + | end |
|
− | + | if not skip then -- has not been added so |
|
+ | table.insert( error_list, alias ); -- add error alias to the error list |
||
− | end |
||
+ | end |
||
− | elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]] |
||
+ | else |
||
− | str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
||
+ | value = args[alias]; -- not yet selected an alias, so select this one |
||
− | if is_set (str) then |
||
+ | selected = alias; |
||
− | ws_url = table.concat ({ -- build a wikisource url |
||
− | wikisource_prefix, -- prefix |
||
− | str, -- article title |
||
− | }); |
||
− | ws_label = str; -- label for the url |
||
− | end |
||
− | elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]]) |
||
− | str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
||
− | if is_set (str) then |
||
− | ws_label = D; -- get ws article name from display portion of interwiki link |
||
− | ws_url = table.concat ({ -- build a wikisource url |
||
− | wikisource_prefix, -- prefix |
||
− | str, -- article title without namespace from link portion of wikilink |
||
− | }); |
||
end |
end |
||
end |
end |
||
+ | return value, selected; -- return newly selected alias, or previously selected alias |
||
− | |||
− | if ws_url then |
||
− | ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable url |
||
− | ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of fragment marker |
||
− | end |
||
− | |||
− | return ws_url, ws_label, L or D; -- return proper url or nil and a label or nil |
||
end |
end |
||
− | --[[--------------------------< |
+ | --[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- |
+ | Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just |
||
− | Format the three periodical parameters: |script-<periodical>=, |<periodical>=, and |trans-<periodical>= into a single Periodical meta- |
||
+ | names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified |
||
− | parameter. |
||
+ | by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'. |
||
+ | Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities. |
||
− | ]] |
||
− | local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) |
||
− | local periodical_error = ''; |
||
+ | Generates an error if more than one match is present. |
||
− | if not is_set (periodical) then |
||
− | periodical = ''; -- to be safe for concatenation |
||
− | else |
||
− | periodical = wrap_style ('italic-title', periodical); -- style |
||
− | end |
||
+ | ]] |
||
− | periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
||
+ | local function select_one( args, aliases_list, error_condition, index ) |
||
− | if is_set (trans_periodical) then |
||
+ | local value = nil; -- the value assigned to the selected parameter |
||
− | trans_periodical = wrap_style ('trans-italic-title', trans_periodical); |
||
+ | local selected = ''; -- the name of the parameter we have chosen |
||
− | if is_set (periodical) then |
||
+ | local error_list = {}; |
||
− | periodical = periodical .. ' ' .. trans_periodical; |
||
+ | |||
− | else -- here when trans-periodical without periodical or script-periodical |
||
+ | if index ~= nil then index = tostring(index); end |
||
− | periodical = trans_periodical; |
||
+ | |||
− | periodical_error = ' ' .. set_error ('trans_missing_title', {'periodical'}); |
||
+ | for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list |
||
+ | if alias:match ('#') then -- if this alias can be enumerated |
||
+ | if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases |
||
+ | value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias |
||
+ | end |
||
+ | value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias |
||
+ | else |
||
+ | value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias |
||
end |
end |
||
end |
end |
||
+ | if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names() |
||
− | return periodical .. periodical_error; |
||
+ | local error_str = ""; |
||
+ | for _, k in ipairs( error_list ) do |
||
+ | if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end |
||
+ | error_str = error_str .. wrap_style ('parameter', k); |
||
+ | end |
||
+ | if #error_list > 1 then |
||
+ | error_str = error_str .. cfg.messages['parameter-final-separator']; |
||
+ | else |
||
+ | error_str = error_str .. cfg.messages['parameter-pair-separator']; |
||
+ | end |
||
+ | error_str = error_str .. wrap_style ('parameter', selected); |
||
+ | table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } ); |
||
+ | end |
||
+ | |||
+ | return value, selected; |
||
end |
end |
||
第695行: | 第748行: | ||
]] |
]] |
||
− | local function format_chapter_title (scriptchapter |
+ | local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) |
local chapter_error = ''; |
local chapter_error = ''; |
||
+ | |||
− | |||
− | local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource url and label from a wikisource interwiki link |
||
− | if ws_url then |
||
− | ws_label = ws_label:gsub ('_', ''); -- replace underscore separaters with space characters |
||
− | chapter = ws_label; |
||
− | end |
||
− | |||
if not is_set (chapter) then |
if not is_set (chapter) then |
||
chapter = ''; -- to be safe for concatenation |
chapter = ''; -- to be safe for concatenation |
||
else |
else |
||
if false == no_quotes then |
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 = 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); |
chapter = wrap_style ('quoted-title', chapter); |
||
end |
end |
||
end |
end |
||
− | chapter = script_concatenate (chapter, scriptchapter |
+ | chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
− | |||
− | if is_set (chapterurl) then |
||
− | chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate |
||
− | elseif ws_url then |
||
− | chapter = external_link (ws_url, chapter .. ' ', 'ws link in chapter'); -- adds bare_url_missing_title error if appropriate; space char to move icon away from chap text; TODO: better way to do this? |
||
− | chapter = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter}); |
||
− | end |
||
if is_set (transchapter) then |
if is_set (transchapter) then |
||
第727行: | 第767行: | ||
chapter = chapter .. ' ' .. transchapter; |
chapter = chapter .. ' ' .. transchapter; |
||
else -- here when transchapter without chapter or script-chapter |
else -- here when transchapter without chapter or script-chapter |
||
− | chapter = transchapter; |
+ | chapter = transchapter; -- |
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); |
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); |
||
end |
end |
||
+ | end |
||
+ | |||
+ | if is_set (chapterurl) then |
||
+ | chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate |
||
end |
end |
||
return chapter .. chapter_error; |
return chapter .. chapter_error; |
||
end |
end |
||
− | |||
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- |
--[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- |
||
第745行: | 第788行: | ||
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref) |
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(). |
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 |
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker |
||
第758行: | 第803行: | ||
local i=1; |
local i=1; |
||
local stripmarker, apostrophe; |
local stripmarker, apostrophe; |
||
− | |||
− | capture = string.match (v, '[%w%p ]*'); -- Test for values that are simple ASCII text and bypass other tests if true |
||
− | if capture == v then -- if same there are no unicode characters |
||
− | return; |
||
− | end |
||
while cfg.invisible_chars[i] do |
while cfg.invisible_chars[i] do |
||
第768行: | 第808行: | ||
local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it |
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 |
position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern |
||
− | |||
− | if position and (char == 'zero width joiner') then -- if we found a zero width joiner character |
||
− | if mw.ustring.find (v, cfg.indic_script) then -- its ok if one of the indic scripts |
||
− | position = nil; -- unset position |
||
− | end |
||
− | end |
||
if position then |
if position then |
||
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) |
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) |
||
− | ('templatestyles' == capture |
+ | ('templatestyles' == capture) then -- templatestyles stripmarker allowed |
stripmarker = true; -- set a flag |
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 |
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 |
position = nil; -- unset |
||
else |
else |
||
local err_msg; |
local err_msg; |
||
if capture then |
if capture then |
||
− | err_msg = capture .. ' ' .. char; |
+ | err_msg = capture .. ' ' .. cfg.invisible_chars[i][3] or char; |
else |
else |
||
− | err_msg = |
+ | err_msg = cfg.invisible_chars[i][3] or (char .. ' character'); |
end |
end |
||
第832行: | 第870行: | ||
-- maybe let through instead of raising an error? |
-- maybe let through instead of raising an error? |
||
-- v, origin[k] = args[k], k; |
-- v, origin[k] = args[k], k; |
||
− | error( cfg.messages['unknown_argument_map'] |
+ | error( cfg.messages['unknown_argument_map'] ); |
end |
end |
||
-- Empty strings, not nil; |
-- Empty strings, not nil; |
||
if v == nil then |
if v == nil then |
||
− | + | v = cfg.defaults[k] or ''; |
|
− | v = ''; |
||
origin[k] = ''; |
origin[k] = ''; |
||
end |
end |
||
第846行: | 第883行: | ||
end, |
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: |
||
+ | 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 |
||
+ | |||
+ | |||
+ | -- Formats a wiki style internal link |
||
+ | local function internal_link_id(options) |
||
+ | return mw.ustring.format( '[[%s%s%s|\<span title\=\"%s\"\>%s\<\/span\>%s%s]]', |
||
+ | options.prefix, options.id, options.suffix or "", |
||
+ | options.link, options.label, options.separator or " ", |
||
+ | mw.text.nowiki(options.id) |
||
+ | ); |
||
end |
end |
||
第873行: | 第953行: | ||
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(). |
||
+ | If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes, |
||
+ | spaces and other non-isxn characters. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function is_valid_isxn (isxn_str, len) |
||
+ | local temp = 0; |
||
+ | isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58 |
||
+ | len = len+1; -- adjust to be a loop counter |
||
+ | for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum |
||
+ | if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58) |
||
+ | temp = temp + 10*( len - i ); -- it represents 10 decimal |
||
+ | else |
||
+ | temp = temp + tonumber( string.char(v) )*(len-i); |
||
+ | end |
||
+ | end |
||
+ | return temp % 11 == 0; -- returns true if calculation result is zero |
||
+ | end |
||
+ | |||
+ | |||
+ | --[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >---------------------------------------------- |
||
+ | |||
+ | ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit. |
||
+ | If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length |
||
+ | and stripped of dashes, spaces and other non-isxn-13 characters. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function is_valid_isxn_13 (isxn_str) |
||
+ | local temp=0; |
||
+ | |||
+ | isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39 |
||
+ | for i, v in ipairs( isxn_str ) do |
||
+ | 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 |
||
+ | end |
||
+ | return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------ |
||
+ | |||
+ | Determines whether an ISBN string is valid |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function check_isbn( isbn_str ) |
||
+ | if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X |
||
+ | isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces |
||
+ | local len = isbn_str:len(); |
||
+ | |||
+ | if len ~= 10 and len ~= 13 then |
||
+ | return false; |
||
+ | end |
||
+ | |||
+ | if len == 10 then |
||
+ | if isbn_str:match( "^%d*X?$" ) == nil then return false; end |
||
+ | return is_valid_isxn(isbn_str, 10); |
||
+ | else |
||
+ | local temp = 0; |
||
+ | if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979 |
||
+ | return is_valid_isxn_13 (isbn_str); |
||
+ | end |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< 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 |
||
+ | same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf |
||
+ | section 2, pages 9–12. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | 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, e) |
||
+ | local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate |
||
+ | local handler; |
||
+ | local text; |
||
+ | local valid_issn = true; |
||
+ | |||
+ | if e then |
||
+ | handler = cfg.id_handlers['EISSN']; |
||
+ | else |
||
+ | handler = cfg.id_handlers['ISSN']; |
||
+ | end |
||
+ | |||
+ | id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn |
||
+ | |||
+ | if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position |
||
+ | valid_issn=false; -- wrong length or improper character |
||
+ | else |
||
+ | valid_issn=is_valid_isxn(id, 8); -- validate issn |
||
+ | end |
||
+ | |||
+ | if true == valid_issn then |
||
+ | id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version |
||
+ | else |
||
+ | id = issn_copy; -- if not valid, use the show the invalid issn with error message |
||
+ | end |
||
+ | |||
+ | text = external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
||
+ | |||
+ | if false == valid_issn then |
||
+ | text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid |
||
+ | end |
||
+ | |||
+ | return text |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< 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 |
||
+ | elseif not id:match("^%u[%d%u]+$") then |
||
+ | err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha |
||
+ | end |
||
+ | end |
||
+ | if not is_set(domain) then |
||
+ | domain = "com"; |
||
+ | elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom |
||
+ | domain = "co." .. domain; |
||
+ | elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico |
||
+ | domain = "com." .. domain; |
||
+ | end |
||
+ | local handler = cfg.id_handlers['ASIN']; |
||
+ | return external_link_id({link=handler.link, |
||
+ | label=handler.label, prefix=handler.prefix .. domain .. "/dp/", |
||
+ | id=id, encode=handler.encode, separator = handler.separator}) .. err_cat; |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< A R X I V >-------------------------------------------------------------------- |
||
+ | |||
+ | See: http://arxiv.org/help/arxiv_identifier |
||
+ | |||
+ | format and error check arXiv identifier. There are three valid forms of the identifier: |
||
+ | 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 handler = cfg.id_handlers['ARXIV']; |
||
+ | local year, month, version; |
||
+ | local err_cat = ''; |
||
+ | local text; |
||
+ | |||
+ | if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version |
||
+ | year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$"); |
||
+ | year = tonumber(year); |
||
+ | month = tonumber(month); |
||
+ | if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month |
||
+ | ((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok? |
||
+ | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
||
+ | end |
||
+ | elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version |
||
+ | year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); |
||
+ | year = tonumber(year); |
||
+ | month = tonumber(month); |
||
+ | if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years) |
||
+ | ((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)? |
||
+ | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
||
+ | end |
||
+ | elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version |
||
+ | year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); |
||
+ | year = tonumber(year); |
||
+ | month = tonumber(month); |
||
+ | if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years) |
||
+ | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message |
||
+ | end |
||
+ | else |
||
+ | err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format |
||
+ | end |
||
+ | |||
+ | text = external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; |
||
+ | |||
+ | if is_set (class) then |
||
+ | class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink |
||
+ | else |
||
+ | class = ''; -- empty string for concatenation |
||
+ | end |
||
+ | |||
+ | return text .. class; |
||
+ | end |
||
+ | |||
+ | --[[ |
||
+ | lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization) |
||
+ | 1. Remove all blanks. |
||
+ | 2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash. |
||
+ | 3. If there is a hyphen in the string: |
||
+ | a. Remove it. |
||
+ | b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out): |
||
+ | 1. All these characters should be digits, and there should be six or less. (not done in this function) |
||
+ | 2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six. |
||
+ | |||
+ | Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function. |
||
+ | ]] |
||
+ | |||
+ | local function normalize_lccn (lccn) |
||
+ | lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace |
||
+ | |||
+ | if nil ~= string.find (lccn,'/') then |
||
+ | lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it |
||
+ | end |
||
+ | |||
+ | local prefix |
||
+ | local suffix |
||
+ | prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix |
||
+ | |||
+ | if nil ~= suffix then -- if there was a hyphen |
||
+ | suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6 |
||
+ | lccn=prefix..suffix; -- reassemble the lccn |
||
+ | end |
||
+ | |||
+ | return lccn; |
||
+ | end |
||
+ | |||
+ | --[[ |
||
+ | Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the |
||
+ | rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/ |
||
+ | |||
+ | length = 8 then all digits |
||
+ | length = 9 then lccn[1] is lower case alpha |
||
+ | length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits |
||
+ | length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits |
||
+ | length = 12 then lccn[1] and lccn[2] are both lower case alpha |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function lccn(lccn) |
||
+ | local handler = cfg.id_handlers['LCCN']; |
||
+ | local err_cat = ''; -- presume that LCCN is valid |
||
+ | local id = lccn; -- local copy of the lccn |
||
+ | |||
+ | id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) |
||
+ | local len = id:len(); -- get the length of the lccn |
||
+ | |||
+ | if 8 == len then |
||
+ | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message |
||
+ | end |
||
+ | elseif 9 == len then -- LCCN should be adddddddd |
||
+ | if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern? |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message |
||
+ | end |
||
+ | elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd |
||
+ | if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... |
||
+ | if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
||
+ | end |
||
+ | end |
||
+ | elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd |
||
+ | if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
||
+ | end |
||
+ | elseif 12 == len then -- LCCN should be aadddddddddd |
||
+ | if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message |
||
+ | end |
||
+ | else |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message |
||
+ | end |
||
+ | |||
+ | if not is_set (err_cat) and nil ~= lccn:find ('%s') then |
||
+ | err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message |
||
+ | end |
||
+ | |||
+ | return external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat; |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< P M I D >---------------------------------------------------------------------- |
||
+ | |||
+ | 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) |
||
+ | local test_limit = 33000000; -- update this value as PMIDs approach |
||
+ | local handler = cfg.id_handlers['PMID']; |
||
+ | local err_cat = ''; -- presume that PMID is valid |
||
+ | |||
+ | if id:match("[^%d]") then -- if PMID has anything but digits |
||
+ | err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message |
||
+ | 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 |
||
+ | |||
+ | 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 |
||
+ | return ''; -- |embargo= not set return empty string |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< P M C >------------------------------------------------------------------------ |
||
+ | |||
+ | Format a PMC, do simple error checking, and check for embargoed articles. |
||
+ | |||
+ | The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not |
||
+ | be linked to the article. If the embargo 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 test_limit = 7000000; -- update this value as PMCs approach |
||
+ | local handler = cfg.id_handlers['PMC']; |
||
+ | local err_cat = ''; -- presume that PMC is valid |
||
+ | local id_num; |
||
+ | local text; |
||
+ | |||
+ | id_num = id:match ('^[Pp][Mm][Cc](%d+)$'); -- identifier with pmc prefix |
||
+ | |||
+ | if is_set (id_num) then |
||
+ | add_maint_cat ('pmc_format'); |
||
+ | else -- plain number without pmc prefix |
||
+ | id_num = id:match ('^%d+$'); -- if here id is all digits |
||
+ | end |
||
+ | |||
+ | if is_set (id_num) then -- id_num has a value so test it |
||
+ | id_num = tonumber(id_num); -- convert id_num to a number for range testing |
||
+ | if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries |
||
+ | err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message |
||
+ | else |
||
+ | id = tostring (id_num); -- make sure id is a string |
||
+ | end |
||
+ | else -- when id format incorrect |
||
+ | err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message |
||
+ | end |
||
+ | |||
+ | if is_set (embargo) then -- is PMC is still embargoed? |
||
+ | text = table.concat ( -- still embargoed so no external link |
||
+ | { |
||
+ | make_wikilink (handler.link, handler.label), |
||
+ | handler.separator, |
||
+ | id, |
||
+ | err_cat |
||
+ | }); |
||
+ | 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 |
||
+ | |||
+ | --[[--------------------------< D O I >------------------------------------------------------------------------ |
||
+ | |||
+ | 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; |
||
+ | if is_set(inactive) then |
||
+ | local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date |
||
+ | if is_set(inactive_year) then |
||
+ | table.insert( z.error_categories, "自" .. inactive_year .. "年含有不活躍DOI的頁面" ); |
||
+ | else |
||
+ | table.insert( z.error_categories, "含有不活躍DOI的頁面" ); -- when inactive doesn't contain a recognizable year |
||
+ | end |
||
+ | inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")" |
||
+ | end |
||
+ | text = external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. (inactive or '') |
||
+ | |||
+ | if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma |
||
+ | cat = ' ' .. set_error( 'bad_doi' ); |
||
+ | end |
||
+ | |||
+ | return text .. cat |
||
+ | end |
||
+ | |||
+ | |||
+ | --[[--------------------------< H D L >------------------------------------------------------------------------ |
||
+ | |||
+ | Formats an HDL with minor error checking. |
||
+ | |||
+ | HDL names contain two parts: prefix and suffix separated by a forward slash. |
||
+ | Prefix: character string using any character in the UCS-2 character set except '/' |
||
+ | Suffix: character string of any length using any character in the UCS-2 character set chosen by the registrant |
||
+ | |||
+ | This function checks a HDL name for: prefix/suffix. If the HDL name contains spaces, endashes, or, if it ends |
||
+ | with a period or a comma, this function will emit a bad_hdl error message. |
||
+ | |||
+ | HDL names are case-insensitive and can incorporate any printable Unicode characters so the test for endashes and |
||
+ | terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely |
||
+ | if ever used in HDLs. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function hdl(id) |
||
+ | local handler = cfg.id_handlers['HDL']; |
||
+ | |||
+ | local text = external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
||
+ | |||
+ | if nil == id:match("^[^%s–]-/[^%s–]-[^%.,]$") then -- hdl must contain a fwd slash, must not contain spaces, endashes, and must not end with period or comma |
||
+ | text = text .. ' ' .. set_error( 'bad_hdl' ); |
||
+ | end |
||
+ | return text; |
||
+ | end |
||
+ | |||
+ | --[[--------------------------< O P E N L I B R A R Y >-------------------------------------------------------- |
||
+ | |||
+ | Formats an OpenLibrary link, and checks for associated errors. |
||
+ | |||
+ | ]] |
||
+ | local function openlibrary(id) |
||
+ | local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W' |
||
+ | local handler = cfg.id_handlers['OL']; |
||
+ | |||
+ | if ( code == "A" ) then |
||
+ | return external_link_id({link=handler.link, label=handler.label, |
||
+ | prefix=handler.prefix .. 'authors/OL', |
||
+ | id=id, separator=handler.separator, encode = handler.encode}) |
||
+ | elseif ( code == "M" ) then |
||
+ | return external_link_id({link=handler.link, label=handler.label, |
||
+ | prefix=handler.prefix .. 'books/OL', |
||
+ | id=id, separator=handler.separator, encode = handler.encode}) |
||
+ | elseif ( code == "W" ) then |
||
+ | return external_link_id({link=handler.link, label=handler.label, |
||
+ | prefix=handler.prefix .. 'works/OL', |
||
+ | id=id, separator=handler.separator, encode = handler.encode}) |
||
+ | else |
||
+ | return external_link_id({link=handler.link, label=handler.label, |
||
+ | prefix=handler.prefix .. 'OL', |
||
+ | id=id, separator=handler.separator, encode = handler.encode}) .. ' ' .. set_error( 'bad_ol' ); |
||
+ | end |
||
+ | end |
||
+ | |||
+ | |||
+ | --[[--------------------------< M E S S A G E _ I D >---------------------------------------------------------- |
||
+ | |||
+ | Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in |
||
+ | '<' and/or '>' angle brackets. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function message_id (id) |
||
+ | local handler = cfg.id_handlers['USENETID']; |
||
+ | |||
+ | text = external_link_id({link = handler.link, label = handler.label, |
||
+ | prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) |
||
+ | |||
+ | if not id:match('^.+@.+$') 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 |
||
+ | end |
||
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- |
--[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- |
||
第883行: | 第1,539行: | ||
local function set_titletype (cite_class, title_type) |
local function set_titletype (cite_class, title_type) |
||
if is_set(title_type) then |
if is_set(title_type) then |
||
+ | if "none" == title_type then |
||
− | |||
− | if cfg.keywords_xlate[title_type] == 'none' then |
||
title_type = ""; -- if |type=none then type parameter not displayed |
title_type = ""; -- if |type=none then type parameter not displayed |
||
end |
end |
||
第893行: | 第1,548行: | ||
end |
end |
||
+ | --[[--------------------------< C L E A N _ I S B N >---------------------------------------------------------- |
||
+ | Removes irrelevant text and dashes from ISBN number |
||
− | --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- |
||
+ | Similar to that used for Special:BookSources |
||
+ | ]] |
||
− | 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) |
||
+ | local function clean_isbn( isbn_str ) |
||
− | any other forms are returned unmodified. |
||
+ | 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 >---------------------------------- |
||
− | str may be a comma- or semicolon-separated list |
||
+ | Returns a string where all of lua's magic characters have been escaped. This is important because functions like |
||
+ | string.gsub() treat their pattern and replace strings as patterns, not literal strings. |
||
]] |
]] |
||
+ | local function escape_lua_magic_chars (argument) |
||
+ | argument = argument:gsub("%%", "%%%%"); -- replace % with %% |
||
+ | argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters |
||
+ | return argument; |
||
+ | end |
||
+ | --[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >-------------------------------- |
||
− | local function hyphen_to_dash( str ) |
||
+ | |||
− | if not is_set (str) then |
||
+ | Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata. |
||
− | return str; |
||
+ | This function strips common patterns of apostrophe markup. We presume that editors who have taken the time to |
||
+ | markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function strip_apostrophe_markup (argument) |
||
+ | if not is_set (argument) then return argument; end |
||
+ | |||
+ | while true do |
||
+ | if argument:match ("%'%'%'%'%'") then -- bold italic (5) |
||
+ | argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it |
||
+ | elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4) |
||
+ | argument=argument:gsub("%'%'%'%'", ""); |
||
+ | elseif argument:match ("%'%'%'") then -- bold (3) |
||
+ | argument=argument:gsub("%'%'%'", ""); |
||
+ | elseif argument:match ("%'%'") then -- italic (2) |
||
+ | argument=argument:gsub("%'%'", ""); |
||
+ | else |
||
+ | break; |
||
+ | end |
||
end |
end |
||
+ | return argument; -- done |
||
− | |||
+ | end |
||
− | str, count = str:gsub ('^%(%((.+)%)%)$', '%1'); -- remove accept-this-as-written markup when it wraps all of str |
||
+ | |||
− | if 0 ~= count then -- non-zero when markup removed; zero else |
||
+ | --[[--------------------------< M A K E _ C O I N S _ T I T L E >---------------------------------------------- |
||
− | return str; -- nothing to do, we're done |
||
+ | |||
+ | 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) |
||
+ | 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 |
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) |
||
− | str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split |
||
+ | script = strip_apostrophe_markup (script); -- strip any apostrophe markup |
||
− | str = str:gsub ('-', '-'); -- replace html numeric entity with hyphen character |
||
+ | else |
||
− | str = str:gsub (' ', ' '); -- replace entity with generic keyboard space character |
||
+ | script=''; -- if not set, make sure script is an empty string |
||
− | |||
+ | end |
||
− | local out = {}; |
||
+ | if is_set (title) and is_set (script) then |
||
− | local list = mw.text.split (str, '%s*[,;]%s*'); -- split str at comma or semicolon separators if there are any |
||
+ | 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 >------------------------------------------------ |
||
− | 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 |
||
+ | Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS. |
||
− | 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 get_coins_pages (pages) |
||
− | item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter |
||
+ | local pattern; |
||
− | item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters |
||
+ | if not is_set (pages) then return pages; end -- if no page numbers then we're done |
||
− | else |
||
+ | |||
− | item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous white space |
||
+ | while true do |
||
− | end |
||
+ | pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url " |
||
− | end |
||
+ | if nil == pattern then break; end -- no more urls |
||
− | item = item:gsub ('^%(%((.+)%)%)$', '%1'); -- remove the accept-this-as-written markup |
||
+ | pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters |
||
− | table.insert (out, item); -- add the (possibly modified) item to the output table |
||
+ | pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible |
||
end |
end |
||
+ | pages = pages:gsub("[%[%]]", ""); -- remove the brackets |
||
+ | pages = pages:gsub("–", "-" ); -- replace endashes with hyphens |
||
+ | pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like? |
||
+ | return pages; |
||
+ | end |
||
+ | -- Gets the display text for a wikilink like [[A|B]] or [[B]] gives B |
||
− | return table.concat (out, ', '); -- concatenate the output table into a comma separated string |
||
+ | local function remove_wiki_link( str ) |
||
+ | return (str:gsub( "%[%[([^%[%]]*)%]%]", function(l) |
||
+ | return l:gsub( "^[^|]*|(.*)$", "%1" ):gsub("^%s*(.-)%s*$", "%1"); |
||
+ | end)); |
||
end |
end |
||
+ | -- Converts a hyphen to a dash |
||
+ | 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 >------------------------------------------------------------ |
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------ |
||
第954行: | 第1,667行: | ||
local function safe_join( tbl, duplicate_char ) |
local function safe_join( tbl, duplicate_char ) |
||
+ | --[[ |
||
− | local f = {}; -- create a function table appropriate to type of 'dupicate character' |
||
+ | Note: we use string functions here, rather than ustring functions. |
||
− | if 1 == #duplicate_char then -- for single byte ascii characters use the string library functions |
||
+ | |||
− | f.gsub=string.gsub |
||
+ | This has considerably faster performance and should work correctly as |
||
− | f.match=string.match |
||
+ | long as the duplicate_char is strict ASCII. The strings |
||
− | f.sub=string.sub |
||
+ | in tbl may be ASCII or UTF8. |
||
− | else -- for multi-byte characters use the ustring library functions |
||
+ | ]] |
||
− | f.gsub=mw.ustring.gsub |
||
+ | |||
− | f.match=mw.ustring.match |
||
− | f.sub=mw.ustring.sub |
||
− | end |
||
− | |||
local str = ''; -- the output string |
local str = ''; -- the output string |
||
local comp = ''; -- what does 'comp' mean? |
local comp = ''; -- what does 'comp' mean? |
||
第981行: | 第1,691行: | ||
end |
end |
||
-- typically duplicate_char is sepc |
-- typically duplicate_char is sepc |
||
− | if |
+ | if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character? |
− | -- Because individual string segments often (always?) begin with terminal punct for |
+ | -- Because individual string segments often (always?) begin with terminal punct for th |
-- preceding segment: 'First element' .. 'sepc next element' .. etc? |
-- preceding segment: 'First element' .. 'sepc next element' .. etc? |
||
trim = false; |
trim = false; |
||
− | end_chr = |
+ | end_chr = str:sub(-1,-1); -- get the last character of the output string |
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? |
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? |
||
if end_chr == duplicate_char then -- if same as separator |
if end_chr == duplicate_char then -- if same as separator |
||
− | str = |
+ | str = str:sub(1,-2); -- remove it |
elseif end_chr == "'" then -- if it might be wikimarkup |
elseif end_chr == "'" then -- if it might be wikimarkup |
||
− | if |
+ | if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' |
− | str = |
+ | str = str:sub(1, -4) .. "''"; -- remove them and add back '' |
− | elseif |
+ | 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? |
trim = true; -- why? why do this and next differently from previous? |
||
− | elseif |
+ | elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' |
trim = true; -- same question |
trim = true; -- same question |
||
end |
end |
||
elseif end_chr == "]" then -- if it might be wikimarkup |
elseif end_chr == "]" then -- if it might be wikimarkup |
||
− | if |
+ | if str:sub(-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; |
trim = true; |
||
− | elseif |
+ | elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link |
trim = true; |
trim = true; |
||
− | elseif |
+ | elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. |
trim = true; |
trim = true; |
||
end |
end |
||
elseif end_chr == " " then -- if last char of output string is a space |
elseif end_chr == " " then -- if last char of output string is a space |
||
− | if |
+ | if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> |
− | str = |
+ | str = str:sub(1,-3); -- remove them both |
end |
end |
||
end |
end |
||
第1,016行: | 第1,724行: | ||
if value ~= comp then -- value does not equal comp when value contains html markup |
if value ~= comp then -- value does not equal comp when value contains html markup |
||
local dup2 = duplicate_char; |
local dup2 = duplicate_char; |
||
− | if |
+ | if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it |
− | value = |
+ | value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup |
else |
else |
||
− | value = |
+ | value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character |
end |
end |
||
end |
end |
||
第1,028行: | 第1,736行: | ||
end |
end |
||
return str; |
return str; |
||
− | end |
+ | end |
− | |||
− | |||
− | --[[--------------------------< I S _ S U F F I X >------------------------------------------------------------ |
||
− | |||
− | returns true is suffix is properly formed Jr, Sr, or ordinal in the range 2–9. Puncutation not allowed. |
||
− | |||
− | ]] |
||
− | |||
− | local function is_suffix (suffix) |
||
− | if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then |
||
− | return true; |
||
− | end |
||
− | return false; |
||
− | end |
||
− | |||
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >-------------------------------------------- |
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >-------------------------------------------- |
||
第1,061行: | 第1,754行: | ||
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods |
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods |
||
+ | At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here |
||
− | This original test: |
||
+ | because the code editor gets confused between character insertion point and cursor position. |
||
− | if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then |
||
− | was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position. |
||
− | The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary |
||
− | to use an external editor to maintain this code. |
||
− | |||
− | \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) |
||
− | \195\152-\195\182 – Ø-ö (U+00D8-U+00F6 – C0 controls) |
||
− | \195\184-\198\191 – ø-ƿ (U+00F8-U+01BF – C0 controls, Latin extended A & B) |
||
− | \199\132-\201\143 – DŽ-ɏ (U+01C4-U+024F – Latin extended B) |
||
]] |
]] |
||
local function is_good_vanc_name (last, first) |
local function is_good_vanc_name (last, first) |
||
+ | if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then |
||
− | local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it |
||
+ | add_vanc_error (); |
||
− | |||
+ | return false; -- not a string of latin characters; Vancouver required Romanization |
||
− | if is_set (suffix) then |
||
− | if not is_suffix (suffix) then |
||
− | add_vanc_error (cfg.err_msg_supl.suffix); |
||
− | return false; -- not a name with an appropriate suffix |
||
− | end |
||
− | end |
||
− | if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") or |
||
− | nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then |
||
− | add_vanc_error (cfg.err_msg_supl['non-Latin character']); |
||
− | return false; -- not a string of latin characters; Vancouver requires Romanization |
||
end; |
end; |
||
return true; |
return true; |
||
end |
end |
||
− | |||
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
||
第1,098行: | 第1,773行: | ||
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/. |
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. |
||
− | Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. |
+ | Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not |
+ | currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. |
||
− | This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. |
||
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (). |
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (). |
||
第1,106行: | 第1,781行: | ||
local function reduce_to_initials(first) |
local function reduce_to_initials(first) |
||
− | + | if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do |
|
+ | local initials = {} |
||
− | |||
− | + | local i = 0; -- counter for number of initials |
|
− | + | for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods |
|
+ | table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops. |
||
+ | i = i + 1; -- bump the counter |
||
+ | if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit |
||
end |
end |
||
− | |||
− | if name then -- if first is initials with or without suffix |
||
− | if 3 > mw.ustring.len (name) then -- if one or two initials |
||
− | if suffix then -- if there is a suffix |
||
− | if is_suffix (suffix) then -- is it legitimate? |
||
− | return first; -- one or two initials and a valid suffix so nothing to do |
||
− | else |
||
− | add_vanc_error (cfg.err_msg_supl.suffix); -- one or two initials with invalid suffix so error message |
||
− | return first; -- and return first unmolested |
||
− | end |
||
− | else |
||
− | return first; -- one or two initials without suffix; nothing to do |
||
− | end |
||
− | end |
||
− | end -- if here then name has 3 or more uppercase letters so treat them as a word |
||
− | |||
− | local initials, names = {}, {}; -- tables to hold name parts and initials |
||
− | local i = 1; -- counter for number of initials |
||
− | |||
− | names = mw.text.split (first, '[%s,]+'); -- split into a table of names and possible suffix |
||
− | |||
− | while names[i] do -- loop through the table |
||
− | if 1 < i and names[i]:match ('[%dJS][%drndth]+%.?$') then -- if not the first name, and looks like a suffix (may have trailing dot) |
||
− | names[i] = names[i]:gsub ('%.', ''); -- remove terminal dot if present |
||
− | 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 |
||
− | break; -- and done because suffix must fall at the end of a name |
||
− | end -- no error message if not a suffix; possibly because of Romanization |
||
− | end |
||
− | if 3 > i then |
||
− | table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the intial at end of initials table |
||
− | end |
||
− | i = i+1; -- bump the counter |
||
− | end |
||
− | |||
return table.concat(initials) -- Vancouver format does not include spaces. |
return table.concat(initials) -- Vancouver format does not include spaces. |
||
end |
end |
||
− | |||
--[[--------------------------< L I S T _ P E O P L E >------------------------------------------------------- |
--[[--------------------------< L I S T _ P E O P L E >------------------------------------------------------- |
||
第1,156行: | 第1,798行: | ||
]] |
]] |
||
− | local function list_people(control, people, etal) |
+ | local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function |
local sep; |
local sep; |
||
local namesep; |
local namesep; |
||
第1,165行: | 第1,807行: | ||
if 'vanc' == format then -- Vancouver-like author/editor name styling? |
if 'vanc' == format then -- Vancouver-like author/editor name styling? |
||
− | sep = |
+ | sep = ','; -- name-list separator between authors is a comma |
− | namesep = |
+ | namesep = ' '; -- last/first separator is a space |
− | lastauthoramp = nil; -- unset because isn't used by Vancouver style |
||
else |
else |
||
− | sep = |
+ | sep = ';' -- name-list separator between authors is a semicolon |
− | namesep = |
+ | namesep = ', ' -- last/first separator is <comma><space> |
end |
end |
||
第1,195行: | 第1,836行: | ||
one = person.last |
one = person.last |
||
local first = person.first |
local first = person.first |
||
− | if is_set(first) then |
+ | if is_set(first) then |
if ( "vanc" == format ) then -- if vancouver format |
if ( "vanc" == format ) then -- if vancouver format |
||
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |
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 |
+ | if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested |
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials |
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials |
||
end |
end |
||
end |
end |
||
− | one = one .. namesep .. first |
+ | one = one .. namesep .. first |
+ | end |
||
+ | if is_set(person.link) and person.link ~= control.page_name then |
||
+ | one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page |
||
end |
end |
||
end |
end |
||
+ | table.insert( text, one ) |
||
− | if is_set (person.link) then |
||
+ | table.insert( text, sep_one ) |
||
− | one = make_wikilink (person.link, one); -- link author/editor |
||
− | end |
||
− | table.insert (text, one) |
||
− | table.insert (text, sep_one) |
||
end |
end |
||
end |
end |
||
第1,228行: | 第1,869行: | ||
return result, count |
return result, count |
||
end |
end |
||
− | |||
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------ |
--[[--------------------------< A N C H O R _ I D >------------------------------------------------------------ |
||
第1,237行: | 第1,877行: | ||
]] |
]] |
||
− | |||
local function anchor_id (namelist, year) |
local function anchor_id (namelist, year) |
||
local names={}; -- a table for the one to four names and year |
local names={}; -- a table for the one to four names and year |
||
第1,256行: | 第1,895行: | ||
--[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- |
--[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- |
||
− | Evaluates the content of |
+ | 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. |
the et al. is removed, a flag is set to true and the function returns the modified name and the flag. |
||
This function never sets the flag to false but returns it's previous state because it may have been set by |
This function never sets the flag to false but returns it's previous state because it may have been set by |
||
− | previous passes through this function or by the |
+ | 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 name_has_etal (name, etal, nocat) |
if is_set (name) then -- name can be nil in which case just return |
if is_set (name) then -- name can be nil in which case just return |
||
+ | local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme |
||
− | local patterns = cfg.et_al_patterns; --get patterns from configuration |
||
+ | local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. |
||
− | + | if name:match (etal_pattern) then -- variants on et al. |
|
− | + | name = name:gsub (etal_pattern, ''); -- if found, remove |
|
+ | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
||
− | name = name:gsub (pattern, ''); -- remove the offending text |
||
− | + | if not nocat then -- no categorization for |vauthors= |
|
− | + | add_maint_cat ('etal'); -- and add a category if not already added |
|
+ | end |
||
− | table.insert( z.message_tail, {set_error ('etal', {param})}); -- and set an error if not added |
||
+ | elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? |
||
− | end |
||
+ | name = name:gsub (others_pattern, ''); -- if found, remove |
||
+ | etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
||
+ | if not nocat then -- no categorization for |vauthors= |
||
+ | add_maint_cat ('etal'); -- and add a category if not already added |
||
end |
end |
||
end |
end |
||
end |
end |
||
− | |||
return name, etal; -- |
return name, etal; -- |
||
end |
end |
||
− | |||
− | |||
− | --[[--------------------------< N A M E _ I S _ N U M E R I C >------------------------------------------------ |
||
− | |||
− | Add maint cat when name parameter value does not contain letters. Does not catch mixed alphanumeric names so |
||
− | |last=A. Green (1922-1987) does not get caught in the current version of this test but |first=(1888) is caught. |
||
− | |||
− | returns nothing |
||
− | |||
− | ]] |
||
− | |||
− | local function name_is_numeric (name, list_name) |
||
− | if is_set (name) then |
||
− | if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters |
||
− | add_maint_cat ('numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template |
||
− | end |
||
− | end |
||
− | end |
||
− | |||
− | |||
− | --[[--------------------------< N A M E _ H A S _ E D _ M A R K U P >------------------------------------------ |
||
− | |||
− | Evaluates the content of author and editor parameters for 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. |
||
− | |||
− | returns nothing |
||
− | |||
− | ]] |
||
− | |||
− | local function name_has_ed_markup (name, list_name) |
||
− | local patterns = cfg.editor_markup_patterns; -- get patterns from configuration |
||
− | |||
− | 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 |
||
− | |||
− | |||
− | --[[--------------------------< N A M E _ H A S _ M U L T _ N A M E S >---------------------------------------- |
||
− | |||
− | 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. |
||
− | |||
− | returns nothing |
||
− | |||
− | ]] |
||
− | |||
− | 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 |
||
− | end |
||
− | |||
− | |||
− | --[[--------------------------< N A M E _ C H E C K S >-------------------------------------------------------- |
||
− | |||
− | This function calls various name checking functions used to validate the content of the various name-holding |
||
− | parameters. |
||
− | |||
− | ]] |
||
− | |||
− | local function name_checks (last, first, list_name) |
||
− | if is_set (last) then |
||
− | if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
||
− | last = last:match ('^%(%((.*)%)%)$'); -- strip parens |
||
− | else |
||
− | name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) |
||
− | name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation |
||
− | name_is_numeric (last, list_name); -- check for names that are compsed of digits and punctuation |
||
− | end |
||
− | end |
||
− | if is_set (first) then |
||
− | if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
||
− | first = first:match ('^%(%((.*)%)%)$'); -- strip parens |
||
− | else |
||
− | name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation |
||
− | name_is_numeric (first, list_name); -- check for names that are compsed of digits and punctuation |
||
− | end |
||
− | end |
||
− | return last, first; -- done |
||
− | end |
||
− | |||
--[[--------------------------< E X T R A C T _ N A M E S >---------------------------------------------------- |
--[[--------------------------< E X T R A C T _ N A M E S >---------------------------------------------------- |
||
第1,404行: | 第1,953行: | ||
local etal=false; -- return value set to true when we find some form of et al. in an author parameter |
local etal=false; -- return value set to true when we find some form of et al. in an author parameter |
||
+ | local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary |
||
− | local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging |
||
while true do |
while true do |
||
− | last |
+ | last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 |
− | first |
+ | first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ); |
− | link |
+ | link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); |
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); |
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); |
||
− | last, etal = name_has_etal (last, etal, false |
+ | last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al. |
− | first, etal = name_has_etal (first, etal, false |
+ | 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 |
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', { |
+ | 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? |
elseif not first and not last then -- if both firstn and lastn aren't found, are we done? |
||
count = count + 1; -- number of times we haven't found last and first |
count = count + 1; -- number of times we haven't found last and first |
||
第1,423行: | 第1,971行: | ||
end |
end |
||
else -- we have last with or without a first |
else -- we have last with or without a first |
||
+ | if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last |
||
− | link_title_ok (link, link_alias, last, last_alias); -- check for improper wikimarkup |
||
+ | table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link; |
||
− | if first then |
||
− | link_title_ok (link, link_alias, first, first_alias); -- check for improper wikimarkup |
||
end |
end |
||
− | |||
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) |
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 |
n = n + 1; -- point to next location in the names table |
||
if 1 == count then -- if the previous name was missing |
if 1 == count then -- if the previous name was missing |
||
− | table.insert( z.message_tail, { set_error( 'missing_name', { |
+ | table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message |
end |
end |
||
count = 0; -- reset the counter, we're looking for two consecutive missing names |
count = 0; -- reset the counter, we're looking for two consecutive missing names |
||
第1,441行: | 第1,987行: | ||
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 |
||
− | --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ |
||
+ | 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 |
||
+ | ]] |
||
− | Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. |
||
+ | local function extract_ids( args ) |
||
− | Returns the language name and associated two- or three-character code. Because case of the source may be incorrect |
||
+ | local id_list = {}; -- list of identifiers found in args |
||
− | or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is |
||
+ | 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 |
||
− | found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we |
||
+ | 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 |
||
− | return the original language name string. |
||
+ | if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list |
||
+ | end |
||
+ | return id_list; |
||
+ | end |
||
+ | --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- |
||
− | mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include |
||
− | extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support |
||
− | code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they |
||
− | are used as sub-domain names: cbk-zam.wikipedia.org. A list of language names and codes supported by fetchLanguageNames() |
||
− | can be found at Template:Citation Style documentation/language/doc |
||
+ | Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs. |
||
− | Names that are included in the list will be found if that name is provided in the |language= parameter. For example, |
||
− | if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found |
||
− | and the associated code is not two or three characters, this function returns only the WikiMedia language name. |
||
+ | inputs: |
||
− | Some language names have multiple entries under different codes: |
||
+ | id_list – table of identifiers built by extract_ids() |
||
− | Aromanian has code rup and code roa-rup |
||
+ | options – table of various template parameter values used to modify some manually handled identifiers |
||
− | When this occurs, this function returns the language name and the 2- or 3-character code |
||
+ | ]] |
||
− | Adapted from code taken from Module:Check ISO 639-1. |
||
+ | |||
+ | local function build_id_list( id_list, options ) |
||
+ | local new_list, handler = {}; |
||
+ | |||
+ | function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end; |
||
+ | |||
+ | 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 == 'HDL' then |
||
+ | table.insert( new_list, {handler.label, hdl( v ) } ); |
||
+ | 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 == 'EISSN' then |
||
+ | table.insert( new_list, {handler.label, issn( v, true ) } ); -- true distinguishes eissn from issn |
||
+ | 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 |
||
+ | |||
+ | function comp( a, b ) -- used in following table.sort() |
||
+ | return a[1] < b[1]; |
||
+ | end |
||
+ | |||
+ | table.sort( new_list, comp ); |
||
+ | for k, v in ipairs( new_list ) do |
||
+ | new_list[k] = v[2]; |
||
+ | end |
||
+ | |||
+ | return new_list; |
||
+ | end |
||
+ | |||
+ | |||
+ | --[[--------------------------< C O I N S _ C L E A N U P >---------------------------------------------------- |
||
+ | |||
+ | Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities. |
||
+ | |||
+ | 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate content |
||
+ | when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 |
||
+ | TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible |
||
+ | characters table? |
||
]] |
]] |
||
− | local function |
+ | local function coins_cleanup (value) |
+ | value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content |
||
− | 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) |
||
+ | value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s |
||
− | 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 |
||
+ | 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 |
||
+ | |||
+ | |||
+ | --[[--------------------------< C O I N S >-------------------------------------------------------------------- |
||
+ | |||
+ | COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | local function COinS(data, class) |
||
+ | if 'table' ~= type(data) or nil == next(data) then |
||
+ | return ''; |
||
+ | end |
||
+ | |||
+ | for k, v in pairs (data) do -- spin through all of the metadata parameter values |
||
+ | if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) |
||
+ | data[k] = coins_cleanup (v); |
||
+ | end |
||
end |
end |
||
+ | local ctx_ver = "Z39.88-2004"; |
||
− | local ietf_code; -- because some languages have both ietf-like codes and iso 639-like codes |
||
− | local ietf_name; |
||
+ | -- treat table strictly as an array with only set values. |
||
− | local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia |
||
+ | local OCinSoutput = setmetatable( {}, { |
||
+ | __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 |
||
+ | |||
+ | --[[ |
||
+ | for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? |
||
+ | local id, value = cfg.id_handlers[k].COinS; |
||
+ | if k == 'ISBN' then value = clean_isbn( v ); else value = v; end |
||
+ | if string.sub( id or "", 1, 4 ) == 'info' then |
||
+ | OCinSoutput["rft_id"] = table.concat{ id, "/", v }; |
||
+ | else |
||
+ | OCinSoutput[ id ] = value; |
||
+ | end |
||
+ | end |
||
+ | ]] |
||
+ | local last, first; |
||
+ | for k, v in ipairs( data.Authors ) do |
||
+ | last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers |
||
+ | if k == 1 then -- for the first author name only |
||
+ | if is_set(last) and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name |
||
+ | OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation |
||
+ | OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation |
||
+ | elseif is_set(last) then |
||
+ | OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name |
||
+ | end |
||
+ | else -- for all other authors |
||
+ | if is_set(last) and is_set(first) then |
||
+ | OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation |
||
+ | elseif is_set(last) then |
||
+ | OCinSoutput["rft.au"] = last; -- book, journal, dissertation |
||
+ | end |
||
+ | end |
||
+ | end |
||
+ | |||
+ | 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 |
||
+ | |||
+ | |||
+ | --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ |
||
+ | |||
+ | Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian where |
||
+ | ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR. |
||
+ | |||
+ | Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia |
||
+ | uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along |
||
+ | with the code. When there is no match, we return the original language name string. |
||
+ | |||
+ | mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included |
||
+ | in the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan Aramaic, that name will be |
||
+ | found with the associated code 'sam', not an ISO639-1 code. When names are found and the associated code is not two characters, this function |
||
+ | returns only the Wikimedia language name. |
||
+ | |||
+ | Adapted from code taken from Module:Check ISO 639-1. |
||
+ | |||
+ | ]] |
||
+ | |||
+ | 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(mw.getContentLanguage():getCode(), 'all') -- get a list of language names known to Wikimedia |
||
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) |
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) |
||
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons |
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 |
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 langlc == mw.ustring.lower(name) then |
||
− | if 2 |
+ | if 2 ~= code:len() then -- ISO639-1 codes only |
− | return name |
+ | return name; -- so return the name but not the code |
end |
end |
||
− | + | return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code |
|
− | ietf_name = name; -- but keep looking for a 2- or 3-char code |
||
end |
end |
||
end |
end |
||
− | + | return lang; -- not valid language; return language in original case and nil for ISO639-1 code |
|
− | return ietf_code and ietf_name or lang; -- associated name; return original language text else |
||
end |
end |
||
− | |||
--[[--------------------------< L A N G U A G E _ P A R A M E T E R >------------------------------------------ |
--[[--------------------------< 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. |
|
− | use the returned name; if not, then use the value that was provided with the language parameter. |
||
+ | There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and |
||
− | When |language= contains a recognized language (either code or name), the page is assigned to the category for |
||
+ | Norwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appears |
||
− | that code: Category:Norwegian-language sources (no). For valid three-character code languages, the page is assigned |
||
+ | 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. |
||
− | to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. |
||
+ | 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 |
||
− | Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character |
||
+ | return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them. |
||
− | equivalents of two-character codes: code 'ar' is recognized but code 'ara' is not. |
||
+ | See Help talk:Citation Style_1#An ISO 639-1 language name test |
||
− | This function supports multiple languages in the form |language=nb, French, th where the language names or codes are |
||
+ | |||
− | separated from each other by commas with optional space characters. |
||
+ | When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if |
||
+ | the page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way. |
||
+ | |||
+ | This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas. |
||
]] |
]] |
||
local function language_parameter (lang) |
local function language_parameter (lang) |
||
− | local code; -- the |
+ | local code; -- the ISO639-1 two character code |
local name; -- the language name |
local name; -- the language name |
||
local language_list = {}; -- table of language names to be rendered |
local language_list = {}; -- table of language names to be rendered |
||
local names_table = {}; -- table made from the value assigned to |language= |
local names_table = {}; -- table made from the value assigned to |language= |
||
− | |||
− | local this_wiki_name = mw.language.fetchLanguageName(cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name |
||
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
||
for _, lang in ipairs (names_table) do -- reuse lang |
for _, lang in ipairs (names_table) do -- reuse lang |
||
− | name = cfg.lang_code_remap[lang:lower()]; -- first see if this is a code that is not supported by MediaWiki but is in remap |
||
+ | if lang:match ('^%a%a%-') or 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes) |
||
− | if name then -- there was a remapped code so |
||
− | if |
+ | if lang:match ('^zh-') then |
+ | name = mw.language.fetchLanguageName( lang:lower(), lang:lower() ); |
||
− | lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip ietf tags from code |
||
− | + | else |
|
+ | name = mw.language.fetchLanguageName( lang:lower(), mw.getContentLanguage():getCode() ); -- get ISO 639-1 language name if Language is a proper code |
||
− | else |
||
− | lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip any ietf-like tags from code |
||
− | if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code |
||
− | name = mw.language.fetchLanguageName (lang:lower(), cfg.this_wiki_code); -- get language name if |language= is a proper code |
||
end |
end |
||
end |
end |
||
+ | |||
− | |||
− | if is_set (name) then -- if |
+ | if is_set (name) then -- if Language specified a valid ISO639-1 code |
code = lang:lower(); -- save it |
code = lang:lower(); -- save it |
||
else |
else |
||
− | name, code = get_iso639_code (lang |
+ | name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) |
end |
end |
||
− | if is_set (code) then |
+ | if is_set (code) then |
− | + | if 'no' == code then name = '挪威语' end; -- override wikimedia when code is 'no' |
|
+ | if 'zh' ~= code and not code:match ('^zh-') then -- English not the language |
||
− | |||
+ | add_prop_cat ('foreign_lang_source', {name, code}) |
||
− | if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language |
||
− | if 2 == code:len() then -- and is a two-character code |
||
− | add_prop_cat ('foreign_lang_source' .. code, {name, code}); -- categorize it; code appended to allow for multiple language categorization |
||
− | else -- or is a recognized language (but has a three-character code) |
||
− | add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template |
||
− | end |
||
− | elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled |
||
− | add_prop_cat ('local_lang_source', {name, code}); -- categorize it |
||
end |
end |
||
else |
else |
||
第1,564行: | 第2,341行: | ||
code = #language_list -- reuse code as number of languages in the list |
code = #language_list -- reuse code as number of languages in the list |
||
if 2 >= code then |
if 2 >= code then |
||
− | name = table.concat (language_list, |
+ | name = table.concat (language_list, '及') -- insert '及' between two language names |
elseif 2 < code then |
elseif 2 < code then |
||
+ | language_list[code] = '及' .. language_list[code]; -- prepend last name with '及' |
||
− | name = table.concat (language_list, cfg.messages['parameter-separator'], 1, code-1); -- concatenate all but last |
||
− | name = table.concat ( |
+ | name = table.concat (language_list, '、'); -- and concatenate with '<comma><space>' separators |
+ | name = name:gsub ('、及', '及', 1); |
||
− | end |
||
− | if this_wiki_name == name then |
||
− | return ''; -- if one language and that language is this wiki's return an empty string (no annotation) |
||
end |
end |
||
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' |
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' |
||
− | --[[ TODO: should only return blank or name rather than full list |
||
− | so we can clean up the bunched parenthetical elements Language, Type, Format |
||
− | ]] |
||
end |
end |
||
− | |||
--[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- |
--[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- |
||
Set style settings for CS1 citation templates. Returns separator and postscript settings |
Set style settings for CS1 citation templates. Returns separator and postscript settings |
||
− | At en.wiki, for cs1: |
||
− | ps gets: '.' |
||
− | sep gets: '.' |
||
]] |
]] |
||
local function set_cs1_style (ps) |
local function set_cs1_style (ps) |
||
− | if not is_set (ps) then -- unless |
+ | if not is_set (ps) then -- unless explicitely set to something |
− | ps = |
+ | ps = '.'; -- terminate the rendered citation with a period |
end |
end |
||
− | return |
+ | return '.', ps; -- separator is a full stop |
end |
end |
||
− | |||
--[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- |
--[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- |
||
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings |
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings |
||
− | At en.wiki, for cs2: |
||
− | ps gets: '' (empty string - no terminal punctuation) |
||
− | sep gets: ',' |
||
]] |
]] |
||
第1,607行: | 第2,371行: | ||
local function set_cs2_style (ps, ref) |
local function set_cs2_style (ps, ref) |
||
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default |
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default |
||
− | ps = |
+ | ps = ''; -- make sure it isn't nil |
end |
end |
||
if not is_set (ref) then -- if |ref= is not set |
if not is_set (ref) then -- if |ref= is not set |
||
ref = "harv"; -- set default |ref=harv |
ref = "harv"; -- set default |ref=harv |
||
end |
end |
||
− | return |
+ | return ',', ps, ref; -- separator is a comma |
end |
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 >---------------------- |
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- |
||
第1,633行: | 第2,396行: | ||
return sep, ps, ref -- return them all |
return sep, ps, ref -- return them all |
||
end |
end |
||
− | |||
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ |
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ |
||
第1,651行: | 第2,413行: | ||
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass |
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass |
||
end |
end |
||
+ | if 'none' == ps:lower() then -- if assigned value is 'none' then |
||
− | |||
− | if cfg.keywords_xlate[ps:lower()] == 'none' then -- if assigned value is 'none' then |
||
ps = ''; -- set to empty string |
ps = ''; -- set to empty string |
||
end |
end |
||
第1,658行: | 第2,419行: | ||
return sep, ps, ref |
return sep, ps, ref |
||
end |
end |
||
− | |||
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------ |
--[=[-------------------------< I S _ P D F >------------------------------------------------------------------ |
||
第1,665行: | 第2,425行: | ||
applying the pdf icon to external links. |
applying the pdf icon to external links. |
||
− | returns true if file extension is one of the recognized |
+ | returns true if file extension is one of the recognized extension, else false |
]=] |
]=] |
||
local function is_pdf (url) |
local function is_pdf (url) |
||
− | return url:match ('%.pdf |
+ | return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?'); |
− | url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or |
||
− | url:match ('%.PDF#') or url:match ('%.pdf#'); |
||
end |
end |
||
− | |||
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ |
--[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ |
||
第1,687行: | 第2,444行: | ||
local function style_format (format, url, fmt_param, url_param) |
local function style_format (format, url, fmt_param, url_param) |
||
if is_set (format) then |
if is_set (format) then |
||
− | format = wrap_style ('format', format); -- add leading space, |
+ | format = wrap_style ('format', format); -- add leading space, parenthases, resize |
if not is_set (url) then |
if not is_set (url) then |
||
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message |
format = format .. set_error( 'format_missing_url', {fmt_param, url_param} ); -- add an error message |
||
第1,699行: | 第2,456行: | ||
end |
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. |
||
− | --[[--------------------------< G E T _ D I S P L A Y _ N A M E S >-------------------------------------------- |
||
− | |||
− | Returns a number that defines the number of names displayed for author and editor name lists and a boolean flag |
||
− | to indicate when et al. should be appended to the name list. |
||
− | When the value assigned to |display- |
+ | 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 |
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.'). |
some variant of the text 'et al.'). |
||
− | When the value assigned to |display- |
+ | 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 |
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.' |
the names in the name list followed by 'et al.' |
||
In all other cases, returns nil and the previous state of the 'etal' flag. |
In all other cases, returns nil and the previous state of the 'etal' flag. |
||
− | |||
− | inputs: |
||
− | max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal |
||
− | count: #a or #e |
||
− | list_name: 'authors' or 'editors' |
||
− | etal: author_etal or editor_etal |
||
]] |
]] |
||
− | local function |
+ | local function get_display_authors_editors (max, count, list_name, etal) |
if is_set (max) then |
if is_set (max) then |
||
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings |
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings |
||
第1,730行: | 第2,479行: | ||
elseif max:match ('^%d+$') then -- if is a string of numbers |
elseif max:match ('^%d+$') then -- if is a string of numbers |
||
max = tonumber (max); -- make it a number |
max = tonumber (max); -- make it a number |
||
− | if max >= count then |
+ | if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors |
− | add_maint_cat (' |
+ | add_maint_cat ('disp_auth_ed', list_name); |
end |
end |
||
else -- not a valid keyword or number |
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 |
table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message |
||
− | max = nil; -- unset |
+ | max = nil; -- unset |
end |
end |
||
+ | elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category |
||
+ | max = count + 1; -- number of authors + 1 |
||
end |
end |
||
return max, etal; |
return max, etal; |
||
end |
end |
||
− | |||
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------ |
--[[--------------------------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >------------------------------ |
||
第1,755行: | 第2,505行: | ||
local function extra_text_in_page_check (page) |
local function extra_text_in_page_check (page) |
||
+ | -- local good_pattern = '^P[^%.P%l]'; |
||
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? |
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? |
||
+ | -- local bad_pattern = '^[Pp][Pp]'; |
||
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; |
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; |
||
第1,761行: | 第2,513行: | ||
add_maint_cat ('extra_text'); |
add_maint_cat ('extra_text'); |
||
end |
end |
||
+ | -- if Page:match ('^[Pp]?[Pp]%.?[ %d]') or Page:match ('^[Pp]ages?[ %d]') or |
||
− | end |
||
+ | -- Pages:match ('^[Pp]?[Pp]%.?[ %d]') or Pages:match ('^[Pp]ages?[ %d]') then |
||
− | |||
+ | -- add_maint_cat ('extra_text'); |
||
− | |||
+ | -- end |
||
− | --[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- |
||
− | |||
− | split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled |
||
− | 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 |
||
− | |||
− | |vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.)) |
||
− | |||
− | ]=] |
||
− | |||
− | local function get_v_name_table (vparam, output_table, output_link_table) |
||
− | local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas |
||
− | local wl_type, label, link; -- wl_type not used here; just a place holder |
||
− | |||
− | local i = 1; |
||
− | |||
− | while name_table[i] do |
||
− | if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parens |
||
− | local name = name_table[i]; |
||
− | 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 |
||
− | i = i+1; |
||
− | end |
||
− | return output_table; |
||
end |
end |
||
第1,816行: | 第2,528行: | ||
may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance |
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. |
tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests. |
||
− | |||
− | Supports generational suffixes Jr, 2nd, 3rd, 4th–6th. |
||
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials. |
This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials. |
||
第1,826行: | 第2,536行: | ||
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= |
local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= |
||
local v_name_table = {}; |
local v_name_table = {}; |
||
− | local v_link_table = {}; -- when name is wikilinked, targets go in this table |
||
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter |
local etal = false; -- return value set to true when we find some form of et al. vauthors parameter |
||
− | local last, first, link, mask |
+ | local last, first, link, mask; |
local corporate = false; |
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) |
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 |
||
− | v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas |
||
+ | 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 |
for i, v_name in ipairs(v_name_table) do |
||
− | if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled |
+ | if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection |
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
||
− | last = v_name:match ('^%(%((.+)%)%)$') |
+ | last = v_name:match ('^%(%((.+)%)%)$') |
− | corporate = true; |
+ | corporate = true; |
elseif string.find(v_name, "%s") then |
elseif string.find(v_name, "%s") then |
||
+ | lastfirstTable = {} |
||
− | if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; |
||
+ | lastfirstTable = mw.text.split(v_name, "%s") |
||
− | add_vanc_error (cfg.err_msg_supl.punctuation); |
||
+ | first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials |
||
− | end |
||
+ | last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials |
||
− | local lastfirstTable = {} |
||
+ | if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then |
||
− | lastfirstTable = mw.text.split(v_name, "%s") |
||
+ | add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials |
||
− | 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 (cfg.err_msg_supl['missing comma']); -- matches last II last; the case when a comma is missing |
||
− | end |
||
− | if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test |
||
− | add_vanc_error (cfg.err_msg_supl.name); -- matches a space between two intiials |
||
end |
end |
||
else |
else |
||
第1,862行: | 第2,564行: | ||
end |
end |
||
+ | if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else |
||
− | if is_set (first) then |
||
+ | add_vanc_error (); |
||
− | if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else |
||
− | add_vanc_error (cfg.err_msg_supl.initials); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials |
||
− | 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 |
||
− | else |
||
− | if not corporate then |
||
− | is_good_vanc_name (last, ''); |
||
− | end |
||
end |
end |
||
+ | -- this from extract_names () |
||
− | |||
− | link = select_one( args, cfg.aliases[list_name .. '-Link'], '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 ); |
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 |
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list |
||
第1,883行: | 第2,574行: | ||
return names, etal; -- all done, return our list of names |
return names, etal; -- all done, return our list of names |
||
end |
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 >------------------------ |
--[[--------------------------< S E L E C T _ A U T H O R _ E D I T O R _ S O U R C E >------------------------ |
||
第1,904行: | 第2,594行: | ||
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) |
local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) |
||
− | + | local lastfirst = false; |
|
− | if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a |
+ | if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1 |
− | select_one( args, cfg.aliases[list_name .. '- |
+ | select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then |
− | select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or |
||
− | select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then |
||
lastfirst=true; |
lastfirst=true; |
||
end |
end |
||
第1,935行: | 第2,623行: | ||
This function is used to validate a parameter's assigned value for those parameters that have only a limited number |
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, |
+ | of allowable values (yes, y, true, no, etc). When the parameter value has not been assigned a value (missing or empty |
− | + | in the source template) the function refurns true. If the parameter value is one of the list of allowed values returns |
|
− | + | true; else, emits an error message and returns false. |
|
− | specified by ret_val. |
||
]] |
]] |
||
− | local function is_valid_parameter_value (value, name, possible |
+ | local function is_valid_parameter_value (value, name, possible) |
if not is_set (value) then |
if not is_set (value) then |
||
− | return |
+ | return true; -- an empty parameter is ok |
− | elseif in_array |
+ | elseif in_array(value:lower(), possible) then |
+ | return true; |
||
− | return cfg.keywords_xlate[value]; -- return translation of parameter keyword |
||
else |
else |
||
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message |
table.insert( z.message_tail, { set_error( 'invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message |
||
− | return |
+ | return false |
end |
end |
||
end |
end |
||
第1,964行: | 第2,651行: | ||
local function terminate_name_list (name_list, sepc) |
local function terminate_name_list (name_list, sepc) |
||
− | if (string.sub (name_list,-3,-1) == sepc .. ' |
+ | if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char |
− | return name_list; -- just return the name list |
||
− | elseif (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char |
||
return name_list .. " "; -- don't add another |
return name_list .. " "; -- don't add another |
||
else |
else |
||
第1,995行: | 第2,680行: | ||
end |
end |
||
end |
end |
||
+ | |||
− | |||
+ | local vol = ''; |
||
− | if 'podcast' == cite_class and is_set (issue) then |
||
− | return wrap_msg ('issue', {sepc, issue}, lower); |
||
− | end |
||
− | |||
− | local vol = ''; -- here for all cites except magazine |
||
if is_set (volume) then |
if is_set (volume) then |
||
+ | if (6 < mw.ustring.len(volume)) then |
||
− | if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase roman numerals |
||
− | vol = substitute (cfg. |
+ | vol = substitute (cfg.messages['j-vol'], {sepc, volume}); |
+ | else |
||
− | elseif (4 < mw.ustring.len(volume)) then -- not all digits or roman numerals and longer than 4 characters |
||
− | vol = |
+ | vol = wrap_style ('vol-bold', hyphen_to_dash(volume)); |
− | add_prop_cat ('long_vol'); |
||
− | else -- four or less characters |
||
− | vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold |
||
end |
end |
||
end |
end |
||
第2,046行: | 第2,724行: | ||
end |
end |
||
− | local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map |
+ | local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'journal' == origin); |
+ | |||
− | |||
if is_set (page) then |
if is_set (page) then |
||
if is_journal then |
if is_journal then |
||
第2,059行: | 第2,737行: | ||
if is_journal then |
if is_journal then |
||
return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; |
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 |
+ | 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}), '', ''; |
return '', substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; |
||
elseif not nopp then |
elseif not nopp then |
||
第2,070行: | 第2,748行: | ||
return '', '', '', ''; -- return empty strings |
return '', '', '', ''; -- return empty strings |
||
end |
end |
||
− | |||
− | |||
− | --[[--------------------------< I N S O U R C E _ L O C _ G E T >---------------------------------------------- |
||
− | |||
− | returns one of the in-source locators: page, pages, or at. |
||
− | |||
− | If any of these are interwiki links to wikisource, returns the label portion of the interwikilink as plain text |
||
− | for use in COinS. This COinS thing is done because here we convert an interwiki link to and external link and |
||
− | add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? |
||
− | |||
− | TODO: add support for sheet and sheets?; streamline; |
||
− | |||
− | TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned |
||
− | to a new name)? |
||
− | |||
− | ]] |
||
− | |||
− | local function insource_loc_get (page, pages, at) |
||
− | local ws_url, ws_label, coins_pages, L; -- for wikisource interwikilinks; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?) |
||
− | |||
− | 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. |
||
− | |||
− | ws_url, ws_label, L = wikisource_url_make (page); -- make ws url from |page= interwiki link; link portion L becomes tool tip label |
||
− | if ws_url then |
||
− | page = external_link (ws_url, ws_label .. ' ', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
||
− | page = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page}); |
||
− | coins_pages = ws_label; |
||
− | end |
||
− | 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. |
||
− | |||
− | ws_url, ws_label, L = wikisource_url_make (pages); -- make ws url from |pages= interwiki link; link portion L becomes tool tip label |
||
− | if ws_url then |
||
− | pages = external_link (ws_url, ws_label .. ' ', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
||
− | pages = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages}); |
||
− | coins_pages = ws_label; |
||
− | end |
||
− | elseif is_set (at) then |
||
− | ws_url, ws_label, L = wikisource_url_make (at); -- make ws url from |at= interwiki link; link portion L becomes tool tip label |
||
− | if ws_url then |
||
− | at = external_link (ws_url, ws_label .. ' ', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
||
− | at = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at}); |
||
− | coins_pages = ws_label; |
||
− | end |
||
− | end |
||
− | |||
− | return page, pages, at, coins_pages; |
||
− | end |
||
− | |||
− | |||
− | --[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- |
||
− | |||
− | Check archive.org urls to make sure they at least look like they are pointing at valid archives and not to the |
||
− | save snapshot url or to calendar pages. When the archive url is 'https://web.archive.org/save/' (or http://...) |
||
− | archive.org saves a snapshot of the target page in the url. That is something that Wikipedia should not allow |
||
− | unwitting readers to do. |
||
− | |||
− | When the archive.org url does not have a complete timestamp, archive.org chooses a snapshot according to its own |
||
− | algorithm or provides a calendar 'search' result. [[WP:ELNO]] discourages links to search results. |
||
− | |||
− | This function looks at the value assigned to |archive-url= and returns empty strings for |archive-url= and |
||
− | |archive-date= and an error message when: |
||
− | |archive-url= holds an archive.org save command url |
||
− | |archive-url= is an archive.org url that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the |
||
− | correct place |
||
− | otherwise returns |archive-url= and |archive-date= |
||
− | |||
− | There are two mostly compatible archive.org urls: |
||
− | //web.archive.org/<timestamp>... -- the old form |
||
− | //web.archive.org/web/<timestamp>... -- the new form |
||
− | |||
− | The old form does not support or map to the new form when it contains a display flag. There are four identified flags |
||
− | ('id_', 'js_', 'cs_', 'im_') but since archive.org ignores others following the same form (two letters and an underscore) |
||
− | we don't check for these specific flags but we do check the form. |
||
− | |||
− | This function supports a preview mode. When the article is rendered in preview mode, this 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*/) |
||
− | |||
− | ]=] |
||
− | |||
− | local function archive_url_check (url, date) |
||
− | 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 |
||
− | |||
− | if url:match('//web%.archive%.org/save/') then -- if a save command url, we don't want to allow saving of the target page |
||
− | err_msg = cfg.err_msg_supl.save; |
||
− | url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL |
||
− | elseif url:match('//liveweb%.archive%.org/') then |
||
− | err_msg = cfg.err_msg_supl.liveweb; |
||
− | else |
||
− | path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the url parts for evaluation |
||
− | |||
− | if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here |
||
− | err_msg = cfg.err_msg_supl.timestamp; |
||
− | if '*' ~= flag then |
||
− | url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat) |
||
− | end |
||
− | elseif is_set(path) and 'web/' ~= path then -- older archive urls do not have the extra 'web/' path element |
||
− | err_msg = cfg.err_msg_supl.path; |
||
− | elseif is_set (flag) and not is_set (path) then -- flag not allowed with the old form url (without the 'web/' path element) |
||
− | err_msg = cfg.err_msg_supl.flag; |
||
− | elseif is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element) |
||
− | err_msg = cfg.err_msg_supl.flag; |
||
− | else |
||
− | return url, date; -- return ArchiveURL and ArchiveDate |
||
− | end |
||
− | end |
||
− | -- 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 |
||
− | |||
− | |||
− | --[[--------------------------< P L A C E _ C H E C K >-------------------------------------------------------- |
||
− | |||
− | check |place=, |publication-place=, |location= to see if these params include digits. This function added because |
||
− | many editors mis-use location to specify the in-source location (|page(s)= and |at= are supposed to do that) |
||
− | |||
− | returns the original parameter value without modification; added maint cat when parameter value contains digits |
||
− | |||
− | ]] |
||
− | |||
− | local function place_check (param_val) |
||
− | if not is_set (param_val) then -- parameter empty or omitted |
||
− | return param_val; -- return that empty state |
||
− | end |
||
− | |||
− | if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value |
||
− | add_maint_cat ('location'); -- yep, add maint cat |
||
− | end |
||
− | |||
− | return param_val; -- and done |
||
− | end |
||
− | |||
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ |
--[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ |
||
第2,240行: | 第2,765行: | ||
-- Pick out the relevant fields from the arguments. Different citation templates |
-- Pick out the relevant fields from the arguments. Different citation templates |
||
-- define different field names for the same underlying things. |
-- define different field names for the same underlying things. |
||
− | |||
− | local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], ''); |
||
− | |||
local author_etal; |
local author_etal; |
||
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
||
local Authors; |
local Authors; |
||
+ | local NameListFormat = A['NameListFormat']; |
||
− | |||
− | local NameListFormat = is_valid_parameter_value (A['NameListFormat'], A:ORIGIN('NameListFormat'), cfg.keywords_lists['name-list-format'], ''); |
||
− | local Collaboration = A['Collaboration']; |
||
do -- to limit scope of selected |
do -- to limit scope of selected |
||
第2,259行: | 第2,779行: | ||
elseif 3 == selected then |
elseif 3 == selected then |
||
Authors = A['Authors']; -- use content of |authors= |
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 |
||
end |
end |
||
+ | local Coauthors = A['Coauthors']; |
||
local Others = A['Others']; |
local Others = A['Others']; |
||
第2,283行: | 第2,798行: | ||
elseif 3 == selected then |
elseif 3 == selected then |
||
Editors = A['Editors']; -- use content of |editors= |
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 |
||
end |
end |
||
− | local translator_etal; |
||
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs |
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs |
||
local Translators; -- assembled translators name list |
local Translators; -- assembled translators name list |
||
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
||
+ | |||
− | |||
− | local interviewer_etal; |
||
− | local interviewers_list = {}; |
||
− | local Interviewers; -- used later |
||
− | interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters |
||
− | |||
− | local contributor_etal; |
||
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
||
local Contributors; -- assembled contributors name list |
local Contributors; -- assembled contributors name list |
||
− | local Contribution = A['Contribution']; |
+ | local Contribution = A['Contribution']; |
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites |
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites |
||
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= |
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= |
||
第2,321行: | 第2,828行: | ||
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' |
||
− | if is_set (Others) then |
||
+ | NameListFormat = ''; -- anything else, set to empty string |
||
− | if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= |
||
− | add_maint_cat ('others'); |
||
− | end |
||
end |
end |
||
第2,340行: | 第2,845行: | ||
local TitleNote = A['TitleNote']; |
local TitleNote = A['TitleNote']; |
||
local TitleLink = A['TitleLink']; |
local TitleLink = A['TitleLink']; |
||
+ | if is_set (TitleLink) and false == link_param_ok (TitleLink) then |
||
− | link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set |
||
+ | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=; |
||
+ | end |
||
+ | local Chapter = A['Chapter']; |
||
− | local Chapter = A['Chapter']; -- TODO: insert test, assignment, and then unset Chapter when |section= in cite map; test is at c. line 3220 |
||
local ScriptChapter = A['ScriptChapter']; |
local ScriptChapter = A['ScriptChapter']; |
||
− | local ScriptChapterOrigin = A:ORIGIN ('ScriptChapter'); |
||
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode |
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode |
||
local TransChapter = A['TransChapter']; |
local TransChapter = A['TransChapter']; |
||
第2,351行: | 第2,857行: | ||
local Docket = A['Docket']; |
local Docket = A['Docket']; |
||
local ArchiveFormat = A['ArchiveFormat']; |
local ArchiveFormat = A['ArchiveFormat']; |
||
+ | local ArchiveURL = A['ArchiveURL']; |
||
− | |||
− | local ArchiveDate; |
||
− | local ArchiveURL; |
||
− | |||
− | ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) |
||
− | |||
− | local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); |
||
− | |||
− | |||
local URL = A['URL'] |
local URL = A['URL'] |
||
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL |
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL |
||
第2,367行: | 第2,865行: | ||
local ConferenceURL = A['ConferenceURL']; |
local ConferenceURL = A['ConferenceURL']; |
||
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds 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 |
||
− | -- TODO: mailinglist should be removed from Periodical alias list; Periodical should be assigned value from |mailinglist= here wh |
||
− | local Periodical = A['Periodical']; -- cite mailinglist or citation and |mailinglist=; error check for duplicate work params (Periodical already set) |
||
− | local Periodical_origin = ''; |
||
− | if is_set (Periodical) then |
||
− | Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter |
||
− | local i; |
||
− | Periodical, i = strip_apostrophe_markup (Periodical); -- strip appostrophe markup so that metadata isn't contaminated |
||
− | if i then -- non-zero when markup was stripped so emit an error message |
||
− | table.insert( z.message_tail, {set_error ('apostrophe_markup', {Periodical_origin}, true)}); |
||
− | end |
||
− | end |
||
− | -- TODO: mailinglist assignment here? iff Periodical not set; err msg else; see TODO c. line 2607 |
||
− | local ScriptPeriodical = A['ScriptPeriodical']; |
||
− | local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); |
||
− | -- web and news not tested for now because of |
||
− | -- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors? |
||
− | if not (is_set (Periodical) or is_set (ScriptPeriodical)) then -- 'periodical' templates require periodical parameter |
||
− | -- local p = {['journal'] = 'journal', ['magazine'] = 'magazine', ['news'] = 'newspaper', ['web'] = 'website'}; -- for error message |
||
− | local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message |
||
− | if p[config.CitationClass] then |
||
− | table.insert( z.message_tail, {set_error ('missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)}); |
||
− | end |
||
− | end |
||
− | |||
− | local TransPeriodical = A['TransPeriodical']; |
||
local Series = A['Series']; |
local Series = A['Series']; |
||
第2,402行: | 第2,876行: | ||
local At; |
local At; |
||
− | if ' |
+ | if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then |
− | if is_set (Periodical) then |
||
− | if not in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals' |
||
− | Volume = A['Volume']; -- but does for all other 'periodicals' |
||
− | end |
||
− | elseif is_set (ScriptPeriodical) then |
||
− | if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website= |
||
− | Volume = A['Volume']; -- but does for all other 'periodicals' |
||
− | end |
||
− | else |
||
− | Volume = A['Volume']; -- and does for non-'periodical' cites |
||
− | end |
||
− | elseif in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings |
||
Volume = A['Volume']; |
Volume = A['Volume']; |
||
− | end |
||
− | |||
− | if 'citation' == config.CitationClass then |
||
− | if is_set (Periodical) and in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals' |
||
− | is_set (ScriptPeriodical) and in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals' |
||
− | Issue = hyphen_to_dash (A['Issue']); |
||
− | end |
||
− | elseif in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table |
||
− | if not (in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (is_set (Periodical) or is_set (ScriptPeriodical))) then |
||
− | Issue = hyphen_to_dash (A['Issue']); |
||
− | end |
||
end |
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 = ''; |
local Position = ''; |
||
if not in_array (config.CitationClass, cfg.templates_not_using_page) then |
if not in_array (config.CitationClass, cfg.templates_not_using_page) then |
||
Page = A['Page']; |
Page = A['Page']; |
||
− | Pages = hyphen_to_dash |
+ | Pages = hyphen_to_dash( A['Pages'] ); |
At = A['At']; |
At = A['At']; |
||
end |
end |
||
local Edition = A['Edition']; |
local Edition = A['Edition']; |
||
− | local PublicationPlace = |
+ | local PublicationPlace = A['PublicationPlace'] |
− | local Place = |
+ | local Place = A['Place']; |
local PublisherName = A['PublisherName']; |
local PublisherName = A['PublisherName']; |
||
− | local |
+ | local RegistrationRequired = A['RegistrationRequired']; |
+ | if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then |
||
− | if is_set (PublisherName) then |
||
+ | RegistrationRequired=nil; |
||
− | local i=0; |
||
− | PublisherName, i = strip_apostrophe_markup (PublisherName); -- strip appostrophe markup so that metadata isn't contaminated; publisher is never italicized |
||
− | |||
− | if i then -- non-zero when markup was stripped so emit an error message |
||
− | table.insert( z.message_tail, {set_error ('apostrophe_markup', {PublisherName_origin}, true)}); |
||
− | end |
||
end |
end |
||
+ | local SubscriptionRequired = A['SubscriptionRequired']; |
||
− | |||
+ | if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then |
||
− | local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup? |
||
+ | SubscriptionRequired=nil; |
||
− | local Newsgroup_origin = A:ORIGIN('Newsgroup'); |
||
− | |||
− | if 'newsgroup' == config.CitationClass then |
||
− | if is_set (PublisherName) then -- general use parmeter |publisher= not allowed in cite newsgroup |
||
− | local error_text = set_error ('parameter_ignored', {PublisherName_origin}, true); |
||
− | if is_set (error_text) then |
||
− | table.insert( z.message_tail, {error_text, error_state} ); |
||
− | end |
||
− | end |
||
− | |||
− | PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS |
||
− | end |
||
− | |||
− | local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); |
||
− | 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 |
||
− | |||
− | local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); |
||
− | if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then |
||
− | ChapterUrlAccess = nil; |
||
− | table.insert( z.message_tail, { set_error( 'param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } ); |
||
− | end |
||
− | |||
− | local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil); |
||
− | if not is_set(A['MapURL']) and is_set(MapUrlAccess) then |
||
− | MapUrlAccess = nil; |
||
− | table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'map-url'}, true ) } ); |
||
end |
end |
||
local Via = A['Via']; |
local Via = A['Via']; |
||
local AccessDate = A['AccessDate']; |
local AccessDate = A['AccessDate']; |
||
+ | local ArchiveDate = A['ArchiveDate']; |
||
local Agency = A['Agency']; |
local Agency = A['Agency']; |
||
+ | local DeadURL = A['DeadURL'] |
||
+ | if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' |
||
+ | DeadURL = ''; -- anything else, set to empty string |
||
+ | end |
||
local Language = A['Language']; |
local Language = A['Language']; |
||
第2,493行: | 第2,918行: | ||
local ID = A['ID']; |
local ID = A['ID']; |
||
local ASINTLD = A['ASINTLD']; |
local ASINTLD = A['ASINTLD']; |
||
− | local IgnoreISBN = |
+ | 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 Embargo = A['Embargo']; |
||
local Class = A['Class']; -- arxiv class identifier |
local Class = A['Class']; -- arxiv class identifier |
||
local ID_list = extract_ids( args ); |
local ID_list = extract_ids( args ); |
||
− | if is_set (DoiBroken) and not ID_list['DOI'] then |
||
− | table.insert( z.message_tail, { set_error( 'doibroken_missing_doi', A:ORIGIN('DoiBroken'))}); |
||
− | end |
||
− | local ID_access_levels = extract_id_access_levels( args, ID_list ); |
||
local Quote = A['Quote']; |
local Quote = A['Quote']; |
||
第2,513行: | 第2,937行: | ||
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL |
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL |
||
− | local LastAuthorAmp = |
+ | local LastAuthorAmp = A['LastAuthorAmp']; |
+ | if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then |
||
+ | LastAuthorAmp = nil; -- set to empty string |
||
+ | end |
||
+ | local no_tracking_cats = A['NoTracking']; |
||
+ | if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then |
||
+ | no_tracking_cats = nil; -- set to empty string |
||
+ | end |
||
+ | --these are used by cite interview |
||
− | local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil); |
||
+ | local Callsign = A['Callsign']; |
||
+ | local City = A['City']; |
||
+ | local Program = A['Program']; |
||
− | + | --local variables that are not cs1 parameters |
|
local use_lowercase; -- controls capitalization of certain static text |
local use_lowercase; -- controls capitalization of certain static text |
||
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language |
local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language |
||
第2,523行: | 第2,957行: | ||
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification |
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification |
||
+ | -- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values |
||
− | local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], ''); |
||
+ | local Mode = A['Mode']; |
||
− | if not is_set (DF) then |
||
+ | if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then |
||
− | DF = cfg.global_df; -- local df if present overrides global df set by {{use xxx date}} template |
||
+ | Mode = ''; |
||
end |
end |
||
+ | local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma |
||
− | |||
− | local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma |
||
local PostScript; |
local PostScript; |
||
− | local Ref |
+ | local Ref; |
+ | sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass); |
||
− | if 'harv' == Ref then |
||
+ | use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text |
||
− | add_maint_cat ('ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value |
||
− | elseif not is_set (Ref) then |
||
− | Ref = 'harv'; -- set as default when not set externally |
||
− | end |
||
− | |||
− | sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], 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 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 |
if in_array (this_page.nsText, cfg.uncategorized_namespaces) then |
||
第2,552行: | 第2,980行: | ||
end |
end |
||
end |
end |
||
− | -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) |
||
− | select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters'); -- this is a dummy call simply to get the error message and category |
||
+ | -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) |
||
− | local coins_pages; |
||
+ | 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 |
||
− | |||
− | Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At); |
||
− | local NoPP = |
+ | 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 (PublicationPlace) and is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different |
||
+ | if is_set(Pages) or is_set(At) then |
||
− | add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together |
||
+ | Pages = ''; -- unset the others |
||
− | if PublicationPlace == Place then |
||
+ | At = ''; |
||
− | Place = ''; -- unset; don't need both if they are the same |
||
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. |
||
− | elseif not is_set (PublicationPlace) and is_set (Place) then -- when only |place= (|location=) is set ... |
||
+ | elseif is_set(Pages) then |
||
− | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
||
+ | if is_set(At) then |
||
− | end |
||
+ | At = ''; -- unset |
||
+ | end |
||
+ | extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. |
||
+ | end |
||
+ | -- both |publication-place= and |place= (|location=) allowed if different |
||
− | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
||
+ | if not is_set(PublicationPlace) and is_set(Place) then |
||
+ | PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
||
+ | end |
||
+ | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
||
− | --[[ |
||
− | Parameter remapping for cite encyclopedia: |
||
− | When the citation has these parameters: |
||
− | |encyclopedia and |title then map |title to |article and |encyclopedia to |title |
||
− | |encyclopedia and |article then map |encyclopedia to |title |
||
− | |||
− | |trans-title maps to |trans-chapter when |title is re-mapped |
||
− | |url maps to |chapterurl when |title is remapped |
||
+ | --[[ |
||
− | All other combinations of |encyclopedia, |title, and |article are not modified |
||
+ | 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 |
||
+ | |||
+ | ]] |
||
− | + | local Encyclopedia = A['Encyclopedia']; |
|
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation |
if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation |
||
− | if is_set |
+ | if is_set(Periodical) then -- Periodical is set when |encyclopedia is set |
if is_set(Title) or is_set (ScriptTitle) then |
if is_set(Title) or is_set (ScriptTitle) then |
||
if not is_set(Chapter) then |
if not is_set(Chapter) then |
||
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
||
ScriptChapter = ScriptTitle; |
ScriptChapter = ScriptTitle; |
||
− | ScriptChapterOrigin = A:ORIGIN('ScriptTitle') |
||
TransChapter = TransTitle; |
TransChapter = TransTitle; |
||
ChapterURL = URL; |
ChapterURL = URL; |
||
− | ChapterURLorigin = A:ORIGIN('URL') |
||
− | |||
− | ChapterUrlAccess = UrlAccess; |
||
− | |||
if not is_set (ChapterURL) and is_set (TitleLink) then |
if not is_set (ChapterURL) and is_set (TitleLink) then |
||
− | Chapter |
+ | Chapter= '[[' .. TitleLink .. '|' .. Chapter .. ']]'; |
end |
end |
||
Title = Periodical; |
Title = Periodical; |
||
第2,612行: | 第3,047行: | ||
ScriptTitle = ''; |
ScriptTitle = ''; |
||
end |
end |
||
− | + | else -- |title not set |
|
− | Title = Periodical; -- |encyclopedia set and |article set so map |encyclopedia to |title |
+ | Title = Periodical; -- |encyclopedia set and |article set or not set so map |encyclopedia to |title |
Periodical = ''; -- redundant so unset |
Periodical = ''; -- redundant so unset |
||
end |
end |
||
第2,619行: | 第3,054行: | ||
end |
end |
||
− | + | -- Special case for cite techreport. |
|
if (config.CitationClass == "techreport") then -- special case for cite techreport |
if (config.CitationClass == "techreport") then -- special case for cite techreport |
||
− | if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' |
+ | if is_set(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"? |
if not is_set(ID) then -- can we use ID for the "number"? |
||
− | ID = A['Number']; -- yes, use it |
+ | ID = A['Number']; -- yes, use it |
else -- ID has a value so emit error message |
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 )}); |
table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )}); |
||
第2,630行: | 第3,065行: | ||
end |
end |
||
− | + | -- special case for cite interview |
|
− | if (config.CitationClass == " |
+ | if (config.CitationClass == "interview") then |
+ | if is_set(Program) then |
||
+ | ID = ' ' .. Program; |
||
+ | end |
||
+ | if is_set(Callsign) then |
||
+ | if is_set(ID) then |
||
+ | ID = ID .. sepc .. ' ' .. Callsign; |
||
+ | else |
||
+ | ID = ' ' .. Callsign; |
||
+ | end |
||
+ | end |
||
+ | if is_set(City) then |
||
+ | if is_set(ID) then |
||
+ | ID = ID .. sepc .. ' ' .. City; |
||
+ | else |
||
+ | ID = ' ' .. City; |
||
+ | end |
||
+ | end |
||
+ | |||
+ | if is_set(Others) then |
||
+ | if is_set(TitleType) then |
||
+ | Others = ' ' .. TitleType .. ' with ' .. Others; |
||
+ | TitleType = ''; |
||
+ | else |
||
+ | Others = ' ' .. 'Interview with ' .. Others; |
||
+ | end |
||
+ | else |
||
+ | Others = '(Interview)'; |
||
+ | end |
||
+ | end |
||
+ | |||
+ | -- special case for cite mailing list |
||
+ | if (config.CitationClass == "mailinglist") then |
||
Periodical = A ['MailingList']; |
Periodical = A ['MailingList']; |
||
− | elseif 'mailinglist' == |
+ | elseif 'mailinglist' == A:ORIGIN('Periodical') then |
Periodical = ''; -- unset because mailing list is only used for cite mailing list |
Periodical = ''; -- unset because mailing list is only used for cite mailing list |
||
end |
end |
||
− | + | -- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
|
if 'conference' == config.CitationClass then |
if 'conference' == config.CitationClass then |
||
if is_set(BookTitle) then |
if is_set(BookTitle) then |
||
Chapter = Title; |
Chapter = Title; |
||
− | + | -- ChapterLink = TitleLink; -- |chapterlink= is deprecated |
|
ChapterURL = URL; |
ChapterURL = URL; |
||
− | ChapterUrlAccess = UrlAccess; |
||
ChapterURLorigin = URLorigin; |
ChapterURLorigin = URLorigin; |
||
URLorigin = ''; |
URLorigin = ''; |
||
第2,650行: | 第3,116行: | ||
Title = BookTitle; |
Title = BookTitle; |
||
Format = ''; |
Format = ''; |
||
− | + | -- TitleLink = ''; |
|
TransTitle = ''; |
TransTitle = ''; |
||
URL = ''; |
URL = ''; |
||
第2,658行: | 第3,124行: | ||
end |
end |
||
− | + | -- cite map oddities |
|
local Cartography = ""; |
local Cartography = ""; |
||
local Scale = ""; |
local Scale = ""; |
||
第2,666行: | 第3,132行: | ||
Chapter = A['Map']; |
Chapter = A['Map']; |
||
ChapterURL = A['MapURL']; |
ChapterURL = A['MapURL']; |
||
+ | TransChapter = A['TransMap']; |
||
ChapterURLorigin = A:ORIGIN('MapURL'); |
ChapterURLorigin = A:ORIGIN('MapURL'); |
||
− | TransChapter = A['TransMap']; |
||
− | ScriptChapter = A['ScriptMap'] |
||
− | ScriptChapterOrigin = A:ORIGIN('ScriptMap') |
||
− | |||
− | ChapterUrlAccess = MapUrlAccess; |
||
ChapterFormat = A['MapFormat']; |
ChapterFormat = A['MapFormat']; |
||
+ | |||
− | |||
Cartography = A['Cartography']; |
Cartography = A['Cartography']; |
||
if is_set( Cartography ) then |
if is_set( Cartography ) then |
||
第2,684行: | 第3,146行: | ||
end |
end |
||
− | + | -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. |
|
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then |
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then |
||
+ | local AirDate = A['AirDate']; |
||
local SeriesLink = A['SeriesLink']; |
local SeriesLink = A['SeriesLink']; |
||
+ | if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then |
||
− | |||
+ | table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))}); |
||
− | link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wikimarkup in |series-link= or wikimarkup in |series= when |series-link= is set |
||
+ | end |
||
− | |||
local Network = A['Network']; |
local Network = A['Network']; |
||
local Station = A['Station']; |
local Station = A['Station']; |
||
第2,698行: | 第3,161行: | ||
ID = table.concat(n, sepc .. ' '); |
ID = table.concat(n, sepc .. ' '); |
||
+ | if not is_set (Date) and is_set (AirDate) then -- promote airdate to date |
||
+ | Date = AirDate; |
||
+ | end |
||
+ | |||
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
||
local Season = A['Season']; |
local Season = A['Season']; |
||
第2,708行: | 第3,175行: | ||
-- assemble a table of parts concatenated later into Series |
-- assemble a table of parts concatenated later into Series |
||
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
||
− | if is_set(SeriesNumber) then table.insert(s, wrap_msg (' |
+ | 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 |
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end |
||
Issue = ''; -- unset because this is not a unique parameter |
Issue = ''; -- unset because this is not a unique parameter |
||
第2,714行: | 第3,181行: | ||
Chapter = Title; -- promote title parameters to chapter |
Chapter = Title; -- promote title parameters to chapter |
||
ScriptChapter = ScriptTitle; |
ScriptChapter = ScriptTitle; |
||
− | ScriptChapterOrigin = A:ORIGIN('ScriptTitle'); |
||
ChapterLink = TitleLink; -- alias episodelink |
ChapterLink = TitleLink; -- alias episodelink |
||
TransChapter = TransTitle; |
TransChapter = TransTitle; |
||
ChapterURL = URL; |
ChapterURL = URL; |
||
− | ChapterUrlAccess = UrlAccess; |
||
ChapterURLorigin = A:ORIGIN('URL'); |
ChapterURLorigin = A:ORIGIN('URL'); |
||
第2,726行: | 第3,191行: | ||
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL |
if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL |
||
− | Chapter = |
+ | Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink |
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; |
elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; |
||
− | Series = |
+ | Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly |
end |
end |
||
URL = ''; -- unset |
URL = ''; -- unset |
||
第2,738行: | 第3,203行: | ||
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? |
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? |
||
if is_set (Series) and is_set (SeriesLink) then |
if is_set (Series) and is_set (SeriesLink) then |
||
− | Series = |
+ | Series = '[[' .. SeriesLink .. '|' .. Series .. ']]'; |
end |
end |
||
Series = wrap_style ('italic-title', Series); -- series is italicized |
Series = wrap_style ('italic-title', Series); -- series is italicized |
||
end |
end |
||
end |
end |
||
− | + | -- end of {{cite episode}} stuff |
|
− | + | -- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. |
|
+ | if 'arxiv' == config.CitationClass then |
||
− | do |
||
+ | if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv |
||
− | if in_array (config.CitationClass, whitelist.preprint_template_list) then |
||
+ | table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message |
||
− | if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates |
||
+ | elseif is_set (Series) then -- series is an alias of version |
||
− | table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message |
||
+ | ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier |
||
− | end |
||
+ | Series = ''; -- unset |
||
+ | 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 |
||
− | Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass]; |
||
+ | PublisherName = ''; -- (if the article has been published, use cite journal, or other) |
||
+ | Chapter = ''; |
||
+ | URL = ''; |
||
+ | Format = ''; |
||
+ | Page = ''; Pages = ''; At = ''; |
||
end |
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 in_array(config.CitationClass, {"AV-media-notes", " |
+ | if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then |
TitleType = set_titletype (config.CitationClass, TitleType); |
TitleType = set_titletype (config.CitationClass, TitleType); |
||
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis |
if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis |
||
− | TitleType = Degree .. |
+ | TitleType = Degree .. "论文"; |
end |
end |
||
end |
end |
||
if is_set(TitleType) then -- if type parameter is specified |
if is_set(TitleType) then -- if type parameter is specified |
||
− | + | TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses |
|
− | -- TODO: Hack on TitleType to fix bunched parentheses problem |
||
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. |
|
− | local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging |
||
− | |||
if not is_set (Date) then |
if not is_set (Date) then |
||
Date = Year; -- promote Year to Date |
Date = Year; -- promote Year to Date |
||
第2,778行: | 第3,255行: | ||
Date = PublicationDate; -- promote PublicationDate to Date |
Date = PublicationDate; -- promote PublicationDate to Date |
||
PublicationDate = ''; -- unset, no longer needed |
PublicationDate = ''; -- unset, no longer needed |
||
− | Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter |
||
− | else |
||
− | Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter |
||
end |
end |
||
− | else |
||
− | Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging |
||
end |
end |
||
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation |
if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation |
||
− | + | --[[ |
|
− | + | Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where |
|
− | + | we get the date used in the metadata. |
|
+ | |||
− | |||
− | + | Date validation supporting code is in Module:Citation/CS1/Date_validation |
|
− | + | ]] |
|
− | do -- create defined block to contain local variables error_message |
+ | do -- create defined block to contain local variables error_message and mismatch |
local error_message = ''; |
local error_message = ''; |
||
-- AirDate has been promoted to Date so not necessary to check it |
-- AirDate has been promoted to Date so not necessary to check it |
||
+ | anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, |
||
− | local date_parameters_list = { |
||
+ | ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date); |
||
− | ['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 temporary Julian / Gregorian calendar uncertainty categorization |
||
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; |
if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; |
||
第2,826行: | 第3,283行: | ||
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 |
||
+ | if is_set(error_message) then |
||
− | if true == date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate |
||
− | 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 |
||
− | |||
− | if modified then -- if the date_parameters_list values were modified |
||
− | AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values |
||
− | ArchiveDate = date_parameters_list['archive-date'].val; |
||
− | Date = date_parameters_list['date'].val; |
||
− | DoiBroken = date_parameters_list['doi-broken-date'].val; |
||
− | LayDate = date_parameters_list['lay-date'].val; |
||
− | PublicationDate = date_parameters_list['publication-date'].val; |
||
− | end |
||
− | else |
||
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message |
table.insert( z.message_tail, { set_error( 'bad_date', {error_message}, true ) } ); -- add this error message |
||
end |
end |
||
end -- end of do |
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); |
+ | Embargo = is_embargoed (Embargo); -- |
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
||
第2,867行: | 第3,297行: | ||
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed |
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= |
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 |
||
− | |||
end |
end |
||
end |
end |
||
− | + | -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. |
|
-- Test if citation has no title |
-- Test if citation has no title |
||
if not is_set(Title) and |
if not is_set(Title) and |
||
第2,886行: | 第3,311行: | ||
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 |
||
− | if cfg.keywords_xlate[Title] == 'none' and |
||
+ | Title = ''; -- set title to empty string |
||
− | in_array (config.CitationClass, {'journal', 'citation'}) and |
||
+ | add_maint_cat ('untitled'); |
||
− | (is_set (Periodical) or is_set (ScriptPeriodical)) and |
||
− | ('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites |
||
− | Title = ''; -- set title to empty string |
||
− | add_maint_cat ('untitled'); |
||
end |
end |
||
− | check_for_url ({ -- add error message when any of these parameters |
+ | check_for_url ({ -- add error message when any of these parameters contains a URL |
['title']=Title, |
['title']=Title, |
||
[A:ORIGIN('Chapter')]=Chapter, |
[A:ORIGIN('Chapter')]=Chapter, |
||
− | [ |
+ | [A:ORIGIN('Periodical')]=Periodical, |
− | [ |
+ | [A:ORIGIN('PublisherName')] = PublisherName, |
}); |
}); |
||
第2,919行: | 第3,341行: | ||
coins_author = c; -- use that instead |
coins_author = c; -- use that instead |
||
end |
end |
||
+ | |||
− | |||
-- this is the function call to COinS() |
-- this is the function call to COinS() |
||
local OCinSoutput = COinS({ |
local OCinSoutput = COinS({ |
||
− | ['Periodical'] = |
+ | ['Periodical'] = Periodical, |
− | ['Encyclopedia'] = |
+ | ['Encyclopedia'] = Encyclopedia, |
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup |
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup |
||
+ | ['Map'] = Map, |
||
['Degree'] = Degree; -- cite thesis only |
['Degree'] = Degree; -- cite thesis only |
||
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup |
['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup |
||
第2,934行: | 第3,357行: | ||
['Volume'] = Volume, |
['Volume'] = Volume, |
||
['Issue'] = Issue, |
['Issue'] = Issue, |
||
− | ['Pages'] = |
+ | ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links |
['Edition'] = Edition, |
['Edition'] = Edition, |
||
− | ['PublisherName'] = PublisherName |
+ | ['PublisherName'] = PublisherName, |
['URL'] = first_set ({ChapterURL, URL}, 2), |
['URL'] = first_set ({ChapterURL, URL}, 2), |
||
['Authors'] = coins_author, |
['Authors'] = coins_author, |
||
第2,943行: | 第3,366行: | ||
}, config.CitationClass); |
}, config.CitationClass); |
||
− | + | -- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data. |
|
− | if |
+ | 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 |
+ | Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal |
end |
end |
||
− | + | -- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text |
|
− | if 'newsgroup' == config.CitationClass |
+ | if 'newsgroup' == config.CitationClass then |
+ | if is_set (PublisherName) then |
||
− | PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil )); |
||
+ | PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName') )); |
||
+ | end |
||
end |
end |
||
+ | |||
+ | |||
-- Now perform various field substitutions. |
-- Now perform various field substitutions. |
||
第2,959行: | 第3,386行: | ||
do |
do |
||
local last_first_list; |
local last_first_list; |
||
+ | local maximum; |
||
local control = { |
local control = { |
||
format = NameListFormat, -- empty string or 'vanc' |
format = NameListFormat, -- empty string or 'vanc' |
||
maximum = nil, -- as if display-authors or display-editors not set |
maximum = nil, -- as if display-authors or display-editors not set |
||
lastauthoramp = LastAuthorAmp, |
lastauthoramp = LastAuthorAmp, |
||
+ | page_name = this_page.text -- get current page name so that we don't wikilink to it via editorlinkn |
||
− | mode = Mode |
||
}; |
}; |
||
− | do -- do editor name list first because |
+ | 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. |
||
− | last_first_list, EditorCount = list_people(control, e, editor_etal); |
||
+ | 临时修复"Category:含有旧式缩略标签的引用的页面 in editors"的问题,中文版目前与英文版逻辑不一样,暂时不需要这个分类。等以后更新时再看怎么处理 --2017.6.23 shizhao |
||
+ | |||
+ | 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 |
if is_set (Editors) then |
||
− | Editors, editor_etal = name_has_etal (Editors, editor_etal, false, 'editors'); -- find and remove variations on et al. |
||
if editor_etal then |
if editor_etal then |
||
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal |
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal |
||
+ | EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation |
||
+ | else |
||
+ | EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation |
||
end |
end |
||
− | EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation |
||
else |
else |
||
Editors = last_first_list; -- either an author name list or an empty string |
Editors = last_first_list; -- either an author name list or an empty string |
||
第2,983行: | 第3,423行: | ||
EditorCount = 2; -- spoof to display (eds.) annotation |
EditorCount = 2; -- spoof to display (eds.) annotation |
||
end |
end |
||
− | end |
||
− | do -- now do interviewers |
||
− | control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal); |
||
− | Interviewers = list_people (control, interviewers_list, interviewer_etal); |
||
end |
end |
||
do -- now do translators |
do -- now do translators |
||
− | control.maximum |
+ | control.maximum = #t; -- number of translators |
− | Translators = list_people |
+ | Translators = list_people(control, t, false, 'translator'); -- et al not currently supported |
end |
end |
||
do -- now do contributors |
do -- now do contributors |
||
− | control.maximum |
+ | control.maximum = #c; -- number of contributors |
− | Contributors = list_people |
+ | Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported |
end |
end |
||
do -- now do authors |
do -- now do authors |
||
− | control.maximum , author_etal = |
+ | 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. |
||
− | last_first_list = list_people(control, a, author_etal); |
||
+ | control.lastauthoramp = nil; |
||
+ | control.maximum = #a + 1; |
||
+ | end |
||
+ | |||
+ | last_first_list = list_people(control, a, author_etal, 'author'); |
||
if is_set (Authors) then |
if is_set (Authors) then |
||
− | Authors, author_etal = name_has_etal (Authors, author_etal, false |
+ | Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. |
if author_etal then |
if author_etal then |
||
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter |
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter |
||
第3,010行: | 第3,451行: | ||
end |
end |
||
end -- end of do |
end -- end of do |
||
+ | |||
− | |||
− | if |
+ | if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified |
+ | table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message |
||
− | Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. |
||
end |
end |
||
− | |||
end |
end |
||
− | + | -- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation, |
|
− | + | -- 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'); |
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); |
||
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); |
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); |
||
第3,025行: | 第3,465行: | ||
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); |
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); |
||
− | + | -- special case for chapter format so no error message or cat when chapter not supported |
|
− | if not (in_array(config.CitationClass, {'web', |
+ | if not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or |
− | ('citation' == config.CitationClass and |
+ | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then |
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); |
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); |
||
end |
end |
||
− | if not is_set(URL) then |
+ | if not is_set(URL) then --and |
− | if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) |
+ | if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty |
+ | table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); |
||
− | ('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website= |
||
− | table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); |
||
end |
end |
||
− | -- |
+ | -- Test if accessdate is given without giving a URL |
− | if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when |
+ | if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test? |
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
||
AccessDate = ''; |
AccessDate = ''; |
||
第3,044行: | 第3,483行: | ||
end |
end |
||
− | local OriginalURL, OriginalURLorigin, OriginalFormat |
+ | local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set? |
− | + | DeadURL = DeadURL:lower(); -- used later when assembling archived text |
|
if is_set( ArchiveURL ) then |
if is_set( ArchiveURL ) then |
||
− | if is_set ( |
+ | if 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= |
||
+ | 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 |
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text |
||
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages |
OriginalURLorigin = ChapterURLorigin; -- name of chapter-url parameter for error messages |
||
− | OriginalFormat = ChapterFormat; -- and original | |
+ | OriginalFormat = ChapterFormat; -- and original |format= |
+ | if 'no' ~= DeadURL then |
||
− | |||
− | if 'live' ~= UrlStatus then |
||
ChapterURL = ArchiveURL -- swap-in the archive's url |
ChapterURL = ArchiveURL -- swap-in the archive's url |
||
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages |
ChapterURLorigin = A:ORIGIN('ArchiveURL') -- name of archive-url parameter for error messages |
||
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
||
− | ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived urls |
||
end |
end |
||
+ | 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 'live' ~= UrlStatus 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 |
||
− | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', |
+ | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia |
− | ('citation' == config.CitationClass and |
+ | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then |
local chap_param; |
local chap_param; |
||
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters |
if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters |
||
第3,083行: | 第3,517行: | ||
chap_param = A:ORIGIN ('ChapterURL') |
chap_param = A:ORIGIN ('ChapterURL') |
||
elseif is_set (ScriptChapter) then |
elseif is_set (ScriptChapter) then |
||
− | chap_param = |
+ | chap_param = A:ORIGIN ('ScriptChapter') |
else is_set (ChapterFormat) |
else is_set (ChapterFormat) |
||
chap_param = A:ORIGIN ('ChapterFormat') |
chap_param = A:ORIGIN ('ChapterFormat') |
||
第3,099行: | 第3,533行: | ||
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value |
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 is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) |
||
− | if in_array (Contribution:lower(), cfg. |
+ | if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title |
no_quotes = true; -- then render it unquoted |
no_quotes = true; -- then render it unquoted |
||
end |
end |
||
end |
end |
||
− | Chapter = format_chapter_title (ScriptChapter |
+ | Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter |
if is_set (Chapter) then |
if is_set (Chapter) then |
||
− | Chapter = Chapter .. ChapterFormat ; |
||
if 'map' == config.CitationClass and is_set (TitleType) then |
if 'map' == config.CitationClass and is_set (TitleType) then |
||
− | Chapter = Chapter .. ' ' .. TitleType; |
+ | Chapter = Chapter .. ' ' .. TitleType; |
end |
end |
||
− | Chapter = Chapter.. sepc .. ' '; |
+ | Chapter = Chapter .. ChapterFormat .. sepc .. ' '; |
elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... |
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 |
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it |
||
第3,116行: | 第3,549行: | ||
end |
end |
||
+ | -- Format main title. |
||
− | -- Format main title. TODO: add support for non-English versions of 'Archived copy' when used on other-language wikis |
||
− | if is_set |
+ | if is_set(TitleLink) and is_set(Title) then |
+ | Title = "[[" .. TitleLink .. "|" .. Title .. "]]" |
||
− | (mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation.archived_copy.en) or -- if title is 'Archived copy' (place holder added by bots that can't find proper title) |
||
− | mw.ustring.match (mw.ustring.lower(Title), cfg.special_case_translation.archived_copy['local'])) then -- local-wiki's form |
||
− | add_maint_cat ('archived_copy'); -- add maintenance category before we modify the content of Title |
||
end |
end |
||
+ | if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or |
||
− | if Title:match ('^%(%(.*%)%)$') then -- if keep as written markup: |
||
+ | ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or |
||
− | Title= Title:gsub ('^%(%((.*)%)%)$', '%1') -- remove the markup |
||
+ | ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article |
||
− | else |
||
− | if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title= |
||
− | Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three |
||
− | elseif not mw.ustring.find (Title, '%.%s*%a%.$') and -- end of title is not a 'dot-(optional space-)letter-dot' initialism ... |
||
− | not mw.ustring.find (Title, '%s+%a%.$') then -- ...and not a 'space-letter-dot' initial (''Allium canadense'' L.) |
||
− | Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character; sepc and ms.ustring() here for languages that use multibyte separator characters |
||
− | end |
||
− | end |
||
− | |||
− | if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or |
||
− | ('citation' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical)) and not is_set (Encyclopedia)) or |
||
− | ('map' == config.CitationClass and (is_set (Periodical) or is_set (ScriptPeriodical))) 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 = 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 = wrap_style ('quoted-title', Title); |
||
+ | |||
− | Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
||
+ | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
||
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
||
elseif 'report' == config.CitationClass then -- no styling for cite report |
elseif 'report' == config.CitationClass then -- no styling for cite report |
||
− | Title = script_concatenate (Title, ScriptTitle |
+ | Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped |
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title |
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title |
||
else |
else |
||
Title = wrap_style ('italic-title', Title); |
Title = wrap_style ('italic-title', Title); |
||
− | Title = script_concatenate (Title, ScriptTitle |
+ | 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); |
TransTitle = wrap_style ('trans-italic-title', TransTitle); |
||
end |
end |
||
− | + | TransError = ""; |
|
if is_set(TransTitle) then |
if is_set(TransTitle) then |
||
if is_set(Title) then |
if is_set(Title) then |
||
第3,158行: | 第3,579行: | ||
end |
end |
||
end |
end |
||
+ | |||
− | |||
+ | Title = Title .. TransTitle; |
||
− | if is_set (Title) then -- TODO: is this the right place to be making wikisource urls? |
||
+ | |||
− | if not is_set (TitleLink) and is_set (URL) then |
||
+ | if is_set(Title) then |
||
− | Title = external_link (URL, Title, URLorigin, UrlAccess) .. TransTitle .. TransError .. Format; |
||
+ | if not is_set(TitleLink) and is_set(URL) then |
||
− | URL = ''; -- unset these because no longer needed |
||
+ | Title = external_link( URL, Title, URLorigin ) .. TransError .. Format; |
||
+ | URL = ""; |
||
Format = ""; |
Format = ""; |
||
− | elseif is_set (TitleLink) and not is_set (URL) then |
||
− | local ws_url; |
||
− | ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here |
||
− | if ws_url then |
||
− | Title = external_link (ws_url, Title .. ' ', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? |
||
− | Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title}); |
||
− | Title = Title .. TransTitle .. TransError; |
||
− | else |
||
− | Title = make_wikilink (TitleLink, Title) .. TransTitle .. TransError; |
||
− | end |
||
else |
else |
||
+ | Title = Title .. TransError; |
||
− | local ws_url, ws_label; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink) |
||
− | ws_url, ws_label, L = wikisource_url_make (Title:gsub('[\'"](.-)[\'"]', '%1')); -- make ws url from |title= interwiki link (strip italic or quote markup); link portion L becomes tool tip label |
||
− | if ws_url then |
||
− | Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup |
||
− | Title = external_link (ws_url, Title .. ' ', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? |
||
− | Title = substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); |
||
− | Title = Title .. TransTitle .. TransError; |
||
− | else |
||
− | Title = Title .. TransTitle .. TransError; |
||
− | end |
||
end |
end |
||
− | else |
||
− | Title = TransTitle .. TransError; |
||
end |
end |
||
第3,196行: | 第3,598行: | ||
if is_set (Conference) then |
if is_set (Conference) then |
||
if is_set (ConferenceURL) then |
if is_set (ConferenceURL) then |
||
− | Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin |
+ | Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin ); |
end |
end |
||
Conference = sepc .. " " .. Conference .. ConferenceFormat; |
Conference = sepc .. " " .. Conference .. ConferenceFormat; |
||
elseif is_set(ConferenceURL) then |
elseif is_set(ConferenceURL) then |
||
− | Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin |
+ | Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin ); |
end |
end |
||
第3,233行: | 第3,635行: | ||
At = is_set(At) and (sepc .. " " .. At) or ""; |
At = is_set(At) and (sepc .. " " .. At) or ""; |
||
Position = is_set(Position) and (sepc .. " " .. Position) or ""; |
Position = is_set(Position) and (sepc .. " " .. Position) or ""; |
||
− | if config.CitationClass == 'map' then |
+ | if config.CitationClass == 'map' then |
− | local Section = A['Section']; |
+ | local Section = A['Section']; |
local Sections = A['Sections']; |
local Sections = A['Sections']; |
||
local Inset = A['Inset']; |
local Inset = A['Inset']; |
||
第3,254行: | 第3,656行: | ||
else |
else |
||
Language=""; -- language not specified so make sure this is an empty string; |
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 |
||
第3,262行: | 第3,661行: | ||
if is_set (Translators) then |
if is_set (Translators) then |
||
− | Others = |
+ | Others = sepc .. ' 由' .. Translators .. '翻译 ' .. Others; |
end |
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 ""; |
TitleNote = is_set(TitleNote) and (sepc .. " " .. TitleNote) or ""; |
||
if is_set (Edition) then |
if is_set (Edition) then |
||
第3,278行: | 第3,674行: | ||
end |
end |
||
− | Series = is_set |
+ | Series = is_set(Series) and (sepc .. " " .. Series) or ""; |
− | OrigYear = is_set |
+ | OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; |
− | Agency = is_set |
+ | Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; |
+ | |||
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
||
------------------------------------ totally unrelated data |
------------------------------------ totally unrelated data |
||
− | + | if is_set(Via) then |
|
+ | Via = " " .. wrap_msg ('via', Via); |
||
+ | end |
||
+ | |||
+ | --[[ |
||
+ | Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link |
||
+ | note is displayed. There are no error messages for this condition. |
||
+ | |||
+ | ]] |
||
+ | 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 |
if is_set(AccessDate) then |
||
第3,290行: | 第3,702行: | ||
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
||
− | if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if |
+ | if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case |
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text |
AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text |
||
+ | -- neither of these work; don't know why; it seems that substitute() isn't being called |
||
− | |||
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
||
end |
end |
||
第3,304行: | 第3,716行: | ||
end |
end |
||
− | ID_list = build_id_list( ID_list, { |
+ | ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); |
if is_set(URL) then |
if is_set(URL) then |
||
− | URL = " " .. external_link( URL, nil, URLorigin |
+ | URL = " " .. external_link( URL, nil, URLorigin ); |
end |
end |
||
第3,320行: | 第3,732行: | ||
local Archived |
local Archived |
||
if is_set(ArchiveURL) then |
if is_set(ArchiveURL) then |
||
− | local arch_text; |
||
if not is_set(ArchiveDate) then |
if not is_set(ArchiveDate) then |
||
ArchiveDate = set_error('archive_missing_date'); |
ArchiveDate = set_error('archive_missing_date'); |
||
end |
end |
||
− | if " |
+ | if "no" == DeadURL then |
− | arch_text = cfg.messages['archived']; |
+ | local arch_text = cfg.messages['archived']; |
if sepc ~= "." then arch_text = arch_text:lower() end |
if sepc ~= "." then arch_text = arch_text:lower() end |
||
− | Archived = sepc .. " " .. substitute( cfg.messages['archived- |
+ | Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], |
− | { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') |
+ | { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } ); |
− | if not is_set |
+ | if not is_set(OriginalURL) then |
Archived = Archived .. " " .. set_error('archive_missing_url'); |
Archived = Archived .. " " .. set_error('archive_missing_url'); |
||
end |
end |
||
− | elseif is_set(OriginalURL) then -- |
+ | elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' |
+ | local arch_text = cfg.messages['archived-dead']; |
||
− | if in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then |
||
+ | if sepc ~= "." then arch_text = arch_text:lower() end |
||
− | arch_text = cfg.messages['archived-unfit']; |
||
+ | if in_array (DeadURL, {'unfit', 'usurped'}) then |
||
− | if sepc ~= "." then arch_text = arch_text:lower() end |
||
− | Archived = sepc .. " " .. |
+ | Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled |
+ | else -- DeadURL is empty, 'yes', 'true', or 'y' |
||
− | if 'bot: unknown' == UrlStatus 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 -- UrlStatus is empty, 'dead' |
||
− | arch_text = cfg.messages['archived-dead']; |
||
− | if sepc ~= "." then arch_text = arch_text:lower() end |
||
Archived = sepc .. " " .. substitute( arch_text, |
Archived = sepc .. " " .. substitute( arch_text, |
||
− | { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin |
+ | { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled |
end |
end |
||
+ | else |
||
− | else -- OriginalUrl not set |
||
− | arch_text = cfg.messages['archived-missing']; |
+ | local arch_text = cfg.messages['archived-missing']; |
if sepc ~= "." then arch_text = arch_text:lower() end |
if sepc ~= "." then arch_text = arch_text:lower() end |
||
Archived = sepc .. " " .. substitute( arch_text, |
Archived = sepc .. " " .. substitute( arch_text, |
||
第3,369行: | 第3,773行: | ||
end |
end |
||
if sepc == '.' then |
if sepc == '.' then |
||
− | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') |
+ | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate |
else |
else |
||
− | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') |
+ | Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate |
end |
end |
||
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= |
elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= |
||
第3,379行: | 第3,783行: | ||
if is_set(Transcript) then |
if is_set(Transcript) then |
||
if is_set(TranscriptURL) then |
if is_set(TranscriptURL) then |
||
− | Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin |
+ | Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin ); |
end |
end |
||
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
||
elseif is_set(TranscriptURL) then |
elseif is_set(TranscriptURL) then |
||
− | Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin |
+ | Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin ); |
end |
end |
||
local Publisher; |
local Publisher; |
||
− | if is_set( |
+ | if is_set(Periodical) and |
+ | not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then |
||
− | PublicationDate = wrap_msg ('published', PublicationDate); |
||
+ | if is_set(PublisherName) then |
||
− | end |
||
− | + | if is_set(PublicationPlace) then |
|
− | + | Publisher = PublicationPlace .. ": " .. PublisherName; |
|
+ | else |
||
− | Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
||
+ | Publisher = PublisherName; |
||
− | else |
||
+ | end |
||
− | Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
||
+ | elseif is_set(PublicationPlace) then |
||
− | end |
||
− | + | Publisher= PublicationPlace; |
|
+ | else |
||
− | Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
||
+ | Publisher = ""; |
||
− | else |
||
+ | end |
||
− | Publisher = PublicationDate; |
||
+ | if is_set(Publisher) then |
||
+ | Publisher = " (" .. Publisher .. ")"; |
||
+ | end |
||
+ | else |
||
+ | if is_set(PublisherName) then |
||
+ | if is_set(PublicationPlace) then |
||
+ | Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName; |
||
+ | else |
||
+ | Publisher = sepc .. " " .. PublisherName; |
||
+ | end |
||
+ | elseif is_set(PublicationPlace) then |
||
+ | Publisher= sepc .. " " .. PublicationPlace; |
||
+ | else |
||
+ | Publisher = ''; |
||
+ | end |
||
end |
end |
||
-- Several of the above rely upon detecting this as nil, so do it last. |
-- Several of the above rely upon detecting this as nil, so do it last. |
||
− | if |
+ | if is_set(Periodical) then |
if is_set(Title) or is_set(TitleNote) then |
if is_set(Title) or is_set(TitleNote) then |
||
− | Periodical = sepc .. " " .. |
+ | Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical) |
else |
else |
||
− | Periodical = |
+ | Periodical = wrap_style ('italic-title', Periodical) |
end |
end |
||
end |
end |
||
− | + | --[[ |
|
− | + | Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that |
|
− | + | the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). |
|
− | + | ]] |
|
− | if "speech" == config.CitationClass then |
+ | if "speech" == config.CitationClass then -- cite speech only |
− | TitleNote = " (Speech)"; |
+ | TitleNote = " (Speech)"; -- annotate the citation |
− | if is_set (Periodical) then |
+ | if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter |
− | if is_set (Conference) then |
+ | if is_set (Conference) then -- and if |event= is set |
− | Conference = Conference .. sepc .. " "; |
+ | Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering |
end |
end |
||
end |
end |
||
第3,432行: | 第3,851行: | ||
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
||
− | if is_set(Others) then Others = |
+ | if is_set(Others) then Others = Others .. sepc .. " " end |
− | tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, |
+ | tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, |
+ | Edition, Publisher, Agency}, sepc ); |
||
+ | |||
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites |
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites |
||
if is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc |
if 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 |
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 |
+ | tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); |
else |
else |
||
− | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series |
+ | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Volume, Others, Edition, Publisher, Agency}, sepc ); |
end |
end |
||
elseif 'map' == config.CitationClass then -- special cases for cite map |
elseif 'map' == config.CitationClass then -- special cases for cite map |
||
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter |
if is_set (Chapter) then -- map in a book; TitleType is part of Chapter |
||
− | tcommon = safe_join( {Title, Format, Edition, Scale, Series |
+ | tcommon = safe_join( {Title, Format, Edition, Scale, Series, Cartography, Others, Publisher, Volume}, sepc ); |
elseif is_set (Periodical) then -- map in a periodical |
elseif is_set (Periodical) then -- map in a periodical |
||
− | tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series |
+ | tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Cartography, Others, Publisher, Volume}, sepc ); |
else -- a sheet or stand-alone map |
else -- a sheet or stand-alone map |
||
− | tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series |
+ | tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Cartography, Others, Publisher}, sepc ); |
end |
end |
||
elseif 'episode' == config.CitationClass then -- special case for cite episode |
elseif 'episode' == config.CitationClass then -- special case for cite episode |
||
− | tcommon = safe_join( {Title, TitleNote, TitleType, Series, |
+ | tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Edition, Publisher}, sepc ); |
− | |||
else -- all other CS1 templates |
else -- all other CS1 templates |
||
− | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series |
+ | tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, |
Volume, Others, Edition, Publisher, Agency}, sepc ); |
Volume, Others, Edition, Publisher, Agency}, sepc ); |
||
end |
end |
||
第3,465行: | 第3,885行: | ||
end |
end |
||
+ | -- LOCAL |
||
− | local idcommon; |
||
+ | local xDate = Date |
||
− | if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript |
||
+ | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
||
− | idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc ); |
||
+ | if ( is_set(Periodical) and Date ~= '' and |
||
− | else |
||
+ | not in_array(config.CitationClass, {"encyclopaedia","web"}) ) |
||
− | idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc ); |
||
+ | or ( in_array(config.CitationClass, {"book","news"}) ) then |
||
+ | if in_array(config.CitationClass, {"journal","citation"}) and ( Volume ~= '' or Issue ~= '' ) then |
||
+ | xDate = xDate .. ',' .. Volume |
||
+ | end |
||
+ | xDate = xDate .. pgtext |
||
+ | pgtext = '' |
||
+ | end |
||
+ | if PublicationDate and PublicationDate ~= '' then |
||
+ | xDate = xDate .. ' (' .. PublicationDate .. ')' |
||
+ | end |
||
+ | if OrigYear ~= '' then |
||
+ | xDate = xDate .. OrigYear |
||
+ | end |
||
+ | if AccessDate ~= '' then |
||
+ | xDate = xDate .. ' ' .. AccessDate |
||
+ | end |
||
+ | if xDate ~= '' then |
||
+ | xDate = sepc .. ' ' .. xDate |
||
end |
end |
||
+ | -- END LOCAL |
||
+ | local idcommon = safe_join( { URL, xDate, ID_list, Archived, Via, SubscriptionRequired, Lay, Language, Quote }, sepc ); |
||
local text; |
local text; |
||
− | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
||
− | if is_set( |
+ | if is_set(Authors) then |
+ | if is_set(Coauthors) then |
||
− | if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set |
||
+ | if 'vanc' == NameListFormat then -- separate authors and coauthors with proper name-list-separator |
||
− | Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses |
||
+ | Authors = Authors .. ', ' .. Coauthors; |
||
− | 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 |
else |
||
− | + | Authors = Authors .. '; ' .. Coauthors; |
|
end |
end |
||
end |
end |
||
+ | Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space |
||
− | end |
||
− | if is_set(Authors) then |
||
− | 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 |
if is_set(Editors) then |
||
local in_text = " "; |
local in_text = " "; |
||
第3,495行: | 第3,928行: | ||
if is_set(Chapter) and 0 == #c then |
if is_set(Chapter) and 0 == #c then |
||
in_text = in_text .. cfg.messages['in'] .. " " |
in_text = in_text .. cfg.messages['in'] .. " " |
||
− | if (sepc ~= '.') then |
+ | if (sepc ~= '.') then in_text = in_text:lower() end -- lowercase for cs2 |
+ | else |
||
− | in_text = in_text:lower() -- lowercase for cs2 |
||
+ | if EditorCount <= 1 then |
||
+ | post_text = ", " .. cfg.messages['editor']; |
||
+ | else |
||
+ | post_text = ", " .. cfg.messages['editors']; |
||
end |
end |
||
− | end |
+ | end |
− | if EditorCount <= 1 then |
||
− | post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case |
||
− | else |
||
− | post_text = " (" .. cfg.messages['editors'] .. ")"; |
||
− | end |
||
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
||
end |
end |
||
第3,510行: | 第3,942行: | ||
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 |
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 |
||
Authors = by_text .. Authors; -- author follows title so tweak it here |
Authors = by_text .. Authors; -- author follows title so tweak it here |
||
− | if is_set (Editors |
+ | 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 |
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space |
||
end |
end |
||
+ | Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space |
||
− | if (not is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination |
||
− | + | text = safe_join( {Contributors, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); |
|
− | end |
||
− | text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); |
||
else |
else |
||
− | text = safe_join( {Authors |
+ | text = safe_join( {Authors, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); |
end |
end |
||
elseif is_set(Editors) then |
elseif is_set(Editors) then |
||
− | if |
+ | if EditorCount <= 1 then |
+ | Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " |
||
− | if EditorCount <= 1 then |
||
− | Editors = Editors .. ", " .. cfg.messages['editor']; |
||
− | else |
||
− | Editors = Editors .. ", " .. cfg.messages['editors']; |
||
− | end |
||
else |
else |
||
+ | Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " |
||
− | if EditorCount <= 1 then |
||
− | Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " |
||
− | else |
||
− | Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " |
||
− | end |
||
end |
end |
||
− | text = safe_join( {Editors |
+ | text = safe_join( {Editors, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
else |
else |
||
− | if |
+ | if config.CitationClass=="journal" and is_set(Periodical) then |
− | text = safe_join( {Chapter, Place, tcommon, pgtext |
+ | text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
else |
else |
||
− | text = safe_join( {Chapter, Place, tcommon |
+ | text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
end |
end |
||
end |
end |
||
if is_set(PostScript) and PostScript ~= sepc then |
if is_set(PostScript) and PostScript ~= sepc then |
||
− | text = safe_join( {text, sepc}, sepc ); |
+ | text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc. |
text = text:sub(1,-sepc:len()-1); |
text = text:sub(1,-sepc:len()-1); |
||
end |
end |
||
第3,560行: | 第3,982行: | ||
end |
end |
||
− | if is_set(Ref) and |
+ | if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate |
local id = Ref |
local id = Ref |
||
if ('harv' == Ref ) then |
if ('harv' == Ref ) then |
||
local namelist = {}; -- holds selected contributor, author, editor name list |
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 |
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation |
||
第3,573行: | 第3,996行: | ||
namelist = e; |
namelist = e; |
||
end |
end |
||
− | + | id = anchor_id (namelist, year); -- go make the CITEREF anchor |
|
− | id = anchor_id (namelist, year); -- go make the CITEREF anchor |
||
− | else |
||
− | id = ''; -- unset |
||
− | end |
||
end |
end |
||
options.id = id; |
options.id = id; |
||
end |
end |
||
− | if string.len(text:gsub("<span[^>/]*> |
+ | if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then |
z.error_categories = {}; |
z.error_categories = {}; |
||
text = set_error('empty_citation'); |
text = set_error('empty_citation'); |
||
第3,588行: | 第4,007行: | ||
end |
end |
||
+ | if is_set(options.id) then |
||
− | local render = {}; -- here we collect the final bits for concatenation into the rendered citation |
||
+ | text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; |
||
− | |||
− | if is_set(options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags |
||
− | table.insert (render, substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set |
||
else |
else |
||
− | + | text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; |
|
end |
end |
||
+ | local empty_span = '<span style="display:none;"> </span>'; |
||
− | table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation |
||
+ | |||
− | |||
+ | -- Note: Using display: none on the COinS span breaks some clients. |
||
− | if 0 ~= #z.message_tail then |
||
+ | local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>'; |
||
− | table.insert (render, ' '); |
||
+ | text = text .. OCinS; |
||
+ | |||
+ | if #z.message_tail ~= 0 then |
||
+ | text = text .. " "; |
||
for i,v in ipairs( z.message_tail ) do |
for i,v in ipairs( z.message_tail ) do |
||
if is_set(v[1]) then |
if is_set(v[1]) then |
||
if i == #z.message_tail then |
if i == #z.message_tail then |
||
− | + | text = text .. error_comment( v[1], v[2] ); |
|
else |
else |
||
− | + | text = text .. error_comment( v[1] .. "; ", v[2] ); |
|
end |
end |
||
end |
end |
||
第3,611行: | 第4,032行: | ||
end |
end |
||
− | if |
+ | if #z.maintenance_cats ~= 0 then |
+ | text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">'; |
||
− | local maint_msgs = {}; -- here we collect all of the maint messages |
||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
||
+ | text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])'; |
||
− | local maint = {}; -- here we assemble a maintenence message |
||
− | table.insert (maint, v); -- maint msg is the category name |
||
− | table.insert (maint, ' ('); -- open the link text |
||
− | table.insert (maint, make_wikilink (':Category:' .. v, 'link')); -- add the link |
||
− | table.insert (maint, ')'); -- and close it |
||
− | table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table |
||
end |
end |
||
+ | text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now) |
||
− | table.insert (render, substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save |
||
end |
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 |
for _, v in ipairs( z.error_categories ) do |
||
− | + | text = text .. '[[Category:' .. v ..']]'; |
|
end |
end |
||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
||
− | + | text = text .. '[[Category:' .. v ..']]'; |
|
end |
end |
||
− | for _, v in ipairs( z.properties_cats ) do -- append |
+ | for _, v in ipairs( z.properties_cats ) do -- append maintenance categories |
− | + | text = text .. '[[Category:' .. v ..']]'; |
|
end |
end |
||
end |
end |
||
− | |||
− | return table.concat (render); |
||
− | end |
||
− | |||
− | |||
− | --[[--------------------------< V A L I D A T E >-------------------------------------------------------------- |
||
− | |||
− | Looks for a parameter's name in one of several whitelists. |
||
− | |||
− | Parameters in the whitelist can have three values: |
||
− | true - active, supported parameters |
||
− | false - deprecated, supported parameters |
||
− | nil - unsupported parameters |
||
+ | return text |
||
− | ]] |
||
− | |||
− | local function validate (name, cite_class) |
||
− | local name = tostring (name); |
||
− | local state; |
||
− | local function state_test (state, name) -- local function to do testing of state values |
||
− | if true == state then return true; end -- valid actively supported parameter |
||
− | if false == state then |
||
− | deprecated_parameter (name); -- parameter is deprecated but still supported |
||
− | return true; |
||
− | end |
||
− | return nil; |
||
− | end |
||
− | |||
− | if name:find ('#') then -- # is a cs1|2 reserved character so parameters with # not permitted |
||
− | return nil; |
||
− | end |
||
− | |||
− | if in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates |
||
− | state = whitelist.limited_basic_arguments[name]; |
||
− | if true == state_test (state, name) then return true; end |
||
− | |||
− | state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class |
||
− | if true == state_test (state, name) then return true; end |
||
− | |||
− | -- limited enumerated parameters list |
||
− | 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_test (state, name) then return true; end |
||
− | |||
− | return false; -- not supported because not found or name is set to nil |
||
− | end -- end limited parameter-set templates |
||
− | |||
− | if in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list |
||
− | state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class |
||
− | if true == state_test (state, name) then return true; end |
||
− | end -- if here, fall into general validation |
||
− | |||
− | state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed |
||
− | if true == state_test (state, name) then return true; end |
||
− | |||
− | -- all enumerated parameters allowed |
||
− | name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) |
||
− | state = whitelist.numbered_arguments[name]; |
||
− | if true == state_test (state, name) then return true; end |
||
− | |||
− | return false; -- not supported because not found or name is set to nil |
||
end |
end |
||
+ | --[[--------------------------< 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. |
||
− | --[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ |
||
− | + | 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 |
||
− | sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a |
||
+ | of the rendered citation. This function will detect the replacement character when it is part of the wikisource. |
||
− | parameter that is missing its pipe: |
||
− | {{cite ... |title=Title access-date=2016-03-17}} |
||
+ | Output of this function is an error message that identifies the character or the Unicode group that the character |
||
− | cs1|2 shares some parameter names with xml/html atributes: class=, title=, etc. To prevent false positives xml/html |
||
+ | belongs to along with its position in the parameter value. |
||
− | tags are removed before the search. |
||
− | |||
− | If a missing pipe is detected, this function adds the missing pipe maintenance category. |
||
]] |
]] |
||
+ | --[[ |
||
+ | local function has_invisible_chars (param, v) |
||
+ | local position = ''; |
||
+ | local i=1; |
||
+ | while cfg.invisible_chars[i] do |
||
− | local function missing_pipe_check (parameter, value) |
||
+ | local char=cfg.invisible_chars[i][1] -- the character or group name |
||
− | local capture; |
||
+ | local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it |
||
− | value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc |
||
+ | 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 |
||
− | capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes |
||
+ | if position then |
||
− | if capture and validate (capture) then -- if the capture is a valid parameter name |
||
− | table.insert( z.message_tail, { |
+ | 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 |
||
end |
end |
||
− | |||
− | |||
− | --[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >-------------------------------------- |
||
− | |||
− | look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked |
||
− | |||
]] |
]] |
||
+ | --[[--------------------------< Z . C I T A T I O N >---------------------------------------------------------- |
||
− | local function has_extraneous_punc (param, value) |
||
− | if cfg.punct_skip[param] then |
||
− | return; -- parameter name found in the skip table so done |
||
− | end |
||
− | |||
− | if value:match ('[,;:]$') then |
||
− | add_maint_cat ('extra_punct'); -- has extraneous punctuation; add maint cat |
||
− | end |
||
− | end |
||
− | |||
− | |||
− | --[[--------------------------< C I T A T I O N >-------------------------------------------------------------- |
||
This is used by templates such as {{cite book}} to create the actual citation text. |
This is used by templates such as {{cite book}} to create the actual citation text. |
||
第3,747行: | 第4,093行: | ||
]] |
]] |
||
− | + | function z.citation(frame) |
|
− | Frame = frame; -- save a copy incase we need to display an error message in preview mode |
||
local pframe = frame:getParent() |
local pframe = frame:getParent() |
||
− | local validation |
+ | local validation; |
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
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 |
+ | cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of Configuration and Whitelist and ... |
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); |
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); |
||
− | + | validation = require ('Module:Citation/CS1/Date_validation/sandbox'); -- ... sandbox version of date validation code |
|
+ | |||
− | validation = require ('Module:Citation/CS1/Date_validation/sandbox'); |
||
− | identifiers = require ('Module:Citation/CS1/Identifiers/sandbox'); |
||
− | metadata = require ('Module:Citation/CS1/COinS/sandbox'); |
||
− | styles = 'Module:Citation/CS1/sandbox/styles.css'; |
||
− | |||
else -- otherwise |
else -- otherwise |
||
− | cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of |
+ | cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of Configuration and Whitelist and ... |
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); |
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); |
||
− | + | validation = require ('Module:Citation/CS1/Date_validation'); -- ... live version of date validation code |
|
− | validation = require ('Module:Citation/CS1/Date_validation'); |
||
− | identifiers = require ('Module:Citation/CS1/Identifiers'); |
||
− | metadata = require ('Module:Citation/CS1/COinS'); |
||
− | styles = 'Module:Citation/CS1/styles.css'; |
||
− | |||
end |
end |
||
− | + | dates = validation.dates; -- imported functions |
|
− | identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module |
||
− | validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module |
||
− | metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module |
||
− | |||
− | dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation |
||
year_date_check = validation.year_date_check; |
year_date_check = validation.year_date_check; |
||
− | reformat_dates = validation.reformat_dates; |
||
− | date_hyphen_to_dash = validation.date_hyphen_to_dash; |
||
− | date_name_xlate = validation.date_name_xlate; |
||
+ | local args = {}; |
||
− | is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities |
||
+ | local suggestions = {}; |
||
− | 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; |
||
− | strip_apostrophe_markup = utilities.strip_apostrophe_markup; |
||
− | |||
− | z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities |
||
− | |||
− | extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers |
||
− | build_id_list = identifiers.build_id_list; |
||
− | is_embargoed = identifiers.is_embargoed; |
||
− | extract_id_access_levels = identifiers.extract_id_access_levels; |
||
− | |||
− | make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS |
||
− | get_coins_pages = metadata.get_coins_pages; |
||
− | COinS = metadata.COinS; |
||
− | |||
− | local args = {}; -- table where we store all of the template's arguments |
||
− | local suggestions = {}; -- table where we store suggestions if we need to loadData them |
||
local error_text, error_state; |
local error_text, error_state; |
||
− | local config = {}; |
+ | local config = {}; |
for k, v in pairs( frame.args ) do |
for k, v in pairs( frame.args ) do |
||
config[k] = v; |
config[k] = v; |
||
+ | args[k] = v; |
||
− | -- args[k] = v; -- debug tool that allows us to render a citation from module {{#invoke:}} |
||
end |
end |
||
第3,820行: | 第4,124行: | ||
for k, v in pairs( pframe.args ) do |
for k, v in pairs( pframe.args ) do |
||
if v ~= '' then |
if v ~= '' then |
||
− | if ( |
+ | if not validate( k ) then |
− | k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9 |
||
− | end |
||
− | if not validate( k, config.CitationClass ) then |
||
error_text = ""; |
error_text = ""; |
||
if type( k ) ~= 'string' then |
if type( k ) ~= 'string' then |
||
第3,830行: | 第4,131行: | ||
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() |
+ | elseif validate( k:lower() ) 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 ); |
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 |
||
第3,843行: | 第4,144行: | ||
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 = 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 |
||
− | v = ''; -- unset |
||
− | end |
||
end |
end |
||
end |
end |
||
第3,857行: | 第4,153行: | ||
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 |
||
第3,865行: | 第4,160行: | ||
end |
end |
||
end |
end |
||
− | missing_pipe_check (k, 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 |
+ | args[k] = v; |
||
− | args[k] = v; -- why do we do this? we don't support 'empty' parameters |
||
end |
end |
||
end |
end |
||
第3,876行: | 第4,169行: | ||
if 'string' == type (k) then -- don't evaluate positional parameters |
if 'string' == type (k) then -- don't evaluate positional parameters |
||
has_invisible_chars (k, v); |
has_invisible_chars (k, v); |
||
− | has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values |
||
end |
end |
||
end |
end |
||
+ | return citation0( config, args) |
||
− | |||
− | return table.concat ({citation0( config, args), frame:extensionTag ('templatestyles', '', {src=styles})}); |
||
end |
end |
||
+ | return z |
||
− | --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ |
||
− | ]] |
||
− | |||
− | return {citation = citation}; |
2020年4月22日 (三) 14:30的最新版本
此模块的文档可以在Module:Citation/CS1/doc创建
local z = { 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 >-------------------------------------- ]] local dates, year_date_check -- functions in Module:Citation/CS1/Date_validation local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist --[[--------------------------< I S _ S E T >------------------------------------------------------------------ Returns true if argument is set; false otherwise. Argument is 'set' when it exists (not nil) or when it is not an empty string. This function is global because it is called from both this module and from Date validation ]] function is_set( var ) return not (var == nil or var == ''); end --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ Locates and returns the first set value in a table of values where the order established in the table, left-to-right (or top-to-bottom), is the order in which the values are evaluated. Returns nil if none are set. This version replaces the original 'for _, val in pairs do' and a similar version that used ipairs. With the pairs version the order of evaluation could not be guaranteed. With the ipairs version, a nil value would terminate the for-loop before it reached the actual end of the list. ]] local function first_set (list, count) local i = 1; while i <= count do -- loop through all items in list if is_set( list[i] ) then return list[i]; -- return the first set list member end i = i + 1; -- point to next end end --[[--------------------------< I N _ A R R A Y >-------------------------------------------------------------- Whether needle is in haystack ]] local function in_array( needle, haystack ) if needle == nil then return false; end for n,v in ipairs( haystack ) do if v == needle then return n; end end return false; end --[[--------------------------< S U B S T I T U T E >---------------------------------------------------------- Populates numbered arguments in a message string using an argument table. ]] local function substitute( msg, args ) return args and mw.message.newRawMessage( msg, args ):plain() or msg; end --[[--------------------------< E R R O R _ C O M M E N T >---------------------------------------------------- Wraps error messages with css markup according to the state of hidden. ]] local function error_comment( content, hidden ) return substitute( hidden and cfg.presentation['hidden-error'] or cfg.presentation['visible-error'], content ); end --[[--------------------------< S E T _ E R R O R >-------------------------------------------------------------- Sets an error condition and returns the appropriate error message. The actual placement of the error message in the output is the responsibility of the calling function. ]] local function set_error( error_id, arguments, raw, prefix, suffix ) local error_state = cfg.error_conditions[ error_id ]; prefix = prefix or ""; suffix = suffix or ""; if error_state == nil then error( cfg.messages['undefined_error'] ); elseif is_set( error_state.category ) then table.insert( z.error_categories, error_state.category ); end local message = substitute( error_state.message, arguments ); message = message .. " ([[" .. cfg.messages['help page link'] .. "#" .. error_state.anchor .. "|" .. cfg.messages['help page label'] .. "]])"; z.error_ids[ error_id ] = true; if in_array( error_id, { 'bare_url_missing_title', 'trans_missing_title' } ) and z.error_ids['citation_missing_title'] then return '', false; end message = table.concat({ prefix, message, suffix }); if raw == true then return message, error_state.hidden; end return error_comment( message, error_state.hidden ); end --[[--------------------------< A D D _ M A I N T _ C A T >------------------------------------------------------ Adds a category to z.maintenance_cats using names from the configuration file with additional text if any. To prevent duplication, the added_maint_cats table lists the categories by key that have been added to z.maintenance_cats. ]] local added_maint_cats = {} -- list of maintenance categories that have been added to z.maintenance_cats local function add_maint_cat (key, arguments) if not added_maint_cats [key] then added_maint_cats [key] = true; -- note that we've added this category table.insert( z.maintenance_cats, substitute (cfg.maint_cats [key], arguments)); -- make name then add to table end end --[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- Adds a category to z.properties_cats using names from the configuration file with additional text if any. ]] local added_prop_cats = {} -- list of property categories that have been added to z.properties_cats local function add_prop_cat (key, arguments) if not added_prop_cats [key] then added_prop_cats [key] = true; -- note that we've added this category table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table end end --[[--------------------------< A D D _ V A N C _ E R R O R >---------------------------------------------------- Adds a single Vancouver system error message to the template's output regardless of how many error actually exist. To prevent duplication, added_vanc_errs is nil until an error message is emitted. ]] local added_vanc_errs; -- flag so we only emit one Vancouver error / category local function add_vanc_error () if not added_vanc_errs then added_vanc_errs = true; -- note that we've added this category table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } ); end end --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ does this thing that purports to be a uri scheme seem to be a valid scheme? The scheme is checked to see if it is in agreement with http://tools.ietf.org/html/std66#section-3.1 which says: Scheme names consist of a sequence of characters beginning with a letter and followed by any combination of letters, digits, plus ("+"), period ("."), or hyphen ("-"). returns true if it does, else false ]] local function is_scheme (scheme) return scheme and scheme:match ('^%a[%a%d%+%.%-]*:'); -- true if scheme is set and matches the pattern end --[=[-------------------------< I S _ D O M A I N _ N A M E >-------------------------------------------------- Does this thing that purports to be a domain name seem to be a valid domain name? Syntax defined here: http://tools.ietf.org/html/rfc1034#section-3.5 BNF defined here: https://tools.ietf.org/html/rfc4234 Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; see also [[Single-letter second-level domain]] list of tlds: https://www.iana.org/domains/root/db rfc952 (modified by rfc 1123) requires the first and last character of a hostname to be a letter or a digit. Between the first and last characters the name may use letters, digits, and the hyphen. Also allowed are IPv4 addresses. IPv6 not supported domain is expected to be stripped of any path so that the last character in the last character of the tld. tld is two or more alpha characters. Any preceding '//' (from splitting a url with a scheme) will be stripped here. Perhaps not necessary but retained incase it is necessary for IPv4 dot decimal. There are several tests: the first character of the whole domain name including subdomains must be a letter or a digit single-letter/digit second-level domains in the .org TLD q, x, and z SL domains in the .com TLD i and q SL domains in the .net TLD single-letter SL domains in the ccTLDs (where the ccTLD is two letters) two-character SL domains in gTLDs (where the gTLD is two or more letters) three-plus-character SL domains in gTLDs (where the gTLD is two or more letters) IPv4 dot-decimal address format; TLD not allowed returns true if domain appears to be a proper name and tld or IPv4 address, else false ]=] local function is_domain_name (domain) if not domain then return false; -- if not set, abandon end domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once if not domain:match ('^[%a%d]') then -- first character must be letter or digit return false; end if domain:match ('%f[%a%d][%a%d]%.org$') then -- one character .org hostname return true; elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) return true; elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) return true; elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix return true; elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname return true; elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) return true; elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld return true; elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.%a%a+$') then -- three or more character hostname.hostname or hostname.tld return true; elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address return true; else return false; end end --[[--------------------------< I S _ U R L >------------------------------------------------------------------ returns true if the scheme and domain parts of a url appear to be a valid url; else false. This function is the last step in the validation process. This function is separate because there are cases that are not covered by split_url(), for example is_parameter_ext_wikilink() which is looking for bracketted external wikilinks. ]] local function is_url (scheme, domain) if is_set (scheme) then -- if scheme is set check it and domain return is_scheme (scheme) and is_domain_name (domain); else return is_domain_name (domain); -- scheme not set when url is protocol relative end end --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ Split a url into a scheme, authority indicator, and domain. If protocol relative url, return nil scheme and domain else return nil for both scheme and domain. When not protocol relative, get scheme, authority indicator, and domain. If there is an authority indicator (one or more '/' characters following the scheme's colon), make sure that there are only 2. ]] local function split_url (url_str) local scheme, authority, domain; url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') if url_str:match ('^//%S*') then -- if there is what appears to be a protocol relative url domain = url_str:match ('^//(%S*)') elseif url_str:match ('%S-:/*%S+') then -- if there is what appears to be a scheme, optional authority indicator, and domain name scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; if is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then return scheme; -- return scheme only making domain nil which will cause an error message end domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present end return scheme, domain; end --[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- checks the content of |title-link=, |series-link=, |author-link= etc for properly formatted content: no wikilinks, no urls Link parameters are to hold the title of a wikipedia article so none of the WP:TITLESPECIALCHARACTERS are allowed: # < > [ ] | { } _ except the underscore which is used as a space in wiki urls and # which is used for section links returns false when the value contains any of these characters. When there are no illegal characters, this function returns TRUE if value DOES NOT appear to be a valid url (the |<param>-link= parameter is ok); else false when value appears to be a valid url (the |<param>-link= parameter is NOT ok). ]] local function link_param_ok (value) local scheme, domain; if value:find ('[<>%[%]|{}]') then -- if any prohibited characters return false; end scheme, domain = split_url (value); -- get scheme or nil and domain or nil from url; return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid url end --[[--------------------------< C H E C K _ U R L >------------------------------------------------------------ Determines whether a URL string appears to be valid. First we test for space characters. If any are found, return false. Then split the url into scheme and domain portions, or for protocol relative (//example.com) urls, just the domain. Use is_url() to validate the two portions of the url. If both are valid, or for protocol relative if domain is valid, return true, else false. ]] local function check_url( url_str ) if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper url return false; end local scheme, domain; scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from url; return is_url (scheme, domain); -- return true if value appears to be a valid url end --[=[-------------------------< I S _ P A R A M E T E R _ E X T _ W I K I L I N K >---------------------------- Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first non-space characters following the opening bracket appear to be a url. The test will also find external wikilinks that use protocol relative urls. Also finds bare urls. The frontier pattern prevents a match on interwiki links which are similar to scheme:path urls. The tests that find bracketed urls are required because the parameters that call this test (currently |title=, |chapter=, |work=, and |publisher=) may have wikilinks and there are articles or redirects like '//Hus' so, while uncommon, |title=[[//Hus]] is possible as might be [[en://Hus]]. ]=] local function is_parameter_ext_wikilink (value) local scheme, domain; value = value:gsub ('([^%s/])/[%a%d].*', '%1'); -- strip path information (the capture prevents false replacement of '//') if value:match ('%f[%[]%[%a%S*:%S+.*%]') then -- if ext wikilink with scheme and domain: [xxxx://yyyyy.zzz] scheme, domain = value:match ('%f[%[]%[(%a%S*:)(%S+).*%]') elseif value:match ('%f[%[]%[//%S*%.%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] domain = value:match ('%f[%[]%[//(%S*%.%S+).*%]'); elseif value:match ('%a%S*:%S+') then -- if bare url with scheme; may have leading or trailing plain text scheme, domain = value:match ('(%a%S*:)(%S+)'); elseif value:match ('//%S*%.%S+') then -- if protocol relative bare url: //yyyyy.zzz; may have leading or trailing plain text domain = value:match ('//(%S*%.%S+)'); -- what is left should be the domain else return false; -- didn't find anything that is obviously a url end return is_url (scheme, domain); -- return true if value appears to be a valid url end --[[-------------------------< C H E C K _ F O R _ U R L >----------------------------------------------------- loop through a list of parameters and their values. Look at the value and if it has an external link, emit an error message. ]] local function check_for_url (parameter_list) local error_message = ''; for k, v in pairs (parameter_list) do -- for each parameter in the list if is_parameter_ext_wikilink (v) then -- look at the value; if there is a url add an error message if is_set(error_message) then -- once we've added the first portion of the error message ... error_message=error_message .. ", "; -- ... add a comma space separator end error_message=error_message .. "|" .. k .. "="; -- add the failed parameter end end if is_set (error_message) then -- done looping, if there is an error message, display it table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } ); end end --[[--------------------------< S A F E _ F O R _ I T A L I C S >---------------------------------------------- Protects a string that will be wrapped in wiki italic markup '' ... '' Note: We cannot use <i> for italics, as the expected behavior for italics specified by ''...'' in the title is that they will be inverted (i.e. unitalicized) in the resulting references. In addition, <i> and '' tend to interact poorly under Mediawiki's HTML tidy. ]] local function safe_for_italics( str ) if not is_set(str) then return str; else if str:sub(1,1) == "'" then str = "<span></span>" .. str; end if str:sub(-1,-1) == "'" then str = str .. "<span></span>"; end -- Remove newlines as they break italics. return str:gsub( '\n', ' ' ); end end --[[--------------------------< S A F E _ F O R _ U R L >------------------------------------------------------ Escape sequences for content that will be used for URL descriptions ]] local function safe_for_url( str ) if str:match( "%[%[.-%]%]" ) ~= nil then table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } ); end return str:gsub( '[%[%]\n]', { ['['] = '[', [']'] = ']', ['\n'] = ' ' } ); end --[[--------------------------< W R A P _ S T Y L E >---------------------------------------------------------- Applies styling to various parameters. Supplied string is wrapped using a message_list configuration taking one argument; protects italic styled parameters. Additional text taken from citation_config.presentation - the reason this function is similar to but separate from wrap_msg(). ]] local function wrap_style (key, str) if not is_set( str ) then return ""; elseif in_array( key, { 'italic-title', 'trans-italic-title' } ) then str = safe_for_italics( str ); end return substitute( cfg.presentation[key], {str} ); end --[[--------------------------< E X T E R N A L _ L I N K >---------------------------------------------------- Format an external link with error checking ]] local function external_link( URL, label, source ) local error_str = ""; if not is_set( label ) then label = URL; if is_set( source ) then error_str = set_error( 'bare_url_missing_title', { wrap_style ('parameter', source) }, false, " " ); else error( cfg.messages["bare_url_no_origin"] ); end end if not check_url( URL ) then error_str = set_error( 'bad_url', {wrap_style ('parameter', source)}, false, " " ) .. error_str; end return table.concat({ "[", URL, " ", safe_for_url( label ), "]", error_str }); end --[[--------------------------< E X T E R N A L _ L I N K _ I D >---------------------------------------------- Formats a wiki style external link ]] 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 return mw.ustring.format( '[%s%s%s \<span title\=\"%s\"\>%s%s%s\<\/span\>]', options.prefix, url_string, options.suffix or "", options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) ); end --[[--------------------------< D E P R E C A T E D _ P A R A M E T E R >-------------------------------------- Categorize and emit an error message when the citation contains one or more deprecated parameters. The function includes the offending parameter name to the error message. Only one error message is emitted regardless of the number of deprecated parameters in the citation. ]] local page_in_deprecated_cat; -- sticky flag so that the category is added only once local function deprecated_parameter(name) if not page_in_deprecated_cat then page_in_deprecated_cat = true; -- note that we've added this category table.insert( z.message_tail, { set_error( 'deprecated_params', {name}, true ) } ); -- add error message end end --[[--------------------------< 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: "'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) Double single quotes (italic or bold wikimarkup) are not kerned. Call this function for chapter titles, for website titles, etc; not for book titles. ]] local function kern_quotes (str) local cap=''; local cap2=''; cap, cap2 = str:match ("^([\"\'])([^\'].+)"); -- match leading double or single quote but not double single quotes if is_set (cap) then str = substitute (cfg.presentation['kern-left'], {cap, cap2}); end cap, cap2 = str:match ("^(.+[^\'])([\"\'])$") if is_set (cap) then str = substitute (cfg.presentation['kern-right'], {cap, cap2}); 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 not be italicized and may be written right-to-left. The value supplied by |script-title= is concatenated onto Title after Title has been wrapped in italic markup. Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate rtl languages from the English left to right. |script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO639-1 language code and a colon: |script-title=ja:*** *** (where * represents a Japanese character) Spaces between the two-character code and the colon and the colon and the first script character are allowed: |script-title=ja : *** *** |script-title=ja: *** *** |script-title=ja :*** *** Spaces preceding the prefix are allowed: |script-title = ja:*** *** The prefix is checked for validity. If it is a valid ISO639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute is not added. At this time there is no error message for this condition. Supports |script-title= and |script-chapter= TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script; ]] local function format_script_value (script_value) local lang=''; -- initialize to empty string local name; if script_value:match('^%l%l%s*:') then -- if first 3 non-space characters are script language prefix lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script if not is_set (lang) then return ''; -- script_value was just the prefix so return empty string end -- if we get this far we have prefix and script name = mw.language.fetchLanguageName( lang, mw.getContentLanguage():getCode() ); -- get language name so that we can use it to categorize if is_set (name) then -- is prefix a proper ISO 639-1 language code? script_value = script_value:gsub ('^%l%l%s*:%s*', ''); -- strip prefix from script -- is prefix one of these language codes? if in_array (lang, {'ar', 'bg', 'bs', 'dv', 'el', 'fa', 'he', 'hy', 'ja', 'ka', 'ko', 'ku', 'mk', 'ps', 'ru', 'sd', 'sr', 'th', 'uk', 'ug', 'yi', 'zh'}) then add_prop_cat ('script_with_name', {name, lang}) else add_prop_cat ('script') end lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute else lang = ''; -- invalid so set lang to empty string end end if is_set(script_value) then script_value = '-{R|' .. script_value .. '}-'; end script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is rtl return script_value; end --[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ Initially for |title= and |script-title=, this function concatenates those two parameter values after the script value has been wrapped in <bdi> tags. ]] local function script_concatenate (title, script) if is_set(title) then title = '-{zh;zh-hans;zh-hant|' .. title .. '}-'; end if is_set (script) then script = format_script_value (script); -- <bdi> tags, lang atribute, categorization, etc; returns empty string on error if is_set (script) then title = title .. ' ' .. script; -- concatenate title and script title end end return title; end --[[--------------------------< W R A P _ M S G >-------------------------------------------------------------- Applies additional message text to various parameter values. Supplied string is wrapped using a message_list configuration taking one argument. Supports lower case text for {{citation}} templates. Additional text taken from citation_config.messages - the reason this function is similar to but separate from wrap_style(). ]] local function wrap_msg (key, str, lower) if not is_set( str ) then return ""; end if true == lower then local msg; msg = cfg.messages[key]:lower(); -- set the message to lower case before return substitute( msg, str ); -- including template text else return substitute( cfg.messages[key], str ); end end --[[-------------------------< I S _ A L I A S _ U S E D >----------------------------------------------------- This function is used by select_one() to determine if one of a list of alias parameters is in the argument list provided by the template. Input: args – pointer to the arguments table from calling template alias – one of the list of possible aliases in the aliases lists from Module:Citation/CS1/Configuration index – for enumerated parameters, identifies which one enumerated – true/false flag used choose how enumerated aliases are examined value – value associated with an alias that has previously been selected; nil if not yet selected selected – the alias that has previously been selected; nil if not yet selected error_list – list of aliases that are duplicates of the alias already selected Returns: value – value associated with alias we selected or that was previously selected or nil if an alias not yet selected selected – the alias we selected or the alias that was previously selected or nil if an alias not yet selected ]] local function is_alias_used (args, alias, index, enumerated, value, selected, error_list) if enumerated then -- is this a test for an enumerated parameters? alias = alias:gsub ('#', index); -- replace '#' with the value in index else alias = alias:gsub ('#', ''); -- remove '#' if it exists end if is_set(args[alias]) then -- alias is in the template's argument list if value ~= nil and selected ~= alias then -- if we have already selected one of the aliases local skip; for _, v in ipairs(error_list) do -- spin through the error list to see if we've added this alias if v == alias then skip = true; break; -- has been added so stop looking end end if not skip then -- has not been added so table.insert( error_list, alias ); -- add error alias to the error list end else value = args[alias]; -- not yet selected an alias, so select this one selected = alias; end end return value, selected; -- return newly selected alias, or previously selected alias end --[[--------------------------< S E L E C T _ O N E >---------------------------------------------------------- Chooses one matching parameter from a list of parameters to consider. The list of parameters to consider is just names. For parameters that may be enumerated, the position of the numerator in the parameter name is identified by the '#' so |author-last1= and |author1-last= are represented as 'author-last#' and 'author#-last'. Because enumerated parameter |<param>1= is an alias of |<param>= we must test for both possibilities. Generates an error if more than one match is present. ]] local function select_one( args, aliases_list, error_condition, index ) local value = nil; -- the value assigned to the selected parameter local selected = ''; -- the name of the parameter we have chosen local error_list = {}; if index ~= nil then index = tostring(index); end for _, alias in ipairs( aliases_list ) do -- for each alias in the aliases list if alias:match ('#') then -- if this alias can be enumerated if '1' == index then -- when index is 1 test for enumerated and non-enumerated aliases value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); -- first test for non-enumerated alias end value, selected = is_alias_used (args, alias, index, true, value, selected, error_list); -- test for enumerated alias else value, selected = is_alias_used (args, alias, index, false, value, selected, error_list); --test for non-enumerated alias end end if #error_list > 0 and 'none' ~= error_condition then -- for cases where this code is used outside of extract_names() local error_str = ""; for _, k in ipairs( error_list ) do if error_str ~= "" then error_str = error_str .. cfg.messages['parameter-separator'] end error_str = error_str .. wrap_style ('parameter', k); end if #error_list > 1 then error_str = error_str .. cfg.messages['parameter-final-separator']; else error_str = error_str .. cfg.messages['parameter-pair-separator']; end error_str = error_str .. wrap_style ('parameter', selected); table.insert( z.message_tail, { set_error( error_condition, {error_str}, true ) } ); end return value, selected; end --[[--------------------------< F O R M A T _ C H A P T E R _ T I T L E >-------------------------------------- Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta- parameter (chapter_url_source used for error messages). ]] local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes) local chapter_error = ''; if not is_set (chapter) then chapter = ''; -- to be safe for concatenation else if false == no_quotes then chapter = kern_quotes (chapter); -- if necessary, separate chapter title's leading and trailing quote marks from Module provided quote marks chapter = wrap_style ('quoted-title', chapter); end end chapter = script_concatenate (chapter, scriptchapter) -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped if is_set (transchapter) then transchapter = wrap_style ('trans-quoted-title', transchapter); if is_set (chapter) then chapter = chapter .. ' ' .. transchapter; else -- here when transchapter without chapter or script-chapter chapter = transchapter; -- chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); end end if is_set (chapterurl) then chapter = external_link (chapterurl, chapter, chapter_url_source); -- adds bare_url_missing_title error if appropriate end return chapter .. chapter_error; end --[[--------------------------< H A S _ I N V I S I B L E _ C H A R S >---------------------------------------- This function searches a parameter's value for nonprintable or invisible characters. The search stops at the first match. This function will detect the visible replacement character when it is part of the wikisource. Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref) and identifies them with a slightly different error message. See also coins_cleanup(). Detects but ignores the character pattern that results from the transclusion of {{'}} templates. Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the parameter value. ]] local function has_invisible_chars (param, v) local position = ''; -- position of invisible char or starting position of stripmarker local dummy; -- end of matching string; not used but required to hold end position when a capture is returned local capture; -- used by stripmarker detection to hold name of the stripmarker local i=1; local stripmarker, apostrophe; while cfg.invisible_chars[i] do local char=cfg.invisible_chars[i][1] -- the character or group name local pattern=cfg.invisible_chars[i][2] -- the pattern used to find it position, dummy, capture = mw.ustring.find (v, pattern) -- see if the parameter value contains characters that match the pattern if position then if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) ('templatestyles' == capture) then -- templatestyles stripmarker allowed 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 .. ' ' .. cfg.invisible_chars[i][3] or char; else err_msg = cfg.invisible_chars[i][3] or (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 local args, list, v = args, cfg.aliases[k]; if type( list ) == 'table' then v, origin[k] = select_one( args, list, 'redundant_parameters' ); if origin[k] == nil then origin[k] = ''; -- Empty string, not nil end elseif list ~= nil then v, origin[k] = args[list], list; else -- maybe let through instead of raising an error? -- v, origin[k] = args[k], k; error( cfg.messages['unknown_argument_map'] ); end -- Empty strings, not nil; if v == nil then v = cfg.defaults[k] or ''; origin[k] = ''; end tbl = rawset( tbl, k, v ); return v; 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: 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 -- Formats a wiki style internal link local function internal_link_id(options) return mw.ustring.format( '[[%s%s%s|\<span title\=\"%s\"\>%s\<\/span\>%s%s]]', options.prefix, options.id, options.suffix or "", options.link, options.label, options.separator or " ", mw.text.nowiki(options.id) ); end --[[--------------------------< N O W R A P _ D A T E >-------------------------------------------------------- When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY DOES NOT yet support MMMM YYYY or any of the date ranges. ]] local function nowrap_date (date) local cap=''; local cap2=''; if date:match("^%d%d%d%d%-%d%d%-%d%d$") then date = substitute (cfg.presentation['nowrap1'], date); elseif date:match("^%a+%s*%d%d?,%s+%d%d%d%d$") or date:match ("^%d%d?%s*%a+%s+%d%d%d%d$") then cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$"); date = substitute (cfg.presentation['nowrap2'], {cap, cap2}); end return date; end --[[--------------------------< IS _ V A L I D _ I S X N >----------------------------------------------------- ISBN-10 and ISSN validator code calculates checksum across all isbn/issn digits including the check digit. ISBN-13 is checked in check_isbn(). If the number is valid the result will be 0. Before calling this function, issbn/issn must be checked for length and stripped of dashes, spaces and other non-isxn characters. ]] local function is_valid_isxn (isxn_str, len) local temp = 0; isxn_str = { isxn_str:byte(1, len) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39, 'X' → 0x58 len = len+1; -- adjust to be a loop counter for i, v in ipairs( isxn_str ) do -- loop through all of the bytes and calculate the checksum if v == string.byte( "X" ) then -- if checkdigit is X (compares the byte value of 'X' which is 0x58) temp = temp + 10*( len - i ); -- it represents 10 decimal else temp = temp + tonumber( string.char(v) )*(len-i); end end return temp % 11 == 0; -- returns true if calculation result is zero end --[[--------------------------< IS _ V A L I D _ I S X N _ 1 3 >---------------------------------------------- ISBN-13 and ISMN validator code calculates checksum across all 13 isbn/ismn digits including the check digit. If the number is valid, the result will be 0. Before calling this function, isbn-13/ismn must be checked for length and stripped of dashes, spaces and other non-isxn-13 characters. ]] local function is_valid_isxn_13 (isxn_str) local temp=0; isxn_str = { isxn_str:byte(1, 13) }; -- make a table of byte values '0' → 0x30 .. '9' → 0x39 for i, v in ipairs( isxn_str ) do 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 end return temp % 10 == 0; -- sum modulo 10 is zero when isbn-13/ismn is correct end --[[--------------------------< C H E C K _ I S B N >------------------------------------------------------------ Determines whether an ISBN string is valid ]] local function check_isbn( isbn_str ) if nil ~= isbn_str:match("[^%s-0-9X]") then return false; end -- fail if isbn_str contains anything but digits, hyphens, or the uppercase X isbn_str = isbn_str:gsub( "-", "" ):gsub( " ", "" ); -- remove hyphens and spaces local len = isbn_str:len(); if len ~= 10 and len ~= 13 then return false; end if len == 10 then if isbn_str:match( "^%d*X?$" ) == nil then return false; end return is_valid_isxn(isbn_str, 10); else local temp = 0; if isbn_str:match( "^97[89]%d*$" ) == nil then return false; end -- isbn13 begins with 978 or 979; ismn begins with 979 return is_valid_isxn_13 (isbn_str); end end --[[--------------------------< C H E C K _ I S M N >------------------------------------------------------------ Determines whether an ISMN string is valid. Similar to isbn-13, ismn is 13 digits begining 979-0-... and uses the same check digit calculations. See http://www.ismn-international.org/download/Web_ISMN_Users_Manual_2008-6.pdf section 2, pages 9–12. ]] local function ismn (id) local handler = cfg.id_handlers['ISMN']; local text; local valid_ismn = true; id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the ismn if 13 ~= id:len() or id:match( "^9790%d*$" ) == 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, e) local issn_copy = id; -- save a copy of unadulterated issn; use this version for display if issn does not validate local handler; local text; local valid_issn = true; if e then handler = cfg.id_handlers['EISSN']; else handler = cfg.id_handlers['ISSN']; end id=id:gsub( "[%s-–]", "" ); -- strip spaces, hyphens, and endashes from the issn if 8 ~= id:len() or nil == id:match( "^%d*X?$" ) then -- validate the issn: 8 digits long, containing only 0-9 or X in the last position valid_issn=false; -- wrong length or improper character else valid_issn=is_valid_isxn(id, 8); -- validate issn end if true == valid_issn then id = string.sub( id, 1, 4 ) .. "-" .. string.sub( id, 5 ); -- if valid, display correctly formatted version else id = issn_copy; -- if not valid, use the show the invalid issn with error message end text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) if false == valid_issn then text = text .. ' ' .. set_error( 'bad_issn' ) -- add an error message if the issn is invalid end return text end --[[--------------------------< A M A Z O N >------------------------------------------------------------------ Formats a link to Amazon. Do simple error checking: asin must be mix of 10 numeric or uppercase alpha characters. If a mix, first character must be uppercase alpha; if all numeric, asins must be 10-digit isbn. If 10-digit isbn, add a maintenance category so a bot or awb script can replace |asin= with |isbn=. Error message if not 10 characters, if not isbn10, if mixed and first character is a digit. ]] local function amazon(id, domain) local err_cat = "" if not id:match("^[%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u][%d%u]$") 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]$") then -- if 10-digit numeric (or 9 digits with terminal X) if check_isbn( id ) then -- see if asin value is isbn10 add_maint_cat ('ASIN'); elseif not is_set (err_cat) then err_cat = ' ' .. set_error ('bad_asin'); -- asin is not isbn10 end elseif not id:match("^%u[%d%u]+$") then err_cat = ' ' .. set_error ('bad_asin'); -- asin doesn't begin with uppercase alpha end end if not is_set(domain) then domain = "com"; elseif in_array (domain, {'jp', 'uk'}) then -- Japan, United Kingdom domain = "co." .. domain; elseif in_array (domain, {'au', 'br', 'mx'}) then -- Australia, Brazil, Mexico domain = "com." .. domain; end local handler = cfg.id_handlers['ASIN']; return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. domain .. "/dp/", id=id, encode=handler.encode, separator = handler.separator}) .. err_cat; end --[[--------------------------< A R X I V >-------------------------------------------------------------------- See: http://arxiv.org/help/arxiv_identifier format and error check arXiv identifier. There are three valid forms of the identifier: 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 handler = cfg.id_handlers['ARXIV']; local year, month, version; local err_cat = ''; local text; if id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%d$") or id:match("^%a[%a%.%-]+/[90]%d[01]%d%d%d%dv%d+$") then -- test for the 9108-0703 format w/ & w/o version year, month = id:match("^%a[%a%.%-]+/([90]%d)([01]%d)%d%d%d[v%d]*$"); year = tonumber(year); month = tonumber(month); if ((not (90 < year or 8 > year)) or (1 > month or 12 < month)) or -- if invalid year or invalid month ((91 == year and 7 > month) or (7 == year and 3 < month)) then -- if years ok, are starting and ending months ok? err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message end elseif id:match("^%d%d[01]%d%.%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%dv%d+$") then -- test for the 0704-1412 w/ & w/o version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d[v%d]*$"); year = tonumber(year); month = tonumber(month); if ((7 > year) or (14 < year) or (1 > month or 12 < month)) or -- is year invalid or is month invalid? (doesn't test for future years) ((7 == year) and (4 > month)) then --or -- when year is 07, is month invalid (before April)? err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message end elseif id:match("^%d%d[01]%d%.%d%d%d%d%d$") or id:match("^%d%d[01]%d%.%d%d%d%d%dv%d+$") then -- test for the 1501- format w/ & w/o version year, month = id:match("^(%d%d)([01]%d)%.%d%d%d%d%d[v%d]*$"); year = tonumber(year); month = tonumber(month); if ((15 > year) or (1 > month or 12 < month)) then -- is year invalid or is month invalid? (doesn't test for future years) err_cat = ' ' .. set_error( 'bad_arxiv' ); -- set error message end else err_cat = ' ' .. set_error( 'bad_arxiv' ); -- arXiv id doesn't match any format end text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. err_cat; if is_set (class) then class = ' [[' .. '//arxiv.org/archive/' .. class .. ' ' .. class .. ']]'; -- external link within square brackets, not wikilink else class = ''; -- empty string for concatenation end return text .. class; end --[[ lccn normalization (http://www.loc.gov/marc/lccn-namespace.html#normalization) 1. Remove all blanks. 2. If there is a forward slash (/) in the string, remove it, and remove all characters to the right of the forward slash. 3. If there is a hyphen in the string: a. Remove it. b. Inspect the substring following (to the right of) the (removed) hyphen. Then (and assuming that steps 1 and 2 have been carried out): 1. All these characters should be digits, and there should be six or less. (not done in this function) 2. If the length of the substring is less than 6, left-fill the substring with zeroes until the length is six. Returns a normalized lccn for lccn() to validate. There is no error checking (step 3.b.1) performed in this function. ]] local function normalize_lccn (lccn) lccn = lccn:gsub ("%s", ""); -- 1. strip whitespace if nil ~= string.find (lccn,'/') then lccn = lccn:match ("(.-)/"); -- 2. remove forward slash and all character to the right of it end local prefix local suffix prefix, suffix = lccn:match ("(.+)%-(.+)"); -- 3.a remove hyphen by splitting the string into prefix and suffix if nil ~= suffix then -- if there was a hyphen suffix=string.rep("0", 6-string.len (suffix)) .. suffix; -- 3.b.2 left fill the suffix with 0s if suffix length less than 6 lccn=prefix..suffix; -- reassemble the lccn end return lccn; end --[[ Format LCCN link and do simple error checking. LCCN is a character string 8-12 characters long. The length of the LCCN dictates the character type of the first 1-3 characters; the rightmost eight are always digits. http://info-uri.info/registry/OAIHandler?verb=GetRecord&metadataPrefix=reg&identifier=info:lccn/ length = 8 then all digits length = 9 then lccn[1] is lower case alpha length = 10 then lccn[1] and lccn[2] are both lower case alpha or both digits length = 11 then lccn[1] is lower case alpha, lccn[2] and lccn[3] are both lower case alpha or both digits length = 12 then lccn[1] and lccn[2] are both lower case alpha ]] local function lccn(lccn) local handler = cfg.id_handlers['LCCN']; local err_cat = ''; -- presume that LCCN is valid local id = lccn; -- local copy of the lccn id = normalize_lccn (id); -- get canonical form (no whitespace, hyphens, forward slashes) local len = id:len(); -- get the length of the lccn if 8 == len then if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message end elseif 9 == len then -- LCCN should be adddddddd if nil == id:match("%l%d%d%d%d%d%d%d%d") then -- does it match our pattern? err_cat = ' ' .. set_error( 'bad_lccn' ); -- set an error message end elseif 10 == len then -- LCCN should be aadddddddd or dddddddddd if id:match("[^%d]") then -- if LCCN has anything but digits (nil if only digits) ... if nil == id:match("^%l%l%d%d%d%d%d%d%d%d") then -- ... see if it matches our pattern err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message end end elseif 11 == len then -- LCCN should be aaadddddddd or adddddddddd if not (id:match("^%l%l%l%d%d%d%d%d%d%d%d") or id:match("^%l%d%d%d%d%d%d%d%d%d%d")) then -- see if it matches one of our patterns err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message end elseif 12 == len then -- LCCN should be aadddddddddd if not id:match("^%l%l%d%d%d%d%d%d%d%d%d%d") then -- see if it matches our pattern err_cat = ' ' .. set_error( 'bad_lccn' ); -- no match, set an error message end else err_cat = ' ' .. set_error( 'bad_lccn' ); -- wrong length, set an error message end if not is_set (err_cat) and nil ~= lccn:find ('%s') then err_cat = ' ' .. set_error( 'bad_lccn' ); -- lccn contains a space, set an error message end return external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=lccn,separator=handler.separator, encode=handler.encode}) .. err_cat; end --[[--------------------------< P M I D >---------------------------------------------------------------------- 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) local test_limit = 33000000; -- update this value as PMIDs approach local handler = cfg.id_handlers['PMID']; local err_cat = ''; -- presume that PMID is valid if id:match("[^%d]") then -- if PMID has anything but digits err_cat = ' ' .. set_error( 'bad_pmid' ); -- set an error message 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 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 return ''; -- |embargo= not set return empty string end --[[--------------------------< P M C >------------------------------------------------------------------------ Format a PMC, do simple error checking, and check for embargoed articles. The embargo parameter takes a date for a value. If the embargo date is in the future the PMC identifier will not be linked to the article. If the embargo 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 test_limit = 7000000; -- update this value as PMCs approach local handler = cfg.id_handlers['PMC']; local err_cat = ''; -- presume that PMC is valid local id_num; local text; id_num = id:match ('^[Pp][Mm][Cc](%d+)$'); -- identifier with pmc prefix if is_set (id_num) then add_maint_cat ('pmc_format'); else -- plain number without pmc prefix id_num = id:match ('^%d+$'); -- if here id is all digits end if is_set (id_num) then -- id_num has a value so test it id_num = tonumber(id_num); -- convert id_num to a number for range testing if 1 > id_num or test_limit < id_num then -- if PMC is outside test limit boundaries err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message else id = tostring (id_num); -- make sure id is a string end else -- when id format incorrect err_cat = ' ' .. set_error( 'bad_pmc' ); -- set an error message end if is_set (embargo) then -- is PMC is still embargoed? text = table.concat ( -- still embargoed so no external link { make_wikilink (handler.link, handler.label), handler.separator, id, err_cat }); 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 --[[--------------------------< D O I >------------------------------------------------------------------------ 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; if is_set(inactive) then local inactive_year = inactive:match("%d%d%d%d") or ''; -- try to get the year portion from the inactive date if is_set(inactive_year) then table.insert( z.error_categories, "自" .. inactive_year .. "年含有不活躍DOI的頁面" ); else table.insert( z.error_categories, "含有不活躍DOI的頁面" ); -- when inactive doesn't contain a recognizable year end inactive = " (" .. cfg.messages['inactive'] .. " " .. inactive .. ")" end text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) .. (inactive or '') if nil == id:match("^10%.[^%s–]-/[^%s–]-[^%.,]$") then -- doi must begin with '10.', must contain a fwd slash, must not contain spaces or endashes, and must not end with period or comma cat = ' ' .. set_error( 'bad_doi' ); end return text .. cat end --[[--------------------------< H D L >------------------------------------------------------------------------ Formats an HDL with minor error checking. HDL names contain two parts: prefix and suffix separated by a forward slash. Prefix: character string using any character in the UCS-2 character set except '/' Suffix: character string of any length using any character in the UCS-2 character set chosen by the registrant This function checks a HDL name for: prefix/suffix. If the HDL name contains spaces, endashes, or, if it ends with a period or a comma, this function will emit a bad_hdl error message. HDL names are case-insensitive and can incorporate any printable Unicode characters so the test for endashes and terminal punctuation may not be technically correct but it appears, that in practice these characters are rarely if ever used in HDLs. ]] local function hdl(id) local handler = cfg.id_handlers['HDL']; local text = external_link_id({link = handler.link, label = handler.label, prefix=handler.prefix,id=id,separator=handler.separator, encode=handler.encode}) if nil == id:match("^[^%s–]-/[^%s–]-[^%.,]$") then -- hdl must contain a fwd slash, must not contain spaces, endashes, and must not end with period or comma text = text .. ' ' .. set_error( 'bad_hdl' ); end return text; end --[[--------------------------< O P E N L I B R A R Y >-------------------------------------------------------- Formats an OpenLibrary link, and checks for associated errors. ]] local function openlibrary(id) local code = id:match("^%d+([AMW])$"); -- only digits followed by 'A', 'M', or 'W' local handler = cfg.id_handlers['OL']; if ( code == "A" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'authors/OL', id=id, separator=handler.separator, encode = handler.encode}) elseif ( code == "M" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'books/OL', id=id, separator=handler.separator, encode = handler.encode}) elseif ( code == "W" ) then return external_link_id({link=handler.link, label=handler.label, prefix=handler.prefix .. 'works/OL', id=id, separator=handler.separator, encode = handler.encode}) else 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 --[[--------------------------< M E S S A G E _ I D >---------------------------------------------------------- Validate and format a usenet message id. Simple error checking, looks for 'id-left@id-right' not enclosed in '<' and/or '>' angle brackets. ]] 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 end --[[--------------------------< S E T _ T I T L E T Y P E >---------------------------------------------------- This function sets default title types (equivalent to the citation including |type=<default value>) for those 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 return cfg.title_types [cite_class] or ''; -- set template's default title type; else empty string for concatenation end --[[--------------------------< C L E A N _ I S B N >---------------------------------------------------------- Removes irrelevant text and dashes from ISBN number Similar to that used for Special:BookSources ]] local function clean_isbn( isbn_str ) return isbn_str:gsub( "[^-0-9X]", "" ); end --[[--------------------------< E S C A P E _ L U A _ M A G I C _ C H A R S >---------------------------------- Returns a string where all of lua's magic characters have been escaped. This is important because functions like string.gsub() treat their pattern and replace strings as patterns, not literal strings. ]] local function escape_lua_magic_chars (argument) argument = argument:gsub("%%", "%%%%"); -- replace % with %% argument = argument:gsub("([%^%$%(%)%.%[%]%*%+%-%?])", "%%%1"); -- replace all other lua magic pattern characters return argument; end --[[--------------------------< S T R I P _ A P O S T R O P H E _ M A R K U P >-------------------------------- Strip wiki italic and bold markup from argument so that it doesn't contaminate COinS metadata. This function strips common patterns of apostrophe markup. We presume that editors who have taken the time to markup a title have, as a result, provided valid markup. When they don't, some single apostrophes are left behind. ]] local function strip_apostrophe_markup (argument) if not is_set (argument) then return argument; end while true do if argument:match ("%'%'%'%'%'") then -- bold italic (5) argument=argument:gsub("%'%'%'%'%'", ""); -- remove all instances of it elseif argument:match ("%'%'%'%'") then -- italic start and end without content (4) argument=argument:gsub("%'%'%'%'", ""); elseif argument:match ("%'%'%'") then -- bold (3) argument=argument:gsub("%'%'%'", ""); elseif argument:match ("%'%'") then -- italic (2) argument=argument:gsub("%'%'", ""); else break; end end return argument; -- done end --[[--------------------------< M A K E _ C O I N S _ T I T L E >---------------------------------------------- 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) if is_set (title) then title = strip_apostrophe_markup (title); -- strip any apostrophe markup else title=''; -- if not set, make sure title is an empty string end if is_set (script) then script = script:gsub ('^%l%l%s*:%s*', ''); -- remove language prefix if present (script value may now be empty string) script = strip_apostrophe_markup (script); -- strip any apostrophe markup else script=''; -- if not set, make sure script is an empty string end if is_set (title) and is_set (script) then script = ' ' .. script; -- add a space before we concatenate end return title .. script; -- return the concatenation end --[[--------------------------< G E T _ C O I N S _ P A G E S >------------------------------------------------ Extract page numbers from external wikilinks in any of the |page=, |pages=, or |at= parameters for use in COinS. ]] local function get_coins_pages (pages) local pattern; if not is_set (pages) then return pages; end -- if no page numbers then we're done while true do pattern = pages:match("%[(%w*:?//[^ ]+%s+)[%w%d].*%]"); -- pattern is the opening bracket, the url and following space(s): "[url " if nil == pattern then break; end -- no more urls pattern = escape_lua_magic_chars (pattern); -- pattern is not a literal string; escape lua's magic pattern characters pages = pages:gsub(pattern, ""); -- remove as many instances of pattern as possible end pages = pages:gsub("[%[%]]", ""); -- remove the brackets pages = pages:gsub("–", "-" ); -- replace endashes with hyphens pages = pages:gsub("&%w+;", "-" ); -- and replace html entities (– etc.) with hyphens; do we need to replace numerical entities like   and the like? return pages; end -- 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 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 >------------------------------------------------------------ Joins a sequence of strings together while checking for duplicate separation characters. ]] local function safe_join( tbl, duplicate_char ) --[[ Note: we use string functions here, rather than ustring functions. This has considerably faster performance and should work correctly as long as the duplicate_char is strict ASCII. The strings in tbl may be ASCII or UTF8. ]] local str = ''; -- the output string local comp = ''; -- what does 'comp' mean? local end_chr = ''; local trim; for _, value in ipairs( tbl ) do if value == nil then value = ''; end if str == '' then -- if output string is empty str = value; -- assign value to it (first time through the loop) elseif value ~= '' then if value:sub(1,1) == '<' then -- Special case of values enclosed in spans and other markup. comp = value:gsub( "%b<>", "" ); -- remove html markup (<span>string</span> -> string) else comp = value; end -- typically duplicate_char is sepc if comp:sub(1,1) == duplicate_char then -- is first charactier same as duplicate_char? why test first character? -- Because individual string segments often (always?) begin with terminal punct for th -- preceding segment: 'First element' .. 'sepc next element' .. etc? trim = false; end_chr = str:sub(-1,-1); -- get the last character of the output string -- str = str .. "<HERE(enchr=" .. end_chr.. ")" -- debug stuff? if end_chr == duplicate_char then -- if same as separator str = str:sub(1,-2); -- remove it elseif end_chr == "'" then -- if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' str = str:sub(1, -4) .. "''"; -- remove them and add back '' elseif str:sub(-5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' trim = true; -- why? why do this and next differently from previous? elseif str:sub(-4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' trim = true; -- same question end elseif end_chr == "]" then -- if it might be wikimarkup if str:sub(-3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink trim = true; elseif str:sub(-2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link trim = true; elseif str:sub(-4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. trim = true; end elseif end_chr == " " then -- if last char of output string is a space if str:sub(-2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> str = str:sub(1,-3); -- remove them both end end if trim then if value ~= comp then -- value does not equal comp when value contains html markup local dup2 = duplicate_char; if dup2:match( "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it value = value:gsub( "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows html markup else value = value:sub( 2, -1 ); -- remove duplicate_char when it is first character end end end 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 uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character. When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters. These things are not currently possible in this module so are left to the editor to do. This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF [http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F [http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F |lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here because the code editor gets confused between character insertion point and cursor position. ]] local function is_good_vanc_name (last, first) if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then add_vanc_error (); return false; -- not a string of latin characters; Vancouver required Romanization end; return true; end --[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ Attempts to convert names to initials in support of |name-list-format=vanc. Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name (). ]] local function reduce_to_initials(first) if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do local initials = {} local i = 0; -- counter for number of initials for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops. i = i + 1; -- bump the counter if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit end return table.concat(initials) -- Vancouver format does not include spaces. end --[[--------------------------< L I S T _ P E O P L E >------------------------------------------------------- Formats a list of people (e.g. authors / editors) ]] local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function local sep; local namesep; local format = control.format local maximum = control.maximum local lastauthoramp = control.lastauthoramp; local text = {} if 'vanc' == format then -- Vancouver-like author/editor name styling? sep = ','; -- name-list separator between authors is a comma namesep = ' '; -- last/first separator is a space else sep = ';' -- name-list separator between authors is a semicolon namesep = ', ' -- last/first separator is <comma><space> end if sep:sub(-1,-1) ~= " " then sep = sep .. " " end if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors for i,person in ipairs(people) do if is_set(person.last) then local mask = person.mask local one local sep_one = sep; if is_set (maximum) and i > maximum then etal = true; break; elseif (mask ~= nil) then local n = tonumber(mask) if (n ~= nil) then one = string.rep("—",n) else one = mask; sep_one = " "; end else one = person.last local first = person.first if is_set(first) then if ( "vanc" == format ) then -- if vancouver format one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested first = reduce_to_initials(first) -- attempt to convert first name(s) to initials end end one = one .. namesep .. first end if is_set(person.link) and person.link ~= control.page_name then one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page end end table.insert( text, one ) table.insert( text, sep_one ) end end local count = #text / 2; -- (number of names + number of separators) divided by 2 if count > 0 then if count > 1 and is_set(lastauthoramp) and not etal then text[#text-2] = " & "; -- replace last separator with ampersand text end text[#text] = nil; -- erase the last separator end local result = table.concat(text) -- construct list if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al. end return result, count 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. namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year. ]] local function anchor_id (namelist, year) local names={}; -- a table for the one to four names and year for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names names[i] = v.last if i == 4 then break end -- if four then done end table.insert (names, year); -- add the year at the end local id = table.concat(names); -- concatenate names and year for CITEREF id if 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 --[[--------------------------< N A M E _ H A S _ E T A L >---------------------------------------------------- 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. This function never sets the flag to false but returns it's previous state because it may have been set by previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal ]] local function name_has_etal (name, etal, nocat) 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 --[[--------------------------< 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. Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the search is done. This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3= are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the template's metadata. When this occurs, the page is added to a maintenance category. ]] local function extract_names(args, list_name) local names = {}; -- table of names local last; -- individual name components local first; local link; local mask; local i = 1; -- loop counter/indexer local n = 1; -- output table indexer local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors) local etal=false; -- return value set to true when we find some form of et al. in an author parameter local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary while true do last = select_one( args, cfg.aliases[list_name .. '-Last'], 'redundant_parameters', i ); -- search through args for name components beginning at 1 first = select_one( args, cfg.aliases[list_name .. '-First'], 'redundant_parameters', i ); link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al. first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al. if first and not last then -- if there is a firstn without a matching lastn table.insert( z.message_tail, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message elseif not first and not last then -- if both firstn and lastn aren't found, are we done? count = count + 1; -- number of times we haven't found last and first if 2 <= count then -- two missing names and we give up break; -- normal exit or there is a two-name hole in the list; can't tell which end else -- we have last with or without a first if is_set (link) and false == link_param_ok (link) then -- do this test here in case link is missing last table.insert( z.message_tail, { set_error( 'bad_paramlink', list_name:match ("(%w+)List"):lower() .. '-link' .. i )}); -- url or wikilink in author link; end names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) n = n + 1; -- point to next location in the names table if 1 == count then -- if the previous name was missing table.insert( z.message_tail, { set_error( 'missing_name', {err_msg_list_name, i-1}, true ) } ); -- add this error message end 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 --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- Populates ID table from arguments using configuration settings. Loops through cfg.id_handlers and searches args for any of the parameters listed in each cfg.id_handlers['...'].parameters. If found, adds the parameter and value to the identifier list. Emits redundant error message is more than one alias exists in args ]] local function extract_ids( args ) local id_list = {}; -- list of identifiers found in args for k, v in pairs( cfg.id_handlers ) do -- k is uc identifier name as index to cfg.id_handlers; e.g. cfg.id_handlers['ISBN'], v is a table v = select_one( args, v.parameters, 'redundant_parameters' ); -- v.parameters is a table of aliases for k; here we pick one from args if present if is_set(v) then id_list[k] = v; end -- if found in args, add identifier to our list end return id_list; end --[[--------------------------< B U I L D _ I D _ L I S T >-------------------------------------------------------- Takes a table of IDs created by extract_ids() and turns it into a table of formatted ID outputs. inputs: id_list – table of identifiers built by extract_ids() options – table of various template parameter values used to modify some manually handled identifiers ]] local function build_id_list( id_list, options ) local new_list, handler = {}; function fallback(k) return { __index = function(t,i) return cfg.id_handlers[k][i] end } end; 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 == 'HDL' then table.insert( new_list, {handler.label, hdl( v ) } ); 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 == 'EISSN' then table.insert( new_list, {handler.label, issn( v, true ) } ); -- true distinguishes eissn from issn 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 function comp( a, b ) -- used in following table.sort() return a[1] < b[1]; end table.sort( new_list, comp ); for k, v in ipairs( new_list ) do new_list[k] = v[2]; end return new_list; end --[[--------------------------< C O I N S _ C L E A N U P >---------------------------------------------------- Cleanup parameter values for the metadata by removing or replacing invisible characters and certain html entities. 2015-12-10: there is a bug in mw.text.unstripNoWiki (). It replaced math stripmarkers with the appropriate content when it shouldn't. See https://phabricator.wikimedia.org/T121085 and Wikipedia_talk:Lua#stripmarkers_and_mw.text.unstripNoWiki.28.29 TODO: move the replacement patterns and replacement values into a table in /Configuration similar to the invisible characters table? ]] local function coins_cleanup (value) value = mw.text.unstripNoWiki (value); -- replace nowiki stripmarkers with their content value = value:gsub ('<span class="nowrap" style="padding%-left:0%.1em;">'s</span>', "'s"); -- replace {{'s}} template with simple apostrophe-s value = value:gsub ('‍\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe value = value:gsub ('\226\128\138\039\226\128\139', "'"); -- replace {{'}} with simple apostrophe (as of 2015-12-11) value = value:gsub (' ', ' '); -- replace entity with plain space value = value:gsub ('\226\128\138', ' '); -- replace hair space with plain space value = value:gsub ('‍', ''); -- remove ‍ entities value = value:gsub ('[\226\128\141\226\128\139]', '') -- remove zero-width joiner, zero-width space value = value:gsub ('[\194\173\009\010\013]', ' '); -- replace soft hyphen, horizontal tab, line feed, carriage return with plain space return value; end --[[--------------------------< C O I N S >-------------------------------------------------------------------- COinS metadata (see <http://ocoins.info/>) allows automated tools to parse the citation information. ]] local function COinS(data, class) if 'table' ~= type(data) or nil == next(data) then return ''; end for k, v in pairs (data) do -- spin through all of the metadata parameter values if 'ID_list' ~= k and 'Authors' ~= k then -- except the ID_list and Author tables (author nowiki stripmarker done when Author table processed) data[k] = coins_cleanup (v); end end local ctx_ver = "Z39.88-2004"; -- treat table strictly as an array with only set values. local OCinSoutput = setmetatable( {}, { __newindex = function(self, key, value) if is_set(value) then rawset( self, #self+1, table.concat{ key, '=', mw.uri.encode( 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 --[[ for k, v in pairs( data.ID_list ) do -- what to do about these? For now assume that they are common to all? local id, value = cfg.id_handlers[k].COinS; if k == 'ISBN' then value = clean_isbn( v ); else value = v; end if string.sub( id or "", 1, 4 ) == 'info' then OCinSoutput["rft_id"] = table.concat{ id, "/", v }; else OCinSoutput[ id ] = value; end end ]] local last, first; for k, v in ipairs( data.Authors ) do last, first = coins_cleanup (v.last), coins_cleanup (v.first or ''); -- replace any nowiki strip markers, non-printing or invisible characers if k == 1 then -- for the first author name only if is_set(last) and is_set(first) then -- set these COinS values if |first= and |last= specify the first author name OCinSoutput["rft.aulast"] = last; -- book, journal, dissertation OCinSoutput["rft.aufirst"] = first; -- book, journal, dissertation elseif is_set(last) then OCinSoutput["rft.au"] = last; -- book, journal, dissertation -- otherwise use this form for the first name end else -- for all other authors if is_set(last) and is_set(first) then OCinSoutput["rft.au"] = table.concat{ last, ", ", first }; -- book, journal, dissertation elseif is_set(last) then OCinSoutput["rft.au"] = last; -- book, journal, dissertation end end end 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 --[[--------------------------< G E T _ I S O 6 3 9 _ C O D E >------------------------------------------------ Validates language names provided in |language= parameter if not an ISO639-1 code. Handles the special case that is Norwegian where ISO639-1 code 'no' is mapped to language name 'Norwegian Bokmål' by Extention:CLDR. Returns the language name and associated ISO639-1 code. Because case of the source may be incorrect or different from the case that Wikimedia uses, the name comparisons are done in lower case and when a match is found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we return the original language name string. mw.language.fetchLanguageNames() will return a list of languages that aren't part of ISO639-1. Names that aren't ISO639-1 but that are included in the list will be found if that name is provided in the |language= parameter. For example, if |language=Samaritan Aramaic, that name will be found with the associated code 'sam', not an ISO639-1 code. When names are found and the associated code is not two characters, this function returns only the Wikimedia language name. Adapted from code taken from Module:Check ISO 639-1. ]] 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(mw.getContentLanguage():getCode(), 'all') -- get a list of language names known to Wikimedia -- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) local langlc = mw.ustring.lower(lang); -- lower case version for comparisons for code, name in pairs(languages) do -- scan the list to see if we can find our language if langlc == mw.ustring.lower(name) then if 2 ~= code:len() then -- ISO639-1 codes only return name; -- so return the name but not the code end return name, code; -- found it, return name to ensure proper capitalization and the ISO639-1 code end end return lang; -- not valid language; return language in original case and nil for ISO639-1 code end --[[--------------------------< 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. There is an exception. There are three ISO639-1 codes for Norewegian language variants. There are two official variants: Norwegian Bokmål (code 'nb') and Norwegian Nynorsk (code 'nn'). The third, code 'no', is defined by ISO639-1 as 'Norwegian' though in Norway this is pretty much meaningless. However, it appears that on enwiki, editors are for the most part unaware of the nb and nn variants (compare page counts for these variants at Category:Articles with non-English-language external links. Because Norwegian Bokmål is the most common language variant, Media wiki has been modified to return Norwegian Bokmål for ISO639-1 code 'no'. Here we undo that and return 'Norwegian' when editors use |language=no. We presume that editors don't know about the variants or can't descriminate between them. See Help talk:Citation Style_1#An ISO 639-1 language name test When |language= contains a valid ISO639-1 code, the page is assigned to the category for that code: Category:Norwegian-language sources (no) if the page is a mainspace page and the ISO639-1 code is not 'en'. Similarly, if the parameter is |language=Norwegian, it will be categorized in the same way. This function supports multiple languages in the form |language=nb, French, th where the language names or codes are separated from each other by commas. ]] local function language_parameter (lang) local code; -- the ISO639-1 two character code local name; -- the language name local language_list = {}; -- table of language names to be rendered local names_table = {}; -- table made from the value assigned to |language= names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list for _, lang in ipairs (names_table) do -- reuse lang if lang:match ('^%a%a%-') or 2 == lang:len() then -- ISO639-1 language code are 2 characters (fetchLanguageName also supports 3 character codes) if lang:match ('^zh-') then name = mw.language.fetchLanguageName( lang:lower(), lang:lower() ); else name = mw.language.fetchLanguageName( lang:lower(), mw.getContentLanguage():getCode() ); -- get ISO 639-1 language name if Language is a proper code end end if is_set (name) then -- if Language specified a valid ISO639-1 code code = lang:lower(); -- save it else name, code = get_iso639_code (lang); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) end if is_set (code) then if 'no' == code then name = '挪威语' end; -- override wikimedia when code is 'no' if 'zh' ~= code and not code:match ('^zh-') then -- English not the language add_prop_cat ('foreign_lang_source', {name, code}) end else add_maint_cat ('unknown_lang'); -- add maint category if not already added end table.insert (language_list, name); name = ''; -- so we can reuse it end code = #language_list -- reuse code as number of languages in the list if 2 >= code then name = table.concat (language_list, '及') -- insert '及' between two language names elseif 2 < code then language_list[code] = '及' .. language_list[code]; -- prepend last name with '及' name = table.concat (language_list, '、'); -- and concatenate with '<comma><space>' separators name = name:gsub ('、及', '及', 1); end return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' end --[[--------------------------< S E T _ C S 1 _ S T Y L E >---------------------------------------------------- Set style settings for CS1 citation templates. Returns separator and postscript settings ]] local function set_cs1_style (ps) if not is_set (ps) then -- unless explicitely set to something ps = '.'; -- terminate the rendered citation with a period end return '.', ps; -- separator is a full stop end --[[--------------------------< S E T _ C S 2 _ S T Y L E >---------------------------------------------------- Set style settings for CS2 citation templates. Returns separator, postscript, ref settings ]] local function set_cs2_style (ps, ref) if not is_set (ps) then -- if |postscript= has not been set, set cs2 default ps = ''; -- make sure it isn't nil end if not is_set (ref) then -- if |ref= is not set ref = "harv"; -- set default |ref=harv end return ',', ps, ref; -- separator is a comma end --[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish rendered style. ]] local function get_settings_from_cite_class (ps, ref, cite_class) local sep; if (cite_class == "citation") then -- for citation templates (CS2) sep, ps, ref = set_cs2_style (ps, ref); else -- not a citation template so CS1 sep, ps = set_cs1_style (ps); end return sep, ps, ref -- return them all 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 config.CitationClass from the template's #invoke: to establish style. ]] local function set_style (mode, ps, ref, cite_class) local sep; if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style sep, ps, ref = set_cs2_style (ps, ref); elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style sep, ps = set_cs1_style (ps); else -- anything but cs1 or cs2 sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass end if 'none' == ps:lower() then -- if assigned value is 'none' then ps = ''; -- set to empty string end return sep, ps, ref end --[=[-------------------------< I S _ P D F >------------------------------------------------------------------ Determines if a url has the file extension that is one of the pdf file extensions used by [[MediaWiki:Common.css]] when applying the pdf icon to external links. returns true if file extension is one of the recognized extension, else false ]=] local function is_pdf (url) return url:match ('%.pdf[%?#]?') or url:match ('%.PDF[%?#]?'); end --[[--------------------------< S T Y L E _ F O R M A T >------------------------------------------------------ Applies css style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does not have a matching url parameter. If the format parameter is not set and the url contains a file extension that is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with the appropriate styling. ]] local function style_format (format, url, fmt_param, url_param) if 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) if is_set (max) then if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings max = count + 1; -- number of authors + 1 so display all author name plus et al. etal = true; -- overrides value set by extract_names() elseif max:match ('^%d+$') then -- if is a string of numbers max = tonumber (max); -- make it a number if max >= count and 'authors' == list_name then -- AUTHORS ONLY -- if |display-xxxxors= value greater than or equal to number of authors/editors add_maint_cat ('disp_auth_ed', list_name); end else -- not a valid keyword or number table.insert( z.message_tail, { set_error( 'invalid_param_val', {'display-' .. list_name, max}, true ) } ); -- add error message max = nil; -- unset end elseif 'authors' == list_name then -- AUTHORS ONLY need to clear implicit et al category max = count + 1; -- number of authors + 1 end return max, etal; end --[[--------------------------< 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. abbreviation in the first characters of the parameter content. check Page and Pages for extraneous p, p., pp, and pp. at start of parameter value: good pattern: '^P[^%.P%l]' matches when |page(s)= begins PX or P# but not Px where x and X are letters and # is a dgiit bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP ]] local function extra_text_in_page_check (page) -- local good_pattern = '^P[^%.P%l]'; 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? -- 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 add_maint_cat ('extra_text'); end -- 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 --[[--------------------------< P A R S E _ V A U T H O R S _ V E D I T O R S >-------------------------------- This function extracts author / editor names from |vauthors= or |veditors= and finds matching |xxxxor-maskn= and |xxxxor-linkn= in args. It then returns a table of assembled names just as extract_names() does. Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names may sometimes be required and because such names will often fail the is_good_vanc_name() and other format compliance tests, are wrapped in doubled paranethese ((corporate name)) to suppress the format tests. This function sets the vancouver error when a reqired comma is missing and when there is a space between an author's initials. ]] local function parse_vauthors_veditors (args, vparam, list_name) local names = {}; -- table of names assembled from |vauthors=, |author-maskn=, |author-linkn= local v_name_table = {}; local 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 if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parenthese to supress vanc formatting and error detection first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor last = v_name:match ('^%(%((.+)%)%)$') corporate = true; elseif string.find(v_name, "%s") then lastfirstTable = {} lastfirstTable = mw.text.split(v_name, "%s") first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be author intials last = table.concat(lastfirstTable, " ") -- returns a string that is the concatenation of all other names that are not initials if mw.ustring.match (last, '%a+%s+%u+%s+%a+') or mw.ustring.match (v_name, ' %u %u$') then add_vanc_error (); -- matches last II last; the case when a comma is missing or a space between two intiials end else first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? end if is_set (first) and not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else add_vanc_error (); end -- this from extract_names () link = select_one( args, cfg.aliases[list_name .. '-Link'], 'redundant_parameters', i ); mask = select_one( args, cfg.aliases[list_name .. '-Mask'], 'redundant_parameters', i ); names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list end return names, etal; -- all done, return our list of names end --[[--------------------------< 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. Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest and similarly, |editorn= (and aliases) highest and |editors= lowest When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second test which mimicks the test used in extract_names() when looking for a hole in the author name list. There may be a better way to do this, I just haven't discovered what that way is. Emits an error message when more than one xxxxor name source is provided. In this function, vxxxxors = vauthors or veditors; xxxxors = authors or editors as appropriate. ]] local function select_author_editor_source (vxxxxors, xxxxors, args, list_name) local lastfirst = false; if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice incase we have a first 1 without a last1 select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) then lastfirst=true; end if (is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions (is_set (vxxxxors) and is_set (xxxxors)) or (true == lastfirst and is_set (xxxxors)) then local err_name; if 'AuthorList' == list_name then -- figure out which name should be used in error message err_name = 'author'; else err_name = 'editor'; end table.insert( z.message_tail, { set_error( 'redundant_parameters', {err_name .. '-name-list parameters'}, true ) } ); -- add error message end if true == lastfirst then return 1 end; -- return a number indicating which author name source to use if is_set (vxxxxors) then return 2 end; if is_set (xxxxors) then return 3 end; return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last end --[[--------------------------< 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 refurns 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 is_valid_parameter_value (value, name, possible) if not is_set (value) then 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 --[[--------------------------< T E R M I N A T E _ N A M E _ L I S T >---------------------------------------- This function terminates a name list (author, contributor, editor) with a separator character (sepc) and a space when the last character is not a sepc character or when the last three characters are not sepc followed by two closing square brackets (close of a wikilink). When either of these is true, the name_list is terminated with a single space character. ]] local function terminate_name_list (name_list, sepc) if (string.sub (name_list,-1,-1) == sepc) or (string.sub (name_list,-3,-1) == sepc .. ']]') then -- if last name in list ends with sepc char return name_list .. " "; -- don't add another else return name_list .. sepc .. ' '; -- otherwise terninate the name list end end --[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- returns the concatenation of the formatted volume and issue parameters as a single string; or formatted volume or formatted issue, or an empty string if neither are set. ]] local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) 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 (6 < 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 if is_set (issue) then return vol .. substitute (cfg.messages['j-issue'], issue); end return vol; end --[[-------------------------< F O R M A T _ P A G E S _ S H E E T S >----------------------------------------- adds static text to one of |page(s)= or |sheet(s)= values and returns it with all of the others set to empty strings. The return order is: page, pages, sheet, sheets Singular has priority over plural when both are provided. ]] local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) if 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators if is_set (sheet) then 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 local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) 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 return '', '', '', ''; -- return empty strings end --[[--------------------------< C I T A T I O N 0 >------------------------------------------------------------ This is the main function doing the majority of the citation formatting. ]] local function citation0( config, args) --[[ Load Input Parameters The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. ]] local A = argument_wrapper( args ); local i -- Pick out the relevant fields from the arguments. Different citation templates -- define different field names for the same underlying things. local author_etal; local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= local Authors; local NameListFormat = A['NameListFormat']; do -- to limit scope of selected local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList'); if 1 == selected then a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= elseif 2 == selected then NameListFormat = 'vanc'; -- override whatever |name-list-format= might be a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= elseif 3 == selected then Authors = A['Authors']; -- use content of |authors= end end local Coauthors = A['Coauthors']; local Others = A['Others']; 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= end end local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs local Translators; -- assembled translators name list t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs local Contributors; -- assembled contributors name list local Contribution = A['Contribution']; if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= if 0 < #c then if not is_set (Contribution) then -- |contributor= requires |contribution= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'contribution')}); -- add missing contribution error message c = {}; -- blank the contributors' table; it is used as a flag later end if 0 == #a then -- |contributor= requires |author= table.insert( z.message_tail, { set_error( 'contributor_missing_required_param', 'author')}); -- add missing author error message c = {}; -- blank the contributors' table; it is used as a flag later end end else -- if not a book cite if select_one (args, cfg.aliases['ContributorList-Last'], 'redundant_parameters', 1 ) then -- are there contributor name list parameters? table.insert( z.message_tail, { set_error( 'contributor_ignored')}); -- add contributor ignored error message end Contribution = nil; -- unset end if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc' NameListFormat = ''; -- anything else, set to empty string end local Year = A['Year']; local PublicationDate = A['PublicationDate']; local OrigYear = A['OrigYear']; local Date = A['Date']; local LayDate = A['LayDate']; ------------------------------------------------- Get title data local Title = A['Title']; local ScriptTitle = A['ScriptTitle']; local BookTitle = A['BookTitle']; local Conference = A['Conference']; local TransTitle = A['TransTitle']; local TitleNote = A['TitleNote']; local TitleLink = A['TitleLink']; if is_set (TitleLink) and false == link_param_ok (TitleLink) then table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('TitleLink'))}); -- url or wikilink in |title-link=; end local Chapter = A['Chapter']; local ScriptChapter = A['ScriptChapter']; local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode local TransChapter = A['TransChapter']; local TitleType = A['TitleType']; local Degree = A['Degree']; local Docket = A['Docket']; local ArchiveFormat = A['ArchiveFormat']; local ArchiveURL = A['ArchiveURL']; local URL = A['URL'] local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL local ChapterURL = A['ChapterURL']; local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL local ConferenceFormat = A['ConferenceFormat']; local ConferenceURL = A['ConferenceURL']; local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL local Periodical = A['Periodical']; local Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter local Series = A['Series']; local Volume; local Issue; local Page; local Pages; local At; if in_array (config.CitationClass, cfg.templates_using_volume) and not ('conference' == config.CitationClass and not is_set (Periodical)) then Volume = A['Volume']; end if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then Issue = A['Issue']; end local Position = ''; if not in_array (config.CitationClass, cfg.templates_not_using_page) then Page = A['Page']; Pages = hyphen_to_dash( A['Pages'] ); At = A['At']; end local Edition = A['Edition']; local PublicationPlace = A['PublicationPlace'] local Place = A['Place']; local PublisherName = A['PublisherName']; local RegistrationRequired = A['RegistrationRequired']; if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then RegistrationRequired=nil; end local SubscriptionRequired = A['SubscriptionRequired']; if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then SubscriptionRequired=nil; end local Via = A['Via']; local AccessDate = A['AccessDate']; local ArchiveDate = A['ArchiveDate']; local Agency = A['Agency']; local DeadURL = A['DeadURL'] if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' DeadURL = ''; -- anything else, set to empty string end local Language = A['Language']; local Format = A['Format']; local ChapterFormat = A['ChapterFormat']; local DoiBroken = A['DoiBroken']; local ID = A['ID']; local ASINTLD = A['ASINTLD']; local IgnoreISBN = A['IgnoreISBN']; if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then IgnoreISBN = nil; -- anything else, set to empty string end local Embargo = A['Embargo']; local Class = A['Class']; -- arxiv class identifier local ID_list = extract_ids( args ); local Quote = A['Quote']; local LayFormat = A['LayFormat']; local LayURL = A['LayURL']; local LaySource = A['LaySource']; local Transcript = A['Transcript']; local TranscriptFormat = A['TranscriptFormat']; local TranscriptURL = A['TranscriptURL'] local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL local LastAuthorAmp = A['LastAuthorAmp']; if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then LastAuthorAmp = nil; -- set to empty string end local no_tracking_cats = A['NoTracking']; if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then no_tracking_cats = nil; -- set to empty string end --these are used by cite interview local Callsign = A['Callsign']; local City = A['City']; local Program = A['Program']; --local variables that are not cs1 parameters local use_lowercase; -- controls capitalization of certain static text local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language local anchor_year; -- used in the CITEREF identifier local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification -- set default parameter values defined by |mode= parameter. If |mode= is empty or omitted, use CitationClass to set these values local Mode = A['Mode']; if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then Mode = ''; end local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma local PostScript; local Ref; sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass); use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text --check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories if not is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page if in_array (this_page.nsText, cfg.uncategorized_namespaces) then no_tracking_cats = "true"; -- set no_tracking_cats end for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns if this_page.text:match (v) then -- test page name against each pattern no_tracking_cats = "true"; -- set no_tracking_cats break; -- bail out if one is found end end end -- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category local NoPP = A['NoPP'] if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then NoPP = true; else NoPP = nil; -- unset, used as a flag later end if is_set(Page) then if is_set(Pages) or is_set(At) then Pages = ''; -- unset the others At = ''; end extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp. elseif is_set(Pages) then if is_set(At) then At = ''; -- unset end extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. end -- both |publication-place= and |place= (|location=) allowed if different if not is_set(PublicationPlace) and is_set(Place) then PublicationPlace = Place; -- promote |place= (|location=) to |publication-place end if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same --[[ Parameter remapping for cite encyclopedia: 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 ]] local Encyclopedia = A['Encyclopedia']; if ( config.CitationClass == "encyclopaedia" ) or ( config.CitationClass == "citation" and is_set (Encyclopedia)) then -- test code for citation if is_set(Periodical) then -- Periodical is set when |encyclopedia is set if is_set(Title) or is_set (ScriptTitle) then if not is_set(Chapter) then Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title 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 -- Special case for cite techreport. if (config.CitationClass == "techreport") then -- special case for cite techreport if is_set(A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' if not is_set(ID) then -- can we use ID for the "number"? ID = A['Number']; -- yes, use it else -- ID has a value so emit error message table.insert( z.message_tail, { set_error('redundant_parameters', {wrap_style ('parameter', 'id') .. ' and ' .. wrap_style ('parameter', 'number')}, true )}); end end end -- special case for cite interview if (config.CitationClass == "interview") then if is_set(Program) then ID = ' ' .. Program; end if is_set(Callsign) then if is_set(ID) then ID = ID .. sepc .. ' ' .. Callsign; else ID = ' ' .. Callsign; end end if is_set(City) then if is_set(ID) then ID = ID .. sepc .. ' ' .. City; else ID = ' ' .. City; end end if is_set(Others) then if is_set(TitleType) then Others = ' ' .. TitleType .. ' with ' .. Others; TitleType = ''; else Others = ' ' .. 'Interview with ' .. Others; end else Others = '(Interview)'; end end -- special case for cite mailing list if (config.CitationClass == "mailinglist") then Periodical = A ['MailingList']; elseif 'mailinglist' == A:ORIGIN('Periodical') then Periodical = ''; -- unset because mailing list is only used for cite mailing list end -- Account for the oddity that is {{cite conference}}, before generation of COinS data. if 'conference' == config.CitationClass then if is_set(BookTitle) then Chapter = Title; -- ChapterLink = TitleLink; -- |chapterlink= is deprecated ChapterURL = URL; ChapterURLorigin = URLorigin; URLorigin = ''; ChapterFormat = Format; TransChapter = TransTitle; Title = BookTitle; Format = ''; -- TitleLink = ''; TransTitle = ''; URL = ''; end elseif 'speech' ~= config.CitationClass then Conference = ''; -- not cite conference or cite speech so make sure this is empty string end -- cite map oddities local Cartography = ""; local Scale = ""; local Sheet = A['Sheet'] or ''; local Sheets = A['Sheets'] or ''; if config.CitationClass == "map" then Chapter = A['Map']; ChapterURL = A['MapURL']; TransChapter = A['TransMap']; ChapterURLorigin = A:ORIGIN('MapURL'); ChapterFormat = A['MapFormat']; Cartography = A['Cartography']; if is_set( Cartography ) then Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); end Scale = A['Scale']; if is_set( Scale ) then Scale = sepc .. " " .. Scale; end end -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. if 'episode' == config.CitationClass or 'serial' == config.CitationClass then local AirDate = A['AirDate']; local SeriesLink = A['SeriesLink']; if is_set (SeriesLink) and false == link_param_ok (SeriesLink) then table.insert( z.message_tail, { set_error( 'bad_paramlink', A:ORIGIN('SeriesLink'))}); end local Network = A['Network']; local Station = A['Station']; local s, n = {}, {}; -- do common parameters first if is_set(Network) then table.insert(n, Network); end if is_set(Station) then table.insert(n, Station); end ID = table.concat(n, sepc .. ' '); if not is_set (Date) and is_set (AirDate) then -- promote airdate to date Date = AirDate; end if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} local Season = A['Season']; local SeriesNumber = A['SeriesNumber']; if is_set (Season) and is_set (SeriesNumber) then -- these are mutually exclusive so if both are set table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'season') .. ' and ' .. wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message SeriesNumber = ''; -- unset; prefer |season= over |seriesno= end -- assemble a table of parts concatenated later into Series if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end if is_set(SeriesNumber) then table.insert(s, wrap_msg ('series', SeriesNumber, use_lowercase)); end if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end Issue = ''; -- unset because this is not a unique parameter Chapter = Title; -- promote title parameters to chapter ScriptChapter = ScriptTitle; ChapterLink = TitleLink; -- alias episodelink TransChapter = TransTitle; ChapterURL = URL; ChapterURLorigin = A:ORIGIN('URL'); Title = Series; -- promote series to title TitleLink = SeriesLink; Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number if is_set (ChapterLink) and not is_set (ChapterURL) then -- link but not URL Chapter = '[[' .. ChapterLink .. '|' .. Chapter .. ']]'; -- ok to wikilink elseif is_set (ChapterLink) and is_set (ChapterURL) then -- if both are set, URL links episode; Series = '[[' .. ChapterLink .. '|' .. Series .. ']]'; -- series links with ChapterLink (episodelink -> TitleLink -> ChapterLink) ugly end URL = ''; -- unset TransTitle = ''; ScriptTitle = ''; 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 of {{cite episode}} stuff -- Account for the oddities that are {{cite arxiv}}, before generation of COinS data. if 'arxiv' == config.CitationClass then if not is_set (ID_list['ARXIV']) then -- |arxiv= or |eprint= required for cite arxiv table.insert( z.message_tail, { set_error( 'arxiv_missing', {}, true ) } ); -- add error message elseif is_set (Series) then -- series is an alias of version ID_list['ARXIV'] = ID_list['ARXIV'] .. Series; -- concatenate version onto the end of the arxiv identifier Series = ''; -- unset 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 PublisherName = ''; -- (if the article has been published, use cite journal, or other) Chapter = ''; URL = ''; Format = ''; Page = ''; Pages = ''; At = ''; end Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string end -- handle type parameter for those CS1 citations that have default values if in_array(config.CitationClass, {"AV-media-notes", "DVD-notes", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then TitleType = set_titletype (config.CitationClass, TitleType); if is_set(Degree) and "Thesis" == TitleType then -- special case for cite thesis TitleType = Degree .. "论文"; end end if is_set(TitleType) then -- if type parameter is specified TitleType = substitute( cfg.messages['type'], TitleType); -- display it in parentheses 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 not is_set (Date) then Date = Year; -- promote Year to Date Year = nil; -- make nil so Year as empty string isn't used for CITEREF if not 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 end end if PublicationDate == Date then PublicationDate = ''; end -- if PublicationDate is same as Date, don't display in rendered citation --[[ Go test all of the date-holding parameters for valid MOS:DATE format and make sure that dates are real dates. This must be done before we do COinS because here is where we get the date used in the metadata. Date validation supporting code is in Module:Citation/CS1/Date_validation ]] do -- create defined block to contain local variables error_message and mismatch local error_message = ''; -- AirDate has been promoted to Date so not necessary to check it anchor_year, error_message = dates({['access-date']=AccessDate, ['archive-date']=ArchiveDate, ['date']=Date, ['doi-broken-date']=DoiBroken, ['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}, COinS_date); if is_set (Year) and is_set (Date) then -- both |date= and |year= not normally needed; local mismatch = year_date_check (Year, Date) if 0 == mismatch then -- |year= does not match a year-value in |date= if is_set (error_message) then -- if there is already an error message error_message = error_message .. ', '; -- tack on this additional message end error_message = error_message .. '|year= / |date= mismatch'; elseif 1 == mismatch then -- |year= matches year-value in |date= add_maint_cat ('date_year'); end end 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 -- At this point fields may be nil if they weren't specified in the template use. We can use that fact. -- Test if citation has no title if not is_set(Title) and not is_set(TransTitle) and not is_set(ScriptTitle) then if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); else table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); end end if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites Title = ''; -- set title to empty string add_maint_cat ('untitled'); end check_for_url ({ -- add error message when any of these parameters contains a URL ['title']=Title, [A:ORIGIN('Chapter')]=Chapter, [A:ORIGIN('Periodical')]=Periodical, [A:ORIGIN('PublisherName')] = PublisherName, }); -- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. -- handle the oddity that is cite encyclopedia and {{citation |encyclopedia=something}}. Here we presume that -- when Periodical, Title, and Chapter are all set, then Periodical is the book (encyclopedia) title, Title -- is the article title, and Chapter is a section within the article. So, we remap local coins_chapter = Chapter; -- default assuming that remapping not required local coins_title = Title; -- et tu if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used then coins_chapter = Title; -- remap coins_title = Periodical; end end local coins_author = a; -- default for coins rft.au if 0 < #c then -- but if contributor list coins_author = c; -- use that instead end -- this is the function call to COinS() local OCinSoutput = COinS({ ['Periodical'] = Periodical, ['Encyclopedia'] = Encyclopedia, ['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wikimarkup ['Map'] = Map, ['Degree'] = Degree; -- cite thesis only ['Title'] = make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wikimarkup ['PublicationPlace'] = PublicationPlace, ['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; ['Season'] = COinS_date.rftssn, ['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit? ['Series'] = Series, ['Volume'] = Volume, ['Issue'] = Issue, ['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links ['Edition'] = Edition, ['PublisherName'] = PublisherName, ['URL'] = first_set ({ChapterURL, URL}, 2), ['Authors'] = coins_author, ['ID_list'] = ID_list, ['RawPage'] = this_page.prefixedText, }, config.CitationClass); -- Account for the oddities that are {{cite arxiv}}, AFTER generation of COinS data. if 'arxiv' == config.CitationClass then -- we have set rft.jtitle in COinS to arXiv, now unset so it isn't displayed Periodical = ''; -- periodical not allowed in cite arxiv; if article has been published, use cite journal end -- 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') )); end end -- Now perform various field substitutions. -- 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. 临时修复"Category:含有旧式缩略标签的引用的页面 in editors"的问题,中文版目前与英文版逻辑不一样,暂时不需要这个分类。等以后更新时再看怎么处理 --2017.6.23 shizhao 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 if editor_etal then Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation else EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation end else Editors = last_first_list; -- either an author name list or an empty string end if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then EditorCount = 2; -- spoof to display (eds.) annotation end end do -- now do translators control.maximum = #t; -- number of translators Translators = list_people(control, t, false, 'translator'); -- et al not currently supported end do -- now do contributors control.maximum = #c; -- number of contributors Contributors = list_people(control, c, false, 'contributor'); -- et al not currently supported end do -- now do authors control.maximum , author_etal = get_display_authors_editors (A['DisplayAuthors'], #a, 'authors', author_etal); if is_set(Coauthors) then -- if the coauthor field is also used, prevent ampersand and et al. formatting. control.lastauthoramp = nil; control.maximum = #a + 1; end last_first_list = list_people(control, a, author_etal, 'author'); if is_set (Authors) then Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. if author_etal then Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter end else Authors = last_first_list; -- either an author name list or an empty string end end -- end of do if not is_set(Authors) and is_set(Coauthors) then -- coauthors aren't displayed if one of authors=, authorn=, or lastn= isn't specified table.insert( z.message_tail, { set_error('coauthors_missing_author', {}, true) } ); -- emit error message end end -- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation, -- 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 not (in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); end if not is_set(URL) then --and if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) then -- Test if cite web or cite podcast |url= is missing or empty table.insert( z.message_tail, { set_error( 'cite_web_url', {}, true ) } ); end -- Test if accessdate is given without giving a URL if is_set(AccessDate) and not is_set(ChapterURL)then -- ChapterURL may be set when the others are not set; TODO: move this to a separate test? table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); AccessDate = ''; end end local OriginalURL, OriginalURLorigin, OriginalFormat; -- TODO: swap chapter and title here so that archive applies to most specific if both are set? DeadURL = DeadURL:lower(); -- used later when assembling archived text if is_set( ArchiveURL ) then if 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= 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 end if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'arxiv'}) or -- if any of the 'periodical' cites except encyclopedia ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) then local chap_param; if is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters chap_param = A:ORIGIN ('Chapter') elseif is_set (TransChapter) then chap_param = A:ORIGIN ('TransChapter') elseif is_set (ChapterURL) then chap_param = A:ORIGIN ('ChapterURL') elseif is_set (ScriptChapter) then chap_param = A:ORIGIN ('ScriptChapter') else is_set (ChapterFormat) chap_param = A:ORIGIN ('ChapterFormat') end if is_set (chap_param) then -- if we found one table.insert( z.message_tail, { set_error( 'chapter_ignored', {chap_param}, true ) } ); -- add error message Chapter = ''; -- and set them to empty string to be safe with concatenation TransChapter = ''; ChapterURL = ''; ScriptChapter = ''; ChapterFormat = ''; end else -- otherwise, format chapter / article title local no_quotes = false; -- default assume that we will be quoting the chapter parameter value if is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) if in_array (Contribution:lower(), cfg.keywords.contribution) then -- and a generic contribution title no_quotes = true; -- then render it unquoted end end Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, ChapterURLorigin, no_quotes); -- Contribution is also in Chapter if is_set (Chapter) then if 'map' == config.CitationClass and is_set (TitleType) then Chapter = Chapter .. ' ' .. TitleType; end Chapter = Chapter .. ChapterFormat .. sepc .. ' '; elseif is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it end end -- Format main title. if is_set(TitleLink) and is_set(Title) then Title = "[[" .. TitleLink .. "|" .. Title .. "]]" end if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease','podcast', 'newsgroup', 'mailinglist', 'arxiv'}) or ('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia)) or ('map' == config.CitationClass and is_set (Periodical)) then -- special case for cite map when the map is in a periodical treat as an article Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from Module provided quote marks Title = wrap_style ('quoted-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); elseif 'report' == config.CitationClass then -- no styling for cite report Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle= wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title else Title = wrap_style ('italic-title', Title); Title = script_concatenate (Title, ScriptTitle); -- <bdi> tags, lang atribute, categorization, etc; must be done after title is wrapped TransTitle = wrap_style ('trans-italic-title', TransTitle); end TransError = ""; if is_set(TransTitle) then if is_set(Title) then TransTitle = " " .. TransTitle; else TransError = " " .. set_error( 'trans_missing_title', {'title'} ); end end Title = Title .. TransTitle; if is_set(Title) then if not is_set(TitleLink) and is_set(URL) then Title = external_link( URL, Title, URLorigin ) .. TransError .. Format; URL = ""; Format = ""; else Title = Title .. TransError; end end if is_set(Place) then Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; end if is_set (Conference) then if is_set (ConferenceURL) then Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin ); end Conference = sepc .. " " .. Conference .. ConferenceFormat; elseif is_set(ConferenceURL) then Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURLorigin ); end if not is_set(Position) then local Minutes = A['Minutes']; local Time = A['Time']; if is_set(Minutes) then if is_set (Time) then table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'minutes') .. ' and ' .. wrap_style ('parameter', 'time')}, true ) } ); end Position = " " .. Minutes .. " " .. cfg.messages['minutes']; else if is_set(Time) then local TimeCaption = A['TimeCaption'] if not is_set(TimeCaption) then TimeCaption = cfg.messages['event']; if sepc ~= '.' then TimeCaption = TimeCaption:lower(); end end Position = " " .. TimeCaption .. " " .. Time; end end else Position = " " .. Position; At = ''; end Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); At = is_set(At) and (sepc .. " " .. At) or ""; Position = is_set(Position) and (sepc .. " " .. Position) or ""; if config.CitationClass == 'map' then local Section = A['Section']; local Sections = A['Sections']; local Inset = A['Inset']; if is_set( Inset ) then Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); end if 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 At = At .. Inset .. Section; end if is_set (Language) then Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc else Language=""; -- language not specified so make sure this is an empty string; end Others = is_set(Others) and (sepc .. " " .. Others) or ""; if is_set (Translators) then Others = sepc .. ' 由' .. Translators .. '翻译 ' .. Others; 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 ""; Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); ------------------------------------ totally unrelated data if is_set(Via) then Via = " " .. wrap_msg ('via', Via); end --[[ Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link note is displayed. There are no error messages for this condition. ]] 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 local retrv_text = " " .. cfg.messages['retrieved'] AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if 'citation', lower case AccessDate = substitute (retrv_text, AccessDate); -- add retrieved text -- neither of these work; don't know why; it seems that substitute() isn't being called AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates end if is_set(ID) then ID = sepc .." ".. ID; end if "thesis" == config.CitationClass and is_set(Docket) then 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 ID_list = build_id_list( ID_list, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); if is_set(URL) then URL = " " .. external_link( URL, nil, URLorigin ); end if is_set(Quote) then if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks Quote = Quote:sub(2,-2); -- strip them off end Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set end local Archived if is_set(ArchiveURL) then if not is_set(ArchiveDate) then ArchiveDate = set_error('archive_missing_date'); end if "no" == DeadURL then local arch_text = cfg.messages['archived']; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], { external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL') ) .. ArchiveFormat, ArchiveDate } ); if not is_set(OriginalURL) then Archived = Archived .. " " .. set_error('archive_missing_url'); end elseif is_set(OriginalURL) then -- DeadURL is empty, 'yes', 'true', 'y', 'unfit', 'usurped' local arch_text = cfg.messages['archived-dead']; if sepc ~= "." then arch_text = arch_text:lower() end if in_array (DeadURL, {'unfit', 'usurped'}) then Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled else -- DeadURL is empty, 'yes', 'true', or 'y' Archived = sepc .. " " .. substitute( arch_text, { external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin ) .. OriginalFormat, ArchiveDate } ); -- format already styled end else local arch_text = cfg.messages['archived-missing']; if sepc ~= "." then arch_text = arch_text:lower() end Archived = sepc .. " " .. substitute( arch_text, { set_error('archive_missing_url'), ArchiveDate } ); end elseif is_set (ArchiveFormat) then Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message else Archived = "" end local Lay = ''; if is_set(LayURL) then if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end if is_set(LaySource) then LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; else LaySource = ""; end if sepc == '.' then Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate else Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL') ) .. LayFormat .. LaySource .. LayDate end elseif is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message end if is_set(Transcript) then if is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, Transcript, TranscriptURLorigin ); end Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; elseif is_set(TranscriptURL) then Transcript = external_link( TranscriptURL, nil, TranscriptURLorigin ); end local Publisher; if is_set(Periodical) and not in_array(config.CitationClass, {"encyclopaedia","web","pressrelease","podcast"}) then if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = PublicationPlace .. ": " .. PublisherName; else Publisher = PublisherName; end elseif is_set(PublicationPlace) then Publisher= PublicationPlace; else Publisher = ""; end if is_set(Publisher) then Publisher = " (" .. Publisher .. ")"; end else if is_set(PublisherName) then if is_set(PublicationPlace) then Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName; else Publisher = sepc .. " " .. PublisherName; end elseif is_set(PublicationPlace) then Publisher= sepc .. " " .. PublicationPlace; else Publisher = ''; end end -- Several of the above rely upon detecting this as nil, so do it last. if is_set(Periodical) then if is_set(Title) or is_set(TitleNote) then Periodical = sepc .. " " .. wrap_style ('italic-title', Periodical) else Periodical = wrap_style ('italic-title', Periodical) end end --[[ Handle the oddity that is cite speech. This code overrides whatever may be the value assigned to TitleNote (through |department=) and forces it to be " (Speech)" so that the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). ]] if "speech" == config.CitationClass then -- cite speech only 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. -- 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 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, Edition, Publisher, Agency}, 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, Volume, Others, Edition, Publisher, Agency}, sepc ); else tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, 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, Cartography, Others, Publisher, Volume}, sepc ); elseif is_set (Periodical) then -- map in a periodical tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Cartography, Others, Publisher, Volume}, sepc ); else -- a sheet or stand-alone map tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Cartography, Others, Publisher}, sepc ); end elseif 'episode' == config.CitationClass then -- special case for cite episode tcommon = safe_join( {Title, TitleNote, TitleType, Series, Transcript, Edition, Publisher}, sepc ); else -- all other CS1 templates tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, 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 local xDate = Date local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; if ( is_set(Periodical) and Date ~= '' and not in_array(config.CitationClass, {"encyclopaedia","web"}) ) or ( in_array(config.CitationClass, {"book","news"}) ) then if in_array(config.CitationClass, {"journal","citation"}) and ( Volume ~= '' or Issue ~= '' ) then xDate = xDate .. ',' .. Volume end xDate = xDate .. pgtext pgtext = '' end if PublicationDate and PublicationDate ~= '' then xDate = xDate .. ' (' .. PublicationDate .. ')' end if OrigYear ~= '' then xDate = xDate .. OrigYear end if AccessDate ~= '' then xDate = xDate .. ' ' .. AccessDate end if xDate ~= '' then xDate = sepc .. ' ' .. xDate end -- END LOCAL local idcommon = safe_join( { URL, xDate, ID_list, Archived, Via, SubscriptionRequired, Lay, Language, Quote }, sepc ); local text; 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 Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space 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 Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space text = safe_join( {Contributors, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); else text = safe_join( {Authors, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); end elseif is_set(Editors) then if EditorCount <= 1 then Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " else Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " end text = safe_join( {Editors, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); else if config.CitationClass=="journal" and is_set(Periodical) then text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); else text = safe_join( {Chapter, Place, tcommon, pgtext, idcommon}, sepc ); end end if is_set(PostScript) and PostScript ~= sepc then text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc. text = text:sub(1,-sepc:len()-1); end text = safe_join( {text, PostScript}, sepc ); -- Now enclose the whole thing in a <cite/> element local options = {}; if is_set(config.CitationClass) and config.CitationClass ~= "citation" then options.class = config.CitationClass; options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref= else options.class = "citation"; end if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate local id = Ref if ('harv' == Ref ) then local namelist = {}; -- holds selected contributor, author, editor name list -- local year = first_set (Year, anchor_year); -- Year first for legacy citations and for YMD dates that require disambiguation local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation if #c > 0 then -- if there is a contributor list namelist = c; -- select it elseif #a > 0 then -- or an author list namelist = a; elseif #e > 0 then -- or an editor list namelist = e; end id = anchor_id (namelist, year); -- go make the CITEREF anchor end options.id = id; end if string.len(text:gsub("<span[^>/]*>.-</span>", ""):gsub("%b<>","")) <= 2 then z.error_categories = {}; text = set_error('empty_citation'); z.message_tail = {}; end if is_set(options.id) then text = '<cite id="' .. mw.uri.anchorEncode(options.id) ..'" class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; else text = '<cite class="' .. mw.text.nowiki(options.class) .. '">' .. text .. "</cite>"; end local empty_span = '<span style="display:none;"> </span>'; -- Note: Using display: none on the COinS span breaks some clients. local OCinS = '<span title="' .. OCinSoutput .. '" class="Z3988">' .. empty_span .. '</span>'; text = text .. OCinS; if #z.message_tail ~= 0 then text = text .. " "; for i,v in ipairs( z.message_tail ) do if is_set(v[1]) then if i == #z.message_tail then text = text .. error_comment( v[1], v[2] ); else text = text .. error_comment( v[1] .. "; ", v[2] ); end end end end if #z.maintenance_cats ~= 0 then text = text .. '<span class="citation-comment" style="display:none; color:#33aa33">'; for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories text = text .. ' ' .. v .. ' ([[:Category:' .. v ..'|link]])'; end text = text .. '</span>'; -- maintenance mesages (realy just the names of the categories for now) end no_tracking_cats = no_tracking_cats:lower(); if in_array(no_tracking_cats, {"", "no", "false", "n"}) then for _, v in ipairs( z.error_categories ) do text = text .. '[[Category:' .. v ..']]'; end for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories text = text .. '[[Category:' .. v ..']]'; end for _, v in ipairs( z.properties_cats ) do -- append maintenance categories text = text .. '[[Category:' .. v ..']]'; end end return text end --[[--------------------------< 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 = ""; if type( k ) ~= 'string' then -- Exclude empty numbered parameters if v:match("%S+") ~= nil then error_text, error_state = set_error( 'text_ignored', {v}, true ); end elseif validate( k:lower() ) then error_text, error_state = set_error( 'parameter_ignored_suggest', {k, k:lower()}, true ); else if nil == suggestions.suggestions then -- if this table is nil then we need to load it if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version else suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version end end for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter capture = k:match (pattern); -- the whole match if no caputre in pattern else the capture if a match if capture then -- if the pattern matches param = substitute( param, capture ); -- add the capture to the suggested parameter (typically the enumerator) error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message end end if not is_set (error_text) then -- couldn't match with a pattern, is there an expicit suggestion? if suggestions.suggestions[ k:lower() ] ~= nil then error_text, error_state = set_error( 'parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); else error_text, error_state = set_error( 'parameter_ignored', {k}, true ); end end end if error_text ~= '' then table.insert( z.message_tail, {error_text, error_state} ); end end args[k] = v; elseif args[k] ~= nil or (k == 'postscript') then args[k] = v; end end for k, v in pairs( args ) do if 'string' == type (k) then -- don't evaluate positional parameters has_invisible_chars (k, v); end end return citation0( config, args) end return z