sync from sandbox;
(Created page with " --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- ]] local dates, year_date_check, reformat_dates, date_hyphen_...") |
>Trappist the monk (sync from sandbox;) |
||
| Line 1: | Line 1: | ||
require('Module:No globals'); | |||
--[[--------------------------< 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 >-------------------------------------- | ||
each of these counts against the Lua upvalue limit | |||
]] | |||
local | local validation; -- functions in Module:Citation/CS1/Date_validation | ||
local | local utilities; -- functions in Module:Citation/CS1/Utilities | ||
local z ={}; -- table of tables in Module:Citation/CS1/Utilities | |||
local | |||
local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers | |||
local metadata; -- functions in Module:Citation/CS1/COinS | |||
local cfg = {}; -- table of configuration tables that are defined in Module:Citation/CS1/Configuration | local 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 | local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist | ||
| Line 22: | Line 21: | ||
--[[--------------------------< P A G E S C O P E V A R I A B L E S >-------------------------------------- | --[[--------------------------< P A G E S C O P E V A R I A B L E S >-------------------------------------- | ||
declare variables here that have page-wide scope that are not brought in from other modules; that are created here and used here | |||
and used here | |||
]] | ]] | ||
local added_deprecated_cat; -- | local added_deprecated_cat; -- Boolean flag so that the category is added only once | ||
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category | |||
local added_vanc_errs; -- | |||
local Frame; -- holds the module's frame table | local Frame; -- holds the module's frame table | ||
| Line 48: | Line 45: | ||
local i = 1; | local i = 1; | ||
while i <= count do -- loop through all items in list | while i <= count do -- loop through all items in list | ||
if is_set( list[i] ) then | if utilities.is_set( list[i] ) then | ||
return list[i]; -- return the first set list member | return list[i]; -- return the first set list member | ||
end | end | ||
i = i + 1; -- point to next | i = i + 1; -- point to next | ||
end | end | ||
end | end | ||
| Line 81: | Line 58: | ||
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 | added_vanc_errs is a Boolean declared in page scope variables above | ||
]] | ]] | ||
| Line 88: | Line 65: | ||
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, { | table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source}, true ) } ); | ||
end | end | ||
end | end | ||
| Line 95: | Line 72: | ||
--[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ | --[[--------------------------< I S _ S C H E M E >------------------------------------------------------------ | ||
does this thing that purports to be a | 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: | 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 | Scheme names consist of a sequence of characters beginning with a | ||
| Line 118: | Line 95: | ||
Single character names are generally reserved; see https://tools.ietf.org/html/draft-ietf-dnsind-iana-dns-01#page-15; | 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]] | see also [[Single-letter second-level domain]] | ||
list of | list of TLDs: https://www.iana.org/domains/root/db | ||
RFC 952 (modified by RFC 1123) requires the first and last character of a hostname to be a letter or a digit. Between | |||
the first and last characters the name may use letters, digits, and the hyphen. | the first and last characters the name may use letters, digits, and the hyphen. | ||
Also allowed are IPv4 addresses. IPv6 not supported | 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 | 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 | is two or more alpha characters. Any preceding '//' (from splitting a URL with a scheme) will be stripped | ||
here. Perhaps not necessary but retained | here. Perhaps not necessary but retained in case it is necessary for IPv4 dot decimal. | ||
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 | ||
internationalized domain name ( | 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 | 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 | ||
| Line 140: | Line 117: | ||
IPv4 dot-decimal address format; TLD not allowed | IPv4 dot-decimal address format; TLD not allowed | ||
returns true if domain appears to be a proper name and | returns true if domain appears to be a proper name and TLD or IPv4 address, else false | ||
]=] | ]=] | ||
| Line 155: | Line 132: | ||
end | end | ||
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at | if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource | ||
return false; | return false; | ||
end | end | ||
local patterns = { -- patterns that look like | local patterns = { -- patterns that look like URLs | ||
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld | '%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld | ||
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix | '%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix | ||
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10) | '%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10) | ||
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10) | '%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10) | ||
'%f[%w][%w]%.%a%a$', -- one character hostname and | '%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars) | ||
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and | '%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD | ||
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address | '^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address | ||
} | } | ||
| Line 171: | Line 148: | ||
for _, pattern in ipairs (patterns) do -- loop through the patterns list | for _, pattern in ipairs (patterns) do -- loop through the patterns list | ||
if domain:match (pattern) then | if domain:match (pattern) then | ||
return true; -- if a match then we think that this thing that purports to be a | return true; -- if a match then we think that this thing that purports to be a URL is a URL | ||
end | end | ||
end | end | ||
| Line 186: | Line 163: | ||
--[[--------------------------< I S _ U R L >------------------------------------------------------------------ | --[[--------------------------< I S _ U R L >------------------------------------------------------------------ | ||
returns true if the scheme and domain parts of a | 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 | This function is the last step in the validation process. This function is separate because there are cases that | ||
| Line 195: | Line 172: | ||
local function is_url (scheme, domain) | local function is_url (scheme, domain) | ||
if is_set (scheme) then | if utilities.is_set (scheme) then -- if scheme is set check it and domain | ||
return is_scheme (scheme) and is_domain_name (domain); | return is_scheme (scheme) and is_domain_name (domain); | ||
else | else | ||
return is_domain_name (domain); -- scheme not set when | return is_domain_name (domain); -- scheme not set when URL is protocol-relative | ||
end | end | ||
end | end | ||
| Line 205: | Line 182: | ||
--[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ | --[[--------------------------< S P L I T _ U R L >------------------------------------------------------------ | ||
Split a | Split a URL into a scheme, authority indicator, and domain. | ||
First remove Fully Qualified Domain Name terminator (a dot following | First remove Fully Qualified Domain Name terminator (a dot following TLD) (if any) and any path(/), query(?) or fragment(#). | ||
If protocol relative | 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 immediately following the scheme's colon), make sure that there are only 2. | or more '/' characters immediately following the scheme's colon), make sure that there are only 2. | ||
Any URL that does not have news: scheme must have authority indicator (//). TODO: are there other common schemes | |||
like news: that don't use authority indicator? | |||
Strip off any port and path; | Strip off any port and path; | ||
| Line 223: | Line 203: | ||
url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%1'); -- strip FQDN terminator and path(/), query(?), fragment (#) (the capture prevents false replacement of '//') | url_str = url_str:gsub ('([%a%d])%.?[/%?#].*$', '%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 | if url_str:match ('^//%S*') then -- if there is what appears to be a protocol-relative URL | ||
domain = url_str:match ('^//(%S*)') | 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 | 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 | scheme, authority, domain = url_str:match ('(%S-:)(/*)(%S+)'); -- extract the scheme, authority indicator, and domain portions | ||
authority = authority:gsub ('//', '', 1); | if utilities.is_set (authority) then | ||
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; | |||
return scheme; | if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then | ||
return scheme; -- return scheme only making domain nil which will cause an error message | |||
end | |||
else | |||
if not scheme:match ('^news:') then -- except for news:..., MediaWiki won't link URLs that do not have authority indicator; TODO: a better way to do this test? | |||
return scheme; -- return scheme only making domain nil which will cause an error message | |||
end | |||
end | end | ||
domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present | domain = domain:gsub ('(%a):%d+', '%1'); -- strip port number if present | ||
| Line 240: | Line 226: | ||
--[[--------------------------< L I N K _ P A R A M _ O K >--------------------------------------------------- | --[[--------------------------< 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 | 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 | 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 | 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. | 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 | 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 | |<param>-link= parameter is ok); else false when value appears to be a valid URL (the |<param>-link= parameter is NOT ok). | ||
]] | ]] | ||
| Line 259: | Line 245: | ||
end | end | ||
scheme, domain = split_url (value); -- get scheme or nil and domain or nil from | 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 | return not is_url (scheme, domain); -- return true if value DOES NOT appear to be a valid URL | ||
end | end | ||
| Line 268: | Line 254: | ||
Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value. | Use link_param_ok() to validate |<param>-link= value and its matching |<title>= value. | ||
|<title>= may be | |<title>= may be wiki-linked but not when |<param>-link= has a value. This function emits an error message when | ||
that condition exists | that condition exists | ||
check <link> for inter-language interwiki-link prefix. prefix must be a MediaWiki-recognized language | |||
code and must begin with a colon. | |||
]] | ]] | ||
| Line 275: | Line 264: | ||
local function link_title_ok (link, lorig, title, torig) | local function link_title_ok (link, lorig, title, torig) | ||
local orig; | local orig; | ||
if utilities.is_set (link) then -- don't bother if <param>-link doesn't have a value | |||
if is_set (link) then | |||
if not link_param_ok (link) then -- check |<param>-link= markup | if not link_param_ok (link) then -- check |<param>-link= markup | ||
orig = lorig; -- identify the failing link parameter | orig = lorig; -- identify the failing link parameter | ||
elseif title:find ('%[%[') then -- check |title= for wikilink markup | elseif title:find ('%[%[') then -- check |title= for wikilink markup | ||
orig = torig; -- identify the failing |title= parameter | orig = torig; -- identify the failing |title= parameter | ||
elseif link:match ('^%a+:') then -- if the link is what looks like an interwiki | |||
local prefix = link:match ('^(%a+):'):lower(); -- get the interwiki prefix | |||
if cfg.inter_wiki_map[prefix] then -- if prefix is in the map, must have preceding colon | |||
orig = lorig; -- flag as error | |||
end | |||
end | end | ||
end | end | ||
if is_set (orig) then | if utilities.is_set (orig) then | ||
table.insert( z.message_tail, { | link = ''; -- unset | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_bad_paramlink', orig)}); -- URL or wikilink in |title= with |title-link=; | |||
end | end | ||
return link; -- link if ok, empty string else | |||
end | end | ||
| Line 294: | Line 291: | ||
Determines whether a URL string appears to be valid. | Determines whether a URL string appears to be valid. | ||
First we test for space characters. If any are found, return false. Then split the | 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) | portions, or for protocol-relative (//example.com) URLs, just the domain. Use is_url() to validate the two | ||
portions of the | 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 | 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 | 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 | is at https://tools.ietf.org/html/rfc5536#section-3.1.4 | ||
| Line 305: | Line 302: | ||
local function check_url( url_str ) | local function check_url( url_str ) | ||
if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper | if nil == url_str:match ("^%S+$") then -- if there are any spaces in |url=value it can't be a proper URL | ||
return false; | return false; | ||
end | end | ||
local scheme, domain; | local scheme, domain; | ||
scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from | scheme, domain = split_url (url_str); -- get scheme or nil and domain or nil from URL; | ||
if 'news:' == scheme then -- special case for newsgroups | if 'news:' == scheme then -- special case for newsgroups | ||
| Line 316: | Line 313: | ||
end | end | ||
return is_url (scheme, domain); -- return true if value appears to be a valid | return is_url (scheme, domain); -- return true if value appears to be a valid URL | ||
end | end | ||
| Line 323: | Line 320: | ||
Return true if a parameter value has a string that begins and ends with square brackets [ and ] and the first | 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 | non-space characters following the opening bracket appear to be a URL. The test will also find external wikilinks | ||
that use protocol relative | that use protocol-relative URLs. Also finds bare URLs. | ||
The frontier pattern prevents a match on interwiki links which are similar to scheme:path | The frontier pattern prevents a match on interwiki-links which are similar to scheme:path URLs. The tests that | ||
find bracketed | 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]] | 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]]. | is possible as might be [[en://Hus]]. | ||
| Line 336: | Line 333: | ||
local scheme, domain; | local scheme, domain; | ||
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 = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); | scheme, domain = split_url (value:match ('%f[%[]%[(%a%S*:%S+).*%]')); | ||
elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol relative ext wikilink: [//yyyyy.zzz] | elseif value:match ('%f[%[]%[//%S+.*%]') then -- if protocol-relative ext. wikilink: [//yyyyy.zzz] | ||
scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]')); | scheme, domain = split_url (value:match ('%f[%[]%[(//%S+).*%]')); | ||
elseif value:match ('%a%S*:%S+') then -- if bare | elseif value:match ('%a%S*:%S+') then -- if bare URL with scheme; may have leading or trailing plain text | ||
scheme, domain = split_url (value:match ('(%a%S*:%S+)')); | scheme, domain = split_url (value:match ('(%a%S*:%S+)')); | ||
elseif value:match ('//%S+') then -- if protocol relative bare | elseif value:match ('//%S+') then -- if protocol-relative bare URL: //yyyyy.zzz; may have leading or trailing plain text | ||
scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain | scheme, domain = split_url (value:match ('(//%S+)')); -- what is left should be the domain | ||
else | else | ||
return false; -- didn't find anything that is obviously a | return false; -- didn't find anything that is obviously a URL | ||
end | end | ||
return is_url (scheme, domain); -- return true if value appears to be a valid | return is_url (scheme, domain); -- return true if value appears to be a valid URL | ||
end | end | ||
| Line 361: | Line 358: | ||
local error_message = ''; | local error_message = ''; | ||
for k, v in pairs (parameter_list) do -- for each parameter in the list | 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 | 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 | if utilities.is_set(error_message) then -- once we've added the first portion of the error message ... | ||
error_message=error_message .. ", "; -- ... add a comma space separator | error_message = error_message .. ", "; -- ... add a comma space separator | ||
end | end | ||
error_message=error_message .. "|" .. k .. "="; -- add the failed parameter | error_message = error_message .. "|" .. k .. "="; -- add the failed parameter | ||
end | end | ||
end | end | ||
if is_set (error_message) then | if utilities.is_set (error_message) then -- done looping, if there is an error message, display it | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_param_has_ext_link', {error_message}, true ) } ); | ||
end | end | ||
end | end | ||
| Line 382: | Line 379: | ||
local function safe_for_url( str ) | local function safe_for_url( str ) | ||
if str:match( "%[%[.-%]%]" ) ~= nil then | if str:match( "%[%[.-%]%]" ) ~= nil then | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); | ||
end | end | ||
| Line 404: | Line 401: | ||
local base_url; | local base_url; | ||
if not is_set( label ) then | if not utilities.is_set ( label ) then | ||
label = URL; | label = URL; | ||
if is_set( source ) then | if utilities.is_set ( source ) then | ||
error_str = | error_str = utilities.set_message ( 'err_bare_url_missing_title', { utilities.wrap_style ('parameter', source) }, false, " " ); | ||
else | else | ||
error( cfg.messages["bare_url_no_origin"] ); | error( cfg.messages["bare_url_no_origin"] ); | ||
| Line 413: | Line 410: | ||
end | end | ||
if not check_url( URL ) then | if not check_url( URL ) then | ||
error_str = | error_str = utilities.set_message ( 'err_bad_url', {utilities.wrap_style ('parameter', source)}, false, " " ) .. error_str; | ||
end | end | ||
domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the | domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path | ||
if path then -- if there is a path portion | if path then -- if there is a path portion | ||
path = path:gsub ('[%[%]]', {['[']='%5b',[']']='%5d'}); -- replace '[' and ']' with their percent encoded values | path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values | ||
URL = table.concat ({domain, path}); -- and reassemble | URL = table.concat ({domain, path}); -- and reassemble | ||
end | end | ||
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a | base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL | ||
if is_set (access) then | if utilities.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 | base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon | ||
end | end | ||
| Line 438: | Line 435: | ||
parameters in the citation. | parameters in the citation. | ||
added_deprecated_cat is a | added_deprecated_cat is a Boolean declared in page scope variables above | ||
]] | ]] | ||
| Line 445: | Line 442: | ||
if not added_deprecated_cat then | if not added_deprecated_cat then | ||
added_deprecated_cat = true; -- note that we've added this category | added_deprecated_cat = true; -- note that we've added this category | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } ); -- add error message | ||
end | end | ||
end | end | ||
| Line 452: | Line 449: | ||
--[=[-------------------------< K E R N _ Q U O T E S >-------------------------------------------------------- | --[=[-------------------------< K E R N _ Q U O T E S >-------------------------------------------------------- | ||
Apply kerning to open the space between the quote mark provided by the | 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. | mark contained in a |title= or |chapter= parameter's value. | ||
| Line 458: | Line 455: | ||
"'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 | Double single quotes (italic or bold wiki-markup) are not kerned. | ||
Replaces | Replaces Unicode quote marks 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. | 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; | local wl_type, label, link; | ||
wl_type, label, link = is_wikilink (str); | wl_type, label, link = utilities.is_wikilink (str); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] | ||
if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks | if 1 == wl_type then -- [[D]] simple wikilink with or without quote marks | ||
if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks | if mw.ustring.match (str, '%[%[[\"“”\'‘’].+[\"“”\'‘’]%]%]') then -- leading and trailing quote marks | ||
str = substitute (cfg.presentation['kern-wl-both'], str); | str = utilities.substitute (cfg.presentation['kern-wl-both'], str); | ||
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks | elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks | ||
str = substitute (cfg.presentation['kern-wl-left'], str); | str = utilities.substitute (cfg.presentation['kern-wl-left'], str); | ||
elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks | elseif mw.ustring.match (str, '%[%[.+[\"“”\'‘’]%]%]') then -- trailing quote marks | ||
str = substitute (cfg.presentation['kern-wl-right'], str); | str = utilities.substitute (cfg.presentation['kern-wl-right'], str); | ||
end | end | ||
else -- plain text or [[L|D]]; text in label variable | else -- plain text or [[L|D]]; text in label variable | ||
label= mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) | label = mw.ustring.gsub (label, '[“”]', '\"'); -- replace “” (U+201C & U+201D) with " (typewriter double quote mark) | ||
label= mw.ustring.gsub (label, '[‘’]', '\''); -- replace ‘’ (U+2018 & U+2019) with ' (typewriter single quote mark) | 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) | cap, cap2 = mw.ustring.match (label, "^([\"\'])([^\'].+)"); -- match leading double or single quote but not doubled single quotes (italic markup) | ||
if is_set (cap) then | if utilities.is_set (cap) then | ||
label = substitute (cfg.presentation['kern-left'], {cap, cap2}); | label = utilities.substitute (cfg.presentation['kern-left'], {cap, cap2}); | ||
end | end | ||
cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) | cap, cap2 = mw.ustring.match (label, "^(.+[^\'])([\"\'])$") -- match trailing double or single quote but not doubled single quotes (italic markup) | ||
if is_set (cap) then | if utilities.is_set (cap) then | ||
label = substitute (cfg.presentation['kern-right'], {cap, cap2}); | label = utilities.substitute (cfg.presentation['kern-right'], {cap, cap2}); | ||
end | end | ||
if 2 == wl_type then | if 2 == wl_type then | ||
str = make_wikilink (link, label); | str = utilities.make_wikilink (link, label); -- reassemble the wikilink | ||
else | else | ||
str = label; | str = label; | ||
| Line 509: | Line 506: | ||
--[[--------------------------< 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 >---------------------------------------- | ||
|script-title= holds title parameters that are not written in Latin based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should | |script-title= holds title parameters that are not written in Latin-based scripts: Chinese, Japanese, Arabic, Hebrew, etc. These scripts should | ||
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 | 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. | in italic markup. | ||
Regardless of language, all values provided by |script-title= are wrapped in <bdi>...</bdi> tags to isolate | 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 | |script-title= provides a unique feature. The value in |script-title= may be prefixed with a two-character ISO 639-1 language code and a colon: | ||
|script-title=ja:*** *** (where * represents a Japanese character) | |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: | Spaces between the two-character code and the colon and the colon and the first script character are allowed: | ||
| Line 523: | Line 520: | ||
Spaces preceding the prefix are allowed: |script-title = ja:*** *** | Spaces preceding the prefix are allowed: |script-title = ja:*** *** | ||
The prefix is checked for validity. If it is a valid | The prefix is checked for validity. If it is a valid ISO 639-1 language code, the lang attribute (lang="ja") is added to the <bdi> tag so that browsers can | ||
know the language the tag contains. This may help the browser render the script more correctly. If the prefix is invalid, the lang attribute | 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. | is not added. At this time there is no error message for this condition. | ||
| Line 534: | Line 531: | ||
local lang=''; -- initialize to empty string | local lang=''; -- initialize to empty string | ||
local name; | local name; | ||
if script_value:match('^%l%l%s*:') then | if script_value:match('^%l%l%l?%s*:') then -- if first 3 or 4 non-space characters are script language prefix | ||
lang = script_value:match('^(%l%l)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script | lang = script_value:match('^(%l%l%l?)%s*:%s*%S.*'); -- get the language prefix or nil if there is no script | ||
if not is_set (lang) then | if not utilities.is_set (lang) then | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_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 = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, | name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize | ||
if is_set (name) then -- is prefix a proper ISO 639-1 language code? | if utilities.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+%s*:%s*', ''); -- strip prefix from script | ||
-- is prefix one of these language codes? | -- is prefix one of these language codes? | ||
if in_array (lang, cfg.script_lang_codes) then | if utilities.in_array (lang, cfg.script_lang_codes) then | ||
add_prop_cat ('script_with_name', {name, lang}) | utilities.add_prop_cat ('script_with_name', {name, lang}) | ||
else | else | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_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, { | table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'invalid language code'}, true ) } ); -- invalid language code; add error message | ||
lang = ''; -- invalid so set lang to empty string | lang = ''; -- invalid so set lang to empty string | ||
end | end | ||
else | else | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_script_parameter', {script_param, 'missing prefix'}, true ) } ); -- no language code prefix; add error message | ||
end | end | ||
script_value = substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is | script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL | ||
return script_value; | return script_value; | ||
| Line 571: | Line 568: | ||
local function script_concatenate (title, script, script_param) | local function script_concatenate (title, script, script_param) | ||
if is_set (script) then | if utilities.is_set (script) then | ||
script = format_script_value (script, script_param); -- <bdi> tags, lang | script = format_script_value (script, script_param); -- <bdi> tags, lang attribute, categorization, etc.; returns empty string on error | ||
if is_set (script) then | if utilities.is_set (script) then | ||
title = title .. ' ' .. script; -- concatenate title and script title | title = title .. ' ' .. script; -- concatenate title and script title | ||
end | end | ||
| Line 590: | Line 587: | ||
local function wrap_msg (key, str, lower) | local function wrap_msg (key, str, lower) | ||
if not is_set( str ) then | if not utilities.is_set ( str ) then | ||
return ""; | return ""; | ||
end | end | ||
| Line 596: | Line 593: | ||
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 utilities.substitute ( msg, str ); -- including template text | ||
else | else | ||
return substitute( cfg.messages[key], str ); | return utilities.substitute ( cfg.messages[key], str ); | ||
end | end | ||
end | end | ||
--[[ | --[[----------------< W I K I S O U R C E _ U R L _ M A K E >------------------- | ||
Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate | |||
label; nil else. | |||
str is the value assigned to |chapter= (or aliases) or |title= or |title-link= | str is the value assigned to |chapter= (or aliases) or |title= or |title-link= | ||
| Line 614: | Line 612: | ||
local wl_type, D, L; | local wl_type, D, L; | ||
local ws_url, ws_label; | local ws_url, ws_label; | ||
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'}); | |||
wl_type, D, L = is_wikilink (str); | wl_type, D, L = utilities.is_wikilink (str); -- wl_type is 0 (not a wikilink), 1 (simple wikilink), 2 (complex wikilink) | ||
if 0 == wl_type then -- not a wikilink; might be from |title-link= | if 0 == wl_type then -- not a wikilink; might be from |title-link= | ||
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace | str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace | ||
if is_set (str) then | if utilities.is_set (str) then | ||
ws_url = table.concat ({ -- build a | ws_url = table.concat ({ -- build a Wikisource URL | ||
wikisource_prefix, -- prefix | |||
str, -- article title | str, -- article title | ||
}); | }); | ||
ws_label = str; -- label for the | ws_label = str; -- label for the URL | ||
end | end | ||
elseif 1 == wl_type then | elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]] | ||
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace | str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace | ||
if is_set (str) then | if utilities.is_set (str) then | ||
ws_url = table.concat ({ -- build a | ws_url = table.concat ({ -- build a Wikisource URL | ||
wikisource_prefix, -- prefix | |||
str, -- article title | str, -- article title | ||
}); | }); | ||
ws_label = str; -- label for the | ws_label = str; -- label for the URL | ||
end | end | ||
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]]) | 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 | 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 | if utilities.is_set (str) then | ||
ws_label = D; -- get ws article name from display portion of interwiki link | ws_label = D; -- get ws article name from display portion of interwiki link | ||
ws_url = table.concat ({ -- build a | ws_url = table.concat ({ -- build a Wikisource URL | ||
wikisource_prefix, -- prefix | |||
str, -- article title without namespace from link portion of wikilink | str, -- article title without namespace from link portion of wikilink | ||
}); | }); | ||
end | end | ||
end | end | ||
if ws_url then | if ws_url then | ||
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable | ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL | ||
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of | ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker | ||
end | end | ||
return ws_url, ws_label, L or D; -- return proper | return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil | ||
end | end | ||
--[[ | --[[----------------< F O R M A T _ P E R I O D I C A L >----------------------- | ||
Format the | Format the three periodical parameters: |script-<periodical>=, |<periodical>=, | ||
parameter. | and |trans-<periodical>= into a single Periodical meta-parameter. | ||
]] | ]] | ||
| Line 665: | Line 664: | ||
local periodical_error = ''; | local periodical_error = ''; | ||
if not is_set (periodical) then | if not utilities.is_set (periodical) then | ||
periodical = ''; -- to be safe for concatenation | periodical = ''; -- to be safe for concatenation | ||
else | else | ||
periodical = wrap_style ('italic-title', periodical); | periodical = utilities.wrap_style ('italic-title', periodical); -- style | ||
end | end | ||
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang | periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | ||
if is_set (trans_periodical) then | if utilities.is_set (trans_periodical) then | ||
trans_periodical = wrap_style ('trans-italic-title', trans_periodical); | trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical); | ||
if is_set (periodical) then | if utilities.is_set (periodical) then | ||
periodical = periodical .. | periodical = periodical .. ' ' .. trans_periodical; | ||
else -- here when | else -- here when trans-periodical without periodical or script-periodical | ||
periodical = trans_periodical; | periodical = trans_periodical; | ||
periodical_error = ' ' .. | periodical_error = ' ' .. utilities.set_message ('err_trans_missing_title', {'periodical'}); | ||
end | end | ||
end | end | ||
| Line 687: | Line 686: | ||
--[[ | --[[------------------< 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 | Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, | ||
parameter (chapter_url_source used for error messages). | and |chapter-url= into a single chapter meta- parameter (chapter_url_source used | ||
for error messages). | |||
]] | ]] | ||
local function format_chapter_title ( | local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access) | ||
local chapter_error = ''; | local chapter_error = ''; | ||
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource | 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 | if ws_url then | ||
ws_label = ws_label:gsub ('_', ''); | ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters | ||
chapter = ws_label; | chapter = ws_label; | ||
end | end | ||
if not is_set (chapter) then | if not utilities.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 | 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 = utilities.wrap_style ('quoted-title', chapter); | ||
end | end | ||
end | end | ||
chapter = script_concatenate (chapter, | chapter = script_concatenate (chapter, script_chapter, script_chapter_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | ||
if is_set ( | if utilities.is_set (chapter_url) then | ||
chapter = external_link ( | chapter = external_link (chapter_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate | ||
elseif ws_url then | 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 = 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}); | chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter}); | ||
end | end | ||
if is_set ( | if utilities.is_set (trans_chapter) then | ||
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter); | |||
if is_set (chapter) then | if utilities.is_set (chapter) then | ||
chapter = chapter .. | chapter = chapter .. ' ' .. trans_chapter; | ||
else -- here when | else -- here when trans_chapter without chapter or script-chapter | ||
chapter = | chapter = trans_chapter; | ||
chapter_error = ' ' .. | chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param> | ||
chapter_error = ' ' .. utilities.set_message ('err_trans_missing_title', {chapter_source}); | |||
end | end | ||
end | end | ||
return chapter .. chapter_error; | return chapter .. chapter_error; | ||
| Line 739: | Line 736: | ||
--[[ | --[[----------------< 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 | This function searches a parameter's value for non-printable or invisible characters. | ||
first match. | The search stops at the first match. | ||
This function will detect the visible replacement character when it is part of the | 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) | Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers | ||
and identifies them with a slightly different error message. | (gallery, math, pre, ref) and identifies them with a slightly different error message. | ||
See also coins_cleanup(). | |||
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker | Output of this function is an error message that identifies the character or the | ||
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the | Unicode group, or the stripmarker that was detected along with its position (or, | ||
parameter value. | for multi-byte characters, the position of its first byte) in the parameter value. | ||
]] | ]] | ||
| Line 759: | Line 757: | ||
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned | 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 capture; -- used by stripmarker detection to hold name of the stripmarker | ||
local i=1; | local i = 1; | ||
local stripmarker, apostrophe; | local stripmarker, apostrophe; | ||
capture = string.match (v, '[%w%p ]*'); -- | 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 | if capture == v then -- if same there are no Unicode characters | ||
return; | return; | ||
end | end | ||
while cfg.invisible_chars[i] do | while cfg.invisible_chars[i] do | ||
local char=cfg.invisible_chars[i][1] -- the character or group name | 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 | 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 position and (char == 'zero width joiner') then -- if we found a zero-width joiner character | ||
if mw.ustring.find (v, cfg.indic_script) then -- | if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts | ||
position = nil; -- unset position | position = nil; -- unset position | ||
end | end | ||
| Line 780: | Line 778: | ||
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 and in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters | ('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters | ||
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 | ||
| Line 792: | Line 790: | ||
end | end | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true ) } ); -- add error message | ||
return; -- and done with this parameter | return; -- and done with this parameter | ||
end | end | ||
end | end | ||
i=i+1; | i = i + 1; -- bump our index | ||
end | end | ||
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 | Argument wrapper. This function provides support for argument mapping defined | ||
multiple names can be transparently aliased to single internal variable. | in the configuration file so that multiple names can be transparently aliased to | ||
single internal variable. | |||
]] | ]] | ||
local function argument_wrapper( args ) | local function argument_wrapper ( args ) | ||
local origin = {}; | local origin = {}; | ||
return setmetatable({ | return setmetatable({ | ||
ORIGIN = function( self, k ) | ORIGIN = function ( self, k ) | ||
local dummy = self[k]; --force the variable to be loaded. | local dummy = self[k]; -- force the variable to be loaded. | ||
return origin[k]; | return origin[k]; | ||
end | end | ||
| Line 826: | Line 825: | ||
if type( list ) == 'table' then | if type( list ) == 'table' then | ||
v, origin[k] = select_one( args, list, ' | v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' ); | ||
if origin[k] == nil then | if origin[k] == nil then | ||
origin[k] = ''; -- Empty string, not nil | origin[k] = ''; -- Empty string, not nil | ||
| Line 840: | Line 839: | ||
-- Empty strings, not nil; | -- Empty strings, not nil; | ||
if v == nil then | if v == nil then | ||
v = | v = ''; | ||
origin[k] = ''; | origin[k] = ''; | ||
end | end | ||
| Line 851: | Line 850: | ||
--[[--------------------------< N O W R A P _ D A T E > | --[[--------------------------< 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 YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. | ||
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY | When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span: | ||
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY | |||
DOES NOT yet support MMMM YYYY or any of the date ranges. | DOES NOT yet support MMMM YYYY or any of the date ranges. | ||
| Line 861: | Line 861: | ||
local function nowrap_date (date) | local function nowrap_date (date) | ||
local cap=''; | local cap = ''; | ||
local cap2=''; | local cap2 = ''; | ||
if date:match("^%d%d%d%d%-%d%d%-%d%d$") then | if date:match("^%d%d%d%d%-%d%d%-%d%d$") then | ||
date = substitute (cfg.presentation['nowrap1'], date); | date = utilities.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 | 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)$"); | cap, cap2 = string.match (date, "^(.*)%s+(%d%d%d%d)$"); | ||
date = substitute (cfg.presentation['nowrap2'], {cap, cap2}); | date = utilities.substitute (cfg.presentation['nowrap2'], {cap, cap2}); | ||
end | end | ||
| Line 876: | Line 876: | ||
--[[--------------------------< S E T _ T I T L E T Y P E > | --[[--------------------------< 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. | This function sets default title types (equivalent to the citation including | ||
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none). | |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) | local function set_titletype (cite_class, title_type) | ||
if is_set(title_type) then | if utilities.is_set (title_type) then | ||
if | if 'none' == cfg.keywords_xlate[title_type] then | ||
title_type = | title_type = ''; -- if |type=none then type parameter not displayed | ||
end | end | ||
return title_type; -- if |type= has been set to any other value use that value | return title_type; -- if |type= has been set to any other value use that value | ||
| Line 897: | Line 899: | ||
--[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- | --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- | ||
Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items are | Converts a hyphen to a dash under certain conditions. The hyphen must separate | ||
returned unmodified. These forms are modified: | like items; unlike items are returned unmodified. These forms are modified: | ||
letter - letter (A - B) | letter - letter (A - B) | ||
digit - digit (4-5) | digit - digit (4-5) | ||
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) | 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) | letterdigit - letterdigit (A1-A5) (an optional separator between letter and | ||
digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d) | digit is supported – a.1-a.5 or a-1-a-5) | ||
digitletter - digitletter (5a - 5d) (an optional separator between letter and | |||
digit is supported – 5.a-5.d or 5-a-5-d) | |||
any other forms are returned unmodified. | any other forms are returned unmodified. | ||
| Line 912: | Line 916: | ||
local function hyphen_to_dash( str ) | local function hyphen_to_dash( str ) | ||
if not is_set (str) then | if not utilities.is_set (str) then | ||
return str; | return str; | ||
end | end | ||
local accept; -- Boolean | |||
str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split | |||
str = str:gsub ('-', '-'); -- replace HTML numeric entity with hyphen character | |||
str = str:gsub ('[^%-]%-%-%-[^%-]', '—'); -- replace triple-hyphen with emdash | |||
str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities | str = str:gsub ('[^%-]%-%-[^%-]', '–'); -- replace double-hyphen (as found in BibTeX entries) with endash | ||
str = str:gsub (' ', ' '); -- replace entity with generic keyboard space character | |||
local out = {}; | local out = {}; | ||
| Line 927: | Line 933: | ||
for _, item in ipairs (list) do -- for each item in the list | for _, item in ipairs (list) do -- for each item in the list | ||
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators | item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item | ||
if item:match ('%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+') or | if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators | ||
item:match ('%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+') or -- digitletter hyphen digitletter (optional separator between digit and letter) | if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) | ||
item:match ('%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+') or | item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter) | ||
item:match ('%d+%s*%-%s*%d+') or -- digit hyphen digit | item:match ('^%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+$') or -- digit separator digit hyphen digit separator digit | ||
item:match ('%a+%s*%-%s*%a+') then | item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit | ||
item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter | |||
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters | item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2'); -- replace hyphen, remove extraneous space characters | ||
else | else | ||
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous | item = mw.ustring.gsub (item, '%s*[–—]%s*', '–'); -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace | ||
end | end | ||
end | end | ||
table.insert (out, item); -- add the (possibly modified) item to the output table | table.insert (out, item); -- add the (possibly modified) item to the output table | ||
end | end | ||
local temp_str = ''; -- concatenate the output table into a comma separated string | |||
temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out | |||
if accept then | |||
return utilities.has_accept_as_written (str); -- when global markup removed, return original str | |||
else | |||
return temp_str; -- else, return assembled temp_str | |||
end | |||
end | end | ||
--[[--------------------------< S A F E _ J O I N >----------------------------- | |||
--[[--------------------------< S A F E _ J O I N > | |||
Joins a sequence of strings together while checking for duplicate separation characters. | Joins a sequence of strings together while checking for duplicate separation characters. | ||
| Line 953: | Line 964: | ||
local function safe_join( tbl, duplicate_char ) | local function safe_join( tbl, duplicate_char ) | ||
local f = {}; -- create a function table appropriate to type of ' | local f = {}; -- create a function table appropriate to type of 'duplicate character' | ||
if 1 == #duplicate_char then -- for single byte | if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions | ||
f.gsub=string.gsub | f.gsub = string.gsub | ||
f.match=string.match | f.match = string.match | ||
f.sub=string.sub | f.sub = string.sub | ||
else -- for multi-byte characters use the ustring library functions | else -- for multi-byte characters use the ustring library functions | ||
f.gsub=mw.ustring.gsub | f.gsub = mw.ustring.gsub | ||
f.match=mw.ustring.match | f.match = mw.ustring.match | ||
f.sub=mw.ustring.sub | f.sub = mw.ustring.sub | ||
end | end | ||
| Line 974: | Line 985: | ||
str = value; -- assign value to it (first time through the loop) | str = value; -- assign value to it (first time through the loop) | ||
elseif value ~= '' then | elseif value ~= '' then | ||
if value:sub(1,1) == '<' then -- | if value:sub(1, 1) == '<' then -- special case of values enclosed in spans and other markup. | ||
comp = value:gsub( "%b<>", "" ); -- remove | comp = value:gsub( "%b<>", "" ); -- remove HTML markup (<span>string</span> -> string) | ||
else | else | ||
comp = value; | comp = value; | ||
end | end | ||
-- typically duplicate_char is sepc | -- typically duplicate_char is sepc | ||
if f.sub(comp, 1,1) == duplicate_char then -- is first character same as duplicate_char? why test first character? | if f.sub(comp, 1, 1) == duplicate_char then -- is first character same as duplicate_char? why test first character? | ||
-- Because individual string segments often (always?) begin with terminal punct for the | -- Because individual string segments often (always?) begin with terminal punct for the | ||
-- preceding segment: 'First element' .. 'sepc next element' .. etc? | -- preceding segment: 'First element' .. 'sepc next element' .. etc.? | ||
trim = false; | trim = false; | ||
end_chr = f.sub(str, -1,-1); -- get the last character of the output string | end_chr = f.sub(str, -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 = f.sub(str, 1,-2); -- remove it | str = f.sub(str, 1, -2); -- remove it | ||
elseif end_chr == "'" then -- if it might be | elseif end_chr == "'" then -- if it might be wiki-markup | ||
if f.sub(str, -3,-1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' | if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' | ||
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' | str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' | ||
elseif f.sub(str, -5,-1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' | elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' | ||
trim = true; -- why? why do this and next differently from previous? | trim = true; -- why? why do this and next differently from previous? | ||
elseif f.sub(str, -4,-1) == duplicate_char .. "]''" then -- if last four chars of str are sepc]'' | elseif f.sub(str, -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 | elseif end_chr == "]" then -- if it might be wiki-markup | ||
if f.sub(str, -3,-1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink | if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -3,-1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link | elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -2,-1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link | elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -4,-1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. | elseif f.sub(str, -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 f.sub(str, -2,-1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> | if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> | ||
str = f.sub(str, 1,-3); -- remove them both | str = f.sub(str, 1, -3); -- remove them both | ||
end | end | ||
end | end | ||
if trim then | if trim then | ||
if value ~= comp then -- value does not equal comp when value contains | if value ~= comp then -- value does not equal comp when value contains HTML markup | ||
local dup2 = duplicate_char; | local dup2 = duplicate_char; | ||
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it | if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it | ||
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows | value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup | ||
else | else | ||
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character | value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character | ||
| Line 1,023: | Line 1,034: | ||
end | end | ||
end | end | ||
str = str .. value; | str = str .. value; -- add it to the output string | ||
end | end | ||
end | end | ||
| Line 1,030: | Line 1,041: | ||
--[[--------------------------< I S _ S U F F I X > | --[[--------------------------< I S _ S U F F I X >----------------------------- | ||
returns true is suffix is properly formed Jr, Sr, or ordinal in the range | returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9. | ||
Puncutation not allowed. | |||
]] | ]] | ||
local function is_suffix (suffix) | local function is_suffix (suffix) | ||
if in_array (suffix, {'Jr', 'Sr', '2nd', '3rd'}) or suffix:match ('^%dth$') then | if utilities.in_array (suffix, {'Jr', 'Sr', 'Jnr', 'Snr', '1st', '2nd', '3rd'}) or suffix:match ('^%dth$') then | ||
return true; | return true; | ||
end | end | ||
| Line 1,044: | Line 1,056: | ||
--[[ | --[[--------------------< I S _ G O O D _ V A N C _ N A M E >------------------- | ||
For Vancouver | For Vancouver style, author/editor names are supposed to be rendered in Latin | ||
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character. | (read ASCII) characters. When a name uses characters that contain diacritical marks, | ||
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters. | 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. The module doesn't do this so editors may/must. | |||
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets | 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/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/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF | ||
| Line 1,057: | Line 1,071: | ||
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F | [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/) | |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 | |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods | ||
This original test: | This original test: | ||
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then | if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") | ||
was written | or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then | ||
The test has been rewritten to use decimal character escape sequence for the individual bytes of the | was written outside of the code editor and pasted here because the code editor | ||
to use an external editor to maintain this code. | gets confused between character insertion point and cursor position. The test has | ||
been rewritten to use decimal character escape sequence for the individual bytes | |||
of the Unicode characters so that it is not necessary to use an external editor | |||
to maintain this code. | |||
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) | \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) | ||
| Line 1,073: | Line 1,091: | ||
]] | ]] | ||
local function is_good_vanc_name (last, first) | local function is_good_vanc_name (last, first, suffix) | ||
if not suffix then | |||
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix | |||
if is_set (suffix) then | first = first:match ('(.-)[,%s]+'); -- get name/initials | ||
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix | |||
end | |||
end | |||
if utilities.is_set (suffix) then | |||
if not is_suffix (suffix) then | if not is_suffix (suffix) then | ||
add_vanc_error ( | add_vanc_error (cfg.err_msg_supl.suffix); | ||
return false; -- not a name with an appropriate suffix | return false; -- not a name with an appropriate suffix | ||
end | end | ||
| Line 1,084: | Line 1,106: | ||
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%']*$") or | if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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%'%.]*$") then | nil == mw.ustring.find (first, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%'%.]*$") then | ||
add_vanc_error ('non-Latin | add_vanc_error (cfg.err_msg_supl['non-Latin char']); | ||
return false; -- not a string of | return false; -- not a string of Latin characters; Vancouver requires Romanization | ||
end; | end; | ||
return true; | return true; | ||
| Line 1,093: | Line 1,115: | ||
--[[--------------------------< 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 >------------------------------------------ | ||
Attempts to convert names to initials in support of |name-list- | Attempts to convert names to initials in support of |name-list-style=vanc. | ||
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. | Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. | ||
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. | |||
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. | Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered | ||
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. | as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. | ||
This code only accepts and understands generational suffix in the Vancouver format | |||
because Roman numerals look like, and can be mistaken for, initials. | |||
This function uses ustring functions because firstname initials may be any of the | This function uses ustring functions because firstname initials may be any of the | ||
Unicode Latin characters accepted by is_good_vanc_name (). | |||
]] | ]] | ||
| Line 1,108: | Line 1,134: | ||
if not name then -- if not initials and a suffix | if not name then -- if not initials and a suffix | ||
name = mw.ustring.match(first, "^(%u+)$"); -- is it just | name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials? | ||
end | end | ||
| Line 1,117: | Line 1,143: | ||
return first; -- one or two initials and a valid suffix so nothing to do | return first; -- one or two initials and a valid suffix so nothing to do | ||
else | else | ||
add_vanc_error ( | add_vanc_error (cfg.err_msg_supl.suffix); -- one or two initials with invalid suffix so error message | ||
return first; -- and return first unmolested | return first; -- and return first unmolested | ||
end | end | ||
| Line 1,125: | Line 1,151: | ||
end | end | ||
end -- if here then name has 3 or more uppercase letters so treat them as a word | 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 initials, names = {}, {}; -- tables to hold name parts and initials | ||
| Line 1,141: | Line 1,166: | ||
end | end | ||
if 3 > i then | if 3 > i then | ||
table.insert (initials, mw.ustring.sub(names[i],1,1)); -- insert the | table.insert (initials, mw.ustring.sub(names[i], 1, 1)); -- insert the initial at end of initials table | ||
end | end | ||
i = i+1; -- bump the counter | i = i + 1; -- bump the counter | ||
end | end | ||
| Line 1,150: | Line 1,175: | ||
--[[--------------------------< L I S T | --[[--------------------------< L I S T _ P E O P L E >-------------------------- | ||
Formats a list of people ( | Formats a list of people (authors, contributors, editors, interviewers, translators) | ||
names in the list will be linked when | |||
|<name>-link= has a value | |||
|<name>-mask- does NOT have a value; masked names are presumed to have been | |||
rendered previously so should have been linked there | |||
when |<name>-mask=0, the associated name is not rendered | |||
]] | ]] | ||
local function list_people(control, people, etal) | local function list_people (control, people, etal) | ||
local sep; | local sep; | ||
local namesep; | local namesep; | ||
local format = control.format | local format = control.format; | ||
local maximum = control.maximum | local maximum = control.maximum; | ||
local name_list = {}; | |||
local | |||
if 'vanc' == format then -- Vancouver-like | if 'vanc' == format then -- Vancouver-like name styling? | ||
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between | sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma | ||
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space | namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space | ||
else | else | ||
sep = cfg.presentation['sep_nl']; -- name-list separator between | sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon | ||
namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space> | namesep = cfg.presentation['sep_name']; -- last/first separator is <comma><space> | ||
end | end | ||
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end | if sep:sub (-1, -1) ~= " " then sep = sep .. " " end | ||
if is_set (maximum) and maximum < 1 then return "", 0; end | if utilities.is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for other names | ||
for i,person in ipairs(people) do | for i, person in ipairs (people) do | ||
if is_set(person.last) then | if utilities.is_set (person.last) then | ||
local mask = person.mask | local mask = person.mask; | ||
local one | local one; | ||
local sep_one = sep; | local sep_one = sep; | ||
if is_set (maximum) and i > maximum then | |||
if utilities.is_set (maximum) and i > maximum then | |||
etal = true; | etal = true; | ||
break; | break; | ||
end | |||
local n = tonumber(mask) | |||
if | if mask then | ||
one = string.rep("—",n) | local n = tonumber (mask); -- convert to a number if it can be converted; nil else | ||
if n then | |||
one = 0 ~= n and string.rep("—", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name | |||
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil | |||
else | else | ||
one = mask; | one = mask; -- replace name with mask text (must include name-list separator) | ||
sep_one = " "; | sep_one = " "; -- modify name-list separator | ||
end | end | ||
else | else | ||
one = person.last | one = person.last; -- get surname | ||
local first = person.first | local first = person.first -- get given name | ||
if is_set(first) then | if utilities.is_set (first) then | ||
if ( "vanc" == format ) 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/) | 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 | end | ||
end | end | ||
table.insert( | if utilities.is_set (person.link) then | ||
one = utilities.make_wikilink (person.link, one); -- link author/editor | |||
end | |||
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement) | |||
table.insert (name_list, one); -- add it to the list of names | |||
table.insert (name_list, sep_one); -- add the proper name-list separator | |||
end | |||
end | end | ||
end | end | ||
local count = # | local count = #name_list / 2; -- (number of names + number of separators) divided by 2 | ||
if count | if 0 < count then | ||
if count | if 1 < count and not etal then | ||
if 'amp' == format then | |||
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text | |||
elseif 'and' == format then | |||
if 2 == count then | |||
name_list[#name_list-2] = cfg.presentation.sep_nl_and; -- replace last separator with 'and' text | |||
else | |||
name_list[#name_list-2] = cfg.presentation.sep_nl_end; -- replace last separator with '(sep) and' text | |||
end | |||
end | |||
end | end | ||
name_list[#name_list] = nil; -- erase the last separator | |||
end | end | ||
local result = table.concat( | local result = table.concat (name_list); -- construct list | ||
if etal and is_set (result) then | if etal and utilities.is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list | ||
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've | result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al. | ||
end | end | ||
return result, count | return result, count; -- return name-list string and count of number of names (count used for editor names only) | ||
end | end | ||
--[[--------------------------< A N C H O R _ I D > | --[[--------------------------< 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. | 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. | 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 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 | ||
| Line 1,244: | Line 1,292: | ||
table.insert (names, year); -- add the year at the end | table.insert (names, year); -- add the year at the end | ||
local id = table.concat(names); -- concatenate names and year for CITEREF id | local id = table.concat(names); -- concatenate names and year for CITEREF id | ||
if is_set (id) then | if utilities.is_set (id) then -- if concatenation is not an empty string | ||
return "CITEREF" .. id; -- add the CITEREF portion | return "CITEREF" .. id; -- add the CITEREF portion | ||
else | else | ||
| Line 1,252: | Line 1,300: | ||
--[[ | --[[---------------------< N A M E _ H A S _ E T A L >-------------------------- | ||
Evaluates the content of name parameters (author, editor, etc) for variations on the theme of et al. If found, | Evaluates the content of name parameters (author, editor, etc.) for variations on | ||
the et al. is removed, a flag is set to true and the function returns the modified name and the flag. | 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 | This function never sets the flag to false but returns its previous state because | ||
previous passes through this function or by the associated |display-<names>=etal parameter | it may have been set by previous passes through this function or by the associated | ||
|display-<names>=etal parameter | |||
]] | ]] | ||
| Line 1,264: | Line 1,314: | ||
local function name_has_etal (name, etal, nocat, param) | local function name_has_etal (name, etal, nocat, param) | ||
if is_set (name) then | if utilities.is_set (name) then -- name can be nil in which case just return | ||
local patterns = cfg.et_al_patterns; | local patterns = cfg.et_al_patterns; -- get patterns from configuration | ||
for _, pattern in ipairs (patterns) do -- loop through all of the patterns | for _, pattern in ipairs (patterns) do -- loop through all of the patterns | ||
| Line 1,272: | Line 1,322: | ||
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) | etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) | ||
if not nocat then -- no categorization for |vauthors= | if not nocat then -- no categorization for |vauthors= | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, {utilities.set_message ('err_etal', {param})}); -- and set an error if not added | ||
end | end | ||
end | end | ||
| Line 1,278: | Line 1,328: | ||
end | end | ||
return name, etal; | return name, etal; | ||
end | end | ||
--[[ | --[[---------------------< N A M E _ I S _ N U M E R I C >---------------------- | ||
Evaluates the content of author and editor parameters for | Add maint cat when name parameter value does not contain letters. Does not catch | ||
These | mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the | ||
adds the editor markup maintenance category. | current version of this test but |first=(1888) is caught. | ||
returns nothing | |||
]] | |||
local function name_is_numeric (name, list_name) | |||
if utilities.is_set (name) then | |||
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters | |||
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template | |||
end | |||
end | |||
end | |||
--[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------ | |||
Evaluates the content of author and editor parameters for extraneous editor annotations: | |||
ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and | |||
are redundant in editor parameters. If found, the function adds the editor markup | |||
maintenance category. | |||
returns nothing | |||
]] | ]] | ||
local function name_has_ed_markup (name, list_name) | local function name_has_ed_markup (name, list_name) | ||
local patterns = cfg.editor_markup_patterns; -- get patterns from configuration | local patterns = cfg.editor_markup_patterns; -- get patterns from configuration | ||
if is_set (name) then | if utilities.is_set (name) then | ||
for _, pattern in ipairs (patterns) do -- spin through patterns table and | for _, pattern in ipairs (patterns) do -- spin through patterns table and | ||
if name:match (pattern) then | if name:match (pattern) then | ||
utilities.set_message ('maint_extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template | |||
break; | break; | ||
end | end | ||
end | end | ||
end | end | ||
end | end | ||
--[[ | --[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------ | ||
Evaluates the content of last/surname (authors etc.) parameters for multiple names. | |||
Multiple names are indicated if there is more than one comma or any "unescaped" | |||
semicolons. Escaped semicolons are ones used as part of selected HTML entities. | |||
If the condition is met, the function adds the multiple name maintenance category. | |||
returns nothing | |||
]] | ]] | ||
local function name_has_mult_names (name, list_name) | local function name_has_mult_names (name, list_name) | ||
local | local _, commas, semicolons, nbsps; | ||
if is_set (name) then | if utilities.is_set (name) then | ||
_, count = name:gsub (' | _, commas = name:gsub (',', ''); -- count the number of commas | ||
_, semicolons = name:gsub (';', ''); -- count the number of semicolons | |||
-- nbsps probably should be its own separate count rather than merged in | |||
-- some way with semicolons because Lua patterns do not support the | |||
-- grouping operator that regex does, which means there is no way to add | |||
-- more entities to escape except by adding more counts with the new | |||
-- entities | |||
_, nbsps = name:gsub (' ',''); -- count nbsps | |||
-- There is exactly 1 semicolon per entity, so subtract nbsps | |||
-- from semicolons to 'escape' them. If additional entities are added, | |||
-- they also can be subtracted. | |||
if 1 < commas or 0 < (semicolons - nbsps) then | |||
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message | |||
end | end | ||
end | 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. | This function calls various name checking functions used to validate the content | ||
of the various name-holding parameters. | |||
]] | ]] | ||
local function name_checks (last, first, list_name) | local function name_checks (last, first, list_name) | ||
if is_set (last) then | local accept_name; | ||
if utilities.is_set (last) then | |||
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last> | |||
if not accept_name then -- <last> not wrapped in accept-as-written markup | |||
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) | |||
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation | |||
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation | |||
end | end | ||
end | end | ||
if is_set (first) then | |||
if utilities.is_set (first) then | |||
first | first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> | ||
if not accept_name then -- <first> not wrapped in accept-as-written markup | |||
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation | |||
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation | |||
end | end | ||
end | end | ||
return last, first; -- done | return last, first; -- done | ||
end | |||
--[[ | --[[----------------------< E X T R A C T _ N A M E S >------------------------- | ||
Gets name list from the input arguments | Gets name list from the input arguments | ||
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. | Searches through args in sequential order to find |lastn= and |firstn= 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 | (or their aliases), and their matching link and mask parameters. Stops searching | ||
find |last4= and |last5= then the search is done. | 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= | This function emits an error message when there is a |firstn= without a matching | ||
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. | |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 | When an author or editor parameter contains some form of 'et al.', the 'et al.' | ||
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the | is stripped from the parameter and a flag (etal) returned that will cause list_people() | ||
template's metadata. When this occurs, | to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps | ||
'et al.' out of the template's metadata. When this occurs, an error is emitted. | |||
]] | ]] | ||
local function extract_names(args, list_name) | local function extract_names(args, list_name) | ||
local names = {}; | local names = {}; -- table of names | ||
local last; | local last; -- individual name components | ||
local first; | local first; | ||
local link; | local link; | ||
local mask; | local mask; | ||
local i = 1; | local i = 1; -- loop counter/indexer | ||
local n = 1; | local n = 1; -- output table indexer | ||
local count = 0; | 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; | local etal = false; -- return value set to true when we find some form of et al. in an author parameter | ||
local last_alias, first_alias; | local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging | ||
while true do | while true do | ||
last, last_alias = select_one( args, cfg.aliases[list_name .. '-Last'], ' | last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1 | ||
first, first_alias = select_one( args, cfg.aliases[list_name .. '-First'], ' | first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'err_redundant_parameters', i ); | ||
link = select_one( args, cfg.aliases[list_name .. '-Link'], ' | link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ); | ||
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], ' | mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i ); | ||
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al. | last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al. | ||
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al. | first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al. | ||
last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks | 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, { | local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias | ||
table.insert (z.message_tail, { utilities.set_message ( 'err_first_missing_last', { | |||
first_alias, -- param name of alias missing its mate | |||
first_alias:gsub (alias, {['first'] = 'last', ['given'] = 'surname'}), -- make param name appropriate to the alias form | |||
}, true ) } ); -- add this error message | |||
elseif not first and not last then -- if both firstn and lastn aren't found, are we done? | 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 | ||
| Line 1,399: | Line 1,497: | ||
end | end | ||
else -- we have last with or without a first | else -- we have last with or without a first | ||
link_title_ok (link, | local result; | ||
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup | |||
if first then | |||
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup | |||
end | |||
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) | 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, { | table.insert( z.message_tail, { utilities.set_message ( 'err_missing_name', {list_name:match ("(%w+)List"):lower(), 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 | ||
| Line 1,411: | Line 1,513: | ||
end | end | ||
return names, etal; -- all done, return our list of names | return names, etal; -- all done, return our list of names and the etal flag | ||
end | end | ||
| Line 1,419: | Line 1,521: | ||
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. | Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. | ||
Returns the language name and associated two- or three-character code. Because case of the source may be incorrect | Returns the language name and associated two- or three-character code. Because | ||
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is | case of the source may be incorrect or different from the case that WikiMedia uses, | ||
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we | the name comparisons are done in lower case and when a match is found, the Wikimedia | ||
return the original language name string. | version (assumed to be correct) is returned along with the code. When there is no | ||
match, we return the original language name string. | |||
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include | mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of | ||
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support | languages that in some cases may include extensions. For example, code 'cbk-zam' | ||
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they | and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support | ||
are used as sub-domain names: cbk-zam.wikipedia.org. | code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a | ||
can be found at Template:Citation Style documentation/language/doc | 'language' codes per se, rather they are used as sub-domain names: cbk-zam.wikipedia.org. | ||
A list of language names and codes supported by fetchLanguageNames() can be found | |||
at Template:Citation Style documentation/language/doc | |||
Names that are included in the list will be found if that name is provided in the |language= parameter. For example, | Names that are included in the list will be found if that name is provided in the | ||
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found | |language= parameter. For example, if |language=Chavacano de Zamboanga, that name | ||
and the associated code is not two or three characters, this function returns only the WikiMedia language name. | will be found with the associated code 'cbk-zam'. When names are found and the | ||
associated code is not two or three characters, this function returns only the | |||
WikiMedia language name. | |||
Some language names have multiple entries under different codes: | Some language names have multiple entries under different codes: | ||
| Line 1,447: | Line 1,554: | ||
end | end | ||
local ietf_code; -- because some languages have both | local ietf_code; -- because some languages have both IETF-like codes and ISO 639-like codes | ||
local ietf_name; | local ietf_name; | ||
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 | for code, name in pairs (cfg.languages) do -- scan the list to see if we can find our language | ||
if langlc == mw.ustring.lower(name) then | if langlc == mw.ustring.lower (name) then | ||
if 2 == code | if 2 == #code or 3 == #code then -- two- or three-character codes only; IETF extensions not supported | ||
return name, code; -- so return the name and the code | return name, code; -- so return the name and the code | ||
end | end | ||
ietf_code = code; -- remember that we found an | ietf_code = code; -- remember that we found an IETF-like code and save its name | ||
ietf_name = name; -- but keep looking for a 2- or 3-char code | ietf_name = name; -- but keep looking for a 2- or 3-char code | ||
end | end | ||
end | end | ||
-- didn't find name with 2- or 3-char code; if | -- didn't find name with 2- or 3-char code; if IETF-like code found return | ||
return ietf_code and ietf_name or lang; -- associated name; return original language text else | 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 >------------------ | ||
Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki, | Gets language name from a provided two- or three-character ISO 639 code. If a code | ||
use the returned name; if not, then use the value that was provided with the language parameter. | is recognized by MediaWiki, use the returned name; if not, then use the value that | ||
was provided with the language parameter. | |||
When |language= contains a recognized language (either code or name), the page is assigned to the category for | When |language= contains a recognized language (either code or name), the page is | ||
that code: Category:Norwegian-language sources (no). | assigned to the category for that code: Category:Norwegian-language sources (no). | ||
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. | For valid three-character code languages, the page is assigned to the single category | ||
for '639-2' codes: Category:CS1 ISO 639-2 language sources. | |||
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character | Languages that are the same as the local wiki are not categorized. MediaWiki does | ||
equivalents of two-character codes: code 'ar' is recognized | not recognize three-character equivalents of two-character codes: code 'ar' is | ||
recognized but code 'ara' is not. | |||
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are | This function supports multiple languages in the form |language=nb, French, th | ||
separated from each other by commas. | where the language names or codes are separated from each other by commas with | ||
optional space characters. | |||
]] | ]] | ||
| Line 1,491: | Line 1,600: | ||
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 | |||
local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name | |||
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list | names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list | ||
| Line 1,501: | Line 1,608: | ||
if name then -- there was a remapped code so | if name then -- there was a remapped code so | ||
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); | if not lang:match ('^%a%a%a?%-x%-%a+$') then -- if not a private IETF tag | ||
lang = lang:gsub ('^(%a%a%a?)%-.*', '%1'); -- strip IETF tags from code | |||
end | |||
else | 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 | if 2 == lang:len() or 3 == lang:len() then -- if two-or three-character code | ||
name = mw.language.fetchLanguageName (lang:lower(), this_wiki_code); -- get language name if |language= is a proper 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 utilities.is_set (name) then -- if |language= specified a valid code | ||
code = lang:lower(); -- save it | code = lang:lower(); -- save it | ||
else | else | ||
name, code = get_iso639_code (lang, this_wiki_code); | name, code = get_iso639_code (lang, cfg.this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) | ||
end | end | ||
if is_set (code) then | if utilities.is_set (code) then -- only 2- or 3-character codes | ||
name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names | name = cfg.lang_code_remap[code] or name; -- override wikimedia when they misuse language codes/names | ||
if this_wiki_code ~= code then | if cfg.this_wiki_code ~= code then -- when the language is not the same as this wiki's language | ||
if 2 == code:len() then -- and is a two-character code | if 2 == code:len() then -- and is a two-character code | ||
add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it | utilities.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) | 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 | utilities.add_prop_cat ('foreign_lang_source_2' .. code, {code}); -- categorize it differently TODO: support multiple three-character code categories per cs1|2 template | ||
end | end | ||
elseif cfg.local_lang_cat_enable then -- when the language and this wiki's language are the same and categorization is enabled | |||
utilities.add_prop_cat ('local_lang_source', {name, code}); -- categorize it | |||
end | end | ||
else | else | ||
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added | |||
end | end | ||
| Line 1,534: | Line 1,643: | ||
name = ''; -- so we can reuse it | name = ''; -- so we can reuse it | ||
end | end | ||
name = utilities.make_sep_list (#language_list, language_list); | |||
if this_wiki_name == name then | if this_wiki_name == name then | ||
return ''; -- if one language and that language is this wiki's return an empty string (no annotation) | return ''; -- if one language and that language is this wiki's return an empty string (no annotation) | ||
| Line 1,552: | Line 1,656: | ||
--[[ | --[[----------------------< 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 | ||
| Line 1,562: | Line 1,666: | ||
local function set_cs1_style (ps) | local function set_cs1_style (ps) | ||
if not is_set (ps) then | if not utilities.is_set (ps) then -- unless explicitly set to something | ||
ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation | ps = cfg.presentation['ps_cs1']; -- terminate the rendered citation | ||
end | end | ||
| Line 1,569: | Line 1,673: | ||
--[[ | --[[-----------------------< 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 | ||
| Line 1,579: | Line 1,683: | ||
local function set_cs2_style (ps, ref) | local function set_cs2_style (ps, ref) | ||
if not is_set (ps) then | if not utilities.is_set (ps) then -- if |postscript= has not been set, set cs2 default | ||
ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation | ps = cfg.presentation['ps_cs2']; -- terminate the rendered citation | ||
end | end | ||
if not is_set (ref) then | if not utilities.is_set (ref) then -- if |ref= is not set | ||
ref = "harv"; -- set default |ref=harv | ref = "harv"; -- set default |ref=harv | ||
end | end | ||
| Line 1,589: | Line 1,693: | ||
--[[ | --[[---------< 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 | When |mode= is not set or when its value is invalid, use config.CitationClass and | ||
rendered style. | parameter values to establish rendered style. | ||
]] | ]] | ||
| Line 1,610: | Line 1,714: | ||
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ | --[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ | ||
Establish basic style settings to be used when rendering the citation. | Establish basic style settings to be used when rendering the citation. Uses |mode= | ||
config.CitationClass from the template's #invoke: to establish style. | if set and valid or uses config.CitationClass from the template's #invoke: to establish style. | ||
]] | ]] | ||
| Line 1,624: | Line 1,728: | ||
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 | |||
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 | ||
| Line 1,632: | Line 1,737: | ||
--[=[-------------------------< I S _ P D F > | --[=[-------------------------< I S _ P D F >----------------------------------- | ||
Determines if a | Determines if a URL has the file extension that is one of the PDF file extensions | ||
applying the | used by [[MediaWiki:Common.css]] when applying the PDF icon to external links. | ||
returns true if file extension is one of the recognized extensions, else false | returns true if file extension is one of the recognized extensions, else false | ||
| Line 1,648: | Line 1,753: | ||
--[[--------------------------< S T Y L E _ F O R M A T > | --[[--------------------------< S T Y L E _ F O R M A T >----------------------- | ||
Applies | Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message | ||
not have a matching | if the format parameter does not have a matching URL parameter. If the format parameter | ||
is recognized as a | 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. | the appropriate styling. | ||
| Line 1,658: | Line 1,764: | ||
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 utilities.is_set (format) then | ||
format = wrap_style ('format', format); | format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize | ||
if not is_set (url) then | if not utilities.is_set (url) then | ||
format = format .. | format = format .. ' ' .. utilities.set_message ( 'err_format_missing_url', {fmt_param, url_param} ); -- add an error message | ||
end | end | ||
elseif is_pdf (url) then -- format is not set so if | elseif is_pdf (url) then -- format is not set so if URL is a PDF file then | ||
format = wrap_style ('format', 'PDF'); | format = utilities.wrap_style ('format', 'PDF'); -- set format to PDF | ||
else | else | ||
format = ''; -- empty string for concatenation | format = ''; -- empty string for concatenation | ||
| Line 1,672: | Line 1,778: | ||
--[[ | --[[---------------------< 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 | Returns a number that defines the number of names displayed for author and editor | ||
to indicate when et al. should be appended to the name list. | name lists and a Boolean flag to indicate when et al. should be appended to the name list. | ||
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and | When the value assigned to |display-xxxxors= is a number greater than or equal to zero, | ||
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains | return the number and the previous state of the 'etal' flag (false by default | ||
some variant of the text 'et al.'). | but may have been set to true if the name list contains some variant of the text 'et al.'). | ||
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the | When the value assigned to |display-xxxxors= is the keyword 'etal', return a number | ||
number of authors in the list and set the 'etal' flag true. | that is one greater than the number of authors in the list and set the 'etal' flag true. | ||
the names in the name list followed by 'et al.' | 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. | In all other cases, returns nil and the previous state of the 'etal' flag. | ||
| Line 1,696: | Line 1,802: | ||
local function get_display_names (max, count, list_name, etal) | local function get_display_names (max, count, list_name, etal) | ||
if is_set (max) then | if utilities.is_set (max) then | ||
if 'etal' == max:lower():gsub("[ '%.]", '') then -- the :gsub() portion makes 'etal' from a variety of 'et al.' spellings and stylings | 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. | max = count + 1; -- number of authors + 1 so display all author name plus et al. | ||
| Line 1,703: | Line 1,809: | ||
max = tonumber (max); -- make it a number | max = tonumber (max); -- make it a number | ||
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors | if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors | ||
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {cfg.special_case_translation [list_name], max}, true)}); -- add error message | |||
max = nil; | |||
end | end | ||
else -- not a valid keyword or number | else -- not a valid keyword or number | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {cfg.special_case_translation [list_name], max}, true)}); -- add error message | ||
max = nil; -- unset; as if |display-xxxxors= had not been set | max = nil; -- unset; as if |display-xxxxors= had not been set | ||
end | end | ||
| Line 1,715: | Line 1,822: | ||
--[[ | --[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >--------------- | ||
Adds page | Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be | ||
abbreviation in the first characters of the parameter content. | some form of p. or pp. abbreviation in the first characters of the parameter content. | ||
check | check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value: | ||
good pattern: '^P[^%.P%l]' matches when | good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px | ||
bad pattern: '^[Pp][ | where x and X are letters and # is a digit | ||
bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG | |||
]] | ]] | ||
local function extra_text_in_page_check (page) | local function extra_text_in_page_check (page) | ||
local good_pattern = '^P[^%. | local good_pattern = '^P[^%.PpGg]'; -- OK to begin with uppercase P: P7 (page 7 of section P), but not p123 (page 123) | ||
local bad_pattern = '^[Pp] | local bad_pattern = '^[Pp][PpGg]?%.?[ %d]'; | ||
if not page:match (good_pattern) and (page:match (bad_pattern) or | if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?') or page:match ('^[Pp]gs.?')) then | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_pages')}); -- add error | |||
end | end | ||
end | end | ||
| Line 1,739: | Line 1,847: | ||
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled | 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 | parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the | ||
rendered citation and in the metadata. Individual author names may be wikilinked | rendered citation and in the metadata. Individual author names may be wikilinked | ||
| Line 1,748: | Line 1,856: | ||
local function get_v_name_table (vparam, output_table, output_link_table) | 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 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 | local wl_type, label, link; -- wl_type not used here; just a placeholder | ||
local i = 1; | local i = 1; | ||
while name_table[i] do | while name_table[i] do | ||
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled | if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses | ||
local name = name_table[i]; | local name = name_table[i]; | ||
i=i+1; -- bump indexer to next segment | i = i + 1; -- bump indexer to next segment | ||
while name_table[i] do | while name_table[i] do | ||
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments | name = name .. ', ' .. name_table[i]; -- concatenate with previous segments | ||
if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled | if name_table[i]:match ('^.*%)%)$') then -- if this table member has the closing doubled parentheses | ||
break; -- and done reassembling so | break; -- and done reassembling so | ||
end | end | ||
i=i+1; | i = i + 1; -- bump indexer | ||
end | end | ||
table.insert (output_table, name); -- and add corporate name to the output table | table.insert (output_table, name); -- and add corporate name to the output table | ||
table.insert (output_link_table, ''); -- no wikilink | table.insert (output_link_table, ''); -- no wikilink | ||
else | else | ||
wl_type, label, link = is_wikilink (name_table[i]); | wl_type, label, link = utilities.is_wikilink (name_table[i]); -- wl_type is: 0, no wl (text in label variable); 1, [[D]]; 2, [[L|D]] | ||
table.insert (output_table, label); -- add this name | table.insert (output_table, label); -- add this name | ||
if 1 == wl_type then | if 1 == wl_type then | ||
| Line 1,774: | Line 1,882: | ||
end | end | ||
end | end | ||
i = i+1; | i = i + 1; | ||
end | end | ||
return output_table; | return output_table; | ||
| Line 1,787: | Line 1,895: | ||
Author / editor names in |vauthors= or |veditors= must be in Vancouver system style. Corporate or institutional names | 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 | 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 | tests, are wrapped in doubled parentheses ((corporate name)) to suppress the format tests. | ||
Supports generational suffixes Jr, 2nd, 3rd, 4th–6th. | Supports generational suffixes Jr, 2nd, 3rd, 4th–6th. | ||
This function sets the | This function sets the Vancouver error when a required comma is missing and when there is a space between an author's initials. | ||
]] | ]] | ||
| Line 1,807: | Line 1,915: | ||
for i, v_name in ipairs(v_name_table) do | for i, v_name in ipairs(v_name_table) do | ||
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to | first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor | ||
local accept_name; | |||
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name> | |||
-- if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to suppress vanc formatting and error detection | |||
-- last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parentheses | |||
if accept_name then | |||
last = v_name; | |||
corporate = true; -- flag used in list_people() | corporate = true; -- flag used in list_people() | ||
elseif string.find(v_name, "%s") then | elseif string.find(v_name, "%s") then | ||
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; | if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; | ||
add_vanc_error ( | add_vanc_error (cfg.err_msg_supl.punctuation); | ||
end | end | ||
local lastfirstTable = {} | local lastfirstTable = {} | ||
lastfirstTable = mw.text.split(v_name, "%s") | lastfirstTable = mw.text.split(v_name, "%s+") | ||
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be | first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix | ||
if | |||
suffix = first -- | if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters | ||
suffix = first; -- not initials so assume that whatever we got is a generational suffix | |||
first = table.remove(lastfirstTable); -- get what should be the initials from the table | first = table.remove(lastfirstTable); -- get what should be the initials from the table | ||
end | end | ||
last = table.concat(lastfirstTable, | last = table.concat(lastfirstTable, ' ') -- returns a string that is the concatenation of all other names that are not initials and generational suffix | ||
if not utilities.is_set (last) then | |||
first = ''; -- unset | |||
last = v_name; -- last empty because something wrong with first | |||
add_vanc_error (cfg.err_msg_supl.name); | |||
end | |||
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then | if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then | ||
add_vanc_error ('missing comma'); | add_vanc_error (cfg.err_msg_supl['missing comma']); -- matches last II last; the case when a comma is missing | ||
end | end | ||
if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test | if mw.ustring.match (v_name, ' %u %u$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test | ||
add_vanc_error ( | add_vanc_error (cfg.err_msg_supl.name); -- matches a space between two initials | ||
end | end | ||
else | else | ||
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? | last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? | ||
end | end | ||
if is_set (first) then | if utilities.is_set (first) then | ||
if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else | if not mw.ustring.match (first, "^%u?%u$") then -- first shall contain one or two upper-case letters, nothing else | ||
add_vanc_error ( | add_vanc_error (cfg.err_msg_supl.initials); -- too many initials; mixed case initials (which may be ok Romanization); hyphenated initials | ||
end | end | ||
is_good_vanc_name (last, first); | is_good_vanc_name (last, first, suffix); -- check first and last before restoring the suffix which may have a non-Latin digit | ||
if is_set (suffix) then | if utilities.is_set (suffix) then | ||
first = first .. ' ' .. suffix; -- if there was a suffix concatenate with the initials | 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 | suffix = ''; -- unset so we don't add this suffix to all subsequent names | ||
| Line 1,849: | Line 1,967: | ||
end | end | ||
link = select_one( args, cfg.aliases[list_name .. '-Link'], ' | link = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i ) or v_link_table[i]; | ||
mask = select_one( args, cfg.aliases[list_name .. '-Mask'], ' | mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i ); | ||
names[i] = {last = last, first = first, link = link, mask = mask, corporate=corporate}; -- add this assembled name to our names list | names[i] = {last = last, first = first, link = link, mask = mask, corporate = corporate}; -- add this assembled name to our names list | ||
end | end | ||
return names, etal; -- all done, return our list of names | return names, etal; -- all done, return our list of names | ||
| Line 1,860: | Line 1,978: | ||
Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or | Select one of |authors=, |authorn= / |lastn / firstn=, or |vauthors= as the source of the author name list or | ||
select one of | select one of |editorn= / editor-lastn= / |editor-firstn= or |veditors= as the source of the editor name list. | ||
Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest | Only one of these appropriate three will be used. The hierarchy is: |authorn= (and aliases) highest and |authors= lowest; | ||
|editorn= (and aliases) highest and |veditors= lowest (support for |editors= withdrawn) | |||
When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second | When looking for |authorn= / |editorn= parameters, test |xxxxor1= and |xxxxor2= (and all of their aliases); stops after the second | ||
| Line 1,871: | Line 1,989: | ||
Emits an error message when more than one xxxxor name source is provided. | Emits an error message when more than one xxxxor name source is provided. | ||
In this function, vxxxxors = vauthors or veditors; xxxxors = authors | In this function, vxxxxors = vauthors or veditors; xxxxors = authors as appropriate. | ||
]] | ]] | ||
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; | local lastfirst = false; | ||
if select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice | if utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 1 ) or -- do this twice in case we have a |first1= without a |last1=; this ... | ||
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors= | utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 1 ) or -- ... also catches the case where |first= is used with |vauthors= | ||
select_one( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or | utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'none', 2 ) or | ||
select_one( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then | utilities.select_one ( args, cfg.aliases[list_name .. '-First'], 'none', 2 ) then | ||
lastfirst=true; | lastfirst = true; | ||
end | end | ||
if (is_set (vxxxxors) and true == lastfirst) or | if (utilities.is_set (vxxxxors) and true == lastfirst) or -- these are the three error conditions | ||
(is_set (vxxxxors) and is_set (xxxxors)) or | (utilities.is_set (vxxxxors) and utilities.is_set (xxxxors)) or | ||
(true == lastfirst and is_set (xxxxors)) then | (true == lastfirst and utilities.is_set (xxxxors)) then | ||
local err_name; | local err_name; | ||
if 'AuthorList' == list_name then -- figure out which name should be used in error message | if 'AuthorList' == list_name then -- figure out which name should be used in error message | ||
| Line 1,893: | Line 2,011: | ||
err_name = 'editor'; | err_name = 'editor'; | ||
end | end | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', | ||
{err_name .. '-name-list parameters'}, true ) } ); -- add error message | {err_name .. '-name-list parameters'}, true ) } ); -- add error message | ||
end | end | ||
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use | 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 utilities.is_set (vxxxxors) then return 2 end; | ||
if is_set (xxxxors) then return 3 end; | if utilities.is_set (xxxxors) then return 3 end; | ||
return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last | return 1; -- no authors so return 1; this allows missing author name test to run in case there is a first without last | ||
end | end | ||
| Line 1,907: | Line 2,025: | ||
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, live, dead, etc.). When the parameter value has not been assigned a value (missing | ||
in the source template) the function returns | or empty in the source template) the function returns the value specified by ret_val. If the parameter value is one | ||
of the list of allowed values returns the translated value; else, emits an error message and returns the value | |||
specified by ret_val. | |||
]] | ]] | ||
local function is_valid_parameter_value (value, name, possible) | local function is_valid_parameter_value (value, name, possible, ret_val) | ||
if not is_set (value) then | if not utilities.is_set (value) then | ||
return | return ret_val; -- an empty parameter is ok | ||
elseif in_array (value, possible) then | elseif utilities.in_array (value, possible) then | ||
return | return cfg.keywords_xlate[value]; -- return translation of parameter keyword | ||
else | else | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_invalid_param_val', {name, value}, true ) } ); -- not an allowed value so add error message | ||
return | return ret_val; | ||
end | end | ||
end | end | ||
| Line 1,935: | Line 2,054: | ||
local function terminate_name_list (name_list, sepc) | local function terminate_name_list (name_list, sepc) | ||
if (string.sub (name_list,-3,-1) == sepc .. '. ') then | if (string.sub (name_list, -3, -1) == sepc .. '. ') then -- if already properly terminated | ||
return name_list; -- just return the name list | 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 | 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 | ||
return name_list .. sepc .. ' '; -- otherwise | return name_list .. sepc .. ' '; -- otherwise terminate the name list | ||
end | end | ||
end | end | ||
| Line 1,953: | Line 2,072: | ||
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) | local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) | ||
if not is_set (volume) and not is_set (issue) then | if not utilities.is_set (volume) and not utilities.is_set (issue) then | ||
return ''; | return ''; | ||
end | end | ||
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then | if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then | ||
if is_set (volume) and is_set (issue) then | if utilities.is_set (volume) and utilities.is_set (issue) then | ||
return wrap_msg ('vol-no', {sepc, volume, issue}, lower); | return wrap_msg ('vol-no', {sepc, hyphen_to_dash (volume), issue}, lower); | ||
elseif is_set (volume) then | elseif utilities.is_set (volume) then | ||
return wrap_msg ('vol', {sepc, volume}, lower); | return wrap_msg ('vol', {sepc, hyphen_to_dash (volume)}, lower); | ||
else | else | ||
return wrap_msg ('issue', {sepc, issue}, lower); | return wrap_msg ('issue', {sepc, issue}, lower); | ||
end | end | ||
end | |||
if 'podcast' == cite_class and utilities.is_set (issue) then | |||
return wrap_msg ('issue', {sepc, issue}, lower); | |||
end | end | ||
local vol = ''; -- here for all cites except magazine | local vol = ''; -- here for all cites except magazine | ||
if is_set (volume) then | if utilities.is_set (volume) then | ||
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')then -- volume value is all digits or all uppercase | if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals | ||
vol = substitute (cfg.presentation['vol-bold'], {sepc, | vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face | ||
elseif (4 < mw.ustring.len(volume)) then -- not all digits or | elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters | ||
vol = substitute (cfg.messages['j-vol'], {sepc, volume}); | vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)}); -- not bold | ||
add_prop_cat ('long_vol'); | utilities.add_prop_cat ('long_vol'); | ||
else -- four or less characters | else -- four or less characters | ||
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold | vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold | ||
end | end | ||
end | end | ||
if is_set (issue) then | if utilities.is_set (issue) then | ||
return vol .. substitute (cfg.messages['j-issue'], issue); | return vol .. utilities.substitute (cfg.messages['j-issue'], issue); | ||
end | end | ||
return vol; | return vol; | ||
| Line 1,998: | Line 2,121: | ||
local function format_pages_sheets (page, pages, sheet, sheets, cite_class, origin, sepc, nopp, lower) | 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 'map' == cite_class then -- only cite map supports sheet(s) as in-source locators | ||
if is_set (sheet) then | if utilities.is_set (sheet) then | ||
if 'journal' == origin then | if 'journal' == origin then | ||
return '', '', wrap_msg ('j-sheet', sheet, lower), ''; | return '', '', wrap_msg ('j-sheet', sheet, lower), ''; | ||
| Line 2,004: | Line 2,127: | ||
return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; | return '', '', wrap_msg ('sheet', {sepc, sheet}, lower), ''; | ||
end | end | ||
elseif is_set (sheets) then | elseif utilities.is_set (sheets) then | ||
if 'journal' == origin then | if 'journal' == origin then | ||
return '', '', '', wrap_msg ('j-sheets', sheets, lower); | return '', '', '', wrap_msg ('j-sheets', sheets, lower); | ||
| Line 2,013: | Line 2,136: | ||
end | end | ||
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); | local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); | ||
if is_set (page) then | if utilities.is_set (page) then | ||
if is_journal then | if is_journal then | ||
return substitute (cfg.messages['j-page(s)'], page), '', '', ''; | return utilities.substitute (cfg.messages['j-page(s)'], page), '', '', ''; | ||
elseif not nopp then | elseif not nopp then | ||
return substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; | return utilities.substitute (cfg.messages['p-prefix'], {sepc, page}), '', '', ''; | ||
else | else | ||
return substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; | return utilities.substitute (cfg.messages['nopp'], {sepc, page}), '', '', ''; | ||
end | end | ||
elseif is_set(pages) then | elseif utilities.is_set (pages) then | ||
if is_journal then | if is_journal then | ||
return substitute (cfg.messages['j-page(s)'], pages), '', '', ''; | return utilities.substitute (cfg.messages['j-page(s)'], pages), '', '', ''; | ||
elseif tonumber(pages) ~= nil and not nopp then -- if pages is only digits, assume a single page number | 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 '', utilities.substitute (cfg.messages['p-prefix'], {sepc, pages}), '', ''; | ||
elseif not nopp then | elseif not nopp then | ||
return '', substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; | return '', utilities.substitute (cfg.messages['pp-prefix'], {sepc, pages}), '', ''; | ||
else | else | ||
return '', substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; | return '', utilities.substitute (cfg.messages['nopp'], {sepc, pages}), '', ''; | ||
end | end | ||
end | end | ||
| Line 2,043: | Line 2,166: | ||
returns one of the in-source locators: page, pages, or at. | returns one of the in-source locators: page, pages, or at. | ||
If any of these are interwiki links to | If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text | ||
for use in COinS. This COinS thing is done because here we convert an interwiki link to | for use in COinS. This COinS thing is done because here we convert an interwiki-link to an external link and | ||
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? | add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? | ||
| Line 2,055: | Line 2,178: | ||
local function insource_loc_get (page, pages, at) | local function insource_loc_get (page, pages, at) | ||
local ws_url, ws_label, coins_pages, L; -- for | local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?) | ||
if is_set (page) then | if utilities.is_set (page) then | ||
if is_set (pages) or is_set(at) then | if utilities.is_set (pages) or utilities.is_set (at) then | ||
pages = ''; -- unset the others | pages = ''; -- unset the others | ||
at = ''; | at = ''; | ||
end | end | ||
extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p. | extra_text_in_page_check (page); -- add this page to maint cat if |page= value begins with what looks like p., pp., etc. | ||
ws_url, ws_label, L = wikisource_url_make (page); -- make ws | ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label | ||
if ws_url then | 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 = 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}); | page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page}); | ||
coins_pages = ws_label; | coins_pages = ws_label; | ||
end | end | ||
elseif is_set (pages) then | elseif utilities.is_set (pages) then | ||
if is_set (at) then | if utilities.is_set (at) then | ||
at = ''; -- unset | at = ''; -- unset | ||
end | end | ||
extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p. | extra_text_in_page_check (pages); -- add this page to maint cat if |pages= value begins with what looks like p., pp., etc. | ||
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws | ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label | ||
if ws_url then | 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 = 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}); | pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages}); | ||
coins_pages = ws_label; | coins_pages = ws_label; | ||
end | end | ||
elseif is_set (at) then | elseif utilities.is_set (at) then | ||
ws_url, ws_label, L = wikisource_url_make (at); -- make ws | ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label | ||
if ws_url then | 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 = 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}); | at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at}); | ||
coins_pages = ws_label; | coins_pages = ws_label; | ||
end | end | ||
| Line 2,093: | Line 2,216: | ||
return page, pages, at, coins_pages; | return page, pages, at, coins_pages; | ||
end | end | ||
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- | --[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- | ||
Check archive.org | Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the | ||
save snapshot | 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 | archive.org saves a snapshot of the target page in the URL. That is something that Wikipedia should not allow | ||
unwitting readers to do. | unwitting readers to do. | ||
When the archive.org | 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. | 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 | 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-date= and an error message when: | ||
|archive-url= holds an archive.org save command | |archive-url= holds an archive.org save command URL | ||
|archive-url= is an archive.org | |archive-url= is an archive.org URL that does not have a complete timestamp (YYYYMMDDhhmmss 14 digits) in the | ||
correct place | correct place | ||
otherwise returns |archive-url= and |archive-date= | otherwise returns |archive-url= and |archive-date= | ||
There are two mostly compatible archive.org | There are two mostly compatible archive.org URLs: | ||
//web.archive.org/<timestamp>... -- the old form | //web.archive.org/<timestamp>... -- the old form | ||
//web.archive.org/web/<timestamp>... -- the new form | //web.archive.org/web/<timestamp>... -- the new form | ||
| Line 2,121: | Line 2,243: | ||
we don't check for these specific flags but we do check the form. | 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 | This function supports a preview mode. When the article is rendered in preview mode, this function may return a modified | ||
archive | archive URL: | ||
for save command errors, return undated wildcard (/*/) | for save command errors, return undated wildcard (/*/) | ||
for timestamp errors when the timestamp has a wildcard, return the | 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*/) | for timestamp errors when the timestamp does not have a wildcard, return with timestamp limited to six digits plus wildcard (/yyyymm*/) | ||
| Line 2,131: | Line 2,253: | ||
local function archive_url_check (url, date) | local function archive_url_check (url, date) | ||
local err_msg = ''; -- start with the error message empty | local err_msg = ''; -- start with the error message empty | ||
local path, timestamp, flag; -- portions of the archive. | local path, timestamp, flag; -- portions of the archive.org URL | ||
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine | 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 | return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate | ||
end | end | ||
if url:match('//web%.archive%.org/save/') then -- if a save command | 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 = | err_msg = cfg.err_msg_supl.save; | ||
url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL | url = url:gsub ('(//web%.archive%.org)/save/', '%1/*/', 1); -- for preview mode: modify ArchiveURL | ||
elseif url:match('//liveweb%.archive%.org/') then | elseif url:match('//liveweb%.archive%.org/') then | ||
err_msg = | err_msg = cfg.err_msg_supl.liveweb; | ||
else | else | ||
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the | 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 | if not utilities.is_set (timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here | ||
err_msg = | err_msg = cfg.err_msg_supl.timestamp; | ||
if '*' ~= flag then | 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) | url=url:gsub ('(//web%.archive%.org/[^%d]*%d?%d?%d?%d?%d?%d?)[^/]*', '%1*', 1) -- for preview, modify ts to be yearmo* max (0-6 digits plus splat) | ||
end | end | ||
elseif is_set(path) and 'web/' ~= path then | elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element | ||
err_msg = | err_msg = cfg.err_msg_supl.path; | ||
elseif is_set (flag) and not is_set (path) then | elseif utilities.is_set (flag) and not utilities.is_set (path) then -- flag not allowed with the old form URL (without the 'web/' path element) | ||
err_msg = | err_msg = cfg.err_msg_supl.flag; | ||
elseif is_set (flag) and not flag:match ('%a%a_') then | elseif utilities.is_set (flag) and not flag:match ('%a%a_') then -- flag if present must be two alpha characters and underscore (requires 'web/' path element) | ||
err_msg = | err_msg = cfg.err_msg_supl.flag; | ||
else | else | ||
return url, date; -- return | return url, date; -- return ArchiveURL and ArchiveDate | ||
end | end | ||
end | end | ||
-- if here, something not right so | -- if here, something not right so | ||
table.insert( z.message_tail, { | table.insert( z.message_tail, { utilities.set_message ( 'err_archive_url', {err_msg}, true ) } ); -- add error message and | ||
if is_set (Frame:preprocess('{{REVISIONID}}')) then | if utilities.is_set (Frame:preprocess('{{REVISIONID}}')) then | ||
return '', ''; -- return empty strings for | return '', ''; -- return empty strings for ArchiveURL and ArchiveDate | ||
else | else | ||
return url, date; -- preview mode so return | return url, date; -- preview mode so return ArchiveURL and ArchiveDate | ||
end | end | ||
end | end | ||
--[[--------------------------< C | --[[--------------------------< P L A C E _ C H E C K >-------------------------------------------------------- | ||
check |place=, |publication-place=, |location= to see if these params include digits. This function added because | |||
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that) | |||
returns the original parameter value without modification; added maint cat when parameter value contains digits | |||
]] | ]] | ||
local function | local function place_check (param_val) | ||
-- | if not utilities.is_set (param_val) then -- parameter empty or omitted | ||
return param_val; -- return that empty state | |||
end | |||
if mw.ustring.find (param_val, '%d') then -- not empty, are there digits in the parameter value | |||
utilities.set_message ('maint_location'); -- yep, add maint cat | |||
end | |||
return param_val; -- and done | |||
end | |||
--[[--------------------------< I S _ G E N E R I C _ T I T L E >---------------------------------------------- | |||
compares |title= value against list of known generic title patterns. Returns true when pattern matches; nil else | |||
the k/v pairs in 'generic_titles' each contain two tables, one for English and one for another 'local' language | |||
Each of those tables contain another table that holds the string or pattern (whole title or title fragment) in | |||
index [1]. index [2] is a Boolean that tells string.find() or mw.ustring.find() to do plain-text search (true) | |||
or a pattern search (false). The intent of all this complexity is to make these searches as fast as possible so | |||
that we don't run out of processing time on very large articles. | |||
]] | |||
do | local function is_generic_title (title) | ||
title = mw.ustring.lower(title); -- switch title to lower case | |||
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments | |||
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then | |||
elseif | return true; -- found English generic title so done | ||
elseif generic_title['local'] then -- to keep work load down, generic_title['local'] should be nil except when there is a local version of the generic title | |||
if mw.ustring.find (title, generic_title['local'][1], 1, generic_title['local'][2]) then -- mw.ustring() because might not be Latin script | |||
return true; -- found local generic title so done | |||
end | end | ||
end | end | ||
end | end | ||
end | |||
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >---------------------------------------------- | |||
compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else | |||
]] | |||
local function is_archived_copy (title) | |||
title = mw.ustring.lower(title); -- switch title to lower case | |||
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy' | |||
return true; | |||
elseif cfg.special_case_translation.archived_copy['local'] then | |||
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script | |||
return true; | |||
elseif | |||
end | end | ||
end | end | ||
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 | local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], ''); | ||
local | local author_etal; | ||
local | local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= | ||
local Authors; | |||
local | |||
local | local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], ''); | ||
local | local Collaboration = A['Collaboration']; | ||
do -- to limit scope of selected | |||
local selected = select_author_editor_source (A['Vauthors'], A['Authors'], args, 'AuthorList'); | |||
if 1 == selected then | |||
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= | |||
elseif 2 == selected then | |||
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be | |||
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= | |||
elseif 3 == selected then | |||
Authors = A['Authors']; -- use content of |authors= | |||
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors= | |||
utilities.set_message ('maint_authors'); -- because use of this parameter is discouraged; what to do about the aliases is a TODO: | |||
end | end | ||
end | end | ||
if utilities.is_set (Collaboration) then | |||
author_etal = true; -- so that |display-authors=etal not required | |||
end | |||
end | |||
local | local Others = A['Others']; | ||
local | local editor_etal; | ||
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= | |||
local Editors; | |||
local | do -- to limit scope of selected | ||
local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn | |||
if 1 == selected then | |||
e, editor_etal = extract_names (args, 'EditorList'); -- fetch editor list from |editorn= / |editor-lastn= / |editor-firstn=, |editor-linkn=, and |editor-maskn= | |||
elseif 2 == selected then | |||
NameListStyle = 'vanc'; -- override whatever |name-list-style= might be | |||
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= | |||
if | |||
end | end | ||
end | end | ||
local | local translator_etal; | ||
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 | local interviewer_etal; | ||
local | local interviewers_list = {}; | ||
local Interviewers; -- used later | |||
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters | |||
local | |||
local contributor_etal; | |||
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs | |||
local Contributors; -- assembled contributors name list | |||
local | local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases | ||
if | local Chapter_origin = A:ORIGIN ('Chapter'); | ||
local Contribution; -- because contribution is required for contributor(s) | |||
if 'contribution' == A:ORIGIN ('Chapter') then | |||
Contribution = A['Chapter']; -- get the name of the contribution | |||
end | end | ||
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites | |||
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= | |||
if is_set ( | if 0 < #c then | ||
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution= | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'contribution')}); -- add missing contribution error message | |||
c = {}; -- blank the contributors' table; it is used as a flag later | |||
end | |||
if 0 == #a then -- |contributor= requires |author= | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_missing_required_param', 'author')}); -- add missing author error message | |||
c = {}; -- blank the contributors' table; it is used as a flag later | |||
end | |||
end | end | ||
if | else -- if not a book cite | ||
table.insert( z.message_tail, { | if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters? | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_contributor_ignored')}); -- add contributor ignored error message | |||
end | end | ||
Contribution = nil; -- unset | |||
end | |||
if utilities.is_set (Others) then | |||
if 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= | |||
utilities.set_message ('maint_others'); | |||
if | |||
end | end | ||
end | |||
local | local Year = A['Year']; | ||
local PublicationDate = A['PublicationDate']; | |||
local OrigDate = A['OrigDate']; | |||
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 TransTitle_origin = A:ORIGIN ('TransTitle'); | |||
local TitleNote = A['TitleNote']; | |||
local TitleLink = A['TitleLink']; | |||
local | local auto_select = ''; -- default is auto | ||
local | local accept_link; | ||
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup | |||
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords | |||
auto_select = TitleLink; -- remember selection for later | |||
TitleLink = ''; -- treat as if |title-link= would have been empty | |||
end | |||
TitleLink = link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wiki-markup in |title-link= or wiki-markup in |title= when |title-link= is set | |||
local | local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used | ||
if 'map' == config.CitationClass and 'section' == A:ORIGIN ('Chapter') then | |||
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}} | |||
Chapter = ''; -- unset for now; will be reset later from |map= if present | |||
end | end | ||
local | local ScriptChapter = A['ScriptChapter']; | ||
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter'); | |||
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode | |||
local TransChapter = A['TransChapter']; | |||
local | local TransChapter_origin = A:ORIGIN ('TransChapter'); | ||
local TitleType = A['TitleType']; | |||
local Degree = A['Degree']; | |||
local Docket = A['Docket']; | |||
local ArchiveFormat = A['ArchiveFormat']; | |||
local | local ArchiveDate; | ||
local ArchiveURL; | |||
local | ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) | ||
local | |||
local | local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); | ||
local | |||
local | local URL = A['URL'] | ||
local | local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL | ||
local | local ChapterURL = A['ChapterURL']; | ||
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL | |||
local ConferenceFormat = A['ConferenceFormat']; | |||
local ConferenceURL = A['ConferenceURL']; | |||
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL | |||
local | local Periodical = A['Periodical']; | ||
local Periodical_origin = ''; | |||
if utilities.is_set (Periodical) then | |||
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter | |||
local i; | |||
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe 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, {utilities.set_message ('err_apostrophe_markup', {Periodical_origin}, true)}); | |||
end | end | ||
end | |||
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} | |||
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error | |||
table.insert( z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}, true )}); | |||
end | end | ||
Periodical = A ['MailingList']; -- error or no, set Periodical to |mailinglist= value because this template is {{cite mailing list}} | |||
Periodical_origin = A:ORIGIN('MailingList'); | |||
end | end | ||
local | local ScriptPeriodical = A['ScriptPeriodical']; | ||
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); | |||
-- | -- web and news not tested for now because of | ||
if not is_set ( | -- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors? | ||
if not (utilities.is_set (Periodical) or utilities.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, {utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}, true)}); | |||
end | end | ||
end | end | ||
local TransPeriodical = A['TransPeriodical']; | |||
local TransPeriodical_origin = A:ORIGIN ('TransPeriodical'); | |||
local | local Series = A['Series']; | ||
Page | local Volume; | ||
local Issue; | |||
local Page; | |||
local Pages; | |||
local At; | |||
if 'citation' == config.CitationClass then | |||
if utilities.is_set (Periodical) then | |||
if not utilities.in_array (Periodical_origin, {'website', 'mailinglist'}) then -- {{citation}} does not render volume for these 'periodicals' | |||
Volume = A['Volume']; -- but does for all other 'periodicals' | |||
end | |||
elseif utilities.is_set (ScriptPeriodical) then | |||
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website= | |||
Volume = A['Volume']; -- but does for all other 'periodicals' | |||
end | |||
else | |||
Volume = A['Volume']; -- and does for non-'periodical' cites | |||
end | |||
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings | |||
Volume = A['Volume']; | |||
end | |||
if 'citation' == config.CitationClass then | |||
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals' | |||
utilities.is_set (ScriptPeriodical) and utilities.in_array (ScriptPeriodical_origin, {'script-journal', 'script-magazine', 'script-newspaper', 'script-periodical', 'script-work'}) then -- and these 'script-periodicals' | |||
Issue = hyphen_to_dash (A['Issue']); | |||
end | |||
elseif utilities.in_array (config.CitationClass, cfg.templates_using_issue) then -- conference & map books do not support issue; {{citation}} listed here because included in settings table | |||
if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then | |||
Issue = hyphen_to_dash (A['Issue']); | |||
end | |||
end | end | ||
if not | local Position = ''; | ||
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then | |||
Page = A['Page']; | |||
Pages = hyphen_to_dash (A['Pages']); | |||
At = A['At']; | |||
end | end | ||
local QuotePage = A['QuotePage']; | |||
local QuotePages = hyphen_to_dash (A['QuotePages']); | |||
local Edition = A['Edition']; | |||
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace')); | |||
local Place = place_check (A['Place'], A:ORIGIN('Place')); | |||
local PublisherName = A['PublisherName']; | |||
local PublisherName_origin = A:ORIGIN('PublisherName'); | |||
if utilities.is_set (PublisherName) then | |||
local i = 0; | |||
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized | |||
if i then -- non-zero when markup was stripped so emit an error message | |||
table.insert( z.message_tail, {utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}, true)}); | |||
end | |||
end | |||
local | local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup? | ||
local Newsgroup_origin = A:ORIGIN('Newsgroup'); | |||
if | if 'newsgroup' == config.CitationClass then | ||
if is_set ( | if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup | ||
local error_text, error_state = utilities.set_message ('err_parameter_ignored', {PublisherName_origin}, true); | |||
if utilities.is_set (error_text) then | |||
table.insert( z.message_tail, {error_text, error_state} ); | |||
end | |||
end | |||
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS | |||
end | end | ||
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); | |||
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then | |||
UrlAccess = nil; | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } ); | |||
end | |||
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); | |||
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then | |||
ChapterUrlAccess = nil; | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}, true ) } ); | |||
end | end | ||
- | local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil); | ||
if ( | if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then | ||
MapUrlAccess = nil; | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'map-url'}, true ) } ); | |||
end | end | ||
local Via = A['Via']; | |||
local AccessDate = A['AccessDate']; | |||
local Agency = A['Agency']; | |||
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 Embargo = A['Embargo']; | |||
local Class = A['Class']; -- arxiv class identifier | |||
local Quote = A['Quote']; | |||
local | local ScriptQuote = A['ScriptQuote']; | ||
local | local TransQuote = A['TransQuote']; | ||
local LayFormat = A['LayFormat']; | |||
local | local LayURL = A['LayURL']; | ||
local LaySource = A['LaySource']; | |||
local Transcript = A['Transcript']; | |||
local TranscriptFormat = A['TranscriptFormat']; | |||
local TranscriptURL = A['TranscriptURL'] | |||
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL | |||
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil); | |||
-- 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 | |||
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], ''); | |||
if not utilities.is_set (DF) then | |||
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template | |||
end | |||
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma | |||
local PostScript; | |||
local Ref = A['Ref']; | |||
if 'harv' == Ref then | |||
utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value | |||
elseif not utilities.is_set (Ref) then | |||
Ref = 'harv'; -- set as default when not set externally | |||
end | |||
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 utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page | |||
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then | |||
no_tracking_cats = "true"; -- set no_tracking_cats | |||
end | |||
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 | |||
end | |||
end | end | ||
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) | |||
utilities.select_one (args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'err_redundant_parameters'); -- this is a dummy call simply to get the error message and category | |||
local coins_pages; | |||
Page, Pages, At, coins_pages = insource_loc_get (Page, Pages, At); | |||
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil); | |||
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different | |||
utilities.add_prop_cat ('location test'); -- add property cat to evaluate how often PublicationPlace and Place are used together | |||
if PublicationPlace == Place then | |||
Place = ''; -- unset; don't need both if they are the same | |||
end | end | ||
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ... | |||
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place | |||
end | end | ||
-- | if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same | ||
--[[ | |||
Parameter remapping for cite encyclopedia: | |||
When the citation has these parameters: | |||
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title= | |||
|encyclopedia= and |article= then map |encyclopedia= to |title= | |||
|trans-title= maps to |trans-chapter= when |title= is re-mapped | |||
|url= maps to |chapter-url= when |title= is remapped | |||
All other combinations of |encyclopedia=, |title=, and |article= are not modified | |||
]] | |||
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS | |||
if | if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}} | ||
if 'encyclopaedia' ~= config.CitationClass and 'citation' ~= config.CitationClass then | |||
table.insert (z.message_tail, {utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}, true)}); | |||
Encyclopedia = nil; -- unset because not supported by this template | |||
end | end | ||
end | end | ||
if | if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then | ||
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error | |||
table.insert (z.message_tail, {utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}, true )}); | |||
end | |||
if utilities.is_set (Encyclopedia) then | |||
Periodical = Encyclopedia; -- error or no, set Periodical to Encyclopedia; allow periodical without encyclopedia | |||
Periodical_origin = A:ORIGIN ('Encyclopedia'); | |||
end | |||
if utilities.is_set (Periodical) then -- Periodical is set when |encyclopedia= is set | |||
if utilities.is_set (Title) or utilities.is_set (ScriptTitle) then | |||
if not utilities.is_set (Chapter) then | |||
Chapter = Title; -- |encyclopedia= and |title= are set so map |title= to |article= and |encyclopedia= to |title= | |||
ScriptChapter = ScriptTitle; | |||
ScriptChapter_origin = A:ORIGIN('ScriptTitle') | |||
TransChapter = TransTitle; | |||
ChapterURL = URL; | |||
ChapterURL_origin = A:ORIGIN('URL') | |||
ChapterUrlAccess = UrlAccess; | |||
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then | |||
Chapter = utilities.make_wikilink (TitleLink, Chapter); | |||
end | |||
Title = Periodical; | |||
ChapterFormat = Format; | |||
Periodical = ''; -- redundant so unset | |||
TransTitle = ''; | |||
URL = ''; | |||
Format = ''; | |||
TitleLink = ''; | |||
ScriptTitle = ''; | |||
end | end | ||
elseif utilities.is_set (Chapter) then -- |title= not set | |||
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= | |||
Periodical = ''; -- redundant so unset | |||
end | end | ||
end | end | ||
end | |||
-- special case for cite techreport. | |||
if (config.CitationClass == "techreport") then -- special case for cite techreport | |||
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' | |||
if not utilities.is_set (ID) then -- can we use ID for the "number"? | |||
ID = A['Number']; -- yes, use it | |||
else -- ID has a value so emit error message | |||
table.insert( z.message_tail, { utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}, true )}); | |||
end | end | ||
end | |||
end | |||
-- Account for the oddity that is {{cite conference}}, before generation of COinS data. | |||
if 'conference' == config.CitationClass then | |||
if utilities.is_set (BookTitle) then | |||
Chapter = Title; | |||
Chapter_origin = 'title'; | |||
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated | |||
ChapterURL = URL; | |||
ChapterUrlAccess = UrlAccess; | |||
ChapterURL_origin = URL_origin; | |||
URL_origin = ''; | |||
ChapterFormat = Format; | |||
TransChapter = TransTitle; | |||
TransChapter_origin = TransTitle_origin; | |||
Title = BookTitle; | |||
Format = ''; | |||
-- TitleLink = ''; | |||
TransTitle = ''; | |||
URL = ''; | |||
end | end | ||
elseif 'speech' ~= config.CitationClass then | |||
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 ''; | |||
if config.CitationClass == " | local Sheets = A['Sheets'] or ''; | ||
if | if config.CitationClass == "map" then | ||
if utilities.is_set (Chapter) then | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}, true ) } ); -- add error message | |||
end | |||
Chapter = A['Map']; | |||
Chapter_origin = A:ORIGIN('Map'); | |||
ChapterURL = A['MapURL']; | |||
ChapterURL_origin = A:ORIGIN('MapURL'); | |||
TransChapter = A['TransMap']; | |||
ScriptChapter = A['ScriptMap'] | |||
ScriptChapter_origin = A:ORIGIN('ScriptMap') | |||
ChapterUrlAccess = MapUrlAccess; | |||
ChapterFormat = A['MapFormat']; | |||
Cartography = A['Cartography']; | |||
if utilities.is_set ( Cartography ) then | |||
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); | |||
end | |||
Scale = A['Scale']; | |||
if utilities.is_set ( Scale ) then | |||
Scale = sepc .. " " .. Scale; | |||
end | end | ||
end | end | ||
-- | -- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. | ||
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then | |||
local SeriesLink = A['SeriesLink']; | |||
SeriesLink = link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for wiki-markup in |series-link= or wiki-markup in |series= when |series-link= is set | |||
local Network = A['Network']; | |||
[' | local Station = A['Station']; | ||
local s, n = {}, {}; | |||
-- do common parameters first | |||
[ | if utilities.is_set (Network) then table.insert(n, Network); end | ||
if utilities.is_set (Station) then table.insert(n, Station); end | |||
ID = table.concat(n, sepc .. ' '); | |||
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} | |||
local Season = A['Season']; | |||
local SeriesNumber = A['SeriesNumber']; | |||
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}, true ) } ); -- add error message | |||
SeriesNumber = ''; -- unset; prefer |season= over |seriesno= | |||
end | |||
-- assemble a table of parts concatenated later into Series | |||
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end | |||
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end | |||
if utilities.is_set (Issue) then table.insert(s, wrap_msg ('episode', Issue, use_lowercase)); end | |||
Issue = ''; -- unset because this is not a unique parameter | |||
Chapter = Title; -- promote title parameters to chapter | |||
ScriptChapter = ScriptTitle; | |||
ScriptChapter_origin = A:ORIGIN('ScriptTitle'); | |||
ChapterLink = TitleLink; -- alias |episode-link= | |||
TransChapter = TransTitle; | |||
ChapterURL = URL; | |||
ChapterUrlAccess = UrlAccess; | |||
ChapterURL_origin = 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 utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL | |||
Chapter = utilities.make_wikilink (ChapterLink, Chapter); | |||
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode; | |||
Series = utilities.make_wikilink (ChapterLink, Series); | |||
end | |||
URL = ''; -- unset | |||
TransTitle = ''; | |||
ScriptTitle = ''; | |||
else -- now oddities that are cite serial | |||
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of cite serial | |||
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? | |||
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then | |||
Series = utilities.make_wikilink (SeriesLink, Series); | |||
end | |||
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized | |||
end | |||
end | end | ||
-- end of {{cite episode}} stuff | |||
-- | -- handle type parameter for those CS1 citations that have default values | ||
if | if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then | ||
if is_set ( | TitleType = set_titletype (config.CitationClass, TitleType); | ||
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis | |||
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower(); | |||
end | end | ||
end | end | ||
-- | if utilities.is_set (TitleType) then -- if type parameter is specified | ||
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses | |||
-- | -- TODO: Hack on TitleType to fix bunched parentheses problem | ||
end | |||
-- legacy: 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 utilities.is_set (Date) then | |||
Date = Year; -- promote Year to Date | |||
Year = nil; -- make nil so Year as empty string isn't used for CITEREF | |||
if not utilities.is_set (Date) and utilities.is_set (PublicationDate) then -- use PublicationDate when |date= and |year= are not set | |||
Date = PublicationDate; -- promote PublicationDate to Date | |||
PublicationDate = ''; -- unset, no longer needed | |||
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter | |||
else | |||
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter | |||
end | |||
else | |||
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging | |||
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, date_parameters_list, mismatch | |||
local error_message = ''; | |||
-- AirDate has been promoted to Date so not necessary to check it | |||
local date_parameters_list = { | |||
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')}, | |||
['archive-date'] = {val = ArchiveDate, name = A:ORIGIN ('ArchiveDate')}, | |||
['date'] = {val = Date, name = Date_origin}, | |||
['doi-broken-date'] = {val = DoiBroken, name = A:ORIGIN ('DoiBroken')}, | |||
['pmc-embargo-date'] = {val = Embargo, name = A:ORIGIN ('Embargo')}, | |||
['lay-date'] = {val = LayDate, name = A:ORIGIN ('LayDate')}, | |||
['publication-date'] = {val = PublicationDate, name = A:ORIGIN ('PublicationDate')}, | |||
['year'] = {val = Year, name = A:ORIGIN ('Year')}, | |||
}; | |||
local error_list = {}; | |||
anchor_year, Embargo = validation.dates(date_parameters_list, COinS_date, error_list); | |||
-- start temporary Julian / Gregorian calendar uncertainty categorization | |||
if COinS_date.inter_cal_cat then | |||
utilities.add_prop_cat ('jul_greg_uncertainty'); | |||
end | end | ||
-- end temporary Julian / Gregorian calendar uncertainty categorization | |||
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed; | |||
local mismatch = validation.year_date_check (Year, Date); | |||
if 0 == mismatch then -- |year= does not match a year-value in |date= | |||
table.insert (error_list, '<code class="cs1-code">|year= / |date= mismatch</code>'); | |||
elseif 1 == mismatch then -- |year= matches year-value in |date= | |||
utilities.set_message ('maint_date_year'); -- add a maint cat | |||
end | |||
end | end | ||
if 0 == #error_list then -- error free dates only; 0 when error_list is empty | |||
local modified = false; -- flag | |||
if utilities.is_set (DF) then -- if we need to reformat dates | |||
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate | |||
end | |||
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate | |||
modified = true; | |||
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category | |||
end | |||
-- for those wikis that can and want to have English date names translated to the local language, | |||
-- uncomment the next three lines. Not supported by en.wiki (for obvious reasons) | |||
-- set validation.date_name_xlate() second argument to true to translate English digits to local digits (will translate ymd dates) | |||
-- if validation.date_name_xlate (date_parameters_list, false) then | |||
-- modified = true; | |||
-- end | |||
if | if modified then -- if the date_parameters_list values were modified | ||
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values | |||
ArchiveDate = date_parameters_list['archive-date'].val; | |||
Date = date_parameters_list['date'].val; | |||
DoiBroken = date_parameters_list['doi-broken-date'].val; | |||
LayDate = date_parameters_list['lay-date'].val; | |||
PublicationDate = date_parameters_list['publication-date'].val; | |||
end | end | ||
else | |||
table.insert (z.message_tail, {utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}, true)}); -- add this error message | |||
end | end | ||
end -- end of do | |||
local ID_list = {}; -- sequence table of rendered identifiers | |||
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key | |||
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = ASINTLD, Embargo = Embargo, Class = Class}); | |||
if utilities.is_set (DoiBroken) and not ID_list_coins['DOI'] then | |||
table.insert (z.message_tail, {utilities.set_message ('err_doibroken_missing_doi', A:ORIGIN('DoiBroken'))}); | |||
end | end | ||
-- | -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data. | ||
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then | |||
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates | |||
table.insert (z.message_tail, {utilities.set_message ('err_' .. config.CitationClass .. '_missing', {}, true)}); -- add error message | |||
end | |||
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass]; | |||
end | end | ||
if not is_set(URL) | -- Link the title of the work if no |url= was provided, but we have a |pmc= or a |doi= with |doi-access=free | ||
if config.CitationClass == "journal" and not utilities.is_set (URL) and not utilities.is_set (TitleLink) and not utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) then -- TODO: remove 'none' once existing citations have been switched to 'off', so 'none' can be used as token for "no title" instead | |||
if 'none' ~= cfg.keywords_xlate[auto_select] then -- if auto-linking not disabled | |||
if identifiers.auto_link_urls[auto_select] then -- manual selection | |||
URL = identifiers.auto_link_urls[auto_select]; -- set URL to be the same as identifier's external link | |||
URL_origin = cfg.id_handlers[auto_select:upper()].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title= | |||
if is_set( | elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC | ||
table.insert( z.message_tail, { | URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed | ||
AccessDate = ''; | URL_origin = cfg.id_handlers['PMC'].parameters[1]; -- set URL_origin to parameter name for use in error message if citation is missing a |title= | ||
elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI | |||
URL = identifiers.auto_link_urls['doi']; | |||
URL_origin = cfg.id_handlers['DOI'].parameters[1]; | |||
end | |||
end | |||
if utilities.is_set (URL) and utilities.is_set (AccessDate) then -- access date requires |url=; identifier-created URL is not |url= | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); -- add an error message | |||
AccessDate = ''; -- unset | |||
end | end | ||
end | end | ||
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. | |||
-- | -- Test if citation has no title | ||
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode | |||
if is_set( | table.insert( z.message_tail, { utilities.set_message ( 'err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}, true ) } ); | ||
end | end | ||
if in_array( | if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and | ||
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and | |||
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and | |||
('journal' == Periodical_origin or 'script-journal' == ScriptPeriodical_origin) then -- special case for journal cites | |||
Title = ''; -- set title to empty string | |||
utilities.set_message ('maint_untitled'); -- add maint cat | |||
end | |||
check_for_url ({ -- add error message when any of these parameters hold a URL | |||
['title'] = Title, | |||
[A:ORIGIN('Chapter')] = Chapter, | |||
[Periodical_origin] = Periodical, | |||
[PublisherName_origin] = 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 utilities.is_set (Encyclopedia)) then | |||
if utilities.is_set (Chapter) and utilities.is_set (Title) and utilities.is_set (Periodical) then -- if all are used then | |||
coins_chapter = Title; -- remap | |||
coins_title = Periodical; | |||
end | end | ||
end | end | ||
local coins_author = a; -- default for coins rft.au | |||
-- | if 0 < #c then -- but if contributor list | ||
if | coins_author = c; -- use that instead | ||
end | end | ||
-- this is the function call to COinS() | |||
local OCinSoutput = metadata.COinS({ | |||
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata | |||
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS | |||
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic wiki-markup | |||
['Degree'] = Degree; -- cite thesis only | |||
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic wiki-markup | |||
['PublicationPlace'] = PublicationPlace, | |||
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; | |||
['Season'] = COinS_date.rftssn, | |||
['Quarter'] = COinS_date.rftquarter, | |||
['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit? | |||
['Series'] = Series, | |||
['Volume'] = Volume, | |||
['Issue'] = Issue, | |||
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At, QuotePage, QuotePages}, 7)), -- pages stripped of external links | |||
['Edition'] = Edition, | |||
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName | |||
['URL'] = first_set ({ChapterURL, URL}, 2), | |||
['Authors'] = coins_author, | |||
['ID_list'] = ID_list_coins, | |||
['RawPage'] = this_page.prefixedText, | |||
}, config.CitationClass); | |||
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data. | |||
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- we have set rft.jtitle in COinS to arXiv, bioRxiv, CiteSeerX, or ssrn now unset so it isn't displayed | |||
Periodical = ''; -- periodical not allowed in these templates; 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 is_set( | if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then | ||
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil )); | |||
end | 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 control = { | |||
format = NameListStyle, -- empty string or 'vanc' | |||
if | maximum = nil, -- as if display-authors or display-editors not set | ||
mode = Mode | |||
}; | |||
do -- do editor name list first because the now unsupported coauthors used to modify control table | |||
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal); | |||
Editors, EditorCount = list_people (control, e, editor_etal); | |||
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 | ||
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 | |||
control.maximum , translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal); | |||
Translators = list_people (control, t, translator_etal); | |||
end | |||
do -- now do contributors | |||
control.maximum , contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal); | |||
Contributors = list_people (control, c, contributor_etal); | |||
end | |||
do -- now do authors | |||
control.maximum , author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal); | |||
last_first_list = list_people(control, a, author_etal); | |||
if utilities.is_set (Authors) then | |||
if is_set ( | Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al. | ||
if author_etal then | |||
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter | |||
end | end | ||
else | |||
Authors = last_first_list; -- either an author name list or an empty string | |||
end | end | ||
end -- end of do | |||
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then | |||
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. | |||
end | 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'); | |||
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 (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or | |||
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia))) then | |||
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); | |||
end | |||
if not utilities.is_set (URL) then | |||
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite mailinglist | |||
('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, { utilities.set_message ( 'err_cite_web_url', {}, true ) } ); | |||
end | |||
if is_set( | -- do we have |accessdate= without either |url= or |chapter-url=? | ||
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set; | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_accessdate_missing_url', {}, true ) } ); | |||
AccessDate = ''; | |||
end | end | ||
end | end | ||
local OriginalURL, OriginalURL_origin, OriginalFormat, OriginalAccess; | |||
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text | |||
if utilities.is_set ( ArchiveURL ) then | |||
if utilities.is_set (ChapterURL) then -- if chapter-url= is set apply archive url to it | |||
OriginalURL = ChapterURL; -- save copy of source chapter's url for archive text | |||
OriginalURL_origin = ChapterURL_origin; -- name of |chapter-url= parameter for error messages | |||
OriginalFormat = ChapterFormat; -- and original |chapter-format= | |||
if | |||
if 'live' ~= UrlStatus then | |||
ChapterURL = ArchiveURL -- swap-in the archive's URL | |||
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages | |||
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format | |||
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs | |||
end | |||
elseif utilities.is_set (URL) then | |||
OriginalURL = URL; -- save copy of original source URL | |||
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages | |||
OriginalFormat = Format; -- and original |format= | |||
OriginalAccess = UrlAccess; | |||
if 'live' ~= UrlStatus then -- if URL set then |archive-url= applies to it | |||
URL = ArchiveURL -- swap-in the archive's URL | |||
URL_origin = A:ORIGIN('ArchiveURL') -- name of archive URL parameter for error messages | |||
Format = ArchiveFormat or ''; -- swap in archive's format | |||
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs | |||
end | |||
end | |||
end | end | ||
if is_set( | if utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or -- if any of the 'periodical' cites except encyclopedia | ||
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then | |||
local chap_param; | |||
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters | |||
chap_param = A:ORIGIN ('Chapter') | |||
elseif utilities.is_set (TransChapter) then | |||
chap_param = A:ORIGIN ('TransChapter') | |||
elseif utilities.is_set (ChapterURL) then | |||
chap_param = A:ORIGIN ('ChapterURL') | |||
elseif utilities.is_set (ScriptChapter) then | |||
chap_param = ScriptChapter_origin; | |||
else utilities.is_set (ChapterFormat) | |||
chap_param = A:ORIGIN ('ChapterFormat') | |||
end | |||
if utilities.is_set (chap_param) then -- if we found one | |||
if ( | table.insert( z.message_tail, { utilities.set_message ( 'err_chapter_ignored', {chap_param}, true ) } ); -- add error message | ||
Chapter = ''; -- and set them to empty string to be safe with concatenation | |||
TransChapter = ''; | |||
ChapterURL = ''; | |||
ScriptChapter = ''; | |||
ChapterFormat = ''; | |||
end | |||
else -- otherwise, format chapter / article title | |||
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value | |||
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) | |||
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title | |||
no_quotes = true; -- then render it unquoted | |||
end | |||
end | |||
Chapter = format_chapter_title (ScriptChapter, ScriptChapter_origin, Chapter, Chapter_origin, TransChapter, TransChapter_origin, ChapterURL, ChapterURL_origin, no_quotes, ChapterUrlAccess); -- Contribution is also in Chapter | |||
if utilities.is_set (Chapter) then | |||
Chapter = Chapter .. ChapterFormat ; | |||
if 'map' == config.CitationClass and utilities.is_set (TitleType) then | |||
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title | |||
end | |||
Chapter = Chapter .. sepc .. ' '; | |||
elseif utilities.is_set (ChapterFormat) then -- |chapter= not set but |chapter-format= is so ... | |||
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it | |||
end | |||
end | end | ||
-- Format main title | |||
local plain_title = false; | |||
local accept_title; | |||
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title> | |||
if accept_title and ('' == Title) then -- only support forced empty for now "(())" | |||
Title = cfg.messages['notitle']; -- replace by predefined "No title" message | |||
-- TODO: utilities.set_message ( 'err_redundant_parameters', ...); -- issue proper error message instead of muting | |||
ScriptTitle = ''; -- just mute for now | |||
TransTitle = ''; -- just mute for now | |||
plain_title = true; -- suppress text decoration for descriptive title | |||
utilities.set_message ('maint_untitled'); -- add maint cat | |||
end | end | ||
if not accept_title then -- <Title> not wrapped in accept-as-written markup | |||
if '...' == Title:sub (-3) then -- if ellipsis 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 | |||
if utilities.is_set (ArchiveURL) and is_archived_copy (Title) then | |||
utilities.set_message ('maint_archived_copy'); -- add maintenance category before we modify the content of Title | |||
end | |||
if is_generic_title (Title) then | |||
table.insert (z.message_tail, {utilities.set_message ( 'err_generic_title', {}, true ) } ); -- set an error message | |||
end | |||
end | end | ||
if (not plain_title) and (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or | |||
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) or | |||
('map' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)))) then -- special case for cite map when the map is in a periodical treat as an article | |||
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks | |||
Title = utilities.wrap_style ('quoted-title', Title); | |||
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | |||
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); | |||
elseif plain_title or ('report' == config.CitationClass) then -- no styling for cite report and descriptive titles (otherwise same as above) | |||
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | |||
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title | |||
else | |||
Title = utilities.wrap_style ('italic-title', Title); | |||
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | |||
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle); | |||
end | |||
if is_set( | local TransError = ""; | ||
if utilities.is_set (TransTitle) then | |||
if utilities.is_set (Title) then | |||
TransTitle = " " .. TransTitle; | |||
else | |||
TransError = " " .. utilities.set_message ( 'err_trans_missing_title', {'title'} ); | |||
end | |||
end | end | ||
if is_set( | if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs? | ||
if | if utilities.is_set (TitleLink) and utilities.is_set (URL) then | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_wikilink_in_url', {}, true ) } ); -- set an error message because we can't have both | |||
TitleLink = ''; -- unset | |||
end | end | ||
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then | |||
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format; | |||
URL = ''; -- unset these because no longer needed | |||
Format = ""; | |||
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then | |||
local ws_url; | |||
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here | |||
if ws_url then | |||
Title = external_link (ws_url, Title .. ' ', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? | |||
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title}); | |||
Title = Title .. TransTitle .. TransError; | |||
else | |||
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle .. TransError; | |||
end | end | ||
else | else | ||
local | local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink) | ||
if | ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label | ||
if ws_url then | |||
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup | |||
Title = external_link (ws_url, Title .. ' ', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? | |||
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); | |||
Title = Title .. TransTitle .. TransError; | |||
else | |||
Title = Title .. TransTitle .. TransError; | |||
end | |||
end | end | ||
else | else | ||
Title = TransTitle .. TransError; | |||
end | |||
if utilities.is_set (Place) then | |||
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; | |||
end | end | ||
if utilities.is_set (Conference) then | |||
if is_set( | if utilities.is_set (ConferenceURL) then | ||
if | Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil ); | ||
end | end | ||
Conference = sepc .. " " .. Conference .. ConferenceFormat; | |||
elseif utilities.is_set (ConferenceURL) then | |||
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil ); | |||
end | end | ||
if is_set( | if not utilities.is_set (Position) then | ||
if is_set( | local Minutes = A['Minutes']; | ||
local Time = A['Time']; | |||
if utilities.is_set (Minutes) then | |||
if utilities.is_set (Time) then | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}, true ) } ); | |||
end | |||
Position = " " .. Minutes .. " " .. cfg.messages['minutes']; | |||
else | |||
if utilities.is_set (Time) then | |||
local TimeCaption = A['TimeCaption'] | |||
if not utilities.is_set (TimeCaption) then | |||
TimeCaption = cfg.messages['event']; | |||
if sepc ~= '.' then | |||
TimeCaption = TimeCaption:lower(); | |||
end | |||
end | |||
Position = " " .. TimeCaption .. " " .. Time; | |||
end | |||
end | end | ||
else | |||
Position = " " .. Position; | |||
At = ''; | |||
end | end | ||
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); | |||
At = utilities.is_set (At) and (sepc .. " " .. At) or ""; | |||
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or ""; | |||
if config.CitationClass == 'map' then | |||
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier | |||
local Inset = A['Inset']; | |||
if utilities.is_set ( Inset ) then | |||
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); | |||
end | end | ||
if utilities.is_set ( Sections ) then | |||
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); | |||
elseif utilities.is_set ( Section ) then | |||
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); | |||
end | end | ||
end | At = At .. Inset .. Section; | ||
end | |||
-- | if utilities.is_set (Language) then | ||
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc. | |||
the | else | ||
Language=""; -- language not specified so make sure this is an empty string; | |||
--[[ TODO: need to extract the wrap_msg from language_parameter | |||
so that we can solve parentheses bunching problem with Format/Language/TitleType | |||
]] | ]] | ||
end | end | ||
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | |||
if | if utilities.is_set (Translators) then | ||
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc); | |||
end | end | ||
if utilities.is_set (Interviewers) then | |||
if | Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc); | ||
end | end | ||
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; | |||
if ' | if utilities.is_set (Edition) then | ||
if Edition:match ('%f[%a][Ee]d%n?%.?$') or Edition:match ('%f[%a][Ee]dition$') then -- Ed, ed, Ed., ed., Edn, edn, Edn., edn. | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_edition')}); -- add error | |||
end | |||
Edition = " " .. wrap_msg ('edition', Edition); | |||
else | else | ||
Edition = ''; | |||
end | end | ||
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum | |||
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or ''; | |||
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or ""; | |||
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); | |||
------------------------------------ totally unrelated data | |||
Via = utilities.is_set (Via) and wrap_msg ('via', Via) or ''; | |||
if utilities.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 mode is cs2, lower case | |||
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text | |||
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates | |||
end | |||
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end | |||
if "thesis" == config.CitationClass and utilities.is_set (Docket) then | |||
ID = sepc .. " Docket " .. Docket .. ID; | |||
end | |||
if "report" == config.CitationClass and utilities.is_set (Docket) then -- for cite report when |docket= is set | |||
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set | |||
end | |||
if utilities.is_set (URL) then | |||
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess ); | |||
end | |||
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then | |||
if utilities.is_set (Quote) then | |||
if Quote:sub(1, 1) == '"' and Quote:sub(-1, -1) == '"' then -- if first and last characters of quote are quote marks | |||
Quote = Quote:sub(2, -2); -- strip them off | |||
end | end | ||
end | end | ||
if is_set( | Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags | ||
if ( | |||
if utilities.is_set (ScriptQuote) then | |||
Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped | |||
end | |||
if utilities.is_set (TransQuote) then | |||
if TransQuote:sub(1, 1) == '"' and TransQuote:sub(-1, -1) == '"' then -- if first and last characters of |trans-quote are quote marks | |||
TransQuote = TransQuote:sub(2, -2); -- strip them off | |||
end | |||
Quote = Quote .. " " .. utilities.wrap_style ('trans-quoted-title', TransQuote ); | |||
end | end | ||
if is_set( | |||
local | -- if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) | ||
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix | |||
if is_set( | local quote_prefix = ''; | ||
if utilities.is_set (QuotePage) then | |||
if ( | extra_text_in_page_check (QuotePage); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc. | ||
if not NoPP then | |||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', ''; | |||
else | |||
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', ''; | |||
end | |||
elseif utilities.is_set (QuotePages) then | |||
extra_text_in_page_check (QuotePages); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc. | |||
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page | |||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', ''; | |||
elseif not NoPP then | |||
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', ''; | |||
else | |||
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', ''; | |||
end | end | ||
end | end | ||
Quote = quote_prefix .. ": " .. Quote; | |||
else | |||
Quote = sepc .. " " .. Quote; | |||
end | end | ||
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set | |||
end | |||
local Archived | |||
if utilities.is_set (ArchiveURL) then | |||
local arch_text; | |||
if not utilities.is_set (ArchiveDate) then | |||
ArchiveDate = utilities.set_message ('err_archive_missing_date'); | |||
end | end | ||
if "live" == UrlStatus then | |||
if | arch_text = cfg.messages['archived']; | ||
if sepc ~= "." then arch_text = arch_text:lower() end | |||
Archived = sepc .. " " .. utilities.substitute ( cfg.messages['archived-live'], | |||
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } ); | |||
if not utilities.is_set (OriginalURL) then | |||
Archived = Archived .. " " .. utilities.set_message ('err_archive_missing_url'); | |||
end | end | ||
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' | |||
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then | |||
arch_text = cfg.messages['archived-unfit']; | |||
if sepc ~= "." then arch_text = arch_text:lower() end | |||
Archived = sepc .. " " .. arch_text .. ArchiveDate; -- format already styled | |||
if 'bot: unknown' == UrlStatus then | |||
utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added | |||
else | |||
utilities.set_message ('maint_unfit'); -- and add a category if not already added | |||
end | |||
else -- UrlStatus is empty, 'dead' | |||
arch_text = cfg.messages['archived-dead']; | |||
if sepc ~= "." then arch_text = arch_text:lower() end | |||
Archived = sepc .. " " .. utilities.substitute ( arch_text, | |||
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled | |||
end | |||
else -- OriginalUrl not set | |||
arch_text = cfg.messages['archived-missing']; | |||
if sepc ~= "." then arch_text = arch_text:lower() end | |||
Archived = sepc .. " " .. utilities.substitute ( arch_text, | |||
{ utilities.set_message ('err_archive_missing_url'), ArchiveDate } ); | |||
end | end | ||
elseif utilities.is_set (ArchiveFormat) then | |||
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message | |||
else | else | ||
if | Archived = "" | ||
end | |||
local Lay = ''; | |||
if utilities.is_set (LayURL) then | |||
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end | |||
if utilities.is_set (LaySource) then | |||
LaySource = " – ''" .. utilities.safe_for_italics (LaySource) .. "''"; | |||
else | else | ||
LaySource = ""; | |||
end | end | ||
if sepc == '.' then | |||
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary'], A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate | |||
else | |||
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate | |||
end | |||
elseif utilities.is_set (LayFormat) then -- Test if |lay-format= is given without giving a |lay-url= | |||
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message | |||
end | end | ||
if utilities.is_set (Transcript) then | |||
if utilities.is_set (TranscriptURL) then | |||
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil ); | |||
if is_set( | end | ||
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; | |||
elseif utilities.is_set (TranscriptURL) then | |||
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil ); | |||
end | end | ||
if is_set( | local Publisher; | ||
if utilities.is_set (PublicationDate) then | |||
PublicationDate = wrap_msg ('published', PublicationDate); | |||
end | |||
if utilities.is_set (PublisherName) then | |||
if utilities.is_set (PublicationPlace) then | |||
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; | |||
else | |||
Publisher = sepc .. " " .. PublisherName .. PublicationDate; | |||
end | |||
elseif utilities.is_set (PublicationPlace) then | |||
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; | |||
else | |||
Publisher = PublicationDate; | |||
end | end | ||
if | -- Several of the above rely upon detecting this as nil, so do it last. | ||
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then | |||
if utilities.is_set (Title) or utilities.is_set (TitleNote) then | |||
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); | |||
else | |||
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); | |||
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 -- cite speech only | |||
TitleNote = " (Speech)"; -- annotate the citation | |||
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter | |||
if utilities.is_set (Conference) then -- and if |event= is set | |||
if | Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering | ||
end | end | ||
end | end | ||
end | end | ||
-- Piece all bits together at last. Here, all should be non-nil. | |||
-- We build things this way because it is more efficient in LUA | |||
-- not to keep reassigning to the same string variable over and over. | |||
local tcommon; | |||
local tcommon2; -- used for book cite when |contributor= is set | |||
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then | |||
if in_array( | if utilities.is_set (Others) then Others = safe_join ({Others, sepc .. " "}, sepc) end -- add terminal punctuation & space; check for dup sepc; TODO why do we need to do this here? | ||
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); | |||
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites | |||
if utilities.is_set (Contributors) then -- when we are citing foreword, preface, introduction, etc. | |||
tcommon = safe_join( {Title, TitleNote}, sepc ); -- author and other stuff will come after this and before tcommon2 | |||
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); | |||
else | |||
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); | |||
end | end | ||
elseif 'map' == config.CitationClass then -- special cases for cite map | |||
if utilities.is_set (Chapter) then -- map in a book; TitleType is part of Chapter | |||
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); | |||
elseif utilities.is_set (Periodical) then -- map in a periodical | |||
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); | |||
else -- a sheet or stand-alone map | |||
tcommon = safe_join( {Title, TitleType, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher}, sepc ); | |||
end | end | ||
elseif 'episode' == config.CitationClass then -- special case for cite episode | |||
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc ); | |||
else -- all other CS1 templates | |||
tcommon = safe_join( {Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, | |||
Volume, Others, Edition, Publisher, Agency}, sepc ); | |||
end | end | ||
if #ID_list > 0 then | |||
ID_list = safe_join( { sepc .. " ", table.concat( ID_list, sepc .. " " ), ID }, sepc ); | |||
local | else | ||
ID_list = ID; | |||
end | |||
local idcommon; | |||
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript | |||
idcommon = safe_join( { ID_list, URL, Archived, Transcript, AccessDate, Via, Lay, Quote }, sepc ); | |||
else | |||
idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, Lay, Quote }, sepc ); | |||
end | |||
local text; | |||
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; | |||
if utilities.is_set (Date) then | |||
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set | |||
Date = " (" .. Date .. ")" .. OrigDate .. sepc .. " "; -- in parentheses | |||
else -- neither of authors and editors set | |||
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc | |||
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc | |||
else | |||
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc | |||
end | |||
end | end | ||
end | |||
if utilities.is_set (Authors) then | |||
if (not utilities.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 | end | ||
if utilities.is_set (Editors) then | |||
local in_text = " "; | |||
local post_text = ""; | |||
if utilities.is_set (Chapter) and 0 == #c then | |||
in_text = in_text .. cfg.messages['in'] .. " " | |||
if (sepc ~= '.') then | |||
in_text = in_text:lower() -- lowercase for cs2 | |||
end | |||
end | |||
if EditorCount <= 1 then | |||
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case | |||
else | |||
post_text = " (" .. cfg.messages['editors'] .. ")"; | |||
end | |||
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space | |||
end | |||
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc. | |||
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; | |||
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 | |||
Authors = by_text .. Authors; -- author follows title so tweak it here | |||
if utilities.is_set (Editors) and utilities.is_set (Date) then -- when Editors make sure that Authors gets terminated | |||
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space | |||
end | |||
if (not utilities.is_set (Date)) then -- when date is set it's in parentheses; no Contributors termination | |||
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space | |||
end | |||
text = safe_join( {Contributors, Date, Chapter, tcommon, Authors, Place, Editors, tcommon2, pgtext, idcommon }, sepc ); | |||
else | |||
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); | |||
end | |||
elseif utilities.is_set (Editors) then | |||
if utilities.is_set (Date) then | |||
if EditorCount <= 1 then | |||
Editors = Editors .. ", " .. cfg.messages['editor']; | |||
else | |||
Editors = Editors .. ", " .. cfg.messages['editors']; | |||
end | |||
else | |||
if EditorCount <= 1 then | |||
Editors = Editors .. " (" .. cfg.messages['editor'] .. ")" .. sepc .. " " | |||
else | |||
Editors = Editors .. " (" .. cfg.messages['editors'] .. ")" .. sepc .. " " | |||
end | |||
end | |||
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); | |||
else | |||
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then | |||
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); | |||
else | |||
text = safe_join( {Chapter, Place, tcommon, Date, pgtext, idcommon}, sepc ); | |||
end | |||
end | |||
if utilities.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 utilities.is_set (config.CitationClass) and config.CitationClass ~= "citation" then | |||
options.class = string.format ('%s %s %s', 'citation', config.CitationClass, utilities.is_set (Mode) and Mode or 'cs1'); -- class=citation required for blue highlight when used with |ref= | |||
else | |||
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2'); | |||
end | |||
if utilities.is_set (Ref) and 'none' ~= cfg.keywords_xlate[Ref:lower()] then | |||
local id = Ref | |||
if ('harv' == Ref ) then | |||
local namelist = {}; -- holds selected contributor, author, editor name list | |||
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation | |||
if #c > 0 then -- if there is a contributor list | |||
namelist = c; -- select it | |||
elseif #a > 0 then -- or an author list | |||
namelist = a; | |||
elseif #e > 0 then -- or an editor list | |||
namelist = e; | |||
end | |||
if #namelist > 0 then -- if there are names in namelist | |||
id = anchor_id (namelist, year); -- go make the CITEREF anchor | |||
else | |||
id = ''; -- unset | |||
end | |||
end | |||
options.id = id; | |||
end | |||
if string.len(text:gsub("<span[^>/]*>(.-)</span>", "%1"):gsub("%b<>", "")) <= 2 then -- remove <span> tags and other HTML-like markup; then get length of what remains | |||
z.error_categories = {}; | |||
text = utilities.set_message ('err_empty_citation'); | |||
z.message_tail = {}; | |||
end | |||
local render = {}; -- here we collect the final bits for concatenation into the rendered citation | |||
if utilities.is_set (options.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags | |||
table.insert (render, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options.id), mw.text.nowiki(options.class), text})); -- when |ref= is set | |||
else | |||
table.insert (render, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options.class), text})); -- all other cases | |||
end | |||
table.insert (render, utilities.substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation | |||
if 0 ~= #z.message_tail then | |||
table.insert (render, ' '); | |||
for i,v in ipairs( z.message_tail ) do | |||
if utilities.is_set (v[1]) then | |||
if i == #z.message_tail then | |||
table.insert (render, utilities.error_comment ( v[1], v[2] )); | |||
else | |||
table.insert (render, utilities.error_comment ( v[1] .. "; ", v[2] )); | |||
end | |||
end | |||
end | |||
end | |||
if 0 ~= #z.maintenance_cats then | |||
local maint_msgs = {}; -- here we collect all of the maint messages | |||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories | |||
local maint = {}; -- here we assemble a maintenence message | |||
table.insert (maint, v); -- maint msg is the category name | |||
table.insert (maint, ' ('); -- open the link text | |||
table.insert (maint, utilities.substitute (cfg.messages[':cat wikilink'], {v})); -- add the link | |||
table.insert (maint, ')'); -- and close it | |||
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table | |||
end | |||
table.insert (render, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs, ' '))); -- wrap the group of maint message with proper presentation and save | |||
end | |||
if not no_tracking_cats then | |||
for _, v in ipairs( z.error_categories ) do -- append error categories | |||
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | |||
end | |||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories | |||
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | |||
end | |||
for _, v in ipairs( z.properties_cats ) do -- append properties categories | |||
table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | |||
end | |||
end | |||
return table.concat (render); | |||
end | |||
--[[--------------------------< V A L I D A T E >-------------------------------------------------------------- | |||
Looks for a parameter's name in one of several whitelists. | |||
Parameters in the whitelist can have three values: | |||
true - active, supported parameters | |||
false - deprecated, supported parameters | |||
nil - unsupported parameters | |||
]] | |||
local function validate (name, cite_class, empty) | |||
local name = tostring (name); | |||
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#' | |||
local state; | |||
local function state_test (state, name) -- local function to do testing of state values | |||
if true == state then return true; end -- valid actively supported parameter | |||
if false == state then | |||
if empty then return nil; end -- deprecated empty parameters are treated as unknowns | |||
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 utilities.in_array (cite_class, whitelist.preprint_template_list ) then -- limited parameter sets allowed for these templates | |||
state = whitelist.limited_basic_arguments[name]; | |||
if true == state_test (state, name) then return true; end | |||
state = whitelist.preprint_arguments[cite_class][name]; -- look in the parameter-list for the template identified by cite_class | |||
if true == state_test (state, name) then return true; end | |||
-- limited enumerated parameters list | |||
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) | |||
state = whitelist.limited_numbered_arguments[enum_name]; | |||
if true == state_test (state, name) then return true; end | |||
return false; -- not supported because not found or name is set to nil | |||
end -- end limited parameter-set templates | |||
if utilities.in_array (cite_class, whitelist.unique_param_template_list) then -- experiment for template-specific parameters for templates that accept parameters from the basic argument list | |||
state = whitelist.unique_arguments[cite_class][name]; -- look in the template-specific parameter-lists for the template identified by cite_class | |||
if true == state_test (state, name) then return true; end | |||
end -- if here, fall into general validation | |||
state = whitelist.basic_arguments[name]; -- all other templates; all normal parameters allowed | |||
if true == state_test (state, name) then return true; end | |||
-- all enumerated parameters allowed | |||
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) | |||
state = whitelist.numbered_arguments[enum_name]; | |||
if true == state_test (state, name) then return true; end | |||
return false; -- not supported because not found or name is set to nil | |||
end | |||
--[=[-------------------------< I N T E R _ W I K I _ C H E C K >---------------------------------------------- | |||
check <value> for inter-language interwiki-link markup. <prefix> must be a MediaWiki-recognized language | |||
code. when these values have the form (without leading colon): | |||
[[<prefix>:link|label]] return label as plain-text | |||
[[<prefix>:link]] return <prefix>:link as plain-text | |||
return value as is else | |||
]=] | |||
local function inter_wiki_check (parameter, value) | |||
local prefix = value:match ('%[%[(%a+):'); -- get an interwiki prefix if one exists | |||
local _; | |||
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so | |||
table.insert( z.message_tail, {utilities.set_message ('err_bad_paramlink', parameter)}); -- emit an error message | |||
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink | |||
end | |||
return value; | |||
end | |||
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ | |||
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal | |||
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a | |||
parameter that is missing its pipe. There are two tests made: | |||
{{cite ... |title=Title access-date=2016-03-17}} -- the first parameter has a value and whitespace separates that value from the missing pipe parameter name | |||
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki) | |||
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc. To prevent false positives XML/HTML | |||
tags are removed before the search. | |||
If a missing pipe is detected, this function adds the missing pipe maintenance category. | |||
]] | |||
local function missing_pipe_check (parameter, value) | |||
local capture; | |||
value = value:gsub ('%b<>', ''); -- remove XML/HTML tags because attributes: class=, title=, etc. | |||
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes | |||
if capture and validate (capture) then -- if the capture is a valid parameter name | |||
table.insert( z.message_tail, {utilities.set_message ('err_missing_pipe', parameter)}); | |||
end | |||
end | |||
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >-------------------------------------- | |||
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked | |||
]] | |||
local function has_extraneous_punc (param, value) | |||
if 'number' == type (param) then | |||
return; | |||
return | |||
end | end | ||
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize | |||
- | |||
if cfg.punct_skip[param] then | if cfg.punct_skip[param] then | ||
return; -- parameter name found in the skip table so done | return; -- parameter name found in the skip table so done | ||
| Line 3,741: | Line 3,987: | ||
if value:match ('[,;:]$') then | if value:match ('[,;:]$') then | ||
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat | |||
end | end | ||
end | end | ||
| Line 3,753: | Line 3,999: | ||
local function citation(frame) | local function citation(frame) | ||
Frame = frame; -- save a copy | Frame = frame; -- save a copy in case we need to display an error message in preview mode | ||
local pframe = frame:getParent() | local pframe = frame:getParent() | ||
local | local styles; | ||
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? | ||
| Line 3,774: | Line 4,020: | ||
metadata = require ('Module:Citation/CS1/COinS'); | metadata = require ('Module:Citation/CS1/COinS'); | ||
styles = 'Module:Citation/CS1/styles.css'; | styles = 'Module:Citation/CS1/styles.css'; | ||
end | end | ||
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables | utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables | ||
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module | 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 | 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 | metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module | ||
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities | z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities | ||
local args = {}; -- table where we store all of the template's arguments | local args = {}; -- table where we store all of the template's arguments | ||
| Line 3,817: | Line 4,034: | ||
local config = {}; -- table to store parameters from the module {{#invoke:}} | local config = {}; -- table to store parameters from the module {{#invoke:}} | ||
for k, v in pairs( frame.args ) do | for k, v in pairs( frame.args ) do -- get parameters from the {{#invoke}} frame | ||
config[k] = v; | config[k] = v; | ||
-- | -- args[k] = v; -- crude debug support that allows us to render a citation from module {{#invoke:}}; skips parameter validation; TODO: keep? | ||
end | end | ||
local capture; -- the single supported capture when matching unknown parameters using patterns | local capture; -- the single supported capture when matching unknown parameters using patterns | ||
for k, v in pairs( pframe.args ) do | local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing | ||
for k, v in pairs( pframe.args ) do -- get parameters from the parent (template) frame | |||
v = mw.ustring.gsub (v, '^%s*(.-)%s*$', '%1'); -- trim leading/trailing whitespace; when v is only whitespace, becomes empty string | |||
if v ~= '' then | if v ~= '' then | ||
if ('string' == type (k)) then | if ('string' == type (k)) then | ||
| Line 3,831: | Line 4,050: | ||
error_text = ""; | error_text = ""; | ||
if type( k ) ~= 'string' then | if type( k ) ~= 'string' then | ||
-- | -- exclude empty numbered parameters | ||
if v:match("%S+") ~= nil then | if v:match("%S+") ~= nil then | ||
error_text, error_state = | error_text, error_state = utilities.set_message ( 'err_text_ignored', {v}, true ); | ||
end | end | ||
elseif validate( k:lower(), config.CitationClass ) then | elseif validate( k:lower(), config.CitationClass ) then | ||
error_text, error_state = | error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, k:lower()}, true ); -- suggest the lowercase version of the parameter | ||
else | else | ||
if nil == suggestions.suggestions then -- if this table is nil then we need to load it | if nil == suggestions.suggestions then -- if this table is nil then we need to load it | ||
| Line 3,846: | Line 4,065: | ||
end | end | ||
for pattern, param in pairs (suggestions.patterns) do -- loop through the patterns to see if we can suggest a proper parameter | 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 | capture = k:match (pattern); -- the whole match if no capture in pattern else the capture if a match | ||
if capture then -- if the pattern matches | if capture then -- if the pattern matches | ||
param = substitute (param, capture); | param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator) | ||
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) | 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 = | error_text, error_state = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message | ||
else | else | ||
error_text, error_state = | error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {param}, true ); -- suggested param not supported by this template | ||
v = ''; -- unset | |||
end | end | ||
end | end | ||
end | end | ||
if not is_set (error_text) then | if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an explicit suggestion? | ||
if suggestions.suggestions[ k:lower() ] ~= nil then | if suggestions.suggestions[ k:lower() ] ~= nil then | ||
error_text, error_state = | error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); | ||
else | else | ||
error_text, error_state = | error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true ); | ||
v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists) | v = ''; -- unset value assigned to unrecognized parameters (this for the limited parameter lists) | ||
end | end | ||
| Line 3,869: | Line 4,089: | ||
end | end | ||
end | end | ||
-- TODO: | args[k] = v; -- save this parameter and its value | ||
elseif not utilities.is_set (v) then -- for empty parameters | |||
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter | |||
end | k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text | ||
table.insert (empty_unknowns, utilities.wrap_style ('parameter', k)); -- format for error message and add to the list | |||
end | |||
-- crude debug support that allows us to render a citation from module {{#invoke:}} TODO: keep? | |||
-- elseif args[k] ~= nil or (k == 'postscript') then -- when args[k] has a value from {{#invoke}} frame (we don't normally do that) | |||
-- args[k] = v; -- overwrite args[k] with empty string from pframe.args[k] (template frame); v is empty string here | |||
end -- not sure about the postscript bit; that gets handled in parameter validation; historical artifact? | |||
end | end | ||
if 0 ~= #empty_unknowns then -- create empty unknown error message | |||
table.insert (z.message_tail, {utilities.set_message ('err_param_unknown_empty', { | |||
1 == #empty_unknowns and '' or 's', | |||
utilities.make_sep_list (#empty_unknowns, empty_unknowns) | |||
}, true )}); | |||
end | |||
for k, v in pairs( args ) do | for k, v in pairs( args ) do | ||
if 'string' == type (k) then -- don't evaluate positional parameters | if 'string' == type (k) then -- don't evaluate positional parameters | ||
has_invisible_chars | has_invisible_chars (k, v); -- look for invisible characters | ||
end | end | ||
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values | |||
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe? | |||
args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label | |||
end | end | ||
return table.concat ({ | |||
return table.concat ({ | |||
frame:extensionTag ('templatestyles', '', {src=styles}), | |||
citation0( config, args) | |||
}); | |||
end | end | ||