Module:Citation/CS1: Difference between revisions
Content added Content deleted
Vivaporius (talk | contribs) m (1 revision imported) |
en>Trappist the monk (sync from sandbox;) |
||
Line 1: | Line 1: | ||
require('strict'); |
|||
local cs1 ={}; |
|||
--[[--------------------------< 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 dates, year_date_check, reformat_dates, date_hyphen_to_dash, -- functions in Module:Citation/CS1/Date_validation |
|||
date_name_xlate |
|||
]] |
|||
local is_set, in_array, substitute, error_comment, set_error, select_one, -- functions in Module:Citation/CS1/Utilities |
|||
add_maint_cat, wrap_style, safe_for_italics, is_wikilink, make_wikilink; |
|||
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 make_coins_title, get_coins_pages, COinS; -- functions in Module:Citation/CS1/COinS |
|||
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 |
||
--[[ |
--[[------------------< 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 |
|||
and used here |
other modules; that are created here and used here |
||
]] |
]] |
||
local added_deprecated_cat; -- |
local added_deprecated_cat; -- Boolean flag so that the category is added only once |
||
local |
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category |
||
local |
local added_generic_name_errs; -- Boolean flag so we only emit one generic name error / category and stop testing names once an error is encountered |
||
local Frame; -- holds the module's frame table |
local Frame; -- holds the module's frame table |
||
local is_preview_mode; -- true when article is in preview mode; false when using 'Preview page with this template' (previewing the module) |
|||
local is_sandbox; -- true when using sandbox modules to render citation |
|||
Line 49: | Line 47: | ||
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 |
|||
--[[--------------------------< A D D _ P R O P _ C A T >-------------------------------------------------------- |
|||
Adds a category to z.properties_cats using names from the configuration file with additional text if any. |
|||
foreign_lang_source and foreign_lang_source_2 keys have a language code appended to them so that multiple languages |
|||
may be categorized but multiples of the same language are not categorized. |
|||
added_prop_cats is a table declared in page scope variables above |
|||
]] |
|||
local function add_prop_cat (key, arguments) |
|||
if not added_prop_cats [key] then |
|||
added_prop_cats [key] = true; -- note that we've added this category |
|||
key = key:gsub ('(foreign_lang_source_?2?)%a%a%a?', '%1'); -- strip lang code from keyname |
|||
table.insert( z.properties_cats, substitute (cfg.prop_cats [key], arguments)); -- make name then add to table |
|||
end |
end |
||
end |
end |
||
Line 82: | Line 60: | ||
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 |
||
]] |
]] |
||
local function add_vanc_error (source) |
local function add_vanc_error (source, position) |
||
if |
if added_vanc_errs then return end |
||
added_vanc_errs = true; -- note that we've added this category |
|||
added_vanc_errs = true; -- note that we've added this category |
|||
table.insert( z.message_tail, { set_error( 'vancouver', {source}, true ) } ); |
|||
utilities.set_message ('err_vancouver', {source, position}); |
|||
end |
|||
end |
end |
||
Line 96: | Line 74: | ||
--[[--------------------------< 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 119: | Line 97: | ||
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 and . |
single-letter/digit second-level domains in the .org, .cash, and .today TLDs |
||
q, x, and z SL domains in the .com TLD |
q, x, and z SL domains in the .com TLD |
||
i and q SL domains in the .net TLD |
i and q SL domains in the .net TLD |
||
Line 141: | Line 119: | ||
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 152: | Line 130: | ||
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once |
domain = domain:gsub ('^//', ''); -- strip '//' from domain name if present; done here so we only have to do it once |
||
if not domain:match ('^[% |
if not domain:match ('^[%w]') then -- first character must be letter or digit |
||
return false; |
return false; |
||
end |
end |
||
-- Do most common case first |
|||
if domain:match (' |
if domain:match ('^%a+:') then -- hack to detect things that look like s:Page:Title where Page: is namespace at Wikisource |
||
return true; |
|||
elseif domain:match ('%f[%a%d][%a%d][%a%d%-]+[%a%d]%.xn%-%-[%a%d]+$') then -- internationalized domain name with ACE prefix |
|||
return true; |
|||
elseif domain:match ('%f[%a%d][%a%d]%.cash$') then -- one character/digit .cash hostname |
|||
return true; |
|||
elseif domain:match ('%f[%a%d][%a%d]%.org$') then -- one character/digit .org hostname |
|||
return true; |
|||
elseif domain:match ('%f[%a][qxz]%.com$') then -- assigned one character .com hostname (x.com times out 2015-12-10) |
|||
return true; |
|||
elseif domain:match ('%f[%a][iq]%.net$') then -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
|||
return true; |
|||
elseif domain:match ('%f[%a%d][%a%d]%.%a%a$') then -- one character hostname and cctld (2 chars) |
|||
return true; |
|||
elseif domain:match ('%f[%a%d][%a%d][%a%d]%.%a%a+$') then -- two character hostname and tld |
|||
return true; |
|||
elseif domain:match ('^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?') then -- IPv4 address |
|||
return true; |
|||
else |
|||
return false; |
return false; |
||
end |
end |
||
local patterns = { -- patterns that look like URLs |
|||
'%f[%w][%w][%w%-]+[%w]%.%a%a+$', -- three or more character hostname.hostname or hostname.tld |
|||
'%f[%w][%w][%w%-]+[%w]%.xn%-%-[%w]+$', -- internationalized domain name with ACE prefix |
|||
'%f[%a][qxz]%.com$', -- assigned one character .com hostname (x.com times out 2015-12-10) |
|||
'%f[%a][iq]%.net$', -- assigned one character .net hostname (q.net registered but not active 2015-12-10) |
|||
'%f[%w][%w]%.%a%a$', -- one character hostname and ccTLD (2 chars) |
|||
'%f[%w][%w][%w]%.%a%a+$', -- two character hostname and TLD |
|||
'^%d%d?%d?%.%d%d?%d?%.%d%d?%d?%.%d%d?%d?', -- IPv4 address |
|||
} |
|||
for _, pattern in ipairs (patterns) do -- loop through the patterns list |
|||
if domain:match (pattern) then |
|||
return true; -- if a match then we think that this thing that purports to be a URL is a URL |
|||
end |
|||
end |
|||
for _, d in ipairs (cfg.single_letter_2nd_lvl_domains_t) do -- look for single letter second level domain names for these top level domains |
|||
if domain:match ('%f[%w][%w]%.' .. d) then |
|||
return true |
|||
end |
|||
end |
|||
return false; -- no matches, we don't know what this thing is |
|||
end |
end |
||
Line 182: | Line 165: | ||
--[[--------------------------< 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 191: | Line 174: | ||
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 201: | Line 184: | ||
--[[--------------------------< 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 |
If protocol-relative URL, return nil scheme and domain else return nil for both scheme and domain. |
||
When not protocol |
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 219: | Line 205: | ||
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 |
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 |
||
if utilities.is_set (authority) then |
|||
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; |
|||
authority = authority:gsub ('//', '', 1); -- replace place 1 pair of '/' with nothing; |
|||
if utilities.is_set(authority) then -- if anything left (1 or 3+ '/' where authority should be) then |
|||
return scheme; -- return scheme only making domain nil which will cause an error message |
|||
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 236: | Line 228: | ||
--[[--------------------------< 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 255: | Line 247: | ||
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 264: | Line 256: | ||
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. |
|||
]] |
]] |
||
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 -- don't bother if <param>-link doesn't have a value |
|||
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 |
||
link = ''; -- unset |
|||
table.insert( z.message_tail, { set_error( 'bad_paramlink', orig)}); -- url or wikilink in |title= with |title-link=; |
|||
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 290: | Line 293: | ||
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 |
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 301: | Line 304: | ||
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 312: | Line 315: | ||
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 319: | Line 322: | ||
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 |
that use protocol-relative URLs. Also finds bare URLs. |
||
The frontier pattern prevents a match on interwiki |
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 332: | Line 335: | ||
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 |
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 |
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 354: | Line 357: | ||
]] |
]] |
||
local function check_for_url (parameter_list) |
local function check_for_url (parameter_list, error_list) |
||
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 |
||
table.insert (error_list, utilities.wrap_style ('parameter', k)); |
|||
if is_set(error_message) then -- once we've added the first portion of the error message ... |
|||
error_message=error_message .. ", "; -- ... add a comma space separator |
|||
end |
|||
error_message=error_message .. "|" .. k .. "="; -- add the failed parameter |
|||
end |
end |
||
end |
|||
if is_set (error_message) then -- done looping, if there is an error message, display it |
|||
table.insert( z.message_tail, { set_error( 'param_has_ext_link', {error_message}, true ) } ); |
|||
end |
end |
||
end |
end |
||
Line 378: | Line 374: | ||
local function safe_for_url( str ) |
local function safe_for_url( str ) |
||
if str:match( "%[%[.-%]%]" ) ~= nil then |
if str:match( "%[%[.-%]%]" ) ~= nil then |
||
utilities.set_message ('err_wikilink_in_url', {}); |
|||
table.insert( z.message_tail, { set_error( 'wikilink_in_url', {}, true ) } ); |
|||
end |
end |
||
Line 394: | Line 390: | ||
]] |
]] |
||
local function external_link |
local function external_link (URL, label, source, access) |
||
local |
local err_msg = ''; |
||
local domain; |
local domain; |
||
local path; |
local path; |
||
local base_url; |
local base_url; |
||
if not is_set( |
if not utilities.is_set (label) then |
||
label = URL; |
label = URL; |
||
if is_set( |
if utilities.is_set (source) then |
||
utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)}); |
|||
else |
else |
||
error |
error (cfg.messages["bare_url_no_origin"]); -- programmer error; valid parameter name does not have matching meta-parameter |
||
end |
end |
||
end |
end |
||
if not check_url( |
if not check_url (URL) then |
||
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); |
|||
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'}); |
path = path:gsub ('[%[%]]', {['['] = '%5b', [']'] = '%5d'}); -- replace '[' and ']' with their percent-encoded values |
||
URL=domain |
URL = table.concat ({domain, path}); -- and reassemble |
||
end |
end |
||
if is_set (access) then -- access level (subscription, registration, limited) |
|||
label = safe_for_url (label); -- replace square brackets and newlines |
|||
base_url = table.concat ({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL |
|||
{ |
|||
if utilities.is_set (access) then -- access level (subscription, registration, limited) |
|||
'<span class="plainlinks">[', -- opening css and url markup |
|||
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon |
|||
URL, -- the url |
|||
' ', -- the required space |
|||
label, |
|||
'<span style="padding-left:0.15em">', -- signal spacing css |
|||
cfg.presentation[access], -- the appropriate icon |
|||
'</span>', -- close signal spacing span |
|||
']</span>' -- close url markup and plain links span |
|||
}); |
|||
else |
|||
base_url = table.concat({ "[", URL, " ", safe_for_url( label ), "]" }); -- no signal markup |
|||
end |
end |
||
return |
return base_url; |
||
end |
end |
||
Line 446: | Line 430: | ||
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 453: | Line 437: | ||
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 |
||
utilities.set_message ('err_deprecated_params', {name}); -- add error message |
|||
end |
end |
||
end |
end |
||
Line 460: | Line 444: | ||
--[=[-------------------------< 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 466: | Line 450: | ||
"'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 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- |
str = utilities.substitute (cfg.presentation['kern-left'], str); |
||
str = utilities.substitute (cfg.presentation['kern-right'], str); |
|||
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks |
elseif mw.ustring.match (str, '%[%[[\"“”\'‘’].+%]%]') then -- leading quote marks |
||
str = substitute (cfg.presentation['kern |
str = utilities.substitute (cfg.presentation['kern-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 |
str = utilities.substitute (cfg.presentation['kern-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 |
cap = 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'], |
label = utilities.substitute (cfg.presentation['kern-left'], cap); |
||
end |
end |
||
cap |
cap = 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'], |
label = utilities.substitute (cfg.presentation['kern-right'], cap); |
||
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 517: | Line 501: | ||
--[[--------------------------< 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 |
|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 531: | Line 515: | ||
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. |
||
Supports |script-title= |
Supports |script-title=, |script-chapter=, |script-<periodical>= |
||
TODO: error messages when prefix is invalid ISO639-1 code; when script_value has prefix but no script; |
|||
]] |
]] |
||
local function format_script_value (script_value) |
local function format_script_value (script_value, script_param) |
||
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 |
||
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing title part']}); -- 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 = 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 |
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 (' |
utilities.add_prop_cat ('script', {name, lang}) |
||
else |
else |
||
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['unknown language code']}); -- unknown script-language; add error message |
|||
add_prop_cat ('script') |
|||
end |
end |
||
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute |
lang = ' lang="' .. lang .. '" '; -- convert prefix into a lang attribute |
||
else |
else |
||
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['invalid language code']}); -- 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 |
|||
utilities.set_message ('err_script_parameter', {script_param, cfg.err_msg_supl['missing prefix']}); -- 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 558: | ||
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ |
--[[--------------------------< S C R I P T _ C O N C A T E N A T E >------------------------------------------ |
||
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script |
Initially for |title= and |script-title=, this function concatenates those two parameter values after the script |
||
wrapped in <bdi> tags. |
value has been wrapped in <bdi> tags. |
||
]] |
]] |
||
local function script_concatenate (title, script) |
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 = 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 595: | Line 583: | ||
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 601: | Line 589: | ||
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 |
|||
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, and |chapter-url= into a single Chapter meta- |
|||
label; nil else. |
|||
parameter (chapter_url_source used for error messages). |
|||
str is the value assigned to |chapter= (or aliases) or |title= or |title-link= |
|||
]] |
]] |
||
local function wikisource_url_make (str) |
|||
local function format_chapter_title (scriptchapter, chapter, transchapter, chapterurl, chapter_url_source, no_quotes, access) |
|||
local |
local wl_type, D, L; |
||
local ws_url, ws_label; |
|||
local wikisource_prefix = table.concat ({'https://', cfg.this_wiki_code, '.wikisource.org/wiki/'}); |
|||
if not is_set (chapter) then |
|||
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= |
|||
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
|||
if utilities.is_set (str) then |
|||
ws_url = table.concat ({ -- build a Wikisource URL |
|||
wikisource_prefix, -- prefix |
|||
str, -- article title |
|||
}); |
|||
ws_label = str; -- label for the URL |
|||
end |
|||
elseif 1 == wl_type then -- simple wikilink: [[Wikisource:ws article]] |
|||
str = D:match ('^[Ww]ikisource:(.+)') or D:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
|||
if utilities.is_set (str) then |
|||
ws_url = table.concat ({ -- build a Wikisource URL |
|||
wikisource_prefix, -- prefix |
|||
str, -- article title |
|||
}); |
|||
ws_label = str; -- label for the URL |
|||
end |
|||
elseif 2 == wl_type then -- non-so-simple wikilink: [[Wikisource:ws article|displayed text]] ([[L|D]]) |
|||
str = L:match ('^[Ww]ikisource:(.+)') or L:match ('^[Ss]:(.+)'); -- article title from interwiki link with long-form or short-form namespace |
|||
if utilities.is_set (str) then |
|||
ws_label = D; -- get ws article name from display portion of interwiki link |
|||
ws_url = table.concat ({ -- build a Wikisource URL |
|||
wikisource_prefix, -- prefix |
|||
str, -- article title without namespace from link portion of wikilink |
|||
}); |
|||
end |
|||
end |
|||
if ws_url then |
|||
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL |
|||
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker |
|||
end |
|||
return ws_url, ws_label, L or D; -- return proper URL or nil and a label or nil |
|||
end |
|||
--[[----------------< F O R M A T _ P E R I O D I C A L >----------------------- |
|||
Format the three periodical parameters: |script-<periodical>=, |<periodical>=, |
|||
and |trans-<periodical>= into a single Periodical meta-parameter. |
|||
]] |
|||
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) |
|||
if not utilities.is_set (periodical) then |
|||
periodical = ''; -- to be safe for concatenation |
|||
else |
|||
periodical = utilities.wrap_style ('italic-title', periodical); -- style |
|||
end |
|||
periodical = script_concatenate (periodical, script_periodical, script_periodical_source); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped |
|||
if utilities.is_set (trans_periodical) then |
|||
trans_periodical = utilities.wrap_style ('trans-italic-title', trans_periodical); |
|||
if utilities.is_set (periodical) then |
|||
periodical = periodical .. ' ' .. trans_periodical; |
|||
else -- here when trans-periodical without periodical or script-periodical |
|||
periodical = trans_periodical; |
|||
utilities.set_message ('err_trans_missing_title', {'periodical'}); |
|||
end |
|||
end |
|||
return periodical; |
|||
end |
|||
--[[------------------< F O R M A T _ C H A P T E R _ T I T L E >--------------- |
|||
Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, |
|||
and |chapter-url= into a single chapter meta- parameter (chapter_url_source used |
|||
for error messages). |
|||
]] |
|||
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access) |
|||
local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link |
|||
if ws_url then |
|||
ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters |
|||
chapter = ws_label; |
|||
end |
|||
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_url, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate |
|||
transchapter = wrap_style ('trans-quoted-title', transchapter); |
|||
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 = chapter .. ' ' .. transchapter; |
|||
chapter = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, chapter}); |
|||
else -- here when transchapter without chapter or script-chapter |
|||
chapter = transchapter; -- |
|||
chapter_error = ' ' .. set_error ('trans_missing_title', {'chapter'}); |
|||
end |
|||
end |
end |
||
if is_set ( |
if utilities.is_set (trans_chapter) then |
||
trans_chapter = utilities.wrap_style ('trans-quoted-title', trans_chapter); |
|||
chapter = external_link (chapterurl, chapter, chapter_url_source, access); -- adds bare_url_missing_title error if appropriate |
|||
if utilities.is_set (chapter) then |
|||
chapter = chapter .. ' ' .. trans_chapter; |
|||
else -- here when trans_chapter without chapter or script-chapter |
|||
chapter = trans_chapter; |
|||
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param> |
|||
utilities.set_message ('err_trans_missing_title', {chapter_source}); |
|||
end |
|||
end |
end |
||
return chapter |
return chapter; |
||
end |
end |
||
--[[ |
--[[----------------< H A S _ I N V I S I B L E _ C H A R S >------------------- |
||
This function searches a parameter's value for |
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 |
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 |
|||
Detects but ignores the character pattern that results from the transclusion of {{'}} templates. |
|||
Unicode group, or the stripmarker that was detected along with its position (or, |
|||
for multi-byte characters, the position of its first byte) in the parameter value. |
|||
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker |
|||
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the |
|||
parameter value. |
|||
]] |
]] |
||
Line 667: | Line 748: | ||
local function has_invisible_chars (param, v) |
local function has_invisible_chars (param, v) |
||
local position = ''; -- position of invisible char or starting position of stripmarker |
local position = ''; -- position of invisible char or starting position of stripmarker |
||
local dummy; -- end of matching string; not used but required to hold end position when a capture is returned |
|||
local capture; -- used by stripmarker detection to hold name of the stripmarker |
local capture; -- used by stripmarker detection to hold name of the stripmarker |
||
local stripmarker; -- boolean set true when a stripmarker is found |
|||
local i=1; |
|||
local stripmarker, apostrophe; |
|||
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true |
|||
capture = |
if capture == v then -- if same there are no Unicode characters |
||
if capture == v then -- if same there are no unicode characters |
|||
return; |
return; |
||
end |
end |
||
for _, invisible_char in ipairs (cfg.invisible_chars) do |
|||
local |
local char_name = invisible_char[1]; -- the character or group name |
||
local pattern= |
local pattern = invisible_char[2]; -- the pattern used to find it |
||
position, |
position, _, capture = mw.ustring.find (v, pattern); -- see if the parameter value contains characters that match the pattern |
||
if position and ( |
if position and (cfg.invisible_defs.zwj == capture) then -- if we found a zero-width joiner character |
||
if mw.ustring.find (v, cfg.indic_script) then -- |
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts |
||
position = nil; -- unset position |
|||
elseif cfg.emoji_t[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}? |
|||
position = nil; -- unset position |
position = nil; -- unset position |
||
end |
end |
||
Line 689: | Line 770: | ||
if position then |
if position then |
||
if 'nowiki' == capture or 'math' == capture |
if 'nowiki' == capture or 'math' == capture or -- nowiki and math stripmarkers (not an error condition) |
||
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters |
|||
stripmarker = true; -- set a flag |
|||
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 cfg.invisible_defs.del == capture then -- because stripmakers begin and end with the delete char, assume that we've found one end of a stripmarker |
|||
position = nil; -- unset |
position = nil; -- unset |
||
else |
else |
||
local err_msg; |
local err_msg; |
||
if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == capture) then |
|||
if capture then |
|||
err_msg = capture .. ' ' .. |
err_msg = capture .. ' ' .. char_name; |
||
else |
else |
||
err_msg = |
err_msg = char_name .. ' ' .. 'character'; |
||
end |
end |
||
utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}); -- add error message |
|||
return; -- and done with this parameter |
return; -- and done with this parameter |
||
end |
end |
||
end |
end |
||
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 |
Argument wrapper. This function provides support for argument mapping defined |
||
multiple names can be transparently aliased to |
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]; |
local dummy = self[k]; -- force the variable to be loaded. |
||
return origin[k]; |
return origin[k]; |
||
end |
end |
||
Line 735: | Line 817: | ||
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] = ''; |
origin[k] = ''; -- Empty string, not nil |
||
end |
end |
||
elseif list ~= nil then |
elseif list ~= nil then |
||
Line 744: | Line 826: | ||
-- maybe let through instead of raising an error? |
-- maybe let through instead of raising an error? |
||
-- v, origin[k] = args[k], k; |
-- v, origin[k] = args[k], k; |
||
error( cfg.messages['unknown_argument_map'] ); |
error( cfg.messages['unknown_argument_map'] .. ': ' .. k); |
||
end |
end |
||
-- 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 760: | Line 842: | ||
--[[--------------------------< |
--[[--------------------------< 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>. |
|||
Looks for a parameter's name in one of several whitelists. |
|||
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 |
|||
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 ) |
|||
local name = tostring( name ); |
|||
local state; |
|||
if in_array (cite_class, {'arxiv', 'biorxiv', 'citeseerx'}) then -- limited parameter sets allowed for these templates |
|||
state = whitelist.limited_basic_arguments[ name ]; |
|||
if true == state then return true; end -- valid actively supported parameter |
|||
if false == state then |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
return true; |
|||
end |
|||
if 'arxiv' == cite_class then -- basic parameters unique to these templates |
|||
state = whitelist.arxiv_basic_arguments[name]; |
|||
end |
|||
if 'biorxiv' == cite_class then |
|||
state = whitelist.biorxiv_basic_arguments[name]; |
|||
end |
|||
if 'citeseerx' == cite_class then |
|||
state = whitelist.citeseerx_basic_arguments[name]; |
|||
end |
|||
if true == state then return true; end -- valid actively supported parameter |
|||
if false == state then |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
return true; |
|||
end |
|||
-- limited enumerated parameters list |
|||
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) |
|||
state = whitelist.limited_numbered_arguments[ name ]; |
|||
if true == state then return true; end -- valid actively supported parameter |
|||
if false == state then |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
return true; |
|||
end |
|||
return false; -- not supported because not found or name is set to nil |
|||
end -- end limited parameter-set templates |
|||
state = whitelist.basic_arguments[ name ]; -- all other templates; all normal parameters allowed |
|||
if true == state then return true; end -- valid actively supported parameter |
|||
if false == state then |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
return true; |
|||
end |
|||
-- all enumerated parameters allowed |
|||
name = name:gsub( "%d+", "#" ); -- replace digit(s) with # (last25 becomes last# |
|||
state = whitelist.numbered_arguments[ name ]; |
|||
if true == state then return true; end -- valid actively supported parameter |
|||
if false == state then |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
return true; |
|||
end |
|||
return false; -- not supported because not found or name is set to nil |
|||
end |
|||
--[[--------------------------< N O W R A P _ D A T E >-------------------------------------------------------- |
|||
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. When date is DD MMMM YYYY or is |
|||
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY |
|||
DOES NOT yet support MMMM YYYY or any of the date ranges. |
DOES NOT yet support MMMM YYYY or any of the date ranges. |
||
Line 841: | Line 853: | ||
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 856: | Line 868: | ||
--[[--------------------------< 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 |
This function sets default title types (equivalent to the citation including |
||
|type=<default value>) for those templates that have defaults. Also handles the |
|||
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none). |
|||
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 875: | Line 889: | ||
--[[--------------------------< |
--[[--------------------------< S A F E _ J O I N >----------------------------- |
||
Converts a hyphen to a dash |
|||
]] |
|||
local function hyphen_to_dash( str ) |
|||
if not is_set(str) or str:match( "[%[%]{}<>]" ) ~= nil then |
|||
return str; |
|||
end |
|||
return str:gsub( '-', '–' ); |
|||
end |
|||
--[[--------------------------< S A F E _ J O I N >------------------------------------------------------------ |
|||
Joins a sequence of strings together while checking for duplicate separation characters. |
Joins a sequence of strings together while checking for duplicate separation characters. |
||
Line 896: | Line 896: | ||
local function safe_join( tbl, duplicate_char ) |
local function safe_join( tbl, duplicate_char ) |
||
local f = {}; -- create a function table appropriate to type of 'duplicate character' |
|||
--[[ |
|||
if 1 == #duplicate_char then -- for single byte ASCII characters use the string library functions |
|||
Note: we use string functions here, rather than ustring functions. |
|||
f.gsub = string.gsub |
|||
f.match = string.match |
|||
This has considerably faster performance and should work correctly as |
|||
f.sub = string.sub |
|||
long as the duplicate_char is strict ASCII. The strings |
|||
else -- for multi-byte characters use the ustring library functions |
|||
in tbl may be ASCII or UTF8. |
|||
f.gsub = mw.ustring.gsub |
|||
]] |
|||
f.match = mw.ustring.match |
|||
f.sub = mw.ustring.sub |
|||
end |
|||
local str = ''; -- the output string |
local str = ''; -- the output string |
||
local comp = ''; -- what does 'comp' mean? |
local comp = ''; -- what does 'comp' mean? |
||
Line 914: | Line 917: | ||
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 |
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 |
-- 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 = |
end_chr = f.sub(str, -1, -1); -- get the last character of the output string |
||
-- str = str .. "<HERE(enchr=" .. end_chr.. ")" |
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff? |
||
if end_chr == duplicate_char then -- if same as separator |
if end_chr == duplicate_char then -- if same as separator |
||
str = |
str = 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 |
if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' |
||
str = |
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' |
||
elseif |
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 |
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 |
if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink |
||
trim = true; |
trim = true; |
||
elseif |
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link |
||
trim = true; |
trim = true; |
||
elseif |
elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link |
||
trim = true; |
trim = true; |
||
elseif |
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 |
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> |
||
str = |
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 |
if f.match(dup2, "%A" ) then dup2 = "%" .. dup2; end -- if duplicate_char not a letter then escape it |
||
value = |
value = f.gsub(value, "(%b<>)" .. dup2, "%1", 1 ) -- remove duplicate_char if it follows HTML markup |
||
else |
else |
||
value = |
value = f.sub(value, 2, -1 ); -- remove duplicate_char when it is first character |
||
end |
end |
||
end |
end |
||
end |
end |
||
str = str .. value; |
str = str .. value; -- add it to the output string |
||
end |
end |
||
end |
end |
||
return str; |
return str; |
||
end |
end |
||
--[[--------------------------< I S _ S U F F I X > |
--[[--------------------------< I S _ S U F F I X >----------------------------- |
||
returns true |
returns true if 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 984: | Line 988: | ||
--[[ |
--[[--------------------< 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 |
||
(read ASCII) characters. When a name uses characters that contain diacritical |
|||
marks, those characters are to be converted to the corresponding Latin |
|||
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters. |
|||
character. When a name is written using a non-Latin alphabet or logogram, that |
|||
These things are not currently possible in this module so are left to the editor to do. |
|||
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 |
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 997: | Line 1,004: | ||
[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. |
|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%']*$") |
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") |
||
or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then |
|||
was written ouside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position. |
|||
was written outside of the code editor and pasted here because the code editor |
|||
The test has been rewritten to use decimal character escape sequence for the individual bytes of the unicode characters so that it is not necessary |
|||
gets confused between character insertion point and cursor position. The test has |
|||
to use an external editor to maintain this code. |
|||
been rewritten to use decimal character escape sequence for the individual bytes |
|||
of the Unicode characters so that it is not necessary to use an external editor |
|||
to maintain this code. |
|||
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) |
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) |
||
Line 1,013: | Line 1,024: | ||
]] |
]] |
||
local function is_good_vanc_name (last, first) |
local function is_good_vanc_name (last, first, suffix, position) |
||
if not suffix then |
|||
local first, suffix = first:match ('(.-),?%s*([%dJS][%drndth]+)%.?$') or first; -- if first has something that looks like a generational suffix, get it |
|||
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix |
|||
first = first:match ('(.-)[,%s]+'); -- get name/initials |
|||
if is_set (suffix) then |
|||
suffix = first:match ('[,%s]+(.+)$'); -- get generational suffix |
|||
end |
|||
end |
|||
if utilities.is_set (suffix) then |
|||
if not is_suffix (suffix) then |
if not is_suffix (suffix) then |
||
add_vanc_error ( |
add_vanc_error (cfg.err_msg_supl.suffix, position); |
||
return false; -- not a name with an appropriate suffix |
return false; -- not a name with an appropriate suffix |
||
end |
end |
||
Line 1,024: | Line 1,039: | ||
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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%'%.]*$") then |
||
add_vanc_error ('non-Latin |
add_vanc_error (cfg.err_msg_supl['non-Latin char'], position); |
||
return false; -- not a string of |
return false; -- not a string of Latin characters; Vancouver requires Romanization |
||
end; |
end; |
||
return true; |
return true; |
||
Line 1,033: | Line 1,048: | ||
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------ |
||
Attempts to convert names to initials in support of |name-list- |
Attempts to convert names to initials in support of |name-list-style=vanc. |
||
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period |
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. |
||
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. |
|||
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered |
Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered |
||
as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. |
|||
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. |
|||
This code only accepts and understands generational suffix in the Vancouver format |
|||
because Roman numerals look like, and can be mistaken for, initials. |
|||
This function uses ustring functions because firstname initials may be any of the |
This function uses ustring functions because firstname initials may be any of the |
||
Unicode Latin characters accepted by is_good_vanc_name (). |
|||
]] |
]] |
||
local function reduce_to_initials(first) |
local function reduce_to_initials(first, position) |
||
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$"); |
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$"); |
||
if not name then -- if not initials and a suffix |
if not name then -- if not initials and a suffix |
||
name = mw.ustring.match(first, "^(%u+)$"); -- is it just |
name = mw.ustring.match(first, "^(%u+)$"); -- is it just initials? |
||
end |
end |
||
Line 1,057: | Line 1,076: | ||
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, position); -- 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 1,065: | Line 1,084: | ||
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 1,081: | Line 1,099: | ||
end |
end |
||
if 3 > i then |
if 3 > i then |
||
table.insert (initials, mw.ustring.sub(names[i],1,1)); |
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 1,090: | Line 1,108: | ||
--[[--------------------------< |
--[[--------------------------< I N T E R W I K I _ P R E F I X E N _ G E T >---------------------------------- |
||
extract interwiki prefixen from <value>. Returns two one or two values: |
|||
Formats a list of people (e.g. authors / editors) |
|||
false – no prefixen |
|||
nil – prefix exists but not recognized |
|||
project prefix, language prefix – when value has either of: |
|||
:<project>:<language>:<article> |
|||
:<language>:<project>:<article> |
|||
project prefix, nil – when <value> has only a known single-letter prefix |
|||
nil, language prefix – when <value> has only a known language prefix |
|||
accepts single-letter project prefixen: 'd' (wikidata), 's' (wikisource), and 'w' (wikipedia) prefixes; at this |
|||
writing, the other single-letter prefixen (b (wikibook), c (commons), m (meta), n (wikinews), q (wikiquote), and |
|||
v (wikiversity)) are not supported. |
|||
]] |
|||
local function interwiki_prefixen_get (value, is_link) |
|||
if not value:find (':%l+:') then -- if no prefix |
|||
return false; -- abandon; boolean here to distinguish from nil fail returns later |
|||
end |
|||
local prefix_patterns_linked_t = { -- sequence of valid interwiki and inter project prefixen |
|||
'^%[%[:([dsw]):(%l%l+):', -- wikilinked; project and language prefixes |
|||
'^%[%[:(%l%l+):([dsw]):', -- wikilinked; language and project prefixes |
|||
'^%[%[:([dsw]):', -- wikilinked; project prefix |
|||
'^%[%[:(%l%l+):', -- wikilinked; language prefix |
|||
} |
|||
local prefix_patterns_unlinked_t = { -- sequence of valid interwiki and inter project prefixen |
|||
'^:([dsw]):(%l%l+):', -- project and language prefixes |
|||
'^:(%l%l+):([dsw]):', -- language and project prefixes |
|||
'^:([dsw]):', -- project prefix |
|||
'^:(%l%l+):', -- language prefix |
|||
} |
|||
local cap1, cap2; |
|||
for _, pattern in ipairs ((is_link and prefix_patterns_linked_t) or prefix_patterns_unlinked_t) do |
|||
cap1, cap2 = value:match (pattern); |
|||
if cap1 then |
|||
break; -- found a match so stop looking |
|||
end |
|||
end |
|||
if cap1 and cap2 then -- when both then :project:language: or :language:project: (both forms allowed) |
|||
if 1 == #cap1 then -- length == 1 then :project:language: |
|||
if cfg.inter_wiki_map[cap2] then -- is language prefix in the interwiki map? |
|||
return cap1, cap2; -- return interwiki project and interwiki language |
|||
end |
|||
else -- here when :language:project: |
|||
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map? |
|||
return cap2, cap1; -- return interwiki project and interwiki language |
|||
end |
|||
end |
|||
return nil; -- unknown interwiki language |
|||
elseif not (cap1 or cap2) then -- both are nil? |
|||
return nil; -- we got something that looks like a project prefix but isn't; return fail |
|||
elseif 1 == #cap1 then -- here when one capture |
|||
return cap1, nil; -- length is 1 so return project, nil language |
|||
else -- here when one capture and its length it more than 1 |
|||
if cfg.inter_wiki_map[cap1] then -- is language prefix in the interwiki map? |
|||
return nil, cap1; -- return nil project, language |
|||
end |
|||
end |
|||
end |
|||
--[[--------------------------< L I S T _ P E O P L E >-------------------------- |
|||
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 |
local name_list = {}; |
||
local text = {} |
|||
if 'vanc' == format then -- Vancouver-like |
if 'vanc' == format then -- Vancouver-like name styling? |
||
sep = ' |
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma |
||
namesep = ' |
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space |
||
else |
else |
||
sep = '; |
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon |
||
namesep = ' |
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 |
|||
elseif (mask ~= nil) then |
|||
local n = tonumber(mask) |
|||
if mask then |
|||
local n = tonumber (mask); -- convert to a number if it can be converted; nil else |
|||
one = string.rep("—",n) |
|||
if n then |
|||
one = 0 ~= n and string.rep("—", n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name |
|||
person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil |
|||
else |
else |
||
one = mask; -- replace name with mask text (must include name-list separator) |
|||
one = mask; |
|||
sep_one = " "; |
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 ( |
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, nil, i) then -- and name is all Latin characters; corporate authors not tested |
||
first = reduce_to_initials(first) |
first = reduce_to_initials (first, i); -- attempt to convert first name(s) to initials |
||
end |
end |
||
end |
end |
||
one = one .. namesep .. first; |
one = one .. namesep .. first; |
||
end |
end |
||
end |
|||
if is_set(person.link) and person.link ~= control.page_name then |
|||
if utilities.is_set (person.link) then |
|||
one = make_wikilink (person.link, one); -- link author/editor if this page is not the author's/editor's page |
|||
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) |
|||
local proj, tag = interwiki_prefixen_get (one, true); -- get the interwiki prefixen if present |
|||
if 'w' == proj and ('Wikipedia' == mw.site.namespaces.Project['name']) then |
|||
proj = nil; -- for stuff like :w:de:<article>, :w is unnecessary TODO: maint cat? |
|||
end |
end |
||
if proj then |
|||
proj = ({['d'] = 'Wikidata', ['s'] = 'Wikisource', ['w'] = 'Wikipedia'})[proj]; -- :w (wikipedia) for linking from a non-wikipedia project |
|||
if proj then |
|||
one = one .. utilities.wrap_style ('interproj', proj); -- add resized leading space, brackets, static text, language name |
|||
tag = nil; -- unset; don't do both project and language |
|||
end |
|||
end |
|||
if tag == cfg.this_wiki_code then |
|||
tag = nil; -- stuff like :en:<article> at en.wiki is pointless TODO: maint cat? |
|||
end |
|||
if tag then |
|||
local lang = cfg.lang_code_remap[tag] or cfg.mw_languages_by_tag_t[tag]; |
|||
if lang then -- error messaging done in extract_names() where we know parameter names |
|||
one = one .. utilities.wrap_style ('interwiki', lang); -- add resized leading space, brackets, static text, language name |
|||
end |
|||
end |
|||
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 |
||
table.insert( text, one ) |
|||
table.insert( text, sep_one ) |
|||
end |
end |
||
end |
end |
||
local count = # |
local count = #name_list / 2; -- (number of names + number of separators) divided by 2 |
||
if |
if 0 < count then |
||
if |
if 1 < count and not etal then |
||
if 'amp' == format then |
|||
text[#text-2] = " & "; -- replace last separator with ampersand text |
|||
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 name-list string and count of number of names (count used for editor names only) |
|||
return result, count |
|||
end |
end |
||
--[[ |
--[[--------------------< M A K E _ C I T E R E F _ I D >----------------------- |
||
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise |
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 |
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 make_citeref_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 |
|||
for i,v in ipairs (namelist) do -- loop through the list and take up to the first four last names |
|||
names[i] = v.last |
|||
names[i] = v.last |
|||
if i == 4 then break end -- if four then done |
|||
if i == 4 then break end -- if four then done |
|||
end |
end |
||
table.insert (names, year); |
table.insert (names, year); -- add the year at the end |
||
local id = table.concat(names); |
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; |
return "CITEREF" .. id; -- add the CITEREF portion |
||
else |
else |
||
return ''; |
return ''; -- return an empty string; no reason to include CITEREF id in this citation |
||
end |
end |
||
end |
end |
||
--[[--------------------------< |
--[[--------------------------< C I T E _ C L A S S _A T T R I B U T E _M A K E >------------------------------ |
||
construct <cite> tag class attribute for this citation. |
|||
Evaluates the content of author and editor name parameters for variations on the theme of et al. If found, |
|||
the et al. is removed, a flag is set to true and the function returns the modified name and the flag. |
|||
<cite_class> – config.CitationClass from calling template |
|||
This function never sets the flag to false but returns it's previous state because it may have been set by |
|||
<mode> – value from |mode= parameter |
|||
previous passes through this function or by the parameters |display-authors=etal or |display-editors=etal |
|||
]] |
]] |
||
local function |
local function cite_class_attribute_make (cite_class, mode) |
||
local class_t = {}; |
|||
table.insert (class_t, 'citation'); -- required for blue highlight |
|||
if 'citation' ~= cite_class then |
|||
table.insert (class_t, cite_class); -- identify this template for user css |
|||
table.insert (class_t, utilities.is_set (mode) and mode or 'cs1'); -- identify the citation style for user css or javascript |
|||
else |
|||
table.insert (class_t, utilities.is_set (mode) and mode or 'cs2'); -- identify the citation style for user css or javascript |
|||
end |
|||
for _, prop_key in ipairs (z.prop_keys_t) do |
|||
table.insert (class_t, prop_key); -- identify various properties for user css or javascript |
|||
end |
|||
return table.concat (class_t, ' '); -- make a big string and done |
|||
end |
|||
--[[---------------------< N A M E _ H A S _ E T A L >-------------------------- |
|||
Evaluates the content of name parameters (author, editor, etc.) for variations on |
|||
the theme of et al. If found, the et al. is removed, a flag is set to true and |
|||
the function returns the modified name and the flag. |
|||
This function never sets the flag to false but returns its previous state because |
|||
it may have been set by previous passes through this function or by the associated |
|||
|display-<names>=etal parameter |
|||
]] |
|||
local function name_has_etal (name, etal, nocat, param) |
|||
if 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; -- get patterns from configuration |
|||
local etal_pattern = "[;,]? *[\"']*%f[%a][Ee][Tt] *[Aa][Ll][%.\"']*$" -- variations on the 'et al' theme |
|||
local others_pattern = "[;,]? *%f[%a]and [Oo]thers"; -- and alternate to et al. |
|||
for _, pattern in ipairs (patterns) do -- loop through all of the patterns |
|||
if name:match (pattern) then -- if this 'et al' pattern is found in name |
|||
name = name:gsub (pattern, ''); -- remove the offending text |
|||
etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
|||
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) |
|||
if not nocat then -- no categorization for |vauthors= |
|||
utilities.set_message ('err_etal', {param}); -- and set an error if not added |
|||
end |
|||
end |
|||
elseif name:match (others_pattern) then -- if not 'et al.', then 'and others'? |
|||
name = name:gsub (others_pattern, ''); -- if found, remove |
|||
etal = true; -- set flag (may have been set previously here or by |display-authors=etal) |
|||
if not nocat then -- no categorization for |vauthors= |
|||
add_maint_cat ('etal'); -- and add a category if not already added |
|||
end |
end |
||
end |
end |
||
end |
end |
||
return name, etal; -- |
|||
return name, etal; |
|||
end |
end |
||
--[[ |
--[[---------------------< N A M E _ I S _ N U M E R I C >---------------------- |
||
Add maint cat when name parameter value does not contain letters. Does not catch |
|||
Evaluates the content of author and editor parameters for extranious editor annotations: ed, ed., eds, (Ed.), etc. |
|||
mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the |
|||
These annotation do not belong in author parameters and are redundant in editor parameters. If found, the function |
|||
current version of this test but |first=(1888) is caught. |
|||
adds the editor markup maintenance category. |
|||
returns nothing |
|||
]] |
]] |
||
local function |
local function name_is_numeric (name, list_name) |
||
if utilities.is_set (name) then |
|||
local _, pattern; |
|||
if mw.ustring.match (name, '^[%A]+$') then -- when name does not contain any letters |
|||
local patterns = { -- these patterns match annotations at end of name |
|||
utilities.set_message ('maint_numeric_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template |
|||
'%f[%(%[][%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]?$', -- (ed) or (eds): leading '(', case insensitive 'ed', optional 's', '.' and/or ')' |
|||
end |
|||
'[,%.%s]%f[e]eds?%.?$', -- ed or eds: without '('or ')'; case sensitive (ED could be initials Ed could be name) |
|||
end |
|||
'%f[%(%[][%(%[]%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?%s*[%)%]]?$', -- (editor) or (editors): leading '(', case insensitive, optional '.' and/or ')' |
|||
end |
|||
'[,%.%s]%f[Ee][Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%.?$', -- editor or editors: without '('or ')'; case insensitive |
|||
--[[-----------------< N A M E _ H A S _ M U L T _ N A M E S >------------------ |
|||
Evaluates the content of last/surname (authors etc.) parameters for multiple names. |
|||
Multiple names are indicated if there is more than one comma or any "unescaped" |
|||
semicolons. Escaped semicolons are ones used as part of selected HTML entities. |
|||
If the condition is met, the function adds the multiple name maintenance category. |
|||
returns nothing |
|||
]] |
|||
local function name_has_mult_names (name, list_name) |
|||
local _, commas, semicolons, nbsps; |
|||
if utilities.is_set (name) then |
|||
_, commas = name:gsub (',', ''); -- count the number of commas |
|||
_, semicolons = name:gsub (';', ''); -- count the number of semicolons |
|||
-- nbsps probably should be its own separate count rather than merged in |
|||
-- some way with semicolons because Lua patterns do not support the |
|||
-- grouping operator that regex does, which means there is no way to add |
|||
-- more entities to escape except by adding more counts with the new |
|||
-- entities |
|||
_, nbsps = name:gsub (' ',''); -- count nbsps |
|||
-- There is exactly 1 semicolon per entity, so subtract nbsps |
|||
-- these patterns match annotations at beginning of name |
|||
-- from semicolons to 'escape' them. If additional entities are added, |
|||
'^eds?[%.,;]', -- ed. or eds.: lower case only, optional 's', requires '.' |
|||
-- they also can be subtracted. |
|||
'^[%(%[]%s*[Ee][Dd][Ss]?%.?%s*[%)%]]', -- (ed) or (eds): also sqare brackets, case insensitive, optional 's', '.' |
|||
if 1 < commas or 0 < (semicolons - nbsps) then |
|||
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Oo][Rr][Ss]?%A', -- (editor or (editors: also sq brackets, case insensitive, optional brackets, 's' |
|||
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message |
|||
'^[%(%[]?%s*[Ee][Dd][Ii][Tt][Ee][Dd]%A', -- (edited: also sq brackets, case insensitive, optional brackets |
|||
end |
|||
end |
|||
end |
|||
--[=[-------------------------< I S _ G E N E R I C >---------------------------------------------------------- |
|||
Compares values assigned to various parameters according to the string provided as <item> in the function call. |
|||
<item> can have on of two values: |
|||
'generic_names' – for name-holding parameters: |last=, |first=, |editor-last=, etc |
|||
'generic_titles' – for |title= |
|||
There are two types of generic tests. The 'accept' tests look for a pattern that should not be rejected by the |
|||
'reject' test. For example, |
|||
|author=[[John Smith (author)|Smith, John]] |
|||
would be rejected by the 'author' reject test. But piped wikilinks with 'author' disambiguation should not be |
|||
rejected so the 'accept' test prevents that from happening. Accept tests are always performed before reject |
|||
tests. |
|||
Each of the 'accept' and 'reject' sequence tables hold tables for en.wiki (['en']) and local.wiki (['local']) |
|||
that each can hold a test sequence table The sequence table holds, at index [1], a test pattern, and, at index |
|||
[2], a boolean control value. The control value 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. |
|||
Returns |
|||
true when a reject test finds the pattern or string |
|||
false when an accept test finds the pattern or string |
|||
nil else |
|||
]=] |
|||
local function is_generic (item, value, wiki) |
|||
local test_val; |
|||
local str_lower = { -- use string.lower() for en.wiki (['en']) and use mw.ustring.lower() or local.wiki (['local']) |
|||
['en'] = string.lower, |
|||
['local'] = mw.ustring.lower, |
|||
} |
|||
local str_find = { -- use string.find() for en.wiki (['en']) and use mw.ustring.find() or local.wiki (['local']) |
|||
['en'] = string.find, |
|||
['local'] = mw.ustring.find, |
|||
} |
} |
||
local function test (val, test_t, wiki) -- local function to do the testing; <wiki> selects lower() and find() functions |
|||
if is_set (name) then |
|||
val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value |
|||
for _, pattern in ipairs (patterns) do -- spin through patterns table and |
|||
return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched |
|||
if name:match (pattern) then |
|||
end |
|||
add_maint_cat ('extra_text_names', cfg.special_case_translation [list_name]); -- add a maint cat for this template |
|||
break; |
|||
local test_types_t = {'accept', 'reject'}; -- test accept patterns first, then reject patterns |
|||
local wikis_t = {'en', 'local'}; -- do tests for each of these keys; en.wiki first, local.wiki second |
|||
for _, test_type in ipairs (test_types_t) do -- for each test type |
|||
for _, generic_value in pairs (cfg.special_case_translation[item][test_type]) do -- spin through the list of generic value fragments to accept or reject |
|||
for _, wiki in ipairs (wikis_t) do |
|||
if generic_value[wiki] then |
|||
if test (value, generic_value[wiki], wiki) then -- go do the test |
|||
return ('reject' == test_type); -- param value rejected, return true; false else |
|||
end |
|||
end |
|||
end |
end |
||
end |
end |
||
end |
end |
||
return name; -- and done |
|||
end |
end |
||
--[[--------------------------< N A M E _ |
--[[--------------------------< N A M E _ I S _ G E N E R I C >------------------------------------------------ |
||
calls is_generic() to determine if <name> is a 'generic name' listed in cfg.generic_names; <name_alias> is the |
|||
Evaluates the content of author and editor (surnames only) parameters for multiple names. Multiple names are |
|||
parameter name used in error messaging |
|||
indicated if there is more than one comma and or semicolon. If found, the function adds the multiple name |
|||
(author or editor) maintenance category. |
|||
]] |
]] |
||
local function |
local function name_is_generic (name, name_alias) |
||
if not added_generic_name_errs and is_generic ('generic_names', name) then |
|||
local count, _; |
|||
utilities.set_message ('err_generic_name', name_alias); -- set an error message |
|||
if is_set (name) then |
|||
added_generic_name_errs = true; |
|||
_, count = name:gsub ('[;,]', ''); -- count the number of separator-like characters |
|||
if 1 < count then -- param could be |author= or |editor= so one separator character is acceptable |
|||
add_maint_cat ('mult_names', cfg.special_case_translation [list_name]); -- more than one separator indicates multiple names so add a maint cat for this template |
|||
end |
|||
end |
end |
||
return name; -- and done |
|||
end |
end |
||
--[[--------------------------< N A M E _ C H E C K S >-------------------------------------------------------- |
--[[--------------------------< 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 |
|||
This function calls various name checking functions used to validate the content of the various name-holding parameters. |
|||
parameters. |
|||
]] |
]] |
||
local function name_checks (last, first, list_name) |
local function name_checks (last, first, list_name, last_alias, first_alias) |
||
local accept_name; |
|||
if is_set (last) then |
|||
if last:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
|||
if utilities.is_set (last) then |
|||
last = last:match ('^%(%((.*)%)%)$'); -- strip parens |
|||
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last> |
|||
else |
|||
last = name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) |
|||
if not accept_name then -- <last> not wrapped in accept-as-written markup |
|||
last = name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation |
|||
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) |
|||
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation |
|||
name_is_generic (last, last_alias); -- check for names found in the generic names list |
|||
end |
end |
||
end |
end |
||
if is_set (first) then |
|||
if utilities.is_set (first) then |
|||
if first:match ('^%(%(.*%)%)$') then -- if wrapped in doubled parentheses, accept as written |
|||
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> |
|||
first = first:match ('^%(%((.*)%)%)$'); -- strip parens |
|||
else |
|||
if not accept_name then -- <first> not wrapped in accept-as-written markup |
|||
first = 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 |
|||
name_is_generic (first, first_alias); -- check for names found in the generic names list |
|||
end |
|||
local wl_type, D = utilities.is_wikilink (first); |
|||
if 0 ~= wl_type then |
|||
first = D; |
|||
utilities.set_message ('err_bad_paramlink', first_alias); |
|||
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 |
Searches through args in sequential order to find |lastn= and |firstn= parameters |
||
(or their aliases), and their matching link and mask parameters. Stops searching |
|||
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't |
|||
when both |lastn= and |firstn= are not found in args after two sequential attempts: |
|||
find |last4= and |last5= then the search is done. |
|||
found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the |
|||
search is done. |
|||
This function emits an error message when there is a |firstn= without a matching |
This function emits an error message when there is a |firstn= without a matching |
||
|lastn=. When there are 'holes' in the list of last names, |last1= and |last3= |
|||
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. |
|||
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.' |
When an author or editor parameter contains some form of 'et al.', the 'et al.' |
||
is stripped from the parameter and a flag (etal) returned that will cause list_people() |
|||
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the |
|||
to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps |
|||
template's metadata. When this occurs, the page is added to a maintenance category. |
|||
'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 = {}; -- table of names |
local names = {}; -- table of names |
||
local last; -- individual name components |
local last; -- individual name components |
||
local first; |
local first; |
||
local link; |
local link; |
||
local mask; |
local mask; |
||
local i = 1; -- loop counter/indexer |
local i = 1; -- loop counter/indexer |
||
local n = 1; -- output table indexer |
local n = 1; -- output table indexer |
||
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors) |
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors) |
||
local etal=false; -- return value set to true when we find some form of et al. in an author parameter |
local etal = false; -- return value set to true when we find some form of et al. in an author parameter |
||
local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging |
|||
local err_msg_list_name = list_name:match ("(%w+)List") .. 's list'; -- modify AuthorList or EditorList for use in error messages if necessary |
|||
while true do |
while true do |
||
last = 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 = 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 ); |
||
if last then -- error check |lastn= alias for unknown interwiki link prefix; done here because this is where we have the parameter name |
|||
last, etal = name_has_etal (last, etal, false); -- find and remove variations on et al. |
|||
local project, language = interwiki_prefixen_get (last, true); -- true because we expect interwiki links in |lastn= to be wikilinked |
|||
first, etal = name_has_etal (first, etal, false); -- find and remove variations on et al. |
|||
if nil == project and nil == language then -- when both are nil |
|||
last, first= name_checks (last, first, list_name); -- multiple names, extraneous annotation, etc checks |
|||
utilities.set_message ('err_bad_paramlink', last_alias); -- not known, emit an error message -- TODO: err_bad_interwiki? |
|||
last = utilities.remove_wiki_link (last); -- remove wikilink markup; show display value only |
|||
end |
|||
end |
|||
if link then -- error check |linkn= alias for unknown interwiki link prefix |
|||
local project, language = interwiki_prefixen_get (link, false); -- false because wiki links in |author-linkn= is an error |
|||
if nil == project and nil == language then -- when both are nil |
|||
utilities.set_message ('err_bad_paramlink', link_alias); -- not known, emit an error message -- TODO: err_bad_interwiki? |
|||
link = nil; -- unset so we don't link |
|||
link_alias = nil; |
|||
end |
|||
end |
|||
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. |
|||
last, first = name_checks (last, first, list_name, last_alias, first_alias); -- 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 |
||
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, { set_error( 'first_missing_last', {err_msg_list_name, i}, true ) } ); -- add this error message |
|||
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 |
|||
}); -- 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 1,354: | Line 1,618: | ||
end |
end |
||
else -- we have last with or without a first |
else -- we have last with or without a first |
||
local result; |
|||
link_title_ok (link, list_name:match ("(%w+)List"):lower() .. '-link' .. i, last, list_name:match ("(%w+)List"):lower() .. '-last' .. i); -- check for improper wikimarkup |
|||
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup |
|||
if first then |
|||
names[n] = {last = last, first = first, link = link, mask = mask, corporate=false}; -- add this name to our names list (corporate for |vauthors= only) |
|||
link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup |
|||
end |
|||
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only) |
|||
n = n + 1; -- point to next location in the names table |
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 |
||
utilities.set_message ('err_missing_name', {list_name:match ("(%w+)List"):lower(), i - 1}); -- 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 1,366: | Line 1,635: | ||
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 |
||
--[[--------------------------< |
--[[--------------------------< N A M E _ T A G _ G E T >------------------------------------------------------ |
||
attempt to decode |language=<lang_param> and return language name and matching tag; nil else. |
|||
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. |
|||
This function looks for: |
|||
Returns the language name and associated two- or three-character code. Because case of the source may be incorrect |
|||
<lang_param> as a tag in cfg.lang_code_remap{} |
|||
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is |
|||
<lang_param> as a name in cfg.lang_name_remap{} |
|||
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we |
|||
return the original language name string. |
|||
<lang_param> as a name in cfg.mw_languages_by_name_t |
|||
<lang_param> as a tag in cfg.mw_languages_by_tag_t |
|||
when those fail, presume that <lang_param> is an IETF-like tag that MediaWiki does not recognize. Strip all |
|||
script, region, variant, whatever subtags from <lang_param> to leave just a two or three character language tag |
|||
and look for the new <lang_param> in cfg.mw_languages_by_tag_t{} |
|||
on success, returns name (in properly capitalized form) and matching tag (in lowercase); on failure returns nil |
|||
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include |
|||
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support |
|||
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they |
|||
are used as sub-domain names: cbk-zam.wikipedia.org. These names can be found (for the time being) at |
|||
https://phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEn.php |
|||
]] |
|||
Names but that are included in the list will be found if that name is provided in the |language= parameter. For example, |
|||
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found |
|||
and the associated code is not two or three characters, this function returns only the Wikimedia language name. |
|||
local function name_tag_get (lang_param) |
|||
Adapted from code taken from Module:Check ISO 639-1. |
|||
local lang_param_lc = mw.ustring.lower (lang_param); -- use lowercase as an index into the various tables |
|||
local name; |
|||
local tag; |
|||
name = cfg.lang_code_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name |
|||
]] |
|||
if name then -- when <name>, <lang_param> is a tag for a remapped language name |
|||
return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc> |
|||
end |
|||
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags |
|||
name = cfg.lang_code_remap[tag]; -- attempt to get remapped language name with language subtag only |
|||
if name then -- when <name>, <tag> is a tag for a remapped language name |
|||
return name, tag; -- so return <name> from remap and <tag> |
|||
end |
|||
if cfg.lang_name_remap[lang_param_lc] then -- not a tag, assume <lang_param_lc> is a name; attempt to get remapped language tag |
|||
return cfg.lang_name_remap[lang_param_lc][1], cfg.lang_name_remap[lang_param_lc][2]; -- for this <lang_param_lc>, return a (possibly) new name and appropriate tag |
|||
end |
|||
tag = cfg.mw_languages_by_name_t[lang_param_lc]; -- assume that <lang_param_lc> is a language name; attempt to get its matching tag |
|||
local function get_iso639_code (lang, this_wiki_code) |
|||
local remap = { |
|||
['bangla'] = {'Bengali', 'bn'}, -- MediaWiki returns Bangla (the endonym) but we want Bengali (the exonym); here we remap |
|||
['bengali'] = {'Bengali', 'bn'}, -- MediaWiki doesn't use exonym so here we provide correct language name and 639-1 code |
|||
['bihari'] = {'Bihari', 'bh'}, -- MediaWiki replace 'Bihari' with 'Bhojpuri' so 'Bihari' cannot be found |
|||
['bhojpuri'] = {'Bhojpuri', 'bho'}, -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org |
|||
} |
|||
if |
if tag then |
||
return |
return cfg.mw_languages_by_tag_t[tag], tag; -- <lang_param_lc> is a name so return the name from the table and <tag> |
||
end |
end |
||
name = cfg.mw_languages_by_tag_t[lang_param_lc]; -- assume that <lang_param_lc> is a tag; attempt to get its matching language name |
|||
local languages = mw.language.fetchLanguageNames(this_wiki_code, 'all') -- get a list of language names known to Wikimedia |
|||
-- ('all' is required for North Ndebele, South Ndebele, and Ojibwa) |
|||
local langlc = mw.ustring.lower(lang); -- lower case version for comparisons |
|||
if name then |
|||
for code, name in pairs(languages) do -- scan the list to see if we can find our language |
|||
return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name> |
|||
if langlc == mw.ustring.lower(name) then |
|||
end |
|||
if 2 ~= code:len() and 3 ~= code:len() then -- two- or three-character codes only; extensions not supported |
|||
return name; -- so return the name but not the code |
|||
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- is <lang_param_lc> an IETF-like tag that MediaWiki doesn't recognize? <tag> gets the language subtag; nil else |
|||
end |
|||
return name, code; -- found it, return name to ensure proper capitalization and the the code |
|||
if tag then |
|||
name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag> |
|||
if name then |
|||
return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag |
|||
end |
end |
||
end |
end |
||
return lang; -- not valid language; return language in original case and nil for the code |
|||
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 |
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 |
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 |
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). |
||
For valid three-character code languages, the page is assigned to the single category |
|||
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. |
|||
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 |
Languages that are the same as the local wiki are not categorized. MediaWiki does |
||
equivalents of two-character codes: code 'ar' is |
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 |
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. |
|||
]] |
]] |
||
local function language_parameter (lang) |
local function language_parameter (lang) |
||
local |
local tag; -- some form of IETF-like language tag; language subtag with optional region, sript, vatiant, etc subtags |
||
local lang_subtag; -- ve populates |language= with mostly unecessary region subtags the MediaWiki does not recognize; this is the base language subtag |
|||
local name; -- the language name |
local name; -- the language name |
||
local language_list = {}; -- table of language names to be rendered |
local language_list = {}; -- table of language names to be rendered |
||
local |
local names_t = {}; -- table made from the value assigned to |language= |
||
local |
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name |
||
local this_wiki_code = this_wiki:getCode() -- get this wiki's language code |
|||
local this_wiki_name = mw.language.fetchLanguageName(this_wiki_code, this_wiki_code); -- get this wiki's language name |
|||
names_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
|||
local remap = { |
|||
['bh'] = 'Bihari', -- MediaWiki uses 'bh' as a subdomain name for Bhojpuri wWikipedia: bh.wikipedia.org |
|||
['bn'] = 'Bengali', -- MediaWiki returns Bangla |
|||
} |
|||
for _, lang in ipairs (names_t) do -- reuse lang here because we don't yet know if lang is a language name or a language tag |
|||
names_table = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list |
|||
name, tag = name_tag_get (lang); -- attempt to get name/tag pair for <lang>; <name> has proper capitalization; <tag> is lowercase |
|||
if utilities.is_set (tag) then |
|||
for _, lang in ipairs (names_table) do -- reuse lang |
|||
lang_subtag = tag:gsub ('^(%a%a%a?)%-.*', '%1'); -- for categorization, strip any IETF-like tags from language tag |
|||
if |
if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language |
||
if 2 == lang_subtag:len() then -- and is a two-character tag |
|||
lang = lang:match ('(%a%a)%-') -- keep only 639-1 code portion to lang; TODO: do something with 3166 alpha 2 country code? |
|||
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization |
|||
end |
|||
else -- or is a recognized language (but has a three-character tag) |
|||
utilities.add_prop_cat ('foreign-lang-source-2', {lang_subtag}, lang_subtag); -- categorize it differently TODO: support multiple three-character tag categories per cs1|2 template? |
|||
name = mw.language.fetchLanguageName( lang:lower(), this_wiki_code); -- get language name if |language= is a proper code |
|||
end |
|||
if is_set (name) then -- if |language= specified a valid code |
|||
code = lang:lower(); -- save it |
|||
else |
|||
name, code = get_iso639_code (lang, this_wiki_code); -- attempt to get code from name (assign name here so that we are sure of proper capitalization) |
|||
end |
|||
if is_set (code) then -- only 2- or 3-character codes |
|||
name = remap[code] or name; -- override wikimedia when they misuse language codes/names |
|||
if this_wiki_code ~= code then -- when the language is not the same as this wiki's language |
|||
if 2 == code:len() then -- and is a two-character code |
|||
add_prop_cat ('foreign_lang_source' .. code, {name, code}) -- categorize it |
|||
else -- or is a recognized language (but has a three-character code) |
|||
add_prop_cat ('foreign_lang_source_2' .. code, {code}) -- categorize it differently TODO: support mutliple three-character code categories per cs1|2 template |
|||
end |
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, lang_subtag}); -- categorize it |
|||
end |
end |
||
else |
else |
||
name = lang; -- return whatever <lang> has so that we show something |
|||
utilities.set_message ('maint_unknown_lang'); -- add maint category if not already added |
|||
end |
end |
||
Line 1,487: | Line 1,755: | ||
name = ''; -- so we can reuse it |
name = ''; -- so we can reuse it |
||
end |
end |
||
name = utilities.make_sep_list (#language_list, language_list); |
|||
code = #language_list -- reuse code as number of languages in the list |
|||
if (1 == #language_list) and (lang_subtag == cfg.this_wiki_code) then -- when only one language, find lang name in this wiki lang name; for |language=en-us, 'English' in 'American English' |
|||
if 2 >= code then |
|||
name = table.concat (language_list, ' and ') -- insert '<space>and<space>' between two language names |
|||
elseif 2 < code then |
|||
language_list[code] = 'and ' .. language_list[code]; -- prepend last name with 'and<space>' |
|||
name = table.concat (language_list, ', ') -- and concatenate with '<comma><space>' separators |
|||
end |
|||
if 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) |
||
end |
end |
||
Line 1,505: | Line 1,767: | ||
--[[ |
--[[-----------------------< S E T _ C S _ S T Y L E >-------------------------- |
||
Gets the default CS style configuration for the given mode. |
|||
Set style settings for CS1 citation templates. Returns separator and postscript settings |
|||
Returns default separator and either postscript as passed in or the default. |
|||
In CS1, the default postscript and separator are '.'. |
|||
In CS2, the default postscript is the empty string and the default separator is ','. |
|||
]] |
]] |
||
local function |
local function set_cs_style (postscript, mode) |
||
if utilities.is_set(postscript) then |
|||
if not is_set (ps) then -- unless explicitely set to something |
|||
-- emit a maintenance message if user postscript is the default cs1 postscript |
|||
ps = '.'; -- terminate the rendered citation with a period |
|||
-- we catch the opposite case for cs2 in set_style |
|||
if mode == 'cs1' and postscript == cfg.presentation['ps_' .. mode] then |
|||
utilities.set_message ('maint_postscript'); |
|||
end |
|||
else |
|||
postscript = cfg.presentation['ps_' .. mode]; |
|||
end |
end |
||
return cfg.presentation['sep_' .. mode], postscript; |
|||
return '.', ps; -- separator is a full stop |
|||
end |
end |
||
--[[--------------------------< S E T |
--[[--------------------------< S E T _ S T Y L E >----------------------------- |
||
Sets the separator and postscript styles. Checks the |mode= first and the |
|||
Set style settings for CS2 citation templates. Returns separator, postscript, ref settings |
|||
#invoke CitationClass second. Removes the postscript if postscript == none. |
|||
]] |
]] |
||
local function |
local function set_style (mode, postscript, cite_class) |
||
if not is_set (ps) then -- if |postscript= has not been set, set cs2 default |
|||
ps = ''; -- make sure it isn't nil |
|||
end |
|||
if not is_set (ref) then -- if |ref= is not set |
|||
ref = "harv"; -- set default |ref=harv |
|||
end |
|||
return ',', ps, ref; -- separator is a comma |
|||
end |
|||
--[[--------------------------< G E T _ S E T T I N G S _ F R O M _ C I T E _ C L A S S >---------------------- |
|||
When |mode= is not set or when its value is invalid, use config.CitationClass and parameter values to establish |
|||
rendered style. |
|||
]] |
|||
local function get_settings_from_cite_class (ps, ref, cite_class) |
|||
local sep; |
local sep; |
||
if 'cs2' == mode then |
|||
if (cite_class == "citation") then -- for citation templates (CS2) |
|||
sep, |
sep, postscript = set_cs_style (postscript, 'cs2'); |
||
elseif 'cs1' == mode then |
|||
else -- not a citation template so CS1 |
|||
sep, |
sep, postscript = set_cs_style (postscript, 'cs1'); |
||
elseif 'citation' == cite_class then |
|||
sep, postscript = set_cs_style (postscript, 'cs2'); |
|||
else |
|||
sep, postscript = set_cs_style (postscript, 'cs1'); |
|||
end |
end |
||
if cfg.keywords_xlate[postscript:lower()] == 'none' then |
|||
return sep, ps, ref -- return them all |
|||
-- emit a maintenance message if user postscript is the default cs2 postscript |
|||
end |
|||
-- we catch the opposite case for cs1 in set_cs_style |
|||
if 'cs2' == mode or 'citation' == cite_class then |
|||
utilities.set_message ('maint_postscript'); |
|||
--[[--------------------------< S E T _ S T Y L E >------------------------------------------------------------ |
|||
end |
|||
postscript = ''; |
|||
Establish basic style settings to be used when rendering the citation. Uses |mode= if set and valid or uses |
|||
config.CitationClass from the template's #invoke: to establish style. |
|||
]] |
|||
local function set_style (mode, ps, ref, cite_class) |
|||
local sep; |
|||
if 'cs2' == mode then -- if this template is to be rendered in CS2 (citation) style |
|||
sep, ps, ref = set_cs2_style (ps, ref); |
|||
elseif 'cs1' == mode then -- if this template is to be rendered in CS1 (cite xxx) style |
|||
sep, ps = set_cs1_style (ps); |
|||
else -- anything but cs1 or cs2 |
|||
sep, ps, ref = get_settings_from_cite_class (ps, ref, cite_class); -- get settings based on the template's CitationClass |
|||
end |
|||
if 'none' == ps:lower() then -- if assigned value is 'none' then |
|||
ps = ''; -- set to empty string |
|||
end |
end |
||
return sep, |
return sep, postscript |
||
end |
end |
||
--[=[-------------------------< 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 1,589: | Line 1,832: | ||
local function is_pdf (url) |
local function is_pdf (url) |
||
return url:match ('%.pdf$') or url:match ('%.PDF$') or |
return url:match ('%.pdf$') or url:match ('%.PDF$') or |
||
url:match ('%.pdf[%?#]') or url:match ('%.PDF[%?#]') or |
|||
url:match ('%.PDF#') or url:match ('%.pdf#'); |
|||
end |
end |
||
--[[--------------------------< 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 not set and the URL contains a file extension that is recognized as a PDF document |
|||
is recognized as a pdf document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with |
|||
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with |
|||
the appropriate styling. |
the appropriate styling. |
||
Line 1,603: | Line 1,849: | ||
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 |
||
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 1,617: | Line 1,863: | ||
--[[ |
--[[---------------------< 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 |
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, |
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 |
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 |
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 1,640: | Line 1,886: | ||
]] |
]] |
||
local function |
local function get_display_names (max, count, list_name, etal, param) |
||
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 1,648: | Line 1,894: | ||
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 |
||
utilities.set_message ('err_disp_name', {param, max}); -- add error message |
|||
add_maint_cat ('disp_auth_ed', cfg.special_case_translation [list_name]); |
|||
max = nil; |
|||
end |
end |
||
else -- not a valid keyword or number |
else -- not a valid keyword or number |
||
utilities.set_message ('err_disp_name', {param, max}); -- 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 1,660: | Line 1,907: | ||
--[[ |
--[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >--------------- |
||
Adds |
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 |
||
where x and X are letters and # is a digit |
|||
bad pattern: '^[Pp][Pp]' matches matches when |page(s)= begins pp or pP or Pp or PP |
|||
bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG |
|||
]] |
]] |
||
local function extra_text_in_page_check ( |
local function extra_text_in_page_check (val, name) |
||
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then |
|||
local good_pattern = '^P[^%.Pp]'; -- ok to begin with uppercase P: P7 (pg 7 of section P) but not p123 (page 123) TODO: add Gg for PG or Pg? |
|||
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns |
|||
local bad_pattern = '^[Pp]?[Pp]%.?[ %d]'; |
|||
if val:match (pattern) then -- when a match, error so |
|||
utilities.set_message ('err_extra_text_pages', name); -- add error message |
|||
return; -- and done |
|||
end |
|||
end |
|||
end |
|||
end |
|||
if not page:match (good_pattern) and (page:match (bad_pattern) or page:match ('^[Pp]ages?')) then |
|||
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------ |
|||
add_maint_cat ('extra_text'); |
|||
Adds error if |volume= or |issue= has what appears to be some form of redundant 'type' indicator. |
|||
For |volume=: |
|||
'V.', or 'Vol.' (with or without the dot) abbreviations or 'Volume' in the first characters of the parameter |
|||
content (all case insensitive). 'V' and 'v' (without the dot) are presumed to be roman numerals so |
|||
are allowed. |
|||
For |issue=: |
|||
'No.', 'I.', 'Iss.' (with or without the dot) abbreviations, or 'Issue' in the first characters of the |
|||
parameter content (all case insensitive). |
|||
Single character values ('v', 'i', 'n') allowed when not followed by separator character ('.', ':', '=', or |
|||
whitespace character) – param values are trimmed of whitespace by MediaWiki before delivered to the module. |
|||
<val> is |volume= or |issue= parameter value |
|||
<name> is |volume= or |issue= parameter name for error message |
|||
<selector> is 'v' for |volume=, 'i' for |issue= |
|||
sets error message on failure; returns nothing |
|||
]] |
|||
local function extra_text_in_vol_iss_check (val, name, selector) |
|||
if not utilities.is_set (val) then |
|||
return; |
|||
end |
|||
local patterns = 'v' == selector and cfg.vol_iss_pg_patterns.vpatterns or cfg.vol_iss_pg_patterns.ipatterns; |
|||
local handler = 'v' == selector and 'err_extra_text_volume' or 'err_extra_text_issue'; |
|||
val = val:lower(); -- force parameter value to lower case |
|||
for _, pattern in ipairs (patterns) do -- spin through the selected sequence table of patterns |
|||
if val:match (pattern) then -- when a match, error so |
|||
utilities.set_message (handler, name); -- add error message |
|||
return; -- and done |
|||
end |
|||
end |
end |
||
end |
end |
||
Line 1,684: | Line 1,976: | ||
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 1,693: | Line 1,985: | ||
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 ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses |
||
local name = name_table[i]; |
local name = name_table[i]; |
||
i=i+1; |
i = i + 1; -- bump indexer to next segment |
||
while name_table[i] do |
while name_table[i] do |
||
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments |
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments |
||
if name_table[i]:match ('^.*%)%)$') 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 1,719: | Line 2,011: | ||
end |
end |
||
end |
end |
||
i = i+1; |
i = i + 1; |
||
end |
end |
||
return output_table; |
return output_table; |
||
Line 1,732: | Line 2,024: | ||
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 1,749: | Line 2,041: | ||
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) |
vparam, etal = name_has_etal (vparam, etal, true); -- find and remove variations on et al. do not categorize (do it here because et al. might have a period) |
||
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); |
v_name_table = get_v_name_table (vparam, v_name_table, v_link_table); -- names are separated by commas |
||
for i, v_name in ipairs(v_name_table) do |
for i, v_name in ipairs(v_name_table) do |
||
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
|||
if v_name:match ('^%(%(.+%)%)$') then -- corporate authors are wrapped in doubled parentheses to supress vanc formatting and error detection |
|||
local accept_name; |
|||
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
|||
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name> |
|||
last = v_name:match ('^%(%((.+)%)%)$') -- remove doubled parntheses |
|||
if accept_name then |
|||
last = v_name; |
|||
corporate = true; -- flag used in list_people() |
corporate = true; -- flag used in list_people() |
||
elseif string.find(v_name, "%s") then |
elseif string.find(v_name, "%s") then |
||
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; |
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; |
||
add_vanc_error ( |
add_vanc_error (cfg.err_msg_supl.punctuation, i); |
||
end |
end |
||
local lastfirstTable = {} |
local lastfirstTable = {} |
||
lastfirstTable = mw.text.split(v_name, "%s") |
lastfirstTable = mw.text.split(v_name, "%s+") |
||
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be |
first = table.remove(lastfirstTable); -- removes and returns value of last element in table which should be initials or generational suffix |
||
if is_suffix (first) then -- if a valid suffix |
|||
if not mw.ustring.match (first, '^%u+$') then -- mw.ustring here so that later we will catch non-Latin characters |
|||
suffix = first -- save it as a suffix and |
|||
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 -- no suffix error message here because letter combination may be result of Romanization; check for digits? |
|||
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, i); |
|||
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'], i); -- 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.initials, i); -- matches a space between two initials |
||
end |
end |
||
else |
else |
||
first = ''; -- set to empty string for concatenation and because it may have been set for previous author/editor |
|||
last = v_name; -- last name or single corporate name? Doesn't support multiword corporate names? do we need this? |
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, i); -- 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, i); -- 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 1,790: | Line 2,090: | ||
else |
else |
||
if not corporate then |
if not corporate then |
||
is_good_vanc_name (last, ''); |
is_good_vanc_name (last, '', nil, i); |
||
end |
end |
||
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 1,805: | Line 2,105: | ||
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 1,816: | Line 2,116: | ||
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 1,838: | Line 2,138: | ||
err_name = 'editor'; |
err_name = 'editor'; |
||
end |
end |
||
utilities.set_message ('err_redundant_parameters', err_name .. '-name-list parameters'); -- add error message |
|||
table.insert( z.message_tail, { set_error( 'redundant_parameters', |
|||
{err_name .. '-name-list parameters'}, true ) } ); -- add error message |
|||
end |
end |
||
if true == lastfirst then return 1 end; -- return a number indicating which author name source to use |
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 1,852: | Line 2,151: | ||
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. |
|||
TODO: explain <invert> |
|||
]] |
]] |
||
local function is_valid_parameter_value (value, name, possible) |
local function is_valid_parameter_value (value, name, possible, ret_val, invert) |
||
if not is_set (value) then |
if not utilities.is_set (value) then |
||
return |
return ret_val; -- an empty parameter is ok |
||
end |
|||
elseif in_array(value:lower(), possible) then |
|||
return true; |
|||
if (not invert and utilities.in_array (value, possible)) then -- normal; <value> is in <possible> table |
|||
return cfg.keywords_xlate[value]; -- return translation of parameter keyword |
|||
elseif invert and not utilities.in_array (value, possible) then -- invert; <value> is not in <possible> table |
|||
return value; -- return <value> as it is |
|||
else |
else |
||
utilities.set_message ('err_invalid_param_val', {name, value}); -- not an allowed value so add error message |
|||
return |
return ret_val; |
||
end |
end |
||
end |
end |
||
Line 1,880: | Line 2,186: | ||
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 |
||
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >---------------------------------------- |
--[[-------------------------< F O R M A T _ V O L U M E _ I S S U E >----------------------------------------- |
||
returns the concatenation of the formatted volume and issue |
returns the concatenation of the formatted volume and issue (or journal article number) parameters as a single |
||
or formatted issue, or an empty string if neither are set. |
string; or formatted volume or formatted issue, or an empty string if neither are set. |
||
]] |
]] |
||
local function format_volume_issue (volume, issue, cite_class, origin, sepc, lower) |
local function format_volume_issue (volume, issue, article, 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) and not utilities.is_set (article) then |
||
return ''; |
return ''; |
||
end |
end |
||
-- same condition as in format_pages_sheets() |
|||
local is_journal = 'journal' == cite_class or (utilities.in_array (cite_class, {'citation', 'map', 'interview'}) and 'journal' == origin); |
|||
local is_numeric_vol = volume and (volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$')); -- is only uppercase roman numerals or only digits? |
|||
local is_long_vol = volume and (4 < mw.ustring.len(volume)); -- is |volume= value longer than 4 characters? |
|||
if volume and (not is_numeric_vol and is_long_vol) then -- when not all digits or Roman numerals, is |volume= longer than 4 characters? |
|||
if 'magazine' == cite_class or (in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then |
|||
utilities.add_prop_cat ('long-vol'); -- yes, add properties cat |
|||
if is_set (volume) and is_set (issue) then |
|||
return wrap_msg ('vol-no', {sepc, volume, issue}, lower); |
|||
elseif is_set (volume) then |
|||
return wrap_msg ('vol', {sepc, volume}, lower); |
|||
else |
|||
return wrap_msg ('issue', {sepc, issue}, lower); |
|||
end |
|||
end |
end |
||
if is_journal then -- journal-style formatting |
|||
local vol = ''; |
|||
local vol = ''; |
|||
if is_set (volume) then |
|||
if |
if utilities.is_set (volume) then |
||
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals? |
|||
vol = substitute (cfg.messages['j-vol'], {sepc, volume}); |
|||
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face |
|||
else |
|||
elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters? |
|||
vol = substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); |
|||
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, utilities.hyphen_to_dash (volume)}); -- not bold |
|||
else -- four or fewer characters |
|||
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, utilities.hyphen_to_dash (volume)}); -- bold |
|||
end |
|||
end |
end |
||
vol = vol .. (utilities.is_set (issue) and utilities.substitute (cfg.messages['j-issue'], issue) or '') |
|||
vol = vol .. (utilities.is_set (article) and utilities.substitute (cfg.messages['j-article-num'], article) or '') |
|||
return vol; |
|||
end |
end |
||
if is_set (issue) then |
|||
if 'podcast' == cite_class and utilities.is_set (issue) then |
|||
return vol .. substitute (cfg.messages['j-issue'], issue); |
|||
return wrap_msg ('issue', {sepc, issue}, lower); |
|||
end |
|||
if 'conference' == cite_class and utilities.is_set (article) then -- |article-number= supported only in journal and conference cites |
|||
if utilities.is_set (volume) and utilities.is_set (article) then -- both volume and article number |
|||
return wrap_msg ('vol-art', {sepc, utilities.hyphen_to_dash (volume), article}, lower); |
|||
elseif utilities.is_set (article) then -- article number alone; when volume alone, handled below |
|||
return wrap_msg ('art', {sepc, article}, lower); |
|||
end |
|||
end |
|||
-- all other types of citation |
|||
if utilities.is_set (volume) and utilities.is_set (issue) then |
|||
return wrap_msg ('vol-no', {sepc, utilities.hyphen_to_dash (volume), issue}, lower); |
|||
elseif utilities.is_set (volume) then |
|||
return wrap_msg ('vol', {sepc, utilities.hyphen_to_dash (volume)}, lower); |
|||
else |
|||
return wrap_msg ('issue', {sepc, issue}, lower); |
|||
end |
end |
||
return vol; |
|||
end |
end |
||
Line 1,940: | Line 2,270: | ||
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 1,946: | Line 2,276: | ||
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 1,955: | Line 2,285: | ||
end |
end |
||
local is_journal = 'journal' == cite_class or (in_array (cite_class, {'citation', 'map'}) 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 |
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 |
||
return '', '', '', ''; -- return empty strings |
return '', '', '', ''; -- return empty strings |
||
end |
|||
--[[--------------------------< I N S O U R C E _ L O C _ G E T >---------------------------------------------- |
|||
returns one of the in-source locators: page, pages, or at. |
|||
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text |
|||
for use in COinS. This COinS thing is done because here we convert an interwiki-link to an external link and |
|||
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? |
|||
TODO: add support for sheet and sheets?; streamline; |
|||
TODO: make it so that this function returns only one of the three as the single in-source (the return value assigned |
|||
to a new name)? |
|||
]] |
|||
local function insource_loc_get (page, page_orig, pages, pages_orig, at) |
|||
local ws_url, ws_label, coins_pages, L; -- for Wikisource interwiki-links; TODO: this corrupts page metadata (span remains in place after cleanup; fix there?) |
|||
if utilities.is_set (page) then |
|||
if utilities.is_set (pages) or utilities.is_set (at) then |
|||
pages = ''; -- unset the others |
|||
at = ''; |
|||
end |
|||
extra_text_in_page_check (page, page_orig); -- emit error message when |page= value begins with what looks like p., pp., etc. |
|||
ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label |
|||
if ws_url then |
|||
page = external_link (ws_url, ws_label .. ' ', 'ws link in page'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
|||
page = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, page}); |
|||
coins_pages = ws_label; |
|||
end |
|||
elseif utilities.is_set (pages) then |
|||
if utilities.is_set (at) then |
|||
at = ''; -- unset |
|||
end |
|||
extra_text_in_page_check (pages, pages_orig); -- emit error message when |page= value begins with what looks like p., pp., etc. |
|||
ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label |
|||
if ws_url then |
|||
pages = external_link (ws_url, ws_label .. ' ', 'ws link in pages'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
|||
pages = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, pages}); |
|||
coins_pages = ws_label; |
|||
end |
|||
elseif utilities.is_set (at) then |
|||
ws_url, ws_label, L = wikisource_url_make (at); -- make ws URL from |at= interwiki link; link portion L becomes tooltip label |
|||
if ws_url then |
|||
at = external_link (ws_url, ws_label .. ' ', 'ws link in at'); -- space char after label to move icon away from in-source text; TODO: a better way to do this? |
|||
at = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, at}); |
|||
coins_pages = ws_label; |
|||
end |
|||
end |
|||
return page, pages, at, coins_pages; |
|||
end |
|||
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------ |
|||
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value |
|||
]] |
|||
local function is_unique_archive_url (archive, url, c_url, source, date) |
|||
if utilities.is_set (archive) then |
|||
if archive == url or archive == c_url then |
|||
utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}); -- add error message |
|||
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url= |
|||
end |
|||
end |
|||
return archive, date; |
|||
end |
end |
||
Line 1,983: | Line 2,386: | ||
--[=[-------------------------< 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 2,006: | Line 2,409: | ||
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 2,016: | Line 2,419: | ||
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+)([^/]*)/'); |
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation |
||
if not path then -- malformed in some way; pattern did not match |
|||
err_msg = cfg.err_msg_supl.timestamp; |
|||
if not is_set(timestamp) or 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here |
|||
elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here |
|||
err_msg = 'timestamp'; |
|||
err_msg = cfg.err_msg_supl.timestamp; |
|||
if '*' ~= flag then |
if '*' ~= flag then |
||
local replacement = timestamp:match ('^%d%d%d%d%d%d') or timestamp:match ('^%d%d%d%d'); -- get the first 6 (YYYYMM) or first 4 digits (YYYY) |
|||
if replacement then -- nil if there aren't at least 4 digits (year) |
|||
replacement = replacement .. string.rep ('0', 14 - replacement:len()); -- year or yearmo (4 or 6 digits) zero-fill to make 14-digit timestamp |
|||
url=url:gsub ('(//web%.archive%.org/[^%d]*)%d[^/]*', '%1' .. replacement .. '*', 1) -- for preview, modify ts to 14 digits plus splat for calendar display |
|||
end |
|||
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 |
||
utilities.set_message ('err_archive_url', {err_msg}); -- add error message and |
|||
if is_set (Frame:preprocess('{{REVISIONID}}')) then |
|||
if is_preview_mode then |
|||
return '', ''; -- return empty strings for archiveURL and ArchiveDate |
|||
return url, date; -- preview mode so return ArchiveURL and ArchiveDate |
|||
else |
else |
||
return |
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate |
||
end |
end |
||
end |
end |
||
--[[--------------------------< |
--[[--------------------------< P L A C E _ C H E C K >-------------------------------------------------------- |
||
check |place=, |publication-place=, |location= to see if these params include digits. This function added because |
|||
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal |
|||
many editors misuse location to specify the in-source location (|page(s)= and |at= are supposed to do that) |
|||
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: |
|||
{{cite ... |title=Title access-date=2016-03-17}} |
|||
returns the original parameter value without modification; added maint cat when parameter value contains digits |
|||
cs1|2 shares some parameter names with xml/html atributes: 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 |
local function place_check (param_val) |
||
if not utilities.is_set (param_val) then -- parameter empty or omitted |
|||
local capture; |
|||
return param_val; -- return that empty state |
|||
value = value:gsub ('%b<>', ''); -- remove xml/html tags because attributes: class=, title=, etc |
|||
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 |
|||
capture = value:match ('%s+(%a[%a%d]+)%s*=') or value:match ('^(%a[%a%d]+)%s*='); -- find and categorize parameters with possible missing pipes |
|||
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >---------------------------------------------- |
|||
if capture and validate (capture) then -- if the capture is a valid parameter name |
|||
add_maint_cat ('missing_pipe'); |
|||
compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else |
|||
]] |
|||
local function is_archived_copy (title) |
|||
title = mw.ustring.lower(title); -- switch title to lower case |
|||
if title:find (cfg.special_case_translation.archived_copy.en) then -- if title is 'Archived copy' |
|||
return true; |
|||
elseif cfg.special_case_translation.archived_copy['local'] then |
|||
if mw.ustring.find (title, cfg.special_case_translation.archived_copy['local']) then -- mw.ustring() because might not be Latin script |
|||
return true; |
|||
end |
|||
end |
end |
||
end |
end |
||
Line 2,086: | Line 2,510: | ||
]] |
]] |
||
local function citation0( config, args) |
local function citation0( config, args ) |
||
--[[ |
--[[ |
||
Load Input Parameters |
Load Input Parameters |
||
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. |
The argument_wrapper facilitates the mapping of multiple aliases to single internal variable. |
||
]] |
]] |
||
local A = argument_wrapper( args ); |
local A = argument_wrapper ( args ); |
||
local i |
local i |
||
-- Pick out the relevant fields from the arguments. Different citation templates |
-- Pick out the relevant fields from the arguments. Different citation templates |
||
-- define different field names for the same underlying things. |
-- define different field names for the same underlying things. |
||
-- set default parameter values defined by |mode= parameter. |
|||
local Mode = A['Mode']; |
|||
if not is_valid_parameter_value (Mode, 'mode', cfg.keywords['mode']) then |
|||
Mode = ''; |
|||
end |
|||
local author_etal; |
local author_etal; |
||
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
local a = {}; -- authors list from |lastn= / |firstn= pairs or |vauthors= |
||
local Authors; |
local Authors; |
||
local NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], ''); |
|||
local NameListFormat = A['NameListFormat']; |
|||
local Collaboration = A['Collaboration']; |
local Collaboration = A['Collaboration']; |
||
Line 2,114: | Line 2,532: | ||
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= |
a, author_etal = extract_names (args, 'AuthorList'); -- fetch author list from |authorn= / |lastn= / |firstn=, |author-linkn=, and |author-maskn= |
||
elseif 2 == selected then |
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= |
a, author_etal = parse_vauthors_veditors (args, args.vauthors, 'AuthorList'); -- fetch author list from |vauthors=, |author-linkn=, and |author-maskn= |
||
elseif 3 == selected then |
elseif 3 == selected then |
||
Authors = A['Authors']; -- use content of |authors= |
Authors = A['Authors']; -- use content of |authors= |
||
if 'authors' == A:ORIGIN('Authors') then -- but add a maint cat if the parameter is |authors= |
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 is_set (Collaboration) then |
if utilities.is_set (Collaboration) then |
||
author_etal = true; -- so that |display-authors=etal not required |
author_etal = true; -- so that |display-authors=etal not required |
||
end |
end |
||
end |
end |
||
local Others = A['Others']; |
|||
local editor_etal; |
local editor_etal; |
||
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= |
local e = {}; -- editors list from |editor-lastn= / |editor-firstn= pairs or |veditors= |
||
local Editors; |
|||
do -- to limit scope of selected |
do -- to limit scope of selected |
||
local selected = select_author_editor_source (A['Veditors'], |
local selected = select_author_editor_source (A['Veditors'], nil, args, 'EditorList'); -- support for |editors= withdrawn |
||
if 1 == selected then |
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= |
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 |
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= |
e, editor_etal = parse_vauthors_veditors (args, args.veditors, 'EditorList'); -- fetch editor list from |veditors=, |editor-linkn=, and |editor-maskn= |
||
elseif 3 == selected then |
|||
Editors = A['Editors']; -- use content of |editors= |
|||
add_maint_cat ('editors'); -- but add a maint cat because use of this parameter is discouraged |
|||
end |
end |
||
end |
end |
||
local |
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases |
||
local Chapter_origin = A:ORIGIN ('Chapter'); |
|||
local Translators; -- assembled translators name list |
|||
local Contribution; -- because contribution is required for contributor(s) |
|||
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
|||
if 'contribution' == Chapter_origin then |
|||
Contribution = Chapter; -- get the name of the contribution |
|||
local interviewers_list = {}; |
|||
end |
|||
local Interviewers = A['Interviewers'] |
|||
if is_set (Interviewers) then -- add a maint cat if the |interviewers= is used |
|||
add_maint_cat ('interviewers'); -- because use of this parameter is discouraged |
|||
else |
|||
interviewers_list = extract_names (args, 'InterviewerList'); -- else, process preferred interviewers parameters |
|||
end |
|||
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs |
||
local Contributors; -- assembled contributors name list |
|||
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites |
|||
local Contribution = A['Contribution']; |
|||
if in_array(config.CitationClass, {"book","citation"}) and not is_set(A['Periodical']) then -- |contributor= and |contribution= only supported in book cites |
|||
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= |
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= |
||
if 0 < #c then |
if 0 < #c then |
||
if not is_set (Contribution) then |
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution= |
||
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 |
c = {}; -- blank the contributors' table; it is used as a flag later |
||
end |
end |
||
if 0 == #a then -- |contributor= requires |author= |
if 0 == #a then -- |contributor= requires |author= |
||
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 |
c = {}; -- blank the contributors' table; it is used as a flag later |
||
end |
end |
||
end |
end |
||
else -- if not a book cite |
else -- if not a book cite |
||
if select_one (args, cfg.aliases['ContributorList-Last'], ' |
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters? |
||
utilities.set_message ('err_contributor_ignored'); -- add contributor ignored error message |
|||
end |
end |
||
Contribution = nil; -- unset |
Contribution = nil; -- unset |
||
end |
end |
||
if not is_valid_parameter_value (NameListFormat, 'name-list-format', cfg.keywords['name-list-format']) then -- only accepted value for this parameter is 'vanc' |
|||
NameListFormat = ''; -- anything else, set to empty string |
|||
end |
|||
local Year = A['Year']; |
|||
local PublicationDate = A['PublicationDate']; |
|||
local OrigYear = A['OrigYear']; |
|||
local Date = A['Date']; |
|||
local LayDate = A['LayDate']; |
|||
------------------------------------------------- Get title data |
|||
local Title = A['Title']; |
local Title = A['Title']; |
||
local ScriptTitle = A['ScriptTitle']; |
|||
local BookTitle = A['BookTitle']; |
|||
local Conference = A['Conference']; |
|||
local TransTitle = A['TransTitle']; |
|||
local TitleNote = A['TitleNote']; |
|||
local TitleLink = A['TitleLink']; |
local TitleLink = A['TitleLink']; |
||
link_title_ok (TitleLink, A:ORIGIN ('TitleLink'), Title, 'title'); -- check for wikimarkup in |title-link= or wikimarkup in |title= when |title-link= is set |
|||
local |
local auto_select = ''; -- default is auto |
||
local accept_link; |
|||
local ScriptChapter = A['ScriptChapter']; |
|||
TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup |
|||
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode |
|||
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords |
|||
local TransChapter = A['TransChapter']; |
|||
auto_select = TitleLink; -- remember selection for later |
|||
local TitleType = A['TitleType']; |
|||
TitleLink = ''; -- treat as if |title-link= would have been empty |
|||
local Degree = A['Degree']; |
|||
end |
|||
local Docket = A['Docket']; |
|||
local ArchiveFormat = A['ArchiveFormat']; |
|||
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 ArchiveDate; |
|||
local ArchiveURL; |
|||
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used |
|||
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) |
|||
if 'map' == config.CitationClass and 'section' == Chapter_origin then |
|||
Section = A['Chapter']; -- get |section= from |chapter= alias list; |chapter= and the other aliases not supported in {{cite map}} |
|||
local DeadURL = A['DeadURL'] |
|||
Chapter = ''; -- unset for now; will be reset later from |map= if present |
|||
if not is_valid_parameter_value (DeadURL, 'dead-url', cfg.keywords ['deadurl']) then -- set in config.defaults to 'yes' |
|||
end |
|||
DeadURL = ''; -- anything else, set to empty string |
|||
end |
|||
local URL = A['URL'] |
|||
local URLorigin = A:ORIGIN('URL'); -- get name of parameter that holds URL |
|||
local ChapterURL = A['ChapterURL']; |
|||
local ChapterURLorigin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL |
|||
local ConferenceFormat = A['ConferenceFormat']; |
|||
local ConferenceURL = A['ConferenceURL']; |
|||
local ConferenceURLorigin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL |
|||
local Periodical = A['Periodical']; |
local Periodical = A['Periodical']; |
||
local Periodical_origin = |
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 |
|||
utilities.set_message ('err_apostrophe_markup', {Periodical_origin}); |
|||
end |
|||
end |
|||
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} |
|||
local Series = A['Series']; |
|||
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error TODO: make a function for this and similar? |
|||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', Periodical_origin) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'mailinglist')}); |
|||
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 |
|||
local ScriptPeriodical = A['ScriptPeriodical']; |
|||
-- web and news not tested for now because of |
|||
-- Wikipedia:Administrators%27_noticeboard#Is_there_a_semi-automated_tool_that_could_fix_these_annoying_"Cite_Web"_errors? |
|||
if not (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 |
|||
utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}); |
|||
end |
|||
end |
|||
local Volume; |
local Volume; |
||
local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); |
|||
if 'citation' == config.CitationClass then |
|||
if utilities.is_set (Periodical) then |
|||
if not utilities.in_array (Periodical_origin, cfg.citation_no_volume_t) then -- {{citation}} does not render |volume= when these parameters are used |
|||
Volume = A['Volume']; -- but does for all other 'periodicals' |
|||
end |
|||
elseif utilities.is_set (ScriptPeriodical) then |
|||
if 'script-website' ~= ScriptPeriodical_origin then -- {{citation}} does not render volume for |script-website= |
|||
Volume = A['Volume']; -- but does for all other 'periodicals' |
|||
end |
|||
else |
|||
Volume = A['Volume']; -- and does for non-'periodical' cites |
|||
end |
|||
elseif utilities.in_array (config.CitationClass, cfg.templates_using_volume) then -- render |volume= for cs1 according to the configuration settings |
|||
Volume = A['Volume']; |
|||
end |
|||
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v'); |
|||
local Issue; |
local Issue; |
||
if 'citation' == config.CitationClass then |
|||
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, cfg.citation_issue_t) then -- {{citation}} may render |issue= when these parameters are used |
|||
Issue = utilities.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 = utilities.hyphen_to_dash (A['Issue']); |
|||
end |
|||
end |
|||
local ArticleNumber; |
|||
if utilities.in_array (config.CitationClass, {'journal', 'conference'}) or ('citation' == config.CitationClass and utilities.is_set (Periodical) and 'journal' == Periodical_origin) then |
|||
ArticleNumber = A['ArticleNumber']; |
|||
end |
|||
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i'); |
|||
local Page; |
local Page; |
||
local Pages; |
local Pages; |
||
local At; |
local At; |
||
local QuotePage; |
|||
local QuotePages; |
|||
if in_array (config.CitationClass, cfg.templates_using_volume) then |
|||
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then -- TODO: rewrite to emit ignored parameter error message? |
|||
Volume = A['Volume']; |
|||
end |
|||
-- conference & map books do not support issue |
|||
if in_array (config.CitationClass, cfg.templates_using_issue) and not (in_array (config.CitationClass, {'conference', 'map'}) and not is_set (Periodical))then |
|||
Issue = A['Issue']; |
|||
end |
|||
local Position = ''; |
|||
if not in_array (config.CitationClass, cfg.templates_not_using_page) then |
|||
Page = A['Page']; |
Page = A['Page']; |
||
Pages = hyphen_to_dash( |
Pages = utilities.hyphen_to_dash (A['Pages']); |
||
At = A['At']; |
At = A['At']; |
||
QuotePage = A['QuotePage']; |
|||
QuotePages = utilities.hyphen_to_dash (A['QuotePages']); |
|||
end |
end |
||
local Edition = A['Edition']; |
local Edition = A['Edition']; |
||
local PublicationPlace = A['PublicationPlace'] |
local PublicationPlace = place_check (A['PublicationPlace'], A:ORIGIN('PublicationPlace')); |
||
local Place = A['Place']; |
local Place = place_check (A['Place'], A:ORIGIN('Place')); |
||
local PublisherName = A['PublisherName']; |
local PublisherName = A['PublisherName']; |
||
local |
local PublisherName_origin = A:ORIGIN('PublisherName'); |
||
if utilities.is_set (PublisherName) then |
|||
if not is_valid_parameter_value (RegistrationRequired, 'registration', cfg.keywords ['yes_true_y']) then |
|||
local i = 0; |
|||
RegistrationRequired=nil; |
|||
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 |
|||
utilities.set_message ('err_apostrophe_markup', {PublisherName_origin}); |
|||
end |
end |
||
end |
|||
local Newsgroup = A['Newsgroup']; -- TODO: strip apostrophe markup? |
|||
local SubscriptionRequired = A['SubscriptionRequired']; |
|||
local Newsgroup_origin = A:ORIGIN('Newsgroup'); |
|||
if not is_valid_parameter_value (SubscriptionRequired, 'subscription', cfg.keywords ['yes_true_y']) then |
|||
SubscriptionRequired=nil; |
|||
end |
|||
if 'newsgroup' == config.CitationClass then |
|||
local UrlAccess = A['UrlAccess']; |
|||
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup |
|||
if not is_valid_parameter_value (UrlAccess, 'url-access', cfg.keywords ['url-access']) then |
|||
utilities.set_message ('err_parameter_ignored', {PublisherName_origin}); |
|||
UrlAccess = nil; |
|||
end |
|||
if not is_set(URL) and is_set(UrlAccess) then |
|||
UrlAccess = nil; |
|||
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'url'}, true ) } ); |
|||
end |
end |
||
PublisherName = nil; -- ensure that this parameter is unset for the time being; will be used again after COinS |
|||
if is_set (UrlAccess) and is_set (SubscriptionRequired) then -- while not aliases, these are much the same so if both are set |
|||
end |
|||
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'subscription')}, true ) } ); -- add error message |
|||
SubscriptionRequired = nil; -- unset; prefer |access= over |subscription= |
|||
end |
|||
if is_set (UrlAccess) and is_set (RegistrationRequired) then -- these are not the same but contradictory so if both are set |
|||
table.insert( z.message_tail, { set_error( 'redundant_parameters', {wrap_style ('parameter', 'url-access') .. ' and ' .. wrap_style ('parameter', 'registration')}, true ) } ); -- add error message |
|||
RegistrationRequired = nil; -- unset; prefer |access= over |registration= |
|||
end |
|||
local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL? |
|||
local ChapterUrlAccess = A['ChapterUrlAccess']; |
|||
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); |
|||
ChapterUrlAccess = nil; |
|||
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then |
|||
end |
|||
UrlAccess = nil; |
|||
if not is_set(ChapterURL) and is_set(ChapterUrlAccess) then |
|||
utilities.set_message ('err_param_access_requires_param', 'url'); |
|||
ChapterUrlAccess = nil; |
|||
end |
|||
table.insert( z.message_tail, { set_error( 'param_access_requires_param', {'chapter-url'}, true ) } ); |
|||
end |
|||
local ChapterURL = A['ChapterURL']; |
|||
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); |
|||
if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then |
|||
ChapterUrlAccess = nil; |
|||
utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}); |
|||
end |
|||
local MapUrlAccess = is_valid_parameter_value (A['MapUrlAccess'], A:ORIGIN('MapUrlAccess'), cfg.keywords_lists['url-access'], nil); |
|||
local Via = A['Via']; |
|||
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then |
|||
local AccessDate = A['AccessDate']; |
|||
MapUrlAccess = nil; |
|||
local Agency = A['Agency']; |
|||
utilities.set_message ('err_param_access_requires_param', {'map-url'}); |
|||
end |
|||
local Language = A['Language']; |
|||
local Format = A['Format']; |
|||
local ChapterFormat = A['ChapterFormat']; |
|||
local DoiBroken = A['DoiBroken']; |
|||
local ID = A['ID']; |
|||
local ASINTLD = A['ASINTLD']; |
|||
local IgnoreISBN = A['IgnoreISBN']; |
|||
if not is_valid_parameter_value (IgnoreISBN, 'ignore-isbn-error', cfg.keywords ['yes_true_y']) then |
|||
IgnoreISBN = nil; -- anything else, set to empty string |
|||
end |
|||
local Embargo = A['Embargo']; |
|||
local Class = A['Class']; -- arxiv class identifier |
|||
local ID_list = extract_ids( args ); |
|||
local ID_access_levels = extract_id_access_levels( args, ID_list ); |
|||
local Quote = A['Quote']; |
|||
local LayFormat = A['LayFormat']; |
|||
local LayURL = A['LayURL']; |
|||
local LaySource = A['LaySource']; |
|||
local Transcript = A['Transcript']; |
|||
local TranscriptFormat = A['TranscriptFormat']; |
|||
local TranscriptURL = A['TranscriptURL'] |
|||
local TranscriptURLorigin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL |
|||
local LastAuthorAmp = A['LastAuthorAmp']; |
|||
if not is_valid_parameter_value (LastAuthorAmp, 'last-author-amp', cfg.keywords ['yes_true_y']) then |
|||
LastAuthorAmp = nil; -- set to empty string |
|||
end |
|||
local no_tracking_cats = A['NoTracking']; |
|||
if not is_valid_parameter_value (no_tracking_cats, 'no-tracking', cfg.keywords ['yes_true_y']) then |
|||
no_tracking_cats = nil; -- set to empty string |
|||
end |
|||
--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 this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language |
||
local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil); |
|||
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 = A['DF']; -- date format set in cs1|2 template |
|||
if not is_valid_parameter_value (DF, 'df', cfg.keywords['date-format']) then -- validate reformatting keyword |
|||
DF = ''; -- not valid, set to empty string |
|||
end |
|||
local sepc; -- separator between citation elements for CS1 a period, for CS2, a comma |
|||
local PostScript; |
|||
local Ref; |
|||
sepc, PostScript, Ref = set_style (Mode:lower(), A['PostScript'], A['Ref'], config.CitationClass); |
|||
use_lowercase = ( sepc == ',' ); -- used to control capitalization for certain static text |
|||
--check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories |
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories |
||
if not is_set (no_tracking_cats) then |
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page |
||
if |
if cfg.uncategorized_namespaces[this_page.namespace] then -- is this page's namespace id one of the uncategorized namespace ids? |
||
no_tracking_cats = "true"; -- set no_tracking_cats |
no_tracking_cats = "true"; -- set no_tracking_cats |
||
end |
end |
||
for _,v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns |
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 |
if this_page.text:match (v) then -- test page name against each pattern |
||
no_tracking_cats = "true"; -- set no_tracking_cats |
no_tracking_cats = "true"; -- set no_tracking_cats |
||
Line 2,362: | Line 2,749: | ||
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; |
|||
-- check for extra |page=, |pages= or |at= parameters. (also sheet and sheets while we're at it) |
|||
select_one( args, {'page', 'p', 'pp', 'pages', 'at', 'sheet', 'sheets'}, 'redundant_parameters' ); -- this is a dummy call simply to get the error message and category |
|||
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At); |
|||
local NoPP = A['NoPP'] |
local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil); |
||
if is_set (NoPP) and is_valid_parameter_value (NoPP, 'nopp', cfg.keywords ['yes_true_y']) then |
|||
NoPP = true; |
|||
else |
|||
NoPP = nil; -- unset, used as a flag later |
|||
end |
|||
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different |
|||
if is_set(Page) then |
|||
utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together |
|||
if is_set(Pages) or is_set(At) then |
|||
if PublicationPlace == Place then |
|||
Pages = ''; -- unset the others |
|||
Place = ''; -- unset; don't need both if they are the same |
|||
At = ''; |
|||
end |
end |
||
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ... |
|||
extra_text_in_page_check (Page); -- add this page to maint cat if |page= value begins with what looks like p. or pp. |
|||
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
|||
elseif is_set(Pages) then |
|||
if is_set(At) then |
|||
At = ''; -- unset |
|||
end |
|||
extra_text_in_page_check (Pages); -- add this page to maint cat if |pages= value begins with what looks like p. or pp. |
|||
end |
|||
-- both |publication-place= and |place= (|location=) allowed if different |
|||
if not is_set(PublicationPlace) and is_set(Place) then |
|||
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place |
|||
end |
end |
||
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
|||
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL |
|||
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same |
|||
local ChapterURL_origin = A:ORIGIN('ChapterURL'); -- get name of parameter that holds ChapterURL |
|||
local ScriptChapter = A['ScriptChapter']; |
|||
local ScriptChapter_origin = A:ORIGIN ('ScriptChapter'); |
|||
local Format = A['Format']; |
|||
local ChapterFormat = A['ChapterFormat']; |
|||
local TransChapter = A['TransChapter']; |
|||
local TransChapter_origin = A:ORIGIN ('TransChapter'); |
|||
local TransTitle = A['TransTitle']; |
|||
local ScriptTitle = A['ScriptTitle']; |
|||
--[[ |
--[[ |
||
Parameter remapping for cite encyclopedia: |
Parameter remapping for cite encyclopedia: |
||
When the citation has these parameters: |
When the citation has these parameters: |
||
|encyclopedia and |title then map |title to |article and |encyclopedia to |title |
|encyclopedia= and |title= then map |title= to |article= and |encyclopedia= to |title= |
||
|encyclopedia and |article then map |encyclopedia to |title |
|encyclopedia= and |article= then map |encyclopedia= to |title= |
||
|encyclopedia then map |encyclopedia to |title |
|||
|trans-title= maps to |trans-chapter= when |title= is re-mapped |
|||
|url= maps to |chapter-url= when |title= is remapped |
|||
All other combinations of |encyclopedia=, |title=, and |article= are not modified |
|||
|trans-title maps to |trans-chapter when |title is re-mapped |
|||
|url maps to |chapterurl when |title is remapped |
|||
All other combinations of |encyclopedia, |title, and |article are not modified |
|||
]] |
]] |
||
local Encyclopedia = A['Encyclopedia']; |
local Encyclopedia = A['Encyclopedia']; -- used as a flag by this module and by ~/COinS |
||
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 |
|||
utilities.set_message ('err_parameter_ignored', {A:ORIGIN ('Encyclopedia')}); |
|||
Encyclopedia = nil; -- unset because not supported by this template |
|||
end |
|||
end |
|||
if ( config.CitationClass |
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then |
||
if is_set(Periodical) then |
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error TODO: make a function for this and similar? |
||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', A:ORIGIN ('Encyclopedia')) .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Periodical_origin)}); |
|||
if is_set(Title) or is_set (ScriptTitle) then |
|||
end |
|||
if not is_set(Chapter) then |
|||
Chapter = Title; -- |encyclopedia and |title are set so map |title to |article and |encyclopedia to |title |
|||
if 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 = ScriptTitle; |
||
ScriptChapter_origin = A:ORIGIN('ScriptTitle') |
|||
TransChapter = TransTitle; |
TransChapter = TransTitle; |
||
ChapterURL = URL; |
ChapterURL = URL; |
||
ChapterURL_origin = URL_origin; |
|||
ChapterUrlAccess = UrlAccess; |
ChapterUrlAccess = UrlAccess; |
||
if not is_set (ChapterURL) and is_set (TitleLink) then |
if not utilities.is_set (ChapterURL) and utilities.is_set (TitleLink) then |
||
Chapter = make_wikilink (TitleLink, Chapter); |
Chapter = utilities.make_wikilink (TitleLink, Chapter); |
||
end |
end |
||
Title = Periodical; |
Title = Periodical; |
||
Line 2,431: | Line 2,836: | ||
ScriptTitle = ''; |
ScriptTitle = ''; |
||
end |
end |
||
elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set |
|||
Title = Periodical; -- |encyclopedia set and |article |
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= |
||
Periodical = ''; -- redundant so unset |
Periodical = ''; -- redundant so unset |
||
end |
end |
||
Line 2,438: | Line 2,843: | ||
end |
end |
||
-- |
-- special case for cite techreport. |
||
local ID = A['ID']; |
|||
if (config.CitationClass == "techreport") then -- special case for cite techreport |
if (config.CitationClass == "techreport") then -- special case for cite techreport |
||
if is_set(A['Number']) then |
if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' |
||
if not is_set(ID) then |
if not utilities.is_set (ID) then -- can we use ID for the "number"? |
||
ID = A['Number']; -- yes, use it |
ID = A['Number']; -- yes, use it |
||
else -- ID has a value so emit error message |
else -- ID has a value so emit error message |
||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'id') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'number')}); |
|||
end |
end |
||
end |
end |
||
end |
|||
-- special case for cite mailing list |
|||
if (config.CitationClass == "mailinglist") then |
|||
Periodical = A ['MailingList']; |
|||
elseif 'mailinglist' == A:ORIGIN('Periodical') then |
|||
Periodical = ''; -- unset because mailing list is only used for cite mailing list |
|||
end |
end |
||
-- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
-- Account for the oddity that is {{cite conference}}, before generation of COinS data. |
||
local ChapterLink -- = A['ChapterLink']; -- deprecated as a parameter but still used internally by cite episode |
|||
local Conference = A['Conference']; |
|||
local BookTitle = A['BookTitle']; |
|||
local TransTitle_origin = A:ORIGIN ('TransTitle'); |
|||
if 'conference' == config.CitationClass then |
if 'conference' == config.CitationClass then |
||
if is_set(BookTitle) then |
if utilities.is_set (BookTitle) then |
||
Chapter = Title; |
Chapter = Title; |
||
Chapter_origin = 'title'; |
|||
-- ChapterLink = TitleLink; -- |chapterlink= is deprecated |
|||
-- ChapterLink = TitleLink; -- |chapter-link= is deprecated |
|||
ChapterURL = URL; |
ChapterURL = URL; |
||
ChapterUrlAccess = UrlAccess; |
ChapterUrlAccess = UrlAccess; |
||
ChapterURL_origin = URL_origin; |
|||
URL_origin = ''; |
|||
ChapterFormat = Format; |
ChapterFormat = Format; |
||
TransChapter = TransTitle; |
TransChapter = TransTitle; |
||
TransChapter_origin = TransTitle_origin; |
|||
Title = BookTitle; |
Title = BookTitle; |
||
Format = ''; |
Format = ''; |
||
-- |
-- TitleLink = ''; |
||
TransTitle = ''; |
TransTitle = ''; |
||
URL = ''; |
URL = ''; |
||
Line 2,476: | Line 2,881: | ||
Conference = ''; -- not cite conference or cite speech so make sure this is empty string |
Conference = ''; -- not cite conference or cite speech so make sure this is empty string |
||
end |
end |
||
-- CS1/2 mode |
|||
local Mode = is_valid_parameter_value (A['Mode'], A:ORIGIN('Mode'), cfg.keywords_lists['mode'], ''); |
|||
-- separator character and postscript |
|||
local sepc, PostScript = set_style (Mode:lower(), A['PostScript'], config.CitationClass); |
|||
-- controls capitalization of certain static text |
|||
local use_lowercase = ( sepc == ',' ); |
|||
-- cite map oddities |
-- cite map oddities |
||
local Cartography = ""; |
local Cartography = ""; |
||
Line 2,483: | Line 2,895: | ||
local Sheets = A['Sheets'] or ''; |
local Sheets = A['Sheets'] or ''; |
||
if config.CitationClass == "map" then |
if config.CitationClass == "map" then |
||
if utilities.is_set (Chapter) then --TODO: make a function for this and similar? |
|||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'map') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', Chapter_origin)}); -- add error message |
|||
end |
|||
Chapter = A['Map']; |
Chapter = A['Map']; |
||
Chapter_origin = A:ORIGIN('Map'); |
|||
ChapterURL = A['MapURL']; |
ChapterURL = A['MapURL']; |
||
ChapterURL_origin = A:ORIGIN('MapURL'); |
|||
ChapterUrlAccess = UrlAccess; |
|||
TransChapter = A['TransMap']; |
TransChapter = A['TransMap']; |
||
ScriptChapter = A['ScriptMap'] |
|||
ChapterURLorigin = A:ORIGIN('MapURL'); |
|||
ScriptChapter_origin = A:ORIGIN('ScriptMap') |
|||
ChapterUrlAccess = MapUrlAccess; |
|||
ChapterFormat = A['MapFormat']; |
ChapterFormat = A['MapFormat']; |
||
Cartography = A['Cartography']; |
Cartography = A['Cartography']; |
||
if is_set( Cartography ) then |
if utilities.is_set ( Cartography ) then |
||
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); |
Cartography = sepc .. " " .. wrap_msg ('cartography', Cartography, use_lowercase); |
||
end |
end |
||
Scale = A['Scale']; |
Scale = A['Scale']; |
||
if is_set( Scale ) then |
if utilities.is_set ( Scale ) then |
||
Scale = sepc .. " " .. Scale; |
Scale = sepc .. " " .. Scale; |
||
end |
end |
||
Line 2,501: | Line 2,920: | ||
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. |
-- Account for the oddities that are {{cite episode}} and {{cite serial}}, before generation of COinS data. |
||
local Series = A['Series']; |
|||
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then |
if 'episode' == config.CitationClass or 'serial' == config.CitationClass then |
||
local AirDate = A['AirDate']; |
|||
local SeriesLink = A['SeriesLink']; |
local SeriesLink = A['SeriesLink']; |
||
link_title_ok (SeriesLink, A:ORIGIN ('SeriesLink'), Series, 'series'); -- check for |
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 Network = A['Network']; |
||
Line 2,511: | Line 2,930: | ||
local s, n = {}, {}; |
local s, n = {}, {}; |
||
-- do common parameters first |
-- do common parameters first |
||
if is_set(Network) then table.insert(n, Network); end |
if utilities.is_set (Network) then table.insert(n, Network); end |
||
if is_set(Station) then table.insert(n, Station); end |
if utilities.is_set (Station) then table.insert(n, Station); end |
||
ID = table.concat(n, sepc .. ' '); |
ID = table.concat(n, sepc .. ' '); |
||
if not is_set (Date) and is_set (AirDate) then -- promote airdate to date |
|||
Date = AirDate; |
|||
end |
|||
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
if 'episode' == config.CitationClass then -- handle the oddities that are strictly {{cite episode}} |
||
local Season = A['Season']; |
local Season = A['Season']; |
||
local SeriesNumber = A['SeriesNumber']; |
local SeriesNumber = A['SeriesNumber']; |
||
if is_set (Season) and is_set (SeriesNumber) then |
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set TODO: make a function for this and similar? |
||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'season') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'seriesno')}); -- add error message |
|||
SeriesNumber = ''; -- unset; prefer |season= over |seriesno= |
SeriesNumber = ''; -- unset; prefer |season= over |seriesno= |
||
end |
end |
||
-- assemble a table of parts concatenated later into Series |
-- assemble a table of parts concatenated later into Series |
||
if is_set(Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
if utilities.is_set (Season) then table.insert(s, wrap_msg ('season', Season, use_lowercase)); end |
||
if is_set(SeriesNumber) then table.insert(s, wrap_msg (' |
if utilities.is_set (SeriesNumber) then table.insert(s, wrap_msg ('seriesnum', SeriesNumber, use_lowercase)); end |
||
if is_set(Issue) then table.insert(s, wrap_msg ('episode', Issue, 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 |
Issue = ''; -- unset because this is not a unique parameter |
||
Chapter = Title; -- promote title parameters to chapter |
Chapter = Title; -- promote title parameters to chapter |
||
ScriptChapter = ScriptTitle; |
ScriptChapter = ScriptTitle; |
||
ScriptChapter_origin = A:ORIGIN('ScriptTitle'); |
|||
ChapterLink = TitleLink; -- alias episodelink |
|||
ChapterLink = TitleLink; -- alias |episode-link= |
|||
TransChapter = TransTitle; |
TransChapter = TransTitle; |
||
ChapterURL = URL; |
ChapterURL = URL; |
||
ChapterUrlAccess = UrlAccess; |
ChapterUrlAccess = UrlAccess; |
||
ChapterURL_origin = URL_origin; |
|||
ChapterURLorigin = A:ORIGIN('URL'); |
|||
ChapterFormat = Format; |
|||
Title = Series; -- promote series to title |
Title = Series; -- promote series to title |
||
TitleLink = SeriesLink; |
TitleLink = SeriesLink; |
||
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number |
Series = table.concat(s, sepc .. ' '); -- this is concatenation of season, seriesno, episode number |
||
if is_set (ChapterLink) and not is_set (ChapterURL) then |
if utilities.is_set (ChapterLink) and not utilities.is_set (ChapterURL) then -- link but not URL |
||
Chapter = make_wikilink (ChapterLink, Chapter); |
Chapter = utilities.make_wikilink (ChapterLink, Chapter); |
||
elseif is_set (ChapterLink) and is_set (ChapterURL) then |
elseif utilities.is_set (ChapterLink) and utilities.is_set (ChapterURL) then -- if both are set, URL links episode; |
||
Series = make_wikilink (ChapterLink, Series); |
Series = utilities.make_wikilink (ChapterLink, Series); |
||
end |
end |
||
URL = ''; -- unset |
URL = ''; -- unset |
||
TransTitle = ''; |
TransTitle = ''; |
||
ScriptTitle = ''; |
ScriptTitle = ''; |
||
Format = ''; |
|||
else -- now oddities that are cite serial |
else -- now oddities that are cite serial |
||
Issue = ''; -- unset because this parameter no longer supported by the citation/core version of 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? |
Chapter = A['Episode']; -- TODO: make |episode= available to cite episode someday? |
||
if is_set (Series) and is_set (SeriesLink) then |
if utilities.is_set (Series) and utilities.is_set (SeriesLink) then |
||
Series = make_wikilink (SeriesLink, Series); |
Series = utilities.make_wikilink (SeriesLink, Series); |
||
end |
end |
||
Series = wrap_style ('italic-title', Series); |
Series = utilities.wrap_style ('italic-title', Series); -- series is italicized |
||
end |
end |
||
end |
end |
||
-- end of {{cite episode}} stuff |
-- end of {{cite episode}} stuff |
||
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, before generation of COinS data. |
|||
do |
|||
if in_array (config.CitationClass, {'arxiv', 'biorxiv', 'citeseerx'}) then |
|||
if not is_set (ID_list[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates |
|||
table.insert( z.message_tail, { set_error( config.CitationClass .. '_missing', {}, true ) } ); -- add error message |
|||
end |
|||
if 'arxiv' == config.CitationClass then |
|||
Periodical = 'arXiv'; -- set to arXiv for COinS; after that, must be set to empty string |
|||
end |
|||
if 'biorxiv' == config.CitationClass then |
|||
Periodical = 'bioRxiv'; -- set to bioRxiv for COinS; after that, must be set to empty string |
|||
end |
|||
if 'citeseerx' == config.CitationClass then |
|||
Periodical = 'CiteSeerX'; -- set to CiteSeerX for COinS; after that, must be set to empty string |
|||
end |
|||
end |
|||
end |
|||
-- handle type parameter for those CS1 citations that have default values |
-- handle type parameter for those CS1 citations that have default values |
||
local TitleType = A['TitleType']; |
|||
if in_array(config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then |
|||
local Degree = A['Degree']; |
|||
if utilities.in_array (config.CitationClass, {'AV-media-notes', 'interview', 'mailinglist', 'map', 'podcast', 'pressrelease', 'report', 'speech', 'techreport', 'thesis'}) then |
|||
TitleType = set_titletype (config.CitationClass, TitleType); |
TitleType = set_titletype (config.CitationClass, TitleType); |
||
if is_set(Degree) and "Thesis" == TitleType then |
if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis |
||
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower(); |
TitleType = Degree .. ' ' .. cfg.title_types ['thesis']:lower(); |
||
end |
end |
||
end |
end |
||
if is_set(TitleType) then |
if utilities.is_set (TitleType) then -- if type parameter is specified |
||
TitleType = substitute( cfg.messages['type'], TitleType); |
TitleType = utilities.substitute ( cfg.messages['type'], TitleType); -- display it in parentheses |
||
-- TODO: Hack on TitleType to fix bunched parentheses problem |
-- TODO: Hack on TitleType to fix bunched parentheses problem |
||
end |
end |
||
-- legacy: promote PublicationDate to Date if neither Date nor Year are set. |
-- legacy: promote PublicationDate to Date if neither Date nor Year are set. |
||
local Date = A['Date']; |
|||
local Date_origin; -- to hold the name of parameter promoted to Date; required for date error messaging |
|||
local PublicationDate = A['PublicationDate']; |
|||
local Year = A['Year']; |
|||
if not utilities.is_set (Date) then |
|||
Date = Year; -- promote Year to Date |
Date = Year; -- promote Year to Date |
||
Year = nil; -- make nil so Year as empty string isn't used for CITEREF |
Year = nil; -- make nil so Year as empty string isn't used for CITEREF |
||
if not is_set (Date) and is_set(PublicationDate) then |
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 |
Date = PublicationDate; -- promote PublicationDate to Date |
||
PublicationDate = ''; -- unset, no longer needed |
PublicationDate = ''; -- unset, no longer needed |
||
Date_origin = A:ORIGIN('PublicationDate'); -- save the name of the promoted parameter |
|||
else |
|||
Date_origin = A:ORIGIN('Year'); -- save the name of the promoted parameter |
|||
end |
end |
||
else |
|||
Date_origin = A:ORIGIN('Date'); -- not a promotion; name required for error messaging |
|||
end |
end |
||
Line 2,617: | Line 3,026: | ||
Date validation supporting code is in Module:Citation/CS1/Date_validation |
Date validation supporting code is in Module:Citation/CS1/Date_validation |
||
]] |
]] |
||
local DF = is_valid_parameter_value (A['DF'], A:ORIGIN('DF'), cfg.keywords_lists['df'], ''); |
|||
if not utilities.is_set (DF) then |
|||
DF = cfg.global_df; -- local |df= if present overrides global df set by {{use xxx date}} template |
|||
end |
|||
local ArchiveURL; |
|||
local ArchiveDate; |
|||
local ArchiveFormat = A['ArchiveFormat']; |
|||
ArchiveURL, ArchiveDate = archive_url_check (A['ArchiveURL'], A['ArchiveDate']) |
|||
ArchiveFormat = style_format (ArchiveFormat, ArchiveURL, 'archive-format', 'archive-url'); |
|||
ArchiveURL, ArchiveDate = is_unique_archive_url (ArchiveURL, URL, ChapterURL, A:ORIGIN('ArchiveURL'), ArchiveDate); -- add error message when URL or ChapterURL == ArchiveURL |
|||
local AccessDate = A['AccessDate']; |
|||
local LayDate = A['LayDate']; |
|||
local COinS_date = {}; -- holds date info extracted from |date= for the COinS metadata by Module:Date verification |
|||
local DoiBroken = A['DoiBroken']; |
|||
local Embargo = A['Embargo']; |
|||
local anchor_year; -- used in the CITEREF identifier |
|||
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch |
do -- create defined block to contain local variables error_message, date_parameters_list, mismatch |
||
local error_message = ''; |
local error_message = ''; |
||
-- AirDate has been promoted to Date so not necessary to check it |
-- AirDate has been promoted to Date so not necessary to check it |
||
local date_parameters_list = { |
local date_parameters_list = { |
||
['access-date'] = {val = AccessDate, name = A:ORIGIN ('AccessDate')}, |
|||
['embargo']=Embargo, ['lay-date']=LayDate, ['publication-date']=PublicationDate, ['year']=Year}; |
|||
['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); |
|||
anchor_year, Embargo, error_message = dates(date_parameters_list, COinS_date); |
|||
-- start temporary Julian / Gregorian calendar uncertainty categorization |
-- start temporary Julian / Gregorian calendar uncertainty categorization |
||
if COinS_date.inter_cal_cat then |
if COinS_date.inter_cal_cat then |
||
add_prop_cat (' |
utilities.add_prop_cat ('jul-greg-uncertainty'); |
||
end |
end |
||
-- end temporary Julian / Gregorian calendar uncertainty categorization |
-- end temporary Julian / Gregorian calendar uncertainty categorization |
||
if is_set (Year) and is_set (Date) then |
if utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed; |
||
validation.year_date_check (Year, A:ORIGIN ('Year'), Date, A:ORIGIN ('Date'), error_list); |
|||
local mismatch = year_date_check (Year, Date) |
|||
if 0 == mismatch then -- |year= does not match a year-value in |date= |
|||
if is_set (error_message) then -- if there is already an error message |
|||
error_message = error_message .. ', '; -- tack on this additional message |
|||
end |
|||
error_message = error_message .. '|year= / |date= mismatch'; |
|||
elseif 1 == mismatch then -- |year= matches year-value in |date= |
|||
add_maint_cat ('date_year'); |
|||
end |
|||
end |
end |
||
if |
if 0 == #error_list then -- error free dates only; 0 when error_list is empty |
||
local modified = false; -- flag |
local modified = false; -- flag |
||
if is_set (DF) then |
if utilities.is_set (DF) then -- if we need to reformat dates |
||
modified = reformat_dates (date_parameters_list, DF |
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate |
||
end |
end |
||
if true == date_hyphen_to_dash (date_parameters_list) then |
if true == validation.date_hyphen_to_dash (date_parameters_list) then -- convert hyphens to dashes where appropriate |
||
modified = true; |
modified = true; |
||
utilities.set_message ('maint_date_format'); -- hyphens were converted so add maint category |
|||
end |
end |
||
-- for those wikis that can and want to have English date names translated to the local language |
-- for those wikis that can and want to have English date names translated to the local language; not supported at en.wiki |
||
if cfg.date_name_auto_xlate_enable and validation.date_name_xlate (date_parameters_list, cfg.date_digit_auto_xlate_enable ) then |
|||
-- uncomment these three lines. Not supported by en.wiki (for obvious reasons) |
|||
utilities.set_message ('maint_date_auto_xlated'); -- add maint cat |
|||
-- if date_name_xlate (date_parameters_list) then |
|||
modified = true; |
|||
end |
|||
if modified then -- if the date_parameters_list values were modified |
if modified then -- if the date_parameters_list values were modified |
||
AccessDate = date_parameters_list['access-date']; |
AccessDate = date_parameters_list['access-date'].val; -- overwrite date holding parameters with modified values |
||
ArchiveDate = date_parameters_list['archive-date']; |
ArchiveDate = date_parameters_list['archive-date'].val; |
||
Date = date_parameters_list['date']; |
Date = date_parameters_list['date'].val; |
||
DoiBroken = date_parameters_list['doi-broken-date']; |
DoiBroken = date_parameters_list['doi-broken-date'].val; |
||
LayDate = date_parameters_list['lay-date']; |
LayDate = date_parameters_list['lay-date'].val; |
||
PublicationDate = date_parameters_list['publication-date']; |
PublicationDate = date_parameters_list['publication-date'].val; |
||
end |
end |
||
else |
else |
||
utilities.set_message ('err_bad_date', {utilities.make_sep_list (#error_list, error_list)}); -- add this error message |
|||
end |
end |
||
end -- end of do |
end -- end of do |
||
local ID_list = {}; -- sequence table of rendered identifiers |
|||
-- Account for the oddity that is {{cite journal}} with |pmc= set and |url= not set. Do this after date check but before COInS. |
|||
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key |
|||
-- Here we unset Embargo if PMC not embargoed (|embargo= not set in the citation) or if the embargo time has expired. Otherwise, holds embargo date |
|||
local Class = A['Class']; -- arxiv class identifier |
|||
Embargo = is_embargoed (Embargo); |
|||
local ID_support = { |
|||
{A['ASINTLD'], 'ASIN', 'err_asintld_missing_asin', A:ORIGIN ('ASINTLD')}, |
|||
{DoiBroken, 'DOI', 'err_doibroken_missing_doi', A:ORIGIN ('DoiBroken')}, |
|||
{Embargo, 'PMC', 'err_embargo_missing_pmc', A:ORIGIN ('Embargo')}, |
|||
} |
|||
ID_list, ID_list_coins = identifiers.identifier_lists_get (args, {DoiBroken = DoiBroken, ASINTLD = A['ASINTLD'], Embargo = Embargo, Class = Class}, ID_support); |
|||
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data. |
|||
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv=, |citeseerx=, |ssrn= required for their templates |
|||
if not (args[cfg.id_handlers[config.CitationClass:upper()].parameters[1]] or -- can't use ID_list_coins k/v table here because invalid parameters omitted |
|||
args[cfg.id_handlers[config.CitationClass:upper()].parameters[2]]) then -- which causes unexpected parameter missing error message |
|||
utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message |
|||
end |
|||
Periodical = ({['arxiv'] = 'arXiv', ['biorxiv'] = 'bioRxiv', ['citeseerx'] = 'CiteSeerX', ['ssrn'] = 'Social Science Research Network'})[config.CitationClass]; |
|||
end |
|||
-- 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= |
|||
elseif identifiers.auto_link_urls['pmc'] then -- auto-select PMC |
|||
URL = identifiers.auto_link_urls['pmc']; -- set URL to be the same as the PMC external link if not embargoed |
|||
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) then -- set when using an identifier-created URL |
|||
if config.CitationClass == "journal" and not is_set(URL) and is_set(ID_list['PMC']) then |
|||
if |
if utilities.is_set (AccessDate) then -- |access-date= requires |url=; identifier-created URL is not |url= |
||
utilities.set_message ('err_accessdate_missing_url'); -- add an error message |
|||
URL=cfg.id_handlers['PMC'].prefix .. ID_list['PMC']; -- set url to be the same as the PMC external link if not embargoed |
|||
URLorigin = cfg.id_handlers['PMC'].parameters[1]; -- set URLorigin to parameter name for use in error message if citation is missing a |title= |
|||
if is_set(AccessDate) then -- access date requires |url=; pmc created url is not |url= |
|||
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
|||
AccessDate = ''; -- unset |
AccessDate = ''; -- unset |
||
end |
end |
||
if utilities.is_set (ArchiveURL) then -- |archive-url= requires |url=; identifier-created URL is not |url= |
|||
utilities.set_message ('err_archive_missing_url'); -- add an error message |
|||
ArchiveURL = ''; -- unset |
|||
end |
|||
end |
end |
||
end |
end |
||
Line 2,691: | Line 3,159: | ||
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. |
-- At this point fields may be nil if they weren't specified in the template use. We can use that fact. |
||
-- Test if citation has no title |
-- Test if citation has no title |
||
if not utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode |
|||
if not is_set(Title) and |
|||
utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}); |
|||
not is_set(TransTitle) and |
|||
not is_set(ScriptTitle) then |
|||
if 'episode' == config.CitationClass then -- special case for cite episode; TODO: is there a better way to do this? |
|||
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'series'}, true ) } ); |
|||
else |
|||
table.insert( z.message_tail, { set_error( 'citation_missing_title', {'title'}, true ) } ); |
|||
end |
|||
end |
end |
||
if utilities.in_array (cfg.keywords_xlate[Title], {'off', 'none'}) and |
|||
if 'none' == Title and in_array (config.CitationClass, {'journal', 'citation'}) and is_set (Periodical) and 'journal' == A:ORIGIN('Periodical') then -- special case for journal cites |
|||
utilities.in_array (config.CitationClass, {'journal', 'citation'}) and |
|||
Title = ''; -- set title to empty string |
|||
(utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and |
|||
add_maint_cat ('untitled'); |
|||
('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 |
end |
||
check_for_url ({ -- add error message when any of these parameters contains a URL |
|||
['title']=Title, |
|||
[A:ORIGIN('Chapter')]=Chapter, |
|||
[A:ORIGIN('Periodical')]=Periodical, |
|||
[A:ORIGIN('PublisherName')] = PublisherName |
|||
}); |
|||
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. |
-- COinS metadata (see <http://ocoins.info/>) for automated parsing of citation information. |
||
Line 2,720: | Line 3,178: | ||
local coins_chapter = Chapter; -- default assuming that remapping not required |
local coins_chapter = Chapter; -- default assuming that remapping not required |
||
local coins_title = Title; -- et tu |
local coins_title = Title; -- et tu |
||
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and is_set (Encyclopedia)) then |
if 'encyclopaedia' == config.CitationClass or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then |
||
if is_set (Chapter) and is_set (Title) and is_set (Periodical) then -- if all are used 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_chapter = Title; -- remap |
||
coins_title = Periodical; |
coins_title = Periodical; |
||
Line 2,730: | Line 3,188: | ||
coins_author = c; -- use that instead |
coins_author = c; -- use that instead |
||
end |
end |
||
-- this is the function call to COinS() |
-- this is the function call to COinS() |
||
local OCinSoutput = COinS({ |
local OCinSoutput = metadata.COinS({ |
||
['Periodical'] = Periodical, |
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata |
||
['Encyclopedia'] = Encyclopedia, |
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS |
||
['Chapter'] = make_coins_title (coins_chapter, ScriptChapter), |
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic / accept-as-written markup |
||
['Degree'] = Degree; -- cite thesis only |
['Degree'] = Degree; -- cite thesis only |
||
['Title'] = make_coins_title (coins_title, ScriptTitle), |
['Title'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic / accept-as-written markup |
||
['PublicationPlace'] = PublicationPlace, |
['PublicationPlace'] = PublicationPlace, |
||
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; |
['Date'] = COinS_date.rftdate, -- COinS_date has correctly formatted date if Date is valid; |
||
['Season'] = COinS_date.rftssn, |
['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? |
['Chron'] = COinS_date.rftchron or (not COinS_date.rftdate and Date) or '', -- chron but if not set and invalid date format use Date; keep this last bit? |
||
['Series'] = Series, |
['Series'] = Series, |
||
['Volume'] = Volume, |
['Volume'] = Volume, |
||
['Issue'] = Issue, |
['Issue'] = Issue, |
||
['ArticleNumber'] = ArticleNumber, |
|||
['Pages'] = get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, 5)), -- pages stripped of external links |
|||
['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, |
['Edition'] = Edition, |
||
['PublisherName'] = PublisherName, |
['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName |
||
['URL'] = first_set ({ChapterURL, URL}, 2), |
['URL'] = first_set ({ChapterURL, URL}, 2), |
||
['Authors'] = coins_author, |
['Authors'] = coins_author, |
||
['ID_list'] = |
['ID_list'] = ID_list_coins, |
||
['RawPage'] = this_page.prefixedText, |
['RawPage'] = this_page.prefixedText, |
||
}, config.CitationClass); |
}, config.CitationClass); |
||
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, and {{cite |
-- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, and {{cite ssrn}} AFTER generation of COinS data. |
||
if in_array (config.CitationClass, |
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 |
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 |
-- special case for cite newsgroup. Do this after COinS because we are modifying Publishername to include some static text |
||
if 'newsgroup' == config.CitationClass then |
if 'newsgroup' == config.CitationClass and utilities.is_set (Newsgroup) then |
||
PublisherName = utilities.substitute (cfg.messages['newsgroup'], external_link( 'news:' .. Newsgroup, Newsgroup, Newsgroup_origin, nil )); |
|||
if is_set (PublisherName) then |
|||
PublisherName = substitute (cfg.messages['newsgroup'], external_link( 'news:' .. PublisherName, PublisherName, A:ORIGIN('PublisherName'), nil )); |
|||
end |
|||
end |
end |
||
local Editors; |
|||
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list |
|||
local Contributors; -- assembled contributors name list |
|||
local contributor_etal; |
|||
local Translators; -- assembled translators name list |
|||
local translator_etal; |
|||
local t = {}; -- translators list from |translator-lastn= / translator-firstn= pairs |
|||
t = extract_names (args, 'TranslatorList'); -- fetch translator list from |translatorn= / |translator-lastn=, -firstn=, -linkn=, -maskn= |
|||
local Interviewers; |
|||
local interviewers_list = {}; |
|||
interviewers_list = extract_names (args, 'InterviewerList'); -- process preferred interviewers parameters |
|||
local interviewer_etal; |
|||
-- Now perform various field substitutions. |
-- Now perform various field substitutions. |
||
-- We also add leading spaces and surrounding markup and punctuation to the |
-- We also add leading spaces and surrounding markup and punctuation to the |
||
-- various parts of the citation, but only when they are non-nil. |
-- various parts of the citation, but only when they are non-nil. |
||
local EditorCount; -- used only for choosing {ed.) or (eds.) annotation at end of editor name-list |
|||
do |
do |
||
local last_first_list; |
local last_first_list; |
||
local control = { |
local control = { |
||
format = |
format = NameListStyle, -- empty string or 'vanc' |
||
maximum = nil, -- as if display-authors or display-editors not set |
maximum = nil, -- as if display-authors or display-editors not set |
||
lastauthoramp = LastAuthorAmp, |
|||
page_name = this_page.text, -- get current page name so that we don't wikilink to it via editorlinkn |
|||
mode = Mode |
mode = Mode |
||
}; |
}; |
||
do -- do editor name list first because the now unsupported coauthors used to modify control table |
do -- do editor name list first because the now unsupported coauthors used to modify control table |
||
control.maximum , editor_etal = |
control.maximum , editor_etal = get_display_names (A['DisplayEditors'], #e, 'editors', editor_etal, A:ORIGIN ('DisplayEditors')); |
||
Editors, EditorCount = list_people (control, e, editor_etal); |
|||
if is_set (Editors) then |
|||
if editor_etal then |
|||
Editors = Editors .. ' ' .. cfg.messages['et al']; -- add et al. to editors parameter beause |display-editors=etal |
|||
EditorCount = 2; -- with et al., |editors= is multiple names; spoof to display (eds.) annotation |
|||
else |
|||
EditorCount = 2; -- we don't know but assume |editors= is multiple names; spoof to display (eds.) annotation |
|||
end |
|||
else |
|||
Editors = last_first_list; -- either an author name list or an empty string |
|||
end |
|||
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then |
if 1 == EditorCount and (true == editor_etal or 1 < #e) then -- only one editor displayed but includes etal then |
||
Line 2,802: | Line 3,257: | ||
end |
end |
||
do -- now do interviewers |
do -- now do interviewers |
||
control.maximum = #interviewers_list |
control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal, A:ORIGIN ('DisplayInterviewers')); |
||
Interviewers = list_people(control, interviewers_list, |
Interviewers = list_people (control, interviewers_list, interviewer_etal); |
||
end |
end |
||
do -- now do translators |
do -- now do translators |
||
control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators')); |
|||
control.maximum = #t; -- number of translators |
|||
Translators = list_people(control, t, |
Translators = list_people (control, t, translator_etal); |
||
end |
end |
||
do -- now do contributors |
do -- now do contributors |
||
control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors')); |
|||
control.maximum = #c; -- number of contributors |
|||
Contributors = list_people(control, c, |
Contributors = list_people (control, c, contributor_etal); |
||
end |
end |
||
do -- now do authors |
do -- now do authors |
||
control.maximum |
control.maximum, author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal, A:ORIGIN ('DisplayAuthors')); |
||
last_first_list = list_people(control, a, author_etal); |
last_first_list = list_people (control, a, author_etal); |
||
if is_set (Authors) then |
if utilities.is_set (Authors) then |
||
Authors, author_etal = name_has_etal (Authors, author_etal, false); -- find and remove variations on et al. |
Authors, author_etal = name_has_etal (Authors, author_etal, false, 'authors'); -- find and remove variations on et al. |
||
if author_etal then |
if author_etal then |
||
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter |
Authors = Authors .. ' ' .. cfg.messages['et al']; -- add et al. to authors parameter |
||
Line 2,828: | Line 3,283: | ||
end -- end of do |
end -- end of do |
||
if is_set (Authors) and is_set (Collaboration) then |
if utilities.is_set (Authors) and utilities.is_set (Collaboration) then |
||
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. |
Authors = Authors .. ' (' .. Collaboration .. ')'; -- add collaboration after et al. |
||
end |
end |
||
Line 2,834: | Line 3,289: | ||
end |
end |
||
local ConferenceFormat = A['ConferenceFormat']; |
|||
-- apply |[xx-]format= styling; at the end, these parameters hold correctly styled format annotation, |
|||
local ConferenceURL = A['ConferenceURL']; |
|||
-- 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'); |
ConferenceFormat = style_format (ConferenceFormat, ConferenceURL, 'conference-format', 'conference-url'); |
||
Format = style_format (Format, URL, 'format', '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 |
-- special case for chapter format so no error message or cat when chapter not supported |
||
if not (in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or |
if not (utilities.in_array (config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx', 'ssrn'}) or |
||
('citation' == config.CitationClass and is_set (Periodical) and not is_set (Encyclopedia))) then |
('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'); |
ChapterFormat = style_format (ChapterFormat, ChapterURL, 'chapter-format', 'chapter-url'); |
||
end |
end |
||
if not is_set(URL) then |
if not utilities.is_set (URL) then |
||
if in_array(config.CitationClass, {"web","podcast", "mailinglist"}) |
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, { set_error( 'cite_web_url', {}, true ) } ); |
|||
utilities.set_message ('err_cite_web_url'); |
|||
end |
end |
||
-- do we have |accessdate= without either |url= or |chapter-url=? |
-- do we have |accessdate= without either |url= or |chapter-url=? |
||
if is_set(AccessDate) and not is_set(ChapterURL)then |
if utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set; |
||
utilities.set_message ('err_accessdate_missing_url'); |
|||
table.insert( z.message_tail, { set_error( 'accessdate_missing_url', {}, true ) } ); |
|||
AccessDate = ''; |
AccessDate = ''; |
||
end |
end |
||
end |
end |
||
local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); |
|||
local OriginalURL, OriginalURLorigin, OriginalFormat, OriginalAccess; |
|||
local OriginalURL |
|||
DeadURL = DeadURL:lower(); -- used later when assembling archived text |
|||
local OriginalURL_origin |
|||
if is_set( ArchiveURL ) then |
|||
local OriginalFormat |
|||
if is_set (ChapterURL) then -- URL not set so if chapter-url is set apply archive url to it |
|||
local 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 = 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 |format= |
OriginalFormat = ChapterFormat; -- and original |chapter-format= |
||
if 'no' ~= DeadURL then |
|||
if 'live' ~= UrlStatus then |
|||
ChapterURL = ArchiveURL -- swap-in the archive's url |
|||
ChapterURL = ArchiveURL -- swap-in the archive's URL |
|||
ChapterURL_origin = A:ORIGIN('ArchiveURL') -- name of |archive-url= parameter for error messages |
|||
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
ChapterFormat = ArchiveFormat or ''; -- swap in archive's format |
||
ChapterUrlAccess = nil; -- restricted access levels do not make sense for archived URLs |
|||
end |
end |
||
elseif is_set (URL) then |
elseif utilities.is_set (URL) then |
||
OriginalURL = URL; -- save copy of original source URL |
OriginalURL = URL; -- save copy of original source URL |
||
OriginalURL_origin = URL_origin; -- name of URL parameter for error messages |
|||
OriginalFormat = Format; -- and original |format= |
OriginalFormat = Format; -- and original |format= |
||
OriginalAccess = UrlAccess; |
OriginalAccess = UrlAccess; |
||
if 'no' ~= DeadURL then -- if URL set then archive-url applies to it |
|||
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 |
Format = ArchiveFormat or ''; -- swap in archive's format |
||
UrlAccess = nil; -- restricted access levels do not make sense for archived |
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs |
||
end |
end |
||
end |
|||
elseif utilities.is_set (UrlStatus) then -- if |url-status= is set when |archive-url= is not set |
|||
utilities.set_message ('maint_url_status'); -- add maint cat |
|||
end |
end |
||
if in_array(config.CitationClass, {'web','news','journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'arxiv', 'biorxiv', 'citeseerx'}) or -- if any of the 'periodical' cites except encyclopedia |
if 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 is_set (Periodical) and not is_set (Encyclopedia)) then |
('citation' == config.CitationClass and (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical)) and not utilities.is_set (Encyclopedia)) then |
||
local chap_param; |
local chap_param; |
||
if is_set (Chapter) then |
if utilities.is_set (Chapter) then -- get a parameter name from one of these chapter related meta-parameters |
||
chap_param = A:ORIGIN ('Chapter') |
chap_param = A:ORIGIN ('Chapter') |
||
elseif is_set (TransChapter) then |
elseif utilities.is_set (TransChapter) then |
||
chap_param = A:ORIGIN ('TransChapter') |
chap_param = A:ORIGIN ('TransChapter') |
||
elseif is_set (ChapterURL) then |
elseif utilities.is_set (ChapterURL) then |
||
chap_param = A:ORIGIN ('ChapterURL') |
chap_param = A:ORIGIN ('ChapterURL') |
||
elseif is_set (ScriptChapter) then |
elseif utilities.is_set (ScriptChapter) then |
||
chap_param = |
chap_param = ScriptChapter_origin; |
||
else is_set (ChapterFormat) |
else utilities.is_set (ChapterFormat) |
||
chap_param = A:ORIGIN ('ChapterFormat') |
chap_param = A:ORIGIN ('ChapterFormat') |
||
end |
end |
||
if is_set (chap_param) then |
if utilities.is_set (chap_param) then -- if we found one |
||
utilities.set_message ('err_chapter_ignored', {chap_param}); -- add error message |
|||
Chapter = ''; -- and set them to empty string to be safe with concatenation |
Chapter = ''; -- and set them to empty string to be safe with concatenation |
||
TransChapter = ''; |
TransChapter = ''; |
||
Line 2,911: | Line 3,373: | ||
else -- otherwise, format chapter / article title |
else -- otherwise, format chapter / article title |
||
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value |
local no_quotes = false; -- default assume that we will be quoting the chapter parameter value |
||
if is_set (Contribution) and 0 < #c then |
if utilities.is_set (Contribution) and 0 < #c then -- if this is a contribution with contributor(s) |
||
if in_array (Contribution:lower(), cfg. |
if utilities.in_array (Contribution:lower(), cfg.keywords_lists.contribution) then -- and a generic contribution title |
||
no_quotes = true; -- then render it unquoted |
no_quotes = true; -- then render it unquoted |
||
end |
end |
||
end |
end |
||
Chapter = format_chapter_title (ScriptChapter, Chapter, TransChapter, ChapterURL, |
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 is_set (Chapter) then |
if utilities.is_set (Chapter) then |
||
Chapter = Chapter .. ChapterFormat ; |
Chapter = Chapter .. ChapterFormat ; |
||
if 'map' == config.CitationClass and is_set (TitleType) then |
if 'map' == config.CitationClass and utilities.is_set (TitleType) then |
||
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title |
Chapter = Chapter .. ' ' .. TitleType; -- map annotation here; not after title |
||
end |
end |
||
Chapter = Chapter.. sepc .. ' '; |
Chapter = Chapter .. sepc .. ' '; |
||
elseif is_set (ChapterFormat) then |
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 |
Chapter = ChapterFormat .. sepc .. ' '; -- ... ChapterFormat has error message, we want to see it |
||
end |
end |
||
end |
end |
||
-- Format main title |
-- Format main title |
||
local plain_title = false; |
|||
if '...' == Title:sub (-3) then -- if elipsis is the last three characters of |title= |
|||
local accept_title; |
|||
Title = mw.ustring.gsub (Title, '(%.%.%.)%.+$', '%1'); -- limit the number of dots to three |
|||
Title, accept_title = utilities.has_accept_as_written (Title, true); -- remove accept-this-as-written markup when it wraps all of <Title> |
|||
elseif not mw.ustring.find (Title, '%.%s*%a%.') then -- end of title is not a 'dot-(optional space-)letter-dot' initialism |
|||
if accept_title and ('' == Title) then -- only support forced empty for now "(())" |
|||
Title = mw.ustring.gsub(Title, '%'..sepc..'$', ''); -- remove any trailing separator character |
|||
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 is_set(TitleLink) and is_set(Title) then |
|||
if not accept_title then -- <Title> not wrapped in accept-as-written markup |
|||
Title = make_wikilink (TitleLink, Title); |
|||
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 ('generic_titles', Title) then |
|||
utilities.set_message ('err_generic_title'); -- set an error message |
|||
end |
|||
end |
end |
||
if in_array(config.CitationClass, {'web', 'news', 'journal', 'magazine', 'pressrelease', 'podcast', 'newsgroup', 'mailinglist', 'interview', 'arxiv', 'biorxiv', 'citeseerx'}) or |
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 is_set (Periodical) and not is_set (Encyclopedia)) 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 is_set (Periodical)) then |
('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 |
Title = kern_quotes (Title); -- if necessary, separate title's leading and trailing quote marks from module provided quote marks |
||
Title = wrap_style ('quoted-title', Title); |
Title = utilities.wrap_style ('quoted-title', Title); |
||
Title = script_concatenate (Title, ScriptTitle); |
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped |
||
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); |
||
elseif 'report' == config.CitationClass then |
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); |
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped |
||
TransTitle= wrap_style ('trans-quoted-title', TransTitle ); |
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title |
||
else |
else |
||
Title = wrap_style ('italic-title', Title); |
Title = utilities.wrap_style ('italic-title', Title); |
||
Title = script_concatenate (Title, ScriptTitle); |
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped |
||
TransTitle = wrap_style ('trans-italic-title', TransTitle); |
TransTitle = utilities.wrap_style ('trans-italic-title', TransTitle); |
||
end |
end |
||
if utilities.is_set (TransTitle) then |
|||
local TransError = ""; |
|||
if utilities.is_set (Title) then |
|||
if is_set(Title) then |
|||
TransTitle = " " .. TransTitle; |
TransTitle = " " .. TransTitle; |
||
else |
else |
||
utilities.set_message ('err_trans_missing_title', {'title'}); |
|||
end |
end |
||
end |
end |
||
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs? |
|||
if utilities.is_set (TitleLink) and utilities.is_set (URL) then |
|||
utilities.set_message ('err_wikilink_in_url'); -- set an error message because we can't have both |
|||
TitleLink = ''; -- unset |
|||
end |
|||
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then |
|||
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. Format; |
|||
if not is_set(TitleLink) and is_set(URL) then |
|||
Title = external_link( URL, Title, URLorigin, UrlAccess ) .. TransTitle .. TransError .. Format; |
|||
URL = ''; -- unset these because no longer needed |
URL = ''; -- unset these because no longer needed |
||
Format = ""; |
Format = ""; |
||
elseif utilities.is_set (TitleLink) and not utilities.is_set (URL) then |
|||
local ws_url; |
|||
ws_url = wikisource_url_make (TitleLink); -- ignore ws_label return; not used here |
|||
if ws_url then |
|||
Title = external_link (ws_url, Title .. ' ', 'ws link in title-link'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? |
|||
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title}); |
|||
Title = Title .. TransTitle; |
|||
else |
|||
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle; |
|||
end |
|||
else |
else |
||
local ws_url, ws_label, L; -- Title has italic or quote markup by the time we get here which causes is_wikilink() to return 0 (not a wikilink) |
|||
Title = Title .. TransTitle .. TransError; |
|||
ws_url, ws_label, L = wikisource_url_make (Title:gsub('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label |
|||
if ws_url then |
|||
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup |
|||
Title = external_link (ws_url, Title .. ' ', 'ws link in title'); -- space char after Title to move icon away from italic text; TODO: a better way to do this? |
|||
Title = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); |
|||
Title = Title .. TransTitle; |
|||
else |
|||
Title = Title .. TransTitle; |
|||
end |
|||
end |
end |
||
else |
else |
||
Title = TransTitle |
Title = TransTitle; |
||
end |
end |
||
if is_set(Place) then |
if utilities.is_set (Place) then |
||
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; |
Place = " " .. wrap_msg ('written', Place, use_lowercase) .. sepc .. " "; |
||
end |
end |
||
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL |
|||
if is_set (Conference) then |
|||
if utilities.is_set (Conference) then |
|||
if utilities.is_set (ConferenceURL) then |
|||
Conference = external_link( ConferenceURL, Conference, ConferenceURLorigin, nil ); |
|||
Conference = external_link( ConferenceURL, Conference, ConferenceURL_origin, nil ); |
|||
end |
end |
||
Conference = sepc .. " " .. Conference .. ConferenceFormat; |
Conference = sepc .. " " .. Conference .. ConferenceFormat; |
||
elseif is_set(ConferenceURL) then |
elseif utilities.is_set (ConferenceURL) then |
||
Conference = sepc .. " " .. external_link( ConferenceURL, nil, |
Conference = sepc .. " " .. external_link( ConferenceURL, nil, ConferenceURL_origin, nil ); |
||
end |
end |
||
local Position = ''; |
|||
if not utilities.is_set (Position) then |
|||
local Minutes = A['Minutes']; |
local Minutes = A['Minutes']; |
||
local Time = A['Time']; |
local Time = A['Time']; |
||
if is_set(Minutes) then |
if utilities.is_set (Minutes) then |
||
if is_set (Time) then |
if utilities.is_set (Time) then --TODO: make a function for this and similar? |
||
utilities.set_message ('err_redundant_parameters', {utilities.wrap_style ('parameter', 'minutes') .. cfg.presentation['sep_list_pair'] .. utilities.wrap_style ('parameter', 'time')}); |
|||
end |
end |
||
Position = " " .. Minutes .. " " .. cfg.messages['minutes']; |
Position = " " .. Minutes .. " " .. cfg.messages['minutes']; |
||
else |
else |
||
if is_set(Time) then |
if utilities.is_set (Time) then |
||
local TimeCaption = A['TimeCaption'] |
local TimeCaption = A['TimeCaption'] |
||
if not is_set(TimeCaption) then |
if not utilities.is_set (TimeCaption) then |
||
TimeCaption = cfg.messages['event']; |
TimeCaption = cfg.messages['event']; |
||
if sepc ~= '.' then |
if sepc ~= '.' then |
||
Line 3,018: | Line 3,524: | ||
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); |
Page, Pages, Sheet, Sheets = format_pages_sheets (Page, Pages, Sheet, Sheets, config.CitationClass, Periodical_origin, sepc, NoPP, use_lowercase); |
||
At = is_set(At) and (sepc .. " " .. At) or ""; |
At = utilities.is_set (At) and (sepc .. " " .. At) or ""; |
||
Position = is_set(Position) and (sepc .. " " .. Position) or ""; |
Position = utilities.is_set (Position) and (sepc .. " " .. Position) or ""; |
||
if config.CitationClass == 'map' then |
if config.CitationClass == 'map' then |
||
local Sections = A['Sections']; -- Section (singular) is an alias of Chapter so set earlier |
|||
local Section = A['Section']; |
|||
local Sections = A['Sections']; |
|||
local Inset = A['Inset']; |
local Inset = A['Inset']; |
||
if is_set( Inset ) then |
if utilities.is_set ( Inset ) then |
||
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); |
Inset = sepc .. " " .. wrap_msg ('inset', Inset, use_lowercase); |
||
end |
end |
||
if is_set( Sections ) then |
if utilities.is_set ( Sections ) then |
||
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); |
Section = sepc .. " " .. wrap_msg ('sections', Sections, use_lowercase); |
||
elseif is_set( Section ) then |
elseif utilities.is_set ( Section ) then |
||
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); |
Section = sepc .. " " .. wrap_msg ('section', Section, use_lowercase); |
||
end |
end |
||
Line 3,037: | Line 3,542: | ||
end |
end |
||
local Others = A['Others']; |
|||
if is_set (Language) then |
|||
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= |
|||
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc |
|||
if config.CitationClass == "AV-media-notes" |
|||
else |
|||
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now |
|||
Language=""; -- language not specified so make sure this is an empty string; |
|||
utilities.set_message ('maint_others_avm') |
|||
--[[ TODO: need to extract the wrap_msg from language_parameter |
|||
else |
|||
so that we can solve parentheses bunching problem with Format/Language/TitleType |
|||
utilities.set_message ('maint_others'); |
|||
]] |
|||
end |
|||
end |
end |
||
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; |
|||
Others = is_set(Others) and (sepc .. " " .. Others) or ""; |
|||
if is_set (Translators) then |
if utilities.is_set (Translators) then |
||
Others = sepc .. ' ' |
Others = safe_join ({sepc .. ' ', wrap_msg ('translated', Translators, use_lowercase), Others}, sepc); |
||
end |
end |
||
if is_set (Interviewers) then |
if utilities.is_set (Interviewers) then |
||
Others = sepc .. ' ' |
Others = safe_join ({sepc .. ' ', wrap_msg ('interview', Interviewers, use_lowercase), Others}, sepc); |
||
end |
end |
||
TitleNote = |
local TitleNote = A['TitleNote']; |
||
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; |
|||
if is_set (Edition) then |
|||
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. |
|||
add_maint_cat ('extra_text', 'edition'); |
|||
utilities.set_message ('err_extra_text_edition'); -- add error message |
|||
end |
end |
||
Edition = " " .. wrap_msg ('edition', Edition); |
Edition = " " .. wrap_msg ('edition', Edition); |
||
Line 3,065: | Line 3,571: | ||
end |
end |
||
Series = is_set(Series) and (sepc |
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum |
||
local Agency = A['Agency']; |
|||
OrigYear = is_set(OrigYear) and (" [" .. OrigYear .. "]") or ""; -- TODO: presentation |
|||
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or ""; |
|||
Volume = format_volume_issue (Volume, Issue, ArticleNumber, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
|||
if utilities.is_set (AccessDate) then |
|||
Agency = is_set(Agency) and (sepc .. " " .. Agency) or ""; |
|||
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); |
|||
------------------------------------ totally unrelated data |
|||
if is_set(Via) then |
|||
Via = " " .. wrap_msg ('via', Via); |
|||
end |
|||
--[[ |
|||
Subscription implies paywall; Registration does not. If both are used in a citation, the subscription required link |
|||
note is displayed. There are no error messages for this condition. |
|||
]] |
|||
if is_set (SubscriptionRequired) then |
|||
SubscriptionRequired = sepc .. " " .. cfg.messages['subscription']; -- subscription required message |
|||
elseif is_set (RegistrationRequired) then |
|||
SubscriptionRequired = sepc .. " " .. cfg.messages['registration']; -- registration required message |
|||
else |
|||
SubscriptionRequired = ''; -- either or both might be set to something other than yes true y |
|||
end |
|||
if is_set(AccessDate) then |
|||
local retrv_text = " " .. cfg.messages['retrieved'] |
local retrv_text = " " .. cfg.messages['retrieved'] |
||
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
AccessDate = nowrap_date (AccessDate); -- wrap in nowrap span if date in appropriate format |
||
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case |
if (sepc ~= ".") then retrv_text = retrv_text:lower() end -- if mode is cs2, lower case |
||
AccessDate = substitute (retrv_text, AccessDate); |
AccessDate = utilities.substitute (retrv_text, AccessDate); -- add retrieved text |
||
AccessDate = substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
AccessDate = utilities.substitute (cfg.presentation['accessdate'], {sepc, AccessDate}); -- allow editors to hide accessdates |
||
end |
end |
||
if is_set(ID) then ID = sepc .." ".. ID; end |
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end |
||
if "thesis" == config.CitationClass and is_set(Docket) then |
|||
local Docket = A['Docket']; |
|||
if "thesis" == config.CitationClass and utilities.is_set (Docket) then |
|||
ID = sepc .. " Docket " .. Docket .. ID; |
|||
end |
end |
||
if "report" == config.CitationClass and is_set(Docket) then |
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 |
ID = sepc .. ' ' .. Docket; -- overwrite ID even if |id= is set |
||
end |
end |
||
if utilities.is_set (URL) then |
|||
ID_list = build_id_list( ID_list, {IdAccessLevels=ID_access_levels, DoiBroken = DoiBroken, ASINTLD = ASINTLD, IgnoreISBN = IgnoreISBN, Embargo=Embargo, Class = Class} ); |
|||
URL = " " .. external_link( URL, nil, URL_origin, UrlAccess ); |
|||
if is_set(URL) then |
|||
URL = " " .. external_link( URL, nil, URLorigin, UrlAccess ); |
|||
end |
end |
||
local Quote = A['Quote']; |
|||
local TransQuote = A['TransQuote']; |
|||
if Quote:sub(1,1) == '"' and Quote:sub(-1,-1) == '"' then -- if first and last characters of quote are quote marks |
|||
local ScriptQuote = A['ScriptQuote']; |
|||
Quote = Quote:sub(2,-2); -- strip them off |
|||
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 |
||
Quote = sepc .." " .. wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags |
|||
Quote = kern_quotes (Quote); -- kern if needed |
|||
Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags |
|||
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 |
|||
if utilities.is_set (QuotePage) or utilities.is_set (QuotePages) then -- add page prefix |
|||
local quote_prefix = ''; |
|||
if utilities.is_set (QuotePage) then |
|||
extra_text_in_page_check (QuotePage, 'quote-page'); -- add to maint cat if |quote-page= value begins with what looks like p., pp., etc. |
|||
if not NoPP then |
|||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', ''; |
|||
else |
|||
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePage}), '', '', ''; |
|||
end |
|||
elseif utilities.is_set (QuotePages) then |
|||
extra_text_in_page_check (QuotePages, 'quote-pages'); -- add to maint cat if |quote-pages= value begins with what looks like p., pp., etc. |
|||
if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page |
|||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', ''; |
|||
elseif not NoPP then |
|||
quote_prefix = utilities.substitute (cfg.messages['pp-prefix'], {sepc, QuotePages}), '', ''; |
|||
else |
|||
quote_prefix = utilities.substitute (cfg.messages['nopp'], {sepc, QuotePages}), '', ''; |
|||
end |
|||
end |
|||
Quote = quote_prefix .. ": " .. Quote; |
|||
else |
|||
Quote = sepc .. " " .. Quote; |
|||
end |
|||
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set |
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set |
||
end |
end |
||
-- We check length of PostScript here because it will have been nuked by |
|||
local Archived |
|||
-- the quote parameters. We'd otherwise emit a message even if there wasn't |
|||
if is_set(ArchiveURL) then |
|||
-- a displayed postscript. |
|||
if not is_set(ArchiveDate) then |
|||
-- TODO: Should the max size (1) be configurable? |
|||
ArchiveDate = set_error('archive_missing_date'); |
|||
-- TODO: Should we check a specific pattern? |
|||
if utilities.is_set(PostScript) and mw.ustring.len(PostScript) > 1 then |
|||
utilities.set_message ('maint_postscript') |
|||
end |
|||
local Archived; |
|||
if utilities.is_set (ArchiveURL) then |
|||
local arch_text; |
|||
if not utilities.is_set (ArchiveDate) then |
|||
utilities.set_message ('err_archive_missing_date'); |
|||
ArchiveDate = ''; -- empty string for concatenation |
|||
end |
end |
||
if " |
if "live" == UrlStatus then |
||
arch_text = cfg.messages['archived']; |
|||
if sepc ~= "." then arch_text = arch_text:lower() end |
if sepc ~= "." then arch_text = arch_text:lower() end |
||
if utilities.is_set (ArchiveDate) then |
|||
Archived = sepc .. " " .. substitute( cfg.messages['archived-not-dead'], |
|||
Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'], |
|||
{ external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil ) .. ArchiveFormat, ArchiveDate } ); |
|||
{external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } ); |
|||
if not is_set(OriginalURL) then |
|||
else |
|||
Archived = Archived .. " " .. set_error('archive_missing_url'); |
|||
Archived = ''; |
|||
end |
end |
||
if not utilities.is_set (OriginalURL) then |
|||
utilities.set_message ('err_archive_missing_url'); |
|||
local arch_text = cfg.messages['archived-dead']; |
|||
Archived = ''; -- empty string for concatenation |
|||
if sepc ~= "." then arch_text = arch_text:lower() end |
|||
end |
|||
if in_array (DeadURL, {'unfit', 'usurped', 'bot: unknown'}) then |
|||
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' |
|||
Archived = sepc .. " " .. 'Archived from the original on ' .. ArchiveDate; -- format already styled |
|||
if utilities.in_array (UrlStatus, {'unfit', 'usurped', 'bot: unknown'}) then |
|||
arch_text = cfg.messages['archived-unfit']; |
|||
add_maint_cat ('bot:_unknown'); -- and add a category if not already added |
|||
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 |
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 |
|||
if utilities.is_set (ArchiveDate) then |
|||
Archived = sepc .. " " .. utilities.substitute ( arch_text, |
|||
{ external_link( OriginalURL, cfg.messages['original'], OriginalURL_origin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled |
|||
else |
|||
Archived = ''; -- unset for concatenation |
|||
end |
end |
||
else -- DeadURL is empty, 'yes', 'true', or 'y' |
|||
Archived = sepc .. " " .. substitute( arch_text, |
|||
{ external_link( OriginalURL, cfg.messages['original'], OriginalURLorigin, OriginalAccess ) .. OriginalFormat, ArchiveDate } ); -- format already styled |
|||
end |
end |
||
else -- OriginalUrl not set |
|||
else |
|||
arch_text = cfg.messages['archived-missing']; |
|||
if sepc ~= "." then arch_text = arch_text:lower() end |
if sepc ~= "." then arch_text = arch_text:lower() end |
||
utilities.set_message ('err_archive_missing_url'); |
|||
Archived = sepc .. " " .. substitute( arch_text, |
|||
Archived = ''; -- empty string for concatenation |
|||
{ set_error('archive_missing_url'), ArchiveDate } ); |
|||
end |
end |
||
elseif is_set (ArchiveFormat) then |
elseif utilities.is_set (ArchiveFormat) then |
||
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message |
Archived = ArchiveFormat; -- if set and ArchiveURL not set ArchiveFormat has error message |
||
else |
else |
||
Archived = |
Archived = ''; |
||
end |
end |
||
local Lay = ''; |
local Lay = ''; |
||
local LaySource = A['LaySource']; |
|||
if is_set(LayURL) then |
|||
local LayURL = A['LayURL']; |
|||
if is_set(LayDate) then LayDate = " (" .. LayDate .. ")" end |
|||
local LayFormat = A['LayFormat']; |
|||
if is_set(LaySource) then |
|||
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); |
|||
LaySource = " – ''" .. safe_for_italics(LaySource) .. "''"; |
|||
if utilities.is_set (LayURL) then |
|||
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end |
|||
if utilities.is_set (LaySource) then |
|||
LaySource = " – ''" .. utilities.safe_for_italics (LaySource) .. "''"; |
|||
else |
else |
||
LaySource = ""; |
LaySource = ""; |
||
Line 3,174: | Line 3,731: | ||
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate |
Lay = sepc .. " " .. external_link( LayURL, cfg.messages['lay summary']:lower(), A:ORIGIN('LayURL'), nil ) .. LayFormat .. LaySource .. LayDate |
||
end |
end |
||
elseif is_set (LayFormat) then |
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 |
Lay = sepc .. LayFormat; -- if set and LayURL not set, then LayFormat has error message |
||
end |
end |
||
local TranscriptURL = A['TranscriptURL'] |
|||
if is_set(Transcript) then |
|||
local TranscriptFormat = A['TranscriptFormat']; |
|||
if is_set(TranscriptURL) then |
|||
TranscriptFormat = style_format (TranscriptFormat, TranscriptURL, 'transcript-format', 'transcripturl'); |
|||
local Transcript = A['Transcript']; |
|||
local TranscriptURL_origin = A:ORIGIN('TranscriptURL'); -- get name of parameter that holds TranscriptURL |
|||
if utilities.is_set (Transcript) then |
|||
if utilities.is_set (TranscriptURL) then |
|||
Transcript = external_link( TranscriptURL, Transcript, TranscriptURL_origin, nil ); |
|||
end |
end |
||
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
Transcript = sepc .. ' ' .. Transcript .. TranscriptFormat; |
||
elseif is_set(TranscriptURL) then |
elseif utilities.is_set (TranscriptURL) then |
||
Transcript = external_link( TranscriptURL, nil, |
Transcript = external_link( TranscriptURL, nil, TranscriptURL_origin, nil ); |
||
end |
end |
||
local Publisher; |
local Publisher; |
||
if is_set(PublicationDate) then |
if utilities.is_set (PublicationDate) then |
||
PublicationDate = wrap_msg ('published', PublicationDate); |
PublicationDate = wrap_msg ('published', PublicationDate); |
||
end |
end |
||
if is_set(PublisherName) then |
if utilities.is_set (PublisherName) then |
||
if is_set(PublicationPlace) then |
if utilities.is_set (PublicationPlace) then |
||
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
Publisher = sepc .. " " .. PublicationPlace .. ": " .. PublisherName .. PublicationDate; |
||
else |
else |
||
Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
Publisher = sepc .. " " .. PublisherName .. PublicationDate; |
||
end |
end |
||
elseif is_set(PublicationPlace) then |
elseif utilities.is_set (PublicationPlace) then |
||
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
Publisher= sepc .. " " .. PublicationPlace .. PublicationDate; |
||
else |
else |
||
Line 3,203: | Line 3,765: | ||
end |
end |
||
local TransPeriodical = A['TransPeriodical']; |
|||
local TransPeriodical_origin = A:ORIGIN ('TransPeriodical'); |
|||
-- Several of the above rely upon detecting this as nil, so do it last. |
-- Several of the above rely upon detecting this as nil, so do it last. |
||
if is_set(Periodical) then |
if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then |
||
if is_set(Title) or is_set(TitleNote) then |
if utilities.is_set (Title) or utilities.is_set (TitleNote) then |
||
Periodical = sepc .. " " .. |
Periodical = sepc .. " " .. format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); |
||
else |
else |
||
Periodical = |
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); |
||
end |
end |
||
end |
|||
local Language = A['Language']; |
|||
if utilities.is_set (Language) then |
|||
Language = language_parameter (Language); -- format, categories, name from ISO639-1, etc. |
|||
else |
|||
Language=''; -- language not specified so make sure this is an empty string; |
|||
--[[ TODO: need to extract the wrap_msg from language_parameter |
|||
so that we can solve parentheses bunching problem with Format/Language/TitleType |
|||
]] |
|||
end |
end |
||
Line 3,216: | Line 3,790: | ||
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). |
the annotation directly follows the |title= parameter value in the citation rather than the |event= parameter value (if provided). |
||
]] |
]] |
||
if "speech" == config.CitationClass then -- cite speech only |
if "speech" == config.CitationClass then -- cite speech only |
||
TitleNote = |
TitleNote = TitleType; -- move TitleType to TitleNote so that it renders ahead of |event= |
||
TitleType = ''; -- and unset |
|||
if is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter |
|||
if is_set (Conference) then -- and if |event= is set |
|||
if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter |
|||
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering |
|||
if utilities.is_set (Conference) then -- and if |event= is set |
|||
Conference = Conference .. sepc .. " "; -- then add appropriate punctuation to the end of the Conference variable before rendering |
|||
end |
end |
||
end |
end |
||
Line 3,232: | Line 3,808: | ||
local tcommon2; -- used for book cite when |contributor= is set |
local tcommon2; -- used for book cite when |contributor= is set |
||
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then |
||
if not (utilities.is_set (Authors) or utilities.is_set (Editors)) then |
|||
if is_set(Others) then Others = Others .. sepc .. " " end |
|||
Others = Others:gsub ('^' .. sepc .. ' ', ''); -- when no authors and no editors, strip leading sepc and space |
|||
end |
|||
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 ); |
tcommon = safe_join( {Others, Title, TitleNote, Conference, Periodical, Format, TitleType, Series, Language, Edition, Publisher, Agency, Volume}, sepc ); |
||
elseif in_array(config.CitationClass, {"book","citation"}) and not is_set(Periodical) then -- special cases for book cites |
elseif utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (Periodical) then -- special cases for book cites |
||
if is_set (Contributors) then |
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 |
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 ); |
tcommon2 = safe_join( {Conference, Periodical, Format, TitleType, Series, Language, Volume, Others, Edition, Publisher, Agency}, sepc ); |
||
Line 3,244: | Line 3,823: | ||
elseif 'map' == config.CitationClass then -- special cases for cite map |
elseif 'map' == config.CitationClass then -- special cases for cite map |
||
if is_set (Chapter) then |
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 ); |
tcommon = safe_join( {Title, Format, Edition, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); |
||
elseif is_set (Periodical) then |
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 ); |
tcommon = safe_join( {Title, TitleType, Format, Periodical, Scale, Series, Language, Cartography, Others, Publisher, Volume}, sepc ); |
||
else -- a sheet or stand-alone map |
else -- a sheet or stand-alone map |
||
Line 3,253: | Line 3,832: | ||
elseif 'episode' == config.CitationClass then -- special case for cite episode |
elseif 'episode' == config.CitationClass then -- special case for cite episode |
||
tcommon = safe_join( {Title, TitleNote, TitleType, Series |
tcommon = safe_join( {Title, TitleNote, TitleType, Series, Language, Edition, Publisher}, sepc ); |
||
else -- all other CS1 templates |
else -- all other CS1 templates |
||
Line 3,266: | Line 3,845: | ||
end |
end |
||
local Via = A['Via']; |
|||
local idcommon = safe_join( { ID_list, URL, Archived, AccessDate, Via, SubscriptionRequired, Lay, Quote }, sepc ); |
|||
Via = utilities.is_set (Via) and wrap_msg ('via', Via) or ''; |
|||
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 text; |
||
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; |
||
local OrigDate = A['OrigDate']; |
|||
if is_set(Date) then |
|||
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or ''; |
|||
if is_set (Authors) or is_set (Editors) then -- date follows authors or editors when authors not set |
|||
if utilities.is_set (Date) then |
|||
Date = " (" .. Date ..")" .. OrigYear .. sepc .. " "; -- in paranetheses |
|||
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 |
else -- neither of authors and editors set |
||
if (string.sub(tcommon,-1,-1) == sepc) then |
if (string.sub(tcommon, -1, -1) == sepc) then -- if the last character of tcommon is sepc |
||
Date = " " .. Date .. |
Date = " " .. Date .. OrigDate; -- Date does not begin with sepc |
||
else |
else |
||
Date = sepc .. " " .. Date .. |
Date = sepc .. " " .. Date .. OrigDate; -- Date begins with sepc |
||
end |
end |
||
end |
end |
||
end |
end |
||
if is_set(Authors) then |
if utilities.is_set (Authors) then |
||
if (not is_set (Date)) 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 |
Authors = terminate_name_list (Authors, sepc); -- when no date, terminate with 0 or 1 sepc and a space |
||
end |
end |
||
if is_set(Editors) then |
if utilities.is_set (Editors) then |
||
local in_text = " "; |
local in_text = " "; |
||
local post_text = ""; |
local post_text = ""; |
||
if is_set(Chapter) and 0 == #c then |
if utilities.is_set (Chapter) and 0 == #c then |
||
in_text = in_text .. cfg.messages['in'] .. " " |
in_text = in_text .. cfg.messages['in'] .. " " |
||
if (sepc ~= '.') then |
if (sepc ~= '.') then |
||
in_text = in_text:lower() -- lowercase for cs2 |
in_text = in_text:lower() -- lowercase for cs2 |
||
end |
|||
else |
|||
if EditorCount <= 1 then |
|||
post_text = ", " .. cfg.messages['editor']; |
|||
else |
|||
post_text = ", " .. cfg.messages['editors']; |
|||
end |
end |
||
end |
end |
||
if EditorCount <= 1 then |
|||
post_text = " (" .. cfg.messages['editor'] .. ")"; -- be consistent with no-author, no-date case |
|||
else |
|||
post_text = " (" .. cfg.messages['editors'] .. ")"; |
|||
end |
|||
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
Editors = terminate_name_list (in_text .. Editors .. post_text, sepc); -- terminate with 0 or 1 sepc and a space |
||
end |
end |
||
if is_set (Contributors) then |
if utilities.is_set (Contributors) then -- book cite and we're citing the intro, preface, etc. |
||
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; |
local by_text = sepc .. ' ' .. cfg.messages['by'] .. ' '; |
||
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 |
if (sepc ~= '.') then by_text = by_text:lower() end -- lowercase for cs2 |
||
Authors = by_text .. Authors; -- author follows title so tweak it here |
Authors = by_text .. Authors; -- author follows title so tweak it here |
||
if is_set (Editors) and is_set (Date) then |
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 |
Authors = terminate_name_list (Authors, sepc); -- terminate with 0 or 1 sepc and a space |
||
end |
end |
||
if (not is_set (Date)) then |
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 |
Contributors = terminate_name_list (Contributors, sepc); -- terminate with 0 or 1 sepc and a space |
||
end |
end |
||
Line 3,316: | Line 3,904: | ||
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); |
text = safe_join( {Authors, Date, Chapter, Place, Editors, tcommon, pgtext, idcommon }, sepc ); |
||
end |
end |
||
elseif is_set(Editors) then |
elseif utilities.is_set (Editors) then |
||
if is_set(Date) then |
if utilities.is_set (Date) then |
||
if EditorCount <= 1 then |
if EditorCount <= 1 then |
||
Editors = Editors .. |
Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editor']; |
||
else |
else |
||
Editors = Editors .. |
Editors = Editors .. cfg.presentation['sep_name'] .. cfg.messages['editors']; |
||
end |
end |
||
else |
else |
||
Line 3,332: | Line 3,920: | ||
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
text = safe_join( {Editors, Date, Chapter, Place, tcommon, pgtext, idcommon}, sepc ); |
||
else |
else |
||
if in_array(config.CitationClass, {"journal","citation"}) and is_set(Periodical) then |
if utilities.in_array (config.CitationClass, {"journal", "citation"}) and utilities.is_set (Periodical) then |
||
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); |
text = safe_join( {Chapter, Place, tcommon, pgtext, Date, idcommon}, sepc ); |
||
else |
else |
||
Line 3,339: | Line 3,927: | ||
end |
end |
||
if is_set(PostScript) and PostScript ~= sepc then |
if utilities.is_set (PostScript) and PostScript ~= sepc then |
||
text = safe_join( {text, sepc}, sepc ); |
text = safe_join( {text, sepc}, sepc ); -- Deals with italics, spaces, etc. |
||
text = text:sub(1,-sepc:len()-1); |
text = text:sub(1, -sepc:len() - 1); |
||
end |
end |
||
text = safe_join( {text, PostScript}, sepc ); |
text = safe_join( {text, PostScript}, sepc ); |
||
-- Now enclose the whole thing in a <cite |
-- Now enclose the whole thing in a <cite> element |
||
local |
local options_t = {}; |
||
options_t.class = cite_class_attribute_make (config.CitationClass, Mode); |
|||
if is_set(config.CitationClass) and config.CitationClass ~= "citation" then |
|||
options.class = config.CitationClass; |
|||
options.class = "citation " .. config.CitationClass; -- class=citation required for blue highlight when used with |ref= |
|||
else |
|||
options.class = "citation"; |
|||
end |
|||
if is_set(Ref) and Ref:lower() ~= "none" then -- set reference anchor if appropriate |
|||
local id = Ref |
|||
if ('harv' == Ref ) then |
|||
local namelist = {}; -- holds selected contributor, author, editor name list |
|||
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation |
|||
local Ref = is_valid_parameter_value (A['Ref'], A:ORIGIN('Ref'), cfg.keywords_lists['ref'], nil, true); -- nil when |ref=harv; A['Ref'] else |
|||
if #c > 0 then -- if there is a contributor list |
|||
namelist = c; -- select it |
|||
if 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then |
|||
elseif #a > 0 then -- or an author list |
|||
local namelist_t = {}; -- holds selected contributor, author, editor name list |
|||
namelist = a; |
|||
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation |
|||
elseif #e > 0 then -- or an editor list |
|||
namelist = e; |
|||
if #c > 0 then -- if there is a contributor list |
|||
end |
|||
namelist_t = c; -- select it |
|||
elseif #a > 0 then -- or an author list |
|||
namelist_t = a; |
|||
else |
|||
elseif #e > 0 then -- or an editor list |
|||
namelist_t = e; |
|||
end |
|||
local citeref_id; |
|||
if #namelist_t > 0 then -- if there are names in namelist_t |
|||
citeref_id = make_citeref_id (namelist_t, year); -- go make the CITEREF anchor |
|||
if mw.uri.anchorEncode (citeref_id) == ((Ref and mw.uri.anchorEncode (Ref)) or '') then -- Ref may already be encoded (by {{sfnref}}) so citeref_id must be encoded before comparison |
|||
utilities.set_message ('maint_ref_duplicates_default'); |
|||
end |
end |
||
else |
|||
citeref_id = ''; -- unset |
|||
end |
end |
||
options_t.id = Ref or citeref_id; |
|||
end |
end |
||
if string.len(text:gsub( |
if string.len (text:gsub('%b<>', '')) <= 2 then -- remove html and html-like tags; then get length of what remains; |
||
z.error_cats_t = {}; -- blank the categories list |
|||
z.error_categories = {}; |
|||
z.error_msgs_t = {}; -- blank the error messages list |
|||
text = set_error('empty_citation'); |
|||
OCinSoutput = nil; -- blank the metadata string |
|||
z.message_tail = {}; |
|||
text = ''; -- blank the the citation |
|||
utilities.set_message ('err_empty_citation'); -- set empty citation message and category |
|||
end |
end |
||
local |
local render_t = {}; -- here we collect the final bits for concatenation into the rendered citation |
||
if is_set( |
if utilities.is_set (options_t.id) then -- here we wrap the rendered citation in <cite ...>...</cite> tags |
||
table.insert ( |
table.insert (render_t, utilities.substitute (cfg.presentation['cite-id'], {mw.uri.anchorEncode(options_t.id), mw.text.nowiki(options_t.class), text})); -- when |ref= is set or when there is a namelist |
||
else |
else |
||
table.insert ( |
table.insert (render_t, utilities.substitute (cfg.presentation['cite'], {mw.text.nowiki(options_t.class), text})); -- when |ref=none or when namelist_t empty and |ref= is missing or is empty |
||
end |
end |
||
if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span |
|||
table.insert (render, substitute (cfg.presentation['ocins'], {OCinSoutput})); -- append metadata to the citation |
|||
table.insert (render_t, utilities.substitute (cfg.presentation['ocins'], OCinSoutput)); -- format and append metadata to the citation |
|||
end |
|||
local template_name = ('citation' == config.CitationClass) and 'citation' or 'cite ' .. (cfg.citation_class_map_t[config.CitationClass] or config.CitationClass); |
|||
if #z.message_tail ~= 0 then |
|||
local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]'; |
|||
table.insert (render, ' '); |
|||
local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: '; |
|||
for i,v in ipairs( z.message_tail ) do |
|||
if is_set(v[1]) then |
|||
if 0 ~= #z.error_msgs_t then |
|||
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, template_link)); |
|||
table.insert (render, error_comment( v[1], v[2] )); |
|||
else |
|||
table.insert (render_t, ' '); -- insert a space between citation and its error messages |
|||
table.sort (z.error_msgs_t); -- sort the error messages list; sorting includes wrapping <span> and <code> tags; hidden-error sorts ahead of visible-error |
|||
end |
|||
local hidden = true; -- presume that the only error messages emited by this template are hidden |
|||
for _, v in ipairs (z.error_msgs_t) do -- spin through the list of error messages |
|||
if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name |
|||
hidden = false; -- found one; so don't hide the error message prefix |
|||
break; -- and done because no need to look further |
|||
end |
end |
||
end |
end |
||
z.error_msgs_t[1] = table.concat ({utilities.error_comment (msg_prefix, hidden), z.error_msgs_t[1]}); -- add error message prefix to first error message to prevent extraneous punctuation |
|||
table.insert (render_t, table.concat (z.error_msgs_t, '; ')); -- make a big string of error messages and add it to the rendering |
|||
end |
end |
||
if |
if 0 ~= #z.maint_cats_t then |
||
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, template_link)); |
|||
table.insert (render, '<span class="citation-comment" style="display:none; color:#33aa33; margin-left:0.3em">'); |
|||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories |
|||
table.sort (z.maint_cats_t); -- sort the maintenance messages list |
|||
table.insert (render, v); |
|||
table.insert (render, ' ('); |
|||
local maint_msgs_t = {}; -- here we collect all of the maint messages |
|||
table.insert (render, make_wikilink (':Category:' .. v, 'link')); |
|||
table.insert (render, ') '); |
|||
if 0 == #z.error_msgs_t then -- if no error messages |
|||
table.insert (maint_msgs_t, msg_prefix); -- insert message prefix in maint message livery |
|||
end |
end |
||
table.insert (render, '</span>'); |
|||
for _, v in ipairs( z.maint_cats_t ) do -- append maintenance categories |
|||
table.insert (maint_msgs_t, -- assemble new maint message and add it to the maint_msgs_t table |
|||
table.concat ({v, ' (', utilities.substitute (cfg.messages[':cat wikilink'], v), ')'}) |
|||
); |
|||
end |
|||
table.insert (render_t, utilities.substitute (cfg.presentation['hidden-maint'], table.concat (maint_msgs_t, ' '))); -- wrap the group of maint messages with proper presentation and save |
|||
end |
end |
||
if not no_tracking_cats then |
|||
for _, v in ipairs (z.error_cats_t) do -- append error categories |
|||
if in_array(no_tracking_cats, {"", "no", "false", "n"}) then |
|||
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); |
|||
for _, v in ipairs( z.error_categories ) do |
|||
table.insert (render, make_wikilink ('Category:' .. v)); |
|||
end |
end |
||
for _, v in ipairs( |
for _, v in ipairs (z.maint_cats_t) do -- append maintenance categories |
||
table.insert ( |
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); |
||
end |
end |
||
for _, v in ipairs( |
for _, v in ipairs (z.prop_cats_t) do -- append properties categories |
||
table.insert ( |
table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); |
||
end |
end |
||
end |
end |
||
return table.concat ( |
return table.concat (render_t); -- make a big string and done |
||
end |
end |
||
--[[--------------------------< |
--[[--------------------------< V A L I D A T E >-------------------------------------------------------------- |
||
Looks for a parameter's name in one of several whitelists. |
|||
This is used by templates such as {{cite book}} to create the actual citation text. |
|||
Parameters in the whitelist can have three values: |
|||
true - active, supported parameters |
|||
false - deprecated, supported parameters |
|||
nil - unsupported parameters |
|||
]] |
]] |
||
function |
local function validate (name, cite_class, empty) |
||
local name = tostring (name); |
|||
Frame = frame; -- save a copy incase we need to display an error message in preview mode |
|||
local enum_name; -- for enumerated parameters, is name with enumerator replaced with '#' |
|||
local pframe = frame:getParent() |
|||
local state; |
|||
local validation, utilities, identifiers, metadata; |
|||
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 nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
|||
if false == state then |
|||
cfg = mw.loadData ('Module:Citation/CS1/Configuration/sandbox'); -- load sandbox versions of support modules |
|||
if empty then return nil; end -- empty deprecated parameters are treated as unknowns |
|||
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist/sandbox'); |
|||
deprecated_parameter (name); -- parameter is deprecated but still supported |
|||
utilities = require ('Module:Citation/CS1/Utilities/sandbox'); |
|||
return true; |
|||
validation = require ('Module:Citation/CS1/Date_validation/sandbox'); |
|||
end |
|||
identifiers = require ('Module:Citation/CS1/Identifiers/sandbox'); |
|||
if 'tracked' == state then |
|||
metadata = require ('Module:Citation/CS1/COinS/sandbox'); |
|||
local base_name = name:gsub ('%d', ''); -- strip enumerators from parameter names that have them to get the base name |
|||
utilities.add_prop_cat ('tracked-param', {base_name}, base_name); -- add a properties category; <base_name> modifies <key> |
|||
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 |
|||
else -- otherwise |
|||
if true == state_test (state, name) then return true; end |
|||
cfg = mw.loadData ('Module:Citation/CS1/Configuration'); -- load live versions of support modules |
|||
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist'); |
|||
-- all enumerated parameters allowed |
|||
utilities = require ('Module:Citation/CS1/Utilities'); |
|||
enum_name = name:gsub("%d+", "#" ); -- replace digit(s) with # (last25 becomes last#) (mw.ustring because non-Western 'local' digits) |
|||
validation = require ('Module:Citation/CS1/Date_validation'); |
|||
state = whitelist.numbered_arguments[enum_name]; |
|||
identifiers = require ('Module:Citation/CS1/Identifiers'); |
|||
if true == state_test (state, name) then return true; end |
|||
metadata = require ('Module:Citation/CS1/COinS'); |
|||
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 |
|||
utilities.set_message ('err_bad_paramlink', parameter); -- emit an error message |
|||
_, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink |
|||
end |
end |
||
return value; |
|||
end |
|||
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the cfg tables |
|||
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module |
|||
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module |
|||
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module |
|||
--[[--------------------------< M I S S I N G _ P I P E _ C H E C K >------------------------------------------ |
|||
dates = validation.dates; -- imported functions from Module:Citation/CS1/Date validation |
|||
year_date_check = validation.year_date_check; |
|||
reformat_dates = validation.reformat_dates; |
|||
date_hyphen_to_dash = validation.date_hyphen_to_dash; |
|||
date_name_xlate = validation.date_name_xlate; |
|||
Look at the contents of a parameter. If the content has a string of characters and digits followed by an equal |
|||
is_set = utilities.is_set; -- imported functions from Module:Citation/CS1/Utilities |
|||
sign, compare the alphanumeric string to the list of cs1|2 parameters. If found, then the string is possibly a |
|||
in_array = utilities.in_array; |
|||
parameter that is missing its pipe. There are two tests made: |
|||
substitute = utilities.substitute; |
|||
{{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 |
|||
error_comment = utilities.error_comment; |
|||
{{cite ... |title=access-date=2016-03-17}} -- the first parameter has no value (whitespace after the first = is trimmed by MediaWiki) |
|||
set_error = utilities.set_error; |
|||
cs1|2 shares some parameter names with XML/HTML attributes: class=, title=, etc. To prevent false positives XML/HTML |
|||
select_one = utilities.select_one; |
|||
tags are removed before the search. |
|||
add_maint_cat = utilities.add_maint_cat; |
|||
wrap_style = utilities.wrap_style; |
|||
safe_for_italics = utilities.safe_for_italics; |
|||
is_wikilink = utilities.is_wikilink; |
|||
make_wikilink = utilities.make_wikilink; |
|||
If a missing pipe is detected, this function adds the missing pipe maintenance category. |
|||
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities |
|||
]] |
|||
extract_ids = identifiers.extract_ids; -- imported functions from Module:Citation/CS1/Identifiers |
|||
build_id_list = identifiers.build_id_list; |
|||
local function missing_pipe_check (parameter, value) |
|||
is_embargoed = identifiers.is_embargoed; |
|||
local capture; |
|||
extract_id_access_levels = identifiers.extract_id_access_levels; |
|||
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 |
|||
utilities.set_message ('err_missing_pipe', parameter); |
|||
end |
|||
end |
|||
--[[--------------------------< H A S _ E X T R A N E O U S _ P U N C T >-------------------------------------- |
|||
look for extraneous terminal punctuation in most parameter values; parameters listed in skip table are not checked |
|||
]] |
|||
local function has_extraneous_punc (param, value) |
|||
if 'number' == type (param) then |
|||
return; |
|||
end |
|||
param = param:gsub ('%d+', '#'); -- enumerated name-list mask params allow terminal punct; normalize |
|||
make_coins_title = metadata.make_coins_title; -- imported functions from Module:Citation/CS1/COinS |
|||
if cfg.punct_skip[param] then |
|||
get_coins_pages = metadata.get_coins_pages; |
|||
return; -- parameter name found in the skip table so done |
|||
COinS = metadata.COinS; |
|||
end |
|||
if value:match ('[,;:]$') then |
|||
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat |
|||
end |
|||
if value:match ('^=') then -- sometimes an extraneous '=' character appears ... |
|||
utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat |
|||
end |
|||
end |
|||
local args = {}; -- table where we store all of the template's arguments |
|||
--[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------ |
|||
local suggestions = {}; -- table where we store suggestions if we need to loadData them |
|||
local error_text, error_state; |
|||
look for extraneous url parameter values; parameters listed in skip table are not checked |
|||
]] |
|||
local function has_extraneous_url (url_param_t) |
|||
local url_error_t = {}; |
|||
check_for_url (url_param_t, url_error_t); -- extraneous url check |
|||
if 0 ~= #url_error_t then -- non-zero when there are errors |
|||
table.sort (url_error_t); |
|||
utilities.set_message ('err_param_has_ext_link', {utilities.make_sep_list (#url_error_t, url_error_t)}); -- add this error message |
|||
end |
|||
end |
|||
--[[--------------------------< C I T A T I O N >-------------------------------------------------------------- |
|||
This is used by templates such as {{cite book}} to create the actual citation text. |
|||
]] |
|||
local function citation(frame) |
|||
Frame = frame; -- save a copy in case we need to display an error message in preview mode |
|||
local 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 |
||
-- i18n: set the name that your wiki uses to identify sandbox subpages from sandbox template invoke (or can be set here) |
|||
local sandbox = ((config.SandboxPath and '' ~= config.SandboxPath) and config.SandboxPath) or '/sandbox'; -- sandbox path from {{#invoke:Citation/CS1/sandbox|citation|SandboxPath=/...}} |
|||
is_sandbox = nil ~= string.find (frame:getTitle(), sandbox, 1, true); -- is this invoke the sandbox module? |
|||
sandbox = is_sandbox and sandbox or ''; -- use i18n sandbox to load sandbox modules when this module is the sandox; live modules else |
|||
local pframe = frame:getParent() |
|||
local styles; |
|||
cfg = mw.loadData ('Module:Citation/CS1/Configuration' .. sandbox); -- load sandbox versions of support modules when {{#invoke:Citation/CS1/sandbox|...}}; live modules else |
|||
whitelist = mw.loadData ('Module:Citation/CS1/Whitelist' .. sandbox); |
|||
utilities = require ('Module:Citation/CS1/Utilities' .. sandbox); |
|||
validation = require ('Module:Citation/CS1/Date_validation' .. sandbox); |
|||
identifiers = require ('Module:Citation/CS1/Identifiers' .. sandbox); |
|||
metadata = require ('Module:Citation/CS1/COinS' .. sandbox); |
|||
styles = 'Module:Citation/CS1' .. sandbox .. '/styles.css'; |
|||
utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables |
|||
identifiers.set_selected_modules (cfg, utilities); -- so that functions in Identifiers can see the selected cfg tables and selected Utilities module |
|||
validation.set_selected_modules (cfg, utilities); -- so that functions in Date validataion can see selected cfg tables and the selected Utilities module |
|||
metadata.set_selected_modules (cfg, utilities); -- so that functions in COinS can see the selected cfg tables and selected Utilities module |
|||
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities |
|||
is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}')); |
|||
local args = {}; -- table where we store all of the template's arguments |
|||
local suggestions = {}; -- table where we store suggestions if we need to loadData them |
|||
local error_text; -- used as a flag |
|||
local capture; -- the single supported capture when matching unknown parameters using patterns |
local capture; -- the single supported capture when matching unknown parameters using patterns |
||
local empty_unknowns = {}; -- sequence table to hold empty unknown params for error message listing |
|||
for k, v in pairs( pframe.args ) do |
|||
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 |
|||
k = mw.ustring.gsub (k, '%d', cfg.date_names.local_digits); -- for enumerated parameters, translate 'local' digits to Western 0-9 |
|||
end |
|||
if not validate( k, config.CitationClass ) then |
if not validate( k, config.CitationClass ) then |
||
if type (k) ~= 'string' then -- exclude empty numbered parameters |
|||
error_text = ""; |
|||
if type( k ) ~= 'string' then |
|||
-- Exclude empty numbered parameters |
|||
if v:match("%S+") ~= nil then |
if v:match("%S+") ~= nil then |
||
error_text |
error_text = utilities.set_message ('err_text_ignored', {v}); |
||
end |
end |
||
elseif validate( |
elseif validate (k:lower(), config.CitationClass) then |
||
error_text |
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, k:lower()}); -- 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 |
||
suggestions = mw.loadData ('Module:Citation/CS1/Suggestions' .. sandbox); --load sandbox version of suggestion module when {{#invoke:Citation/CS1/sandbox|...}}; live module else |
|||
if nil ~= string.find (frame:getTitle(), 'sandbox', 1, true) then -- did the {{#invoke:}} use sandbox version? |
|||
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version |
|||
else |
|||
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions' ); -- use the live version |
|||
end |
|||
end |
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 = 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) |
|||
error_text, error_state = set_error( 'parameter_ignored_suggest', {k, param}, true ); -- set the error message |
|||
error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message |
|||
else |
|||
error_text = utilities.set_message ('err_parameter_ignored', {k}); -- suggested param not supported by this template |
|||
v = ''; -- unset |
|||
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) and validate (suggestions.suggestions[ k:lower() ], config.CitationClass) then |
||
utilities.set_message ('err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}); |
|||
else |
else |
||
utilities.set_message ('err_parameter_ignored', {k}); |
|||
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 |
||
end |
end |
||
end |
end |
||
if error_text ~= '' then |
|||
table.insert( z.message_tail, {error_text, error_state} ); |
|||
end |
|||
end |
end |
||
missing_pipe_check (v); -- do we think that there is a parameter that is missing a pipe? |
|||
args[k] = v; -- save this parameter and its value |
|||
args[k] = v; |
|||
elseif not utilities.is_set (v) then -- for empty parameters |
|||
elseif args[k] ~= nil or (k == 'postscript') then |
|||
if not validate (k, config.CitationClass, true) then -- is this empty parameter a valid parameter |
|||
args[k] = v; |
|||
k = ('' == k) and '(empty string)' or k; -- when k is empty string (or was space(s) trimmed to empty string), replace with descriptive text |
|||
end |
|||
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 |
|||
utilities.set_message ('err_param_unknown_empty', { |
|||
1 == #empty_unknowns and '' or 's', |
|||
utilities.make_sep_list (#empty_unknowns, empty_unknowns) |
|||
}); |
|||
end |
|||
local url_param_t = {}; |
|||
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 (k, v); |
has_invisible_chars (k, v); -- look for invisible characters |
||
end |
|||
has_extraneous_punc (k, v); -- look for extraneous terminal punctuation in parameter values |
|||
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe? |
|||
args[k] = inter_wiki_check (k, v); -- when language interwiki-linked parameter missing leading colon replace with wiki-link label |
|||
if 'string' == type (k) and not cfg.url_skip[k] then -- when parameter k is not positional and not in url skip table |
|||
url_param_t[k] = v; -- make a parameter/value list for extraneous url check |
|||
end |
end |
||
end |
end |
||
return citation0( config, args) |
|||
has_extraneous_url (url_param_t); -- look for url in parameter values where a url does not belong |
|||
return table.concat ({ |
|||
frame:extensionTag ('templatestyles', '', {src=styles}), |
|||
citation0( config, args) |
|||
}); |
|||
end |
end |
||
return cs1; |
|||
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ |
|||
]] |
|||
return {citation = citation}; |