Module:Citation/CS1: Difference between revisions

From Vigyanwiki
m (1 revision imported from alpha:Module:Citation/CS1)
m (1 revision imported)
 
(16 intermediate revisions by 7 users not shown)
Line 1: Line 1:
require ('Module:No globals');
require ('strict');


--[[--------------------------< 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 >--------------------------------------
Line 10: Line 10:


local utilities; -- functions in Module:Citation/CS1/Utilities
local utilities; -- functions in Module:Citation/CS1/Utilities
local z ={}; -- table of tables in Module:Citation/CS1/Utilities
local z = {}; -- table of tables in Module:Citation/CS1/Utilities


local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
local identifiers; -- functions and tables in Module:Citation/CS1/Identifiers
Line 154: Line 154:
end
end


for _, d in ipairs ({'cash', 'company', 'today', 'org'}) do -- look for single letter second level domain names for these top level domains
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
if domain:match ('%f[%w][%w]%.' .. d) then
return true
return true
Line 265: Line 265:


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 utilities.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
Line 401: Line 401:
utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)});
utilities.set_message ('err_bare_url_missing_title', {utilities.wrap_style ('parameter', source)});
else
else
error (cfg.messages["bare_url_no_origin"]);
error (cfg.messages["bare_url_no_origin"]); -- programmer error; valid parameter name does not have matching meta-parameter
end
end
end
end
Line 533: Line 533:
end
end
-- if we get this far we have prefix and script
-- if we get this far we have prefix and script
name = cfg.lang_code_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
name = cfg.lang_tag_remap[lang] or mw.language.fetchLanguageName( lang, cfg.this_wiki_code ); -- get language name so that we can use it to categorize
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
if utilities.is_set (name) then -- is prefix a proper ISO 639-1 language code?
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
script_value = script_value:gsub ('^%l+%s*:%s*', ''); -- strip prefix from script
Line 764: Line 764:
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
if mw.ustring.find (v, cfg.indic_script) then -- it's ok if one of the Indic scripts
position = nil; -- unset position
position = nil; -- unset position
elseif cfg.emoji[mw.ustring.codepoint (v, position+1)] then -- is zwj followed by a character listed in emoji{}?
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 1,105: Line 1,105:
return table.concat(initials) -- Vancouver format does not include spaces.
return table.concat(initials) -- Vancouver format does not include spaces.
end
--[[--------------------------< 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:
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
end


Line 1,175: Line 1,242:
one = utilities.make_wikilink (person.link, one); -- link author/editor
one = utilities.make_wikilink (person.link, one); -- link author/editor
end
end
if one then -- if <one> has a value (name, mdash replacement, or mask text replacement)
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
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_tag_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, one); -- add it to the list of names
table.insert (name_list, sep_one); -- add the proper name-list separator
table.insert (name_list, sep_one); -- add the proper name-list separator
Line 1,200: Line 1,290:
local result = table.concat (name_list); -- construct list
local result = table.concat (name_list); -- construct list
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
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 got a last-first list and etal so add et al.
result = result .. sep .. cfg.messages['et al']; -- we've got a last-first list and etal so add et al.
end
end
Line 1,316: Line 1,406:
semicolons. Escaped semicolons are ones used as part of selected HTML entities.
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.
If the condition is met, the function adds the multiple name maintenance category.
Same test for first except that commas should not appear in given names (MOS:JR says
that the generational suffix does not take a separator character).  Titles, degrees,
postnominals, affiliations, all normally comma separated don't belong in a citation.
<name> – name parameter value
<list_name> – AuthorList, EditorList, etc
<limit> – number of allowed commas; 1 (default) for surnames; 0 for given names


returns nothing
returns nothing
Line 1,321: Line 1,419:
]]
]]


local function name_has_mult_names (name, list_name)
local function name_has_mult_names (name, list_name, limit)
local _, commas, semicolons, nbsps;
local _, commas, semicolons, nbsps;
limit = limit and limit or 1;
if utilities.is_set (name) then
if utilities.is_set (name) then
_, commas = name:gsub (',', ''); -- count the number of commas
_, commas = name:gsub (',', ''); -- count the number of commas
Line 1,336: Line 1,435:
-- from semicolons to 'escape' them. If additional entities are added,
-- from semicolons to 'escape' them. If additional entities are added,
-- they also can be subtracted.
-- they also can be subtracted.
if 1 < commas or 0 < (semicolons - nbsps) then
if limit < commas or 0 < (semicolons - nbsps) then
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message
end
end
Line 1,431: Line 1,530:


if not accept_name then -- <last> not wrapped in accept-as-written markup
if not accept_name then -- <last> not wrapped in accept-as-written markup
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only)
name_has_mult_names (last, list_name); -- check for multiple names in the parameter
name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation
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
name_is_generic (last, last_alias); -- check for names found in the generic names list
Line 1,441: Line 1,540:


if not accept_name then -- <first> not wrapped in accept-as-written markup
if not accept_name then -- <first> not wrapped in accept-as-written markup
name_has_mult_names (first, list_name, 0); -- check for multiple names in the parameter; 0 is number of allowed commas in a given name
name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation
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
name_is_generic (first, first_alias); -- check for names found in the generic names list
Line 1,494: Line 1,594:
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
link, link_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Link'], 'err_redundant_parameters', i );
mask = utilities.select_one ( args, cfg.aliases[list_name .. '-Mask'], 'err_redundant_parameters', i );
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
local project, language = interwiki_prefixen_get (last, true); -- true because we expect interwiki links in |lastn= to be wikilinked
if nil == project and nil == language then -- when both are nil
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.
last, etal = name_has_etal (last, etal, false, last_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
first, etal = name_has_etal (first, etal, false, first_alias); -- find and remove variations on et al.
Line 1,537: Line 1,654:


This function looks for:
This function looks for:
<lang_param> as a tag in cfg.lang_code_remap{}
<lang_param> as a tag in cfg.lang_tag_remap{}
<lang_param> as a name in cfg.lang_name_remap{}
<lang_param> as a name in cfg.lang_name_remap{}
Line 1,555: Line 1,672:
local tag;
local tag;


name = cfg.lang_code_remap[lang_param_lc]; -- assume <lang_param_lc> is a tag; attempt to get remapped language name  
name = cfg.lang_tag_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
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>
return name, lang_param_lc; -- so return <name> from remap and <lang_param_lc>
Line 1,561: Line 1,678:


tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags
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
name = cfg.lang_tag_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
if name then -- when <name>, <tag> is a tag for a remapped language name
return name, tag; -- so return <name> from remap and <tag>
return name, tag; -- so return <name> from remap and <tag>
Line 1,633: Line 1,750:
if cfg.this_wiki_code ~= lang_subtag then -- when the language is not the same as this wiki's language
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
if 2 == lang_subtag:len() then -- and is a two-character tag
-- utilities.add_prop_cat ('foreign-lang-source', {name, lang_subtag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
utilities.add_prop_cat ('foreign-lang-source', {name, tag}, lang_subtag); -- categorize it; tag appended to allow for multiple language categorization
else -- or is a recognized language (but has a three-character tag)
else -- or is a recognized language (but has a three-character tag)
Line 1,682: Line 1,798:
return cfg.presentation['sep_' .. mode], postscript;
return cfg.presentation['sep_' .. mode], postscript;
end
end


--[[--------------------------< S E T _ S T Y L E >-----------------------------
--[[--------------------------< S E T _ S T Y L E >-----------------------------
Line 1,772: Line 1,889:


inputs:
inputs:
max: A['DisplayAuthors'] or A['DisplayEditors']; a number or some flavor of etal
max: A['DisplayAuthors'] or A['DisplayEditors'], etc; a number or some flavor of etal
count: #a or #e
count: #a or #e
list_name: 'authors' or 'editors'
list_name: 'authors' or 'editors'
etal: author_etal or editor_etal
etal: author_etal or editor_etal
This function sets an error message when |display-xxxxors= value greater than or equal to number of names but
not when <max> comes from {{cs1 config}} global settings.  When using global settings, <param> is set to the
keyword 'cs1 config' which is used to supress the normal error.  Error is suppressed because it is to be expected
that some citations in an article will have the same or fewer names that the limit specified in {{cs1 config}}.


]]
]]
Line 1,786: Line 1,908:
elseif max:match ('^%d+$') then -- if is a string of numbers
elseif max:match ('^%d+$') then -- if is a string of numbers
max = tonumber (max); -- make it a number
max = tonumber (max); -- make it a number
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors
if (max >= count) and ('cs1 config' ~= param) then -- error when local |display-xxxxors= value greater than or equal to number of names; not an error when using global setting
utilities.set_message ('err_disp_name', {param, max}); -- add error message
utilities.set_message ('err_disp_name', {param, max}); -- add error message
max = nil;
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
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 2,089: Line 2,211:




--[[-------------------------< 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 parameters as a single string; or formatted volume
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 utilities.is_set (volume) and not utilities.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
Line 2,113: Line 2,235:
if is_journal then -- journal-style formatting
if is_journal then -- journal-style formatting
local vol = '';
local vol = '';
 
if utilities.is_set (volume) then
if utilities.is_set (volume) then
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals?
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals?
Line 2,123: Line 2,245:
end
end
end
end
if utilities.is_set (issue) then
vol = vol .. (utilities.is_set (issue) and utilities.substitute (cfg.messages['j-issue'], issue) or '')
return vol .. utilities.substitute (cfg.messages['j-issue'], issue);
vol = vol .. (utilities.is_set (article) and utilities.substitute (cfg.messages['j-article-num'], article) or '')
end
return vol;
return vol;
end
end
Line 2,131: Line 2,252:
if 'podcast' == cite_class and utilities.is_set (issue) then
if 'podcast' == cite_class and utilities.is_set (issue) then
return wrap_msg ('issue', {sepc, issue}, lower);
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
end


Line 2,300: Line 2,429:
for timestamp errors when the timestamp has a wildcard, return the URL unmodified
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*/)
A secondary function is to return an archive-url timestamp from those urls that have them (archive.org and
archive.today).  The timestamp is used by validation.archive_date_check() to see if the value in |archive-date=
matches the timestamp in the archive url.


]=]
]=]
Line 2,307: Line 2,440:
local path, timestamp, flag; -- portions of the archive.org URL
local path, timestamp, flag; -- portions of the archive.org URL
timestamp = url:match ('//archive.today/(%d%d%d%d%d%d%d%d%d%d%d%d%d%d)/'); -- get timestamp from archive.today urls
if timestamp then -- if this was an archive.today url ...
return url, date, timestamp; -- return ArchiveURL, ArchiveDate, and timestamp from |archive-url=, and done
end
-- here for archive.org urls
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
if (not url:match('//web%.archive%.org/')) and (not url:match('//liveweb%.archive%.org/')) then -- also deprecated liveweb Wayback machine URL
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
return url, date; -- not an archive.org archive, return ArchiveURL and ArchiveDate
Line 2,336: Line 2,474:
err_msg = cfg.err_msg_supl.flag;
err_msg = cfg.err_msg_supl.flag;
else
else
return url, date; -- return ArchiveURL and ArchiveDate
return url, date, timestamp; -- return ArchiveURL, ArchiveDate, and timestamp from |archive-url=
end
end
end
end
Line 2,343: Line 2,481:


if is_preview_mode then
if is_preview_mode then
return url, date; -- preview mode so return ArchiveURL and ArchiveDate
return url, date, timestamp; -- preview mode so return ArchiveURL, ArchiveDate, and timestamp from |archive-url=
else
else
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate
Line 2,410: Line 2,548:
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 NameListStyle;
if cfg.global_cs1_config_t['NameListStyle'] then -- global setting in {{cs1 config}} overrides local |name-list-style= parameter value; nil when empty or assigned value invalid
NameListStyle = is_valid_parameter_value (cfg.global_cs1_config_t['NameListStyle'], 'cs1 config: name-list-style', cfg.keywords_lists['name-list-style'], ''); -- error messaging 'param' here is a hoax
else
NameListStyle = is_valid_parameter_value (A['Nam