Module:Citation/CS1: Difference between revisions
m
1 revision imported
Johnrdorazio (talk | contribs) m (1 revision imported) |
Johnrdorazio (talk | contribs) m (1 revision imported) |
||
| (5 intermediate revisions by 3 users not shown) | |||
| Line 1: | Line 1: | ||
require ('strict'); | |||
require(' | |||
--[[--------------------------< 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 19: | Line 18: | ||
--[[ | --[[------------------< P A G E S C O P E V A R I A B L E S >--------------- | ||
declare variables here that have page-wide scope that are not brought in from other modules; that are created here and used here | declare variables here that have page-wide scope that are not brought in from | ||
other modules; that are created here and used here | |||
]] | ]] | ||
| Line 27: | Line 27: | ||
local added_deprecated_cat; -- Boolean flag so that the category is added only once | local added_deprecated_cat; -- Boolean flag so that the category is added only once | ||
local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category | local added_vanc_errs; -- Boolean flag so we only emit one Vancouver error / category | ||
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 62: | Line 64: | ||
]] | ]] | ||
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; | |||
added_vanc_errs = true; -- note that we've added this category | |||
utilities.set_message ('err_vancouver', {source, position}); | |||
end | end | ||
| Line 280: | Line 282: | ||
if utilities.is_set (orig) then | if utilities.is_set (orig) then | ||
link = ''; -- unset | link = ''; -- unset | ||
utilities.set_message ('err_bad_paramlink', orig); -- URL or wikilink in |title= with |title-link=; | |||
end | end | ||
| Line 355: | Line 357: | ||
]] | ]] | ||
local function check_for_url (parameter_list) | local function check_for_url (parameter_list, error_list) | ||
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 URL add an error message | 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)); | |||
end | end | ||
end | end | ||
end | end | ||
| Line 379: | 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', {}); | |||
end | end | ||
| Line 395: | Line 390: | ||
]] | ]] | ||
local function external_link( URL, label, source, access) | 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 utilities.is_set ( label ) then | if not utilities.is_set (label) then | ||
label = URL; | label = URL; | ||
if utilities.is_set ( source ) then | if utilities.is_set (source) then | ||
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"]); | ||
end | end | ||
end | end | ||
if not check_url( URL ) then | 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]+)([/%?#].*)$'); -- split the URL into scheme plus domain and path | domain, path = URL:match ('^([/%.%-%+:%a%d]+)([/%?#].*)$'); -- 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 = table.concat ({domain, path}); -- and reassemble | URL = table.concat ({domain, path}); -- and reassemble | ||
end | end | ||
base_url = table.concat({ "[", URL, " ", safe_for_url (label), "]" }); -- assemble a wiki-markup URL | 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) | if utilities.is_set (access) then -- access level (subscription, registration, limited) | ||
base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon | base_url = utilities.substitute (cfg.presentation['ext-link-access-signal'], {cfg.presentation[access].class, cfg.presentation[access].title, base_url}); -- add the appropriate icon | ||
end | end | ||
return | return base_url; | ||
end | end | ||
| Line 442: | 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 466: | Line 461: | ||
local function kern_quotes (str) | local function kern_quotes (str) | ||
local cap = ''; | local cap = ''; | ||
local wl_type, label, link; | local wl_type, label, link; | ||
| Line 473: | Line 467: | ||
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 = utilities.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 = utilities.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 = utilities.substitute (cfg.presentation['kern | str = utilities.substitute (cfg.presentation['kern-right'], str); | ||
end | end | ||
| Line 484: | Line 479: | ||
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 utilities.is_set (cap) then | if utilities.is_set (cap) then | ||
label = utilities.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 utilities.is_set (cap) then | if utilities.is_set (cap) then | ||
label = utilities.substitute (cfg.presentation['kern-right'], | label = utilities.substitute (cfg.presentation['kern-right'], cap); | ||
end | end | ||
| Line 534: | Line 529: | ||
lang = script_value:match('^(%l%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 utilities.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 = 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_code_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 | 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 | ||
-- is prefix one of these language codes? | -- is prefix one of these language codes? | ||
if utilities.in_array (lang, cfg.script_lang_codes) then | if utilities.in_array (lang, cfg.script_lang_codes) then | ||
utilities.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 | |||
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 | 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 = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL | script_value = utilities.substitute (cfg.presentation['bdi'], {lang, script_value}); -- isolate in case script is RTL | ||
| Line 563: | 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 value has been | 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. | ||
]] | ]] | ||
| Line 600: | Line 596: | ||
--[[ | --[[----------------< W I K I S O U R C E _ U R L _ M A K E >------------------- | ||
Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate label; nil else. | Makes a Wikisource URL from Wikisource interwiki-link. Returns the URL and appropriate | ||
label; nil else. | |||
str is the value assigned to |chapter= (or aliases) or |title= or |title-link= | str is the value assigned to |chapter= (or aliases) or |title= or |title-link= | ||
| Line 643: | Line 640: | ||
end | end | ||
end | end | ||
if ws_url then | if ws_url then | ||
ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL | ws_url = mw.uri.encode (ws_url, 'WIKI'); -- make a usable URL | ||
ws_url = ws_url:gsub ('%%23', '#'); -- undo percent encoding of fragment marker | ws_url = ws_url:gsub ('%%23', '#'); -- undo percent-encoding of fragment marker | ||
end | end | ||
| Line 653: | Line 650: | ||
--[[ | --[[----------------< 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- | Format the three periodical parameters: |script-<periodical>=, |<periodical>=, | ||
parameter. | and |trans-<periodical>= into a single Periodical meta-parameter. | ||
]] | ]] | ||
local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) | local function format_periodical (script_periodical, script_periodical_source, periodical, trans_periodical) | ||
if not utilities.is_set (periodical) then | if not utilities.is_set (periodical) then | ||
| Line 677: | Line 673: | ||
else -- here when trans-periodical without periodical or script-periodical | else -- here when trans-periodical without periodical or script-periodical | ||
periodical = trans_periodical; | periodical = trans_periodical; | ||
utilities.set_message ('err_trans_missing_title', {'periodical'}); | |||
end | end | ||
end | end | ||
return periodical | return periodical; | ||
end | 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- | Format the four chapter parameters: |script-chapter=, |chapter=, |trans-chapter=, | ||
parameter (chapter_url_source used for error messages). | and |chapter-url= into a single chapter meta- parameter (chapter_url_source used | ||
for error messages). | |||
]] | ]] | ||
local function format_chapter_title (script_chapter, script_chapter_source, chapter, chapter_source, trans_chapter, trans_chapter_source, chapter_url, chapter_url_source, no_quotes, access) | 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 | local ws_url, ws_label, L = wikisource_url_make (chapter); -- make a wikisource URL and label from a wikisource interwiki link | ||
if ws_url then | if ws_url then | ||
ws_label = ws_label:gsub ('_', ''); | ws_label = ws_label:gsub ('_', ' '); -- replace underscore separators with space characters | ||
chapter = ws_label; | chapter = ws_label; | ||
end | end | ||
| Line 726: | Line 721: | ||
chapter = trans_chapter; | chapter = trans_chapter; | ||
chapter_source = trans_chapter_source:match ('trans%-?(.+)'); -- when no chapter, get matching name from trans-<param> | 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 | 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 non-printable or invisible characters. | 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 Wikisource. | This function will detect the visible replacement character when it is part of the Wikisource. | ||
Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers (gallery, math, pre, ref) | Detects but ignores nowiki and math stripmarkers. Also detects other named stripmarkers | ||
and identifies them with a slightly different error message. | (gallery, math, pre, ref) and identifies them with a slightly different error message. | ||
See also coins_cleanup(). | |||
Output of this function is an error message that identifies the character or the Unicode group, or the stripmarker | Output of this function is an error message that identifies the character or the | ||
that was detected along with its position (or, for multi-byte characters, the position of its first byte) in the | Unicode group, or the stripmarker that was detected along with its position (or, | ||
parameter value. | for multi-byte characters, the position of its first byte) in the parameter value. | ||
]] | ]] | ||
| Line 752: | 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 capture; -- used by stripmarker detection to hold name of the stripmarker | local capture; -- used by stripmarker detection to hold name of the stripmarker | ||
local | local stripmarker; -- boolean set true when a stripmarker is found | ||
capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true | capture = string.match (v, '[%w%p ]*'); -- test for values that are simple ASCII text and bypass other tests if true | ||
if capture == v then -- if same there are no Unicode characters | if capture == v then -- if same there are no Unicode characters | ||
| Line 762: | Line 756: | ||
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 -- 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 | |||
elseif cfg.emoji[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 777: | Line 773: | ||
('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters | ('templatestyles' == capture and utilities.in_array (param, {'id', 'quote'})) then -- templatestyles stripmarker allowed in these parameters | ||
stripmarker = true; -- set a flag | stripmarker = true; -- set a flag | ||
elseif true == stripmarker and | 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 then | if capture and not (cfg.invisible_defs.del == capture or cfg.invisible_defs.zwj == 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 | ||
end | end | ||
end | end | ||
--[[ | --[[-------------------< A R G U M E N T _ W R A P P E R >---------------------- | ||
Argument wrapper. This function provides support for argument mapping defined in the configuration file so that | Argument wrapper. This function provides support for argument mapping defined | ||
multiple names can be transparently aliased to single internal variable. | in the configuration file so that multiple names can be transparently aliased to | ||
single internal variable. | |||
]] | ]] | ||
| Line 808: | Line 804: | ||
return setmetatable({ | return setmetatable({ | ||
ORIGIN = function ( self, k ) | ORIGIN = function ( self, k ) | ||
local dummy = self[k]; --force the variable to be loaded. | local dummy = self[k]; -- force the variable to be loaded. | ||
return origin[k]; | return origin[k]; | ||
end | end | ||
| Line 823: | Line 819: | ||
v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' ); | v, origin[k] = utilities.select_one ( args, list, 'err_redundant_parameters' ); | ||
if origin[k] == nil then | if origin[k] == nil then | ||
origin[k] = ''; -- Empty string, not nil | origin[k] = ''; -- Empty string, not nil | ||
end | end | ||
elseif list ~= nil then | elseif list ~= nil then | ||
| Line 846: | Line 842: | ||
--[[--------------------------< N O W R A P _ D A T E > | --[[--------------------------< N O W R A P _ D A T E >------------------------- | ||
When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. | When date is YYYY-MM-DD format wrap in nowrap span: <span ...>YYYY-MM-DD</span>. | ||
MMMM DD, YYYY then wrap in nowrap span: <span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY | When date is DD MMMM YYYY or is MMMM DD, YYYY then wrap in nowrap span: | ||
<span ...>DD MMMM</span> YYYY or <span ...>MMMM DD,</span> YYYY | |||
DOES NOT yet support MMMM YYYY or any of the date ranges. | DOES NOT yet support MMMM YYYY or any of the date ranges. | ||
| Line 871: | 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 |type=<default value>) for those templates that have defaults. | This function sets default title types (equivalent to the citation including | ||
Also handles the special case where it is desirable to omit the title type from the rendered citation (|type=none). | |type=<default value>) for those templates that have defaults. Also handles the | ||
special case where it is desirable to omit the title type from the rendered citation | |||
(|type=none). | |||
]] | ]] | ||
| Line 890: | Line 889: | ||
--[[--------------------------< S A F E _ J O I N >----------------------------- | |||
--[[--------------------------< S A F E _ J O I N > | |||
Joins a sequence of strings together while checking for duplicate separation characters. | Joins a sequence of strings together while checking for duplicate separation characters. | ||
| Line 983: | Line 928: | ||
trim = false; | trim = false; | ||
end_chr = f.sub(str, -1, -1); -- get the last character of the output string | end_chr = f.sub(str, -1, -1); -- get the last character of the output string | ||
-- str = str .. "<HERE(enchr=" .. end_chr .. ")" | -- str = str .. "<HERE(enchr=" .. end_chr .. ")" -- debug stuff? | ||
if end_chr == duplicate_char then -- if same as separator | if end_chr == duplicate_char then -- if same as separator | ||
str = f.sub(str, 1, -2); | str = f.sub(str, 1, -2); -- remove it | ||
elseif end_chr == "'" then -- if it might be wiki-markup | elseif end_chr == "'" then -- if it might be wiki-markup | ||
if f.sub(str, -3, -1) == duplicate_char .. "''" then | if f.sub(str, -3, -1) == duplicate_char .. "''" then -- if last three chars of str are sepc'' | ||
str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' | str = f.sub(str, 1, -4) .. "''"; -- remove them and add back '' | ||
elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' | elseif f.sub(str, -5, -1) == duplicate_char .. "]]''" then -- if last five chars of str are sepc]]'' | ||
| Line 995: | Line 940: | ||
end | end | ||
elseif end_chr == "]" then -- if it might be wiki-markup | elseif end_chr == "]" then -- if it might be wiki-markup | ||
if f.sub(str, -3, -1) == duplicate_char .. "]]" then | if f.sub(str, -3, -1) == duplicate_char .. "]]" then -- if last three chars of str are sepc]] wikilink | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then | elseif f.sub(str, -3, -1) == duplicate_char .. '"]' then -- if last three chars of str are sepc"] quoted external link | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -2, -1) == duplicate_char .. "]" then | elseif f.sub(str, -2, -1) == duplicate_char .. "]" then -- if last two chars of str are sepc] external link | ||
trim = true; | trim = true; | ||
elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. | elseif f.sub(str, -4, -1) == duplicate_char .. "'']" then -- normal case when |url=something & |title=Title. | ||
| Line 1,006: | Line 951: | ||
elseif end_chr == " " then -- if last char of output string is a space | elseif end_chr == " " then -- if last char of output string is a space | ||
if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> | if f.sub(str, -2, -1) == duplicate_char .. " " then -- if last two chars of str are <sepc><space> | ||
str = f.sub(str, 1, -3); | str = f.sub(str, 1, -3); -- remove them both | ||
end | end | ||
end | end | ||
| Line 1,021: | Line 966: | ||
end | end | ||
end | end | ||
str = str .. value; --add it to the output string | str = str .. value; -- add it to the output string | ||
end | end | ||
end | end | ||
| Line 1,028: | Line 973: | ||
--[[--------------------------< 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. | |||
]] | ]] | ||
| Line 1,042: | Line 988: | ||
--[[ | --[[--------------------< I S _ G O O D _ V A N C _ N A M E >------------------- | ||
For Vancouver style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name | For Vancouver style, author/editor names are supposed to be rendered in Latin | ||
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character. | (read ASCII) characters. When a name uses characters that contain diacritical | ||
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters. | marks, those characters are to be converted to the corresponding Latin | ||
character. When a name is written using a non-Latin alphabet or logogram, that | |||
name is to be transliterated into Latin characters. The module doesn't do this | |||
so editors may/must. | |||
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets | This test allows |first= and |last= names to contain any of the letters defined | ||
in the four Unicode Latin character sets | |||
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A | [http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A | ||
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF | [http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF | ||
| Line 1,055: | 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. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) | |lastn= also allowed to contain hyphens, spaces, and apostrophes. | ||
(http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) | |||
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods | |firstn= also allowed to contain hyphens, spaces, apostrophes, and periods | ||
This original test: | This original test: | ||
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then | if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") | ||
was written outside of the code editor and pasted here because the code editor gets confused between character insertion point and cursor position. | or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]+[2-6%a]*$") then | ||
The test has been rewritten to use decimal character escape sequence for the individual bytes of the Unicode characters so that it is not necessary | was written outside of the code editor and pasted here because the code editor | ||
to use an external editor to maintain this code. | gets confused between character insertion point and cursor position. The test has | ||
been rewritten to use decimal character escape sequence for the individual bytes | |||
of the Unicode characters so that it is not necessary to use an external editor | |||
to maintain this code. | |||
\195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) | \195\128-\195\150 – À-Ö (U+00C0–U+00D6 – C0 controls) | ||
| Line 1,071: | Line 1,024: | ||
]] | ]] | ||
local function is_good_vanc_name (last, first, suffix) | local function is_good_vanc_name (last, first, suffix, position) | ||
if not suffix then | if not suffix then | ||
if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix | if first:find ('[,%s]') then -- when there is a space or comma, might be first name/initials + generational suffix | ||
| Line 1,080: | Line 1,033: | ||
if utilities.is_set (suffix) then | if utilities.is_set (suffix) then | ||
if not is_suffix (suffix) then | if not is_suffix (suffix) then | ||
add_vanc_error (cfg.err_msg_supl.suffix); | add_vanc_error (cfg.err_msg_supl.suffix, position); | ||
return false; -- not a name with an appropriate suffix | return false; -- not a name with an appropriate suffix | ||
end | end | ||
| Line 1,086: | Line 1,039: | ||
if nil == mw.ustring.find (last, "^[A-Za-z\195\128-\195\150\195\152-\195\182\195\184-\198\191\199\132-\201\143%-%s%']*$") 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%'%.]*$") then | ||
add_vanc_error (cfg.err_msg_supl['non-Latin char']); | add_vanc_error (cfg.err_msg_supl['non-Latin char'], position); | ||
return false; -- not a string of Latin characters; Vancouver requires Romanization | return false; -- not a string of Latin characters; Vancouver requires Romanization | ||
end; | end; | ||
| Line 1,097: | Line 1,050: | ||
Attempts to convert names to initials in support of |name-list-style=vanc. | Attempts to convert names to initials in support of |name-list-style=vanc. | ||
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. | Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. | ||
See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/. | |||
Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. | Vancouver style requires family rank designations (Jr, II, III, etc.) to be rendered | ||
This code only accepts and understands generational suffix in the Vancouver format because Roman numerals look like, and can be mistaken for, initials. | as Jr, 2nd, 3rd, etc. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/. | ||
This code only accepts and understands generational suffix in the Vancouver format | |||
because Roman numerals look like, and can be mistaken for, initials. | |||
This function uses ustring functions because firstname initials may be any of the Unicode Latin characters accepted by is_good_vanc_name (). | This function uses ustring functions because firstname initials may be any of the | ||
Unicode Latin characters accepted by is_good_vanc_name (). | |||
]] | ]] | ||
local function reduce_to_initials(first) | local function reduce_to_initials(first, position) | ||
local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$"); | local name, suffix = mw.ustring.match(first, "^(%u+) ([%dJS][%drndth]+)$"); | ||
| Line 1,119: | 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 (cfg.err_msg_supl.suffix); | 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 1,142: | 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 1,151: | Line 1,108: | ||
--[[--------------------------< L I S T _ P E O P L E > | --[[--------------------------< L I S T _ P E O P L E >-------------------------- | ||
Formats a list of people ( | Formats a list of people (authors, contributors, editors, interviewers, translators) | ||
names in the list will be linked when | names in the list will be linked when | ||
|<name>-link= has a value | |<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 | |<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 | when |<name>-mask=0, the associated name is not rendered | ||
| Line 1,168: | Line 1,126: | ||
local format = control.format; | local format = control.format; | ||
local maximum = control.maximum; | local maximum = control.maximum; | ||
local name_list = {}; | local name_list = {}; | ||
| Line 1,174: | Line 1,131: | ||
sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma | sep = cfg.presentation['sep_nl_vanc']; -- name-list separator between names is a comma | ||
namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space | namesep = cfg.presentation['sep_name_vanc']; -- last/first separator is a space | ||
else | else | ||
sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon | sep = cfg.presentation['sep_nl']; -- name-list separator between names is a semicolon | ||
| Line 1,197: | Line 1,153: | ||
local n = tonumber (mask); -- convert to a number if it can be converted; nil else | local n = tonumber (mask); -- convert to a number if it can be converted; nil else | ||
if n then | if n then | ||
one = 0 ~= n and string.rep("—",n) or nil; -- make a string of (n > 0) mdashes, nil else, to replace name | 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 | person.link = nil; -- don't create link to name if name is replaces with mdash string or has been set nil | ||
else | else | ||
| Line 1,209: | Line 1,165: | ||
if ("vanc" == format) then -- if Vancouver format | if ("vanc" == format) then -- if Vancouver format | ||
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) | one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/) | ||
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested | if not person.corporate and is_good_vanc_name (one, first, 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 | ||
| Line 1,229: | Line 1,185: | ||
if 0 < count then | if 0 < count then | ||
if 1 < count and not etal then | if 1 < count and not etal then | ||
if 'amp' == format | if 'amp' == format then | ||
name_list[#name_list-2] = " & "; -- replace last separator with ampersand text | name_list[#name_list-2] = " & "; -- replace last separator with ampersand text | ||
elseif 'and' == format then | elseif 'and' == format then | ||
| Line 1,251: | Line 1,207: | ||
--[[ | --[[--------------------< 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 returns an empty string. | Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise | ||
returns an empty string. | |||
namelist is one of the contributor-, author-, or editor-name lists chosen in that order. year is Year or anchor_year. | namelist is one of the contributor-, author-, or editor-name lists chosen in that | ||
order. year is Year or anchor_year. | |||
]] | ]] | ||
local function | local function make_citeref_id (namelist, year) | ||
local names={}; | local names={}; -- a table for the one to four names and year | ||
for i,v in ipairs (namelist) do | 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 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 utilities.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. | |||
This function never sets the flag to false but returns | <cite_class> – config.CitationClass from calling template | ||
previous passes through this function or by the associated |display-<names>=etal parameter | <mode> – value from |mode= parameter | ||
]] | |||
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 | |||
]] | ]] | ||
| Line 1,288: | Line 1,274: | ||
if utilities.is_set (name) then -- name can be nil in which case just return | if utilities.is_set (name) then -- name can be nil in which case just return | ||
local patterns = cfg.et_al_patterns; | local patterns = cfg.et_al_patterns; -- get patterns from configuration | ||
for _, pattern in ipairs (patterns) do -- loop through all of the patterns | for _, pattern in ipairs (patterns) do -- loop through all of the patterns | ||
| Line 1,295: | Line 1,281: | ||
etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) | etal = true; -- set flag (may have been set previously here or by |display-<names>=etal) | ||
if not nocat then -- no categorization for |vauthors= | if not nocat then -- no categorization for |vauthors= | ||
utilities.set_message ('err_etal', {param}); -- and set an error if not added | |||
end | end | ||
end | end | ||
| Line 1,305: | Line 1,291: | ||
--[[ | --[[---------------------< N A M E _ I S _ N U M E R I C >---------------------- | ||
Add maint cat when name parameter value does not contain letters. Does not catch mixed alphanumeric names so | Add maint cat when name parameter value does not contain letters. Does not catch | ||
|last=A. Green (1922-1987) does not get caught in the current version of this test but |first=(1888) is caught. | mixed alphanumeric names so |last=A. Green (1922-1987) does not get caught in the | ||
current version of this test but |first=(1888) is caught. | |||
returns nothing | returns nothing | ||
| Line 1,323: | Line 1,310: | ||
--[[ | --[[-----------------< 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. | Evaluates the content of last/surname (authors etc.) parameters for multiple names. | ||
if there is more than one comma or any semicolons. | 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 | returns nothing | ||
| Line 1,357: | Line 1,322: | ||
local function name_has_mult_names (name, list_name) | local function name_has_mult_names (name, list_name) | ||
local _, commas, semicolons; | local _, commas, semicolons, nbsps; | ||
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 | ||
_, semicolons = name:gsub (';', ''); -- count the number of semicolons | _, 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 | |||
if 1 < commas or 0 < semicolons then | -- There is exactly 1 semicolon per entity, so subtract nbsps | ||
-- from semicolons to 'escape' them. If additional entities are added, | |||
-- they also can be subtracted. | |||
if 1 < commas or 0 < (semicolons - nbsps) then | |||
utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message | utilities.set_message ('maint_mult_names', cfg.special_case_translation [list_name]); -- add a maint message | ||
end | end | ||
| Line 1,369: | Line 1,343: | ||
--[[ | --[=[-------------------------< 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. | |||
local | 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 | |||
val = test_t[2] and str_lower[wiki](value) or val; -- when <test_t[2]> set to 'true', plaintext search using lowercase value | |||
return str_find[wiki] (val, test_t[1], 1, test_t[2]); -- return nil when not found or matched | |||
end | |||
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 | |||
--[[--------------------------< 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 | |||
parameter name used in error messaging | |||
]] | |||
-- | local function name_is_generic (name, name_alias) | ||
if not added_generic_name_errs and is_generic ('generic_names', name) then | |||
utilities.set_message ('err_generic_name', name_alias); -- set an error message | |||
added_generic_name_errs = true; | |||
end | |||
end | |||
--[[--------------------------< N A M E _ C H E C K S >-------------------------------------------------------- | |||
This function calls various name checking functions used to validate the content of the various name-holding parameters. | |||
]] | ]] | ||
local function | local function name_checks (last, first, list_name, last_alias, first_alias) | ||
local accept_name; | |||
local | |||
if utilities.is_set (last) then | |||
last, accept_name = utilities.has_accept_as_written (last); -- remove accept-this-as-written markup when it wraps all of <last> | |||
last, | |||
if not accept_name then -- <last> not wrapped in accept-as-written markup | |||
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) | |||
name_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 utilities.is_set (first) then | |||
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> | |||
if not accept_name then -- <first> not wrapped in accept-as-written markup | |||
name_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 | |||
return last, first; -- done | |||
end | end | ||
--[[ | --[[----------------------< E X T R A C T _ N A M E S >------------------------- | ||
Gets | Gets name list from the input arguments | ||
Searches through args in sequential order to find |lastn= and |firstn= parameters | |||
(or their aliases), and their matching link and mask parameters. Stops searching | |||
when both |lastn= and |firstn= are not found in args after two sequential attempts: | |||
found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the | |||
search is done. | |||
This function emits an error message when there is a |firstn= without a matching | |||
|lastn=. When there are 'holes' in the list of last names, |last1= and |last3= | |||
are present but |last2= is missing, an error message is emitted. |lastn= is not | |||
required to have a matching |firstn=. | |||
When an author or editor parameter contains some form of 'et al.', the 'et al.' | |||
is stripped from the parameter and a flag (etal) returned that will cause list_people() | |||
to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps | |||
'et al.' out of the template's metadata. When this occurs, an error is emitted. | |||
]] | ]] | ||
local function | local function extract_names(args, list_name) | ||
local | local names = {}; -- table of names | ||
local | local last; -- individual name components | ||
local | local first; | ||
local | local link; | ||
local mask; | |||
local i = 1; -- loop counter/indexer | |||
local n = 1; -- output table indexer | |||
local count = 0; -- used to count the number of times we haven't found a |last= (or alias for authors, |editor-last or alias for editors) | |||
local etal = false; -- return value set to true when we find some form of et al. in an author parameter | |||
local | local last_alias, first_alias, link_alias; -- selected parameter aliases used in error messaging | ||
while true do | |||
last, last_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-Last'], 'err_redundant_parameters', i ); -- search through args for name components beginning at 1 | |||
first, first_alias = utilities.select_one ( args, cfg.aliases[list_name .. '-First'], '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 ); | |||
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 | |||
local alias = first_alias:find ('given', 1, true) and 'given' or 'first'; -- get first or given form of the alias | |||
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? | |||
count = count + 1; -- number of times we haven't found last and first | |||
if 2 <= count then -- two missing names and we give up | |||
break; -- normal exit or there is a two-name hole in the list; can't tell which | |||
end | |||
else -- we have last with or without a first | |||
local result; | |||
link = link_title_ok (link, link_alias, last, last_alias); -- check for improper wiki-markup | |||
if first then | |||
if | link = link_title_ok (link, link_alias, first, first_alias); -- check for improper wiki-markup | ||
end | end | ||
names[n] = {last = last, first = first, link = link, mask = mask, corporate = false}; -- add this name to our names list (corporate for |vauthors= only) | |||
if | n = n + 1; -- point to next location in the names table | ||
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 | |||
end | end | ||
i = i + 1; -- point to next args location | |||
end | |||
return names, etal; -- all done, return our list of names and the etal flag | |||
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. | |||
This function looks for: | |||
<lang_param> as a tag in cfg.lang_code_remap{} | |||
<lang_param> as a name in cfg.lang_name_remap{} | |||
<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 | |||
]] | |||
local function name_tag_get (lang_param) | |||
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> | |||
name | |||
end | end | ||
tag = lang_param_lc:match ('^(%a%a%a?)%-.*'); -- still assuming that <lang_param_lc> is a tag; strip script, region, variant subtags | |||
return | 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 | 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 | ||
if tag then | |||
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 | |||
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 | |||
if name then | |||
return name, lang_param_lc; -- <lang_param_lc> is a tag so return it and <name> | |||
end | |||
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 | |||
if tag then | |||
name = cfg.mw_languages_by_tag_t[tag]; -- attempt to get a language name using the shortened <tag> | |||
if name then | |||
if | return name, tag; -- <lang_param_lc> is an unrecognized IETF-like tag so return <name> and language subtag | ||
end | |||
end | end | ||
end | end | ||
--[[ | --[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------ | ||
Gets language name from a provided two- or three-character ISO 639 code. If a code | |||
is recognized by MediaWiki, use the returned name; if not, then use the value that | |||
was provided with the language parameter. | |||
When |language= contains a recognized language (either code or name), the page is | |||
assigned to the category for that code: Category:Norwegian-language sources (no). | |||
For valid three-character code languages, the page is assigned to the single category | |||
for '639-2' codes: Category:CS1 ISO 639-2 language sources. | |||
local | Languages that are the same as the local wiki are not categorized. MediaWiki does | ||
not recognize three-character equivalents of two-character codes: code 'ar' is | |||
recognized but code 'ara' is not. | |||
This function supports multiple languages in the form |language=nb, French, th | |||
where the language names or codes are separated from each other by commas with | |||
optional space characters. | |||
]] | ]] | ||
local function | 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 language_list = {}; -- table of language names to be rendered | |||
local names_t = {}; -- table made from the value assigned to |language= | |||
local this_wiki_name = mw.language.fetchLanguageName (cfg.this_wiki_code, cfg.this_wiki_code); -- get this wiki's language name | |||
names_t = mw.text.split (lang, '%s*,%s*'); -- names should be a comma separated list | |||
-- | 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 | ||
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 | |||
lang_subtag = tag:gsub ('^(%a%a%a?)%-.*', '%1'); -- for categorization, strip any IETF-like tags from language tag | |||
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 | |||
-- 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 | |||
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? | |||
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 | |||
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 | |||
table.insert (language_list, name); | |||
name = ''; -- so we can reuse it | |||
end | |||
name = utilities.make_sep_list (#language_list, language_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' | |||
return ''; -- if one language and that language is this wiki's return an empty string (no annotation) | |||
end | |||
return (" " .. wrap_msg ('language', name)); -- otherwise wrap with '(in ...)' | |||
--[[ TODO: should only return blank or name rather than full list | |||
so we can clean up the bunched parenthetical elements Language, Type, Format | |||
]] | |||
end | |||
--[[-----------------------< S E T _ C S _ S T Y L E >-------------------------- | |||
Gets the default CS style configuration for the given mode. | |||
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 set_style (mode, | local function set_cs_style (postscript, mode) | ||
if utilities.is_set(postscript) then | |||
-- emit a maintenance message if user postscript is the default cs1 postscript | |||
-- 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 | |||
return cfg.presentation['sep_' .. mode], postscript; | |||
end | |||
--[[--------------------------< S E T _ S T Y L E >----------------------------- | |||
Sets the separator and postscript styles. Checks the |mode= first and the | |||
#invoke CitationClass second. Removes the postscript if postscript == none. | |||
]] | |||
local function set_style (mode, postscript, cite_class) | |||
local sep; | local sep; | ||
if 'cs2' == mode then | if 'cs2' == mode then | ||
sep, | sep, postscript = set_cs_style (postscript, 'cs2'); | ||
elseif 'cs1' == mode then | elseif 'cs1' == mode then | ||
sep, | sep, postscript = set_cs_style (postscript, 'cs1'); | ||
else | elseif 'citation' == cite_class then | ||
sep, | sep, postscript = set_cs_style (postscript, 'cs2'); | ||
else | |||
sep, postscript = set_cs_style (postscript, 'cs1'); | |||
end | end | ||
if cfg.keywords_xlate[ | if cfg.keywords_xlate[postscript:lower()] == 'none' then | ||
-- emit a maintenance message if user postscript is the default cs2 postscript | |||
-- we catch the opposite case for cs1 in set_cs_style | |||
if 'cs2' == mode or 'citation' == cite_class then | |||
utilities.set_message ('maint_postscript'); | |||
end | |||
postscript = ''; | |||
end | end | ||
return sep, | return sep, postscript | ||
end | end | ||
--[=[-------------------------< I S _ P D F > | --[=[-------------------------< I S _ P D F >----------------------------------- | ||
Determines if a URL has the file extension that is one of the PDF file extensions used by [[MediaWiki:Common.css]] when | Determines if a URL has the file extension that is one of the PDF file extensions | ||
applying the PDF icon to external links. | 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 1,699: | Line 1,731: | ||
--[[--------------------------< S T Y L E _ F O R M A T > | --[[--------------------------< S T Y L E _ F O R M A T >----------------------- | ||
Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message if the format parameter does | Applies CSS style to |format=, |chapter-format=, etc. Also emits an error message | ||
not have a matching URL parameter. If the format parameter is not set and the URL contains a file extension that | if the format parameter does not have a matching URL parameter. If the format parameter | ||
is recognized as a PDF document by MediaWiki's commons.css, this code will set the format parameter to (PDF) with | is not set and the URL contains a file extension that is recognized as a PDF document | ||
by MediaWiki's commons.css, this code will set the format parameter to (PDF) with | |||
the appropriate styling. | the appropriate styling. | ||
| Line 1,712: | Line 1,745: | ||
format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize | format = utilities.wrap_style ('format', format); -- add leading space, parentheses, resize | ||
if not utilities.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 URL is a PDF file then | elseif is_pdf (url) then -- format is not set so if URL is a PDF file then | ||
| Line 1,723: | Line 1,756: | ||
--[[ | --[[---------------------< G E T _ D I S P L A Y _ N A M E S >------------------ | ||
Returns a number that defines the number of names displayed for author and editor name lists and a Boolean flag | Returns a number that defines the number of names displayed for author and editor | ||
to indicate when et al. should be appended to the name list. | name lists and a Boolean flag to indicate when et al. should be appended to the name list. | ||
When the value assigned to |display-xxxxors= is a number greater than or equal to zero, return the number and | When the value assigned to |display-xxxxors= is a number greater than or equal to zero, | ||
the previous state of the 'etal' flag (false by default but may have been set to true if the name list contains | return the number and the previous state of the 'etal' flag (false by default | ||
some variant of the text 'et al.'). | but may have been set to true if the name list contains some variant of the text 'et al.'). | ||
When the value assigned to |display-xxxxors= is the keyword 'etal', return a number that is one greater than the | When the value assigned to |display-xxxxors= is the keyword 'etal', return a number | ||
number of authors in the list and set the 'etal' flag true. | that is one greater than the number of authors in the list and set the 'etal' flag true. | ||
the names in the name list followed by 'et al.' | This will cause the list_people() to display all of the names in the name list followed by 'et al.' | ||
In all other cases, returns nil and the previous state of the 'etal' flag. | In all other cases, returns nil and the previous state of the 'etal' flag. | ||
| Line 1,746: | Line 1,779: | ||
]] | ]] | ||
local function get_display_names (max, count, list_name, etal) | local function get_display_names (max, count, list_name, etal, param) | ||
if utilities.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 | ||
| Line 1,754: | Line 1,787: | ||
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 | |||
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 | |||
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 1,767: | Line 1,800: | ||
--[[ | --[[----------< E X T R A _ T E X T _ I N _ P A G E _ C H E C K >--------------- | ||
Adds page | Adds error if |page=, |pages=, |quote-page=, |quote-pages= has what appears to be | ||
abbreviation in the first characters of the parameter content. | some form of p. or pp. abbreviation in the first characters of the parameter content. | ||
check | check page for extraneous p, p., pp, pp., pg, pg. at start of parameter value: | ||
good pattern: '^P[^%.P%l]' matches when | good pattern: '^P[^%.P%l]' matches when page begins PX or P# but not Px | ||
bad pattern: '^[Pp][ | where x and X are letters and # is a digit | ||
bad pattern: '^[Pp][PpGg]' matches when page begins pp, pP, Pp, PP, pg, pG, Pg, PG | |||
]] | ]] | ||
local function extra_text_in_page_check ( | local function extra_text_in_page_check (val, name) | ||
if not val:match (cfg.vol_iss_pg_patterns.good_ppattern) then | |||
for _, pattern in ipairs (cfg.vol_iss_pg_patterns.bad_ppatterns) do -- spin through the selected sequence table of patterns | |||
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 | |||
end | |||
--[[--------------------------< E X T R A _ T E X T _ I N _ V O L _ I S S _ C H E C K >------------------------ | |||
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 | ||
| Line 1,800: | Line 1,878: | ||
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; | ||
| Line 1,807: | Line 1,885: | ||
if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses | if name_table[i]:match ('^%(%(.*[^%)][^%)]$') then -- first segment of corporate with one or more commas; this segment has the opening doubled parentheses | ||
local name = name_table[i]; | local name = name_table[i]; | ||
i = i + 1; | i = i + 1; -- bump indexer to next segment | ||
while name_table[i] do | while name_table[i] do | ||
name = name .. ', ' .. name_table[i]; -- concatenate with previous segments | name = name .. ', ' .. name_table[i]; -- concatenate with previous segments | ||
| Line 1,863: | Line 1,941: | ||
v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name> | v_name, accept_name = utilities.has_accept_as_written (v_name); -- remove accept-this-as-written markup when it wraps all of <v_name> | ||
if accept_name then | if accept_name then | ||
last = v_name; | last = v_name; | ||
| Line 1,870: | Line 1,946: | ||
elseif string.find(v_name, "%s") then | elseif string.find(v_name, "%s") then | ||
if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; | if v_name:find('[;%.]') then -- look for commonly occurring punctuation characters; | ||
add_vanc_error (cfg.err_msg_supl.punctuation); | add_vanc_error (cfg.err_msg_supl.punctuation, i); | ||
end | end | ||
local lastfirstTable = {} | local lastfirstTable = {} | ||
| Line 1,884: | Line 1,960: | ||
first = ''; -- unset | first = ''; -- unset | ||
last = v_name; -- last empty because something wrong with first | last = v_name; -- last empty because something wrong with first | ||
add_vanc_error (cfg.err_msg_supl.name); | add_vanc_error (cfg.err_msg_supl.name, i); | ||
end | end | ||
if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then | if mw.ustring.match (last, '%a+%s+%u+%s+%a+') then | ||
add_vanc_error (cfg.err_msg_supl['missing comma']); | add_vanc_error (cfg.err_msg_supl['missing comma'], i); -- matches last II last; the case when a comma is missing | ||
end | end | ||
if mw.ustring.match (v_name, ' %u %u$') 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$') then -- this test is in the wrong place TODO: move or replace with a more appropriate test | ||
add_vanc_error (cfg.err_msg_supl. | add_vanc_error (cfg.err_msg_supl.initials, i); -- matches a space between two initials | ||
end | end | ||
else | else | ||
| Line 1,898: | Line 1,974: | ||
if utilities.is_set (first) then | if utilities.is_set (first) then | ||
if not mw.ustring.match (first, "^%u?%u$") 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 (cfg.err_msg_supl.initials); | 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, suffix); -- check first and last before restoring the suffix which may have a non-Latin digit | is_good_vanc_name (last, first, suffix, i); -- check first and last before restoring the suffix which may have a non-Latin digit | ||
if utilities.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 | ||
| Line 1,907: | Line 1,983: | ||
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 | ||
| Line 1,922: | Line 1,998: | ||
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 1,933: | Line 2,009: | ||
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. | ||
]] | ]] | ||
| Line 1,955: | Line 2,031: | ||
err_name = 'editor'; | err_name = 'editor'; | ||
end | end | ||
utilities.set_message ('err_redundant_parameters', err_name .. '-name-list parameters'); -- add error message | |||
end | end | ||
| Line 1,973: | Line 2,048: | ||
of the list of allowed values returns the translated value; else, emits an error message and returns the value | of the list of allowed values returns the translated value; else, emits an error message and returns the value | ||
specified by ret_val. | specified by ret_val. | ||
TODO: explain <invert> | |||
]] | ]] | ||
local function is_valid_parameter_value (value, name, possible, ret_val) | local function is_valid_parameter_value (value, name, possible, ret_val, invert) | ||
if not utilities.is_set (value) then | if not utilities.is_set (value) then | ||
return ret_val; -- an empty parameter is ok | return ret_val; -- an empty parameter is ok | ||
end | |||
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 | 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 ret_val; | return ret_val; | ||
end | end | ||
| Line 2,019: | Line 2,100: | ||
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 | 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 utilities.is_set (volume | utilities.add_prop_cat ('long-vol'); -- yes, add properties cat | ||
end | |||
if is_journal then -- journal-style formatting | |||
local vol = ''; | |||
return | |||
if utilities.is_set (volume) then | |||
if is_numeric_vol then -- |volume= value all digits or all uppercase Roman numerals? | |||
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face | |||
elseif is_long_vol then -- not all digits or Roman numerals; longer than 4 characters? | |||
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 | |||
if utilities.is_set (issue) then | |||
return vol .. utilities.substitute (cfg.messages['j-issue'], issue); | |||
end | end | ||
return vol; | |||
end | end | ||
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 | end | ||
-- all other types of citation | |||
if utilities.is_set (volume) and utilities.is_set (issue) then | |||
if utilities.is_set (volume) | 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); | |||
return | |||
end | end | ||
end | end | ||
| Line 2,111: | Line 2,202: | ||
If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text | If any of these are interwiki links to Wikisource, returns the label portion of the interwiki-link as plain text | ||
for use in COinS. This COinS thing is done because here we convert an interwiki-link to | for use in COinS. This COinS thing is done because here we convert an interwiki-link to an external link and | ||
add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? | add an icon span around that; get_coins_pages() doesn't know about the span. TODO: should it? | ||
| Line 2,121: | Line 2,212: | ||
]] | ]] | ||
local function insource_loc_get (page, pages, at) | 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?) | 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?) | ||
| Line 2,129: | Line 2,220: | ||
at = ''; | at = ''; | ||
end | end | ||
extra_text_in_page_check (page); | 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 | ws_url, ws_label, L = wikisource_url_make (page); -- make ws URL from |page= interwiki link; link portion L becomes tooltip label | ||
| Line 2,141: | Line 2,232: | ||
at = ''; -- unset | at = ''; -- unset | ||
end | end | ||
extra_text_in_page_check (pages); | 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 | ws_url, ws_label, L = wikisource_url_make (pages); -- make ws URL from |pages= interwiki link; link portion L becomes tooltip label | ||
| Line 2,161: | Line 2,252: | ||
end | end | ||
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------ | |||
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- | 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 | |||
--[=[-------------------------< A R C H I V E _ U R L _ C H E C K >-------------------------------------------- | |||
Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the | Check archive.org URLs to make sure they at least look like they are pointing at valid archives and not to the | ||
| Line 2,210: | Line 2,318: | ||
else | else | ||
path, timestamp, flag = url:match('//web%.archive%.org/([^%d]*)(%d+)([^/]*)/'); -- split out some of the URL parts for evaluation | 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 | |||
if not | err_msg = cfg.err_msg_supl.timestamp; | ||
elseif 14 ~= timestamp:len() then -- path and flag optional, must have 14-digit timestamp here | |||
err_msg = cfg.err_msg_supl.timestamp; | err_msg = cfg.err_msg_supl.timestamp; | ||
if '*' ~= flag then | if '*' ~= flag then | ||
url=url:gsub ('(//web%.archive%.org/[^%d]*%d | 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 utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element | elseif utilities.is_set (path) and 'web/' ~= path then -- older archive URLs do not have the extra 'web/' path element | ||
| Line 2,227: | Line 2,340: | ||
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 | |||
if is_preview_mode then | |||
return url, date; -- preview mode so return ArchiveURL and ArchiveDate | |||
else | |||
return '', ''; -- return empty strings for ArchiveURL and ArchiveDate | return '', ''; -- return empty strings for ArchiveURL and ArchiveDate | ||
end | end | ||
end | end | ||
| Line 2,255: | Line 2,369: | ||
return param_val; -- and done | return param_val; -- and done | ||
end | end | ||
| Line 2,286: | Line 2,374: | ||
--[[--------------------------< I S _ A R C H I V E D _ C O P Y >---------------------------------------------- | --[[--------------------------< I S _ A R C H I V E D _ C O P Y >---------------------------------------------- | ||
compares |title= to 'Archived copy' ( | compares |title= to 'Archived copy' (placeholder added by bots that can't find proper title); if matches, return true; nil else | ||
]] | ]] | ||
| Line 2,308: | Line 2,396: | ||
]] | ]] | ||
local function citation0( config, args) | local function citation0( config, args ) | ||
--[[ | --[[ | ||
Load Input Parameters | Load Input Parameters | ||
| Line 2,318: | Line 2,406: | ||
-- Pick out the relevant fields from the arguments. Different citation templates | -- Pick out the relevant fields from the arguments. Different citation templates | ||
-- define different field names for the same underlying things. | -- define different field names for the same underlying things. | ||
local 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 NameListStyle = is_valid_parameter_value (A['NameListStyle'], A:ORIGIN('NameListStyle'), cfg.keywords_lists['name-list-style'], ''); | ||
local Collaboration = A['Collaboration']; | local Collaboration = A['Collaboration']; | ||
| Line 2,333: | Line 2,418: | ||
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'; | 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 | ||
| Line 2,345: | Line 2,430: | ||
end | end | ||
end | end | ||
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= | ||
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'; | 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= | ||
end | end | ||
end | end | ||
local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases | local Chapter = A['Chapter']; -- done here so that we have access to |contribution= from |chapter= aliases | ||
local Chapter_origin = A:ORIGIN ('Chapter'); | local Chapter_origin = A:ORIGIN ('Chapter'); | ||
local Contribution; -- because contribution is required for contributor(s) | local Contribution; -- because contribution is required for contributor(s) | ||
if 'contribution' == | if 'contribution' == Chapter_origin then | ||
Contribution = | Contribution = Chapter; -- get the name of the contribution | ||
end | end | ||
local c = {}; -- contributors list from |contributor-lastn= / contributor-firstn= pairs | |||
if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites | if utilities.in_array (config.CitationClass, {"book", "citation"}) and not utilities.is_set (A['Periodical']) then -- |contributor= and |contribution= only supported in book cites | ||
c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= | c = extract_names (args, 'ContributorList'); -- fetch contributor list from |contributorn= / |contributor-lastn=, -firstn=, -linkn=, -maskn= | ||
| Line 2,390: | Line 2,457: | ||
if 0 < #c then | if 0 < #c then | ||
if not utilities.is_set (Contribution) then -- |contributor= requires |contribution= | 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 | ||
| Line 2,400: | Line 2,467: | ||
else -- if not a book cite | else -- if not a book cite | ||
if utilities.select_one (args, cfg.aliases['ContributorList-Last'], 'err_redundant_parameters', 1 ) then -- are there contributor name list parameters? | 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 | ||
local Title = A['Title']; | local Title = A['Title']; | ||
local TitleLink = A['TitleLink']; | local TitleLink = A['TitleLink']; | ||
local auto_select = ''; -- default is auto | local auto_select = ''; -- default is auto | ||
local accept_link; | local accept_link; | ||
TitleLink, accept_link = utilities.has_accept_as_written(TitleLink, true); -- test for accept-this-as-written markup | TitleLink, accept_link = utilities.has_accept_as_written (TitleLink, true); -- test for accept-this-as-written markup | ||
if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords | if (not accept_link) and utilities.in_array (TitleLink, {'none', 'pmc', 'doi'}) then -- check for special keywords | ||
auto_select = TitleLink; -- remember selection for later | auto_select = TitleLink; -- remember selection for later | ||
TitleLink = ''; -- treat as if |title-link= would have been empty | TitleLink = ''; -- treat as if |title-link= would have been empty | ||
end | end | ||
| Line 2,437: | Line 2,486: | ||
local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used | local Section = ''; -- {{cite map}} only; preset to empty string for concatenation if not used | ||
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}} | |||
Chapter = ''; -- unset for now; will be reset later from |map= if present | |||
end | |||
local Periodical = A['Periodical']; | |||
local Periodical_origin = ''; | |||
local Periodical = A['Periodical']; | |||
local Periodical_origin = ''; | |||
if utilities.is_set (Periodical) then | if utilities.is_set (Periodical) then | ||
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter | Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter | ||
| Line 2,474: | Line 2,498: | ||
Periodical, i = utilities.strip_apostrophe_markup (Periodical); -- strip apostrophe markup so that metadata isn't contaminated | 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 | if i then -- non-zero when markup was stripped so emit an error message | ||
utilities.set_message ('err_apostrophe_markup', {Periodical_origin}); | |||
end | end | ||
end | end | ||
if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} | if 'mailinglist' == config.CitationClass then -- special case for {{cite mailing list}} | ||
if utilities.is_set (Periodical) and utilities.is_set (A ['MailingList']) then -- both set emit an error | 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) .. ' and ' .. utilities.wrap_style ('parameter', 'mailinglist')}); | |||
end | end | ||
| Line 2,488: | Line 2,512: | ||
local ScriptPeriodical = A['ScriptPeriodical']; | local ScriptPeriodical = A['ScriptPeriodical']; | ||
-- web and news not tested for now because of | -- web and news not tested for now because of | ||
| Line 2,496: | Line 2,519: | ||
local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message | local p = {['journal'] = 'journal', ['magazine'] = 'magazine'}; -- for error message | ||
if p[config.CitationClass] then | if p[config.CitationClass] then | ||
utilities.set_message ('err_missing_periodical', {config.CitationClass, p[config.CitationClass]}); | |||
end | end | ||
end | end | ||
local Volume; | local Volume; | ||
local | local ScriptPeriodical_origin = A:ORIGIN('ScriptPeriodical'); | ||
if 'citation' == config.CitationClass then | if 'citation' == config.CitationClass then | ||
if utilities.is_set (Periodical) then | if utilities.is_set (Periodical) then | ||
if not utilities.in_array (Periodical_origin, | 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' | Volume = A['Volume']; -- but does for all other 'periodicals' | ||
end | end | ||
| Line 2,526: | Line 2,540: | ||
Volume = A['Volume']; | Volume = A['Volume']; | ||
end | end | ||
extra_text_in_vol_iss_check (Volume, A:ORIGIN ('Volume'), 'v'); | |||
local Issue; | |||
if 'citation' == config.CitationClass then | if 'citation' == config.CitationClass then | ||
if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, | 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 | ||
utilities. | Issue = utilities.hyphen_to_dash (A['Issue']); | ||
end | 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 | 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 | if not (utilities.in_array (config.CitationClass, {'conference', 'map', 'citation'}) and not (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical))) then | ||
Issue = hyphen_to_dash (A['Issue']); | Issue = utilities.hyphen_to_dash (A['Issue']); | ||
end | end | ||
end | end | ||
extra_text_in_vol_iss_check (Issue, A:ORIGIN ('Issue'), 'i'); | |||
local | local Page; | ||
local Pages; | |||
local At; | |||
if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then | if not utilities.in_array (config.CitationClass, cfg.templates_not_using_page) then | ||
Page = A['Page']; | Page = A['Page']; | ||
Pages = hyphen_to_dash (A['Pages']); | Pages = utilities.hyphen_to_dash (A['Pages']); | ||
At = A['At']; | At = A['At']; | ||
end | end | ||
| Line 2,555: | Line 2,573: | ||
PublisherName, i = utilities.strip_apostrophe_markup (PublisherName); -- strip apostrophe markup so that metadata isn't contaminated; publisher is never italicized | 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 | 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 | end | ||
| Line 2,564: | Line 2,582: | ||
if 'newsgroup' == config.CitationClass then | if 'newsgroup' == config.CitationClass then | ||
if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup | if utilities.is_set (PublisherName) then -- general use parameter |publisher= not allowed in cite newsgroup | ||
utilities.set_message ('err_parameter_ignored', {PublisherName_origin}); | |||
end | end | ||
| Line 2,573: | Line 2,588: | ||
end | end | ||
local URL = A['URL']; -- TODO: better way to do this for URL, ChapterURL, and MapURL? | |||
local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); | local UrlAccess = is_valid_parameter_value (A['UrlAccess'], A:ORIGIN('UrlAccess'), cfg.keywords_lists['url-access'], nil); | ||
if not utilities.is_set (URL) and utilities.is_set (UrlAccess) then | |||
UrlAccess = nil; | |||
utilities.set_message ('err_param_access_requires_param', 'url'); | |||
end | |||
local ChapterURL = A['ChapterURL']; | |||
local ChapterUrlAccess = is_valid_parameter_value (A['ChapterUrlAccess'], A:ORIGIN('ChapterUrlAccess'), cfg.keywords_lists['url-access'], nil); | 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 | if not utilities.is_set (ChapterURL) and utilities.is_set (ChapterUrlAccess) then | ||
ChapterUrlAccess = nil; | ChapterUrlAccess = nil; | ||
utilities.set_message ('err_param_access_requires_param', {A:ORIGIN('ChapterUrlAccess'):gsub ('%-access', '')}); | |||
end | end | ||
| Line 2,588: | Line 2,606: | ||
if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then | if not utilities.is_set (A['MapURL']) and utilities.is_set (MapUrlAccess) then | ||
MapUrlAccess = nil; | MapUrlAccess = nil; | ||
utilities.set_message ('err_param_access_requires_param', {'map-url'}); | |||
end | end | ||
local | local this_page = mw.title.getCurrentTitle(); -- also used for COinS and for language | ||
local | local no_tracking_cats = is_valid_parameter_value (A['NoTracking'], A:ORIGIN('NoTracking'), cfg.keywords_lists['yes_true_y'], nil); | ||
-- check this page to see if it is in one of the namespaces that cs1 is not supposed to add to the error categories | |||
if not utilities.is_set (no_tracking_cats) then -- ignore if we are already not going to categorize this page | |||
if utilities.in_array (this_page.nsText, cfg.uncategorized_namespaces) then | |||
no_tracking_cats = "true"; -- set no_tracking_cats | |||
end | |||
for _, v in ipairs (cfg.uncategorized_subpages) do -- cycle through page name patterns | |||
if this_page.text:match (v) then -- test page name against each pattern | |||
no_tracking_cats = "true"; -- set no_tracking_cats | |||
break; -- bail out if one is found | |||
end | |||
end | |||
end | |||
-- 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 | local coins_pages; | ||
Page, Pages, At, coins_pages = insource_loc_get (Page, A:ORIGIN('Page'), Pages, A:ORIGIN('Pages'), At); | |||
local | local NoPP = is_valid_parameter_value (A['NoPP'], A:ORIGIN('NoPP'), cfg.keywords_lists['yes_true_y'], nil); | ||
if utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- both |publication-place= and |place= (|location=) allowed if different | |||
utilities.add_prop_cat ('location-test'); -- add property cat to evaluate how often PublicationPlace and Place are used together | |||
if PublicationPlace == Place then | |||
Place = ''; -- unset; don't need both if they are the same | |||
end | |||
elseif not utilities.is_set (PublicationPlace) and utilities.is_set (Place) then -- when only |place= (|location=) is set ... | |||
PublicationPlace = Place; -- promote |place= (|location=) to |publication-place | |||
end | end | ||
if PublicationPlace == Place then Place = ''; end -- don't need both if they are the same | |||
if | |||
local URL_origin = A:ORIGIN('URL'); -- get name of parameter that holds URL | |||
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']; | |||
local | |||
local | |||
--[[ | --[[ | ||
| Line 2,698: | Line 2,672: | ||
if utilities.is_set (Encyclopedia) then -- emit error message when Encyclopedia set but template is other than {{cite encyclopedia}} or {{citation}} | 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 | 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 | Encyclopedia = nil; -- unset because not supported by this template | ||
end | end | ||
| Line 2,704: | Line 2,678: | ||
if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then | if ('encyclopaedia' == config.CitationClass) or ('citation' == config.CitationClass and utilities.is_set (Encyclopedia)) then | ||
if utilities.is_set (Periodical) and utilities.is_set (Encyclopedia) then -- when both set emit an error | 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')) .. ' and ' .. utilities.wrap_style ('parameter', Periodical_origin)}); | |||
end | end | ||
| Line 2,721: | Line 2,695: | ||
TransChapter = TransTitle; | TransChapter = TransTitle; | ||
ChapterURL = URL; | ChapterURL = URL; | ||
ChapterURL_origin = | ChapterURL_origin = URL_origin; | ||
ChapterUrlAccess = UrlAccess; | ChapterUrlAccess = UrlAccess; | ||
| Line 2,737: | Line 2,711: | ||
ScriptTitle = ''; | ScriptTitle = ''; | ||
end | end | ||
elseif utilities.is_set (Chapter) then -- |title= not set | elseif utilities.is_set (Chapter) or utilities.is_set (ScriptChapter) then -- |title= not set | ||
Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= | Title = Periodical; -- |encyclopedia= set and |article= set so map |encyclopedia= to |title= | ||
Periodical = ''; -- redundant so unset | Periodical = ''; -- redundant so unset | ||
| Line 2,745: | Line 2,719: | ||
-- special case for cite techreport. | -- 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 utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' | if utilities.is_set (A['Number']) then -- cite techreport uses 'number', which other citations alias to 'issue' | ||
| Line 2,750: | Line 2,725: | ||
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') .. ' and ' .. utilities.wrap_style ('parameter', 'number')}); | |||
end | end | ||
end | end | ||
| Line 2,756: | Line 2,731: | ||
-- 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 utilities.is_set (BookTitle) then | if utilities.is_set (BookTitle) then | ||
| Line 2,777: | Line 2,756: | ||
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 2,784: | Line 2,770: | ||
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 | 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') .. ' and ' .. utilities.wrap_style ('parameter', Chapter_origin)}); -- add error message | |||
end | end | ||
Chapter = A['Map']; | Chapter = A['Map']; | ||
| Line 2,809: | Line 2,795: | ||
-- 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 SeriesLink = A['SeriesLink']; | local SeriesLink = A['SeriesLink']; | ||
| Line 2,826: | Line 2,813: | ||
local SeriesNumber = A['SeriesNumber']; | local SeriesNumber = A['SeriesNumber']; | ||
if utilities.is_set (Season) and utilities.is_set (SeriesNumber) then -- these are mutually exclusive so if both are set | 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') .. ' and ' .. utilities.wrap_style ('parameter', 'seriesno')}); -- add error message | |||
SeriesNumber = ''; -- unset; prefer |season= over |seriesno= | SeriesNumber = ''; -- unset; prefer |season= over |seriesno= | ||
end | end | ||
| Line 2,843: | Line 2,830: | ||
ChapterURL = URL; | ChapterURL = URL; | ||
ChapterUrlAccess = UrlAccess; | ChapterUrlAccess = UrlAccess; | ||
ChapterURL_origin = | ChapterURL_origin = URL_origin; | ||
ChapterFormat = Format; | |||
Title = Series; -- promote series to title | Title = Series; -- promote series to title | ||
TitleLink = SeriesLink; | TitleLink = SeriesLink; | ||
| Line 2,857: | Line 2,845: | ||
TransTitle = ''; | TransTitle = ''; | ||
ScriptTitle = ''; | ScriptTitle = ''; | ||
Format = ''; | |||
else -- now oddities that are cite serial | else -- now oddities that are cite serial | ||
| Line 2,870: | Line 2,859: | ||
-- handle type parameter for those CS1 citations that have default values | -- handle type parameter for those CS1 citations that have default values | ||
if utilities.in_array (config.CitationClass, { | local TitleType = A['TitleType']; | ||
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 utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis | if utilities.is_set (Degree) and "Thesis" == TitleType then -- special case for cite thesis | ||
| Line 2,883: | Line 2,874: | ||
-- 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 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 | if not utilities.is_set (Date) then | ||
| Line 2,907: | Line 2,901: | ||
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 = ''; | ||
| Line 2,926: | Line 2,942: | ||
-- 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 | ||
utilities.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 utilities.is_set (Year) and utilities.is_set (Date) then -- both |date= and |year= not normally needed; | 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); | |||
end | end | ||
| Line 2,951: | Line 2,962: | ||
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 | |||
utilities.set_message ('maint_date_auto_xlated'); -- add maint cat | |||
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 | ||
| Line 2,967: | Line 2,977: | ||
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_coins = | local ID_list = {}; -- sequence table of rendered identifiers | ||
local ID_list_coins = {}; -- table of identifiers and their values from args; key is same as cfg.id_handlers's key | |||
local Class = A['Class']; -- arxiv class identifier | |||
local | |||
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. | -- Account for the oddities that are {{cite arxiv}}, {{cite biorxiv}}, {{cite citeseerx}}, {{cite ssrn}}, before generation of COinS data. | ||
if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then | if utilities.in_array (config.CitationClass, whitelist.preprint_template_list) then | ||
if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates | if not utilities.is_set (ID_list_coins[config.CitationClass:upper()]) then -- |arxiv= or |eprint= required for cite arxiv; |biorxiv= & |citeseerx= required for their templates | ||
utilities.set_message ('err_' .. config.CitationClass .. '_missing'); -- add error message | |||
end | end | ||
| Line 2,990: | Line 3,005: | ||
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 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 | 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 = 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= | 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 | 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 = 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= | 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 | elseif identifiers.auto_link_urls['doi'] then -- auto-select DOI | ||
URL = identifiers.auto_link_urls['doi']; | URL = identifiers.auto_link_urls['doi']; | ||
URL_origin = cfg.id_handlers['DOI'].parameters[1]; | URL_origin = cfg.id_handlers['DOI'].parameters[1]; | ||
| Line 3,003: | Line 3,018: | ||
end | end | ||
if utilities.is_set (URL) | if utilities.is_set (URL) then -- set when using an identifier-created URL | ||
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 | |||
AccessDate = ''; -- unset | |||
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 3,012: | Line 3,034: | ||
-- 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 utilities.is_set (Title) and not utilities.is_set (TransTitle) and not utilities.is_set (ScriptTitle) then -- has special case for cite episode | ||
utilities.set_message ('err_citation_missing_title', {'episode' == config.CitationClass and 'series' or 'title'}); | |||
end | end | ||
| Line 3,022: | Line 3,044: | ||
utilities.set_message ('maint_untitled'); -- add maint cat | utilities.set_message ('maint_untitled'); -- add maint cat | ||
end | end | ||
-- 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 3,047: | Line 3,062: | ||
coins_author = c; -- use that instead | coins_author = c; -- use that instead | ||
end | end | ||
local QuotePage = A['QuotePage']; | |||
local QuotePages = utilities.hyphen_to_dash (A['QuotePages']); | |||
-- this is the function call to COinS() | -- this is the function call to COinS() | ||
| Line 3,052: | Line 3,070: | ||
['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata | ['Periodical'] = utilities.strip_apostrophe_markup (Periodical), -- no markup in the metadata | ||
['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS | ['Encyclopedia'] = Encyclopedia, -- just a flag; content ignored by ~/COinS | ||
['Chapter'] = metadata.make_coins_title (coins_chapter, ScriptChapter), -- Chapter and ScriptChapter stripped of bold / italic | ['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'] = metadata.make_coins_title (coins_title, ScriptTitle), -- Title and ScriptTitle stripped of bold / italic | ['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; | ||
| Line 3,063: | Line 3,081: | ||
['Volume'] = Volume, | ['Volume'] = Volume, | ||
['Issue'] = Issue, | ['Issue'] = Issue, | ||
['Pages'] = coins_pages or metadata.get_coins_pages (first_set ({Sheet, Sheets, Page, Pages, At}, | ['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 or Newsgroup, -- any apostrophe markup already removed from PublisherName | ['PublisherName'] = PublisherName or Newsgroup, -- any apostrophe markup already removed from PublisherName | ||
| Line 3,082: | Line 3,100: | ||
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. | ||
do | do | ||
local last_first_list; | local last_first_list; | ||
local control = { | local control = { | ||
format = NameListStyle, | 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 | ||
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 = get_display_names (A['DisplayEditors'], #e, 'editors', 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 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 3,114: | Line 3,133: | ||
end | end | ||
do -- now do interviewers | do -- now do interviewers | ||
control.maximum , interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal); | control.maximum, interviewer_etal = get_display_names (A['DisplayInterviewers'], #interviewers_list, 'interviewers', interviewer_etal, A:ORIGIN ('DisplayInterviewers')); | ||
Interviewers = list_people (control, interviewers_list, interviewer_etal); | 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); | control.maximum, translator_etal = get_display_names (A['DisplayTranslators'], #t, 'translators', translator_etal, A:ORIGIN ('DisplayTranslators')); | ||
Translators = list_people (control, t, translator_etal); | 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); | control.maximum, contributor_etal = get_display_names (A['DisplayContributors'], #c, 'contributors', contributor_etal, A:ORIGIN ('DisplayContributors')); | ||
Contributors = list_people (control, c, contributor_etal); | Contributors = list_people (control, c, contributor_etal); | ||
end | end | ||
do -- now do authors | do -- now do authors | ||
control.maximum , author_etal = get_display_names (A['DisplayAuthors'], #a, 'authors', author_etal); | 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 utilities.is_set (Authors) then | if utilities.is_set (Authors) then | ||
| Line 3,146: | Line 3,165: | ||
end | end | ||
local ConferenceFormat = A['ConferenceFormat']; | |||
local ConferenceURL = A['ConferenceURL']; | |||
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'); | ||
-- 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 | ||
| Line 3,163: | Line 3,179: | ||
if utilities.in_array (config.CitationClass, {"web", "podcast", "mailinglist"}) or -- |url= required for cite web, cite podcast, and cite 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= | ('citation' == config.CitationClass and ('website' == Periodical_origin or 'script-website' == ScriptPeriodical_origin)) then -- and required for {{citation}} with |website= or |script-website= | ||
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 utilities.is_set (AccessDate) and not utilities.is_set (ChapterURL) then -- ChapterURL may be set when URL is not set; | 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'); | |||
AccessDate = ''; | AccessDate = ''; | ||
end | end | ||
end | end | ||
local OriginalURL | local UrlStatus = is_valid_parameter_value (A['UrlStatus'], A:ORIGIN('UrlStatus'), cfg.keywords_lists['url-status'], ''); | ||
local OriginalURL | |||
local OriginalURL_origin | |||
local OriginalFormat | |||
local OriginalAccess; | |||
UrlStatus = UrlStatus:lower(); -- used later when assembling archived text | UrlStatus = UrlStatus:lower(); -- used later when assembling archived text | ||
if utilities.is_set ( ArchiveURL ) then | if utilities.is_set ( ArchiveURL ) then | ||
| Line 3,199: | Line 3,219: | ||
UrlAccess = nil; -- restricted access levels do not make sense for archived URLs | 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 | ||
| Line 3,218: | Line 3,240: | ||
if utilities.is_set (chap_param) then -- if we found one | 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 3,258: | Line 3,280: | ||
end | end | ||
if not accept_title then -- <Title> not wrapped in accept-as-written markup | if not accept_title then -- <Title> not wrapped in accept-as-written markup | ||
if '...' == Title:sub (-3) then -- if ellipsis is the last three characters of |title= | 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 | Title = Title:gsub ('(%.%.%.)%.+$', '%1'); -- limit the number of dots to three | ||
| Line 3,270: | Line 3,292: | ||
end | end | ||
if | if is_generic ('generic_titles', Title) then | ||
utilities.set_message ('err_generic_title'); -- set an error message | |||
end | end | ||
end | end | ||
| Line 3,282: | Line 3,304: | ||
Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | ||
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); | TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); | ||
elseif plain_title or ('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, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | Title = script_concatenate (Title, ScriptTitle, 'script-title'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after title is wrapped | ||
TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); | TransTitle = utilities.wrap_style ('trans-quoted-title', TransTitle ); -- for cite report, use this form for trans-title | ||
else | else | ||
Title = utilities.wrap_style ('italic-title', Title); | Title = utilities.wrap_style ('italic-title', Title); | ||
| Line 3,291: | Line 3,313: | ||
end | end | ||
if utilities.is_set (TransTitle) then | if utilities.is_set (TransTitle) then | ||
if utilities.is_set (Title) then | if utilities.is_set (Title) then | ||
TransTitle = " " .. TransTitle; | TransTitle = " " .. TransTitle; | ||
else | else | ||
utilities.set_message ('err_trans_missing_title', {'title'}); | |||
end | end | ||
end | end | ||
| Line 3,302: | Line 3,323: | ||
if utilities.is_set (Title) then -- TODO: is this the right place to be making Wikisource URLs? | 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 | 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 | TitleLink = ''; -- unset | ||
end | end | ||
if not utilities.is_set (TitleLink) and utilities.is_set (URL) then | if not utilities.is_set (TitleLink) and utilities.is_set (URL) then | ||
Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle | Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. Format; | ||
URL = ''; -- unset these because no longer needed | URL = ''; -- unset these because no longer needed | ||
Format = ""; | Format = ""; | ||
| Line 3,316: | Line 3,337: | ||
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 = 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], TitleLink, Title}); | ||
Title = Title .. TransTitle | Title = Title .. TransTitle; | ||
else | else | ||
Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle | Title = utilities.make_wikilink (TitleLink, Title) .. TransTitle; | ||
end | 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) | 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) | ||
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 | 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 | if ws_url then | ||
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup | 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 = 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 = utilities.substitute (cfg.presentation['interwiki-icon'], {cfg.presentation['class-wikisource'], L, Title}); | ||
Title = Title .. TransTitle | Title = Title .. TransTitle; | ||
else | else | ||
Title = Title .. TransTitle | Title = Title .. TransTitle; | ||
end | end | ||
end | end | ||
else | else | ||
Title = TransTitle | Title = TransTitle; | ||
end | end | ||
| Line 3,340: | Line 3,361: | ||
end | end | ||
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL | |||
if utilities.is_set (Conference) then | if utilities.is_set (Conference) then | ||
if utilities.is_set (ConferenceURL) then | if utilities.is_set (ConferenceURL) then | ||
| Line 3,349: | Line 3,371: | ||
end | end | ||
local Position = ''; | |||
if not utilities.is_set (Position) then | if not utilities.is_set (Position) then | ||
local Minutes = A['Minutes']; | local Minutes = A['Minutes']; | ||
| Line 3,354: | Line 3,377: | ||
if utilities.is_set (Minutes) then | if utilities.is_set (Minutes) then | ||
if utilities.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') .. ' and ' .. utilities.wrap_style ('parameter', 'time')}); | |||
end | end | ||
Position = " " .. Minutes .. " " .. cfg.messages['minutes']; | Position = " " .. Minutes .. " " .. cfg.messages['minutes']; | ||
| Line 3,395: | Line 3,418: | ||
end | end | ||
if utilities.is_set ( | local Others = A['Others']; | ||
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= | |||
if config.CitationClass == "AV-media-notes" | |||
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now | |||
utilities.set_message ('maint_others_avm') | |||
else | |||
utilities.set_message ('maint_others'); | |||
end | |||
end | end | ||
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | ||
| Line 3,413: | Line 3,436: | ||
end | end | ||
local TitleNote = A['TitleNote']; | |||
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; | TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; | ||
if utilities.is_set (Edition) then | if utilities.is_set (Edition) then | ||
if Edition:match ('%f[%a][Ee]d%.?$') or Edition:match ('%f[%a][Ee]dition$') 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. | ||
utilities.set_message (' | utilities.set_message ('err_extra_text_edition'); -- add error message | ||
end | end | ||
Edition = " " .. wrap_msg ('edition', Edition); | Edition = " " .. wrap_msg ('edition', Edition); | ||
| Line 3,424: | Line 3,448: | ||
Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum | Series = utilities.is_set (Series) and wrap_msg ('series', {sepc, Series}) or ""; -- not the same as SeriesNum | ||
local Agency = A['Agency']; | |||
Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or ""; | Agency = utilities.is_set (Agency) and wrap_msg ('agency', {sepc, Agency}) or ""; | ||
Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); | Volume = format_volume_issue (Volume, Issue, config.CitationClass, Periodical_origin, sepc, use_lowercase); | ||
if utilities.is_set (AccessDate) then | if utilities.is_set (AccessDate) then | ||
| Line 3,442: | Line 3,463: | ||
if utilities.is_set (ID) then ID = sepc .. " " .. ID; end | if utilities.is_set (ID) then ID = sepc .. " " .. ID; end | ||
local Docket = A['Docket']; | |||
if "thesis" == config.CitationClass and utilities.is_set (Docket) then | if "thesis" == config.CitationClass and utilities.is_set (Docket) then | ||
ID = sepc .. " Docket " .. Docket .. ID; | ID = sepc .. " Docket " .. Docket .. ID; | ||
| Line 3,453: | Line 3,476: | ||
end | end | ||
local Quote = A['Quote']; | |||
local TransQuote = A['TransQuote']; | |||
local ScriptQuote = A['ScriptQuote']; | |||
if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then | if utilities.is_set (Quote) or utilities.is_set (TransQuote) or utilities.is_set (ScriptQuote) then | ||
| Line 3,461: | Line 3,487: | ||
end | end | ||
Quote = utilities.wrap_style ('quoted-text', Quote ); | Quote = utilities.wrap_style ('quoted-text', Quote ); -- wrap in <q>...</q> tags | ||
if utilities.is_set (ScriptQuote) then | 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 | Quote = script_concatenate (Quote, ScriptQuote, 'script-quote'); -- <bdi> tags, lang attribute, categorization, etc.; must be done after quote is wrapped | ||
end | end | ||
| Line 3,477: | Line 3,503: | ||
local quote_prefix = ''; | local quote_prefix = ''; | ||
if utilities.is_set (QuotePage) then | 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 | if not NoPP then | ||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', ''; | quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePage}), '', '', ''; | ||
| Line 3,483: | Line 3,510: | ||
end | end | ||
elseif utilities.is_set (QuotePages) then | 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 | if tonumber(QuotePages) ~= nil and not NoPP then -- if only digits, assume single page | ||
quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', ''; | quote_prefix = utilities.substitute (cfg.messages['p-prefix'], {sepc, QuotePages}), '', ''; | ||
| Line 3,500: | Line 3,528: | ||
end | end | ||
local Archived | -- We check length of PostScript here because it will have been nuked by | ||
-- the quote parameters. We'd otherwise emit a message even if there wasn't | |||
-- a displayed postscript. | |||
-- TODO: Should the max size (1) be configurable? | |||
-- 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 | if utilities.is_set (ArchiveURL) then | ||
local arch_text; | local arch_text; | ||
if not utilities.is_set (ArchiveDate) then | if not utilities.is_set (ArchiveDate) then | ||
utilities.set_message ('err_archive_missing_date'); | |||
ArchiveDate = ''; -- empty string for concatenation | |||
end | end | ||
if "live" == UrlStatus then | if "live" == UrlStatus then | ||
arch_text = cfg.messages['archived']; | arch_text = cfg.messages['archived']; | ||
if sepc ~= "." then arch_text = arch_text:lower() end | if sepc ~= "." then arch_text = arch_text:lower() end | ||
Archived = sepc .. | if utilities.is_set (ArchiveDate) then | ||
Archived = sepc .. ' ' .. utilities.substitute ( cfg.messages['archived-live'], | |||
{external_link( ArchiveURL, arch_text, A:ORIGIN('ArchiveURL'), nil) .. ArchiveFormat, ArchiveDate } ); | |||
else | |||
Archived = ''; | |||
end | |||
if not utilities.is_set (OriginalURL) then | if not utilities.is_set (OriginalURL) then | ||
utilities.set_message ('err_archive_missing_url'); | |||
Archived = ''; -- empty string for concatenation | |||
end | end | ||
elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' | elseif utilities.is_set (OriginalURL) then -- UrlStatus is empty, 'dead', 'unfit', 'usurped', 'bot: unknown' | ||
| Line 3,518: | Line 3,561: | ||
arch_text = cfg.messages['archived-unfit']; | arch_text = cfg.messages['archived-unfit']; | ||
if sepc ~= "." then arch_text = arch_text:lower() end | if sepc ~= "." then arch_text = arch_text:lower() end | ||
Archived = sepc .. | Archived = sepc .. ' ' .. arch_text .. ArchiveDate; -- format already styled | ||
if 'bot: unknown' == UrlStatus then | if 'bot: unknown' == UrlStatus then | ||
utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added | utilities.set_message ('maint_bot_unknown'); -- and add a category if not already added | ||
| Line 3,527: | Line 3,570: | ||
arch_text = cfg.messages['archived-dead']; | arch_text = cfg.messages['archived-dead']; | ||
if sepc ~= "." then arch_text = arch_text:lower() end | if sepc ~= "." then arch_text = arch_text:lower() end | ||
Archived = sepc .. " " .. utilities.substitute ( arch_text, | 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 | end | ||
else -- OriginalUrl not set | else -- OriginalUrl not set | ||
arch_text = cfg.messages['archived-missing']; | 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 = ''; -- empty string for concatenation | |||
end | end | ||
elseif utilities.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']; | |||
local LayURL = A['LayURL']; | |||
local LayFormat = A['LayFormat']; | |||
LayFormat = style_format (LayFormat, LayURL, 'lay-format', 'lay-url'); | |||
if utilities.is_set (LayURL) then | if utilities.is_set (LayURL) then | ||
if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end | if utilities.is_set (LayDate) then LayDate = " (" .. LayDate .. ")" end | ||
| Line 3,559: | Line 3,610: | ||
end | end | ||
local TranscriptURL = A['TranscriptURL'] | |||
local TranscriptFormat = A['TranscriptFormat']; | |||
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 (Transcript) then | ||
if utilities.is_set (TranscriptURL) then | if utilities.is_set (TranscriptURL) then | ||
| Line 3,584: | Line 3,640: | ||
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 (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then | if (utilities.is_set (Periodical) or utilities.is_set (ScriptPeriodical) or utilities.is_set (TransPeriodical)) then | ||
| Line 3,591: | Line 3,649: | ||
Periodical = format_periodical (ScriptPeriodical, ScriptPeriodical_origin, Periodical, TransPeriodical, TransPeriodical_origin); | 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 3,598: | Line 3,666: | ||
]] | ]] | ||
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 utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter | if utilities.is_set (Periodical) then -- if Periodical, perhaps because of an included |website= or |journal= parameter | ||
if utilities.is_set (Conference) then -- and if |event= is set | if utilities.is_set (Conference) then -- and if |event= is set | ||
| Line 3,647: | Line 3,717: | ||
end | end | ||
local Via = A['Via']; | |||
Via = utilities.is_set (Via) and wrap_msg ('via', Via) or ''; | |||
local idcommon; | local idcommon; | ||
if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript | if 'audio-visual' == config.CitationClass or 'episode' == config.CitationClass then -- special case for cite AV media & cite episode position transcript | ||
| Line 3,657: | Line 3,729: | ||
local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; | local pgtext = Position .. Sheet .. Sheets .. Page .. Pages .. At; | ||
local OrigDate = A['OrigDate']; | |||
OrigDate = utilities.is_set (OrigDate) and wrap_msg ('origdate', OrigDate) or ''; | |||
if utilities.is_set (Date) then | if utilities.is_set (Date) then | ||
if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set | if utilities.is_set (Authors) or utilities.is_set (Editors) then -- date follows authors or editors when authors not set | ||
| Line 3,726: | Line 3,800: | ||
if utilities.is_set (PostScript) and PostScript ~= sepc then | if utilities.is_set (PostScript) and PostScript ~= sepc then | ||
text = safe_join( {text, sepc}, sepc ); --Deals with italics, spaces, etc. | 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 | ||
| Line 3,732: | Line 3,806: | ||
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); | |||
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 'none' ~= cfg.keywords_xlate[(Ref and Ref:lower()) or ''] then | |||
local namelist_t = {}; -- holds selected contributor, author, editor name list | |||
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation | |||
if | |||
local | |||
if #c > 0 then -- if there is a contributor list | |||
namelist_t = c; -- select it | |||
elseif #a > 0 then -- or an author list | |||
namelist_t = a; | |||
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. | z.error_cats_t = {}; -- blank the categories list | ||
text = utilities.set_message ('err_empty_citation'); | z.error_msgs_t = {}; -- blank the error messages list | ||
OCinSoutput = nil; -- blank the metadata string | |||
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 utilities.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 | ||
table.insert ( | if OCinSoutput then -- blanked when citation is 'empty' so don't bother to add boilerplate metadata span | ||
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); | |||
local template_link = '[[Template:' .. template_name .. '|' .. template_name .. ']]'; | |||
local msg_prefix = '<code class="cs1-code">{{' .. template_link .. '}}</code>: '; | |||
if 0 ~= #z.error_msgs_t then | |||
mw.addWarning (utilities.substitute (cfg.messages.warning_msg_e, template_link)); | |||
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 | |||
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 | |||
for | if v:find ('cs1-visible-error', 1, true) then -- look for the visible error class name | ||
if | 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 0 ~= #z. | if 0 ~= #z.maint_cats_t then | ||
local | mw.addWarning (utilities.substitute (cfg.messages.warning_msg_m, template_link)); | ||
for _, v in ipairs( z. | |||
table.sort (z.maint_cats_t); -- sort the maintenance messages list | |||
table.insert ( | |||
local maint_msgs_t = {}; -- here we collect all of the maint messages | |||
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 | |||
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 | end | ||
table.insert ( | 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 | if not no_tracking_cats then | ||
for _, v in ipairs( z. | for _, v in ipairs (z.error_cats_t) do -- append error categories | ||
table.insert ( | table.insert (render_t, utilities.substitute (cfg.messages['cat wikilink'], v)); | ||
end | end | ||
for _, v in ipairs( z. | 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( z. | 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 | ||
| Line 3,841: | Line 3,930: | ||
if true == state then return true; end -- valid actively supported parameter | if true == state then return true; end -- valid actively supported parameter | ||
if false == state then | if false == state then | ||
if empty then return nil; end -- deprecated | if empty then return nil; end -- empty deprecated parameters are treated as unknowns | ||
deprecated_parameter (name); -- parameter is deprecated but still supported | deprecated_parameter (name); -- parameter is deprecated but still supported | ||
return true; | |||
end | |||
if 'tracked' == state then | |||
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; | return true; | ||
end | end | ||
| Line 3,900: | Line 3,994: | ||
if prefix and cfg.inter_wiki_map[prefix:lower()] then -- if prefix is in the map, needs preceding colon so | 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 | _, value, _ = utilities.is_wikilink (value); -- extract label portion from wikilink | ||
end | end | ||
| Line 3,927: | Line 4,021: | ||
capture = value:match ('%s+(%a[%w%-]+)%s*=') or value:match ('^(%a[%w%-]+)%s*='); -- find and categorize parameters with possible missing pipes | 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 | if capture and validate (capture) then -- if the capture is a valid parameter name | ||
utilities.set_message ('err_missing_pipe', parameter); | |||
end | end | ||
end | end | ||
| Line 3,949: | Line 4,043: | ||
if value:match ('[,;:]$') then | if value:match ('[,;:]$') 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 | utilities.set_message ('maint_extra_punct'); -- has extraneous punctuation; add maint cat | ||
end | |||
end | |||
--[[--------------------------< H A S _ E X T R A N E O U S _ U R L >------------------------------------------ | |||
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 | ||
end | end | ||
| Line 3,962: | Line 4,076: | ||
local function citation(frame) | local function citation(frame) | ||
Frame = frame; -- save a copy in case we need to display an error message in preview mode | Frame = frame; -- save a copy in case we need to display an error message in preview mode | ||
local sandbox = '/sandbox' -- i18n: replace this rvalue with the name that your wiki uses to identify sandbox subpages | |||
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 pframe = frame:getParent() | ||
local styles; | 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 | utilities.set_selected_modules (cfg); -- so that functions in Utilities can see the selected cfg tables | ||
| Line 3,990: | Line 4,097: | ||
z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities | z = utilities.z; -- table of error and category tables in Module:Citation/CS1/Utilities | ||
is_preview_mode = not utilities.is_set (frame:preprocess ('{{REVISIONID}}')); | |||
local args = {}; -- table where we store all of the template's arguments | 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 suggestions = {}; -- table where we store suggestions if we need to loadData them | ||
local error_text | local error_text; -- used as a flag | ||
local config = {}; -- table to store parameters from the module {{#invoke:}} | local config = {}; -- table to store parameters from the module {{#invoke:}} | ||
| Line 4,010: | Line 4,119: | ||
end | end | ||
if not validate( k, config.CitationClass ) then | if not validate( k, config.CitationClass ) then | ||
if type (k) ~= 'string' then -- exclude empty numbered parameters | |||
if type( k ) ~= 'string' then | |||
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( k:lower(), config.CitationClass ) then | 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 | ||
if | if is_sandbox then -- did the {{#invoke:}} use sandbox version? | ||
suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version | suggestions = mw.loadData( 'Module:Citation/CS1/Suggestions/sandbox' ); -- use the sandbox version | ||
else | else | ||
| Line 4,031: | Line 4,138: | ||
param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator) | param = utilities.substitute (param, capture); -- add the capture to the suggested parameter (typically the enumerator) | ||
if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists) | if validate (param, config.CitationClass) then -- validate the suggestion to make sure that the suggestion is supported by this template (necessary for limited parameter lists) | ||
error_text | error_text = utilities.set_message ('err_parameter_ignored_suggest', {k, param}); -- set the suggestion error message | ||
else | else | ||
error_text | error_text = utilities.set_message ('err_parameter_ignored', {k}); -- suggested param not supported by this template | ||
v = ''; -- unset | v = ''; -- unset | ||
end | end | ||
end | end | ||
end | end | ||
if not utilities.is_set (error_text) then -- couldn't match with a pattern, is there an | 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 | ||
end | end | ||
| Line 4,066: | Line 4,170: | ||
if 0 ~= #empty_unknowns then -- create empty unknown error message | if 0 ~= #empty_unknowns then -- create empty unknown error message | ||
utilities.set_message ('err_param_unknown_empty', { | |||
1 == #empty_unknowns and '' or 's', | 1 == #empty_unknowns and '' or 's', | ||
utilities.make_sep_list (#empty_unknowns, empty_unknowns) | utilities.make_sep_list (#empty_unknowns, empty_unknowns) | ||
}); | |||
end | end | ||
local url_param_t = {}; | |||
for k, v in pairs( args ) do | for k, v in pairs( args ) do | ||
| Line 4,079: | Line 4,185: | ||
missing_pipe_check (k, v); -- do we think that there is a parameter that is missing a pipe? | 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 | 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 | ||
return table.concat ({ | 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 | ||
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ | --[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------ | ||