Anonymous user
Module:Citation/CS1: Difference between revisions
hyphen_to_dash() fix;
m (deprecated enumerated parameter error message fix;) |
(hyphen_to_dash() fix;) |
||
| Line 3: | Line 3: | ||
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- | --[[--------------------------< F O R W A R D D E C L A R A T I O N S >-------------------------------------- | ||
each of these counts against the Lua upvalue limit | each of these counts against the Lua upvalue limit | ||
]] | ]] | ||
| Line 18: | Line 16: | ||
local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist | local whitelist = {}; -- table of tables listing valid template parameter names; defined in Module:Citation/CS1/Whitelist | ||
--[[------------------< P A G E S C O P E V A R I A B L E S >--------------- | |||
--[[ | declare variables here that have page-wide scope that are not brought in from | ||
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 | |||
]] | ]] | ||
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_discouraged_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 Frame; -- holds the module's frame table | local Frame; -- holds the module's frame table | ||
--[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ | --[[--------------------------< F I R S T _ S E T >------------------------------------------------------------ | ||
| Line 62: | Line 56: | ||
]] | ]] | ||
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 | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_vancouver', {source, position}, true ) } ); | |||
end | end | ||
| Line 415: | Line 409: | ||
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 | ||
| Line 443: | Line 437: | ||
added_deprecated_cat = true; -- note that we've added this category | added_deprecated_cat = true; -- note that we've added this category | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } ); -- add error message | table.insert( z.message_tail, { utilities.set_message ( 'err_deprecated_params', {name}, true ) } ); -- add error message | ||
end | |||
end | |||
--[[--------------------------< D I S C O U R A G E D _ P A R A M E T E R >------------------------------------ | |||
Categorize and emit an maintenance message when the citation contains one or more discouraged parameters. Only | |||
one error message is emitted regardless of the number of discouraged parameters in the citation. | |||
added_discouraged_cat is a Boolean declared in page scope variables above | |||
]] | |||
local function discouraged_parameter(name) | |||
if not added_discouraged_cat then | |||
added_discouraged_cat = true; -- note that we've added this category | |||
table.insert( z.message_tail, { utilities.set_message ( 'maint_discouraged', {name}, true ) } ); -- add maint message | |||
end | end | ||
end | end | ||
| Line 539: | Line 550: | ||
-- 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? | ||
| Line 600: | Line 611: | ||
--[[ | --[[----------------< 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 655: | ||
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 665: | ||
--[[ | --[[----------------< 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. | ||
]] | ]] | ||
| Line 685: | Line 697: | ||
--[[ | --[[------------------< 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). | |||
]] | ]] | ||
| Line 697: | Line 710: | ||
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 734: | Line 747: | ||
--[[ | --[[----------------< 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 766: | ||
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 774: | ||
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 791: | ||
('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 | ||
table.insert( z.message_tail, { utilities.set_message ( 'err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true ) } ); -- add error message | table.insert (z.message_tail, {utilities.set_message ('err_invisible_char', {err_msg, utilities.wrap_style ('parameter', param), position}, true)}); -- add error message | ||
return; -- and done with this parameter | return; -- and done with this parameter | ||
end | end | ||
end | end | ||
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 822: | ||
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 837: | ||
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 860: | ||
--[[--------------------------< 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 886: | ||
--[[--------------------------< 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 892: | Line 909: | ||
--[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- | --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- | ||
Converts a hyphen to a dash under certain conditions. The hyphen must separate like items; unlike items are | Converts a hyphen to a dash under certain conditions. The hyphen must separate | ||
returned unmodified. These forms are modified: | like items; unlike items are returned unmodified. These forms are modified: | ||
letter - letter (A - B) | letter - letter (A - B) | ||
digit - digit (4-5) | digit - digit (4-5) | ||
digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) | digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) | ||
letterdigit - letterdigit (A1-A5) (an optional separator between letter and digit is supported – a.1-a.5 or a-1-a-5) | letterdigit - letterdigit (A1-A5) (an optional separator between letter and | ||
digitletter - digitletter (5a - 5d) (an optional separator between letter and digit is supported – 5.a-5.d or 5-a-5-d) | digit is supported – a.1-a.5 or a-1-a-5) | ||
digitletter - digitletter (5a - 5d) (an optional separator between letter and | |||
digit is supported – 5.a-5.d or 5-a-5-d) | |||
any other forms are returned unmodified. | any other forms are returned unmodified. | ||
| Line 911: | Line 930: | ||
end | end | ||
local accept; | local accept; -- Boolean | ||
str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split | str = str:gsub ('&[nm]dash;', {['–'] = '–', ['—'] = '—'}); -- replace — and – entities with their characters; semicolon mucks up the text.split | ||
str = str:gsub ('-', '-'); | str = str:gsub ('-', '-'); -- replace HTML numeric entity with hyphen character | ||
str = str:gsub (' ', ' '); | |||
str = str:gsub (' ', ' '); -- replace entity with generic keyboard space character | |||
local out = {}; | local out = {}; | ||
| Line 925: | Line 941: | ||
for _, item in ipairs (list) do -- for each item in the list | for _, item in ipairs (list) do -- for each item in the list | ||
if mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators | item, accept = utilities.has_accept_as_written (item); -- remove accept-this-as-written markup when it wraps all of item | ||
if not accept and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators | |||
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) | if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) | ||
item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter) | item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or -- digitletter hyphen digitletter (optional separator between digit and letter) | ||
| Line 936: | Line 953: | ||
end | end | ||
end | end | ||
table.insert (out, item); -- add the (possibly modified) item to the output table | table.insert (out, item); -- add the (possibly modified) item to the output table | ||
end | end | ||
local temp_str = ''; -- concatenate the output table into a comma separated string | |||
temp_str, accept = utilities.has_accept_as_written (table.concat (out, ', ')); -- remove accept-this-as-written markup when it wraps all of concatenated out | |||
if accept then | |||
temp_str = utilities.has_accept_as_written (str); -- when global markup removed, return original str; do it this way to suppress boolean second return value | |||
return temp_str; | |||
else | |||
return temp_str; -- else, return assembled temp_str | |||
end | |||
end | end | ||
--[[--------------------------< S A F E _ J O I N > | --[[--------------------------< S A F E _ J O I N >----------------------------- | ||
Joins a sequence of strings together while checking for duplicate separation characters. | Joins a sequence of strings together while checking for duplicate separation characters. | ||
| Line 983: | Line 1,006: | ||
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 1,018: | ||
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 1,029: | ||
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 1,044: | ||
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 1,051: | ||
--[[--------------------------< I S _ S U F F I X > | --[[--------------------------< I S _ S U F F I X >----------------------------- | ||
returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9. | returns true is suffix is properly formed Jr, Sr, or ordinal in the range 1–9. | ||
Puncutation not allowed. | |||
]] | ]] | ||
| Line 1,042: | Line 1,066: | ||
--[[ | --[[--------------------< 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 1,082: | ||
[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 1,102: | ||
]] | ]] | ||
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 1,111: | ||
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 1,117: | ||
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 1,128: | ||
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 1,154: | ||
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 1,177: | ||
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 1,186: | ||
--[[--------------------------< 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 1,204: | ||
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 1,209: | ||
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 1,231: | ||
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 1,243: | ||
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 1,263: | ||
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 1,250: | Line 1,284: | ||
end | end | ||
--[[--------------------< M A K E _ C I T E R E F _ I D >----------------------- | |||
Generates a CITEREF anchor ID if we have at least one name or a date. Otherwise | |||
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 | ||
--[[ | --[[---------------------< N A M E _ H A S _ E T A L >-------------------------- | ||
Evaluates the content of name parameters (author, editor, etc.) for variations on the theme of et al. If found, | Evaluates the content of name parameters (author, editor, etc.) for variations on | ||
the et al. is removed, a flag is set to true and the function returns the modified name and the flag. | the theme of et al. If found, the et al. is removed, a flag is set to true and | ||
the function returns the modified name and the flag. | |||
This function never sets the flag to false but returns | This function never sets the flag to false but returns its previous state because | ||
previous passes through this function or by the associated |display-<names>=etal parameter | it may have been set by previous passes through this function or by the associated | ||
|display-<names>=etal parameter | |||
]] | ]] | ||
| Line 1,288: | Line 1,325: | ||
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 1,305: | Line 1,342: | ||
--[[ | --[[---------------------< 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 1,361: | ||
--[[ | --[[-------------------< N A M E _ H A S _ E D _ M A R K U P >------------------ | ||
Evaluates the content of author and editor parameters for extraneous editor annotations: ed, ed., eds, (Ed.), etc. | Evaluates the content of author and editor parameters for extraneous editor annotations: | ||
These | ed, ed., eds, (Ed.), etc. These annotations do not belong in author parameters and | ||
adds the editor markup maintenance category. | are redundant in editor parameters. If found, the function adds the editor markup | ||
maintenance category. | |||
returns nothing | returns nothing | ||
| Line 1,347: | Line 1,386: | ||
--[[ | --[[-----------------< 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 1,398: | ||
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 1,419: | ||
--[[ | --[[------------------------< N A M E _ C H E C K S >--------------------------- | ||
This function calls various name checking functions used to validate the content of the various name-holding | This function calls various name checking functions used to validate the content | ||
parameters. | of the various name-holding parameters. | ||
]] | ]] | ||
| Line 1,385: | Line 1,435: | ||
name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) | name_has_mult_names (last, list_name); -- check for multiple names in the parameter (last only) | ||
name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation | name_has_ed_markup (last, list_name); -- check for extraneous 'editor' annotation | ||
name_is_numeric (last, list_name); -- check for names that are | name_is_numeric (last, list_name); -- check for names that are composed of digits and punctuation | ||
end | end | ||
end | end | ||
| Line 1,392: | Line 1,442: | ||
first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> | first, accept_name = utilities.has_accept_as_written (first); -- remove accept-this-as-written markup when it wraps all of <first> | ||
if not accept_name then | if not accept_name then -- <first> not wrapped in accept-as-written markup | ||
name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation | name_has_ed_markup (first, list_name); -- check for extraneous 'editor' annotation | ||
name_is_numeric (first, list_name); -- check for names that are | name_is_numeric (first, list_name); -- check for names that are composed of digits and punctuation | ||
end | end | ||
end | end | ||
| Line 1,402: | Line 1,452: | ||
--[[ | --[[----------------------< E X T R A C T _ N A M E S >------------------------- | ||
Gets name list from the input arguments | Gets name list from the input arguments | ||
Searches through args in sequential order to find |lastn= and |firstn= parameters (or their aliases), and their matching link and mask parameters. | Searches through args in sequential order to find |lastn= and |firstn= parameters | ||
Stops searching when both |lastn= and |firstn= are not found in args after two sequential attempts: found |last1=, |last2=, and |last3= but doesn't | (or their aliases), and their matching link and mask parameters. Stops searching | ||
find |last4= and |last5= then the search is done. | when both |lastn= and |firstn= are not found in args after two sequential attempts: | ||
found |last1=, |last2=, and |last3= but doesn't find |last4= and |last5= then the | |||
search is done. | |||
This function emits an error message when there is a |firstn= without a matching |lastn=. When there are 'holes' in the list of last names, |last1= and |last3= | This function emits an error message when there is a |firstn= without a matching | ||
are present but |last2= is missing, an error message is emitted. |lastn= is not required to have a matching |firstn=. | |lastn=. When there are 'holes' in the list of last names, |last1= and |last3= | ||
are present but |last2= is missing, an error message is emitted. |lastn= is not | |||
required to have a matching |firstn=. | |||
When an author or editor parameter contains some form of 'et al.', the 'et al.' is stripped from the parameter and a flag (etal) returned | When an author or editor parameter contains some form of 'et al.', the 'et al.' | ||
that will cause list_people() to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps 'et al.' out of the | is stripped from the parameter and a flag (etal) returned that will cause list_people() | ||
template's metadata. When this occurs, | to add the static 'et al.' text from Module:Citation/CS1/Configuration. This keeps | ||
'et al.' out of the template's metadata. When this occurs, an error is emitted. | |||
]] | ]] | ||
| Line 1,472: | Line 1,527: | ||
--[[ | --[[---------------------< G E T _ I S O 6 3 9 _ C O D E >---------------------- | ||
Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. | Validates language names provided in |language= parameter if not an ISO639-1 or 639-2 code. | ||
Returns the language name and associated two- or three-character code. Because case of the source may be incorrect | Returns the language name and associated two- or three-character code. Because | ||
or different from the case that WikiMedia uses, the name comparisons are done in lower case and when a match is | case of the source may be incorrect or different from the case that WikiMedia uses, | ||
found, the Wikimedia version (assumed to be correct) is returned along with the code. When there is no match, we | the name comparisons are done in lower case and when a match is found, the Wikimedia | ||
return the original language name string. | version (assumed to be correct) is returned along with the code. When there is no | ||
match, we return the original language name string. | |||
mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of languages that in some cases may include | mw.language.fetchLanguageNames(<local wiki language>, 'all') returns a list of | ||
extensions. For example, code 'cbk-zam' and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support | languages that in some cases may include extensions. For example, code 'cbk-zam' | ||
code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a 'language' codes per se, rather they | and its associated name 'Chavacano de Zamboanga' (MediaWiki does not support | ||
are used as sub-domain names: cbk-zam.wikipedia.org. | code 'cbk' or name 'Chavacano'. Most (all?) of these languages are not used a | ||
can be found at Template:Citation Style documentation/language/doc | 'language' codes per se, rather they are used as sub-domain names: cbk-zam.wikipedia.org. | ||
A list of language names and codes supported by fetchLanguageNames() can be found | |||
at Template:Citation Style documentation/language/doc | |||
Names that are included in the list will be found if that name is provided in the |language= parameter. For example, | Names that are included in the list will be found if that name is provided in the | ||
if |language=Chavacano de Zamboanga, that name will be found with the associated code 'cbk-zam'. When names are found | |language= parameter. For example, if |language=Chavacano de Zamboanga, that name | ||
and the associated code is not two or three characters, this function returns only the WikiMedia language name. | will be found with the associated code 'cbk-zam'. When names are found and the | ||
associated code is not two or three characters, this function returns only the | |||
WikiMedia language name. | |||
Some language names have multiple entries under different codes: | Some language names have multiple entries under different codes: | ||
| Line 1,523: | Line 1,583: | ||
--[[ | --[[-------------------< L A N G U A G E _ P A R A M E T E R >------------------ | ||
Gets language name from a provided two- or three-character ISO 639 code. If a code is recognized by MediaWiki, | Gets language name from a provided two- or three-character ISO 639 code. If a code | ||
use the returned name; if not, then use the value that was provided with the language parameter. | is recognized by MediaWiki, use the returned name; if not, then use the value that | ||
was provided with the language parameter. | |||
When |language= contains a recognized language (either code or name), the page is assigned to the category for | When |language= contains a recognized language (either code or name), the page is | ||
that code: Category:Norwegian-language sources (no). | assigned to the category for that code: Category:Norwegian-language sources (no). | ||
to the single category for '639-2' codes: Category:CS1 ISO 639-2 language sources. | For valid three-character code languages, the page is assigned to the single category | ||
for '639-2' codes: Category:CS1 ISO 639-2 language sources. | |||
Languages that are the same as the local wiki are not categorized. MediaWiki does not recognize three-character | Languages that are the same as the local wiki are not categorized. MediaWiki does | ||
equivalents of two-character codes: code 'ar' is recognized but code 'ara' is not. | not recognize three-character equivalents of two-character codes: code 'ar' is | ||
recognized but code 'ara' is not. | |||
This function supports multiple languages in the form |language=nb, French, th where the language names or codes are | This function supports multiple languages in the form |language=nb, French, th | ||
separated from each other by commas with optional space characters. | where the language names or codes are separated from each other by commas with | ||
optional space characters. | |||
]] | ]] | ||
| Line 1,601: | Line 1,665: | ||
end | 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_cs_style (postscript, mode) | |||
local function | if utilities.is_set(postscript) then | ||
if | -- 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 | end | ||
return cfg.presentation[' | return cfg.presentation['sep_' .. mode], postscript; | ||
end | end | ||
--[[--------------------------< S E T _ S T Y L E >----------------------------- | |||
--[[--------------------------< S E T | 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 function | |||
local sep; | local sep; | ||
if ( | if 'cs2' == mode then | ||
sep, | sep, postscript = set_cs_style (postscript, 'cs2'); | ||
else | elseif 'cs1' == mode then | ||
sep, | sep, postscript = set_cs_style (postscript, 'cs1'); | ||
elseif 'citation' == cite_class then | |||
sep, postscript = set_cs_style (postscript, 'cs2'); | |||
else | |||
sep, postscript = set_cs_style (postscript, 'cs1'); | |||
end | end | ||
if cfg.keywords_xlate[postscript:lower()] == 'none' then | |||
-- 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 >----------------------------------- | |||
Determines if a URL has the file extension that is one of the PDF file extensions | |||
used by [[MediaWiki:Common.css]] when applying the PDF icon to external links. | |||
Determines if a URL has the file extension that is one of the PDF file extensions used by [[MediaWiki:Common.css]] when | |||
applying the PDF icon to external links. | |||
returns true if file extension is one of the recognized extensions, else false | returns true if file extension is one of the recognized extensions, else false | ||
| Line 1,699: | Line 1,728: | ||
--[[--------------------------< 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 1,723: | Line 1,753: | ||
--[[ | --[[---------------------< 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 1,776: | ||
]] | ]] | ||
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 1,784: | ||
max = tonumber (max); -- make it a number | max = tonumber (max); -- make it a number | ||
if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors | if max >= count then -- if |display-xxxxors= value greater than or equal to number of authors/editors | ||
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', { | table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message | ||
max = nil; | max = nil; | ||
end | end | ||
else -- not a valid keyword or number | else -- not a valid keyword or number | ||
table.insert( z.message_tail, {utilities.set_message ('err_disp_name', { | table.insert( z.message_tail, {utilities.set_message ('err_disp_name', {param, max}, true)}); -- add error message | ||
max = nil; -- unset; as if |display-xxxxors= had not been set | max = nil; -- unset; as if |display-xxxxors= had not been set | ||
end | end | ||
| Line 1,767: | Line 1,797: | ||
--[[ | --[[----------< 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 | |||
table.insert (z.message_tail, {utilities.set_message ('err_extra_text_pages', {name}, true)}); -- add error message | |||
return; -- and done | |||
end | 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= | |||
local function get_v_name_table (vparam, output_table, output_link_table) | 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 | |||
table.insert (z.message_tail, {utilities.set_message (handler, {name}, true)}); -- add error message | |||
return; -- and done | |||
end | |||
end | |||
end | |||
--[=[-------------------------< G E T _ V _ N A M E _ T A B L E >---------------------------------------------- | |||
split apart a |vauthors= or |veditors= parameter. This function allows for corporate names, wrapped in doubled | |||
parentheses to also have commas; in the old version of the code, the doubled parentheses were included in the | |||
rendered citation and in the metadata. Individual author names may be wikilinked | |||
|vauthors=Jones AB, [[E. B. White|White EB]], ((Black, Brown, and Co.)) | |||
]=] | |||
local function get_v_name_table (vparam, output_table, output_link_table) | |||
local name_table = mw.text.split(vparam, "%s*,%s*"); -- names are separated by commas | local 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 1,882: | ||
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 1,938: | ||
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 1,943: | ||
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 1,957: | ||
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 1,971: | ||
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 1,980: | ||
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 1,995: | ||
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 2,006: | ||
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 2,022: | Line 2,095: | ||
if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then | if 'magazine' == cite_class or (utilities.in_array (cite_class, {'citation', 'map'}) and 'magazine' == origin) then | ||
if utilities.is_set (volume) and utilities.is_set (issue) then | if utilities.is_set (volume) and utilities.is_set (issue) then | ||
return wrap_msg ('vol-no', {sepc, volume, issue}, lower); | return wrap_msg ('vol-no', {sepc, hyphen_to_dash (volume), issue}, lower); | ||
elseif utilities.is_set (volume) then | elseif utilities.is_set (volume) then | ||
return wrap_msg ('vol', {sepc, volume}, lower); | return wrap_msg ('vol', {sepc, hyphen_to_dash (volume)}, lower); | ||
else | else | ||
return wrap_msg ('issue', {sepc, issue}, lower); | return wrap_msg ('issue', {sepc, issue}, lower); | ||
| Line 2,038: | Line 2,111: | ||
if utilities.is_set (volume) then | if utilities.is_set (volume) then | ||
if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals | if volume:match ('^[MDCLXVI]+$') or volume:match ('^%d+$') then -- volume value is all digits or all uppercase Roman numerals | ||
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, | vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, volume}); -- render in bold face | ||
elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters | elseif (4 < mw.ustring.len(volume)) then -- not all digits or Roman numerals and longer than 4 characters | ||
vol = utilities.substitute (cfg.messages['j-vol'], {sepc, volume}); -- not bold | vol = utilities.substitute (cfg.messages['j-vol'], {sepc, hyphen_to_dash (volume)}); -- not bold | ||
utilities.add_prop_cat ('long_vol'); | utilities.add_prop_cat ('long_vol'); | ||
else -- four or less characters | else -- four or less characters | ||
vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash(volume)}); -- bold | vol = utilities.substitute (cfg.presentation['vol-bold'], {sepc, hyphen_to_dash (volume)}); -- bold | ||
end | end | ||
end | end | ||
| Line 2,111: | Line 2,184: | ||
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 2,194: | ||
]] | ]] | ||
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 2,202: | ||
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 2,214: | ||
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 2,159: | Line 2,232: | ||
return page, pages, at, coins_pages; | return page, pages, at, coins_pages; | ||
end | |||
--[[--------------------------< I S _ U N I Q U E _ A R C H I V E _ U R L >------------------------------------ | |||
add error message when |archive-url= value is same as |url= or chapter-url= (or alias...) value | |||
]] | |||
local function is_unique_archive_url (archive, url, c_url, source, date) | |||
if utilities.is_set (archive) then | |||
if archive == url or archive == c_url then | |||
table.insert (z.message_tail, {utilities.set_message ('err_bad_url', {utilities.wrap_style ('parameter', source)}, true)}); -- add error message | |||
return '', ''; -- unset |archive-url= and |archive-date= because same as |url= or |chapter-url= | |||
end | |||
end | |||
return archive, date; | |||
end | end | ||
| Line 2,272: | Line 2,362: | ||
local function is_generic_title (title) | local function is_generic_title (title) | ||
title = mw.ustring.lower(title); -- switch title to lower case | title = mw.ustring.lower(title); -- switch title to lower case | ||
for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do --spin through the list of known generic title fragments | for _, generic_title in ipairs (cfg.special_case_translation['generic_titles']) do -- spin through the list of known generic title fragments | ||
if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then | if title:find (generic_title['en'][1], 1, generic_title['en'][2]) then | ||
return true; -- found English generic title so done | return true; -- found English generic title so done | ||
| Line 2,286: | Line 2,376: | ||
--[[--------------------------< 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 2,398: | ||
]] | ]] | ||
local function citation0( config, args) | local function citation0( config, args ) | ||
--[[ | --[[ | ||
Load Input Parameters | Load Input Parameters | ||
| Line 2,318: | Line 2,408: | ||
-- 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 2,420: | ||
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 2,432: | ||
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 2,405: | Line 2,474: | ||
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 2,488: | ||
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 = ''; | |||
if utilities.is_set (Periodical) then | |||
local Periodical = A['Periodical']; | |||
local Periodical_origin = ''; | |||
if utilities.is_set (Periodical) then | |||
Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter | Periodical_origin = A:ORIGIN('Periodical'); -- get the name of the periodical parameter | ||
local i; | local i; | ||
| Line 2,488: | Line 2,514: | ||
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 2,499: | Line 2,524: | ||
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 | ||
| Line 2,526: | Line 2,542: | ||
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, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals' | if utilities.is_set (Periodical) and utilities.in_array (Periodical_origin, {'journal', 'magazine', 'newspaper', 'periodical', 'work'}) or -- {{citation}} renders issue for these 'periodicals' | ||
| Line 2,537: | Line 2,555: | ||
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']; | ||
| Line 2,573: | Line 2,594: | ||
end | end | ||
local URL = A['URL'] | |||
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; | |||
table.insert( z.message_tail, { utilities.set_message ( 'err_param_access_requires_param', {'url'}, true ) } ); | |||
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 | ||
| Line 2,591: | Line 2,615: | ||
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 2,721: | Line 2,701: | ||
TransChapter = TransTitle; | TransChapter = TransTitle; | ||
ChapterURL = URL; | ChapterURL = URL; | ||
ChapterURL_origin = | ChapterURL_origin = URL_origin; | ||
ChapterUrlAccess = UrlAccess; | ChapterUrlAccess = UrlAccess; | ||
| Line 2,745: | Line 2,725: | ||
-- 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 2,756: | Line 2,737: | ||
-- 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 2,762: | ||
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 2,809: | Line 2,801: | ||
-- 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 2,843: | Line 2,836: | ||
ChapterURL = URL; | ChapterURL = URL; | ||
ChapterUrlAccess = UrlAccess; | ChapterUrlAccess = UrlAccess; | ||
ChapterURL_origin = | ChapterURL_origin = URL_origin; | ||
Title = Series; -- promote series to title | Title = Series; -- promote series to title | ||
| Line 2,870: | Line 2,863: | ||
-- handle type parameter for those CS1 citations that have default values | -- handle type parameter for those CS1 citations that have default values | ||
local TitleType = A['TitleType']; | |||
local Degree = A['Degree']; | |||
if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then | if utilities.in_array (config.CitationClass, {"AV-media-notes", "interview", "mailinglist", "map", "podcast", "pressrelease", "report", "techreport", "thesis"}) then | ||
TitleType = set_titletype (config.CitationClass, TitleType); | TitleType = set_titletype (config.CitationClass, TitleType); | ||
| Line 2,883: | Line 2,878: | ||
-- 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 2,905: | ||
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 2,931: | Line 2,951: | ||
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 2,942: | Line 2,957: | ||
local modified = false; -- flag | local modified = false; -- flag | ||
if validation.edtf_transform (date_parameters_list) then -- edtf dates to MOS compliant format | |||
modified = true; | |||
end | |||
if utilities.is_set (DF) then -- if we need to reformat dates | if utilities.is_set (DF) then -- if we need to reformat dates | ||
modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate | modified = validation.reformat_dates (date_parameters_list, DF); -- reformat to DF format, use long month names if appropriate | ||
| Line 2,971: | Line 2,990: | ||
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 | ||
| Line 2,990: | Line 3,014: | ||
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 3,024: | Line 3,048: | ||
check_for_url ({ -- add error message when any of these parameters hold a URL | check_for_url ({ -- add error message when any of these parameters hold a URL | ||
['title']=Title, | ['title'] = Title, | ||
[A:ORIGIN('Chapter')]=Chapter, | [A:ORIGIN('Chapter')] = Chapter, | ||
[Periodical_origin] = Periodical, | [Periodical_origin] = Periodical, | ||
[PublisherName_origin] = PublisherName | [PublisherName_origin] = PublisherName | ||
| Line 3,047: | Line 3,071: | ||
coins_author = c; -- use that instead | coins_author = c; -- use that instead | ||
end | end | ||
local QuotePage = A['QuotePage']; | |||
local QuotePages = hyphen_to_dash (A['QuotePages']); | |||
-- this is the function call to COinS() | -- this is the function call to COinS() | ||
| Line 3,063: | Line 3,090: | ||
['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 3,109: | ||
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 3,142: | ||
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 3,174: | ||
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 3,173: | Line 3,198: | ||
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 3,305: | Line 3,334: | ||
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 .. TransError .. Format; | Title = external_link (URL, Title, URL_origin, UrlAccess) .. TransTitle .. TransError .. Format; | ||
| Line 3,322: | Line 3,351: | ||
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('^[\'"]*(.-)[\'"]*$', '%1')); -- make ws URL from |title= interwiki link (strip italic or quote markup); link portion L becomes tooltip label | ||
if ws_url then | if ws_url then | ||
Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup | Title = Title:gsub ('%b[]', ws_label); -- replace interwiki link with ws_label to retain markup | ||
| Line 3,340: | Line 3,369: | ||
end | end | ||
local ConferenceURL_origin = A:ORIGIN('ConferenceURL'); -- get name of parameter that holds ConferenceURL | |||
if utilities.is_set (Conference) then | if utilities.is_set (Conference) then | ||
if utilities.is_set (ConferenceURL) then | if utilities.is_set (ConferenceURL) then | ||
| Line 3,349: | Line 3,379: | ||
end | end | ||
local Position = ''; | |||
if not utilities.is_set (Position) then | if not utilities.is_set (Position) then | ||
local Minutes = A['Minutes']; | local Minutes = A['Minutes']; | ||
| Line 3,395: | Line 3,426: | ||
end | end | ||
if utilities.is_set ( | local Others = A['Others']; | ||
if utilities.is_set (Others) and 0 == #a and 0 == #e then -- add maint cat when |others= has value and used without |author=, |editor= | |||
if config.CitationClass == "AV-media-notes" | |||
or config.CitationClass == "audio-visual" then -- special maint for AV/M which has a lot of 'false' positives right now | |||
utilities.set_message ('maint_others_avm') | |||
else | |||
utilities.set_message ('maint_others'); | |||
end | |||
end | end | ||
Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | Others = utilities.is_set (Others) and (sepc .. " " .. Others) or ""; | ||
| Line 3,413: | Line 3,444: | ||
end | end | ||
local TitleNote = A['TitleNote']; | |||
TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; | TitleNote = utilities.is_set (TitleNote) and (sepc .. " " .. TitleNote) or ""; | ||
if utilities.is_set (Edition) then | if utilities.is_set (Edition) then | ||
if Edition:match ('%f[%a][Ee]d%.?$') 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 (' | table.insert( z.message_tail, { utilities.set_message ( 'err_extra_text_edition')}); -- add error | ||
end | end | ||
Edition = " " .. wrap_msg ('edition', Edition); | Edition = " " .. wrap_msg ('edition', Edition); | ||
| Line 3,424: | Line 3,456: | ||
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 3,471: | ||
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 3,484: | ||
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 3,495: | ||
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 3,511: | ||
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 3,518: | ||
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 3,498: | Line 3,534: | ||
PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set | PostScript = ""; -- cs1|2 does not supply terminal punctuation when |quote= is set | ||
end | |||
-- 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 | end | ||
| Line 3,543: | Line 3,588: | ||
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 3,608: | ||
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 3,638: | ||
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 3,647: | ||
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 3,647: | Line 3,713: | ||
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 3,725: | ||
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 3,796: | ||
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 3,802: | ||
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 options = {}; | local options = {}; | ||
| Line 3,740: | Line 3,810: | ||
options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2'); | options.class = string.format ('%s %s', 'citation', utilities.is_set (Mode) and Mode or 'cs2'); | ||
end | end | ||
if utilities.is_set (Ref) | local Ref = A['Ref']; | ||
if 'harv' == Ref then -- need to check this before setting to default | |||
utilities.set_message ('maint_ref_harv'); -- add maint cat to identify templates that have this now-extraneous param value | |||
elseif not utilities.is_set (Ref) then | |||
Ref = 'harv'; -- set as default when not set externally | |||
end | |||
if 'none' ~= cfg.keywords_xlate[Ref:lower()] then | |||
local id = Ref | local id = Ref | ||
local namelist = {}; -- holds selected contributor, author, editor name list | |||
local year = first_set ({Year, anchor_year}, 2); -- Year first for legacy citations and for YMD dates that require disambiguation | |||
if #c > 0 then -- if there is a contributor list | |||
namelist = c; -- select it | |||
elseif #a > 0 then -- or an author list | |||
namelist = a; | |||
elseif #e > 0 then -- or an editor list | |||
namelist = e; | |||
end | |||
local citeref_id | |||
if #namelist > 0 then -- if there are names in namelist | |||
citeref_id = make_citeref_id (namelist, year); -- go make the CITEREF anchor | |||
else | |||
end | citeref_id = ''; -- unset | ||
end | |||
if citeref_id == Ref then | |||
utilities.set_message ('maint_ref_duplicates_default'); | |||
end | |||
if 'harv' == Ref then | |||
id = citeref_id | |||
end | end | ||
options.id = id; | options.id = id; | ||
| Line 3,798: | Line 3,879: | ||
table.insert (maint, v); -- maint msg is the category name | table.insert (maint, v); -- maint msg is the category name | ||
table.insert (maint, ' ('); -- open the link text | table.insert (maint, ' ('); -- open the link text | ||
table.insert (maint, utilities. | table.insert (maint, utilities.substitute (cfg.messages[':cat wikilink'], {v})); -- add the link | ||
table.insert (maint, ')'); -- and close it | table.insert (maint, ')'); -- and close it | ||
table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table | table.insert (maint_msgs, table.concat (maint)); -- assemble new maint message and add it to the maint_msgs table | ||
| Line 3,806: | Line 3,887: | ||
if not no_tracking_cats then | if not no_tracking_cats then | ||
for _, v in ipairs( z.error_categories ) do | for _, v in ipairs( z.error_categories ) do -- append error categories | ||
table.insert (render, utilities. | table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | ||
end | end | ||
for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories | for _, v in ipairs( z.maintenance_cats ) do -- append maintenance categories | ||
table.insert (render, utilities. | table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | ||
end | end | ||
for _, v in ipairs( z.properties_cats ) do -- append properties categories | for _, v in ipairs( z.properties_cats ) do -- append properties categories | ||
table.insert (render, utilities. | table.insert (render, utilities.substitute (cfg.messages['cat wikilink'], {v})); | ||
end | end | ||
end | end | ||
| Line 3,841: | Line 3,920: | ||
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 'discouraged' == state then | |||
discouraged_parameter (name); -- parameter is discouraged but still supported | |||
return true; | return true; | ||
end | end | ||
| Line 4,033: | Line 4,116: | ||
error_text, error_state = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message | error_text, error_state = utilities.set_message ('err_parameter_ignored_suggest', {k, param}, true); -- set the suggestion error message | ||
else | else | ||
error_text, error_state = utilities.set_message ( 'err_parameter_ignored', { | error_text, error_state = utilities.set_message ( 'err_parameter_ignored', {k}, true ); -- 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 | ||
error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); | error_text, error_state = utilities.set_message ( 'err_parameter_ignored_suggest', {k, suggestions.suggestions[ k:lower() ]}, true ); | ||
else | else | ||
| Line 4,081: | Line 4,164: | ||
end | end | ||
return table.concat ({ | return table.concat ({ | ||
frame:extensionTag ('templatestyles', '', {src=styles}), | |||
citation0( config, args) | |||
}); | |||
end | end | ||