Content deleted Content added
Matthiaspaul (talk | contribs) added tracking message/cat for abbreviated year ranges in |date=, |publication-date= and |year= parameters |
FlatLanguage (talk | contribs) if we select this, double check is not needed |
||
| (87 intermediate revisions by 12 users not shown) | |||
Line 1:
--[[
History of changes since last sync:
2025-05-25: make |date=Jan 0500, |date=0999–1000, |date=090–100 error, accept |date=Jan 500.
2025-05-25: make |date=2000-10-01|year=2010 error
]]
Line 12 ⟶ 13:
]]
local add_prop_cat, is_set, in_array, set_message, substitute, wrap_style;
local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration
Line 32 ⟶ 33:
Wikipedia start date is 2001-01-15T00:00:00 UTC which is 979516800 seconds after 1970-01-01T00:00:00 UTC (the start of Unix time)
accessdate is the date provided in |
today is the current date at time 00:00:00 UTC plus 48 hours
if today is 2015-01-01T00:00:00 then
Line 39 ⟶ 40:
This function does not work if it is fed month names for languages other than English. Wikimedia #time: parser
apparently doesn't understand non-
contains a non-English month name because good1 is false after the call to lang.formatDate(). To get around that
call this function with YYYY-MM-DD format dates.
Line 47 ⟶ 48:
local function is_valid_accessdate (accessdate)
local good1, good2;
local access_ts, tomorrow_ts; -- to hold
good1, access_ts = pcall (lang_object.formatDate, lang_object, 'U', accessdate ); -- convert accessdate value to
good2, tomorrow_ts = pcall (lang_object.formatDate, lang_object, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow
if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which which tonumber() may not understand
access_ts = tonumber (access_ts) or lang_object:parseFormattedNumber (access_ts);
tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts);
else
return false; -- one or both failed to convert to
end
Line 64 ⟶ 65:
return false; -- accessdate out of range
end
end
Line 94 ⟶ 76:
local function get_month_number (month)
return cfg.date_names['local'].long[month] or cfg.date_names['local'].short[month] or
cfg.date_names['en'].long[month] or cfg.date_names['en'].short[month] or
0;
end
Line 108 ⟶ 90:
returns 0 when <param> is not |date=
Season numbering is defined by Extended Date/Time Format (EDTF)
which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard defines various divisions using
numbers 21-41. cs1|2 only supports generic seasons. EDTF does support the distinction between north and south
These additional divisions not currently supported:
Line 140 ⟶ 122:
returns 0 when <param> is not |date=
Quarter numbering is defined by Extended Date/Time Format (EDTF)
which became part of ISO 8601 in 2019. See '§Sub-year groupings'. The standard defines various divisions using
numbers 21-41. cs1|2 only supports generic seasons and quarters.
Line 204 ⟶ 186:
Function gets current year from the server and compares it to year from a citation parameter. Years more than one
year in the future are not acceptable.
Special case for |pmc-embargo-date=: years more than two years in the future are not acceptable
]]
local function is_valid_year (year, param)
if not is_set (year_limit) then
year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once
end
year = tonumber (year) or lang_object:parseFormattedNumber (year); -- convert to
if year and (100 > year) then -- years less than 100 not supported
return false;
end
if 'pmc-embargo-date' == param then -- special case for |pmc-embargo-date=
return year and (year <= tonumber(os.date("%Y"))+2) or false; -- years more than two years in the future are not accepted
end
return year and (year <= year_limit) or false;
end
Line 228 ⟶ 219:
]]
local function is_valid_date (year, month, day, param)
local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
local month_length;
if not is_valid_year (year, param) then
return false;
end
month = tonumber (month); -- required for YYYY-MM-DD dates
if (2 == month) then
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
if 0 == (year%4) then
month_length = 29; -- if leap year then 29 days in February
end
else -- Gregorian calendar
if (0 == (year%4) and (0 ~= (year%100) or 0 == (year%400))) then
month_length = 29; -- if leap year then 29 days in February
end
end
else
month_length = days_in_month[month];
end
Line 262 ⟶ 253:
Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August.
This function looks in cfg.date_names{} to see if both month names are listed in the long subtable or both are
listed in the short subtable. When both have the same style (both are listed in the same table), returns true; false else
]]
local function is_valid_month_range_style (month1, month2)
if (cfg.date_names.en.long[month1] and cfg.date_names.en.long[month2]) or -- are both English names listed in the long subtable?
(cfg.date_names.en.short[month1] and cfg.date_names.en.short[month2]) or -- are both English names listed in the short subtable?
(cfg.date_names['local'].long[month1] and cfg.date_names['local'].long[month2]) or -- are both local names listed in the long subtable?
(cfg.date_names['local'].short[month1] and cfg.date_names['local'].short[month2]) then -- are both local names listed in the short subtable?
return true;
end
return false; -- names are mixed
end
Line 289 ⟶ 275:
Month pairs are expected to be left to right, earliest to latest in time.
All season ranges are accepted as valid because there are publishers out there who have published a Summer–Spring YYYY issue,
]]
Line 308 ⟶ 294:
-- here when range_start is a month
range_end_number = get_month_number (range_end); -- get end month number
if range_start_number < range_end_number
return true; -- proper order and same style
end
return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month
Line 340 ⟶ 325:
the output table receives:
rftdate: an
rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and proper-name dates)
rftssn: one of four season keywords: winter, spring, summer, fall (lowercase)
Line 350 ⟶ 335:
local date; -- one date or first date in a range
local date2 = ''; -- end of range date
input.year = tonumber (input.year) or lang_object:parseFormattedNumber (input.year); -- language-aware tonumber()
input.year2 = tonumber (input.year2) or lang_object:parseFormattedNumber (input.year2); -- COinS dates are pseudo-ISO 8601 so convert to Arabic numerals
if ((1582 == input.year) and (10 > tonumber(input.month))) or (1582 > input.year) then -- if a Julian calendar date
tCOinS_date.rftdate = tostring (input.year); -- &rft.date gets year only
return; -- done
end
-- here for all forms of Gregorian dates
if 20 < tonumber (input.month) then -- if season, quarter, or proper-name date
if 0 ~= input.year2 and input.year ~= input.year2 then -- if a range, only the second year portion when not the same as range start year
date = string.format ('%.4d/%.4d',
end
if 0 ~= input.month2 then
tCOinS_date.rftchron = string.format ('%s %s – %s %s', season[input.month], input.year, season[input.month2], input.year2); -- used in journal metadata only
end
else -- season–season year range
tCOinS_date.rftchron = season[input.month] .. '–' .. season[input.month2]; -- season–season year range; used in journal metadata only
end
end
tCOinS_date.rftdate = tostring (date);
return; -- done
end
-- here for gregorian calendar dates
if 0 ~= input.day then
date = string.format ('%s-%.2d-%.2d', input.year, tonumber(input.month), tonumber(input.day)); -- whole date
Line 416 ⟶ 395:
--[[--------------------------< P A T T E R N S _ T >
this is the list of patterns for date formats that this module recognizes. Approximately the first half of these
Line 428 ⟶ 407:
]]
local
-- year-initial numerical year-month-day
['ymd'] = {'^(
-- month-initial: month day, year
['Mdy'] = {'^(%D-) +([1-9]%d?), +((
-- month-initial day range: month day–day, year; days are separated by endash
['Md-dy'] = {'^(%D-) +([1-9]%d?)[%-–]([1-9]%d?), +(([1-9]%d%d%d
-- day-initial: day month year
['dMy'] = {'^([1-9]%d?) +(%D-) +((
-- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki
-- ['yMd'] = {'^((
-- day-range-initial: day–day month year; days are separated by endash
['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +(([1-9]%d%d%d
-- day initial month-day-range: day month - day month year; uses spaced endash
['dM-dMy'] = {'^([1-9]%d?) +(%D-) +[%-–] +([1-9]%d?) +(%D-) +(([1-9]%d%d%d
-- month initial month-day-range: month day – month day, year; uses spaced endash
['Md-Mdy'] = {'^(%D-) +([1-9]%d?) +[%-–] +(%D-) +([1-9]%d?), +(([1-9]%d%d%d
-- day initial month-day-year-range: day month year - day month year; uses spaced endash
['dMy-dMy'] = {'^([1-9]%d?) +(%D-) +([1-9]%d%d%d
-- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
['Mdy-Mdy'] = {'^(%D-) +([1-9]%d?), +([1-9]%d%d%d
-- these date formats cannot be converted, per se, but month name can be rendered short or long
-- month/season year - month/season year; separated by spaced endash
['My-My'] = {'^(%D-) +([1-9]%d%d%d
-- month/season range year; months separated by endash
['M-My'] = {'^(%D-)[%-–](%D-) +(([1-9]%d%d%d
-- month/season year or proper-name year; quarter year when First Quarter YYYY etc.
['My'] = {'^([^%d–]-) +(([1-9]%d%d%d
-- these date formats cannot be converted
['Sy-y'] = {'^(%D-) +([1-9]%d%d%d?)[%-–](([1-9]%d%d%d?)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash
['
['
['
}
--[[--------------------------< I S _ V A L I D _ E M B A R G O _ D A T E >------------------------------------
returns true and date value if that value has proper dmy, mdy, ymd format.
returns false and 9999 (embargoed forever) when date value is not proper format; assumes that when |pmc-embargo-date= is
set, the editor intended to embargo a PMC but |pmc-embargo-date= does not hold a single date.
]]
local function is_valid_embargo_date (v)
if v:match (patterns_t['ymd'][1]) or -- ymd
v:match (patterns_t['Mdy'][1]) or -- dmy
v:match (patterns_t['dMy'][1]) then -- mdy
return true, v;
end
return false, '9999'; -- if here not good date so return false and set embargo date to long time in future
end
Line 477 ⟶ 473:
If the date fails the format tests, this function returns false and does not return values for anchor_year and
COinS_date. When this happens, the date parameter is (DEBUG: not?) used in the COinS metadata and the CITEREF identifier gets
its year from the year parameter if present otherwise CITEREF does not get a date value.
Inputs:
date_string - date string from date-holding parameters (date, year,
Returns:
Line 493 ⟶ 489:
local function check_date (date_string, param, tCOinS_date)
local year; -- assume that year2, months, and days are not used;
local year2 = 0;
local month = 0;
local month2 = 0;
local day = 0;
local day2 = 0; -- second day in a day range
local anchor_year;
local coins_date;
if date_string:match (
year, month, day = date_string:match (
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar
anchor_year = year;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
elseif mw.ustring.match(date_string,
month, day, day2, anchor_year, year = mw.ustring.match(date_string,
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
month2=month; -- for metadata
year2 = year;
elseif mw.ustring.match(date_string,
day, month, anchor_year, year = mw.ustring.match(date_string,
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
--[[ NOT supported at en.wiki
elseif mw.ustring.match(date_string,
anchor_year, year, month, day = mw.ustring.match(date_string,
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
-- end NOT supported at en.wiki ]]
elseif mw.ustring.match(date_string,
day, day2, month, anchor_year, year = mw.ustring.match(date_string,
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
month2 = month; -- for metadata
year2 = year;
elseif mw.ustring.match(date_string,
day, month, day2, month2, anchor_year, year = mw.ustring.match(date_string,
if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end -- date range order is left to right: earlier to later;
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
year2 = year;
elseif mw.ustring.match(date_string,
month, day, month2, day2, anchor_year, year = mw.ustring.match(date_string,
if (not is_valid_month_season_range(month, month2, param)) or not is_valid_year(year) then return false; end
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
year2 = year;
elseif mw.ustring.match(date_string,
day, month, year, day2, month2, anchor_year, year2 = mw.ustring.match(date_string,
if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style
Line 567 ⟶ 557:
if 0 == month or 0 == month2 then return false; end -- both must be valid
elseif mw.ustring.match(date_string,
month, day, year, month2, day2, anchor_year, year2 = mw.ustring.match(date_string,
if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style
month = get_month_number (month); -- for metadata
month2 = get_month_number
if 0 == month or 0 == month2 then return false; end -- both must be valid
elseif mw.ustring.match(date_string,
local century;
month, year, century, anchor_year, year2 = mw.ustring.match(date_string,
if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer
anchor_year = year .. '–' .. anchor_year;
year2 = century..year2; -- add the century to year2 for comparisons
if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
month = get_season_number
elseif mw.ustring.match(date_string,
month, year, anchor_year, year2 = mw.ustring.match(date_string,
if (month ~= cfg.date_names['en'].season['Winter']) and (month ~= cfg.date_names['en'].season['Summer']) then
return false; -- not Summer or Winter; abandon
end
anchor_year = year .. '–' .. anchor_year; -- assemble anchor_year from both years
if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif mw.ustring.match(date_string,
month, year, month2, anchor_year, year2 = mw.ustring.match(date_string,
anchor_year = year .. '–' .. anchor_year;
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
Line 608 ⟶ 600:
end
elseif mw.ustring.match(date_string,
month, month2, anchor_year, year = mw.ustring.match(date_string,
if (not is_valid_month_season_range(month, month2, param)) or (not is_valid_year(year)) then return false; end
if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season
Line 619 ⟶ 611:
month2 = get_season_number(month2, param);
end
year2 = year;
elseif mw.ustring.match(date_string,
month, anchor_year, year = mw.ustring.match(date_string,
if not is_valid_year(year) then return false; end
month = get_element_number
if not month then return false; end -- not valid whatever it is
elseif mw.ustring.match(date_string,
year, anchor_year, year2 = mw.ustring.match(date_string,
anchor_year = year .. '–' .. anchor_year;
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif mw.ustring.match(date_string,
local century;
year, century, anchor_year, year2 = mw.ustring.match(date_string,
anchor_year = year .. '–' .. anchor_year;
if 13 > tonumber(year2) then return false; end -- don't allow 2003-05 which might be May 2003
year2 = century .. year2;
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
if in_array (param, {'date', 'publication-date', 'year'}) then -- here when 'valid' abbreviated year range; if one of these parameters
add_prop_cat ('year-range-abbreviated'); -- add properties cat
end
elseif mw.ustring.match(date_string, patterns_t['y'][1]) then -- year; here accept either YYY or YYYY
anchor_year, year = mw.ustring.match(date_string, patterns_t['y'][1]);
if false == is_valid_year(year) then
return false;
Line 656 ⟶ 649:
end
if param ~= '
if anchor_year:match ('%l$') then
return false;
end
end
if 'access-date' == param then -- test access-date here because we have numerical date parts
if 0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required
0 == year2 and 0 == month2 and 0 == day2 then -- none of these;
if not is_valid_accessdate
return false; -- return false when
end
else
return false; -- return false when
end
end
if 'archive-date' == param then -- test archive-date here because we have numerical date parts
if not (0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required
0 == year2 and 0 == month2 and 0 == day2) then -- none of these; archive-date must not be a range
return false; -- return false when archive-date is a range of two dates
end
end
Line 669 ⟶ 675:
local result=true; -- check whole dates for validity; assume true because not all dates will go through this test
if 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 == month2 and 0 == day2 then -- YMD (simple whole date)
result = is_valid_date (year, month, day, param); -- <param> for |pmc-embargo-date=
elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 == month2 and 0 ~= day2 then -- YMD-d (day range)
result = is_valid_date (year, month, day);
result = result and is_valid_date (year, month, day2);
elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 ~= month2 and 0 ~= day2 then -- YMD-md (day month range)
result = is_valid_date (year, month, day);
result = result and is_valid_date (year, month2, day2);
elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 ~= year2 and 0 ~= month2 and 0 ~= day2 then -- YMD-ymd (day month year range)
result = is_valid_date(year, month, day);
result = result and is_valid_date(year2, month2, day2);
end
Line 687 ⟶ 693:
if nil ~= tCOinS_date then -- this table only passed into this function when testing |date= parameter values
make_COinS_date ({year = year, month = month, day = day, year2 = year2, month2 = month2, day2 = day2}, tCOinS_date); -- make an ISO 8601 date string for COinS
end
Line 709 ⟶ 715:
local COinS_date; -- will return as nil if the date being tested is not |date=
local embargo_date; -- if embargo date is a good dmy, mdy, ymd date then holds original value else reset to 9999
local good_date = false;
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(v.val) then -- if the parameter has a value
v.val = mw.ustring.gsub
if v.val:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
if 'date' == k then
anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
good_date = is_valid_year(year);
elseif 'year' == k then
good_date = is_valid_year(year);
end
elseif 'date' == k then -- if the parameter is |date=
if v.val:match("^n%.d%.%a?$") then -- ToDo: I18N -- if |date=n.d. with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); -- ToDo: I18N -- "n.d."; no error when date parameter is set to no date
elseif v.val:match("^nd%a?$") then -- ToDo: I18N -- if |date=nd with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); -- ToDo: I18N -- "nd"; no error when date parameter is set to no date
else
good_date, anchor_year, COinS_date = check_date (v.val, k, tCOinS_date); -- go test the date
end
elseif 'year' == k then -- if the parameter is |year= it should hold only a year value
if v.val:match("^[1-9]%d%d%d?%a?$") then -- if |year = 3 or 4 digits only with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)");
end
elseif 'pmc-embargo-date' == k then
good_date = check_date (v.val, k); -- go test the date
if true == good_date then -- if the date is a valid date
good_date, embargo_date = is_valid_embargo_date (v.val); -- is |pmc-embargo-date= date a single dmy, mdy, or ymd formatted date? yes: returns embargo date; no: returns 9999
end
else -- any other date-holding parameter
good_date = check_date (v.val, k); -- go test the date
end
if false == good_date then -- assemble one error message so we don't add the tracking category multiple times
table.insert (error_list, wrap_style ('parameter', v.name)); -- make parameter name suitable for error message list
end
end
end
return anchor_year, embargo_date; -- and done
end
--[[--------------------------< Y E A R _ C H E C K >----------------------------------------------------------
Temporary function to test |year= for acceptable values:
YYY, YYYY, year-only ranges, their circa forms, with or without CITEREF disambiguators.
When |year= holds some form of date that is not one of these year-only dates, emit a maintenance message.
This function necessary because many non-cs1|2 templates have a |year= parameter so cirrus searches are more-or-
less useless
]]
local function year_check (year)
year = year:gsub ('c%. *', ''); -- remove circa annotation (if present) before testing <year>
for _, index in ipairs ({'y-y', 'y4-y2', 'y'}) do -- spin through these indexes into patterns_t
if mw.ustring.match (year, patterns_t[index][1]) then
return; -- if a match then |year= holds a valid 'year'
end
end
set_message ('maint_year'); -- if here, |year= value is not an accepted value; add a maint cat
end
Line 759 ⟶ 784:
--[[--------------------------< Y E A R _ D A T E _ C H E C K >------------------------------------------------
Compare the value provided in |year= with the year value(s) provided in |date=. This function
0 - year value does not match the year value in date
1 - (default) year value matches the year value in date or one of the year values when date contains two years
2 - year value matches the year value in date when date is in the form YYYY-MM-DD and year is disambiguated (|year=YYYYx)
the numeric value in <result> determines the 'output' if any from this function:
0 – adds error message to error_list sequence table
1 – adds maint cat
2 – does nothing
]]
local function year_date_check (year_string, year_origin, date_string, date_origin, error_list)
local year;
local date1;
local date2;
local result = 1; -- result of the test; assume that the test passes
year = year_string:match ('(%d%d%d%d?)');
if date_string:match ('%d%d%d%d%-%d%d%-%d%d
date1 = date_string:match ('(%d%d%d%d)');
year = year_string:match ('(%d%d%d%d)');
if year ~= date1 then
result = 0; -- years don't match
elseif year_string:match ('%d%d%d%d%a') then
result = 2; -- years match; but because disambiguated, don't add to maint cat
end
Line 802 ⟶ 832:
result = 0;
end
else -- should never get here; this function called only when no other date errors
result = 0; -- no recognizable year in date
end
if 0 == result then -- year / date mismatch
table.insert (error_list, substitute (cfg.messages['mismatch'], {year_origin, date_origin})); -- add error message to error_list sequence table
elseif 1 == result then -- redundant year / date
set_message ('maint_date_year'); -- add a maint cat
end
end
Line 817 ⟶ 852:
format string used by string.format()
identifier letters ('d', 'm', 'y', 'd2', 'm2', 'y2') that serve as indexes into a table t{} that holds captures
from mw.ustring.match() for the various date parts specified by
Items in
['ymd'] = {'^(%d%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'}, where:
['ymd'] is pattern_idx
when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifier
Line 833 ⟶ 868:
format_param set to the desired format. This function loads table t{} as described and then calls string.format()
with the format string specified by re_format[pattern_idx][format_param][1] using values taken from t{} according
to the capture identifier letters specified by
]]
Line 841 ⟶ 876:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'},
},
['Mdy'] = { -- date format is Mdy; reformat to:
Line 847 ⟶ 882:
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'},
},
['dMy'] = { -- date format is dMy; reformat to:
Line 853 ⟶ 888:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'},
},
['Md-dy'] = { -- date format is Md-dy; reformat to:
Line 888 ⟶ 923:
['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic
},
-- ['yMd'] = {
-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'},
-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'},
-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'},
-- },
}
Line 898 ⟶ 933:
local function reformatter (date, pattern_idx, format_param, mon_len)
if not in_array (pattern_idx, {'ymd', 'Mdy', 'Md-dy', 'dMy', 'yMd', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My-My', 'M-My', 'My'}) then
return; -- not in this set of date format
end
Line 909 ⟶ 944:
end
-- if 'yMd' == format_param and in_array (pattern_idx, {'yMd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy'}) then -- these formats not convertable; yMd not supported at en.wiki
return; -- not a reformattable date
end
local c1, c2, c3, c4, c5, c6, c7; -- these hold the captures specified in
c1, c2, c3, c4, c5, c6, c7 = mw.ustring.match (date,
local t = { -- table that holds k/v pairs of date parts from the captures and
[
[
[
[
[
[
[
};
if t.a then -- if this date has an anchor year capture (all convertable date formats except ymd)
t.y2 = t.a; -- use the anchor year capture when reassembling the date
else -- here for single date formats (except ymd)
t.y = t.a; -- use the anchor year capture when reassembling the date
end
end
if tonumber(t.m) then -- if raw month is a number (converting from ymd)
if 's' == mon_len then -- if we are to use abbreviated month names
t.m = cfg.date_names['
else
t.m = cfg.date_names['
end
t.d = t.d:gsub ('0(%d)', '%1'); -- strip leading '0' from day if present
elseif 'ymd' == format_param then -- when converting to ymd
t.y = t.y:gsub ('%a', ''); -- strip CITREF disambiguator if present; anchor year already known so process can proceed; TODO: maint message?
if 1582 > tonumber (t.y) then -- ymd format dates not allowed before 1582
return;
end
Line 952 ⟶ 990:
t[mon] = get_month_number (t[mon]); -- get the month number for this month (is length agnostic)
if 0 == t[mon] then return; end -- seasons and named dates can't be converted
t[mon] = (('s' == mon_len) and cfg.date_names['
end
end
Line 1,022 ⟶ 1,060:
if is_set (param_val.val) then -- if the parameter has a value
if not (not all and in_array (param_name, {'access-date', 'archive-date'})) then -- skip access- or archive-date unless format is xxx-all; yeah, ugly; TODO: find a better way
for pattern_idx, pattern in pairs (
if mw.ustring.match (param_val.val, pattern[1]) then
if all and in_array (param_name, {'access-date', 'archive-date'}) then -- if this date is an access- or archive-date
Line 1,033 ⟶ 1,071:
date_parameters_list[param_name].val = new_date; -- update date in date list
result = true; -- and announce that changes have been made
break;
end
end -- if
Line 1,039 ⟶ 1,078:
end -- if
end -- for
return result;
end
Line 1,056 ⟶ 1,095:
local n;
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set (param_val.val)
param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash
if 0 ~= n then
Line 1,063 ⟶ 1,102:
result = true;
end
end
end
Line 1,072 ⟶ 1,110:
--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------
Attempts to translate English
date parser function. This is simple name-for-name replacement and may not work for all languages.
if xlat_dig is true, this function will also translate
This will also translate ymd dates.
]]
local function
local xlate;
local mode; -- long or short month names
Line 1,086 ⟶ 1,124:
local date;
local sources_t = {
{cfg.date_names.en.long, cfg.date_names.inv_local_long}, -- for translating long English month names to long local month names
{cfg.date_names.en.short, cfg.date_names.inv_local_short}, -- short month names
{cfg.date_names.en.quarter, cfg.date_names.inv_local_quarter}, -- quarter date names
{cfg.date_names.en.season, cfg.date_names.inv_local_season}, -- season date nam
{cfg.date_names.en.named, cfg.date_names.inv_local_named}, -- named dates
}
local function is_xlateable (month) -- local function to get local date name that replaces existing English-language date name
for _, date_names_t in ipairs (sources_t) do -- for each sequence table in date_names_t
if date_names_t[1][month] then -- if date name is English month (long or short), quarter, season or named and
if date_names_t[2][date_names_t[1][month]] then -- if there is a matching local date name
return date_names_t[2][date_names_t[1][month]]; -- return the local date name
end
end
end
end
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(param_val.val) then -- if the parameter has a value
date = param_val.val;
for month in mw.ustring.gmatch (date, '[%a ]+') do
month = mw.text.trim (month); -- this because quarterly dates contain whitespace
if xlate then
date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation
date_parameters_list[param_name].val = date; -- save the translated date
Line 1,107 ⟶ 1,157:
if xlt_dig then -- shall we also translate digits?
date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from
date_parameters_list[param_name].val = date; -- save the translated date
modified = true;
Line 1,115 ⟶ 1,165:
return modified;
Line 1,125 ⟶ 1,175:
local function set_selected_modules (cfg_table_ptr, utilities_page_ptr)
is_set = utilities_page_ptr.is_set;
substitute = utilities_page_ptr.substitute;
wrap_style = utilities_page_ptr.wrap_style;
cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration
end
--[[--------------------------< A R C H I V E _ D A T E _ C H E C K >------------------------------------------
Compare value in |archive-date= with the timestamp in Wayback machine urls. Emits an error message with suggested
date from the |archive-url= timestamp in an appropriate format when the value in |archive-date= does not match
the timestamp.
this function never called when any date in a cs1|2 template has errors
error message suggests new |archive-date= value in an appropriate format specified by <df>. <df> is either
|df= or cfg.global_df in that order. If <df> is nil, suggested date has format from |archive-date=. There is
a caveat: when |df=dmy or |df=mdy, the reformatter leaves |access-date= and |archive-date= formats as they are.
The error message suggested date is passed to the formatter as YYYY-MM-DD so when |df=dmy or |df=mdy, the format
is not changed.
]]
local function archive_date_check (archive_date, archive_url_timestamp, df)
local archive_date_format = 'dmy-y'; -- holds the date format of date in |archive-date; default to ymd; 'dmy' used here to spoof reformat_dates()
for _, v_t in ipairs ({{'dMy', 'dmy-all'}, {'Mdy', 'mdy-all'}}) do -- is |archive-date= format dmy or mdy?
if archive_date:match (patterns_t[v_t[1]][1]) then -- does the pattern match?
archive_date_format = cfg.keywords_xlate[v_t[2]]; -- get appropriate |df= supported keyword from the i18n translator table
break;
end
end
local dates_t = {};
dates_t['archive-date'] = {val=archive_date, name=''}; -- setup to call reformat_dates(); never called when errors so <name> unset as not needed
reformat_dates (dates_t, 'dmy-y'); -- reformat |archive-date= to ymd; 'dmy' used here to spoof reformat_dates()
local archive_url_date = archive_url_timestamp:gsub ('(%d%d%d%d)(%d%d)(%d%d)%d*', '%1-%2-%3'); -- make ymd format date from timestamp
if dates_t['archive-date'].val == archive_url_date then -- are the two dates the same
return; -- yes, done
else
dates_t['archive-date'] = {val=archive_url_date, name=''}; -- setup to call reformat_dates() with the timestamp date
reformat_dates (dates_t, df or archive_date_format); -- reformat timestamp to format specified by <df> or format used in |archive-date=
archive_url_date = dates_t['archive-date'].val;
set_message ('err_archive_date_url_ts_mismatch', archive_url_date); -- emit an error message
end
end
Line 1,137 ⟶ 1,232:
return { -- return exported functions
archive_date_check = archive_date_check,
date_hyphen_to_dash = date_hyphen_to_dash,
date_name_xlate = date_name_xlate,
dates = dates,
reformat_dates = reformat_dates,
set_selected_modules = set_selected_modules,
year_check = year_check,
year_date_check = year_date_check,
}
| |||