Open main menu

Changes

Module:Citation/CS1/Date validation

12,903 bytes added, 11:05, 3 September 2019
sync from sandbox;
 
local p = {}
 
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
local is_set, in_array; -- imported functions from selected Module:Citation/CS1/Utilities
local cfg; -- table of tables imported from slected selected Module:Citation/CS1/Configuration 
--[=[-------------------------< I S _ V A L I D _ A C C E S S D A T E >----------------------------------------
37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each)
40-41 = Semestral 1, Semestral-2 (6 months each)
 
]]
0; -- not a recognized season name
end
 
--[[--------------------------< I S _ P R O P E R _ N A M E >--------------------------------------------------
0; -- not a recognized named date
end
 
--[[--------------------------< I S _ V A L I D _ M O N T H _ O R _ S E A S O N >------------------------------
local function is_valid_month_or_season (month_season)
if 0 == get_month_number (month_season) then -- if month text isn't one of the twelve months, might be a season if 0 == get_season_number (month_season) then -- not a month, is it a season? return false; -- return false not a month or one of the five seasons
end
end
return true;
end
 
--[[--------------------------< I S _ V A L I D _ Y E A R >----------------------------------------------------
local function is_valid_year(year)
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
return tonumber(year) <= year_limit; -- false if year is in the future more than one year
end
 
--[[--------------------------< I S _ V A L I D _ D A T E >----------------------------------------------------
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
if 0==(year%4) then -- is a leap year? month_length = 29; -- if leap year then 29 days in February
end
else -- Gregorian calendar
return true;
end
 
--[[--------------------------< I S _ V A L I D _ M O N T H _ R A N G E _ S T Y L E >--------------------------
return;
end
 
 
--[[--------------------------< P A T T E R N S >--------------------------------------------------------------
 
this is the list of patterns for date formats that this module recognizes. Approximately the first half of these
patterns represent formats that might be reformatted into another format. Those that might be reformatted have
'indicator' letters that identify the content of the matching capture: 'd' (day), 'm' (month), 'a' (anchor year),
'y' (year); second day, month, year have a '2' suffix.
 
These patterns are used for both date validation and for reformatting. This table should not be moved to ~/Configuration
because changes to this table require changes to check_date() and to reformatter() and reformat_date()
 
]]
 
local patterns = {
-- year-initial numerical year-month-day
['ymd'] = {'^(%d%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'},
-- month-initial: month day, year
['Mdy'] = {'^(%D-) +([1-9]%d?), +((%d%d%d%d?)%a?)$', 'm', 'd', 'a', 'y'},
-- month-initial day range: month day–day, year; days are separated by endash
['Md-dy'] = {'^(%D-) +([1-9]%d?)[%-–]([1-9]%d?), +((%d%d%d%d)%a?)$', 'm', 'd', 'd2', 'a', 'y'},
-- day-initial: day month year
['dMy'] = {'^([1-9]%d?) *(%D-) +((%d%d%d%d?)%a?)$', 'd', 'm', 'a', 'y'},
-- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki
-- ['yMd'] = {'^((%d%d%d%d?)%a?) +(%D-) +(%d%d?)$', 'a', 'y', 'm', 'd'},
-- day-range-initial: day–day month year; days are separated by endash
['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'd2', 'm', 'a', 'y'},
-- day initial month-day-range: day month - day month year; uses spaced endash
['dM-dMy'] = {'^([1-9]%d?) +(%D-) +[%-–] +([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'm', 'd2', 'm2', 'a', 'y'},
-- month initial month-day-range: month day – month day, year; uses spaced endash
['Md-Mdy'] = {'^(%D-) +([1-9]%d?) +[%-–] +(%D-) +([1-9]%d?), +((%d%d%d%d)%a?)$','m', 'd', 'm2', 'd2', 'a', 'y'},
-- day initial month-day-year-range: day month year - day month year; uses spaced endash
['dMy-dMy'] = {'^([1-9]%d?) +(%D-) +(%d%d%d%d) +[%-–] +([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'm', 'y', 'd2', 'm2', 'a', 'y2'},
-- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
['Mdy-Mdy'] = {'^(%D-) +([1-9]%d?), +(%d%d%d%d) +[%-–] +(%D-) +([1-9]%d?), +((%d%d%d%d)%a?)$', 'm', 'd', 'y', 'm2', 'd2', 'a', 'y2'},
 
-- 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-) +(%d%d%d%d) +[%-–] +(%D-) +((%d%d%d%d)%a?)$', 'm', 'y', 'm2', 'a', 'y2'},
-- month/season range year; months separated by endash
['M-My'] = {'^(%D-)[%-–](%D-) +((%d%d%d%d)%a?)$', 'm', 'm2', 'a', 'y'},
-- month/season year or proper-name year
['My'] = {'^([^%d–]-) +((%d%d%d%d)%a?)$', 'm', 'a', 'y'}, -- this way because endash is a member of %D; %D- will match January–March 2019 when it shouldn't
-- these date formats cannot be converted
['Sy4-y2'] = {'^(%D-) +((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
['Sy-y'] = {'^(%D-) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash
['y-y'] = {'^(%d%d%d%d?)[%-–]((%d%d%d%d?)%a?)$'}, -- year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
['y4-y2'] = {'^((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- year range: YYYY–YY; separated by unspaced endash
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- year; here accept either YYY or YYYY
}
local coins_date;
if date_string:match("^%d%d%d%d%-%d%d%-%d%d$"patterns['ymd'][1]) then -- year-initial numerical year month day format year, month, day=string.date_string:match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)"patterns['ymd'][1]);
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar
anchor_year = year;
elseif mw.ustring.match(date_string, "^%D- +patterns[1-9'Mdy']%d?, +[1-9]%d%d%d%a?$") then -- month-initial: month day, year month, day, anchor_year, year=mw.ustring.match(date_string, "(%D-) +(%d%d?),%s*((%d%d%d%d?)%a?)"patterns['Mdy'][1]);
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, "^%D- +[1-9]%d?[%-–]patterns[1'Md-9dy']%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash month, day, day2, anchor_year, year=mw.ustring.match(date_string, "(%Dpatterns['Md-) +(%d%d?)dy'][%-–1](%d%d?), +((%d%d%d%d)%a?)"); if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months month2=month; -- for metadata
year2=year;
elseif mw.ustring.match(date_string, "^patterns[1-9'dMy']%d? +%D- +[1-9]%d%d%d%a?$") then -- day-initial: day month year day, month, anchor_year, year=mw.ustring.match(date_string, "(%d%d*)%s*(%D-) +((%d%d%d%d?)%a?)"patterns['dMy'][1]);
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, "^[1-9]%d?[%-–]patterns[1-9'yMd']%d? +%D- +[1-9]%d%d%d%a?$") then -- day-rangeyear-initial: day–day year month yearday; days are separated by endashday: 1 or 2 two digits, leading zero allowed dayanchor_year, day2year, month, anchor_year, yearday=mw.ustring.match(date_string, "(%d%d?)patterns['yMd'][%-–1](%d%d?) +(%D-) +((%d%d%d%d)%a?)"); if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months-- end NOT supported at en.wiki ]]  elseif mw.ustring.match(date_string, patterns['d-dMy'][1]) then -- day-range-initial: day–day month year; days are separated by endash day, day2, month, anchor_year, year=mw.ustring.match(date_string, patterns['d-dMy'][1]); if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same; month = get_month_number (month); if 0 == month then return false; end -- return false if month text isn't one of the twelve months month2=month; -- for metadata
year2=year;
elseif mw.ustring.match(date_string, "^patterns[1-9]%d? +%D- +[%'dM-dMy'] +[1-9]%d? +%D- +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash day, month, day2, month2, anchor_year, year=mw.ustring.match(date_string, "(%d%d?) +(%Dpatterns['dM-) +dMy'][%-–1] +(%d%d?) +(%D-) +((%d%d%d%d)%a?)");
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, "^%D- +patterns[1'Md-9Mdy']%d? +[%-–] +%D- +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-range: month day – month day, year; uses spaced endash month, day, month2, day2, anchor_year, year=mw.ustring.match(date_string, "(%Dpatterns['Md-) +(%d%d?) +Mdy'][%-–1] +(%D-) +(%d%d?), +((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
year2=year;
elseif mw.ustring.match(date_string, "^patterns[1-9]%d? +%D- +[1-9]%d%d%d +[%'dMy-dMy'] +[1-9]%d? +%D- +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash day, month, year, day2, month2, anchor_year, year2=mw.ustring.match(date_string, "(%d%d?) +(%Dpatterns['dMy-) +(%d%d%d%d) +dMy'][%-–1] +(%d%d?) +(%D-) +((%d%d%d%d)%a?)"); 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 (month2);
elseif mw.ustring.match(date_string, "^%D- +patterns[1'Mdy-9Mdy']%d?, +[1-9]%d%d%d +[%-–] +%D- +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash month, day, year, month2, day2, anchor_year, year2=mw.ustring.match(date_string, "(%Dpatterns['Mdy-) +(%d%d?), +(%d%d%d%d) +Mdy'][%-–1] +(%D-) +(%d%d?), +((%d%d%d%d)%a?)"); if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
elseif mw.ustring.match(date_string, "^%D- +patterns[1'Sy4-9y2']%d%d%d[%-–1]%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
local century;
month, year, century, anchor_year, year2=mw.ustring.match(date_string, "(%Dpatterns['Sy4-) +((%d%d)%d%d)y2'][%-–1]((%d%d)%a?)"); if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years 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 (month);
elseif mw.ustring.match(date_string, "^%D- +patterns[1'Sy-9]%d%d%d[%-–y'][1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash month, year, anchor_year, year2=mw.ustring.match(date_string, "(%Dpatterns['Sy-) +(%d%d%d%d)y'][%-–1]((%d%d%d%d)%a?)"); if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later if not is_valid_year(year2) then return false; end -- no year farther in the future than next year month = get_season_number (month); -- for metadata
elseif mw.ustring.match(date_string, "^%D- +patterns[1'My-9My']%d%d%d +[%-–] +%D- +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash month, year, month2, anchor_year, year2=mw.ustring.match(date_string, "(%Dpatterns['My-) +(%d%d%d%d) +My'][%-–1] +(%D-) +((%d%d%d%d)%a?)"); anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years 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 0 ~= get_month_number(month) and 0 ~= get_month_number(month2) and is_valid_month_range_style(month, month2) then -- both must be month year, same month style
month = get_month_number(month);
month2 = get_month_number(month2);
elseif 0 ~= get_season_number(month) and 0 ~= get_season_number(month2) then -- both must be or season year, not mixed
month = get_season_number(month);
month2 = get_season_number(month2);
end
elseif mw.ustring.match(date_string, "^%D-patterns[%'M-My']%D- +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash month, month2, anchor_year, year=mw.ustring.match(date_string, "(%Dpatterns['M-)My'][%-–1](%D-)%s*((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or (not is_valid_year(year)) then return false; end
if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season
year2=year;
elseif mw.ustring.match(date_string, "^%D- +%d%d%d%d%a?$"patterns['My'][1]) then -- month/season year or proper-name year month, anchor_year, year=mw.ustring.match(date_string, "(%D-)%s*((%d%d%d%d)%a?)"patterns['My'][1]);
if not is_valid_year(year) then return false; end
if not is_valid_month_or_season (month) and 0 == is_proper_name (month) then return false; end
end
elseif mw.ustring.match(date_string, "^patterns[1-9]%d%d%d?[%'y-y'][1-9]%d%d%d?%a?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999 year, anchor_year, year2=mw.ustring.match(date_string, "(%d%d%d%d?)patterns[%'y-y'][1]((%d%d%d%d?)%a?)");
anchor_year=year..'–'..anchor_year; -- assemble anchor year from both years
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif mw.ustring.match(date_string, "^patterns[1'y4-9y2']%d%d%d[%-–1]%d%d%a?$") then -- Year range: YYYY–YY; separated by unspaced endash
local century;
year, century, anchor_year, year2=mw.ustring.match(date_string, "((%d%d)%d%d)patterns[%'y4-y2'][1]((%d%d)%a?)");
anchor_year=year..'–'..anchor_year; -- assemble anchor year from both years
if 13 > tonumber(year2) then return false; end -- don't allow 2003-05 which might be May 2003
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif date_string:match("^patterns['y'][1-9]%d%d%d?%a?$") then -- year; here accept either YYY or YYYY anchor_year, year=date_string:match("((%d%d%d%d?)%a?)"patterns['y'][1]);
if false == is_valid_year(year) then
return false;
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(v.val) then -- if the parameter has a value v.val = mw.ustring.gsub (v.val, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9 if v.val:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year= v = mw.ustring.gsub (v, '%d', cfg.date_names.local_digits); 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
end
elseif 'date'==k then -- if the parameter is |date=
if v.val:match("^n%.d%.%a?$") then -- if |date=n.d. with or without a CITEREF disambiguator good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date elseif v.val:match("^nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
else
good_date, anchor_year, COinS_date = check_date (v.val, 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 'access-date'==k then -- if the parameter is |date=
good_date = check_date (v.val, nil, true); -- go test the date; nil is a placeholder; true is the test_accessdate flag
elseif 'embargo'==k then -- if the parameter is |embargo=
good_date = check_date (v.val); -- 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 |embargo= date a single dmy, mdy, or ymd formatted date? yes:returns embargo; no: returns 9999
end
else -- any other date-holding parameter
good_date = check_date (v.val); -- go test the date
end
if false==good_date then -- assemble one error message so we don't add the tracking category multiple times
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "&#124;" .. k v.name .. "="; -- add the failed parameter
end
end
end
return anchor_year, embargo_date, error_message; -- and done
end
end
elseif mw.ustring.match(date_string, "%d%d%d%d[%-–]%d%d") then -- YYYY-YY date ranges
local century;
date1, century, date2 = mw.ustring.match(date_string, "((%d%d)%d%d)[%-–]+(%d%d)");
--[[--------------------------< R E F O R M A T T A B L E S R >--------------------------------------------------------
These table are used exclusively reformat 'date' into new format specified by format_param if pattern_idx (the current format of 'date') can bereformatted. Does the grunt work for reformatting datesreformat_dates().
The table re_formats maps patern_idx (current format) and format_param (desired format) to a table that holds: 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 patterns[pattern_idx][1]
local source_patterns = Items in patterns{ -- this table holds patterns that match allowed date formats used to extract date components} have the general form: ['dmyymd'] = {'^(%d%d?)%s+(d%a+d)%s+-(%d%d)%-(%d%d)$', ['mdyy', '] = m'^(%a+)%s+(%d%d?),%s+(%d%d%'d%d)$'},where: ['ymd'] = is pattern_idx patterns['ymd'^][1] is the match pattern with captures for mw.ustring.match(%d%d%d%d)%-(%d%d)-(%d%d)$ patterns['ymd',][2] is an indicator letter identifying the content of the first capture } patterns['ymd'][3] ... the second capture etc
local short_formats = when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifiercharacters as indexes into t{ -- this table holds format strings used by os.} For the above, a ymd date() for short month namesis in t{} as: ['dmy'] t.y = '%e %b %Y'first capture (year), ['mdy'] t.m = '%b %esecond capture (month), %Y', ['ymd'] t.d = '%F', }third capture (day)
local long_formats = { -- To reformat, this function is called with the pattern_idx that matches the current format of the date and withformat_param set to the desired format. This function loads table holds t{} as described and then calls string.format strings used by os.date() for long month names with the format string specified by re_format['dmy'pattern_idx] = '%e %B %Y', ['mdy'format_param] = '%B %e, %Y', ['ymd'1] = '%F', using values taken from t{}according  --to the capture identifier letters specified by patterns[pattern_idx][format_param][-------------------------< G E T _ D M Y _ D A T E _ P A R T S >------------------------------------------ extracts year, month and day from DMY formatted date, places them in the source_date table, and returnsn] where n is 2..
]]
local function get_dmy_date_parts (re_formats = { ['ymd'] = { -- dateformat is ymd; reformat to: ['mdy'] = {'%s %s, %s', 'm', source_date)'d', 'y'}, -- |df=mdy ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy-- source_date['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.daywiki }, ['Mdy'] = { -- date format is Mdy; reformat to: ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- for long/short reformatting ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd-- ['yMd'] = {'%s %s %s', 'y', 'm', source_date'd'}, -- |df=yMd; not supported at en.monthwiki }, ['dMy'] = { -- date format is dMy; reformat to: ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s, %s', 'm', 'd', source_date'y'}, -- |df=mdy ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.year wiki }, ['Md-dy'] = { -- dateformat is Md-dy; reformat to:match (source_patterns ['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- for long/short reformatting ['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- |df=dmy-> d-dMy }, ['d-dMy'])= { -- date format is d-d>y; reformat to: ['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- |df=mdy -> Md-dy }, ['dM-dMy'] = { -- get date components as stringsformat is dM-dMy; reformat to: ['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- for long/short reformatting ['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- |df=mdy -> Md-Mdy }, ['Md-Mdy'] = { -- date format is Md-Mdy; reformat to: ['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- for long/short reformatting ['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- |df=dmy -> dM-dMy }, ['dMy-dMy'] = { -- date format is dMy-dMy; reformat to: ['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- for long/short reformatting ['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- |df=mdy -> Mdy-Mdy }, source_date['Mdy-Mdy'] = { -- date format is Mdy-Mdy; reformat to: ['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- for long/short reformatting ['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- |df=dmy -> dMy-dMy }, ['My-My'] = { -- these for long/short reformatting ['any'] = {'%s %s – %s %s', 'm', 'y', 'm2', 'y2'}, -- dmy/mdy agnostic }, ['M-My'] = { -- these for long/short reformatting ['any'] = {'%s–%s %s', 'm', 'm2', 'y'}, -- dmy/mdy agnostic }, ['My'] = { -- these for long/short reformatting ['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic },-- ['yMd'] = { -- not supported at en.month wiki-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df= get_month_number (source_date.month); mdy-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd-- get month number },end }
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 patterns then not a reformattable date end if 'ymd' == format_param and in_array (pattern_idx, {'ymd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My---------< G E T _ My', 'M D Y _ D A T E _ P A R T S >----------------------------------------My', 'My'}) then return; --ymd date ranges not supported at en.wiki; no point in reformatting ymd to ymd end
extracts year if in_array (pattern_idx, month and day from MDY formatted date{'My', places them in the source_date table'M-My', and returns.'My-My'}) then -- these are not dmy/mdy so can't be 'reformatted' into either format_param = 'any'; -- so format-agnostic end
-- if 'yMd' == format_param and in_array (pattern_idx, {'yMd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy'}) then -- not supported at en.wiki if 'yMd' == format_param then -- 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 patterns[pattern_idx][1] c1, c2, c3, c4, c5, c6, c7 = mw.ustring.match (date, patterns[pattern_idx][1]); -- get the captures
local function get_mdy_date_parts (t = { -- table that holds k/v pairs of date, source_date) source_dateparts from the captures and patterns[pattern_idx][2.month, source_date.day, source_date.year ] [patterns[pattern_idx][2]] = c1; -- at minimum there is always one capture with a matching indicator letter [patterns[pattern_idx][3] or 'x'] = date:match (source_patternsc2; -- patterns can have a variable number of captures; each capture requires an indicator letter; [patterns[pattern_idx][4] or 'mdyx'])= c3; -- get date components as stringswhere there is no capture, there is no indicator letter so n in patterns[pattern_idx][n] will be nil; source_date.month [patterns[pattern_idx][5] or 'x'] = get_month_number (source_date.month)c4; -- get month numberthe 'x' here spoofs an indicator letter to prevent 'table index is nil' error [patterns[pattern_idx][6] or 'x'] = c5; [patterns[pattern_idx][7] or 'x'] = c6; [patterns[pattern_idx][8] or 'x'] = c7;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['inv_local_s'][tonumber(t.m)]; -- convert it to a month name
else
t.m = cfg.date_names['inv_local_l'][tonumber(t.m)]; -- convert it to a month name
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
if 1582 > tonumber(t.y) then -- ymd format dates not allowed before 1582
return;
end
t.m = string.format ('%02d', get_month_number (t.m)); -- make sure that month and day are two digits
t.d = string.format ('%02d', t.d);
elseif mon_len then -- if mon_len is set to either 'short' or 'long'
for _, mon in ipairs ({'m', 'm2'}) do -- because there can be two month names, check both
if t[mon] then
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['inv_local_s'][t[mon]]) or cfg.date_names['inv_local_l'][t[mon]]; -- fetch month name according to length
end
end
end
local new_date = string.format (re_formats[pattern_idx][format_param][1], --format string t[re_formats[pattern_idx][format_param][2]], -------------------------< G E T _ Y M D _ D A T E _ P A R T S >------------------------------------------named captures from t{} t[re_formats[pattern_idx][format_param][3]], t[re_formats[pattern_idx][format_param][4]], t[re_formats[pattern_idx][format_param][5]], t[re_formats[pattern_idx][format_param][6]], t[re_formats[pattern_idx][format_param][7]], t[re_formats[pattern_idx][format_param][8]] );
extracts year, month and day from YMD formatted date, places them in the source_date table, and returns. ]] local function get_ymd_date_parts (date, source_date) source_date.year, source_date.month, source_date.day = date:match (source_patterns['ymd'])return new_date; -- get date components as strings
end
--[[-------------------------< R E F O R M A T _ D A T E S >--------------------------------------------------
Reformats existing dates into the format specified by format and short.
format is one of several manual keywords: dmy, dmy-all, mdy, mdy-all, ymd, ymd-all. The -all version includes access- andarchive-dates; otherwise these dates are not reformatted.
Date rangesThis function allows automatic date formatting. In ~/Configuration, season the article source is searched for one ofthe {{use xxx dates}} templates. If found, proper name xxx becomes the global date format as xxx-all. If |cs1-dates= in{{use xxx dates}} has legitimate value then that value determines how cs1|2 dates will be rendered. Legitimatevalues for |cs1-dates= are: l - all dates are rendered with long month names ls - publication dates use long month names; access-/archive-dates use abbreviated month names ly - publication dates use long month names; access-/archive-dates rendered in ymd format s - all dates are not currently supported.rendered with abbreviated (short) month names sy - publication dates use abbreviated month names; access-/archive-dates rendered in ymd format y - all dates are rendered in ymd format
For i18n: This code works only at en.wiki because os.the format argument for automatic date() doesn't support any languages other than English.formatting will be the format specified by {{use xxx dates}} with themw.getContentLanguage()value supplied by |cs1-dates so one of:formatDate() will work at nonxxx-l, xxx-ls, xxx-ly, xxx-s, xxx-English wikis only when the date format is yyyysy, xxx-mmy, or simply xxx (|cs1-dd. This isdates=the same issue that plagues is_valid_accessdate(empty, omitted, or invalid)where xxx shall be either of dmy or mdy.
It dates are extracted from date_parameters_list, reformatted (if appropriate), and then written back into thelist in the new format. Dates in date_parameters_list are presumed here to be valid (no errors). This functionreturns true when a date has been reformatted, false else. Actual reformatting is possible that a solution like that written for ht:Module:Citation/CS1/Date_validation date_name_xlatedone by reformatter() could be applied to this problem.
]]
local function reformat_dates (date_parameters_list, format, short)
local all = false; -- set to false to skip access- and archive-dates
local format_strlen_p = 'l'; -- default publication date length shall be long local len_a = 'l'; -- default access-/archive-date length shall be long local source_date result = {}false; local new_date;
if format:match('%a+%-all') then -- manual df keyword; auto df keyword when length not specified in {{use xxx dates}};
format = format:match('(%a+)%-all'); -- extract the format
all = true; -- set to all dates are long format dates because this keyword doesn't specify length elseif format:match('%a+%-[lsy][sy]?') then -- auto df keywords; internal only all = true ; -- auto df applies to all dates; use length specified by capture len_p for all dates format, len_p, len_a = format:match('(%a+)%-([lsy])([sy]?)'); -- extract the format and length keywords if 'y' == len_p then -- because allowed by MOS:DATEUNIFY (sort of) range dates and My dates not reformatted format = 'ymd'; -- override {{use xxx dates}} elseif (not is_set(len_a)) or (len_p == len_a) then -- no access- and /archive-date length specified or same length as publication datesthen len_a = len_p; -- in case len_a not set end end -- else only publication dates and they are long
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 if not (not all and in_array (param_name, {'access-date', 'archive-date'})) then -- if skip access- or archive-date and unless format not is xxx-all; yeah, ugly; TODO: find a better way param_val = ''; -- set to empty string so we don't process this date end for sourcepattern_idx, pattern in pairs (source_patternspatterns) do if param_val:mw.ustring.match (param_val.val, pattern[1]) then if all and in_array (param_name, {'ymdaccess-date' == source then get_ymd_date_parts (param_val, source_date'archive-date'}); then -- if this date is an access-or archive- get the date parts into the source_date table elseif 'dmy' new_date == source then get_dmy_date_parts reformatter (param_val.val, pattern_idx, source_date); -- get the date parts into the source_date table elseif (('mdyy' == source then get_mdy_date_parts (param_val, source_datelen_a); -- get the date parts into the source_date table end  if and 'ymd' == ) or format and 1582 > tonumber(source_date.year, len_a) then ; -- choose ymd format dates not allowed before 1582or dmy/mdy according to len_a setting return false; else -- abandon reformattingall other dates end if short then format_str new_date = short_formats[reformatter (param_val.val, pattern_idx, format], len_p); else end format_str = long_formats[format]; end if new_date then -- convert set when date and save;was reformatted date_parameters_list[param_name] .val = mw.text.trim (os.new_date; -- update date in date (format_str, os.time(source_date)))list result = true; -- strip leading space when single digit day and %e is first formatannounce that changes have been made end end -- if end -- for end -- if end -- if end -- for return trueresult; -- declare success boolean result and done
end
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) then if not param_val:mw.ustring.match (param_val.val, '%d%d%d%d%-%d%d%-%d%d') then -- for those that are not ymd dates(ustring because here digits may not be western) param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash if 0 ~= n then date_parameters_list[param_name] .val = param_val.val; -- update the list result = true; end
end
end
Attempts to translate English month names to local-language month names using names supplied by MediaWiki's
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 western (English) digits to the local language's digits.
This will also translate ymd dates.
]]
local function date_name_xlate (date_parameters_list, xlt_dig)
local xlate;
local mode; -- long or short month names
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 -- iterate through all dates in the date (single date or date range)
if cfg.date_names.en.long[month] then
end
if mode then -- might be a season xlate = mw.getContentLanguage():formatDate(mode, '1' .. month); -- translate the month name to this local language date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation date_parameters_list[param_name] .val = date; -- save the translated date
modified = true;
end
end
if xlt_dig then -- shall we also translate digits?
date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from western to 'local digits'
date_parameters_list[param_name].val = date; -- save the translated date
modified = true;
end
end
end
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
return { -- return exported functions