Module:Citation/CS1/Date validation

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 Module:Citation/CS1/Configuration

--[=[-------------------------< I S _ V A L I D _ A C C E S S D A T E >----------------------------------------

returns true if: Wikipedia start date <= accessdate < today + 2 days

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 |accessdate= at time 00:00:00 UTC today is the current date at time 00:00:00 UTC plus 48 hours if today is 2015-01-01T00:00:00 then adding 24 hours gives 2015-01-02T00:00:00 – one second more than today adding 24 hours gives 2015-01-03T00:00:00 – one second more than tomorrow

This function does not work if it is fed month names for languages other than English. Wikimedia #time: parser apparently doesn't understand non-Engish date month names. This function will always return false when the date 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.

]=]

local function is_valid_accessdate (accessdate) local lang = mw.getContentLanguage(); local good1, good2; local access_ts, tomorrow_ts; -- to hold unix time stamps representing the dates

good1, access_ts = pcall( lang.formatDate, lang, 'U', accessdate ); -- convert accessdate value to unix timesatmp good2, tomorrow_ts = pcall( lang.formatDate, lang, '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:parseFormattedNumber (access_ts); -- convert to numbers for the comparison; tomorrow_ts = tonumber (tomorrow_ts) or lang:parseFormattedNumber (tomorrow_ts); else return false; -- one or both failed to convert to unix time stamp end

if 979516800 <= access_ts and access_ts < tomorrow_ts then -- Wikipedia start date <= accessdate < tomorrow's date return true; else return false; -- accessdate out of range end end

--[[--------------------------< G E T _ M O N T H _ N U M B E R >----------------------------------------------

returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct. If not a valid month, returns 0

]]

local function get_month_number (month) return cfg.date_names['local'].long[month] or cfg.date_names['local'].short[month] or -- look for local names first cfg.date_names['en'].long[month] or cfg.date_names['en'].short[month] or -- failing that, look for English names 0; -- not a recognized month name end

--[[--------------------------< 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 |embargo= is set, the editor intended to embargo a pmc but |embargo= does not hold a single date.

]]

local function is_valid_embargo_date (v) if v:match ('^%d%d%d%d%-%d%d%-%d%d$') or -- ymd v:match ('^%d%d?%s+%a+%s+%d%d%d%d$') or -- dmy v:match ('^%a+%s+%d%d?%s*,%s*%d%d%d%d$') 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

--[[--------------------------< G E T _ S E A S O N _ N U M B E R >--------------------------------------------

returns a number according to the sequence of seasons in a year: 1 for Winter, etc. Capitalization and spelling must be correct. If not a valid season, returns 0

Uses ISO DIS 8601 2016 part 2 §4.7 Divisions of a year for hemishpere-independent seasons: 21-24 = Spring, Summer, Autumn, Winter, independent of “Hemisphere”

These additional divisions not currently supported: 25-28 = Spring - Northern Hemisphere, Summer- Northern Hemisphere, Autumn - Northern Hemisphere, Winter - Northern Hemisphere 29-32 = Spring – Southern Hemisphere, Summer– Southern Hemisphere, Autumn – Southern Hemisphere, Winter - Southern Hemisphere 33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each) 37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each) 40-41 = Semestral 1, Semestral-2 (6 months each)

]]

local function get_season_number (season) return cfg.date_names['local'].season[season] or -- look for local names first cfg.date_names['en'].season[season] or -- failing that, look for English names 0; -- not a recognized season name end

--[[--------------------------< I S _ P R O P E R _ N A M E >--------------------------------------------------

returns a non-zero number if date contains a recognized proper name. Capitalization and spelling must be correct.

]]

local function is_proper_name (name) return cfg.date_names['local'].named[name] or -- look for local names dates first cfg.date_names['en'].named[name] or -- failing that, look for English names 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 >------------------------------

--returns true if month or season is valid (properly spelled, capitalized, abbreviated)

]]

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 >----------------------------------------------------

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.

]] local year_limit; 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 >---------------------------------------------------- Returns true if day is less than or equal to the number of days in month and year is no farther into the future than next year; else returns false.

Assumes Julian calendar prior to year 1582 and Gregorian calendar thereafter. Accounts for Julian calendar leap years before 1582 and Gregorian leap years after 1582. Where the two calendars overlap (1582 to approximately 1923) dates are assumed to be Gregorian.

]]

local function is_valid_date (year, month, day) 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) then -- no farther into the future than next year return false; end

month = tonumber(month); -- required for YYYY-MM-DD dates

if (2==month) then -- if February month_length = 28; -- then 28 days unless if 1582 > tonumber(year) then -- Julian calendar if 0==(year%4) then month_length = 29; end else -- Gregorian calendar if (0==(year%4) and (0~=(year%100) or 0==(year%400))) then -- is a leap year? month_length = 29; -- if leap year then 29 days in February end end else month_length=days_in_month[month]; end

if tonumber (day) > month_length then return false; end 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 >--------------------------

Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August. There is a special test for May because it can be either short or long form.

Returns true when style for both months is the same

]]

local function is_valid_month_range_style (month1, month2) local len1 = month1:len(); local len2 = month2:len(); if len1 == len2 then return true; -- both months are short form so return true elseif 'May' == month1 or 'May'== month2 then return true; -- both months are long form so return true elseif 3 == len1 or 3 == len2 then return false; -- months are mixed form so return false else return true; -- both months are long form so return true end end

--[[--------------------------< I S _ V A L I D _ M O N T H _ S E A S O N _ R A N G E >------------------------

Check a pair of months or seasons to see if both are valid members of a month or season pair.

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 so ... ok

]]

local function is_valid_month_season_range(range_start, range_end) local range_start_number = get_month_number (range_start); local range_end_number;

if 0 == range_start_number then -- is this a month range? range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number range_end_number = get_season_number (range_end); -- get end season number

if (0 ~= range_start_number) and (0 ~= range_end_number) then return true; -- any season pairing is accepted end return false; -- range_start and/or range_end is not a season end -- 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 then -- range_start is a month; does range_start precede range_end? if is_valid_month_range_style (range_start, range_end) then -- do months have the same style? return true; -- proper order and same style end end return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month end

--[[--------------------------< M A K E _ C O I N S _ D A T E >------------------------------------------------

This function receives a table of date parts for one or two dates and an empty table reference declared in Module:Citation/CS1. The function is called only for |date= parameters and only if the |date=<value> is determined to be a valid date format. The question of what to do with invalid date formats is not answered here.

The date parts in the input table are converted to an ISO 8601 conforming date string: single whole dates: yyyy-mm-dd month and year dates: yyyy-mm year dates: yyyy ranges: yyyy-mm-dd/yyyy-mm-dd yyyy-mm/yyyy-mm yyyy/yyyy

Dates in the Julian calendar are reduced to year or year/year so that we don't have to do calendar conversion from Julian to Proleptic Gregorian.

The input table has: year, year2 – always present; if before 1582, ignore months and days if present month, month2 – 0 if not provided, 1-12 for months, 21-24 for seasons; 99 Christmas day, day2 – 0 if not provided, 1-31 for days

the output table receives: rftdate: an IS8601 formatted date rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and propername dates) rftssn: one of four season keywords: winter, spring, summer, fall (lowercase)

]]

local function make_COinS_date (input, tCOinS_date) local date; -- one date or first date in a range local date2 = ; -- end of range date -- start temporary Julian / Gregorian calendar uncertainty detection local year = tonumber(input.year); -- this temporary code to determine the extent of sources dated to the Julian/Gregorian local month = tonumber(input.month); -- interstice 1 October 1582 – 1 January 1926 local day = tonumber (input.day); if (0 ~= day) and -- day must have a value for this to be a whole date (((1582 == year) and (10 <= month) and (12 >= month)) or -- any whole 1582 date from 1 october to 31 December or ((1926 == year) and (1 == month) and (1 == input.day)) or -- 1 January 1926 or ((1582 < year) and (1925 >= year))) then -- any date 1 January 1583 – 31 December 1925 tCOinS_date.inter_cal_cat = true; -- set category flag true end -- end temporary Julian / Gergorian calendar uncertainty detection

if 1582 > tonumber(input.year) or 20 < tonumber(input.month) then -- Julian calendar or season so &rft.date gets year only date = input.year; 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', tonumber(input.year), tonumber(input.year2)) -- assemble the date range end if 20 < tonumber(input.month) then -- if season or propername date local season = {[24]='winter', [21]='spring', [22]='summer', [23]='fall', [99]='Christmas'}; -- seasons lowercase, no autumn; proper names use title case if 0 == input.month2 then -- single season date if 30 <tonumber(input.month) then tCOinS_date.rftchron = season[input.month]; -- proper name dates else tCOinS_date.rftssn = season[input.month]; -- seasons end else -- season range with a second season specified if input.year ~= input.year2 then -- season year – season year range or season year–year tCOinS_date.rftssn = season[input.month]; -- start of range season; keep this? if 0~= input.month2 then tCOinS_date.rftchron = string.format ('%s %s – %s %s', season[input.month], input.year, season[input.month2], input.year2); end else -- season–season year range tCOinS_date.rftssn = season[input.month]; -- start of range season; keep this? tCOinS_date.rftchron = season[input.month] .. '–' .. season[input.month2]; -- season–season year range end end end tCOinS_date.rftdate = date; return; -- done end

if 0 ~= input.day then date = string.format ('%s-%.2d-%.2d', input.year, tonumber(input.month), tonumber(input.day)); -- whole date elseif 0 ~= input.month then date = string.format ('%s-%.2d', input.year, tonumber(input.month)); -- year and month else date = string.format ('%s', input.year); -- just year end

if 0 ~= input.year2 then if 0 ~= input.day2 then date2 = string.format ('/%s-%.2d-%.2d', input.year2, tonumber(input.month2), tonumber(input.day2)); -- whole date elseif 0 ~= input.month2 then date2 = string.format ('/%s-%.2d', input.year2, tonumber(input.month2)); -- year and month else date2 = string.format ('/%s', input.year2); -- just year end end

tCOinS_date.rftdate = date .. date2; -- date2 has the '/' separator return; end

--[[--------------------------< C H E C K _ D A T E >----------------------------------------------------------

Check date format to see that it is one of the formats approved by WP:DATESNO or WP:DATERANGE. Exception: only allowed range separator is endash. Additionally, check the date to see that it is a real date: no 31 in 30-day months; no 29 February when not a leap year. Months, both long-form and three character abbreviations, and seasons must be spelled correctly. Future years beyond next year are not allowed.

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 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, accessdate, embargo, archivedate, etc.)

Returns: false if date string is not a real date; else true, anchor_year, COinS_date anchor_year can be used in CITEREF anchors COinS_date is ISO 8601 format date; see make_COInS_date()

]]

local function check_date (date_string, tCOinS_date, test_accessdate) local year; -- assume that year2, months, and days are not used; local year2=0; -- second year in a year range local month=0; local month2=0; -- second month in a month range local day=0; local day2=0; -- second day in a day range local anchor_year; local coins_date;

if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- year-initial numerical year month day format year, month, day=string.match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)"); if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar anchor_year = year; elseif mw.ustring.match(date_string, "^%D- +[1-9]%d?, +[1-9]%d%d%d%a?$") 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?)"); 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?[%-–][1-9]%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, "(%D-) +(%d%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 month2=month; -- for metadata year2=year;

elseif mw.ustring.match(date_string, "^[1-9]%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?)"); 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%d%d%a? +%D- +%d%d?$") then -- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed anchor_year, year, month, day=mw.ustring.match(date_string, "((%d%d%d%d?)%a?) +(%D-) +(%d%d?)"); 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, "^[1-9]%d?[%-–][1-9]%d? +%D- +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash day, day2, month, anchor_year, year=mw.ustring.match(date_string, "(%d%d?)[%-–](%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 month2=month; -- for metadata year2=year;

elseif mw.ustring.match(date_string, "^[1-9]%d? +%D- +[%-–] +[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?) +(%D-) +[%-–] +(%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- +[1-9]%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, "(%D-) +(%d%d?) +[%-–] +(%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, "^[1-9]%d? +%D- +[1-9]%d%d%d +[%-–] +[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?) +(%D-) +(%d%d%d%d) +[%-–] +(%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- +[1-9]%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, "(%D-) +(%d%d?), +(%d%d%d%d) +[%-–] +(%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- +[1-9]%d%d%d[%-–]%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, "(%D-) +((%d%d)%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 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- +[1-9]%d%d%d[%-–][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, "(%D-) +(%d%d%d%d)[%-–]((%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- +[1-9]%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, "(%D-) +(%d%d%d%d) +[%-–] +(%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); else return false; end

elseif mw.ustring.match(date_string, "^%D-[%-–]%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, "(%D-)[%-–](%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 month = get_month_number(month); month2 = get_month_number(month2); else month = get_season_number(month); month2 = get_season_number(month2); end year2=year;

elseif mw.ustring.match(date_string, "^%D- +%d%d%d%d%a?$") then -- month/season year or proper-name year month, anchor_year, year=mw.ustring.match(date_string, "(%D-)%s*((%d%d%d%d)%a?)"); 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 if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season month = get_month_number(month); elseif 0 ~= get_season_number(month) then month = get_season_number(month); else month = is_proper_name (month); -- must be proper name; not supported in COinS end

elseif mw.ustring.match(date_string, "^[1-9]%d%d%d?[%-–][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?)[%-–]((%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, "^[1-9]%d%d%d[%-–]%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)[%-–]((%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 year2 = century..year2; -- add the century to year2 for comparisons 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 date_string:match("^[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?)"); if false == is_valid_year(year) then return false; end

else return false; -- date format not one of the MOS:DATE approved formats end

if test_accessdate then -- test accessdate 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; accessdate must not be a range if not is_valid_accessdate (year..'-'..month..'-'..day) then return false; -- return false when accessdate out of bounds end else return false; -- return false when accessdate is a range of two dates end end

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);

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

if false == result then return false; end

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

return true, anchor_year; -- format is good and date string represents a real date end

--[[--------------------------< D A T E S >--------------------------------------------------------------------

Cycle the date-holding parameters in passed table date_parameters_list through check_date() to check compliance with MOS:DATE. For all valid dates, check_date() returns true. The |date= parameter test is unique, it is the only date holding parameter from which values for anchor_year (used in CITEREF identifiers) and COinS_date (used in the COinS metadata) are derived. The |date= parameter is the only date-holding parameter that is allowed to contain the no-date keywords "n.d." or "nd" (without quotes).

Unlike most error messages created in this module, only one error message is created by this function. Because all of the date holding parameters are processed serially, a single error message is created as the dates are tested.

]]

local function dates(date_parameters_list, tCOinS_date) local anchor_year; -- will return as nil if the date being tested is not |date= 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 error_message = ""; 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 (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?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year= local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested if 'date'==k then anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter good_date = is_valid_year(year); elseif 'year'==k then good_date = is_valid_year(year); end elseif 'date'==k then -- if the parameter is |date= if v.val:match("^n%.d%.%a?$") then -- 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 if is_set(error_message) then -- once we've added the first portion of the error message ... error_message=error_message .. ", "; -- ... add a comma space separator end error_message=error_message .. "|" .. v.name .. "="; -- add the failed parameter end end end return anchor_year, embargo_date, error_message; -- and done end

--[[--------------------------< 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 returns a numeric value: 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)

]]

local function year_date_check (year_string, date_string) 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') and year_string:match ('%d%d%d%d%a') then --special case where both date and year are required YYYY-MM-DD and YYYYx 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 else result = 2; -- years match; but because disambiguated, don't add to maint cat end

elseif date_string:match ("%d%d%d%d?.-%d%d%d%d?") then -- any of the standard range formats of date with two three- or four-digit years date1, date2 = date_string:match ("(%d%d%d%d?).-(%d%d%d%d?)"); if year ~= date1 and year ~= date2 then result = 0; 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)"); date2 = century..date2; -- convert YY to YYYY if year ~= date1 and year ~= date2 then result = 0; end

elseif date_string:match ("%d%d%d%d?") then -- any of the standard formats of date with one year date1 = date_string:match ("(%d%d%d%d?)"); if year ~= date1 then result = 0; end else result = 0; -- no recognizable year in date end return result; end

--[[-------------------------< R E F O R M A T T A B L E S >------------------------------------------------

These table are used exclusively for reformatting dates

]]

local source_patterns = { -- this table holds patterns that match allowed date formats used to extract date components ['dmy'] = '^(%d%d?)%s+(%a+)%s+(%d%d%d%d)$', ['mdy'] = '^(%a+)%s+(%d%d?),%s+(%d%d%d%d)$', ['ymd'] = '^(%d%d%d%d)%-(%d%d)-(%d%d)$', }

local short_formats = { -- this table holds format strings used by os.date() for short month names ['dmy'] = '%e %b %Y', ['mdy'] = '%b %e, %Y', ['ymd'] = '%F', }

local long_formats = { -- this table holds format strings used by os.date() for long month names ['dmy'] = '%e %B %Y', ['mdy'] = '%B %e, %Y', ['ymd'] = '%F', }

--[[-------------------------< 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 returns.

]]

local function get_dmy_date_parts (date, source_date) source_date.day, source_date.month, source_date.year = date:match (source_patterns['dmy']); -- get date components as strings source_date.month = get_month_number (source_date.month); -- get month number end

--[[-------------------------< G E T _ M D Y _ D A T E _ P A R T S >------------------------------------------

extracts year, month and day from MDY formatted date, places them in the source_date table, and returns.

]]

local function get_mdy_date_parts (date, source_date) source_date.month, source_date.day, source_date.year = date:match (source_patterns['mdy']); -- get date components as strings source_date.month = get_month_number (source_date.month); -- get month number end

--[[-------------------------< G E T _ Y M D _ D A T E _ P A R T S >------------------------------------------

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']); -- 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 keywords: dmy, dmy-all, mdy, mdy-all, ymd, ymd-all. The all version includes access- and archive-dates; otherwise these dates are not reformatted

Date ranges, season dates, proper name dates are not currently supported.

For i18n: This code works only at en.wiki because os.date() doesn't support any languages other than English. mw.getContentLanguage():formatDate() will work at non-English wikis only when the date format is yyyy-mm-dd. This is the same issue that plagues is_valid_accessdate()

It is possible that a solution like that written for ht:Module:Citation/CS1/Date_validation date_name_xlate() 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 result = false; local format_str; local source_date = {};

if format:match('%a+%-all') then format = format:match('(%a+)%-all'); -- extract the format all = true; -- set to true to format access- and archive-dates 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 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 source, pattern in pairs (source_patterns) do if param_val.val:match (pattern) then if 'ymd' == source then get_ymd_date_parts (param_val.val, source_date); -- get the date parts into the source_date table elseif 'dmy' == source then get_dmy_date_parts (param_val.val, source_date); -- get the date parts into the source_date table elseif 'mdy' == source then get_mdy_date_parts (param_val.val, source_date); -- get the date parts into the source_date table end

if 'ymd' == format and 1582 > tonumber(source_date.year) then -- ymd format dates not allowed before 1582 return false; -- abandon reformatting end

if short then format_str = short_formats[format]; else format_str = long_formats[format]; end -- convert date and save; date_parameters_list[param_name].val = mw.text.trim (os.date (format_str, os.time(source_date))); -- strip leading space when single digit day and %e is first format result = true; end -- if end -- for end -- if end -- if end -- for return result; -- declare result and done end

--[[--------------------------< D A T E _ H Y P H E N _ T O _ D A S H >----------------------------------------

Loops through the list of date-holding parameters and converts any hyphen to an ndash. Not called if the cs1|2 template has any date errors.

Modifies the date_parameters_list and returns true if hyphens are replaced, else returns false.

]]

local function date_hyphen_to_dash (date_parameters_list) local result = false; 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 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 end return result; -- so we know if any hyphens were replaced end

--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------

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 local modified = false; local date;

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 mode = 'F'; -- English name is long so use long local name elseif cfg.date_names.en.short[month] then mode = 'M'; -- English name is short so use short local name else mode = nil; -- not an English month name; could be local language month name or an English season name 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

return modified; end

--[[--------------------------< S E T _ S E L E C T E D _ M O D U L E S >--------------------------------------

Sets local imported functions table to same (live or sandbox) as that used by the other modules.

]]

local function set_selected_modules (cfg_table_ptr, utilities_page_ptr) is_set = utilities_page_ptr.is_set; -- import functions from selected Module:Citation/CS1/Utilities module in_array = utilities_page_ptr.in_array; -- import functions from selected Module:Citation/CS1/Utilities module cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration end

return { -- return exported functions dates = dates, year_date_check = year_date_check, reformat_dates = reformat_dates, date_hyphen_to_dash = date_hyphen_to_dash, date_name_xlate = date_name_xlate, set_selected_modules = set_selected_modules }