Module:Citation/CS1/Date validation: Difference between revisions

Content added Content deleted
m (1 revision imported: Math)
(Synch from sandbox;)
Line 2: Line 2:
local p = {}
local p = {}



--[[--------------------------< I S _ V A L I D _ A C C E S S D A T E >----------------------------------------
--[[--------------------------< 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 function from selected Module:Citation/CS1/Utilities


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


returns true if:
returns true if:
Line 14: Line 21:
adding 24 hours gives 2015-01-03T00:00:00 – one second more than tomorrow
adding 24 hours gives 2015-01-03T00:00:00 – one second more than tomorrow


This function does not work 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.

For the time being, to use this function, supply it with YYYY-MM-DD format dates. See
[[bs:Modul:Citation/CS1/Date validation/igralište]] for one possible solution.

]=]


local function is_valid_accessdate (accessdate)
local function is_valid_accessdate (accessdate)
Line 37: Line 51:
end
end
end
end



--[[--------------------------< G E T _ M O N T H _ N U M B E R >----------------------------------------------
--[[--------------------------< G E T _ M O N T H _ N U M B E R >----------------------------------------------
Line 47: Line 62:
local long_months = {['January']=1, ['February']=2, ['March']=3, ['April']=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12};
local long_months = {['January']=1, ['February']=2, ['March']=3, ['April']=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12};
local short_months = {['Jan']=1, ['Feb']=2, ['Mar']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12};
local short_months = {['Jan']=1, ['Feb']=2, ['Mar']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12};
return long_months[month] or -- if month is the long-form name
local temp;
short_months[month] or -- if month is the short-form name
temp=long_months[month];
0; -- misspelled, improper case, or not a month name
if temp then return temp; end -- if month is the long-form name
temp=short_months[month];
if temp then return temp; end -- if month is the short-form name
return 0; -- misspelled, improper case, or not a month name
end
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 >--------------------------------------------
--[[--------------------------< G E T _ S E A S O N _ N U M B E R >--------------------------------------------
Line 62: Line 94:


local function get_season_number (season)
local function get_season_number (season)
local season_list = {['Winter']=1, ['Spring']=2, ['Summer']=3, ['Fall']=4, ['Autumn']=4}
local season_list = {['Winter']=21, ['Spring']=22, ['Summer']=23, ['Fall']=24, ['Autumn']=24}; -- make sure these numbers do not overlap month numbers
local temp;
local temp;
temp=season_list[season];
temp=season_list[season];
if temp then return temp; end -- if season is a valid name return its number
if temp then return temp; end -- if season is a valid name return its number
return 0; -- misspelled, improper case, or not a season name
return 0; -- misspelled, improper case, or not a season name
end
end


Line 76: Line 108:


local function is_proper_name (name)
local function is_proper_name (name)
local name_list = {['Christmas']=1}
local name_list = {['Christmas']=31}
local temp;
local temp;
temp=name_list[name];
temp=name_list[name];
Line 97: Line 129:
return true;
return true;
end
end



--[[--------------------------< I S _ V A L I D _ Y E A R >----------------------------------------------------
--[[--------------------------< I S _ V A L I D _ Y E A R >----------------------------------------------------
Line 104: Line 135:


]]
]]
local year_limit;

local function is_valid_year(year)
local function is_valid_year(year)
if not is_set(year_limit) then
if not is_set(year_limit) then
Line 112: Line 143:
end
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.
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.


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 function is_valid_date (year, month, day)
local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
local days_in_month = {31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31};
local month_length;
local month_length;
if not is_valid_year(year) then -- no farther into the future than next year
if not is_valid_year(year) then -- no farther into the future than next year
return false;
return false;
end
end
if (2==month) then -- if February
month = tonumber(month); -- required for YYYY-MM-DD dates
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
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
if 0==(year%4) then
month_length = 29;
month_length = 29;
end
end
else -- Gregorian calendar
else -- Gregorian calendar
if (0==(year%4) and (0~=(year%100) or 0==(year%400))) then -- is a leap year?
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
month_length = 29; -- if leap year then 29 days in February
end
end
end
end
Line 183: Line 220:
local function is_valid_month_season_range(range_start, range_end)
local function is_valid_month_season_range(range_start, range_end)
local range_start_number = get_month_number (range_start);
local range_start_number = get_month_number (range_start);
local range_end_number;
if 0 == range_start_number then -- is this a month range?
if 0 == range_start_number then -- is this a month range?
local range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number
local range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number
local range_end_number = get_season_number (range_end); -- get end season number
range_end_number = get_season_number (range_end); -- get end season number


if 0 ~= range_start_number then -- is start of range a season?
if 0 ~= range_start_number then -- is start of range a season?
if range_start_number < range_end_number then -- range_start is a season
if range_start_number < range_end_number then -- range_start is a season
return true; -- return true when range_end is also a season and follows start season; else false
return true; -- return true when range_end is also a season and follows start season; else false
end
end
if 4 == range_start_number and 1 == range_end_number then -- special case when range is Fall-Winter or Autumn-Winter
if 24 == range_start_number and 21 == range_end_number then -- special case when season range is Fall-Winter or Autumn-Winter
return true;
return true;
end
end
Line 199: Line 237:
end
end


local range_end_number = get_month_number (range_end); -- get end month number
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 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?
if is_valid_month_range_style (range_start, range_end) then -- do months have the same style?
return true; -- proper order and same style
return true; -- proper order and same style
end
end
end
end
return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month
return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month
end
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; 31– proper name dates
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
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 = {[21]='winter', [22]='spring', [23]='summer', [24]='fall', [31]='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 >----------------------------------------------------------
--[[--------------------------< 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.
Check date format to see that it is one of the formats approved by WP:DATESNO or WP:DATERANGE. Exception: only
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
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
character abbreviations, and seasons must be spelled correctly. Future years beyond next year are not allowed.
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
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
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.
its year from the year parameter if present otherwise CITEREF does not get a date value.


Inputs:
Inputs:
Line 224: Line 350:
true, anchor_year, COinS_date
true, anchor_year, COinS_date
anchor_year can be used in CITEREF anchors
anchor_year can be used in CITEREF anchors
COinS_date is date_string without anchor_year disambiguator if any
COinS_date is ISO 8601 format date; see make_COInS_date()

]]
]]

local function check_date (date_string)
local function check_date (date_string, tCOinS_date)
local year; -- assume that year2, months, and days are not used;
local year; -- assume that year2, months, and days are not used;
local year2=0; -- second year in a year range
local year2=0; -- second year in a year range
Line 238: Line 366:
if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- year-initial numerical year month day format
if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- year-initial numerical year month day format
year, month, day=string.match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)");
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
month=tonumber(month);
if 12 < month or 1 > month or 1583 > tonumber(year) then return false; end -- month number not valid or not Gregorian calendar
anchor_year = year;
anchor_year = year;


Line 247: Line 374:
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
elseif date_string:match("^%a+ +[1-9]%d?–[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d?[%-–][1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash
month, day, day2, anchor_year, year=string.match(date_string, "(%a+) +(%d%d?)–(%d%d?), +((%d%d%d%d)%a?)");
month, day, day2, anchor_year, year=mw.ustring.match(date_string, "(%a+) +(%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;
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);
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
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 date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-initial: day month year
elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-initial: day month year
Line 258: Line 387:
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
if 0 == month then return false; end -- return false if month text isn't one of the twelve months


elseif date_string:match("^[1-9]%d?–[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash
elseif mw.ustring.match(date_string, "^[1-9]%d?[%-–][1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash
day, day2, month, anchor_year, year=string.match(date_string, "(%d%d?)–(%d%d?) +(%a+) +((%d%d%d%d)%a?)");
day, day2, month, anchor_year, year=mw.ustring.match(date_string, "(%d%d?)[%-–](%d%d?) +(%a+) +((%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;
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);
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
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 date_string:match("^[1-9]%d? +%a+ – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash
elseif mw.ustring.match(date_string, "^[1-9]%d? +%a+ [%-–] [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash
day, month, day2, month2, anchor_year, year=date_string:match("(%d%d?) +(%a+) – (%d%d?) +(%a+) +((%d%d%d%d)%a?)");
day, month, day2, month2, anchor_year, year=mw.ustring.match(date_string, "(%d%d?) +(%a+) [%-–] (%d%d?) +(%a+) +((%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;
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);
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);
year2=year;


elseif date_string:match("^%a+ +[1-9]%d? – %a+ +[1-9]%d?, +[1-9]%d%d%d?%a?$") then -- month initial month-day-range: month day – month day, year; uses spaced endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d? [%-–] %a+ +[1-9]%d?, +[1-9]%d%d%d?%a?$") then -- month initial month-day-range: month day – month day, year; uses spaced endash
month, day, month2, day2, anchor_year, year=date_string:match("(%a+) +(%d%d?) – (%a+) +(%d%d?), +((%d%d%d%d)%a?)");
month, day, month2, day2, anchor_year, year=mw.ustring.match(date_string, "(%a+) +(%d%d?) [%-–] (%a+) +(%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
if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end
month = get_month_number (month);
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);
year2=year;


elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
elseif mw.ustring.match(date_string, "^[1-9]%d? +%a+ +[1-9]%d%d%d [%-–] [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
day, month, year, day2, month2, anchor_year, year2=date_string:match("(%d%d?) +(%a+) +(%d%d%d%d?) – (%d%d?) +(%a+) +((%d%d%d%d?)%a?)");
day, month, year, day2, month2, anchor_year, year2=mw.ustring.match(date_string, "(%d%d?) +(%a+) +(%d%d%d%d?) [%-–] (%d%d?) +(%a+) +((%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 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
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);
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);


elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d – %a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d?, +[1-9]%d%d%d [%-–] %a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
month, day, year, month2, day2, anchor_year, year2=date_string:match("(%a+) +(%d%d?), +(%d%d%d%d) – (%a+) +(%d%d?), +((%d%d%d%d)%a?)");
month, day, year, month2, day2, anchor_year, year2=mw.ustring.match(date_string, "(%a+) +(%d%d?), +(%d%d%d%d) [%-–] (%a+) +(%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 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
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);
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);


elseif date_string:match("^%a+ +[1-9]%d%d%d–%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d%d%d[%-–]%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
if nil == date_string:match("^Winter") and nil == date_string:match("^Summer") then return false end; -- 'month' can only be Winter or Summer
local century;
local century;
year, century, anchor_year, year2=date_string:match("%a+ +((%d%d)%d%d)–((%d%d)%a?)");
month, year, century, anchor_year, year2=mw.ustring.match(date_string, "(%a+) +((%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
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
year2 = century..year2; -- add the century to year2 for comparisons
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 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
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 date_string:match("^%a+ +[1-9]%d%d%d–[1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d%d%d[%-–][1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash
month, year, anchor_year, year2=mw.ustring.match(date_string, "(%a+) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)");
if nil == date_string:match("^Winter") and nil == date_string:match("^Summer") then return false end; -- 'month' can only be Winter or Summer
if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer
year, anchor_year, year2=date_string:match("%a+ +(%d%d%d%d)–((%d%d%d%d)%a?)");
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
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 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
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 date_string:match("^%a+ +[1-9]%d%d%d% – %a+ +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash
elseif mw.ustring.match(date_string, "^%a+ +[1-9]%d%d%d% [%-–] %a+ +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash
month, year, month2, anchor_year, year2=date_string:match("(%a+) +(%d%d%d%d) – (%a+) +((%d%d%d%d)%a?)");
month, year, month2, anchor_year, year2=mw.ustring.match(date_string, "(%a+) +(%d%d%d%d) [%-–] (%a+) +((%d%d%d%d)%a?)");
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
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 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 not is_valid_year(year2) then return false; end -- no year farther in the future than next year
if not((0 ~= get_month_number(month) and 0 ~= get_month_number(month2) and is_valid_month_range_style(month, month2)) or -- both must be month year, same month style
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);
(0 ~= get_season_number(month) and 0 ~= get_season_number(month2))) then return false; end -- or season year, not mixed
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 date_string:match ("^%a+–%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash
elseif mw.ustring.match(date_string, "^%a+[%-–]%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash
month, month2, anchor_year, year=date_string:match ("(%a+)–(%a+)%s*((%d%d%d%d)%a?)");
month, month2, anchor_year, year=mw.ustring.match(date_string, "(%a+)[%-–](%a+)%s*((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or (not is_valid_year(year)) then
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
return false;
month = get_month_number(month);
month2 = get_month_number(month2);
else
month = get_season_number(month);
month2 = get_season_number(month2);
end
end
year2=year;
elseif date_string:match("^%a+ +%d%d%d%d%a?$") then -- month/season year or proper-name year
elseif date_string:match("^%a+ +%d%d%d%d%a?$") then -- month/season year or proper-name year
Line 324: Line 472:
if not is_valid_year(year) then return false; end
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 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 date_string:match("^[1-9]%d%d%d?–[1-9]%d%d%d?%a?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
elseif mw.ustring.match(date_string, "^[1-9]%d%d%d?[%-–][1-9]%d%d%d?%a?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
year, anchor_year, year2=date_string:match("(%d%d%d%d?)–((%d%d%d%d?)%a?)");
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
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 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 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–%d%d%a?$") then -- Year range: YYYY–YY; separated by unspaced endash
elseif mw.ustring.match(date_string, "^[1-9]%d%d%d[%-–]%d%d%a?$") then -- Year range: YYYY–YY; separated by unspaced endash
local century;
local century;
year, century, anchor_year, year2=date_string:match("((%d%d)%d%d)–((%d%d)%a?)");
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
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 13 > tonumber(year2) then return false; end -- don't allow 2003-05 which might be May 2003
Line 347: Line 502:


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


local result=true; -- check whole dates for validity; assume true because not all dates will go through this test
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)
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);
result=is_valid_date(year,month,day);
Line 368: Line 523:
if false == result then return false; end
if false == result then return false; end

-- if here, then date_string is valid; get coins_date from date_string (leave CITEREF disambiguator) ...
if nil ~= tCOinS_date then -- this table only passed into this function when testing |date= parameter values
coins_date=date_string:match("^(.+%d)%a?$"); -- last character of valid disambiguatable date is always a digit
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
coins_date= mw.ustring.gsub(coins_date, "–", "-" ); -- ... and replace any ndash with a hyphen
end
return true, anchor_year, coins_date; -- format is good and date string represents a real date
return true, anchor_year; -- format is good and date string represents a real date
end
end



--[[--------------------------< D A T E S >--------------------------------------------------------------------
--[[--------------------------< D A T E S >--------------------------------------------------------------------
Line 386: Line 543:
]]
]]


--function p.dates(date_parameters_list)
local function dates(date_parameters_list, tCOinS_date)
local function dates(date_parameters_list)
local anchor_year; -- will return as nil if the date being tested is not |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 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 error_message = "";
local mismatch = 0;
local good_date = false;
local good_date = false;
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(v) then -- if the parameter has a value
if is_set(v) then -- if the parameter has a value
if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
local year = v:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
local year = v:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
if 'date'==k then
if 'date'==k then
anchor_year, COinS_date = v:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
anchor_year, COinS_date = v:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
Line 404: Line 560:
good_date = is_valid_year(year);
good_date = is_valid_year(year);
end
end
elseif 'date'==k then -- if the parameter is |date=
elseif 'date'==k then -- if the parameter is |date=
if v:match("^n%.d%.%a?") then -- if |date=n.d. with or without a CITEREF disambiguator
if v:match("^n%.d%.%a?") then -- if |date=n.d. with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
good_date, anchor_year, COinS_date = true, v:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
elseif v:match("^nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator
elseif v:match("^nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
good_date, anchor_year, COinS_date = true, v:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
else
else
good_date, anchor_year, COinS_date = check_date (v); -- go test the date
good_date, anchor_year, COinS_date = check_date (v, tCOinS_date); -- go test the date
end
elseif 'access-date'==k then -- if the parameter is |access-date=
good_date = check_date (v); -- go test the date
if true == good_date then -- if the date is a valid date
good_date = is_valid_accessdate (v); -- is Wikipedia start date < accessdate < tomorrow's date?
end
end
elseif 'accessdate'==k then -- if the parameter is |date=
elseif 'embargo'==k then -- if the parameter is |embargo=
good_date = check_date (v); -- go test the date
good_date = check_date (v); -- go test the date
if true == good_date then -- if the date is a valid date
if true == good_date then -- if the date is a valid date
good_date = is_valid_accessdate (v); -- is Wikipedia start date < accessdate < tomorrow's date?
good_date, embargo_date = is_valid_embargo_date (v); -- is |embargo= date a single dmy, mdy, or ymd formatted date? yes:returns embargo; no: returns 9999
end
end
else -- any other date-holding parameter
else -- any other date-holding parameter
good_date = check_date (v); -- go test the date
good_date = check_date (v); -- go test the date
end
end
if false==good_date then -- assemble one error message so we don't add the tracking category multiple times
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 ...
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
error_message=error_message .. ", "; -- ... add a comma space separator
end
end
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
error_message=error_message .. "&#124;" .. k .. "="; -- add the failed parameter
end
end
end
end
end
end
return anchor_year, COinS_date, error_message, mismatch; -- and done
return anchor_year, embargo_date, error_message; -- and done
end
end



--[[--------------------------< Y E A R _ D A T E _ C H E C K >------------------------------------------------
--[[--------------------------< Y E A R _ D A T E _ C H E C K >------------------------------------------------
Line 448: Line 610:
year = year_string:match ('(%d%d%d%d?)');
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 date and year required YYYY-MM-DD and YYYYx
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)');
date1 = date_string:match ('(%d%d%d%d)');
year = year_string:match ('(%d%d%d%d)');
year = year_string:match ('(%d%d%d%d)');
Line 457: Line 619:
end
end
elseif date_string:match ("%d%d%d%d?.-%d%d%d%d?") then -- any of the standard formats of date with two three- or four-digit years
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?)");
date1, date2 = date_string:match ("(%d%d%d%d?).-(%d%d%d%d?)");
if year ~= date1 and year ~= date2 then
if year ~= date1 and year ~= date2 then
Line 463: Line 625:
end
end


elseif date_string:match ("%d%d%d%d[%s%-–]+%d%d") then -- YYYY-YY date ranges
elseif mw.ustring.match(date_string, "%d%d%d%d[%-–]%d%d") then -- YYYY-YY date ranges
local century;
local century;
date1, century, date2 = date_string:match ("((%d%d)%d%d)[%s%-–]+(%d%d)");
date1, century, date2 = mw.ustring.match(date_string, "((%d%d)%d%d)[%-–]+(%d%d)");
date2 = century..date2; -- convert YY to YYYY
date2 = century..date2; -- convert YY to YYYY
if year ~= date1 and year ~= date2 then
if year ~= date1 and year ~= date2 then
Line 476: Line 638:
result = 0;
result = 0;
end
end
else
result = 0; -- no recognizable year in date
end
end
return result;
return result;
end
end



return {dates = dates, year_date_check = year_date_check} -- return exported functions
--[[-------------------------< 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.

]]

local function reformat_dates (date_parameters_list, format, short)
local all = false; -- set to false to skip access- and archive-dates
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) then -- if the parameter has a value
if not all and in_array (param_name, {'access-date', 'archive-date'}) then -- if access- or archive-date and format not xxx-all
param_val = ''; -- set to empty string so we don't process this date
end
for source, pattern in pairs(source_patterns) do
if param_val:match(pattern) then
if 'ymd' == source then
get_ymd_date_parts (param_val, source_date); -- get the date parts into the source_date table
elseif 'dmy' == source then
get_dmy_date_parts (param_val, source_date); -- get the date parts into the source_date table
elseif 'mdy' == source then
get_mdy_date_parts (param_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
date_parameters_list[param_name] = os.date (format_str, os.time(source_date)); -- convert date and save
end
end
end
end
return true; -- declare success 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 not param_val:match ('%d%d%d%d%-%d%d%-%d%d') then -- for those that are not ymd dates
param_val, n = param_val:gsub ('%-', '–'); -- replace any hyphen with ndash
if 0 ~= n then
date_parameters_list[param_name] = param_val; -- update the list
result = true;
end
end
end
return result; -- so we know if
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 (utilities_page_ptr)
is_set = utilities_page_ptr.is_set; -- import functions from select Module:Citation/CS1/Utilities module
in_array = utilities_page_ptr.in_array; -- import functions from select Module:Citation/CS1/Utilities module
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,
set_selected_modules = set_selected_modules
}
Retrieved from "https://wiki.whentheycry.org/wiki/Module:Citation/CS1/Date_validation"