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

Synch from sandbox;
m>Trappist the monk
(Synch from sandbox;)
m>Trappist the monk
(Synch from sandbox;)
Line 62: Line 62:


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 76:


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 137: Line 137:
end
end
else
else
month_length=days_in_month[month];
month_length=days_in_month[tonumber(month)];
end
end


Line 184: Line 184:
local range_start_number = get_month_number (range_start);
local range_start_number = get_month_number (range_start);
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
local 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 199:
end
end


local range_end_number = get_month_number (range_end); -- get end month number
local 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 invlaid 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~= 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 >----------------------------------------------------------
Line 224: Line 310:
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 date_string without anchor_year disambiguator if any -- this is being obsoleted.  In future:
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 325:
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)");
month=tonumber(month);
if 12 < tonumber(month) or 1 > tonumber(month) or 1583 > tonumber(year) then return false; end -- month number not valid or not Gregorian calendar
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 252: Line 338:
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 263: Line 351:
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?$") then -- day initial month-day-range: day month - day month year; uses spaced endash
elseif date_string:match("^[1-9]%d? +%a+ – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash
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=date_string:match("(%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?$") then -- month initial month-day-range: month day – month day, year;  uses spaced endash
elseif date_string:match("^%a+ +[1-9]%d? – %a+ +[1-9]%d?, +[1-9]%d%d%d?%a?$") then -- month initial month-day-range: month day – month day, year;  uses spaced endash
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=date_string:match("(%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?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
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=date_string:match("(%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?$") then -- month initial month-day-year-range: month day, year – month day, year;  uses spaced endash
elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d – %a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year;  uses spaced endash
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=date_string:match("(%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?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
elseif date_string:match("^%a+ +[1-9]%d%d%d–%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
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=date_string:match("(%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?$") then -- special case Winter/Summer year-year; year separated with unspaced endash
elseif date_string:match("^%a+ +[1-9]%d%d%d–[1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash
if nil == date_string:match("^Winter") and nil == date_string:match("^Summer") then return false end; -- 'month' can only be Winter or Summer
month, year, anchor_year, year2=date_string:match("(%a+) +(%d%d%d%d)–((%d%d%d%d)%a?)");
year, anchor_year, year2=date_string:match("%a+ +(%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
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?$") then -- month/season year - month/season year; separated by spaced endash
elseif date_string:match("^%a+ +[1-9]%d%d%d% – %a+ +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash
Line 311: Line 405:
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
(0 ~= get_season_number(month) and 0 ~= get_season_number(month2))) then return false; end -- or season year, not mixed
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 date_string:match ("^%a+–%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash  
elseif date_string:match ("^%a+–%a+ +[1-9]%d%d%d%a?$") 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=date_string:match ("(%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
return false;
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
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 431:
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?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
elseif date_string:match("^[1-9]%d%d%d?–[1-9]%d%d%d?%a?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
Line 369: Line 483:
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 here, then date_string is valid; get coins_date from date_string (leave CITEREF disambiguator) ...
coins_date=date_string:match("^(.+%d)%a?$"); -- last character of valid disambiguatable date is always a digit
-- coins_date=date_string:match("^(.+%d)%a?$"); -- last character of valid disambiguatable date is always a digit
coins_date= mw.ustring.gsub(coins_date, "–", "-" ); -- ... and replace any ndash with a hyphen
-- coins_date= mw.ustring.gsub(coins_date, "–", "-" ); -- ... and replace any ndash with a hyphen
 
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, 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
-- return true, anchor_year, coins_date; -- format is good and date string represents a real date
end
end


Line 386: Line 505:
]]
]]


--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 error_message = "";
local error_message = "";
local mismatch = 0;
-- local mismatch = 0;
local good_date = false;
local good_date = false;
Line 410: Line 528:
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
end
elseif 'access-date'==k then -- if the parameter is |date=
elseif 'access-date'==k then -- if the parameter is |date=
Line 428: Line 546:
end
end
end
end
return anchor_year, COinS_date, error_message, mismatch; -- and done
-- return anchor_year, COinS_date, error_message, mismatch; -- and done
return anchor_year, error_message; -- and done
end
end


Anonymous user