Editing Module:Citation/CS1/Date validation
The edit can be undone. Please check the comparison below to verify that this is what you want to do, and then publish the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 1: | Line 1: | ||
local p = {} | |||
local | |||
--[[- | --[[--------------------------< I S _ V A L I D _ A C C E S S D A T E >---------------------------------------- | ||
returns true if: | returns true if: | ||
Line 23: | Line 8: | ||
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) | 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 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 | today is the current date at time 00:00:00 UTC plus 48 hours | ||
if today is 2015-01-01T00:00:00 then | if today is 2015-01-01T00:00:00 then | ||
Line 29: | Line 14: | ||
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 | ||
]] | |||
] | |||
local function is_valid_accessdate (accessdate) | local function is_valid_accessdate (accessdate) | ||
local lang = mw.getContentLanguage(); | |||
local good1, good2; | local good1, good2; | ||
local access_ts, tomorrow_ts; -- to hold | local access_ts, tomorrow_ts; -- to hold unix time stamps representing the dates | ||
good1, access_ts = pcall ( | good1, access_ts = pcall( lang.formatDate, lang, 'U', accessdate ); -- convert accessdate value to unix timesatmp | ||
good2, tomorrow_ts = pcall ( | 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 | if good1 and good2 then | ||
access_ts = tonumber | access_ts = tonumber (access_ts); -- convert to numbers for the comparison | ||
tomorrow_ts = tonumber | tomorrow_ts = tonumber (tomorrow_ts); | ||
else | else | ||
return false; -- one or both failed to convert to | return false; -- one or both failed to convert to unix time stamp | ||
end | end | ||
if 979516800 <= access_ts and access_ts < tomorrow_ts then -- Wikipedia start date <= accessdate < tomorrow's date | if 979516800 <= access_ts and access_ts < tomorrow_ts then -- Wikipedia start date <= accessdate < tomorrow's date | ||
return true; | return true; | ||
Line 56: | Line 37: | ||
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 >---------------------------------------------- | ||
returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct. | 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 | ||
If not a valid month, returns 0 | |||
]] | ]] | ||
local function get_month_number (month) | local function get_month_number (month) | ||
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}; | |||
0; | local temp; | ||
temp=long_months[month]; | |||
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 | ||
--[[--------------------------< 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 >-------------------------------------------- | ||
returns a number according to the sequence of seasons in a year: | 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 | ||
must be correct. If not a valid season, returns 0 | |||
]] | ]] | ||
local function | local function get_season_number (season) | ||
local season_list = {['Winter']=21, ['Spring']=22, ['Summer']=23, ['Fall']=24, ['Autumn']=24}; -- make sure these numbers do not overlap month numbers | |||
local temp; | |||
temp=season_list[season]; | |||
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 | |||
end | 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. | |||
returns a non-zero number if date contains a recognized proper | |||
]] | ]] | ||
local function | local function is_proper_name (name) | ||
local name_list = {['Christmas']=31} | |||
local temp; | |||
temp=name_list[name]; | |||
if temp then return temp; end -- if name is a valid name return its number | |||
return 0; -- misspelled, improper case, or not a proper name | |||
end | 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) | ||
returns true if month or season | |||
]] | ]] | ||
local function | 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 | |||
if 0 | |||
return | |||
end | end | ||
end | end | ||
return | return true; | ||
end | end | ||
Line 193: | Line 101: | ||
--[[--------------------------< I S _ V A L I D _ Y E A R >---------------------------------------------------- | --[[--------------------------< 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 | 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. | ||
year in the future are not acceptable. | |||
]] | ]] | ||
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 | ||
year_limit = tonumber(os.date("%Y"))+1; | year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once | ||
end | end | ||
return tonumber(year) <= year_limit; -- false if year is in the future more than one year | |||
end | end | ||
--[[ | |||
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 | 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_length = 28; -- then 28 days unless | |||
if (2 == month) then | if 1582 > tonumber(year) then -- Julian calendar | ||
month_length = 28; | if 0==(year%4) then | ||
if 1582 > tonumber(year) then | month_length = 29; | ||
if 0 == (year%4) then | |||
month_length = 29; | |||
end | end | ||
else | 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; | month_length = 29; -- if leap year then 29 days in February | ||
end | end | ||
end | end | ||
else | else | ||
month_length = days_in_month[month]; | month_length=days_in_month[tonumber(month)]; | ||
end | end | ||
Line 248: | Line 145: | ||
return true; | return true; | ||
end | end | ||
--[[--------------------------< I S _ V A L I D _ M O N T H _ R A N G E _ S T Y L E >-------------------------- | --[[--------------------------< I S _ V A L I D _ M O N T H _ R A N G E _ S T Y L E >-------------------------- | ||
Line 264: | Line 160: | ||
if len1 == len2 then | if len1 == len2 then | ||
return true; -- both months are short form so return true | return true; -- both months are short form so return true | ||
elseif 'May' == month1 or 'May'== month2 then | elseif 'May' == month1 or 'May'== month2 then | ||
return true; -- both months are long form so return true | return true; -- both months are long form so return true | ||
elseif 3 == len1 or 3 == len2 then | elseif 3 == len1 or 3 == len2 then | ||
Line 280: | Line 176: | ||
Month pairs are expected to be left to right, earliest to latest in time. | Month pairs are expected to be left to right, earliest to latest in time. | ||
Similarly, seasons are also left to right, earliest to latest in time. There is an oddity with seasons: winter is assigned a value of 1, spring 2, ..., | |||
fall and autumn 4. Because winter can follow fall/autumn at the end of a calender year, a special test is made to see if |date=Fall-Winter yyyy (4-1) is the date. | |||
]] | ]] | ||
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); | ||
if 0 == range_start_number then -- is this a month range? | if 0 == range_start_number then -- is this a month range? | ||
range_start_number = get_season_number (range_start | local 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 | local range_end_number = get_season_number (range_end); -- get end season number | ||
if | 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 | |||
return true; -- return true when range_end is also a season and follows start season; else false | |||
end | |||
if 24 == range_start_number and 21 == range_end_number then -- special case when season range is Fall-Winter or Autumn-Winter | |||
return true; | |||
end | |||
end | end | ||
return false; | return false; -- range_start is not a month or a season; or range_start is a season and range_end is not; or improper season sequence | ||
end | end | ||
range_end_number = get_month_number (range_end); | local range_end_number = get_month_number (range_end); -- get end month number | ||
if range_start_number < range_end_number | if range_start_number < range_end_number then -- range_start is a month; does range_start precede range_end? | ||
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 | ||
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 | ||
Line 311: | Line 213: | ||
This function receives a table of date parts for one or two dates and an empty table reference declared in | 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 | 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 | 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: | The date parts in the input table are converted to an ISO 8601 conforming date string: | ||
Line 326: | Line 228: | ||
The input table has: | The input table has: | ||
year, year2 – always present; if before 1582, ignore months and days if present | 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; | 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 | day, day2 – 0 if not provided, 1-31 for days | ||
the output table receives: | the output table receives: | ||
rftdate: an | rftdate: an IS8601 formatted date | ||
rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and | 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) | rftssn: one of four season keywords: winter, spring, summer, fall (lowercase) | ||
]] | ]] | ||
Line 340: | Line 241: | ||
local date; -- one date or first date in a range | local date; -- one date or first date in a range | ||
local date2 = ''; -- end of range date | 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 | if 1582 > tonumber(input.year) or 20 < tonumber(input.month) then -- Julian calendar or season so &rft.date gets year only | ||
Line 357: | Line 247: | ||
date = string.format ('%.4d/%.4d', tonumber(input.year), tonumber(input.year2)) -- assemble the date range | date = string.format ('%.4d/%.4d', tonumber(input.year), tonumber(input.year2)) -- assemble the date range | ||
end | end | ||
if 20 < tonumber(input.month) then -- if season or | if 20 < tonumber(input.month) then -- if season or propername date | ||
local season = {[ | 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 0 == input.month2 then -- single season date | ||
if | if 30 <tonumber(input.month) then | ||
tCOinS_date.rftchron = season[input.month]; -- proper | tCOinS_date.rftchron = season[input.month]; -- proper name dates | ||
else | else | ||
tCOinS_date.rftssn = season[input.month]; -- seasons | tCOinS_date.rftssn = season[input.month]; -- seasons | ||
Line 370: | Line 258: | ||
if input.year ~= input.year2 then -- season year – season year range or season year–year | 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? | tCOinS_date.rftssn = season[input.month]; -- start of range season; keep this? | ||
if 0~= | if 0~= month2 then | ||
tCOinS_date.rftchron = string.format ('%s %s – %s %s', season[input.month], input.year, season[input.month2], input.year2); | tCOinS_date.rftchron = string.format ('%s %s – %s %s', season[input.month], input.year, season[input.month2], input.year2); | ||
end | end | ||
Line 404: | Line 292: | ||
return; | return; | ||
end | 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 | 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. | ||
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 | ||
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. | |||
If the date fails the format tests, this function returns false and does not return values for anchor_year and | 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 | ||
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. | ||
its year from the year parameter if present otherwise CITEREF does not get a date value. | |||
Inputs: | Inputs: | ||
date_string - date string from date-holding parameters (date, year, | date_string - date string from date-holding parameters (date, year, accessdate, embargo, archivedate, etc.) | ||
Returns: | Returns: | ||
Line 476: | 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 -- this is being obsoleted. In future: | |||
COinS_date is ISO 8601 format date; see make_COInS_date() | COinS_date is ISO 8601 format date; see make_COInS_date() | ||
]] | ]] | ||
local function check_date (date_string, tCOinS_date) | |||
local function check_date (date_string | local year; -- assume that year2, months, and days are not used; | ||
local year; | local year2=0; -- second year in a year range | ||
local year2 = 0; | local month=0; | ||
local month = 0; | local month2=0; -- second month in a month range | ||
local month2 = 0; | local day=0; | ||
local day = 0; | local day2=0; -- second day in a day range | ||
local day2 = 0; | |||
local anchor_year; | local anchor_year; | ||
local coins_date; | local coins_date; | ||
if date_string:match ( | if date_string:match("^%d%d%d%d%-%d%d%-%d%d$") then -- year-initial numerical year month day format | ||
year, month, day = | year, month, day=string.match(date_string, "(%d%d%d%d)%-(%d%d)%-(%d%d)"); | ||
if 12 < tonumber(month) or 1 > tonumber(month) or 1583 > tonumber(year) then return false; end -- month number not valid or not Gregorian calendar | |||
if 12 < tonumber(month) or 1 > tonumber(month) or | |||
anchor_year = year; | anchor_year = year; | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial: month day, year | ||
month, day, anchor_year, year = | month, day, anchor_year, year=string.match(date_string, "(%a+)%s*(%d%d?),%s*((%d%d%d%d)%a?)"); | ||
month = get_month_number (month); | month = get_month_number (month); | ||
if 0 == month then return false; end | if 0 == month then return false; end -- return false if month text isn't one of the twelve months | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d?–[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash | ||
month, day, day2, anchor_year, year = | month, day, day2, anchor_year, year=string.match(date_string, "(%a+) +(%d%d?)–(%d%d?), +((%d%d%d%d)%a?)"); | ||
if tonumber(day) >= tonumber(day2) then return false; end | if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same; | ||
month = get_month_number (month); | month = get_month_number (month); | ||
if 0 == month then return false; end | if 0 == month then return false; end -- return false if month text isn't one of the twelve months | ||
month2=month; -- for metadata | |||
year2=year; | |||
elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-initial: day month year | |||
elseif | day, month, anchor_year, year=string.match(date_string, "(%d%d*)%s*(%a+)%s*((%d%d%d%d)%a?)"); | ||
month = get_month_number (month); | month = get_month_number (month); | ||
if 0 == month then return false; end | if 0 == month then return false; end -- return false if month text isn't one of the twelve months | ||
elseif | elseif date_string:match("^[1-9]%d?–[1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash | ||
day, day2, month, anchor_year, year = | day, day2, month, anchor_year, year=string.match(date_string, "(%d%d?)–(%d%d?) +(%a+) +((%d%d%d%d)%a?)"); | ||
if tonumber(day) >= tonumber(day2) then return false; end | if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same; | ||
month = get_month_number (month); | month = get_month_number (month); | ||
if 0 == month then return false; end | if 0 == month then return false; end -- return false if month text isn't one of the twelve months | ||
month2 = month; | month2=month; -- for metadata | ||
year2 = year; | year2=year; | ||
elseif | elseif date_string:match("^[1-9]%d? +%a+ – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash | ||
day, month, day2, month2, anchor_year, year = | 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; | year2=year; | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d? – %a+ +[1-9]%d?, +[1-9]%d%d%d?%a?$") then -- month initial month-day-range: month day – month day, year; uses spaced endash | ||
month, day, month2, day2, anchor_year, year = | month, day, month2, day2, anchor_year, year=date_string:match("(%a+) +(%d%d?) – (%a+) +(%d%d?), +((%d%d%d%d)%a?)"); | ||
if (not is_valid_month_season_range(month, month2 | if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end | ||
month = get_month_number (month); | month = get_month_number (month); -- for metadata | ||
month2 = get_month_number (month2); | month2 = get_month_number (month2); | ||
year2 = year; | year2=year; | ||
elseif | elseif date_string:match("^[1-9]%d? +%a+ +[1-9]%d%d%d – [1-9]%d? +%a+ +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash | ||
day, month, year, day2, month2, anchor_year, year2 = | 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 | 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 | elseif date_string:match("^%a+ +[1-9]%d?, +[1-9]%d%d%d – %a+ +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash | ||
month, day, year, month2, day2, anchor_year, year2 = | month, day, year, month2, day2, anchor_year, year2=date_string:match("(%a+) +(%d%d?), +(%d%d%d%d) – (%a+) +(%d%d?), +((%d%d%d%d)%a?)"); | ||
if tonumber(year2) <= tonumber(year) then return false; end | if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later | ||
if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style | if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style | ||
month = get_month_number (month); | month = get_month_number (month); -- for metadata | ||
month2 = get_month_number(month2); | month2 = get_month_number (month2); | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d%d%d–%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash | ||
local century; | local century; | ||
month, year, century, anchor_year, year2 = | 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; | if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer | ||
anchor_year = year .. '–' .. anchor_year; | anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years | ||
year2 = century..year2; | year2 = century..year2; -- add the century to year2 for comparisons | ||
if 1 ~= tonumber(year2) - tonumber(year) then return false; end | 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 | if not is_valid_year(year2) then return false; end -- no year farther in the future than next year | ||
month = get_season_number(month | month = get_season_number (month); | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d%d%d–[1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash | ||
month, year, anchor_year, year2 = | month, year, anchor_year, year2=date_string:match("(%a+) +(%d%d%d%d)–((%d%d%d%d)%a?)"); | ||
if 'Winter' ~= month and 'Summer' ~= month then return false end; | if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer | ||
anchor_year = year .. '–' .. anchor_year; | anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years | ||
if 1 ~= tonumber(year2) - tonumber(year) then return false; end | if 1 ~= tonumber(year2) - tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later | ||
if not is_valid_year(year2) then return false; end | if not is_valid_year(year2) then return false; end -- no year farther in the future than next year | ||
month = get_season_number (month | month = get_season_number (month); -- for metadata | ||
elseif | elseif date_string:match("^%a+ +[1-9]%d%d%d% – %a+ +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash | ||
month, year, month2, anchor_year, year2 = | month, year, month2, anchor_year, year2=date_string:match("(%a+) +(%d%d%d%d) – (%a+) +((%d%d%d%d)%a?)"); | ||
anchor_year = year .. '–' .. anchor_year; | anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years | ||
if tonumber(year) >= tonumber(year2) then return false; end | 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 | 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 | 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); | month = get_month_number(month); | ||
month2 = get_month_number(month2); | month2 = get_month_number(month2); | ||
elseif 0 ~= get_season_number(month | 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 | month = get_season_number(month); | ||
month2 = get_season_number(month2 | month2 = get_season_number(month2); | ||
else | else | ||
return false; | return false; | ||
end | end | ||
elseif | elseif date_string:match ("^%a+–%a+ +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash | ||
month, month2, anchor_year, year = | month, month2, anchor_year, year=date_string:match ("(%a+)–(%a+)%s*((%d%d%d%d)%a?)"); | ||
if (not is_valid_month_season_range(month, month2 | if (not is_valid_month_season_range(month, month2)) or (not is_valid_year(year)) then return false; end | ||
if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season | if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season | ||
month = get_month_number(month); | month = get_month_number(month); | ||
month2 = get_month_number(month2); | month2 = get_month_number(month2); | ||
else | else | ||
month = get_season_number(month | month = get_season_number(month); | ||
month2 = get_season_number(month2 | month2 = get_season_number(month2); | ||
end | end | ||
year2 = year; | year2=year; | ||
elseif | elseif date_string:match("^%a+ +%d%d%d%d%a?$") then -- month/season year or proper-name year | ||
month, anchor_year, year = | month, anchor_year, year=date_string:match("(%a+)%s*((%d%d%d%d)%a?)"); | ||
if not is_valid_year(year) then return false; end | if not is_valid_year(year) then return false; end | ||
month = | 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 | elseif date_string:match("^[1-9]%d%d%d?–[1-9]%d%d%d?%a?$") then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999 | ||
year, anchor_year, year2 = | year, anchor_year, year2=date_string:match("(%d%d%d%d?)–((%d%d%d%d?)%a?)"); | ||
anchor_year = year .. '–' .. anchor_year; | anchor_year=year..'–'..anchor_year; -- assemble anchor year from both years | ||
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same | if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same | ||
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year | if not is_valid_year(year2) then return false; end -- no year farther in the future than next year | ||
elseif | elseif date_string:match("^[1-9]%d%d%d–%d%d%a?$") then -- Year range: YYYY–YY; separated by unspaced endash | ||
local century; | local century; | ||
year, century, anchor_year, year2 = | year, century, anchor_year, year2=date_string:match("((%d%d)%d%d)–((%d%d)%a?)"); | ||
anchor_year = year .. '–' .. anchor_year; | 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 | ||
year2 = century .. year2; -- add the century to year2 for comparisons | 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 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 | elseif date_string:match("^[1-9]%d%d%d?%a?$") then -- year; here accept either YYY or YYYY | ||
anchor_year, year = | anchor_year, year=date_string:match("((%d%d%d%d?)%a?)"); | ||
if false == is_valid_year(year) then | if false == is_valid_year(year) then | ||
return false; | return false; | ||
Line 642: | Line 461: | ||
else | else | ||
return false; | 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; | |||
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); | ||
elseif 0 ~= year and 0 ~= month and 0 ~= day and 0 == year2 and 0 == month2 and 0 ~= day2 then -- YMD-d (day range) | 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=is_valid_date(year,month,day); | ||
result = result and is_valid_date(year, month, day2); | 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) | 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=is_valid_date(year,month,day); | ||
result = result and is_valid_date(year, month2, day2); | 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) | 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=is_valid_date(year,month,day); | ||
result = result and is_valid_date(year2, month2, day2); | result=result and is_valid_date(year2,month2,day2); | ||
end | end | ||
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) ... | |||
-- 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 | |||
if nil ~= tCOinS_date then -- this table only passed into this function when testing |date= parameter values | 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 | 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 | end | ||
return true, anchor_year; | 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 | ||
--[[--------------------------< D A T E S >-------------------------------------------------------------------- | --[[--------------------------< D A T E S >-------------------------------------------------------------------- | ||
Line 690: | Line 501: | ||
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, | 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 function dates(date_parameters_list, tCOinS_date) | ||
local anchor_year; | local anchor_year; -- will return as nil if the date being tested is not |date= | ||
local COinS_date; | local COinS_date; -- will return as nil if the date being tested is not |date= | ||
local | local error_message = ""; | ||
-- local mismatch = 0; | |||
local good_date = false; | local good_date = false; | ||
for k, v in pairs(date_parameters_list) do | for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list | ||
if is_set(v | if is_set(v) then -- if the parameter has a value | ||
if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year= | |||
if v | local year = v:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested | ||
local year = v | if 'date'==k then | ||
if 'date' == k then | anchor_year, COinS_date = v:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter | ||
anchor_year, COinS_date = v | |||
good_date = is_valid_year(year); | good_date = is_valid_year(year); | ||
elseif 'year' == k then | elseif 'year'==k then | ||
good_date = is_valid_year(year); | good_date = is_valid_year(year); | ||
end | end | ||
elseif 'date' == k then | elseif 'date'==k then -- if the parameter is |date= | ||
if v | if v:match("^n%.d%.%a?") then -- if |date=n.d. with or without a CITEREF disambiguator | ||
good_date, anchor_year, COinS_date = true, v | good_date, anchor_year, COinS_date = true, v:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date | ||
elseif v | elseif v:match("^nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator | ||
good_date, anchor_year, COinS_date = true, v | 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 | good_date, anchor_year, COinS_date = check_date (v, tCOinS_date); -- go test the date | ||
end | end | ||
elseif ' | elseif 'access-date'==k then -- if the parameter is |date= | ||
good_date = check_date (v); -- go test the date | |||
good_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 | ||
else -- any other date-holding parameter | |||
good_date = check_date (v | good_date = check_date (v); -- 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 | end | ||
error_message=error_message .. "|" .. k .. "="; -- add the failed parameter | |||
end | end | ||
end | end | ||
end | end | ||
return anchor_year, | -- return anchor_year, COinS_date, error_message, mismatch; -- and done | ||
return anchor_year, 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 >------------------------------------------------ | ||
Compare the value provided in |year= with the year value(s) provided in |date=. This function | 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 | 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 | 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) | 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 | local function year_date_check (year_string, date_string) | ||
local year; | local year; | ||
local date1; | local date1; | ||
local date2; | local date2; | ||
local result = 1; -- result of the test; assume that the test passes | local result = 1; -- result of the test; assume that the test passes | ||
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 | 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 | ||
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 771: | Line 576: | ||
end | end | ||
elseif date_string:match ("%d%d%d%d?.-%d%d%d%d?") then -- any of the standard | 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 | ||
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 777: | Line 582: | ||
end | end | ||
elseif | elseif date_string:match ("%d%d%d%d[%s%-–]+%d%d") then -- YYYY-YY date ranges | ||
local century; | local century; | ||
date1, century, date2 = | date1, century, date2 = date_string:match ("((%d%d)%d%d)[%s%-–]+(%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 789: | Line 594: | ||
if year ~= date1 then | if year ~= date1 then | ||
result = 0; | result = 0; | ||
end | end | ||
end | end | ||
return result; | |||
return result; | |||
end | end | ||
return {dates = dates, year_date_check = year_date_check} -- return exported functions | |||