Seeds of the Word

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

Module Discussion

Module:Citation/CS1/Date validation (view source)

Revision as of 16:23, May 4, 2023

3,274 bytes added ,  1 year ago
m
1 revision imported
m (1 revision imported)
m (1 revision imported)
 
(7 intermediate revisions by 2 users not shown)
Line 1: Line 1:
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
--[[--------------------------< F O R W A R D  D E C L A R A T I O N S >--------------------------------------
]]
]]


local is_set, in_array; -- imported functions from selected Module:Citation/CS1/Utilities
local add_prop_cat, is_set, in_array, set_message, substitute, wrap_style; -- imported functions from selected Module:Citation/CS1/Utilities
local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration
local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration


Line 23: Line 22:


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= at time 00:00:00 UTC
accessdate is the date provided in |access-date= 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 30: Line 29:


This function does not work if it is fed month names for languages other than English.  Wikimedia #time: parser
This function does not work if it is fed month names for languages other than English.  Wikimedia #time: parser
apparently doesn't understand non-Engish date month names. This function will always return false when the date
apparently doesn't understand non-English date month names. This function will always return false when the date
contains a non-English month name because good1 is false after the call to lang.formatDate().  To get around that
contains a non-English month name because good1 is false after the call to lang.formatDate().  To get around that
call this function with YYYY-MM-DD format dates.
call this function with YYYY-MM-DD format dates.
Line 38: Line 37:
local function is_valid_accessdate (accessdate)
local function is_valid_accessdate (accessdate)
local good1, good2;
local good1, good2;
local access_ts, tomorrow_ts; -- to hold unix time stamps representing the dates
local access_ts, tomorrow_ts; -- to hold Unix time stamps representing the dates


good1, access_ts = pcall (lang_object.formatDate, lang_object, 'U', accessdate ); -- convert accessdate value to unix timesatmp
good1, access_ts = pcall (lang_object.formatDate, lang_object, 'U', accessdate ); -- convert accessdate value to Unix timestamp
good2, tomorrow_ts = pcall (lang_object.formatDate, lang_object, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow
good2, tomorrow_ts = pcall (lang_object.formatDate, lang_object, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow
if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which which tonumber() may not understand
if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which which tonumber() may not understand
access_ts = tonumber (access_ts) or lang_object:parseFormattedNumber (access_ts); -- convert to numbers for the comparison;
access_ts = tonumber (access_ts) or lang_object:parseFormattedNumber (access_ts); -- convert to numbers for the comparison;
tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts);
tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts);
else
else
return false; -- one or both failed to convert to unix time stamp
return false; -- one or both failed to convert to Unix time stamp
end
end


Line 55: Line 54:
return false; -- accessdate out of range
return false; -- accessdate out of range
end
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
end


Line 85: Line 65:


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


Line 99: Line 79:
returns 0 when <param> is not |date=
returns 0 when <param> is not |date=


Season numbering is defined by Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/)
Season numbering is defined by Extended Date/Time Format (EDTF) specification (https://www.loc.gov/standards/datetime/)
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'.  The standard defines various divisions using
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'.  The standard defines various divisions using
numbers 21-41.  cs1|2 only supports generic seasons.  EDTF does support the distinction between north and south
numbers 21-41.  cs1|2 only supports generic seasons.  EDTF does support the distinction between north and south
hemispere seasons but cs1|2 has no way to make that distinction.
hemisphere seasons but cs1|2 has no way to make that distinction.


These additional divisions not currently supported:
These additional divisions not currently supported:
Line 131: Line 111:
returns 0 when <param> is not |date=
returns 0 when <param> is not |date=


Quarter numbering is defined by Extended Date/Time Format (EDTF) Specification (https://www.loc.gov/standards/datetime/)
Quarter numbering is defined by Extended Date/Time Format (EDTF) specification (https://www.loc.gov/standards/datetime/)
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'.  The standard defines various divisions using
which became part of ISO 8601 in 2019.  See '§Sub-year groupings'.  The standard defines various divisions using
numbers 21-41.  cs1|2 only supports generic seasons and quarters.
numbers 21-41.  cs1|2 only supports generic seasons and quarters.
Line 195: Line 175:
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.
Special case for |pmc-embargo-date=: years more than two years in the future are not acceptable


]]
]]


local function is_valid_year (year)
local function is_valid_year (year, param)
if not is_set(year_limit) then
if not is_set (year_limit) then
year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once
year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once
end
end


year = tonumber (year) or lang_object:parseFormattedNumber (year); -- convert to numbers for the comparison;
year = tonumber (year) or lang_object:parseFormattedNumber (year); -- convert to number for the comparison;
if 'pmc-embargo-date' == param then -- special case for |pmc-embargo-date=
return year and (year <= tonumber(os.date("%Y"))+2) or false; -- years more than two years in the future are not accepted
end
return year and (year <= year_limit) or false;
return year and (year <= year_limit) or false;
end
end
Line 219: Line 205:
]]
]]


local function is_valid_date (year, month, day)
local function is_valid_date (year, month, day, param)
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, param) then -- no farther into the future than next year except |pmc-embargo-date= no more than two years in the future
return false;
return false;
end
end
month = tonumber(month); -- required for YYYY-MM-DD dates
month = tonumber (month); -- required for YYYY-MM-DD dates
if (2==month) then -- if February
if (2 == month) then -- if February
month_length = 28; -- then 28 days unless
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
if 1582 > tonumber(year) then -- Julian calendar
if 0==(year%4) then -- is a leap year?
if 0 == (year%4) 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
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
else
else
month_length=days_in_month[month];
month_length = days_in_month[month];
end
end


Line 253: Line 239:


Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August.  
Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August.  
There is a special test for May because it can be either short or long form.
This function looks in cfg.date_names{} to see if both month names are listed in the long subtable or both are
 
listed in the short subtable. When both have the same style (both are listed in the same table), returns true; false else
Returns true when style for both months is the same


]]
]]


local function is_valid_month_range_style (month1, month2)
local function is_valid_month_range_style (month1, month2)
local len1 = month1:len();
if (cfg.date_names.en.long[month1] and cfg.date_names.en.long[month2]) or -- are both English names listed in the long subtable?
local len2 = month2:len();
(cfg.date_names.en.short[month1] and cfg.date_names.en.short[month2]) or -- are both English names listed in the short subtable?
if len1 == len2 then
(cfg.date_names['local'].long[month1] and cfg.date_names['local'].long[month2]) or -- are both local names listed in the long subtable?
return true; -- both months are short form so return true
(cfg.date_names['local'].short[month1] and cfg.date_names['local'].short[month2]) then -- are both local names listed in the short subtable?
elseif 'May' == month1 or 'May'== month2 then
return true;
return true; -- both months are long form so return true
elseif 3 == len1 or 3 == len2 then
return false; -- months are mixed form so return false
else
return true; -- both months are long form so return true
end
end
return false; -- names are mixed
end
end


Line 280: Line 261:
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.


All season ranges are accepted as valid because there are publishers out there who have published a Summer–Spring YYYY issue so ... ok
All season ranges are accepted as valid because there are publishers out there who have published a Summer–Spring YYYY issue, hence treat as ok


]]
]]
Line 292: Line 273:
range_end_number = get_season_number (range_end, param); -- get end season number
range_end_number = get_season_number (range_end, param); -- get end season number


if (0 ~= range_start_number) and (0 ~= range_end_number) then
if (0 ~= range_start_number) and (0 ~= range_end_number) and (range_start_number ~= range_end_number) then
return true; -- any season pairing is accepted
return true; -- any season pairing is accepted except when both are the same
end
end
return false; -- range_start and/or range_end is not a season
return false; -- range_start and/or range_end is not a season
Line 299: Line 280:
-- here when range_start is a month
-- here when range_start is a month
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 and -- 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?
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 331: Line 311:
the output table receives:
the output table receives:
rftdate: an IS8601 formatted date
rftdate: an ISO 8601 formatted date
rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and proper-name dates)
rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and proper-name dates)
rftssn: one of four season keywords: winter, spring, summer, fall (lowercase)
rftssn: one of four season keywords: winter, spring, summer, fall (lowercase)
Line 346: Line 326:
local day = tonumber (input.day);
local day = tonumber (input.day);
if (0 ~= day) and -- day must have a value for this to be a whole date
if (0 ~= day) and -- day must have a value for this to be a whole date
(((1582 == year) and (10 <= month) and (12 >= month)) or -- any whole 1582 date from 1 october to 31 December or
(((1582 == year) and (10 <= month) and (12 >= month)) or -- any whole 1582 date from 1 October to 31 December or
((1926 == year) and (1 == month) and (1 == input.day)) or -- 1 January 1926 or
((1926 == year) and (1 == month) and (1 == input.day)) or -- 1 January 1926 or
((1582 < year) and (1925 >= year))) then -- any date 1 January 1583 – 31 December 1925
((1582 < year) and (1925 >= year))) then -- any date 1 January 1583 – 31 December 1925
tCOinS_date.inter_cal_cat = true; -- set category flag true
tCOinS_date.inter_cal_cat = true; -- set category flag true
end
end
-- end temporary Julian / Gergorian calendar uncertainty detection
-- end temporary Julian / Gregorian calendar uncertainty detection
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 359: Line 339:
end
end
if 20 < tonumber(input.month) then -- if season or proper-name date
if 20 < tonumber(input.month) then -- if season or proper-name date
local season = {[24]='winter', [21]='spring', [22]='summer', [23]='fall', [33]='1', [34]='2', [35]='3', [36]='4', [98]='Easter', [99]='Christmas'}; -- seasons lowercase, no autumn; proper-names use title case
local season = {[24] = 'winter', [21] = 'spring', [22] = 'summer', [23] = 'fall', [33] = '1', [34] = '2', [35] = '3', [36] = '4', [98] = 'Easter', [99] = '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 40 <tonumber(input.month) then
if 40 < tonumber(input.month) then
tCOinS_date.rftchron = season[input.month]; -- proper-name dates
tCOinS_date.rftchron = season[input.month]; -- proper-name dates
elseif 30 <tonumber(input.month) then
elseif 30 < tonumber(input.month) then
tCOinS_date.rftquarter = season[input.month]; -- quarters
tCOinS_date.rftquarter = season[input.month]; -- quarters
else
else
Line 429: Line 409:
['dMy'] = {'^([1-9]%d?) +(%D-) +((%d%d%d%d?)%a?)$', 'd', 'm', 'a', 'y'},
['dMy'] = {'^([1-9]%d?) +(%D-) +((%d%d%d%d?)%a?)$', 'd', 'm', 'a', 'y'},
-- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki
-- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki
-- ['yMd'] = {'^((%d%d%d%d?)%a?) +(%D-) +(%d%d?)$', 'a', 'y', 'm', 'd'},
-- ['yMd'] = {'^((%d%d%d%d?)%a?) +(%D-) +(%d%d?)$', 'a', 'y', 'm', 'd'},
-- day-range-initial: day–day month year; days are separated by endash
-- day-range-initial: day–day month year; days are separated by endash
['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'd2', 'm', 'a', 'y'},
['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'd2', 'm', 'a', 'y'},
Line 446: Line 426:
-- month/season range year; months separated by endash
-- month/season range year; months separated by endash
['M-My'] = {'^(%D-)[%-–](%D-) +((%d%d%d%d)%a?)$', 'm', 'm2', 'a', 'y'},
['M-My'] = {'^(%D-)[%-–](%D-) +((%d%d%d%d)%a?)$', 'm', 'm2', 'a', 'y'},
-- month/season year or proper-name year; quarter year when First Quarter YYYY etc
-- month/season year or proper-name year; quarter year when First Quarter YYYY etc.
['My'] = {'^([^%d–]-) +((%d%d%d%d)%a?)$', 'm', 'a', 'y'}, -- this way because endash is a member of %D; %D- will match January–March 2019 when it shouldn't
['My'] = {'^([^%d–]-) +((%d%d%d%d)%a?)$', 'm', 'a', 'y'}, -- this way because endash is a member of %D; %D- will match January–March 2019 when it shouldn't


-- these date formats cannot be converted
-- these date formats cannot be converted
-- ['Q,y'] = {'^(Q%a* +[1-4]), +((%d%d%d%d)%a?)$'}, -- Quarter n, yyyy
['Sy4-y2'] = {'^(%D-) +((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
['Sy4-y2'] = {'^(%D-) +((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
['Sy-y'] = {'^(%D-) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash
['Sy-y'] = {'^(%D-) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash
Line 458: Line 436:
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- year; here accept either YYY or YYYY
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- year; here accept either YYY or YYYY
}
}
--[[--------------------------< 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 |pmc-embargo-date= is
set, the editor intended to embargo a PMC but |pmc-embargo-date= does not hold a single date.
]]
local function is_valid_embargo_date (v)
if v:match (patterns['ymd'][1]) or -- ymd
v:match (patterns['Mdy'][1]) or -- dmy
v:match (patterns['dMy'][1]) 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




Line 468: Line 465:


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 used in the COinS metadata and the CITEREF identifier gets
COinS_date.  When this happens, the date parameter is (DEBUG: not?) 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, accessdate, embargo, archivedate, etc.)
date_string - date string from date-holding parameters (date, year, publication-date, access-date, pmc-embargo-date, archive-date, lay-date)


Returns:
Returns:
Line 484: Line 481:
local function check_date (date_string, param, tCOinS_date)
local function check_date (date_string, param, 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
local month=0;
local month = 0;
local month2=0; -- second month in a month range
local month2 = 0; -- second month in a month range
local day=0;
local day = 0;
local day2=0; -- second day in a day range
local day2 = 0; -- second day in a day range
local anchor_year;
local anchor_year;
local coins_date;
local coins_date;


if date_string:match (patterns['ymd'][1]) then -- year-initial numerical year month day format
if date_string:match (patterns['ymd'][1]) then -- year-initial numerical year month day format
year, month, day=date_string:match (patterns['ymd'][1]);
year, month, day = date_string:match (patterns['ymd'][1]);
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar
anchor_year = year;
anchor_year = year;
-- elseif mw.ustring.match(date_string, patterns['Q,y'][1]) then -- quarter n, year; here because much the same as Mdy
-- month, anchor_year, year=mw.ustring.match(date_string, patterns['Q,y'][1]);
-- if not is_valid_year(year) then return false; end
-- month = get_quarter_number (month, param); -- get quarter number or nil
-- if not month then return false; end -- not valid whatever it is
elseif mw.ustring.match(date_string, patterns['Mdy'][1]) then -- month-initial: month day, year
elseif mw.ustring.match(date_string, patterns['Mdy'][1]) then -- month-initial: month day, year
month, day, anchor_year, year=mw.ustring.match(date_string, patterns['Mdy'][1]);
month, day, anchor_year, year = mw.ustring.match(date_string, patterns['Mdy'][1]);
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
elseif mw.ustring.match(date_string, patterns['Md-dy'][1]) then -- month-initial day range: month day–day, year; days are separated by endash
elseif mw.ustring.match(date_string, patterns['Md-dy'][1]) then -- month-initial day range: month day–day, year; days are separated by endash
month, day, day2, anchor_year, year=mw.ustring.match(date_string, patterns['Md-dy'][1]);
month, day, day2, anchor_year, year = mw.ustring.match(date_string, patterns['Md-dy'][1]);
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
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
month2=month; -- for metadata
year2=year;
year2 = year;


elseif mw.ustring.match(date_string, patterns['dMy'][1]) then -- day-initial: day month year
elseif mw.ustring.match(date_string, patterns['dMy'][1]) then -- day-initial: day month year
day, month, anchor_year, year=mw.ustring.match(date_string, patterns['dMy'][1]);
day, month, anchor_year, year = mw.ustring.match(date_string, patterns['dMy'][1]);
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
Line 523: Line 514:
--[[ NOT supported at en.wiki
--[[ NOT supported at en.wiki
elseif mw.ustring.match(date_string, patterns['yMd'][1]) then -- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed
elseif mw.ustring.match(date_string, patterns['yMd'][1]) then -- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed
anchor_year, year, month, day=mw.ustring.match(date_string, patterns['yMd'][1]);
anchor_year, year, month, day = mw.ustring.match(date_string, patterns['yMd'][1]);
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
Line 529: Line 520:


elseif mw.ustring.match(date_string, patterns['d-dMy'][1]) then -- day-range-initial: day–day month year; days are separated by endash
elseif mw.ustring.match(date_string, patterns['d-dMy'][1]) then -- day-range-initial: day–day month year; days are separated by endash
day, day2, month, anchor_year, year=mw.ustring.match(date_string, patterns['d-dMy'][1]);
day, day2, month, anchor_year, year = mw.ustring.match(date_string, patterns['d-dMy'][1]);
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
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
month2 = month; -- for metadata
year2=year;
year2 = year;


elseif mw.ustring.match(date_string, patterns['dM-dMy'][1]) then -- day initial month-day-range: day month - day month year; uses spaced endash
elseif mw.ustring.match(date_string, patterns['dM-dMy'][1]) then -- day initial month-day-range: day month - day month year; uses spaced endash
day, month, day2, month2, anchor_year, year=mw.ustring.match(date_string, patterns['dM-dMy'][1]);
day, month, day2, month2, anchor_year, year = mw.ustring.match(date_string, patterns['dM-dMy'][1]);
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); -- for metadata
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);
year2=year;
year2 = year;


elseif mw.ustring.match(date_string, patterns['Md-Mdy'][1]) then -- month initial month-day-range: month day – month day, year; uses spaced endash
elseif mw.ustring.match(date_string, patterns['Md-Mdy'][1]) then -- month initial month-day-range: month day – month day, year; uses spaced endash
month, day, month2, day2, anchor_year, year=mw.ustring.match(date_string, patterns['Md-Mdy'][1]);
month, day, month2, day2, anchor_year, year = mw.ustring.match(date_string, patterns['Md-Mdy'][1]);
if (not is_valid_month_season_range(month, month2, param)) or not is_valid_year(year) then return false; end
if (not is_valid_month_season_range(month, month2, param)) or not is_valid_year(year) then return false; end
month = get_month_number (month); -- for metadata
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);
year2=year;
year2 = year;


elseif mw.ustring.match(date_string, patterns['dMy-dMy'][1]) then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
elseif mw.ustring.match(date_string, patterns['dMy-dMy'][1]) then -- day initial month-day-year-range: day month year - day month year; uses spaced endash
day, month, year, day2, month2, anchor_year, year2=mw.ustring.match(date_string, patterns['dMy-dMy'][1]);
day, month, year, day2, month2, anchor_year, year2 = mw.ustring.match(date_string, patterns['dMy-dMy'][1]);
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); -- for metadata
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number (month2);
if 0 == month or 0 == month2 then return false; end -- both must be valid


elseif mw.ustring.match(date_string, patterns['Mdy-Mdy'][1]) then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
elseif mw.ustring.match(date_string, patterns['Mdy-Mdy'][1]) then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
month, day, year, month2, day2, anchor_year, year2=mw.ustring.match(date_string, patterns['Mdy-Mdy'][1]);
month, day, year, month2, day2, anchor_year, year2 = mw.ustring.match(date_string, patterns['Mdy-Mdy'][1]);
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); -- for metadata
month = get_month_number (month); -- for metadata
month2 = get_month_number (month2);
month2 = get_month_number(month2);
if 0 == month or 0 == month2 then return false; end -- both must be valid


elseif mw.ustring.match(date_string, patterns['Sy4-y2'][1]) then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
elseif mw.ustring.match(date_string, patterns['Sy4-y2'][1]) then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
local century;
local century;
month, year, century, anchor_year, year2=mw.ustring.match(date_string, patterns['Sy4-y2'][1]);
month, year, century, anchor_year, year2 = mw.ustring.match(date_string, patterns['Sy4-y2'][1]);
if 'Winter' ~= month and 'Summer' ~= month 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
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, param);
month = get_season_number(month, param);


elseif mw.ustring.match(date_string, patterns['Sy-y'][1]) then -- special case Winter/Summer year-year; year separated with unspaced endash
elseif mw.ustring.match(date_string, patterns['Sy-y'][1]) then -- special case Winter/Summer year-year; year separated with unspaced endash
month, year, anchor_year, year2=mw.ustring.match(date_string, patterns['Sy-y'][1]);
month, year, anchor_year, year2 = mw.ustring.match(date_string, patterns['Sy-y'][1]);
if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer
month = get_season_number (month, param); -- <month> can only be winter or summer; also for metadata
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
if (month ~= cfg.date_names['en'].season['Winter']) and (month ~= cfg.date_names['en'].season['Summer']) then
return false; -- not Summer or Winter; abandon
end
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, param); -- for metadata


elseif mw.ustring.match(date_string, patterns['My-My'][1]) then -- month/season year - month/season year; separated by spaced endash
elseif mw.ustring.match(date_string, patterns['My-My'][1]) then -- month/season year - month/season year; separated by spaced endash
month, year, month2, anchor_year, year2=mw.ustring.match(date_string, patterns['My-My'][1]);
month, year, month2, anchor_year, year2 = mw.ustring.match(date_string, patterns['My-My'][1]);
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
Line 598: Line 593:


elseif mw.ustring.match(date_string, patterns['M-My'][1]) then -- month/season range year; months separated by endash  
elseif mw.ustring.match(date_string, patterns['M-My'][1]) then -- month/season range year; months separated by endash  
month, month2, anchor_year, year=mw.ustring.match(date_string, patterns['M-My'][1]);
month, month2, anchor_year, year = mw.ustring.match(date_string, patterns['M-My'][1]);
if (not is_valid_month_season_range(month, month2, param)) or (not is_valid_year(year)) then return false; end
if (not is_valid_month_season_range(month, month2, param)) 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);
if 0 == month or 0 == month2 then return false; end
else
else
month = get_season_number(month, param);
month = get_season_number(month, param);
month2 = get_season_number(month2, param);
month2 = get_season_number(month2, param);
end
end
year2=year;
year2 = year;
elseif mw.ustring.match(date_string, patterns['My'][1]) then -- month/season/quarter/proper-name year
elseif mw.ustring.match(date_string, patterns['My'][1]) then -- month/season/quarter/proper-name year
month, anchor_year, year=mw.ustring.match(date_string, patterns['My'][1]);
month, anchor_year, year = mw.ustring.match(date_string, patterns['My'][1]);
if not is_valid_year(year) then return false; end
if not is_valid_year(year) then return false; end
month = get_element_number (month, param); -- get month season quarter proper-name number or nil
month = get_element_number(month, param); -- get month season quarter proper-name number or nil
if not month then return false; end -- not valid whatever it is
if not month then return false; end -- not valid whatever it is


elseif mw.ustring.match(date_string, patterns['y-y'][1]) then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
elseif mw.ustring.match(date_string, patterns['y-y'][1]) then -- Year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
year, anchor_year, year2=mw.ustring.match(date_string, patterns['y-y'][1]);
year, anchor_year, year2 = mw.ustring.match(date_string, patterns['y-y'][1]);
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
Line 623: Line 619:
elseif mw.ustring.match(date_string, patterns['y4-y2'][1]) then -- Year range: YYYY–YY; separated by unspaced endash
elseif mw.ustring.match(date_string, patterns['y4-y2'][1]) then -- Year range: YYYY–YY; separated by unspaced endash
local century;
local century;
year, century, anchor_year, year2=mw.ustring.match(date_string, patterns['y4-y2'][1]);
year, century, anchor_year, year2 = mw.ustring.match(date_string, patterns['y4-y2'][1]);
anchor_year=year..'–'..anchor_year; -- assemble anchor year from both years
anchor_year = year .. '–' .. anchor_year; -- assemble anchor year from both years
 
if in_array (param, {'date', 'publication-date', 'year'}) then
add_prop_cat ('year-range-abbreviated');
end
 
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 mw.ustring.match (date_string, patterns['y'][1]) then -- year; here accept either YYY or YYYY
elseif mw.ustring.match(date_string, patterns['y'][1]) then -- year; here accept either YYY or YYYY
anchor_year, year=mw.ustring.match (date_string, patterns['y'][1]);
anchor_year, year = mw.ustring.match(date_string, patterns['y'][1]);
if false == is_valid_year(year) then
if false == is_valid_year(year) then
return false;
return false;
Line 638: Line 639:
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
if param ~= 'date' then -- CITEREF disambiguation only allowed in |date=; |year= & |publication-date= promote to date
if anchor_year:match ('%l$') then
return false;
end
end
end


Line 643: Line 650:
if 0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required
if 0 ~= year and 0 ~= month and 0 ~= day and -- all parts of a single date required
0 == year2 and 0 == month2 and 0 == day2 then -- none of these; accessdate must not be a range
0 == year2 and 0 == month2 and 0 == day2 then -- none of these; accessdate must not be a range
if not is_valid_accessdate (year..'-'..month..'-'..day) then
if not is_valid_accessdate(year .. '-' .. month .. '-' .. day) then
return false; -- return false when accessdate out of bounds
return false; -- return false when accessdate out of bounds
end
end
Line 653: Line 660:
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, param); -- <param> for |pmc-embargo-date=


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
Line 671: Line 678:


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
Line 685: Line 692:


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.
parameters with errors are added to the <error_list> sequence table as the dates are tested.


]]
]]


local function dates(date_parameters_list, tCOinS_date)
local function dates(date_parameters_list, tCOinS_date, error_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 embargo_date; -- if embargo date is a good dmy, mdy, ymd date then holds original value else reset to 9999
local error_message = "";
local good_date = false;
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.val) then -- if the parameter has a value
if is_set(v.val) then -- if the parameter has a value
v.val = mw.ustring.gsub (v.val, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9
v.val = mw.ustring.gsub(v.val, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9
if v.val:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
if v.val:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
if 'date'==k then
if 'date' == k then
anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
good_date = is_valid_year(year);
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 -- if the parameter is |date=
elseif 'date' == k then -- if the parameter is |date=
if v.val:match("^n%.d%.%a?$") then -- if |date=n.d. with or without a CITEREF disambiguator
if v.val:match("^n%.d%.%a?$") then -- ToDo: I18N -- if |date=n.d. with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); -- ToDo: I18N -- "n.d."; no error when date parameter is set to no date
elseif v.val:match("^nd%a?$") then -- if |date=nd with or without a CITEREF disambiguator
elseif v.val:match("^nd%a?$") then -- ToDo: I18N -- if |date=nd with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); -- ToDo: I18N -- "nd"; no error when date parameter is set to no date
else
else
good_date, anchor_year, COinS_date = check_date (v.val, k, tCOinS_date); -- go test the date
good_date, anchor_year, COinS_date = check_date (v.val, k, tCOinS_date); -- go test the date
end
end
elseif 'year'==k then -- if the parameter is |year= it should hold only a year value
elseif 'year' == k then -- if the parameter is |year= it should hold only a year value
if v.val:match("^[1-9]%d%d%d?%a?$") then -- if |year= 3 or 4 digits only with or without a CITEREF disambiguator
if v.val:match("^[1-9]%d%d%d?%a?$") then -- if |year = 3 or 4 digits only with or without a CITEREF disambiguator
good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)");
good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)");
end
end
elseif 'embargo'==k then -- if the parameter is |embargo=
elseif 'pmc-embargo-date' == k then -- if the parameter is |pmc-embargo-date=
good_date = check_date (v.val, k); -- go test the date
good_date = check_date (v.val, k); -- 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, embargo_date = is_valid_embargo_date (v.val); -- is |embargo= date a single dmy, mdy, or ymd formatted date? yes:returns embargo; no: returns 9999
good_date, embargo_date = is_valid_embargo_date (v.val); -- is |pmc-embargo-date= date a single dmy, mdy, or ymd formatted date? yes: returns embargo date; no: returns 9999
end
end
else -- any other date-holding parameter
else -- any other date-holding parameter
good_date = check_date (v.val, k); -- go test the date
good_date = check_date (v.val, k); -- 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 ...
table.insert (error_list, wrap_style ('parameter', v.name)); -- make parameter name suitable for error message list
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "&#124;" .. v.name .. "="; -- add the failed parameter
end
end
end
end
end
end
return anchor_year, embargo_date, error_message; -- and done
return anchor_year, embargo_date; -- and done
end
end


Line 741: Line 744:
--[[--------------------------< 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 returns a numeric value:
Compare the value provided in |year= with the year value(s) provided in |date=.  This function sets a local 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)
the numeric value in <result> determines the 'output' if any from this function:
0 – adds error message to error_list sequence table
1 – adds maint cat
2 – does nothing


]]
]]


local function year_date_check (year_string, date_string)
local function year_date_check (year_string, year_origin, date_string, date_origin, error_list)
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?)');


Line 784: Line 792:
result = 0;
result = 0;
end
end
else
else -- should never get here; this function called only when no other date errors
result = 0; -- no recognizable year in date
result = 0; -- no recognizable year in date
end
end
return result;
 
if 0 == result then -- year / date mismatch
table.insert (error_list, substitute (cfg.messages['mismatch'], {year_origin, date_origin})); -- add error message to error_list sequence table
elseif 1 == result then -- redundant year / date
set_message ('maint_date_year'); -- add a maint cat
end
end
end


Line 796: Line 809:
reformatted.  Does the grunt work for reformat_dates().
reformatted.  Does the grunt work for reformat_dates().


The table re_formats maps patern_idx (current format) and format_param (desired format) to a table that holds:
The table re_formats maps pattern_idx (current format) and format_param (desired format) to a table that holds:
format string used by string.format()
format string used by string.format()
identifier letters ('d', 'm', 'y', 'd2', 'm2', 'y2') that serve as indexes into a table t{} that holds captures
identifier letters ('d', 'm', 'y', 'd2', 'm2', 'y2') that serve as indexes into a table t{} that holds captures
Line 806: Line 819:
patterns['ymd'][1] is the match pattern with captures for mw.ustring.match()
patterns['ymd'][1] is the match pattern with captures for mw.ustring.match()
patterns['ymd'][2] is an indicator letter identifying the content of the first capture
patterns['ymd'][2] is an indicator letter identifying the content of the first capture
patterns['ymd'][3] ... the second capture etc
patterns['ymd'][3] ... the second capture etc.


when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifier
when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifier
Line 823: Line 836:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
},
},
['Mdy'] = { -- date format is Mdy; reformat to:
['Mdy'] = { -- date format is Mdy; reformat to:
Line 829: Line 842:
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
},
},
['dMy'] = { -- date format is dMy; reformat to:
['dMy'] = { -- date format is dMy; reformat to:
Line 835: Line 848:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
},
},
['Md-dy'] = { -- date format is Md-dy; reformat to:
['Md-dy'] = { -- date format is Md-dy; reformat to:
Line 870: Line 883:
['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic
['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic
},
},
-- ['yMd'] = { -- not supported at en.wiki
-- ['yMd'] = { -- not supported at en.wiki
-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- },
-- },
}
}


Line 891: Line 904:
end
end


-- if 'yMd' == format_param and in_array (pattern_idx, {'yMd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy'}) then -- not supported at en.wiki
-- yMd is not supported at en.wiki; when yMd is supported at your wiki, uncomment the next line
if 'yMd' == format_param then -- not supported at en.wiki
-- if 'yMd' == format_param and in_array (pattern_idx, {'yMd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy'}) then -- these formats not convertable; yMd not supported at en.wiki
if 'yMd' == format_param then -- yMd not supported at en.wiki; when yMd is supported at your wiki, remove or comment-out this line
return; -- not a reformattable date
return; -- not a reformattable date
end
end
Line 909: Line 923:
};
};


if t.a then -- if this date has an anchor year capture
if t.a then -- if this date has an anchor year capture (all convertable date formats except ymd)
t.y = t.a; -- use the anchor year capture when reassembling the date
if t.y2 then -- for year range date formats
t.y2 = t.a; -- use the anchor year capture when reassembling the date
else -- here for single date formats (except ymd)
t.y = t.a; -- use the anchor year capture when reassembling the date
end
end
end


if tonumber(t.m) then -- if raw month is a number (converting from ymd)
if tonumber(t.m) then -- if raw month is a number (converting from ymd)
if 's' == mon_len then -- if we are to use abbreviated month names
if 's' == mon_len then -- if we are to use abbreviated month names
t.m = cfg.date_names['inv_local_s'][tonumber(t.m)]; -- convert it to a month name
t.m = cfg.date_names['inv_local_short'][tonumber(t.m)]; -- convert it to a month name
else
else
t.m = cfg.date_names['inv_local_l'][tonumber(t.m)]; -- convert it to a month name
t.m = cfg.date_names['inv_local_long'][tonumber(t.m)]; -- convert it to a month name
end
end
t.d = t.d:gsub ('0(%d)', '%1'); -- strip leading '0' from day if present
t.d = t.d:gsub ('0(%d)', '%1'); -- strip leading '0' from day if present
elseif 'ymd' == format_param then -- when converting to ymd
elseif 'ymd' == format_param then -- when converting to ymd
if 1582 > tonumber(t.y) then -- ymd format dates not allowed before 1582
t.y = t.y:gsub ('%a', ''); -- strip CITREF disambiguator if present; anchor year already known so process can proceed; TODO: maint message?
if 1582 > tonumber (t.y) then -- ymd format dates not allowed before 1582
return;
return;
end
end
Line 931: Line 950:
t[mon] = get_month_number (t[mon]); -- get the month number for this month (is length agnostic)
t[mon] = get_month_number (t[mon]); -- get the month number for this month (is length agnostic)
if 0 == t[mon] then return; end -- seasons and named dates can't be converted
if 0 == t[mon] then return; end -- seasons and named dates can't be converted
t[mon] = (('s' == mon_len) and cfg.date_names['inv_local_s'][t[mon]]) or cfg.date_names['inv_local_l'][t[mon]]; -- fetch month name according to length
t[mon] = (('s' == mon_len) and cfg.date_names['inv_local_short'][t[mon]]) or cfg.date_names['inv_local_long'][t[mon]]; -- fetch month name according to length
end
end
end
end
Line 1,018: Line 1,037:
end -- if
end -- if
end -- for
end -- for
return result; -- declare boolean result and done
return result; -- declare boolean result and done
end
end


Line 1,035: Line 1,054:
local n;
local n;
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set (param_val.val) then
if is_set (param_val.val) and
if not mw.ustring.match (param_val.val, '%d%d%d%d%-%d%d%-%d%d') then -- for those that are not ymd dates (ustring because here digits may not be western)
not mw.ustring.match (param_val.val, patterns.ymd[1]) then -- for those that are not ymd dates (ustring because here digits may not be Western)
param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash
param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash
if 0 ~= n then
if 0 ~= n then
Line 1,042: Line 1,061:
result = true;
result = true;
end
end
end
end
end
end
end
Line 1,051: Line 1,069:
--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------
--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------


Attempts to translate English month names to local-language month names using names supplied by MediaWiki's
Attempts to translate English date names to local-language date names using names supplied by MediaWiki's
date parser function.  This is simple name-for-name replacement and may not work for all languages.
date parser function.  This is simple name-for-name replacement and may not work for all languages.


if xlat_dig is true, this function will also translate western (English) digits to the local language's digits.
if xlat_dig is true, this function will also translate Western (English) digits to the local language's digits.
This will also translate ymd dates.
This will also translate ymd dates.


]]
]]


local function date_name_xlate (date_parameters_list, xlt_dig)
local function date_name_xlate (date_parameters_list, xlt_dig)
local xlate;
local xlate;
local mode; -- long or short month names
local mode; -- long or short month names
Line 1,065: Line 1,083:
local date;
local date;
local sources_t = {
{cfg.date_names.en.long, cfg.date_names.inv_local_long}, -- for translating long English month names to long local month names
{cfg.date_names.en.short, cfg.date_names.inv_local_short}, -- short month names
{cfg.date_names.en.quarter, cfg.date_names.inv_local_quarter}, -- quarter date names
{cfg.date_names.en.season, cfg.date_names.inv_local_season}, -- season date nam
{cfg.date_names.en.named, cfg.date_names.inv_local_named}, -- named dates
}
local function is_xlateable (month) -- local function to get local date name that replaces existing English-language date name
for _, date_names_t in ipairs (sources_t) do -- for each sequence table in date_names_t
if date_names_t[1][month] then -- if date name is English month (long or short), quarter, season or named and
if date_names_t[2][date_names_t[1][month]] then -- if there is a matching local date name
return date_names_t[2][date_names_t[1][month]]; -- return the local date name
end
end
end
end
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(param_val.val) then -- if the parameter has a value
if is_set(param_val.val) then -- if the parameter has a value
date = param_val.val;
date = param_val.val;
for month in mw.ustring.gmatch (date, '%a+') do -- iterate through all dates in the date (single date or date range)
for month in mw.ustring.gmatch (date, '[%a ]+') do -- iterate through all date names in the date (single date or date range)
if cfg.date_names.en.long[month] then
month = mw.text.trim (month); -- this because quarterly dates contain whitespace
mode = 'F'; -- English name is long so use long local name
xlate = is_xlateable (month); -- get translate <month>; returns translation or nil
elseif cfg.date_names.en.short[month] then
mode = 'M'; -- English name is short so use short local name
if xlate then
else
mode = nil; -- not an English month name; could be local language month name or an English season name
end
if mode then -- might be a season
xlate = lang_object:formatDate(mode, '1' .. month); -- translate the month name to this local language
date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation
date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation
date_parameters_list[param_name].val = date; -- save the translated date
date_parameters_list[param_name].val = date; -- save the translated date
Line 1,086: Line 1,116:


if xlt_dig then -- shall we also translate digits?
if xlt_dig then -- shall we also translate digits?
date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from western to 'local digits'
date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from Western to 'local digits'
date_parameters_list[param_name].val = date; -- save the translated date
date_parameters_list[param_name].val = date; -- save the translated date
modified = true;
modified = true;
Line 1,094: Line 1,124:
return modified;
return modified;
end
end




Line 1,104: Line 1,134:


local function set_selected_modules (cfg_table_ptr, utilities_page_ptr)
local function set_selected_modules (cfg_table_ptr, utilities_page_ptr)
is_set = utilities_page_ptr.is_set; -- import functions from selected Module:Citation/CS1/Utilities module
add_prop_cat = utilities_page_ptr.add_prop_cat ; -- import functions from selected Module:Citation/CS1/Utilities module
in_array = utilities_page_ptr.in_array; -- import functions from selected Module:Citation/CS1/Utilities module
is_set = utilities_page_ptr.is_set;
in_array = utilities_page_ptr.in_array;
set_message = utilities_page_ptr.set_message;
substitute = utilities_page_ptr.substitute;
wrap_style = utilities_page_ptr.wrap_style;
 
cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration
cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration
end
end
Retrieved from "https://en.seminaverbi.bibleget.io/wiki/Special:MobileDiff/400...27096"