32,512
edits
(Synch from sandbox;) |
m (1 revision imported: for franchise page) |
||
(2 intermediate revisions by 2 users not shown) | |||
Line 1:
--[[--------------------------< F O R W A R D D E C L A R A T I O N S >--------------------------------------
]]
local is_set, in_array; -- imported functions from selected Module:Citation/CS1/Utilities
local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration
--[[--------------------------< F I L E - S C O P E D E C L A R A T I O N S >--------------------------------
File-scope variables are declared here
]]
local lang_object = mw.getContentLanguage(); -- used by is_valid_accessdate(), is_valid_year(), date_name_xlate(); TODO: move to ~/Configuration?
local year_limit; -- used by is_valid_year()
Line 29 ⟶ 37:
local function is_valid_accessdate (accessdate)
local good1, good2;
local access_ts, tomorrow_ts; -- to hold unix time stamps representing the dates
good1, access_ts = pcall
good2, tomorrow_ts = pcall
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);
tomorrow_ts = tonumber (tomorrow_ts) or lang_object:parseFormattedNumber (tomorrow_ts);
else
return false; -- one or both failed to convert to unix time stamp
Line 48 ⟶ 55:
return false; -- accessdate out of range
end
end
Line 82 ⟶ 74:
end
return false, '9999'; -- if here not good date so return false and set embargo date to long time in future
end
--[[--------------------------< G E T _ M O N T H _ N U M B E R >----------------------------------------------
returns a number according to the month in a date: 1 for January, etc. Capitalization and spelling must be correct.
If not a valid month, returns 0
]]
local function get_month_number (month)
return cfg.date_names['local'].long[month] or cfg.date_names['local'].short[month] or -- look for local names first
cfg.date_names['en'].long[month] or cfg.date_names['en'].short[month] or -- failing that, look for English names
0; -- not a recognized month name
end
Line 87 ⟶ 93:
--[[--------------------------< 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:
must be correct. If not a valid season, returns 0.
21-24 = Spring, Summer, Autumn, Winter, independent of “Hemisphere”
returns 0 when <param> is not |date=
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
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.
These additional divisions not currently supported:
25-28 = Spring - Northern Hemisphere, Summer- Northern Hemisphere, Autumn - Northern Hemisphere, Winter - Northern Hemisphere
29-32 = Spring – Southern Hemisphere, Summer– Southern Hemisphere, Autumn – Southern Hemisphere, Winter - Southern Hemisphere
33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each)
37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each)
40-41 = Semestral 1, Semestral-2 (6 months each)
]]
local function get_season_number (season, param)
if 'date' ~= param then
return 0; -- season dates only supported by |date=
end
return cfg.date_names['local'].season[season] or -- look for local names first
cfg.date_names['en'].season[season] or -- failing that, look for English names
0; -- not a recognized season name
end
--[[--------------------------< G E T _ Q U A R T E R _ N U M B E R >------------------------------------------
returns a number according to the sequence of quarters in a year: 33 for first quarter, etc. Capitalization and spelling
must be correct. If not a valid quarter, returns 0.
33-36 = Quarter 1, Quarter 2, Quarter 3, Quarter 4 (3 months each)
returns 0 when <param> is not |date=
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
numbers 21-41. cs1|2 only supports generic seasons and quarters.
These additional divisions not currently supported:
37-39 = Quadrimester 1, Quadrimester 2, Quadrimester 3 (4 months each)
40-41 = Semestral 1, Semestral-2 (6 months each)
]]
local function
if 'date' ~= param then
return 0; -- quarter dates only supported by |date=
end
quarter = mw.ustring.gsub (quarter, ' +', ' '); -- special case replace multiple space chars with a single space char
return cfg.date_names['local'].quarter[quarter] or -- look for local names first
cfg.date_names['en'].quarter[quarter] or -- failing that, look for English names
0; -- not a recognized quarter name
end
--[[--------------------------< G E T _ P R O P E R _ N A M E _ N U M B E R >----------------------------------
returns a non-zero number if date contains a recognized proper-name. Capitalization and spelling must be correct.
returns 0 when <param> is not |date=
]]
local function
if 'date' ~= param then
return 0; -- proper-name dates only supported by |date=
end
return cfg.date_names['local'].named[name] or -- look for local names dates first
cfg.date_names['en'].named[name] or -- failing that, look for English names
0; -- not a recognized named date
end
--[[--------------------------< G E T _ E L E M E N T _ N U M B E R <------------------------------------------
returns true if month or season or quarter or proper name is valid (properly spelled, capitalized, abbreviated)
]]
local function get_element_number (element, param)
local num;
local funcs = {get_month_number, get_season_number, get_quarter_number, get_proper_name_number}; -- list of functions to execute in order
for _, func in ipairs (funcs) do -- spin through the function list
num = func (element, param); -- call the function and get the returned number
if 0 ~= num then -- non-zero when valid month season quarter
return num; -- return that number
end
end
return
end
--[[--------------------------< I S _ V A L I D _ Y E A R >----------------------------------------------------
Function gets current year from the server and compares it to year from a citation parameter. Years more than one
year in the future are not acceptable.
]]
local function is_valid_year (year)
if not is_set(year_limit) then
year_limit = tonumber(os.date("%Y"))+1; -- global variable so we only have to fetch it once
end
year = tonumber (year) or lang_object:parseFormattedNumber (year); -- convert to numbers for the comparison;
return year and (year <= year_limit) or false;
end
--[[--------------------------< I S _ V A L I D _ D A T E >----------------------------------------------------
Returns true if day is less than or equal to the number of days in month and year is no farther into the future
than next year; else returns false.
Line 163 ⟶ 231:
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
if 0==(year%4) then -- is a leap year?
month_length = 29; -- if leap year then 29 days in February
end
else -- Gregorian calendar
Line 180 ⟶ 248:
return true;
end
--[[--------------------------< I S _ V A L I D _ M O N T H _ R A N G E _ S T Y L E >--------------------------
Line 211 ⟶ 280:
Month pairs are expected to be left to right, earliest to latest in time.
All season ranges are accepted as valid because there are publishers out there who have published a Summer–Spring YYYY issue so ... ok
]]
local function is_valid_month_season_range(range_start, range_end, param)
local range_start_number = get_month_number (range_start);
local range_end_number;
if 0 == range_start_number then -- is this a month range?
range_end_number = get_season_number (range_end, param);
if (0 ~= range_start_number)
return true; -- any season pairing is accepted
end
return false; -- range_start
end
-- here when range_start is a month
range_end_number = get_month_number (range_end); -- get end month number
if range_start_number < range_end_number then -- range_start is a month; does range_start precede range_end?
Line 264 ⟶ 327:
The input table has:
year, year2 – always present; if before 1582, ignore months and days if present
month, month2 – 0 if not provided, 1-12 for months, 21-24 for seasons;
day, day2 – 0 if not provided, 1-31 for days
the output table receives:
rftdate: an IS8601 formatted date
rftchron: a free-form version of the date, usually without year which is in rftdate (season ranges and
rftssn: one of four season keywords: winter, spring, summer, fall (lowercase)
rftquarter: one of four values: 1, 2, 3, 4
]]
Line 277 ⟶ 341:
local date; -- one date or first date in a range
local date2 = ''; -- end of range date
-- start temporary Julian / Gregorian calendar uncertainty detection
local year = tonumber(input.year); -- this temporary code to determine the extent of sources dated to the Julian/Gregorian
local month = tonumber(input.month); -- interstice 1 October 1582 – 1 January 1926
local day = tonumber (input.day);
if (0 ~= day) and -- day must have a value for this to be a whole date
(((1582 == year) and (10 <= month) and (12 >= month)) or -- any whole 1582 date from 1 october to 31 December or
((1926 == year) and (1 == month) and (1 == input.day)) or -- 1 January 1926 or
((1582 < year) and (1925 >= year))) then -- any date 1 January 1583 – 31 December 1925
tCOinS_date.inter_cal_cat = true; -- set category flag true
end
-- end temporary Julian / Gergorian calendar uncertainty detection
if 1582 > tonumber(input.year) or 20 < tonumber(input.month) then -- Julian calendar or season so &rft.date gets year only
Line 283 ⟶ 358:
date = string.format ('%.4d/%.4d', tonumber(input.year), tonumber(input.year2)) -- assemble the date range
end
if 20 < tonumber(input.month) then -- if season or
local season = {[
if 0 == input.month2 then -- single season date
if
tCOinS_date.rftchron = season[input.month]; -- proper
elseif 30 <tonumber(input.month) then
tCOinS_date.rftquarter = season[input.month]; -- quarters
else
tCOinS_date.rftssn = season[input.month]; -- seasons
Line 328 ⟶ 405:
return;
end
--[[--------------------------< P A T T E R N S >--------------------------------------------------------------
this is the list of patterns for date formats that this module recognizes. Approximately the first half of these
patterns represent formats that might be reformatted into another format. Those that might be reformatted have
'indicator' letters that identify the content of the matching capture: 'd' (day), 'm' (month), 'a' (anchor year),
'y' (year); second day, month, year have a '2' suffix.
These patterns are used for both date validation and for reformatting. This table should not be moved to ~/Configuration
because changes to this table require changes to check_date() and to reformatter() and reformat_date()
]]
local patterns = {
-- year-initial numerical year-month-day
['ymd'] = {'^(%d%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'},
-- month-initial: month day, year
['Mdy'] = {'^(%D-) +([1-9]%d?), +((%d%d%d%d?)%a?)$', 'm', 'd', 'a', 'y'},
-- month-initial day range: month day–day, year; days are separated by endash
['Md-dy'] = {'^(%D-) +([1-9]%d?)[%-–]([1-9]%d?), +((%d%d%d%d)%a?)$', 'm', 'd', 'd2', 'a', 'y'},
-- day-initial: day month year
['dMy'] = {'^([1-9]%d?) +(%D-) +((%d%d%d%d?)%a?)$', 'd', 'm', 'a', 'y'},
-- year-initial: year month day; day: 1 or 2 two digits, leading zero allowed; not supported at en.wiki
-- ['yMd'] = {'^((%d%d%d%d?)%a?) +(%D-) +(%d%d?)$', 'a', 'y', 'm', 'd'},
-- day-range-initial: day–day month year; days are separated by endash
['d-dMy'] = {'^([1-9]%d?)[%-–]([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'd2', 'm', 'a', 'y'},
-- day initial month-day-range: day month - day month year; uses spaced endash
['dM-dMy'] = {'^([1-9]%d?) +(%D-) +[%-–] +([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'm', 'd2', 'm2', 'a', 'y'},
-- month initial month-day-range: month day – month day, year; uses spaced endash
['Md-Mdy'] = {'^(%D-) +([1-9]%d?) +[%-–] +(%D-) +([1-9]%d?), +((%d%d%d%d)%a?)$','m', 'd', 'm2', 'd2', 'a', 'y'},
-- day initial month-day-year-range: day month year - day month year; uses spaced endash
['dMy-dMy'] = {'^([1-9]%d?) +(%D-) +(%d%d%d%d) +[%-–] +([1-9]%d?) +(%D-) +((%d%d%d%d)%a?)$', 'd', 'm', 'y', 'd2', 'm2', 'a', 'y2'},
-- month initial month-day-year-range: month day, year – month day, year; uses spaced endash
['Mdy-Mdy'] = {'^(%D-) +([1-9]%d?), +(%d%d%d%d) +[%-–] +(%D-) +([1-9]%d?), +((%d%d%d%d)%a?)$', 'm', 'd', 'y', 'm2', 'd2', 'a', 'y2'},
-- these date formats cannot be converted, per se, but month name can be rendered short or long
-- month/season year - month/season year; separated by spaced endash
['My-My'] = {'^(%D-) +(%d%d%d%d) +[%-–] +(%D-) +((%d%d%d%d)%a?)$', 'm', 'y', 'm2', 'a', 'y2'},
-- month/season range year; months separated by endash
['M-My'] = {'^(%D-)[%-–](%D-) +((%d%d%d%d)%a?)$', 'm', 'm2', 'a', 'y'},
-- month/season year or proper-name year; quarter year when First Quarter YYYY etc
['My'] = {'^([^%d–]-) +((%d%d%d%d)%a?)$', 'm', 'a', 'y'}, -- this way because endash is a member of %D; %D- will match January–March 2019 when it shouldn't
-- these date formats cannot be converted
-- ['Q,y'] = {'^(Q%a* +[1-4]), +((%d%d%d%d)%a?)$'}, -- Quarter n, yyyy
['Sy4-y2'] = {'^(%D-) +((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
['Sy-y'] = {'^(%D-) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)$'}, -- special case Winter/Summer year-year; year separated with unspaced endash
['y-y'] = {'^(%d%d%d%d?)[%-–]((%d%d%d%d?)%a?)$'}, -- year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
['y4-y2'] = {'^((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- year range: YYYY–YY; separated by unspaced endash
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- year; here accept either YYY or YYYY
}
Line 352 ⟶ 482:
]]
local function check_date (date_string,
local year; -- assume that year2, months, and days are not used;
local year2=0; -- second year in a year range
local month=0;
local month2=0; -- second month in a month range
local day=0;
local day2=0; -- second day in a day range
local anchor_year;
local coins_date;
if date_string:match (
year, month, day=
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or 0 == tonumber(day) then return false; end -- month or day number not valid or not Gregorian calendar
anchor_year = year;
-- elseif mw.ustring.match(date_string, 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
month, day, anchor_year, year=
month = get_month_number (month);
if 0 == month then return false; end
elseif mw.ustring.match(date_string,
month, day, day2, anchor_year, year=mw.ustring.match(date_string,
if tonumber(day) >= tonumber(day2) then return false; end
month = get_month_number (month);
if 0 == month then return false; end
month2=month;
year2=year;
elseif
day, month, anchor_year, year=
month = get_month_number (month);
if 0 == month then return false; end
--[[ NOT supported at en.wiki
anchor_year, year, month, day=mw.ustring.match(date_string, patterns['yMd'][1]);
month = get_month_number (month);
if 0 == month then return false; end
-- end NOT supported at en.wiki ]]
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]);
if tonumber(day) >= tonumber(day2) then return false; end -- date range order is left to right: earlier to later; dates may not be the same;
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
month2=month; -- for metadata
year2=year;
elseif mw.ustring.match(date_string,
day, month, day2, month2, anchor_year, year=mw.ustring.match(date_string,
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);
month2 = get_month_number (month2);
year2=year;
elseif mw.ustring.match(date_string,
month, day, month2, day2, anchor_year, year=mw.ustring.match(date_string,
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);
month2 = get_month_number (month2);
year2=year;
elseif mw.ustring.match(date_string,
day, month, year, day2, month2, anchor_year, year2=mw.ustring.match(date_string,
if tonumber(year2) <= tonumber(year) then return false; end
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);
month2 = get_month_number (month2);
elseif mw.ustring.match(date_string,
month, day, year, month2, day2, anchor_year, year2=mw.ustring.match(date_string,
if tonumber(year2) <= tonumber(year) then return false; end
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);
month2 = get_month_number (month2);
elseif mw.ustring.match(date_string,
local century;
month, year, century, anchor_year, year2=mw.ustring.match(date_string,
if 'Winter' ~= month and 'Summer' ~= month then return false end;
anchor_year=year..'–'..anchor_year;
year2 = century..year2;
if 1 ~= tonumber(year2) - tonumber(year) then return false; end
if not is_valid_year(year2) then return false; end
month = get_season_number (month, param);
elseif mw.ustring.match(date_string,
month, year, anchor_year, year2=mw.ustring.match(date_string,
if 'Winter' ~= month and 'Summer' ~= month then return false end;
anchor_year=year..'–'..anchor_year;
if 1 ~= tonumber(year2) - tonumber(year) then return false; end
if not is_valid_year(year2) then return false; end
month = get_season_number (month, param);
elseif mw.ustring.match(date_string,
month, year, month2, anchor_year, year2=mw.ustring.match(date_string,
anchor_year=year..'–'..anchor_year;
if tonumber(year) >= tonumber(year2) then return false; end
if not is_valid_year(year2) then return false; end
if 0 ~= get_month_number(month) and 0 ~= get_month_number(month2) and is_valid_month_range_style(month, month2) then -- both must be month year, same month style
month = get_month_number(month);
month2 = get_month_number(month2);
elseif 0 ~= get_season_number(month, param) and 0 ~= get_season_number(month2, param) then
month = get_season_number(month, param);
month2 = get_season_number(month2, param);
else
return false;
end
elseif mw.ustring.match(date_string,
month, month2, anchor_year, year=mw.ustring.match(date_string,
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
month = get_month_number(month);
month2 = get_month_number(month2);
else
month = get_season_number(month, param);
month2 = get_season_number(month2, param);
end
year2=year;
elseif
month, anchor_year, year=
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
if
elseif mw.ustring.match(date_string,
year, anchor_year, year2=mw.ustring.match(date_string,
anchor_year=year..'–'..anchor_year; -- assemble anchor year from both years
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif mw.ustring.match(date_string,
local century;
year, century, anchor_year, year2=mw.ustring.match(date_string,
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
Line 493 ⟶ 630:
if not is_valid_year(year2) then return false; end -- no year farther in the future than next year
elseif
anchor_year, year=
if false == is_valid_year(year) then
return false;
Line 503 ⟶ 640:
end
if
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
Line 560 ⟶ 697:
for k, v in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(v.val) then
v.val = mw.ustring.gsub (v.val, '%d', cfg.date_names.local_digits); -- translate 'local' digits to Western 0-9
local year = v.val:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
if 'date'==k then
anchor_year, COinS_date = v.val:match("((c%. [1-9]%d%d%d?)%a?)"); -- anchor year and COinS_date only from |date= parameter
good_date = is_valid_year(year);
elseif 'year'==k then
Line 570 ⟶ 708:
end
elseif 'date'==k then -- if the parameter is |date=
if v.val:match("^n%.d%.%a?$") then
good_date, anchor_year, COinS_date = true, v.val:match("((n%.d%.)%a?)"); --"n.d."; no error when date parameter is set to no date
elseif v.val:match("^nd%a?$") then
good_date, anchor_year, COinS_date = true, v.val:match("((nd)%a?)"); --"nd"; no error when date parameter is set to no date
else
good_date, anchor_year, COinS_date = check_date (v.val, k, tCOinS_date); -- go test the date
end
elseif 'year'==k then -- if the parameter is |year= it should hold only a year value
if v.val:match("^[1-9]%d%d%d?%a?$") then
good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)");
end
elseif 'embargo'==k then -- if the parameter is |embargo=
good_date = check_date (v.val, k);
if true == good_date then -- if the date is a valid date
good_date, embargo_date = is_valid_embargo_date (v.val);
end
else -- any other date-holding parameter
good_date = check_date (v.val, k);
end
if false==good_date then -- assemble one error message so we don't add the tracking category multiple times
Line 595 ⟶ 731:
error_message=error_message .. ", "; -- ... add a comma space separator
end
error_message=error_message .. "|" ..
end
end
end
return anchor_year, embargo_date, error_message;
end
Line 635 ⟶ 771:
end
elseif mw.ustring.match(date_string, "%d%d%d%d[%-–]%d%d") then
local century;
date1, century, date2 = mw.ustring.match(date_string, "((%d%d)%d%d)[%-–]+(%d%d)");
Line 655 ⟶ 791:
--[[--------------------------< R E F O R M A T
reformat 'date' into new format specified by format_param if pattern_idx (the current format of 'date') can be
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:
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
from mw.ustring.match() for the various date parts specified by patterns[pattern_idx][1]
Items in patterns{} have the general form:
['ymd'] = {'^(%d%d%d%d)%-(%d%d)%-(%d%d)$', 'y', 'm', 'd'}, where:
['ymd'] is pattern_idx
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'][3] ... the second capture etc
when a pattern matches a date, the captures are loaded into table t{} in capture order using the idemtifier
characters as indexes into t{} For the above, a ymd date is in t{} as:
t.y = first capture (year), t.m = second capture (month), t.d = third capture (day)
To reformat, this function is called with the pattern_idx that matches the current format of the date and with
format_param set to the desired format. This function loads table t{} as described and then calls string.format()
with the format string specified by re_format[pattern_idx][format_param][1] using values taken from t{} according
to the capture identifier letters specified by patterns[pattern_idx][format_param][n] where n is 2..
]]
local re_formats = {
['ymd'] = { -- date format is ymd; reformat to:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['yMd'] = {'%s %s %s', 'y', 'm', 'd'}, -- |df=yMd; not supported at en.wiki
},
['Mdy'] = { -- date format is Mdy; reformat to:
['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- for long/short reformatting
['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; not supported at en.wiki
},
['dMy'] = { -- date format is dMy; reformat to:
['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- for long/short reformatting
['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; not supported at en.wiki
},
['Md-dy'] = { -- date format is Md-dy; reformat to:
['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- for long/short reformatting
['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- |df=dmy -> d-dMy
},
['d-dMy'] = { -- date format is d-d>y; reformat to:
['dmy'] = {'%s–%s %s %s', 'd', 'd2', 'm', 'y'}, -- for long/short reformatting
['mdy'] = {'%s %s–%s, %s', 'm', 'd', 'd2', 'y'}, -- |df=mdy -> Md-dy
},
['dM-dMy'] = { -- date format is dM-dMy; reformat to:
['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- for long/short reformatting
['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- |df=mdy -> Md-Mdy
},
['Md-Mdy'] = { -- date format is Md-Mdy; reformat to:
['mdy'] = {'%s %s – %s %s, %s', 'm', 'd', 'm2', 'd2', 'y'}, -- for long/short reformatting
['dmy'] = {'%s %s – %s %s %s', 'd', 'm', 'd2', 'm2', 'y'}, -- |df=dmy -> dM-dMy
},
['dMy-dMy'] = { -- date format is dMy-dMy; reformat to:
['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- for long/short reformatting
['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- |df=mdy -> Mdy-Mdy
},
['Mdy-Mdy'] = { -- date format is Mdy-Mdy; reformat to:
['mdy'] = {'%s %s, %s – %s %s, %s', 'm', 'd', 'y', 'm2', 'd2', 'y2'}, -- for long/short reformatting
['dmy'] = {'%s %s %s – %s %s %s', 'd', 'm', 'y', 'd2', 'm2', 'y2'}, -- |df=dmy -> dMy-dMy
},
['My-My'] = { -- these for long/short reformatting
['any'] = {'%s %s – %s %s', 'm', 'y', 'm2', 'y2'}, -- dmy/mdy agnostic
},
['M-My'] = { -- these for long/short reformatting
['any'] = {'%s–%s %s', 'm', 'm2', 'y'}, -- dmy/mdy agnostic
},
['My'] = { -- these for long/short reformatting
['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic
},
-- ['yMd'] = { -- not supported at en.wiki
-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'}, -- |df=mdy
-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'}, -- |df=dmy
-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'}, -- |df=ymd
-- },
}
local function reformatter (date, pattern_idx, format_param, mon_len)
if not in_array (pattern_idx, {'ymd', 'Mdy', 'Md-dy', 'dMy', 'yMd', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My-My', 'M-My', 'My'}) then
return; -- not in this set of date format patterns then not a reformattable date
end
if 'ymd' == format_param and in_array (pattern_idx, {'ymd', 'Md-dy', 'd-dMy', 'dM-dMy', 'Md-Mdy', 'dMy-dMy', 'Mdy-Mdy', 'My-My', 'M-My', 'My'}) then
return; -- ymd date ranges not supported at en.wiki; no point in reformatting ymd to ymd
end
if in_array (pattern_idx, {'My', 'M-My', 'My-My'}) then -- these are not dmy/mdy so can't be 'reformatted' into either
format_param = 'any'; -- so format-agnostic
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
if 'yMd' == format_param then -- not supported at en.wiki
return; -- not a reformattable date
end
local c1, c2, c3, c4, c5, c6, c7; -- these hold the captures specified in patterns[pattern_idx][1]
c1, c2, c3, c4, c5, c6, c7 = mw.ustring.match (date, patterns[pattern_idx][1]); -- get the captures
local t = { -- table that holds k/v pairs of date parts from the captures and patterns[pattern_idx][2..]
[patterns[pattern_idx][2]] = c1; -- at minimum there is always one capture with a matching indicator letter
[patterns[pattern_idx][3] or 'x'] = c2; -- patterns can have a variable number of captures; each capture requires an indicator letter;
[patterns[pattern_idx][4] or 'x'] = c3; -- where there is no capture, there is no indicator letter so n in patterns[pattern_idx][n] will be nil;
[patterns[pattern_idx][5] or 'x'] = c4; -- the 'x' here spoofs an indicator letter to prevent 'table index is nil' error
[patterns[pattern_idx][6] or 'x'] = c5;
[patterns[pattern_idx][7] or 'x'] = c6;
[patterns[pattern_idx][8] or 'x'] = c7;
};
if t.a then -- if this date has an anchor year capture
t.y = t.a; -- use the anchor year capture when reassembling the date
end
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
t.m = cfg.date_names['inv_local_s'][tonumber(t.m)]; -- convert it to a month name
else
t.m = cfg.date_names['inv_local_l'][tonumber(t.m)]; -- convert it to a month name
end
t.d = t.d:gsub ('0(%d)', '%1'); -- strip leading '0' from day if present
elseif 'ymd' == format_param then -- when converting to ymd
if 1582 > tonumber(t.y) then -- ymd format dates not allowed before 1582
return;
end
t.m = string.format ('%02d', get_month_number (t.m)); -- make sure that month and day are two digits
t.d = string.format ('%02d', t.d);
elseif mon_len then -- if mon_len is set to either 'short' or 'long'
for _, mon in ipairs ({'m', 'm2'}) do -- because there can be two month names, check both
if t[mon] then
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
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
end
end
end
local new_date = string.format (re_formats[pattern_idx][format_param][1], -- format string
t[re_formats[pattern_idx][format_param][2]], -- named captures from t{}
t[re_formats[pattern_idx][format_param][3]],
t[re_formats[pattern_idx][format_param][4]],
t[re_formats[pattern_idx][format_param][5]],
t[re_formats[pattern_idx][format_param][6]],
t[re_formats[pattern_idx][format_param][7]],
t[re_formats[pattern_idx][format_param][8]]
);
return new_date;
end
Line 717 ⟶ 952:
--[[-------------------------< R E F O R M A T _ D A T E S >--------------------------------------------------
Reformats existing dates into the format specified by format
format is one of several manual keywords: dmy, dmy-all, mdy, mdy-all, ymd, ymd-all. The -all version includes
access- and archive-dates; otherwise these dates are not reformatted.
This function allows automatic date formatting. In ~/Configuration, the article source is searched for one of
the {{use xxx dates}} templates. If found, xxx becomes the global date format as xxx-all. If |cs1-dates= in
{{use xxx dates}} has legitimate value then that value determines how cs1|2 dates will be rendered. Legitimate
values for |cs1-dates= are:
l - all dates are rendered with long month names
ls - publication dates use long month names; access-/archive-dates use abbreviated month names
ly - publication dates use long month names; access-/archive-dates rendered in ymd format
s - all dates are rendered with abbreviated (short) month names
sy - publication dates use abbreviated month names; access-/archive-dates rendered in ymd format
y - all dates are rendered in ymd format
the format argument for automatic date formatting will be the format specified by {{use xxx dates}} with the
value supplied by |cs1-dates so one of: xxx-l, xxx-ls, xxx-ly, xxx-s, xxx-sy, xxx-y, or simply xxx (|cs1-dates=
empty, omitted, or invalid) where xxx shall be either of dmy or mdy.
dates are extracted from date_parameters_list, reformatted (if appropriate), and then written back into the
list in the new format. Dates in date_parameters_list are presumed here to be valid (no errors). This function
returns true when a date has been reformatted, false else. Actual reformatting is done by reformatter().
]]
local function reformat_dates (date_parameters_list, format
local all = false; -- set to false to skip access- and archive-dates
local len_p = 'l'; -- default publication date length shall be long
local len_a = 'l'; -- default access-/archive-date length shall be long
local result = false;
local new_date;
if format:match('%a+%-all') then -- manual df keyword; auto df keyword when length not specified in {{use xxx dates}};
format = format:match('(%a+)%-all'); -- extract the format
all = true; --
elseif format:match('%a+%-[lsy][sy]?') then -- auto df keywords; internal only
all = true; -- auto df applies to all dates; use length specified by capture len_p for all dates
format, len_p, len_a = format:match('(%a+)%-([lsy])([sy]?)'); -- extract the format and length keywords
if
format = 'ymd'; -- override {{use xxx dates}}
elseif (not is_set(len_a)) or (len_p == len_a) then -- no access-/archive-date length specified or same length as publication dates then
len_a = len_p; -- in case len_a not set
end
end -- else only publication dates and they are long
for param_name, param_val in pairs (date_parameters_list) do -- for each date-holding parameter in the list
if is_set (param_val.val) then -- if the parameter has a value
if not (not all and in_array (param_name, {'access-date', 'archive-date'})) then -- skip access- or archive-date unless format is xxx-all; yeah, ugly; TODO: find a better way
for pattern_idx, pattern in pairs (patterns) do
if mw.ustring.match (param_val.val, pattern[1]) then
if all and in_array (param_name, {'access-date', 'archive-date'}) then -- if this date is an access- or archive-date
new_date = reformatter (param_val.val, pattern_idx, (('y' == len_a) and 'ymd') or format, len_a); -- choose ymd or dmy/mdy according to len_a setting
else -- all other dates
new_date = reformatter (param_val.val, pattern_idx, format, len_p);
end
if new_date then -- set when date was reformatted
date_parameters_list[param_name].val = new_date; -- update date in date list
result = true; -- and announce that changes have been made
end
end -- if
end -- for
end -- if
end -- if
end -- for
return result; -- declare boolean result and done
end
Line 783 ⟶ 1,035:
local n;
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if
if not mw.ustring.match (param_val.val, '%d%d%d%d%-%d%d%-%d%d') then -- for those that are not ymd dates (ustring because here digits may not be western)
param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash
if 0 ~= n then
date_parameters_list[param_name].val = param_val.val; -- update the list
result = true;
end
end
end
end
return result; -- so we know if any hyphens were replaced
end
--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------
Attempts to translate English month names to local-language month names using names supplied by MediaWiki's
date parser function. This is simple name-for-name replacement and may not work for all languages.
if xlat_dig is true, this function will also translate western (English) digits to the local language's digits.
This will also translate ymd dates.
]]
local function date_name_xlate (date_parameters_list, xlt_dig)
local xlate;
local mode; -- long or short month names
local modified = false;
local date;
for param_name, param_val in pairs(date_parameters_list) do -- for each date-holding parameter in the list
if is_set(param_val.val) then -- if the parameter has a value
date = param_val.val;
for month in mw.ustring.gmatch (date, '%a+') do -- iterate through all dates in the date (single date or date range)
if cfg.date_names.en.long[month] then
mode = 'F'; -- English name is long so use long local name
elseif cfg.date_names.en.short[month] then
mode = 'M'; -- English name is short so use short local name
else
mode = nil; -- not an English month name; could be local language month name or an English season name
end
if mode then -- might be a season
xlate = 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_parameters_list[param_name].val = date; -- save the translated date
modified = true;
end
end
if xlt_dig then -- shall we also translate digits?
date = date:gsub ('%d', cfg.date_names.xlate_digits); -- translate digits from western to 'local digits'
date_parameters_list[param_name].val = date; -- save the translated date
modified = true;
end
end
end
return modified;
end
Line 801 ⟶ 1,103:
]]
local function set_selected_modules (cfg_table_ptr, utilities_page_ptr)
is_set = utilities_page_ptr.is_set; -- import functions from
in_array = utilities_page_ptr.in_array;
cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration
end
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
return { -- return exported functions
Line 813 ⟶ 1,118:
reformat_dates = reformat_dates,
date_hyphen_to_dash = date_hyphen_to_dash,
date_name_xlate = date_name_xlate,
set_selected_modules = set_selected_modules
}
|