Module:Citation/CS1/Date validation: Difference between revisions
Module:Citation/CS1/Date validation (view source)
Revision as of 13:07, 3 February 2023
, 1 year ago1 revision imported from wikipedia:Module:Citation/CS1/Date_validation
m (1 revision imported) |
m (1 revision imported from wikipedia:Module:Citation/CS1/Date_validation) |
||
(3 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 add_prop_cat, is_set, in_array, set_message, substitute, wrap_style;
local cfg; -- table of tables imported from selected Module:Citation/CS1/Configuration
Line 44 ⟶ 43:
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
Line 55 ⟶ 54:
return false; -- accessdate out of range
end
end
Line 85 ⟶ 65:
local function get_month_number (month)
return cfg.date_names['local'].long[month] or cfg.date_names['local'].short[month] or
cfg.date_names['en'].long[month] or cfg.date_names['en'].short[month] or
0;
end
Line 102 ⟶ 82:
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
These additional divisions not currently supported:
Line 195 ⟶ 175:
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.
Special case for |pmc-embargo-date=: years more than two years in the future are not acceptable
]]
local function is_valid_year (year, param)
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
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;
end
Line 219 ⟶ 205:
]]
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 month_length;
if not is_valid_year (year, param) then
return false;
end
month = tonumber (month); -- required for YYYY-MM-DD dates
if (2 == month) then
month_length = 28; -- then 28 days unless
if 1582 > tonumber(year) then -- Julian calendar
if 0 == (year%4) then
month_length = 29; -- if leap year then 29 days in February
end
else -- Gregorian calendar
if (0 == (year%4) and (0 ~= (year%100) or 0 == (year%400))) then
month_length = 29; -- if leap year then 29 days in February
end
Line 253 ⟶ 239:
Months in a range are expected to have the same style: Jan–Mar or October–December but not February–Mar or Jul–August.
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
]]
local function is_valid_month_range_style (month1, month2)
if (cfg.date_names.en.long[month1] and cfg.date_names.en.long[month2]) or -- are both English names listed in the long subtable?
(cfg.date_names.en.short[month1] and cfg.date_names.en.short[month2]) or -- are both English names listed in the short subtable?
(cfg.date_names['local'].long[month1] and cfg.date_names['local'].long[month2]) or -- are both local names listed in the long subtable?
(cfg.date_names['local'].short[month1] and cfg.date_names['local'].short[month2]) then -- are both local names listed in the short subtable?
return true;
end
return false; -- names are mixed
end
Line 299 ⟶ 280:
-- 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
return true; -- proper order and same style
end
return false; -- range_start month number is greater than or equal to range end number; or range end isn't a month
Line 429 ⟶ 409:
['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?)$', 'd', 'd2', 'm', 'a', 'y'},
Line 456 ⟶ 436:
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- 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 482 ⟶ 481:
local function check_date (date_string, param, tCOinS_date)
local year; -- assume that year2, months, and days are not used;
local year2 = 0;
local month = 0;
local month2 = 0;
local day = 0;
local day2 = 0; -- second day in a day range
Line 562 ⟶ 561:
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
anchor_year = year .. '–' .. anchor_year;
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
Line 570 ⟶ 569:
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]);
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 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['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]);
anchor_year = year .. '–' .. anchor_year;
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
Line 612 ⟶ 613:
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]);
anchor_year = year .. '–' .. anchor_year;
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
Line 619 ⟶ 620:
local century;
year, century, anchor_year, year2 = mw.ustring.match(date_string, patterns['y4-y2'][1]);
anchor_year = year .. '–' .. anchor_year;
if in_array (param, {'date', 'publication-date', 'year'}) then
add_prop_cat ('
end
if 13 > tonumber(year2) then return false; end -- don't allow 2003-05 which might be May 2003
year2 = century .. year2;
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, patterns['y'][1]) then -- year; here accept either YYY or YYYY
anchor_year, year = mw.ustring.match(date_string, patterns['y'][1]);
if false == is_valid_year(year) then
Line 638 ⟶ 639:
else
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
Line 653 ⟶ 660:
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)
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)
result = is_valid_date (year, month, day);
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)
result = is_valid_date (year, month, day);
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)
Line 718 ⟶ 725:
good_date, anchor_year, COinS_date = true, v.val:match("((%d+)%a?)");
end
elseif 'pmc-embargo-date' == k then
good_date = check_date (v.val, k); -- go test the date
if true == good_date then -- if the date is a valid date
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
else -- any other date-holding parameter
Line 737 ⟶ 744:
--[[--------------------------< 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
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
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, year_origin, date_string, date_origin, error_list)
local year;
local date1;
local date2;
local result = 1; -- result of the test; assume that the test passes
year = year_string:match ('(%d%d%d%d?)');
Line 780 ⟶ 792:
result = 0;
end
else -- should never get here; this function called only when no other date errors
result = 0; -- no recognizable year in date
end
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
Line 819 ⟶ 836:
['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'},
},
['Mdy'] = { -- date format is Mdy; reformat to:
Line 825 ⟶ 842:
['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'},
},
['dMy'] = { -- date format is dMy; reformat to:
Line 831 ⟶ 848:
['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'},
},
['Md-dy'] = { -- date format is Md-dy; reformat to:
Line 866 ⟶ 883:
['any'] = {'%s %s', 'm', 'y'}, -- dmy/mdy agnostic
},
-- ['yMd'] = {
-- ['mdy'] = {'%s %s, %s', 'm', 'd', 'y'},
-- ['dmy'] = {'%s %s %s', 'd', 'm', 'y'},
-- ['ymd'] = {'%s-%s-%s', 'y', 'm', 'd'},
-- },
}
Line 887 ⟶ 904:
end
-- 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
return; -- not a reformattable date
end
Line 908 ⟶ 923:
};
if t.a then -- if this date has an anchor year capture (all convertable date formats except ymd)
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
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['
else
t.m = cfg.date_names['
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
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;
end
Line 930 ⟶ 950:
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['
end
end
Line 1,017 ⟶ 1,037:
end -- if
end -- for
return result;
end
Line 1,034 ⟶ 1,054:
local n;
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)
param_val.val, n = param_val.val:gsub ('%-', '–'); -- replace any hyphen with ndash
if 0 ~= n then
Line 1,041 ⟶ 1,061:
result = true;
end
end
end
Line 1,050 ⟶ 1,069:
--[[-------------------------< D A T E _ N A M E _ X L A T E >------------------------------------------------
Attempts to translate English
date parser function. This is simple name-for-name replacement and may not work for all languages.
Line 1,064 ⟶ 1,083:
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
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
month = mw.text.trim (month); -- this because quarterly dates contain whitespace
if xlate then
date = mw.ustring.gsub (date, month, xlate); -- replace the English with the translation
date_parameters_list[param_name].val = date; -- save the translated date
Line 1,093 ⟶ 1,124:
return modified;
Line 1,106 ⟶ 1,137:
is_set = utilities_page_ptr.is_set;
in_array = utilities_page_ptr.in_array;
substitute = utilities_page_ptr.substitute;
wrap_style = utilities_page_ptr.wrap_style;
|