Seeds of the Word

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

Module Discussion

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

Revision as of 17:45, July 1, 2022

1,905 bytes added ,  1 year ago
sync from sandbox;
m (1 revision imported)
(sync from sandbox;)
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 >--------------------------------------
]]
]]
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 |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 ('^%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 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
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 -- ToDo: I18N
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 453: Line 434:
['y-y'] = {'^(%d%d%d%d?)[%-–]((%d%d%d%d?)%a?)$'}, -- year range: YYY-YYY or YYY-YYYY or YYYY–YYYY; separated by unspaced endash; 100-9999
['y-y'] = {'^(%d%d%d%d?)[%-–]((%d%d%d%d?)%a?)$'}, -- 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?)$'}, -- year range: YYYY–YY; separated by unspaced endash
['y4-y2'] = {'^((%d%d)%d%d)[%-–]((%d%d)%a?)$'}, -- year range: YYYY–YY; separated by unspaced endash
['ymx'] = {'^(%d%d%d%d)%-(%d%d)%-XX$', 'y', 'm'}, -- edtf year-initial numerical year-month-XX
['y'] = {'^((%d%d%d%d?)%a?)$'}, -- 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 495: Line 494:
anchor_year = year;
anchor_year = year;
elseif date_string:match (patterns['ymx'][1]) then -- year-initial numerical year month edtf format
year, month = date_string:match (patterns['ymx'][1]);
if 12 < tonumber(month) or 1 > tonumber(month) or 1582 > tonumber(year) or not is_valid_year(year) then return false; end -- month number not valid or not Gregorian calendar or future year
anchor_year = year;
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]);
Line 575: Line 569:
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
Line 627: Line 623:


if in_array (param, {'date', 'publication-date', 'year'}) then
if in_array (param, {'date', 'publication-date', 'year'}) then
add_prop_cat ('year_range_abbreviated');
add_prop_cat ('year-range-abbreviated');
end
end


Line 658: Line 654:
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)
Line 723: Line 719:
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 'pmc-embargo-date' == k then -- if the parameter is |pmc-embargo-date=
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 |pmc-embargo-date= 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
Line 747: Line 743:
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 numernic value in <result> determines the 'output' if any from this function:
the numeric value in <result> determines the 'output' if any from this function:
0 – adds error message to error_list sequence table
0 – adds error message to error_list sequence table
1 – adds maint cat
1 – adds maint cat
Line 902: Line 898:
end
end


-- yMd is not supported at en.wiki; if yMd is supported at your wiki, uncomment the next line
-- yMd is not supported at en.wiki; when yMd is supported at your wiki, uncomment the next line
-- 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 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 is supported at your wiki, remove or comment-out the next line
if 'yMd' == format_param then -- yMd not supported at en.wiki; when yMd is supported at your wiki, remove or comment-out this line
if 'yMd' == format_param then -- yMd not supported at en.wiki
return; -- not a reformattable date
return; -- not a reformattable date
end
end
Line 922: Line 917:
};
};


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
t.y = t.y:gsub ('%a', ''); -- strip CITREF disambiguator if present; anchor year already known so process can proceed
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
if 1582 > tonumber (t.y) then -- ymd format dates not allowed before 1582
return;
return;
Line 945: Line 944:
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 1,032: Line 1,031:
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 1,059: Line 1,058:
end
end
return result; -- so we know if any hyphens were replaced
return result; -- so we know if any hyphens were replaced
end
--[[--------------------------< E D T F _ T R A N S F O R M >--------------------------------------------------
Loops through the list of date-holding parameters and converts any EDTF formatted dates to MOS compliant dates.
Only YYY-MM-XX supported at this time. Not called if the cs1|2 template has any date errors.
must be done before reformat_dates() and before date_hyphen_to_dash()
Modifies the date_parameters_list and returns true if transformation is performed, else returns false.
]]
local function edtf_transform (date_parameters_list)
local result = false;
local source_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) and param_val.val:match (patterns.ymx[1]) then -- if parameter is set and is an EDTF dates
source_date.year, source_date.month = param_val.val:match (patterns.ymx[1]); -- get year and month number
source_date.day = 1; -- required by os.time()
date_parameters_list[param_name].val = mw.text.trim (os.date ('%B %Y', os.time (source_date)));
result = true;
end
end
return result; -- so we know if a transform was done
end
end


Line 1,091: Line 1,063:
--[[-------------------------< 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.


Line 1,105: Line 1,077:
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 cfg.date_names.en.long[month] then -- long month dates
else
-- if cfg.date_names.inv_local_long[cfg.date_names.en.long[month]] then
mode = nil; -- not an English month name; could be local language month name or an English season name
-- xlate = cfg.date_names.inv_local_long[cfg.date_names.en.long[month]];
end
-- end
---- mode = 'F'; -- English name is long so use long local name
if mode then -- might be a season
-- elseif cfg.date_names.en.short[month] then -- short month dates
xlate = lang_object:formatDate(mode, '1' .. month); -- translate the month name to this local language
-- if cfg.date_names.inv_local_short[cfg.date_names.en.short[month]] then
-- xlate = cfg.date_names.inv_local_short[cfg.date_names.en.short[month]];
-- end
---- mode = 'M'; -- English name is short so use short local name
-- elseif cfg.date_names.en.quarter[month] then -- quarter dates
-- if cfg.date_names.inv_local_quarter[cfg.date_names.en.quarter[month]] then
-- xlate = cfg.date_names.inv_local_quarter[cfg.date_names.en.quarter[month]];
-- end
-- elseif cfg.date_names.en.season[month] then -- season dates
-- if cfg.date_names.inv_local_season[cfg.date_names.en.season[month]] then
-- xlate = cfg.date_names.inv_local_season[cfg.date_names.en.season[month]];
-- end
-- elseif cfg.date_names.en.named[month] then -- named dates
-- if cfg.date_names.inv_local_named[cfg.date_names.en.named[month]] then
-- xlate = cfg.date_names.inv_local_named[cfg.date_names.en.named[month]];
-- end
-- else
-- xlate=nil; -- not an English month name; could be local language month name
---- mode = nil; -- not an English month name; could be local language month name or an English season name
-- end
 
if xlate then
-- 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 1,164: Line 1,177:
date_hyphen_to_dash = date_hyphen_to_dash,
date_hyphen_to_dash = date_hyphen_to_dash,
date_name_xlate = date_name_xlate,
date_name_xlate = date_name_xlate,
edtf_transform = edtf_transform,
set_selected_modules = set_selected_modules
set_selected_modules = set_selected_modules
}
}
Anonymous user
Retrieved from "https://en.seminaverbi.bibleget.io/wiki/Special:MobileDiff/26589"