Changes

Jump to: navigation, search

Module:Citation/CS1/Date validation

3,300 bytes added, 6 years ago
]]
local is_set, in_array; -- imported function functions from selected Module:Citation/CS1/Utilitieslocal cfg; -- table of tables imported from slected Module:Citation/CS1/Configuration
--[=[-------------------------< I S _ V A L I D _ A C C E S S D A T E >----------------------------------------
good2, tomorrow_ts = pcall( lang.formatDate, lang, 'U', 'today + 2 days' ); -- today midnight + 2 days is one second more than all day tomorrow
if good1 and good2 then -- lang.formatDate() returns a timestamp in the local script which which tonumber() may not understand access_ts = tonumber (access_ts) or lang:parseFormattedNumber (access_ts); -- convert to numbers for the comparison; tomorrow_ts = tonumber (tomorrow_ts) or lang:parseFormattedNumber (tomorrow_ts);
else
return false; -- one or both failed to convert to unix time stamp
local function get_month_number (month)
local long_months = { return cfg.date_names['Januarylocal']=1, .long['February'month]=2, or cfg.date_names['Marchlocal']=3, .short['April'month]=4, ['May']=5, ['June']=6, ['July']=7, ['August']=8, ['September']=9, ['October']=10, ['November']=11, ['December']=12};or -- look for local names firstlocal short_months = { cfg.date_names['Janen']=1, .long['Feb'month]=2, or cfg.date_names['Maren']=3, ['Apr']=4, ['May']=5, ['Jun']=6, ['Jul']=7, ['Aug']=8, ['Sep']=9, ['Oct']=10, ['Nov']=11, ['Dec']=12}; return long_months.short[month] or -- if month is the long-form name short_months[month] or -- if month is the short-form namefailing that, look for English names 0; -- misspelled, improper case, or not a recognized month name
end
returns a number according to the sequence of seasons in a year: 1 for Winter, etc. Capitalization and spelling must be correct. If not a valid season, returns 0
 
Uses ISO DIS 8601 2016 part 2 §4.7 Divisions of a year for hemishpere-independent seasons:
21-24 = Spring, Summer, Autumn, Winter, independent of “Hemisphere”
 
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)
local season_list = { return cfg.date_names['Winterlocal']=21, .season['Spring'season]=22, ['Summer']=23, ['Fall']=24, ['Autumn']=24}; or -- make sure these numbers do not overlap month numberslook for local temp;names first temp=season_list cfg.date_names['en'].season[season]; if temp then return temp; end or -- if season is a valid name return its numberfailing that, look for English names return 0; -- misspelled, improper case, or not a recognized season name
end
local function is_proper_name (name)
local name_list = { return cfg.date_names['Christmaslocal']=31}.named[name] or -- look for local temp;names dates first temp=name_list cfg.date_names['en'].named[name]; if temp then return temp; end or -- if name is a valid name return its numberfailing that, look for English names return 0; -- misspelled, improper case, or not a proper namerecognized named date
end
Month pairs are expected to be left to right, earliest to latest in time.
Similarly, seasons All season ranges are also left to right, earliest to latest in time. There is an oddity with seasons: winter is assigned accepted as valid because there are publishers out there who have published a value of 1, spring 2, Summer–Spring YYYY issue so ...,fall and autumn 4. Because winter can follow fall/autumn at the end of a calender year, a special test is made to see if |date=Fall-Winter yyyy (4-1) is the date.ok
]]
if 0 == range_start_number then -- is this a month range?
local range_start_number = get_season_number (range_start); -- not a month; is it a season? get start season number
range_end_number = get_season_number (range_end); -- get end season number
if (0 ~= range_start_number ) and (0 ~= range_end_number) then -- is start of range a season? if range_start_number < range_end_number then -- range_start is a season return true; -- return true when range_end is also a any season and follows start season; else false end if 24 == range_start_number and 21 == range_end_number then -- special case when season range pairing is Fall-Winter or Autumn-Winter return true; endaccepted
end
return false; -- range_start is not a month and/or a season; or range_start is a season and range_end is not; or improper a season sequence
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?
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; 31– proper name dates99 Christmas
day, day2 – 0 if not provided, 1-31 for days
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
end
if 20 < tonumber(input.month) then -- if season or propername date
local season = {[2124]='winter', [2221]='spring', [2322]='summer', [2423]='fall', [3199]='Christmas'}; -- seasons lowercase, no autumn; proper names use title case
if 0 == input.month2 then -- single season date
if 30 <tonumber(input.month) then
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 date_string:mw.ustring.match(date_string, "^%a+ D- +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial: month day, year month, day, anchor_year, year=stringmw.ustring.match(date_string, "(%aD-) +)%s*(%d%d?),%s*((%d%d%d%d?)%a?)");
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d?[%-–][1-9]%d?, +[1-9]%d%d%d%a?$") then -- month-initial day range: month day–day, year; days are separated by endash month, day, day2, anchor_year, year=mw.ustring.match(date_string, "(%a+D-) +(%d%d?)[%-–](%d%d?), +((%d%d%d%d)%a?)");
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);
year2=year;
elseif date_string:mw.ustring.match(date_string, "^[1-9]%d? +%a+ D- +[1-9]%d%d%d%a?$") then -- day-initial: day month year day, month, anchor_year, year=stringmw.ustring.match(date_string, "(%d%d*)%s*(%a+D-)%s*+((%d%d%d%d?)%a?)");
month = get_month_number (month);
if 0 == month then return false; end -- return false if month text isn't one of the twelve months
elseif mw.ustring.match(date_string, "^[1-9]%d?[%-–][1-9]%d? +%a+ D- +[1-9]%d%d%d%a?$") then -- day-range-initial: day–day month year; days are separated by endash day, day2, month, anchor_year, year=mw.ustring.match(date_string, "(%d%d?)[%-–](%d%d?) +(%a+D-) +((%d%d%d%d)%a?)");
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);
year2=year;
elseif mw.ustring.match(date_string, "^[1-9]%d? +%aD- + [%-–] +[1-9]%d? +%a+ D- +[1-9]%d%d%d%a?$") then -- day initial month-day-range: day month - day month year; uses spaced endash day, month, day2, month2, anchor_year, year=mw.ustring.match(date_string, "(%d%d?) +(%a+D-) +[%-–] +(%d%d?) +(%a+D-) +((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end -- date range order is left to right: earlier to later;
month = get_month_number (month); -- for metadata
year2=year;
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d? +[%-–] %a+ %D- +[1-9]%d?, +[1-9]%d%d%d?%a?$") then -- month initial month-day-range: month day – month day, year; uses spaced endash month, day, month2, day2, anchor_year, year=mw.ustring.match(date_string, "(%a+D-) +(%d%d?) +[%-–] +(%a+D-) +(%d%d?), +((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or not is_valid_year(year) then return false; end
month = get_month_number (month); -- for metadata
year2=year;
elseif mw.ustring.match(date_string, "^[1-9]%d? +%a+ D- +[1-9]%d%d%d +[%-–] +[1-9]%d? +%a+ D- +[1-9]%d%d%d%a?$") then -- day initial month-day-year-range: day month year - day month year; uses spaced endash day, month, year, day2, month2, anchor_year, year2=mw.ustring.match(date_string, "(%d%d?) +(%a+D-) +(%d%d%d%d?) +[%-–] +(%d%d?) +(%a+D-) +((%d%d%d%d?)%a?)");
if tonumber(year2) <= tonumber(year) then return false; end -- must be sequential years, left to right, earlier to later
if not is_valid_year(year2) or not is_valid_month_range_style(month, month2) then return false; end -- year2 no more than one year in the future; months same style
month2 = get_month_number (month2);
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d?, +[1-9]%d%d%d +[%-–] %a+ %D- +[1-9]%d?, +[1-9]%d%d%d%a?$") then -- month initial month-day-year-range: month day, year – month day, year; uses spaced endash month, day, year, month2, day2, anchor_year, year2=mw.ustring.match(date_string, "(%a+D-) +(%d%d?), +(%d%d%d%d) +[%-–] +(%a+D-) +(%d%d?), +((%d%d%d%d)%a?)");
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
month2 = get_month_number (month2);
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d%d%d[%-–]%d%d%a?$") then -- special case Winter/Summer year-year (YYYY-YY); year separated with unspaced endash
local century;
month, year, century, anchor_year, year2=mw.ustring.match(date_string, "(%a+D-) +((%d%d)%d%d)[%-–]((%d%d)%a?)");
if 'Winter' ~= month and 'Summer' ~= month then return false end; -- 'month' can only be Winter or Summer
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
month = get_season_number (month);
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d%d%d[%-–][1-9]%d%d%d%a?$") then -- special case Winter/Summer year-year; year separated with unspaced endash month, year, anchor_year, year2=mw.ustring.match(date_string, "(%a+D-) +(%d%d%d%d)[%-–]((%d%d%d%d)%a?)");
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
month = get_season_number (month); -- for metadata
elseif mw.ustring.match(date_string, "^%a+ D- +[1-9]%d%d%d +[%-–] +%a+ D- +[1-9]%d%d%d%a?$") then -- month/season year - month/season year; separated by spaced endash month, year, month2, anchor_year, year2=mw.ustring.match(date_string, "(%a+D-) +(%d%d%d%d) +[%-–] +(%a+D-) +((%d%d%d%d)%a?)");
anchor_year=year..'–'..anchor_year; -- assemble anchor_year from both years
if tonumber(year) >= tonumber(year2) then return false; end -- left to right, earlier to later, not the same
end
elseif mw.ustring.match(date_string, "^%a+D-[%-–]%a+ D- +[1-9]%d%d%d%a?$") then -- month/season range year; months separated by endash month, month2, anchor_year, year=mw.ustring.match(date_string, "(%a+D-)[%-–](%a+D-)%s*((%d%d%d%d)%a?)");
if (not is_valid_month_season_range(month, month2)) or (not is_valid_year(year)) then return false; end
if 0 ~= get_month_number(month) then -- determined to be a valid range so just check this one to know if month or season
year2=year;
elseif date_string:mw.ustring.match(date_string, "^%a+ D- +%d%d%d%d%a?$") then -- month/season year or proper-name year month, anchor_year, year=date_string:mw.ustring.match(date_string, "(%a+D-)%s*((%d%d%d%d)%a?)");
if not is_valid_year(year) then return false; end
if not is_valid_month_or_season (month) and 0 == is_proper_name (month) then return false; end
if is_set(v) then -- if the parameter has a value
if v:match("^c%. [1-9]%d%d%d?%a?$") then -- special case for c. year or with or without CITEREF disambiguator - only |date= and |year=
v = mw.ustring.gsub (v, '%d', cfg.date_names.local_digits);
local year = v:match("c%. ([1-9]%d%d%d?)%a?"); -- get the year portion so it can be tested
if 'date'==k then
local source_patterns = { -- this table holds patterns that match allowed date formats used to extract date components
['dmy'] = '^(%d%d?)%s+(%a+)%s+(%d%d%d%d)$', ['mdy'] = '^(%a+)%s+(%d%d?),%s+(%d%d%d%d)$', ['ymd'] = '^(%d%d%d%d)%-(%d%d)-(%d%d)$',
}
Date ranges, season dates, proper name dates are not currently supported.
 
For i18n: This code works only at en.wiki because os.date() doesn't support any languages other than English.
mw.getContentLanguage():formatDate() will work at non-English wikis only when the date format is yyyy-mm-dd. This is
the same issue that plagues is_valid_accessdate()
 
It is possible that a solution like that written for ht:Module:Citation/CS1/Date_validation date_name_xlate() could be applied to this problem
]]
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) then -- if the parameter has a value
if not all and in_array (param_name, {'access-date', 'archive-date'}) then -- if access- or archive-date and format not xxx-all
param_val = ''; -- set to empty string so we don't process this date
end
for source, pattern in pairs(source_patterns) do if param_val:match(pattern) then
if 'ymd' == source then
get_ymd_date_parts (param_val, source_date); -- get the date parts into the source_date table
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.
 
]]
 
local function date_name_xlate (date_parameters_list)
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) then -- if the parameter has a value
date = param_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 = mw.getContentLanguage():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] = date; -- save the translated date
modified = true;
end
end
 
end
end
return modified;
end
]]
local function set_selected_modules (cfg_table_ptr, utilities_page_ptr) is_set = utilities_page_ptr.is_set; -- import functions from select selected Module:Citation/CS1/Utilities module in_array = utilities_page_ptr.in_array; -- import functions from select selected Module:Citation/CS1/Utilities module cfg = cfg_table_ptr; -- import tables from selected Module:Citation/CS1/Configuration
end
reformat_dates = reformat_dates,
date_hyphen_to_dash = date_hyphen_to_dash,
date_name_xlate = date_name_xlate,
set_selected_modules = set_selected_modules
}
Anonymous user