rizwanreza-chronic 0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (54) hide show
  1. data/README.rdoc +188 -0
  2. data/lib/chronic.rb +57 -0
  3. data/lib/chronic/blunt.rb +234 -0
  4. data/lib/chronic/chronic.rb +326 -0
  5. data/lib/chronic/grabber.rb +26 -0
  6. data/lib/chronic/handlers.rb +549 -0
  7. data/lib/chronic/ordinal.rb +39 -0
  8. data/lib/chronic/pointer.rb +29 -0
  9. data/lib/chronic/repeater.rb +139 -0
  10. data/lib/chronic/repeaters/repeater_day.rb +52 -0
  11. data/lib/chronic/repeaters/repeater_day_name.rb +53 -0
  12. data/lib/chronic/repeaters/repeater_day_portion.rb +94 -0
  13. data/lib/chronic/repeaters/repeater_decade.rb +23 -0
  14. data/lib/chronic/repeaters/repeater_fortnight.rb +70 -0
  15. data/lib/chronic/repeaters/repeater_hour.rb +58 -0
  16. data/lib/chronic/repeaters/repeater_minute.rb +57 -0
  17. data/lib/chronic/repeaters/repeater_month.rb +66 -0
  18. data/lib/chronic/repeaters/repeater_month_name.rb +98 -0
  19. data/lib/chronic/repeaters/repeater_season.rb +150 -0
  20. data/lib/chronic/repeaters/repeater_season_name.rb +45 -0
  21. data/lib/chronic/repeaters/repeater_second.rb +41 -0
  22. data/lib/chronic/repeaters/repeater_time.rb +124 -0
  23. data/lib/chronic/repeaters/repeater_week.rb +73 -0
  24. data/lib/chronic/repeaters/repeater_weekday.rb +77 -0
  25. data/lib/chronic/repeaters/repeater_weekend.rb +65 -0
  26. data/lib/chronic/repeaters/repeater_year.rb +64 -0
  27. data/lib/chronic/scalar.rb +76 -0
  28. data/lib/chronic/separator.rb +91 -0
  29. data/lib/chronic/time_zone.rb +26 -0
  30. data/lib/core_ext/object.rb +7 -0
  31. data/lib/core_ext/time.rb +74 -0
  32. data/lib/numerizer/numerizer.rb +98 -0
  33. data/test/test_Chronic.rb +75 -0
  34. data/test/test_DaylightSavings.rb +119 -0
  35. data/test/test_Handler.rb +110 -0
  36. data/test/test_Numerizer.rb +54 -0
  37. data/test/test_RepeaterDayName.rb +52 -0
  38. data/test/test_RepeaterDecade.rb +46 -0
  39. data/test/test_RepeaterFortnight.rb +63 -0
  40. data/test/test_RepeaterHour.rb +68 -0
  41. data/test/test_RepeaterMinute.rb +35 -0
  42. data/test/test_RepeaterMonth.rb +47 -0
  43. data/test/test_RepeaterMonthName.rb +57 -0
  44. data/test/test_RepeaterSeason.rb +43 -0
  45. data/test/test_RepeaterTime.rb +72 -0
  46. data/test/test_RepeaterWeek.rb +63 -0
  47. data/test/test_RepeaterWeekday.rb +56 -0
  48. data/test/test_RepeaterWeekend.rb +75 -0
  49. data/test/test_RepeaterYear.rb +63 -0
  50. data/test/test_Span.rb +33 -0
  51. data/test/test_Time.rb +50 -0
  52. data/test/test_Token.rb +26 -0
  53. data/test/test_parsing.rb +809 -0
  54. metadata +118 -0
@@ -0,0 +1,76 @@
1
+ module Chronic
2
+
3
+ class Scalar < Tag #:nodoc:
4
+ def self.scan(tokens)
5
+ # for each token
6
+ tokens.each_index do |i|
7
+ if t = self.scan_for_scalars(tokens[i], tokens[i + 1]) then tokens[i].tag(t) end
8
+ if t = self.scan_for_days(tokens[i], tokens[i + 1]) then tokens[i].tag(t) end
9
+ if t = self.scan_for_months(tokens[i], tokens[i + 1]) then tokens[i].tag(t) end
10
+ if t = self.scan_for_years(tokens[i], tokens[i + 1]) then tokens[i].tag(t) end
11
+ end
12
+ tokens
13
+ end
14
+
15
+ def self.scan_for_scalars(token, post_token)
16
+ if token.word =~ /^\d*$/ || token.word =~ /^\d\.\d*$/
17
+ unless post_token && %w{am pm morning afternoon evening night}.include?(post_token)
18
+ return Scalar.new(token.word.to_f)
19
+ end
20
+ end
21
+ return nil
22
+ end
23
+
24
+ def self.scan_for_days(token, post_token)
25
+ if token.word =~ /^\d\d?$/
26
+ toi = token.word.to_i
27
+ unless toi > 31 || toi < 1 || (post_token && %w{am pm morning afternoon evening night}.include?(post_token.word))
28
+ return ScalarDay.new(toi)
29
+ end
30
+ end
31
+ return nil
32
+ end
33
+
34
+ def self.scan_for_months(token, post_token)
35
+ if token.word =~ /^\d\d?$/
36
+ toi = token.word.to_i
37
+ unless toi > 12 || toi < 1 || (post_token && %w{am pm morning afternoon evening night}.include?(post_token.word))
38
+ return ScalarMonth.new(toi)
39
+ end
40
+ end
41
+ return nil
42
+ end
43
+
44
+ def self.scan_for_years(token, post_token)
45
+ if token.word =~ /^([1-9]\d)?\d\d?$/
46
+ unless post_token && %w{am pm morning afternoon evening night}.include?(post_token.word)
47
+ return ScalarYear.new(token.word.to_i)
48
+ end
49
+ end
50
+ return nil
51
+ end
52
+
53
+ def to_s
54
+ 'scalar'
55
+ end
56
+ end
57
+
58
+ class ScalarDay < Scalar #:nodoc:
59
+ def to_s
60
+ super << '-day-' << @type.to_s
61
+ end
62
+ end
63
+
64
+ class ScalarMonth < Scalar #:nodoc:
65
+ def to_s
66
+ super << '-month-' << @type.to_s
67
+ end
68
+ end
69
+
70
+ class ScalarYear < Scalar #:nodoc:
71
+ def to_s
72
+ super << '-year-' << @type.to_s
73
+ end
74
+ end
75
+
76
+ end
@@ -0,0 +1,91 @@
1
+ module Chronic
2
+
3
+ class Separator < Tag #:nodoc:
4
+ def self.scan(tokens)
5
+ tokens.each_index do |i|
6
+ if t = self.scan_for_commas(tokens[i]) then tokens[i].tag(t); next end
7
+ if t = self.scan_for_slash_or_dash(tokens[i]) then tokens[i].tag(t); next end
8
+ if t = self.scan_for_at(tokens[i]) then tokens[i].tag(t); next end
9
+ if t = self.scan_for_in(tokens[i]) then tokens[i].tag(t); next end
10
+ if t = self.scan_for_on(tokens[i]) then tokens[i].tag(t); next end
11
+ end
12
+ tokens
13
+ end
14
+
15
+ def self.scan_for_commas(token)
16
+ scanner = {/^,$/ => :comma}
17
+ scanner.keys.each do |scanner_item|
18
+ return SeparatorComma.new(scanner[scanner_item]) if scanner_item =~ token.word
19
+ end
20
+ return nil
21
+ end
22
+
23
+ def self.scan_for_slash_or_dash(token)
24
+ scanner = {/^-$/ => :dash,
25
+ /^\/$/ => :slash}
26
+ scanner.keys.each do |scanner_item|
27
+ return SeparatorSlashOrDash.new(scanner[scanner_item]) if scanner_item =~ token.word
28
+ end
29
+ return nil
30
+ end
31
+
32
+ def self.scan_for_at(token)
33
+ scanner = {/^(at|@)$/i => :at}
34
+ scanner.keys.each do |scanner_item|
35
+ return SeparatorAt.new(scanner[scanner_item]) if scanner_item =~ token.word
36
+ end
37
+ return nil
38
+ end
39
+
40
+ def self.scan_for_in(token)
41
+ scanner = {/^in$/i => :in}
42
+ scanner.keys.each do |scanner_item|
43
+ return SeparatorIn.new(scanner[scanner_item]) if scanner_item =~ token.word
44
+ end
45
+ return nil
46
+ end
47
+
48
+ def self.scan_for_on(token)
49
+ scanner = {/^on$/i => :on}
50
+ scanner.keys.each do |scanner_item|
51
+ return SeparatorOn.new(scanner[scanner_item]) if scanner_item =~ token.word
52
+ end
53
+ return nil
54
+ end
55
+
56
+ def to_s
57
+ 'separator'
58
+ end
59
+ end
60
+
61
+ class SeparatorComma < Separator #:nodoc:
62
+ def to_s
63
+ super << '-comma'
64
+ end
65
+ end
66
+
67
+ class SeparatorSlashOrDash < Separator #:nodoc:
68
+ def to_s
69
+ super << '-slashordash-' << @type.to_s
70
+ end
71
+ end
72
+
73
+ class SeparatorAt < Separator #:nodoc:
74
+ def to_s
75
+ super << '-at'
76
+ end
77
+ end
78
+
79
+ class SeparatorIn < Separator #:nodoc:
80
+ def to_s
81
+ super << '-in'
82
+ end
83
+ end
84
+
85
+ class SeparatorOn < Separator #:nodoc:
86
+ def to_s
87
+ super << '-on'
88
+ end
89
+ end
90
+
91
+ end
@@ -0,0 +1,26 @@
1
+ module Chronic
2
+ class TimeZone < Tag #:nodoc:
3
+ def self.scan(tokens)
4
+ tokens.each_index do |i|
5
+ if t = self.scan_for_all(tokens[i]) then tokens[i].tag(t); next end
6
+ end
7
+ tokens
8
+ end
9
+
10
+ def self.scan_for_all(token)
11
+ if RUBY_VERSION =~ /1\.9\./
12
+ scanner = {/[PMCE][DS]T/i => :tz}
13
+ else
14
+ scanner = {/[PMCE][DS]T/i => :tz, /(tzminus)?[01]\d[304][05]/ => :tz}
15
+ end
16
+ scanner.keys.each do |scanner_item|
17
+ return self.new(scanner[scanner_item]) if scanner_item =~ token.word
18
+ end
19
+ return nil
20
+ end
21
+
22
+ def to_s
23
+ 'timezone'
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,7 @@
1
+ alias p_orig p
2
+
3
+ def p(val)
4
+ p_orig val
5
+ puts
6
+ end
7
+
@@ -0,0 +1,74 @@
1
+ require 'time'
2
+
3
+ # class Time
4
+ # def self.construct(year, month = 1, day = 1, hour = 0, minute = 0, second = 0)
5
+ # # extra_seconds = second > 60 ? second - 60 : 0
6
+ # # extra_minutes = minute > 59 ? minute - 59 : 0
7
+ # # extra_hours = hour > 23 ? hour - 23 : 0
8
+ # # extra_days = day >
9
+ #
10
+ # if month > 12
11
+ # if month % 12 == 0
12
+ # year += (month - 12) / 12
13
+ # month = 12
14
+ # else
15
+ # year += month / 12
16
+ # month = month % 12
17
+ # end
18
+ # end
19
+ #
20
+ # base = Time.local(year, month)
21
+ # puts base
22
+ # offset = ((day - 1) * 24 * 60 * 60) + (hour * 60 * 60) + (minute * 60) + second
23
+ # puts offset.to_s
24
+ # date = base + offset
25
+ # puts date
26
+ # date
27
+ # end
28
+ # end
29
+
30
+ class Time
31
+ def self.construct(year, month = 1, day = 1, hour = 0, minute = 0, second = 0)
32
+ if second >= 60
33
+ minute += second / 60
34
+ second = second % 60
35
+ end
36
+
37
+ if minute >= 60
38
+ hour += minute / 60
39
+ minute = minute % 60
40
+ end
41
+
42
+ if hour >= 24
43
+ day += hour / 24
44
+ hour = hour % 24
45
+ end
46
+
47
+ # determine if there is a day overflow. this is complicated by our crappy calendar
48
+ # system (non-constant number of days per month)
49
+ day <= 56 || raise("day must be no more than 56 (makes month resolution easier)")
50
+ if day > 28
51
+ # no month ever has fewer than 28 days, so only do this if necessary
52
+ leap_year = (year % 4 == 0) && !(year % 100 == 0)
53
+ leap_year_month_days = [31, 29, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
54
+ common_year_month_days = [31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
55
+ days_this_month = leap_year ? leap_year_month_days[month - 1] : common_year_month_days[month - 1]
56
+ if day > days_this_month
57
+ month += day / days_this_month
58
+ day = day % days_this_month
59
+ end
60
+ end
61
+
62
+ if month > 12
63
+ if month % 12 == 0
64
+ year += (month - 12) / 12
65
+ month = 12
66
+ else
67
+ year += month / 12
68
+ month = month % 12
69
+ end
70
+ end
71
+
72
+ Chronic.time_class.local(year, month, day, hour, minute, second)
73
+ end
74
+ end
@@ -0,0 +1,98 @@
1
+ require 'strscan'
2
+
3
+ class Numerizer
4
+
5
+ DIRECT_NUMS = [
6
+ ['eleven', '11'],
7
+ ['twelve', '12'],
8
+ ['thirteen', '13'],
9
+ ['fourteen', '14'],
10
+ ['fifteen', '15'],
11
+ ['sixteen', '16'],
12
+ ['seventeen', '17'],
13
+ ['eighteen', '18'],
14
+ ['nineteen', '19'],
15
+ ['ninteen', '19'], # Common mis-spelling
16
+ ['zero', '0'],
17
+ ['one', '1'],
18
+ ['two', '2'],
19
+ ['three', '3'],
20
+ ['four(\W|$)', '4\1'], # The weird regex is so that it matches four but not fourty
21
+ ['five', '5'],
22
+ ['six(\W|$)', '6\1'],
23
+ ['seven(\W|$)', '7\1'],
24
+ ['eight(\W|$)', '8\1'],
25
+ ['nine(\W|$)', '9\1'],
26
+ ['ten', '10'],
27
+ ['\ba[\b^$]', '1'] # doesn't make sense for an 'a' at the end to be a 1
28
+ ]
29
+
30
+ TEN_PREFIXES = [ ['twenty', 20],
31
+ ['thirty', 30],
32
+ ['forty', 40],
33
+ ['fourty', 40], # Common misspelling
34
+ ['fifty', 50],
35
+ ['sixty', 60],
36
+ ['seventy', 70],
37
+ ['eighty', 80],
38
+ ['ninety', 90]
39
+ ]
40
+
41
+ BIG_PREFIXES = [ ['hundred', 100],
42
+ ['thousand', 1000],
43
+ ['million', 1_000_000],
44
+ ['billion', 1_000_000_000],
45
+ ['trillion', 1_000_000_000_000],
46
+ ]
47
+
48
+ def self.numerize(string)
49
+ string = string.dup
50
+
51
+ # preprocess
52
+ string.gsub!(/ +|([^\d])-([^\d])/, '\1 \2') # will mutilate hyphenated-words but shouldn't matter for date extraction
53
+ string.gsub!(/a half/, 'haAlf') # take the 'a' out so it doesn't turn into a 1, save the half for the end
54
+
55
+ # easy/direct replacements
56
+
57
+ DIRECT_NUMS.each do |dn|
58
+ string.gsub!(/#{dn[0]}/i, '<num>' + dn[1])
59
+ end
60
+
61
+ # ten, twenty, etc.
62
+
63
+ TEN_PREFIXES.each do |tp|
64
+ string.gsub!(/(?:#{tp[0]}) *<num>(\d(?=[^\d]|$))*/i) { '<num>' + (tp[1] + $1.to_i).to_s }
65
+ end
66
+
67
+ TEN_PREFIXES.each do |tp|
68
+ string.gsub!(/#{tp[0]}/i) { '<num>' + tp[1].to_s }
69
+ end
70
+
71
+ # hundreds, thousands, millions, etc.
72
+
73
+ BIG_PREFIXES.each do |bp|
74
+ string.gsub!(/(?:<num>)?(\d*) *#{bp[0]}/i) { '<num>' + (bp[1] * $1.to_i).to_s}
75
+ andition(string)
76
+ end
77
+
78
+ # fractional addition
79
+ # I'm not combining this with the previous block as using float addition complicates the strings
80
+ # (with extraneous .0's and such )
81
+ string.gsub!(/(\d+)(?: | and |-)*haAlf/i) { ($1.to_f + 0.5).to_s }
82
+
83
+ string.gsub(/<num>/, '')
84
+ end
85
+
86
+ private
87
+
88
+ def self.andition(string)
89
+ sc = StringScanner.new(string)
90
+ while(sc.scan_until(/<num>(\d+)( | and )<num>(\d+)(?=[^\w]|$)/i))
91
+ if sc[2] =~ /and/ || sc[1].size > sc[3].size
92
+ string[(sc.pos - sc.matched_size)..(sc.pos-1)] = '<num>' + (sc[1].to_i + sc[3].to_i).to_s
93
+ sc.reset
94
+ end
95
+ end
96
+ end
97
+
98
+ end
@@ -0,0 +1,75 @@
1
+ require File.expand_path('../../lib/chronic', __FILE__)
2
+ require 'test/unit'
3
+
4
+ class TestChronic < Test::Unit::TestCase
5
+
6
+ def setup
7
+ # Wed Aug 16 14:00:00 UTC 2006
8
+ @now = Time.local(2006, 8, 16, 14, 0, 0, 0)
9
+ end
10
+
11
+ def test_post_normalize_am_pm_aliases
12
+ # affect wanted patterns
13
+
14
+ tokens = [Chronic::Token.new("5:00"), Chronic::Token.new("morning")]
15
+ tokens[0].tag(Chronic::RepeaterTime.new("5:00"))
16
+ tokens[1].tag(Chronic::RepeaterDayPortion.new(:morning))
17
+
18
+ assert_equal :morning, tokens[1].tags[0].type
19
+
20
+ tokens = Chronic.dealias_and_disambiguate_times(tokens, {})
21
+
22
+ assert_equal :am, tokens[1].tags[0].type
23
+ assert_equal 2, tokens.size
24
+
25
+ # don't affect unwanted patterns
26
+
27
+ tokens = [Chronic::Token.new("friday"), Chronic::Token.new("morning")]
28
+ tokens[0].tag(Chronic::RepeaterDayName.new(:friday))
29
+ tokens[1].tag(Chronic::RepeaterDayPortion.new(:morning))
30
+
31
+ assert_equal :morning, tokens[1].tags[0].type
32
+
33
+ tokens = Chronic.dealias_and_disambiguate_times(tokens, {})
34
+
35
+ assert_equal :morning, tokens[1].tags[0].type
36
+ assert_equal 2, tokens.size
37
+ end
38
+
39
+ def test_guess
40
+ span = Chronic::Span.new(Time.local(2006, 8, 16, 0), Time.local(2006, 8, 17, 0))
41
+ assert_equal Time.local(2006, 8, 16, 12), Chronic.guess(span)
42
+
43
+ span = Chronic::Span.new(Time.local(2006, 8, 16, 0), Time.local(2006, 8, 17, 0, 0, 1))
44
+ assert_equal Time.local(2006, 8, 16, 12), Chronic.guess(span)
45
+
46
+ span = Chronic::Span.new(Time.local(2006, 11), Time.local(2006, 12))
47
+ assert_equal Time.local(2006, 11, 16), Chronic.guess(span)
48
+ end
49
+
50
+ def test_date_string
51
+ assert_equal(Chronic.date_string("9pm"), Chronic.date_string("9pm"))
52
+ assert_equal(Chronic.date_string("9/27/2009"), Chronic.date_string("9/27/2009"))
53
+ assert_equal(Chronic.date_string("9/27/2009"), Chronic.date_string("Meeting 9/27/2009"))
54
+ assert_equal(Chronic.date_string("this day"), Chronic.date_string("Meeting today"))
55
+ end
56
+
57
+ def test_tokenize_ignores_trailing_tokens
58
+ # tokenize will keep tokens like "at" in the string "Meeting 9/27/2009 at the bar" even though it is
59
+ # not part of the date
60
+ tokens = Chronic.tokenize("9/27/2009 at")
61
+ assert_nil(tokens[-1].get_tag(Chronic::Separator), "The last token in this string should not be tagged")
62
+ assert_equal(Chronic.date_string("9/27/2009"), Chronic.date_string("9/27/2009 at"))
63
+
64
+ # test a string with two of the same separator -- one of which will be tagged, one will not
65
+ separator_test = "Meeting 9/27/2009 at 7pm at the bar"
66
+ tokens = Chronic.tokenize(separator_test)
67
+ assert_not_nil(tokens[6].get_tag(Chronic::Separator))
68
+ assert_nil(tokens[9].get_tag(Chronic::Separator))
69
+ assert_equal("Meeting at the bar", Chronic.strip_tokens(separator_test))
70
+ assert_equal(Chronic.date_string("9/27/2009 at 7pm"), Chronic.date_string(separator_test), "date_string does not return the correct date string for <#{separator_test}>")
71
+
72
+ # because the trailing "at" separator here is not tagged anymore, it will be part of the strip_tokens string
73
+ assert_equal("Meeting at the bar", Chronic.strip_tokens("Meeting 9/27/2009 at the bar"))
74
+ end
75
+ end