chronic 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README +119 -0
- data/lib/chronic.rb +30 -0
- data/lib/chronic/chronic.rb +242 -0
- data/lib/chronic/grabber.rb +26 -0
- data/lib/chronic/handlers.rb +405 -0
- data/lib/chronic/ordinal.rb +40 -0
- data/lib/chronic/pointer.rb +27 -0
- data/lib/chronic/repeater.rb +114 -0
- data/lib/chronic/repeaters/repeater_day.rb +40 -0
- data/lib/chronic/repeaters/repeater_day_name.rb +41 -0
- data/lib/chronic/repeaters/repeater_day_portion.rb +93 -0
- data/lib/chronic/repeaters/repeater_fortnight.rb +64 -0
- data/lib/chronic/repeaters/repeater_hour.rb +52 -0
- data/lib/chronic/repeaters/repeater_minute.rb +21 -0
- data/lib/chronic/repeaters/repeater_month.rb +54 -0
- data/lib/chronic/repeaters/repeater_month_name.rb +82 -0
- data/lib/chronic/repeaters/repeater_season.rb +23 -0
- data/lib/chronic/repeaters/repeater_season_name.rb +24 -0
- data/lib/chronic/repeaters/repeater_second.rb +34 -0
- data/lib/chronic/repeaters/repeater_time.rb +106 -0
- data/lib/chronic/repeaters/repeater_week.rb +62 -0
- data/lib/chronic/repeaters/repeater_weekend.rb +11 -0
- data/lib/chronic/repeaters/repeater_year.rb +55 -0
- data/lib/chronic/scalar.rb +74 -0
- data/lib/chronic/separator.rb +76 -0
- data/test/parse_numbers.rb +50 -0
- data/test/suite.rb +9 -0
- data/test/test_Chronic.rb +50 -0
- data/test/test_Handler.rb +110 -0
- data/test/test_RepeaterDayName.rb +52 -0
- data/test/test_RepeaterFortnight.rb +63 -0
- data/test/test_RepeaterHour.rb +65 -0
- data/test/test_RepeaterMonth.rb +47 -0
- data/test/test_RepeaterMonthName.rb +57 -0
- data/test/test_RepeaterTime.rb +72 -0
- data/test/test_RepeaterWeek.rb +63 -0
- data/test/test_RepeaterYear.rb +63 -0
- data/test/test_Span.rb +24 -0
- data/test/test_Token.rb +26 -0
- data/test/test_parsing.rb +472 -0
- metadata +87 -0
data/README
ADDED
@@ -0,0 +1,119 @@
|
|
1
|
+
=Chronic
|
2
|
+
|
3
|
+
Chronic is a natural language date/time parser written in pure Ruby. See below for the wide variety of formats Chronic will parse.
|
4
|
+
|
5
|
+
==Installation
|
6
|
+
|
7
|
+
Chronic can be installed via RubyGems:
|
8
|
+
|
9
|
+
$ sudo gem install chronic
|
10
|
+
|
11
|
+
==Usage
|
12
|
+
|
13
|
+
You can parse strings containing a natural language date using the Chronic.parse method.
|
14
|
+
|
15
|
+
require 'chronic'
|
16
|
+
|
17
|
+
Time.now #=> Sun Aug 27 23:18:25 PDT 2006
|
18
|
+
|
19
|
+
#---
|
20
|
+
|
21
|
+
Chronic.parse('tomorrow')
|
22
|
+
#=> Mon Aug 28 12:00:00 PDT 2006
|
23
|
+
|
24
|
+
Chronic.parse('monday', :context => :past)
|
25
|
+
#=> Mon Aug 21 12:00:00 PDT 2006
|
26
|
+
|
27
|
+
Chronic.parse('this tuesday 5:00')
|
28
|
+
#=> Tue Aug 29 17:00:00 PDT 2006
|
29
|
+
|
30
|
+
Chronic.parse('this tuesday 5:00', :ambiguous_time_range => :none)
|
31
|
+
#=> Tue Aug 29 05:00:00 PDT 2006
|
32
|
+
|
33
|
+
Chronic.parse('may 27th', :now => Time.local(2000, 1, 1))
|
34
|
+
#=> Sat May 27 12:00:00 PDT 2000
|
35
|
+
|
36
|
+
Chronic.parse('may 27th', :guess => false)
|
37
|
+
#=> Sun May 27 00:00:00 PDT 2007..Mon May 28 00:00:00 PDT 2007
|
38
|
+
|
39
|
+
See Chronic.parse for detailed usage instructions.
|
40
|
+
|
41
|
+
==Examples
|
42
|
+
|
43
|
+
Chronic can parse a huge variety of date and time formats. Following is a small sample of strings that will be properly parsed. Parsing is case insensitive and will handle common abbreviations and misspellings.
|
44
|
+
|
45
|
+
Simple
|
46
|
+
|
47
|
+
thursday
|
48
|
+
november
|
49
|
+
summer
|
50
|
+
friday 13:00
|
51
|
+
mon 2:35
|
52
|
+
4pm
|
53
|
+
6 in the morning
|
54
|
+
friday 1pm
|
55
|
+
sat 7 in the evening
|
56
|
+
yesterday
|
57
|
+
today
|
58
|
+
tomorrow
|
59
|
+
this tuesday
|
60
|
+
next month
|
61
|
+
last winter
|
62
|
+
this morning
|
63
|
+
last night
|
64
|
+
this second
|
65
|
+
yesterday at 4:00
|
66
|
+
last friday at 20:00
|
67
|
+
last week tuesday
|
68
|
+
tomorrow at 6:45pm
|
69
|
+
afternoon yesterday
|
70
|
+
thursday last week
|
71
|
+
|
72
|
+
Complex
|
73
|
+
|
74
|
+
3 years ago
|
75
|
+
5 months before now
|
76
|
+
7 hours ago
|
77
|
+
7 days from now
|
78
|
+
1 week hence
|
79
|
+
in 3 hours
|
80
|
+
1 year ago tomorrow
|
81
|
+
3 months ago saturday at 5:00 pm
|
82
|
+
7 hours before tomorrow at noon
|
83
|
+
3rd wednesday in november
|
84
|
+
3rd month next year
|
85
|
+
3rd thursday this september
|
86
|
+
4th day last week
|
87
|
+
|
88
|
+
Specific Dates
|
89
|
+
|
90
|
+
January 5
|
91
|
+
dec 25
|
92
|
+
may 27th
|
93
|
+
October 2006
|
94
|
+
oct 06
|
95
|
+
jan 3 2010
|
96
|
+
february 14, 2004
|
97
|
+
3 jan 2000
|
98
|
+
17 april 85
|
99
|
+
5/27/1979
|
100
|
+
27/5/1979
|
101
|
+
05/06
|
102
|
+
1979-05-27
|
103
|
+
Friday
|
104
|
+
5
|
105
|
+
4:00
|
106
|
+
17:00
|
107
|
+
0800
|
108
|
+
|
109
|
+
Specific Times (many of the above with an added time)
|
110
|
+
|
111
|
+
January 5 at 7pm
|
112
|
+
1979-05-27 05:00
|
113
|
+
etc
|
114
|
+
|
115
|
+
==Limitations
|
116
|
+
|
117
|
+
Chronic uses Ruby's built in Time class for all time storage and computation. Because of this, only times that the Time class can handle will be properly parsed. Parsing for times outside of this range will simply return nil. Support for a wider range of times is planned for a future release.
|
118
|
+
|
119
|
+
Time zones other than the local one are not currently supported. Support for other time zones is planned for a future release.
|
data/lib/chronic.rb
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
#=============================================================================
|
2
|
+
#
|
3
|
+
# Name: Chronic
|
4
|
+
# Author: Tom Preston-Werner
|
5
|
+
# Purpose: Parse natural language dates and times into Time or
|
6
|
+
# Chronic::Span objects
|
7
|
+
#
|
8
|
+
#=============================================================================
|
9
|
+
|
10
|
+
require 'date'
|
11
|
+
|
12
|
+
require 'chronic/chronic'
|
13
|
+
require 'chronic/handlers'
|
14
|
+
require 'chronic/grabber'
|
15
|
+
require 'chronic/ordinal'
|
16
|
+
require 'chronic/pointer'
|
17
|
+
require 'chronic/scalar'
|
18
|
+
require 'chronic/separator'
|
19
|
+
|
20
|
+
require 'chronic/repeater'
|
21
|
+
Dir["#{File.dirname(__FILE__)}/chronic/repeaters/*.rb"].each do |file|
|
22
|
+
require file
|
23
|
+
end
|
24
|
+
|
25
|
+
module Chronic
|
26
|
+
def self.debug=(val); @debug = val; end
|
27
|
+
end
|
28
|
+
|
29
|
+
Chronic.debug = false
|
30
|
+
|
@@ -0,0 +1,242 @@
|
|
1
|
+
module Chronic
|
2
|
+
class << self
|
3
|
+
|
4
|
+
# Parses a string containing a natural language date or time. If the parser
|
5
|
+
# can find a date or time, either a Time or Chronic::Span will be returned
|
6
|
+
# (depending on the value of <tt>:guess</tt>). If no date or time can be found,
|
7
|
+
# +nil+ will be returned.
|
8
|
+
#
|
9
|
+
# Options are:
|
10
|
+
#
|
11
|
+
# [<tt>:context</tt>]
|
12
|
+
# <tt>:past</tt> or <tt>:future</tt> (defaults to <tt>:future</tt>)
|
13
|
+
#
|
14
|
+
# If your string represents a birthday, you can set <tt>:context</tt> to <tt>:past</tt>
|
15
|
+
# and if an ambiguous string is given, it will assume it is in the
|
16
|
+
# past. Specify <tt>:future</tt> or omit to set a future context.
|
17
|
+
#
|
18
|
+
# [<tt>:now</tt>]
|
19
|
+
# Time (defaults to Time.now)
|
20
|
+
#
|
21
|
+
# By setting <tt>:now</tt> to a Time, all computations will be based off
|
22
|
+
# of that time instead of Time.now
|
23
|
+
#
|
24
|
+
# [<tt>:guess</tt>]
|
25
|
+
# +true+ or +false+ (defaults to +true+)
|
26
|
+
#
|
27
|
+
# By default, the parser will guess a single point in time for the
|
28
|
+
# given date or time. If you'd rather have the entire time span returned,
|
29
|
+
# set <tt>:guess</tt> to +false+ and a Chronic::Span will be returned.
|
30
|
+
#
|
31
|
+
# [<tt>:ambiguous_time_range</tt>]
|
32
|
+
# Integer or <tt>:none</tt> (defaults to <tt>6</tt> (6am-6pm))
|
33
|
+
#
|
34
|
+
# If an Integer is given, ambiguous times (like 5:00) will be
|
35
|
+
# assumed to be within the range of that time in the AM to that time
|
36
|
+
# in the PM. For example, if you set it to <tt>7</tt>, then the parser will
|
37
|
+
# look for the time between 7am and 7pm. In the case of 5:00, it would
|
38
|
+
# assume that means 5:00pm. If <tt>:none</tt> is given, no assumption
|
39
|
+
# will be made, and the first matching instance of that time will
|
40
|
+
# be used.
|
41
|
+
def parse(text, specified_options = {})
|
42
|
+
# get options and set defaults if necessary
|
43
|
+
default_options = {:context => :future,
|
44
|
+
:now => Time.now,
|
45
|
+
:guess => true,
|
46
|
+
:ambiguous_time_range => 6}
|
47
|
+
options = default_options.merge specified_options
|
48
|
+
|
49
|
+
# ensure the specified options are valid
|
50
|
+
specified_options.keys.each do |key|
|
51
|
+
default_options.keys.include?(key) || raise(InvalidArgumentException, "#{key} is not a valid option key.")
|
52
|
+
end
|
53
|
+
[:past, :future].include?(options[:context]) || raise(InvalidArgumentException, "Invalid value '#{options[:context]}' for :context specified. Valid values are :past and :future.")
|
54
|
+
|
55
|
+
# store now for later =)
|
56
|
+
@now = options[:now]
|
57
|
+
|
58
|
+
# put the text into a normal format to ease scanning
|
59
|
+
text = self.pre_normalize(text)
|
60
|
+
|
61
|
+
# get base tokens for each word
|
62
|
+
@tokens = self.base_tokenize(text)
|
63
|
+
|
64
|
+
# scan the tokens with each token scanner
|
65
|
+
[Repeater].each do |tokenizer|
|
66
|
+
@tokens = tokenizer.scan(@tokens, options)
|
67
|
+
end
|
68
|
+
|
69
|
+
[Grabber, Pointer, Scalar, Ordinal, Separator].each do |tokenizer|
|
70
|
+
@tokens = tokenizer.scan(@tokens)
|
71
|
+
end
|
72
|
+
|
73
|
+
# strip any non-tagged tokens
|
74
|
+
@tokens = @tokens.select { |token| token.tagged? }
|
75
|
+
|
76
|
+
if @debug
|
77
|
+
puts "+---------------------------------------------------"
|
78
|
+
puts "| " + @tokens.to_s
|
79
|
+
puts "+---------------------------------------------------"
|
80
|
+
end
|
81
|
+
|
82
|
+
# do the heavy lifting
|
83
|
+
begin
|
84
|
+
span = self.tokens_to_span(@tokens, options)
|
85
|
+
rescue
|
86
|
+
raise
|
87
|
+
return nil
|
88
|
+
end
|
89
|
+
|
90
|
+
# guess a time within a span if required
|
91
|
+
if options[:guess]
|
92
|
+
return self.guess(span)
|
93
|
+
else
|
94
|
+
return span
|
95
|
+
end
|
96
|
+
end
|
97
|
+
|
98
|
+
# Clean up the specified input text by stripping unwanted characters,
|
99
|
+
# converting idioms to their canonical form, converting number words
|
100
|
+
# to numbers (three => 3), and converting ordinal words to numeric
|
101
|
+
# ordinals (third => 3rd)
|
102
|
+
def pre_normalize(text) #:nodoc:
|
103
|
+
normalized_text = text.downcase
|
104
|
+
normalized_text.gsub!(/['"\.]/, '')
|
105
|
+
normalized_text.gsub!(/([\/\-\,\@])/) { ' ' + $1 + ' ' }
|
106
|
+
normalized_text.gsub!(/\btoday\b/, 'this day')
|
107
|
+
normalized_text.gsub!(/\btomm?orr?ow\b/, 'next day')
|
108
|
+
normalized_text.gsub!(/\byesterday\b/, 'last day')
|
109
|
+
normalized_text.gsub!(/\bnoon\b/, '12:00')
|
110
|
+
normalized_text.gsub!(/\bmidnight\b/, '24:00')
|
111
|
+
normalized_text.gsub!(/\bfrom now\b/, 'future')
|
112
|
+
normalized_text.gsub!(/\bbefore now\b/, 'past')
|
113
|
+
normalized_text.gsub!(/\bnow\b/, 'this second')
|
114
|
+
normalized_text.gsub!(/\b(ago|before)\b/, 'past')
|
115
|
+
normalized_text.gsub!(/\bthis past\b/, 'last')
|
116
|
+
normalized_text.gsub!(/\bthis last\b/, 'last')
|
117
|
+
normalized_text.gsub!(/\b(?:in|during) the (morning)\b/, '\1')
|
118
|
+
normalized_text.gsub!(/\b(?:in the|during the|at) (afternoon|evening|night)\b/, '\1')
|
119
|
+
normalized_text.gsub!(/\btonight\b/, 'this night')
|
120
|
+
normalized_text.gsub!(/(?=\w)([ap]m|oclock)\b/, ' \1')
|
121
|
+
normalized_text.gsub!(/\b(hence|after|from)\b/, 'future')
|
122
|
+
normalized_text.gsub!(/\ba\b/, '1')
|
123
|
+
normalized_text.gsub!(/\s+/, ' ')
|
124
|
+
normalized_text = numericize_numbers(normalized_text)
|
125
|
+
normalized_text = numericize_ordinals(normalized_text)
|
126
|
+
end
|
127
|
+
|
128
|
+
# Convert number words to numbers (three => 3)
|
129
|
+
def numericize_numbers(text) #:nodoc:
|
130
|
+
text
|
131
|
+
end
|
132
|
+
|
133
|
+
# Convert ordinal words to numeric ordinals (third => 3rd)
|
134
|
+
def numericize_ordinals(text) #:nodoc:
|
135
|
+
text
|
136
|
+
end
|
137
|
+
|
138
|
+
# Split the text on spaces and convert each word into
|
139
|
+
# a Token
|
140
|
+
def base_tokenize(text) #:nodoc:
|
141
|
+
text.split(' ').map { |word| Token.new(word) }
|
142
|
+
end
|
143
|
+
|
144
|
+
# Guess a specific time within the given span
|
145
|
+
def guess(span) #:nodoc:
|
146
|
+
return nil if span.nil?
|
147
|
+
if span.width > 1
|
148
|
+
span.begin + (span.width / 2)
|
149
|
+
else
|
150
|
+
span.begin
|
151
|
+
end
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
class Token #:nodoc:
|
156
|
+
attr_accessor :word, :tags
|
157
|
+
|
158
|
+
def initialize(word)
|
159
|
+
@word = word
|
160
|
+
@tags = []
|
161
|
+
end
|
162
|
+
|
163
|
+
# Tag this token with the specified tag
|
164
|
+
def tag(new_tag)
|
165
|
+
@tags << new_tag
|
166
|
+
end
|
167
|
+
|
168
|
+
# Remove all tags of the given class
|
169
|
+
def untag(tag_class)
|
170
|
+
@tags = @tags.select { |m| !m.kind_of? tag_class }
|
171
|
+
end
|
172
|
+
|
173
|
+
# Return true if this token has any tags
|
174
|
+
def tagged?
|
175
|
+
@tags.size > 0
|
176
|
+
end
|
177
|
+
|
178
|
+
# Return the Tag that matches the given class
|
179
|
+
def get_tag(tag_class)
|
180
|
+
matches = @tags.select { |m| m.kind_of? tag_class }
|
181
|
+
#matches.size < 2 || raise("Multiple identical tags found")
|
182
|
+
return matches.first
|
183
|
+
end
|
184
|
+
|
185
|
+
# Print this Token in a pretty way
|
186
|
+
def to_s
|
187
|
+
@word << '(' << @tags.join(', ') << ') '
|
188
|
+
end
|
189
|
+
end
|
190
|
+
|
191
|
+
# A Span represents a range of time. Since this class extends
|
192
|
+
# Range, you can use #begin and #end to get the beginning and
|
193
|
+
# ending times of the span (they will be of class Time)
|
194
|
+
class Span < Range
|
195
|
+
# Returns the width of this span in seconds
|
196
|
+
def width
|
197
|
+
(self.end - self.begin).to_i
|
198
|
+
end
|
199
|
+
|
200
|
+
# Add a number of seconds to this span, returning the
|
201
|
+
# resulting Span
|
202
|
+
def +(seconds)
|
203
|
+
Span.new(self.begin + seconds, self.end + seconds)
|
204
|
+
end
|
205
|
+
|
206
|
+
# Subtract a number of seconds to this span, returning the
|
207
|
+
# resulting Span
|
208
|
+
def -(seconds)
|
209
|
+
self + -seconds
|
210
|
+
end
|
211
|
+
|
212
|
+
# Prints this span in a nice fashion
|
213
|
+
def to_s
|
214
|
+
'(' << self.begin.to_s << '..' << self.end.to_s << ')'
|
215
|
+
end
|
216
|
+
end
|
217
|
+
|
218
|
+
# Tokens are tagged with subclassed instances of this class when
|
219
|
+
# they match specific criteria
|
220
|
+
class Tag #:nodoc:
|
221
|
+
attr_accessor :type
|
222
|
+
|
223
|
+
def initialize(type)
|
224
|
+
@type = type
|
225
|
+
end
|
226
|
+
|
227
|
+
def start=(s)
|
228
|
+
@now = s
|
229
|
+
end
|
230
|
+
end
|
231
|
+
|
232
|
+
# Internal exception
|
233
|
+
class ChronicPain < Exception #:nodoc:
|
234
|
+
|
235
|
+
end
|
236
|
+
|
237
|
+
# This exception is raised if an invalid argument is provided to
|
238
|
+
# any of Chronic's methods
|
239
|
+
class InvalidArgumentException < Exception
|
240
|
+
|
241
|
+
end
|
242
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
#module Chronic
|
2
|
+
|
3
|
+
class Chronic::Grabber < Chronic::Tag #:nodoc:
|
4
|
+
def self.scan(tokens)
|
5
|
+
tokens.each_index do |i|
|
6
|
+
if t = self.scan_for_all(tokens[i]) then tokens[i].tag(t); next end
|
7
|
+
end
|
8
|
+
tokens
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.scan_for_all(token)
|
12
|
+
scanner = {/last/ => :last,
|
13
|
+
/this/ => :this,
|
14
|
+
/next/ => :next}
|
15
|
+
scanner.keys.each do |scanner_item|
|
16
|
+
return self.new(scanner[scanner_item]) if scanner_item =~ token.word
|
17
|
+
end
|
18
|
+
return nil
|
19
|
+
end
|
20
|
+
|
21
|
+
def to_s
|
22
|
+
'grabber-' << @type.to_s
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
#end
|
@@ -0,0 +1,405 @@
|
|
1
|
+
module Chronic
|
2
|
+
|
3
|
+
class << self
|
4
|
+
|
5
|
+
def definitions #:nodoc:
|
6
|
+
@definitions ||=
|
7
|
+
{:time => [Handler.new([:repeater_time, :repeater_day_portion?], nil)],
|
8
|
+
|
9
|
+
:date => [Handler.new([:repeater_month_name, :scalar_day, :scalar_year], :handle_rmn_sd_sy),
|
10
|
+
Handler.new([:repeater_month_name, :scalar_day, :scalar_year, :separator_at?, 'time?'], :handle_rmn_sd_sy),
|
11
|
+
Handler.new([:repeater_month_name, :scalar_day, :separator_at?, 'time?'], :handle_rmn_sd),
|
12
|
+
Handler.new([:repeater_month_name, :ordinal_day, :separator_at?, 'time?'], :handle_rmn_od),
|
13
|
+
Handler.new([:repeater_month_name, :scalar_year], :handle_rmn_sy),
|
14
|
+
Handler.new([:scalar_day, :repeater_month_name, :scalar_year, :separator_at?, 'time?'], :handle_sd_rmn_sy),
|
15
|
+
Handler.new([:scalar_month, :separator_slash_or_dash, :scalar_day, :separator_slash_or_dash, :scalar_year, :separator_at?, 'time?'], :handle_sm_sd_sy),
|
16
|
+
Handler.new([:scalar_day, :separator_slash_or_dash, :scalar_month, :separator_slash_or_dash, :scalar_year, :separator_at?, 'time?'], :handle_sd_sm_sy),
|
17
|
+
Handler.new([:scalar_year, :separator_slash_or_dash, :scalar_month, :separator_slash_or_dash, :scalar_day, :separator_at?, 'time?'], :handle_sy_sm_sd),
|
18
|
+
Handler.new([:scalar_month, :separator_slash_or_dash, :scalar_year], :handle_sm_sy)],
|
19
|
+
|
20
|
+
:anchor => [Handler.new([:grabber?, :repeater, :separator_at?, :repeater?, :repeater?], :handle_r),
|
21
|
+
Handler.new([:repeater, :grabber, :repeater], :handle_r_g_r)],
|
22
|
+
|
23
|
+
:arrow => [Handler.new([:scalar, :repeater, :pointer], :handle_s_r_p),
|
24
|
+
Handler.new([:pointer, :scalar, :repeater], :handle_p_s_r),
|
25
|
+
Handler.new([:scalar, :repeater, :pointer, 'anchor'], :handle_s_r_p_a)],
|
26
|
+
|
27
|
+
:narrow => [Handler.new([:ordinal, :repeater, :separator_in, :repeater], :handle_o_r_s_r),
|
28
|
+
Handler.new([:ordinal, :repeater, :grabber, :repeater], :handle_o_r_g_r)]
|
29
|
+
}
|
30
|
+
end
|
31
|
+
|
32
|
+
def tokens_to_span(tokens, options) #:nodoc:
|
33
|
+
# maybe it's a specific date
|
34
|
+
|
35
|
+
self.definitions[:date].each do |handler|
|
36
|
+
if handler.match(tokens, self.definitions)
|
37
|
+
good_tokens = tokens.select { |o| !o.get_tag Separator }
|
38
|
+
return self.send(handler.handler_method, good_tokens, options)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
# I guess it's not a specific date, maybe it's just an anchor
|
43
|
+
|
44
|
+
self.definitions[:anchor].each do |handler|
|
45
|
+
if handler.match(tokens, self.definitions)
|
46
|
+
good_tokens = tokens.select { |o| !o.get_tag Separator }
|
47
|
+
return self.send(handler.handler_method, good_tokens, options)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
# not an anchor, perhaps it's an arrow
|
52
|
+
|
53
|
+
self.definitions[:arrow].each do |handler|
|
54
|
+
if handler.match(tokens, self.definitions)
|
55
|
+
good_tokens = tokens.reject { |o| o.get_tag(SeparatorAt) || o.get_tag(SeparatorSlashOrDash) || o.get_tag(SeparatorComma) }
|
56
|
+
return self.send(handler.handler_method, good_tokens, options)
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
# not an arrow, let's hope it's an narrow
|
61
|
+
|
62
|
+
self.definitions[:narrow].each do |handler|
|
63
|
+
if handler.match(tokens, self.definitions)
|
64
|
+
#good_tokens = tokens.select { |o| !o.get_tag Separator }
|
65
|
+
return self.send(handler.handler_method, tokens, options)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
# I guess you're out of luck!
|
70
|
+
return nil
|
71
|
+
end
|
72
|
+
|
73
|
+
#--------------
|
74
|
+
|
75
|
+
def day_or_time(day_start, time_tokens, options)
|
76
|
+
outer_span = Span.new(day_start, day_start + (24 * 60 * 60))
|
77
|
+
|
78
|
+
if !time_tokens.empty?
|
79
|
+
@now = outer_span.begin
|
80
|
+
time = get_anchor(dealias_and_disambiguate_times(time_tokens, options), options)
|
81
|
+
return time
|
82
|
+
else
|
83
|
+
return outer_span
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
#--------------
|
88
|
+
|
89
|
+
def handle_m_d(month, day, time_tokens, options) #:nodoc:
|
90
|
+
month.start = @now
|
91
|
+
span = month.next(options[:context])
|
92
|
+
|
93
|
+
day_start = Time.local(span.begin.year, span.begin.month, day)
|
94
|
+
|
95
|
+
day_or_time(day_start, time_tokens, options)
|
96
|
+
end
|
97
|
+
|
98
|
+
def handle_rmn_sd(tokens, options) #:nodoc:
|
99
|
+
handle_m_d(tokens[0].get_tag(RepeaterMonthName), tokens[1].get_tag(ScalarDay).type, tokens[2..tokens.size], options)
|
100
|
+
end
|
101
|
+
|
102
|
+
def handle_rmn_od(tokens, options) #:nodoc:
|
103
|
+
handle_m_d(tokens[0].get_tag(RepeaterMonthName), tokens[1].get_tag(OrdinalDay).type, tokens[2..tokens.size], options)
|
104
|
+
end
|
105
|
+
|
106
|
+
def handle_rmn_sy(tokens, options) #:nodoc:
|
107
|
+
month = tokens[0].get_tag(RepeaterMonthName).index
|
108
|
+
year = tokens[1].get_tag(ScalarYear).type
|
109
|
+
|
110
|
+
if month == 12
|
111
|
+
next_month_year = year + 1
|
112
|
+
next_month_month = 1
|
113
|
+
else
|
114
|
+
next_month_year = year
|
115
|
+
next_month_month = month + 1
|
116
|
+
end
|
117
|
+
|
118
|
+
begin
|
119
|
+
Span.new(Time.local(year, month), Time.local(next_month_year, next_month_month))
|
120
|
+
rescue ArgumentError
|
121
|
+
nil
|
122
|
+
end
|
123
|
+
end
|
124
|
+
|
125
|
+
def handle_rmn_sd_sy(tokens, options) #:nodoc:
|
126
|
+
month = tokens[0].get_tag(RepeaterMonthName).index
|
127
|
+
day = tokens[1].get_tag(ScalarDay).type
|
128
|
+
year = tokens[2].get_tag(ScalarYear).type
|
129
|
+
|
130
|
+
time_tokens = tokens.last(tokens.size - 3)
|
131
|
+
|
132
|
+
begin
|
133
|
+
day_start = Time.local(year, month, day)
|
134
|
+
day_or_time(day_start, time_tokens, options)
|
135
|
+
rescue ArgumentError
|
136
|
+
nil
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
def handle_sd_rmn_sy(tokens, options) #:nodoc:
|
141
|
+
new_tokens = [tokens[1], tokens[0], tokens[2]]
|
142
|
+
time_tokens = tokens.last(tokens.size - 3)
|
143
|
+
self.handle_rmn_sd_sy(new_tokens + time_tokens, options)
|
144
|
+
end
|
145
|
+
|
146
|
+
def handle_sm_sd_sy(tokens, options) #:nodoc:
|
147
|
+
month = tokens[0].get_tag(ScalarMonth).type
|
148
|
+
day = tokens[1].get_tag(ScalarDay).type
|
149
|
+
year = tokens[2].get_tag(ScalarYear).type
|
150
|
+
|
151
|
+
time_tokens = tokens.last(tokens.size - 3)
|
152
|
+
|
153
|
+
begin
|
154
|
+
day_start = Time.local(year, month, day) #:nodoc:
|
155
|
+
day_or_time(day_start, time_tokens, options)
|
156
|
+
rescue ArgumentError
|
157
|
+
nil
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
def handle_sd_sm_sy(tokens, options) #:nodoc:
|
162
|
+
new_tokens = [tokens[1], tokens[0], tokens[2]]
|
163
|
+
time_tokens = tokens.last(tokens.size - 3)
|
164
|
+
self.handle_sm_sd_sy(new_tokens + time_tokens, options)
|
165
|
+
end
|
166
|
+
|
167
|
+
def handle_sy_sm_sd(tokens, options) #:nodoc:
|
168
|
+
new_tokens = [tokens[1], tokens[2], tokens[0]]
|
169
|
+
time_tokens = tokens.last(tokens.size - 3)
|
170
|
+
self.handle_sm_sd_sy(new_tokens + time_tokens, options)
|
171
|
+
end
|
172
|
+
|
173
|
+
def handle_sm_sy(tokens, options) #:nodoc:
|
174
|
+
month = tokens[0].get_tag(ScalarMonth).type
|
175
|
+
year = tokens[1].get_tag(ScalarYear).type
|
176
|
+
|
177
|
+
if month == 12
|
178
|
+
next_month_year = year + 1
|
179
|
+
next_month_month = 1
|
180
|
+
else
|
181
|
+
next_month_year = year
|
182
|
+
next_month_month = month + 1
|
183
|
+
end
|
184
|
+
|
185
|
+
begin
|
186
|
+
Span.new(Time.local(year, month), Time.local(next_month_year, next_month_month))
|
187
|
+
rescue ArgumentError
|
188
|
+
nil
|
189
|
+
end
|
190
|
+
end
|
191
|
+
|
192
|
+
# anchors
|
193
|
+
|
194
|
+
def handle_r(tokens, options) #:nodoc:
|
195
|
+
dd_tokens = dealias_and_disambiguate_times(tokens, options)
|
196
|
+
self.get_anchor(dd_tokens, options)
|
197
|
+
end
|
198
|
+
|
199
|
+
def handle_r_g_r(tokens, options) #:nodoc:
|
200
|
+
new_tokens = [tokens[1], tokens[0], tokens[2]]
|
201
|
+
self.handle_r(new_tokens, options)
|
202
|
+
end
|
203
|
+
|
204
|
+
# arrows
|
205
|
+
|
206
|
+
def handle_srp(tokens, span, options) #:nodoc:
|
207
|
+
distance = tokens[0].get_tag(Scalar).type
|
208
|
+
repeater = tokens[1].get_tag(Repeater)
|
209
|
+
pointer = tokens[2].get_tag(Pointer).type
|
210
|
+
|
211
|
+
repeater.offset(span, distance, pointer)
|
212
|
+
end
|
213
|
+
|
214
|
+
def handle_s_r_p(tokens, options) #:nodoc:
|
215
|
+
repeater = tokens[1].get_tag(Repeater)
|
216
|
+
|
217
|
+
span =
|
218
|
+
case true
|
219
|
+
when [RepeaterYear, RepeaterSeason, RepeaterSeasonName, RepeaterMonth, RepeaterMonthName, RepeaterFortnight, RepeaterWeek].include?(repeater.class)
|
220
|
+
self.parse("this hour", :guess => false, :now => @now)
|
221
|
+
when [RepeaterWeekend, RepeaterDay, RepeaterDayName, RepeaterDayPortion, RepeaterHour].include?(repeater.class)
|
222
|
+
self.parse("this minute", :guess => false, :now => @now)
|
223
|
+
when [RepeaterMinute, RepeaterSecond].include?(repeater.class)
|
224
|
+
self.parse("this second", :guess => false, :now => @now)
|
225
|
+
else
|
226
|
+
raise(ChronicPain, "Invalid repeater: #{repeater.class}")
|
227
|
+
end
|
228
|
+
|
229
|
+
self.handle_srp(tokens, span, options)
|
230
|
+
end
|
231
|
+
|
232
|
+
def handle_p_s_r(tokens, options) #:nodoc:
|
233
|
+
new_tokens = [tokens[1], tokens[2], tokens[0]]
|
234
|
+
self.handle_s_r_p(new_tokens, options)
|
235
|
+
end
|
236
|
+
|
237
|
+
def handle_s_r_p_a(tokens, options) #:nodoc:
|
238
|
+
anchor_span = get_anchor(tokens[3..tokens.size - 1], options)
|
239
|
+
self.handle_srp(tokens, anchor_span, options)
|
240
|
+
end
|
241
|
+
|
242
|
+
# narrows
|
243
|
+
|
244
|
+
def handle_orr(tokens, outer_span, options) #:nodoc:
|
245
|
+
repeater = tokens[1].get_tag(Repeater)
|
246
|
+
repeater.start = outer_span.begin - 1
|
247
|
+
ordinal = tokens[0].get_tag(Ordinal).type
|
248
|
+
span = nil
|
249
|
+
ordinal.times do
|
250
|
+
span = repeater.next(:future)
|
251
|
+
if span.begin > outer_span.end
|
252
|
+
span = nil
|
253
|
+
break
|
254
|
+
end
|
255
|
+
end
|
256
|
+
span
|
257
|
+
end
|
258
|
+
|
259
|
+
def handle_o_r_s_r(tokens, options) #:nodoc:
|
260
|
+
outer_span = get_anchor([tokens[3]], options)
|
261
|
+
handle_orr(tokens[0..1], outer_span, options)
|
262
|
+
end
|
263
|
+
|
264
|
+
def handle_o_r_g_r(tokens, options) #:nodoc:
|
265
|
+
outer_span = get_anchor(tokens[2..3], options)
|
266
|
+
handle_orr(tokens[0..1], outer_span, options)
|
267
|
+
end
|
268
|
+
|
269
|
+
# support methods
|
270
|
+
|
271
|
+
def get_anchor(tokens, options) #:nodoc:
|
272
|
+
grabber = Grabber.new(:this)
|
273
|
+
pointer = :future
|
274
|
+
|
275
|
+
repeaters = self.get_repeaters(tokens)
|
276
|
+
repeaters.size.times { tokens.pop }
|
277
|
+
|
278
|
+
if tokens.last && tokens.last.get_tag(Grabber)
|
279
|
+
grabber = tokens.last.get_tag(Grabber)
|
280
|
+
tokens.pop
|
281
|
+
end
|
282
|
+
|
283
|
+
head = repeaters.shift
|
284
|
+
head.start = @now
|
285
|
+
|
286
|
+
case grabber.type
|
287
|
+
when :last: outer_span = head.next(:past)
|
288
|
+
when :this: outer_span = head.this(options[:context])
|
289
|
+
when :next: outer_span = head.next(:future)
|
290
|
+
else raise(ChronicPain, "Invalid grabber")
|
291
|
+
end
|
292
|
+
|
293
|
+
anchor = find_within(repeaters, outer_span, pointer)
|
294
|
+
end
|
295
|
+
|
296
|
+
def get_repeaters(tokens) #:nodoc:
|
297
|
+
repeaters = []
|
298
|
+
tokens.reverse.each do |token|
|
299
|
+
if t = token.get_tag(Repeater)
|
300
|
+
repeaters << t
|
301
|
+
else
|
302
|
+
break
|
303
|
+
end
|
304
|
+
end
|
305
|
+
repeaters.sort.reverse
|
306
|
+
end
|
307
|
+
|
308
|
+
# Recursively finds repeaters within other repeaters.
|
309
|
+
# Returns a Span representing the innermost time span
|
310
|
+
# or nil if no repeater union could be found
|
311
|
+
def find_within(tags, span, pointer) #:nodoc:
|
312
|
+
return span if tags.empty?
|
313
|
+
|
314
|
+
head, *rest = tags
|
315
|
+
head.start = pointer == :future ? span.begin : span.end
|
316
|
+
h = head.next(pointer)
|
317
|
+
|
318
|
+
if span.include?(h.begin) || span.include?(h.end)
|
319
|
+
return find_within(rest, h, pointer)
|
320
|
+
else
|
321
|
+
return nil
|
322
|
+
end
|
323
|
+
end
|
324
|
+
|
325
|
+
def dealias_and_disambiguate_times(tokens, options) #:nodoc:
|
326
|
+
# handle aliases of am/pm
|
327
|
+
# 5:00 in the morning => 5:00 am
|
328
|
+
# 7:00 in the evening => 7:00 pm
|
329
|
+
#ttokens = []
|
330
|
+
tokens.each_with_index do |t0, i|
|
331
|
+
t1 = tokens[i + 1]
|
332
|
+
if t1 && (t1tag = t1.get_tag(RepeaterDayPortion)) && t0.get_tag(RepeaterTime)
|
333
|
+
if [:morning].include?(t1tag.type)
|
334
|
+
t1.untag(RepeaterDayPortion)
|
335
|
+
t1.tag(RepeaterDayPortion.new(:am))
|
336
|
+
elsif [:afternoon, :evening, :night].include?(t1tag.type)
|
337
|
+
t1.untag(RepeaterDayPortion)
|
338
|
+
t1.tag(RepeaterDayPortion.new(:pm))
|
339
|
+
end
|
340
|
+
end
|
341
|
+
end
|
342
|
+
#tokens = ttokens
|
343
|
+
|
344
|
+
# handle ambiguous times if :ambiguous_time_range is specified
|
345
|
+
if options[:ambiguous_time_range] != :none
|
346
|
+
ttokens = []
|
347
|
+
tokens.each_with_index do |t0, i|
|
348
|
+
ttokens << t0
|
349
|
+
t1 = tokens[i + 1]
|
350
|
+
if t0.get_tag(RepeaterTime) && t0.get_tag(RepeaterTime).type.ambiguous? && (!t1 || !t1.get_tag(RepeaterDayPortion))
|
351
|
+
distoken = Token.new('disambiguator')
|
352
|
+
distoken.tag(RepeaterDayPortion.new(options[:ambiguous_time_range]))
|
353
|
+
ttokens << distoken
|
354
|
+
end
|
355
|
+
end
|
356
|
+
tokens = ttokens
|
357
|
+
end
|
358
|
+
|
359
|
+
tokens
|
360
|
+
end
|
361
|
+
|
362
|
+
end
|
363
|
+
|
364
|
+
class Handler #:nodoc:
|
365
|
+
attr_accessor :pattern, :handler_method
|
366
|
+
|
367
|
+
def initialize(pattern, handler_method)
|
368
|
+
@pattern = pattern
|
369
|
+
@handler_method = handler_method
|
370
|
+
end
|
371
|
+
|
372
|
+
def constantize(name)
|
373
|
+
camel = name.to_s.gsub(/(^|_)(.)/) { $2.upcase }
|
374
|
+
::Chronic.module_eval(camel, __FILE__, __LINE__)
|
375
|
+
end
|
376
|
+
|
377
|
+
def match(tokens, definitions)
|
378
|
+
token_index = 0
|
379
|
+
@pattern.each do |element|
|
380
|
+
name = element.to_s
|
381
|
+
optional = name.reverse[0..0] == '?'
|
382
|
+
name = name.chop if optional
|
383
|
+
if element.instance_of? Symbol
|
384
|
+
klass = constantize(name)
|
385
|
+
match = tokens[token_index] && !tokens[token_index].tags.select { |o| o.kind_of?(klass) }.empty?
|
386
|
+
return false if !match && !optional
|
387
|
+
(token_index += 1; next) if match
|
388
|
+
next if !match && optional
|
389
|
+
elsif element.instance_of? String
|
390
|
+
return true if optional && token_index == tokens.size
|
391
|
+
sub_handlers = definitions[name.intern] || raise(ChronicPain, "Invalid subset #{name} specified")
|
392
|
+
sub_handlers.each do |sub_handler|
|
393
|
+
return true if sub_handler.match(tokens[token_index..tokens.size], definitions)
|
394
|
+
end
|
395
|
+
return false
|
396
|
+
else
|
397
|
+
raise(ChronicPain, "Invalid match type: #{element.class}")
|
398
|
+
end
|
399
|
+
end
|
400
|
+
return false if token_index != tokens.size
|
401
|
+
return true
|
402
|
+
end
|
403
|
+
end
|
404
|
+
|
405
|
+
end
|