sequitur 0.1.15 → 0.1.16
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +6 -14
- data/.ruby-version +1 -1
- data/CHANGELOG.md +4 -0
- data/Gemfile +4 -3
- data/lib/sequitur/constants.rb +1 -1
- data/lib/sequitur/sequitur_grammar.rb +1 -1
- data/spec/sequitur/dynamic_grammar_spec.rb +1 -1
- data/spec/sequitur/formatter/base_text_spec.rb +1 -1
- data/spec/sequitur/production_ref_spec.rb +2 -2
- data/spec/sequitur/production_spec.rb +2 -2
- data/spec/sequitur/sequitur_grammar_spec.rb +304 -304
- metadata +56 -41
checksums.yaml
CHANGED
@@ -1,15 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
metadata.gz: !binary |-
|
9
|
-
NDI0YzNmOWI4ZTBlZGNjNDkxNmNmNTRhNDJjZDMzMDY4OWE4YmU5YmRjZmJl
|
10
|
-
NzI5MjViMjhhNGYyODkyNGQzNGMyMGFhMjRkNjMyMDBlOTFlN2ZhNzgzYzk1
|
11
|
-
MTgxNjYzYTA4YmFkZWE1ZDlmOTc0MDdkMzJmOGQzMTFiYmEzYWQ=
|
12
|
-
data.tar.gz: !binary |-
|
13
|
-
OGI1NWI4NDBlMjhhYzQ3NWUyNDI1MmFkZmI0ZTgzYWRlZWQ1OTZlZWM4Yzg1
|
14
|
-
OTIxMDc4Zjc2NmY1MDExNzQ5OWYyZTkwY2EyZjgwMTczZGFkOGE2YzJkMjAx
|
15
|
-
NGQxMWY2NDBkOTBlNTM1M2I2YWNiNDA1M2U1MjZlMWFjY2RjZTI=
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b1af553fad3ecc43dc57cc44e040b01d855caf01
|
4
|
+
data.tar.gz: 541cc47ff348f3886a95bde5eba649c1f1a91913
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: db612a6216a109a99a216e2cfaca23feaf20243c121fd404956bc76109f5926e67af4cb26c29f747040f93348768ab2f40e1db3070d096fd96dc687d290a3bf9
|
7
|
+
data.tar.gz: 21ae7581e271eb66e7f8a4578ae451e994670cc138afe341f18722cfbf7cd8625a559748281f2986ce121ba10da2a58438c12f1c04b8db0dd6f3e084e0e2d186
|
data/.ruby-version
CHANGED
@@ -1 +1 @@
|
|
1
|
-
|
1
|
+
2.2.3
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,7 @@
|
|
1
|
+
### 0.1.16 / 2015-09-05
|
2
|
+
* [CHANGE] Minor. Code re-formatted to please Rubocop 0.34.0
|
3
|
+
* [FIX] File `sequitur.gemspec`: updated gem version in development dependencies
|
4
|
+
|
1
5
|
### 0.1.15 / 2015-06-16
|
2
6
|
* [CHANGE] Code re-formatted to please Rubocop 0.32.0
|
3
7
|
* [FIX] File `.rubocop.yml`: change some cop settings.
|
data/Gemfile
CHANGED
@@ -3,8 +3,9 @@ source 'https://rubygems.org'
|
|
3
3
|
|
4
4
|
|
5
5
|
group :development do
|
6
|
-
gem 'rake',
|
7
|
-
gem 'rspec', '>=
|
8
|
-
gem 'simplecov', '>= 0.
|
6
|
+
gem 'rake', '>= 10.0.0'
|
7
|
+
gem 'rspec', '>= 2.1.0'
|
8
|
+
gem 'simplecov', '>= 0.8.0'
|
9
9
|
gem 'coveralls', '>= 0.7.0'
|
10
10
|
end
|
11
|
+
|
data/lib/sequitur/constants.rb
CHANGED
@@ -121,7 +121,7 @@ class SequiturGrammar < DynamicGrammar
|
|
121
121
|
# And delete P
|
122
122
|
def restore_utility(prod_index)
|
123
123
|
# Retrieve useless prod from its index
|
124
|
-
useless_prod =
|
124
|
+
useless_prod = productions[prod_index]
|
125
125
|
|
126
126
|
# Retrieve production referencing useless one
|
127
127
|
referencing = nil
|
@@ -71,7 +71,7 @@ describe DynamicGrammar do
|
|
71
71
|
expect(p_b.refcount).to eq(1)
|
72
72
|
expect(p_c.refcount).to eq(1)
|
73
73
|
|
74
|
-
subject.remove_production(1)
|
74
|
+
subject.remove_production(1) # 1 => p_a
|
75
75
|
expect(subject.productions.size).to eq(4)
|
76
76
|
expect(p_b.refcount).to eq(1)
|
77
77
|
expect(p_c.refcount).to eq(1)
|
@@ -60,7 +60,7 @@ SNIPPET
|
|
60
60
|
|
61
61
|
it 'should support visit events with an explicit visitor' do
|
62
62
|
instance = BaseText.new(destination)
|
63
|
-
a_visitor = sample_grammar.visitor
|
63
|
+
a_visitor = sample_grammar.visitor # Use visitor explicitly
|
64
64
|
instance.render(a_visitor)
|
65
65
|
expectations = <<-SNIPPET
|
66
66
|
start :.
|
@@ -72,8 +72,8 @@ describe ProductionRef do
|
|
72
72
|
|
73
73
|
it 'should compare to other production (reference)' do
|
74
74
|
same = ProductionRef.new(target)
|
75
|
-
expect(subject).to eq(subject)
|
76
|
-
expect(subject).to eq(same)
|
75
|
+
expect(subject).to eq(subject) # Strict identity
|
76
|
+
expect(subject).to eq(same) # 2 references pointing to same production
|
77
77
|
expect(subject).to eq(target)
|
78
78
|
end
|
79
79
|
|
@@ -129,7 +129,7 @@ describe Production do
|
|
129
129
|
# Side-effect: refcount of production to append is incremented
|
130
130
|
expect(p_a.refcount).to be(0)
|
131
131
|
|
132
|
-
input = [p_a, :b, :c, :d, p_a, :e, :f]
|
132
|
+
input = [p_a, :b, :c, :d, p_a, :e, :f] # p_a appears twice
|
133
133
|
input.each { |symb| subject.append_symbol(symb) }
|
134
134
|
expect(p_a.refcount).to be(2)
|
135
135
|
end
|
@@ -139,7 +139,7 @@ describe Production do
|
|
139
139
|
ref_a = ProductionRef.new(p_a)
|
140
140
|
expect(p_a.refcount).to be(1)
|
141
141
|
|
142
|
-
input = [ref_a, :b, :c, :d, ref_a]
|
142
|
+
input = [ref_a, :b, :c, :d, ref_a] # ref_a appears twice
|
143
143
|
input.each { |symb| subject.append_symbol(symb) }
|
144
144
|
|
145
145
|
# References in rhs should point to p_a...
|
@@ -1,304 +1,304 @@
|
|
1
|
-
require_relative '../spec_helper'
|
2
|
-
|
3
|
-
# Load the class under test
|
4
|
-
require_relative '../../lib/sequitur/sequitur_grammar'
|
5
|
-
|
6
|
-
module Sequitur # Re-open the module to get rid of qualified names
|
7
|
-
describe SequiturGrammar do
|
8
|
-
# Factory method. Returns an empty enumerator (
|
9
|
-
# i.e. without elements to iterate)
|
10
|
-
def empty_enum()
|
11
|
-
return [].to_enum
|
12
|
-
end
|
13
|
-
|
14
|
-
context 'Creation from an enumeration of tokens:' do
|
15
|
-
it 'could be created with an empty enumerator' do
|
16
|
-
expect { SequiturGrammar.new(empty_enum) }.not_to raise_error
|
17
|
-
|
18
|
-
# Creation
|
19
|
-
instance = SequiturGrammar.new(empty_enum)
|
20
|
-
|
21
|
-
# Initialization
|
22
|
-
expect(instance.productions.size).to eq(1)
|
23
|
-
expect(instance.start).to eq(instance.productions.first)
|
24
|
-
expect(instance.start).to be_empty
|
25
|
-
end
|
26
|
-
|
27
|
-
it 'could be created with single token' do
|
28
|
-
# Creation
|
29
|
-
instance = SequiturGrammar.new([:a].to_enum)
|
30
|
-
|
31
|
-
# Initialization
|
32
|
-
expect(instance.productions.size).to eq(1)
|
33
|
-
expect(instance.start).to eq(instance.productions.first)
|
34
|
-
expect(instance.start.rhs).to eq([:a])
|
35
|
-
end
|
36
|
-
|
37
|
-
it 'could be created with multiple unique tokens' do
|
38
|
-
# Creation
|
39
|
-
instance = SequiturGrammar.new([:a, :b, :c, :d].to_enum)
|
40
|
-
|
41
|
-
# Initialization
|
42
|
-
expect(instance.productions.size).to eq(1)
|
43
|
-
expect(instance.start).to eq(instance.productions.first)
|
44
|
-
expect(instance.start.rhs).to eq([:a, :b, :c, :d])
|
45
|
-
end
|
46
|
-
|
47
|
-
it 'could be created with a repeating digram' do
|
48
|
-
instance = SequiturGrammar.new([:a, :b, :a, :b].to_enum)
|
49
|
-
|
50
|
-
# Expectations:
|
51
|
-
# S : A A.
|
52
|
-
# A : a b.
|
53
|
-
expect(instance.productions.size).to eq(2)
|
54
|
-
p_a = instance.productions[1]
|
55
|
-
expect(p_a.rhs).to eq([:a, :b])
|
56
|
-
expect(instance.start.rhs).to eq([p_a, p_a])
|
57
|
-
end
|
58
|
-
|
59
|
-
it 'should enforce the utility rule' do
|
60
|
-
instance = SequiturGrammar.new([:a, :b, :c, :a, :b, :c].to_enum)
|
61
|
-
|
62
|
-
# Expectations without utility rule:
|
63
|
-
# S : B B.
|
64
|
-
# A : a b.
|
65
|
-
# B : A c.
|
66
|
-
|
67
|
-
# Expectations with utility rule:
|
68
|
-
# S : A A.
|
69
|
-
# A : a b c.
|
70
|
-
expect(instance.productions.size).to eq(2)
|
71
|
-
p_a = instance.productions.last
|
72
|
-
expect(p_a.rhs).to eq([:a, :b, :c])
|
73
|
-
expect(instance.start.rhs).to eq([p_a, p_a])
|
74
|
-
end
|
75
|
-
|
76
|
-
it 'should cope with a pattern that caused an exception' do
|
77
|
-
input = 'aaac'
|
78
|
-
|
79
|
-
# Creation
|
80
|
-
expect { SequiturGrammar.new(input.chars) }.not_to raise_error
|
81
|
-
end
|
82
|
-
|
83
|
-
|
84
|
-
it 'should cope with the example from presentation' do
|
85
|
-
input = 'bbebeebebebbebee'
|
86
|
-
|
87
|
-
# Creation
|
88
|
-
instance = SequiturGrammar.new(input.chars)
|
89
|
-
|
90
|
-
# Expectations:
|
91
|
-
# S: P3 P2 P3
|
92
|
-
# P1: b e
|
93
|
-
# P2: P1 P1
|
94
|
-
# P3: b P2 e
|
95
|
-
expect(instance.productions.size).to eq(4)
|
96
|
-
(p1, p2, p3) = instance.productions[1..3]
|
97
|
-
expect(instance.start.rhs).to eq([p3, p2, p3])
|
98
|
-
expect(p1.rhs).to eq(%w(b e))
|
99
|
-
expect(p2.rhs).to eq([p1, p1])
|
100
|
-
expect(p3.rhs).to eq(['b', p2, 'e'])
|
101
|
-
end
|
102
|
-
|
103
|
-
it 'should work with strings instead of single char input tokens' do
|
104
|
-
# Raw input is sequence of chars
|
105
|
-
raw_input = 'bbebeebebebbebee'
|
106
|
-
|
107
|
-
# Convert them into multichar strings
|
108
|
-
input = raw_input.chars.map do |ch|
|
109
|
-
'letter_' + ch
|
110
|
-
end
|
111
|
-
|
112
|
-
# Creation
|
113
|
-
instance = SequiturGrammar.new(input.to_enum)
|
114
|
-
|
115
|
-
# Expectations:
|
116
|
-
# S: P3 P2 P3
|
117
|
-
# P1: b e
|
118
|
-
# P2: P1 P1
|
119
|
-
# P3: b P2 e
|
120
|
-
expect(instance.productions.size).to eq(4)
|
121
|
-
(p1, p2, p3) = instance.productions[1..3]
|
122
|
-
expect(instance.start.rhs).to eq([p3, p2, p3])
|
123
|
-
expect(p1.rhs).to eq(%w(letter_b letter_e))
|
124
|
-
expect(p2.rhs).to eq([p1, p1])
|
125
|
-
expect(p3.rhs).to eq(['letter_b', p2, 'letter_e'])
|
126
|
-
end
|
127
|
-
|
128
|
-
it 'should work with Symbol instead of single char input tokens' do
|
129
|
-
# Raw input is sequence of single characters
|
130
|
-
raw_input = 'bbebeebebebbebee'
|
131
|
-
|
132
|
-
# Convert them into symbols
|
133
|
-
input = raw_input.chars.map(&:to_sym)
|
134
|
-
|
135
|
-
# Creation
|
136
|
-
instance = SequiturGrammar.new(input.to_enum)
|
137
|
-
|
138
|
-
# Expectations:
|
139
|
-
# S: P3 P2 P3
|
140
|
-
# P1: b e
|
141
|
-
# P2: P1 P1
|
142
|
-
# P3: b P2 e
|
143
|
-
expect(instance.productions.size).to eq(4)
|
144
|
-
(p1, p2, p3) = instance.productions[1..3]
|
145
|
-
expect(instance.start.rhs).to eq([p3, p2, p3])
|
146
|
-
expect(p1.rhs).to eq([:b, :e])
|
147
|
-
expect(p2.rhs).to eq([p1, p1])
|
148
|
-
expect(p3.rhs).to eq([:b, p2, :e])
|
149
|
-
end
|
150
|
-
|
151
|
-
|
152
|
-
it 'should work with integer values as input tokens' do
|
153
|
-
# Raw input is sequence of hex digits
|
154
|
-
raw_input = 'bbebeebebebbebee'
|
155
|
-
|
156
|
-
# Convert them into Fixnums
|
157
|
-
input = raw_input.chars.map { |ch| ch.to_i(16) }
|
158
|
-
|
159
|
-
# Creation
|
160
|
-
instance = SequiturGrammar.new(input.to_enum)
|
161
|
-
|
162
|
-
# Expectations:
|
163
|
-
# S: P3 P2 P3
|
164
|
-
# P1: b e
|
165
|
-
# P2: P1 P1
|
166
|
-
# P3: b P2 e
|
167
|
-
expect(instance.productions.size).to eq(4)
|
168
|
-
(p1, p2, p3) = instance.productions[1..3]
|
169
|
-
expect(instance.start.rhs).to eq([p3, p2, p3])
|
170
|
-
expect(p1.rhs).to eq([0xb, 0xe])
|
171
|
-
expect(p2.rhs).to eq([p1, p1])
|
172
|
-
expect(p3.rhs).to eq([0xb, p2, 0xe])
|
173
|
-
end
|
174
|
-
|
175
|
-
it 'should cope with the example from sequitur.info website' do
|
176
|
-
input = 'abcabdabcabd'
|
177
|
-
instance = SequiturGrammar.new(input.chars)
|
178
|
-
|
179
|
-
# Expectations:
|
180
|
-
# 0 → 2 2
|
181
|
-
# 1 → a b
|
182
|
-
# 2 → 1 c 1 d
|
183
|
-
|
184
|
-
expect(instance.productions.size).to eq(3)
|
185
|
-
(p1, p2) = instance.productions[1..2]
|
186
|
-
expect(instance.start.rhs).to eq([p2, p2])
|
187
|
-
expect(p1.rhs).to eq(%w(a b))
|
188
|
-
expect(p2.rhs).to eq([p1, 'c', p1, 'd'])
|
189
|
-
end
|
190
|
-
|
191
|
-
it "should cope with the example from Salomon's book" do
|
192
|
-
input = 'abcdbcabcdbc'
|
193
|
-
instance = SequiturGrammar.new(input.chars)
|
194
|
-
|
195
|
-
# Expectations:
|
196
|
-
# S → CC
|
197
|
-
# A → bc
|
198
|
-
# C → aAdA
|
199
|
-
|
200
|
-
expect(instance.productions.size).to eq(3)
|
201
|
-
(p_a, p_c) = instance.productions[1..2]
|
202
|
-
expect(instance.start.rhs).to eq([p_c, p_c])
|
203
|
-
expect(p_a.rhs).to eq(%w(b c))
|
204
|
-
expect(p_c.rhs).to eq(['a', p_a, 'd', p_a])
|
205
|
-
end
|
206
|
-
|
207
|
-
it 'should cope with the "porridge" example from sequitur.info' do
|
208
|
-
# Another example from sequitur.info website
|
209
|
-
input = <<-SNIPPET
|
210
|
-
pease porridge hot,
|
211
|
-
pease porridge cold,
|
212
|
-
pease porridge in the pot,
|
213
|
-
nine days old.
|
214
|
-
|
215
|
-
some like it hot,
|
216
|
-
some like it cold,
|
217
|
-
some like it in the pot,
|
218
|
-
nine days old.
|
219
|
-
SNIPPET
|
220
|
-
# Expectations (sequitur.org)
|
221
|
-
# 0 → 1 2 3 4 3 5 ↵ 6 2 7 4 7 5
|
222
|
-
# 1 → p e a s 8 r r i d g 9 pease_porridge_
|
223
|
-
# 2 → h o t hot
|
224
|
-
# 3 → 10 1 ,↵pease_porridge_
|
225
|
-
# 4 → c 11 cold
|
226
|
-
# 5 → 12 _ t h 8 t 10 n 12 9 d a y s _ 11 . ↵
|
227
|
-
# in_the_pot,↵nine_days_old.↵
|
228
|
-
# 6 → s o m 9 l i k 9 i t _ some_like_it_
|
229
|
-
# 7 → 10 6 ,↵some_like_it_
|
230
|
-
# 8 → 9 p o e_po
|
231
|
-
# 9 → e _ e_
|
232
|
-
# 10 → , ↵ ,↵
|
233
|
-
# 11 → o l d old
|
234
|
-
# 12 → i n in
|
235
|
-
|
236
|
-
instance = SequiturGrammar.new(input.chars)
|
237
|
-
expect(instance.productions.size).to eq(13)
|
238
|
-
p0 = instance.start
|
239
|
-
expect(p0.rhs.size).to eq(13)
|
240
|
-
|
241
|
-
(p1, p2, p3, p4, p5, p6, p7, p8, p9) = instance.productions[1..9]
|
242
|
-
(p10, p11, p12) = instance.productions[10..12]
|
243
|
-
|
244
|
-
# Note: the productions aren't sorted the same way as
|
245
|
-
# the sequitur.info implementation.
|
246
|
-
p0_expectation = [
|
247
|
-
p2, p8, p3, p10, p3, p12, "\n",
|
248
|
-
p9, p8, p11, p10, p11, p12
|
249
|
-
]
|
250
|
-
expect(p0.rhs).to eq(p0_expectation)
|
251
|
-
expect(p1.rhs).to eq(['e', ' '])
|
252
|
-
expect(p2.rhs).to eq([%w(p e a s), p4, %w(r r i d g), p1].flatten) # R1
|
253
|
-
expect(p3.rhs).to eq([p5, p2])
|
254
|
-
expect(p4.rhs).to eq([p1, 'p', 'o'])
|
255
|
-
expect(p5.rhs).to eq([',', "\n"])
|
256
|
-
expect(p6.rhs).to eq(%w(i n))
|
257
|
-
expect(p7.rhs).to eq(%w(o l d))
|
258
|
-
expect(p8.rhs).to eq(%w(h o t))
|
259
|
-
p9_expectation = [%w(s o m), p1, %w(l i k), p1, 'i', 't', ' '].flatten
|
260
|
-
expect(p9.rhs).to eq(p9_expectation)
|
261
|
-
expect(p10.rhs).to eq(['c', p7])
|
262
|
-
expect(p11.rhs).to eq([p5, p9])
|
263
|
-
p12_expectation = [
|
264
|
-
p6, ' ', 't', 'h', p4, 't', p5, 'n', p6, p1,
|
265
|
-
%w(d a y s), ' ', p7, '.', "\n"
|
266
|
-
].flatten
|
267
|
-
expect(p12.rhs).to eq(p12_expectation)
|
268
|
-
end
|
269
|
-
|
270
|
-
it 'should work with a sequence of Ruby Symbols' do
|
271
|
-
input = 'abcabdabcabd'.chars.map(&:to_sym)
|
272
|
-
instance = SequiturGrammar.new(input.to_enum)
|
273
|
-
|
274
|
-
# Expectations:
|
275
|
-
# start : P2 P2.
|
276
|
-
# P1 : :a :b
|
277
|
-
# P2 : P1 :c P1 :d.
|
278
|
-
|
279
|
-
expect(instance.productions.size).to eq(3)
|
280
|
-
(p1, p2) = instance.productions[1..2]
|
281
|
-
expect(instance.start.rhs).to eq([p2, p2])
|
282
|
-
expect(p1.rhs).to eq([:a, :b])
|
283
|
-
expect(p2.rhs).to eq([p1, :c, p1, :d])
|
284
|
-
end
|
285
|
-
end # context
|
286
|
-
|
287
|
-
context 'Generating a text representation of itself:' do
|
288
|
-
it 'should generate a text representation when empty' do
|
289
|
-
instance = SequiturGrammar.new(empty_enum)
|
290
|
-
expectation = "#{instance.start.object_id} : ."
|
291
|
-
|
292
|
-
expect(instance.to_string).to eq(expectation)
|
293
|
-
end
|
294
|
-
|
295
|
-
it 'should generate a text representation of a simple production' do
|
296
|
-
instance = SequiturGrammar.new([:a].to_enum)
|
297
|
-
expectation = "#{instance.start.object_id} : a."
|
298
|
-
expect(instance.to_string).to eq(expectation)
|
299
|
-
end
|
300
|
-
end # context
|
301
|
-
end # describe
|
302
|
-
end # module
|
303
|
-
|
304
|
-
# End of file
|
1
|
+
require_relative '../spec_helper'
|
2
|
+
|
3
|
+
# Load the class under test
|
4
|
+
require_relative '../../lib/sequitur/sequitur_grammar'
|
5
|
+
|
6
|
+
module Sequitur # Re-open the module to get rid of qualified names
|
7
|
+
describe SequiturGrammar do
|
8
|
+
# Factory method. Returns an empty enumerator (
|
9
|
+
# i.e. without elements to iterate)
|
10
|
+
def empty_enum()
|
11
|
+
return [].to_enum
|
12
|
+
end
|
13
|
+
|
14
|
+
context 'Creation from an enumeration of tokens:' do
|
15
|
+
it 'could be created with an empty enumerator' do
|
16
|
+
expect { SequiturGrammar.new(empty_enum) }.not_to raise_error
|
17
|
+
|
18
|
+
# Creation
|
19
|
+
instance = SequiturGrammar.new(empty_enum)
|
20
|
+
|
21
|
+
# Initialization
|
22
|
+
expect(instance.productions.size).to eq(1)
|
23
|
+
expect(instance.start).to eq(instance.productions.first)
|
24
|
+
expect(instance.start).to be_empty
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'could be created with single token' do
|
28
|
+
# Creation
|
29
|
+
instance = SequiturGrammar.new([:a].to_enum)
|
30
|
+
|
31
|
+
# Initialization
|
32
|
+
expect(instance.productions.size).to eq(1)
|
33
|
+
expect(instance.start).to eq(instance.productions.first)
|
34
|
+
expect(instance.start.rhs).to eq([:a])
|
35
|
+
end
|
36
|
+
|
37
|
+
it 'could be created with multiple unique tokens' do
|
38
|
+
# Creation
|
39
|
+
instance = SequiturGrammar.new([:a, :b, :c, :d].to_enum)
|
40
|
+
|
41
|
+
# Initialization
|
42
|
+
expect(instance.productions.size).to eq(1)
|
43
|
+
expect(instance.start).to eq(instance.productions.first)
|
44
|
+
expect(instance.start.rhs).to eq([:a, :b, :c, :d])
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'could be created with a repeating digram' do
|
48
|
+
instance = SequiturGrammar.new([:a, :b, :a, :b].to_enum)
|
49
|
+
|
50
|
+
# Expectations:
|
51
|
+
# S : A A.
|
52
|
+
# A : a b.
|
53
|
+
expect(instance.productions.size).to eq(2)
|
54
|
+
p_a = instance.productions[1]
|
55
|
+
expect(p_a.rhs).to eq([:a, :b])
|
56
|
+
expect(instance.start.rhs).to eq([p_a, p_a])
|
57
|
+
end
|
58
|
+
|
59
|
+
it 'should enforce the utility rule' do
|
60
|
+
instance = SequiturGrammar.new([:a, :b, :c, :a, :b, :c].to_enum)
|
61
|
+
|
62
|
+
# Expectations without utility rule:
|
63
|
+
# S : B B.
|
64
|
+
# A : a b.
|
65
|
+
# B : A c.
|
66
|
+
|
67
|
+
# Expectations with utility rule:
|
68
|
+
# S : A A.
|
69
|
+
# A : a b c.
|
70
|
+
expect(instance.productions.size).to eq(2)
|
71
|
+
p_a = instance.productions.last
|
72
|
+
expect(p_a.rhs).to eq([:a, :b, :c])
|
73
|
+
expect(instance.start.rhs).to eq([p_a, p_a])
|
74
|
+
end
|
75
|
+
|
76
|
+
it 'should cope with a pattern that caused an exception' do
|
77
|
+
input = 'aaac' # This sequence raised an exception
|
78
|
+
|
79
|
+
# Creation
|
80
|
+
expect { SequiturGrammar.new(input.chars) }.not_to raise_error
|
81
|
+
end
|
82
|
+
|
83
|
+
|
84
|
+
it 'should cope with the example from presentation' do
|
85
|
+
input = 'bbebeebebebbebee'
|
86
|
+
|
87
|
+
# Creation
|
88
|
+
instance = SequiturGrammar.new(input.chars)
|
89
|
+
|
90
|
+
# Expectations:
|
91
|
+
# S: P3 P2 P3
|
92
|
+
# P1: b e
|
93
|
+
# P2: P1 P1
|
94
|
+
# P3: b P2 e
|
95
|
+
expect(instance.productions.size).to eq(4)
|
96
|
+
(p1, p2, p3) = instance.productions[1..3]
|
97
|
+
expect(instance.start.rhs).to eq([p3, p2, p3])
|
98
|
+
expect(p1.rhs).to eq(%w(b e))
|
99
|
+
expect(p2.rhs).to eq([p1, p1])
|
100
|
+
expect(p3.rhs).to eq(['b', p2, 'e'])
|
101
|
+
end
|
102
|
+
|
103
|
+
it 'should work with strings instead of single char input tokens' do
|
104
|
+
# Raw input is sequence of chars
|
105
|
+
raw_input = 'bbebeebebebbebee'
|
106
|
+
|
107
|
+
# Convert them into multichar strings
|
108
|
+
input = raw_input.chars.map do |ch|
|
109
|
+
'letter_' + ch
|
110
|
+
end
|
111
|
+
|
112
|
+
# Creation
|
113
|
+
instance = SequiturGrammar.new(input.to_enum)
|
114
|
+
|
115
|
+
# Expectations:
|
116
|
+
# S: P3 P2 P3
|
117
|
+
# P1: b e
|
118
|
+
# P2: P1 P1
|
119
|
+
# P3: b P2 e
|
120
|
+
expect(instance.productions.size).to eq(4)
|
121
|
+
(p1, p2, p3) = instance.productions[1..3]
|
122
|
+
expect(instance.start.rhs).to eq([p3, p2, p3])
|
123
|
+
expect(p1.rhs).to eq(%w(letter_b letter_e))
|
124
|
+
expect(p2.rhs).to eq([p1, p1])
|
125
|
+
expect(p3.rhs).to eq(['letter_b', p2, 'letter_e'])
|
126
|
+
end
|
127
|
+
|
128
|
+
it 'should work with Symbol instead of single char input tokens' do
|
129
|
+
# Raw input is sequence of single characters
|
130
|
+
raw_input = 'bbebeebebebbebee'
|
131
|
+
|
132
|
+
# Convert them into symbols
|
133
|
+
input = raw_input.chars.map(&:to_sym)
|
134
|
+
|
135
|
+
# Creation
|
136
|
+
instance = SequiturGrammar.new(input.to_enum)
|
137
|
+
|
138
|
+
# Expectations:
|
139
|
+
# S: P3 P2 P3
|
140
|
+
# P1: b e
|
141
|
+
# P2: P1 P1
|
142
|
+
# P3: b P2 e
|
143
|
+
expect(instance.productions.size).to eq(4)
|
144
|
+
(p1, p2, p3) = instance.productions[1..3]
|
145
|
+
expect(instance.start.rhs).to eq([p3, p2, p3])
|
146
|
+
expect(p1.rhs).to eq([:b, :e])
|
147
|
+
expect(p2.rhs).to eq([p1, p1])
|
148
|
+
expect(p3.rhs).to eq([:b, p2, :e])
|
149
|
+
end
|
150
|
+
|
151
|
+
|
152
|
+
it 'should work with integer values as input tokens' do
|
153
|
+
# Raw input is sequence of hex digits
|
154
|
+
raw_input = 'bbebeebebebbebee'
|
155
|
+
|
156
|
+
# Convert them into Fixnums
|
157
|
+
input = raw_input.chars.map { |ch| ch.to_i(16) }
|
158
|
+
|
159
|
+
# Creation
|
160
|
+
instance = SequiturGrammar.new(input.to_enum)
|
161
|
+
|
162
|
+
# Expectations:
|
163
|
+
# S: P3 P2 P3
|
164
|
+
# P1: b e
|
165
|
+
# P2: P1 P1
|
166
|
+
# P3: b P2 e
|
167
|
+
expect(instance.productions.size).to eq(4)
|
168
|
+
(p1, p2, p3) = instance.productions[1..3]
|
169
|
+
expect(instance.start.rhs).to eq([p3, p2, p3])
|
170
|
+
expect(p1.rhs).to eq([0xb, 0xe])
|
171
|
+
expect(p2.rhs).to eq([p1, p1])
|
172
|
+
expect(p3.rhs).to eq([0xb, p2, 0xe])
|
173
|
+
end
|
174
|
+
|
175
|
+
it 'should cope with the example from sequitur.info website' do
|
176
|
+
input = 'abcabdabcabd'
|
177
|
+
instance = SequiturGrammar.new(input.chars)
|
178
|
+
|
179
|
+
# Expectations:
|
180
|
+
# 0 → 2 2
|
181
|
+
# 1 → a b
|
182
|
+
# 2 → 1 c 1 d
|
183
|
+
|
184
|
+
expect(instance.productions.size).to eq(3)
|
185
|
+
(p1, p2) = instance.productions[1..2]
|
186
|
+
expect(instance.start.rhs).to eq([p2, p2])
|
187
|
+
expect(p1.rhs).to eq(%w(a b))
|
188
|
+
expect(p2.rhs).to eq([p1, 'c', p1, 'd'])
|
189
|
+
end
|
190
|
+
|
191
|
+
it "should cope with the example from Salomon's book" do
|
192
|
+
input = 'abcdbcabcdbc'
|
193
|
+
instance = SequiturGrammar.new(input.chars)
|
194
|
+
|
195
|
+
# Expectations:
|
196
|
+
# S → CC
|
197
|
+
# A → bc
|
198
|
+
# C → aAdA
|
199
|
+
|
200
|
+
expect(instance.productions.size).to eq(3)
|
201
|
+
(p_a, p_c) = instance.productions[1..2]
|
202
|
+
expect(instance.start.rhs).to eq([p_c, p_c])
|
203
|
+
expect(p_a.rhs).to eq(%w(b c))
|
204
|
+
expect(p_c.rhs).to eq(['a', p_a, 'd', p_a])
|
205
|
+
end
|
206
|
+
|
207
|
+
it 'should cope with the "porridge" example from sequitur.info' do
|
208
|
+
# Another example from sequitur.info website
|
209
|
+
input = <<-SNIPPET
|
210
|
+
pease porridge hot,
|
211
|
+
pease porridge cold,
|
212
|
+
pease porridge in the pot,
|
213
|
+
nine days old.
|
214
|
+
|
215
|
+
some like it hot,
|
216
|
+
some like it cold,
|
217
|
+
some like it in the pot,
|
218
|
+
nine days old.
|
219
|
+
SNIPPET
|
220
|
+
# Expectations (sequitur.org)
|
221
|
+
# 0 → 1 2 3 4 3 5 ↵ 6 2 7 4 7 5
|
222
|
+
# 1 → p e a s 8 r r i d g 9 pease_porridge_
|
223
|
+
# 2 → h o t hot
|
224
|
+
# 3 → 10 1 ,↵pease_porridge_
|
225
|
+
# 4 → c 11 cold
|
226
|
+
# 5 → 12 _ t h 8 t 10 n 12 9 d a y s _ 11 . ↵
|
227
|
+
# in_the_pot,↵nine_days_old.↵
|
228
|
+
# 6 → s o m 9 l i k 9 i t _ some_like_it_
|
229
|
+
# 7 → 10 6 ,↵some_like_it_
|
230
|
+
# 8 → 9 p o e_po
|
231
|
+
# 9 → e _ e_
|
232
|
+
# 10 → , ↵ ,↵
|
233
|
+
# 11 → o l d old
|
234
|
+
# 12 → i n in
|
235
|
+
|
236
|
+
instance = SequiturGrammar.new(input.chars)
|
237
|
+
expect(instance.productions.size).to eq(13)
|
238
|
+
p0 = instance.start
|
239
|
+
expect(p0.rhs.size).to eq(13)
|
240
|
+
|
241
|
+
(p1, p2, p3, p4, p5, p6, p7, p8, p9) = instance.productions[1..9]
|
242
|
+
(p10, p11, p12) = instance.productions[10..12]
|
243
|
+
|
244
|
+
# Note: the productions aren't sorted the same way as
|
245
|
+
# the sequitur.info implementation.
|
246
|
+
p0_expectation = [
|
247
|
+
p2, p8, p3, p10, p3, p12, "\n",
|
248
|
+
p9, p8, p11, p10, p11, p12
|
249
|
+
]
|
250
|
+
expect(p0.rhs).to eq(p0_expectation) # Rule 0 above
|
251
|
+
expect(p1.rhs).to eq(['e', ' ']) # Rule 9 above
|
252
|
+
expect(p2.rhs).to eq([%w(p e a s), p4, %w(r r i d g), p1].flatten) # R1
|
253
|
+
expect(p3.rhs).to eq([p5, p2]) # Rule 3 above
|
254
|
+
expect(p4.rhs).to eq([p1, 'p', 'o']) # Rule 8 above
|
255
|
+
expect(p5.rhs).to eq([',', "\n"]) # Rule 10 above
|
256
|
+
expect(p6.rhs).to eq(%w(i n)) # Rule 12 above
|
257
|
+
expect(p7.rhs).to eq(%w(o l d)) # Rule 11 above
|
258
|
+
expect(p8.rhs).to eq(%w(h o t)) # Rule 2 above
|
259
|
+
p9_expectation = [%w(s o m), p1, %w(l i k), p1, 'i', 't', ' '].flatten
|
260
|
+
expect(p9.rhs).to eq(p9_expectation) # Rule 6 above
|
261
|
+
expect(p10.rhs).to eq(['c', p7]) # Rule 4 above
|
262
|
+
expect(p11.rhs).to eq([p5, p9]) # Rule 7 above
|
263
|
+
p12_expectation = [
|
264
|
+
p6, ' ', 't', 'h', p4, 't', p5, 'n', p6, p1,
|
265
|
+
%w(d a y s), ' ', p7, '.', "\n"
|
266
|
+
].flatten
|
267
|
+
expect(p12.rhs).to eq(p12_expectation) # Rule 5 above
|
268
|
+
end
|
269
|
+
|
270
|
+
it 'should work with a sequence of Ruby Symbols' do
|
271
|
+
input = 'abcabdabcabd'.chars.map(&:to_sym)
|
272
|
+
instance = SequiturGrammar.new(input.to_enum)
|
273
|
+
|
274
|
+
# Expectations:
|
275
|
+
# start : P2 P2.
|
276
|
+
# P1 : :a :b
|
277
|
+
# P2 : P1 :c P1 :d.
|
278
|
+
|
279
|
+
expect(instance.productions.size).to eq(3)
|
280
|
+
(p1, p2) = instance.productions[1..2]
|
281
|
+
expect(instance.start.rhs).to eq([p2, p2])
|
282
|
+
expect(p1.rhs).to eq([:a, :b])
|
283
|
+
expect(p2.rhs).to eq([p1, :c, p1, :d])
|
284
|
+
end
|
285
|
+
end # context
|
286
|
+
|
287
|
+
context 'Generating a text representation of itself:' do
|
288
|
+
it 'should generate a text representation when empty' do
|
289
|
+
instance = SequiturGrammar.new(empty_enum)
|
290
|
+
expectation = "#{instance.start.object_id} : ."
|
291
|
+
|
292
|
+
expect(instance.to_string).to eq(expectation)
|
293
|
+
end
|
294
|
+
|
295
|
+
it 'should generate a text representation of a simple production' do
|
296
|
+
instance = SequiturGrammar.new([:a].to_enum)
|
297
|
+
expectation = "#{instance.start.object_id} : a."
|
298
|
+
expect(instance.to_string).to eq(expectation)
|
299
|
+
end
|
300
|
+
end # context
|
301
|
+
end # describe
|
302
|
+
end # module
|
303
|
+
|
304
|
+
# End of file
|
metadata
CHANGED
@@ -1,86 +1,104 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sequitur
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.16
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dimitri Geshef
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-09-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rake
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 0.
|
19
|
+
version: 10.0.0
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 10.0.0
|
20
23
|
type: :development
|
21
24
|
prerelease: false
|
22
25
|
version_requirements: !ruby/object:Gem::Requirement
|
23
26
|
requirements:
|
24
|
-
- -
|
27
|
+
- - "~>"
|
25
28
|
- !ruby/object:Gem::Version
|
26
|
-
version: 0.
|
29
|
+
version: 10.0.0
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 10.0.0
|
27
33
|
- !ruby/object:Gem::Dependency
|
28
34
|
name: rspec
|
29
35
|
requirement: !ruby/object:Gem::Requirement
|
30
36
|
requirements:
|
31
|
-
- -
|
37
|
+
- - "~>"
|
32
38
|
- !ruby/object:Gem::Version
|
33
|
-
version:
|
39
|
+
version: 2.1.0
|
40
|
+
- - ">="
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: 2.1.0
|
34
43
|
type: :development
|
35
44
|
prerelease: false
|
36
45
|
version_requirements: !ruby/object:Gem::Requirement
|
37
46
|
requirements:
|
38
|
-
- -
|
47
|
+
- - "~>"
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: 2.1.0
|
50
|
+
- - ">="
|
39
51
|
- !ruby/object:Gem::Version
|
40
|
-
version:
|
52
|
+
version: 2.1.0
|
41
53
|
- !ruby/object:Gem::Dependency
|
42
54
|
name: simplecov
|
43
55
|
requirement: !ruby/object:Gem::Requirement
|
44
56
|
requirements:
|
45
|
-
- -
|
57
|
+
- - ">="
|
46
58
|
- !ruby/object:Gem::Version
|
47
|
-
version: 0.
|
59
|
+
version: 0.8.0
|
48
60
|
type: :development
|
49
61
|
prerelease: false
|
50
62
|
version_requirements: !ruby/object:Gem::Requirement
|
51
63
|
requirements:
|
52
|
-
- -
|
64
|
+
- - ">="
|
53
65
|
- !ruby/object:Gem::Version
|
54
|
-
version: 0.
|
66
|
+
version: 0.8.0
|
55
67
|
- !ruby/object:Gem::Dependency
|
56
68
|
name: coveralls
|
57
69
|
requirement: !ruby/object:Gem::Requirement
|
58
70
|
requirements:
|
59
|
-
- -
|
71
|
+
- - ">="
|
60
72
|
- !ruby/object:Gem::Version
|
61
73
|
version: 0.7.0
|
62
74
|
type: :development
|
63
75
|
prerelease: false
|
64
76
|
version_requirements: !ruby/object:Gem::Requirement
|
65
77
|
requirements:
|
66
|
-
- -
|
78
|
+
- - ">="
|
67
79
|
- !ruby/object:Gem::Version
|
68
80
|
version: 0.7.0
|
69
81
|
- !ruby/object:Gem::Dependency
|
70
82
|
name: rubygems
|
71
83
|
requirement: !ruby/object:Gem::Requirement
|
72
84
|
requirements:
|
73
|
-
- -
|
85
|
+
- - "~>"
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '2.0'
|
88
|
+
- - ">="
|
74
89
|
- !ruby/object:Gem::Version
|
75
90
|
version: 2.0.0
|
76
91
|
type: :development
|
77
92
|
prerelease: false
|
78
93
|
version_requirements: !ruby/object:Gem::Requirement
|
79
94
|
requirements:
|
80
|
-
- -
|
95
|
+
- - "~>"
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '2.0'
|
98
|
+
- - ">="
|
81
99
|
- !ruby/object:Gem::Version
|
82
100
|
version: 2.0.0
|
83
|
-
description:
|
101
|
+
description: "Ruby implementation of the Sequitur algorithm. This algorithm automatically
|
84
102
|
\nfinds repetitions and hierarchical structures in a given sequence of input \ntokens.
|
85
103
|
It encodes the input into a context-free grammar. \nThe Sequitur algorithm can be
|
86
104
|
used to \na) compress a sequence of items,\nb) discover patterns in an sequence,
|
@@ -91,18 +109,23 @@ extensions: []
|
|
91
109
|
extra_rdoc_files:
|
92
110
|
- README.md
|
93
111
|
files:
|
94
|
-
- .
|
95
|
-
- .
|
96
|
-
- .ruby-gemset
|
97
|
-
- .ruby-version
|
98
|
-
- .simplecov
|
99
|
-
- .travis.yml
|
100
|
-
- .yardopts
|
101
|
-
- Gemfile
|
102
|
-
- Rakefile
|
112
|
+
- ".rspec"
|
113
|
+
- ".rubocop.yml"
|
114
|
+
- ".ruby-gemset"
|
115
|
+
- ".ruby-version"
|
116
|
+
- ".simplecov"
|
117
|
+
- ".travis.yml"
|
118
|
+
- ".yardopts"
|
103
119
|
- CHANGELOG.md
|
120
|
+
- Gemfile
|
104
121
|
- LICENSE.txt
|
105
122
|
- README.md
|
123
|
+
- Rakefile
|
124
|
+
- examples/integer_sample.rb
|
125
|
+
- examples/porridge.rb
|
126
|
+
- examples/simple_case.rb
|
127
|
+
- examples/symbol_sample.rb
|
128
|
+
- examples/word_sample.rb
|
106
129
|
- lib/sequitur.rb
|
107
130
|
- lib/sequitur/constants.rb
|
108
131
|
- lib/sequitur/digram.rb
|
@@ -125,39 +148,31 @@ files:
|
|
125
148
|
- spec/sequitur/sequitur_grammar_spec.rb
|
126
149
|
- spec/sequitur/symbol_sequence_spec.rb
|
127
150
|
- spec/spec_helper.rb
|
128
|
-
- examples/integer_sample.rb
|
129
|
-
- examples/porridge.rb
|
130
|
-
- examples/simple_case.rb
|
131
|
-
- examples/symbol_sample.rb
|
132
|
-
- examples/word_sample.rb
|
133
151
|
homepage: https://github.com/famished-tiger/Sequitur
|
134
152
|
licenses:
|
135
153
|
- MIT
|
136
154
|
metadata: {}
|
137
|
-
post_install_message:
|
138
|
-
|
155
|
+
post_install_message: |
|
156
|
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
139
157
|
Thank you for installing Sequitur...
|
140
|
-
|
141
158
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
142
|
-
|
143
|
-
'
|
144
159
|
rdoc_options:
|
145
160
|
- --charset=UTF-8 --exclude="examples|features|spec"
|
146
161
|
require_paths:
|
147
162
|
- lib
|
148
163
|
required_ruby_version: !ruby/object:Gem::Requirement
|
149
164
|
requirements:
|
150
|
-
- -
|
165
|
+
- - ">="
|
151
166
|
- !ruby/object:Gem::Version
|
152
167
|
version: 1.9.1
|
153
168
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
154
169
|
requirements:
|
155
|
-
- -
|
170
|
+
- - ">="
|
156
171
|
- !ruby/object:Gem::Version
|
157
172
|
version: '0'
|
158
173
|
requirements: []
|
159
174
|
rubyforge_project:
|
160
|
-
rubygems_version: 2.
|
175
|
+
rubygems_version: 2.4.5.1
|
161
176
|
signing_key:
|
162
177
|
specification_version: 4
|
163
178
|
summary: Ruby implementation of the Sequitur algorithm
|