regexp_parser 1.8.0 → 2.0.2
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +70 -0
- data/Gemfile +1 -0
- data/README.md +12 -11
- data/Rakefile +2 -2
- data/lib/regexp_parser/expression.rb +10 -19
- data/lib/regexp_parser/expression/classes/free_space.rb +1 -1
- data/lib/regexp_parser/expression/classes/group.rb +22 -2
- data/lib/regexp_parser/expression/classes/root.rb +4 -16
- data/lib/regexp_parser/expression/methods/match_length.rb +2 -2
- data/lib/regexp_parser/expression/methods/traverse.rb +2 -2
- data/lib/regexp_parser/expression/quantifier.rb +9 -0
- data/lib/regexp_parser/expression/sequence.rb +0 -10
- data/lib/regexp_parser/lexer.rb +2 -2
- data/lib/regexp_parser/parser.rb +27 -0
- data/lib/regexp_parser/scanner.rb +1248 -1258
- data/lib/regexp_parser/scanner/char_type.rl +11 -11
- data/lib/regexp_parser/scanner/property.rl +2 -2
- data/lib/regexp_parser/scanner/scanner.rl +175 -181
- data/lib/regexp_parser/syntax/any.rb +2 -2
- data/lib/regexp_parser/syntax/version_lookup.rb +2 -2
- data/lib/regexp_parser/version.rb +1 -1
- data/regexp_parser.gemspec +1 -1
- data/spec/expression/base_spec.rb +10 -0
- data/spec/expression/subexpression_spec.rb +1 -1
- data/spec/expression/to_s_spec.rb +39 -31
- data/spec/lexer/literals_spec.rb +24 -49
- data/spec/parser/errors_spec.rb +1 -1
- data/spec/parser/escapes_spec.rb +1 -1
- data/spec/parser/free_space_spec.rb +4 -25
- data/spec/parser/quantifiers_spec.rb +16 -0
- data/spec/parser/set/ranges_spec.rb +3 -3
- data/spec/scanner/escapes_spec.rb +7 -0
- data/spec/scanner/free_space_spec.rb +32 -0
- data/spec/scanner/groups_spec.rb +10 -1
- data/spec/scanner/literals_spec.rb +28 -38
- data/spec/scanner/quantifiers_spec.rb +18 -13
- data/spec/scanner/sets_spec.rb +8 -2
- data/spec/spec_helper.rb +1 -0
- metadata +57 -61
- data/spec/expression/root_spec.rb +0 -9
- data/spec/expression/sequence_spec.rb +0 -9
data/spec/scanner/groups_spec.rb
CHANGED
@@ -5,11 +5,20 @@ RSpec.describe('Group scanning') do
|
|
5
5
|
include_examples 'scan', '(?>abc)', 0 => [:group, :atomic, '(?>', 0, 3]
|
6
6
|
include_examples 'scan', '(abc)', 0 => [:group, :capture, '(', 0, 1]
|
7
7
|
|
8
|
+
# Named groups
|
9
|
+
# only names that start with a hyphen or digit (ascii or other) are invalid
|
8
10
|
include_examples 'scan', '(?<name>abc)', 0 => [:group, :named_ab, '(?<name>', 0, 8]
|
9
11
|
include_examples 'scan', "(?'name'abc)", 0 => [:group, :named_sq, "(?'name'", 0, 8]
|
10
|
-
|
11
12
|
include_examples 'scan', '(?<name_1>abc)', 0 => [:group, :named_ab, '(?<name_1>', 0,10]
|
12
13
|
include_examples 'scan', "(?'name_1'abc)", 0 => [:group, :named_sq, "(?'name_1'", 0,10]
|
14
|
+
include_examples 'scan', '(?<name-1>abc)', 0 => [:group, :named_ab, '(?<name-1>', 0,10]
|
15
|
+
include_examples 'scan', "(?'name-1'abc)", 0 => [:group, :named_sq, "(?'name-1'", 0,10]
|
16
|
+
include_examples 'scan', "(?<name'1>abc)", 0 => [:group, :named_ab, "(?<name'1>", 0,10]
|
17
|
+
include_examples 'scan', "(?'name>1'abc)", 0 => [:group, :named_sq, "(?'name>1'", 0,10]
|
18
|
+
include_examples 'scan', '(?<üüuuüü>abc)', 0 => [:group, :named_ab, '(?<üüuuüü>', 0,10]
|
19
|
+
include_examples 'scan', "(?'üüuuüü'abc)", 0 => [:group, :named_sq, "(?'üüuuüü'", 0,10]
|
20
|
+
include_examples 'scan', "(?<😋1234😋>abc)", 0 => [:group, :named_ab, "(?<😋1234😋>", 0,10]
|
21
|
+
include_examples 'scan', "(?'😋1234😋'abc)", 0 => [:group, :named_sq, "(?'😋1234😋'", 0,10]
|
13
22
|
|
14
23
|
include_examples 'scan', '(?:abc)', 0 => [:group, :passive, '(?:', 0, 3]
|
15
24
|
include_examples 'scan', '(?:)', 0 => [:group, :passive, '(?:', 0, 3]
|
@@ -2,48 +2,38 @@ require 'spec_helper'
|
|
2
2
|
|
3
3
|
RSpec.describe('UTF8 scanning') do
|
4
4
|
# ascii, single byte characters
|
5
|
-
include_examples 'scan', 'a',
|
5
|
+
include_examples 'scan', 'a',
|
6
|
+
0 => [:literal, :literal, 'a', 0, 1]
|
6
7
|
|
7
|
-
include_examples 'scan', 'ab+',
|
8
|
-
|
8
|
+
include_examples 'scan', 'ab+',
|
9
|
+
0 => [:literal, :literal, 'ab', 0, 2],
|
10
|
+
1 => [:quantifier, :one_or_more, '+', 2, 3]
|
9
11
|
|
10
|
-
# 2 byte wide characters
|
11
|
-
include_examples 'scan', '
|
12
|
-
|
13
|
-
include_examples 'scan', 'aاbبت?', 0 => [:literal, :literal, 'aاbبت', 0, 8]
|
14
|
-
include_examples 'scan', 'aاbبت?', 1 => [:quantifier, :zero_or_one, '?', 8, 9]
|
15
|
-
|
16
|
-
include_examples 'scan', 'aا?bبcت+', 0 => [:literal, :literal, 'aا', 0, 3]
|
17
|
-
include_examples 'scan', 'aا?bبcت+', 1 => [:quantifier, :zero_or_one, '?', 3, 4]
|
18
|
-
include_examples 'scan', 'aا?bبcت+', 2 => [:literal, :literal, 'bبcت', 4, 10]
|
19
|
-
include_examples 'scan', 'aا?bبcت+', 3 => [:quantifier, :one_or_more, '+', 10, 11]
|
20
|
-
|
21
|
-
include_examples 'scan', 'a(اbب+)cت?', 0 => [:literal, :literal, 'a', 0, 1]
|
22
|
-
include_examples 'scan', 'a(اbب+)cت?', 1 => [:group, :capture, '(', 1, 2]
|
23
|
-
include_examples 'scan', 'a(اbب+)cت?', 2 => [:literal, :literal, 'اbب', 2, 7]
|
24
|
-
include_examples 'scan', 'a(اbب+)cت?', 3 => [:quantifier, :one_or_more, '+', 7, 8]
|
25
|
-
include_examples 'scan', 'a(اbب+)cت?', 4 => [:group, :close, ')', 8, 9]
|
26
|
-
include_examples 'scan', 'a(اbب+)cت?', 5 => [:literal, :literal, 'cت', 9, 12]
|
27
|
-
include_examples 'scan', 'a(اbب+)cت?', 6 => [:quantifier, :zero_or_one, '?', 12, 13]
|
12
|
+
# 2 byte wide characters
|
13
|
+
include_examples 'scan', 'äöü',
|
14
|
+
0 => [:literal, :literal, 'äöü', 0, 3]
|
28
15
|
|
29
16
|
# 3 byte wide characters, Japanese
|
30
|
-
include_examples 'scan', 'ab?れます+cd',
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
17
|
+
include_examples 'scan', 'ab?れます+cd',
|
18
|
+
0 => [:literal, :literal, 'ab', 0, 2],
|
19
|
+
1 => [:quantifier, :zero_or_one, '?', 2, 3],
|
20
|
+
2 => [:literal, :literal, 'れます', 3, 6],
|
21
|
+
3 => [:quantifier, :one_or_more, '+', 6, 7],
|
22
|
+
4 => [:literal, :literal, 'cd', 7, 9]
|
35
23
|
|
36
24
|
# 4 byte wide characters, Osmanya
|
37
|
-
include_examples 'scan', '𐒀𐒁?𐒂ab+𐒃',
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
include_examples 'scan', 'mu𝄞?si*𝄫c+',
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
25
|
+
include_examples 'scan', '𐒀𐒁?𐒂ab+𐒃',
|
26
|
+
0 => [:literal, :literal, '𐒀𐒁', 0, 2],
|
27
|
+
1 => [:quantifier, :zero_or_one, '?', 2, 3],
|
28
|
+
2 => [:literal, :literal, '𐒂ab', 3, 6],
|
29
|
+
3 => [:quantifier, :one_or_more, '+', 6, 7],
|
30
|
+
4 => [:literal, :literal, '𐒃', 7, 8]
|
31
|
+
|
32
|
+
include_examples 'scan', 'mu𝄞?si*𝄫c+',
|
33
|
+
0 => [:literal, :literal, 'mu𝄞', 0, 3],
|
34
|
+
1 => [:quantifier, :zero_or_one, '?', 3, 4],
|
35
|
+
2 => [:literal, :literal, 'si', 4, 6],
|
36
|
+
3 => [:quantifier, :zero_or_more, '*', 6, 7],
|
37
|
+
4 => [:literal, :literal, '𝄫c', 7, 9],
|
38
|
+
5 => [:quantifier, :one_or_more, '+', 9, 10]
|
49
39
|
end
|
@@ -1,20 +1,25 @@
|
|
1
1
|
require 'spec_helper'
|
2
2
|
|
3
3
|
RSpec.describe('Quantifier scanning') do
|
4
|
-
include_examples 'scan', 'a?',
|
5
|
-
include_examples 'scan', 'a??',
|
6
|
-
include_examples 'scan', 'a?+',
|
4
|
+
include_examples 'scan', 'a?', 1 => [:quantifier, :zero_or_one, '?', 1, 2]
|
5
|
+
include_examples 'scan', 'a??', 1 => [:quantifier, :zero_or_one_reluctant, '??', 1, 3]
|
6
|
+
include_examples 'scan', 'a?+', 1 => [:quantifier, :zero_or_one_possessive, '?+', 1, 3]
|
7
7
|
|
8
|
-
include_examples 'scan', 'a*',
|
9
|
-
include_examples 'scan', 'a*?',
|
10
|
-
include_examples 'scan', 'a*+',
|
8
|
+
include_examples 'scan', 'a*', 1 => [:quantifier, :zero_or_more, '*', 1, 2]
|
9
|
+
include_examples 'scan', 'a*?', 1 => [:quantifier, :zero_or_more_reluctant, '*?', 1, 3]
|
10
|
+
include_examples 'scan', 'a*+', 1 => [:quantifier, :zero_or_more_possessive, '*+', 1, 3]
|
11
11
|
|
12
|
-
include_examples 'scan', 'a+',
|
13
|
-
include_examples 'scan', 'a+?',
|
14
|
-
include_examples 'scan', 'a++',
|
12
|
+
include_examples 'scan', 'a+', 1 => [:quantifier, :one_or_more, '+', 1, 2]
|
13
|
+
include_examples 'scan', 'a+?', 1 => [:quantifier, :one_or_more_reluctant, '+?', 1, 3]
|
14
|
+
include_examples 'scan', 'a++', 1 => [:quantifier, :one_or_more_possessive, '++', 1, 3]
|
15
15
|
|
16
|
-
include_examples 'scan', 'a{2}',
|
17
|
-
include_examples 'scan', 'a{2,}',
|
18
|
-
include_examples 'scan', 'a{,2}',
|
19
|
-
include_examples 'scan', 'a{2,4}',
|
16
|
+
include_examples 'scan', 'a{2}', 1 => [:quantifier, :interval, '{2}', 1, 4]
|
17
|
+
include_examples 'scan', 'a{2,}', 1 => [:quantifier, :interval, '{2,}', 1, 5]
|
18
|
+
include_examples 'scan', 'a{,2}', 1 => [:quantifier, :interval, '{,2}', 1, 5]
|
19
|
+
include_examples 'scan', 'a{2,4}', 1 => [:quantifier, :interval, '{2,4}', 1, 6]
|
20
|
+
|
21
|
+
# special case: chained quantifiers
|
22
|
+
include_examples 'scan', 'a+{2}{3}', 1 => [:quantifier, :one_or_more, '+', 1, 2]
|
23
|
+
include_examples 'scan', 'a+{2}{3}', 2 => [:quantifier, :interval, '{2}', 2, 5]
|
24
|
+
include_examples 'scan', 'a+{2}{3}', 3 => [:quantifier, :interval, '{3}', 5, 8]
|
20
25
|
end
|
data/spec/scanner/sets_spec.rb
CHANGED
@@ -18,8 +18,6 @@ RSpec.describe('Set scanning') do
|
|
18
18
|
include_examples 'scan', /[<]/, 1 => [:literal, :literal, '<', 1, 2]
|
19
19
|
include_examples 'scan', /[>]/, 1 => [:literal, :literal, '>', 1, 2]
|
20
20
|
|
21
|
-
include_examples 'scan', /[äöü]/, 2 => [:literal, :literal, 'ö', 3, 5]
|
22
|
-
|
23
21
|
include_examples 'scan', /[\x20]/, 1 => [:escape, :hex, '\x20', 1, 5]
|
24
22
|
|
25
23
|
include_examples 'scan', '[\.]', 1 => [:escape, :dot, '\.', 1, 3]
|
@@ -90,6 +88,14 @@ RSpec.describe('Set scanning') do
|
|
90
88
|
8 => [:set, :range, '-', 9, 10],
|
91
89
|
10=> [:set, :close, ']', 11, 12]
|
92
90
|
|
91
|
+
# multi-byte characters should not affect indices
|
92
|
+
include_examples 'scan', /[れます]/,
|
93
|
+
0 => [:set, :open, '[', 0, 1],
|
94
|
+
1 => [:literal, :literal, 'れ', 1, 2],
|
95
|
+
2 => [:literal, :literal, 'ま', 2, 3],
|
96
|
+
3 => [:literal, :literal, 'す', 3, 4],
|
97
|
+
4 => [:set, :close, ']', 4, 5]
|
98
|
+
|
93
99
|
specify('set literal encoding') do
|
94
100
|
text = RS.scan('[a]')[1][2].to_s
|
95
101
|
expect(text).to eq 'a'
|
data/spec/spec_helper.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: regexp_parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 2.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ammar Ali
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-12-25 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
|
14
14
|
email:
|
@@ -102,8 +102,6 @@ files:
|
|
102
102
|
- spec/expression/methods/tests_spec.rb
|
103
103
|
- spec/expression/methods/traverse_spec.rb
|
104
104
|
- spec/expression/options_spec.rb
|
105
|
-
- spec/expression/root_spec.rb
|
106
|
-
- spec/expression/sequence_spec.rb
|
107
105
|
- spec/expression/subexpression_spec.rb
|
108
106
|
- spec/expression/to_h_spec.rb
|
109
107
|
- spec/expression/to_s_spec.rb
|
@@ -178,86 +176,84 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
178
176
|
requirements:
|
179
177
|
- - ">="
|
180
178
|
- !ruby/object:Gem::Version
|
181
|
-
version:
|
179
|
+
version: 2.0.0
|
182
180
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
183
181
|
requirements:
|
184
182
|
- - ">="
|
185
183
|
- !ruby/object:Gem::Version
|
186
184
|
version: '0'
|
187
185
|
requirements: []
|
188
|
-
rubygems_version: 3.
|
186
|
+
rubygems_version: 3.2.0
|
189
187
|
signing_key:
|
190
188
|
specification_version: 4
|
191
189
|
summary: Scanner, lexer, parser for ruby's regular expressions
|
192
190
|
test_files:
|
193
|
-
- spec/
|
194
|
-
- spec/
|
195
|
-
- spec/
|
196
|
-
- spec/
|
191
|
+
- spec/expression/base_spec.rb
|
192
|
+
- spec/expression/clone_spec.rb
|
193
|
+
- spec/expression/conditional_spec.rb
|
194
|
+
- spec/expression/free_space_spec.rb
|
195
|
+
- spec/expression/methods/match_length_spec.rb
|
196
|
+
- spec/expression/methods/match_spec.rb
|
197
|
+
- spec/expression/methods/strfregexp_spec.rb
|
198
|
+
- spec/expression/methods/tests_spec.rb
|
199
|
+
- spec/expression/methods/traverse_spec.rb
|
200
|
+
- spec/expression/options_spec.rb
|
201
|
+
- spec/expression/subexpression_spec.rb
|
202
|
+
- spec/expression/to_h_spec.rb
|
203
|
+
- spec/expression/to_s_spec.rb
|
197
204
|
- spec/lexer/all_spec.rb
|
198
205
|
- spec/lexer/conditionals_spec.rb
|
199
|
-
- spec/lexer/nesting_spec.rb
|
200
206
|
- spec/lexer/delimiters_spec.rb
|
201
|
-
- spec/lexer/
|
207
|
+
- spec/lexer/escapes_spec.rb
|
208
|
+
- spec/lexer/keep_spec.rb
|
202
209
|
- spec/lexer/literals_spec.rb
|
210
|
+
- spec/lexer/nesting_spec.rb
|
211
|
+
- spec/lexer/refcalls_spec.rb
|
212
|
+
- spec/parser/all_spec.rb
|
213
|
+
- spec/parser/alternation_spec.rb
|
214
|
+
- spec/parser/anchors_spec.rb
|
215
|
+
- spec/parser/conditionals_spec.rb
|
216
|
+
- spec/parser/errors_spec.rb
|
203
217
|
- spec/parser/escapes_spec.rb
|
204
|
-
- spec/parser/properties_spec.rb
|
205
|
-
- spec/parser/sets_spec.rb
|
206
218
|
- spec/parser/free_space_spec.rb
|
219
|
+
- spec/parser/groups_spec.rb
|
207
220
|
- spec/parser/keep_spec.rb
|
208
221
|
- spec/parser/options_spec.rb
|
209
|
-
- spec/parser/all_spec.rb
|
210
|
-
- spec/parser/conditionals_spec.rb
|
211
|
-
- spec/parser/types_spec.rb
|
212
|
-
- spec/parser/anchors_spec.rb
|
213
|
-
- spec/parser/alternation_spec.rb
|
214
222
|
- spec/parser/posix_classes_spec.rb
|
215
|
-
- spec/parser/
|
216
|
-
- spec/parser/set/intersections_spec.rb
|
217
|
-
- spec/parser/errors_spec.rb
|
218
|
-
- spec/parser/refcalls_spec.rb
|
219
|
-
- spec/parser/groups_spec.rb
|
223
|
+
- spec/parser/properties_spec.rb
|
220
224
|
- spec/parser/quantifiers_spec.rb
|
221
|
-
- spec/
|
222
|
-
- spec/
|
223
|
-
- spec/
|
224
|
-
- spec/
|
225
|
-
- spec/
|
226
|
-
- spec/expression/methods/match_length_spec.rb
|
227
|
-
- spec/expression/methods/traverse_spec.rb
|
228
|
-
- spec/expression/methods/strfregexp_spec.rb
|
229
|
-
- spec/expression/methods/tests_spec.rb
|
230
|
-
- spec/expression/free_space_spec.rb
|
231
|
-
- spec/expression/options_spec.rb
|
232
|
-
- spec/expression/to_s_spec.rb
|
233
|
-
- spec/expression/root_spec.rb
|
234
|
-
- spec/expression/sequence_spec.rb
|
235
|
-
- spec/expression/clone_spec.rb
|
236
|
-
- spec/expression/to_h_spec.rb
|
237
|
-
- spec/expression/conditional_spec.rb
|
238
|
-
- spec/expression/base_spec.rb
|
239
|
-
- spec/syntax/syntax_spec.rb
|
240
|
-
- spec/syntax/syntax_token_map_spec.rb
|
241
|
-
- spec/syntax/versions/1.9.3_spec.rb
|
242
|
-
- spec/syntax/versions/2.2.0_spec.rb
|
243
|
-
- spec/syntax/versions/1.9.1_spec.rb
|
244
|
-
- spec/syntax/versions/2.0.0_spec.rb
|
245
|
-
- spec/syntax/versions/1.8.6_spec.rb
|
246
|
-
- spec/syntax/versions/aliases_spec.rb
|
247
|
-
- spec/scanner/escapes_spec.rb
|
248
|
-
- spec/scanner/properties_spec.rb
|
249
|
-
- spec/scanner/sets_spec.rb
|
250
|
-
- spec/scanner/free_space_spec.rb
|
251
|
-
- spec/scanner/keep_spec.rb
|
252
|
-
- spec/scanner/options_spec.rb
|
225
|
+
- spec/parser/refcalls_spec.rb
|
226
|
+
- spec/parser/set/intersections_spec.rb
|
227
|
+
- spec/parser/set/ranges_spec.rb
|
228
|
+
- spec/parser/sets_spec.rb
|
229
|
+
- spec/parser/types_spec.rb
|
253
230
|
- spec/scanner/all_spec.rb
|
254
|
-
- spec/scanner/conditionals_spec.rb
|
255
|
-
- spec/scanner/types_spec.rb
|
256
231
|
- spec/scanner/anchors_spec.rb
|
257
|
-
- spec/scanner/
|
258
|
-
- spec/scanner/errors_spec.rb
|
232
|
+
- spec/scanner/conditionals_spec.rb
|
259
233
|
- spec/scanner/delimiters_spec.rb
|
260
|
-
- spec/scanner/
|
234
|
+
- spec/scanner/errors_spec.rb
|
235
|
+
- spec/scanner/escapes_spec.rb
|
236
|
+
- spec/scanner/free_space_spec.rb
|
261
237
|
- spec/scanner/groups_spec.rb
|
238
|
+
- spec/scanner/keep_spec.rb
|
262
239
|
- spec/scanner/literals_spec.rb
|
240
|
+
- spec/scanner/meta_spec.rb
|
241
|
+
- spec/scanner/options_spec.rb
|
242
|
+
- spec/scanner/properties_spec.rb
|
263
243
|
- spec/scanner/quantifiers_spec.rb
|
244
|
+
- spec/scanner/refcalls_spec.rb
|
245
|
+
- spec/scanner/sets_spec.rb
|
246
|
+
- spec/scanner/types_spec.rb
|
247
|
+
- spec/spec_helper.rb
|
248
|
+
- spec/support/runner.rb
|
249
|
+
- spec/support/shared_examples.rb
|
250
|
+
- spec/support/warning_extractor.rb
|
251
|
+
- spec/syntax/syntax_spec.rb
|
252
|
+
- spec/syntax/syntax_token_map_spec.rb
|
253
|
+
- spec/syntax/versions/1.8.6_spec.rb
|
254
|
+
- spec/syntax/versions/1.9.1_spec.rb
|
255
|
+
- spec/syntax/versions/1.9.3_spec.rb
|
256
|
+
- spec/syntax/versions/2.0.0_spec.rb
|
257
|
+
- spec/syntax/versions/2.2.0_spec.rb
|
258
|
+
- spec/syntax/versions/aliases_spec.rb
|
259
|
+
- spec/token/token_spec.rb
|