regexp_parser 1.7.1 → 2.1.1
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +138 -0
- data/Gemfile +6 -1
- data/README.md +23 -11
- data/Rakefile +8 -8
- data/lib/regexp_parser/error.rb +4 -0
- data/lib/regexp_parser/expression.rb +13 -21
- data/lib/regexp_parser/expression/classes/backref.rb +5 -0
- data/lib/regexp_parser/expression/classes/conditional.rb +11 -1
- data/lib/regexp_parser/expression/classes/free_space.rb +2 -2
- data/lib/regexp_parser/expression/classes/group.rb +28 -3
- data/lib/regexp_parser/expression/classes/property.rb +1 -1
- data/lib/regexp_parser/expression/classes/root.rb +4 -16
- data/lib/regexp_parser/expression/classes/set/range.rb +2 -1
- 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 +10 -1
- data/lib/regexp_parser/expression/sequence.rb +3 -19
- data/lib/regexp_parser/expression/subexpression.rb +1 -1
- data/lib/regexp_parser/lexer.rb +6 -6
- data/lib/regexp_parser/parser.rb +325 -344
- data/lib/regexp_parser/scanner.rb +1320 -1385
- 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 +231 -253
- data/lib/regexp_parser/syntax.rb +8 -6
- data/lib/regexp_parser/syntax/any.rb +3 -3
- data/lib/regexp_parser/syntax/base.rb +1 -1
- data/lib/regexp_parser/syntax/version_lookup.rb +4 -4
- 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/clone_spec.rb +36 -4
- data/spec/expression/free_space_spec.rb +2 -2
- data/spec/expression/methods/match_length_spec.rb +2 -2
- 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/lexer/refcalls_spec.rb +5 -0
- data/spec/parser/all_spec.rb +2 -2
- data/spec/parser/errors_spec.rb +1 -1
- data/spec/parser/escapes_spec.rb +1 -1
- data/spec/parser/options_spec.rb +28 -0
- data/spec/parser/quantifiers_spec.rb +16 -0
- data/spec/parser/refcalls_spec.rb +5 -0
- data/spec/parser/set/ranges_spec.rb +3 -3
- data/spec/scanner/escapes_spec.rb +12 -1
- 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/options_spec.rb +36 -0
- data/spec/scanner/quantifiers_spec.rb +18 -13
- data/spec/scanner/refcalls_spec.rb +19 -0
- data/spec/scanner/sets_spec.rb +65 -16
- data/spec/spec_helper.rb +1 -0
- metadata +61 -60
- data/spec/expression/root_spec.rb +0 -9
- data/spec/expression/sequence_spec.rb +0 -9
data/lib/regexp_parser/syntax.rb
CHANGED
@@ -1,9 +1,11 @@
|
|
1
|
-
require
|
2
|
-
require File.expand_path('../syntax/base', __FILE__)
|
3
|
-
require File.expand_path('../syntax/any', __FILE__)
|
4
|
-
require File.expand_path('../syntax/version_lookup', __FILE__)
|
5
|
-
require File.expand_path('../syntax/versions', __FILE__)
|
1
|
+
require 'regexp_parser/error'
|
6
2
|
|
7
3
|
module Regexp::Syntax
|
8
|
-
class SyntaxError <
|
4
|
+
class SyntaxError < Regexp::Parser::Error; end
|
9
5
|
end
|
6
|
+
|
7
|
+
require_relative 'syntax/tokens'
|
8
|
+
require_relative 'syntax/base'
|
9
|
+
require_relative 'syntax/any'
|
10
|
+
require_relative 'syntax/version_lookup'
|
11
|
+
require_relative 'syntax/versions'
|
@@ -4,12 +4,12 @@ module Regexp::Syntax
|
|
4
4
|
# is useful during development, testing, and should be useful for some types
|
5
5
|
# of transformations as well.
|
6
6
|
class Any < Base
|
7
|
-
def initialize
|
7
|
+
def initialize # rubocop:disable Lint/MissingSuper
|
8
8
|
@implements = { :* => [:*] }
|
9
9
|
end
|
10
10
|
|
11
|
-
def implements?(
|
12
|
-
def implements!(
|
11
|
+
def implements?(_type, _token) true end
|
12
|
+
def implements!(_type, _token) true end
|
13
13
|
end
|
14
14
|
|
15
15
|
end
|
@@ -3,13 +3,13 @@ module Regexp::Syntax
|
|
3
3
|
VERSION_REGEXP = /#{VERSION_FORMAT}/
|
4
4
|
VERSION_CONST_REGEXP = /\AV\d+_\d+(?:_\d+)?\z/
|
5
5
|
|
6
|
-
class InvalidVersionNameError < SyntaxError
|
6
|
+
class InvalidVersionNameError < Regexp::Syntax::SyntaxError
|
7
7
|
def initialize(name)
|
8
8
|
super "Invalid version name '#{name}'. Expected format is '#{VERSION_FORMAT}'"
|
9
9
|
end
|
10
10
|
end
|
11
11
|
|
12
|
-
class UnknownSyntaxNameError < SyntaxError
|
12
|
+
class UnknownSyntaxNameError < Regexp::Syntax::SyntaxError
|
13
13
|
def initialize(name)
|
14
14
|
super "Unknown syntax name '#{name}'."
|
15
15
|
end
|
@@ -74,9 +74,9 @@ module Regexp::Syntax
|
|
74
74
|
end
|
75
75
|
|
76
76
|
def warn_if_future_version(const_name)
|
77
|
-
return if comparable_version(const_name) < comparable_version('
|
77
|
+
return if comparable_version(const_name) < comparable_version('4.0.0')
|
78
78
|
|
79
|
-
warn('This library has only been tested up to Ruby
|
79
|
+
warn('This library has only been tested up to Ruby 3.x, '\
|
80
80
|
"but you are running with #{const_get(const_name).inspect}")
|
81
81
|
end
|
82
82
|
end
|
data/regexp_parser.gemspec
CHANGED
@@ -91,4 +91,14 @@ RSpec.describe(Regexp::Expression::Base) do
|
|
91
91
|
expect(RP.parse(/a*/)[0].repetitions).to eq 0..(Float::INFINITY)
|
92
92
|
expect(RP.parse(/a+/)[0].repetitions).to eq 1..(Float::INFINITY)
|
93
93
|
end
|
94
|
+
|
95
|
+
specify('#base_length') do
|
96
|
+
expect(RP.parse(/(aa)/)[0].base_length).to eq 4
|
97
|
+
expect(RP.parse(/(aa){42}/)[0].base_length).to eq 4
|
98
|
+
end
|
99
|
+
|
100
|
+
specify('#full_length') do
|
101
|
+
expect(RP.parse(/(aa)/)[0].full_length).to eq 4
|
102
|
+
expect(RP.parse(/(aa){42}/)[0].full_length).to eq 8
|
103
|
+
end
|
94
104
|
end
|
@@ -27,8 +27,8 @@ RSpec.describe('Expression#clone') do
|
|
27
27
|
expect(root_2.quantifier.object_id).not_to eq copy_2.quantifier.object_id
|
28
28
|
|
29
29
|
# regression test
|
30
|
-
expect { root_2.clone }.not_to
|
31
|
-
expect { root_2.clone }.not_to
|
30
|
+
expect { root_2.clone }.not_to(change { root_2.quantifier.object_id })
|
31
|
+
expect { root_2.clone }.not_to(change { root_2.quantifier.text.object_id })
|
32
32
|
end
|
33
33
|
|
34
34
|
specify('Subexpression#clone') do
|
@@ -48,7 +48,7 @@ RSpec.describe('Expression#clone') do
|
|
48
48
|
end
|
49
49
|
|
50
50
|
# regression test
|
51
|
-
expect { root.clone }.not_to
|
51
|
+
expect { root.clone }.not_to(change { root.expressions.object_id })
|
52
52
|
end
|
53
53
|
|
54
54
|
specify('Group::Named#clone') do
|
@@ -69,7 +69,39 @@ RSpec.describe('Expression#clone') do
|
|
69
69
|
end
|
70
70
|
|
71
71
|
# regression test
|
72
|
-
expect { root_1.clone }.not_to
|
72
|
+
expect { root_1.clone }.not_to(change { root_1.name.object_id })
|
73
|
+
end
|
74
|
+
|
75
|
+
specify('Group::Options#clone') do
|
76
|
+
root = RP.parse('foo(?i)bar')
|
77
|
+
copy = root.clone
|
78
|
+
|
79
|
+
expect(copy.to_s).to eq root.to_s
|
80
|
+
|
81
|
+
root_1 = root[1]
|
82
|
+
copy_1 = copy[1]
|
83
|
+
|
84
|
+
expect(root_1.option_changes).to eq copy_1.option_changes
|
85
|
+
expect(root_1.option_changes.object_id).not_to eq copy_1.option_changes.object_id
|
86
|
+
|
87
|
+
# regression test
|
88
|
+
expect { root_1.clone }.not_to(change { root_1.option_changes.object_id })
|
89
|
+
end
|
90
|
+
|
91
|
+
specify('Backreference::Base#clone') do
|
92
|
+
root = RP.parse('(foo)\1')
|
93
|
+
copy = root.clone
|
94
|
+
|
95
|
+
expect(copy.to_s).to eq root.to_s
|
96
|
+
|
97
|
+
root_1 = root[1]
|
98
|
+
copy_1 = copy[1]
|
99
|
+
|
100
|
+
expect(root_1.referenced_expression.to_s).to eq copy_1.referenced_expression.to_s
|
101
|
+
expect(root_1.referenced_expression.object_id).not_to eq copy_1.referenced_expression.object_id
|
102
|
+
|
103
|
+
# regression test
|
104
|
+
expect { root_1.clone }.not_to(change { root_1.referenced_expression.object_id })
|
73
105
|
end
|
74
106
|
|
75
107
|
specify('Sequence#clone') do
|
@@ -10,7 +10,7 @@ RSpec.describe(Regexp::Expression::FreeSpace) do
|
|
10
10
|
space = root[0]
|
11
11
|
|
12
12
|
expect(space).to be_instance_of(FreeSpace::WhiteSpace)
|
13
|
-
expect { space.quantify(:dummy, '#') }.to raise_error(
|
13
|
+
expect { space.quantify(:dummy, '#') }.to raise_error(Regexp::Parser::Error)
|
14
14
|
end
|
15
15
|
|
16
16
|
specify('comment quantify raises error') do
|
@@ -22,6 +22,6 @@ RSpec.describe(Regexp::Expression::FreeSpace) do
|
|
22
22
|
comment = root[3]
|
23
23
|
|
24
24
|
expect(comment).to be_instance_of(FreeSpace::Comment)
|
25
|
-
expect { comment.quantify(:dummy, '#') }.to raise_error(
|
25
|
+
expect { comment.quantify(:dummy, '#') }.to raise_error(Regexp::Parser::Error)
|
26
26
|
end
|
27
27
|
end
|
@@ -1,8 +1,8 @@
|
|
1
1
|
require 'spec_helper'
|
2
2
|
|
3
|
-
|
4
|
-
ML = described_class
|
3
|
+
ML = Regexp::MatchLength
|
5
4
|
|
5
|
+
RSpec.describe(Regexp::MatchLength) do
|
6
6
|
specify('literal') { expect(ML.of(/a/).minmax).to eq [1, 1] }
|
7
7
|
specify('literal sequence') { expect(ML.of(/abc/).minmax).to eq [3, 3] }
|
8
8
|
specify('dot') { expect(ML.of(/./).minmax).to eq [1, 1] }
|
@@ -32,7 +32,7 @@ RSpec.describe(Regexp::Expression::Subexpression) do
|
|
32
32
|
}
|
33
33
|
|
34
34
|
root.each_expression do |exp|
|
35
|
-
next unless expected_nesting_level = tests.delete(exp.to_s)
|
35
|
+
next unless (expected_nesting_level = tests.delete(exp.to_s))
|
36
36
|
expect(expected_nesting_level).to eq exp.nesting_level
|
37
37
|
end
|
38
38
|
|
@@ -1,58 +1,50 @@
|
|
1
1
|
require 'spec_helper'
|
2
2
|
|
3
3
|
RSpec.describe('Expression#to_s') do
|
4
|
-
|
5
|
-
pattern
|
4
|
+
def parse_frozen(pattern, ruby_version = nil)
|
5
|
+
IceNine.deep_freeze(RP.parse(pattern, *ruby_version))
|
6
|
+
end
|
7
|
+
|
8
|
+
def expect_round_trip(pattern, ruby_version = nil)
|
9
|
+
parsed = parse_frozen(pattern, ruby_version)
|
6
10
|
|
7
|
-
expect(
|
11
|
+
expect(parsed.to_s).to eql(pattern)
|
8
12
|
end
|
9
13
|
|
10
|
-
specify('
|
11
|
-
|
14
|
+
specify('literal alternation') do
|
15
|
+
expect_round_trip('abcd|ghij|klmn|pqur')
|
16
|
+
end
|
12
17
|
|
13
|
-
|
18
|
+
specify('quantified alternations') do
|
19
|
+
expect_round_trip('(?:a?[b]+(c){2}|d+[e]*(f)?)|(?:g+[h]?(i){2,3}|j*[k]{3,5}(l)?)')
|
14
20
|
end
|
15
21
|
|
16
22
|
specify('quantified sets') do
|
17
|
-
|
18
|
-
|
19
|
-
expect(RP.parse(pattern).to_s).to eq pattern
|
23
|
+
expect_round_trip('[abc]+|[^def]{3,6}')
|
20
24
|
end
|
21
25
|
|
22
26
|
specify('property sets') do
|
23
|
-
|
24
|
-
|
25
|
-
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
27
|
+
expect_round_trip('[\\a\\b\\p{Lu}\\P{Z}\\c\\d]+', 'ruby/1.9')
|
26
28
|
end
|
27
29
|
|
28
30
|
specify('groups') do
|
29
|
-
|
30
|
-
|
31
|
-
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
31
|
+
expect_round_trip("(a(?>b(?:c(?<n>d(?'N'e)??f)+g)*+h)*i)++", 'ruby/1.9')
|
32
32
|
end
|
33
33
|
|
34
34
|
specify('assertions') do
|
35
|
-
|
36
|
-
|
37
|
-
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
35
|
+
expect_round_trip('(a+(?=b+(?!c+(?<=d+(?<!e+)?f+)?g+)?h+)?i+)?', 'ruby/1.9')
|
38
36
|
end
|
39
37
|
|
40
38
|
specify('comments') do
|
41
|
-
|
42
|
-
|
43
|
-
expect(RP.parse(pattern).to_s).to eq pattern
|
39
|
+
expect_round_trip('(?#start)a(?#middle)b(?#end)')
|
44
40
|
end
|
45
41
|
|
46
42
|
specify('options') do
|
47
|
-
|
48
|
-
|
49
|
-
expect(RP.parse(pattern).to_s).to eq pattern
|
43
|
+
expect_round_trip('(?mix:start)a(?-mix:middle)b(?i-mx:end)')
|
50
44
|
end
|
51
45
|
|
52
46
|
specify('url') do
|
53
|
-
|
54
|
-
|
55
|
-
expect(RP.parse(pattern).to_s).to eq pattern
|
47
|
+
expect_round_trip('(^$)|(^(http|https):\\/\\/[a-z0-9]+([\\-\\.]{1}[a-z0-9]+)*' + '\\.[a-z]{2,5}(([0-9]{1,5})?\\/.*)?$)')
|
56
48
|
end
|
57
49
|
|
58
50
|
specify('multiline source') do
|
@@ -64,7 +56,7 @@ RSpec.describe('Expression#to_s') do
|
|
64
56
|
\z
|
65
57
|
/x
|
66
58
|
|
67
|
-
expect(
|
59
|
+
expect(parse_frozen(multiline).to_s).to eql(multiline.source)
|
68
60
|
end
|
69
61
|
|
70
62
|
specify('multiline #to_s') do
|
@@ -76,7 +68,7 @@ RSpec.describe('Expression#to_s') do
|
|
76
68
|
\z
|
77
69
|
/x
|
78
70
|
|
79
|
-
|
71
|
+
expect_round_trip(multiline.to_s)
|
80
72
|
end
|
81
73
|
|
82
74
|
# Free spacing expressions that use spaces between quantifiers and their
|
@@ -93,8 +85,24 @@ RSpec.describe('Expression#to_s') do
|
|
93
85
|
/x
|
94
86
|
|
95
87
|
str = 'bbbcged'
|
96
|
-
root =
|
88
|
+
root = parse_frozen(multiline)
|
89
|
+
|
90
|
+
expect(Regexp.new(root.to_s, Regexp::EXTENDED).match(str)[0]).to eql(multiline.match(str)[0])
|
91
|
+
end
|
92
|
+
|
93
|
+
# special case: implicit groups used for chained quantifiers produce no parens
|
94
|
+
specify 'chained quantifiers #to_s' do
|
95
|
+
pattern = /a+{1}{2}/
|
96
|
+
root = parse_frozen(pattern)
|
97
|
+
expect(root.to_s).to eql('a+{1}{2}')
|
98
|
+
end
|
97
99
|
|
98
|
-
|
100
|
+
# regression test for https://github.com/ammar/regexp_parser/issues/74
|
101
|
+
specify('non-ascii comment') do
|
102
|
+
pattern = '(?x) 😋 # 😋'
|
103
|
+
root = RP.parse(pattern)
|
104
|
+
expect(root.last).to be_a(Regexp::Expression::Comment)
|
105
|
+
expect(root.last.to_s).to eql('# 😋')
|
106
|
+
expect(root.to_s).to eql(pattern)
|
99
107
|
end
|
100
108
|
end
|
data/spec/lexer/literals_spec.rb
CHANGED
@@ -10,67 +10,42 @@ RSpec.describe('Literal lexing') do
|
|
10
10
|
1 => [:literal, :literal, 'b', 1, 2, 0, 0, 0],
|
11
11
|
2 => [:quantifier, :one_or_more, '+', 2, 3, 0, 0, 0]
|
12
12
|
|
13
|
-
# 2 byte wide characters
|
14
|
-
include_examples 'lex', '
|
15
|
-
0 => [:literal, :literal, '
|
16
|
-
|
17
|
-
|
18
|
-
0 => [:literal, :literal, 'aاbبcت', 0, 9, 0, 0, 0]
|
19
|
-
|
20
|
-
include_examples 'lex', 'aاbبت?',
|
21
|
-
0 => [:literal, :literal, 'aاbب', 0, 6, 0, 0, 0],
|
22
|
-
1 => [:literal, :literal, 'ت', 6, 8, 0, 0, 0],
|
23
|
-
2 => [:quantifier, :zero_or_one, '?', 8, 9, 0, 0, 0]
|
24
|
-
|
25
|
-
include_examples 'lex', 'aا?bبcت+',
|
26
|
-
0 => [:literal, :literal, 'a', 0, 1, 0, 0, 0],
|
27
|
-
1 => [:literal, :literal, 'ا', 1, 3, 0, 0, 0],
|
28
|
-
2 => [:quantifier, :zero_or_one, '?', 3, 4, 0, 0, 0],
|
29
|
-
3 => [:literal, :literal, 'bبc', 4, 8, 0, 0, 0],
|
30
|
-
4 => [:literal, :literal, 'ت', 8, 10, 0, 0, 0],
|
31
|
-
5 => [:quantifier, :one_or_more, '+', 10, 11, 0, 0, 0]
|
32
|
-
|
33
|
-
include_examples 'lex', 'a(اbب+)cت?',
|
34
|
-
0 => [:literal, :literal, 'a', 0, 1, 0, 0, 0],
|
35
|
-
1 => [:group, :capture, '(', 1, 2, 0, 0, 0],
|
36
|
-
2 => [:literal, :literal, 'اb', 2, 5, 1, 0, 0],
|
37
|
-
3 => [:literal, :literal, 'ب', 5, 7, 1, 0, 0],
|
38
|
-
4 => [:quantifier, :one_or_more, '+', 7, 8, 1, 0, 0],
|
39
|
-
5 => [:group, :close, ')', 8, 9, 0, 0, 0],
|
40
|
-
6 => [:literal, :literal, 'c', 9, 10, 0, 0, 0],
|
41
|
-
7 => [:literal, :literal, 'ت', 10, 12, 0, 0, 0],
|
42
|
-
8 => [:quantifier, :zero_or_one, '?', 12, 13, 0, 0, 0]
|
13
|
+
# 2 byte wide characters
|
14
|
+
include_examples 'lex', 'äöü+',
|
15
|
+
0 => [:literal, :literal, 'äö', 0, 2, 0, 0, 0],
|
16
|
+
1 => [:literal, :literal, 'ü', 2, 3, 0, 0, 0],
|
17
|
+
2 => [:quantifier, :one_or_more, '+', 3, 4, 0, 0, 0]
|
43
18
|
|
44
19
|
# 3 byte wide characters, Japanese
|
45
20
|
include_examples 'lex', 'ab?れます+cd',
|
46
21
|
0 => [:literal, :literal, 'a', 0, 1, 0, 0, 0],
|
47
22
|
1 => [:literal, :literal, 'b', 1, 2, 0, 0, 0],
|
48
23
|
2 => [:quantifier, :zero_or_one, '?', 2, 3, 0, 0, 0],
|
49
|
-
3 => [:literal, :literal, 'れま', 3,
|
50
|
-
4 => [:literal, :literal, 'す',
|
51
|
-
5 => [:quantifier, :one_or_more, '+',
|
52
|
-
6 => [:literal, :literal, 'cd',
|
24
|
+
3 => [:literal, :literal, 'れま', 3, 5, 0, 0, 0],
|
25
|
+
4 => [:literal, :literal, 'す', 5, 6, 0, 0, 0],
|
26
|
+
5 => [:quantifier, :one_or_more, '+', 6, 7, 0, 0, 0],
|
27
|
+
6 => [:literal, :literal, 'cd', 7, 9, 0, 0, 0]
|
53
28
|
|
54
29
|
# 4 byte wide characters, Osmanya
|
55
30
|
include_examples 'lex', '𐒀𐒁?𐒂ab+𐒃',
|
56
|
-
0 => [:literal, :literal, '𐒀', 0,
|
57
|
-
1 => [:literal, :literal, '𐒁',
|
58
|
-
2 => [:quantifier, :zero_or_one, '?',
|
59
|
-
3 => [:literal, :literal, '𐒂a',
|
60
|
-
4 => [:literal, :literal, 'b',
|
61
|
-
5 => [:quantifier, :one_or_more, '+',
|
62
|
-
6 => [:literal, :literal, '𐒃',
|
31
|
+
0 => [:literal, :literal, '𐒀', 0, 1, 0, 0, 0],
|
32
|
+
1 => [:literal, :literal, '𐒁', 1, 2, 0, 0, 0],
|
33
|
+
2 => [:quantifier, :zero_or_one, '?', 2, 3, 0, 0, 0],
|
34
|
+
3 => [:literal, :literal, '𐒂a', 3, 5, 0, 0, 0],
|
35
|
+
4 => [:literal, :literal, 'b', 5, 6, 0, 0, 0],
|
36
|
+
5 => [:quantifier, :one_or_more, '+', 6, 7, 0, 0, 0],
|
37
|
+
6 => [:literal, :literal, '𐒃', 7, 8, 0, 0, 0]
|
63
38
|
|
64
39
|
include_examples 'lex', 'mu𝄞?si*𝄫c+',
|
65
40
|
0 => [:literal, :literal, 'mu', 0, 2, 0, 0, 0],
|
66
|
-
1 => [:literal, :literal, '𝄞', 2,
|
67
|
-
2 => [:quantifier, :zero_or_one, '?',
|
68
|
-
3 => [:literal, :literal, 's',
|
69
|
-
4 => [:literal, :literal, 'i',
|
70
|
-
5 => [:quantifier, :zero_or_more, '*',
|
71
|
-
6 => [:literal, :literal, '𝄫',
|
72
|
-
7 => [:literal, :literal, 'c',
|
73
|
-
8 => [:quantifier, :one_or_more, '+',
|
41
|
+
1 => [:literal, :literal, '𝄞', 2, 3, 0, 0, 0],
|
42
|
+
2 => [:quantifier, :zero_or_one, '?', 3, 4, 0, 0, 0],
|
43
|
+
3 => [:literal, :literal, 's', 4, 5, 0, 0, 0],
|
44
|
+
4 => [:literal, :literal, 'i', 5, 6, 0, 0, 0],
|
45
|
+
5 => [:quantifier, :zero_or_more, '*', 6, 7, 0, 0, 0],
|
46
|
+
6 => [:literal, :literal, '𝄫', 7, 8, 0, 0, 0],
|
47
|
+
7 => [:literal, :literal, 'c', 8, 9, 0, 0, 0],
|
48
|
+
8 => [:quantifier, :one_or_more, '+', 9, 10, 0, 0, 0]
|
74
49
|
|
75
50
|
specify('lex single 2 byte char') do
|
76
51
|
tokens = RL.lex("\u0627+")
|
data/spec/lexer/refcalls_spec.rb
CHANGED
@@ -32,6 +32,11 @@ RSpec.describe('RefCall lexing') do
|
|
32
32
|
include_examples 'lex', "(abc)\\g'1'",
|
33
33
|
3 => [:backref, :number_call, "\\g'1'", 5, 10, 0, 0, 0]
|
34
34
|
|
35
|
+
include_examples 'lex', '\g<0>',
|
36
|
+
0 => [:backref, :number_call, '\g<0>', 0, 5, 0, 0, 0]
|
37
|
+
include_examples 'lex', "\\g'0'",
|
38
|
+
0 => [:backref, :number_call, "\\g'0'", 0, 5, 0, 0, 0]
|
39
|
+
|
35
40
|
include_examples 'lex', '(abc)\g<-1>',
|
36
41
|
3 => [:backref, :number_rel_call, '\g<-1>', 5, 11, 0, 0, 0]
|
37
42
|
include_examples 'lex', "(abc)\\g'-1'",
|
data/spec/parser/all_spec.rb
CHANGED
@@ -34,10 +34,10 @@ RSpec.describe(Regexp::Parser) do
|
|
34
34
|
end
|
35
35
|
|
36
36
|
specify('parse no quantifier target raises error') do
|
37
|
-
expect { RP.parse('?abc') }.to raise_error(
|
37
|
+
expect { RP.parse('?abc') }.to raise_error(Regexp::Parser::Error)
|
38
38
|
end
|
39
39
|
|
40
40
|
specify('parse sequence no quantifier target raises error') do
|
41
|
-
expect { RP.parse('abc|?def') }.to raise_error(
|
41
|
+
expect { RP.parse('abc|?def') }.to raise_error(Regexp::Parser::Error)
|
42
42
|
end
|
43
43
|
end
|