regexp_parser 1.4.0 → 1.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +27 -1
- data/Gemfile +1 -1
- data/README.md +9 -13
- data/lib/regexp_parser/expression.rb +33 -21
- data/lib/regexp_parser/expression/classes/backref.rb +18 -10
- data/lib/regexp_parser/expression/classes/conditional.rb +4 -0
- data/lib/regexp_parser/expression/classes/group.rb +4 -2
- data/lib/regexp_parser/expression/classes/keep.rb +1 -3
- data/lib/regexp_parser/expression/methods/match_length.rb +172 -0
- data/lib/regexp_parser/expression/quantifier.rb +2 -2
- data/lib/regexp_parser/expression/sequence.rb +0 -4
- data/lib/regexp_parser/expression/subexpression.rb +3 -5
- data/lib/regexp_parser/lexer.rb +31 -24
- data/lib/regexp_parser/parser.rb +25 -3
- data/lib/regexp_parser/syntax/tokens.rb +2 -10
- data/lib/regexp_parser/version.rb +1 -1
- data/regexp_parser.gemspec +2 -2
- data/spec/expression/base_spec.rb +80 -0
- data/spec/expression/clone_spec.rb +120 -0
- data/spec/expression/conditional_spec.rb +89 -0
- data/spec/expression/free_space_spec.rb +27 -0
- data/spec/expression/methods/match_length_spec.rb +141 -0
- data/spec/expression/methods/strfregexp_spec.rb +224 -0
- data/spec/expression/methods/tests_spec.rb +97 -0
- data/spec/expression/methods/traverse_spec.rb +140 -0
- data/spec/expression/subexpression_spec.rb +50 -0
- data/spec/expression/to_h_spec.rb +26 -0
- data/spec/expression/to_s_spec.rb +100 -0
- data/spec/lexer/all_spec.rb +22 -0
- data/{test/lexer/test_conditionals.rb → spec/lexer/conditionals_spec.rb} +31 -35
- data/spec/lexer/escapes_spec.rb +38 -0
- data/spec/lexer/keep_spec.rb +22 -0
- data/{test/lexer/test_literals.rb → spec/lexer/literals_spec.rb} +20 -24
- data/{test/lexer/test_nesting.rb → spec/lexer/nesting_spec.rb} +11 -13
- data/spec/lexer/refcalls_spec.rb +54 -0
- data/spec/parser/all_spec.rb +31 -0
- data/spec/parser/alternation_spec.rb +88 -0
- data/{test/parser/test_anchors.rb → spec/parser/anchors_spec.rb} +7 -10
- data/spec/parser/conditionals_spec.rb +179 -0
- data/spec/parser/errors_spec.rb +51 -0
- data/spec/parser/escapes_spec.rb +132 -0
- data/spec/parser/free_space_spec.rb +130 -0
- data/spec/parser/groups_spec.rb +267 -0
- data/spec/parser/keep_spec.rb +19 -0
- data/spec/parser/posix_classes_spec.rb +27 -0
- data/spec/parser/properties_spec.rb +127 -0
- data/spec/parser/quantifiers_spec.rb +293 -0
- data/spec/parser/refcalls_spec.rb +237 -0
- data/spec/parser/set/intersections_spec.rb +127 -0
- data/spec/parser/set/ranges_spec.rb +111 -0
- data/spec/parser/sets_spec.rb +178 -0
- data/{test/parser/test_types.rb → spec/parser/types_spec.rb} +13 -20
- data/spec/scanner/all_spec.rb +18 -0
- data/{test/scanner/test_anchors.rb → spec/scanner/anchors_spec.rb} +8 -10
- data/{test/scanner/test_conditionals.rb → spec/scanner/conditionals_spec.rb} +49 -53
- data/spec/scanner/errors_spec.rb +90 -0
- data/{test/scanner/test_escapes.rb → spec/scanner/escapes_spec.rb} +8 -10
- data/{test/scanner/test_free_space.rb → spec/scanner/free_space_spec.rb} +48 -52
- data/{test/scanner/test_groups.rb → spec/scanner/groups_spec.rb} +33 -41
- data/spec/scanner/keep_spec.rb +33 -0
- data/{test/scanner/test_literals.rb → spec/scanner/literals_spec.rb} +8 -12
- data/{test/scanner/test_meta.rb → spec/scanner/meta_spec.rb} +8 -10
- data/{test/scanner/test_properties.rb → spec/scanner/properties_spec.rb} +14 -19
- data/{test/scanner/test_quantifiers.rb → spec/scanner/quantifiers_spec.rb} +7 -9
- data/{test/scanner/test_refcalls.rb → spec/scanner/refcalls_spec.rb} +9 -9
- data/{test/scanner/test_scripts.rb → spec/scanner/scripts_spec.rb} +8 -12
- data/{test/scanner/test_sets.rb → spec/scanner/sets_spec.rb} +14 -17
- data/spec/scanner/types_spec.rb +29 -0
- data/spec/scanner/unicode_blocks_spec.rb +28 -0
- data/spec/spec_helper.rb +14 -0
- data/{test → spec}/support/runner.rb +9 -8
- data/{test → spec}/support/warning_extractor.rb +5 -7
- data/spec/syntax/syntax_spec.rb +44 -0
- data/spec/syntax/syntax_token_map_spec.rb +23 -0
- data/spec/syntax/versions/1.8.6_spec.rb +38 -0
- data/spec/syntax/versions/1.9.1_spec.rb +23 -0
- data/spec/syntax/versions/1.9.3_spec.rb +22 -0
- data/spec/syntax/versions/2.0.0_spec.rb +28 -0
- data/spec/syntax/versions/2.2.0_spec.rb +22 -0
- data/spec/syntax/versions/aliases_spec.rb +119 -0
- data/spec/token/token_spec.rb +85 -0
- metadata +131 -140
- data/test/expression/test_all.rb +0 -12
- data/test/expression/test_base.rb +0 -90
- data/test/expression/test_clone.rb +0 -89
- data/test/expression/test_conditionals.rb +0 -113
- data/test/expression/test_free_space.rb +0 -35
- data/test/expression/test_set.rb +0 -84
- data/test/expression/test_strfregexp.rb +0 -230
- data/test/expression/test_subexpression.rb +0 -58
- data/test/expression/test_tests.rb +0 -99
- data/test/expression/test_to_h.rb +0 -59
- data/test/expression/test_to_s.rb +0 -104
- data/test/expression/test_traverse.rb +0 -161
- data/test/helpers.rb +0 -10
- data/test/lexer/test_all.rb +0 -41
- data/test/lexer/test_keep.rb +0 -24
- data/test/lexer/test_refcalls.rb +0 -56
- data/test/parser/set/test_intersections.rb +0 -127
- data/test/parser/set/test_ranges.rb +0 -111
- data/test/parser/test_all.rb +0 -64
- data/test/parser/test_alternation.rb +0 -92
- data/test/parser/test_conditionals.rb +0 -187
- data/test/parser/test_errors.rb +0 -63
- data/test/parser/test_escapes.rb +0 -134
- data/test/parser/test_free_space.rb +0 -139
- data/test/parser/test_groups.rb +0 -289
- data/test/parser/test_keep.rb +0 -21
- data/test/parser/test_posix_classes.rb +0 -27
- data/test/parser/test_properties.rb +0 -134
- data/test/parser/test_quantifiers.rb +0 -301
- data/test/parser/test_refcalls.rb +0 -186
- data/test/parser/test_sets.rb +0 -179
- data/test/scanner/test_all.rb +0 -38
- data/test/scanner/test_errors.rb +0 -91
- data/test/scanner/test_keep.rb +0 -35
- data/test/scanner/test_types.rb +0 -35
- data/test/scanner/test_unicode_blocks.rb +0 -30
- data/test/support/disable_autotest.rb +0 -8
- data/test/syntax/test_all.rb +0 -6
- data/test/syntax/test_syntax.rb +0 -61
- data/test/syntax/test_syntax_token_map.rb +0 -25
- data/test/syntax/versions/test_1.8.rb +0 -55
- data/test/syntax/versions/test_1.9.1.rb +0 -36
- data/test/syntax/versions/test_1.9.3.rb +0 -32
- data/test/syntax/versions/test_2.0.0.rb +0 -37
- data/test/syntax/versions/test_2.2.0.rb +0 -32
- data/test/syntax/versions/test_aliases.rb +0 -129
- data/test/syntax/versions/test_all.rb +0 -5
- data/test/test_all.rb +0 -5
- data/test/token/test_all.rb +0 -2
- data/test/token/test_token.rb +0 -107
@@ -0,0 +1,140 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe('Subexpression#traverse') do
|
4
|
+
specify('Subexpression#traverse') do
|
5
|
+
root = RP.parse(/a(b(c(d)))|g[h-i]j|klmn/)
|
6
|
+
|
7
|
+
enters = 0
|
8
|
+
visits = 0
|
9
|
+
exits = 0
|
10
|
+
|
11
|
+
root.traverse do |event, _exp, _index|
|
12
|
+
enters = (enters + 1) if event == :enter
|
13
|
+
visits = (visits + 1) if event == :visit
|
14
|
+
exits = (exits + 1) if event == :exit
|
15
|
+
end
|
16
|
+
|
17
|
+
expect(enters).to eq 9
|
18
|
+
expect(enters).to eq exits
|
19
|
+
|
20
|
+
expect(visits).to eq 9
|
21
|
+
end
|
22
|
+
|
23
|
+
specify('Subexpression#traverse including self') do
|
24
|
+
root = RP.parse(/a(b(c(d)))|g[h-i]j|klmn/)
|
25
|
+
|
26
|
+
enters = 0
|
27
|
+
visits = 0
|
28
|
+
exits = 0
|
29
|
+
|
30
|
+
root.traverse(true) do |event, _exp, _index|
|
31
|
+
enters = (enters + 1) if event == :enter
|
32
|
+
visits = (visits + 1) if event == :visit
|
33
|
+
exits = (exits + 1) if event == :exit
|
34
|
+
end
|
35
|
+
|
36
|
+
expect(enters).to eq 10
|
37
|
+
expect(enters).to eq exits
|
38
|
+
|
39
|
+
expect(visits).to eq 9
|
40
|
+
end
|
41
|
+
|
42
|
+
specify('Subexpression#walk alias') do
|
43
|
+
root = RP.parse(/abc/)
|
44
|
+
|
45
|
+
expect(root).to respond_to(:walk)
|
46
|
+
end
|
47
|
+
|
48
|
+
specify('Subexpression#each_expression') do
|
49
|
+
root = RP.parse(/a(?x:b(c))|g[h-k]/)
|
50
|
+
|
51
|
+
count = 0
|
52
|
+
root.each_expression { count += 1 }
|
53
|
+
|
54
|
+
expect(count).to eq 13
|
55
|
+
end
|
56
|
+
|
57
|
+
specify('Subexpression#each_expression including self') do
|
58
|
+
root = RP.parse(/a(?x:b(c))|g[h-k]/)
|
59
|
+
|
60
|
+
count = 0
|
61
|
+
root.each_expression(true) { count += 1 }
|
62
|
+
|
63
|
+
expect(count).to eq 14
|
64
|
+
end
|
65
|
+
|
66
|
+
specify('Subexpression#each_expression indices') do
|
67
|
+
root = RP.parse(/a(b)c/)
|
68
|
+
|
69
|
+
indices = []
|
70
|
+
root.each_expression { |_exp, index| (indices << index) }
|
71
|
+
|
72
|
+
expect(indices).to eq [0, 1, 0, 2]
|
73
|
+
end
|
74
|
+
|
75
|
+
specify('Subexpression#each_expression indices including self') do
|
76
|
+
root = RP.parse(/a(b)c/)
|
77
|
+
|
78
|
+
indices = []
|
79
|
+
root.each_expression(true) { |_exp, index| (indices << index) }
|
80
|
+
|
81
|
+
expect(indices).to eq [0, 0, 1, 0, 2]
|
82
|
+
end
|
83
|
+
|
84
|
+
specify('Subexpression#flat_map without block') do
|
85
|
+
root = RP.parse(/a(b([c-e]+))?/)
|
86
|
+
|
87
|
+
array = root.flat_map
|
88
|
+
|
89
|
+
expect(array).to be_instance_of(Array)
|
90
|
+
expect(array.length).to eq 8
|
91
|
+
|
92
|
+
array.each do |item|
|
93
|
+
expect(item).to be_instance_of(Array)
|
94
|
+
expect(item.length).to eq 2
|
95
|
+
expect(item.first).to be_a(Regexp::Expression::Base)
|
96
|
+
expect(item.last).to be_a(Integer)
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
specify('Subexpression#flat_map without block including self') do
|
101
|
+
root = RP.parse(/a(b([c-e]+))?/)
|
102
|
+
|
103
|
+
array = root.flat_map(true)
|
104
|
+
|
105
|
+
expect(array).to be_instance_of(Array)
|
106
|
+
expect(array.length).to eq 9
|
107
|
+
end
|
108
|
+
|
109
|
+
specify('Subexpression#flat_map indices') do
|
110
|
+
root = RP.parse(/a(b([c-e]+))?f*g/)
|
111
|
+
|
112
|
+
indices = root.flat_map { |_exp, index| index }
|
113
|
+
|
114
|
+
expect(indices).to eq [0, 1, 0, 1, 0, 0, 0, 1, 2, 3]
|
115
|
+
end
|
116
|
+
|
117
|
+
specify('Subexpression#flat_map indices including self') do
|
118
|
+
root = RP.parse(/a(b([c-e]+))?f*g/)
|
119
|
+
|
120
|
+
indices = root.flat_map(true) { |_exp, index| index }
|
121
|
+
|
122
|
+
expect(indices).to eq [0, 0, 1, 0, 1, 0, 0, 0, 1, 2, 3]
|
123
|
+
end
|
124
|
+
|
125
|
+
specify('Subexpression#flat_map expressions') do
|
126
|
+
root = RP.parse(/a(b(c(d)))/)
|
127
|
+
|
128
|
+
levels = root.flat_map { |exp, _index| [exp.level, exp.text] if exp.terminal? }.compact
|
129
|
+
|
130
|
+
expect(levels).to eq [[0, 'a'], [1, 'b'], [2, 'c'], [3, 'd']]
|
131
|
+
end
|
132
|
+
|
133
|
+
specify('Subexpression#flat_map expressions including self') do
|
134
|
+
root = RP.parse(/a(b(c(d)))/)
|
135
|
+
|
136
|
+
levels = root.flat_map(true) { |exp, _index| [exp.level, exp.to_s] }.compact
|
137
|
+
|
138
|
+
expect(levels).to eq [[nil, 'a(b(c(d)))'], [0, 'a'], [0, '(b(c(d)))'], [1, 'b'], [1, '(c(d))'], [2, 'c'], [2, '(d)'], [3, 'd']]
|
139
|
+
end
|
140
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe(Regexp::Expression::Subexpression) do
|
4
|
+
specify('#ts, #te') do
|
5
|
+
regx = /abcd|ghij|klmn|pqur/
|
6
|
+
root = RP.parse(regx)
|
7
|
+
|
8
|
+
alt = root.first
|
9
|
+
|
10
|
+
{ 0 => [0, 4], 1 => [5, 9], 2 => [10, 14], 3 => [15, 19] }.each do |index, span|
|
11
|
+
sequence = alt[index]
|
12
|
+
|
13
|
+
expect(sequence.ts).to eq span[0]
|
14
|
+
expect(sequence.te).to eq span[1]
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
specify('#nesting_level') do
|
19
|
+
root = RP.parse(/a(b(\d|[ef-g[h]]))/)
|
20
|
+
|
21
|
+
tests = {
|
22
|
+
'a' => 1,
|
23
|
+
'b' => 2,
|
24
|
+
'\d|[ef-g[h]]' => 3, # alternation
|
25
|
+
'\d' => 4, # first alternative
|
26
|
+
'[ef-g[h]]' => 4, # second alternative
|
27
|
+
'e' => 5,
|
28
|
+
'f-g' => 5,
|
29
|
+
'f' => 6,
|
30
|
+
'g' => 6,
|
31
|
+
'h' => 6,
|
32
|
+
}
|
33
|
+
|
34
|
+
root.each_expression do |exp|
|
35
|
+
next unless expected_nesting_level = tests.delete(exp.to_s)
|
36
|
+
expect(expected_nesting_level).to eq exp.nesting_level
|
37
|
+
end
|
38
|
+
|
39
|
+
expect(tests).to be_empty
|
40
|
+
end
|
41
|
+
|
42
|
+
specify('#dig') do
|
43
|
+
root = RP.parse(/(((a)))/)
|
44
|
+
|
45
|
+
expect(root.dig(0).to_s).to eq '(((a)))'
|
46
|
+
expect(root.dig(0, 0, 0, 0).to_s).to eq 'a'
|
47
|
+
expect(root.dig(0, 0, 0, 0, 0)).to be_nil
|
48
|
+
expect(root.dig(3, 7)).to be_nil
|
49
|
+
end
|
50
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe('Expression#to_h') do
|
4
|
+
specify('Root#to_h') do
|
5
|
+
root = RP.parse('abc')
|
6
|
+
|
7
|
+
hash = root.to_h
|
8
|
+
|
9
|
+
expect(token: :root, type: :expression, text: 'abc', starts_at: 0, length: 3, quantifier: nil, options: {}, level: nil, set_level: nil, conditional_level: nil, expressions: [{ token: :literal, type: :literal, text: 'abc', starts_at: 0, length: 3, quantifier: nil, options: {}, level: 0, set_level: 0, conditional_level: 0 }]).to eq hash
|
10
|
+
end
|
11
|
+
|
12
|
+
specify('Quantifier#to_h') do
|
13
|
+
root = RP.parse('a{2,4}')
|
14
|
+
exp = root.expressions.at(0)
|
15
|
+
|
16
|
+
hash = exp.quantifier.to_h
|
17
|
+
|
18
|
+
expect(max: 4, min: 2, mode: :greedy, text: '{2,4}', token: :interval).to eq hash
|
19
|
+
end
|
20
|
+
|
21
|
+
specify('Conditional#to_h') do
|
22
|
+
root = RP.parse('(?<A>a)(?(<A>)b|c)', 'ruby/2.0')
|
23
|
+
|
24
|
+
expect { root.to_h }.not_to(raise_error)
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,100 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe('Expression#to_s') do
|
4
|
+
specify('literal alternation') do
|
5
|
+
pattern = 'abcd|ghij|klmn|pqur'
|
6
|
+
|
7
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
8
|
+
end
|
9
|
+
|
10
|
+
specify('quantified alternations') do
|
11
|
+
pattern = '(?:a?[b]+(c){2}|d+[e]*(f)?)|(?:g+[h]?(i){2,3}|j*[k]{3,5}(l)?)'
|
12
|
+
|
13
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
14
|
+
end
|
15
|
+
|
16
|
+
specify('quantified sets') do
|
17
|
+
pattern = '[abc]+|[^def]{3,6}'
|
18
|
+
|
19
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
20
|
+
end
|
21
|
+
|
22
|
+
specify('property sets') do
|
23
|
+
pattern = '[\\a\\b\\p{Lu}\\P{Z}\\c\\d]+'
|
24
|
+
|
25
|
+
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
26
|
+
end
|
27
|
+
|
28
|
+
specify('groups') do
|
29
|
+
pattern = "(a(?>b(?:c(?<n>d(?'N'e)??f)+g)*+h)*i)++"
|
30
|
+
|
31
|
+
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
32
|
+
end
|
33
|
+
|
34
|
+
specify('assertions') do
|
35
|
+
pattern = '(a+(?=b+(?!c+(?<=d+(?<!e+)?f+)?g+)?h+)?i+)?'
|
36
|
+
|
37
|
+
expect(RP.parse(pattern, 'ruby/1.9').to_s).to eq pattern
|
38
|
+
end
|
39
|
+
|
40
|
+
specify('comments') do
|
41
|
+
pattern = '(?#start)a(?#middle)b(?#end)'
|
42
|
+
|
43
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
44
|
+
end
|
45
|
+
|
46
|
+
specify('options') do
|
47
|
+
pattern = '(?mix:start)a(?-mix:middle)b(?i-mx:end)'
|
48
|
+
|
49
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
50
|
+
end
|
51
|
+
|
52
|
+
specify('url') do
|
53
|
+
pattern = ('(^$)|(^(http|https):\\/\\/[a-z0-9]+([\\-\\.]{1}[a-z0-9]+)*' + '\\.[a-z]{2,5}(([0-9]{1,5})?\\/.*)?$)')
|
54
|
+
|
55
|
+
expect(RP.parse(pattern).to_s).to eq pattern
|
56
|
+
end
|
57
|
+
|
58
|
+
specify('multiline source') do
|
59
|
+
multiline = /
|
60
|
+
\A
|
61
|
+
a? # One letter
|
62
|
+
b{2,5} # Another one
|
63
|
+
[c-g]+ # A set
|
64
|
+
\z
|
65
|
+
/x
|
66
|
+
|
67
|
+
expect(RP.parse(multiline).to_s).to eq multiline.source
|
68
|
+
end
|
69
|
+
|
70
|
+
specify('multiline #to_s') do
|
71
|
+
multiline = /
|
72
|
+
\A
|
73
|
+
a? # One letter
|
74
|
+
b{2,5} # Another one
|
75
|
+
[c-g]+ # A set
|
76
|
+
\z
|
77
|
+
/x
|
78
|
+
|
79
|
+
expect(RP.parse(multiline.to_s).to_s).to eq multiline.to_s
|
80
|
+
end
|
81
|
+
|
82
|
+
# Free spacing expressions that use spaces between quantifiers and their
|
83
|
+
# targets do not produce identical results due to the way quantifiers are
|
84
|
+
# applied to expressions (members, not nodes) and the merging of consecutive
|
85
|
+
# space nodes. This tests that they produce equivalent results.
|
86
|
+
specify('multiline equivalence') do
|
87
|
+
multiline = /
|
88
|
+
\A
|
89
|
+
a ? # One letter
|
90
|
+
b {2,5} # Another one
|
91
|
+
[c-g] + # A set
|
92
|
+
\z
|
93
|
+
/x
|
94
|
+
|
95
|
+
str = 'bbbcged'
|
96
|
+
root = RP.parse(multiline)
|
97
|
+
|
98
|
+
expect(Regexp.new(root.to_s, Regexp::EXTENDED).match(str)[0]).to eq multiline.match(str)[0]
|
99
|
+
end
|
100
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe(Regexp::Lexer) do
|
4
|
+
specify('lexer returns an array') do
|
5
|
+
expect(RL.lex('abc')).to be_instance_of(Array)
|
6
|
+
end
|
7
|
+
|
8
|
+
specify('lexer returns tokens') do
|
9
|
+
tokens = RL.lex('^abc+[^one]{2,3}\\b\\d\\\\C-C$')
|
10
|
+
expect(tokens).to all(be_a Regexp::Token)
|
11
|
+
expect(tokens.map { |token| token.to_a.length }).to all(eq 8)
|
12
|
+
end
|
13
|
+
|
14
|
+
specify('lexer token count') do
|
15
|
+
tokens = RL.lex(/^(one|two){2,3}([^d\]efm-qz\,\-]*)(ghi)+$/i)
|
16
|
+
expect(tokens.length).to eq 28
|
17
|
+
end
|
18
|
+
|
19
|
+
specify('lexer scan alias') do
|
20
|
+
expect(RL.scan(/a|b|c/)).to eq RL.lex(/a|b|c/)
|
21
|
+
end
|
22
|
+
end
|
@@ -1,8 +1,6 @@
|
|
1
|
-
require
|
2
|
-
|
3
|
-
class LexerConditionals < Test::Unit::TestCase
|
4
|
-
if RUBY_VERSION >= '2.0'
|
1
|
+
require 'spec_helper'
|
5
2
|
|
3
|
+
RSpec.describe('Conditional lexing') do
|
6
4
|
# Basic lexer output and nesting tests
|
7
5
|
tests = {
|
8
6
|
'(?<A>a)(?(<A>)b|c)' => [3, :conditional, :open, '(?', 7, 9, 0, 0, 0],
|
@@ -12,23 +10,23 @@ class LexerConditionals < Test::Unit::TestCase
|
|
12
10
|
}
|
13
11
|
|
14
12
|
tests.each_with_index do |(pattern, (index, type, token, text, ts, te, level, set_level, conditional_level)), count|
|
15
|
-
|
13
|
+
specify("lexer_#{type}_#{token}_#{count}") do
|
16
14
|
tokens = RL.lex(pattern)
|
17
15
|
struct = tokens.at(index)
|
18
16
|
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
17
|
+
expect(struct.type).to eq type
|
18
|
+
expect(struct.token).to eq token
|
19
|
+
expect(struct.text).to eq text
|
20
|
+
expect(struct.ts).to eq ts
|
21
|
+
expect(struct.te).to eq te
|
22
|
+
expect(struct.level).to eq level
|
23
|
+
expect(struct.set_level).to eq set_level
|
24
|
+
expect(struct.conditional_level).to eq conditional_level
|
27
25
|
end
|
28
26
|
end
|
29
27
|
|
30
|
-
|
31
|
-
regexp =
|
28
|
+
specify('lexer conditional mixed nesting') do
|
29
|
+
regexp = '((?<A>a)(?<B>(?(<A>)b|((?(<B>)[e-g]|[h-j])))))'
|
32
30
|
tokens = RL.lex(regexp)
|
33
31
|
|
34
32
|
[
|
@@ -57,19 +55,19 @@ class LexerConditionals < Test::Unit::TestCase
|
|
57
55
|
].each do |index, type, token, text, ts, te, level, set_level, conditional_level|
|
58
56
|
struct = tokens.at(index)
|
59
57
|
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
58
|
+
expect(struct.type).to eq type
|
59
|
+
expect(struct.token).to eq token
|
60
|
+
expect(struct.text).to eq text
|
61
|
+
expect(struct.ts).to eq ts
|
62
|
+
expect(struct.te).to eq te
|
63
|
+
expect(struct.level).to eq level
|
64
|
+
expect(struct.set_level).to eq set_level
|
65
|
+
expect(struct.conditional_level).to eq conditional_level
|
68
66
|
end
|
69
67
|
end
|
70
68
|
|
71
|
-
|
72
|
-
regexp =
|
69
|
+
specify('lexer conditional deep nesting') do
|
70
|
+
regexp = '(a(b(c)))(?(1)(?(2)(?(3)d|e))|(?(3)(?(2)f|g)|(?(1)f|g)))'
|
73
71
|
tokens = RL.lex(regexp)
|
74
72
|
|
75
73
|
[
|
@@ -112,16 +110,14 @@ class LexerConditionals < Test::Unit::TestCase
|
|
112
110
|
].each do |index, type, token, text, ts, te, level, set_level, conditional_level|
|
113
111
|
struct = tokens.at(index)
|
114
112
|
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
113
|
+
expect(struct.type).to eq type
|
114
|
+
expect(struct.token).to eq token
|
115
|
+
expect(struct.text).to eq text
|
116
|
+
expect(struct.ts).to eq ts
|
117
|
+
expect(struct.te).to eq te
|
118
|
+
expect(struct.level).to eq level
|
119
|
+
expect(struct.set_level).to eq set_level
|
120
|
+
expect(struct.conditional_level).to eq conditional_level
|
123
121
|
end
|
124
122
|
end
|
125
|
-
|
126
|
-
end # if RUBY_VERSION >= '2.0'
|
127
123
|
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
RSpec.describe('Escape lexing') do
|
4
|
+
tests = {
|
5
|
+
'\u{62}' => {
|
6
|
+
0 => [:escape, :codepoint_list, '\u{62}', 0, 6, 0, 0, 0],
|
7
|
+
},
|
8
|
+
|
9
|
+
'\u{62 63 64}' => {
|
10
|
+
0 => [:escape, :codepoint_list, '\u{62 63 64}', 0, 12, 0, 0, 0],
|
11
|
+
},
|
12
|
+
|
13
|
+
'\u{62 63 64}+' => {
|
14
|
+
0 => [:escape, :codepoint_list, '\u{62 63}', 0, 9, 0, 0, 0],
|
15
|
+
1 => [:escape, :codepoint_list, '\u{64}', 9, 15, 0, 0, 0],
|
16
|
+
2 => [:quantifier, :one_or_more, '+', 15, 16, 0, 0, 0],
|
17
|
+
},
|
18
|
+
}
|
19
|
+
|
20
|
+
tests.each_with_index do |(pattern, checks), count|
|
21
|
+
specify("lex_escape_runs_#{count}") do
|
22
|
+
tokens = RL.lex(pattern)
|
23
|
+
|
24
|
+
checks.each do |index, (type, token, text, ts, te, level, set_level, conditional_level)|
|
25
|
+
struct = tokens.at(index)
|
26
|
+
|
27
|
+
expect(struct.type).to eq type
|
28
|
+
expect(struct.token).to eq token
|
29
|
+
expect(struct.text).to eq text
|
30
|
+
expect(struct.ts).to eq ts
|
31
|
+
expect(struct.te).to eq te
|
32
|
+
expect(struct.level).to eq level
|
33
|
+
expect(struct.set_level).to eq set_level
|
34
|
+
expect(struct.conditional_level).to eq conditional_level
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|