regexp_parser 1.7.0 → 2.8.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (165) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +364 -22
  3. data/Gemfile +8 -2
  4. data/LICENSE +1 -1
  5. data/README.md +124 -88
  6. data/Rakefile +6 -70
  7. data/lib/regexp_parser/error.rb +4 -0
  8. data/lib/regexp_parser/expression/base.rb +76 -0
  9. data/lib/regexp_parser/expression/classes/alternation.rb +1 -1
  10. data/lib/regexp_parser/expression/classes/anchor.rb +0 -2
  11. data/lib/regexp_parser/expression/classes/{backref.rb → backreference.rb} +22 -2
  12. data/lib/regexp_parser/expression/classes/{set → character_set}/range.rb +4 -8
  13. data/lib/regexp_parser/expression/classes/{set.rb → character_set.rb} +3 -4
  14. data/lib/regexp_parser/expression/classes/{type.rb → character_type.rb} +0 -2
  15. data/lib/regexp_parser/expression/classes/conditional.rb +11 -5
  16. data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb} +15 -7
  17. data/lib/regexp_parser/expression/classes/free_space.rb +5 -5
  18. data/lib/regexp_parser/expression/classes/group.rb +28 -15
  19. data/lib/regexp_parser/expression/classes/keep.rb +2 -0
  20. data/lib/regexp_parser/expression/classes/literal.rb +1 -5
  21. data/lib/regexp_parser/expression/classes/posix_class.rb +5 -1
  22. data/lib/regexp_parser/expression/classes/root.rb +4 -19
  23. data/lib/regexp_parser/expression/classes/{property.rb → unicode_property.rb} +5 -3
  24. data/lib/regexp_parser/expression/methods/construct.rb +41 -0
  25. data/lib/regexp_parser/expression/methods/human_name.rb +43 -0
  26. data/lib/regexp_parser/expression/methods/match_length.rb +11 -7
  27. data/lib/regexp_parser/expression/methods/parts.rb +23 -0
  28. data/lib/regexp_parser/expression/methods/printing.rb +26 -0
  29. data/lib/regexp_parser/expression/methods/strfregexp.rb +1 -1
  30. data/lib/regexp_parser/expression/methods/tests.rb +47 -1
  31. data/lib/regexp_parser/expression/methods/traverse.rb +34 -18
  32. data/lib/regexp_parser/expression/quantifier.rb +57 -17
  33. data/lib/regexp_parser/expression/sequence.rb +11 -47
  34. data/lib/regexp_parser/expression/sequence_operation.rb +4 -9
  35. data/lib/regexp_parser/expression/shared.rb +111 -0
  36. data/lib/regexp_parser/expression/subexpression.rb +27 -19
  37. data/lib/regexp_parser/expression.rb +14 -141
  38. data/lib/regexp_parser/lexer.rb +83 -41
  39. data/lib/regexp_parser/parser.rb +371 -429
  40. data/lib/regexp_parser/scanner/char_type.rl +11 -11
  41. data/lib/regexp_parser/scanner/errors/premature_end_error.rb +8 -0
  42. data/lib/regexp_parser/scanner/errors/scanner_error.rb +6 -0
  43. data/lib/regexp_parser/scanner/errors/validation_error.rb +63 -0
  44. data/lib/regexp_parser/scanner/properties/long.csv +633 -0
  45. data/lib/regexp_parser/scanner/properties/short.csv +248 -0
  46. data/lib/regexp_parser/scanner/property.rl +4 -4
  47. data/lib/regexp_parser/scanner/scanner.rl +295 -368
  48. data/lib/regexp_parser/scanner.rb +1405 -1674
  49. data/lib/regexp_parser/syntax/any.rb +2 -7
  50. data/lib/regexp_parser/syntax/base.rb +92 -67
  51. data/lib/regexp_parser/syntax/token/anchor.rb +15 -0
  52. data/lib/regexp_parser/syntax/{tokens → token}/assertion.rb +2 -2
  53. data/lib/regexp_parser/syntax/token/backreference.rb +33 -0
  54. data/lib/regexp_parser/syntax/token/character_set.rb +16 -0
  55. data/lib/regexp_parser/syntax/{tokens → token}/character_type.rb +3 -3
  56. data/lib/regexp_parser/syntax/{tokens → token}/conditional.rb +3 -3
  57. data/lib/regexp_parser/syntax/token/escape.rb +33 -0
  58. data/lib/regexp_parser/syntax/{tokens → token}/group.rb +7 -7
  59. data/lib/regexp_parser/syntax/{tokens → token}/keep.rb +1 -1
  60. data/lib/regexp_parser/syntax/token/meta.rb +20 -0
  61. data/lib/regexp_parser/syntax/{tokens → token}/posix_class.rb +3 -3
  62. data/lib/regexp_parser/syntax/token/quantifier.rb +35 -0
  63. data/lib/regexp_parser/syntax/token/unicode_property.rb +733 -0
  64. data/lib/regexp_parser/syntax/token/virtual.rb +11 -0
  65. data/lib/regexp_parser/syntax/token.rb +45 -0
  66. data/lib/regexp_parser/syntax/version_lookup.rb +19 -36
  67. data/lib/regexp_parser/syntax/versions/1.8.6.rb +13 -20
  68. data/lib/regexp_parser/syntax/versions/1.9.1.rb +10 -17
  69. data/lib/regexp_parser/syntax/versions/1.9.3.rb +3 -10
  70. data/lib/regexp_parser/syntax/versions/2.0.0.rb +8 -15
  71. data/lib/regexp_parser/syntax/versions/2.2.0.rb +3 -9
  72. data/lib/regexp_parser/syntax/versions/2.3.0.rb +3 -9
  73. data/lib/regexp_parser/syntax/versions/2.4.0.rb +3 -9
  74. data/lib/regexp_parser/syntax/versions/2.4.1.rb +2 -8
  75. data/lib/regexp_parser/syntax/versions/2.5.0.rb +3 -9
  76. data/lib/regexp_parser/syntax/versions/2.6.0.rb +3 -9
  77. data/lib/regexp_parser/syntax/versions/2.6.2.rb +3 -9
  78. data/lib/regexp_parser/syntax/versions/2.6.3.rb +3 -9
  79. data/lib/regexp_parser/syntax/versions/3.1.0.rb +4 -0
  80. data/lib/regexp_parser/syntax/versions/3.2.0.rb +4 -0
  81. data/lib/regexp_parser/syntax/versions.rb +3 -1
  82. data/lib/regexp_parser/syntax.rb +8 -6
  83. data/lib/regexp_parser/token.rb +9 -20
  84. data/lib/regexp_parser/version.rb +1 -1
  85. data/lib/regexp_parser.rb +0 -2
  86. data/regexp_parser.gemspec +20 -22
  87. metadata +49 -166
  88. data/lib/regexp_parser/scanner/properties/long.yml +0 -594
  89. data/lib/regexp_parser/scanner/properties/short.yml +0 -237
  90. data/lib/regexp_parser/syntax/tokens/anchor.rb +0 -15
  91. data/lib/regexp_parser/syntax/tokens/backref.rb +0 -24
  92. data/lib/regexp_parser/syntax/tokens/character_set.rb +0 -13
  93. data/lib/regexp_parser/syntax/tokens/escape.rb +0 -30
  94. data/lib/regexp_parser/syntax/tokens/meta.rb +0 -13
  95. data/lib/regexp_parser/syntax/tokens/quantifier.rb +0 -35
  96. data/lib/regexp_parser/syntax/tokens/unicode_property.rb +0 -675
  97. data/lib/regexp_parser/syntax/tokens.rb +0 -45
  98. data/spec/expression/base_spec.rb +0 -94
  99. data/spec/expression/clone_spec.rb +0 -120
  100. data/spec/expression/conditional_spec.rb +0 -89
  101. data/spec/expression/free_space_spec.rb +0 -27
  102. data/spec/expression/methods/match_length_spec.rb +0 -161
  103. data/spec/expression/methods/match_spec.rb +0 -25
  104. data/spec/expression/methods/strfregexp_spec.rb +0 -224
  105. data/spec/expression/methods/tests_spec.rb +0 -99
  106. data/spec/expression/methods/traverse_spec.rb +0 -161
  107. data/spec/expression/options_spec.rb +0 -128
  108. data/spec/expression/root_spec.rb +0 -9
  109. data/spec/expression/sequence_spec.rb +0 -9
  110. data/spec/expression/subexpression_spec.rb +0 -50
  111. data/spec/expression/to_h_spec.rb +0 -26
  112. data/spec/expression/to_s_spec.rb +0 -100
  113. data/spec/lexer/all_spec.rb +0 -22
  114. data/spec/lexer/conditionals_spec.rb +0 -53
  115. data/spec/lexer/escapes_spec.rb +0 -14
  116. data/spec/lexer/keep_spec.rb +0 -10
  117. data/spec/lexer/literals_spec.rb +0 -89
  118. data/spec/lexer/nesting_spec.rb +0 -99
  119. data/spec/lexer/refcalls_spec.rb +0 -55
  120. data/spec/parser/all_spec.rb +0 -43
  121. data/spec/parser/alternation_spec.rb +0 -88
  122. data/spec/parser/anchors_spec.rb +0 -17
  123. data/spec/parser/conditionals_spec.rb +0 -179
  124. data/spec/parser/errors_spec.rb +0 -30
  125. data/spec/parser/escapes_spec.rb +0 -121
  126. data/spec/parser/free_space_spec.rb +0 -130
  127. data/spec/parser/groups_spec.rb +0 -108
  128. data/spec/parser/keep_spec.rb +0 -6
  129. data/spec/parser/posix_classes_spec.rb +0 -8
  130. data/spec/parser/properties_spec.rb +0 -115
  131. data/spec/parser/quantifiers_spec.rb +0 -51
  132. data/spec/parser/refcalls_spec.rb +0 -112
  133. data/spec/parser/set/intersections_spec.rb +0 -127
  134. data/spec/parser/set/ranges_spec.rb +0 -111
  135. data/spec/parser/sets_spec.rb +0 -178
  136. data/spec/parser/types_spec.rb +0 -18
  137. data/spec/scanner/all_spec.rb +0 -18
  138. data/spec/scanner/anchors_spec.rb +0 -21
  139. data/spec/scanner/conditionals_spec.rb +0 -128
  140. data/spec/scanner/errors_spec.rb +0 -68
  141. data/spec/scanner/escapes_spec.rb +0 -53
  142. data/spec/scanner/free_space_spec.rb +0 -133
  143. data/spec/scanner/groups_spec.rb +0 -52
  144. data/spec/scanner/keep_spec.rb +0 -10
  145. data/spec/scanner/literals_spec.rb +0 -49
  146. data/spec/scanner/meta_spec.rb +0 -18
  147. data/spec/scanner/properties_spec.rb +0 -64
  148. data/spec/scanner/quantifiers_spec.rb +0 -20
  149. data/spec/scanner/refcalls_spec.rb +0 -36
  150. data/spec/scanner/sets_spec.rb +0 -102
  151. data/spec/scanner/types_spec.rb +0 -14
  152. data/spec/spec_helper.rb +0 -15
  153. data/spec/support/runner.rb +0 -42
  154. data/spec/support/shared_examples.rb +0 -77
  155. data/spec/support/warning_extractor.rb +0 -60
  156. data/spec/syntax/syntax_spec.rb +0 -48
  157. data/spec/syntax/syntax_token_map_spec.rb +0 -23
  158. data/spec/syntax/versions/1.8.6_spec.rb +0 -17
  159. data/spec/syntax/versions/1.9.1_spec.rb +0 -10
  160. data/spec/syntax/versions/1.9.3_spec.rb +0 -9
  161. data/spec/syntax/versions/2.0.0_spec.rb +0 -13
  162. data/spec/syntax/versions/2.2.0_spec.rb +0 -9
  163. data/spec/syntax/versions/aliases_spec.rb +0 -37
  164. data/spec/token/token_spec.rb +0 -85
  165. /data/lib/regexp_parser/expression/classes/{set → character_set}/intersection.rb +0 -0
@@ -1,179 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('Conditional parsing') do
4
- specify('parse conditional') do
5
- regexp = /(?<A>a)(?(<A>)T|F)/
6
-
7
- root = RP.parse(regexp, 'ruby/2.0')
8
- exp = root[1]
9
-
10
- expect(exp).to be_a(Conditional::Expression)
11
-
12
- expect(exp.type).to eq :conditional
13
- expect(exp.token).to eq :open
14
- expect(exp.to_s).to eq '(?(<A>)T|F)'
15
- expect(exp.reference).to eq 'A'
16
- end
17
-
18
- specify('parse conditional condition') do
19
- regexp = /(?<A>a)(?(<A>)T|F)/
20
-
21
- root = RP.parse(regexp, 'ruby/2.0')
22
- exp = root[1].condition
23
-
24
- expect(exp).to be_a(Conditional::Condition)
25
-
26
- expect(exp.type).to eq :conditional
27
- expect(exp.token).to eq :condition
28
- expect(exp.to_s).to eq '(<A>)'
29
- expect(exp.reference).to eq 'A'
30
- expect(exp.referenced_expression.to_s).to eq '(?<A>a)'
31
- end
32
-
33
- specify('parse conditional condition with number ref') do
34
- regexp = /(a)(?(1)T|F)/
35
-
36
- root = RP.parse(regexp, 'ruby/2.0')
37
- exp = root[1].condition
38
-
39
- expect(exp).to be_a(Conditional::Condition)
40
-
41
- expect(exp.type).to eq :conditional
42
- expect(exp.token).to eq :condition
43
- expect(exp.to_s).to eq '(1)'
44
- expect(exp.reference).to eq 1
45
- expect(exp.referenced_expression.to_s).to eq '(a)'
46
- end
47
-
48
- specify('parse conditional nested groups') do
49
- regexp = /((a)|(b)|((?(2)(c(d|e)+)?|(?(3)f|(?(4)(g|(h)(i)))))))/
50
-
51
- root = RP.parse(regexp, 'ruby/2.0')
52
-
53
- expect(root.to_s).to eq regexp.source
54
-
55
- group = root.first
56
- expect(group).to be_instance_of(Group::Capture)
57
-
58
- alt = group.first
59
- expect(alt).to be_instance_of(Alternation)
60
- expect(alt.length).to eq 3
61
-
62
- expect(alt.map(&:first)).to all(be_a Group::Capture)
63
-
64
- subgroup = alt[2].first
65
- conditional = subgroup.first
66
-
67
- expect(conditional).to be_instance_of(Conditional::Expression)
68
- expect(conditional.length).to eq 3
69
-
70
- expect(conditional[0]).to be_instance_of(Conditional::Condition)
71
- expect(conditional[0].to_s).to eq '(2)'
72
-
73
- condition = conditional.condition
74
- expect(condition).to be_instance_of(Conditional::Condition)
75
- expect(condition.to_s).to eq '(2)'
76
-
77
- branches = conditional.branches
78
- expect(branches.length).to eq 2
79
- expect(branches).to be_instance_of(Array)
80
- end
81
-
82
- specify('parse conditional nested') do
83
- regexp = /(a(b(c(d)(e))))(?(1)(?(2)d|(?(3)e|f))|(?(4)(?(5)g|h)))/
84
-
85
- root = RP.parse(regexp, 'ruby/2.0')
86
-
87
- expect(root.to_s).to eq regexp.source
88
-
89
- {
90
- 1 => [2, root[1]],
91
- 2 => [2, root[1][1][0]],
92
- 3 => [2, root[1][1][0][2][0]],
93
- 4 => [1, root[1][2][0]],
94
- 5 => [2, root[1][2][0][1][0]]
95
- }.each do |index, example|
96
- branch_count, exp = example
97
-
98
- expect(exp).to be_instance_of(Conditional::Expression)
99
- expect(exp.condition.to_s).to eq "(#{index})"
100
- expect(exp.branches.length).to eq branch_count
101
- end
102
- end
103
-
104
- specify('parse conditional nested alternation') do
105
- regexp = /(a)(?(1)(b|c|d)|(e|f|g))(h)(?(2)(i|j|k)|(l|m|n))|o|p/
106
-
107
- root = RP.parse(regexp, 'ruby/2.0')
108
-
109
- expect(root.to_s).to eq regexp.source
110
-
111
- expect(root.first).to be_instance_of(Alternation)
112
-
113
- [
114
- [3, 'b|c|d', root[0][0][1][1][0][0]],
115
- [3, 'e|f|g', root[0][0][1][2][0][0]],
116
- [3, 'i|j|k', root[0][0][3][1][0][0]],
117
- [3, 'l|m|n', root[0][0][3][2][0][0]]
118
- ].each do |example|
119
- alt_count, alt_text, exp = example
120
-
121
- expect(exp).to be_instance_of(Alternation)
122
- expect(exp.to_s).to eq alt_text
123
- expect(exp.alternatives.length).to eq alt_count
124
- end
125
- end
126
-
127
- specify('parse conditional extra separator') do
128
- regexp = /(?<A>a)(?(<A>)T|)/
129
-
130
- root = RP.parse(regexp, 'ruby/2.0')
131
- branches = root[1].branches
132
-
133
- expect(branches.length).to eq 2
134
-
135
- seq_1, seq_2 = branches
136
-
137
- [seq_1, seq_2].each do |seq|
138
- expect(seq).to be_a(Sequence)
139
-
140
- expect(seq.type).to eq :expression
141
- expect(seq.token).to eq :sequence
142
- end
143
-
144
- expect(seq_1.to_s).to eq 'T'
145
- expect(seq_2.to_s).to eq ''
146
- end
147
-
148
- specify('parse conditional quantified') do
149
- regexp = /(foo)(?(1)\d|(\w)){42}/
150
-
151
- root = RP.parse(regexp, 'ruby/2.0')
152
- conditional = root[1]
153
-
154
- expect(conditional).to be_quantified
155
- expect(conditional.quantifier.to_s).to eq '{42}'
156
- expect(conditional.to_s).to eq '(?(1)\\d|(\\w)){42}'
157
- expect(conditional.branches.any?(&:quantified?)).to be false
158
- end
159
-
160
- specify('parse conditional branch content quantified') do
161
- regexp = /(foo)(?(1)\d{23}|(\w){42})/
162
-
163
- root = RP.parse(regexp, 'ruby/2.0')
164
- conditional = root[1]
165
-
166
- expect(conditional).not_to be_quantified
167
- expect(conditional.branches.any?(&:quantified?)).to be false
168
- expect(conditional.branches[0][0]).to be_quantified
169
- expect(conditional.branches[0][0].quantifier.to_s).to eq '{23}'
170
- expect(conditional.branches[1][0]).to be_quantified
171
- expect(conditional.branches[1][0].quantifier.to_s).to eq '{42}'
172
- end
173
-
174
- specify('parse conditional excessive branches') do
175
- regexp = '(?<A>a)(?(<A>)T|F|X)'
176
-
177
- expect { RP.parse(regexp, 'ruby/2.0') }.to raise_error(Conditional::TooManyBranches)
178
- end
179
- end
@@ -1,30 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('Parsing errors') do
4
- let(:parser) { Regexp::Parser.new }
5
- before { parser.parse(/foo/) } # initializes ivars
6
-
7
- it('raises UnknownTokenTypeError for unknown token types') do
8
- expect { parser.send(:parse_token, Regexp::Token.new(:foo, :bar)) }
9
- .to raise_error(Regexp::Parser::UnknownTokenTypeError)
10
- end
11
-
12
- RSpec.shared_examples 'UnknownTokenError' do |type, token|
13
- it "raises for unkown tokens of type #{type}" do
14
- expect { parser.send(:parse_token, Regexp::Token.new(type, :foo)) }
15
- .to raise_error(Regexp::Parser::UnknownTokenError)
16
- end
17
- end
18
-
19
- include_examples 'UnknownTokenError', :anchor
20
- include_examples 'UnknownTokenError', :backref
21
- include_examples 'UnknownTokenError', :conditional
22
- include_examples 'UnknownTokenError', :free_space
23
- include_examples 'UnknownTokenError', :group
24
- include_examples 'UnknownTokenError', :meta
25
- include_examples 'UnknownTokenError', :nonproperty
26
- include_examples 'UnknownTokenError', :property
27
- include_examples 'UnknownTokenError', :quantifier
28
- include_examples 'UnknownTokenError', :set
29
- include_examples 'UnknownTokenError', :type
30
- end
@@ -1,121 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('EscapeSequence parsing') do
4
- include_examples 'parse', /a\ac/, 1 => [:escape, :bell, EscapeSequence::Bell]
5
- include_examples 'parse', /a\ec/, 1 => [:escape, :escape, EscapeSequence::AsciiEscape]
6
- include_examples 'parse', /a\fc/, 1 => [:escape, :form_feed, EscapeSequence::FormFeed]
7
- include_examples 'parse', /a\nc/, 1 => [:escape, :newline, EscapeSequence::Newline]
8
- include_examples 'parse', /a\rc/, 1 => [:escape, :carriage, EscapeSequence::Return]
9
- include_examples 'parse', /a\tc/, 1 => [:escape, :tab, EscapeSequence::Tab]
10
- include_examples 'parse', /a\vc/, 1 => [:escape, :vertical_tab, EscapeSequence::VerticalTab]
11
-
12
- # meta character escapes
13
- include_examples 'parse', /a\.c/, 1 => [:escape, :dot, EscapeSequence::Literal]
14
- include_examples 'parse', /a\?c/, 1 => [:escape, :zero_or_one, EscapeSequence::Literal]
15
- include_examples 'parse', /a\*c/, 1 => [:escape, :zero_or_more, EscapeSequence::Literal]
16
- include_examples 'parse', /a\+c/, 1 => [:escape, :one_or_more, EscapeSequence::Literal]
17
- include_examples 'parse', /a\|c/, 1 => [:escape, :alternation, EscapeSequence::Literal]
18
- include_examples 'parse', /a\(c/, 1 => [:escape, :group_open, EscapeSequence::Literal]
19
- include_examples 'parse', /a\)c/, 1 => [:escape, :group_close, EscapeSequence::Literal]
20
- include_examples 'parse', /a\{c/, 1 => [:escape, :interval_open, EscapeSequence::Literal]
21
- include_examples 'parse', /a\}c/, 1 => [:escape, :interval_close, EscapeSequence::Literal]
22
-
23
- # unicode escapes
24
- include_examples 'parse', /a\u0640/, 1 => [:escape, :codepoint, EscapeSequence::Codepoint]
25
- include_examples 'parse', /a\u{41 1F60D}/, 1 => [:escape, :codepoint_list, EscapeSequence::CodepointList]
26
- include_examples 'parse', /a\u{10FFFF}/, 1 => [:escape, :codepoint_list, EscapeSequence::CodepointList]
27
-
28
- # hex escapes
29
- include_examples 'parse', /a\xFF/n, 1 => [:escape, :hex, EscapeSequence::Hex]
30
-
31
- # octal escapes
32
- include_examples 'parse', /a\177/n, 1 => [:escape, :octal, EscapeSequence::Octal]
33
-
34
- specify('parse chars and codepoints') do
35
- root = RP.parse(/\n\?\101\x42\u0043\u{44 45}/)
36
-
37
- expect(root[0].char).to eq "\n"
38
- expect(root[0].codepoint).to eq 10
39
-
40
- expect(root[1].char).to eq '?'
41
- expect(root[1].codepoint).to eq 63
42
-
43
- expect(root[2].char).to eq 'A'
44
- expect(root[2].codepoint).to eq 65
45
-
46
- expect(root[3].char).to eq 'B'
47
- expect(root[3].codepoint).to eq 66
48
-
49
- expect(root[4].char).to eq 'C'
50
- expect(root[4].codepoint).to eq 67
51
-
52
- expect(root[5].chars).to eq %w[D E]
53
- expect(root[5].codepoints).to eq [68, 69]
54
-
55
- expect { root[5].char }.to raise_error(/#chars/)
56
- expect { root[5].codepoint }.to raise_error(/#codepoints/)
57
- end
58
-
59
- specify('parse escape control sequence lower') do
60
- root = RP.parse(/a\\\c2b/)
61
-
62
- expect(root[2]).to be_instance_of(EscapeSequence::Control)
63
- expect(root[2].text).to eq '\\c2'
64
- expect(root[2].char).to eq "\x12"
65
- expect(root[2].codepoint).to eq 18
66
- end
67
-
68
- specify('parse escape control sequence upper') do
69
- root = RP.parse(/\d\\\C-C\w/)
70
-
71
- expect(root[2]).to be_instance_of(EscapeSequence::Control)
72
- expect(root[2].text).to eq '\\C-C'
73
- expect(root[2].char).to eq "\x03"
74
- expect(root[2].codepoint).to eq 3
75
- end
76
-
77
- specify('parse escape meta sequence') do
78
- root = RP.parse(/\Z\\\M-Z/n)
79
-
80
- expect(root[2]).to be_instance_of(EscapeSequence::Meta)
81
- expect(root[2].text).to eq '\\M-Z'
82
- expect(root[2].char).to eq "\u00DA"
83
- expect(root[2].codepoint).to eq 218
84
- end
85
-
86
- specify('parse escape meta control sequence') do
87
- root = RP.parse(/\A\\\M-\C-X/n)
88
-
89
- expect(root[2]).to be_instance_of(EscapeSequence::MetaControl)
90
- expect(root[2].text).to eq '\\M-\\C-X'
91
- expect(root[2].char).to eq "\u0098"
92
- expect(root[2].codepoint).to eq 152
93
- end
94
-
95
- specify('parse lower c meta control sequence') do
96
- root = RP.parse(/\A\\\M-\cX/n)
97
-
98
- expect(root[2]).to be_instance_of(EscapeSequence::MetaControl)
99
- expect(root[2].text).to eq '\\M-\\cX'
100
- expect(root[2].char).to eq "\u0098"
101
- expect(root[2].codepoint).to eq 152
102
- end
103
-
104
- specify('parse escape reverse meta control sequence') do
105
- root = RP.parse(/\A\\\C-\M-X/n)
106
-
107
- expect(root[2]).to be_instance_of(EscapeSequence::MetaControl)
108
- expect(root[2].text).to eq '\\C-\\M-X'
109
- expect(root[2].char).to eq "\u0098"
110
- expect(root[2].codepoint).to eq 152
111
- end
112
-
113
- specify('parse escape reverse lower c meta control sequence') do
114
- root = RP.parse(/\A\\\c\M-X/n)
115
-
116
- expect(root[2]).to be_instance_of(EscapeSequence::MetaControl)
117
- expect(root[2].text).to eq '\\c\\M-X'
118
- expect(root[2].char).to eq "\u0098"
119
- expect(root[2].codepoint).to eq 152
120
- end
121
- end
@@ -1,130 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('FreeSpace parsing') do
4
- specify('parse free space spaces') do
5
- regexp = /a ? b * c + d{2,4}/x
6
- root = RP.parse(regexp)
7
-
8
- 0.upto(6) do |i|
9
- if i.odd?
10
- expect(root[i]).to be_instance_of(WhiteSpace)
11
- expect(root[i].text).to eq ' '
12
- else
13
- expect(root[i]).to be_instance_of(Literal)
14
- expect(root[i]).to be_quantified
15
- end
16
- end
17
- end
18
-
19
- specify('parse non free space literals') do
20
- regexp = /a b c d/
21
- root = RP.parse(regexp)
22
-
23
- expect(root.first).to be_instance_of(Literal)
24
- expect(root.first.text).to eq 'a b c d'
25
- end
26
-
27
- specify('parse free space comments') do
28
- regexp = /
29
- a ? # One letter
30
- b {2,5} # Another one
31
- [c-g] + # A set
32
- (h|i|j) | # A group
33
- klm *
34
- nop +
35
- /x
36
-
37
- root = RP.parse(regexp)
38
-
39
- alt = root.first
40
- expect(alt).to be_instance_of(Alternation)
41
-
42
- alt_1 = alt.alternatives.first
43
- expect(alt_1).to be_instance_of(Alternative)
44
- expect(alt_1.length).to eq 15
45
-
46
- [0, 2, 4, 6, 8, 12, 14].each do |i|
47
- expect(alt_1[i]).to be_instance_of(WhiteSpace)
48
- end
49
-
50
- [3, 7, 11].each { |i| expect(alt_1[i].class).to eq Comment }
51
-
52
- alt_2 = alt.alternatives.last
53
- expect(alt_2).to be_instance_of(Alternative)
54
- expect(alt_2.length).to eq 7
55
-
56
- [0, 2, 4, 6].each { |i| expect(alt_2[i].class).to eq WhiteSpace }
57
-
58
- expect(alt_2[1]).to be_instance_of(Comment)
59
- end
60
-
61
- specify('parse free space nested comments') do
62
- regexp = /
63
- # Group one
64
- (
65
- abc # Comment one
66
- \d? # Optional \d
67
- )+
68
-
69
- # Group two
70
- (
71
- def # Comment two
72
- \s? # Optional \s
73
- )?
74
- /x
75
-
76
- root = RP.parse(regexp)
77
-
78
- top_comment_1 = root[1]
79
- expect(top_comment_1).to be_instance_of(Comment)
80
- expect(top_comment_1.text).to eq "# Group one\n"
81
- expect(top_comment_1.starts_at).to eq 7
82
-
83
- top_comment_2 = root[5]
84
- expect(top_comment_2).to be_instance_of(Comment)
85
- expect(top_comment_2.text).to eq "# Group two\n"
86
- expect(top_comment_2.starts_at).to eq 95
87
-
88
- [3, 7].each do |g,|
89
- group = root[g]
90
-
91
- [3, 7].each do |c|
92
- comment = group[c]
93
- expect(comment).to be_instance_of(Comment)
94
- expect(comment.text.length).to eq 14
95
- end
96
- end
97
- end
98
-
99
- specify('parse free space quantifiers') do
100
- regexp = /
101
- a
102
- # comment 1
103
- ?
104
- (
105
- b # comment 2
106
- # comment 3
107
- +
108
- )
109
- # comment 4
110
- *
111
- /x
112
-
113
- root = RP.parse(regexp)
114
-
115
- literal_1 = root[1]
116
- expect(literal_1).to be_instance_of(Literal)
117
- expect(literal_1).to be_quantified
118
- expect(literal_1.quantifier.token).to eq :zero_or_one
119
-
120
- group = root[5]
121
- expect(group).to be_instance_of(Group::Capture)
122
- expect(group).to be_quantified
123
- expect(group.quantifier.token).to eq :zero_or_more
124
-
125
- literal_2 = group[1]
126
- expect(literal_2).to be_instance_of(Literal)
127
- expect(literal_2).to be_quantified
128
- expect(literal_2.quantifier.token).to eq :one_or_more
129
- end
130
- end
@@ -1,108 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('Group parsing') do
4
- include_examples 'parse', /(?=abc)(?!def)/,
5
- 0 => [:assertion, :lookahead, Assertion::Lookahead],
6
- 1 => [:assertion, :nlookahead, Assertion::NegativeLookahead]
7
-
8
- include_examples 'parse', /(?<=abc)(?<!def)/,
9
- 0 => [:assertion, :lookbehind, Assertion::Lookbehind],
10
- 1 => [:assertion, :nlookbehind, Assertion::NegativeLookbehind]
11
-
12
- include_examples 'parse', /a(?# is for apple)b(?# for boy)c(?# cat)/,
13
- 1 => [:group, :comment, Group::Comment],
14
- 3 => [:group, :comment, Group::Comment],
15
- 5 => [:group, :comment, Group::Comment]
16
-
17
- if ruby_version_at_least('2.4.1')
18
- include_examples 'parse', 'a(?~b)c(?~d)e',
19
- 1 => [:group, :absence, Group::Absence],
20
- 3 => [:group, :absence, Group::Absence]
21
- end
22
-
23
- include_examples 'parse', /(?m:a)/,
24
- 0 => [:group, :options, Group::Options, options: { m: true }, option_changes: { m: true }]
25
-
26
- # self-defeating group option
27
- include_examples 'parse', /(?m-m:a)/,
28
- 0 => [:group, :options, Group::Options, options: {}, option_changes: { m: false }]
29
-
30
- # activate one option in nested group
31
- include_examples 'parse', /(?x-mi:a(?m:b))/,
32
- 0 => [:group, :options, Group::Options, options: { x: true }, option_changes: { i: false, m: false, x: true }],
33
- [0, 1] => [:group, :options, Group::Options, options: { m: true, x: true }, option_changes: { m: true }]
34
-
35
- # deactivate one option in nested group
36
- include_examples 'parse', /(?ix-m:a(?-i:b))/,
37
- 0 => [:group, :options, Group::Options, options: { i: true, x: true }, option_changes: { i: true, m: false, x: true }],
38
- [0, 1] => [:group, :options, Group::Options, options: { x: true }, option_changes: { i: false }]
39
-
40
- # invert all options in nested group
41
- include_examples 'parse', /(?xi-m:a(?m-ix:b))/,
42
- 0 => [:group, :options, Group::Options, options: { i: true, x: true }, option_changes: { i: true, m: false, x: true }],
43
- [0, 1] => [:group, :options, Group::Options, options: { m: true }, option_changes: { i: false, m: true, x: false }]
44
-
45
- # nested options affect literal subexpressions
46
- include_examples 'parse', /(?x-mi:a(?m:b))/,
47
- [0, 0] => [:literal, :literal, Literal, text: 'a', options: { x: true }],
48
- [0, 1, 0] => [:literal, :literal, Literal, text: 'b', options: { m: true, x: true }]
49
-
50
- # option switching group
51
- include_examples 'parse', /a(?i-m)b/m,
52
- 0 => [:literal, :literal, Literal, text: 'a', options: { m: true }],
53
- 1 => [:group, :options_switch, Group::Options, options: { i: true }, option_changes: { i: true, m: false }],
54
- 2 => [:literal, :literal, Literal, text: 'b', options: { i: true }]
55
-
56
- # option switch in group
57
- include_examples 'parse', /(a(?i-m)b)c/m,
58
- 0 => [:group, :capture, Group::Capture, options: { m: true }],
59
- [0, 0] => [:literal, :literal, Literal, text: 'a', options: { m: true }],
60
- [0, 1] => [:group, :options_switch, Group::Options, options: { i: true }, option_changes: { i: true, m: false }],
61
- [0, 2] => [:literal, :literal, Literal, text: 'b', options: { i: true }],
62
- 1 => [:literal, :literal, Literal, text: 'c', options: { m: true }]
63
-
64
- # nested option switch in group
65
- include_examples 'parse', /((?i-m)(a(?-i)b))/m,
66
- [0, 1] => [:group, :capture, Group::Capture, options: { i: true }],
67
- [0, 1, 0] => [:literal, :literal, Literal, text: 'a', options: { i: true }],
68
- [0, 1, 1] => [:group, :options_switch, Group::Options, options: {}, option_changes: { i: false }],
69
- [0, 1, 2] => [:literal, :literal, Literal, text: 'b', options: {}]
70
-
71
- # options dau
72
- include_examples 'parse', /(?dua:abc)/,
73
- 0 => [:group, :options, Group::Options, options: { a: true }, option_changes: { a: true }]
74
-
75
- # nested options dau
76
- include_examples 'parse', /(?u:a(?d:b))/,
77
- 0 => [:group, :options, Group::Options, options: { u: true }, option_changes: { u: true }],
78
- [0, 1] => [:group, :options, Group::Options, options: { d: true }, option_changes: { d: true, u: false }],
79
- [0, 1, 0] => [:literal, :literal, Literal, text: 'b', options: { d: true }]
80
-
81
- # nested options da
82
- include_examples 'parse', /(?di-xm:a(?da-x:b))/,
83
- 0 => [:group, :options, Group::Options, options: { d: true, i:true }],
84
- [0, 1] => [:group, :options, Group::Options, options: { a: true, i: true }, option_changes: { a: true, d: false, x: false}],
85
- [0, 1, 0] => [:literal, :literal, Literal, text: 'b', options: { a: true, i: true }]
86
-
87
- specify('parse group number') do
88
- root = RP.parse(/(a)(?=b)((?:c)(d|(e)))/)
89
-
90
- expect(root[0].number).to eq 1
91
- expect(root[1]).not_to respond_to(:number)
92
- expect(root[2].number).to eq 2
93
- expect(root[2][0]).not_to respond_to(:number)
94
- expect(root[2][1].number).to eq 3
95
- expect(root[2][1][0][1][0].number).to eq 4
96
- end
97
-
98
- specify('parse group number at level') do
99
- root = RP.parse(/(a)(?=b)((?:c)(d|(e)))/)
100
-
101
- expect(root[0].number_at_level).to eq 1
102
- expect(root[1]).not_to respond_to(:number_at_level)
103
- expect(root[2].number_at_level).to eq 2
104
- expect(root[2][0]).not_to respond_to(:number_at_level)
105
- expect(root[2][1].number_at_level).to eq 1
106
- expect(root[2][1][0][1][0].number_at_level).to eq 1
107
- end
108
- end
@@ -1,6 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('Keep parsing') do
4
- include_examples 'parse', /ab\Kcd/, 1 => [:keep, :mark, Keep::Mark, text: '\K']
5
- include_examples 'parse', /(a\K)/, [0, 1] => [:keep, :mark, Keep::Mark, text: '\K']
6
- end
@@ -1,8 +0,0 @@
1
- require 'spec_helper'
2
-
3
- RSpec.describe('PosixClass parsing') do
4
- include_examples 'parse', /[[:word:]]/, [0, 0] => [:posixclass, :word, PosixClass,
5
- name: 'word', text: '[:word:]', negative?: false]
6
- include_examples 'parse', /[[:^word:]]/, [0, 0] => [:nonposixclass, :word, PosixClass,
7
- name: 'word', text: '[:^word:]', negative?: true]
8
- end