regexp_parser 1.7.0 → 2.8.3

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.
Files changed (165) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +8 -2
  3. data/LICENSE +1 -1
  4. data/Rakefile +6 -70
  5. data/lib/regexp_parser/error.rb +4 -0
  6. data/lib/regexp_parser/expression/base.rb +76 -0
  7. data/lib/regexp_parser/expression/classes/alternation.rb +1 -1
  8. data/lib/regexp_parser/expression/classes/anchor.rb +0 -2
  9. data/lib/regexp_parser/expression/classes/{backref.rb → backreference.rb} +22 -2
  10. data/lib/regexp_parser/expression/classes/{set → character_set}/range.rb +4 -8
  11. data/lib/regexp_parser/expression/classes/{set.rb → character_set.rb} +3 -4
  12. data/lib/regexp_parser/expression/classes/{type.rb → character_type.rb} +0 -2
  13. data/lib/regexp_parser/expression/classes/conditional.rb +11 -5
  14. data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb} +15 -7
  15. data/lib/regexp_parser/expression/classes/free_space.rb +5 -5
  16. data/lib/regexp_parser/expression/classes/group.rb +28 -15
  17. data/lib/regexp_parser/expression/classes/keep.rb +2 -0
  18. data/lib/regexp_parser/expression/classes/literal.rb +1 -5
  19. data/lib/regexp_parser/expression/classes/posix_class.rb +5 -1
  20. data/lib/regexp_parser/expression/classes/root.rb +4 -19
  21. data/lib/regexp_parser/expression/classes/{property.rb → unicode_property.rb} +5 -3
  22. data/lib/regexp_parser/expression/methods/construct.rb +41 -0
  23. data/lib/regexp_parser/expression/methods/human_name.rb +43 -0
  24. data/lib/regexp_parser/expression/methods/match_length.rb +11 -7
  25. data/lib/regexp_parser/expression/methods/parts.rb +23 -0
  26. data/lib/regexp_parser/expression/methods/printing.rb +26 -0
  27. data/lib/regexp_parser/expression/methods/strfregexp.rb +1 -1
  28. data/lib/regexp_parser/expression/methods/tests.rb +47 -1
  29. data/lib/regexp_parser/expression/methods/traverse.rb +34 -18
  30. data/lib/regexp_parser/expression/quantifier.rb +57 -17
  31. data/lib/regexp_parser/expression/sequence.rb +11 -47
  32. data/lib/regexp_parser/expression/sequence_operation.rb +4 -9
  33. data/lib/regexp_parser/expression/shared.rb +111 -0
  34. data/lib/regexp_parser/expression/subexpression.rb +27 -19
  35. data/lib/regexp_parser/expression.rb +14 -141
  36. data/lib/regexp_parser/lexer.rb +83 -41
  37. data/lib/regexp_parser/parser.rb +371 -429
  38. data/lib/regexp_parser/scanner/char_type.rl +11 -11
  39. data/lib/regexp_parser/scanner/errors/premature_end_error.rb +8 -0
  40. data/lib/regexp_parser/scanner/errors/scanner_error.rb +6 -0
  41. data/lib/regexp_parser/scanner/errors/validation_error.rb +63 -0
  42. data/lib/regexp_parser/scanner/properties/long.csv +633 -0
  43. data/lib/regexp_parser/scanner/properties/short.csv +248 -0
  44. data/lib/regexp_parser/scanner/property.rl +4 -4
  45. data/lib/regexp_parser/scanner/scanner.rl +303 -368
  46. data/lib/regexp_parser/scanner.rb +1423 -1674
  47. data/lib/regexp_parser/syntax/any.rb +2 -7
  48. data/lib/regexp_parser/syntax/base.rb +92 -67
  49. data/lib/regexp_parser/syntax/token/anchor.rb +15 -0
  50. data/lib/regexp_parser/syntax/{tokens → token}/assertion.rb +2 -2
  51. data/lib/regexp_parser/syntax/token/backreference.rb +33 -0
  52. data/lib/regexp_parser/syntax/token/character_set.rb +16 -0
  53. data/lib/regexp_parser/syntax/{tokens → token}/character_type.rb +3 -3
  54. data/lib/regexp_parser/syntax/{tokens → token}/conditional.rb +3 -3
  55. data/lib/regexp_parser/syntax/token/escape.rb +33 -0
  56. data/lib/regexp_parser/syntax/{tokens → token}/group.rb +7 -7
  57. data/lib/regexp_parser/syntax/{tokens → token}/keep.rb +1 -1
  58. data/lib/regexp_parser/syntax/token/meta.rb +20 -0
  59. data/lib/regexp_parser/syntax/{tokens → token}/posix_class.rb +3 -3
  60. data/lib/regexp_parser/syntax/token/quantifier.rb +35 -0
  61. data/lib/regexp_parser/syntax/token/unicode_property.rb +733 -0
  62. data/lib/regexp_parser/syntax/token/virtual.rb +11 -0
  63. data/lib/regexp_parser/syntax/token.rb +45 -0
  64. data/lib/regexp_parser/syntax/version_lookup.rb +19 -36
  65. data/lib/regexp_parser/syntax/versions/1.8.6.rb +13 -20
  66. data/lib/regexp_parser/syntax/versions/1.9.1.rb +10 -17
  67. data/lib/regexp_parser/syntax/versions/1.9.3.rb +3 -10
  68. data/lib/regexp_parser/syntax/versions/2.0.0.rb +8 -15
  69. data/lib/regexp_parser/syntax/versions/2.2.0.rb +3 -9
  70. data/lib/regexp_parser/syntax/versions/2.3.0.rb +3 -9
  71. data/lib/regexp_parser/syntax/versions/2.4.0.rb +3 -9
  72. data/lib/regexp_parser/syntax/versions/2.4.1.rb +2 -8
  73. data/lib/regexp_parser/syntax/versions/2.5.0.rb +3 -9
  74. data/lib/regexp_parser/syntax/versions/2.6.0.rb +3 -9
  75. data/lib/regexp_parser/syntax/versions/2.6.2.rb +3 -9
  76. data/lib/regexp_parser/syntax/versions/2.6.3.rb +3 -9
  77. data/lib/regexp_parser/syntax/versions/3.1.0.rb +4 -0
  78. data/lib/regexp_parser/syntax/versions/3.2.0.rb +4 -0
  79. data/lib/regexp_parser/syntax/versions.rb +3 -1
  80. data/lib/regexp_parser/syntax.rb +8 -6
  81. data/lib/regexp_parser/token.rb +9 -20
  82. data/lib/regexp_parser/version.rb +1 -1
  83. data/lib/regexp_parser.rb +0 -2
  84. data/regexp_parser.gemspec +19 -23
  85. metadata +52 -171
  86. data/CHANGELOG.md +0 -349
  87. data/README.md +0 -470
  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
@@ -10,17 +10,17 @@
10
10
  # --------------------------------------------------------------------------
11
11
  char_type := |*
12
12
  char_type_char {
13
- case text = text(data, ts, te, 1).first
14
- when '\d'; emit(:type, :digit, text, ts - 1, te)
15
- when '\D'; emit(:type, :nondigit, text, ts - 1, te)
16
- when '\h'; emit(:type, :hex, text, ts - 1, te)
17
- when '\H'; emit(:type, :nonhex, text, ts - 1, te)
18
- when '\s'; emit(:type, :space, text, ts - 1, te)
19
- when '\S'; emit(:type, :nonspace, text, ts - 1, te)
20
- when '\w'; emit(:type, :word, text, ts - 1, te)
21
- when '\W'; emit(:type, :nonword, text, ts - 1, te)
22
- when '\R'; emit(:type, :linebreak, text, ts - 1, te)
23
- when '\X'; emit(:type, :xgrapheme, text, ts - 1, te)
13
+ case text = copy(data, ts-1, te)
14
+ when '\d'; emit(:type, :digit, text)
15
+ when '\D'; emit(:type, :nondigit, text)
16
+ when '\h'; emit(:type, :hex, text)
17
+ when '\H'; emit(:type, :nonhex, text)
18
+ when '\s'; emit(:type, :space, text)
19
+ when '\S'; emit(:type, :nonspace, text)
20
+ when '\w'; emit(:type, :word, text)
21
+ when '\W'; emit(:type, :nonword, text)
22
+ when '\R'; emit(:type, :linebreak, text)
23
+ when '\X'; emit(:type, :xgrapheme, text)
24
24
  end
25
25
  fret;
26
26
  };
@@ -0,0 +1,8 @@
1
+ class Regexp::Scanner
2
+ # Unexpected end of pattern
3
+ class PrematureEndError < ScannerError
4
+ def initialize(where = '')
5
+ super "Premature end of pattern at #{where}"
6
+ end
7
+ end
8
+ end
@@ -0,0 +1,6 @@
1
+ require 'regexp_parser/error'
2
+
3
+ class Regexp::Scanner
4
+ # General scanner error (catch all)
5
+ class ScannerError < Regexp::Parser::Error; end
6
+ end
@@ -0,0 +1,63 @@
1
+ class Regexp::Scanner
2
+ # Base for all scanner validation errors
3
+ class ValidationError < ScannerError
4
+ # Centralizes and unifies the handling of validation related errors.
5
+ def self.for(type, problem, reason = nil)
6
+ types.fetch(type).new(problem, reason)
7
+ end
8
+
9
+ def self.types
10
+ @types ||= {
11
+ backref: InvalidBackrefError,
12
+ group: InvalidGroupError,
13
+ group_option: InvalidGroupOption,
14
+ posix_class: UnknownPosixClassError,
15
+ property: UnknownUnicodePropertyError,
16
+ sequence: InvalidSequenceError,
17
+ }
18
+ end
19
+ end
20
+
21
+ # Invalid sequence format. Used for escape sequences, mainly.
22
+ class InvalidSequenceError < ValidationError
23
+ def initialize(what = 'sequence', where = '')
24
+ super "Invalid #{what} at #{where}"
25
+ end
26
+ end
27
+
28
+ # Invalid group. Used for named groups.
29
+ class InvalidGroupError < ValidationError
30
+ def initialize(what, reason)
31
+ super "Invalid #{what}, #{reason}."
32
+ end
33
+ end
34
+
35
+ # Invalid groupOption. Used for inline options.
36
+ # TODO: should become InvalidGroupOptionError in v3.0.0 for consistency
37
+ class InvalidGroupOption < ValidationError
38
+ def initialize(option, text)
39
+ super "Invalid group option #{option} in #{text}"
40
+ end
41
+ end
42
+
43
+ # Invalid back reference. Used for name a number refs/calls.
44
+ class InvalidBackrefError < ValidationError
45
+ def initialize(what, reason)
46
+ super "Invalid back reference #{what}, #{reason}"
47
+ end
48
+ end
49
+
50
+ # The property name was not recognized by the scanner.
51
+ class UnknownUnicodePropertyError < ValidationError
52
+ def initialize(name, _)
53
+ super "Unknown unicode character property name #{name}"
54
+ end
55
+ end
56
+
57
+ # The POSIX class name was not recognized by the scanner.
58
+ class UnknownPosixClassError < ValidationError
59
+ def initialize(text, _)
60
+ super "Unknown POSIX class #{text}"
61
+ end
62
+ end
63
+ end