Module: Regexp::Parser

Includes:
Expression, Syntax
Defined in:
lib/regexp_parser/parser.rb,
lib/regexp_parser/version.rb

Defined Under Namespace

Classes: ParserError, UnknownTokenError, UnknownTokenTypeError

Constant Summary collapse

VERSION = 
'0.2.0'

Constants included from Syntax

Syntax::SYNTAX_SPEC_ROOT

Class Method Summary collapse

Methods included from Syntax

load, new

Methods included from Expression

parsed

Class Method Details

.anchor(token) ⇒ Object 



278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
 
# File 'lib/regexp_parser/parser.rb', line 278

def self.anchor(token)
  case token.token
  when :bol
    @node << Anchor::BeginningOfLine.new(token)
  when :eol
    @node << Anchor::EndOfLine.new(token)
  when :bos
    @node << Anchor::BOS.new(token)
  when :eos
    @node << Anchor::EOS.new(token)
  when :eos_ob_eol
    @node << Anchor::EOSobEOL.new(token)
  when :word_boundary
    @node << Anchor::WordBoundary.new(token)
  when :nonword_boundary
    @node << Anchor::NonWordBoundary.new(token)
  when :match_start
    @node << Anchor::MatchStart.new(token)
  else
    raise UnknownTokenError.new('Anchor', token)
  end
end

.append_set(token) ⇒ Object 



502
503
504
 
# File 'lib/regexp_parser/parser.rb', line 502

def self.append_set(token)
  @set << token.text
end

.backref(token) ⇒ Object 



129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
# File 'lib/regexp_parser/parser.rb', line 129

def self.backref(token)
  case token.token
  when :name_ref
    @node << Backreference::Name.new(token)
  when :name_nest_ref
    @node << Backreference::NameNestLevel.new(token)
  when :name_call
    @node << Backreference::NameCall.new(token)
  when :number, :number_ref
    @node << Backreference::Number.new(token)
  when :number_rel_ref
    @node << Backreference::NumberRelative.new(token)
  when :number_nest_ref
    @node << Backreference::NumberNestLevel.new(token)
  when :number_call
    @node << Backreference::NumberCall.new(token)
  when :number_rel_call
    @node << Backreference::NumberCallRelative.new(token)
  else
    raise UnknownTokenError.new('Backreference', token)
  end
end

.close_group ⇒ Object 



481
482
483
484
485
486
 
# File 'lib/regexp_parser/parser.rb', line 481

def self.close_group
  @nesting.pop

  @node = @nesting.last
  @node = @node.last if @node.last and @node.last.is_a?(Alternation)
end

.close_set(token) ⇒ Object 



506
507
508
 
# File 'lib/regexp_parser/parser.rb', line 506

def self.close_set(token)
  @set.close
end

.conditional(token) ⇒ Object 



175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
 
# File 'lib/regexp_parser/parser.rb', line 175

def self.conditional(token)
  case token.token
  when :open
    nest_conditional(Conditional::Expression.new(token))
  when :condition
    @conditional_nesting.last.condition(Conditional::Condition.new(token))
    @conditional_nesting.last.branch
  when :separator
    @conditional_nesting.last.branch
    @node = @conditional_nesting.last.branches.last
  when :close
    @conditional_nesting.pop

    @node = if @conditional_nesting.empty?
      @nesting.last
    else
      @conditional_nesting.last
    end

  else
    raise UnknownTokenError.new('Conditional', token)
  end
end

.escape(token) ⇒ Object 



301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
 
# File 'lib/regexp_parser/parser.rb', line 301

def self.escape(token)
  case token.token

  when :backspace
    @node << EscapeSequence::Backspace.new(token)

  when :escape
    @node << EscapeSequence::AsciiEscape.new(token)
  when :bell
    @node << EscapeSequence::Bell.new(token)
  when :form_feed
    @node << EscapeSequence::FormFeed.new(token)
  when :newline
    @node << EscapeSequence::Newline.new(token)
  when :carriage
    @node << EscapeSequence::Return.new(token)
  when :space
    @node << EscapeSequence::Space.new(token)
  when :tab
    @node << EscapeSequence::Tab.new(token)
  when :vertical_tab
    @node << EscapeSequence::VerticalTab.new(token)

  when :control
    @node << EscapeSequence::Control.new(token)

  when :meta_sequence
    if token.text =~ /\A\\M-\\C/
      @node << EscapeSequence::MetaControl.new(token)
    else
      @node << EscapeSequence::Meta.new(token)
    end

  else
    # treating everything else as a literal
    @node << EscapeSequence::Literal.new(token)
  end
end

.free_space(token) ⇒ Object 



345
346
347
348
349
350
351
352
353
354
355
356
357
358
 
# File 'lib/regexp_parser/parser.rb', line 345

def self.free_space(token)
  case token.token
  when :comment
    @node << Comment.new(token)
  when :whitespace
    if @node.last and @node.last.is_a?(WhiteSpace)
      @node.last.merge(WhiteSpace.new(token))
    else
      @node << WhiteSpace.new(token)
    end
  else
    raise UnknownTokenError.new('FreeSpace', token)
  end
end

.group(token) ⇒ Object 



425
426
427
428
429
430
431
432
433
434
435
436
 
# File 'lib/regexp_parser/parser.rb', line 425

def self.group(token)
  case token.token
  when :options
    options(token)
  when :close
    close_group
  when :comment
    @node << Group::Comment.new(token)
  else
    open_group(token)
  end
end

.interval(target_node, token) ⇒ Object 



409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
 
# File 'lib/regexp_parser/parser.rb', line 409

def self.interval(target_node, token)
  text = token.text
  mchr = text[text.length-1].chr =~ /[?+]/ ? text[text.length-1].chr : nil
  mode = case mchr
  when '?'; text.chop!; :reluctant
  when '+'; text.chop!; :possessive
  else :greedy
  end

  range = text.gsub(/\{|\}/, '').split(',', 2).each {|i| i.strip}
  min = range[0].empty? ? 0 : range[0]
  max = range[1] ? (range[1].empty? ? -1 : range[1]) : min

  target_node.quantify(:interval, text, min.to_i, max.to_i, mode)
end

.keep(token) ⇒ Object 



341
342
343
 
# File 'lib/regexp_parser/parser.rb', line 341

def self.keep(token)
  @node << Keep::Mark.new(token)
end

.meta(token) ⇒ Object 



99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/regexp_parser/parser.rb', line 99

def self.meta(token)
  case token.token
  when :dot
    @node << CharacterType::Any.new(token)
  when :alternation
    unless @node.token == :alternation
      unless @node.last.is_a?(Alternation)
        alt = Alternation.new(token)
        seq = Alternative.new(alt.level, alt.set_level, alt.conditional_level)

        while @node.expressions.last
          seq.insert @node.expressions.pop
        end
        alt.alternative(seq)

        @node << alt
        @node = alt
        @node.alternative
      else
        @node = @node.last
        @node.alternative
      end
    else
      @node.alternative
    end
  else
    raise UnknownTokenError.new('Meta', token)
  end
end

.negate_set ⇒ Object 



498
499
500
 
# File 'lib/regexp_parser/parser.rb', line 498

def self.negate_set
  @set.negate
end

.nest(exp) ⇒ Object 



37
38
39
40
41
42
 
# File 'lib/regexp_parser/parser.rb', line 37

def self.nest(exp)
  @nesting.push exp

  @node << exp
  @node  = exp
end

.nest_conditional(exp) ⇒ Object 



44
45
46
47
48
49
 
# File 'lib/regexp_parser/parser.rb', line 44

def self.nest_conditional(exp)
  @conditional_nesting.push exp

  @node << exp
  @node  = exp
end

.open_group(token) ⇒ Object 



454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
 
# File 'lib/regexp_parser/parser.rb', line 454

def self.open_group(token)
  case token.token
  when :passive
    exp = Group::Passive.new(token)
  when :atomic
    exp = Group::Atomic.new(token)
  when :named
    exp = Group::Named.new(token)
  when :capture
    exp = Group::Capture.new(token)

  when :lookahead
    exp = Assertion::Lookahead.new(token)
  when :nlookahead
    exp = Assertion::NegativeLookahead.new(token)
  when :lookbehind
    exp = Assertion::Lookbehind.new(token)
  when :nlookbehind
    exp = Assertion::NegativeLookbehind.new(token)

  else
    raise UnknownTokenError.new('Group type open', token)
  end

  nest(exp)
end

.open_set(token) ⇒ Object 



488
489
490
491
492
493
494
495
496
 
# File 'lib/regexp_parser/parser.rb', line 488

def self.open_set(token)
  token.token = :character

  if token.type == :subset
    @set << CharacterSubSet.new(token)
  else
    @node << (@set = CharacterSet.new(token))
  end
end

.options(token) ⇒ Object 



438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
 
# File 'lib/regexp_parser/parser.rb', line 438

def self.options(token)
  opt = token.text.split('-', 2)

  exp = Group::Options.new(token)
  exp.options = {
    :m => opt[0].include?('m') ? true : false,
    :i => opt[0].include?('i') ? true : false,
    :x => opt[0].include?('x') ? true : false,
    :d => opt[0].include?('d') ? true : false,
    :a => opt[0].include?('a') ? true : false,
    :u => opt[0].include?('u') ? true : false
  }

  nest(exp)
end

.parse(input, syntax = "ruby/#{RUBY_VERSION}", &block) ⇒ Object 



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
 
# File 'lib/regexp_parser/parser.rb', line 21

def self.parse(input, syntax = "ruby/#{RUBY_VERSION}", &block)
  @nesting = [@root = @node = Root.new]

  @conditional_nesting = []

  Regexp::Lexer.scan(input, syntax) do |token|
    parse_token token
  end

  if block_given?
    block.call @root
  else
    @root
  end
end

.parse_token(token) ⇒ Object 



51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/regexp_parser/parser.rb', line 51

def self.parse_token(token)
  case token.type
  when :meta;         meta(token)
  when :quantifier;   quantifier(token)
  when :anchor;       anchor(token)
  when :escape;       escape(token)
  when :group;        group(token)
  when :assertion;    group(token)
  when :set, :subset; set(token)
  when :type;         type(token)
  when :backref;      backref(token)
  when :conditional;  conditional(token)
  when :keep;         keep(token)

  when :property, :nonproperty
    property(token)

  when :literal
    @node << Literal.new(token)
  when :free_space
    free_space(token)

  else
    raise UnknownTokenTypeError.new(token.type, token)
  end
end

.property(token) ⇒ Object 



199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
 
# File 'lib/regexp_parser/parser.rb', line 199

def self.property(token)
  include Regexp::Expression::UnicodeProperty

  case token.token
  when :alnum;            @node << Alnum.new(token)
  when :alpha;            @node << Alpha.new(token)
  when :any;              @node << Any.new(token)
  when :ascii;            @node << Ascii.new(token)
  when :blank;            @node << Blank.new(token)
  when :cntrl;            @node << Cntrl.new(token)
  when :digit;            @node << Digit.new(token)
  when :graph;            @node << Graph.new(token)
  when :lower;            @node << Lower.new(token)
  when :print;            @node << Print.new(token)
  when :punct;            @node << Punct.new(token)
  when :space;            @node << Space.new(token)
  when :upper;            @node << Upper.new(token)
  when :word;             @node << Word.new(token)
  when :xdigit;           @node << Xdigit.new(token)
  when :newline;          @node << Newline.new(token)

  when :letter_any;       @node << Letter::Any.new(token)
  when :letter_uppercase; @node << Letter::Uppercase.new(token)
  when :letter_lowercase; @node << Letter::Lowercase.new(token)
  when :letter_titlecase; @node << Letter::Titlecase.new(token)
  when :letter_modifier;  @node << Letter::Modifier.new(token)
  when :letter_other;     @node << Letter::Other.new(token)

  when :mark_any;         @node << Mark::Any.new(token)
  when :mark_nonspacing;  @node << Mark::Nonspacing.new(token)
  when :mark_spacing;     @node << Mark::Spacing.new(token)
  when :mark_enclosing;   @node << Mark::Enclosing.new(token)

  when :number_any;       @node << Number::Any.new(token)
  when :number_decimal;   @node << Number::Decimal.new(token)
  when :number_letter;    @node << Number::Letter.new(token)
  when :number_other;     @node << Number::Other.new(token)

  when :punct_any;        @node << Punctuation::Any.new(token)
  when :punct_connector;  @node << Punctuation::Connector.new(token)
  when :punct_dash;       @node << Punctuation::Dash.new(token)
  when :punct_open;       @node << Punctuation::Open.new(token)
  when :punct_close;      @node << Punctuation::Close.new(token)
  when :punct_initial;    @node << Punctuation::Initial.new(token)
  when :punct_final;      @node << Punctuation::Final.new(token)
  when :punct_other;      @node << Punctuation::Other.new(token)

  when :separator_any;    @node << Separator::Any.new(token)
  when :separator_space;  @node << Separator::Space.new(token)
  when :separator_line;   @node << Separator::Line.new(token)
  when :separator_para;   @node << Separator::Paragraph.new(token)

  when :symbol_any;       @node << Symbol::Any.new(token)
  when :symbol_math;      @node << Symbol::Math.new(token)
  when :symbol_currency;  @node << Symbol::Currency.new(token)
  when :symbol_modifier;  @node << Symbol::Modifier.new(token)
  when :symbol_other;     @node << Symbol::Other.new(token)

  when :other;            @node << Codepoint::Any.new(token)
  when :control;          @node << Codepoint::Control.new(token)
  when :format;           @node << Codepoint::Format.new(token)
  when :surrogate;        @node << Codepoint::Surrogate.new(token)
  when :private_use;      @node << Codepoint::PrivateUse.new(token)
  when :unassigned;       @node << Codepoint::Unassigned.new(token)

  when *Token::UnicodeProperty::Age
    @node << Age.new(token)

  when *Token::UnicodeProperty::Derived
    @node << Derived.new(token)

  when *Regexp::Syntax::Token::UnicodeProperty::Script
    @node << Script.new(token)

  else
    raise UnknownTokenError.new('UnicodeProperty', token)
  end
end

.quantifier(token) ⇒ Object

Raises:

  • (ArgumentError) 


360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
 
# File 'lib/regexp_parser/parser.rb', line 360

def self.quantifier(token)
  offset = -1
  target_node = @node.expressions[offset]
  while target_node and target_node.is_a?(FreeSpace)
    target_node = @node.expressions[offset -= 1]
  end

  raise ArgumentError.new("No valid target found for '#{token.text}' "+
                          "quantifier") unless target_node

  unless target_node
    if token.token == :zero_or_one
      raise "Quantifier given without a target, or the syntax of the group " +
            "or its options is incorrect"
    else
      raise "Quantifier `#{token.text}' given without a target"
    end
  end

  case token.token
  when :zero_or_one
    target_node.quantify(:zero_or_one, token.text, 0, 1, :greedy)
  when :zero_or_one_reluctant
    target_node.quantify(:zero_or_one, token.text, 0, 1, :reluctant)
  when :zero_or_one_possessive
    target_node.quantify(:zero_or_one, token.text, 0, 1, :possessive)

  when :zero_or_more
    target_node.quantify(:zero_or_more, token.text, 0, -1, :greedy)
  when :zero_or_more_reluctant
    target_node.quantify(:zero_or_more, token.text, 0, -1, :reluctant)
  when :zero_or_more_possessive
    target_node.quantify(:zero_or_more, token.text, 0, -1, :possessive)

  when :one_or_more
    target_node.quantify(:one_or_more, token.text, 1, -1, :greedy)
  when :one_or_more_reluctant
    target_node.quantify(:one_or_more, token.text, 1, -1, :reluctant)
  when :one_or_more_possessive
    target_node.quantify(:one_or_more, token.text, 1, -1, :possessive)

  when :interval
    interval(target_node, token)

  else
    raise UnknownTokenError.new('Quantifier', token)
  end
end

.set(token) ⇒ Object 



78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
 
# File 'lib/regexp_parser/parser.rb', line 78

def self.set(token)
  case token.token
  when :open
    open_set(token)
  when :close
    close_set(token)
  when :negate
    negate_set
  when :member, :range, :escape, :collation, :equivalent
    append_set(token)
  when *Token::Escape::All
    append_set(token)
  when *Token::CharacterSet::All
    append_set(token)
  when *Token::UnicodeProperty::All
    append_set(token)
  else
    raise UnknownTokenError.new('CharacterSet', token)
  end
end

.type(token) ⇒ Object 



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
 
# File 'lib/regexp_parser/parser.rb', line 152

def self.type(token)
  case token.token
  when :digit
    @node << CharacterType::Digit.new(token)
  when :nondigit
    @node << CharacterType::NonDigit.new(token)
  when :hex
    @node << CharacterType::Hex.new(token)
  when :nonhex
    @node << CharacterType::NonHex.new(token)
  when :space
    @node << CharacterType::Space.new(token)
  when :nonspace
    @node << CharacterType::NonSpace.new(token)
  when :word
    @node << CharacterType::Word.new(token)
  when :nonword
    @node << CharacterType::NonWord.new(token)
  else
    raise UnknownTokenError.new('CharacterType', token)
  end
end