Class: RubyLexer

Inherits:
Object
  • Object
show all
Defined in:
lib/ruby_lexer.rb

Constant Summary collapse

EOF = 
:eof_haha!
STR_FUNC_BORING =

ruby constants for strings (should this be moved somewhere else?)

0x00
STR_FUNC_ESCAPE =

TODO: remove and replace with REGEXP

0x01
STR_FUNC_EXPAND = 
0x02
STR_FUNC_REGEXP = 
0x04
STR_FUNC_AWORDS = 
0x08
STR_FUNC_SYMBOL = 
0x10
STR_FUNC_INDENT =

<<-HEREDOC

0x20
STR_SQUOTE = 
STR_FUNC_BORING
STR_DQUOTE = 
STR_FUNC_BORING | STR_FUNC_EXPAND
STR_XQUOTE = 
STR_FUNC_BORING | STR_FUNC_EXPAND
STR_REGEXP = 
STR_FUNC_REGEXP | STR_FUNC_ESCAPE | STR_FUNC_EXPAND
STR_SSYM = 
STR_FUNC_SYMBOL
STR_DSYM = 
STR_FUNC_SYMBOL | STR_FUNC_EXPAND

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ RubyLexer

Returns a new instance of RubyLexer.



218
219
220
221
222
223
224
225
226
 
# File 'lib/ruby_lexer.rb', line 218

def initialize
  self.token_buffer = []
  self.cond = StackState.new(:cond)
  self.cmdarg = StackState.new(:cmdarg)
  self.nest = 0
  @comments = []

  reset
end

Instance Attribute Details

#cmdarg ⇒ Object

Returns the value of attribute cmdarg.



7
8
9
 
# File 'lib/ruby_lexer.rb', line 7

def cmdarg
  @cmdarg
end

#command_start ⇒ Object

Returns the value of attribute command_start.



6
7
8
 
# File 'lib/ruby_lexer.rb', line 6

def command_start
  @command_start
end

#cond ⇒ Object

Returns the value of attribute cond.



8
9
10
 
# File 'lib/ruby_lexer.rb', line 8

def cond
  @cond
end

#lex_state ⇒ Object

Additional context surrounding tokens that both the lexer and grammar use.



13
14
15
 
# File 'lib/ruby_lexer.rb', line 13

def lex_state
  @lex_state
end

#lex_strterm ⇒ Object

Returns the value of attribute lex_strterm.



15
16
17
 
# File 'lib/ruby_lexer.rb', line 15

def lex_strterm
  @lex_strterm
end

#nest ⇒ Object

Returns the value of attribute nest.



9
10
11
 
# File 'lib/ruby_lexer.rb', line 9

def nest
  @nest
end

#src ⇒ Object

Stream of data that yylex examines.



18
19
20
 
# File 'lib/ruby_lexer.rb', line 18

def src
  @src
end

#token ⇒ Object

Last token read via yylex.



21
22
23
 
# File 'lib/ruby_lexer.rb', line 21

def token
  @token
end

#token_buffer ⇒ Object

Tempory buffer to build up a potential token. Consumer takes responsibility to reset this before use.



25
26
27
 
# File 'lib/ruby_lexer.rb', line 25

def token_buffer
  @token_buffer
end

#warnings ⇒ Object

What handles warnings



31
32
33
 
# File 'lib/ruby_lexer.rb', line 31

def warnings
  @warnings
end

#yacc_value ⇒ Object

Value of last token which had a value associated with it.



28
29
30
 
# File 'lib/ruby_lexer.rb', line 28

def yacc_value
  @yacc_value
end

Instance Method Details

#advance ⇒ Object

if ENV then

  @@stats = Hash.new 0

  def self.stats
    @@stats
  end

  at_exit {
    require 'pp'
    pp RubyLexer.stats.sort_by {|k,v| -v}.first(20)
  }
end



68
69
70
71
72
73
74
75
 
# File 'lib/ruby_lexer.rb', line 68

def advance
  r = yylex
  self.token = r

  @@stats[r] += 1 if ENV['SPY']

  return r != RubyLexer::EOF
end

#arg_ambiguous ⇒ Object 



77
78
79
 
# File 'lib/ruby_lexer.rb', line 77

def arg_ambiguous
  self.warning("Ambiguous first argument. make sure.")
end

#comments ⇒ Object 



81
82
83
84
85
 
# File 'lib/ruby_lexer.rb', line 81

def comments
  c = @comments.join
  @comments.clear
  c
end

#expr_beg_push(val) ⇒ Object 



87
88
89
90
91
92
 
# File 'lib/ruby_lexer.rb', line 87

def expr_beg_push val
  cond.push false
  cmdarg.push false
  self.lex_state = :expr_beg
  self.yacc_value = s(val)
end

#fix_arg_lex_state ⇒ Object 



94
95
96
97
98
99
100
 
# File 'lib/ruby_lexer.rb', line 94

def fix_arg_lex_state
  self.lex_state = if lex_state == :expr_fname || lex_state == :expr_dot
                     :expr_arg
                   else
                     :expr_beg
                   end
end

#heredoc(here) ⇒ Object

Region has 63 lines, 1595 characters



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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
 
# File 'lib/ruby_lexer.rb', line 102

def heredoc here # Region has 63 lines, 1595 characters
  _, eos, func, last_line = here

  indent  = (func & STR_FUNC_INDENT) != 0
  expand  = (func & STR_FUNC_EXPAND) != 0
  eos_re  = indent ? /[ \t]*#{eos}(\r?\n|\z)/ : /#{eos}(\r?\n|\z)/
  err_msg = "can't match #{eos_re.inspect} anywhere in "

  rb_compile_error err_msg if
    src.eos?

  if src.beginning_of_line? && src.scan(eos_re) then
    src.unread_many last_line # TODO: figure out how to remove this
    self.yacc_value = s(eos)
    return :tSTRING_END
  end

  token_buffer.clear

  if expand then
    case
    when src.scan(/#[$@]/) then
      src.pos -= 1 # FIX omg stupid
      self.yacc_value = s(src.matched)
      return :tSTRING_DVAR
    when src.scan(/#[{]/) then
      self.yacc_value = s(src.matched)
      return :tSTRING_DBEG
    when src.scan(/#/) then
      token_buffer << '#'
    end

    until src.scan(eos_re) do
      c = tokadd_string func, "\n", nil

      rb_compile_error err_msg if
        c == RubyLexer::EOF

      if c != "\n" then
        self.yacc_value = s(:str, token_buffer.join.delete("\r"))
        return :tSTRING_CONTENT
      else
        token_buffer << src.scan(/\n/)
      end

      rb_compile_error err_msg if
        src.eos?
    end

    # tack on a NL after the heredoc token - FIX NL should not be needed
    src.unread_many(eos + "\n") # TODO: remove this... stupid stupid stupid
  else
    until src.check(eos_re) do
      token_buffer << src.scan(/.*(\n|\z)/)
      rb_compile_error err_msg if
        src.eos?
    end
  end

  self.lex_strterm = s(:heredoc, eos, func, last_line)
  self.yacc_value = s(:str, token_buffer.join.delete("\r"))

  return :tSTRING_CONTENT
end

#heredoc_identifier ⇒ Object 



167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
 
# File 'lib/ruby_lexer.rb', line 167

def heredoc_identifier
  term, func = nil, STR_FUNC_BORING
  token_buffer.clear

  case
  when src.scan(/(-?)(['"`])(.*?)\2/) then
    term = src[2]
    unless src[1].empty? then
      func |= STR_FUNC_INDENT
    end
    func |= case term
            when "\'" then
              STR_SQUOTE
            when '"' then
              STR_DQUOTE
            else
              STR_XQUOTE
            end
    token_buffer << src[3]
  when src.scan(/-?(['"`])(?!\1*\Z)/) then
    rb_compile_error "unterminated here document identifier"
  when src.scan(/(-?)(\w+)/) then
    term = '"'
    func |= STR_DQUOTE
    unless src[1].empty? then
      func |= STR_FUNC_INDENT
    end
    token_buffer << src[2]
  else
    return nil
  end

  if src.check(/.*\n/) then
    # TODO: think about storing off the char range instead
    line = src.string[src.pos, src.matched_size]
    src.string[src.pos, src.matched_size] = ''
  else
    line = nil
  end

  self.lex_strterm = s(:heredoc, token_buffer.join, func, line)

  if term == '`' then
    self.yacc_value = s("`")
    return :tXSTRING_BEG
  else
    self.yacc_value = s("\"")
    return :tSTRING_BEG
  end
end

#int_with_base(base) ⇒ Object 



228
229
230
231
232
233
234
 
# File 'lib/ruby_lexer.rb', line 228

def int_with_base base
  if src.matched =~ /__/ then
    rb_compile_error "Invalid numeric format"
  end
  self.yacc_value = src.matched.to_i(base)
  return :tINTEGER
end

#parse_number ⇒ Object

Parse a number from the input stream.

Parameters:

  • c —

    The first character of the number.

Returns:

  • A int constant wich represents a token.



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
277
278
279
 
# File 'lib/ruby_lexer.rb', line 247

def parse_number
  self.lex_state = :expr_end

  case
  when src.scan(/[+-]?0[xbd]\b/) then
    rb_compile_error "Invalid numeric format"
  when src.scan(/[+-]?0x[a-f0-9_]+/i) then
    return int_with_base(16)
  when src.scan(/[+-]?0b[01_]+/) then
    return int_with_base(2)
  when src.scan(/[+-]?0d[0-9_]+/) then
    return int_with_base(10)
  when src.scan(/[+-]?0o?[0-7_]*[89]/) then
    rb_compile_error "Illegal octal digit."
  when src.scan(/[+-]?0o?[0-7_]+|0o/) then
    return int_with_base(8)
  when src.scan(/[+-]?[\d_]+_(e|\.)/) then
    rb_compile_error "Trailing '_' in number."
  when src.scan(/[+-]?[\d_]+\.[\d_]+(e[+-]?[\d_]+)?\b|[+-]?[\d_]+e[+-]?[\d_]+\b/i) then
    number = src.matched
    if number =~ /__/ then
      rb_compile_error "Invalid numeric format"
    end
    self.yacc_value = number.to_f
    return :tFLOAT
  when src.scan(/[+-]?0\b/) then
    return int_with_base(10)
  when src.scan(/[+-]?[\d_]+\b/) then
    return int_with_base(10)
  else
    rb_compile_error "Bad number format"
  end
end

#parse_quote ⇒ Object 



281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
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
 
# File 'lib/ruby_lexer.rb', line 281

def parse_quote
  beg, nnd, short_hand, c = nil, nil, false, nil

  if src.scan(/[a-z0-9]{1,2}/i) then # Long-hand (e.g. %Q{}).
    rb_compile_error "unknown type of %string" if
      src.matched_size == 2
    c = src.matched
    beg = src.getch
    short_hand = false
    # HACK: stupid rubinius
    # c, beg, short_hand = src.matched, src.getch, false
  else                               # Short-hand (e.g. %{, %., %!, etc)
    c = 'Q'
    beg = src.getch
    short_hand = true
    # HACK: stupid rubinius
    # c, beg, short_hand = 'Q', src.getch, true
  end

  if src.eos? or c == RubyLexer::EOF or beg == RubyLexer::EOF then
    rb_compile_error "unterminated quoted string meets end of file"
  end

  # Figure nnd-char.  "\0" is special to indicate beg=nnd and that no nesting?
  nnd = { "(" => ")", "[" => "]", "{" => "}", "<" => ">" }[beg]
  nnd, beg = beg, "\0" if nnd.nil?

  token_type, self.yacc_value = nil, s("%#{c}#{beg}")
  token_type, string_type = case c
                            when 'Q' then
                              ch = short_hand ? nnd : c + beg
                              self.yacc_value = s("%#{ch}")
                              [:tSTRING_BEG,   STR_DQUOTE]
                            when 'q' then
                              [:tSTRING_BEG,   STR_SQUOTE]
                            when 'W' then
                              src.scan(/\s*/)
                              [:tWORDS_BEG,    STR_DQUOTE | STR_FUNC_AWORDS]
                            when 'w' then
                              src.scan(/\s*/)
                              [:tAWORDS_BEG,   STR_SQUOTE | STR_FUNC_AWORDS]
                            when 'x' then
                              [:tXSTRING_BEG,  STR_XQUOTE]
                            when 'r' then
                              [:tREGEXP_BEG,   STR_REGEXP]
                            when 's' then
                              self.lex_state  = :expr_fname
                              [:tSYMBEG,       STR_SSYM]
                            end

  rb_compile_error "Bad %string type. Expected [Qqwxr\W], found '#{c}'." if
    token_type.nil?

  self.lex_strterm = s(:strterm, string_type, nnd, beg)

  return token_type
end

#parse_string(quote) ⇒ Object 



339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
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
 
# File 'lib/ruby_lexer.rb', line 339

def parse_string(quote)
  _, string_type, term, open = quote

  space = false # FIX: remove these
  func = string_type
  paren = open
  term_re = Regexp.escape term

  awords = (func & STR_FUNC_AWORDS) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0
  expand = (func & STR_FUNC_EXPAND) != 0

  unless func then
    return :tSTRING_END
  end

  space = true if awords and src.scan(/\s+/)

  if self.nest == 0 && src.scan(/#{term_re}/) then
    if awords then
      quote[1] = nil
      return ' '
    elsif regexp then
      self.yacc_value = self.regx_options
      return :tREGEXP_END
    else
      self.yacc_value = s(term)
      return :tSTRING_END
    end
  end

  if space then
    return ' '
  end

  self.token_buffer.clear

  if expand
    case
    when src.scan(/#(?=[$@])/) then
      return :tSTRING_DVAR
    when src.scan(/#[{]/) then
      return :tSTRING_DBEG
    when src.scan(/#/) then
      token_buffer << '#'
    end
  end

  if tokadd_string(func, term, paren) == RubyLexer::EOF then
    rb_compile_error "unterminated string meets end of file"
  end

  self.yacc_value = s(:str, token_buffer.join)
  return :tSTRING_CONTENT
end

#rb_compile_error(msg) ⇒ Object

Raises:

  • (SyntaxError) 


395
396
397
398
 
# File 'lib/ruby_lexer.rb', line 395

def rb_compile_error msg
  msg += ". near line #{src.lineno}: #{src.rest[/^.*/].inspect}"
  raise SyntaxError, msg
end

#read_escape ⇒ Object 



400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
 
# File 'lib/ruby_lexer.rb', line 400

def read_escape
  case
  when src.scan(/\\/) then                   # Backslash
    '\\'
  when src.scan(/n/) then                    # newline
    "\n"
  when src.scan(/t/) then                    # horizontal tab
    "\t"
  when src.scan(/r/) then                    # carriage-return
    "\r"
  when src.scan(/f/) then                    # form-feed
    "\f"
  when src.scan(/v/) then                    # vertical tab
    "\13"
  when src.scan(/a/) then                    # alarm(bell)
    "\007"
  when src.scan(/e/) then                    # escape
    "\033"
  when src.scan(/b/) then                    # backspace
    "\010"
  when src.scan(/s/) then                    # space
    " "
  when src.scan(/[0-7]{1,3}/) then           # octal constant
    src.matched.to_i(8).chr
  when src.scan(/x([0-9a-fA-Fa-f]{2})/) then # hex constant
    src[1].to_i(16).chr
  when src.scan(/M-\\/) then
    c = self.read_escape
    c[0] = (c[0].ord | 0x80).chr
    c
  when src.scan(/M-(.)/) then
    c = src[1]
    c[0] = (c[0].ord | 0x80).chr
    c
  when src.scan(/C-\\|c\\/) then
    c = self.read_escape
    c[0] = (c[0].ord & 0x9f).chr
    c
  when src.scan(/C-\?|c\?/) then
    0177.chr
  when src.scan(/(C-|c)(.)/) then
    c = src[2]
    c[0] = (c[0].ord & 0x9f).chr
    c
  when src.scan(/[McCx0-9]/) || src.eos? then
    rb_compile_error("Invalid escape character syntax")
  else
    src.getch
  end
end

#regx_options ⇒ Object 



451
452
453
454
455
456
457
458
459
460
461
462
463
464
 
# File 'lib/ruby_lexer.rb', line 451

def regx_options
  good, bad = [], []

  if src.scan(/[a-z]+/) then
    good, bad = src.matched.split(//).partition { |s| s =~ /^[ixmonesu]$/ }
  end

  unless bad.empty? then
    rb_compile_error("unknown regexp option%s - %s" %
                     [(bad.size > 1 ? "s" : ""), bad.join.inspect])
  end

  return good.join
end

#reset ⇒ Object 



466
467
468
469
470
471
472
473
474
 
# File 'lib/ruby_lexer.rb', line 466

def reset
  self.command_start = true
  self.lex_strterm = nil
  self.token = nil
  self.yacc_value = nil

  @src = nil
  @lex_state = nil
end

#store_comment ⇒ Object 



481
482
483
484
 
# File 'lib/ruby_lexer.rb', line 481

def store_comment
  @comments.push(*self.token_buffer)
  self.token_buffer.clear
end

#tokadd_escape(term) ⇒ Object 



486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
 
# File 'lib/ruby_lexer.rb', line 486

def tokadd_escape term
  case
  when src.scan(/\\\n/) then
    # just ignore
  when src.scan(/\\([0-7]{1,3}|x[0-9a-fA-F]{1,2})/) then
    self.token_buffer << src.matched
  when src.scan(/\\([MC]-|c)(?=\\)/) then
    self.token_buffer << src.matched
    self.tokadd_escape term
  when src.scan(/\\([MC]-|c)(.)/) then
    self.token_buffer << src.matched
  when src.scan(/\\[McCx]/) then
    rb_compile_error "Invalid escape character syntax"
  when src.scan(/\\(.)/m) then
    self.token_buffer << src.matched
  else
    rb_compile_error "Invalid escape character syntax"
  end
end

#tokadd_string(func, term, paren) ⇒ Object 



506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
 
# File 'lib/ruby_lexer.rb', line 506

def tokadd_string(func, term, paren)
  awords = (func & STR_FUNC_AWORDS) != 0
  escape = (func & STR_FUNC_ESCAPE) != 0
  expand = (func & STR_FUNC_EXPAND) != 0
  regexp = (func & STR_FUNC_REGEXP) != 0
  symbol = (func & STR_FUNC_SYMBOL) != 0

  paren_re = paren.nil? ? nil : Regexp.new(Regexp.escape(paren))
  term_re  = Regexp.new(Regexp.escape(term))

  until src.eos? do
    c = nil
    case
    when paren_re && src.scan(paren_re) then
      self.nest += 1
    when self.nest == 0 && src.scan(term_re) then
      src.pos -= 1
      break
    when src.scan(term_re) then
      self.nest -= 1
    when ((awords && src.scan(/\s/)) ||
          (expand && src.scan(/#(?=[\$\@\{])/))) then
      src.pos -= 1
      break
    when awords && src.scan(/\\\n/) then
      token_buffer << "\n"
      next
    when expand && src.scan(/\\\n/) then
      next
    when awords && src.scan(/\\\s/) then
      c = ' '
    when (expand && src.scan(/#(?!\n)/)) || src.scan(/\\\n/) then
      # do nothing
    when src.scan(/\\\\/) then
      if escape then
        token_buffer << '\\'
      end
      c = '\\'
    when regexp && src.check(/\\/) then
      self.tokadd_escape term
      next
    when expand && src.scan(/\\/) then
      c = self.read_escape
    when src.scan(/\\/) then
      unless src.scan(term_re) || paren.nil? || src.scan(paren_re) then
        token_buffer << "\\"
      end
      # \\ case:
      # else if (ismbchar(c)) {
      #   int i, len = mbclen(c)-1;
      #   for (i = 0; i < len; i++) {
      #     tokadd(c);
      #     c = nextc();
      #   }
      # }
    else
      c = src.getch # FIX: I don't like this style
      if symbol && src.scan(/\0/) then
        rb_compile_error "symbol cannot contain '\\0'"
      end
    end

    c = src.matched unless c
    token_buffer << c
  end # until

  c = src.matched unless c
  c = RubyLexer::EOF if src.eos?

  return c
end

#warning(s) ⇒ Object 



578
579
580
 
# File 'lib/ruby_lexer.rb', line 578

def warning s
  # do nothing for now
end

#yylex ⇒ Object

Returns the next token. Also sets yy_val is needed.

TODO: remove ALL sexps coming from here and move up to grammar TODO: only literal values should come up from the lexer.

Returns:

  • Description of the Returned Value



589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
 
# File 'lib/ruby_lexer.rb', line 589

def yylex
  c = ''
  space_seen = false
  command_state = false
  token_buffer.clear
  src = self.src

  self.token = nil
  self.yacc_value = nil

  if lex_strterm then
    token = nil

    if lex_strterm[0] == :heredoc then
      token = self.heredoc(lex_strterm)
      if token == :tSTRING_END then
        self.lex_strterm = nil
        self.lex_state = :expr_end
      end
    else
      token = self.parse_string(lex_strterm)

      if token == :tSTRING_END || token == :tREGEXP_END then
        self.lex_strterm = nil
        self.lex_state = :expr_end
      end
    end

    return token
  end

  command_state = self.command_start
  self.command_start = false

  last_state = lex_state

  loop do
    case
    when src.scan(/\004|\032|\000/), src.eos? then # ^D, ^Z, EOF
      return RubyLexer::EOF
    when src.scan(/\ |\t|\f|\r|\13/) then # white spaces, 13 = '\v
      space_seen = true
      next
    when src.scan(/#|\n/) then
      c = src.matched
      if c == '#' then
        src.unread c # ok

        while src.scan(/\s*#.*(\n+|\z)/) do
          token_buffer << src.matched.gsub(/^ +#/, '#').gsub(/^ +$/, '')
        end

        self.store_comment

        if src.eos? then
          return RubyLexer::EOF
        end
      end
      # Replace a string of newlines with a single one

      src.scan(/\n+/)

      if [:expr_beg, :expr_fname,
          :expr_dot, :expr_class].include? lex_state then
        next
      end

      self.command_start = true
      self.lex_state = :expr_beg
      return "\n"
    when src.scan(/\*\*=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("**")
      return :tOP_ASGN
    when src.scan(/\*\*/) then
      self.yacc_value = s("**")
      self.fix_arg_lex_state
      return :tPOW
    when src.scan(/\*\=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("*")
      return :tOP_ASGN
    when src.scan(/\*/) then
      result = if lex_state.is_argument && space_seen && !src.check(/\s/) then
                 warning("`*' interpreted as argument prefix")
                 :tSTAR
               elsif lex_state == :expr_beg || lex_state == :expr_mid then
                 :tSTAR
               else
                 :tSTAR2
               end

      self.yacc_value = s("*")

      self.fix_arg_lex_state

      return result
    when src.scan(/\!\=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("!=")
      return :tNEQ
    when src.scan(/\!~/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("!~")
      return :tNMATCH
    when src.scan(/\!/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("!")
      return :tBANG
    when src.scan(/\=\=\=/) then
      self.fix_arg_lex_state
      self.yacc_value = s("===")
      return :tEQQ
    when src.scan(/\=\=/) then
      self.fix_arg_lex_state
      self.yacc_value = s("==")
      return :tEQ
    when src.scan(/\=~/) then
      self.fix_arg_lex_state
      self.yacc_value = s("=~")
      return :tMATCH
    when src.scan(/\=>/) then
      self.fix_arg_lex_state
      self.yacc_value = s("=>")
      return :tASSOC
    when src.scan(/\=/) then
      # documentation nodes
      if src.was_begin_of_line and src.scan(/begin(?=\s)/) then
        self.token_buffer << '=' # FIX merge up
        self.token_buffer << src.matched

        unless src.scan(/.*?\n=end(\n|\z)/m) then
          rb_compile_error("embedded document meets end of file")
        end

        self.token_buffer << src.matched
        self.store_comment

        next
      else
        self.fix_arg_lex_state
        self.yacc_value = s("=")
        return '='
      end
    when src.scan(/\<\=\>/) then
      self.fix_arg_lex_state
      self.yacc_value = s("<=>")
      return :tCMP
    when src.scan(/\<\=/) then
      self.fix_arg_lex_state
      self.yacc_value = s("<=")
      return :tLEQ
    when src.scan(/\<\<\=/) then
      self.fix_arg_lex_state
      self.lex_state = :expr_beg
      self.yacc_value = s("\<\<")
      return :tOP_ASGN
    when src.scan(/\<\</) then
      if (! [:expr_end,    :expr_dot,
             :expr_endarg, :expr_class].include?(lex_state) &&
          (!lex_state.is_argument || space_seen)) then
        tok = self.heredoc_identifier
        if tok then
          return tok
        end
      end

      self.fix_arg_lex_state
      self.yacc_value = s("\<\<")
      return :tLSHFT
    when src.scan(/\</) then
      self.fix_arg_lex_state
      self.yacc_value = s("<")
      return :tLT
    when src.scan(/\>\=/) then
      self.fix_arg_lex_state
      self.yacc_value = s(">=")
      return :tGEQ
    when src.scan(/\>\>=/) then
      self.fix_arg_lex_state
      self.lex_state = :expr_beg
      self.yacc_value = s(">>")
      return :tOP_ASGN
    when src.scan(/\>\>/) then
      self.fix_arg_lex_state
      self.yacc_value = s(">>")
      return :tRSHFT
    when src.scan(/\>/) then
      self.fix_arg_lex_state
      self.yacc_value = s(">")
      return :tGT
    when src.scan(/\"/) then
      self.lex_strterm = s(:strterm, STR_DQUOTE, '"', "\0") # TODO: question this
      self.yacc_value = s("\"")
      return :tSTRING_BEG
    when src.scan(/\`/) then
      self.yacc_value = s("`")
      case lex_state
      when :expr_fname then
        self.lex_state = :expr_end
        return :tBACK_REF2
      when :expr_dot then
        self.lex_state = if command_state then
                           :expr_cmdarg
                         else
                           :expr_arg
                         end
        return :tBACK_REF2
      end
      self.lex_strterm = s(:strterm, STR_XQUOTE, '`', "\0")
      return :tXSTRING_BEG
    when src.scan(/\'/) then
      self.lex_strterm = s(:strterm, STR_SQUOTE, "\'", "\0")
      self.yacc_value = s("'")
      return :tSTRING_BEG
    when src.scan(/\?/) then
      if lex_state == :expr_end || lex_state == :expr_endarg then
        self.lex_state = :expr_beg
        self.yacc_value = s("?")
        return '?'
      end

      if src.eos? then
        rb_compile_error "incomplete character syntax"
      end

      if src.check(/\s|\v/) then
        unless lex_state.is_argument then
          c2 = case src.matched
               when " " then
                 's'
               when "\n" then
                 'n'
               when "\t" then
                 't'
               when "\v" then
                 'v'
               when "\r" then
                 'r'
               when "\f" then
                 'f'
               end

          if c2 then
            warning("invalid character syntax; use ?\\" + c2)
          end
        end

        # ternary
        self.lex_state = :expr_beg
        self.yacc_value = s("?")
        return '?'
        # elsif ismbchar(c) then # ternary, also
        # rb_warn "multibyte character literal not supported yet; use ?\\#{c}"
        # support.unread c
        # self.lex_state = :expr_beg
        # return '?'
      elsif src.check(/\w(?=\w)/) then # ternary, also
        self.lex_state = :expr_beg
        self.yacc_value = s("?")
        return '?'
      end

      c = if src.scan(/\\/) then
            self.read_escape
          else
            src.getch
          end
      c[0] = (c[0].ord & 0xff).chr
      self.lex_state = :expr_end
      self.yacc_value = c[0].ord
      return :tINTEGER
    when src.scan(/\&&=/) then
      self.yacc_value = s("&&")
      self.lex_state = :expr_beg
      return :tOP_ASGN
    when src.scan(/\&&/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("&&")
      return :tANDOP
    when src.scan(/\&\=/) then
      self.yacc_value = s("&")
      self.lex_state = :expr_beg
      return :tOP_ASGN
    when src.scan(/&/) then
      result = if lex_state.is_argument && space_seen && !src.check(/\s/) then
                 warning("`&' interpreted as argument prefix")
                 :tAMPER
               elsif lex_state == :expr_beg || lex_state == :expr_mid then
                 :tAMPER
               else
                 :tAMPER2
               end

      self.fix_arg_lex_state
      self.yacc_value = s("&")
      return result
    when src.scan(/\|\|\=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("||")
      return :tOP_ASGN
    when src.scan(/\|\|/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("||")
      return :tOROP
    when src.scan(/\|\=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("|")
      return :tOP_ASGN
    when src.scan(/\|/) then
      self.fix_arg_lex_state
      self.yacc_value = s("|")
      return :tPIPE
    when src.scan(/[+-]/) then
      sign = src.matched
      utype, type = if sign == "+" then
                      [:tUPLUS, :tPLUS]
                    else
                      [:tUMINUS, :tMINUS]
                    end

      if lex_state == :expr_fname || lex_state == :expr_dot then
        self.lex_state = :expr_arg
        if src.scan(/@/) then
          self.yacc_value = s("#{sign}@")
          return utype
        else
          self.yacc_value = s(sign)
          return type
        end
      end

      if src.scan(/\=/) then
        self.lex_state = :expr_beg
        self.yacc_value = s(sign)
        return :tOP_ASGN
      end

      if (lex_state == :expr_beg || lex_state == :expr_mid ||
          (lex_state.is_argument && space_seen && !src.check(/\s/))) then
        if lex_state.is_argument then
          arg_ambiguous
        end

        self.lex_state = :expr_beg
        self.yacc_value = s(sign)

        if src.check(/\d/) then
          if utype == :tUPLUS then
            return self.parse_number
          else
            return :tUMINUS_NUM
          end
        end

        return utype
      end

      self.lex_state = :expr_beg
      self.yacc_value = s(sign)
      return type
    when src.scan(/\.\.\./) then
      self.lex_state = :expr_beg
      self.yacc_value = s("...")
      return :tDOT3
    when src.scan(/\.\./) then
      self.lex_state = :expr_beg
      self.yacc_value = s("..")
      return :tDOT2
    when src.scan(/\.\d/) then
      rb_compile_error "no .<digit> floating literal anymore put 0 before dot"
    when src.scan(/\./) then
      self.lex_state = :expr_dot
      self.yacc_value = s(".")
      return :tDOT
    when src.check(/[0-9]/) then
      return parse_number
    when src.scan(/[\)\]\}]/) then
      cond.lexpop
      cmdarg.lexpop
      self.lex_state = :expr_end
      self.yacc_value = s(src.matched)
      result = {
        ")" => :tRPAREN,
        "]" => :tRBRACK,
        "}" => :tRCURLY
      }[src.matched]
      return result
    when src.scan(/::/) then
      if (lex_state == :expr_beg ||
          lex_state == :expr_mid ||
          lex_state == :expr_class ||
          (lex_state.is_argument && space_seen)) then
        self.lex_state = :expr_beg
        self.yacc_value = s("::")
        return :tCOLON3
      end

      self.lex_state = :expr_dot
      self.yacc_value = s("::")
      return :tCOLON2
    when src.scan(/\:/) then
      if (lex_state == :expr_end || lex_state == :expr_endarg ||
          src.check(/\s/)) then
        self.lex_state = :expr_beg
        self.yacc_value = s(":")
        return ':'
      end

      case
      when src.scan(/\'/) then
        self.lex_strterm = s(:strterm, STR_SSYM, src.matched, "\0")
      when src.scan(/\"/) then
        self.lex_strterm = s(:strterm, STR_DSYM, src.matched, "\0")
      end

      self.lex_state = :expr_fname
      self.yacc_value = s(":")
      return :tSYMBEG
    when src.scan(/\//) then
      if lex_state == :expr_beg || lex_state == :expr_mid then
        self.lex_strterm = s(:strterm, STR_REGEXP, '/', "\0")
        self.yacc_value = s("/")
        return :tREGEXP_BEG
      end

      if src.scan(/\=/) then
        self.yacc_value = s("/")
        self.lex_state = :expr_beg
        return :tOP_ASGN
      end

      if lex_state.is_argument && space_seen then
        unless src.scan(/\s/) then
          arg_ambiguous
          self.lex_strterm = s(:strterm, STR_REGEXP, '/', "\0")
          self.yacc_value = s("/")
          return :tREGEXP_BEG
        end
      end

      self.fix_arg_lex_state

      self.yacc_value = s("/")
      return :tDIVIDE
    when src.scan(/\^=/) then
      self.lex_state = :expr_beg
      self.yacc_value = s("^")
      return :tOP_ASGN
    when src.scan(/\^/) then
      self.fix_arg_lex_state
      self.yacc_value = s("^")
      return :tCARET
    when src.scan(/\;/) then
      self.command_start = true
      self.lex_state = :expr_beg
      self.yacc_value = s(";")
      return src.matched
    when src.scan(/\,/) then
      self.lex_state = :expr_beg
      self.yacc_value = s(",")
      return src.matched
    when src.scan(/\~/) then
      if lex_state == :expr_fname || lex_state == :expr_dot then
        src.scan(/@/)
      end

      self.fix_arg_lex_state
      self.yacc_value = s("~")

      return :tTILDE
    when src.scan(/\(/) then
      result = :tLPAREN2
      self.command_start = true
      if lex_state == :expr_beg || lex_state == :expr_mid then
        result = :tLPAREN
      elsif space_seen then
        if lex_state == :expr_cmdarg then
          result = :tLPAREN_ARG
        elsif lex_state == :expr_arg then
          warning("don't put space before argument parentheses")
          result = :tLPAREN2
        end
      end

      self.expr_beg_push "("

      return result
    when src.scan(/\[/) then
      result = src.matched
      if lex_state == :expr_fname || lex_state == :expr_dot then
        self.lex_state = :expr_arg
        case
        when src.scan(/\]\=/) then
          self.yacc_value = s("[]=")
          return :tASET
        when src.scan(/\]/) then
          self.yacc_value = s("[]")
          return :tAREF
        else
          rb_compile_error "unexpected '['"
        end
      elsif lex_state == :expr_beg || lex_state == :expr_mid then
        result = :tLBRACK
      elsif lex_state.is_argument && space_seen then
        result = :tLBRACK
      end

      self.expr_beg_push("[")

      return result
    when src.scan(/\{/) then
      result = if lex_state.is_argument || lex_state == :expr_end then
                 :tLCURLY      #  block (primary)
               elsif lex_state == :expr_endarg then
                 :tLBRACE_ARG  #  block (expr)
               else
                 :tLBRACE      #  hash
               end

      self.expr_beg_push("{")

      return result
    when src.scan(/\\/) then
      if src.scan(/\n/) then
        space_seen = true
        next
      end
      rb_compile_error "bare backslash only allowed before newline"
    when src.scan(/\%/) then
      if lex_state == :expr_beg || lex_state == :expr_mid then
        return parse_quote
      end

      if src.scan(/\=/) then
        self.lex_state = :expr_beg
        self.yacc_value = s("%")
        return :tOP_ASGN
      end

      if lex_state.is_argument && space_seen && ! src.check(/\s/) then
        return parse_quote
      end

      self.fix_arg_lex_state
      self.yacc_value = s("%")

      return :tPERCENT
    when src.scan(/(\$_)(\w)/) then
      self.lex_state = :expr_end
      token_buffer << src[1]
      # HACK? c = src[2]
      # pass through
    when src.scan(/\$_/) then
      self.lex_state = :expr_end
      token_buffer << src.matched
      self.yacc_value = s(src.matched)
      return :tGVAR
    when src.scan(/\$[~*$?!@\/\\;,.=:<>\"]|\$-\w?/) then
      self.lex_state = :expr_end
      token_buffer << src.matched
      self.yacc_value = s(token_buffer.join)
      return :tGVAR
    when src.scan(/\$([\&\`\'\+])/) then
      self.lex_state = :expr_end
      # Explicit reference to these vars as symbols...
      if last_state == :expr_fname then
        token_buffer << src.matched
        self.yacc_value = s(token_buffer.join)
        return :tGVAR
      else
        self.yacc_value = s(:back_ref, src[1].to_sym)
        return :tBACK_REF
      end
    when src.scan(/\$[1-9]\d*/) then
      self.lex_state = :expr_end
      token_buffer.push(*src.matched.split(//))
      if last_state == :expr_fname then
        self.yacc_value = s(token_buffer.join)
        return :tGVAR
      else
        self.yacc_value = s(:nth_ref, token_buffer.join[1..-1].to_i)
        return :tNTH_REF
      end
    when src.scan(/\$0/) then
      self.lex_state = :expr_end
      token_buffer << '$' # why just this?!?
      # pass through
    when src.scan(/\$\W|\$\z/) then # TODO: remove?
      self.lex_state = :expr_end
      self.yacc_value = s("$")
      return '$'
    when src.scan(/\$/)
      self.lex_state = :expr_end
      token_buffer << src.matched
      src.getch
      # pass through
    when src.scan(/\@/) then
      token_buffer << '@'

      if src.scan(/(@)?\d/) then
        if src[1] then
          rb_compile_error "`@@#{c}` is not allowed as a class variable name"
        else
          rb_compile_error "`@#{c}' is not allowed as an instance variable name"
        end
      end

      if src.scan(/@/) then
        token_buffer << src.matched
      end

      unless src.scan(/\w/) then
        self.yacc_value = s("@")
        return '@'
      end
    when src.scan(/\_/) then
      if src.was_begin_of_line && src.scan(/_END__(\n|\Z)/) then
        return RubyLexer::EOF
      end
    else
      c = src.getch # FIX: I really hate this
      if c =~ /\W/ then
        rb_compile_error "Invalid char '#{c.inspect}' in expression"
      end
    end

    src.pos -= 1 # HACK
    if src.scan(/\w+/) then
      token_buffer.push(*src.matched.split(//)) # TODO: that split is tarded.
    end

    if token_buffer[0] =~ /\w/ && src.scan(/[\!\?](?!=)/) then
      token_buffer << src.matched
    end

    result = nil
    last_state = lex_state

    case token_buffer[0]
    when /^\$/ then
      self.lex_state = :expr_end
      result = :tGVAR
    when '@' then
      self.lex_state = :expr_end
      if token_buffer[1] == '@' then
        result = :tCVAR
      else
        result = :tIVAR
      end
    else
      if token_buffer[-1] =~ /[!?]/ then
        result = :tFID
      else
        if lex_state == :expr_fname then
          # ident=, not =~ => == or followed by =>
          if src.scan(/=(?:(?![~>=])|(?==>))/) then
            result = :tIDENTIFIER
            token_buffer << src.matched
          end
        end

        if result.nil? && token_buffer[0] =~ /[A-Z]/ then
          result = :tCONSTANT
        else
          result = :tIDENTIFIER
        end
      end

      unless lex_state == :expr_dot then
        # See if it is a reserved word.
        keyword = Keyword.keyword(token_buffer.join, token_buffer.length)

        unless keyword.nil? then
          state = lex_state
          self.lex_state = keyword.state

          self.yacc_value = if state == :expr_fname then
                              s(keyword.name)
                            else
                              s(token_buffer.join)
                            end

          if keyword.id0 == :kDO then
            self.command_start = true
            if cond.is_in_state then
              return :kDO_COND
            end
            if cmdarg.is_in_state && state != :expr_cmdarg then
              return :kDO_BLOCK
            end
            if state == :expr_endarg then
              return :kDO_BLOCK
            end
            return :kDO
          end

          if state == :expr_beg then
            return keyword.id0
          end

          if keyword.id0 != keyword.id1 then
            self.lex_state = :expr_beg
          end

          return keyword.id1
        end
      end # lex_state == :expr_dot

      if (lex_state == :expr_beg ||
          lex_state == :expr_mid ||
          lex_state == :expr_dot ||
          lex_state == :expr_arg ||
          lex_state == :expr_cmdarg) then
        if command_state then
          self.lex_state = :expr_cmdarg
        else
          self.lex_state = :expr_arg
        end
      else
        self.lex_state = :expr_end
      end
    end

    # Lame: parsing logic made it into lexer in ruby...So we
    # are emulating
    # FIXME:  I believe this is much simpler now...
    # HACK
    # if (IdUtil.var_type(temp_val) == IdUtil.LOCAL_VAR &&
    #     last_state != :expr_dot &&
    #     (BlockStaticScope === scope && (scope.is_defined(temp_val) >= 0)) ||
    #     (scope.local_scope.is_defined(temp_val) >= 0)) then
    #   self.lex_state = :expr_end
    # end

    self.yacc_value = s(token_buffer.join)

    return result
  end
end