Class: Opal::Lexer

Inherits:
Object show all
Defined in:
opal/lib/opal/parser/lexer.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(source, file) ⇒ Lexer

Returns a new instance of Lexer



11
12
13
14
15
16
17
18
19
20
 
# File 'opal/lib/opal/parser/lexer.rb', line 11

def initialize(source, file)
  @lex_state  = :expr_beg
  @cond       = 0
  @cmdarg     = 0
  @line       = 1
  @file       = file

  @scanner = StringScanner.new(source)
  @scanner_stack = [@scanner]
end

Instance Attribute Details

#lex_state ⇒ Object

Returns the value of attribute lex_state



9
10
11
 
# File 'opal/lib/opal/parser/lexer.rb', line 9

def lex_state
  @lex_state
end

#line ⇒ Object (readonly)

Returns the value of attribute line



7
8
9
 
# File 'opal/lib/opal/parser/lexer.rb', line 7

def line
  @line
end

#scanner ⇒ Object

Returns the value of attribute scanner



9
10
11
 
# File 'opal/lib/opal/parser/lexer.rb', line 9

def scanner
  @scanner
end

#scope ⇒ Object (readonly)

Returns the value of attribute scope



7
8
9
 
# File 'opal/lib/opal/parser/lexer.rb', line 7

def scope
  @scope
end

#scope_line ⇒ Object (readonly)

Returns the value of attribute scope_line



7
8
9
 
# File 'opal/lib/opal/parser/lexer.rb', line 7

def scope_line
  @scope_line
end

#strterm ⇒ Object

Returns the value of attribute strterm



9
10
11
 
# File 'opal/lib/opal/parser/lexer.rb', line 9

def strterm
  @strterm
end

Instance Method Details

#add_heredoc_content(str_buffer, str_parse) ⇒ Object 



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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'opal/lib/opal/parser/lexer.rb', line 245

def add_heredoc_content(str_buffer, str_parse)
  scanner = @scanner

  eos_regx = /[ \t]*#{Regexp.escape(str_parse[:end])}(\r*\n|$)/
  expand = true

  until scanner.eos?
    c = nil
    handled = true

    if scan(/\n/)
      c = scanner.matched
    elsif check(eos_regx) && scanner.bol?
      break # eos!
    elsif expand && check(/#(?=[\$\@\{])/)
      break
    elsif scan(/\\/)
      if str_parse[:type] == :regexp
        if scan(/(.)/)
          c = "\\" + scanner.matched
        end
      else
        c = if scan(/n/)
          "\n"
        elsif scan(/r/)
          "\r"
        elsif scan(/\n/)
          "\n"
        elsif scan(/t/)
          "\t"
        else
          # escaped char doesnt need escaping, so just return it
          scan(/./)
          scanner.matched
        end
      end
    else
      handled = false
    end

    unless handled
      reg = Regexp.new("[^#{Regexp.escape str_parse[:end]}\#\0\\\\\n]+|.")

      scan reg
      c = scanner.matched
    end

    c ||= scanner.matched
    str_buffer << c
  end

  raise "reached EOF while in string" if scanner.eos?
end

#add_string_content(str_buffer, str_parse) ⇒ Object 



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
338
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
 
# File 'opal/lib/opal/parser/lexer.rb', line 299

def add_string_content(str_buffer, str_parse)
  scanner = @scanner
  # regexp for end of string/regexp
  # end_str_re = /#{str_parse[:end]}/
  end_str_re = Regexp.new(Regexp.escape(str_parse[:end]))

  expand = strterm_expand?(str_parse)

  words = ['W', 'w'].include? str_parse[:beg]

  until scanner.eos?
    c = nil
    handled = true

    if check end_str_re
      # eos
      # if its just balancing, add it ass normal content..
      if str_parse[:balance] && (str_parse[:nesting] != 0)
        # we only checked above, so actually scan it
        scan end_str_re
        c = scanner.matched
        str_parse[:nesting] -= 1
      else
        # not balancing, so break (eos!)
        break
      end

    elsif str_parse[:balance] and scan Regexp.new(Regexp.escape(str_parse[:beg]))
      str_parse[:nesting] += 1
      c = scanner.matched

    elsif words && scan(/\s/)
      scanner.pos -= 1
      break

    elsif expand && check(/#(?=[\$\@\{])/)
      break

    #elsif scan(/\\\\/)
      #c = scanner.matched

    elsif scan(/\\/)
      if str_parse[:type] == :regexp
        if scan(/(.)/)
          c = "\\" + scanner.matched
        end
      else
        c = if scan(/n/)
          "\n"
        elsif scan(/r/)
          "\r"
        elsif scan(/\n/)
          "\n"
        elsif scan(/t/)
          "\t"
        else
          # escaped char doesnt need escaping, so just return it
          scan(/./)
          scanner.matched
        end 
      end
    else
      handled = false
    end

    unless handled
      reg = if words
              Regexp.new("[^#{Regexp.escape str_parse[:end]}\#\0\n\ \\\\]+|.")
            elsif str_parse[:balance]
              Regexp.new("[^#{Regexp.escape str_parse[:end]}#{Regexp.escape str_parse[:beg]}\#\0\\\\]+|.")
            else
              Regexp.new("[^#{Regexp.escape str_parse[:end]}\#\0\\\\]+|.")
            end

      scan reg
      c = scanner.matched
    end

    c ||= scanner.matched
    str_buffer << c
  end

  raise "reached EOF while in string" if scanner.eos?
end

#after_operator? ⇒ Boolean

Returns:

  • (Boolean) 


66
67
68
 
# File 'opal/lib/opal/parser/lexer.rb', line 66

def after_operator?
  [:expr_fname, :expr_dot].include? @lex_state
end

#arg? ⇒ Boolean

Returns:

  • (Boolean) 


54
55
56
 
# File 'opal/lib/opal/parser/lexer.rb', line 54

def arg?
  [:expr_arg, :expr_cmdarg].include? @lex_state
end

#beg? ⇒ Boolean

Returns:

  • (Boolean) 


62
63
64
 
# File 'opal/lib/opal/parser/lexer.rb', line 62

def beg?
  [:expr_beg, :expr_value, :expr_mid, :expr_class].include? @lex_state
end

#check(regexp) ⇒ Object 



82
83
84
 
# File 'opal/lib/opal/parser/lexer.rb', line 82

def check(regexp)
  @scanner.check regexp
end

#cmdarg? ⇒ Boolean

Returns:

  • (Boolean) 


50
51
52
 
# File 'opal/lib/opal/parser/lexer.rb', line 50

def cmdarg?
  (@cmdarg & 1) != 0
end

#cmdarg_lexpop ⇒ Object 



46
47
48
 
# File 'opal/lib/opal/parser/lexer.rb', line 46

def cmdarg_lexpop
  @cmdarg = (@cmdarg >> 1) | (@cmdarg & 1)
end

#cmdarg_pop ⇒ Object 



42
43
44
 
# File 'opal/lib/opal/parser/lexer.rb', line 42

def cmdarg_pop
  @cmdarg = @cmdarg >> 1
end

#cmdarg_push(n) ⇒ Object 



38
39
40
 
# File 'opal/lib/opal/parser/lexer.rb', line 38

def cmdarg_push(n)
  @cmdarg = (@cmdarg << 1) | (n & 1)
end

#cond? ⇒ Boolean

Returns:

  • (Boolean) 


34
35
36
 
# File 'opal/lib/opal/parser/lexer.rb', line 34

def cond?
  (@cond & 1) != 0
end

#cond_lexpop ⇒ Object 



30
31
32
 
# File 'opal/lib/opal/parser/lexer.rb', line 30

def cond_lexpop
  @cond = (@cond >> 1) | (@cond & 1)
end

#cond_pop ⇒ Object 



26
27
28
 
# File 'opal/lib/opal/parser/lexer.rb', line 26

def cond_pop
  @cond = @cond >> 1
end

#cond_push(n) ⇒ Object 



22
23
24
 
# File 'opal/lib/opal/parser/lexer.rb', line 22

def cond_push(n)
  @cond = (@cond << 1) | (n & 1)
end

#end? ⇒ Boolean

Returns:

  • (Boolean) 


58
59
60
 
# File 'opal/lib/opal/parser/lexer.rb', line 58

def end?
  [:expr_end, :expr_endarg, :expr_endfn].include? @lex_state
end

#heredoc_identifier ⇒ Object 



384
385
386
387
388
389
390
391
392
393
394
395
396
 
# File 'opal/lib/opal/parser/lexer.rb', line 384

def heredoc_identifier
  if @scanner.scan(/(-?)['"]?(\w+)['"]?/)
    heredoc = @scanner[2]
    self.strterm = new_strterm(:heredoc, heredoc, heredoc)

    # if ruby code at end of line after heredoc, we have to store it to
    # parse after heredoc is finished parsing
    end_of_line = @scanner.scan(/.*\n/)
    self.strterm[:scanner] = StringScanner.new(end_of_line) if end_of_line != "\n"

    return :tSTRING_BEG, heredoc
  end
end

#matched ⇒ Object 



86
87
88
 
# File 'opal/lib/opal/parser/lexer.rb', line 86

def matched
  @scanner.matched
end

#new_strterm(type, start, finish) ⇒ Object 



100
101
102
 
# File 'opal/lib/opal/parser/lexer.rb', line 100

def new_strterm(type, start, finish)
  { :type => type, :beg => start, :end => finish }
end

#new_strterm2(type, start, finish) ⇒ Object 



104
105
106
107
 
# File 'opal/lib/opal/parser/lexer.rb', line 104

def new_strterm2(type, start, finish)
  term = new_strterm(type, start, finish)
  term.merge({ :balance => true, :nesting => 0 })
end

#next_string_token ⇒ Object 



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
166
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
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
 
# File 'opal/lib/opal/parser/lexer.rb', line 128

def next_string_token
  str_parse = self.strterm
  scanner = @scanner
  space = false

  expand = strterm_expand?(str_parse)

  words = ['w', 'W'].include? str_parse[:beg]

  space = true if ['w', 'W'].include?(str_parse[:beg]) and scan(/\s+/)

  # if not end of string, so we must be parsing contents
  str_buffer = []

  if str_parse[:type] == :heredoc
    eos_regx = /[ \t]*#{Regexp.escape(str_parse[:end])}(\r*\n|$)/

    if check(eos_regx)
      scan(/[ \t]*#{Regexp.escape(str_parse[:end])}/)
      self.strterm = nil

      if str_parse[:scanner]
        @scanner_stack << str_parse[:scanner]
        @scanner = str_parse[:scanner]
      end

      @lex_state = :expr_end
      return :tSTRING_END, scanner.matched
    end
  end

  # see if we can read end of string/xstring/regexp markers
  # if scan /#{str_parse[:end]}/
  if scan Regexp.new(Regexp.escape(str_parse[:end]))
    if words && !str_parse[:done_last_space]#&& space
      str_parse[:done_last_space] = true
      scanner.pos -= 1
      return :tSPACE, ' '
    end
    self.strterm = nil

    if str_parse[:balance]
      if str_parse[:nesting] == 0
        @lex_state = :expr_end

        if str_parse[:type] == :regexp
          result = scan(/\w+/)
          return :tREGEXP_END, result
        end
        return :tSTRING_END, scanner.matched
      else
        str_buffer << scanner.matched
        str_parse[:nesting] -= 1
        self.strterm = str_parse
      end

    elsif ['"', "'"].include? str_parse[:beg]
      @lex_state = :expr_end
      return :tSTRING_END, scanner.matched

    elsif str_parse[:beg] == '`'
      @lex_state = :expr_end
      return :tSTRING_END, scanner.matched

    elsif str_parse[:beg] == '/' || str_parse[:type] == :regexp
      result = scan(/\w+/)
      @lex_state = :expr_end
      return :tREGEXP_END, result

    else
      if str_parse[:scanner]
        @scanner_stack << str_parse[:scanner]
        @scanner = str_parse[:scanner]
      end

      @lex_state = :expr_end
      return :tSTRING_END, scanner.matched
    end
  end

  return :tSPACE, ' ' if space

  if str_parse[:balance] and scan Regexp.new(Regexp.escape(str_parse[:beg]))
    str_buffer << scanner.matched
    str_parse[:nesting] += 1
  elsif check(/#[@$]/)
    scan(/#/)
    if expand
      return :tSTRING_DVAR, scanner.matched
    else
      str_buffer << scanner.matched
    end

  elsif scan(/#\{/)
    if expand
      # we are into ruby code, so stop parsing content (for now)
      return :tSTRING_DBEG, scanner.matched
    else
      str_buffer << scanner.matched
    end

  # causes error, so we will just collect it later on with other text
  elsif scan(/\#/)
    str_buffer << '#'
  end

  if str_parse[:type] == :heredoc
    add_heredoc_content str_buffer, str_parse
  else
    add_string_content str_buffer, str_parse
  end

  complete_str = str_buffer.join ''
  @line += complete_str.count("\n")
  return :tSTRING_CONTENT, complete_str
end

#next_token ⇒ Object 



90
91
92
 
# File 'opal/lib/opal/parser/lexer.rb', line 90

def next_token
  self.yylex
end

#process_identifier(matched, cmd_start) ⇒ Object 



398
399
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
450
451
452
453
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
480
481
482
483
484
485
486
487
 
# File 'opal/lib/opal/parser/lexer.rb', line 398

def process_identifier(matched, cmd_start)
  scanner = @scanner
  matched = scanner.matched

  if scanner.peek(2) != '::' && scan(/:/)
    @lex_state = :expr_beg
    return :tLABEL, "#{matched}"
  end

  if matched == 'defined?'
    if after_operator?
      @lex_state = :expr_end
      return :tIDENTIFIER, matched
    end

    @lex_state = :expr_arg
    return :kDEFINED, 'defined?'
  end

  if matched.end_with? '?', '!'
    result = :tIDENTIFIER
  else
    if @lex_state == :expr_fname
      if scan(/\=/)
        result = :tIDENTIFIER
        matched += scanner.matched
      end

    elsif matched =~ /^[A-Z]/
      result = :tCONSTANT
    else
      result = :tIDENTIFIER
    end
  end

  if @lex_state != :expr_dot and kw = Keywords.keyword(matched)
    old_state = @lex_state
    @lex_state = kw.state

    if old_state == :expr_fname
      return [kw.id[0], kw.name]
    end

    if @lex_state == :expr_beg
      cmd_start = true
    end

    if matched == "do"
      if after_operator?
        @lex_state = :expr_end
        return :tIDENTIFIER, matched
      end

      if @start_of_lambda
        @start_of_lambda = false
        @lex_state = :expr_beg
        return [:kDO_LAMBDA, scanner.matched]
      elsif cond?
        @lex_state = :expr_beg
        return :kDO_COND, matched
      elsif cmdarg? && @lex_state != :expr_cmdarg
        @lex_state = :expr_beg
        return :kDO_BLOCK, matched
      elsif @lex_state == :expr_endarg
        return :kDO_BLOCK, matched
      else
        @lex_state = :expr_beg
        return :kDO, matched
      end
    else
      if old_state == :expr_beg or old_state == :expr_value
        return [kw.id[0], matched]
      else
        if kw.id[0] != kw.id[1]
          @lex_state = :expr_beg
        end

        return [kw.id[1], matched]
      end
    end
  end

  if [:expr_beg, :expr_dot, :expr_mid, :expr_arg, :expr_cmdarg].include? @lex_state
    @lex_state = cmd_start ? :expr_cmdarg : :expr_arg
  else
    @lex_state = :expr_end
  end

  return [matched =~ /^[A-Z]/ ? :tCONSTANT : :tIDENTIFIER, matched]
end

#process_numeric ⇒ Object 



109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'opal/lib/opal/parser/lexer.rb', line 109

def process_numeric
  @lex_state = :expr_end
  scanner = @scanner

  if scan(/0b?(0|1|_)+/)
    return [:tINTEGER, scanner.matched.to_i(2)]
  elsif scan(/0o?([0-7]|_)+/)
    return [:tINTEGER, scanner.matched.to_i(8)]
  elsif scan(/[\d_]+\.[\d_]+\b|[\d_]+(\.[\d_]+)?[eE][-+]?[\d_]+\b/)
    return [:tFLOAT, scanner.matched.gsub(/_/, '').to_f]
  elsif scan(/[\d_]+\b/)
    return [:tINTEGER, scanner.matched.gsub(/_/, '').to_i]
  elsif scan(/0(x|X)(\d|[a-f]|[A-F]|_)+/)
    return [:tINTEGER, scanner.matched.to_i(16)]
  else
    raise "Lexing error on numeric type: `#{scanner.peek 5}`"
  end
end

#scan(regexp) ⇒ Object 



78
79
80
 
# File 'opal/lib/opal/parser/lexer.rb', line 78

def scan(regexp)
  @scanner.scan regexp
end

#space? ⇒ Boolean

Returns:

  • (Boolean) 


74
75
76
 
# File 'opal/lib/opal/parser/lexer.rb', line 74

def space?
  @scanner.check(/\s/)
end

#spcarg? ⇒ Boolean

Returns:

  • (Boolean) 


70
71
72
 
# File 'opal/lib/opal/parser/lexer.rb', line 70

def spcarg?
  arg? and @space_seen and !space?
end

#strterm_expand?(strterm) ⇒ Boolean

Returns:

  • (Boolean) 


94
95
96
97
98
 
# File 'opal/lib/opal/parser/lexer.rb', line 94

def strterm_expand?(strterm)
  type = strterm[:type]

  [:dquote, :dsym, :dword, :heredoc, :xquote, :regexp].include? type
end

#yylex ⇒ Object 



489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
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
577
578
579
580
581
582
583
584
585
586
587
588
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
 
# File 'opal/lib/opal/parser/lexer.rb', line 489

def yylex
  @space_seen = false
  cmd_start = false
  c = ''

  if self.strterm
    return next_string_token
  end

  while true
    if scan(/\ |\t|\r/)
      @space_seen = true
      next

    elsif scan(/(\n|#)/)
      c = scanner.matched
      if c == '#' then scan(/(.*)/) else @line += 1; end

      scan(/(\n+)/)
      @line += scanner.matched.length if scanner.matched

      next if [:expr_beg, :expr_dot].include? @lex_state

      if scan(/([\ \t\r\f\v]*)\./)
        @space_seen = true unless scanner[1].empty?
        scanner.pos = scanner.pos - 1

        next unless check(/\.\./)
      end

      cmd_start = true
      @lex_state = :expr_beg
      return :tNL, '\\n'

    elsif scan(/\;/)
      @lex_state = :expr_beg
      return :tSEMI, ';'

    elsif scan(/\*/)
      if scan(/\*/)
        if scan(/\=/)
          @lex_state = :expr_beg
          return :tOP_ASGN, '**'
        end

        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end

        return :tPOW, '**'

      else
        if scan(/\=/)
          @lex_state = :expr_beg
          return :tOP_ASGN, '*'
        end
      end

      if scan(/\*\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '**'
      end

      if scan(/\*/)
        if after_operator?
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end

        return :tPOW, '**'
      end

      if scan(/\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '*'
      else
        result = '*'
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
          return :tSTAR2, result
        elsif @space_seen && check(/\S/)
          @lex_state = :expr_beg
          return :tSTAR, result
        elsif [:expr_beg, :expr_mid].include? @lex_state
          @lex_state = :expr_beg
          return :tSTAR, result
        else
          @lex_state = :expr_beg
          return :tSTAR2, result
        end
      end

    elsif scan(/\!/)
      c = scan(/./)
      if after_operator?
        @lex_state = :expr_arg
        if c == "@"
          return :tBANG, '!'
        end
      else
        @lex_state = :expr_beg
      end

      if c == '='
        return :tNEQ, '!='
      elsif c == '~'
        return :tNMATCH, '!~'
      end

      scanner.pos = scanner.pos - 1
      return :tBANG, '!'

    elsif scan(/\=/)
      if @lex_state == :expr_beg and !@space_seen
        if scan(/begin/) and space?
          scan(/(.*)/) # end of line
          line_count = 0

          while true
            if scanner.eos?
              raise "embedded document meets end of file"
            end

            if scan(/\=end/) and space?
              @line += line_count
              return next_token
            end

            if scan(/\n/)
              line_count += 1
              next
            end

            scan(/(.*)/)
          end
        end
      end

      @lex_state = if after_operator?
                     :expr_arg
                   else
                     :expr_beg
                   end

      if scan(/\=/)
        if scan(/\=/)
          return :tEQQ, '==='
        end

        return :tEQ, '=='
      end

      if scan(/\~/)
        return :tMATCH, '=~'
      elsif scan(/\>/)
        return :tASSOC, '=>'
      end

      return :tEQL, '='

    elsif scan(/\"/)
      self.strterm = new_strterm(:dquote, '"', '"')
      return :tSTRING_BEG, scanner.matched

    elsif scan(/\'/)
      self.strterm = new_strterm(:squote, "'", "'")
      return :tSTRING_BEG, scanner.matched

    elsif scan(/\`/)
      self.strterm = new_strterm(:xquote, '`', '`')
      return :tXSTRING_BEG, scanner.matched

    elsif scan(/\&/)
      if scan(/\&/)
        @lex_state = :expr_beg

        if scan(/\=/)
          return :tOP_ASGN, '&&'
        end

        return :tANDOP, '&&'

      elsif scan(/\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '&'
      end

      if spcarg?
        #puts "warning: `&' interpreted as argument prefix"
        result = :tAMPER
      elsif beg?
        result = :tAMPER
      else
        #puts "warn_balanced: & argument prefix"
        result = :tAMPER2
      end

      @lex_state = after_operator? ? :expr_arg : :expr_beg
      return result, '&'

    elsif scan(/\|/)
      if scan(/\|/)
        @lex_state = :expr_beg
        if scan(/\=/)
          return :tOP_ASGN, '||'
        end

        return :tOROP, '||'

      elsif scan(/\=/)
        return :tOP_ASGN, '|'
      end

      @lex_state = after_operator?() ? :expr_arg : :expr_beg
      return :tPIPE, '|'

    elsif scan(/\%[QqWwixr]/)
      str_type = scanner.matched[1, 1]
      paren = scan(/./)

      term = case paren
             when '(' then ')'
             when '[' then ']'
             when '{' then '}'
             else paren
             end

      case str_type
      when 'Q'
        self.strterm = new_strterm2(:dquote, paren, term)
        return :tSTRING_BEG, scanner.matched
      when 'q'
        self.strterm = new_strterm2(:squote, paren, term)
        return :tSTRING_BEG, scanner.matched
      when 'W'
        self.strterm = new_strterm(:dword, 'W', term)
        scan(/\s*/)
        return :tWORDS_BEG, scanner.matched
      when 'w', 'i'
        self.strterm = new_strterm(:sword, 'w', term)
        scan(/\s*/)
        return :tAWORDS_BEG, scanner.matched
      when 'x'
        self.strterm = new_strterm2(:xquote, paren, term)
        return :tXSTRING_BEG, scanner.matched
      when 'r'
        self.strterm = new_strterm2(:regexp, paren, term)
        return :tREGEXP_BEG, scanner.matched
      end

    elsif scan(/\//)
      if [:expr_beg, :expr_mid].include? @lex_state
        self.strterm = new_strterm(:regexp, '/', '/')
        return :tREGEXP_BEG, scanner.matched
      elsif scan(/\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '/'
      elsif @lex_state == :expr_fname or @lex_state == :expr_dot
        @lex_state = :expr_arg
      elsif @lex_state == :expr_cmdarg || @lex_state == :expr_arg
        if !check(/\s/) && @space_seen
          self.strterm = new_strterm(:regexp, '/', '/')
          return :tREGEXP_BEG, scanner.matched
        end
      else
        @lex_state = :expr_beg
      end

      return :tDIVIDE, '/'

    elsif scan(/\%/)
      if scan(/\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '%'
      elsif check(/[^\s]/)
        if @lex_state == :expr_beg or (@lex_state == :expr_arg && @space_seen)
          start_word  = scan(/./)
          end_word    = { '(' => ')', '[' => ']', '{' => '}' }[start_word] || start_word
          self.strterm = new_strterm2(:dquote, start_word, end_word)
          return :tSTRING_BEG, scanner.matched
        end
      end

      @lex_state = after_operator? ? :expr_arg : :expr_beg

      return :tPERCENT, '%'

    elsif scan(/\\/)
      if scan(/\r?\n/)
        @space_seen = true
        next
      end

      raise SyntaxError, "backslash must appear before newline :#{@file}:#{@line}"

    elsif scan(/\(/)
      result = scanner.matched
      if [:expr_beg, :expr_mid].include? @lex_state
        result = :tLPAREN
      elsif @space_seen && [:expr_arg, :expr_cmdarg].include?(@lex_state)
        result = :tLPAREN_ARG
      else
        result = :tLPAREN2
      end

      @lex_state = :expr_beg
      cond_push 0
      cmdarg_push 0

      return result, scanner.matched

    elsif scan(/\)/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end
      return :tRPAREN, scanner.matched

    elsif scan(/\[/)
      result = scanner.matched

      if [:expr_fname, :expr_dot].include? @lex_state
        @lex_state = :expr_arg
        if scan(/\]=/)
          return :tASET, '[]='
        elsif scan(/\]/)
          return :tAREF, '[]'
        else
          raise "Unexpected '[' token"
        end
      elsif [:expr_beg, :expr_mid].include?(@lex_state) || @space_seen
        @lex_state = :expr_beg
        cond_push 0
        cmdarg_push 0
        return :tLBRACK, scanner.matched
      else
        @lex_state = :expr_beg
        cond_push 0
        cmdarg_push 0
        return :tLBRACK2, scanner.matched
      end

    elsif scan(/\]/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end
      return :tRBRACK, scanner.matched

    elsif scan(/\}/)
      cond_lexpop
      cmdarg_lexpop
      @lex_state = :expr_end

      return :tRCURLY, scanner.matched

    elsif scan(/\.\.\./)
      @lex_state = :expr_beg
      return :tDOT3, scanner.matched

    elsif scan(/\.\./)
      @lex_state = :expr_beg
      return :tDOT2, scanner.matched

    elsif scan(/\./)
      @lex_state = :expr_dot unless @lex_state == :expr_fname
      return :tDOT, scanner.matched

    elsif scan(/\:\:/)
      if [:expr_beg, :expr_mid, :expr_class].include? @lex_state
        @lex_state = :expr_beg
        return :tCOLON3, scanner.matched
      elsif @space_seen && @lex_state == :expr_arg
        @lex_state = :expr_beg
        return :tCOLON3, scanner.matched
      end

      @lex_state = :expr_dot
      return :tCOLON2, scanner.matched

    elsif scan(/\:/)
      if end? || check(/\s/)
        unless check(/\w/)
          @lex_state = :expr_beg
          return :tCOLON, ':'
        end

        @lex_state = :expr_fname
        return :tSYMBEG, ':'
      end

      if scan(/\'/)
        self.strterm = new_strterm(:ssym, "'", "'")
      elsif scan(/\"/)
        self.strterm = new_strterm(:dsym, '"', '"')
      end

      @lex_state = :expr_fname
      return :tSYMBEG, ':'

    elsif scan(/\^\=/)
      @lex_state = :expr_beg
      return :tOP_ASGN, '^'
    elsif scan(/\^/)
      if @lex_state == :expr_fname or @lex_state == :expr_dot
        @lex_state = :expr_arg
        return :tCARET, scanner.matched
      end

      @lex_state = :expr_beg
      return :tCARET, scanner.matched

    elsif check(/\</)
      if scan(/\<\<\=/)
        @lex_state = :expr_beg
        return :tOP_ASGN, '<<'
      elsif scan(/\<\</)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
          return :tLSHFT, '<<'
        elsif ![:expr_dot, :expr_class].include?(@lex_state) && !end? && (!arg? || @space_seen)
          if token = heredoc_identifier
            return token
          end

          @lex_state = :expr_beg
          return :tLSHFT, '<<'
        end
        @lex_state = :expr_beg
        return :tLSHFT, '<<'
      elsif scan(/\<\=\>/)
        if after_operator?
          @lex_state = :expr_arg
        else
          if @lex_state == :expr_class
            cmd_start = true
          end

          @lex_state = :expr_beg
        end

        return :tCMP, '<=>'
      elsif scan(/\<\=/)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end
        return :tLEQ, '<='
      elsif scan(/\</)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end
        return :tLT, '<'
      end

    elsif check(/\>/)
      if scan(/\>\>\=/)
        return :tOP_ASGN, '>>'
      elsif scan(/\>\>/)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end
        return :tRSHFT, '>>'
      elsif scan(/\>\=/)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_end
        else
          @lex_state = :expr_beg
        end
        return :tGEQ, scanner.matched
      elsif scan(/\>/)
        if @lex_state == :expr_fname or @lex_state == :expr_dot
          @lex_state = :expr_arg
        else
          @lex_state = :expr_beg
        end
        return :tGT, '>'
      end

    elsif scan(/->/)
      # FIXME: # should be :expr_arg, but '(' breaks it...
      @lex_state = :expr_end
      @start_of_lambda = true
      return [:tLAMBDA, scanner.matched]

    elsif scan(/[+-]/)
      matched = scanner.matched
      sign, utype = if matched == '+'
                      [:tPLUS, :tUPLUS]
                    else
                      [:tMINUS, :tUMINUS]
                    end

      if beg?
        @lex_state = :expr_mid
        return [utype, matched]
      elsif after_operator?
        @lex_state = :expr_arg
        return [:tIDENTIFIER, matched + '@'] if scan(/@/)
        return [sign, matched]
      end

      if scan(/\=/)
        @lex_state = :expr_beg
        return [:tOP_ASGN, matched]
      end

      if arg?
        if !space? && @space_seen
          @lex_state = :expr_mid
          return [utype, matched]
        end
      end

      @lex_state = :expr_beg
      return [sign, sign]

    elsif scan(/\?/)
      if end?
        @lex_state = :expr_beg
        return :tEH, scanner.matched
      end

      unless check(/\ |\t|\r|\s/)
        @lex_state = :expr_end
        return :tSTRING, scan(/./)
      end

      @lex_state = :expr_beg
      return :tEH, scanner.matched

    elsif scan(/\~/)
      if @lex_state == :expr_fname
        @lex_state = :expr_end
        return :tTILDE, '~'
      end
      @lex_state = :expr_beg
      return :tTILDE, '~'

    elsif check(/\$/)
      if scan(/\$([1-9]\d*)/)
        @lex_state = :expr_end
        return :tNTH_REF, scanner.matched.sub('$', '')

      elsif scan(/(\$_)(\w+)/)
        @lex_state = :expr_end
        return :tGVAR, scanner.matched

      elsif scan(/\$[\+\'\`\&!@\"~*$?\/\\:;=.,<>_]/)
        @lex_state = :expr_end
        return :tGVAR, scanner.matched
      elsif scan(/\$\w+/)
        @lex_state = :expr_end
        return :tGVAR, scanner.matched
      else
        raise "Bad gvar name: #{scanner.peek(5).inspect}"
      end

    elsif scan(/\$\w+/)
      @lex_state = :expr_end
      return :tGVAR, scanner.matched

    elsif scan(/\@\@\w*/)
      @lex_state = :expr_end
      return :tCVAR, scanner.matched

    elsif scan(/\@\w*/)
      @lex_state = :expr_end
      return :tIVAR, scanner.matched

    elsif scan(/\,/)
      @lex_state = :expr_beg
      return :tCOMMA, scanner.matched

    elsif scan(/\{/)
      if @start_of_lambda
        @start_of_lambda = false
        @lex_state = :expr_beg
        return [:tLAMBEG, scanner.matched]

      elsif [:expr_end, :expr_arg, :expr_cmdarg].include? @lex_state
        result = :tLCURLY
      elsif @lex_state == :expr_endarg
        result = :LBRACE_ARG
      else
        result = '{'
      end

      @lex_state = :expr_beg
      cond_push 0
      cmdarg_push 0
      return result, scanner.matched

    elsif check(/[0-9]/)
      return process_numeric

    elsif scan(/(\w)+[\?\!]?/)
      return process_identifier scanner.matched, cmd_start
    end

    if scanner.eos?
      if @scanner_stack.size == 1 # our main scanner, we cant pop this
        return [false, false]
      else # we were probably parsing a heredoc, so pop that parser and continue
        @scanner_stack.pop
        @scanner = @scanner_stack.last
        return next_token
      end
    end

    raise "Unexpected content in parsing stream `#{scanner.peek 5}` :#{@file}:#{@line}"
  end
end