summaryrefslogtreecommitdiff
path: root/lib/irb/ruby-lex.rb
blob: 4c51afbc28aaa240b40caca6c4f2ee8fb20ace11 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
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
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
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
277
278
279
280
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
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
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
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
488
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
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
#
#   irb/ruby-lex.rb - ruby lexcal analizer
#   	$Release Version: 0.9.5$
#   	$Revision$
#   	$Date$
#   	by Keiju ISHITSUKA(keiju@ruby-lang.org)
#
# --
#
#   
#

require "e2mmap"
require "irb/slex"
require "irb/ruby-token"

class RubyLex
  @RCS_ID='-$Id$-'

  extend Exception2MessageMapper
  def_exception(:AlreadyDefinedToken, "Already defined token(%s)")
  def_exception(:TkReading2TokenNoKey, "key nothing(key='%s')")
  def_exception(:TkSymbol2TokenNoKey, "key nothing(key='%s')")
  def_exception(:TkReading2TokenDuplicateError, 
		"key duplicate(token_n='%s', key='%s')")
  def_exception(:SyntaxError, "%s")

  def_exception(:TerminateLineInput, "Terminate Line Input")
  
  include RubyToken

  class << self
    attr_accessor :debug_level
    def debug?
      @debug_level > 0
    end
  end
  @debug_level = 0

  def initialize
    lex_init
    set_input(STDIN)

    @seek = 0
    @exp_line_no = @line_no = 1
    @base_char_no = 0
    @char_no = 0
    @rests = []
    @readed = []
    @here_readed = []

    @indent = 0
    @indent_stack = []
    @lex_state = EXPR_BEG
    @space_seen = false
    @here_header = false
    
    @continue = false
    @line = ""

    @skip_space = false
    @readed_auto_clean_up = false
    @exception_on_syntax_error = true

    @prompt = nil
  end

  attr_accessor :skip_space
  attr_accessor :readed_auto_clean_up
  attr_accessor :exception_on_syntax_error

  attr_reader :seek
  attr_reader :char_no
  attr_reader :line_no
  attr_reader :indent

  # io functions
  def set_input(io, p = nil, &block)
    @io = io
    if p.respond_to?(:call)
      @input = p
    elsif block_given?
      @input = block
    else
      @input = Proc.new{@io.gets}
    end
  end

  def get_readed
    if idx = @readed.reverse.index("\n")
      @base_char_no = idx
    else
      @base_char_no += @readed.size
    end
    
    readed = @readed.join("")
    @readed = []
    readed
  end

  def getc
    while @rests.empty?
#      return nil unless buf_input
      @rests.push nil unless buf_input
    end
    c = @rests.shift
    if @here_header
      @here_readed.push c
    else
      @readed.push c
    end
    @seek += 1
    if c == "\n"
      @line_no += 1 
      @char_no = 0
    else
      @char_no += 1
    end
    c
  end

  def gets
    l = ""
    while c = getc
      l.concat(c)
      break if c == "\n"
    end
    return nil if l == "" and c.nil?
    l
  end

  def eof?
    @io.eof?
  end

  def getc_of_rests
    if @rests.empty?
      nil
    else
      getc
    end
  end

  def ungetc(c = nil)
    if @here_readed.empty?
      c2 = @readed.pop
    else
      c2 = @here_readed.pop
    end
    c = c2 unless c
    @rests.unshift c #c = 
      @seek -= 1
    if c == "\n"
      @line_no -= 1 
      if idx = @readed.reverse.index("\n")
	@char_no = @readed.size - idx
      else
	@char_no = @base_char_no + @readed.size
      end
    else
      @char_no -= 1
    end
  end

  def peek_equal?(str)
    chrs = str.split(//)
    until @rests.size >= chrs.size
      return false unless buf_input
    end
    @rests[0, chrs.size] == chrs
  end

  def peek_match?(regexp)
    while @rests.empty?
      return false unless buf_input
    end
    regexp =~ @rests.join("")
  end

  def peek(i = 0)
    while @rests.size <= i
      return nil unless buf_input
    end
    @rests[i]
  end

  def buf_input
    prompt
    line = @input.call
    return nil unless line
    @rests.concat line.split(//)
    true
  end
  private :buf_input

  def set_prompt(p = nil, &block)
    p = block if block_given?
    if p.respond_to?(:call)
      @prompt = p
    else
      @prompt = Proc.new{print p}
    end
  end

  def prompt
    if @prompt
      @prompt.call(@ltype, @indent, @continue, @line_no)
    end
  end

  def initialize_input
    @ltype = nil
    @quoted = nil
    @indent = 0
    @indent_stack = []
    @lex_state = EXPR_BEG
    @space_seen = false
    @here_header = false
    
    @continue = false
    prompt

    @line = ""
    @exp_line_no = @line_no
  end
  
  def each_top_level_statement
    initialize_input
    catch(:TERM_INPUT) do
      loop do
	begin
	  @continue = false
	  prompt
	  unless l = lex
	    throw :TERM_INPUT if @line == ''
	  else
	    #p l
	    @line.concat l
	    if @ltype or @continue or @indent > 0
	      next
	    end
	  end
	  if @line != "\n"
	    yield @line, @exp_line_no
	  end
	  break unless l
	  @line = ''
	  @exp_line_no = @line_no

	  @indent = 0
	  @indent_stack = []
	  prompt
	rescue TerminateLineInput
	  initialize_input
	  prompt
	  get_readed
	end
      end
    end
  end

  def lex
    until (((tk = token).kind_of?(TkNL) || tk.kind_of?(TkEND_OF_SCRIPT)) &&
	     !@continue or
	     tk.nil?)
      #p tk
      #p @lex_state
      #p self
    end
    line = get_readed
    #      print self.inspect
    if line == "" and tk.kind_of?(TkEND_OF_SCRIPT) || tk.nil?
      nil
    else
      line
    end
  end

  def token
    #      require "tracer"
    #      Tracer.on
    @prev_seek = @seek
    @prev_line_no = @line_no
    @prev_char_no = @char_no
    begin
      begin
	tk = @OP.match(self)
	@space_seen = tk.kind_of?(TkSPACE)
      rescue SyntaxError
	raise if @exception_on_syntax_error
	tk = TkError.new(@seek, @line_no, @char_no)
      end
    end while @skip_space and tk.kind_of?(TkSPACE)
    if @readed_auto_clean_up
      get_readed
    end
    #      Tracer.off
    tk
  end
  
  ENINDENT_CLAUSE = [
    "case", "class", "def", "do", "for", "if",
    "module", "unless", "until", "while", "begin" #, "when"
  ]
  DEINDENT_CLAUSE = ["end" #, "when"
  ]

  PERCENT_LTYPE = {
    "q" => "\'",
    "Q" => "\"",
    "x" => "\`",
    "r" => "\/",
    "w" => "]",
    "W" => "]",
    "s" => ":"
  }
  
  PERCENT_PAREN = {
    "{" => "}",
    "[" => "]",
    "<" => ">",
    "(" => ")"
  }

  Ltype2Token = {
    "\'" => TkSTRING,
    "\"" => TkSTRING,
    "\`" => TkXSTRING,
    "\/" => TkREGEXP,
    "]" => TkDSTRING,
    ":" => TkSYMBOL
  }
  DLtype2Token = {
    "\"" => TkDSTRING,
    "\`" => TkDXSTRING,
    "\/" => TkDREGEXP,
  }

  def lex_init()
    @OP = IRB::SLex.new
    @OP.def_rules("\0", "\004", "\032") do
      Token(TkEND_OF_SCRIPT)
    end

    @OP.def_rules(" ", "\t", "\f", "\r", "\13") do
      @space_seen = true
      while getc =~ /[ \t\f\r\13]/; end
      ungetc
      Token(TkSPACE)
    end

    @OP.def_rule("#") do
      |op, io|
      identify_comment
    end

    @OP.def_rule("=begin", proc{@prev_char_no == 0 && peek(0) =~ /\s/}) do
      |op, io|
      @ltype = "="
      until getc == "\n"; end
      until peek_equal?("=end") && peek(4) =~ /\s/
	until getc == "\n"; end
      end
      gets
      @ltype = nil
      Token(TkRD_COMMENT)
    end

    @OP.def_rule("\n") do
      print "\\n\n" if RubyLex.debug?
      case @lex_state
      when EXPR_BEG, EXPR_FNAME, EXPR_DOT
	@continue = true
      else
	@continue = false
	@lex_state = EXPR_BEG
	until (@indent_stack.empty? || 
	       [TkLPAREN, TkLBRACK, TkLBRACE, 
		 TkfLPAREN, TkfLBRACK, TkfLBRACE].include?(@indent_stack.last))
	  @indent_stack.pop
	end
      end
      @here_header = false
      @here_readed = []
      Token(TkNL)
    end

    @OP.def_rules("*", "**",	
		  "=", "==", "===", 
		  "=~", "<=>",	
		  "<", "<=",
		  ">", ">=", ">>") do
      |op, io|
      case @lex_state
      when EXPR_FNAME, EXPR_DOT
	@lex_state = EXPR_ARG
      else
	@lex_state = EXPR_BEG
      end
      Token(op)
    end

    @OP.def_rules("!", "!=", "!~") do
      |op, io|
      @lex_state = EXPR_BEG
      Token(op)
    end

    @OP.def_rules("<<") do
      |op, io|
      tk = nil
      if @lex_state != EXPR_END && @lex_state != EXPR_CLASS &&
	  (@lex_state != EXPR_ARG || @space_seen)
	c = peek(0)
	if /\S/ =~ c && (/["'`]/ =~ c || /[\w_]/ =~ c || c == "-")
	  tk = identify_here_document
	end
      end
      unless tk
	tk = Token(op)
	case @lex_state
	when EXPR_FNAME, EXPR_DOT
	  @lex_state = EXPR_ARG
	else
	  @lex_state = EXPR_BEG
	end
      end
      tk
    end

    @OP.def_rules("'", '"') do
      |op, io|
      identify_string(op)
    end

    @OP.def_rules("`") do
      |op, io|
      if @lex_state == EXPR_FNAME
	@lex_state = EXPR_END
	Token(op)
      else
	identify_string(op)
      end
    end

    @OP.def_rules('?') do
      |op, io|
      if @lex_state == EXPR_END
	@lex_state = EXPR_BEG
	Token(TkQUESTION)
      else
	ch = getc
	if @lex_state == EXPR_ARG && ch =~ /\s/
	  ungetc
	  @lex_state = EXPR_BEG;
	  Token(TkQUESTION)
	else
	  if (ch == '\\') 
	    read_escape
	  end
	  @lex_state = EXPR_END
	  Token(TkINTEGER)
	end
      end
    end

    @OP.def_rules("&", "&&", "|", "||") do
      |op, io|
      @lex_state = EXPR_BEG
      Token(op)
    end
    
    @OP.def_rules("+=", "-=", "*=", "**=", 
		  "&=", "|=", "^=", "<<=", ">>=", "||=", "&&=") do
      |op, io|
      @lex_state = EXPR_BEG
      op =~ /^(.*)=$/
      Token(TkOPASGN, $1)
    end

    @OP.def_rule("+@", proc{@lex_state == EXPR_FNAME}) do
      |op, io|
      @lex_state = EXPR_ARG
      Token(op)
    end

    @OP.def_rule("-@", proc{@lex_state == EXPR_FNAME}) do
      |op, io|
      @lex_state = EXPR_ARG
      Token(op)
    end

    @OP.def_rules("+", "-") do
      |op, io|
      catch(:RET) do
	if @lex_state == EXPR_ARG
	  if @space_seen and peek(0) =~ /[0-9]/
	    throw :RET, identify_number
	  else
	    @lex_state = EXPR_BEG
	  end
	elsif @lex_state != EXPR_END and peek(0) =~ /[0-9]/
	  throw :RET, identify_number
	else
	  @lex_state = EXPR_BEG
	end
	Token(op)
      end
    end

    @OP.def_rule(".") do
      @lex_state = EXPR_BEG
      if peek(0) =~ /[0-9]/
	ungetc
	identify_number
      else
	# for "obj.if" etc.
	@lex_state = EXPR_DOT
	Token(TkDOT)
      end
    end

    @OP.def_rules("..", "...") do
      |op, io|
      @lex_state = EXPR_BEG
      Token(op)
    end

    lex_int2
  end
  
  def lex_int2
    @OP.def_rules("]", "}", ")") do
      |op, io|
      @lex_state = EXPR_END
      @indent -= 1
      @indent_stack.pop
      Token(op)
    end

    @OP.def_rule(":") do
      if @lex_state == EXPR_END || peek(0) =~ /\s/
	@lex_state = EXPR_BEG
	Token(TkCOLON)
      else
	@lex_state = EXPR_FNAME;
	Token(TkSYMBEG)
      end
    end

    @OP.def_rule("::") do
#      p @lex_state.id2name, @space_seen
      if @lex_state == EXPR_BEG or @lex_state == EXPR_ARG && @space_seen
	@lex_state = EXPR_BEG
	Token(TkCOLON3)
      else
	@lex_state = EXPR_DOT
	Token(TkCOLON2)
      end
    end

    @OP.def_rule("/") do
      |op, io|
      if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
	identify_string(op)
      elsif peek(0) == '='
	getc
	@lex_state = EXPR_BEG
	Token(TkOPASGN, "/") #/)
      elsif @lex_state == EXPR_ARG and @space_seen and peek(0) !~ /\s/
	identify_string(op)
      else 
	@lex_state = EXPR_BEG
	Token("/") #/)
      end
    end

    @OP.def_rules("^") do
      @lex_state = EXPR_BEG
      Token("^")
    end

    #       @OP.def_rules("^=") do
    # 	@lex_state = EXPR_BEG
    # 	Token(OP_ASGN, :^)
    #       end
    
    @OP.def_rules(",") do
      |op, io|
      @lex_state = EXPR_BEG
      Token(op)
    end

    @OP.def_rules(";") do
      |op, io|
      @lex_state = EXPR_BEG
      until (@indent_stack.empty? || 
	     [TkLPAREN, TkLBRACK, TkLBRACE, 
	       TkfLPAREN, TkfLBRACK, TkfLBRACE].include?(@indent_stack.last))
	@indent_stack.pop
      end
      Token(op)
    end

    @OP.def_rule("~") do
      @lex_state = EXPR_BEG
      Token("~")
    end

    @OP.def_rule("~@", proc{@lex_state == EXPR_FNAME}) do
      @lex_state = EXPR_BEG
      Token("~")
    end
    
    @OP.def_rule("(") do
      @indent += 1
      if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
	@lex_state = EXPR_BEG
	tk_c = TkfLPAREN
      else
	@lex_state = EXPR_BEG
	tk_c = TkLPAREN
      end
      @indent_stack.push tk_c
      tk = Token(tk_c)
    end

    @OP.def_rule("[]", proc{@lex_state == EXPR_FNAME}) do
      @lex_state = EXPR_ARG
      Token("[]")
    end

    @OP.def_rule("[]=", proc{@lex_state == EXPR_FNAME}) do
      @lex_state = EXPR_ARG
      Token("[]=")
    end

    @OP.def_rule("[") do
      @indent += 1
      if @lex_state == EXPR_FNAME
	tk_c = TkfLBRACK
      else
	if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
	  tk_c = TkLBRACK
	elsif @lex_state == EXPR_ARG && @space_seen
	  tk_c = TkLBRACK
	else
	  tk_c = TkfLBRACK
	end
	@lex_state = EXPR_BEG
      end
      @indent_stack.push tk_c
      Token(tk_c)
    end

    @OP.def_rule("{") do
      @indent += 1
      if @lex_state != EXPR_END && @lex_state != EXPR_ARG
	tk_c = TkLBRACE
      else
	tk_c = TkfLBRACE
      end
      @lex_state = EXPR_BEG
      @indent_stack.push tk_c
      Token(tk_c)
    end

    @OP.def_rule('\\') do
      if getc == "\n"
	@space_seen = true
	@continue = true
	Token(TkSPACE)
      else
	ungetc
	Token("\\")
      end
    end

    @OP.def_rule('%') do
      |op, io|
      if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
	identify_quotation
      elsif peek(0) == '='
	getc
	Token(TkOPASGN, :%)
      elsif @lex_state == EXPR_ARG and @space_seen and peek(0) !~ /\s/
	identify_quotation
      else
	@lex_state = EXPR_BEG
	Token("%") #))
      end
    end

    @OP.def_rule('$') do
      identify_gvar
    end

    @OP.def_rule('@') do
      if peek(0) =~ /[\w_@]/
	ungetc
	identify_identifier
      else
	Token("@")
      end
    end

    #       @OP.def_rule("def", proc{|op, io| /\s/ =~ io.peek(0)}) do 
    # 	|op, io|
    # 	@indent += 1
    # 	@lex_state = EXPR_FNAME
    # #	@lex_state = EXPR_END
    # #	until @rests[0] == "\n" or @rests[0] == ";"
    # #	  rests.shift
    # #	end
    #       end

    @OP.def_rule("") do
      |op, io|
      printf "MATCH: start %s: %s\n", op, io.inspect if RubyLex.debug?
      if peek(0) =~ /[0-9]/
	t = identify_number
      elsif peek(0) =~ /[\w_]/
	t = identify_identifier
      end
      printf "MATCH: end %s: %s\n", op, io.inspect if RubyLex.debug?
      t
    end
    
    p @OP if RubyLex.debug?
  end
  
  def identify_gvar
    @lex_state = EXPR_END
    
    case ch = getc
    when /[~_*$?!@\/\\;,=:<>".]/   #"
      Token(TkGVAR, "$" + ch)
    when "-"
      Token(TkGVAR, "$-" + getc)
    when "&", "`", "'", "+"
      Token(TkBACK_REF, "$"+ch)
    when /[1-9]/
      while getc =~ /[0-9]/; end
      ungetc
      Token(TkNTH_REF)
    when /\w/
      ungetc
      ungetc
      identify_identifier
    else 
      ungetc
      Token("$")
    end
  end
  
  def identify_identifier
    token = ""
    if peek(0) =~ /[$@]/
      token.concat(c = getc)
      if c == "@" and peek(0) == "@"
	token.concat getc
      end
    end

    while (ch = getc) =~ /\w|_/
      print ":", ch, ":" if RubyLex.debug?
      token.concat ch
    end
    ungetc
    
    if (ch == "!" || ch == "?") && token[0,1] =~ /\w/ && peek(0) != "="
      token.concat getc
    end

    # almost fix token

    case token
    when /^\$/
      return Token(TkGVAR, token)
    when /^\@\@/
      @lex_state = EXPR_END
      # p Token(TkCVAR, token)
      return Token(TkCVAR, token)
    when /^\@/
      @lex_state = EXPR_END
      return Token(TkIVAR, token)
    end
    
    if @lex_state != EXPR_DOT
      print token, "\n" if RubyLex.debug?

      token_c, *trans = TkReading2Token[token]
      if token_c
	# reserved word?

	if (@lex_state != EXPR_BEG &&
	    @lex_state != EXPR_FNAME &&
	    trans[1])
	  # modifiers
	  token_c = TkSymbol2Token[trans[1]]
	  @lex_state = trans[0]
	else
	  if @lex_state != EXPR_FNAME
	    if ENINDENT_CLAUSE.include?(token)
	      # check for ``class = val'' etc.
	      valid = true
	      case token
	      when "class"
		valid = false unless peek_match?(/^\s*(<<|\w|::)/)
	      when "def"
		valid = false if peek_match?(/^\s*(([+-\/*&\|^]|<<|>>|\|\||\&\&)=|\&\&|\|\|)/)
	      when "do"
		valid = false if peek_match?(/^\s*([+-\/*]?=|\*|<|>|\&)/)
	      when *ENINDENT_CLAUSE
		valid = false if peek_match?(/^\s*([+-\/*]?=|\*|<|>|\&|\|)/)
	      else
		# no nothing
	      end
	      if valid
		if token == "do"
		  if ![TkFOR, TkWHILE, TkUNTIL].include?(@indent_stack.last)
		    @indent += 1
		    @indent_stack.push token_c
		  end
		else
		  @indent += 1
		  @indent_stack.push token_c
		end
#		p @indent_stack
	      end

	    elsif DEINDENT_CLAUSE.include?(token)
	      @indent -= 1
	      @indent_stack.pop
	    end
	    @lex_state = trans[0]
	  else
	    @lex_state = EXPR_END
	  end
	end
	return Token(token_c, token)
      end
    end

    if @lex_state == EXPR_FNAME
      @lex_state = EXPR_END
      if peek(0) == '='
	token.concat getc
      end
    elsif @lex_state == EXPR_BEG || @lex_state == EXPR_DOT
      @lex_state = EXPR_ARG
    else
      @lex_state = EXPR_END
    end

    if token[0, 1] =~ /[A-Z]/
      return Token(TkCONSTANT, token)
    elsif token[token.size - 1, 1] =~ /[!?]/
      return Token(TkFID, token)
    else
      return Token(TkIDENTIFIER, token)
    end
  end

  def identify_here_document
    ch = getc
#    if lt = PERCENT_LTYPE[ch]
    if ch == "-"
      ch = getc
      indent = true
    end
    if /['"`]/ =~ ch
      lt = ch
      quoted = ""
      while (c = getc) && c != lt
	quoted.concat c
      end
    else
      lt = '"'
      quoted = ch.dup
      while (c = getc) && c =~ /\w/
	quoted.concat c
      end
      ungetc
    end

    ltback, @ltype = @ltype, lt
    reserve = []
    while ch = getc
      reserve.push ch
      if ch == "\\"
	reserve.push ch = getc
      elsif ch == "\n"
	break
      end
    end

    @here_header = false
    while l = gets
      l = l.sub(/(:?\r)?\n\z/, '')
      if (indent ? l.strip : l) == quoted
 	break
      end
    end

    @here_header = true
    @here_readed.concat reserve
    while ch = reserve.pop
      ungetc ch
    end

    @ltype = ltback
    @lex_state = EXPR_END
    Token(Ltype2Token[lt])
  end
  
  def identify_quotation
    ch = getc
    if lt = PERCENT_LTYPE[ch]
      ch = getc
    elsif ch =~ /\W/
      lt = "\""
    else
      RubyLex.fail SyntaxError, "unknown type of %string"
    end
#     if ch !~ /\W/
#       ungetc
#       next
#     end
    #@ltype = lt
    @quoted = ch unless @quoted = PERCENT_PAREN[ch]
    identify_string(lt, @quoted)
  end

  def identify_number
    @lex_state = EXPR_END

    if peek(0) == "0" && peek(1) !~ /[.eE]/
      getc
      if /[xX]/ =~ peek(0)
	ch = getc
	match = /[0-9a-fA-F_]/
      elsif /[bB]/ =~ peek(0)
	ch = getc
	match = /[01_]/
      elsif /[oO]/ =~ peek(0)
	ch = getc
	match = /[0-7_]/
      else
	match = /[0-7_]/
      end

      len0 = true
      non_digit = false
      while ch = getc
	if match =~ ch
	  if ch == "_"
	    if non_digit
	      RubyLex.fail SyntaxError, "trailing `#{ch}' in number"
	    else
	      non_digit = ch
	    end
	  else
	    non_digit = false
	    len0 = false
	  end
	else
	  ungetc
	  if len0
	    RubyLex.fail SyntaxError, "numeric literal without digits"
	  end
	  if non_digit
	    RubyLex.fail SyntaxError, "trailing `#{non_digit}' in number"
	  end
	  break
	end
      end
      return Token(TkINTEGER)
    end
    
    type = TkINTEGER
    allow_point = true
    allow_e = true
    non_digit = false
    while ch = getc
      case ch
      when /[0-9]/
	non_digit = false
      when "_"
	non_digit = ch
      when allow_point && "."
	if non_digit
	  RubyLex.fail SyntaxError, "trailing `#{non_digit}' in number"
	end
	type = TkFLOAT
	if peek(0) !~ /[0-9]/
	  type = TkINTEGER
	  ungetc
	  break
	end
	allow_point = false
      when allow_e && "e", allow_e && "E"
	if non_digit
	  RubyLex.fail SyntaxError, "trailing `#{non_digit}' in number"
	end
	type = TkFLOAT
	if peek(0) =~ /[+-]/
	  getc
	end
	allow_e = false
	allow_point = false
	non_digit = ch
      else
	if non_digit
	  RubyLex.fail SyntaxError, "trailing `#{non_digit}' in number"
	end
	ungetc
	break
      end
    end
    Token(type)
  end
  
  def identify_string(ltype, quoted = ltype)
    @ltype = ltype
    @quoted = quoted
    subtype = nil
    begin
      nest = 0
      while ch = getc
	if @quoted == ch and nest == 0
	  break
	elsif @ltype != "'" && @ltype != "]" && @ltype != ":" and ch == "#"
	  subtype = true
	elsif ch == '\\' #'
	  read_escape
	end
	if PERCENT_PAREN.values.include?(@quoted) 
	  if PERCENT_PAREN[ch] == @quoted
	    nest += 1
	  elsif ch == @quoted
	    nest -= 1
	  end
	end
      end
      if @ltype == "/"
	if peek(0) =~ /i|m|x|o|e|s|u|n/
	  getc
	end
      end
      if subtype
	Token(DLtype2Token[ltype])
      else
	Token(Ltype2Token[ltype])
      end
    ensure
      @ltype = nil
      @quoted = nil
      @lex_state = EXPR_END
    end
  end
  
  def identify_comment
    @ltype = "#"

    while ch = getc
#      if ch == "\\" #"
#	read_escape
#      end
      if ch == "\n"
	@ltype = nil
	ungetc
	break
      end
    end
    return Token(TkCOMMENT)
  end
  
  def read_escape
    case ch = getc
    when "\n", "\r", "\f"
    when "\\", "n", "t", "r", "f", "v", "a", "e", "b" #"
    when /[0-7]/
      ungetc ch
      3.times do
	case ch = getc
	when /[0-7]/
	when nil
	  break
	else
	  ungetc
	  break
	end
      end
      
    when "x"
      2.times do
	case ch = getc
	when /[0-9a-fA-F]/
	when nil
	  break
	else
	  ungetc
	  break
	end
      end

    when "M"
      if (ch = getc) != '-'
	ungetc
      else
	if (ch = getc) == "\\" #"
	  read_escape
	end
      end

    when "C", "c", "^"
      if ch == "C" and (ch = getc) != "-"
	ungetc
      elsif (ch = getc) == "\\" #"
	read_escape
      end
    else
      # other characters 
    end
  end
end