debug.py 32.9 KB
Newer Older
Thanassis Tsiodras's avatar
Thanassis Tsiodras committed
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
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
# begin[licence]
#
#  [The "BSD licence"]
#  Copyright (c) 2005-2009 Terence Parr
#  All rights reserved.

#  Redistribution and use in source and binary forms, with or without
#  modification, are permitted provided that the following conditions
#  are met:
#  1. Redistributions of source code must retain the above copyright
#     notice, this list of conditions and the following disclaimer.
#  2. Redistributions in binary form must reproduce the above copyright
#     notice, this list of conditions and the following disclaimer in the
#     documentation and/or other materials provided with the distribution.
#  3. The name of the author may not be used to endorse or promote products
#     derived from this software without specific prior written permission.

#  THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
#  IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
#  OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
#  IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
#  INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
#  NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
#  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
#  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
#  THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# end[licence]

import socket
from antlr3 import Parser, TokenStream, RecognitionException, Token
from antlr3.tree import CommonTreeAdaptor, TreeAdaptor, Tree

class DebugParser(Parser):
    def __init__(self, stream, state=None, dbg=None, *args, **kwargs):
        # wrap token stream in DebugTokenStream (unless user already did so).
        if not isinstance(stream, DebugTokenStream):
            stream = DebugTokenStream(stream, dbg)

        super(DebugParser, self).__init__(stream, state, *args, **kwargs)

        # Who to notify when events in the parser occur.
        self._dbg = None

        self.setDebugListener(dbg)


    def setDebugListener(self, dbg):
	"""Provide a new debug event listener for this parser.  Notify the
        input stream too that it should send events to this listener.
	"""

        if hasattr(self.input, 'dbg'):
            self.input.dbg = dbg

        self._dbg = dbg

    def getDebugListener(self):
        return self._dbg

    dbg = property(getDebugListener, setDebugListener)


    def beginResync(self):
        self._dbg.beginResync()


    def endResync(self):
        self._dbg.endResync()


    def beginBacktrack(self, level):
        self._dbg.beginBacktrack(level)


    def endBacktrack(self, level, successful):
        self._dbg.endBacktrack(level,successful)


    def reportError(self, exc):
        if isinstance(exc, RecognitionException):
            self._dbg.recognitionException(exc)

        else:
            traceback.print_exc(exc)


class DebugTokenStream(TokenStream):
    def __init__(self, input, dbg=None):
        self.input = input
        self.initialStreamState = True
        # Track the last mark() call result value for use in rewind().
        self.lastMarker = None

        self._dbg = None
        self.setDebugListener(dbg)

        # force TokenStream to get at least first valid token
        # so we know if there are any hidden tokens first in the stream
        self.input.LT(1)


    def getDebugListener(self):
        return self._dbg

    def setDebugListener(self, dbg):
        self._dbg = dbg

    dbg = property(getDebugListener, setDebugListener)


    def consume(self):
        if self.initialStreamState:
            self.consumeInitialHiddenTokens()

        a = self.input.index()
        t = self.input.LT(1)
        self.input.consume()
        b = self.input.index()
        self._dbg.consumeToken(t)

        if b > a+1:
            # then we consumed more than one token; must be off channel tokens
            for idx in range(a+1, b):
                self._dbg.consumeHiddenToken(self.input.get(idx));


    def consumeInitialHiddenTokens(self):
        """consume all initial off-channel tokens"""
        
        firstOnChannelTokenIndex = self.input.index()
        for idx in range(firstOnChannelTokenIndex):
            self._dbg.consumeHiddenToken(self.input.get(idx))

        self.initialStreamState = False


    def LT(self, i):
        if self.initialStreamState:
            self.consumeInitialHiddenTokens()

        t = self.input.LT(i)
        self._dbg.LT(i, t)
        return t


    def LA(self, i):
        if self.initialStreamState:
            self.consumeInitialHiddenTokens()

        t = self.input.LT(i)
        self._dbg.LT(i, t)
        return t.type


    def get(self, i):
        return self.input.get(i)


    def index(self):
        return self.input.index()


    def mark(self):
        self.lastMarker = self.input.mark()
        self._dbg.mark(self.lastMarker)
        return self.lastMarker


    def rewind(self, marker=None):
        self._dbg.rewind(marker)
        self.input.rewind(marker)


    def release(self, marker):
        pass


    def seek(self, index):
        # TODO: implement seek in dbg interface
        # self._dbg.seek(index);
        self.input.seek(index)


    def size(self):
        return self.input.size()


    def getTokenSource(self):
        return self.input.getTokenSource()


    def getSourceName(self):
        return self.getTokenSource().getSourceName()


    def toString(self, start=None, stop=None):
        return self.input.toString(start, stop)


class DebugTreeAdaptor(TreeAdaptor):
    """A TreeAdaptor proxy that fires debugging events to a DebugEventListener
    delegate and uses the TreeAdaptor delegate to do the actual work.  All
    AST events are triggered by this adaptor; no code gen changes are needed
    in generated rules.  Debugging events are triggered *after* invoking
    tree adaptor routines.

    Trees created with actions in rewrite actions like "-> ^(ADD {foo} {bar})"
    cannot be tracked as they might not use the adaptor to create foo, bar.
    The debug listener has to deal with tree node IDs for which it did
    not see a createNode event.  A single <unknown> node is sufficient even
    if it represents a whole tree.
    """

    def __init__(self, dbg, adaptor):
        self.dbg = dbg
        self.adaptor = adaptor


    def createWithPayload(self, payload):
        if payload.getTokenIndex() < 0:
            # could be token conjured up during error recovery
            return self.createFromType(payload.getType(), payload.getText())

        node = self.adaptor.createWithPayload(payload)
        self.dbg.createNode(node, payload)
        return node

    def createFromToken(self, tokenType, fromToken, text=None):
        node = self.adaptor.createFromToken(tokenType, fromToken, text)
        self.dbg.createNode(node)
        return node

    def createFromType(self, tokenType, text):
        node = self.adaptor.createFromType(tokenType, text)
        self.dbg.createNode(node)
        return node


    def errorNode(self, input, start, stop, exc):
        node = selfadaptor.errorNode(input, start, stop, exc)
        if node is not None:
            dbg.errorNode(node)

        return node


    def dupTree(self, tree):
        t = self.adaptor.dupTree(tree)
        # walk the tree and emit create and add child events
        # to simulate what dupTree has done. dupTree does not call this debug
        # adapter so I must simulate.
        self.simulateTreeConstruction(t)
        return t


    def simulateTreeConstruction(self, t):
	"""^(A B C): emit create A, create B, add child, ..."""
        self.dbg.createNode(t)
        for i in range(self.adaptor.getChildCount(t)):
            child = self.adaptor.getChild(t, i)
            self.simulateTreeConstruction(child)
            self.dbg.addChild(t, child)


    def dupNode(self, treeNode):
        d = self.adaptor.dupNode(treeNode)
        self.dbg.createNode(d)
        return d


    def nil(self):
        node = self.adaptor.nil()
        self.dbg.nilNode(node)
        return node


    def isNil(self, tree):
        return self.adaptor.isNil(tree)


    def addChild(self, t, child):
        if isinstance(child, Token):
            n = self.createWithPayload(child)
            self.addChild(t, n)

        else:
            if t is None or child is None:
                return

            self.adaptor.addChild(t, child)
            self.dbg.addChild(t, child)

    def becomeRoot(self, newRoot, oldRoot):
        if isinstance(newRoot, Token):
            n = self.createWithPayload(newRoot)
            self.adaptor.becomeRoot(n, oldRoot)
        else:
            n = self.adaptor.becomeRoot(newRoot, oldRoot)

        self.dbg.becomeRoot(newRoot, oldRoot)
        return n


    def rulePostProcessing(self, root):
        return self.adaptor.rulePostProcessing(root)


    def getType(self, t):
        return self.adaptor.getType(t)


    def setType(self, t, type):
        self.adaptor.setType(t, type)


    def getText(self, t):
        return self.adaptor.getText(t)


    def setText(self, t, text):
        self.adaptor.setText(t, text)


    def getToken(self, t):
        return self.adaptor.getToken(t)


    def setTokenBoundaries(self, t, startToken, stopToken):
        self.adaptor.setTokenBoundaries(t, startToken, stopToken)
        if t is not None and startToken is not None and stopToken is not None:
            self.dbg.setTokenBoundaries(
                t, startToken.getTokenIndex(),
                stopToken.getTokenIndex())


    def getTokenStartIndex(self, t):
        return self.adaptor.getTokenStartIndex(t)


    def getTokenStopIndex(self, t):
        return self.adaptor.getTokenStopIndex(t)


    def getChild(self, t, i):
        return self.adaptor.getChild(t, i)


    def setChild(self, t, i, child):
        self.adaptor.setChild(t, i, child)


    def deleteChild(self, t, i):
        return self.adaptor.deleteChild(t, i)


    def getChildCount(self, t):
        return self.adaptor.getChildCount(t)


    def getUniqueID(self, node):
        return self.adaptor.getUniqueID(node)


    def getParent(self, t):
        return self.adaptor.getParent(t)


    def getChildIndex(self, t):
        return self.adaptor.getChildIndex(t)


    def setParent(self, t, parent):
        self.adaptor.setParent(t, parent)


    def setChildIndex(self, t, index):
        self.adaptor.setChildIndex(t, index)


    def replaceChildren(self, parent, startChildIndex, stopChildIndex, t):
        self.adaptor.replaceChildren(parent, startChildIndex, stopChildIndex, t)


    ## support

    def getDebugListener(self):
        return dbg

    def setDebugListener(self, dbg):
        self.dbg = dbg


    def getTreeAdaptor(self):
        return self.adaptor



class DebugEventListener(object):
    """All debugging events that a recognizer can trigger.
 
    I did not create a separate AST debugging interface as it would create
    lots of extra classes and DebugParser has a dbg var defined, which makes
    it hard to change to ASTDebugEventListener.  I looked hard at this issue
    and it is easier to understand as one monolithic event interface for all
    possible events.  Hopefully, adding ST debugging stuff won't be bad.  Leave
    for future. 4/26/2006.
    """

    # Moved to version 2 for v3.1: added grammar name to enter/exit Rule
    PROTOCOL_VERSION = "2"

    def enterRule(self, grammarFileName, ruleName):
	"""The parser has just entered a rule. No decision has been made about
        which alt is predicted.  This is fired AFTER init actions have been
        executed.  Attributes are defined and available etc...
        The grammarFileName allows composite grammars to jump around among
        multiple grammar files.
        """

        pass


    def enterAlt(self, alt):
	"""Because rules can have lots of alternatives, it is very useful to
        know which alt you are entering.  This is 1..n for n alts.
        """
        pass


    def exitRule(self, grammarFileName, ruleName):
	"""This is the last thing executed before leaving a rule.  It is
        executed even if an exception is thrown.  This is triggered after
        error reporting and recovery have occurred (unless the exception is
        not caught in this rule).  This implies an "exitAlt" event.
        The grammarFileName allows composite grammars to jump around among
        multiple grammar files.
	"""
        pass


    def enterSubRule(self, decisionNumber):
	"""Track entry into any (...) subrule other EBNF construct"""
        pass


    def exitSubRule(self, decisionNumber):
        pass


    def enterDecision(self, decisionNumber):
	"""Every decision, fixed k or arbitrary, has an enter/exit event
        so that a GUI can easily track what LT/consume events are
        associated with prediction.  You will see a single enter/exit
        subrule but multiple enter/exit decision events, one for each
        loop iteration.
        """
        pass


    def exitDecision(self, decisionNumber):
        pass


    def consumeToken(self, t):
	"""An input token was consumed; matched by any kind of element.
        Trigger after the token was matched by things like match(), matchAny().
	"""
        pass


    def consumeHiddenToken(self, t):
	"""An off-channel input token was consumed.
        Trigger after the token was matched by things like match(), matchAny().
        (unless of course the hidden token is first stuff in the input stream).
	"""
        pass


    def LT(self, i, t):
	"""Somebody (anybody) looked ahead.  Note that this actually gets
        triggered by both LA and LT calls.  The debugger will want to know
        which Token object was examined.  Like consumeToken, this indicates
        what token was seen at that depth.  A remote debugger cannot look
        ahead into a file it doesn't have so LT events must pass the token
        even if the info is redundant.
	"""
        pass


    def mark(self, marker):
	"""The parser is going to look arbitrarily ahead; mark this location,
        the token stream's marker is sent in case you need it.
	"""
        pass


    def rewind(self, marker=None):
	"""After an arbitrairly long lookahead as with a cyclic DFA (or with
        any backtrack), this informs the debugger that stream should be
        rewound to the position associated with marker.

        """
        pass


    def beginBacktrack(self, level):
        pass


    def endBacktrack(self, level, successful):
        pass


    def location(self, line, pos):
	"""To watch a parser move through the grammar, the parser needs to
        inform the debugger what line/charPos it is passing in the grammar.
        For now, this does not know how to switch from one grammar to the
        other and back for island grammars etc...

        This should also allow breakpoints because the debugger can stop
        the parser whenever it hits this line/pos.
	"""
        pass


    def recognitionException(self, e):
	"""A recognition exception occurred such as NoViableAltException.  I made
        this a generic event so that I can alter the exception hierachy later
        without having to alter all the debug objects.

        Upon error, the stack of enter rule/subrule must be properly unwound.
        If no viable alt occurs it is within an enter/exit decision, which
        also must be rewound.  Even the rewind for each mark must be unwount.
        In the Java target this is pretty easy using try/finally, if a bit
        ugly in the generated code.  The rewind is generated in DFA.predict()
        actually so no code needs to be generated for that.  For languages
        w/o this "finally" feature (C++?), the target implementor will have
        to build an event stack or something.

        Across a socket for remote debugging, only the RecognitionException
        data fields are transmitted.  The token object or whatever that
        caused the problem was the last object referenced by LT.  The
        immediately preceding LT event should hold the unexpected Token or
        char.

        Here is a sample event trace for grammar:

        b : C ({;}A|B) // {;} is there to prevent A|B becoming a set
          | D
          ;

        The sequence for this rule (with no viable alt in the subrule) for
        input 'c c' (there are 3 tokens) is:

		commence
		LT(1)
		enterRule b
		location 7 1
		enter decision 3
		LT(1)
		exit decision 3
		enterAlt1
		location 7 5
		LT(1)
		consumeToken [c/<4>,1:0]
		location 7 7
		enterSubRule 2
		enter decision 2
		LT(1)
		LT(1)
		recognitionException NoViableAltException 2 1 2
		exit decision 2
		exitSubRule 2
		beginResync
		LT(1)
		consumeToken [c/<4>,1:1]
		LT(1)
		endResync
		LT(-1)
		exitRule b
		terminate
	"""
        pass


    def beginResync(self):
	"""Indicates the recognizer is about to consume tokens to resynchronize
        the parser.  Any consume events from here until the recovered event
        are not part of the parse--they are dead tokens.
        """
        pass

    
    def endResync(self):
	"""Indicates that the recognizer has finished consuming tokens in order
        to resychronize.  There may be multiple beginResync/endResync pairs
        before the recognizer comes out of errorRecovery mode (in which
        multiple errors are suppressed).  This will be useful
        in a gui where you want to probably grey out tokens that are consumed
        but not matched to anything in grammar.  Anything between
        a beginResync/endResync pair was tossed out by the parser.
	"""
        pass


    def semanticPredicate(self, result, predicate):
	"""A semantic predicate was evaluate with this result and action text"""
        pass


    def commence(self):
	"""Announce that parsing has begun.  Not technically useful except for
        sending events over a socket.  A GUI for example will launch a thread
        to connect and communicate with a remote parser.  The thread will want
        to notify the GUI when a connection is made.  ANTLR parsers
        trigger this upon entry to the first rule (the ruleLevel is used to
        figure this out).
	"""
        pass


    def terminate(self):
        """Parsing is over; successfully or not.  Mostly useful for telling
        remote debugging listeners that it's time to quit.  When the rule
        invocation level goes to zero at the end of a rule, we are done
        parsing.
	"""
        pass


    ## T r e e  P a r s i n g

    def consumeNode(self, t):
        """Input for a tree parser is an AST, but we know nothing for sure
        about a node except its type and text (obtained from the adaptor).
        This is the analog of the consumeToken method.  Again, the ID is
        the hashCode usually of the node so it only works if hashCode is
        not implemented.  If the type is UP or DOWN, then
        the ID is not really meaningful as it's fixed--there is
        just one UP node and one DOWN navigation node.
        """
        pass


    def LT(self, i, t):
	"""The tree parser lookedahead.  If the type is UP or DOWN,
        then the ID is not really meaningful as it's fixed--there is
        just one UP node and one DOWN navigation node.
	"""
        pass



    ## A S T  E v e n t s

    def nilNode(self, t):
	"""A nil was created (even nil nodes have a unique ID...
        they are not "null" per se).  As of 4/28/2006, this
        seems to be uniquely triggered when starting a new subtree
        such as when entering a subrule in automatic mode and when
        building a tree in rewrite mode.

        If you are receiving this event over a socket via
        RemoteDebugEventSocketListener then only t.ID is set.
	"""
        pass


    def errorNode(self, t):
	"""Upon syntax error, recognizers bracket the error with an error node
        if they are building ASTs.
        """
        pass


    def createNode(self, node, token=None):
	"""Announce a new node built from token elements such as type etc...

        If you are receiving this event over a socket via
        RemoteDebugEventSocketListener then only t.ID, type, text are
        set.
	"""
        pass


    def becomeRoot(self, newRoot, oldRoot):
	"""Make a node the new root of an existing root.

        Note: the newRootID parameter is possibly different
        than the TreeAdaptor.becomeRoot() newRoot parameter.
        In our case, it will always be the result of calling
        TreeAdaptor.becomeRoot() and not root_n or whatever.

        The listener should assume that this event occurs
        only when the current subrule (or rule) subtree is
        being reset to newRootID.

        If you are receiving this event over a socket via
        RemoteDebugEventSocketListener then only IDs are set.

        @see antlr3.tree.TreeAdaptor.becomeRoot()
	"""
        pass


    def addChild(self, root, child):
	"""Make childID a child of rootID.

        If you are receiving this event over a socket via
        RemoteDebugEventSocketListener then only IDs are set.

        @see antlr3.tree.TreeAdaptor.addChild()
        """
        pass


    def setTokenBoundaries(self, t, tokenStartIndex, tokenStopIndex):
	"""Set the token start/stop token index for a subtree root or node.

        If you are receiving this event over a socket via
        RemoteDebugEventSocketListener then only t.ID is set.
	"""
        pass


class BlankDebugEventListener(DebugEventListener):
    """A blank listener that does nothing; useful for real classes so
    they don't have to have lots of blank methods and are less
    sensitive to updates to debug interface.

    Note: this class is identical to DebugEventListener and exists purely
    for compatibility with Java.
    """
    pass


class TraceDebugEventListener(DebugEventListener):
    """A listener that simply records text representations of the events.

    Useful for debugging the debugging facility ;)

    Subclasses can override the record() method (which defaults to printing to
    stdout) to record the events in a different way.
    """

    def __init__(self, adaptor=None):
        super(TraceDebugEventListener, self).__init__()

        if adaptor is None:
            adaptor = CommonTreeAdaptor()
        self.adaptor = adaptor

    def record(self, event):
        sys.stdout.write(event + '\n')

    def enterRule(self, grammarFileName, ruleName):
        self.record("enterRule "+ruleName)

    def exitRule(self, grammarFileName, ruleName):
        self.record("exitRule "+ruleName)

    def enterSubRule(self, decisionNumber):
        self.record("enterSubRule")

    def exitSubRule(self, decisionNumber):
        self.record("exitSubRule")

    def location(self, line, pos):
        self.record("location %s:%s" % (line, pos))

    ## Tree parsing stuff

    def consumeNode(self, t):
        self.record("consumeNode %s %s %s" % (
                self.adaptor.getUniqueID(t),
                self.adaptor.getText(t),
                self.adaptor.getType(t)))

    def LT(self, i, t):
        self.record("LT %s %s %s %s" % (
                i,
                self.adaptor.getUniqueID(t),
                self.adaptor.getText(t),
                self.adaptor.getType(t)))


    ## AST stuff
    def nilNode(self, t):
        self.record("nilNode %s" % self.adaptor.getUniqueID(t))

    def createNode(self, t, token=None):
        if token is None:
            self.record("create %s: %s, %s" % (
                    self.adaptor.getUniqueID(t),
                    self.adaptor.getText(t),
                    self.adaptor.getType(t)))

        else:
            self.record("create %s: %s" % (
                    self.adaptor.getUniqueID(t),
                    token.getTokenIndex()))

    def becomeRoot(self, newRoot, oldRoot):
        self.record("becomeRoot %s, %s" % (
                self.adaptor.getUniqueID(newRoot),
                self.adaptor.getUniqueID(oldRoot)))

    def addChild(self, root, child):
        self.record("addChild %s, %s" % (
                self.adaptor.getUniqueID(root),
                self.adaptor.getUniqueID(child)))

    def setTokenBoundaries(self, t, tokenStartIndex, tokenStopIndex):
        self.record("setTokenBoundaries %s, %s, %s" % (
                self.adaptor.getUniqueID(t),
                tokenStartIndex, tokenStopIndex))


class RecordDebugEventListener(TraceDebugEventListener):
    """A listener that records events as strings in an array."""

    def __init__(self, adaptor=None):
        super(RecordDebugEventListener, self).__init__(adaptor)

        self.events = []

    def record(self, event):
        self.events.append(event)


class DebugEventSocketProxy(DebugEventListener):
    """A proxy debug event listener that forwards events over a socket to
    a debugger (or any other listener) using a simple text-based protocol;
    one event per line.  ANTLRWorks listens on server socket with a
    RemoteDebugEventSocketListener instance.  These two objects must therefore
    be kept in sync.  New events must be handled on both sides of socket.
    """

    DEFAULT_DEBUGGER_PORT = 49100

    def __init__(self, recognizer, adaptor=None, port=None,
                 debug=None):
        super(DebugEventSocketProxy, self).__init__()

        self.grammarFileName = recognizer.getGrammarFileName()

	# Almost certainly the recognizer will have adaptor set, but
        # we don't know how to cast it (Parser or TreeParser) to get
        # the adaptor field.  Must be set with a constructor. :(
        self.adaptor = adaptor

        self.port = port or self.DEFAULT_DEBUGGER_PORT

        self.debug = debug

        self.socket = None
        self.connection = None
        self.input = None
        self.output = None


    def log(self, msg):
        if self.debug is not None:
            self.debug.write(msg + '\n')


    def handshake(self):
        if self.socket is None:
            # create listening socket
            self.socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
            self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
            self.socket.bind(('', self.port))
            self.socket.listen(1)
            self.log("Waiting for incoming connection on port %d" % self.port)

            # wait for an incoming connection
            self.connection, addr = self.socket.accept()
            self.log("Accepted connection from %s:%d" % addr)

            self.connection.setblocking(1)
            self.connection.setsockopt(socket.SOL_TCP, socket.TCP_NODELAY, 1)

            # FIXME(pink): wrap into utf8 encoding stream
            self.output = self.connection.makefile('w', 0)
            self.input = self.connection.makefile('r', 0)

            self.write("ANTLR %s" % self.PROTOCOL_VERSION)
            self.write("grammar \"%s" % self.grammarFileName)
            self.ack()


    def write(self, msg):
        self.log("> %s" % msg)
        self.output.write("%s\n" % msg)
        self.output.flush()


    def ack(self):
        t = self.input.readline()
        self.log("< %s" % t.rstrip())


    def transmit(self, event):
        self.write(event);
        self.ack();


    def commence(self):
        # don't bother sending event; listener will trigger upon connection
        pass


    def terminate(self):
        self.transmit("terminate")
        self.output.close()
        self.input.close()
        self.connection.close()
        self.socket.close()


    def enterRule(self, grammarFileName, ruleName):
        self.transmit("enterRule\t%s\t%s" % (grammarFileName, ruleName))


    def enterAlt(self, alt):
        self.transmit("enterAlt\t%d" % alt)


    def exitRule(self, grammarFileName, ruleName):
        self.transmit("exitRule\t%s\t%s" % (grammarFileName, ruleName))


    def enterSubRule(self, decisionNumber):
        self.transmit("enterSubRule\t%d" % decisionNumber)


    def exitSubRule(self, decisionNumber):
        self.transmit("exitSubRule\t%d" % decisionNumber)


    def enterDecision(self, decisionNumber):
        self.transmit("enterDecision\t%d" % decisionNumber)


    def exitDecision(self, decisionNumber):
        self.transmit("exitDecision\t%d" % decisionNumber)


    def consumeToken(self, t):
        self.transmit("consumeToken\t%s" % self.serializeToken(t))


    def consumeHiddenToken(self, t):
        self.transmit("consumeHiddenToken\t%s" % self.serializeToken(t))


    def LT(self, i, o):
        if isinstance(o, Tree):
            return self.LT_tree(i, o)
        return self.LT_token(i, o)


    def LT_token(self, i, t):
        if t is not None:
            self.transmit("LT\t%d\t%s" % (i, self.serializeToken(t)))


    def mark(self, i):
        self.transmit("mark\t%d" % i)


    def rewind(self, i=None):
        if i is not None:
            self.transmit("rewind\t%d" % i)
        else:
            self.transmit("rewind")


    def beginBacktrack(self, level):
        self.transmit("beginBacktrack\t%d" % level)


    def endBacktrack(self, level, successful):
        self.transmit("endBacktrack\t%d\t%s" % (
                level, ['0', '1'][bool(successful)]))


    def location(self, line, pos):
        self.transmit("location\t%d\t%d" % (line, pos))


    def recognitionException(self, exc):
        self.transmit('\t'.join([
                    "exception",
                    exc.__class__.__name__,
                    str(int(exc.index)),
                    str(int(exc.line)),
                    str(int(exc.charPositionInLine))]))


    def beginResync(self):
        self.transmit("beginResync")


    def endResync(self):
        self.transmit("endResync")


    def semanticPredicate(self, result, predicate):
        self.transmit('\t'.join([
                    "semanticPredicate",
                    str(int(result)),
                    self.escapeNewlines(predicate)]))

    ## A S T  P a r s i n g  E v e n t s

    def consumeNode(self, t):
        FIXME(31)
#         StringBuffer buf = new StringBuffer(50);
#         buf.append("consumeNode");
#         serializeNode(buf, t);
#         transmit(buf.toString());


    def LT_tree(self, i, t):
        FIXME(34)
#         int ID = adaptor.getUniqueID(t);
#         String text = adaptor.getText(t);
#         int type = adaptor.getType(t);
#         StringBuffer buf = new StringBuffer(50);
#         buf.append("LN\t"); // lookahead node; distinguish from LT in protocol
#         buf.append(i);
#         serializeNode(buf, t);
#         transmit(buf.toString());


    def serializeNode(self, buf, t):
        FIXME(33)
#         int ID = adaptor.getUniqueID(t);
#         String text = adaptor.getText(t);
#         int type = adaptor.getType(t);
#         buf.append("\t");
#         buf.append(ID);
#         buf.append("\t");
#         buf.append(type);
#         Token token = adaptor.getToken(t);
#         int line = -1;
#         int pos = -1;
#         if ( token!=null ) {
#             line = token.getLine();
#             pos = token.getCharPositionInLine();
#             }
#         buf.append("\t");
#         buf.append(line);
#         buf.append("\t");
#         buf.append(pos);
#         int tokenIndex = adaptor.getTokenStartIndex(t);
#         buf.append("\t");
#         buf.append(tokenIndex);
#         serializeText(buf, text);

	
    ## A S T  E v e n t s

    def nilNode(self, t):
        self.transmit("nilNode\t%d" % self.adaptor.getUniqueID(t))


    def errorNode(self, t):
        self.transmit("errorNode\t%d\t%d\t\"%s" % (
             self.adaptor.getUniqueID(t),
             Token.INVALID_TOKEN_TYPE,
             self.escapeNewlines(t.toString())))



    def createNode(self, node, token=None):
        if token is not None:
            self.transmit("createNode\t%d\t%d" % (
                    self.adaptor.getUniqueID(node),
                    token.getTokenIndex()))

        else:
            self.transmit("createNodeFromTokenElements\t%d\t%d\t\"%s" % (
                    self.adaptor.getUniqueID(node),
                    self.adaptor.getType(node),
                    self.adaptor.getText(node)))


    def becomeRoot(self, newRoot, oldRoot):
        self.transmit("becomeRoot\t%d\t%d" % (
                self.adaptor.getUniqueID(newRoot),
                self.adaptor.getUniqueID(oldRoot)))


    def addChild(self, root, child):
        self.transmit("addChild\t%d\t%d" % (
                self.adaptor.getUniqueID(root),
                self.adaptor.getUniqueID(child)))


    def setTokenBoundaries(self, t, tokenStartIndex, tokenStopIndex):
        self.transmit("setTokenBoundaries\t%d\t%d\t%d" % (
                self.adaptor.getUniqueID(t),
                tokenStartIndex, tokenStopIndex))



    ## support

    def setTreeAdaptor(self, adaptor):
        self.adaptor = adaptor

    def getTreeAdaptor(self):
        return self.adaptor


    def serializeToken(self, t):
        buf = [str(int(t.getTokenIndex())),
               str(int(t.getType())),
               str(int(t.getChannel())),
               str(int(t.getLine() or 0)),
               str(int(t.getCharPositionInLine() or 0)),
               '\"' + self.escapeNewlines(t.getText())]
        return '\t'.join(buf)


    def escapeNewlines(self, txt):
        if txt is None:
            return ''

        txt = txt.replace("%","%25")   # escape all escape char ;)
        txt = txt.replace("\n","%0A")  # escape \n
        txt = txt.replace("\r","%0D")  # escape \r
        return txt