Source

cpython-withatomic / Parser / spark.py

  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
#  Copyright (c) 1998-2002 John Aycock
#
#  Permission is hereby granted, free of charge, to any person obtaining
#  a copy of this software and associated documentation files (the
#  "Software"), to deal in the Software without restriction, including
#  without limitation the rights to use, copy, modify, merge, publish,
#  distribute, sublicense, and/or sell copies of the Software, and to
#  permit persons to whom the Software is furnished to do so, subject to
#  the following conditions:
#
#  The above copyright notice and this permission notice shall be
#  included in all copies or substantial portions of the Software.
#
#  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
#  EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
#  MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
#  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
#  CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
#  TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
#  SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

__version__ = 'SPARK-0.7 (pre-alpha-5)'

import re
import string

def _namelist(instance):
    namelist, namedict, classlist = [], {}, [instance.__class__]
    for c in classlist:
        for b in c.__bases__:
            classlist.append(b)
        for name in c.__dict__.keys():
            if not namedict.has_key(name):
                namelist.append(name)
                namedict[name] = 1
    return namelist

class GenericScanner:
    def __init__(self, flags=0):
        pattern = self.reflect()
        self.re = re.compile(pattern, re.VERBOSE|flags)

        self.index2func = {}
        for name, number in self.re.groupindex.items():
            self.index2func[number-1] = getattr(self, 't_' + name)

    def makeRE(self, name):
        doc = getattr(self, name).__doc__
        rv = '(?P<%s>%s)' % (name[2:], doc)
        return rv

    def reflect(self):
        rv = []
        for name in _namelist(self):
            if name[:2] == 't_' and name != 't_default':
                rv.append(self.makeRE(name))

        rv.append(self.makeRE('t_default'))
        return string.join(rv, '|')

    def error(self, s, pos):
        print "Lexical error at position %s" % pos
        raise SystemExit

    def tokenize(self, s):
        pos = 0
        n = len(s)
        while pos < n:
            m = self.re.match(s, pos)
            if m is None:
                self.error(s, pos)

            groups = m.groups()
            for i in range(len(groups)):
                if groups[i] and self.index2func.has_key(i):
                    self.index2func[i](groups[i])
            pos = m.end()

    def t_default(self, s):
        r'( . | \n )+'
        print "Specification error: unmatched input"
        raise SystemExit

#
#  Extracted from GenericParser and made global so that [un]picking works.
#
class _State:
    def __init__(self, stateno, items):
        self.T, self.complete, self.items = [], [], items
        self.stateno = stateno

class GenericParser:
    #
    #  An Earley parser, as per J. Earley, "An Efficient Context-Free
    #  Parsing Algorithm", CACM 13(2), pp. 94-102.  Also J. C. Earley,
    #  "An Efficient Context-Free Parsing Algorithm", Ph.D. thesis,
    #  Carnegie-Mellon University, August 1968.  New formulation of
    #  the parser according to J. Aycock, "Practical Earley Parsing
    #  and the SPARK Toolkit", Ph.D. thesis, University of Victoria,
    #  2001, and J. Aycock and R. N. Horspool, "Practical Earley
    #  Parsing", unpublished paper, 2001.
    #

    def __init__(self, start):
        self.rules = {}
        self.rule2func = {}
        self.rule2name = {}
        self.collectRules()
        self.augment(start)
        self.ruleschanged = 1

    _NULLABLE = '\e_'
    _START = 'START'
    _BOF = '|-'

    #
    #  When pickling, take the time to generate the full state machine;
    #  some information is then extraneous, too.  Unfortunately we
    #  can't save the rule2func map.
    #
    def __getstate__(self):
        if self.ruleschanged:
            #
            #  XXX - duplicated from parse()
            #
            self.computeNull()
            self.newrules = {}
            self.new2old = {}
            self.makeNewRules()
            self.ruleschanged = 0
            self.edges, self.cores = {}, {}
            self.states = { 0: self.makeState0() }
            self.makeState(0, self._BOF)
        #
        #  XXX - should find a better way to do this..
        #
        changes = 1
        while changes:
            changes = 0
            for k, v in self.edges.items():
                if v is None:
                    state, sym = k
                    if self.states.has_key(state):
                        self.goto(state, sym)
                        changes = 1
        rv = self.__dict__.copy()
        for s in self.states.values():
            del s.items
        del rv['rule2func']
        del rv['nullable']
        del rv['cores']
        return rv

    def __setstate__(self, D):
        self.rules = {}
        self.rule2func = {}
        self.rule2name = {}
        self.collectRules()
        start = D['rules'][self._START][0][1][1]        # Blech.
        self.augment(start)
        D['rule2func'] = self.rule2func
        D['makeSet'] = self.makeSet_fast
        self.__dict__ = D

    #
    #  A hook for GenericASTBuilder and GenericASTMatcher.  Mess
    #  thee not with this; nor shall thee toucheth the _preprocess
    #  argument to addRule.
    #
    def preprocess(self, rule, func):       return rule, func

    def addRule(self, doc, func, _preprocess=1):
        fn = func
        rules = string.split(doc)

        index = []
        for i in range(len(rules)):
            if rules[i] == '::=':
                index.append(i-1)
        index.append(len(rules))

        for i in range(len(index)-1):
            lhs = rules[index[i]]
            rhs = rules[index[i]+2:index[i+1]]
            rule = (lhs, tuple(rhs))

            if _preprocess:
                rule, fn = self.preprocess(rule, func)

            if self.rules.has_key(lhs):
                self.rules[lhs].append(rule)
            else:
                self.rules[lhs] = [ rule ]
            self.rule2func[rule] = fn
            self.rule2name[rule] = func.__name__[2:]
        self.ruleschanged = 1

    def collectRules(self):
        for name in _namelist(self):
            if name[:2] == 'p_':
                func = getattr(self, name)
                doc = func.__doc__
                self.addRule(doc, func)

    def augment(self, start):
        rule = '%s ::= %s %s' % (self._START, self._BOF, start)
        self.addRule(rule, lambda args: args[1], 0)

    def computeNull(self):
        self.nullable = {}
        tbd = []

        for rulelist in self.rules.values():
            lhs = rulelist[0][0]
            self.nullable[lhs] = 0
            for rule in rulelist:
                rhs = rule[1]
                if len(rhs) == 0:
                    self.nullable[lhs] = 1
                    continue
                #
                #  We only need to consider rules which
                #  consist entirely of nonterminal symbols.
                #  This should be a savings on typical
                #  grammars.
                #
                for sym in rhs:
                    if not self.rules.has_key(sym):
                        break
                else:
                    tbd.append(rule)
        changes = 1
        while changes:
            changes = 0
            for lhs, rhs in tbd:
                if self.nullable[lhs]:
                    continue
                for sym in rhs:
                    if not self.nullable[sym]:
                        break
                else:
                    self.nullable[lhs] = 1
                    changes = 1

    def makeState0(self):
        s0 = _State(0, [])
        for rule in self.newrules[self._START]:
            s0.items.append((rule, 0))
        return s0

    def finalState(self, tokens):
        #
        #  Yuck.
        #
        if len(self.newrules[self._START]) == 2 and len(tokens) == 0:
            return 1
        start = self.rules[self._START][0][1][1]
        return self.goto(1, start)

    def makeNewRules(self):
        worklist = []
        for rulelist in self.rules.values():
            for rule in rulelist:
                worklist.append((rule, 0, 1, rule))

        for rule, i, candidate, oldrule in worklist:
            lhs, rhs = rule
            n = len(rhs)
            while i < n:
                sym = rhs[i]
                if not self.rules.has_key(sym) or \
                   not self.nullable[sym]:
                    candidate = 0
                    i = i + 1
                    continue

                newrhs = list(rhs)
                newrhs[i] = self._NULLABLE+sym
                newrule = (lhs, tuple(newrhs))
                worklist.append((newrule, i+1,
                                 candidate, oldrule))
                candidate = 0
                i = i + 1
            else:
                if candidate:
                    lhs = self._NULLABLE+lhs
                    rule = (lhs, rhs)
                if self.newrules.has_key(lhs):
                    self.newrules[lhs].append(rule)
                else:
                    self.newrules[lhs] = [ rule ]
                self.new2old[rule] = oldrule

    def typestring(self, token):
        return None

    def error(self, token):
        print "Syntax error at or near `%s' token" % token
        raise SystemExit

    def parse(self, tokens):
        sets = [ [(1,0), (2,0)] ]
        self.links = {}

        if self.ruleschanged:
            self.computeNull()
            self.newrules = {}
            self.new2old = {}
            self.makeNewRules()
            self.ruleschanged = 0
            self.edges, self.cores = {}, {}
            self.states = { 0: self.makeState0() }
            self.makeState(0, self._BOF)

        for i in xrange(len(tokens)):
            sets.append([])

            if sets[i] == []:
                break
            self.makeSet(tokens[i], sets, i)
        else:
            sets.append([])
            self.makeSet(None, sets, len(tokens))

        #_dump(tokens, sets, self.states)

        finalitem = (self.finalState(tokens), 0)
        if finalitem not in sets[-2]:
            if len(tokens) > 0:
                self.error(tokens[i-1])
            else:
                self.error(None)

        return self.buildTree(self._START, finalitem,
                              tokens, len(sets)-2)

    def isnullable(self, sym):
        #
        #  For symbols in G_e only.  If we weren't supporting 1.5,
        #  could just use sym.startswith().
        #
        return self._NULLABLE == sym[0:len(self._NULLABLE)]

    def skip(self, (lhs, rhs), pos=0):
        n = len(rhs)
        while pos < n:
            if not self.isnullable(rhs[pos]):
                break
            pos = pos + 1
        return pos

    def makeState(self, state, sym):
        assert sym is not None
        #
        #  Compute \epsilon-kernel state's core and see if
        #  it exists already.
        #
        kitems = []
        for rule, pos in self.states[state].items:
            lhs, rhs = rule
            if rhs[pos:pos+1] == (sym,):
                kitems.append((rule, self.skip(rule, pos+1)))
        core = kitems

        core.sort()
        tcore = tuple(core)
        if self.cores.has_key(tcore):
            return self.cores[tcore]
        #
        #  Nope, doesn't exist.  Compute it and the associated
        #  \epsilon-nonkernel state together; we'll need it right away.
        #
        k = self.cores[tcore] = len(self.states)
        K, NK = _State(k, kitems), _State(k+1, [])
        self.states[k] = K
        predicted = {}

        edges = self.edges
        rules = self.newrules
        for X in K, NK:
            worklist = X.items
            for item in worklist:
                rule, pos = item
                lhs, rhs = rule
                if pos == len(rhs):
                    X.complete.append(rule)
                    continue

                nextSym = rhs[pos]
                key = (X.stateno, nextSym)
                if not rules.has_key(nextSym):
                    if not edges.has_key(key):
                        edges[key] = None
                        X.T.append(nextSym)
                else:
                    edges[key] = None
                    if not predicted.has_key(nextSym):
                        predicted[nextSym] = 1
                        for prule in rules[nextSym]:
                            ppos = self.skip(prule)
                            new = (prule, ppos)
                            NK.items.append(new)
            #
            #  Problem: we know K needs generating, but we
            #  don't yet know about NK.  Can't commit anything
            #  regarding NK to self.edges until we're sure.  Should
            #  we delay committing on both K and NK to avoid this
            #  hacky code?  This creates other problems..
            #
            if X is K:
                edges = {}

        if NK.items == []:
            return k

        #
        #  Check for \epsilon-nonkernel's core.  Unfortunately we
        #  need to know the entire set of predicted nonterminals
        #  to do this without accidentally duplicating states.
        #
        core = predicted.keys()
        core.sort()
        tcore = tuple(core)
        if self.cores.has_key(tcore):
            self.edges[(k, None)] = self.cores[tcore]
            return k

        nk = self.cores[tcore] = self.edges[(k, None)] = NK.stateno
        self.edges.update(edges)
        self.states[nk] = NK
        return k

    def goto(self, state, sym):
        key = (state, sym)
        if not self.edges.has_key(key):
            #
            #  No transitions from state on sym.
            #
            return None

        rv = self.edges[key]
        if rv is None:
            #
            #  Target state isn't generated yet.  Remedy this.
            #
            rv = self.makeState(state, sym)
            self.edges[key] = rv
        return rv

    def gotoT(self, state, t):
        return [self.goto(state, t)]

    def gotoST(self, state, st):
        rv = []
        for t in self.states[state].T:
            if st == t:
                rv.append(self.goto(state, t))
        return rv

    def add(self, set, item, i=None, predecessor=None, causal=None):
        if predecessor is None:
            if item not in set:
                set.append(item)
        else:
            key = (item, i)
            if item not in set:
                self.links[key] = []
                set.append(item)
            self.links[key].append((predecessor, causal))

    def makeSet(self, token, sets, i):
        cur, next = sets[i], sets[i+1]

        ttype = token is not None and self.typestring(token) or None
        if ttype is not None:
            fn, arg = self.gotoT, ttype
        else:
            fn, arg = self.gotoST, token

        for item in cur:
            ptr = (item, i)
            state, parent = item
            add = fn(state, arg)
            for k in add:
                if k is not None:
                    self.add(next, (k, parent), i+1, ptr)
                    nk = self.goto(k, None)
                    if nk is not None:
                        self.add(next, (nk, i+1))

            if parent == i:
                continue

            for rule in self.states[state].complete:
                lhs, rhs = rule
                for pitem in sets[parent]:
                    pstate, pparent = pitem
                    k = self.goto(pstate, lhs)
                    if k is not None:
                        why = (item, i, rule)
                        pptr = (pitem, parent)
                        self.add(cur, (k, pparent),
                                 i, pptr, why)
                        nk = self.goto(k, None)
                        if nk is not None:
                            self.add(cur, (nk, i))

    def makeSet_fast(self, token, sets, i):
        #
        #  Call *only* when the entire state machine has been built!
        #  It relies on self.edges being filled in completely, and
        #  then duplicates and inlines code to boost speed at the
        #  cost of extreme ugliness.
        #
        cur, next = sets[i], sets[i+1]
        ttype = token is not None and self.typestring(token) or None

        for item in cur:
            ptr = (item, i)
            state, parent = item
            if ttype is not None:
                k = self.edges.get((state, ttype), None)
                if k is not None:
                    #self.add(next, (k, parent), i+1, ptr)
                    #INLINED --v
                    new = (k, parent)
                    key = (new, i+1)
                    if new not in next:
                        self.links[key] = []
                        next.append(new)
                    self.links[key].append((ptr, None))
                    #INLINED --^
                    #nk = self.goto(k, None)
                    nk = self.edges.get((k, None), None)
                    if nk is not None:
                        #self.add(next, (nk, i+1))
                        #INLINED --v
                        new = (nk, i+1)
                        if new not in next:
                            next.append(new)
                        #INLINED --^
            else:
                add = self.gotoST(state, token)
                for k in add:
                    if k is not None:
                        self.add(next, (k, parent), i+1, ptr)
                        #nk = self.goto(k, None)
                        nk = self.edges.get((k, None), None)
                        if nk is not None:
                            self.add(next, (nk, i+1))

            if parent == i:
                continue

            for rule in self.states[state].complete:
                lhs, rhs = rule
                for pitem in sets[parent]:
                    pstate, pparent = pitem
                    #k = self.goto(pstate, lhs)
                    k = self.edges.get((pstate, lhs), None)
                    if k is not None:
                        why = (item, i, rule)
                        pptr = (pitem, parent)
                        #self.add(cur, (k, pparent),
                        #        i, pptr, why)
                        #INLINED --v
                        new = (k, pparent)
                        key = (new, i)
                        if new not in cur:
                            self.links[key] = []
                            cur.append(new)
                        self.links[key].append((pptr, why))
                        #INLINED --^
                        #nk = self.goto(k, None)
                        nk = self.edges.get((k, None), None)
                        if nk is not None:
                            #self.add(cur, (nk, i))
                            #INLINED --v
                            new = (nk, i)
                            if new not in cur:
                                cur.append(new)
                            #INLINED --^

    def predecessor(self, key, causal):
        for p, c in self.links[key]:
            if c == causal:
                return p
        assert 0

    def causal(self, key):
        links = self.links[key]
        if len(links) == 1:
            return links[0][1]
        choices = []
        rule2cause = {}
        for p, c in links:
            rule = c[2]
            choices.append(rule)
            rule2cause[rule] = c
        return rule2cause[self.ambiguity(choices)]

    def deriveEpsilon(self, nt):
        if len(self.newrules[nt]) > 1:
            rule = self.ambiguity(self.newrules[nt])
        else:
            rule = self.newrules[nt][0]
        #print rule

        rhs = rule[1]
        attr = [None] * len(rhs)

        for i in range(len(rhs)-1, -1, -1):
            attr[i] = self.deriveEpsilon(rhs[i])
        return self.rule2func[self.new2old[rule]](attr)

    def buildTree(self, nt, item, tokens, k):
        state, parent = item

        choices = []
        for rule in self.states[state].complete:
            if rule[0] == nt:
                choices.append(rule)
        rule = choices[0]
        if len(choices) > 1:
            rule = self.ambiguity(choices)
        #print rule

        rhs = rule[1]
        attr = [None] * len(rhs)

        for i in range(len(rhs)-1, -1, -1):
            sym = rhs[i]
            if not self.newrules.has_key(sym):
                if sym != self._BOF:
                    attr[i] = tokens[k-1]
                    key = (item, k)
                    item, k = self.predecessor(key, None)
            #elif self.isnullable(sym):
            elif self._NULLABLE == sym[0:len(self._NULLABLE)]:
                attr[i] = self.deriveEpsilon(sym)
            else:
                key = (item, k)
                why = self.causal(key)
                attr[i] = self.buildTree(sym, why[0],
                                         tokens, why[1])
                item, k = self.predecessor(key, why)
        return self.rule2func[self.new2old[rule]](attr)

    def ambiguity(self, rules):
        #
        #  XXX - problem here and in collectRules() if the same rule
        #        appears in >1 method.  Also undefined results if rules
        #        causing the ambiguity appear in the same method.
        #
        sortlist = []
        name2index = {}
        for i in range(len(rules)):
            lhs, rhs = rule = rules[i]
            name = self.rule2name[self.new2old[rule]]
            sortlist.append((len(rhs), name))
            name2index[name] = i
        sortlist.sort()
        list = map(lambda (a,b): b, sortlist)
        return rules[name2index[self.resolve(list)]]

    def resolve(self, list):
        #
        #  Resolve ambiguity in favor of the shortest RHS.
        #  Since we walk the tree from the top down, this
        #  should effectively resolve in favor of a "shift".
        #
        return list[0]

#
#  GenericASTBuilder automagically constructs a concrete/abstract syntax tree
#  for a given input.  The extra argument is a class (not an instance!)
#  which supports the "__setslice__" and "__len__" methods.
#
#  XXX - silently overrides any user code in methods.
#

class GenericASTBuilder(GenericParser):
    def __init__(self, AST, start):
        GenericParser.__init__(self, start)
        self.AST = AST

    def preprocess(self, rule, func):
        rebind = lambda lhs, self=self: \
                        lambda args, lhs=lhs, self=self: \
                                self.buildASTNode(args, lhs)
        lhs, rhs = rule
        return rule, rebind(lhs)

    def buildASTNode(self, args, lhs):
        children = []
        for arg in args:
            if isinstance(arg, self.AST):
                children.append(arg)
            else:
                children.append(self.terminal(arg))
        return self.nonterminal(lhs, children)

    def terminal(self, token):      return token

    def nonterminal(self, type, args):
        rv = self.AST(type)
        rv[:len(args)] = args
        return rv

#
#  GenericASTTraversal is a Visitor pattern according to Design Patterns.  For
#  each node it attempts to invoke the method n_<node type>, falling
#  back onto the default() method if the n_* can't be found.  The preorder
#  traversal also looks for an exit hook named n_<node type>_exit (no default
#  routine is called if it's not found).  To prematurely halt traversal
#  of a subtree, call the prune() method -- this only makes sense for a
#  preorder traversal.  Node type is determined via the typestring() method.
#

class GenericASTTraversalPruningException:
    pass

class GenericASTTraversal:
    def __init__(self, ast):
        self.ast = ast

    def typestring(self, node):
        return node.type

    def prune(self):
        raise GenericASTTraversalPruningException

    def preorder(self, node=None):
        if node is None:
            node = self.ast

        try:
            name = 'n_' + self.typestring(node)
            if hasattr(self, name):
                func = getattr(self, name)
                func(node)
            else:
                self.default(node)
        except GenericASTTraversalPruningException:
            return

        for kid in node:
            self.preorder(kid)

        name = name + '_exit'
        if hasattr(self, name):
            func = getattr(self, name)
            func(node)

    def postorder(self, node=None):
        if node is None:
            node = self.ast

        for kid in node:
            self.postorder(kid)

        name = 'n_' + self.typestring(node)
        if hasattr(self, name):
            func = getattr(self, name)
            func(node)
        else:
            self.default(node)


    def default(self, node):
        pass

#
#  GenericASTMatcher.  AST nodes must have "__getitem__" and "__cmp__"
#  implemented.
#
#  XXX - makes assumptions about how GenericParser walks the parse tree.
#

class GenericASTMatcher(GenericParser):
    def __init__(self, start, ast):
        GenericParser.__init__(self, start)
        self.ast = ast

    def preprocess(self, rule, func):
        rebind = lambda func, self=self: \
                        lambda args, func=func, self=self: \
                                self.foundMatch(args, func)
        lhs, rhs = rule
        rhslist = list(rhs)
        rhslist.reverse()

        return (lhs, tuple(rhslist)), rebind(func)

    def foundMatch(self, args, func):
        func(args[-1])
        return args[-1]

    def match_r(self, node):
        self.input.insert(0, node)
        children = 0

        for child in node:
            if children == 0:
                self.input.insert(0, '(')
            children = children + 1
            self.match_r(child)

        if children > 0:
            self.input.insert(0, ')')

    def match(self, ast=None):
        if ast is None:
            ast = self.ast
        self.input = []

        self.match_r(ast)
        self.parse(self.input)

    def resolve(self, list):
        #
        #  Resolve ambiguity in favor of the longest RHS.
        #
        return list[-1]

def _dump(tokens, sets, states):
    for i in range(len(sets)):
        print 'set', i
        for item in sets[i]:
            print '\t', item
            for (lhs, rhs), pos in states[item[0]].items:
                print '\t\t', lhs, '::=',
                print string.join(rhs[:pos]),
                print '.',
                print string.join(rhs[pos:])
        if i < len(tokens):
            print
            print 'token', str(tokens[i])
            print
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.