summaryrefslogtreecommitdiffstats
path: root/Lib/xmllib.py
blob: c551debf3881028aaee397c5965f94c9b9354c1e (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
# A parser for XML, using the derived class as static DTD.
# Author: Sjoerd Mullender.

import re
import string


version = '0.2'

# Regular expressions used for parsing

_S = '[ \t\r\n]+'                       # white space
_opS = '[ \t\r\n]*'                     # optional white space
_Name = '[a-zA-Z_:][-a-zA-Z0-9._:]*'    # valid XML name
_QStr = "(?:'[^']*'|\"[^\"]*\")"        # quoted XML string
illegal = re.compile('[^\t\r\n -\176\240-\377]') # illegal chars in content
interesting = re.compile('[]&<]')

amp = re.compile('&')
ref = re.compile('&(' + _Name + '|#[0-9]+|#x[0-9a-fA-F]+)[^-a-zA-Z0-9._:]')
entityref = re.compile('&(?P<name>' + _Name + ')[^-a-zA-Z0-9._:]')
charref = re.compile('&#(?P<char>[0-9]+[^0-9]|x[0-9a-fA-F]+[^0-9a-fA-F])')
space = re.compile(_S + '$')
newline = re.compile('\n')

attrfind = re.compile(
    _S + '(?P<name>' + _Name + ')'
    '(' + _opS + '=' + _opS +
    '(?P<value>'+_QStr+'|[-a-zA-Z0-9.:+*%?!()_#=~]+))?')
starttagopen = re.compile('<' + _Name)
starttagend = re.compile(_opS + '(?P<slash>/?)>')
starttagmatch = re.compile('<(?P<tagname>'+_Name+')'
                      '(?P<attrs>(?:'+attrfind.pattern+')*)'+
                      starttagend.pattern)
endtagopen = re.compile('</')
endbracket = re.compile(_opS + '>')
endbracketfind = re.compile('(?:[^>\'"]|'+_QStr+')*>')
tagfind = re.compile(_Name)
cdataopen = re.compile(r'<!\[CDATA\[')
cdataclose = re.compile(r'\]\]>')
# this matches one of the following:
# SYSTEM SystemLiteral
# PUBLIC PubidLiteral SystemLiteral
_SystemLiteral = '(?P<%s>'+_QStr+')'
_PublicLiteral = '(?P<%s>"[-\'()+,./:=?;!*#@$_%% \n\ra-zA-Z0-9]*"|' \
                        "'[-()+,./:=?;!*#@$_%% \n\ra-zA-Z0-9]*')"
_ExternalId = '(?:SYSTEM|' \
                 'PUBLIC'+_S+_PublicLiteral%'pubid'+ \
              ')'+_S+_SystemLiteral%'syslit'
doctype = re.compile('<!DOCTYPE'+_S+'(?P<name>'+_Name+')'
                     '(?:'+_S+_ExternalId+')?'+_opS)
xmldecl = re.compile('<\?xml'+_S+
                     'version'+_opS+'='+_opS+'(?P<version>'+_QStr+')'+
                     '(?:'+_S+'encoding'+_opS+'='+_opS+
                        "(?P<encoding>'[A-Za-z][-A-Za-z0-9._]*'|"
                        '"[A-Za-z][-A-Za-z0-9._]*"))?'
                     '(?:'+_S+'standalone'+_opS+'='+_opS+
                        '(?P<standalone>\'(?:yes|no)\'|"(?:yes|no)"))?'+
                     _opS+'\?>')
procopen = re.compile(r'<\?(?P<proc>' + _Name + ')' + _opS)
procclose = re.compile(_opS + r'\?>')
commentopen = re.compile('<!--')
commentclose = re.compile('-->')
doubledash = re.compile('--')
attrtrans = string.maketrans(' \r\n\t', '    ')

# definitions for XML namespaces
_NCName = '[a-zA-Z_][-a-zA-Z0-9._]*'    # XML Name, minus the ":"
ncname = re.compile(_NCName + '$')
qname = re.compile('(?:(?P<prefix>' + _NCName + '):)?' # optional prefix
                   '(?P<local>' + _NCName + ')$')

xmlns = re.compile('xmlns(?::(?P<ncname>'+_NCName+'))?$')

# XML parser base class -- find tags and call handler functions.
# Usage: p = XMLParser(); p.feed(data); ...; p.close().
# The dtd is defined by deriving a class which defines methods with
# special names to handle tags: start_foo and end_foo to handle <foo>
# and </foo>, respectively.  The data between tags is passed to the
# parser by calling self.handle_data() with some data as argument (the
# data may be split up in arbutrary chunks).  Entity references are
# passed by calling self.handle_entityref() with the entity reference
# as argument.

class XMLParser:
    attributes = {}                     # default, to be overridden
    elements = {}                       # default, to be overridden

    # Interface -- initialize and reset this instance
    def __init__(self):
        self.reset()

    # Interface -- reset this instance.  Loses all unprocessed data
    def reset(self):
        self.rawdata = ''
        self.stack = []
        self.nomoretags = 0
        self.literal = 0
        self.lineno = 1
        self.__at_start = 1
        self.__seen_doctype = None
        self.__seen_starttag = 0
        self.__namespaces = {'xml':None}   # xml is implicitly declared

    # For derived classes only -- enter literal mode (CDATA) till EOF
    def setnomoretags(self):
        self.nomoretags = self.literal = 1

    # For derived classes only -- enter literal mode (CDATA)
    def setliteral(self, *args):
        self.literal = 1

    # Interface -- feed some data to the parser.  Call this as
    # often as you want, with as little or as much text as you
    # want (may include '\n').  (This just saves the text, all the
    # processing is done by goahead().)
    def feed(self, data):
        self.rawdata = self.rawdata + data
        self.goahead(0)

    # Interface -- handle the remaining data
    def close(self):
        self.goahead(1)

    # Interface -- translate references
    def translate_references(self, data, all = 1):
        i = 0
        while 1:
            res = amp.search(data, i)
            if res is None:
                return data
            res = ref.match(data, res.start(0))
            if res is None:
                self.syntax_error("bogus `&'")
                i =i+1
                continue
            i = res.end(0)
            if data[i - 1] != ';':
                self.syntax_error("`;' missing after entity/char reference")
                i = i-1
            str = res.group(1)
            pre = data[:res.start(0)]
            post = data[i:]
            if str[0] == '#':
                if str[1] == 'x':
                    str = chr(string.atoi(str[2:], 16))
                else:
                    str = chr(string.atoi(str[1:]))
                data = pre + str + post
                i = res.start(0)+len(str)
            elif all:
                if self.entitydefs.has_key(str):
                    data = pre + self.entitydefs[str] + post
                    i = res.start(0)    # rescan substituted text
                else:
                    self.syntax_error('reference to unknown entity')
                    # can't do it, so keep the entity ref in
                    data = pre + '&' + str + ';' + post
                    i = res.start(0) + len(str) + 2
            else:
                # just translating character references
                pass                    # i is already postioned correctly

    # Internal -- handle data as far as reasonable.  May leave state
    # and data to be processed by a subsequent call.  If 'end' is
    # true, force handling all data as if followed by EOF marker.
    def goahead(self, end):
        rawdata = self.rawdata
        i = 0
        n = len(rawdata)
        while i < n:
            if i > 0:
                self.__at_start = 0
            if self.nomoretags:
                data = rawdata[i:n]
                self.handle_data(data)
                self.lineno = self.lineno + string.count(data, '\n')
                i = n
                break
            res = interesting.search(rawdata, i)
            if res:
                    j = res.start(0)
            else:
                    j = n
            if i < j:
                if self.__at_start:
                    self.syntax_error('illegal data at start of file')
                self.__at_start = 0
                data = rawdata[i:j]
                if not self.stack and space.match(data) is None:
                    self.syntax_error('data not in content')
                if illegal.search(data):
                    self.syntax_error('illegal character in content')
                self.handle_data(data)
                self.lineno = self.lineno + string.count(data, '\n')
            i = j
            if i == n: break
            if rawdata[i] == '<':
                if starttagopen.match(rawdata, i):
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + string.count(data, '\n')
                        i = i+1
                        continue
                    k = self.parse_starttag(i)
                    if k < 0: break
                    self.__seen_starttag = 1
                    self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
                    i = k
                    continue
                if endtagopen.match(rawdata, i):
                    k = self.parse_endtag(i)
                    if k < 0: break
                    self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
                    i =  k
                    continue
                if commentopen.match(rawdata, i):
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + string.count(data, '\n')
                        i = i+1
                        continue
                    k = self.parse_comment(i)
                    if k < 0: break
                    self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
                    i = k
                    continue
                if cdataopen.match(rawdata, i):
                    k = self.parse_cdata(i)
                    if k < 0: break
                    self.lineno = self.lineno + string.count(rawdata[i:i], '\n')
                    i = k
                    continue
                res = xmldecl.match(rawdata, i)
                if res:
                    if not self.__at_start:
                        self.syntax_error("<?xml?> declaration not at start of document")
                    version, encoding, standalone = res.group('version',
                                                              'encoding',
                                                              'standalone')
                    if version[1:-1] != '1.0':
                        raise RuntimeError, 'only XML version 1.0 supported'
                    if encoding: encoding = encoding[1:-1]
                    if standalone: standalone = standalone[1:-1]
                    self.handle_xml(encoding, standalone)
                    i = res.end(0)
                    continue
                res = procopen.match(rawdata, i)
                if res:
                    k = self.parse_proc(i)
                    if k < 0: break
                    self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
                    i = k
                    continue
                res = doctype.match(rawdata, i)
                if res:
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + string.count(data, '\n')
                        i = i+1
                        continue
                    if self.__seen_doctype:
                        self.syntax_error('multiple DOCTYPE elements')
                    if self.__seen_starttag:
                        self.syntax_error('DOCTYPE not at beginning of document')
                    k = self.parse_doctype(res)
                    if k < 0: break
                    self.__seen_doctype = res.group('name')
                    self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
                    i = k
                    continue
            elif rawdata[i] == '&':
                if self.literal:
                    data = rawdata[i]
                    self.handle_data(data)
                    i = i+1
                    continue
                res = charref.match(rawdata, i)
                if res is not None:
                    i = res.end(0)
                    if rawdata[i-1] != ';':
                        self.syntax_error("`;' missing in charref")
                        i = i-1
                    if not self.stack:
                        self.syntax_error('data not in content')
                    self.handle_charref(res.group('char')[:-1])
                    self.lineno = self.lineno + string.count(res.group(0), '\n')
                    continue
                res = entityref.match(rawdata, i)
                if res is not None:
                    i = res.end(0)
                    if rawdata[i-1] != ';':
                        self.syntax_error("`;' missing in entityref")
                        i = i-1
                    name = res.group('name')
                    if self.entitydefs.has_key(name):
                        self.rawdata = rawdata = rawdata[:res.start(0)] + self.entitydefs[name] + rawdata[i:]
                        n = len(rawdata)
                        i = res.start(0)
                    else:
                        self.syntax_error('reference to unknown entity')
                        self.unknown_entityref(name)
                    self.lineno = self.lineno + string.count(res.group(0), '\n')
                    continue
            elif rawdata[i] == ']':
                if self.literal:
                    data = rawdata[i]
                    self.handle_data(data)
                    i = i+1
                    continue
                if n-i < 3:
                    break
                if cdataclose.match(rawdata, i):
                    self.syntax_error("bogus `]]>'")
                self.handle_data(rawdata[i])
                i = i+1
                continue
            else:
                raise RuntimeError, 'neither < nor & ??'
            # We get here only if incomplete matches but
            # nothing else
            break
        # end while
        if i > 0:
            self.__at_start = 0
        if end and i < n:
            data = rawdata[i]
            self.syntax_error("bogus `%s'" % data)
            if illegal.search(data):
                self.syntax_error('illegal character in content')
            self.handle_data(data)
            self.lineno = self.lineno + string.count(data, '\n')
            self.rawdata = rawdata[i+1:]
            return self.goahead(end)
        self.rawdata = rawdata[i:]
        if end:
            if not self.__seen_starttag:
                self.syntax_error('no elements in file')
            if self.stack:
                self.syntax_error('missing end tags')
                while self.stack:
                    self.finish_endtag(self.stack[-1][0])

    # Internal -- parse comment, return length or -1 if not terminated
    def parse_comment(self, i):
        rawdata = self.rawdata
        if rawdata[i:i+4] <> '<!--':
            raise RuntimeError, 'unexpected call to handle_comment'
        res = commentclose.search(rawdata, i+4)
        if res is None:
            return -1
        if doubledash.search(rawdata, i+4, res.start(0)):
            self.syntax_error("`--' inside comment")
        if rawdata[res.start(0)-1] == '-':
            self.syntax_error('comment cannot end in three dashes')
        if illegal.search(rawdata, i+4, res.start(0)):
            self.syntax_error('illegal character in comment')
        self.handle_comment(rawdata[i+4: res.start(0)])
        return res.end(0)

    # Internal -- handle DOCTYPE tag, return length or -1 if not terminated
    def parse_doctype(self, res):
        rawdata = self.rawdata
        n = len(rawdata)
        name = res.group('name')
        pubid, syslit = res.group('pubid', 'syslit')
        if pubid is not None:
            pubid = pubid[1:-1]         # remove quotes
            pubid = string.join(string.split(pubid)) # normalize
        if syslit is not None: syslit = syslit[1:-1] # remove quotes
        j = k = res.end(0)
        if k >= n:
            return -1
        if rawdata[k] == '[':
            level = 0
            k = k+1
            dq = sq = 0
            while k < n:
                c = rawdata[k]
                if not sq and c == '"':
                    dq = not dq
                elif not dq and c == "'":
                    sq = not sq
                elif sq or dq:
                    pass
                elif level <= 0 and c == ']':
                    res = endbracket.match(rawdata, k+1)
                    if res is None:
                        return -1
                    self.handle_doctype(name, pubid, syslit, rawdata[j+1:k])
                    return res.end(0)
                elif c == '<':
                    level = level + 1
                elif c == '>':
                    level = level - 1
                    if level < 0:
                        self.syntax_error("bogus `>' in DOCTYPE")
                k = k+1
        res = endbracketfind.match(rawdata, k)
        if res is None:
            return -1
        if endbracket.match(rawdata, k) is None:
            self.syntax_error('garbage in DOCTYPE')
        self.handle_doctype(name, pubid, syslit, None)
        return res.end(0)

    # Internal -- handle CDATA tag, return length or -1 if not terminated
    def parse_cdata(self, i):
        rawdata = self.rawdata
        if rawdata[i:i+9] <> '<![CDATA[':
            raise RuntimeError, 'unexpected call to parse_cdata'
        res = cdataclose.search(rawdata, i+9)
        if res is None:
            return -1
        if illegal.search(rawdata, i+9, res.start(0)):
            self.syntax_error('illegal character in CDATA')
        if not self.stack:
            self.syntax_error('CDATA not in content')
        self.handle_cdata(rawdata[i+9:res.start(0)])
        return res.end(0)

    __xml_namespace_attributes = {'ns':None, 'src':None, 'prefix':None}
    # Internal -- handle a processing instruction tag
    def parse_proc(self, i):
        rawdata = self.rawdata
        end = procclose.search(rawdata, i)
        if end is None:
            return -1
        j = end.start(0)
        if illegal.search(rawdata, i+2, j):
            self.syntax_error('illegal character in processing instruction')
        res = tagfind.match(rawdata, i+2)
        if res is None:
            raise RuntimeError, 'unexpected call to parse_proc'
        k = res.end(0)
        name = res.group(0)
        if name == 'xml:namespace':
            self.syntax_error('old-fashioned namespace declaration')
            # namespace declaration
            # this must come after the <?xml?> declaration (if any)
            # and before the <!DOCTYPE> (if any).
            if self.__seen_doctype or self.__seen_starttag:
                self.syntax_error('xml:namespace declaration too late in document')
            attrdict, namespace, k = self.parse_attributes(name, k, j)
            if namespace:
                self.syntax_error('namespace declaration inside namespace declaration')
            for attrname in attrdict.keys():
                if not self.__xml_namespace_attributes.has_key(attrname):
                    self.syntax_error("unknown attribute `%s' in xml:namespace tag" % attrname)
            if not attrdict.has_key('ns') or not attrdict.has_key('prefix'):
                self.syntax_error('xml:namespace without required attributes')
            prefix = attrdict.get('prefix')
            if ncname.match(prefix) is None:
                self.syntax_error('xml:namespace illegal prefix value')
                return end.end(0)
            if self.__namespaces.has_key(prefix):
                self.syntax_error('xml:namespace prefix not unique')
            self.__namespaces[prefix] = attrdict['ns']
        else:
            if string.find(string.lower(name), 'xml') >= 0:
                self.syntax_error('illegal processing instruction target name')
            self.handle_proc(name, rawdata[k:j])
        return end.end(0)

    # Internal -- parse attributes between i and j
    def parse_attributes(self, tag, i, j):
        rawdata = self.rawdata
        attrdict = {}
        namespace = {}
        while i < j:
            res = attrfind.match(rawdata, i)
            if res is None:
                break
            attrname, attrvalue = res.group('name', 'value')
            i = res.end(0)
            if attrvalue is None:
                self.syntax_error("no value specified for attribute `%s'" % attrname)
                attrvalue = attrname
            elif attrvalue[:1] == "'" == attrvalue[-1:] or \
                 attrvalue[:1] == '"' == attrvalue[-1:]:
                attrvalue = attrvalue[1:-1]
            else:
                self.syntax_error("attribute `%s' value not quoted" % attrname)
            res = xmlns.match(attrname)
            if res is not None:
                # namespace declaration
                ncname = res.group('ncname')
                namespace[ncname or ''] = attrvalue or None
                continue
            if '<' in attrvalue:
                self.syntax_error("`<' illegal in attribute value")
            if attrdict.has_key(attrname):
                self.syntax_error("attribute `%s' specified twice" % attrname)
            attrvalue = string.translate(attrvalue, attrtrans)
            attrdict[attrname] = self.translate_references(attrvalue)
        return attrdict, namespace, i

    # Internal -- handle starttag, return length or -1 if not terminated
    def parse_starttag(self, i):
        rawdata = self.rawdata
        # i points to start of tag
        end = endbracketfind.match(rawdata, i+1)
        if end is None:
            return -1
        tag = starttagmatch.match(rawdata, i)
        if tag is None or tag.end(0) != end.end(0):
            self.syntax_error('garbage in starttag')
            return end.end(0)
        nstag = tagname = tag.group('tagname')
        if not self.__seen_starttag and self.__seen_doctype and \
           tagname != self.__seen_doctype:
            self.syntax_error('starttag does not match DOCTYPE')
        if self.__seen_starttag and not self.stack:
            self.syntax_error('multiple elements on top level')
        k, j = tag.span('attrs')
        attrdict, nsdict, k = self.parse_attributes(tagname, k, j)
        self.stack.append((tagname, nsdict, nstag))
        res = qname.match(tagname)
        if res is not None:
            prefix, nstag = res.group('prefix', 'local')
            if prefix is None:
                prefix = ''
            ns = None
            for t, d, nst in self.stack:
                if d.has_key(prefix):
                    ns = d[prefix]
            if ns is None and prefix != '':
                ns = self.__namespaces.get(prefix)
            if ns is not None:
                nstag = ns + ' ' + nstag
            elif prefix != '':
                nstag = prefix + ':' + nstag # undo split
            self.stack[-1] = tagname, nsdict, nstag
        # translate namespace of attributes
        nattrdict = {}
        for key, val in attrdict.items():
            res = qname.match(key)
            if res is not None:
                aprefix, key = res.group('prefix', 'local')
                if aprefix is None:
                    aprefix = ''
                ans = None
                for t, d, nst in self.stack:
                    if d.has_key(aprefix):
                        ans = d[aprefix]
                if ans is None and aprefix != '':
                    ans = self.__namespaces.get(aprefix)
                if ans is not None:
                    key = ans + ' ' + key
                elif aprefix != '':
                    key = aprefix + ':' + key
                elif ns is not None:
                    key = ns + ' ' + key
            nattrdict[key] = val
        attrdict = nattrdict
        attributes = self.attributes.get(nstag)
        if attributes is not None:
            for key in attrdict.keys():
                if not attributes.has_key(key):
                    self.syntax_error("unknown attribute `%s' in tag `%s'" % (key, tagname))
            for key, val in attributes.items():
                if val is not None and not attrdict.has_key(key):
                    attrdict[key] = val
        method = self.elements.get(nstag, (None, None))[0]
        self.finish_starttag(nstag, attrdict, method)
        if tag.group('slash') == '/':
            self.finish_endtag(tagname)
        return tag.end(0)

    # Internal -- parse endtag
    def parse_endtag(self, i):
        rawdata = self.rawdata
        end = endbracketfind.match(rawdata, i+1)
        if end is None:
            return -1
        res = tagfind.match(rawdata, i+2)
        if res is None:
            if self.literal:
                self.handle_data(rawdata[i])
                return i+1
            self.syntax_error('no name specified in end tag')
            tag = ''
            k = i+2
        else:
            tag = res.group(0)
            if self.literal:
                if not self.stack or tag != self.stack[-1][0]:
                    self.handle_data(rawdata[i])
                    return i+1
                self.literal = 0
            k = res.end(0)
        if endbracket.match(rawdata, k) is None:
            self.syntax_error('garbage in end tag')
        self.finish_endtag(tag)
        return end.end(0)

    # Internal -- finish processing of start tag
    def finish_starttag(self, tagname, attrdict, method):
        if method is not None:
            self.handle_starttag(tagname, method, attrdict)
        else:
            self.unknown_starttag(tagname, attrdict)

    # Internal -- finish processing of end tag
    def finish_endtag(self, tag):
        if not tag:
            self.syntax_error('name-less end tag')
            found = len(self.stack) - 1
            if found < 0:
                self.unknown_endtag(tag)
                return
        else:
            found = -1
            for i in range(len(self.stack)):
                if tag == self.stack[i][0]:
                    found = i
            if found == -1:
                self.syntax_error('unopened end tag')
                method = self.elements.get(tag, (None, None))[1]
                if method is not None:
                    self.handle_endtag(tag, method)
                else:
                    self.unknown_endtag(tag)
                return
        while len(self.stack) > found:
            if found < len(self.stack) - 1:
                self.syntax_error('missing close tag for %s' % self.stack[-1][2])
            nstag = self.stack[-1][2]
            method = self.elements.get(nstag, (None, None))[1]
            if method is not None:
                self.handle_endtag(nstag, method)
            else:
                self.unknown_endtag(nstag)
            del self.stack[-1]

    # Overridable -- handle xml processing instruction
    def handle_xml(self, encoding, standalone):
        pass

    # Overridable -- handle DOCTYPE
    def handle_doctype(self, tag, pubid, syslit, data):
        pass

    # Overridable -- handle start tag
    def handle_starttag(self, tag, method, attrs):
        method(attrs)

    # Overridable -- handle end tag
    def handle_endtag(self, tag, method):
        method()

    # Example -- handle character reference, no need to override
    def handle_charref(self, name):
        try:
            if name[0] == 'x':
                n = string.atoi(name[1:], 16)
            else:
                n = string.atoi(name)
        except string.atoi_error:
            self.unknown_charref(name)
            return
        if not 0 <= n <= 255:
            self.unknown_charref(name)
            return
        self.handle_data(chr(n))

    # Definition of entities -- derived classes may override
    entitydefs = {'lt': '&#60;',        # must use charref
                  'gt': '&#62;',
                  'amp': '&#38;',       # must use charref
                  'quot': '&#34;',
                  'apos': '&#39;',
                  }

    # Example -- handle entity reference, no need to override
    def handle_entityref(self, name):
        table = self.entitydefs
        if table.has_key(name):
            self.handle_data(table[name])
        else:
            self.unknown_entityref(name)
            return

    # Example -- handle data, should be overridden
    def handle_data(self, data):
        pass

    # Example -- handle cdata, could be overridden
    def handle_cdata(self, data):
        pass

    # Example -- handle comment, could be overridden
    def handle_comment(self, data):
        pass

    # Example -- handle processing instructions, could be overridden
    def handle_proc(self, name, data):
        pass

    # Example -- handle relatively harmless syntax errors, could be overridden
    def syntax_error(self, message):
        raise RuntimeError, 'Syntax error at line %d: %s' % (self.lineno, message)

    # To be overridden -- handlers for unknown objects
    def unknown_starttag(self, tag, attrs): pass
    def unknown_endtag(self, tag): pass
    def unknown_charref(self, ref): pass
    def unknown_entityref(self, ref): pass


class TestXMLParser(XMLParser):

    def __init__(self):
        self.testdata = ""
        XMLParser.__init__(self)

    def handle_xml(self, encoding, standalone):
        self.flush()
        print 'xml: encoding =',encoding,'standalone =',standalone

    def handle_doctype(self, tag, pubid, syslit, data):
        self.flush()
        print 'DOCTYPE:',tag, `data`

    def handle_entity(self, name, strval, pubid, syslit, ndata):
        self.flush()
        print 'ENTITY:',`data`

    def handle_data(self, data):
        self.testdata = self.testdata + data
        if len(`self.testdata`) >= 70:
            self.flush()

    def flush(self):
        data = self.testdata
        if data:
            self.testdata = ""
            print 'data:', `data`

    def handle_cdata(self, data):
        self.flush()
        print 'cdata:', `data`

    def handle_proc(self, name, data):
        self.flush()
        print 'processing:',name,`data`

    def handle_comment(self, data):
        self.flush()
        r = `data`
        if len(r) > 68:
            r = r[:32] + '...' + r[-32:]
        print 'comment:', r

    def syntax_error(self, message):
        print 'error at line %d:' % self.lineno, message

    def unknown_starttag(self, tag, attrs):
        self.flush()
        if not attrs:
            print 'start tag: <' + tag + '>'
        else:
            print 'start tag: <' + tag,
            for name, value in attrs.items():
                print name + '=' + '"' + value + '"',
            print '>'

    def unknown_endtag(self, tag):
        self.flush()
        print 'end tag: </' + tag + '>'

    def unknown_entityref(self, ref):
        self.flush()
        print '*** unknown entity ref: &' + ref + ';'

    def unknown_charref(self, ref):
        self.flush()
        print '*** unknown char ref: &#' + ref + ';'

    def close(self):
        XMLParser.close(self)
        self.flush()

def test(args = None):
    import sys

    if not args:
        args = sys.argv[1:]

    if args and args[0] == '-s':
        args = args[1:]
        klass = XMLParser
    else:
        klass = TestXMLParser

    if args:
        file = args[0]
    else:
        file = 'test.xml'

    if file == '-':
        f = sys.stdin
    else:
        try:
            f = open(file, 'r')
        except IOError, msg:
            print file, ":", msg
            sys.exit(1)

    data = f.read()
    if f is not sys.stdin:
        f.close()

    x = klass()
    try:
        for c in data:
            x.feed(c)
        x.close()
    except RuntimeError, msg:
        print msg
        sys.exit(1)


if __name__ == '__main__':
    test()