summaryrefslogtreecommitdiffstats
path: root/Lib/sgmllib.py
blob: 987b65edff313ee6f5f556a89ff64a8e9e29a619 (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
"""A parser for SGML, using the derived class as a static DTD."""

# XXX This only supports those SGML features used by HTML.

# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special).  RCDATA is
# not supported at all.


import markupbase
import re

__all__ = ["SGMLParser", "SGMLParseError"]

# Regular expressions used for parsing

interesting = re.compile('[&<]')
incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
                           '<([a-zA-Z][^<>]*|'
                              '/([a-zA-Z][^<>]*)?|'
                              '![^<>]*)?')

entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref = re.compile('&#([0-9]+)[^0-9]')

starttagopen = re.compile('<[>a-zA-Z]')
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
piclose = re.compile('>')
endbracket = re.compile('[<>]')
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
attrfind = re.compile(
    r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
    r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?')


class SGMLParseError(RuntimeError):
    """Exception raised for all parse errors."""
    pass


# SGML parser base class -- find tags and call handler functions.
# Usage: p = SGMLParser(); 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, or do_foo to handle <foo> by itself.
# (Tags are converted to lower case for this purpose.)  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 arbitrary
# chunks).  Entity references are passed by calling
# self.handle_entityref() with the entity reference as argument.

class SGMLParser(markupbase.ParserBase):
    # Definition of entities -- derived classes may override
    entity_or_charref = re.compile('&(?:'
      '([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
      ')(;?)')

    def __init__(self, verbose=0):
        """Initialize and reset this instance."""
        self.verbose = verbose
        self.reset()

    def reset(self):
        """Reset this instance. Loses all unprocessed data."""
        self.__starttag_text = None
        self.rawdata = ''
        self.stack = []
        self.lasttag = '???'
        self.nomoretags = 0
        self.literal = 0
        markupbase.ParserBase.reset(self)

    def setnomoretags(self):
        """Enter literal mode (CDATA) till EOF.

        Intended for derived classes only.
        """
        self.nomoretags = self.literal = 1

    def setliteral(self, *args):
        """Enter literal mode (CDATA).

        Intended for derived classes only.
        """
        self.literal = 1

    def feed(self, data):
        """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().)
        """

        self.rawdata = self.rawdata + data
        self.goahead(0)

    def close(self):
        """Handle the remaining data."""
        self.goahead(1)

    def error(self, message):
        raise SGMLParseError(message)

    # 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 self.nomoretags:
                self.handle_data(rawdata[i:n])
                i = n
                break
            match = interesting.search(rawdata, i)
            if match: j = match.start()
            else: j = n
            if i < j:
                self.handle_data(rawdata[i:j])
            i = j
            if i == n: break
            if rawdata[i] == '<':
                if starttagopen.match(rawdata, i):
                    if self.literal:
                        self.handle_data(rawdata[i])
                        i = i+1
                        continue
                    k = self.parse_starttag(i)
                    if k < 0: break
                    i = k
                    continue
                if rawdata.startswith("</", i):
                    k = self.parse_endtag(i)
                    if k < 0: break
                    i = k
                    self.literal = 0
                    continue
                if self.literal:
                    if n > (i + 1):
                        self.handle_data("<")
                        i = i+1
                    else:
                        # incomplete
                        break
                    continue
                if rawdata.startswith("<!--", i):
                        # Strictly speaking, a comment is --.*--
                        # within a declaration tag <!...>.
                        # This should be removed,
                        # and comments handled only in parse_declaration.
                    k = self.parse_comment(i)
                    if k < 0: break
                    i = k
                    continue
                if rawdata.startswith("<?", i):
                    k = self.parse_pi(i)
                    if k < 0: break
                    i = i+k
                    continue
                if rawdata.startswith("<!", i):
                    # This is some sort of declaration; in "HTML as
                    # deployed," this should only be the document type
                    # declaration ("<!DOCTYPE html...>").
                    k = self.parse_declaration(i)
                    if k < 0: break
                    i = k
                    continue
            elif rawdata[i] == '&':
                if self.literal:
                    self.handle_data(rawdata[i])
                    i = i+1
                    continue
                match = charref.match(rawdata, i)
                if match:
                    name = match.group(1)
                    self.handle_charref(name)
                    i = match.end(0)
                    if rawdata[i-1] != ';': i = i-1
                    continue
                match = entityref.match(rawdata, i)
                if match:
                    name = match.group(1)
                    self.handle_entityref(name)
                    i = match.end(0)
                    if rawdata[i-1] != ';': i = i-1
                    continue
            else:
                self.error('neither < nor & ??')
            # We get here only if incomplete matches but
            # nothing else
            match = incomplete.match(rawdata, i)
            if not match:
                self.handle_data(rawdata[i])
                i = i+1
                continue
            j = match.end(0)
            if j == n:
                break # Really incomplete
            self.handle_data(rawdata[i:j])
            i = j
        # end while
        if end and i < n:
            self.handle_data(rawdata[i:n])
            i = n
        self.rawdata = rawdata[i:]
        # XXX if end: check for empty stack

    # Extensions for the DOCTYPE scanner:
    _decl_otherchars = '='

    # Internal -- parse processing instr, return length or -1 if not terminated
    def parse_pi(self, i):
        rawdata = self.rawdata
        if rawdata[i:i+2] != '<?':
            self.error('unexpected call to parse_pi()')
        match = piclose.search(rawdata, i+2)
        if not match:
            return -1
        j = match.start(0)
        self.handle_pi(rawdata[i+2: j])
        j = match.end(0)
        return j-i

    def get_starttag_text(self):
        return self.__starttag_text

    # Internal -- handle starttag, return length or -1 if not terminated
    def parse_starttag(self, i):
        self.__starttag_text = None
        start_pos = i
        rawdata = self.rawdata
        if shorttagopen.match(rawdata, i):
            # SGML shorthand: <tag/data/ == <tag>data</tag>
            # XXX Can data contain &... (entity or char refs)?
            # XXX Can data contain < or > (tag characters)?
            # XXX Can there be whitespace before the first /?
            match = shorttag.match(rawdata, i)
            if not match:
                return -1
            tag, data = match.group(1, 2)
            self.__starttag_text = '<%s/' % tag
            tag = tag.lower()
            k = match.end(0)
            self.finish_shorttag(tag, data)
            self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
            return k
        # XXX The following should skip matching quotes (' or ")
        # As a shortcut way to exit, this isn't so bad, but shouldn't
        # be used to locate the actual end of the start tag since the
        # < or > characters may be embedded in an attribute value.
        match = endbracket.search(rawdata, i+1)
        if not match:
            return -1
        j = match.start(0)
        # Now parse the data between i+1 and j into a tag and attrs
        attrs = []
        if rawdata[i:i+2] == '<>':
            # SGML shorthand: <> == <last open tag seen>
            k = j
            tag = self.lasttag
        else:
            match = tagfind.match(rawdata, i+1)
            if not match:
                self.error('unexpected call to parse_starttag')
            k = match.end(0)
            tag = rawdata[i+1:k].lower()
            self.lasttag = tag
        while k < j:
            match = attrfind.match(rawdata, k)
            if not match: break
            attrname, rest, attrvalue = match.group(1, 2, 3)
            if not rest:
                attrvalue = attrname
            else:
                if (attrvalue[:1] == "'" == attrvalue[-1:] or
                    attrvalue[:1] == '"' == attrvalue[-1:]):
                    # strip quotes
                    attrvalue = attrvalue[1:-1]
                attrvalue = self.entity_or_charref.sub(
                    self._convert_ref, attrvalue)
            attrs.append((attrname.lower(), attrvalue))
            k = match.end(0)
        if rawdata[j] == '>':
            j = j+1
        self.__starttag_text = rawdata[start_pos:j]
        self.finish_starttag(tag, attrs)
        return j

    # Internal -- convert entity or character reference
    def _convert_ref(self, match):
        if match.group(2):
            return self.convert_charref(match.group(2)) or \
                '&#%s%s' % match.groups()[1:]
        elif match.group(3):
            return self.convert_entityref(match.group(1)) or \
                '&%s;' % match.group(1)
        else:
            return '&%s' % match.group(1)

    # Internal -- parse endtag
    def parse_endtag(self, i):
        rawdata = self.rawdata
        match = endbracket.search(rawdata, i+1)
        if not match:
            return -1
        j = match.start(0)
        tag = rawdata[i+2:j].strip().lower()
        if rawdata[j] == '>':
            j = j+1
        self.finish_endtag(tag)
        return j

    # Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
    def finish_shorttag(self, tag, data):
        self.finish_starttag(tag, [])
        self.handle_data(data)
        self.finish_endtag(tag)

    # Internal -- finish processing of start tag
    # Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
    def finish_starttag(self, tag, attrs):
        try:
            method = getattr(self, 'start_' + tag)
        except AttributeError:
            try:
                method = getattr(self, 'do_' + tag)
            except AttributeError:
                self.unknown_starttag(tag, attrs)
                return -1
            else:
                self.handle_starttag(tag, method, attrs)
                return 0
        else:
            self.stack.append(tag)
            self.handle_starttag(tag, method, attrs)
            return 1

    # Internal -- finish processing of end tag
    def finish_endtag(self, tag):
        if not tag:
            found = len(self.stack) - 1
            if found < 0:
                self.unknown_endtag(tag)
                return
        else:
            if tag not in self.stack:
                try:
                    method = getattr(self, 'end_' + tag)
                except AttributeError:
                    self.unknown_endtag(tag)
                else:
                    self.report_unbalanced(tag)
                return
            found = len(self.stack)
            for i in range(found):
                if self.stack[i] == tag: found = i
        while len(self.stack) > found:
            tag = self.stack[-1]
            try:
                method = getattr(self, 'end_' + tag)
            except AttributeError:
                method = None
            if method:
                self.handle_endtag(tag, method)
            else:
                self.unknown_endtag(tag)
            del self.stack[-1]

    # 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 -- report an unbalanced </...> tag.
    def report_unbalanced(self, tag):
        if self.verbose:
            print('*** Unbalanced </' + tag + '>')
            print('*** Stack:', self.stack)

    def convert_charref(self, name):
        """Convert character reference, may be overridden."""
        try:
            n = int(name)
        except ValueError:
            return
        if not 0 <= n <= 255:
            return
        return self.convert_codepoint(n)

    def convert_codepoint(self, codepoint):
        return chr(codepoint)

    def handle_charref(self, name):
        """Handle character reference, no need to override."""
        replacement = self.convert_charref(name)
        if replacement is None:
            self.unknown_charref(name)
        else:
            self.handle_data(replacement)

    # Definition of entities -- derived classes may override
    entitydefs = \
            {'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}

    def convert_entityref(self, name):
        """Convert entity references.

        As an alternative to overriding this method; one can tailor the
        results by setting up the self.entitydefs mapping appropriately.
        """
        table = self.entitydefs
        if name in table:
            return table[name]
        else:
            return

    def handle_entityref(self, name):
        """Handle entity references, no need to override."""
        replacement = self.convert_entityref(name)
        if replacement is None:
            self.unknown_entityref(name)
        else:
            self.handle_data(self.convert_entityref(name))

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

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

    # Example -- handle declaration, could be overridden
    def handle_decl(self, decl):
        pass

    # Example -- handle processing instruction, could be overridden
    def handle_pi(self, data):
        pass

    # 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 TestSGMLParser(SGMLParser):

    def __init__(self, verbose=0):
        self.testdata = ""
        SGMLParser.__init__(self, verbose)

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

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

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

    def unknown_starttag(self, tag, attrs):
        self.flush()
        if not attrs:
            print('start tag: <' + tag + '>')
        else:
            print('start tag: <' + tag, end=' ')
            for name, value in attrs:
                print(name + '=' + '"' + value + '"', end=' ')
            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 unknown_decl(self, data):
        self.flush()
        print('*** unknown decl: [' + data + ']')

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


def test(args = None):
    import sys

    if args is None:
        args = sys.argv[1:]

    if args and args[0] == '-s':
        args = args[1:]
        klass = SGMLParser
    else:
        klass = TestSGMLParser

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

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

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

    x = klass()
    for c in data:
        x.feed(c)
    x.close()


if __name__ == '__main__':
    test()