This file is indexed.

/usr/lib/python2.7/dist-packages/podcastparser.py is in python-podcastparser 0.6.2-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
# -*- coding: utf-8 -*-
#
# Podcastparser: A simple, fast and efficient podcast parser
# Copyright (c) 2012, 2013, 2014, Thomas Perl <m@thp.io>
#
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
# REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
# AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
# INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
# LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
# OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
#

""" Simplified, fast RSS parser """

# Will be parsed by setup.py to determine package metadata
__author__ = 'Thomas Perl <m@thp.io>'
__version__ = '0.6.2'
__website__ = 'http://gpodder.org/podcastparser/'
__license__ = 'ISC License'

from xml import sax

import re
import os
import time

try:
    # Python 2
    from htmlentitydefs import entitydefs
    entitydefs = dict((key, value.decode('latin-1')) for key, value in entitydefs.iteritems())
    chr = unichr
except ImportError:
    # Python 3
    from html.entities import entitydefs

try:
    # Python 2
    import urlparse
except ImportError:
    # Python 3
    from urllib import parse as urlparse

try:
    # Python 2
    from rfc822 import parsedate_tz
    import calendar
    # This is taken from Python 3's email._parseaddr, since it handles
    # pre-epoch dates better than what Python 2 does (time.mktime())
    def mktime_tz(data):
        if data[9] is None:
            # No zone info, so localtime is better assumption than GMT
            return time.mktime(data[:8] + (-1,))
        else:
            t = calendar.timegm(data)
            return t - data[9]
except ImportError:
    # Python 3
    from email.utils import mktime_tz, parsedate_tz

import logging
logger = logging.getLogger(__name__)


class Target(object):
    WANT_TEXT = False

    def __init__(self, key=None, filter_func=lambda x: x.strip()):
        self.key = key
        self.filter_func = filter_func

    def start(self, handler, attrs):
        pass

    def end(self, handler, text):
        pass


class RSS(Target):
    def start(self, handler, attrs):
        if 'xml:base' in attrs.keys():
            handler.set_base(attrs.get('xml:base'))


class PodcastItem(Target):
    def end(self, handler, text):
        by_published = lambda entry: entry.get('published')
        handler.data['episodes'].sort(key=by_published, reverse=True)
        if handler.max_episodes:
            episodes = handler.data['episodes'][:handler.max_episodes]
            handler.data['episodes'] = episodes


class PodcastAttr(Target):
    WANT_TEXT = True

    def end(self, handler, text):
        handler.set_podcast_attr(self.key, self.filter_func(text))


class PodcastAttrRelativeLink(PodcastAttr):
    def end(self, handler, text):
        text = urlparse.urljoin(handler.base, text)
        super(PodcastAttrRelativeLink, self).end(handler, text)


class PodcastAttrFromHref(Target):
    def start(self, handler, attrs):
        value = attrs.get('href')
        if value:
            value = urlparse.urljoin(handler.base, value)
            handler.set_podcast_attr(self.key, self.filter_func(value))


class EpisodeItem(Target):
    def start(self, handler, attrs):
        handler.add_episode()

    def end(self, handler, text):
        handler.validate_episode()


class EpisodeAttr(Target):
    WANT_TEXT = True

    def end(self, handler, text):
        handler.set_episode_attr(self.key, self.filter_func(text))


class EpisodeAttrRelativeLink(EpisodeAttr):
    def end(self, handler, text):
        text = urlparse.urljoin(handler.base, text)
        super(EpisodeAttrRelativeLink, self).end(handler, text)


class EpisodeGuid(EpisodeAttr):
    def start(self, handler, attrs):
        if attrs.get('isPermaLink', 'true').lower() == 'true':
            handler.set_episode_attr('_guid_is_permalink', True)
        else:
            handler.set_episode_attr('_guid_is_permalink', False)

    def end(self, handler, text):
        def filter_func(guid):
            guid = guid.strip()
            if handler.get_episode_attr('_guid_is_permalink'):
                return urlparse.urljoin(handler.base, guid)
            return guid

        self.filter_func = filter_func
        EpisodeAttr.end(self, handler, text)


class EpisodeAttrFromHref(Target):
    def start(self, handler, attrs):
        value = attrs.get('href')
        if value:
            value = urlparse.urljoin(handler.base, value)
            handler.set_episode_attr(self.key, self.filter_func(value))


class Enclosure(Target):
    def __init__(self, file_size_attribute):
        Target.__init__(self)
        self.file_size_attribute = file_size_attribute

    def start(self, handler, attrs):
        url = attrs.get('url')
        if url is None:
            return

        url = parse_url(urlparse.urljoin(handler.base, url))
        file_size = parse_length(attrs.get(self.file_size_attribute))
        mime_type = parse_type(attrs.get('type'))

        handler.add_enclosure(url, file_size, mime_type)


class AtomLink(Target):
    def start(self, handler, attrs):
        rel = attrs.get('rel', 'alternate')
        url = parse_url(urlparse.urljoin(handler.base, attrs.get('href')))
        mime_type = parse_type(attrs.get('type', 'text/html'))
        file_size = parse_length(attrs.get('length', '0'))

        if rel == 'enclosure':
            handler.add_enclosure(url, file_size, mime_type)
        elif rel == 'payment':
            handler.set_episode_attr('payment_url', url)
        elif mime_type == 'text/html':
            if rel in ('self', 'alternate'):
                if not handler.get_episode_attr('link'):
                    handler.set_episode_attr('link', url)


class PodcastAtomLink(AtomLink):
    def start(self, handler, attrs):
        rel = attrs.get('rel', 'alternate')
        url = parse_url(urlparse.urljoin(handler.base, attrs.get('href')))
        mime_type = parse_type(attrs.get('type'))

        # RFC 5005 (http://podlove.org/paged-feeds/)
        if rel == 'first':
            handler.set_podcast_attr('paged_feed_first', url)
        elif rel == 'next':
            handler.set_podcast_attr('paged_feed_next', url)
        elif rel == 'payment':
            handler.set_podcast_attr('payment_url', url)
        elif mime_type == 'text/html':
            if rel in ('self', 'alternate'):
                handler.set_podcast_attr('link', url)


class AtomContent(Target):
    WANT_TEXT = True

    def __init__(self):
        self._want_content = False

    def start(self, handler, attrs):
        self._mime_type = attrs.get('type', 'text')

    def end(self, handler, text):
        if self._mime_type == 'html':
            handler.set_episode_attr('description_html', text)
        elif self._mime_type == 'text':
            handler.set_episode_attr('description', squash_whitespace(text))


class PodloveChapters(Target):
    SUPPORTED_VERSIONS = ('1.1', '1.2')

    def start(self, handler, attrs):
        version = attrs.get('version', '1.1')
        if version not in PodloveChapters.SUPPORTED_VERSIONS:
            logger.warn('Possible incompatible chapters version: %s', version)


class PodloveChapter(Target):
    def start(self, handler, attrs):
        # Both the start and title attributes are mandatory
        if attrs.get('start') is None or attrs.get('title') is None:
            logger.warn('Invalid chapter (missing start and/or and title)')
            return

        chapter = {
            'start': parse_time(attrs.get('start')),
            'title': attrs.get('title'),
        }

        for optional in ('href', 'image'):
            value = attrs.get(optional)
            if value:
                chapter[optional] = value

        handler.get_episode_attr('chapters').append(chapter)


class Namespace():
    # Mapping of XML namespaces to prefixes as used in MAPPING below
    NAMESPACES = {
        # iTunes Podcasting, http://www.apple.com/itunes/podcasts/specs.html
        'http://www.itunes.com/dtds/podcast-1.0.dtd': 'itunes',
        'http://www.itunes.com/DTDs/Podcast-1.0.dtd': 'itunes',

        # Atom Syndication Format, http://tools.ietf.org/html/rfc4287
        'http://www.w3.org/2005/Atom': 'atom',
        'http://www.w3.org/2005/Atom/': 'atom',

        # Media RSS, http://www.rssboard.org/media-rss
        'http://search.yahoo.com/mrss/': 'media',

        # From http://www.rssboard.org/media-rss#namespace-declaration:
        #   "Note: There is a trailing slash in the namespace, although
        #    there has been confusion around this in earlier versions."
        'http://search.yahoo.com/mrss': 'media',

        # Podlove Simple Chapters, http://podlove.org/simple-chapters
        'http://podlove.org/simple-chapters': 'psc',
        'http://podlove.org/simple-chapters/': 'psc',

        # Purl RSS Content module
        'http://purl.org/rss/1.0/modules/content/': 'content',
    }

    def __init__(self, attrs, parent=None):
        self.namespaces = self.parse_namespaces(attrs)
        self.parent = parent

    @staticmethod
    def parse_namespaces(attrs):
        """Parse namespace definitions from XML attributes

        >>> expected = {'': 'example'}
        >>> Namespace.parse_namespaces({'xmlns': 'example'}) == expected
        True

        >>> expected = {'foo': 'http://example.com/bar'}
        >>> Namespace.parse_namespaces({'xmlns:foo':
        ...     'http://example.com/bar'}) == expected
        True

        >>> expected = {'': 'foo', 'a': 'bar', 'b': 'bla'}
        >>> Namespace.parse_namespaces({'xmlns': 'foo',
        ...     'xmlns:a': 'bar', 'xmlns:b': 'bla'}) == expected
        True
        """
        result = {}

        for key in attrs.keys():
            if key == 'xmlns':
                result[''] = attrs[key]
            elif key.startswith('xmlns:'):
                result[key[6:]] = attrs[key]

        return result

    def lookup(self, prefix):
        """Look up a namespace URI based on the prefix"""
        current = self
        while current is not None:
            result = current.namespaces.get(prefix, None)
            if result is not None:
                return result
            current = current.parent

        return None

    def map(self, name):
        """Apply namespace prefixes for a given tag

        >>> namespace = Namespace({'xmlns:it':
        ...    'http://www.itunes.com/dtds/podcast-1.0.dtd'}, None)
        >>> namespace.map('it:duration')
        'itunes:duration'
        >>> parent = Namespace({'xmlns:m': 'http://search.yahoo.com/mrss/',
        ...                     'xmlns:x': 'http://example.com/'}, None)
        >>> child = Namespace({}, parent)
        >>> child.map('m:content')
        'media:content'
        >>> child.map('x:y') # Unknown namespace URI
        '!x:y'
        >>> child.map('atom:link') # Undefined prefix
        'atom:link'
        """
        if ':' not in name:
            # <duration xmlns="http://..."/>
            namespace = ''
            namespace_uri = self.lookup(namespace)
        else:
            # <itunes:duration/>
            namespace, name = name.split(':', 1)
            namespace_uri = self.lookup(namespace)
            if namespace_uri is None:
                # Use of "itunes:duration" without xmlns:itunes="..."
                logger.warn('No namespace defined for "%s:%s"', namespace,
                            name)
                return '%s:%s' % (namespace, name)

        if namespace_uri is not None:
            prefix = self.NAMESPACES.get(namespace_uri)
            if prefix is None and namespace:
                # Proper use of namespaces, but unknown namespace
                # logger.warn('Unknown namespace: %s', namespace_uri)
                # We prefix the tag name here to make sure that it does not
                # match any other tag below if we can't recognize the namespace
                name = '!%s:%s' % (namespace, name)
            else:
                name = '%s:%s' % (prefix, name)

        return name


def file_basename_no_extension(filename):
    """ Returns filename without extension

    >>> file_basename_no_extension('/home/me/file.txt')
    'file'

    >>> file_basename_no_extension('file')
    'file'
    """
    base = os.path.basename(filename)
    name, extension = os.path.splitext(base)
    return name


def squash_whitespace(text):
    """ Combine multiple whitespaces into one, trim trailing/leading spaces

    >>> squash_whitespace(' some\t   text  with a    lot of   spaces ')
    'some text with a lot of spaces'
    """
    return re.sub('\s+', ' ', text.strip())


def parse_time(value):
    """Parse a time string into seconds

    See RFC2326, 3.6 "Normal Play Time" (HH:MM:SS.FRACT)

    >>> parse_time('0')
    0
    >>> parse_time('128')
    128
    >>> parse_time('00:00')
    0
    >>> parse_time('00:00:00')
    0
    >>> parse_time('00:20')
    20
    >>> parse_time('00:00:20')
    20
    >>> parse_time('01:00:00')
    3600
    >>> parse_time(' 03:02:01')
    10921
    >>> parse_time('61:08')
    3668
    >>> parse_time('25:03:30 ')
    90210
    >>> parse_time('25:3:30')
    90210
    >>> parse_time('61.08')
    61
    >>> parse_time('01:02:03.500')
    3723
    >>> parse_time(' ')
    0
    """
    value = value.strip()

    if value == '':
        return 0

    hours = minutes = seconds = fraction = 0
    parsed = False

    m = re.match(r'(\d+)[:](\d\d?)[:](\d\d?)([.]\d+)?$', value)
    if not parsed and m:
        hours, minutes, seconds, fraction = m.groups()
        fraction = float(fraction or 0.0)
        parsed = True

    m = re.match(r'(\d+)[:](\d\d?)([.]\d+)?$', value)
    if not parsed and m:
        minutes, seconds, fraction = m.groups()
        fraction = float(fraction or 0.0)
        parsed = True

    m = re.match(r'(\d+)([.]\d+)?$', value)
    if not parsed and m:
        seconds, fraction = m.groups()
        fraction = float(fraction or 0.0)
        parsed = True

    if not parsed:
        try:
            seconds = int(value)
        except ValueError:
            logger.warn('Could not parse time value: "%s"', value)
            return 0

    return (int(hours) * 60 + int(minutes)) * 60 + int(seconds)


def parse_url(text):
    return normalize_feed_url(text.strip())


def parse_length(text):
    """ Parses a file length

    >>> parse_length(None)
    -1

    >>> parse_length('0')
    -1

    >>> parse_length('unknown')
    -1

    >>> parse_length('100')
    100
    """

    if text is None:
        return -1

    try:
        return int(text.strip()) or -1
    except ValueError:
        return -1


def parse_type(text):
    """ "normalize" a mime type

    >>> parse_type('text/plain')
    'text/plain'

    >>> parse_type('text')
    'application/octet-stream'

    >>> parse_type('')
    'application/octet-stream'

    >>> parse_type(None)
    'application/octet-stream'
    """

    if not text or '/' not in text:
        # Maemo bug 10036
        return 'application/octet-stream'

    return text


def parse_pubdate(text):
    """Parse a date string into a Unix timestamp

    >>> parse_pubdate('Fri, 21 Nov 1997 09:55:06 -0600')
    880127706

    >>> parse_pubdate('2003-12-13T00:00:00+02:00')
    1071266400

    >>> parse_pubdate('2003-12-13T18:30:02Z')
    1071340202

    >>> parse_pubdate('Mon, 02 May 1960 09:05:01 +0100')
    -305049299

    >>> parse_pubdate('')
    0

    >>> parse_pubdate('unknown')
    0
    """
    if not text:
        return 0

    parsed = parsedate_tz(text)
    if parsed is not None:
        try:
            pubtimeseconds = int(mktime_tz(parsed))
            return pubtimeseconds
        except(OverflowError,ValueError):
            logger.warn('bad pubdate %s is before epoch or after end of time (2038)',parsed)
            return 0
        
    try:
        parsed = time.strptime(text[:19], '%Y-%m-%dT%H:%M:%S')
        if parsed is not None:
            m = re.match(r'^(?:Z|([+-])([0-9]{2})[:]([0-9]{2}))$', text[19:])
            if m:
                parsed = list(iter(parsed))
                if m.group(1):
                    offset = 3600 * int(m.group(2)) + 60 * int(m.group(3))
                    if m.group(1) == '-':
                        offset = 0 - offset
                else:
                    offset = 0
                parsed.append(offset)
                return int(mktime_tz(tuple(parsed)))
            else:
                return int(time.mktime(parsed))
    except Exception:
        pass

    logger.error('Cannot parse date: %s', repr(text))
    return 0


# If you modify the mapping, don't forget to also update the documentation
# section "Supported XML Elements and Attributes" in doc/index.rst
MAPPING = {
    'rss': RSS(),
    'rss/channel': PodcastItem(),
    'rss/channel/title': PodcastAttr('title', squash_whitespace),
    'rss/channel/link': PodcastAttrRelativeLink('link'),
    'rss/channel/description': PodcastAttr('description', squash_whitespace),
    'rss/channel/image/url': PodcastAttrRelativeLink('cover_url'),
    'rss/channel/itunes:image': PodcastAttrFromHref('cover_url'),
    'rss/channel/atom:link': PodcastAtomLink(),

    'rss/channel/item': EpisodeItem(),
    'rss/channel/item/guid': EpisodeGuid('guid'),
    'rss/channel/item/title': EpisodeAttr('title', squash_whitespace),
    'rss/channel/item/link': EpisodeAttrRelativeLink('link'),
    'rss/channel/item/description': EpisodeAttr('description', squash_whitespace),
    'rss/channel/item/itunes:summary': EpisodeAttr('description', squash_whitespace),
    'rss/channel/item/media:description': EpisodeAttr('description', squash_whitespace),
    'rss/channel/item/itunes:subtitle': EpisodeAttr('subtitle', squash_whitespace),
    'rss/channel/item/content:encoded': EpisodeAttr('description_html'),
    'rss/channel/item/itunes:duration': EpisodeAttr('total_time', parse_time),
    'rss/channel/item/pubDate': EpisodeAttr('published', parse_pubdate),
    'rss/channel/item/atom:link': AtomLink(),

    'rss/channel/item/media:content': Enclosure('fileSize'),
    'rss/channel/item/enclosure': Enclosure('length'),
    'rss/channel/item/psc:chapters': PodloveChapters(),
    'rss/channel/item/psc:chapters/psc:chapter': PodloveChapter(),

    # Basic support for Atom feeds
    'atom:feed': PodcastItem(),
    'atom:feed/atom:title': PodcastAttr('title', squash_whitespace),
    'atom:feed/atom:subtitle': PodcastAttr('description', squash_whitespace),
    'atom:feed/atom:icon': PodcastAttr('cover_url'),
    'atom:feed/atom:link': PodcastAtomLink(),
    'atom:feed/atom:entry': EpisodeItem(),
    'atom:feed/atom:entry/atom:id': EpisodeAttr('guid'),
    'atom:feed/atom:entry/atom:title': EpisodeAttr('title', squash_whitespace),
    'atom:feed/atom:entry/atom:link': AtomLink(),
    'atom:feed/atom:entry/atom:content': AtomContent(),
    'atom:feed/atom:entry/content:encoded': EpisodeAttr('description_html'),
    'atom:feed/atom:entry/atom:published': EpisodeAttr('published', parse_pubdate),
    'atom:feed/atom:entry/atom:updated': EpisodeAttr('published', parse_pubdate),
    'atom:feed/atom:entry/media:group/media:description': EpisodeAttr('description', squash_whitespace),
    'atom:feed/atom:entry/psc:chapters': PodloveChapters(),
    'atom:feed/atom:entry/psc:chapters/psc:chapter': PodloveChapter(),
}

# Derive valid root elements from the supported MAPPINGs
VALID_ROOTS = set(path.split('/')[0] for path in MAPPING.keys())


class FeedParseError(sax.SAXParseException, ValueError):
    """
    Exception raised when asked to parse an invalid feed
    
    This exception allows users of this library to catch exceptions
    without having to import the XML parsing library themselves.
    """
    pass


class PodcastHandler(sax.handler.ContentHandler):
    def __init__(self, url, max_episodes):
        self.url = url
        self.max_episodes = max_episodes
        self.base = url
        self.text = None
        self.episodes = []
        self.data = {
            'title': file_basename_no_extension(url),
            'episodes': self.episodes
        }
        self.path_stack = []
        self.namespace = None

    def set_base(self, base):
        self.base = base

    def set_podcast_attr(self, key, value):
        self.data[key] = value

    def set_episode_attr(self, key, value):
        self.episodes[-1][key] = value

    def get_episode_attr(self, key, default=None):
        return self.episodes[-1].get(key, default)

    def add_episode(self):
        self.episodes.append({
            # title
            'description': '',
            # url
            'published': 0,
            # guid
            'link': '',
            'total_time': 0,
            'payment_url': None,
            'enclosures': [],
            '_guid_is_permalink': False,
            'chapters': [],
        })

    def validate_episode(self):
        entry = self.episodes[-1]

        if len(entry['chapters']) == 0:
            del entry['chapters']

        # Ensures `description` does not contain HTML
        if 'description' in entry and is_html(entry['description']):
            if 'description_html' not in entry:
                entry['description_html'] = entry['description']
            entry['description'] = ''

        # Sets `description` to stripped `description_html` when absent
        if 'description_html' in entry and not entry['description']:
            entry['description'] = remove_html_tags(entry['description_html'])

        if 'guid' not in entry:
            if entry.get('link'):
                # Link element can serve as GUID
                entry['guid'] = entry['link']
            else:
                if len(set(enclosure['url'] for enclosure in entry['enclosures'])) != 1:
                    # Multi-enclosure feeds MUST have a GUID or the same URL for all enclosures
                    self.episodes.pop()
                    return

                # Maemo bug 12073
                entry['guid'] = entry['enclosures'][0]['url']

        if 'title' not in entry:
            if len(entry['enclosures']) != 1:
                self.episodes.pop()
                return

            entry['title'] = file_basename_no_extension(
                entry['enclosures'][0]['url'])

        if not entry.get('link') and entry.get('_guid_is_permalink'):
            entry['link'] = entry['guid']

        del entry['_guid_is_permalink']

    def add_enclosure(self, url, file_size, mime_type):
        self.episodes[-1]['enclosures'].append({
            'url': url,
            'file_size': file_size,
            'mime_type': mime_type,
        })

    def startElement(self, name, attrs):
        self.namespace = Namespace(attrs, self.namespace)
        name = self.namespace.map(name)
        if not self.path_stack and name not in VALID_ROOTS:
            raise FeedParseError(
                msg='Unsupported feed type: {}'.format(name),
                exception=None,
                locator=self._locator,
            )
        self.path_stack.append(name)

        target = MAPPING.get('/'.join(self.path_stack))
        if target is not None:
            target.start(self, attrs)
            if target.WANT_TEXT:
                self.text = []

    def characters(self, chars):
        if self.text is not None:
            self.text.append(chars)

    def endElement(self, name):
        target = MAPPING.get('/'.join(self.path_stack))
        if target is not None:
            content = ''.join(self.text) if self.text is not None else ''
            target.end(self, content)
            self.text = None

        if self.namespace is not None:
            self.namespace = self.namespace.parent
        self.path_stack.pop()


def parse(url, stream, max_episodes=0):
    """Parse a podcast feed from the given URL and stream

    :param url: the URL of the feed. Will be used to resolve relative links
    :param stream: file-like object containing the feed content
    :param max_episodes: maximum number of episodes to return. 0 (default)
                         means no limit
    :returns: a dict with the parsed contents of the feed
    """
    handler = PodcastHandler(url, max_episodes)
    try:
        sax.parse(stream, handler)
    except sax.SAXParseException as e:
        raise FeedParseError(e.getMessage(), e.getException(), e._locator)
    return handler.data


def normalize_feed_url(url):
    """
    Normalize and convert a URL. If the URL cannot be converted
    (invalid or unknown scheme), None is returned.

    This will also normalize feed:// and itpc:// to http://.

    >>> normalize_feed_url('itpc://example.org/podcast.rss')
    'http://example.org/podcast.rss'

    If no URL scheme is defined (e.g. "curry.com"), we will
    simply assume the user intends to add a http:// feed.

    >>> normalize_feed_url('curry.com')
    'http://curry.com/'

    It will also take care of converting the domain name to
    all-lowercase (because domains are not case sensitive):

    >>> normalize_feed_url('http://Example.COM/')
    'http://example.com/'

    Some other minimalistic changes are also taken care of,
    e.g. a ? with an empty query is removed:

    >>> normalize_feed_url('http://example.org/test?')
    'http://example.org/test'

    Leading and trailing whitespace is removed

    >>> normalize_feed_url(' http://example.com/podcast.rss ')
    'http://example.com/podcast.rss'

    Incomplete (too short) URLs are not accepted

    >>> normalize_feed_url('http://') is None
    True

    Unknown protocols are not accepted

    >>> normalize_feed_url('gopher://gopher.hprc.utoronto.ca/file.txt') is None
    True
    """
    url = url.strip()
    if not url or len(url) < 8:
        return None

    # Assume HTTP for URLs without scheme
    if '://' not in url:
        url = 'http://' + url

    scheme, netloc, path, query, fragment = urlparse.urlsplit(url)

    # Schemes and domain names are case insensitive
    scheme, netloc = scheme.lower(), netloc.lower()

    # Normalize empty paths to "/"
    if path == '':
        path = '/'

    # feed://, itpc:// and itms:// are really http://
    if scheme in ('feed', 'itpc', 'itms'):
        scheme = 'http'

    if scheme not in ('http', 'https', 'ftp', 'file'):
        return None

    # urlunsplit might return "a slighty different, but equivalent URL"
    return urlparse.urlunsplit((scheme, netloc, path, query, fragment))

def is_html(text):
    """
    Tests whether the given string contains HTML encoded data
    """
    html_test = re.compile(r'<[a-z][\s\S]*>', re.IGNORECASE)
    return bool(html_test.search(text))

def remove_html_tags(html):
    """
    Remove HTML tags from a string and replace numeric and
    named entities with the corresponding character, so the
    HTML text can be displayed in a simple text view.
    """
    if html is None:
        return None

    # If we would want more speed, we could make these global
    re_strip_tags = re.compile('<[^>]*>')
    re_unicode_entities = re.compile('&#(\d{2,4});')
    re_html_entities = re.compile('&(.{2,8});')
    re_newline_tags = re.compile('(<br[^>]*>|<[/]?ul[^>]*>|</li>)', re.I)
    re_listing_tags = re.compile('<li[^>]*>', re.I)

    result = html

    # Convert common HTML elements to their text equivalent
    result = re_newline_tags.sub('\n', result)
    result = re_listing_tags.sub('\n * ', result)
    result = re.sub('<[Pp]>', '\n\n', result)

    # Remove all HTML/XML tags from the string
    result = re_strip_tags.sub('', result)

    # Convert numeric XML entities to their unicode character
    result = re_unicode_entities.sub(lambda x: chr(int(x.group(1))), result)

    # Convert named HTML entities to their unicode character
    result = re_html_entities.sub(lambda x: entitydefs.get(x.group(1), ''), result)

    # Convert more than two newlines to two newlines
    result = re.sub('([\r\n]{2})([\r\n])+', '\\1', result)

    return result.strip()