summaryrefslogtreecommitdiffstats
path: root/Lib/rfc822.py
blob: 18277d6dff4dbe080e9902d65e961623b1f8e354 (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
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
"""RFC 2822 message manipulation.

Note: This is only a very rough sketch of a full RFC-822 parser; in particular
the tokenizing of addresses does not adhere to all the quoting rules.

Note: RFC 2822 is a long awaited update to RFC 822.  This module should
conform to RFC 2822, and is thus mis-named (it's not worth renaming it).  Some
effort at RFC 2822 updates have been made, but a thorough audit has not been
performed.  Consider any RFC 2822 non-conformance to be a bug.

    RFC 2822: http://www.faqs.org/rfcs/rfc2822.html
    RFC 822 : http://www.faqs.org/rfcs/rfc822.html (obsolete)

Directions for use:

To create a Message object: first open a file, e.g.:

  fp = open(file, 'r')

You can use any other legal way of getting an open file object, e.g. use
sys.stdin or call os.popen().  Then pass the open file object to the Message()
constructor:

  m = Message(fp)

This class can work with any input object that supports a readline method.  If
the input object has seek and tell capability, the rewindbody method will
work; also illegal lines will be pushed back onto the input stream.  If the
input object lacks seek but has an `unread' method that can push back a line
of input, Message will use that to push back illegal lines.  Thus this class
can be used to parse messages coming from a buffered stream.

The optional `seekable' argument is provided as a workaround for certain stdio
libraries in which tell() discards buffered data before discovering that the
lseek() system call doesn't work.  For maximum portability, you should set the
seekable argument to zero to prevent that initial \code{tell} when passing in
an unseekable object such as a a file object created from a socket object.  If
it is 1 on entry -- which it is by default -- the tell() method of the open
file object is called once; if this raises an exception, seekable is reset to
0.  For other nonzero values of seekable, this test is not made.

To get the text of a particular header there are several methods:

  str = m.getheader(name)
  str = m.getrawheader(name)

where name is the name of the header, e.g. 'Subject'.  The difference is that
getheader() strips the leading and trailing whitespace, while getrawheader()
doesn't.  Both functions retain embedded whitespace (including newlines)
exactly as they are specified in the header, and leave the case of the text
unchanged.

For addresses and address lists there are functions

  realname, mailaddress = m.getaddr(name)
  list = m.getaddrlist(name)

where the latter returns a list of (realname, mailaddr) tuples.

There is also a method

  time = m.getdate(name)

which parses a Date-like field and returns a time-compatible tuple,
i.e. a tuple such as returned by time.localtime() or accepted by
time.mktime().

See the class definition for lower level access methods.

There are also some utility functions here.
"""
# Cleanup and extensions by Eric S. Raymond <esr@thyrsus.com>

import time

__all__ = ["Message","AddressList","parsedate","parsedate_tz","mktime_tz"]

_blanklines = ('\r\n', '\n')            # Optimization for islast()


class Message:
    """Represents a single RFC 2822-compliant message."""

    def __init__(self, fp, seekable = 1):
        """Initialize the class instance and read the headers."""
        if seekable == 1:
            # Exercise tell() to make sure it works
            # (and then assume seek() works, too)
            try:
                fp.tell()
            except (AttributeError, IOError):
                seekable = 0
            else:
                seekable = 1
        self.fp = fp
        self.seekable = seekable
        self.startofheaders = None
        self.startofbody = None
        #
        if self.seekable:
            try:
                self.startofheaders = self.fp.tell()
            except IOError:
                self.seekable = 0
        #
        self.readheaders()
        #
        if self.seekable:
            try:
                self.startofbody = self.fp.tell()
            except IOError:
                self.seekable = 0

    def rewindbody(self):
        """Rewind the file to the start of the body (if seekable)."""
        if not self.seekable:
            raise IOError, "unseekable file"
        self.fp.seek(self.startofbody)

    def readheaders(self):
        """Read header lines.

        Read header lines up to the entirely blank line that terminates them.
        The (normally blank) line that ends the headers is skipped, but not
        included in the returned list.  If a non-header line ends the headers,
        (which is an error), an attempt is made to backspace over it; it is
        never included in the returned list.

        The variable self.status is set to the empty string if all went well,
        otherwise it is an error message.  The variable self.headers is a
        completely uninterpreted list of lines contained in the header (so
        printing them will reproduce the header exactly as it appears in the
        file).
        """
        self.dict = {}
        self.unixfrom = ''
        self.headers = list = []
        self.status = ''
        headerseen = ""
        firstline = 1
        startofline = unread = tell = None
        if hasattr(self.fp, 'unread'):
            unread = self.fp.unread
        elif self.seekable:
            tell = self.fp.tell
        while 1:
            if tell:
                try:
                    startofline = tell()
                except IOError:
                    startofline = tell = None
                    self.seekable = 0
            line = self.fp.readline()
            if not line:
                self.status = 'EOF in headers'
                break
            # Skip unix From name time lines
            if firstline and line.startswith('From '):
                self.unixfrom = self.unixfrom + line
                continue
            firstline = 0
            if headerseen and line[0] in ' \t':
                # It's a continuation line.
                list.append(line)
                x = (self.dict[headerseen] + "\n " + line.strip())
                self.dict[headerseen] = x.strip()
                continue
            elif self.iscomment(line):
                # It's a comment.  Ignore it.
                continue
            elif self.islast(line):
                # Note! No pushback here!  The delimiter line gets eaten.
                break
            headerseen = self.isheader(line)
            if headerseen:
                # It's a legal header line, save it.
                list.append(line)
                self.dict[headerseen] = line[len(headerseen)+1:].strip()
                continue
            else:
                # It's not a header line; throw it back and stop here.
                if not self.dict:
                    self.status = 'No headers'
                else:
                    self.status = 'Non-header line where header expected'
                # Try to undo the read.
                if unread:
                    unread(line)
                elif tell:
                    self.fp.seek(startofline)
                else:
                    self.status = self.status + '; bad seek'
                break

    def isheader(self, line):
        """Determine whether a given line is a legal header.

        This method should return the header name, suitably canonicalized.
        You may override this method in order to use Message parsing on tagged
        data in RFC 2822-like formats with special header formats.
        """
        i = line.find(':')
        if i > 0:
            return line[:i].lower()
        else:
            return None

    def islast(self, line):
        """Determine whether a line is a legal end of RFC 2822 headers.

        You may override this method if your application wants to bend the
        rules, e.g. to strip trailing whitespace, or to recognize MH template
        separators ('--------').  For convenience (e.g. for code reading from
        sockets) a line consisting of \r\n also matches.
        """
        return line in _blanklines

    def iscomment(self, line):
        """Determine whether a line should be skipped entirely.

        You may override this method in order to use Message parsing on tagged
        data in RFC 2822-like formats that support embedded comments or
        free-text data.
        """
        return False

    def getallmatchingheaders(self, name):
        """Find all header lines matching a given header name.

        Look through the list of headers and find all lines matching a given
        header name (and their continuation lines).  A list of the lines is
        returned, without interpretation.  If the header does not occur, an
        empty list is returned.  If the header occurs multiple times, all
        occurrences are returned.  Case is not important in the header name.
        """
        name = name.lower() + ':'
        n = len(name)
        list = []
        hit = 0
        for line in self.headers:
            if line[:n].lower() == name:
                hit = 1
            elif not line[:1].isspace():
                hit = 0
            if hit:
                list.append(line)
        return list

    def getfirstmatchingheader(self, name):
        """Get the first header line matching name.

        This is similar to getallmatchingheaders, but it returns only the
        first matching header (and its continuation lines).
        """
        name = name.lower() + ':'
        n = len(name)
        list = []
        hit = 0
        for line in self.headers:
            if hit:
                if not line[:1].isspace():
                    break
            elif line[:n].lower() == name:
                hit = 1
            if hit:
                list.append(line)
        return list

    def getrawheader(self, name):
        """A higher-level interface to getfirstmatchingheader().

        Return a string containing the literal text of the header but with the
        keyword stripped.  All leading, trailing and embedded whitespace is
        kept in the string, however.  Return None if the header does not
        occur.
        """

        list = self.getfirstmatchingheader(name)
        if not list:
            return None
        list[0] = list[0][len(name) + 1:]
        return ''.join(list)

    def getheader(self, name, default=None):
        """Get the header value for a name.

        This is the normal interface: it returns a stripped version of the
        header value for a given header name, or None if it doesn't exist.
        This uses the dictionary version which finds the *last* such header.
        """
        try:
            return self.dict[name.lower()]
        except KeyError:
            return default
    get = getheader

    def getheaders(self, name):
        """Get all values for a header.

        This returns a list of values for headers given more than once; each
        value in the result list is stripped in the same way as the result of
        getheader().  If the header is not given, return an empty list.
        """
        result = []
        current = ''
        have_header = 0
        for s in self.getallmatchingheaders(name):
            if s[0].isspace():
                if current:
                    current = "%s\n %s" % (current, s.strip())
                else:
                    current = s.strip()
            else:
                if have_header:
                    result.append(current)
                current = s[s.find(":") + 1:].strip()
                have_header = 1
        if have_header:
            result.append(current)
        return result

    def getaddr(self, name):
        """Get a single address from a header, as a tuple.

        An example return value:
        ('Guido van Rossum', 'guido@cwi.nl')
        """
        # New, by Ben Escoto
        alist = self.getaddrlist(name)
        if alist:
            return alist[0]
        else:
            return (None, None)

    def getaddrlist(self, name):
        """Get a list of addresses from a header.

        Retrieves a list of addresses from a header, where each address is a
        tuple as returned by getaddr().  Scans all named headers, so it works
        properly with multiple To: or Cc: headers for example.
        """
        raw = []
        for h in self.getallmatchingheaders(name):
            if h[0] in ' \t':
                raw.append(h)
            else:
                if raw:
                    raw.append(', ')
                i = h.find(':')
                if i > 0:
                    addr = h[i+1:]
                raw.append(addr)
        alladdrs = ''.join(raw)
        a = AddressList(alladdrs)
        return a.addresslist

    def getdate(self, name):
        """Retrieve a date field from a header.

        Retrieves a date field from the named header, returning a tuple
        compatible with time.mktime().
        """
        try:
            data = self[name]
        except KeyError:
            return None
        return parsedate(data)

    def getdate_tz(self, name):
        """Retrieve a date field from a header as a 10-tuple.

        The first 9 elements make up a tuple compatible with time.mktime(),
        and the 10th is the offset of the poster's time zone from GMT/UTC.
        """
        try:
            data = self[name]
        except KeyError:
            return None
        return parsedate_tz(data)


    # Access as a dictionary (only finds *last* header of each type):

    def __len__(self):
        """Get the number of headers in a message."""
        return len(self.dict)

    def __getitem__(self, name):
        """Get a specific header, as from a dictionary."""
        return self.dict[name.lower()]

    def __setitem__(self, name, value):
        """Set the value of a header.

        Note: This is not a perfect inversion of __getitem__, because any
        changed headers get stuck at the end of the raw-headers list rather
        than where the altered header was.
        """
        del self[name] # Won't fail if it doesn't exist
        self.dict[name.lower()] = value
        text = name + ": " + value
        lines = text.split("\n")
        for line in lines:
            self.headers.append(line + "\n")

    def __delitem__(self, name):
        """Delete all occurrences of a specific header, if it is present."""
        name = name.lower()
        if not name in self.dict:
            return
        del self.dict[name]
        name = name + ':'
        n = len(name)
        list = []
        hit = 0
        for i in range(len(self.headers)):
            line = self.headers[i]
            if line[:n].lower() == name:
                hit = 1
            elif not line[:1].isspace():
                hit = 0
            if hit:
                list.append(i)
        for i in reversed(list):
            del self.headers[i]

    def setdefault(self, name, default=""):
        lowername = name.lower()
        if lowername in self.dict:
            return self.dict[lowername]
        else:
            text = name + ": " + default
            lines = text.split("\n")
            for line in lines:
                self.headers.append(line + "\n")
            self.dict[lowername] = default
            return default

    def has_key(self, name):
        """Determine whether a message contains the named header."""
        return name.lower() in self.dict

    def __contains__(self, name):
        """Determine whether a message contains the named header."""
        return name.lower() in self.dict

    def __iter__(self):
        return iter(self.dict)

    def keys(self):
        """Get all of a message's header field names."""
        return self.dict.keys()

    def values(self):
        """Get all of a message's header field values."""
        return self.dict.values()

    def items(self):
        """Get all of a message's headers.

        Returns a list of name, value tuples.
        """
        return self.dict.items()

    def __str__(self):
        return ''.join(self.headers)


# Utility functions
# -----------------

# XXX Should fix unquote() and quote() to be really conformant.
# XXX The inverses of the parse functions may also be useful.


def unquote(str):
    """Remove quotes from a string."""
    if len(str) > 1:
        if str.startswith('"') and str.endswith('"'):
            return str[1:-1].replace('\\\\', '\\').replace('\\"', '"')
        if str.startswith('<') and str.endswith('>'):
            return str[1:-1]
    return str


def quote(str):
    """Add quotes around a string."""
    return str.replace('\\', '\\\\').replace('"', '\\"')


def parseaddr(address):
    """Parse an address into a (realname, mailaddr) tuple."""
    a = AddressList(address)
    list = a.addresslist
    if not list:
        return (None, None)
    else:
        return list[0]


class AddrlistClass:
    """Address parser class by Ben Escoto.

    To understand what this class does, it helps to have a copy of
    RFC 2822 in front of you.

    http://www.faqs.org/rfcs/rfc2822.html

    Note: this class interface is deprecated and may be removed in the future.
    Use rfc822.AddressList instead.
    """

    def __init__(self, field):
        """Initialize a new instance.

        `field' is an unparsed address header field, containing one or more
        addresses.
        """
        self.specials = '()<>@,:;.\"[]'
        self.pos = 0
        self.LWS = ' \t'
        self.CR = '\r\n'
        self.atomends = self.specials + self.LWS + self.CR
        # Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it
        # is obsolete syntax.  RFC 2822 requires that we recognize obsolete
        # syntax, so allow dots in phrases.
        self.phraseends = self.atomends.replace('.', '')
        self.field = field
        self.commentlist = []

    def gotonext(self):
        """Parse up to the start of the next address."""
        while self.pos < len(self.field):
            if self.field[self.pos] in self.LWS + '\n\r':
                self.pos = self.pos + 1
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            else: break

    def getaddrlist(self):
        """Parse all addresses.

        Returns a list containing all of the addresses.
        """
        result = []
        while 1:
            ad = self.getaddress()
            if ad:
                result += ad
            else:
                break
        return result

    def getaddress(self):
        """Parse the next address."""
        self.commentlist = []
        self.gotonext()

        oldpos = self.pos
        oldcl = self.commentlist
        plist = self.getphraselist()

        self.gotonext()
        returnlist = []

        if self.pos >= len(self.field):
            # Bad email address technically, no domain.
            if plist:
                returnlist = [(' '.join(self.commentlist), plist[0])]

        elif self.field[self.pos] in '.@':
            # email address is just an addrspec
            # this isn't very efficient since we start over
            self.pos = oldpos
            self.commentlist = oldcl
            addrspec = self.getaddrspec()
            returnlist = [(' '.join(self.commentlist), addrspec)]

        elif self.field[self.pos] == ':':
            # address is a group
            returnlist = []

            fieldlen = len(self.field)
            self.pos = self.pos + 1
            while self.pos < len(self.field):
                self.gotonext()
                if self.pos < fieldlen and self.field[self.pos] == ';':
                    self.pos = self.pos + 1
                    break
                returnlist = returnlist + self.getaddress()

        elif self.field[self.pos] == '<':
            # Address is a phrase then a route addr
            routeaddr = self.getrouteaddr()

            if self.commentlist:
                returnlist = [(' '.join(plist) + ' (' + \
                         ' '.join(self.commentlist) + ')', routeaddr)]
            else: returnlist = [(' '.join(plist), routeaddr)]

        else:
            if plist:
                returnlist = [(' '.join(self.commentlist), plist[0])]
            elif self.field[self.pos] in self.specials:
                self.pos = self.pos + 1

        self.gotonext()
        if self.pos < len(self.field) and self.field[self.pos] == ',':
            self.pos = self.pos + 1
        return returnlist

    def getrouteaddr(self):
        """Parse a route address (Return-path value).

        This method just skips all the route stuff and returns the addrspec.
        """
        if self.field[self.pos] != '<':
            return

        expectroute = 0
        self.pos = self.pos + 1
        self.gotonext()
        adlist = ""
        while self.pos < len(self.field):
            if expectroute:
                self.getdomain()
                expectroute = 0
            elif self.field[self.pos] == '>':
                self.pos = self.pos + 1
                break
            elif self.field[self.pos] == '@':
                self.pos = self.pos + 1
                expectroute = 1
            elif self.field[self.pos] == ':':
                self.pos = self.pos + 1
            else:
                adlist = self.getaddrspec()
                self.pos = self.pos + 1
                break
            self.gotonext()

        return adlist

    def getaddrspec(self):
        """Parse an RFC 2822 addr-spec."""
        aslist = []

        self.gotonext()
        while self.pos < len(self.field):
            if self.field[self.pos] == '.':
                aslist.append('.')
                self.pos = self.pos + 1
            elif self.field[self.pos] == '"':
                aslist.append('"%s"' % self.getquote())
            elif self.field[self.pos] in self.atomends:
                break
            else: aslist.append(self.getatom())
            self.gotonext()

        if self.pos >= len(self.field) or self.field[self.pos] != '@':
            return ''.join(aslist)

        aslist.append('@')
        self.pos = self.pos + 1
        self.gotonext()
        return ''.join(aslist) + self.getdomain()

    def getdomain(self):
        """Get the complete domain name from an address."""
        sdlist = []
        while self.pos < len(self.field):
            if self.field[self.pos] in self.LWS:
                self.pos = self.pos + 1
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            elif self.field[self.pos] == '[':
                sdlist.append(self.getdomainliteral())
            elif self.field[self.pos] == '.':
                self.pos = self.pos + 1
                sdlist.append('.')
            elif self.field[self.pos] in self.atomends:
                break
            else: sdlist.append(self.getatom())
        return ''.join(sdlist)

    def getdelimited(self, beginchar, endchars, allowcomments = 1):
        """Parse a header fragment delimited by special characters.

        `beginchar' is the start character for the fragment.  If self is not
        looking at an instance of `beginchar' then getdelimited returns the
        empty string.

        `endchars' is a sequence of allowable end-delimiting characters.
        Parsing stops when one of these is encountered.

        If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed
        within the parsed fragment.
        """
        if self.field[self.pos] != beginchar:
            return ''

        slist = ['']
        quote = 0
        self.pos = self.pos + 1
        while self.pos < len(self.field):
            if quote == 1:
                slist.append(self.field[self.pos])
                quote = 0
            elif self.field[self.pos] in endchars:
                self.pos = self.pos + 1
                break
            elif allowcomments and self.field[self.pos] == '(':
                slist.append(self.getcomment())
            elif self.field[self.pos] == '\\':
                quote = 1
            else:
                slist.append(self.field[self.pos])
            self.pos = self.pos + 1

        return ''.join(slist)

    def getquote(self):
        """Get a quote-delimited fragment from self's field."""
        return self.getdelimited('"', '"\r', 0)

    def getcomment(self):
        """Get a parenthesis-delimited fragment from self's field."""
        return self.getdelimited('(', ')\r', 1)

    def getdomainliteral(self):
        """Parse an RFC 2822 domain-literal."""
        return '[%s]' % self.getdelimited('[', ']\r', 0)

    def getatom(self, atomends=None):
        """Parse an RFC 2822 atom.

        Optional atomends specifies a different set of end token delimiters
        (the default is to use self.atomends).  This is used e.g. in
        getphraselist() since phrase endings must not include the `.' (which
        is legal in phrases)."""
        atomlist = ['']
        if atomends is None:
            atomends = self.atomends

        while self.pos < len(self.field):
            if self.field[self.pos] in atomends:
                break
            else: atomlist.append(self.field[self.pos])
            self.pos = self.pos + 1

        return ''.join(atomlist)

    def getphraselist(self):
        """Parse a sequence of RFC 2822 phrases.

        A phrase is a sequence of words, which are in turn either RFC 2822
        atoms or quoted-strings.  Phrases are canonicalized by squeezing all
        runs of continuous whitespace into one space.
        """
        plist = []

        while self.pos < len(self.field):
            if self.field[self.pos] in self.LWS:
                self.pos = self.pos + 1
            elif self.field[self.pos] == '"':
                plist.append(self.getquote())
            elif self.field[self.pos] == '(':
                self.commentlist.append(self.getcomment())
            elif self.field[self.pos] in self.phraseends:
                break
            else:
                plist.append(self.getatom(self.phraseends))

        return plist

class AddressList(AddrlistClass):
    """An AddressList encapsulates a list of parsed RFC 2822 addresses."""
    def __init__(self, field):
        AddrlistClass.__init__(self, field)
        if field:
            self.addresslist = self.getaddrlist()
        else:
            self.addresslist = []

    def __len__(self):
        return len(self.addresslist)

    def __str__(self):
        return ", ".join(map(dump_address_pair, self.addresslist))

    def __add__(self, other):
        # Set union
        newaddr = AddressList(None)
        newaddr.addresslist = self.addresslist[:]
        for x in other.addresslist:
            if not x in self.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __iadd__(self, other):
        # Set union, in-place
        for x in other.addresslist:
            if not x in self.addresslist:
                self.addresslist.append(x)
        return self

    def __sub__(self, other):
        # Set difference
        newaddr = AddressList(None)
        for x in self.addresslist:
            if not x in other.addresslist:
                newaddr.addresslist.append(x)
        return newaddr

    def __isub__(self, other):
        # Set difference, in-place
        for x in other.addresslist:
            if x in self.addresslist:
                self.addresslist.remove(x)
        return self

    def __getitem__(self, index):
        # Make indexing, slices, and 'in' work
        return self.addresslist[index]

def dump_address_pair(pair):
    """Dump a (name, address) pair in a canonicalized form."""
    if pair[0]:
        return '"' + pair[0] + '" <' + pair[1] + '>'
    else:
        return pair[1]

# Parse a date field

_monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul',
               'aug', 'sep', 'oct', 'nov', 'dec',
               'january', 'february', 'march', 'april', 'may', 'june', 'july',
               'august', 'september', 'october', 'november', 'december']
_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun']

# The timezone table does not include the military time zones defined
# in RFC822, other than Z.  According to RFC1123, the description in
# RFC822 gets the signs wrong, so we can't rely on any such time
# zones.  RFC1123 recommends that numeric timezone indicators be used
# instead of timezone names.

_timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0,
              'AST': -400, 'ADT': -300,  # Atlantic (used in Canada)
              'EST': -500, 'EDT': -400,  # Eastern
              'CST': -600, 'CDT': -500,  # Central
              'MST': -700, 'MDT': -600,  # Mountain
              'PST': -800, 'PDT': -700   # Pacific
              }


def parsedate_tz(data):
    """Convert a date string to a time tuple.

    Accounts for military timezones.
    """
    if not data:
        return None
    data = data.split()
    if data[0][-1] in (',', '.') or data[0].lower() in _daynames:
        # There's a dayname here. Skip it
        del data[0]
    if len(data) == 3: # RFC 850 date, deprecated
        stuff = data[0].split('-')
        if len(stuff) == 3:
            data = stuff + data[1:]
    if len(data) == 4:
        s = data[3]
        i = s.find('+')
        if i > 0:
            data[3:] = [s[:i], s[i+1:]]
        else:
            data.append('') # Dummy tz
    if len(data) < 5:
        return None
    data = data[:5]
    [dd, mm, yy, tm, tz] = data
    mm = mm.lower()
    if not mm in _monthnames:
        dd, mm = mm, dd.lower()
        if not mm in _monthnames:
            return None
    mm = _monthnames.index(mm)+1
    if mm > 12: mm = mm - 12
    if dd[-1] == ',':
        dd = dd[:-1]
    i = yy.find(':')
    if i > 0:
        yy, tm = tm, yy
    if yy[-1] == ',':
        yy = yy[:-1]
    if not yy[0].isdigit():
        yy, tz = tz, yy
    if tm[-1] == ',':
        tm = tm[:-1]
    tm = tm.split(':')
    if len(tm) == 2:
        [thh, tmm] = tm
        tss = '0'
    elif len(tm) == 3:
        [thh, tmm, tss] = tm
    else:
        return None
    try:
        yy = int(yy)
        dd = int(dd)
        thh = int(thh)
        tmm = int(tmm)
        tss = int(tss)
    except ValueError:
        return None
    tzoffset = None
    tz = tz.upper()
    if tz in _timezones:
        tzoffset = _timezones[tz]
    else:
        try:
            tzoffset = int(tz)
        except ValueError:
            pass
    # Convert a timezone offset into seconds ; -0500 -> -18000
    if tzoffset:
        if tzoffset < 0:
            tzsign = -1
            tzoffset = -tzoffset
        else:
            tzsign = 1
        tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60)
    tuple = (yy, mm, dd, thh, tmm, tss, 0, 1, 0, tzoffset)
    return tuple


def parsedate(data):
    """Convert a time string to a time tuple."""
    t = parsedate_tz(data)
    if type(t) == type( () ):
        return t[:9]
    else: return t


def mktime_tz(data):
    """Turn a 10-tuple as returned by parsedate_tz() into a UTC timestamp."""
    if data[9] is None:
        # No zone info, so localtime is better assumption than GMT
        return time.mktime(data[:8] + (-1,))
    else:
        t = time.mktime(data[:8] + (0,))
        return t - data[9] - time.timezone

def formatdate(timeval=None):
    """Returns time format preferred for Internet standards.

    Sun, 06 Nov 1994 08:49:37 GMT  ; RFC 822, updated by RFC 1123

    According to RFC 1123, day and month names must always be in
    English.  If not for that, this code could use strftime().  It
    can't because strftime() honors the locale and could generated
    non-English names.
    """
    if timeval is None:
        timeval = time.time()
    timeval = time.gmtime(timeval)
    return "%s, %02d %s %04d %02d:%02d:%02d GMT" % (
            ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"][timeval[6]],
            timeval[2],
            ["Jan", "Feb", "Mar", "Apr", "May", "Jun",
             "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"][timeval[1]-1],
                                timeval[0], timeval[3], timeval[4], timeval[5])


# When used as script, run a small test program.
# The first command line argument must be a filename containing one
# message in RFC-822 format.

if __name__ == '__main__':
    import sys, os
    file = os.path.join(os.environ['HOME'], 'Mail/inbox/1')
    if sys.argv[1:]: file = sys.argv[1]
    f = open(file, 'r')
    m = Message(f)
    print 'From:', m.getaddr('from')
    print 'To:', m.getaddrlist('to')
    print 'Subject:', m.getheader('subject')
    print 'Date:', m.getheader('date')
    date = m.getdate_tz('date')
    tz = date[-1]
    date = time.localtime(mktime_tz(date))
    if date:
        print 'ParsedDate:', time.asctime(date),
        hhmmss = tz
        hhmm, ss = divmod(hhmmss, 60)
        hh, mm = divmod(hhmm, 60)
        print "%+03d%02d" % (hh, mm),
        if ss: print ".%02d" % ss,
        print
    else:
        print 'ParsedDate:', None
    m.rewindbody()
    n = 0
    while f.readline():
        n = n + 1
    print 'Lines:', n
    print '-'*70
    print 'len =', len(m)
    if 'Date' in m: print 'Date =', m['Date']
    if 'X-Nonsense' in m: pass
    print 'keys =', m.keys()
    print 'values =', m.values()
    print 'items =', m.items()