~sambuddhabasu1/mailman/fix_mailman_run_error

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
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
# Copyright (C) 1998-2009 by the Free Software Foundation, Inc.
#
# This file is part of GNU Mailman.
#
# GNU Mailman is free software: you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free
# Software Foundation, either version 3 of the License, or (at your option)
# any later version.
#
# GNU Mailman is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
# more details.
#
# You should have received a copy of the GNU General Public License along with
# GNU Mailman.  If not, see <http://www.gnu.org/licenses/>.

"""HyperArch: Pipermail archiving for Mailman

     - The Dragon De Monsyne <dragondm@integral.org>

   TODO:
     - Should be able to force all HTML to be regenerated next time the
       archive is run, in case a template is changed.
     - Run a command to generate tarball of html archives for downloading
       (probably in the 'update_dirty_archives' method).
"""

import os
import re
import sys
import gzip
import time
import errno
import urllib
import logging
import weakref
import binascii

from email.Charset import Charset
from email.Errors import HeaderParseError
from email.Header import decode_header, make_header
from lazr.config import as_boolean
from locknix.lockfile import Lock
from string import Template

from mailman import Utils
from mailman import i18n
from mailman.Archiver import HyperDatabase
from mailman.Archiver import pipermail
from mailman.config import config


log = logging.getLogger('mailman.error')

# Set up i18n.  Assume the current language has already been set in the caller.
_ = i18n._

EMPTYSTRING = ''
NL = '\n'

# MacOSX has a default stack size that is too small for deeply recursive
# regular expressions.  We see this as crashes in the Python test suite when
# running test_re.py and test_sre.py.  The fix is to set the stack limit to
# 2048; the general recommendation is to do in the shell before running the
# test suite.  But that's inconvenient for a daemon like the qrunner.
#
# AFAIK, this problem only affects the archiver, so we're adding this work
# around to this file (it'll get imported by the bundled pipermail or by the
# bin/arch script.  We also only do this on darwin, a.k.a. MacOSX.
if sys.platform == 'darwin':
    try:
        import resource
    except ImportError:
        pass
    else:
        soft, hard = resource.getrlimit(resource.RLIMIT_STACK)
        newsoft = min(hard, max(soft, 1024*2048))
        resource.setrlimit(resource.RLIMIT_STACK, (newsoft, hard))



def html_quote(s, langcode=None):
    repls = ( ('&', '&amp;'),
              ("<", '&lt;'),
              (">", '&gt;'),
              ('"', '&quot;'))
    for thing, repl in repls:
        s = s.replace(thing, repl)
    return Utils.uncanonstr(s, langcode)


def url_quote(s):
    return urllib.quote(s)


def null_to_space(s):
    return s.replace('\000', ' ')


def sizeof(filename, lang):
    try:
        size = os.path.getsize(filename)
    except OSError, e:
        # ENOENT can happen if the .mbox file was moved away or deleted, and
        # an explicit mbox file name was given to bin/arch.
        if e.errno <> errno.ENOENT: raise
        return _('size not available')
    if size < 1000:
        with i18n.using_language(lang.code):
            out = _(' %(size)i bytes ')
        return out
    elif size < 1000000:
        return ' %d KB ' % (size / 1000)
    # GB?? :-)
    return ' %d MB ' % (size / 1000000)


html_charset = '<META http-equiv="Content-Type" ' \
               'content="text/html; charset=%s">'

def CGIescape(arg, lang=None):
    if isinstance(arg, unicode):
        s = Utils.websafe(arg)
    else:
        s = Utils.websafe(str(arg))
    return Utils.uncanonstr(s.replace('"', '&quot;'), lang.code)

# Parenthesized human name
paren_name_pat = re.compile(r'([(].*[)])')

# Subject lines preceded with 'Re:'
REpat = re.compile( r"\s*RE\s*(\[\d+\]\s*)?:\s*", re.IGNORECASE)

# E-mail addresses and URLs in text
emailpat = re.compile(r'([-+,.\w]+@[-+.\w]+)')

#  Argh!  This pattern is buggy, and will choke on URLs with GET parameters.
urlpat = re.compile(r'(\w+://[^>)\s]+)') # URLs in text

# Blank lines
blankpat = re.compile(r'^\s*$')

# Starting <html> directive
htmlpat = re.compile(r'^\s*<HTML>\s*$', re.IGNORECASE)
# Ending </html> directive
nohtmlpat = re.compile(r'^\s*</HTML>\s*$', re.IGNORECASE)
# Match quoted text
quotedpat = re.compile(r'^([>|:]|&gt;)+')



# Like Utils.maketext() but with caching to improve performance.
#
# _templatefilepathcache is used to associate a (templatefile, lang, listname)
# key with the file system path to a template file.  This path is the one that
# the Utils.findtext() function has computed is the one to match the values in
# the key tuple.
#
# _templatecache associate a file system path as key with the text
# returned after processing the contents of that file by Utils.findtext()
#
# We keep two caches to reduce the amount of template text kept in memory,
# since the _templatefilepathcache is a many->one mapping and _templatecache
# is a one->one mapping.  Imagine 1000 lists all using the same default
# English template.

_templatefilepathcache = {}
_templatecache = {}

def quick_maketext(templatefile, dict=None, lang=None, mlist=None):
    if mlist is None:
        listname = ''
    else:
        listname = mlist.fqdn_listname
    if lang is None:
        if mlist is None:
            lang = config.mailman.default_language
        else:
            lang = mlist.preferred_language
    cachekey = (templatefile, lang, listname)
    filepath =  _templatefilepathcache.get(cachekey)
    if filepath:
        template = _templatecache.get(filepath)
    if filepath is None or template is None:
        # Use the basic maketext, with defaults to get the raw template
        template, filepath = Utils.findtext(templatefile, lang=lang.code,
                                            raw=True, mlist=mlist)
        _templatefilepathcache[cachekey] = filepath
        _templatecache[filepath] = template
    # Copied from Utils.maketext()
    text = template
    if dict is not None:
        try:
            try:
                text = Template(template).safe_substitute(**dict)
            except UnicodeError:
                # Try again after coercing the template to unicode
                utemplate = unicode(template, lang.charset, 'replace')
                text = Template(utemplate).safe_substitute(**dict)
        except (TypeError, ValueError):
            # The template is really screwed up
            pass
    # Make sure the text is in the given character set, or html-ify any bogus
    # characters.
    return Utils.uncanonstr(text, lang.code)



# Note: I'm overriding most, if not all of the pipermail Article class
#       here -ddm
# The Article class encapsulates a single posting.  The attributes are:
#
#  sequence : Sequence number, unique for each article in a set of archives
#  subject  : Subject
#  datestr  : The posting date, in human-readable format
#  date     : The posting date, in purely numeric format
#  fromdate : The posting date, in `unixfrom' format
#  headers  : Any other headers of interest
#  author   : The author's name (and possibly organization)
#  email    : The author's e-mail address
#  msgid    : A unique message ID
#  in_reply_to : If !="", this is the msgid of the article being replied to
#  references: A (possibly empty) list of msgid's of earlier articles in
#              the thread
#  body     : A list of strings making up the message body

class Article(pipermail.Article):
    __super_init = pipermail.Article.__init__
    __super_set_date = pipermail.Article._set_date

    _last_article_time = time.time()

    def __init__(self, message=None, sequence=0, keepHeaders=[],
                       lang=config.mailman.default_language, mlist=None):
        self.__super_init(message, sequence, keepHeaders)
        self.prev = None
        self.next = None
        # Trim Re: from the subject line
        i = 0
        while i != -1:
            result = REpat.match(self.subject)
            if result:
                i = result.end(0)
                self.subject = self.subject[i:]
            else:
                i = -1
        # Useful to keep around
        self._lang = lang
        self._mlist = mlist

        if as_boolean(config.archiver.pipermail.obscure_email_addresses):
            # Avoid i18n side-effects.  Note that the language for this
            # article (for this list) could be different from the site-wide
            # preferred language, so we need to ensure no side-effects will
            # occur.  Think what happens when executing bin/arch.
            with i18n.using_language(lang.code):
                if self.author == self.email:
                    self.author = self.email = re.sub('@', _(' at '),
                                                      self.email)
                else:
                    self.email = re.sub('@', _(' at '), self.email)
        # Snag the content-* headers.  RFC 1521 states that their values are
        # case insensitive.
        ctype = message.get('Content-Type', 'text/plain')
        cenc = message.get('Content-Transfer-Encoding', '')
        self.ctype = ctype.lower()
        self.cenc = cenc.lower()
        self.decoded = {}
        cset = mlist.preferred_language.charset
        cset_out = Charset(cset).output_charset or cset
        charset = message.get_content_charset(cset_out)
        if charset:
            charset = charset.lower().strip()
            if charset[0]=='"' and charset[-1]=='"':
                charset = charset[1:-1]
            if charset[0]=="'" and charset[-1]=="'":
                charset = charset[1:-1]
            try:
                body = message.get_payload(decode=True)
            except binascii.Error:
                body = None
            if body and charset != self._lang.charset:
                # decode body
                try:
                    body = unicode(body, charset)
                except (UnicodeError, LookupError):
                    body = None
            if body:
                self.body = [l + "\n" for l in body.splitlines()]

        self.decode_headers()

    def __getstate__(self):
        d = self.__dict__.copy()
        # We definitely don't want to pickle the MailList instance, so just
        # pickle a reference to it.
        if d.has_key('_mlist'):
            mlist = d['_mlist']
            del d['_mlist']
        else:
            mlist = None
        if mlist:
            d['__listname'] = self._mlist.fqdn_listname
        else:
            d['__listname'] = None
        # Delete a few other things we don't want in the pickle
        for attr in ('prev', 'next', 'body'):
            if d.has_key(attr):
                del d[attr]
        d['body'] = []
        return d

    def __setstate__(self, d):
        # For loading older Articles via pickle.  All this stuff was added
        # when Simone Piunni and Tokio Kikuchi i18n'ified Pipermail.  See SF
        # patch #594771.
        self.__dict__ = d
        listname = d.get('__listname')
        if listname:
            del d['__listname']
            d['_mlist'] = config.db.list_manager.get(listname)
        if not d.has_key('_lang'):
            if hasattr(self, '_mlist'):
                self._lang = self._mlist.preferred_language
            else:
                self._lang = config.mailman.default_language
        if not d.has_key('cenc'):
            self.cenc = None
        if not d.has_key('decoded'):
            self.decoded = {}

    def setListIfUnset(self, mlist):
        if getattr(self, '_mlist', None) is None:
            self._mlist = mlist

    def quote(self, buf):
        return html_quote(buf, self._lang.code)

    def decode_headers(self):
        """MIME-decode headers.

        If the email, subject, or author attributes contain non-ASCII
        characters using the encoded-word syntax of RFC 2047, decoded versions
        of those attributes are placed in the self.decoded (a dictionary).

        If the list's charset differs from the header charset, an attempt is
        made to decode the headers as Unicode.  If that fails, they are left
        undecoded.
        """
        author = self.decode_charset(self.author)
        subject = self.decode_charset(self.subject)
        if author:
            self.decoded['author'] = author
            email = self.decode_charset(self.email)
            if email:
                self.decoded['email'] = email
        if subject:
            if as_boolean(config.archiver.pipermail.obscure_email_addresses):
                with i18n.using_language(self._lang.code):
                    atmark = _(' at ')
                    subject = re.sub(r'([-+,.\w]+)@([-+.\w]+)',
                              '\g<1>' + atmark + '\g<2>', subject)
            self.decoded['subject'] = subject
        self.decoded['stripped'] = self.strip_subject(subject or self.subject)

    def strip_subject(self, subject):
        # Strip subject_prefix and Re: for subject sorting
        # This part was taken from CookHeaders.py (TK)
        prefix = self._mlist.subject_prefix.strip()
        if prefix:
            prefix_pat = re.escape(prefix)
            prefix_pat = '%'.join(prefix_pat.split(r'\%'))
            prefix_pat = re.sub(r'%\d*d', r'\s*\d+\s*', prefix_pat)
            subject = re.sub(prefix_pat, '', subject)
        subject = subject.lstrip()
        strip_pat = re.compile('^((RE|AW|SV|VS)(\[\d+\])?:\s*)+', re.I)
        stripped = strip_pat.sub('', subject)
        return stripped

    def decode_charset(self, field):
        # TK: This function was rewritten for unifying to Unicode.
        # Convert 'field' into Unicode one line string.
        try:
            pairs = decode_header(field)
            ustr = make_header(pairs).__unicode__()
        except (LookupError, UnicodeError, ValueError, HeaderParseError):
            # assume list's language
            cset = self._mlist.preferred_language.charset
            if cset == 'us-ascii':
                cset = 'iso-8859-1' # assume this for English list
            ustr = unicode(field, cset, 'replace')
        return u''.join(ustr.splitlines())

    def as_html(self):
        d = self.__dict__.copy()
        # avoid i18n side-effects
        with i18n.using_language(self._lang.code):
            d["prev"], d["prev_wsubj"] = self._get_prev()
            d["next"], d["next_wsubj"] = self._get_next()

            d["email_html"] = self.quote(self.email)
            d["title"] = self.quote(self.subject)
            d["subject_html"] = self.quote(self.subject)
            d["subject_url"] = url_quote(self.subject)
            d["in_reply_to_url"] = url_quote(self.in_reply_to)
            if as_boolean(config.archiver.pipermail.obscure_email_addresses):
                # Point the mailto url back to the list
                author = re.sub('@', _(' at '), self.author)
                emailurl = self._mlist.posting_address
            else:
                author = self.author
                emailurl = self.email
            d["author_html"] = self.quote(author)
            d["email_url"] = url_quote(emailurl)
            d["datestr_html"] = self.quote(i18n.ctime(int(self.date)))
            d["body"] = self._get_body()
            d['listurl'] = self._mlist.script_url('listinfo')
            d['listname'] = self._mlist.real_name
            d['encoding'] = ''
        charset = self._lang.charset
        d["encoding"] = html_charset % charset

        self._add_decoded(d)
        return quick_maketext(
             'article.html', d,
             lang=self._lang, mlist=self._mlist)

    def _get_prev(self):
        """Return the href and subject for the previous message"""
        if self.prev:
            subject = self._get_subject_enc(self.prev)
            prev = ('<LINK REL="Previous"  HREF="%s">'
                    % (url_quote(self.prev.filename)))
            prev_wsubj = ('<LI>' + _('Previous message (by thread):') +
                          ' <A HREF="%s">%s\n</A></li>'
                          % (url_quote(self.prev.filename),
                             self.quote(subject)))
        else:
            prev = prev_wsubj = ""
        return prev, prev_wsubj

    def _get_subject_enc(self, art):
        """Return the subject of art, decoded if possible.

        If the charset of the current message and art match and the
        article's subject is encoded, decode it.
        """
        return art.decoded.get('subject', art.subject)

    def _get_next(self):
        """Return the href and subject for the previous message"""
        if self.next:
            subject = self._get_subject_enc(self.next)
            next = ('<LINK REL="Next"  HREF="%s">'
                    % (url_quote(self.next.filename)))
            next_wsubj = ('<LI>' + _('Next message (by thread):') +
                          ' <A HREF="%s">%s\n</A></li>'
                          % (url_quote(self.next.filename),
                             self.quote(subject)))
        else:
            next = next_wsubj = ""
        return next, next_wsubj

    _rx_quote = re.compile('=([A-F0-9][A-F0-9])')
    _rx_softline = re.compile('=[ \t]*$')

    def _get_body(self):
        """Return the message body ready for HTML, decoded if necessary"""
        try:
            body = self.html_body
        except AttributeError:
            body = self.body
        return null_to_space(EMPTYSTRING.join(body))

    def _add_decoded(self, d):
        """Add encoded-word keys to HTML output"""
        for src, dst in (('author', 'author_html'),
                         ('email', 'email_html'),
                         ('subject', 'subject_html'),
                         ('subject', 'title')):
            if self.decoded.has_key(src):
                d[dst] = self.quote(self.decoded[src])

    def as_text(self):
        d = self.__dict__.copy()
        # We need to guarantee a valid From_ line, even if there are
        # bososities in the headers.
        if not d.get('fromdate', '').strip():
            d['fromdate'] = time.ctime(time.time())
        if not d.get('email', '').strip():
            d['email'] = 'bogus@does.not.exist.com'
        if not d.get('datestr', '').strip():
            d['datestr'] = time.ctime(time.time())
        #
        headers = ['From %(email)s  %(fromdate)s',
                 'From: %(email)s (%(author)s)',
                 'Date: %(datestr)s',
                 'Subject: %(subject)s']
        if d['_in_reply_to']:
            headers.append('In-Reply-To: %(_in_reply_to)s')
        if d['_references']:
            headers.append('References: %(_references)s')
        if d['_message_id']:
            headers.append('Message-ID: %(_message_id)s')
        body = EMPTYSTRING.join(self.body)
        cset = self._lang.charset
        # Coerce the body to Unicode and replace any invalid characters.
        if not isinstance(body, unicode):
            body = unicode(body, cset, 'replace')
        if as_boolean(config.archiver.pipermail.obscure_email_addresses):
            with i18n.using_language(self._lang.code):
                atmark = _(' at ')
                body = re.sub(r'([-+,.\w]+)@([-+.\w]+)',
                              '\g<1>' + atmark + '\g<2>', body)
        # Return body to character set of article.
        body = body.encode(cset, 'replace')
        return NL.join(headers) % d + '\n\n' + body + '\n'

    def _set_date(self, message):
        self.__super_set_date(message)
        self.fromdate = time.ctime(int(self.date))

    def loadbody_fromHTML(self,fileobj):
        self.body = []
        begin = 0
        while 1:
            line = fileobj.readline()
            if not line:
                break
            if not begin:
                if line.strip() == '<!--beginarticle-->':
                    begin = 1
                continue
            if line.strip() == '<!--endarticle-->':
                break
            self.body.append(line)

    def finished_update_article(self):
        self.body = []
        try:
            del self.html_body
        except AttributeError:
            pass


class HyperArchive(pipermail.T):
    __super_init = pipermail.T.__init__
    __super_update_archive = pipermail.T.update_archive
    __super_update_dirty_archives = pipermail.T.update_dirty_archives
    __super_add_article = pipermail.T.add_article

    # some defaults
    DIRMODE = 02775
    FILEMODE = 0660

    VERBOSE = 0
    DEFAULTINDEX = 'thread'
    ARCHIVE_PERIOD = 'month'

    THREADLAZY = 0
    THREADLEVELS = 3

    ALLOWHTML = 1             # "Lines between <html></html>" handled as is.
    SHOWHTML = 0              # Eg, nuke leading whitespace in html manner.
    IQUOTES = 1               # Italicize quoted text.
    SHOWBR = 0                # Add <br> onto every line

    def __init__(self, maillist):
        # can't init the database while other processes are writing to it!
        dir = maillist.archive_dir()
        db = HyperDatabase.HyperDatabase(dir, maillist)
        self.__super_init(dir, reload=1, database=db)

        self.maillist = maillist
        self._lock_file = None
        self.lang = maillist.preferred_language
        self.charset = maillist.preferred_language.charset

        if hasattr(self.maillist,'archive_volume_frequency'):
            if self.maillist.archive_volume_frequency == 0:
                self.ARCHIVE_PERIOD='year'
            elif self.maillist.archive_volume_frequency == 2:
                self.ARCHIVE_PERIOD='quarter'
            elif self.maillist.archive_volume_frequency == 3:
                self.ARCHIVE_PERIOD='week'
            elif self.maillist.archive_volume_frequency == 4:
                self.ARCHIVE_PERIOD='day'
            else:
                self.ARCHIVE_PERIOD='month'

        yre = r'(?P<year>[0-9]{4,4})'
        mre = r'(?P<month>[01][0-9])'
        dre = r'(?P<day>[0123][0-9])'
        self._volre = {
            'year':    '^' + yre + '$',
            'quarter': '^' + yre + r'q(?P<quarter>[1234])$',
            'month':   '^' + yre + r'-(?P<month>[a-zA-Z]+)$',
            'week':    r'^Week-of-Mon-' + yre + mre + dre,
            'day':     '^' + yre + mre + dre + '$'
            }

    def _makeArticle(self, msg, sequence):
        return Article(msg, sequence,
                       lang=self.maillist.preferred_language,
                       mlist=self.maillist)

    def html_foot(self):
        # avoid i18n side-effects
        mlist = self.maillist
        # Convenience
        def quotetime(s):
            return html_quote(i18n.ctime(s), self.lang.code)
        with i18n.using_language(mlist.preferred_language.code):
            d = {"lastdate": quotetime(self.lastdate),
                 "archivedate": quotetime(self.archivedate),
                 "listinfo": mlist.script_url('listinfo'),
                 "version": self.version,
                 }
            i = {"thread": _("thread"),
                 "subject": _("subject"),
                 "author": _("author"),
                 "date": _("date")
                 }
        for t in i.keys():
            cap = t[0].upper() + t[1:]
            if self.type == cap:
                d["%s_ref" % (t)] = ""
            else:
                d["%s_ref" % (t)] = ('<a href="%s.html#start">[ %s ]</a>'
                                     % (t, i[t]))
        return quick_maketext(
            'archidxfoot.html', d,
            mlist=mlist)

    def html_head(self):
        # avoid i18n side-effects
        mlist = self.maillist
        # Convenience
        def quotetime(s):
            return html_quote(i18n.ctime(s), self.lang.code)
        with i18n.using_language(mlist.preferred_language.code):
            d = {"listname": html_quote(mlist.real_name, self.lang.code),
                 "archtype": self.type,
                 "archive":  self.volNameToDesc(self.archive),
                 "listinfo": mlist.script_url('listinfo'),
                 "firstdate": quotetime(self.firstdate),
                 "lastdate": quotetime(self.lastdate),
                 "size": self.size,
                 }
            i = {"thread": _("thread"),
                 "subject": _("subject"),
                 "author": _("author"),
                 "date": _("date"),
                 }
        for t in i.keys():
            cap = t[0].upper() + t[1:]
            if self.type == cap:
                d["%s_ref" % (t)] = ""
                d["archtype"] = i[t]
            else:
                d["%s_ref" % (t)] = ('<a href="%s.html#start">[ %s ]</a>'
                                     % (t, i[t]))
        if self.charset:
            d["encoding"] = html_charset % self.charset
        else:
            d["encoding"] = ""
        return quick_maketext(
            'archidxhead.html', d,
            mlist=mlist)

    def html_TOC(self):
        mlist = self.maillist
        listname = mlist.fqdn_listname
        mbox = os.path.join(mlist.archive_dir()+'.mbox', listname+'.mbox')
        d = {"listname": mlist.real_name,
             "listinfo": mlist.script_url('listinfo'),
             "fullarch": '../%s.mbox/%s.mbox' % (listname, listname),
             "size": sizeof(mbox, mlist.preferred_language),
             'meta': '',
             }
        # Avoid i18n side-effects
        with i18n.using_language(mlist.preferred_language.code):
            if not self.archives:
                d["noarchive_msg"] = _(
                    '<P>Currently, there are no archives. </P>')
                d["archive_listing_start"] = ""
                d["archive_listing_end"] = ""
                d["archive_listing"] = ""
            else:
                d["noarchive_msg"] = ""
                d["archive_listing_start"] = quick_maketext(
                    'archliststart.html',
                    lang=mlist.preferred_language,
                    mlist=mlist)
                d["archive_listing_end"] = quick_maketext(
                    'archlistend.html',
                    mlist=mlist)

                accum = []
                for a in self.archives:
                    accum.append(self.html_TOC_entry(a))
                d["archive_listing"] = EMPTYSTRING.join(accum)
        # The TOC is always in the charset of the list's preferred language
        d['meta'] += html_charset % mlist.preferred_language.charset
        # The site can disable public access to the mbox file.
        if as_boolean(config.archiver.pipermail.public_mbox):
            template = 'archtoc.html'
        else:
            template = 'archtocnombox.html'
        return quick_maketext(template, d, mlist=mlist)

    def html_TOC_entry(self, arch):
        # Check to see if the archive is gzip'd or not
        txtfile = os.path.join(self.maillist.archive_dir(), arch + '.txt')
        gzfile = txtfile + '.gz'
        # which exists?  .txt.gz first, then .txt
        if os.path.exists(gzfile):
            file = gzfile
            url = arch + '.txt.gz'
            templ = '<td><A href="%(url)s">[ ' + _('Gzip\'d Text%(sz)s') \
                    + ']</a></td>'
        elif os.path.exists(txtfile):
            file = txtfile
            url = arch + '.txt'
            templ = '<td><A href="%(url)s">[ ' + _('Text%(sz)s') + ']</a></td>'
        else:
            # neither found?
            file = None
        # in Python 1.5.2 we have an easy way to get the size
        if file:
            textlink = templ % {
                'url': url,
                'sz' : sizeof(file, self.maillist.preferred_language)
                }
        else:
            # there's no archive file at all... hmmm.
            textlink = ''
        return quick_maketext(
            'archtocentry.html',
            {'archive': arch,
             'archivelabel': self.volNameToDesc(arch),
             'textlink': textlink
             },
            mlist=self.maillist)

    def GetArchLock(self):
        if self._lock_file:
            return 1
        self._lock_file = Lock(
            os.path.join(config.LOCK_DIR,
                         self.maillist.fqdn_listname + '-arch.lock'))
        try:
            self._lock_file.lock(timeout=0.5)
        except lockfile.TimeOutError:
            return 0
        return 1

    def DropArchLock(self):
        if self._lock_file:
            self._lock_file.unlock(unconditionally=1)
            self._lock_file = None

    def processListArch(self):
        name = self.maillist.ArchiveFileName()
        wname= name+'.working'
        ename= name+'.err_unarchived'
        try:
            os.stat(name)
        except (IOError,os.error):
            #no archive file, nothin to do -ddm
            return

        #see if arch is locked here -ddm
        if not self.GetArchLock():
            #another archiver is running, nothing to do. -ddm
            return

        #if the working file is still here, the archiver may have
        # crashed during archiving. Save it, log an error, and move on.
        try:
            wf = open(wname)
            log.error('Archive working file %s present.  '
                      'Check %s for possibly unarchived msgs',
                      wname, ename)
            omask = os.umask(007)
            try:
                ef = open(ename, 'a+')
            finally:
                os.umask(omask)
            ef.seek(1,2)
            if ef.read(1) <> '\n':
                ef.write('\n')
            ef.write(wf.read())
            ef.close()
            wf.close()
            os.unlink(wname)
        except IOError:
            pass
        os.rename(name,wname)
        archfile = open(wname)
        self.processUnixMailbox(archfile)
        archfile.close()
        os.unlink(wname)
        self.DropArchLock()

    def get_filename(self, article):
        return '%06i.html' % (article.sequence,)

    def get_archives(self, article):
        """Return a list of indexes where the article should be filed.
        A string can be returned if the list only contains one entry,
        and the empty list is legal."""
        res = self.dateToVolName(float(article.date))
        self.message(_("figuring article archives\n"))
        self.message(res + "\n")
        return res

    def volNameToDesc(self, volname):
        volname = volname.strip()
        # Don't make these module global constants since we have to runtime
        # translate them anyway.
        monthdict = [
            '',
            _('January'),   _('February'), _('March'),    _('April'),
            _('May'),       _('June'),     _('July'),     _('August'),
            _('September'), _('October'),  _('November'), _('December')
            ]
        for each in self._volre.keys():
            match = re.match(self._volre[each], volname)
            # Let ValueErrors percolate up
            if match:
                year = int(match.group('year'))
                if each == 'quarter':
                    d =["", _("First"), _("Second"), _("Third"), _("Fourth") ]
                    ord = d[int(match.group('quarter'))]
                    return _("%(ord)s quarter %(year)i")
                elif each == 'month':
                    monthstr = match.group('month').lower()
                    for i in range(1, 13):
                        monthname = time.strftime("%B", (1999,i,1,0,0,0,0,1,0))
                        if monthstr.lower() == monthname.lower():
                            month = monthdict[i]
                            return _("%(month)s %(year)i")
                    raise ValueError, "%s is not a month!" % monthstr
                elif each == 'week':
                    month = monthdict[int(match.group("month"))]
                    day = int(match.group("day"))
                    return _("The Week Of Monday %(day)i %(month)s %(year)i")
                elif each == 'day':
                    month = monthdict[int(match.group("month"))]
                    day = int(match.group("day"))
                    return _("%(day)i %(month)s %(year)i")
                else:
                    return match.group('year')
        raise ValueError, "%s is not a valid volname" % volname

# The following two methods should be inverses of each other. -ddm

    def dateToVolName(self,date):
        datetuple=time.localtime(date)
        if self.ARCHIVE_PERIOD=='year':
            return time.strftime("%Y",datetuple)
        elif self.ARCHIVE_PERIOD=='quarter':
            if datetuple[1] in [1,2,3]:
                return time.strftime("%Yq1",datetuple)
            elif datetuple[1] in [4,5,6]:
                return time.strftime("%Yq2",datetuple)
            elif datetuple[1] in [7,8,9]:
                return time.strftime("%Yq3",datetuple)
            else:
                return time.strftime("%Yq4",datetuple)
        elif self.ARCHIVE_PERIOD == 'day':
            return time.strftime("%Y%m%d", datetuple)
        elif self.ARCHIVE_PERIOD == 'week':
            # Reconstruct "seconds since epoch", and subtract weekday
            # multiplied by the number of seconds in a day.
            monday = time.mktime(datetuple) - datetuple[6] * 24 * 60 * 60
            # Build a new datetuple from this "seconds since epoch" value
            datetuple = time.localtime(monday)
            return time.strftime("Week-of-Mon-%Y%m%d", datetuple)
        # month. -ddm
        else:
            return time.strftime("%Y-%B",datetuple)


    def volNameToDate(self, volname):
        volname = volname.strip()
        for each in self._volre.keys():
            match = re.match(self._volre[each],volname)
            if match:
                year = int(match.group('year'))
                month = 1
                day = 1
                if each == 'quarter':
                    q = int(match.group('quarter'))
                    month = (q * 3) - 2
                elif each == 'month':
                    monthstr = match.group('month').lower()
                    m = []
                    for i in range(1,13):
                        m.append(
                            time.strftime("%B",(1999,i,1,0,0,0,0,1,0)).lower())
                    try:
                        month = m.index(monthstr) + 1
                    except ValueError:
                        pass
                elif each == 'week' or each == 'day':
                    month = int(match.group("month"))
                    day = int(match.group("day"))
                try:
                    return time.mktime((year,month,1,0,0,0,0,1,-1))
                except OverflowError:
                    return 0.0
        return 0.0

    def sortarchives(self):
        def sf(a, b):
            al = self.volNameToDate(a)
            bl = self.volNameToDate(b)
            if al > bl:
                return 1
            elif al < bl:
                return -1
            else:
                return 0
        if self.ARCHIVE_PERIOD in ('month','year','quarter'):
            self.archives.sort(sf)
        else:
            self.archives.sort()
        self.archives.reverse()

    def message(self, msg):
        if self.VERBOSE:
            f = sys.stderr
            f.write(msg)
            if msg[-1:] != '\n':
                f.write('\n')
            f.flush()

    def open_new_archive(self, archive, archivedir):
        index_html = os.path.join(archivedir, 'index.html')
        try:
            os.unlink(index_html)
        except:
            pass
        os.symlink(self.DEFAULTINDEX+'.html',index_html)

    def write_index_header(self):
        self.depth=0
        print self.html_head()
        if not self.THREADLAZY and self.type=='Thread':
            self.message(_("Computing threaded index\n"))
            self.updateThreadedIndex()

    def write_index_footer(self):
        for i in range(self.depth):
            print '</UL>'
        print self.html_foot()

    def write_index_entry(self, article):
        subject = self.get_header("subject", article)
        author = self.get_header("author", article)
        if as_boolean(config.archiver.pipermail.obscure_email_addresses):
            try:
                author = re.sub('@', _(' at '), author)
            except UnicodeError:
                # Non-ASCII author contains '@' ... no valid email anyway
                pass
        subject = CGIescape(subject, self.lang)
        author = CGIescape(author, self.lang)

        d = {
            'filename': urllib.quote(article.filename),
            'subject':  subject,
            'sequence': article.sequence,
            'author':   author
        }
        print quick_maketext(
            'archidxentry.html', d,
            mlist=self.maillist)

    def get_header(self, field, article):
        # if we have no decoded header, return the encoded one
        result = article.decoded.get(field)
        if result is None:
            return getattr(article, field)
        # otherwise, the decoded one will be Unicode
        return result

    def write_threadindex_entry(self, article, depth):
        if depth < 0:
            self.message('depth<0')
            depth = 0
        if depth > self.THREADLEVELS:
            depth = self.THREADLEVELS
        if depth < self.depth:
            for i in range(self.depth-depth):
                print '</UL>'
        elif depth > self.depth:
            for i in range(depth-self.depth):
                print '<UL>'
        print '<!--%i %s -->' % (depth, article.threadKey)
        self.depth = depth
        self.write_index_entry(article)

    def write_TOC(self):
        self.sortarchives()
        omask = os.umask(002)
        try:
            toc = open(os.path.join(self.basedir, 'index.html'), 'w')
        finally:
            os.umask(omask)
        toc.write(self.html_TOC())
        toc.close()

    def write_article(self, index, article, path):
        # called by add_article
        omask = os.umask(002)
        try:
            f = open(path, 'w')
        finally:
            os.umask(omask)
        f.write(article.as_html())
        f.close()

        # Write the text article to the text archive.
        path = os.path.join(self.basedir, "%s.txt" % index)
        omask = os.umask(002)
        try:
            f = open(path, 'a+')
        finally:
            os.umask(omask)
        f.write(article.as_text())
        f.close()

    def update_archive(self, archive):
        self.__super_update_archive(archive)
        # only do this if the gzip module was imported globally, and
        # gzip'ing was enabled via Defaults.GZIP_ARCHIVE_TXT_FILES.  See
        # above.
        if gzip:
            archz = None
            archt = None
            txtfile = os.path.join(self.basedir, '%s.txt' % archive)
            gzipfile = os.path.join(self.basedir, '%s.txt.gz' % archive)
            oldgzip = os.path.join(self.basedir, '%s.old.txt.gz' % archive)
            try:
                # open the plain text file
                archt = open(txtfile)
            except IOError:
                return
            try:
                os.rename(gzipfile, oldgzip)
                archz = gzip.open(oldgzip)
            except (IOError, RuntimeError, os.error):
                pass
            try:
                ou = os.umask(002)
                newz = gzip.open(gzipfile, 'w')
            finally:
                # XXX why is this a finally?
                os.umask(ou)
            if archz:
                newz.write(archz.read())
                archz.close()
                os.unlink(oldgzip)
            # XXX do we really need all this in a try/except?
            try:
                newz.write(archt.read())
                newz.close()
                archt.close()
            except IOError:
                pass
            os.unlink(txtfile)

    _skip_attrs = ('maillist', '_lock_file', 'charset')

    def getstate(self):
        d={}
        for each in self.__dict__.keys():
            if not (each in self._skip_attrs
                    or each.upper() == each):
                d[each] = self.__dict__[each]
        return d

    # Add <A HREF="..."> tags around URLs and e-mail addresses.

    def __processbody_URLquote(self, lines):
        # XXX a lot to do here:
        # 1. use lines directly, rather than source and dest
        # 2. make it clearer
        # 3. make it faster
        # TK: Prepare for unicode obscure.
        atmark = _(' at ')
        if lines and isinstance(lines[0], unicode):
            atmark = unicode(atmark, self.lang.charset, 'replace')
        source = lines[:]
        dest = lines
        last_line_was_quoted = 0
        for i in xrange(0, len(source)):
            Lorig = L = source[i]
            prefix = suffix = ""
            if L is None:
                continue
            # Italicise quoted text
            if self.IQUOTES:
                quoted = quotedpat.match(L)
                if quoted is None:
                    last_line_was_quoted = 0
                else:
                    quoted = quoted.end(0)
                    prefix = CGIescape(L[:quoted], self.lang) + '<i>'
                    suffix = '</I>'
                    if self.SHOWHTML:
                        suffix += '<BR>'
                        if not last_line_was_quoted:
                            prefix = '<BR>' + prefix
                    L = L[quoted:]
                    last_line_was_quoted = 1
            # Check for an e-mail address
            L2 = ""
            jr = emailpat.search(L)
            kr = urlpat.search(L)
            while jr is not None or kr is not None:
                if jr == None:
                    j = -1
                else:
                    j = jr.start(0)
                if kr is None:
                    k = -1
                else:
                    k = kr.start(0)
                if j != -1 and (j < k or k == -1):
                    text = jr.group(1)
                    length = len(text)
                    if as_boolean(
                        config.archiver.pipermail.obscure_email_addresses):
                        text = re.sub('@', atmark, text)
                        URL = self.maillist.script_url('listinfo')
                    else:
                        URL = 'mailto:' + text
                    pos = j
                elif k != -1 and (j > k or j == -1):
                    text = URL = kr.group(1)
                    length = len(text)
                    pos = k
                else: # j==k
                    raise ValueError, "j==k: This can't happen!"
                #length = len(text)
                #self.message("URL: %s %s %s \n"
                #             % (CGIescape(L[:pos]), URL, CGIescape(text)))
                L2 += '%s<A HREF="%s">%s</A>' % (
                    CGIescape(L[:pos], self.lang),
                    html_quote(URL), CGIescape(text, self.lang))
                L = L[pos+length:]
                jr = emailpat.search(L)
                kr = urlpat.search(L)
            if jr is None and kr is None:
                L = CGIescape(L, self.lang)
            L = prefix + L2 + L + suffix
            source[i] = None
            dest[i] = L

    # Perform Hypermail-style processing of <HTML></HTML> directives
    # in message bodies.  Lines between <HTML> and </HTML> will be written
    # out precisely as they are; other lines will be passed to func2
    # for further processing .

    def __processbody_HTML(self, lines):
        # XXX need to make this method modify in place
        source = lines[:]
        dest = lines
        l = len(source)
        i = 0
        while i < l:
            while i < l and htmlpat.match(source[i]) is None:
                i = i + 1
            if i < l:
                source[i] = None
                i = i + 1
            while i < l and nohtmlpat.match(source[i]) is None:
                dest[i], source[i] = source[i], None
                i = i + 1
            if i < l:
                source[i] = None
                i = i + 1

    def format_article(self, article):
        # called from add_article
        # TBD: Why do the HTML formatting here and keep it in the
        # pipermail database?  It makes more sense to do the html
        # formatting as the article is being written as html and toss
        # the data after it has been written to the archive file.
        lines = filter(None, article.body)
        # Handle <HTML> </HTML> directives
        if self.ALLOWHTML:
            self.__processbody_HTML(lines)
        self.__processbody_URLquote(lines)
        if not self.SHOWHTML and lines:
            lines.insert(0, '<PRE>')
            lines.append('</PRE>')
        else:
            # Do fancy formatting here
            if self.SHOWBR:
                lines = map(lambda x:x + "<BR>", lines)
            else:
                for i in range(0, len(lines)):
                    s = lines[i]
                    if s[0:1] in ' \t\n':
                        lines[i] = '<P>' + s
        article.html_body = lines
        return article

    def update_article(self, arcdir, article, prev, next):
        seq = article.sequence
        filename = os.path.join(arcdir, article.filename)
        self.message(_('Updating HTML for article %(seq)s'))
        try:
            f = open(filename)
            article.loadbody_fromHTML(f)
            f.close()
        except IOError, e:
            if e.errno <> errno.ENOENT: raise
            self.message(_('article file %(filename)s is missing!'))
        article.prev = prev
        article.next = next
        omask = os.umask(002)
        try:
            f = open(filename, 'w')
        finally:
            os.umask(omask)
        f.write(article.as_html())
        f.close()