aboutsummaryrefslogtreecommitdiffstats
path: root/misc/xml/be-mbox-to-xml
blob: 1fc41e0fcb6eb0a3e4e9bfad7960ac2236fdfa65 (plain) (blame)
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
#!/usr/bin/env python
# Copyright (C) 2009-2010 W. Trevor King <wking@drexel.edu>
#
# This program 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 2 of the License, or
# (at your option) any later version.
#
# This program 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 this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Convert an mbox into xml suitable for input into be.
  $ be-mbox-to-xml file.mbox | be import-xml -c <ID> -
mbox is a flat-file format, consisting of a series of messages.
Messages begin with a a From_ line, followed by RFC 822 email,
followed by a blank line.
"""

import base64
import email.utils
from libbe.encoding import get_encoding, set_IO_stream_encodings
from libbe.utility import time_to_str
from mailbox import mbox, Message  # the mailbox people really want an on-disk copy
from time import asctime, gmtime, mktime
import types
from xml.sax.saxutils import escape

DEFAULT_ENCODING = get_encoding()
set_IO_stream_encodings(DEFAULT_ENCODING)

KNOWN_IDS = []

def normalize_email_address(address):
    """
    Standardize whitespace, etc.
    """
    addr = email.utils.formataddr(email.utils.parseaddr(address))
    if len(addr) == 0:
        return None
    return addr

def normalize_RFC_2822_date(date):
    """
    Some email clients write non-RFC 2822-compliant date tags like:
      Fri, 18 Sep 2009 08:49:02 -0400 (EDT)
    with the non-standard (EDT) timezone name.  This funtion attempts
    to deal with such inconsistencies.
    """
    time_tuple = email.utils.parsedate(date)
    assert time_tuple != None, \
        'unparsable date: "%s"' % date
    return time_to_str(mktime(time_tuple))

def comment_message_to_xml(message, fields=None):
    if fields == None:
        fields = {}
    new_fields = {}
    new_fields[u'alt-id'] = message[u'message-id']
    new_fields[u'in-reply-to'] = message[u'in-reply-to']
    new_fields[u'author'] = normalize_email_address(message[u'from'])
    new_fields[u'date'] = message[u'date']
    if new_fields[u'date'] != None:
        new_fields[u'date'] = normalize_RFC_2822_date(new_fields[u'date'])
    new_fields[u'content-type'] = message.get_content_type()
    for k,v in new_fields.items():
        if v != None and type(v) != types.UnicodeType:
            fields[k] = unicode(v, encoding=DEFAULT_ENCODING)
        elif v == None and k in fields:
            new_fields[k] = fields[k]
    for k,v in fields.items():
        if k not in new_fields:
            new_fields.k = fields[k]
    fields = new_fields

    if fields[u'in-reply-to'] == None:
        if message[u'references'] != None:
            refs = message[u'references'].split()
            for ref in refs: # search for a known reference id.
                if ref in KNOWN_IDS:
                    fields[u'in-reply-to'] = ref
                    break
            if fields[u'in-reply-to'] == None and len(refs) > 0:
                fields[u'in-reply-to'] = refs[0] # default to the first
    else: # check for mutliple in-reply-to references.
        refs = fields[u'in-reply-to'].split()
        found_ref = False
        for ref in refs: # search for a known reference id.
            if ref in KNOWN_IDS:
                fields[u'in-reply-to'] = ref
                found_ref = True
                break
        if found_ref == False and len(refs) > 0:
            fields[u'in-reply-to'] = refs[0] # default to the first

    if fields[u'alt-id'] != None:
        KNOWN_IDS.append(fields[u'alt-id'])

    if message.is_multipart():
        ret = []
        alt_id = fields[u'alt-id']
        from_str = fields[u'author']
        date = fields[u'date']
        for m in message.walk():
            if m == message:
                continue
            fields[u'author'] = from_str
            fields[u'date'] = date
            if len(ret) > 0: # we've added one part already
                fields.pop(u'alt-id') # don't pass alt-id to other parts
                fields[u'in-reply-to'] = alt_id # others respond to first
            ret.append(comment_message_to_xml(m, fields))
            return u'\n'.join(ret)

    charset = message.get_content_charset(DEFAULT_ENCODING).lower()
    #assert charset == DEFAULT_ENCODING.lower(), \
    #    u"Unknown charset: %s" % charset

    if message[u'content-transfer-encoding'] == None:
        encoding = DEFAULT_ENCODING
    else:
        encoding = message[u'content-transfer-encoding'].lower()
    body = message.get_payload(decode=True) # attempt to decode
    assert body != None, "Unable to decode?"
    if fields[u'content-type'].startswith(u"text/"):
        body = unicode(body, encoding=charset).rstrip(u'\n')
    else:
        body = base64.encode(body)
    fields[u'body'] = body
    lines = [u"<comment>"]
    for tag,body in fields.items():
        if body != None:
            ebody = escape(body)
            lines.append(u"  <%s>%s</%s>" % (tag, ebody, tag))
    lines.append(u"</comment>")
    return u'\n'.join(lines)

def main(mbox_filename):
    mb = mbox(mbox_filename)
    print u'<?xml version="1.0" encoding="%s" ?>' % DEFAULT_ENCODING
    print u"<be-xml>"
    for message in mb:
        print comment_message_to_xml(message)
    print u"</be-xml>"


if __name__ == "__main__":
    import sys
    main(sys.argv[1])