diff options
Diffstat (limited to 'xml/be-mbox-to-xml')
| -rwxr-xr-x | xml/be-mbox-to-xml | 104 |
1 files changed, 0 insertions, 104 deletions
diff --git a/xml/be-mbox-to-xml b/xml/be-mbox-to-xml deleted file mode 100755 index 840a2a6..0000000 --- a/xml/be-mbox-to-xml +++ /dev/null @@ -1,104 +0,0 @@ -#!/usr/bin/env python -# Copyright (C) 2009 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 imput into be. - $ cat mbox | be-mbox-to-xml | be comment --xml <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 mailbox import mbox, Message # the mailbox people really want an on-disk copy -from time import asctime, gmtime -import types -from xml.sax import make_parser -from xml.sax.handler import ContentHandler -from xml.sax.saxutils import escape - -DEFAULT_ENCODING = get_encoding() -set_IO_stream_encodings(DEFAULT_ENCODING) - -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'from'] = message[u'from'] - new_fields[u'date'] = message[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 message.is_multipart(): - ret = [] - alt_id = fields[u'alt-id'] - from_str = fields[u'from'] - date = fields[u'date'] - for m in message.walk(): - if m == message: - continue - fields[u'from'] = from_str - fields[u'date'] = date - if len(ret) >= 0: - fields.pop(u'alt-id') - fields[u'in-reply-to'] = alt_id - 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 - - 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"<comment-list>" - for message in mb: - print comment_message_to_xml(message) - print u"</comment-list>" - - -if __name__ == "__main__": - import sys - main(sys.argv[1]) |