Convert Juno 4 OLE messages to MBOX format

readme.md

Juno 4 uses .FRM files to store emails, which are OLE format

This script uses OleFileIO_PL to extract the messages and writes them to mbox format so they can be imported into other software.

It converts \r\n to \r\r\n, which is probably wrong. I just replaced those manually in Notepad++ afterwards.

The files are in mboxo format, so a line starting with >from is ambiguous. Thunderbird opens them in mboxrd format, which interprets these as from . These can also be fixed manually by hand, if you care, by searching for \n>from and replacing it by \n>>from , replacing \n>>from with \n>>>from , etc.

Juno_OLE_to_mbox.py

# -*- coding: utf-8 -*-
"""
Created on Sat May 28 09:53:24 2011

@author: [email protected]
"""

import mailbox
import OleFileIO_PL
from collections import defaultdict

filename = "FOLD0001"

def frm_to_dict(filename):
    source = OleFileIO_PL.OleFileIO(filename + '.frm')
    messages = defaultdict(dict)
    for file in source.listdir():
        if len(file) == 2: # Messages, not 'Directory'
            msg_num = int(file[0])
            msg_type = file[1]
            stream = source.openstream(file).readlines()
            messages[msg_num].update({msg_type: stream})
    return messages

def dict_to_mbox(messages, filename):
    destination = mailbox.mbox(filename + '.mbox')
    for msg_num, streams in messages.iteritems():
        content = streams['Header'] + streams['Body']
        content = ''.join(content)
        message = mailbox.mboxMessage(content)
        destination.add(message)
    destination.close()

messages = frm_to_dict(filename)
dict_to_mbox(messages, filename)