Mercurial > libpst

view python/test.py @ 359:a3e674fade6c

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
From Jeffrey Morlan: pst_parse_block misreads Table Contexts (aka "type 2") with a multi-block Row Matrix ("ind2"). Rows are never split between blocks - every block except the last has padding at the end which should be ignored. I've only seen this affect the recipients table, but presumably it could affect attachments too. This was causing out-of-bounds memory ranges to be returned from pst_getBlockOffset and later access; patch fixes both the table reading issue and adds a missing bounds check to pst_getBlockOffset (so as not to risk a segfault if the PST is corrupted).
author Carl Byington <carl@five-ten-sg.com>
date Wed, 06 Jul 2016 10:20:12 -0700
parents 1ddc61fd6189
children
line wrap: on
line source

import _libpst, sys

ft = _libpst.FILETIME()
ft.dwLowDateTime = 0
ft.dwHighDateTime = 1


for i in range(1,len(sys.argv)):
    print "try file %s" % (sys.argv[i])
    pst = _libpst.pst(sys.argv[i], "")
    topf = pst.pst_getTopOfFolders()

    print pst.pst_rfc2425_datetime_format(ft)
    print pst.pst_rfc2445_datetime_format(ft)

    while (topf):
        #print "topf d_id is %d\n" % (topf.d_id)
        item = pst.pst_parse_item(topf, None)
        if (item):
            if (item.type == 1):
                em = item.email
                if (em):
                    print "default charset %s" % (pst.pst_default_charset(item))
                    ft = em.arrival_date
                    if (ft):
                        print "message arrived at %s" % (pst.pst_rfc2425_datetime_format(ft))
                    if (em.messageid.str):
                        print "message id is <%s>" % (em.messageid.str)
                    subj = item.subject;
                    rtf  = em.rtf_compressed;
                    if rtf and (len(rtf) > 0): print "rtf compressed size", len(rtf)
                    if (subj and subj.str):
                        was = subj.is_utf8;
                        pst.pst_convert_utf8(item, subj)
                        now = subj.is_utf8;
                        if (was != now):
                            print "subject was converted to utf8"
                        print "subject is %s" % (subj.str)
                    body = item.body
                    #if (body.str):
                    #    print "message body is %s" % (body.str)
                    att = item.attach
                    att = None
                    while (att):
                        attid = att.i_id
                        att1  = att.filename1
                        att2  = att.filename2
                        print "attachment id %d file name short '%s' long '%s'" % (attid, att1.str, att2.str)
                        if (1):
                            attdata = pst.pst_attach_to_mem(att)
                            if (attdata):
                                print "data size %d" % (len(attdata))
                        if (0):
                            f = pst.ppst_open_file(att2.str, 'w')
                            if (f):
                                si = pst.pst_attach_to_file_base64(att, f)
                                pst.ppst_close_file(f)
                                print "wrote %d bytes in %s" % (si, att2.str)
                        if (0):
                            f = pst.ppst_open_file(att2.str, 'w')
                            if (f):
                                si = pst.pst_attach_to_file(att, f)
                                pst.ppst_close_file(f)
                                print "wrote %d bytes in %s" % (si, att2.str)
                        att = att.next
            pst.pst_freeItem(item)
        topf = pst.pst_getNextDptr(topf)
    print "done"