From c8985785eb741ff646082879f1ca5e9cfe3873b0 Mon Sep 17 00:00:00 2001 From: "W. Trevor King" Date: Wed, 20 Jan 2010 15:22:28 -0500 Subject: 'be-mbox-to-xml' -> 'be-mail-to-xml' + support for several formats. --- misc/xml/be-mail-to-xml | 166 ++++++++++++++++++++++++++++++++++++++++++++++++ misc/xml/be-mbox-to-xml | 154 -------------------------------------------- 2 files changed, 166 insertions(+), 154 deletions(-) create mode 100755 misc/xml/be-mail-to-xml delete mode 100755 misc/xml/be-mbox-to-xml (limited to 'misc') diff --git a/misc/xml/be-mail-to-xml b/misc/xml/be-mail-to-xml new file mode 100755 index 0000000..2add065 --- /dev/null +++ b/misc/xml/be-mail-to-xml @@ -0,0 +1,166 @@ +#!/usr/bin/env python +# Copyright (C) 2009-2010 W. Trevor King +# +# 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 - +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 codecs +import email.utils +from libbe.util.encoding import get_output_encoding +from libbe.util.utility import time_to_str +import mailbox # the mailbox people really want an on-disk copy +import optparse +import sys +from time import asctime, gmtime, mktime +import types +from xml.sax.saxutils import escape + +DEFAULT_ENCODING = get_output_encoding() +sys.stdout = codecs.getwriter(DEFAULT_ENCODING)(sys.stdout) + +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""] + for tag,body in fields.items(): + if body != None: + ebody = escape(body) + lines.append(u" <%s>%s" % (tag, ebody, tag)) + lines.append(u"") + return u'\n'.join(lines) + +def main(argv): + parser = optparse.OptionParser(usage='%prog [options] mailbox') + formats = ['mbox', 'Maildir', 'MH', 'Babyl', 'MMDF'] + parser.add_option('-f', '--format', type='choice', dest='format', + help="Select the mailbox format from %s. See the mailbox module's documention for descriptions of these formats." \ + % ', '.join(formats), + default='mbox', choices=formats) + options,args = parser.parse_args(argv) + mailbox_file = args[1] + reader = getattr(mailbox, options.format) + mb = reader(mailbox_file, factory=None) + print u'' % DEFAULT_ENCODING + print u"" + for message in mb: + print comment_message_to_xml(message) + print u"" + + +if __name__ == "__main__": + import sys + main(sys.argv) diff --git a/misc/xml/be-mbox-to-xml b/misc/xml/be-mbox-to-xml deleted file mode 100755 index 1fc41e0..0000000 --- a/misc/xml/be-mbox-to-xml +++ /dev/null @@ -1,154 +0,0 @@ -#!/usr/bin/env python -# Copyright (C) 2009-2010 W. Trevor King -# -# 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 - -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""] - for tag,body in fields.items(): - if body != None: - ebody = escape(body) - lines.append(u" <%s>%s" % (tag, ebody, tag)) - lines.append(u"") - return u'\n'.join(lines) - -def main(mbox_filename): - mb = mbox(mbox_filename) - print u'' % DEFAULT_ENCODING - print u"" - for message in mb: - print comment_message_to_xml(message) - print u"" - - -if __name__ == "__main__": - import sys - main(sys.argv[1]) -- cgit