[Assorted-commits] SF.net SVN: assorted: [704] mailing-list-filter

[<yan...@us...>]

Revision: 704
          http://assorted.svn.sourceforge.net/assorted/?rev=704&view=rev
Author:   yangzhang
Date:     2008-05-07 09:06:28 -0700 (Wed, 07 May 2008)

Log Message:
-----------
added mailing list filter! still exploring how gmail imap starred messages work

Added Paths:
-----------
    mailing-list-filter/
    mailing-list-filter/trunk/
    mailing-list-filter/trunk/src/
    mailing-list-filter/trunk/src/filter.py

Added: mailing-list-filter/trunk/src/filter.py
===================================================================
--- mailing-list-filter/trunk/src/filter.py	                        (rev 0)
+++ mailing-list-filter/trunk/src/filter.py	2008-05-07 16:06:28 UTC (rev 704)
@@ -0,0 +1,149 @@
+#!/usr/bin/env python
+
+"""
+Given an IMAP mailbox, mark all messages as read except for those threads in
+which you were a participant, where thread grouping is performed via the
+In-Reply-To and References headers.
+
+Currently, we assume that the server specification points to a mailbox
+containing all messages (both sent and received), and a message is determined
+to have been sent by you by looking at the From: header field. This should work
+well with Gmail. An alternative strategy is to look through two folders, one
+that's the Inbox and one that's the Sent mailbox, and treat all messages in
+Sent as having been sent by you.
+"""
+
+from __future__ import with_statement
+from collections import defaultdict
+from email import message_from_string
+from getpass import getpass
+from imaplib import IMAP4_SSL
+from argparse import ArgumentParser
+from path import path
+from re import match
+from functools import partial
+from commons.decs import pickle_memoized
+from commons.log import *
+from commons.files import cleanse_filename, soft_makedirs
+from commons.misc import default_if_none
+from commons.networking import logout
+from commons.seqs import concat, grouper
+from commons.startup import run_main
+from contextlib import closing
+
+info  = partial(info,  '')
+debug = partial(debug, '')
+error = partial(error, '')
+die   = partial(die,   '')
+
+def getmail(imap):
+  info( 'finding max seqno' )
+  ok, [seqnos] = imap.search(None, 'ALL')
+  maxseqno = int( seqnos.split()[-1] )
+  del seqnos
+
+  info( 'actually fetching the messages in chunks' )
+  # The syntax/fields of the FETCH command is documented in RFC 2060.  Also,
+  # this article contains a brief overview:
+  # http://www.devshed.com/c/a/Python/Python-Email-Libraries-part-2-IMAP/3/
+  # BODY.PEEK prevents the message from automatically being flagged as \Seen.
+  query = '(FLAGS BODY.PEEK[HEADER.FIELDS (Message-ID References In-Reply-To From Subject)])'
+  step = 1000
+  return list( concat(
+    imap.fetch('%d:%d' % (start, start + step - 1), query)[1]
+    for start in xrange(1, maxseqno + 1, step) ) )
+
+def main(argv):
+  import logging
+  config_logging(level = logging.INFO, do_console = True)
+
+  p = ArgumentParser(description = __doc__)
+  p.add_argument('--credfile', default = path( '~/.mlf.auth' ).expanduser(),
+      help = """File containing your login credentials, with the username on the
+      first line and the password on the second line.  Ignored iff --prompt.""")
+  p.add_argument('--cachedir', default = path( '~/.mlf.cache' ).expanduser(),
+      help = "Directory to use for caching our data.")
+  p.add_argument('--prompt', action = 'store_true',
+      help = "Interactively prompt for the username and password.")
+  p.add_argument('sender',
+      help = "Your email address.")
+  p.add_argument('server',
+      help = "The server in the format: <host>[:<port>][/<mailbox>].")
+
+  cfg = p.parse_args(argv[1:])
+
+  if cfg.prompt:
+    print "username:",
+    cfg.user = raw_input()
+    print "password:",
+    cfg.passwd = getpass()
+  else:
+    with file(cfg.credfile) as f:
+      [cfg.user, cfg.passwd] = map(lambda x: x.strip('\r\n'), f.readlines())
+
+  try:
+    m = match( r'(?P<host>[^:/]+)(:(?P<port>\d+))?(/(?P<mailbox>.+))?$', cfg.server )
+    cfg.host = m.group('host')
+    cfg.port = int( default_if_none(m.group('port'), 993) )
+    cfg.mailbox = default_if_none(m.group('mailbox'), 'INBOX')
+  except:
+    p.error('Need to specify the server in the correct format.')
+
+  soft_makedirs(cfg.cachedir)
+
+  with logout(IMAP4_SSL(cfg.host, cfg.port)) as imap:
+    imap.login(cfg.user, cfg.passwd)
+    with closing(imap) as imap:
+      # Select the main mailbox (INBOX).
+      imap.select(cfg.mailbox)
+
+      # Fetch message IDs, references, and senders.
+      xs = pickle_memoized \
+          (lambda imap: cfg.cachedir / cleanse_filename(cfg.sender)) \
+          (getmail) \
+          (imap)
+
+      debug('fetched:', xs)
+
+      info('determining the set of messages that were sent by you')
+
+      sent = set()
+      for (envelope, data), paren in grouper(2, xs):
+        msg = message_from_string(data)
+        if cfg.sender in msg['From']:
+          sent.add( msg['Message-ID'] )
+
+      info( 'find the threads in which I am a participant' )
+
+      # Every second item is just a closing paren.
+      # Example data:
+      # [('13300 (BODY[HEADER.FIELDS (Message-ID References In-Reply-To)] {67}',
+      #   'Message-ID: <mai...@py...>\r\n\r\n'),
+      #  ')',
+      #  ('13301 (BODY[HEADER.FIELDS (Message-ID References In-Reply-To)] {59}',
+      #   'Message-Id: <200...@hv...>\r\n\r\n'),
+      #  ')',
+      #  ('13302 (BODY[HEADER.FIELDS (Message-ID References In-Reply-To)] {92}',
+      #   'Message-ID: <C43EAFC0.2E3AE%ni...@ya...>\r\nIn-Reply-To: <481...@gm...>\r\n\r\n')]
+      for (envelope, data), paren in grouper(2, xs):
+        m = match( r"(?P<seqno>\d+) \(FLAGS \((?P<flags>[^)]+)\)", envelope )
+        seqno = m.group('seqno')
+        flags = m.group('flags')
+        if r'\Flagged' in flags: # flags != r'\Seen' and flags != r'\Seen NonJunk':
+          print 'FLAG'
+          print seqno, flags
+          print '\n'.join( map( str, msg.items() ) )
+          print
+        msg   = message_from_string(data)
+        id    = msg['Message-ID']
+        irt   = default_if_none( msg.get_all('In-Reply-To'), [] )
+        refs  = default_if_none( msg.get_all('References'), [] )
+        refs  = set( ' '.join( irt + refs ).split() )
+        if refs & sent:
+          print 'SENT'
+          print seqno, flags
+          print '\n'.join( map( str, msg.items() ) )
+          print
+#       if refs & sent:
+
+run_main()


Property changes on: mailing-list-filter/trunk/src/filter.py
___________________________________________________________________
Name: svn:executable
   + *


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.