sb_server.py

用python实现的邮件过滤器

        if options["globals", "verbose"]:
            print "Asked to add languages: " + \
                  ", ".join(options["globals", "language"])
            print "Set language to " + \
                  str(self.lang_manager.current_langs_codes)

        # Open the log file.
        if options["globals", "verbose"]:
            self.logFile = open('_pop3proxy.log', 'wb', 0)

        if not hasattr(self, "servers"):
            # Could have already been set via the command line.
            self.servers = []
            if options["pop3proxy", "remote_servers"]:
                for server in options["pop3proxy", "remote_servers"]:
                    server = server.strip()
                    if server.find(':') > -1:
                        server, port = server.split(':', 1)
                    else:
                        port = '110'
                    self.servers.append((server, int(port)))

        if not hasattr(self, "proxyPorts"):
            # Could have already been set via the command line.
            self.proxyPorts = []
            if options["pop3proxy", "listen_ports"]:
                splitPorts = options["pop3proxy", "listen_ports"]
                self.proxyPorts = map(_addressAndPort, splitPorts)

        if len(self.servers) != len(self.proxyPorts):
            print "pop3proxy_servers & pop3proxy_ports are different lengths!"
            sys.exit()

        # Remember reported errors.
        self.reported_errors = {}

        # Set up the statistics.
        self.totalSessions = 0
        self.activeSessions = 0
        self.numSpams = 0
        self.numHams = 0
        self.numUnsure = 0

        # Unique names for cached messages - see `getNewMessageName()` below.
        self.lastBaseMessageName = ''
        self.uniquifier = 2

    def close(self):
        assert self.prepared, "closed without being prepared!"
        self.servers = None
        if self.bayes is not None:
            # Only store a non-empty db.
            if self.bayes.nham != 0 and self.bayes.nspam != 0:
                state.bayes.store()
            self.bayes.close()
            self.bayes = None
        if self.mdb is not None:
            self.mdb.store()
            self.mdb.close()
            self.mdb = None
            spambayes.message.Message.message_info_db = None

        self.spamCorpus = self.hamCorpus = self.unknownCorpus = None
        self.spamTrainer = self.hamTrainer = None

        self.prepared = False
        close_platform_mutex(self.platform_mutex)
        self.platform_mutex = None

    def prepare(self, can_stop=True):
        """Do whatever needs to be done to prepare for running.  If
        can_stop is False, then we may not let the user shut down the
        proxy - for example, running as a Windows service this should
        be the case."""
        # If we can, prevent multiple servers from running at the same time.
        assert self.platform_mutex is None, "Should not already have the mutex"
        self.platform_mutex = open_platform_mutex()

        self.can_stop = can_stop

        # Do whatever we've been asked to do...
        self.createWorkers()
        self.prepared = True

    def buildServerStrings(self):
        """After the server details have been set up, this creates string
        versions of the details, for display in the Status panel."""
        serverStrings = ["%s:%s" % (s, p) for s, p in self.servers]
        self.serversString = ', '.join(serverStrings)
        self.proxyPortsString = ', '.join(map(_addressPortStr, self.proxyPorts))

    def buildStatusStrings(self):
        """Build the status message(s) to display on the home page of the
        web interface."""
        nspam = self.bayes.nspam
        nham = self.bayes.nham
        if nspam > 10 and nham > 10:
            db_ratio = nham/float(nspam)
            big = small = None
            if db_ratio > 5.0:
                self.warning = _("Warning: you have much more ham than " \
                                 "spam - SpamBayes works best with " \
                                 "approximately even numbers of ham and " \
                                 "spam.")
            elif db_ratio < (1/5.0):
                self.warning = _("Warning: you have much more spam than " \
                                 "ham - SpamBayes works best with " \
                                 "approximately even numbers of ham and " \
                                 "spam.")
            else:
                self.warning = ""
        elif nspam > 0 or nham > 0:
            self.warning = _("Database only has %d good and %d spam - " \
                             "you should consider performing additional " \
                             "training.") % (nham, nspam)
        else:
            self.warning = _("Database has no training information.  " \
                             "SpamBayes will classify all messages as " \
                             "'unsure', ready for you to train.")
        # Add an additional warning message if the user's thresholds are
        # truly odd.
        spam_cut = options["Categorization", "spam_cutoff"]
        ham_cut = options["Categorization", "ham_cutoff"]
        if spam_cut < 0.5:
            self.warning += _("<br/>Warning: we do not recommend " \
                              "setting the spam threshold less than 0.5.")
        if ham_cut > 0.5:
            self.warning += _("<br/>Warning: we do not recommend " \
                              "setting the ham threshold greater than 0.5.")
        if ham_cut > spam_cut:
            self.warning += _("<br/>Warning: your ham threshold is " \
                              "<b>higher</b> than your spam threshold. " \
                              "Results are unpredictable.")

    def createWorkers(self):
        """Using the options that were initialised in __init__ and then
        possibly overridden by the driver code, create the Bayes object,
        the Corpuses, the Trainers and so on."""
        print "Loading database...",
        if self.isTest:
            self.useDB = "pickle"
            self.DBName = '_pop3proxy_test.pickle'   # This is never saved.
        if not hasattr(self, "DBName"):
            self.DBName, self.useDB = storage.database_type([])
        self.bayes = storage.open_storage(self.DBName, self.useDB)
        self.mdb = spambayes.message.Message().message_info_db

        # Load stats manager.
        self.stats = Stats.Stats(options, self.mdb)

        self.buildStatusStrings()

        # Don't set up the caches and training objects when running the self-test,
        # so as not to clutter the filesystem.
        if not self.isTest:
            # Create/open the Corpuses.  Use small cache sizes to avoid hogging
            # lots of memory.
            sc = get_pathname_option("Storage", "spam_cache")
            hc = get_pathname_option("Storage", "ham_cache")
            uc = get_pathname_option("Storage", "unknown_cache")
            map(storage.ensureDir, [sc, hc, uc])
            if self.gzipCache:
                factory = GzipFileMessageFactory()
            else:
                factory = FileMessageFactory()
            age = options["Storage", "cache_expiry_days"]*24*60*60
            self.spamCorpus = ExpiryFileCorpus(age, factory, sc,
                                               '[0123456789\-]*',
                                               cacheSize=20)
            self.hamCorpus = ExpiryFileCorpus(age, factory, hc,
                                              '[0123456789\-]*',
                                              cacheSize=20)
            self.unknownCorpus = ExpiryFileCorpus(age, factory, uc,
                                                  '[0123456789\-]*',
                                                  cacheSize=20)

            # Given that (hopefully) users will get to the stage
            # where they do not need to do any more regular training to
            # be satisfied with spambayes' performance, we expire old
            # messages from not only the trained corpora, but the unknown
            # as well.
            self.spamCorpus.removeExpiredMessages()
            self.hamCorpus.removeExpiredMessages()
            self.unknownCorpus.removeExpiredMessages()

            # Create the Trainers.
            self.spamTrainer = storage.SpamTrainer(self.bayes)
            self.hamTrainer = storage.HamTrainer(self.bayes)
            self.spamCorpus.addObserver(self.spamTrainer)
            self.hamCorpus.addObserver(self.hamTrainer)

    def getNewMessageName(self):
        # The message name is the time it arrived, with a uniquifier
        # appended if two arrive within one clock tick of each other.
        messageName = "%10.10d" % long(time.time())
        if messageName == self.lastBaseMessageName:
            messageName = "%s-%d" % (messageName, self.uniquifier)
            self.uniquifier += 1
        else:
            self.lastBaseMessageName = messageName
            self.uniquifier = 2
        return messageName

    def RecordClassification(self, cls, score):
        """Record the classification in the session statistics.

        cls should match one of the options["Headers", "header_*_string"]
        values.

        score is the score the message received.        
        """
        if cls == options["Headers", "header_ham_string"]:
            self.numHams += 1
        elif cls == options["Headers", "header_spam_string"]:
            self.numSpams += 1
        else:
            self.numUnsure += 1
        self.stats.RecordClassification(score)


# Option-parsing helper functions
def _addressAndPort(s):
    """Decode a string representing a port to bind to, with optional address."""
    s = s.strip()
    if ':' in s:
        addr, port = s.split(':')
        return addr, int(port)
    else:
        return '', int(s)

def _addressPortStr((addr, port)):
    """Encode a string representing a port to bind to, with optional address."""
    if not addr:
        return str(port)
    else:
        return '%s:%d' % (addr, port)


state = State()
proxyListeners = []
def _createProxies(servers, proxyPorts):
    """Create BayesProxyListeners for all the given servers."""
    for (server, serverPort), proxyPort in zip(servers, proxyPorts):
        ssl = options["pop3proxy", "use_ssl"]
        if ssl == "automatic":
            ssl = serverPort == 995
        listener = BayesProxyListener(server, serverPort, proxyPort, ssl)
        proxyListeners.append(listener)

def _recreateState():
    global state

    # Close the existing listeners and create new ones.  This won't
    # affect any running proxies - once a listener has created a proxy,
    # that proxy is then independent of it.
    # (but won't closing the database screw them?)
    for proxy in proxyListeners:
        proxy.close()
    del proxyListeners[:]

    if state.prepared:    
        # Close the state (which saves if necessary)
        state.close()
    # And get a new one going.
    state = State()

    prepare()
    _createProxies(state.servers, state.proxyPorts)
    return state

def main(servers, proxyPorts, uiPort, launchUI):
    """Runs the proxy forever or until a 'KILL' command is received or
    someone hits Ctrl+Break."""
    _createProxies(servers, proxyPorts)
    httpServer = UserInterfaceServer(uiPort)
    proxyUI = ProxyUserInterface(state, _recreateState)
    httpServer.register(proxyUI)
    Dibbler.run(launchBrowser=launchUI)

def prepare(can_stop=True):
    state.init()
    state.prepare(can_stop)
    # Launch any SMTP proxies.  Note that if the user hasn't specified any
    # SMTP proxy information in their configuration, then nothing will
    # happen.
    from spambayes import smtpproxy
    servers, proxyPorts = smtpproxy.LoadServerInfo()
    proxyListeners.extend(smtpproxy.CreateProxies(servers, proxyPorts,
                                                  smtpproxy.SMTPTrainer(state.bayes, state)))

    # setup info for the web interface
    state.buildServerStrings()

def start():
    # kick everything off
    assert state.prepared, "starting before preparing state"
    try:
        main(state.servers, state.proxyPorts, state.uiPort, state.launchUI)
    finally:
        state.close()

def stop():
    # Shutdown as though through the web UI.  This will save the DB, allow
    # any open proxy connections to complete, etc.
    from urllib import urlopen, urlencode
    urlopen('http://localhost:%d/save' % state.uiPort,
            urlencode({'how': _('Save & shutdown')})).read()


# ===================================================================
# __main__ driver.
# ===================================================================

def run():
    global state
    # Read the arguments.
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hbd:p:l:u:o:')
    except getopt.error, msg:
        print >>sys.stderr, str(msg) + '\n\n' + __doc__
        sys.exit()

    runSelfTest = False
    for opt, arg in opts:
        if opt == '-h':
            print >>sys.stderr, __doc__
            sys.exit()
        elif opt == '-b':
            state.launchUI = True
        # '-p' and '-d' are handled by the storage.database_type call
        # below, in case you are wondering why they are missing.
        elif opt == '-l':
            state.proxyPorts = [_addressAndPort(a) for a in arg.split(',')]
        elif opt == '-u':
            state.uiPort = int(arg)
        elif opt == '-o':
            options.set_from_cmdline(arg, sys.stderr)

    state.DBName, state.useDB = storage.database_type(opts)

    # Let the user know what they are using...
    v = get_current_version()
    print "%s\n" % (v.get_long_version("SpamBayes POP3 Proxy"),)

    if 0 <= len(args) <= 2:
        # Normal usage, with optional server name and port number.
        if len(args) == 1:
            state.servers = [(args[0], 110)]
        elif len(args) == 2:
            state.servers = [(args[0], int(args[1]))]

        # Default to listening on port 110 for command-line-specified servers.
        if len(args) > 0 and state.proxyPorts == []:
            state.proxyPorts = [('', 110)]

        try:
            prepare()
        except AlreadyRunningException:
            print  >>sys.stderr, \
                   "ERROR: The proxy is already running on this machine."
            print  >>sys.stderr, "Please stop the existing proxy and try again"
            return
        start()

    else:
        print >>sys.stderr, __doc__

if __name__ == '__main__':
    run()