proxyui.py

用python实现的邮件过滤器

"""POP3Proxy and SMTPProxy Web Interface

Classes:
    ProxyUserInterface - Interface class for pop3proxy and smtpproxy

Abstract:

This module implements a browser based Spambayes user interface for the
POP3, IMAP4 SMTP proxies.  Users may use it to interface with the
proxies.

The following functions are currently included:
[From the base class UserInterface]
  onClassify - classify a given message
  onWordquery - query a word from the database
  onTrain - train a message or mbox
  onSave - save the database and possibly shutdown
[Here]
  onHome - a home page with various options
  onUpload - upload a message for later training (used by proxytee.py)
  onReview - show messages in corpii
  onView - view a message from one of the corpii
  onShowclues - show clues for a message

To do:

Web training interface:

 o Review already-trained messages, and purge them.
 o Add a Today button on the Review page.

User interface improvements:

 o Can it cleanly dynamically update its status display while having a POP3
   conversation?  Hammering reload sucks.

 o Suggestions?
"""

# This module is part of the spambayes project, which is Copyright 2002-3
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

# This module was once part of pop3proxy.py; if you are looking through
# the history of the file, you may need to go back there.

__author__ = "Richie Hindle <[e-mail]>"
__credits__ = "Tim Peters, Neale Pickett, Tim Stone, all the Spambayes folk."

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

import re
import cgi
import time
import types
import bisect

try:
    # We have three possibilities for Set:
    #  (a) With Python 2.2 and earlier, we use our compatsets class
    #  (b) With Python 2.3, we use the sets.Set class
    #  (c) With Python 2.4 and later, we use the builtin set class
    Set = set
except NameError:
    try:
        from sets import Set
    except ImportError:
        from spambayes.compatsets import Set

import tokenizer
import UserInterface
from spambayes.Options import options, _
from email.Iterators import typed_subpart_iterator

global state

# These are the options that will be offered on the configuration page.
# If the option is None, then the entry is a header and the following
# options will appear in a new box on the configuration page.
# These are also used to generate http request parameters and template
# fields/variables.
parm_ini_map = (
    ('POP3 Proxy Options',  None),
    ('pop3proxy',           'remote_servers'),
    ('pop3proxy',           'listen_ports'),
#    ('IMAP4 Proxy Options',  None),
#    ('imap4proxy',          'remote_servers'),
#    ('imap4proxy',          'listen_ports'),
    ('SMTP Proxy Options',  None),
    ('smtpproxy',           'remote_servers'),
    ('smtpproxy',           'listen_ports'),
    ('smtpproxy',           'ham_address'),
    ('smtpproxy',           'spam_address'),
    ('smtpproxy',           'use_cached_message'),
    ('Header Options',      None),
    ('Headers',             'notate_to'),
    ('Headers',             'notate_subject'),
    ('Storage Options',     None),
    ('Storage',             'persistent_storage_file'),
    ('Storage',             'messageinfo_storage_file'),
    ('Storage',             'cache_messages'),
    ('Storage',             'no_cache_bulk_ham'),
    ('Storage',             'no_cache_large_messages'),
    ('Statistics Options',  None),
    ('Categorization',      'ham_cutoff'),
    ('Categorization',      'spam_cutoff'),
)

# Like the above, but hese are the options that will be offered on the
# advanced configuration page.
adv_map = (
    (_('Statistics Options'), None),
    ('Classifier',            'max_discriminators'),
    ('Classifier',            'minimum_prob_strength'),
    ('Classifier',            'unknown_word_prob'),
    ('Classifier',            'unknown_word_strength'),
    ('Classifier',            'use_bigrams'),
    (_('Header Options'),     None),
    ('Headers',               'include_score'),
    ('Headers',               'header_score_digits'),
    ('Headers',               'header_score_logarithm'),
    ('Headers',               'include_thermostat'),
    ('Headers',               'include_evidence'),
    ('Headers',               'clue_mailheader_cutoff'),
    (_('Storage Options'),    None),
    ('Storage',               'persistent_use_database'),
    ('Storage',               'cache_expiry_days'),
    ('Storage',               'cache_use_gzip'),
    ('Storage',               'ham_cache'),
    ('Storage',               'spam_cache'),
    ('Storage',               'unknown_cache'),
    (_('Tokenising Options'), None),
    ('Tokenizer',             'mine_received_headers'),
    ('Tokenizer',             'replace_nonascii_chars'),
    ('Tokenizer',             'summarize_email_prefixes'),
    ('Tokenizer',             'summarize_email_suffixes'),
    (_('Training Options'),   None),
    ('Hammie',                'train_on_filter'),
    (_('Interface Options'),  None),
    ('html_ui',               'display_headers'),
    ('html_ui',               'display_received_time'),
    ('html_ui',               'display_score'),
    ('html_ui',               'display_adv_find'),
    ('html_ui',               'default_ham_action'),
    ('html_ui',               'default_spam_action'),
    ('html_ui',               'default_unsure_action'),
    ('html_ui',               'ham_discard_level'),
    ('html_ui',               'spam_discard_level'),
    ('html_ui',               'allow_remote_connections'),
    ('html_ui',               'http_authentication'),
    ('html_ui',               'http_user_name'),
    ('html_ui',               'http_password'),
    ('pop3proxy',             'allow_remote_connections'),
    ('smtpproxy',             'allow_remote_connections'),
    ('globals',               'language'),
    (_('POP3 Proxy Options'), None),
    ('pop3proxy',             'retrieval_timeout'),
)

class ProxyUserInterface(UserInterface.UserInterface):
    """Serves the HTML user interface for the proxies."""

    def __init__(self, proxy_state, state_recreator):
        global state
        UserInterface.UserInterface.__init__(self, proxy_state.bayes,
                                             parm_ini_map, adv_map,
                                             proxy_state.lang_manager,
                                             proxy_state.stats)
        state = proxy_state
        self.state_recreator = state_recreator # ugly
        self.app_for_version = "SpamBayes Proxy"
        self.previous_sort = None
        if not proxy_state.can_stop:
            self.html._readonly = False
            self.html.shutdownTableCell = "&nbsp;"
            self.html._readonly = True

    def onHome(self):
        """Serve up the homepage."""
        state.buildStatusStrings()
        stateDict = state.__dict__.copy()
        stateDict.update(state.bayes.__dict__)
        statusTable = self.html.statusTable.clone()
        if not state.servers:
            statusTable.proxyDetails = _("No POP3 proxies running.<br/>")
        findBox = self._buildBox(_('Word query'), 'query.gif',
                                 self.html.wordQuery)
        if not options["html_ui", "display_adv_find"]:
            del findBox.advanced
        content = (self._buildBox(_('Status and Configuration'),
                                  'status.gif', statusTable % stateDict)+
                   self._buildBox(_('Train on proxied messages'),
                                  'train.gif', self.html.reviewText) +
                   self._buildTrainBox() +
                   self._buildClassifyBox() +
                   findBox +
                   self._buildBox(_('Find message'), 'query.gif',
                                  self.html.findMessage)
                   )
        self._writePreamble(_("Home"))
        self.write(content)
        self._writePostamble(help_topic="home_proxy")

    def onUpload(self, file):
        """Save a message for later training - used by Skip's proxytee.py."""
        # Convert platform-specific line endings into unix-style.
        file = file.replace('\r\n', '\n').replace('\r', '\n')

        # Get a message list from the upload and write it into the cache.
        messages = self._convertUploadToMessageList(file)
        for m in messages:
            messageName = state.getNewMessageName()
            message = state.unknownCorpus.makeMessage(messageName, m)
            state.unknownCorpus.addMessage(message)

        # Return a link Home.
        self.write(_("<p>OK. Return <a href='home'>Home</a>.</p>"))

    def _keyToTimestamp(self, key):
        """Given a message key (as seen in a Corpus), returns the timestamp
        for that message.  This is the time that the message was received,
        not the Date header."""
        return long(key[:10])

    def _getTimeRange(self, timestamp):
        """Given a unix timestamp, returns a 3-tuple: the start timestamp
        of the given day, the end timestamp of the given day, and the
        formatted date of the given day."""
        this = time.localtime(timestamp)
        start = (this[0], this[1], this[2], 0, 0, 0, this[6], this[7], this[8])
        end = time.localtime(time.mktime(start) + 36*60*60)
        end = (end[0], end[1], end[2], 0, 0, 0, end[6], end[7], end[8])
        date = time.strftime("%A, %B %d, %Y", start)
        return time.mktime(start), time.mktime(end), date

    def _buildReviewKeys(self, timestamp):
        """Builds an ordered list of untrained message keys, ready for output
        in the Review list.  Returns a 5-tuple: the keys, the formatted date
        for the list (eg. "Friday, November 15, 2002"), the start of the prior
        page or zero if there isn't one, likewise the start of the given page,
        and likewise the start of the next page."""
        # Fetch all the message keys
        allKeys = state.unknownCorpus.keys()
        # We have to sort here to split into days.
        # Later on, we also sort the messages that will be on the page
        # (by whatever column we wish).
        allKeys.sort()

        # The default start timestamp is derived from the most recent message,
        # or the system time if there are no messages (not that it gets used).
        if not timestamp:
            if allKeys:
                timestamp = self._keyToTimestamp(allKeys[-1])
            else:
                timestamp = time.time()
        start, end, date = self._getTimeRange(timestamp)

        # Find the subset of the keys within this range.
        startKeyIndex = bisect.bisect(allKeys, "%d" % long(start))
        endKeyIndex = bisect.bisect(allKeys, "%d" % long(end))
        keys = allKeys[startKeyIndex:endKeyIndex]
        keys.reverse()

        # What timestamps to use for the prior and next days?  If there any
        # messages before/after this day's range, use the timestamps of those
        # messages - this will skip empty days.
        prior = end = 0
        if startKeyIndex != 0:
            prior = self._keyToTimestamp(allKeys[startKeyIndex-1])
        if endKeyIndex != len(allKeys):
            end = self._keyToTimestamp(allKeys[endKeyIndex])

        # Return the keys and their date.