proxyui.py

用python实现的邮件过滤器

        return keys, date, prior, start, end

    def _sortMessages(self, messages, sort_order, reverse=False):
        """Sorts the message by the appropriate attribute.  If this was the
        previous sort order, then reverse it."""
        if sort_order is None or sort_order == "received":
            # Default sorting, which is in reverse order of appearance.
            # This is complicated because the 'received' info is the key.
            messages.sort()
            if self.previous_sort == sort_order:
                messages.reverse()
                self.previous_sort = None
            else:
                self.previous_sort = 'received'
            return messages
        tmplist = [(getattr(x[1], sort_order), x) for x in messages]
        tmplist.sort()
        if reverse:
            tmplist.reverse()
        return [x for (key, x) in tmplist]

    def _appendMessages(self, table, keyedMessageInfo, label, sort_order,
                        reverse=False):
        """Appends the rows of a table of messages to 'table'."""
        stripe = 0

        keyedMessageInfo = self._sortMessages(keyedMessageInfo, sort_order,
                                              reverse)
        nrows = options["html_ui", "rows_per_section"]
        for key, messageInfo in keyedMessageInfo[:nrows]:
            unused, unused, messageInfo.received = \
                    self._getTimeRange(self._keyToTimestamp(key))
            row = self.html.reviewRow.clone()
            try:
                score = messageInfo.score
            except ValueError:
                score = None
            if label == _('Spam'):
                if score is not None \
                   and score > options["html_ui", "spam_discard_level"]:
                    r_att = getattr(row, 'discard')
                else:
                    r_att = getattr(row, options["html_ui",
                                           "default_spam_action"])
            elif label == _('Ham'):
                if score is not None \
                   and score < options["html_ui", "ham_discard_level"]:
                    r_att = getattr(row, 'discard')
                else:
                    r_att = getattr(row, options["html_ui",
                                           "default_ham_action"])
            else:
                r_att = getattr(row, options["html_ui",
                                           "default_unsure_action"])
            setattr(r_att, "checked", 1)

            row.optionalHeadersValues = '' # make way for real list
            for header in options["html_ui", "display_headers"]:
                header = header.lower()
                text = getattr(messageInfo, "%sHeader" % (header,))
                if header == "subject":
                    # Subject is special, because it links to the body.
                    # If the user doesn't display the subject, then there
                    # is no link to the body.
                    h = self.html.reviewRow.linkedHeaderValue.clone()
                    h.text.title = messageInfo.bodySummary
                    h.text.href = "view?key=%s&corpus=%s" % (key, label)
                else:
                    h = self.html.reviewRow.headerValue.clone()
                h.text = text
                row.optionalHeadersValues += h

            # Apart from any message headers, we may also wish to display
            # the message score, and the time the message was received.
            if options["html_ui", "display_score"]:
                if isinstance(messageInfo.score, types.StringTypes):
                    # Presumably either "?" or "Err".
                    row.score_ = messageInfo.score
                else:
                    row.score_ = "%.2f%%" % (messageInfo.score,)
            else:
                del row.score_
            if options["html_ui", "display_received_time"]:
                row.received_ = messageInfo.received
            else:
                del row.received_

            # Many characters can't go in the URL or they cause problems
            # (&, ;, ?, etc).  So we use the hex values for them all.
            subj_list = []
            for c in messageInfo.subjectHeader:
                subj_list.append("%%%s" % (hex(ord(c))[2:],))
            subj = "".join(subj_list)
            row.classify.href="showclues?key=%s&subject=%s" % (key, subj)
            row.tokens.href="showclues?key=%s&subject=%s&tokens=1" % (key, subj)
            setattr(row, 'class', ['stripe_on', 'stripe_off'][stripe]) # Grr!
            setattr(row, 'onMouseOut',
                    ["this.className='stripe_on';",
                     "this.className='stripe_off';"][stripe])
            row = str(row).replace('TYPE', label).replace('KEY', key)
            table += row
            stripe = stripe ^ 1

    def onReview(self, **params):
        """Present a list of message for (re)training."""
        # Train/discard sumbitted messages.
        self._writePreamble("Review")
        id = ''
        numTrained = 0
        numDeferred = 0
        if params.get('go') != _('Refresh'):
            for key, value in params.items():
                if key.startswith('classify:'):
                    old_class, id = key.split(':')[1:3]
                    if value == _('spam'):
                        targetCorpus = state.spamCorpus
                        stats_as_ham = False
                    elif value == _('ham'):
                        targetCorpus = state.hamCorpus
                        stats_as_ham = True
                    elif value == _('discard'):
                        targetCorpus = None
                        try:
                            state.unknownCorpus.removeMessage(\
                                state.unknownCorpus[id])
                        except KeyError:
                            pass  # Must be a reload.
                    else: # defer
                        targetCorpus = None
                        numDeferred += 1
                    if targetCorpus:
                        sourceCorpus = None
                        if state.unknownCorpus.get(id) is not None:
                            sourceCorpus = state.unknownCorpus
                        elif state.hamCorpus.get(id) is not None:
                            sourceCorpus = state.hamCorpus
                        elif state.spamCorpus.get(id) is not None:
                            sourceCorpus = state.spamCorpus
                        if sourceCorpus is not None:
                            try:
                                # fromCache is a fix for sf #851785.
                                # See the comments in Corpus.py
                                targetCorpus.takeMessage(id, sourceCorpus,
                                                         fromCache=True)
                                if numTrained == 0:
                                    self.write(_("<p><b>Training... "))
                                    self.flush()
                                numTrained += 1
                                self.stats.RecordTraining(\
                                  stats_as_ham, old_class=old_class)
                            except KeyError:
                                pass  # Must be a reload.

        # Report on any training, and save the database if there was any.
        if numTrained > 0:
            plural = ''
            if numTrained == 1:
                response = "Trained on one message. "
            else:
                response = "Trained on %d messages. " % (numTrained,)
            self._doSave()
            self.write(response)
            self.write("<br>&nbsp;")

        title = ""
        keys = []
        sourceCorpus = state.unknownCorpus
        # If any messages were deferred, show the same page again.
        if numDeferred > 0:
            start = self._keyToTimestamp(id)

        # Else after submitting a whole page, display the prior page or the
        # next one.  Derive the day of the submitted page from the ID of the
        # last processed message.
        elif id:
            start = self._keyToTimestamp(id)
            unused, unused, prior, unused, next = self._buildReviewKeys(start)
            if prior:
                start = prior
            else:
                start = next

        # Else if they've hit Previous or Next, display that page.
        elif params.get('go') == _('Next day'):
            start = self._keyToTimestamp(params['next'])
        elif params.get('go') == _('Previous day'):
            start = self._keyToTimestamp(params['prior'])

        # Else if an id has been specified, just show that message
        # Else if search criteria have been specified, show the messages
        # that match those criteria.
        elif params.get('find') is not None:
            prior = next = 0
            keys = Set()        # so we don't end up with duplicates
            push = keys.add
            try:
                max_results = int(params['max_results'])
            except ValueError:
                max_results = 1
            key = params['find']
            if params.has_key('ignore_case'):
                ic = True
            else:
                ic = False
            error = False
            if key == "":
                error = True
                page = _("<p>You must enter a search string.</p>")
            else:
                if len(keys) < max_results and \
                   params.has_key('id'):
                    if state.unknownCorpus.get(key):
                        push((key, state.unknownCorpus))
                    elif state.hamCorpus.get(key):
                        push((key, state.hamCorpus))
                    elif state.spamCorpus.get(key):
                        push((key, state.spamCorpus))
                if params.has_key('subject') or params.has_key('body') or \
                   params.has_key('headers'):
                    # This is an expensive operation, so let the user know
                    # that something is happening.
                    self.write(_('<p>Searching...</p>'))
                    for corp in [state.unknownCorpus, state.hamCorpus,
                                   state.spamCorpus]:
                        for k in corp.keys():
                            if len(keys) >= max_results:
                                break
                            msg = corp[k]
                            msg.load()
                            if params.has_key('subject'):
                                subj = str(msg['Subject'])
                                if self._contains(subj, key, ic):
                                    push((k, corp))
                            if params.has_key('body'):
                                # For [ 906581 ] Assertion failed in search
                                # subject.  Can the headers be a non-string?
                                msg_body = msg.as_string()
                                msg_body = msg_body[msg_body.index('\r\n\r\n'):]
                                if self._contains(msg_body, key, ic):
                                    push((k, corp))
                            if params.has_key('headers'):
                                for nm, val in msg.items():
                                    # For [ 906581 ] Assertion failed in
                                    # search subject.  Can the headers be
                                    # a non-string?
                                    nm = str(nm)
                                    val = str(val)
                                    if self._contains(nm, key, ic) or \
                                       self._contains(val, key, ic):
                                        push((k, corp))
                if len(keys):
                    if len(keys) == 1:
                        title = _("Found message")
                    else:                      
                        title = _("Found messages")
                    keys = list(keys)
                else:
                    page = _("<p>Could not find any matching messages. " \
                             "Maybe they expired?</p>")
                    title = _("Did not find message")
                    box = self._buildBox(title, 'status.gif', page)
                    self.write(box)
                    self.write(self._buildBox(_('Find message'),
                                              'query.gif',
                                              self.html.findMessage))
                    self._writePostamble()
                    return

        # Else show the most recent day's page, as decided by _buildReviewKeys.
        else:
            start = 0

        # Build the lists of messages: spams, hams and unsure.
        if len(keys) == 0:
            keys, date, prior, this, next = self._buildReviewKeys(start)
        keyedMessageInfo = {options["Headers", "header_unsure_string"]: [],
                            options["Headers", "header_ham_string"]: [],