msgstore.py

用python实现的邮件过滤器

        # Problem #2:  Outlook decodes quoted-printable and base64 on its
        # own, but leaves any Content-Transfer-Encoding line in the headers.
        # This can cause the email pkg to try to decode the text again,
        # with unpleasant (but rarely fatal) results.  If we strip that
        # header too, no problem -- although the fact that a msg was
        # encoded in base64 is usually a good spam clue, and we miss that.
        #
        # Short course:  we either have to synthesize non-insane MIME
        # structure, or eliminate all evidence of original MIME structure.
        # Since we don't have a way to the former, by default this function
        # does the latter.
        import email
        text = self._GetMessageText()
        try:
            try:
                msg = email.message_from_string(text)
            except email.Errors.BoundaryError:
                # In case this is the
                #    "No terminating boundary and no trailing empty line"
                # flavor of BoundaryError, we can supply a trailing empty
                # line to shut it up.  It's certainly ill-formed MIME, and
                # probably spam.  We don't care about the exact MIME
                # structure, just the words it contains, so no harm and
                # much good in trying to suppress this error.
                try:
                    msg = email.message_from_string(text + "\n\n")
                except email.Errors.BoundaryError:
                    msg = None
            except email.Errors.HeaderParseError:
                # This exception can come from parsing the header *or* the
                # body of a mime message.
                msg = None
            # But even this doesn't get *everything*.  We can still see:
            #  "multipart message with no defined boundary" or the
            # HeaderParseError above.  Time to get brutal - hack out
            # the Content-Type header, so we see it as plain text.
            if msg is None:
                butcher_pos = text.lower().find("\ncontent-type: ")
                if butcher_pos < 0:
                    # This error just just gunna get caught below anyway
                    raise RuntimeError(
                        "email package croaked with a MIME related error, but "
                        "there appears to be no 'Content-Type' header")
                # Put it back together, skipping the original "\n" but
                # leaving the header leaving "\nSpamBayes-Content-Type: "
                butchered = text[:butcher_pos] + "\nSpamBayes-" + \
                            text[butcher_pos+1:] + "\n\n"
                msg = email.message_from_string(butchered)
        except:
            print "FAILED to create email.message from: ", `text`
            raise

        if strip_mime_headers:
            if msg.has_key('content-type'):
                del msg['content-type']
            if msg.has_key('content-transfer-encoding'):
                del msg['content-transfer-encoding']

        return msg

    def SetField(self, prop, val):
        # Future optimization note - from GetIDsFromNames doco
        # Name-to-identifier mapping is represented by an object's
        # PR_MAPPING_SIGNATURE property. PR_MAPPING_SIGNATURE contains
        # a MAPIUID structure that indicates the service provider
        # responsible for the object. If the PR_MAPPING_SIGNATURE
        # property is the same for two objects, assume that these
        # objects use the same name-to-identifier mapping.
        # [MarkH: MAPIUID objects are supported and hashable]

        # XXX If the SpamProb (Hammie, whatever) property is passed in as an
        # XXX int, Outlook displays the field as all blanks, and sorting on
        # XXX it doesn't do anything, etc.  I don't know why.  Since I'm
        # XXX running Python 2.2.2, the _MapiTypeMap above confuses ints
        # XXX with bools, but the problem persists even if I comment out the
        # XXX PT_BOOLEAN entry from that dict.  Dumping in prints below show
        # XXX that type_tag is 3 then, and that matches the defn of PT_I4 in
        # XXX my system header files.
        # XXX Later:  This works after all, but the field shows up as all
        # XXX blanks unless I *first* modify the view (like Messages) in
        # XXX Outlook to define a custom Integer field of the same name.
        self._EnsureObject()
        try:
            if type(prop) != type(0):
                props = ( (mapi.PS_PUBLIC_STRINGS, prop), )
                propIds = self.mapi_object.GetIDsFromNames(props, mapi.MAPI_CREATE)
                type_tag = _MapiTypeMap.get(type(val))
                if type_tag is None:
                    raise ValueError, "Don't know what to do with '%r' ('%s')" % (
                                         val, type(val))
                prop = PROP_TAG(type_tag, PROP_ID(propIds[0]))
            help_test_suite("MAPIMsgStoreMsg.SetField")
            if val is None:
                # Delete the property
                self.mapi_object.DeleteProps((prop,))
            else:
                self.mapi_object.SetProps(((prop,val),))
            self.dirty = True
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def GetField(self, prop):
        # xxx - still raise_errors?
        self._EnsureObject()
        if type(prop) != type(0):
            props = ( (mapi.PS_PUBLIC_STRINGS, prop), )
            prop = self.mapi_object.GetIDsFromNames(props, 0)[0]
            if PROP_TYPE(prop) == PT_ERROR: # No such property
                return None
            prop = PROP_TAG( PT_UNSPECIFIED, PROP_ID(prop))
        try:
            hr, props = self.mapi_object.GetProps((prop,), 0)
            ((tag, val), ) = props
            if PROP_TYPE(tag) == PT_ERROR:
                if val == mapi.MAPI_E_NOT_ENOUGH_MEMORY:
                    # Too big for simple properties - get via a stream
                    return GetPropFromStream(self.mapi_object, prop)
                return None
            return val
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def GetReadState(self):
        val = self.GetField(PR_MESSAGE_FLAGS)
        return (val&MSGFLAG_READ) != 0

    def SetReadState(self, is_read):
        try:
            self._EnsureObject()
            # always try and clear any pending delivery reports of read/unread
            help_test_suite("MAPIMsgStoreMsg.SetReadState")
            if is_read:
                self.mapi_object.SetReadFlag(USE_DEFERRED_ERRORS|SUPPRESS_RECEIPT)
            else:
                self.mapi_object.SetReadFlag(USE_DEFERRED_ERRORS|CLEAR_READ_FLAG)
            if __debug__:
                if self.GetReadState() != is_read:
                    print "MAPI SetReadState appears to have failed to change the message state"
                    print "Requested set to %s but the MAPI field after was %r" % \
                          (is_read, self.GetField(PR_MESSAGE_FLAGS))
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def Save(self):
        assert self.dirty, "asking me to save a clean message!"
        # It seems that *not* specifying mapi.MAPI_DEFERRED_ERRORS solves a lot
        # problems!  So we don't!
        try:
            help_test_suite("MAPIMsgStoreMsg.Save")
            self.mapi_object.SaveChanges(mapi.KEEP_OPEN_READWRITE)
            self.dirty = False
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def _DoCopyMove(self, folder, isMove):
        assert not self.dirty, \
               "asking me to move a dirty message - later saves will fail!"
        try:
            dest_folder = self.msgstore._OpenEntry(folder.id)
            source_folder = self.msgstore._OpenEntry(self.folder_id)
            flags = 0
            if isMove: flags |= MESSAGE_MOVE
            eid = self.id[1]
            help_test_suite("MAPIMsgStoreMsg._DoCopyMove")
            source_folder.CopyMessages((eid,),
                                        None,
                                        dest_folder,
                                        0,
                                        None,
                                        flags)
            # At this stage, I think we have lost meaningful ID etc values
            # Set everything to None to make it clearer what is wrong should
            # this become an issue.  We would need to re-fetch the eid of
            # the item, and set the store_id to the dest folder.
            self.id = None
            self.folder_id = None
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def MoveTo(self, folder):
        self._DoCopyMove(folder, True)

    def CopyTo(self, folder):
        self._DoCopyMove(folder, False)

    # Functions to perform operations, but report the error (ONCE!) to the
    # user.  Any errors are re-raised so the caller can degrade gracefully if
    # necessary.
    # XXX - not too happy with these - they should go, and the caller should
    # handle (especially now that we work exclusively with exceptions from
    # this module.
    def MoveToReportingError(self, manager, folder):
        try:
            self.MoveTo(folder)
        except MsgStoreException, details:
            ReportMAPIError(manager, _("Moving a message"),
                            details.mapi_exception)
    def CopyToReportingError(self, manager, folder):
        try:
            self.MoveTo(folder)
        except MsgStoreException, details:
            ReportMAPIError(manager, _("Copying a message"),
                            details.mapi_exception)

    def GetFolder(self):
        # return a folder object with the parent, or None
        folder_id = (mapi.HexFromBin(self.folder_id[0]),
                     mapi.HexFromBin(self.folder_id[1]))
        return self.msgstore.GetFolder(folder_id)

    def RememberMessageCurrentFolder(self):
        self._EnsureObject()
        try:
            folder = self.GetFolder()
            # Also save this information in our messageinfo database, which
            # means that restoring should work even with IMAP.
            self.original_folder = folder.id[0], folder.id[1]
            props = ( (mapi.PS_PUBLIC_STRINGS, "SpamBayesOriginalFolderStoreID"),
                      (mapi.PS_PUBLIC_STRINGS, "SpamBayesOriginalFolderID")
                      )
            resolve_ids = self.mapi_object.GetIDsFromNames(props, mapi.MAPI_CREATE)
            prop_ids = PROP_TAG( PT_BINARY, PROP_ID(resolve_ids[0])), \
                       PROP_TAG( PT_BINARY, PROP_ID(resolve_ids[1]))

            prop_tuples = (prop_ids[0],folder.id[0]), (prop_ids[1],folder.id[1])
            self.mapi_object.SetProps(prop_tuples)
            self.dirty = True
        except pythoncom.com_error, details:
            raise MsgStoreExceptionFromCOMException(details)

    def GetRememberedFolder(self):
        props = ( (mapi.PS_PUBLIC_STRINGS, "SpamBayesOriginalFolderStoreID"),
                  (mapi.PS_PUBLIC_STRINGS, "SpamBayesOriginalFolderID")
                  )
        try:
            self._EnsureObject()
            resolve_ids = self.mapi_object.GetIDsFromNames(props, mapi.MAPI_CREATE)
            prop_ids = PROP_TAG( PT_BINARY, PROP_ID(resolve_ids[0])), \
                       PROP_TAG( PT_BINARY, PROP_ID(resolve_ids[1]))
            hr, data = self.mapi_object.GetProps(prop_ids,0)
            if hr != 0:
                return None
            (store_tag, store_id), (eid_tag, eid) = data
            folder_id = mapi.HexFromBin(store_id), mapi.HexFromBin(eid)
            help_test_suite("MAPIMsgStoreMsg.GetRememberedFolder")
            return self.msgstore.GetFolder(folder_id)
        except:
            # Try to get it from the message info database, if possible
            if self.original_folder:
                return self.msgstore.GetFolder(self.original_folder)
            print "Error locating origin of message", self
            return None

def test():
    from win32com.client import Dispatch
    outlook = Dispatch("Outlook.Application")
    inbox = outlook.Session.GetDefaultFolder(constants.olFolderInbox)
    folder_id = inbox.Parent.StoreID, inbox.EntryID
    store = MAPIMsgStore()
    for folder in store.GetFolderGenerator([folder_id,], True):
        print folder
        for msg in folder.GetMessageGenerator():
            print msg
    store.Close()

if __name__=='__main__':
    test()