dibbler.py

用python实现的邮件过滤器

           (or a `socketMap` argument for pure asyncore listeners).  The
           incoming socket will be prepended to this list, and passed as the
           first argument.  See `HTTPServer` for an example.

         o socketMap: Optional.  The asyncore socket map to use.  If you're
           using a `Dibbler.Context`, pass context._map.

        See `HTTPServer` for an example `Listener` - it's a good deal smaller
        than this description!"""

        asyncore.dispatcher.__init__(self, map=socketMap)
        self.socketMap = socketMap
        self.factory = factory
        self.factoryArgs = factoryArgs
        s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        s.setblocking(False)
        self.set_socket(s, self.socketMap)
        self.set_reuse_addr()
        if type(port) != type(()):
            port = ('', port)
        self.bind(port)
        self.listen(5)

    def handle_accept(self):
        """Asyncore override."""
        # If an incoming connection is instantly reset, eg. by following a
        # link in the web interface then instantly following another one or
        # hitting stop, handle_accept() will be triggered but accept() will
        # return None.
        result = self.accept()
        if result:
            clientSocket, clientAddress = result
            args = [clientSocket] + list(self.factoryArgs)
            self.factory(*args)


class HTTPServer(Listener):
    """A web server with which you can register `HTTPPlugin`s to serve up
    your content - see `HTTPPlugin` for detailed documentation and examples.

    `port` specifies the TCP/IP (address, port) on which to run, defaulting
    to ('', 80).

    `context` optionally specifies a `Dibbler.Context` for the server.
    """

    NO_AUTHENTICATION     = "None"
    BASIC_AUTHENTICATION  = "Basic"
    DIGEST_AUTHENTICATION = "Digest"

    def __init__(self, port=('', 80), context=_defaultContext):
        """Create an `HTTPServer` for the given port."""
        Listener.__init__(self, port, _HTTPHandler,
                          (self, context), context._map)
        self._plugins = []
        try:
            context._HTTPPort = port[1]
        except TypeError:
            context._HTTPPort = port

    def register(self, *plugins):
        """Registers one or more `HTTPPlugin`-derived objects with the
        server."""
        for plugin in plugins:
            self._plugins.append(plugin)

    def requestAuthenticationMode(self):
        """Override: HTTP Authentication. It should return a value among
        NO_AUTHENTICATION, BASIC_AUTHENTICATION and DIGEST_AUTHENTICATION.
        The two last values will force HTTP authentication respectively
        through Base64 and MD5 encodings."""
        return self.NO_AUTHENTICATION

    def isValidUser(self, name, password):
        """Override: Return True for authorized logins."""
        return True

    def getPasswordForUser(self, name):
        """Override: Return the password associated to the specified user
        name."""
        return ''

    def getRealm(self):
        """Override: Specify the HTTP authentication realm."""
        return "Dibbler application server"

    def getCancelMessage(self):
        """Override: Specify the cancel message for an HTTP Authentication."""
        return "You must log in."


class _HTTPHandler(BrighterAsyncChat):
    """This is a helper for the HTTP server class - one of these is created
    for each incoming request, and does the job of decoding the HTTP traffic
    and driving the plugins."""

    # RE to extract option="value" fields from
    # digest auth login field
    _login_splitter = re.compile('([a-zA-Z]+)=(".*?"|.*?),?')

    def __init__(self, clientSocket, server, context):
        # Grumble: asynchat.__init__ doesn't take a 'map' argument,
        # hence the two-stage construction.
        BrighterAsyncChat.__init__(self, map=context._map)
        BrighterAsyncChat.set_socket(self, clientSocket, context._map)
        self._context = context
        self._server = server
        self._request = ''
        self.set_terminator('\r\n\r\n')

        # Because a methlet is likely to call `writeOKHeaders` before doing
        # anything else, an unexpected exception won't send back a 500, which
        # is poor.  So we buffer any sent headers until either a plain `write`
        # happens or the methlet returns.
        self._bufferedHeaders = []
        self._headersWritten = False

        # Tell the plugins about the connection, letting them veto it.
        for plugin in self._server._plugins:
            if not plugin.onIncomingConnection(clientSocket):
                self.close()

    def collect_incoming_data(self, data):
        """Asynchat override."""
        self._request = self._request + data

    def found_terminator(self):
        """Asynchat override."""
        # Parse the HTTP request.
        requestLine, headers = (self._request+'\r\n').split('\r\n', 1)
        try:
            method, url, version = requestLine.strip().split()
        except ValueError:
            self.writeError(400, "Malformed request: '%s'" % requestLine)
            self.close_when_done()
            return

        # Parse the URL, and deal with POST vs. GET requests.
        method = method.upper()
        unused, unused, path, unused, query, unused = urlparse.urlparse(url)
        cgiParams = cgi.parse_qs(query, keep_blank_values=True)
        if self.get_terminator() == '\r\n\r\n' and method == 'POST':
            # We need to read the body - set a numeric async_chat terminator
            # equal to the Content-Length.
            match = re.search(r'(?i)content-length:\s*(\d+)', headers)
            contentLength = int(match.group(1))
            if contentLength > 0:
                self.set_terminator(contentLength)
                self._request = self._request + '\r\n\r\n'
                return

        # Have we just read the body of a POSTed request?  Decode the body,
        # which will contain parameters and possibly uploaded files.
        if type(self.get_terminator()) is type(1):
            self.set_terminator('\r\n\r\n')
            body = self._request.split('\r\n\r\n', 1)[1]
            match = re.search(r'(?i)content-type:\s*([^\r\n]+)', headers)
            contentTypeHeader = match.group(1)
            contentType, pdict = cgi.parse_header(contentTypeHeader)
            if contentType == 'multipart/form-data':
                # multipart/form-data - probably a file upload.
                bodyFile = StringIO.StringIO(body)
                cgiParams.update(cgi.parse_multipart(bodyFile, pdict))
            else:
                # A normal x-www-form-urlencoded.
                cgiParams.update(cgi.parse_qs(body, keep_blank_values=True))

        # Convert the cgi params into a simple dictionary.
        params = {}
        for name, value in cgiParams.iteritems():
            params[name] = value[0]

        # Parse the headers.
        headersRegex = re.compile('([^:]*):\s*(.*)')
        headersDict = dict([headersRegex.match(line).groups(2)
                           for line in headers.split('\r\n')
                           if headersRegex.match(line)])

        # HTTP Basic/Digest Authentication support.
        serverAuthMode = self._server.requestAuthenticationMode()
        if serverAuthMode != HTTPServer.NO_AUTHENTICATION:
            # The server wants us to authenticate the user.
            authResult = False
            authHeader = headersDict.get('Authorization')
            if authHeader:
                authMatch = re.search('(\w+)\s+(.*)', authHeader)
                authenticationMode, login = authMatch.groups()

                if authenticationMode == HTTPServer.BASIC_AUTHENTICATION:
                    authResult = self._basicAuthentication(login)
                elif authenticationMode == HTTPServer.DIGEST_AUTHENTICATION:
                    authResult = self._digestAuthentication(login, method)
                else:
                    print >>sys.stdout, "Unknown mode: %s" % authenticationMode

            if not authResult:
                self.writeUnauthorizedAccess(serverAuthMode)

        # Find and call the methlet.  '/eggs.gif' becomes 'onEggsGif'.
        if path == '/':
            path = '/Home'
        pieces = path[1:].split('.')
        name = 'on' + ''.join([piece.capitalize() for piece in pieces])
        for plugin in self._server._plugins:
            if hasattr(plugin, name):
                # The plugin's APIs (`write`, etc) reflect back to us via
                # `plugin._handler`.
                plugin._handler = self
                try:
                    # Call the methlet.
                    getattr(plugin, name)(**params)
                    if self._bufferedHeaders:
                        # The methlet returned without writing anything other
                        # than headers.  This isn't unreasonable - it might
                        # have written a 302 or something.  Flush the buffered
                        # headers
                        self.write(None)
                except:
                    # The methlet raised an exception - send the traceback to
                    # the browser, unless it's SystemExit in which case we let
                    # it go.
                    eType, eValue, eTrace = sys.exc_info()
                    if eType == SystemExit:
                        # Close all the listeners so that no further incoming
                        # connections appear.
                        contextMap = self._context._map
                        for dispatcher in contextMap.values():
                            if isinstance(dispatcher, Listener):
                                dispatcher.close()

                        # Let any existing connections close down first.  This
                        # has happened when all we have left are _HTTPHandlers
                        # (this one plus any others that are using keep-alive;
                        # none of the others can be actually doing any work
                        # because *we're* the one doing the work).
                        def isProtected(dispatcher):
                            return not isinstance(dispatcher, _HTTPHandler)

                        while len(filter(isProtected, contextMap.values())) > 0:
                            asyncore.poll(timeout=1, map=contextMap)

                        raise SystemExit

                    message = """<h3>500 Server error</h3><pre>%s</pre>"""
                    details = traceback.format_exception(eType, eValue, eTrace)
                    details = '\n'.join(details)
                    self.writeError(500, message % cgi.escape(details))
                plugin._handler = None
                break
        else:
            self.onUnknown(path, params)

        # `close_when_done` and `Connection: close` ensure that we don't
        # support keep-alives or pipelining.  There are problems with some
        # browsers, for instance with extra characters being appended after
        # the body of a POSTed request.
        self.close_when_done()

    def onUnknown(self, path, params):
        """Handler for unknown URLs.  Returns a 404 page."""
        self.writeError(404, "Not found: '%s'" % path)

    def writeOKHeaders(self, contentType, extraHeaders={}):
        """Reflected from `HTTPPlugin`s."""
        # Buffer the headers until there's a `write`, in case an error occurs.