# -*- Mode: Python; tab-width: 4 -*-
# Id: asynchat.py,v 2.26 2000/09/07 22:29:26 rushing Exp
# Author: Sam Rushing <rushing@nightmare.com>
# ======================================================================
# Copyright 1996 by Sam Rushing
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Sam
# Rushing not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# SAM RUSHING DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL SAM RUSHING BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
# ======================================================================
r"""A class supporting chat-style (command/response) protocols.
This class adds support for 'chat' style protocols - where one side
sends a 'command', and the other sends a response (examples would be
the common internet protocols - smtp, nntp, ftp, etc..).
The handle_read() method looks at the input stream for the current
'terminator' (usually '\r\n' for single-line responses, '\r\n.\r\n'
for multi-line output), calling self.found_terminator() on its
Say you build an async nntp client using this class. At the start
of the connection, you'll have self.terminator set to '\r\n', in
order to process the single-line greeting. Just before issuing a
'LIST' command you'll set it to '\r\n.\r\n'. The output of the LIST
command will be accumulated (using your own 'collect_incoming_data'
method) up to the terminator, and then control will be returned to
you - by calling your self.found_terminator() method.
from collections import deque
class async_chat(asyncore.dispatcher):
"""This is an abstract class. You must derive from this class, and add
the two methods collect_incoming_data() and found_terminator()"""
# these are overridable defaults
ac_in_buffer_size = 65536
ac_out_buffer_size = 65536
# we don't want to enable the use of encoding by default, because that is a
# sign of an application bug that we don't want to pass silently
def __init__(self, sock=None, map=None):
# for string terminator matching
# we use a list here rather than io.BytesIO for a few reasons...
# del lst[:] is faster than bio.truncate(0)
# lst = [] is faster than bio.truncate(0)
# we toss the use of the "simple producer" and replace it with
# a pure deque, which the original fifo was a wrapping of
self.producer_fifo = deque()
asyncore.dispatcher.__init__(self, sock, map)
def collect_incoming_data(self, data):
raise NotImplementedError("must be implemented in subclass")
def _collect_incoming_data(self, data):
self.incoming.append(data)
d = b''.join(self.incoming)
def found_terminator(self):
raise NotImplementedError("must be implemented in subclass")
def set_terminator(self, term):
"""Set the input delimiter.
Can be a fixed string of any length, an integer, or None.
if isinstance(term, str) and self.use_encoding:
term = bytes(term, self.encoding)
elif isinstance(term, int) and term < 0:
raise ValueError('the number of received bytes must be positive')
def get_terminator(self):
# grab some more data from the socket,
# throw it to the collector method,
# check for the terminator,
# if found, transition to the next state.
data = self.recv(self.ac_in_buffer_size)
if isinstance(data, str) and self.use_encoding:
data = bytes(str, self.encoding)
self.ac_in_buffer = self.ac_in_buffer + data
# Continue to search for self.terminator in self.ac_in_buffer,
# while calling self.collect_incoming_data. The while loop
# is necessary because we might read several data+terminator
# combos with a single recv(4096).
lb = len(self.ac_in_buffer)
terminator = self.get_terminator()
# no terminator, collect it all
self.collect_incoming_data(self.ac_in_buffer)
elif isinstance(terminator, int):
self.collect_incoming_data(self.ac_in_buffer)
self.terminator = self.terminator - lb
self.collect_incoming_data(self.ac_in_buffer[:n])
self.ac_in_buffer = self.ac_in_buffer[n:]
# 1) end of buffer matches terminator exactly:
# collect data, transition
# 2) end of buffer matches some prefix:
# collect data to the prefix
# 3) end of buffer does not match any prefix:
terminator_len = len(terminator)
index = self.ac_in_buffer.find(terminator)
# we found the terminator
# don't bother reporting the empty string
# (source of subtle bugs)
self.collect_incoming_data(self.ac_in_buffer[:index])
self.ac_in_buffer = self.ac_in_buffer[index+terminator_len:]
# This does the Right Thing if the terminator
# check for a prefix of the terminator
index = find_prefix_at_end(self.ac_in_buffer, terminator)
# we found a prefix, collect up to the prefix
self.collect_incoming_data(self.ac_in_buffer[:-index])
self.ac_in_buffer = self.ac_in_buffer[-index:]
# no prefix, collect it all
self.collect_incoming_data(self.ac_in_buffer)
if not isinstance(data, (bytes, bytearray, memoryview)):
raise TypeError('data argument must be byte-ish (%r)',
sabs = self.ac_out_buffer_size
for i in range(0, len(data), sabs):
self.producer_fifo.append(data[i:i+sabs])
self.producer_fifo.append(data)
def push_with_producer(self, producer):
self.producer_fifo.append(producer)
"predicate for inclusion in the readable for select()"
# cannot use the old predicate, it violates the claim of the
# return (len(self.ac_in_buffer) <= self.ac_in_buffer_size)
"predicate for inclusion in the writable for select()"
return self.producer_fifo or (not self.connected)
def close_when_done(self):
"automatically close this channel once the outgoing queue is empty"
self.producer_fifo.append(None)
while self.producer_fifo and self.connected:
first = self.producer_fifo[0]
# handle empty string/buffer or None entry
del self.producer_fifo[0]
# handle classic producer behavior
obs = self.ac_out_buffer_size
self.producer_fifo.appendleft(data)
del self.producer_fifo[0]
if isinstance(data, str) and self.use_encoding:
data = bytes(data, self.encoding)
num_sent = self.send(data)
if num_sent < len(data) or obs < len(first):
self.producer_fifo[0] = first[num_sent:]
del self.producer_fifo[0]
# we tried to send some actual data
def discard_buffers(self):
self.producer_fifo.clear()
def __init__(self, data, buffer_size=512):
self.buffer_size = buffer_size
if len(self.data) > self.buffer_size:
result = self.data[:self.buffer_size]
self.data = self.data[self.buffer_size:]
# Given 'haystack', see if any prefix of 'needle' is at its end. This
# assumes an exact match has already been checked. Return the number of
# f_p_a_e("qwerty\r", "\r\n") => 1
# f_p_a_e("qwertydkjf", "\r\n") => 0
# f_p_a_e("qwerty\r\n", "\r\n") => <undefined>
# this could maybe be made faster with a computed regex?
# [answer: no; circa Python-2.0, Jan 2001]
def find_prefix_at_end(haystack, needle):
while l and not haystack.endswith(needle[:l]):