added more of the medusa distribution as needed.

ZServer/medusa/counter.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+# It is tempting to add an __int__ method to this class, but it's not
+# a good idea.  This class tries to gracefully handle integer
+# overflow, and to hide this detail from both the programmer and the
+# user.  Note that the __str__ method can be relied on for printing out
+# the value of a counter:
+#
+# >>> print 'Total Client: %s' % self.total_clients
+#
+# If you need to do arithmetic with the value, then use the 'as_long'
+# method, the use of long arithmetic is a reminder that the counter
+# will overflow.
+
+class counter:
+	"general-purpose counter"
+
+	def __init__ (self, initial_value=0):
+		self.value = initial_value
+	
+	def increment (self, delta=1):
+		result = self.value
+		try:
+			self.value = self.value + delta
+		except OverflowError:
+			self.value = long(self.value) + delta
+		return result
+
+	def decrement (self, delta=1):
+		result = self.value
+		try:
+			self.value = self.value - delta
+		except OverflowError:
+			self.value = long(self.value) - delta
+		return result
+
+	def as_long (self):
+		return long(self.value)
+
+	def __nonzero__ (self):
+		return self.value != 0
+
+	def __repr__ (self):
+		return '<counter value=%s at %x>' % (self.value, id(self))
+
+	def __str__ (self):
+		return str(long(self.value))[:-1]

ZServer/medusa/default_handler.py

+# -*- Mode: Python; tab-width: 4 -*-
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#	Copyright 1997 by Sam Rushing
+#						 All Rights Reserved.
+#
+# This software is provided free for non-commercial use.  If you are
+# interested in using this software in a commercial context, or in
+# purchasing support, please contact the author.
+
+RCS_ID = '$Id: default_handler.py,v 1.1 1999/01/09 03:17:31 amos Exp $'
+
+# standard python modules
+import os
+import regex
+import posixpath
+import stat
+import string
+import time
+
+# medusa modules
+import http_date
+import http_server
+import mime_type_table
+import status_handler
+import producers
+
+# from <lib/urllib.py>
+_quoteprog = regex.compile('%[0-9a-fA-F][0-9a-fA-F]')
+def unquote(s):
+	i = 0
+	n = len(s)
+	res = []
+	while 0 <= i < n:
+		j = _quoteprog.search(s, i)
+		if j < 0:
+			res.append(s[i:])
+			break
+		res.append(s[i:j] + chr(string.atoi(s[j+1:j+3], 16)))
+		i = j+3
+	return string.join (res, '')
+
+# split a uri
+# <path>;<params>?<query>#<fragment>
+path_regex = regex.compile (
+#        path        params        query       fragment
+	'\\([^;?#]*\\)\\(;[^?#]*\\)?\\(\\?[^#]*\)?\(#.*\)?'
+	)
+
+def split_path (path):
+	if path_regex.match (path) != len(path):
+		raise ValueError, "bad path"
+	else:
+		return map (lambda i,r=path_regex: r.group(i), range(1,5))
+
+# This is the 'default' handler.  it implements the base set of
+# features expected of a simple file-delivering HTTP server.  file
+# services are provided through a 'filesystem' object, the very same
+# one used by the FTP server.
+#
+# You can replace or modify this handler if you want a non-standard
+# HTTP server.  You can also derive your own handler classes from
+# it.
+#
+# support for handling POST requests is available in the derived
+# class <default_with_post_handler>, defined below.
+#
+
+from counter import counter
+
+class default_handler:
+
+	valid_commands = ['get', 'head']
+
+	IDENT = 'Default HTTP Request Handler'
+
+	# Pathnames that are tried when a URI resolves to a directory name
+	directory_defaults = [
+		'index.html',
+		'default.html'
+		]
+
+	default_file_producer = producers.file_producer
+
+	def __init__ (self, filesystem):
+		self.filesystem = filesystem
+		# count total hits
+		self.hit_counter = counter()
+		# count file deliveries
+		self.file_counter = counter()
+		# count cache hits
+		self.cache_counter = counter()
+
+	hit_counter = 0
+
+	def __repr__ (self):
+		return '<%s (%s hits) at %x>' % (
+			self.IDENT,
+			self.hit_counter,
+			id (self)
+			)
+
+	# always match, since this is a default
+	def match (self, request):
+		return 1
+
+	# handle a file request, with caching.
+
+	def handle_request (self, request):
+
+		if request.command not in self.valid_commands:
+			request.error (400) # bad request
+			return
+
+		self.hit_counter.increment()
+
+		[path, params, query, fragment] = split_path (request.uri)
+
+		# unquote path if necessary (thanks to Skip Montaro for pointing
+		# out that we must unquote in piecemeal fashion).
+		if '%' in path:
+			path = unquote (path)
+
+		# strip off all leading slashes
+		while path and path[0] == '/':
+			path = path[1:]
+
+		if self.filesystem.isdir (path):
+			if path and path[-1] != '/':
+				request['Location'] = 'http://%s/%s/' % (
+					request.channel.server.server_name,
+					path
+					)
+				request.error (301)
+				return
+
+			# we could also generate a directory listing here,
+			# may want to move this into another method for that
+			# purpose
+			found = 0
+			if path and path[-1] != '/':
+				path = path + '/'
+			for default in self.directory_defaults:
+				p = path + default
+				if self.filesystem.isfile (p):
+					path = p
+					found = 1
+					break
+			if not found:
+				request.error (404) # Not Found 
+				return
+
+		elif not self.filesystem.isfile (path):
+			request.error (404) # Not Found
+			return
+
+		file_length = self.filesystem.stat (path)[stat.ST_SIZE]
+
+		ims = get_header (IF_MODIFIED_SINCE, request.header)
+
+		length_match = 1
+		if ims:
+			length = IF_MODIFIED_SINCE.group(4)
+			if length:
+				try:
+					length = string.atoi (length)
+					if length != file_length:
+						length_match = 0
+				except:
+					pass
+
+		ims_date = 0
+
+		if ims:
+			ims_date = http_date.parse_http_date (ims)
+
+		try:
+			mtime = self.filesystem.stat (path)[stat.ST_MTIME]
+		except:
+			request.error (404)
+			return
+
+		if length_match and ims_date:
+			if mtime <= ims_date:
+				request.reply_code = 304
+				request.done()
+				self.cache_counter.increment()
+				return
+		try:
+			file = self.filesystem.open (path, 'rb')
+		except IOError:
+			request.error (404)
+			return
+
+		request['Last-Modified'] = http_date.build_http_date (mtime)
+		request['Content-Length'] = file_length
+		self.set_content_type (path, request)
+
+		if request.command == 'get':
+			request.push (self.default_file_producer (file))
+
+		self.file_counter.increment()
+		request.done()
+
+	def set_content_type (self, path, request):
+		ext = get_extension (path)
+		if mime_type_table.content_type_map.has_key (ext):
+			request['Content-Type'] = mime_type_table.content_type_map[ext]
+		else:
+			# TODO: test a chunk off the front of the file for 8-bit
+			# characters, and use application/octet-stream instead.
+			request['Content-Type'] = 'text/plain'
+
+	def status (self):
+		return producers.simple_producer (
+			'<li>%s' % status_handler.html_repr (self)
+			+ '<ul>'
+			+ '  <li><b>Total Hits:</b> %s'			% self.hit_counter
+			+ '  <li><b>Files Delivered:</b> %s'	% self.file_counter
+			+ '  <li><b>Cache Hits:</b> %s'			% self.cache_counter
+			+ '</ul>'
+			)
+
+ACCEPT = regex.compile ('Accept: \(.*\)', regex.casefold)
+
+# HTTP/1.0 doesn't say anything about the "; length=nnnn" addition
+# to this header.  I suppose it's purpose is to avoid the overhead
+# of parsing dates...
+IF_MODIFIED_SINCE = regex.compile (
+	'If-Modified-Since: \([^;]+\)\(\(; length=\([0-9]+\)$\)\|$\)',
+	regex.casefold
+	)
+
+USER_AGENT = regex.compile ('User-Agent: \(.*\)', regex.casefold)
+
+boundary_chars = "A-Za-z0-9'()+_,./:=?-"
+
+CONTENT_TYPE = regex.compile (
+	'Content-Type: \([^;]+\)\(\(; boundary=\([%s]+\)$\)\|$\)' % boundary_chars,
+	regex.casefold
+	)
+
+get_header = http_server.get_header
+
+def get_extension (path):
+	dirsep = string.rfind (path, '/')
+	dotsep = string.rfind (path, '.')
+	if dotsep > dirsep:
+		return path[dotsep+1:]
+	else:
+		return ''

ZServer/medusa/http_date.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+import regex
+import string
+import time
+
+def concat (*args):
+	return string.joinfields (args, '')
+
+def join (seq, field=' '):
+	return string.joinfields (seq, field)
+
+def group (s):
+	return '\\(' + s + '\\)'
+
+short_days = ['sun','mon','tue','wed','thu','fri','sat']
+long_days = ['sunday','monday','tuesday','wednesday','thursday','friday','saturday']
+
+short_day_reg = group (join (short_days, '\\|'))
+long_day_reg = group (join (long_days, '\\|'))
+
+daymap = {}
+for i in range(7):
+	daymap[short_days[i]] = i
+	daymap[long_days[i]] = i
+
+hms_reg = join (3 * [group('[0-9][0-9]')], ':')
+
+months = ['jan','feb','mar','apr','may','jun','jul','aug','sep','oct','nov','dec']
+
+monmap = {}
+for i in range(12):
+	monmap[months[i]] = i+1
+
+months_reg = group (join (months, '\\|'))
+
+# From draft-ietf-http-v11-spec-07.txt/3.3.1
+#       Sun, 06 Nov 1994 08:49:37 GMT  ; RFC 822, updated by RFC 1123
+#       Sunday, 06-Nov-94 08:49:37 GMT ; RFC 850, obsoleted by RFC 1036
+#       Sun Nov  6 08:49:37 1994       ; ANSI C's asctime() format
+
+# rfc822 format
+rfc822_date = join (
+	[concat (short_day_reg,','),	# day
+	 group('[0-9][0-9]?'),			# date
+	 months_reg,					# month
+	 group('[0-9]+'),				# year
+	 hms_reg,						# hour minute second
+	 'gmt'
+	 ],
+	' '
+	)
+
+rfc822_reg = regex.compile (rfc822_date)
+
+def unpack_rfc822 ():
+	g = rfc822_reg.group
+	a = string.atoi
+	return (
+		a(g(4)),	   	# year
+		monmap[g(3)],	# month
+		a(g(2)),		# day
+		a(g(5)),		# hour
+		a(g(6)),		# minute
+		a(g(7)),		# second
+		0,
+		0,
+		0
+		)
+
+# rfc850 format
+rfc850_date = join (
+	[concat (long_day_reg,','),
+	 join (
+		 [group ('[0-9][0-9]?'),
+		  months_reg,
+		  group ('[0-9]+')
+		  ],
+		 '-'
+		 ),
+	 hms_reg,
+	 'gmt'
+	 ],
+	' '
+	)
+
+rfc850_reg = regex.compile (rfc850_date)
+# they actually unpack the same way
+def unpack_rfc850 ():
+	g = rfc850_reg.group
+	a = string.atoi
+	return (
+		a(g(4)),	   	# year
+		monmap[g(3)],	# month
+		a(g(2)),		# day
+		a(g(5)),		# hour
+		a(g(6)),		# minute
+		a(g(7)),		# second
+		0,
+		0,
+		0
+		)
+
+# parsdate.parsedate	- ~700/sec.
+# parse_http_date    	- ~1333/sec.
+
+def build_http_date (when):
+	return time.strftime ('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(when))
+
+def parse_http_date (d):
+	d = string.lower (d)
+	# Thanks to Craig Silverstein <csilvers@google.com> for pointing
+	# out the DST discrepancy
+	if time.daylight:
+		tz = time.altzone
+	else:
+		tz = time.timezone
+	# rfc850 comes first, netscape uses it. <frown>
+	if rfc850_reg.match (d) == len(d):
+		return int (time.mktime (unpack_rfc850()) - tz)
+	elif rfc822_reg.match (d) == len(d):
+		return int (time.mktime (unpack_rfc822()) - tz)
+	else:
+		return 0

ZServer/medusa/http_server.py

+#! /usr/local/bin/python
+# -*- Mode: Python; tab-width: 4 -*-
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#	Copyright 1996, 1997 by Sam Rushing
+#						 All Rights Reserved.
+#
+# This software is provided free for non-commercial use.  If you are
+# interested in using this software in a commercial context, or in
+# purchasing support, please contact the author.
+
+RCS_ID =  '$Id: http_server.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+# python modules
+import os
+import regex
+import socket
+import stat
+import string
+import sys
+import time
+
+# async modules
+import asyncore
+import asynchat
+
+# medusa modules
+import http_date
+import producers
+import status_handler
+import logger
+
+VERSION_STRING = string.split(RCS_ID)[2]
+
+from counter import counter
+
+# ===========================================================================
+#							Request Object
+# ===========================================================================
+
+class http_request:
+
+	# default reply code
+	reply_code = 200
+
+	request_counter = counter()
+
+	# Whether to automatically use chunked encoding when
+	# 
+	#   HTTP version is 1.1
+	#   Content-Length is not set
+	#   Chunked encoding is not already in effect
+	#
+	# If your clients are having trouble, you might want to disable this.
+	use_chunked = 1
+	
+
+	# by default, this request object ignores user data.
+	collector = None
+
+	def __init__ (self, *args):
+		# unpack information about the request
+		(self.channel, self.request,
+		 self.command, self.uri, self.version,
+		 self.header) = args
+
+		self.outgoing = fifo()
+		self.reply_headers = {
+			'Server'	: 'Medusa/%s' % VERSION_STRING,
+			'Date'		: http_date.build_http_date (time.time())
+			}
+		self.request_number = http_request.request_counter.increment()
+
+	# --------------------------------------------------
+	# reply header management
+	# --------------------------------------------------
+	def __setitem__ (self, key, value):
+		self.reply_headers[key] = value
+
+	def __getitem__ (self, key):
+		return self.reply_headers[key]
+
+	def has_key (self, key):
+		return self.reply_headers.has_key (key)
+
+	def build_reply_header (self):
+		return string.join (
+			[self.response(self.reply_code)] + map (
+				lambda x: '%s: %s' % x,
+				self.reply_headers.items()
+				),
+			'\r\n'
+			) + '\r\n\r\n'
+
+	# --------------------------------------------------
+	# user data
+	# --------------------------------------------------
+
+	def collect_incoming_data (self, data):
+		if self.collector:
+			self.collector.collect_incoming_data (data)
+		else:
+			sys.stderr.write (
+				'warning: dropping %d bytes of incoming request data\n' % len(data)
+				)
+
+	def found_terminator (self):
+		if self.collector:
+			self.collector.collect_incoming_data (data)
+		else:
+			sys.stderr.write (
+				'warning: unexpected end-of-record for incoming request\n'
+				)
+
+	def push (self, producer):
+		if type(producer) == type(''):
+			self.outgoing.push (producers.simple_producer (producer))
+		else:
+			self.outgoing.push (producer)
+
+	def response (self, code=200):
+		message = self.responses[code]
+		self.reply_code = code
+		return 'HTTP/%s %d %s' % (self.version, code, message)
+
+	def error (self, code):
+		self.reply_code = code
+		message = self.responses[code]
+		s = self.DEFAULT_ERROR_MESSAGE % {
+			'code': code,
+			'message': message,
+			}
+		self['Content-Length'] = len(s)
+		self['Content-Type'] = 'text/html'
+		# make an error reply
+		self.push (s)
+		self.done()
+
+	# can also be used for empty replies
+	reply_now = error
+
+	def done (self):
+		"finalize this transaction - send output to the http channel"
+
+		# ----------------------------------------
+		# persistent connection management
+		# ----------------------------------------
+
+		#  --- BUCKLE UP! ----
+
+		connection = string.lower (get_header (CONNECTION, self.header))
+
+		close_it = 0
+		wrap_in_chunking = 0
+
+		if self.version == '1.0':
+			if connection == 'keep-alive':
+				if not self.has_key ('Content-Length'):
+					close_it = 1
+				else:
+					self['Connection'] = 'Keep-Alive'
+			else:
+				close_it = 1
+		elif self.version == '1.1':
+			if connection == 'close':
+				close_it = 1
+			elif not self.has_key ('Content-Length'):
+				if self.has_key ('Transfer-Encoding'):
+					if not self['Transfer-Encoding'] == 'chunked':
+						close_it = 1
+				elif self.use_chunked:
+					self['Transfer-Encoding'] = 'chunked'
+					wrap_in_chunking = 1
+				else:
+					close_it = 1
+					
+		outgoing_header = producers.simple_producer (self.build_reply_header())
+
+		if close_it:
+			self['Connection'] = 'close'
+
+		if wrap_in_chunking:
+			outgoing_producer = producers.chunked_producer (
+				producers.composite_producer (self.outgoing)
+				)
+			# prepend the header
+			outgoing_producer = producers.composite_producer (
+				fifo([outgoing_header, outgoing_producer])
+				)
+		else:
+			# prepend the header
+			self.outgoing.push_front (outgoing_header)
+			outgoing_producer = producers.composite_producer (self.outgoing)
+
+		# apply a few final transformations to the output
+		self.channel.push_with_producer (
+			# globbing gives us large packets
+			producers.globbing_producer (
+				# hooking lets us log the number of bytes sent
+				producers.hooked_producer (
+					outgoing_producer,
+					self.log
+					)
+				)
+			)
+
+		self.channel.current_request = None
+
+		if close_it:
+			self.channel.close_when_done()
+
+	def log (self, bytes):
+		print 'request %3d: %s %d bytes' % (
+			self.request_counter,
+			self.request,
+			bytes
+			)
+
+	def log_date_string (self, when):
+		return time.strftime (
+			'%d/%b/%Y:%H:%M:%S ',
+			time.gmtime(when)
+			) + tz_for_log
+
+	def log (self, bytes):
+		self.channel.server.logger.log (
+			self.channel.addr[0],
+			'%d - - [%s] "%s" %d %d\n' % (
+				self.channel.addr[1],
+				self.log_date_string (time.time()),
+				self.request,
+				self.reply_code,
+				bytes
+				)
+			)
+
+	responses = {
+		100: "Continue",
+		101: "Switching Protocols",
+		200: "OK",
+		201: "Created",
+		202: "Accepted",
+		203: "Non-Authoritative Information",
+		204: "No Content",
+		205: "Reset Content",
+		206: "Partial Content",
+		300: "Multiple Choices",
+		301: "Moved Permanently",
+		302: "Moved Temporarily",
+		303: "See Other",
+		304: "Not Modified",
+		305: "Use Proxy",
+		400: "Bad Request",
+		401: "Unauthorized",
+		402: "Payment Required",
+		403: "Forbidden",
+		404: "Not Found",
+		405: "Method Not Allowed",
+		406: "Not Acceptable",
+		407: "Proxy Authentication Required",
+		408: "Request Time-out",
+		409: "Conflict",
+		410: "Gone",
+		411: "Length Required",
+		412: "Precondition Failed",
+		413: "Request Entity Too Large",
+		414: "Request-URI Too Large",
+		415: "Unsupported Media Type",
+		500: "Internal Server Error",
+		501: "Not Implemented",
+		502: "Bad Gateway",
+		503: "Service Unavailable",
+		504: "Gateway Time-out",
+		505: "HTTP Version not supported"
+		}
+
+	# Default error message
+	DEFAULT_ERROR_MESSAGE = string.join (
+		['<head>',
+		 '<title>Error response</title>',
+		 '</head>',
+		 '<body>',
+		 '<h1>Error response</h1>',
+		 '<p>Error code %(code)d.',
+		 '<p>Message: %(message)s.',
+		 '</body>',
+		 ''
+		 ],
+		'\r\n'
+		)
+
+
+# ===========================================================================
+#						 HTTP Channel Object
+# ===========================================================================
+
+class http_channel (asynchat.async_chat):
+
+	# use a larger default output buffer
+	ac_out_buffer_size = 1<<16
+
+	current_request = None
+	channel_counter = counter()
+
+	def __init__ (self, server, conn, addr):
+		self.channel_number = http_channel.channel_counter.increment()
+		self.request_counter = counter()
+		asynchat.async_chat.__init__ (self, conn)
+		self.server = server
+		self.addr = addr
+		self.set_terminator ('\r\n\r\n')
+		self.in_buffer = ''
+		self.creation_time = int (time.time())
+		self.check_maintenance()
+
+	def __repr__ (self):
+		ar = asynchat.async_chat.__repr__(self)[1:-1]
+		return '<%s channel#: %s requests:%s>' % (
+			ar,
+			self.channel_number,
+			self.request_counter
+			)
+
+	# Channel Counter, Maintenance Interval...
+	maintenance_interval = 500
+
+	def check_maintenance (self):
+		if not self.channel_number % self.maintenance_interval:
+			self.maintenance()
+
+	def maintenance (self):
+		self.kill_zombies()
+
+	# 30-minute zombie timeout.  status_handler also knows how to kill zombies.
+	zombie_timeout = 30 * 60
+
+	def kill_zombies (self):
+		now = int (time.time())
+		for channel in asyncore.socket_map.keys():
+			if channel.__class__ == http_channel:
+				if (now - channel.creation_time) > channel.zombie_timeout:
+					channel.close()
+
+	# --------------------------------------------------
+	# send/recv overrides, good place for instrumentation.
+	# --------------------------------------------------
+	
+	# this information needs to get into the request object,
+	# so that it may log correctly.
+	def send (self, data):
+		result = asynchat.async_chat.send (self, data)
+		self.server.bytes_out.increment (len(data))
+		return result
+
+	def recv (self, buffer_size):
+		result = asynchat.async_chat.recv (self, buffer_size)
+		self.server.bytes_in.increment (len(result))
+		return result
+
+	def log (self, *args):
+		pass
+
+	# --------------------------------------------------
+	# async_chat methods
+	# --------------------------------------------------
+
+	def collect_incoming_data (self, data):
+		if self.current_request:
+			# we are receiving data (probably POST data) for a request
+			self.current_request.collect_incoming_data (data)
+		else:
+			# we are receiving header (request) data
+			self.in_buffer = self.in_buffer + data
+
+	def found_terminator (self):
+		if self.current_request:
+			self.current_request.found_terminator()
+		else:
+			header = self.in_buffer
+			self.in_buffer = ''
+			lines = string.split (header, '\r\n')
+
+			# --------------------------------------------------
+			# crack the request header
+			# --------------------------------------------------
+			request = lines[0]
+			command, uri, version = crack_request (request)
+			header = join_headers (lines[1:])
+
+			r = http_request (self, request, command, uri, version, header)
+			self.request_counter.increment()
+			self.server.total_requests.increment()
+
+			# --------------------------------------------------
+			# handler selection and dispatch
+			# --------------------------------------------------
+			for h in self.server.handlers:
+				if h.match (r):
+					try:
+						self.current_request = r
+						# This isn't used anywhere.
+						# r.handler = h # CYCLE
+						h.handle_request (r)
+					except:
+						self.server.exceptions.increment()
+						t,v,tb = sys.exc_info()
+						(file,fun,line),tbinfo = asyncore.compact_traceback (t,v,tb)
+						while tb.tb_next:
+							tb = tb.tb_next
+						# Log this to a better place.
+						print 'Server Error: %s, %s: file: %s line: %s' % (t,v,file,line)
+						# IMPORTANT: without this <del>, this entire connection will leak. [why?]
+						del t,v,tb
+						try:
+							r.error (500)
+						except:
+							pass
+					return
+
+			# no handlers, so complain
+			r.error (404)
+
+	def writable (self):
+		# this is just the normal async_chat 'writable', here for comparison
+		return self.ac_out_buffer or len(self.producer_fifo)
+
+	def writable_for_proxy (self):
+		# this version of writable supports the idea of a 'stalled' producer
+		# [i.e., it's not ready to produce any output yet] This is needed by
+		# the proxy, which will be waiting for the magic combination of
+		# 1) hostname resolved
+		# 2) connection made
+		# 3) data available.
+		if self.ac_out_buffer:
+			return 1
+		elif len(self.producer_fifo):
+			p = self.producer_fifo.first()
+			if hasattr (p, 'stalled'):
+				return not p.stalled()
+			else:
+				return 1
+
+# ===========================================================================
+#						 HTTP Server Object
+# ===========================================================================
+
+class http_server (asyncore.dispatcher):
+
+	SERVER_IDENT = 'HTTP Server (V%s)' % VERSION_STRING
+
+	channel_class = http_channel
+
+	def __init__ (self, ip, port, resolver=None, logger_object=None):
+		self.ip = ip
+		self.port = port
+		asyncore.dispatcher.__init__ (self)
+		self.create_socket (socket.AF_INET, socket.SOCK_STREAM)
+
+		self.handlers = []
+
+		if not logger_object:
+			logger_object = logger.file_logger (sys.stdout)
+
+		self.set_reuse_addr()
+		self.bind ((ip, port))
+		self.listen (5)
+		host, port = self.socket.getsockname()
+		if not ip:
+			print 'Warning: computing default hostname'
+			self.server_name = socket.gethostbyaddr (
+				socket.gethostbyname (socket.gethostname())
+				)[0]
+		else:
+			self.server_name = socket.gethostbyaddr (ip)[0]
+		self.server_port = port
+		self.total_clients = counter()
+		self.total_requests = counter()
+		self.exceptions = counter()
+		self.bytes_out = counter()
+		self.bytes_in  = counter()
+
+		if not logger_object:
+			logger_object = logger.file_logger (sys.stdout)
+
+		if resolver:
+			self.logger = logger.resolving_logger (resolver, logger_object)
+		else:
+			self.logger = logger.unresolving_logger (logger_object)
+
+		sys.stdout.write (
+			'Medusa (V%s) started at %s'
+			'\n\tHostname: %s'
+			'\n\tPort:%d'
+			'\n' % (
+				VERSION_STRING,
+				time.ctime(time.time()),
+				self.server_name,
+				port,
+				)
+			)
+
+	def writable (self):
+		return 0
+
+	def handle_read (self):
+		pass
+
+	def readable (self):
+		return self.accepting
+
+	def handle_connect (self):
+		pass
+
+	def handle_accept (self):
+		self.total_clients.increment()
+		try:
+			conn, addr = self.accept()
+		except socket.error:
+			# linux: on rare occasions we get a bogus socket back from
+			# accept.  socketmodule.c:makesockaddr complains that the
+			# address family is unknown.  We don't want the whole server
+			# to shut down because of this.
+			sys.stderr.write ('warning: server accept() threw an exception\n')
+			return
+
+		self.channel_class (self, conn, addr)
+
+	def install_handler (self, handler, back=0):
+		if back:
+			self.handlers.append (handler)
+		else:
+			self.handlers.insert (0, handler)
+
+	def remove_handler (self, handler):
+		self.handlers.remove (handler)
+
+	def status (self):
+		def nice_bytes (n):
+			return string.join (status_handler.english_bytes (n))
+
+		handler_stats = filter (None, map (maybe_status, self.handlers))
+		
+		if self.total_clients:
+			ratio = float(self.total_requests.as_long()/self.total_clients.as_long())
+		else:
+			ratio = 0.0
+		
+		return producers.composite_producer (
+			fifo ([producers.lines_producer (
+				['<h2>%s</h2>'							% self.SERVER_IDENT,
+				'<br>Listening on: <b>Host:</b> %s'		% self.server_name,
+				'<b>Port:</b> %d'						% self.port,
+				 '<p><ul>'
+				 '<li>Total <b>Clients:</b> %s'			% self.total_clients,
+				 '<b>Requests:</b> %s'					% self.total_requests,
+				 '<b>Requests/Client:</b> %.1f'			% (ratio),
+				 '<li>Total <b>Bytes In:</b> %s'	% (nice_bytes (self.bytes_in.as_long())),
+				 '<b>Bytes Out:</b> %s'				% (nice_bytes (self.bytes_out.as_long())),
+				 '<li>Total <b>Exceptions:</b> %s'		% self.exceptions,
+				 '</ul><p>'
+				 '<b>Extension List</b><ul>',
+				 ])] + handler_stats + [producers.simple_producer('</ul>')]
+				  )
+			)
+
+def maybe_status (thing):
+	if hasattr (thing, 'status'):
+		return thing.status()
+	else:
+		return None
+
+CONNECTION = regex.compile ('Connection: \(.*\)', regex.casefold)
+
+# merge multi-line headers
+# [486dx2: ~500/sec]
+def join_headers (headers):
+	r = []
+	for i in range(len(headers)):
+		if headers[i][0] in ' \t':	
+			r[-1] = r[-1] + headers[i][1:]
+		else:
+			r.append (headers[i])
+	return r
+
+def get_header (head_reg, lines, group=1):
+	for line in lines:
+		if head_reg.match (line) == len(line):
+			return head_reg.group(group)
+	return ''
+
+REQUEST = regex.compile ('\([^ ]+\) \([^ ]+\)\(\( HTTP/\([0-9.]+\)\)$\|$\)')
+
+def crack_request (r):
+	if REQUEST.match (r) == len(r):
+		if REQUEST.group(3):
+			version = REQUEST.group(5)
+		else:
+			version = None
+		return string.lower (REQUEST.group (1)), REQUEST.group(2), version
+
+class fifo:
+	def __init__ (self, list=None):
+		if not list:
+			self.list = []
+		else:
+			self.list = list
+		
+	def __len__ (self):
+		return len(self.list)
+
+	def first (self):
+		return self.list[0]
+
+	def push_front (self, object):
+		self.list.insert (0, object)
+
+	def push (self, data):
+		self.list.append (data)
+
+	def pop (self):
+		if self.list:
+			result = self.list[0]
+			del self.list[0]
+			return (1, result)
+		else:
+			return (0, None)
+
+def compute_timezone_for_log ():
+	if time.daylight:
+		tz = time.altzone
+	else:
+		tz = time.timezone
+	if tz > 0:
+		neg = 1
+	else:
+		neg = 0
+		tz = -tz
+	h, rem = divmod (tz, 3600)
+	m, rem = divmod (rem, 60)
+	if neg:
+		return '-%02d%02d' % (h, m)
+	else:
+		return '+%02d%02d' % (h, m)
+
+# if you run this program over a TZ change boundary, this will be invalid.
+tz_for_log = compute_timezone_for_log()
+
+if __name__ == '__main__':
+	import sys
+	if len(sys.argv) < 2:
+		print 'usage: %s <root> <port>' % (sys.argv[0])
+	else:
+		import monitor
+		import filesys
+		import default_handler
+		import status_handler
+		import ftp_server
+		import chat_server
+		import resolver
+		import logger
+		rs = resolver.caching_resolver ('127.0.0.1')
+		lg = logger.file_logger (sys.stdout)
+		ms = monitor.secure_monitor_server ('fnord', '127.0.0.1', 9999)
+		fs = filesys.os_filesystem (sys.argv[1])
+		dh = default_handler.default_handler (fs)
+		hs = http_server ('', string.atoi (sys.argv[2]), rs, lg)
+		hs.install_handler (dh)
+		ftp = ftp_server.ftp_server (
+			ftp_server.dummy_authorizer(sys.argv[1]),
+			port=8021,
+			resolver=rs,
+			logger_object=lg
+			)
+		cs = chat_server.chat_server ('', 7777)
+		sh = status_handler.status_extension([hs,ms,ftp,cs,rs])
+		hs.install_handler (sh)
+		if ('-p' in sys.argv):
+			def profile_loop ():
+				try:
+					asyncore.loop()
+				except KeyboardInterrupt:
+					pass
+			import profile
+			profile.run ('profile_loop()', 'profile.out')
+		else:
+			asyncore.loop()

ZServer/medusa/logger.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+import asynchat
+import socket
+import string
+
+#
+# three types of log:
+# 1) file
+#    with optional flushing.
+# 2) socket
+#    dump output directly to a socket connection. [how do we
+#    keep it open?]
+# 3) syslog
+#    log to syslog via tcp.  this is a per-line protocol.
+#
+
+#
+# The 'standard' interface to a logging object is simply
+# log_object.log (message)
+#
+
+# a file-like object that captures output, and
+# makes sure to flush it always...  this could
+# be connected to:
+#  o	stdio file
+#  o	low-level file
+#  o	socket channel
+#  o	syslog output...
+
+class file_logger:
+			
+	# pass this either a path or a file object.
+	def __init__ (self, file, flush=1, mode='wa'):
+		if type(file) == type(''):
+			if (file == '-'):
+				import sys
+				self.file = sys.stdout
+			else:
+				self.file = open (file, mode)
+		else:
+			self.file = file
+		self.do_flush = flush
+
+	def __repr__ (self):
+		return '<file logger: %s>' % self.file
+
+	def write (self, data):
+		self.file.write (data)
+		self.maybe_flush()
+		
+	def writeline (self, line):
+		self.file.writeline (line)
+		self.maybe_flush()
+		
+	def writelines (self, lines):
+		self.file.writelines (lines)
+		self.maybe_flush()
+
+	def maybe_flush (self):
+		if self.do_flush:
+			self.file.flush()
+
+	def flush (self):
+		self.file.flush()
+
+	def softspace (self, *args):
+		pass
+
+	def log (self, message):
+		if message[-1] not in ('\r', '\n'):
+			self.write (message + '\n')
+		else:
+			self.write (message)
+
+# syslog is a line-oriented log protocol - this class would be
+# appropriate for FTP or HTTP logs, but not for dumping stderr to.
+
+# TODO: a simple safety wrapper that will ensure that the line sent
+# to syslog is reasonable.
+
+# TODO: async version of syslog_client: now, log entries use blocking
+# send()
+
+import m_syslog
+syslog_logger = m_syslog.syslog_client
+
+class syslog_logger (m_syslog.syslog_client):
+	def __init__ (self, address, facility='user'):
+		m_syslog.syslog_client.__init__ (self, address)
+		self.facility = m_syslog.facility_names[facility]
+		self.address=address
+
+	def __repr__ (self):
+		return '<syslog logger address=%s>' % (repr(self.address))
+
+	def log (self, message):
+		m_syslog.syslog_client.log (
+			self,
+			message,
+			facility=self.facility,
+			priority=m_syslog.LOG_INFO
+			)
+
+# log to a stream socket, asynchronously
+
+class socket_logger (asynchat.async_chat):
+
+	def __init__ (self, address):
+
+		if type(address) == type(''):
+			self.create_socket (socket.AF_UNIX, socket.SOCK_STREAM)
+		else:
+			self.create_socket (socket.AF_INET, socket.SOCK_STREAM)
+
+		self.connect (address)
+		self.address = address
+		
+	def __repr__ (self):
+		return '<socket logger: address=%s>' % (self.address)
+
+	def log (self, message):
+		if message[-2:] != '\r\n':
+			self.socket.push (message + '\r\n')
+		else:
+			self.socket.push (message)
+
+# log to multiple places
+class multi_logger:
+	def __init__ (self, loggers):
+		self.loggers = loggers
+
+	def __repr__ (self):
+		return '<multi logger: %s>' % (repr(self.loggers))
+
+	def log (self, message):
+		for logger in self.loggers:
+			logger.log (message)
+
+class resolving_logger:
+	"""Feed (ip, message) combinations into this logger to get a
+	resolved hostname in front of the message.  The message will not
+	be logged until the PTR request finishes (or fails)."""
+
+	def __init__ (self, resolver, logger):
+		self.resolver = resolver
+		self.logger = logger
+
+	class logger_thunk:
+		def __init__ (self, message, logger):
+			self.message = message
+			self.logger = logger
+
+		def __call__ (self, host, ttl, answer):
+			if not answer:
+				answer = host
+			self.logger.log ('%s:%s' % (answer, self.message))
+
+	def log (self, ip, message):
+		self.resolver.resolve_ptr (
+			ip,
+			self.logger_thunk (
+				message,
+				self.logger
+				)
+			)
+
+class unresolving_logger:
+	"Just in case you don't want to resolve"
+	def __init__ (self, logger):
+		self.logger = logger
+
+	def log (self, ip, message):
+		self.logger.log ('%s:%s' % (ip, message))
+
+
+def strip_eol (line):
+	while line and line[-1] in '\r\n':
+		line = line[:-1]
+	return line
+
+class tail_logger:
+	"Keep track of the last <size> log messages"
+	def __init__ (self, logger, size=500):
+		self.size = size
+		self.logger = logger
+		self.messages = []
+
+	def log (self, message):
+		self.messages.append (strip_eol (message))
+		if len (self.messages) > self.size:
+			del self.messages[0]
+		self.logger.log (message)

ZServer/medusa/m_syslog.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+# ======================================================================
+# Copyright 1997 by Sam Rushing
+# 
+#                         All Rights Reserved
+# 
+# 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
+# permission.
+# 
+# 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.
+# ======================================================================
+
+"""socket interface to unix syslog.
+On Unix, there are usually two ways of getting to syslog: via a
+local unix-domain socket, or via the TCP service.
+
+Usually "/dev/log" is the unix domain socket.  This may be different
+for other systems.
+
+>>> my_client = syslog_client ('/dev/log')
+
+Otherwise, just use the UDP version, port 514.
+
+>>> my_client = syslog_client (('my_log_host', 514))
+
+On win32, you will have to use the UDP version.  Note that
+you can use this to log to other hosts (and indeed, multiple
+hosts).
+
+This module is not a drop-in replacement for the python
+<syslog> extension module - the interface is different.
+
+Usage:
+
+>>> c = syslog_client()
+>>> c = syslog_client ('/strange/non_standard_log_location')
+>>> c = syslog_client (('other_host.com', 514))
+>>> c.log ('testing', facility='local0', priority='debug')
+
+"""
+
+# TODO: support named-pipe syslog.
+# [see ftp://sunsite.unc.edu/pub/Linux/system/Daemons/syslog-fifo.tar.z]
+
+# from <linux/sys/syslog.h>:
+# ===========================================================================
+# priorities/facilities are encoded into a single 32-bit quantity, where the
+# bottom 3 bits are the priority (0-7) and the top 28 bits are the facility
+# (0-big number).  Both the priorities and the facilities map roughly
+# one-to-one to strings in the syslogd(8) source code.  This mapping is
+# included in this file.
+#
+# priorities (these are ordered)
+
+LOG_EMERG		= 0		#  system is unusable 
+LOG_ALERT		= 1		#  action must be taken immediately 
+LOG_CRIT		= 2		#  critical conditions 
+LOG_ERR			= 3		#  error conditions 
+LOG_WARNING		= 4		#  warning conditions 
+LOG_NOTICE		= 5		#  normal but significant condition 
+LOG_INFO		= 6		#  informational 
+LOG_DEBUG		= 7		#  debug-level messages 
+
+#  facility codes 
+LOG_KERN		= 0		#  kernel messages 
+LOG_USER		= 1		#  random user-level messages 
+LOG_MAIL		= 2		#  mail system 
+LOG_DAEMON		= 3		#  system daemons 
+LOG_AUTH		= 4		#  security/authorization messages 
+LOG_SYSLOG		= 5		#  messages generated internally by syslogd 
+LOG_LPR			= 6		#  line printer subsystem 
+LOG_NEWS		= 7		#  network news subsystem 
+LOG_UUCP		= 8		#  UUCP subsystem 
+LOG_CRON		= 9		#  clock daemon 
+LOG_AUTHPRIV	= 10	#  security/authorization messages (private) 
+
+#  other codes through 15 reserved for system use 
+LOG_LOCAL0		= 16		#  reserved for local use 
+LOG_LOCAL1		= 17		#  reserved for local use 
+LOG_LOCAL2		= 18		#  reserved for local use 
+LOG_LOCAL3		= 19		#  reserved for local use 
+LOG_LOCAL4		= 20		#  reserved for local use 
+LOG_LOCAL5		= 21		#  reserved for local use 
+LOG_LOCAL6		= 22		#  reserved for local use 
+LOG_LOCAL7		= 23		#  reserved for local use 
+
+priority_names = {
+	"alert":	LOG_ALERT,
+	"crit":		LOG_CRIT,
+	"debug":	LOG_DEBUG,
+	"emerg":	LOG_EMERG,
+	"err":		LOG_ERR,
+	"error":	LOG_ERR,		#  DEPRECATED 
+	"info":		LOG_INFO,
+	"notice":	LOG_NOTICE,
+	"panic": 	LOG_EMERG,		#  DEPRECATED 
+	"warn":		LOG_WARNING,		#  DEPRECATED 
+	"warning":	LOG_WARNING,
+	}
+
+facility_names = {
+	"auth":		LOG_AUTH,
+	"authpriv":	LOG_AUTHPRIV,
+	"cron": 	LOG_CRON,
+	"daemon":	LOG_DAEMON,
+	"kern":		LOG_KERN,
+	"lpr":		LOG_LPR,
+	"mail":		LOG_MAIL,
+	"news":		LOG_NEWS,
+	"security":	LOG_AUTH,		#  DEPRECATED 
+	"syslog":	LOG_SYSLOG,
+	"user":		LOG_USER,
+	"uucp":		LOG_UUCP,
+	"local0":	LOG_LOCAL0,
+	"local1":	LOG_LOCAL1,
+	"local2":	LOG_LOCAL2,
+	"local3":	LOG_LOCAL3,
+	"local4":	LOG_LOCAL4,
+	"local5":	LOG_LOCAL5,
+	"local6":	LOG_LOCAL6,
+	"local7":	LOG_LOCAL7,
+	}
+
+import socket
+
+class syslog_client:
+	def __init__ (self, address='/dev/log'):
+		self.address = address
+		if type (address) == type(''):
+			self.socket = socket.socket (socket.AF_UNIX, socket.SOCK_STREAM)
+			self.socket.connect (address)
+			self.unix = 1
+		else:
+			self.socket = socket.socket (socket.AF_INET, socket.SOCK_DGRAM)
+			self.unix = 0
+
+	# curious: when talking to the unix-domain '/dev/log' socket, a
+	#   zero-terminator seems to be required.  this string is placed
+	#   into a class variable so that it can be overridden if
+	#   necessary.
+
+	log_format_string = '<%d>%s\000'
+
+	def log (self, message, facility=LOG_USER, priority=LOG_INFO):
+		message = self.log_format_string % (
+			self.encode_priority (facility, priority),
+			message
+			)
+		if self.unix:
+			self.socket.send (message)
+		else:
+			self.socket.sendto (message, self.address)
+
+	def encode_priority (self, facility, priority):
+		if type(facility) == type(''):
+			facility = facility_names[facility]
+		if type(priority) == type(''):
+			priority = priority_names[priority]			
+		return (facility<<3) | priority
+
+	def close (self):
+		if self.unix:
+			self.socket.close()
+

ZServer/medusa/medusa_gif.py

+# -*- Mode: Python -*-
+
+# the medusa icon as a python source file.
+
+width = 97
+height = 61
+
+data = 'GIF89aa\000=\000\204\000\000\000\000\000\255\255\255\245\245\245ssskkkccc111)))\326\326\326!!!\316\316\316\300\300\300\204\204\000\224\224\224\214\214\214\200\200\200RRR\377\377\377JJJ\367\367\367BBB\347\347\347\000\204\000\020\020\020\265\265\265\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000!\371\004\001\000\000\021\000,\000\000\000\000a\000=\000\000\005\376`$\216di\236h\252\256l\353\276p,\317tm\337x\256\357|m\001@\240E\305\000\364\2164\206R)$\005\201\214\007r\012{X\255\312a\004\260\\>\026\3240\353)\224n\001W+X\334\373\231~\344.\303b\216\024\027x<\273\307\255G,rJiWN\014{S}k"?ti\013EdPQ\207G@_%\000\026yy\\\201\202\227\224<\221Fs$pOjWz\241<r@vO\236\231\233k\247M\2544\203F\177\235\236L#\247\256Z\270,\266BxJ[\276\256A]iE\304\305\262\273E\313\201\275i#\\\303\321\'h\203V\\\177\326\276\216\220P~\335\230_\264\013\342\275\344KF\233\360Q\212\352\246\000\367\274s\361\236\334\347T\341;\341\246\2202\177\3142\211`\242o\325@S\202\264\031\252\207\260\323\256\205\311\036\236\270\002\'\013\302\177\274H\010\324X\002\0176\212\037\376\321\360\032\226\207\244\2674(+^\202\346r\205J\0211\375\241Y#\256f\0127\315>\272\002\325\307g\012(\007\205\312#j\317(\012A\200\224.\241\003\346GS\247\033\245\344\264\366\015L\'PXQl]\266\263\243\232\260?\245\316\371\362\225\035\332\243J\273\332Q\263\357-D\241T\327\270\265\013W&\330\010u\371b\322IW0\214\261]\003\033Va\365Z#\207\213a\030k\2647\262\014p\354\024[n\321N\363\346\317\003\037P\000\235C\302\000\3228(\244\363YaA\005\022\255_\237@\260\000A\212\326\256qbp\321\332\266\011\334=T\023\010"!B\005\003A\010\224\020\220 H\002\337#\020 O\276E\357h\221\327\003\\\000b@v\004\351A.h\365\354\342B\002\011\257\025\\ \220\340\301\353\006\000\024\214\200pA\300\353\012\364\241k/\340\033C\202\003\000\310fZ\011\003V\240R\005\007\354\376\026A\000\000\360\'\202\177\024\004\210\003\000\305\215\360\000\000\015\220\240\332\203\027@\'\202\004\025VpA\000%\210x\321\206\032J\341\316\010\262\211H"l\333\341\200\200>"]P\002\212\011\010`\002\0066FP\200\001\'\024p]\004\027(8B\221\306]\000\201w>\002iB\001\007\340\260"v7J1\343(\257\020\251\243\011\242i\263\017\215\337\035\220\200\221\365m4d\015\016D\251\341iN\354\346Ng\253\200I\240\031\35609\245\2057\311I\302\2007t\231"&`\314\310\244\011e\226(\236\010w\212\300\234\011\012HX(\214\253\311@\001\233^\222pg{% \340\035\224&H\000\246\201\362\215`@\001"L\340\004\030\234\022\250\'\015(V:\302\235\030\240q\337\205\224\212h@\177\006\000\250\210\004\007\310\207\337\005\257-P\346\257\367]p\353\203\271\256:\203\236\211F\340\247\010\3329g\244\010\307*=A\000\203\260y\012\304s#\014\007D\207,N\007\304\265\027\021C\233\207%B\366[m\353\006\006\034j\360\306+\357\274a\204\000\000;'

ZServer/medusa/mime_type_table.py

+# -*- Python -*-
+# Converted by ./convert_mime_type_table.py from:
+# /usr/src2/apache_1.2b6/conf/mime.types
+#
+content_type_map = \
+  {
+        'ai':  'application/postscript',
+       'aif':  'audio/x-aiff',
+      'aifc':  'audio/x-aiff',
+      'aiff':  'audio/x-aiff',
+        'au':  'audio/basic',
+       'avi':  'video/x-msvideo',
+     'bcpio':  'application/x-bcpio',
+       'bin':  'application/octet-stream',
+       'cdf':  'application/x-netcdf',
+     'class':  'application/octet-stream',
+      'cpio':  'application/x-cpio',
+       'cpt':  'application/mac-compactpro',
+       'csh':  'application/x-csh',
+       'dcr':  'application/x-director',
+       'dir':  'application/x-director',
+       'dms':  'application/octet-stream',
+       'doc':  'application/msword',
+       'dvi':  'application/x-dvi',
+       'dxr':  'application/x-director',
+       'eps':  'application/postscript',
+       'etx':  'text/x-setext',
+       'exe':  'application/octet-stream',
+       'gif':  'image/gif',
+      'gtar':  'application/x-gtar',
+        'gz':  'application/x-gzip',
+       'hdf':  'application/x-hdf',
+       'hqx':  'application/mac-binhex40',
+       'htm':  'text/html',
+      'html':  'text/html',
+       'ice':  'x-conference/x-cooltalk',
+       'ief':  'image/ief',
+       'jpe':  'image/jpeg',
+      'jpeg':  'image/jpeg',
+       'jpg':  'image/jpeg',
+       'kar':  'audio/midi',
+     'latex':  'application/x-latex',
+       'lha':  'application/octet-stream',
+       'lzh':  'application/octet-stream',
+       'man':  'application/x-troff-man',
+        'me':  'application/x-troff-me',
+       'mid':  'audio/midi',
+      'midi':  'audio/midi',
+       'mif':  'application/x-mif',
+       'mov':  'video/quicktime',
+     'movie':  'video/x-sgi-movie',
+       'mp2':  'audio/mpeg',
+       'mpe':  'video/mpeg',
+      'mpeg':  'video/mpeg',
+       'mpg':  'video/mpeg',
+      'mpga':  'audio/mpeg',
+       'mp3':  'audio/mpeg',
+        'ms':  'application/x-troff-ms',
+        'nc':  'application/x-netcdf',
+       'oda':  'application/oda',
+       'pbm':  'image/x-portable-bitmap',
+       'pdb':  'chemical/x-pdb',
+       'pdf':  'application/pdf',
+       'pgm':  'image/x-portable-graymap',
+       'png':  'image/png',
+       'pnm':  'image/x-portable-anymap',
+       'ppm':  'image/x-portable-pixmap',
+       'ppt':  'application/powerpoint',
+        'ps':  'application/postscript',
+        'qt':  'video/quicktime',
+        'ra':  'audio/x-realaudio',
+       'ram':  'audio/x-pn-realaudio',
+       'ras':  'image/x-cmu-raster',
+       'rgb':  'image/x-rgb',
+      'roff':  'application/x-troff',
+       'rpm':  'audio/x-pn-realaudio-plugin',
+       'rtf':  'application/rtf',
+       'rtx':  'text/richtext',
+       'sgm':  'text/x-sgml',
+      'sgml':  'text/x-sgml',
+        'sh':  'application/x-sh',
+      'shar':  'application/x-shar',
+       'sit':  'application/x-stuffit',
+       'skd':  'application/x-koan',
+       'skm':  'application/x-koan',
+       'skp':  'application/x-koan',
+       'skt':  'application/x-koan',
+       'snd':  'audio/basic',
+       'src':  'application/x-wais-source',
+   'sv4cpio':  'application/x-sv4cpio',
+    'sv4crc':  'application/x-sv4crc',
+         't':  'application/x-troff',
+       'tar':  'application/x-tar',
+       'tcl':  'application/x-tcl',
+       'tex':  'application/x-tex',
+      'texi':  'application/x-texinfo',
+   'texinfo':  'application/x-texinfo',
+       'tif':  'image/tiff',
+      'tiff':  'image/tiff',
+        'tr':  'application/x-troff',
+       'tsv':  'text/tab-separated-values',
+       'txt':  'text/plain',
+     'ustar':  'application/x-ustar',
+       'vcd':  'application/x-cdlink',
+      'vrml':  'x-world/x-vrml',
+       'wav':  'audio/x-wav',
+       'wrl':  'x-world/x-vrml',
+       'xbm':  'image/x-xbitmap',
+       'xpm':  'image/x-xpixmap',
+       'xwd':  'image/x-xwindowdump',
+       'xyz':  'chemical/x-pdb',
+       'zip':  'application/zip',
+  }

ZServer/medusa/producers.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+RCS_ID = '$Id: producers.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+import string
+
+"""
+A collection of producers.
+Each producer implements a particular feature:  They can be combined
+in various ways to get interesting and useful behaviors.
+
+For example, you can feed dynamically-produced output into the compressing
+producer, then wrap this with the 'chunked' transfer-encoding producer.
+"""
+
+class simple_producer:
+	"producer for a string"
+	def __init__ (self, data, buffer_size=1024):
+		self.data = data
+		self.buffer_size = buffer_size
+
+	def more (self):
+		if len (self.data) > self.buffer_size:
+			result = self.data[:self.buffer_size]
+			self.data = self.data[self.buffer_size:]
+			return result
+		else:
+			result = self.data
+			self.data = ''
+			return result
+
+class scanning_producer:
+	"like simple_producer, but more efficient for large strings"
+	def __init__ (self, data, buffer_size=1024):
+		self.data = data
+		self.buffer_size = buffer_size
+		self.pos = 0
+
+	def more (self):
+		if self.pos < len(self.data):
+			lp = self.pos
+			rp = min (
+				len(self.data),
+				self.pos + self.buffer_size
+				)
+			result = self.data[lp:rp]
+			self.pos = self.pos + len(result)
+			return result
+		else:
+			return ''
+
+class lines_producer:
+	"producer for a list of lines"
+
+	def __init__ (self, lines):
+		self.lines = lines
+
+	def ready (self):
+		return len(self.lines)
+
+	def more (self):
+		if self.lines:
+			chunk = self.lines[:50]
+			self.lines = self.lines[50:]
+			return string.join (chunk, '\r\n') + '\r\n'
+		else:
+			return ''
+
+class file_producer:
+	"producer wrapper for file[-like] objects"
+
+	# match http_channel's outgoing buffer size
+	out_buffer_size = 1<<16
+
+	def __init__ (self, file):
+		self.done = 0
+		self.file = file
+
+	def more (self):
+		if self.done:
+			return ''
+		else:
+			data = self.file.read (self.out_buffer_size)
+			if not data:
+				self.file.close()
+				del self.file
+				self.done = 1
+				return ''
+			else:
+				return data
+
+# A simple output producer.  This one does not [yet] have
+# the safety feature builtin to the monitor channel:  runaway
+# output will not be caught.
+
+# don't try to print from within any of the methods
+# of this object.
+
+class output_producer:
+	"Acts like an output file; suitable for capturing sys.stdout"
+	def __init__ (self):
+		self.data = ''
+			
+	def write (self, data):
+		lines = string.splitfields (data, '\n')
+		data = string.join (lines, '\r\n')
+		self.data = self.data + data
+		
+	def writeline (self, line):
+		self.data = self.data + line + '\r\n'
+		
+	def writelines (self, lines):
+		self.data = self.data + string.joinfields (
+			lines,
+			'\r\n'
+			) + '\r\n'
+
+	def ready (self):
+		return (len (self.data) > 0)
+
+	def flush (self):
+		pass
+
+	def softspace (self, *args):
+		pass
+
+	def more (self):
+		if self.data:
+			result = self.data[:512]
+			self.data = self.data[512:]
+			return result
+		else:
+			return ''
+
+class composite_producer:
+	"combine a fifo of producers into one"
+	def __init__ (self, producers):
+		self.producers = producers
+
+	def more (self):
+		while len(self.producers):
+			p = self.producers.first()
+			d = p.more()
+			if d:
+				return d
+			else:
+				self.producers.pop()
+		else:
+			return ''
+
+
+class globbing_producer:
+	"""
+	'glob' the output from a producer into a particular buffer size.
+	helps reduce the number of calls to send().  [this appears to
+	gain about 30% performance on requests to a single channel]
+	"""
+
+	def __init__ (self, producer, buffer_size=1<<16):
+		self.producer = producer
+		self.buffer = ''
+		self.buffer_size = buffer_size
+
+	def more (self):
+		while len(self.buffer) < self.buffer_size:
+			data = self.producer.more()
+			if data:
+				self.buffer = self.buffer + data
+			else:
+				break
+		r = self.buffer
+		self.buffer = ''
+		return r
+
+
+class hooked_producer:
+	"""
+	A producer that will call <function> when it empties,.
+	with an argument of the number of bytes produced.  Useful
+	for logging/instrumentation purposes.
+	"""
+
+	def __init__ (self, producer, function):
+		self.producer = producer
+		self.function = function
+		self.bytes = 0
+
+	def more (self):
+		if self.producer:
+			result = self.producer.more()
+			if not result:
+				self.producer = None
+				self.function (self.bytes)
+			else:
+				self.bytes = self.bytes + len(result)
+			return result
+		else:
+			return ''
+
+# HTTP 1.1 emphasizes that an advertised Content-Length header MUST be
+# correct.  In the face of Strange Files, it is conceivable that
+# reading a 'file' may produce an amount of data not matching that
+# reported by os.stat() [text/binary mode issues, perhaps the file is
+# being appended to, etc..]  This makes the chunked encoding a True
+# Blessing, and it really ought to be used even with normal files.
+# How beautifully it blends with the concept of the producer.
+
+class chunked_producer:
+	"""A producer that implements the 'chunked' transfer coding for HTTP/1.1.
+	Here is a sample usage:
+		request['Transfer-Encoding'] = 'chunked'
+		request.push (
+			producers.chunked_producer (your_producer)
+			)
+		request.done()
+	"""
+
+	def __init__ (self, producer, footers=None):
+		self.producer = producer
+		self.footers = footers
+
+	def more (self):
+		if self.producer:
+			data = self.producer.more()
+			if data:
+				return '%x\r\n%s\r\n' % (len(data), data)
+			else:
+				self.producer = None
+				if self.footers:
+					return string.join (
+						['0'] + self.footers,
+						'\r\n'
+						) + '\r\n\r\n'
+				else:
+					return '0\r\n\r\n'
+		else:
+			return ''
+
+# Unfortunately this isn't very useful right now (Aug 97), because
+# apparently the browsers don't do on-the-fly decompression.  Which
+# is sad, because this could _really_ speed things up, especially for
+# low-bandwidth clients (i.e., most everyone).
+
+try:
+	import zlib
+except ImportError:
+	zlib = None
+
+class compressed_producer:
+	"""
+	Compress another producer on-the-fly, using ZLIB
+	[Unfortunately, none of the current browsers seem to support this]
+	"""
+
+	# Note: It's not very efficient to have the server repeatedly
+	# compressing your outgoing files: compress them ahead of time, or
+	# use a compress-once-and-store scheme.  However, if you have low
+	# bandwidth and low traffic, this may make more sense than
+	# maintaining your source files compressed.
+	#
+	# Can also be used for compressing dynamically-produced output.
+
+	def __init__ (self, producer, level=5):
+		self.producer = producer
+		self.compressor = zlib.compressobj (level)
+
+	def more (self):
+		if self.producer:
+			cdata = ''
+			# feed until we get some output
+			while not cdata:
+				data = self.producer.more()
+				if not data:
+					self.producer = None
+					return self.compressor.flush()
+				else:
+					cdata = self.compressor.compress (data)
+			return cdata
+		else:
+			return ''
+
+class escaping_producer:
+
+	"A producer that escapes a sequence of characters"
+	" Common usage: escaping the CRLF.CRLF sequence in SMTP, NNTP, etc..."
+
+	def __init__ (self, producer, esc_from='\r\n.', esc_to='\r\n..'):
+		self.producer = producer
+		self.esc_from = esc_from
+		self.esc_to = esc_to
+		self.buffer = ''
+		from asynchat import find_prefix_at_end
+		self.find_prefix_at_end = find_prefix_at_end
+
+	def more (self):
+		esc_from = self.esc_from
+		esc_to   = self.esc_to
+
+		buffer = self.buffer + self.producer.more()
+
+		if buffer:
+			buffer = string.replace (buffer, esc_from, esc_to)
+			i = self.find_prefix_at_end (buffer, esc_from)
+			if i:
+				# we found a prefix
+				self.buffer = buffer[-i:]
+				return buffer[:-i]
+			else:
+				# no prefix, return it all
+				self.buffer = ''
+				return buffer
+		else:
+			return buffer

ZServer/medusa/resolver.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#
+
+RCS_ID =  '$Id: resolver.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+# Fast, low-overhead asynchronous name resolver.  uses 'pre-cooked'
+# DNS requests, unpacks only as much as it needs of the reply.
+
+# see rfc1035 for details
+
+import string
+
+VERSION = string.split(RCS_ID)[2]
+
+# header
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      ID                       |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |QR|   Opcode  |AA|TC|RD|RA|   Z    |   RCODE   |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    QDCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    ANCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    NSCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    ARCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+
+# question
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                                               |
+#    /                     QNAME                     /
+#    /                                               /
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     QTYPE                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     QCLASS                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+# build a DNS address request, _quickly_
+def fast_address_request (host, id=0):
+	return (
+		'%c%c' % (chr((id>>8)&0xff),chr(id&0xff))
+		+ '\001\000\000\001\000\000\000\000\000\000%s\000\000\001\000\001' % (
+			string.join (
+				map (
+					lambda part: '%c%s' % (chr(len(part)),part),
+					string.split (host, '.')
+					), ''
+				)
+			)
+		)
+
+def fast_ptr_request (host, id=0):
+	return (
+		'%c%c' % (chr((id>>8)&0xff),chr(id&0xff))
+		+ '\001\000\000\001\000\000\000\000\000\000%s\000\000\014\000\001' % (
+			string.join (
+				map (
+					lambda part: '%c%s' % (chr(len(part)),part),
+					string.split (host, '.')
+					), ''
+				)
+			)
+		)
+
+def unpack_name (r,pos):
+	n = []
+	while 1:
+		ll = ord(r[pos])
+		if (ll&0xc0):
+			# compression
+			pos = (ll&0x3f << 8) + (ord(r[pos+1]))
+		elif ll == 0:
+			break			
+		else:
+			pos = pos + 1
+			n.append (r[pos:pos+ll])
+			pos = pos + ll
+	return string.join (n,'.')
+
+def skip_name (r,pos):
+	s = pos
+	while 1:
+		ll = ord(r[pos])
+		if (ll&0xc0):
+			# compression
+			return pos + 2
+		elif ll == 0:
+			pos = pos + 1
+			break
+		else:
+			pos = pos + ll + 1
+	return pos
+
+def unpack_ttl (r,pos):
+	return reduce (
+		lambda x,y: (x<<8)|y,
+		map (ord, r[pos:pos+4])
+		)
+
+# resource record
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                                               |
+#    /                                               /
+#    /                      NAME                     /
+#    |                                               |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      TYPE                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     CLASS                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      TTL                      |
+#    |                                               |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                   RDLENGTH                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--|
+#    /                     RDATA                     /
+#    /                                               /
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+def unpack_address_reply (r):
+	ancount = (ord(r[6])<<8) + (ord(r[7]))
+	# skip question, first name starts at 12,
+	# this is followed by QTYPE and QCLASS
+	pos = skip_name (r, 12) + 4
+	if ancount:
+		# we are looking very specifically for
+		# an answer with TYPE=A, CLASS=IN (\000\001\000\001)
+		for an in range(ancount):
+			pos = skip_name (r, pos)
+			if r[pos:pos+4] == '\000\001\000\001':
+				return (
+					unpack_ttl (r,pos+4),
+					'%d.%d.%d.%d' % tuple(map(ord,r[pos+10:pos+14]))
+					)
+			# skip over TYPE, CLASS, TTL, RDLENGTH, RDATA
+			pos = pos + 8
+			rdlength = (ord(r[pos])<<8) + (ord(r[pos+1]))
+			pos = pos + 2 + rdlength
+		return 0, None
+	else:
+		return 0, None
+
+def unpack_ptr_reply (r):
+	ancount = (ord(r[6])<<8) + (ord(r[7]))
+	# skip question, first name starts at 12,
+	# this is followed by QTYPE and QCLASS
+	pos = skip_name (r, 12) + 4
+	if ancount:
+		# we are looking very specifically for
+		# an answer with TYPE=PTR, CLASS=IN (\000\014\000\001)
+		for an in range(ancount):
+			pos = skip_name (r, pos)
+			if r[pos:pos+4] == '\000\014\000\001':
+				return (
+					unpack_ttl (r,pos+4),
+					unpack_name (r, pos+10)
+					)
+			# skip over TYPE, CLASS, TTL, RDLENGTH, RDATA
+			pos = pos + 8
+			rdlength = (ord(r[pos])<<8) + (ord(r[pos+1]))
+			pos = pos + 2 + rdlength
+		return 0, None
+	else:
+		return 0, None
+
+
+from counter import counter
+import asyncore
+import socket
+import sys
+
+# This is a UDP (datagram) resolver.
+
+#
+# It may be useful to implement a TCP resolver.  This would presumably
+# give us more reliable behavior when things get too busy.  A TCP
+# client would have to manage the connection carefully, since the
+# server is allowed to close it at will (the RFC recommends closing
+# after 2 minutes of idle time).
+#
+# Note also that the TCP client will have to prepend each request
+# with a 2-byte length indicator (see rfc1035).
+#
+
+class resolver (asyncore.dispatcher):
+	id = counter()
+	def __init__ (self, server='127.0.0.1'):
+		asyncore.dispatcher.__init__ (self)
+		self.create_socket (socket.AF_INET, socket.SOCK_DGRAM)
+		self.server = server
+		self.request_map = {}
+
+	def writable (self):
+		return 0
+
+	def log (self, *args):
+		pass
+
+	def handle_close (self):
+		print 'closing!'
+		self.close()
+
+	def get_id (self):
+		return (self.id.as_long() % (1<<16))
+
+	def resolve (self, host, callback):
+		self.socket.sendto (
+			fast_address_request (host, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, unpack_address_reply, callback
+		self.id.increment()
+
+	def resolve_ptr (self, host, callback):
+		ip = string.split (host, '.')
+		ip.reverse()
+		ip = string.join (ip, '.') + '.in-addr.arpa'
+		self.socket.sendto (
+			fast_ptr_request (ip, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, unpack_ptr_reply, callback
+		self.id.increment()
+
+	def handle_read (self):
+		reply, whence = self.socket.recvfrom (512)
+		# for security reasons we may want to double-check
+		# that <whence> is the server we sent the request to.
+		id = (ord(reply[0])<<8) + ord(reply[1])
+		if self.request_map.has_key (id):
+			host, unpack, callback = self.request_map[id]
+			del self.request_map[id]
+			ttl, answer = unpack (reply)
+			try:
+				callback (host, ttl, answer)
+			except:
+				t,v,tb = sys.exc_info()
+				(file,fun,line), tbinfo = asyncore.compact_traceback (t,v,tb)
+				print t,v
+				print tbinfo
+
+class rbl (resolver):
+
+	def resolve_maps (self, host, callback):
+		ip = string.split (host, '.')
+		ip.reverse()
+		ip = string.join (ip, '.') + '.rbl.maps.vix.com'
+		self.socket.sendto (
+			fast_ptr_request (ip, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, self.check_reply, callback
+		self.id.increment()
+	
+	def check_reply (self, r):
+		# we only need to check RCODE.
+		rcode = (ord(r[3])&0xf)
+		print 'MAPS RBL; RCODE =%02x' % rcode
+		print repr(r)
+		return 0, rcode # (ttl, answer)
+
+import time
+
+class hooked_callback:
+	def __init__ (self, hook, callback):
+		self.hook, self.callback = hook, callback
+
+	def __call__ (self, *args):
+		apply (self.hook, args)
+		apply (self.callback, args)
+
+class caching_resolver (resolver):
+	"Cache DNS queries.  Will need to honor the TTL value in the replies"
+
+	def __init__ (*args):
+		apply (resolver.__init__, args)
+		self = args[0]
+		self.cache = {}
+		self.forward_requests = counter()
+		self.reverse_requests = counter()
+		self.cache_hits = counter()
+
+	def resolve (self, host, callback):
+		self.forward_requests.increment()
+		if self.cache.has_key (host):
+			when, ttl, answer = self.cache[host]
+			# ignore TTL for now
+			callback (host, ttl, answer)
+			self.cache_hits.increment()
+		else:
+			resolver.resolve (
+				self,
+				host,
+				hooked_callback (
+					self.callback_hook,
+					callback
+					)
+				)
+			
+	def resolve_ptr (self, host, callback):
+		self.reverse_requests.increment()
+		if self.cache.has_key (host):
+			when, ttl, answer = self.cache[host]
+			# ignore TTL for now
+			callback (host, ttl, answer)
+			self.cache_hits.increment()
+		else:
+			resolver.resolve_ptr (
+				self,
+				host,
+				hooked_callback (
+					self.callback_hook,
+					callback
+					)
+				)
+
+	def callback_hook (self, host, ttl, answer):
+		self.cache[host] = time.time(), ttl, answer
+
+	SERVER_IDENT = 'Caching DNS Resolver (V%s)' % VERSION
+
+	def status (self):
+		import status_handler
+		import producers
+		return producers.simple_producer (
+			'<h2>%s</h2>'					% self.SERVER_IDENT
+			+ '<br>Server: %s'				% self.server
+			+ '<br>Cache Entries: %d'		% len(self.cache)
+			+ '<br>Outstanding Requests: %d' % len(self.request_map)
+			+ '<br>Forward Requests: %s'	% self.forward_requests
+			+ '<br>Reverse Requests: %s'	% self.reverse_requests
+			+ '<br>Cache Hits: %s'			% self.cache_hits
+			)
+
+#test_reply = """\000\000\205\200\000\001\000\001\000\002\000\002\006squirl\011nightmare\003com\000\000\001\000\001\300\014\000\001\000\001\000\001Q\200\000\004\315\240\260\005\011nightmare\003com\000\000\002\000\001\000\001Q\200\000\002\300\014\3006\000\002\000\001\000\001Q\200\000\015\003ns1\003iag\003net\000\300\014\000\001\000\001\000\001Q\200\000\004\315\240\260\005\300]\000\001\000\001\000\000\350\227\000\004\314\033\322\005"""
+# def test_unpacker ():
+# 	print unpack_address_reply (test_reply)
+# 
+# import time
+# class timer:
+# 	def __init__ (self):
+# 		self.start = time.time()
+# 	def end (self):
+# 		return time.time() - self.start
+# 
+# # I get ~290 unpacks per second for the typical case, compared to ~48
+# # using dnslib directly.  also, that latter number does not include
+# # picking the actual data out.
+# 
+# def benchmark_unpacker():
+# 
+# 	r = range(1000)
+# 	t = timer()
+# 	for i in r:
+# 		unpack_address_reply (test_reply)
+# 	print '%.2f unpacks per second' % (1000.0 / t.end())
+
+if __name__ == '__main__':
+	import sys
+	if len(sys.argv) == 1:
+		print 'usage: %s [-r] [-s <server_IP>] host [host ...]' % sys.argv[0]
+		sys.exit(0)
+	elif ('-s' in sys.argv):
+		i = sys.argv.index('-s')
+		server = sys.argv[i+1]
+		del sys.argv[i:i+2]
+	else:
+		server = '127.0.0.1'
+
+	if ('-r' in sys.argv):
+		reverse = 1
+		i = sys.argv.index('-r')
+		del sys.argv[i]
+	else:
+		reverse = 0
+
+	if ('-m' in sys.argv):
+		maps = 1
+		sys.argv.remove ('-m')
+	else:
+		maps = 0
+
+	if maps:
+		r = rbl (server)
+	else:
+		r = caching_resolver(server)
+
+	count = len(sys.argv) - 1
+
+	def print_it (host, ttl, answer):
+		global count
+		print '%s: %s' % (host, answer)
+		count = count - 1
+		if not count:
+			r.close()
+
+	for host in sys.argv[1:]:
+		if reverse:
+			r.resolve_ptr (host, print_it)
+		elif maps:
+			r.resolve_maps (host, print_it)
+		else:
+			r.resolve (host, print_it)
+
+	# hooked asyncore.loop()
+	while asyncore.socket_map:
+		asyncore.poll (30.0)
+		print 'requests outstanding: %d' % len(r.request_map)

ZServer/medusa/status_handler.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+#			
+# medusa status extension
+#
+
+import string
+import time
+import regex
+
+import asyncore
+import http_server
+import medusa_gif
+import producers
+from counter import counter
+
+START_TIME = long(time.time())
+
+# split a uri
+# <path>;<params>?<query>#<fragment>
+path_regex = regex.compile (
+#        path        params        query       fragment
+	'\\([^;?#]*\\)\\(;[^?#]*\\)?\\(\\?[^#]*\)?\(#.*\)?'
+	)
+
+def split_path (path):
+	if path_regex.match (path) != len(path):
+		raise ValueError, "bad path"
+	else:
+		return map (lambda i,r=path_regex: r.group(i), range(1,5))
+
+class status_extension:
+	hit_counter = counter()
+
+	hyper_regex = regex.compile ('/status/object/\([0-9]+\)/.*')
+
+	def __init__ (self, objects, regexp='/status\(/.*\)?'):
+		self.objects = objects
+		self.regexp = regex.compile (regexp)
+		self.hyper_objects = []
+		for object in objects:
+			self.register_hyper_object (object)
+
+	def __repr__ (self):
+		return '<Status Extension (%s hits) at %x>' % (
+			self.hit_counter,
+			id(self)
+			)
+
+	def match (self, request):
+		[path, params, query, fragment] = split_path (request.uri)
+		return self.regexp.match (path) == len(path)
+
+	# Possible Targets:
+	# /status
+	# /status/channel_list
+	# /status/medusa.gif
+
+	# can we have 'clickable' objects?
+	# [yes, we can use id(x) and do a linear search]
+
+	# Dynamic producers:
+	# HTTP/1.0: we must close the channel, because it's dynamic output
+	# HTTP/1.1: we can use the chunked transfer-encoding, and leave
+	#   it open.
+
+	def handle_request (self, request):
+		[path, params, query, fragment] = split_path (request.uri)
+		self.hit_counter.increment()
+		if path == '/status':
+			up_time = string.join (english_time (long(time.time()) - START_TIME))
+			request['Content-Type'] = 'text/html'
+			request.push (
+				'<html>'
+				'<title>Medusa Status Reports</title>'
+				'<body bgcolor="#ffffff">'
+				'<h1>Medusa Status Reports</h1>'
+				'<b>Up:</b> %s' % up_time
+				)
+			for i in range(len(self.objects)):
+				request.push (self.objects[i].status())
+				request.push ('<hr>\r\n')
+			request.push (
+				'<p><a href="/status/channel_list">Channel List</a>'
+				'<hr>'
+				'<img src="/status/medusa.gif" align=right width=%d height=%d>' % (
+					medusa_gif.width,
+					medusa_gif.height
+					) +
+				'</body></html>'
+				)
+			request.done()
+
+		elif path == '/status/channel_list':
+			request['Content-Type'] = 'text/html'
+			request.push ('<html><body>')
+			request.push(channel_list_producer())
+			request.push (
+				'<hr>'
+				'<img src="/status/medusa.gif" align=right width=%d height=%d>' % (
+					medusa_gif.width,
+					medusa_gif.height
+					) +
+				'</body></html>'
+				)
+			request.done()
+
+		elif path == '/status/medusa.gif':
+			request['Content-Type'] = 'image/gif'
+			request['Content-Length'] = len(medusa_gif.data)
+			request.push (medusa_gif.data)
+			request.done()
+
+		elif path == '/status/close_zombies':
+			message = (
+				'<h2>Closing all zombie http client connections...</h2>'
+				'<p><a href="/status">Back to the status page</a>'
+				)
+			request['Content-Type'] = 'text/html'
+			request['Content-Length'] = len (message)
+			request.push (message)
+			now = int (time.time())
+			for channel in asyncore.socket_map.keys():
+				if channel.__class__ == http_server.http_channel:
+					if channel != request.channel:
+						if (now - channel.creation_time) > channel.zombie_timeout:
+							channel.close()
+			request.done()
+
+		# Emergency Debug Mode
+		# If a server is running away from you, don't KILL it!
+		# Move all the AF_INET server ports and perform an autopsy...
+		# [disabled by default to protect the innocent]
+		#elif path == '/status/emergency_debug':
+		elif 0:
+			request.push ('<html>Moving All Servers...</html>')
+			request.done()
+			for channel in asyncore.socket_map.keys():
+				if channel.accepting:
+					if type(channel.addr) is type(()):
+						ip, port = channel.addr
+						channel.socket.close()
+						channel.del_channel()
+						channel.addr = (ip, port+10000)
+						fam, typ = channel.family_and_type
+						channel.create_socket (fam, typ)
+						channel.set_reuse_addr()
+						channel.bind (channel.addr)
+						channel.listen(5)
+
+		elif self.hyper_regex.match (path) != -1:
+			oid = string.atoi (self.hyper_regex.group (1))
+			for object in self.hyper_objects:
+				if id (object) == oid:
+					if hasattr (object, 'hyper_respond'):
+						object.hyper_respond (self, path, request)
+		else:
+			request.error (404)
+			return
+
+	def status (self):
+		return producers.simple_producer (
+			'<li>Status Extension <b>Hits</b> : %s' % self.hit_counter
+			)
+
+	def register_hyper_object (self, object):
+		if not object in self.hyper_objects:
+			self.hyper_objects.append (object)
+
+import logger
+
+class logger_for_status (logger.tail_logger):
+
+	def status (self):
+		return 'Last %d log entries for: %s' % (
+			len (self.messages),
+			html_repr (self)
+			)
+
+	def hyper_respond (self, sh, path, request):
+		request['Content-Type'] = 'text/plain'
+		messages = self.messages[:]
+		messages.reverse()
+		request.push (lines_producer (messages))
+		request.done()
+
+class lines_producer:
+	def __init__ (self, lines):
+		self.lines = lines
+
+	def ready (self):
+		return len(self.lines)
+
+	def more (self):
+		if self.lines:
+			chunk = self.lines[:50]
+			self.lines = self.lines[50:]
+			return string.join (chunk, '\r\n') + '\r\n'
+		else:
+			return ''
+
+class channel_list_producer (lines_producer):
+	def __init__ (self):
+		channel_reprs = map (
+			lambda x: '&lt;' + repr(x)[1:-1] + '&gt;',
+			asyncore.socket_map.keys()
+			)
+		channel_reprs.sort()
+		lines_producer.__init__ (
+			self,
+			['<h1>Active Channel List</h1>',
+			 '<pre>'
+			 ] + channel_reprs + [
+				 '</pre>',
+				 '<p><a href="/status">Status Report</a>'
+				 ]
+			)
+
+
+# this really needs a full-blown quoter...
+def sanitize (s):
+	if '<' in s:
+		s = string.join (string.split (s, '<'), '&lt;')
+	if '>' in s:
+		s = string.join (string.split (s, '>'), '&gt;')
+	return s
+
+def html_repr (object):
+	so = sanitize (repr (object))
+	if hasattr (object, 'hyper_respond'):
+		return '<a href="/status/object/%d/">%s</a>' % (id (object), so)
+	else:
+		return so
+
+def html_reprs (list, front='', back=''):
+	reprs = map (
+		lambda x,f=front,b=back: '%s%s%s' % (f,x,b),
+		map (lambda x: sanitize (html_repr(x)), list)
+		)
+	reprs.sort()
+	return reprs
+
+# for example, tera, giga, mega, kilo
+# p_d (n, (1024, 1024, 1024, 1024))
+# smallest divider goes first - for example
+# minutes, hours, days
+# p_d (n, (60, 60, 24))
+
+def progressive_divide (n, parts):
+	result = []
+	for part in parts:
+		n, rem = divmod (n, part)
+		result.append (rem)
+	result.append (n)
+	return result
+
+# b,k,m,g,t
+def split_by_units (n, units, dividers, format_string):
+	divs = progressive_divide (n, dividers)
+	result = []
+	for i in range(len(units)):
+		if divs[i]:
+			result.append (format_string % (divs[i], units[i]))
+	result.reverse()
+	if not result:
+		return [format_string % (0, units[0])]
+	else:
+		return result
+
+def english_bytes (n):
+	return split_by_units (
+		n,
+		('','K','M','G','T'),
+		(1024, 1024, 1024, 1024, 1024),
+		'%d %sB'
+		)
+
+def english_time (n):
+	return split_by_units (
+		n,
+		('secs', 'mins', 'hours', 'days', 'weeks', 'years'),
+		(         60,     60,      24,     7,       52),
+		'%d %s'
+		)

lib/python/ZServer/medusa/counter.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+# It is tempting to add an __int__ method to this class, but it's not
+# a good idea.  This class tries to gracefully handle integer
+# overflow, and to hide this detail from both the programmer and the
+# user.  Note that the __str__ method can be relied on for printing out
+# the value of a counter:
+#
+# >>> print 'Total Client: %s' % self.total_clients
+#
+# If you need to do arithmetic with the value, then use the 'as_long'
+# method, the use of long arithmetic is a reminder that the counter
+# will overflow.
+
+class counter:
+	"general-purpose counter"
+
+	def __init__ (self, initial_value=0):
+		self.value = initial_value
+	
+	def increment (self, delta=1):
+		result = self.value
+		try:
+			self.value = self.value + delta
+		except OverflowError:
+			self.value = long(self.value) + delta
+		return result
+
+	def decrement (self, delta=1):
+		result = self.value
+		try:
+			self.value = self.value - delta
+		except OverflowError:
+			self.value = long(self.value) - delta
+		return result
+
+	def as_long (self):
+		return long(self.value)
+
+	def __nonzero__ (self):
+		return self.value != 0
+
+	def __repr__ (self):
+		return '<counter value=%s at %x>' % (self.value, id(self))
+
+	def __str__ (self):
+		return str(long(self.value))[:-1]

lib/python/ZServer/medusa/default_handler.py

+# -*- Mode: Python; tab-width: 4 -*-
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#	Copyright 1997 by Sam Rushing
+#						 All Rights Reserved.
+#
+# This software is provided free for non-commercial use.  If you are
+# interested in using this software in a commercial context, or in
+# purchasing support, please contact the author.
+
+RCS_ID = '$Id: default_handler.py,v 1.1 1999/01/09 03:17:31 amos Exp $'
+
+# standard python modules
+import os
+import regex
+import posixpath
+import stat
+import string
+import time
+
+# medusa modules
+import http_date
+import http_server
+import mime_type_table
+import status_handler
+import producers
+
+# from <lib/urllib.py>
+_quoteprog = regex.compile('%[0-9a-fA-F][0-9a-fA-F]')
+def unquote(s):
+	i = 0
+	n = len(s)
+	res = []
+	while 0 <= i < n:
+		j = _quoteprog.search(s, i)
+		if j < 0:
+			res.append(s[i:])
+			break
+		res.append(s[i:j] + chr(string.atoi(s[j+1:j+3], 16)))
+		i = j+3
+	return string.join (res, '')
+
+# split a uri
+# <path>;<params>?<query>#<fragment>
+path_regex = regex.compile (
+#        path        params        query       fragment
+	'\\([^;?#]*\\)\\(;[^?#]*\\)?\\(\\?[^#]*\)?\(#.*\)?'
+	)
+
+def split_path (path):
+	if path_regex.match (path) != len(path):
+		raise ValueError, "bad path"
+	else:
+		return map (lambda i,r=path_regex: r.group(i), range(1,5))
+
+# This is the 'default' handler.  it implements the base set of
+# features expected of a simple file-delivering HTTP server.  file
+# services are provided through a 'filesystem' object, the very same
+# one used by the FTP server.
+#
+# You can replace or modify this handler if you want a non-standard
+# HTTP server.  You can also derive your own handler classes from
+# it.
+#
+# support for handling POST requests is available in the derived
+# class <default_with_post_handler>, defined below.
+#
+
+from counter import counter
+
+class default_handler:
+
+	valid_commands = ['get', 'head']
+
+	IDENT = 'Default HTTP Request Handler'
+
+	# Pathnames that are tried when a URI resolves to a directory name
+	directory_defaults = [
+		'index.html',
+		'default.html'
+		]
+
+	default_file_producer = producers.file_producer
+
+	def __init__ (self, filesystem):
+		self.filesystem = filesystem
+		# count total hits
+		self.hit_counter = counter()
+		# count file deliveries
+		self.file_counter = counter()
+		# count cache hits
+		self.cache_counter = counter()
+
+	hit_counter = 0
+
+	def __repr__ (self):
+		return '<%s (%s hits) at %x>' % (
+			self.IDENT,
+			self.hit_counter,
+			id (self)
+			)
+
+	# always match, since this is a default
+	def match (self, request):
+		return 1
+
+	# handle a file request, with caching.
+
+	def handle_request (self, request):
+
+		if request.command not in self.valid_commands:
+			request.error (400) # bad request
+			return
+
+		self.hit_counter.increment()
+
+		[path, params, query, fragment] = split_path (request.uri)
+
+		# unquote path if necessary (thanks to Skip Montaro for pointing
+		# out that we must unquote in piecemeal fashion).
+		if '%' in path:
+			path = unquote (path)
+
+		# strip off all leading slashes
+		while path and path[0] == '/':
+			path = path[1:]
+
+		if self.filesystem.isdir (path):
+			if path and path[-1] != '/':
+				request['Location'] = 'http://%s/%s/' % (
+					request.channel.server.server_name,
+					path
+					)
+				request.error (301)
+				return
+
+			# we could also generate a directory listing here,
+			# may want to move this into another method for that
+			# purpose
+			found = 0
+			if path and path[-1] != '/':
+				path = path + '/'
+			for default in self.directory_defaults:
+				p = path + default
+				if self.filesystem.isfile (p):
+					path = p
+					found = 1
+					break
+			if not found:
+				request.error (404) # Not Found 
+				return
+
+		elif not self.filesystem.isfile (path):
+			request.error (404) # Not Found
+			return
+
+		file_length = self.filesystem.stat (path)[stat.ST_SIZE]
+
+		ims = get_header (IF_MODIFIED_SINCE, request.header)
+
+		length_match = 1
+		if ims:
+			length = IF_MODIFIED_SINCE.group(4)
+			if length:
+				try:
+					length = string.atoi (length)
+					if length != file_length:
+						length_match = 0
+				except:
+					pass
+
+		ims_date = 0
+
+		if ims:
+			ims_date = http_date.parse_http_date (ims)
+
+		try:
+			mtime = self.filesystem.stat (path)[stat.ST_MTIME]
+		except:
+			request.error (404)
+			return
+
+		if length_match and ims_date:
+			if mtime <= ims_date:
+				request.reply_code = 304
+				request.done()
+				self.cache_counter.increment()
+				return
+		try:
+			file = self.filesystem.open (path, 'rb')
+		except IOError:
+			request.error (404)
+			return
+
+		request['Last-Modified'] = http_date.build_http_date (mtime)
+		request['Content-Length'] = file_length
+		self.set_content_type (path, request)
+
+		if request.command == 'get':
+			request.push (self.default_file_producer (file))
+
+		self.file_counter.increment()
+		request.done()
+
+	def set_content_type (self, path, request):
+		ext = get_extension (path)
+		if mime_type_table.content_type_map.has_key (ext):
+			request['Content-Type'] = mime_type_table.content_type_map[ext]
+		else:
+			# TODO: test a chunk off the front of the file for 8-bit
+			# characters, and use application/octet-stream instead.
+			request['Content-Type'] = 'text/plain'
+
+	def status (self):
+		return producers.simple_producer (
+			'<li>%s' % status_handler.html_repr (self)
+			+ '<ul>'
+			+ '  <li><b>Total Hits:</b> %s'			% self.hit_counter
+			+ '  <li><b>Files Delivered:</b> %s'	% self.file_counter
+			+ '  <li><b>Cache Hits:</b> %s'			% self.cache_counter
+			+ '</ul>'
+			)
+
+ACCEPT = regex.compile ('Accept: \(.*\)', regex.casefold)
+
+# HTTP/1.0 doesn't say anything about the "; length=nnnn" addition
+# to this header.  I suppose it's purpose is to avoid the overhead
+# of parsing dates...
+IF_MODIFIED_SINCE = regex.compile (
+	'If-Modified-Since: \([^;]+\)\(\(; length=\([0-9]+\)$\)\|$\)',
+	regex.casefold
+	)
+
+USER_AGENT = regex.compile ('User-Agent: \(.*\)', regex.casefold)
+
+boundary_chars = "A-Za-z0-9'()+_,./:=?-"
+
+CONTENT_TYPE = regex.compile (
+	'Content-Type: \([^;]+\)\(\(; boundary=\([%s]+\)$\)\|$\)' % boundary_chars,
+	regex.casefold
+	)
+
+get_header = http_server.get_header
+
+def get_extension (path):
+	dirsep = string.rfind (path, '/')
+	dotsep = string.rfind (path, '.')
+	if dotsep > dirsep:
+		return path[dotsep+1:]
+	else:
+		return ''

lib/python/ZServer/medusa/http_date.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+import regex
+import string
+import time
+
+def concat (*args):
+	return string.joinfields (args, '')
+
+def join (seq, field=' '):
+	return string.joinfields (seq, field)
+
+def group (s):
+	return '\\(' + s + '\\)'
+
+short_days = ['sun','mon','tue','wed','thu','fri','sat']
+long_days = ['sunday','monday','tuesday','wednesday','thursday','friday','saturday']
+
+short_day_reg = group (join (short_days, '\\|'))
+long_day_reg = group (join (long_days, '\\|'))
+
+daymap = {}
+for i in range(7):
+	daymap[short_days[i]] = i
+	daymap[long_days[i]] = i
+
+hms_reg = join (3 * [group('[0-9][0-9]')], ':')
+
+months = ['jan','feb','mar','apr','may','jun','jul','aug','sep','oct','nov','dec']
+
+monmap = {}
+for i in range(12):
+	monmap[months[i]] = i+1
+
+months_reg = group (join (months, '\\|'))
+
+# From draft-ietf-http-v11-spec-07.txt/3.3.1
+#       Sun, 06 Nov 1994 08:49:37 GMT  ; RFC 822, updated by RFC 1123
+#       Sunday, 06-Nov-94 08:49:37 GMT ; RFC 850, obsoleted by RFC 1036
+#       Sun Nov  6 08:49:37 1994       ; ANSI C's asctime() format
+
+# rfc822 format
+rfc822_date = join (
+	[concat (short_day_reg,','),	# day
+	 group('[0-9][0-9]?'),			# date
+	 months_reg,					# month
+	 group('[0-9]+'),				# year
+	 hms_reg,						# hour minute second
+	 'gmt'
+	 ],
+	' '
+	)
+
+rfc822_reg = regex.compile (rfc822_date)
+
+def unpack_rfc822 ():
+	g = rfc822_reg.group
+	a = string.atoi
+	return (
+		a(g(4)),	   	# year
+		monmap[g(3)],	# month
+		a(g(2)),		# day
+		a(g(5)),		# hour
+		a(g(6)),		# minute
+		a(g(7)),		# second
+		0,
+		0,
+		0
+		)
+
+# rfc850 format
+rfc850_date = join (
+	[concat (long_day_reg,','),
+	 join (
+		 [group ('[0-9][0-9]?'),
+		  months_reg,
+		  group ('[0-9]+')
+		  ],
+		 '-'
+		 ),
+	 hms_reg,
+	 'gmt'
+	 ],
+	' '
+	)
+
+rfc850_reg = regex.compile (rfc850_date)
+# they actually unpack the same way
+def unpack_rfc850 ():
+	g = rfc850_reg.group
+	a = string.atoi
+	return (
+		a(g(4)),	   	# year
+		monmap[g(3)],	# month
+		a(g(2)),		# day
+		a(g(5)),		# hour
+		a(g(6)),		# minute
+		a(g(7)),		# second
+		0,
+		0,
+		0
+		)
+
+# parsdate.parsedate	- ~700/sec.
+# parse_http_date    	- ~1333/sec.
+
+def build_http_date (when):
+	return time.strftime ('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(when))
+
+def parse_http_date (d):
+	d = string.lower (d)
+	# Thanks to Craig Silverstein <csilvers@google.com> for pointing
+	# out the DST discrepancy
+	if time.daylight:
+		tz = time.altzone
+	else:
+		tz = time.timezone
+	# rfc850 comes first, netscape uses it. <frown>
+	if rfc850_reg.match (d) == len(d):
+		return int (time.mktime (unpack_rfc850()) - tz)
+	elif rfc822_reg.match (d) == len(d):
+		return int (time.mktime (unpack_rfc822()) - tz)
+	else:
+		return 0

lib/python/ZServer/medusa/http_server.py

+#! /usr/local/bin/python
+# -*- Mode: Python; tab-width: 4 -*-
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#	Copyright 1996, 1997 by Sam Rushing
+#						 All Rights Reserved.
+#
+# This software is provided free for non-commercial use.  If you are
+# interested in using this software in a commercial context, or in
+# purchasing support, please contact the author.
+
+RCS_ID =  '$Id: http_server.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+# python modules
+import os
+import regex
+import socket
+import stat
+import string
+import sys
+import time
+
+# async modules
+import asyncore
+import asynchat
+
+# medusa modules
+import http_date
+import producers
+import status_handler
+import logger
+
+VERSION_STRING = string.split(RCS_ID)[2]
+
+from counter import counter
+
+# ===========================================================================
+#							Request Object
+# ===========================================================================
+
+class http_request:
+
+	# default reply code
+	reply_code = 200
+
+	request_counter = counter()
+
+	# Whether to automatically use chunked encoding when
+	# 
+	#   HTTP version is 1.1
+	#   Content-Length is not set
+	#   Chunked encoding is not already in effect
+	#
+	# If your clients are having trouble, you might want to disable this.
+	use_chunked = 1
+	
+
+	# by default, this request object ignores user data.
+	collector = None
+
+	def __init__ (self, *args):
+		# unpack information about the request
+		(self.channel, self.request,
+		 self.command, self.uri, self.version,
+		 self.header) = args
+
+		self.outgoing = fifo()
+		self.reply_headers = {
+			'Server'	: 'Medusa/%s' % VERSION_STRING,
+			'Date'		: http_date.build_http_date (time.time())
+			}
+		self.request_number = http_request.request_counter.increment()
+
+	# --------------------------------------------------
+	# reply header management
+	# --------------------------------------------------
+	def __setitem__ (self, key, value):
+		self.reply_headers[key] = value
+
+	def __getitem__ (self, key):
+		return self.reply_headers[key]
+
+	def has_key (self, key):
+		return self.reply_headers.has_key (key)
+
+	def build_reply_header (self):
+		return string.join (
+			[self.response(self.reply_code)] + map (
+				lambda x: '%s: %s' % x,
+				self.reply_headers.items()
+				),
+			'\r\n'
+			) + '\r\n\r\n'
+
+	# --------------------------------------------------
+	# user data
+	# --------------------------------------------------
+
+	def collect_incoming_data (self, data):
+		if self.collector:
+			self.collector.collect_incoming_data (data)
+		else:
+			sys.stderr.write (
+				'warning: dropping %d bytes of incoming request data\n' % len(data)
+				)
+
+	def found_terminator (self):
+		if self.collector:
+			self.collector.collect_incoming_data (data)
+		else:
+			sys.stderr.write (
+				'warning: unexpected end-of-record for incoming request\n'
+				)
+
+	def push (self, producer):
+		if type(producer) == type(''):
+			self.outgoing.push (producers.simple_producer (producer))
+		else:
+			self.outgoing.push (producer)
+
+	def response (self, code=200):
+		message = self.responses[code]
+		self.reply_code = code
+		return 'HTTP/%s %d %s' % (self.version, code, message)
+
+	def error (self, code):
+		self.reply_code = code
+		message = self.responses[code]
+		s = self.DEFAULT_ERROR_MESSAGE % {
+			'code': code,
+			'message': message,
+			}
+		self['Content-Length'] = len(s)
+		self['Content-Type'] = 'text/html'
+		# make an error reply
+		self.push (s)
+		self.done()
+
+	# can also be used for empty replies
+	reply_now = error
+
+	def done (self):
+		"finalize this transaction - send output to the http channel"
+
+		# ----------------------------------------
+		# persistent connection management
+		# ----------------------------------------
+
+		#  --- BUCKLE UP! ----
+
+		connection = string.lower (get_header (CONNECTION, self.header))
+
+		close_it = 0
+		wrap_in_chunking = 0
+
+		if self.version == '1.0':
+			if connection == 'keep-alive':
+				if not self.has_key ('Content-Length'):
+					close_it = 1
+				else:
+					self['Connection'] = 'Keep-Alive'
+			else:
+				close_it = 1
+		elif self.version == '1.1':
+			if connection == 'close':
+				close_it = 1
+			elif not self.has_key ('Content-Length'):
+				if self.has_key ('Transfer-Encoding'):
+					if not self['Transfer-Encoding'] == 'chunked':
+						close_it = 1
+				elif self.use_chunked:
+					self['Transfer-Encoding'] = 'chunked'
+					wrap_in_chunking = 1
+				else:
+					close_it = 1
+					
+		outgoing_header = producers.simple_producer (self.build_reply_header())
+
+		if close_it:
+			self['Connection'] = 'close'
+
+		if wrap_in_chunking:
+			outgoing_producer = producers.chunked_producer (
+				producers.composite_producer (self.outgoing)
+				)
+			# prepend the header
+			outgoing_producer = producers.composite_producer (
+				fifo([outgoing_header, outgoing_producer])
+				)
+		else:
+			# prepend the header
+			self.outgoing.push_front (outgoing_header)
+			outgoing_producer = producers.composite_producer (self.outgoing)
+
+		# apply a few final transformations to the output
+		self.channel.push_with_producer (
+			# globbing gives us large packets
+			producers.globbing_producer (
+				# hooking lets us log the number of bytes sent
+				producers.hooked_producer (
+					outgoing_producer,
+					self.log
+					)
+				)
+			)
+
+		self.channel.current_request = None
+
+		if close_it:
+			self.channel.close_when_done()
+
+	def log (self, bytes):
+		print 'request %3d: %s %d bytes' % (
+			self.request_counter,
+			self.request,
+			bytes
+			)
+
+	def log_date_string (self, when):
+		return time.strftime (
+			'%d/%b/%Y:%H:%M:%S ',
+			time.gmtime(when)
+			) + tz_for_log
+
+	def log (self, bytes):
+		self.channel.server.logger.log (
+			self.channel.addr[0],
+			'%d - - [%s] "%s" %d %d\n' % (
+				self.channel.addr[1],
+				self.log_date_string (time.time()),
+				self.request,
+				self.reply_code,
+				bytes
+				)
+			)
+
+	responses = {
+		100: "Continue",
+		101: "Switching Protocols",
+		200: "OK",
+		201: "Created",
+		202: "Accepted",
+		203: "Non-Authoritative Information",
+		204: "No Content",
+		205: "Reset Content",
+		206: "Partial Content",
+		300: "Multiple Choices",
+		301: "Moved Permanently",
+		302: "Moved Temporarily",
+		303: "See Other",
+		304: "Not Modified",
+		305: "Use Proxy",
+		400: "Bad Request",
+		401: "Unauthorized",
+		402: "Payment Required",
+		403: "Forbidden",
+		404: "Not Found",
+		405: "Method Not Allowed",
+		406: "Not Acceptable",
+		407: "Proxy Authentication Required",
+		408: "Request Time-out",
+		409: "Conflict",
+		410: "Gone",
+		411: "Length Required",
+		412: "Precondition Failed",
+		413: "Request Entity Too Large",
+		414: "Request-URI Too Large",
+		415: "Unsupported Media Type",
+		500: "Internal Server Error",
+		501: "Not Implemented",
+		502: "Bad Gateway",
+		503: "Service Unavailable",
+		504: "Gateway Time-out",
+		505: "HTTP Version not supported"
+		}
+
+	# Default error message
+	DEFAULT_ERROR_MESSAGE = string.join (
+		['<head>',
+		 '<title>Error response</title>',
+		 '</head>',
+		 '<body>',
+		 '<h1>Error response</h1>',
+		 '<p>Error code %(code)d.',
+		 '<p>Message: %(message)s.',
+		 '</body>',
+		 ''
+		 ],
+		'\r\n'
+		)
+
+
+# ===========================================================================
+#						 HTTP Channel Object
+# ===========================================================================
+
+class http_channel (asynchat.async_chat):
+
+	# use a larger default output buffer
+	ac_out_buffer_size = 1<<16
+
+	current_request = None
+	channel_counter = counter()
+
+	def __init__ (self, server, conn, addr):
+		self.channel_number = http_channel.channel_counter.increment()
+		self.request_counter = counter()
+		asynchat.async_chat.__init__ (self, conn)
+		self.server = server
+		self.addr = addr
+		self.set_terminator ('\r\n\r\n')
+		self.in_buffer = ''
+		self.creation_time = int (time.time())
+		self.check_maintenance()
+
+	def __repr__ (self):
+		ar = asynchat.async_chat.__repr__(self)[1:-1]
+		return '<%s channel#: %s requests:%s>' % (
+			ar,
+			self.channel_number,
+			self.request_counter
+			)
+
+	# Channel Counter, Maintenance Interval...
+	maintenance_interval = 500
+
+	def check_maintenance (self):
+		if not self.channel_number % self.maintenance_interval:
+			self.maintenance()
+
+	def maintenance (self):
+		self.kill_zombies()
+
+	# 30-minute zombie timeout.  status_handler also knows how to kill zombies.
+	zombie_timeout = 30 * 60
+
+	def kill_zombies (self):
+		now = int (time.time())
+		for channel in asyncore.socket_map.keys():
+			if channel.__class__ == http_channel:
+				if (now - channel.creation_time) > channel.zombie_timeout:
+					channel.close()
+
+	# --------------------------------------------------
+	# send/recv overrides, good place for instrumentation.
+	# --------------------------------------------------
+	
+	# this information needs to get into the request object,
+	# so that it may log correctly.
+	def send (self, data):
+		result = asynchat.async_chat.send (self, data)
+		self.server.bytes_out.increment (len(data))
+		return result
+
+	def recv (self, buffer_size):
+		result = asynchat.async_chat.recv (self, buffer_size)
+		self.server.bytes_in.increment (len(result))
+		return result
+
+	def log (self, *args):
+		pass
+
+	# --------------------------------------------------
+	# async_chat methods
+	# --------------------------------------------------
+
+	def collect_incoming_data (self, data):
+		if self.current_request:
+			# we are receiving data (probably POST data) for a request
+			self.current_request.collect_incoming_data (data)
+		else:
+			# we are receiving header (request) data
+			self.in_buffer = self.in_buffer + data
+
+	def found_terminator (self):
+		if self.current_request:
+			self.current_request.found_terminator()
+		else:
+			header = self.in_buffer
+			self.in_buffer = ''
+			lines = string.split (header, '\r\n')
+
+			# --------------------------------------------------
+			# crack the request header
+			# --------------------------------------------------
+			request = lines[0]
+			command, uri, version = crack_request (request)
+			header = join_headers (lines[1:])
+
+			r = http_request (self, request, command, uri, version, header)
+			self.request_counter.increment()
+			self.server.total_requests.increment()
+
+			# --------------------------------------------------
+			# handler selection and dispatch
+			# --------------------------------------------------
+			for h in self.server.handlers:
+				if h.match (r):
+					try:
+						self.current_request = r
+						# This isn't used anywhere.
+						# r.handler = h # CYCLE
+						h.handle_request (r)
+					except:
+						self.server.exceptions.increment()
+						t,v,tb = sys.exc_info()
+						(file,fun,line),tbinfo = asyncore.compact_traceback (t,v,tb)
+						while tb.tb_next:
+							tb = tb.tb_next
+						# Log this to a better place.
+						print 'Server Error: %s, %s: file: %s line: %s' % (t,v,file,line)
+						# IMPORTANT: without this <del>, this entire connection will leak. [why?]
+						del t,v,tb
+						try:
+							r.error (500)
+						except:
+							pass
+					return
+
+			# no handlers, so complain
+			r.error (404)
+
+	def writable (self):
+		# this is just the normal async_chat 'writable', here for comparison
+		return self.ac_out_buffer or len(self.producer_fifo)
+
+	def writable_for_proxy (self):
+		# this version of writable supports the idea of a 'stalled' producer
+		# [i.e., it's not ready to produce any output yet] This is needed by
+		# the proxy, which will be waiting for the magic combination of
+		# 1) hostname resolved
+		# 2) connection made
+		# 3) data available.
+		if self.ac_out_buffer:
+			return 1
+		elif len(self.producer_fifo):
+			p = self.producer_fifo.first()
+			if hasattr (p, 'stalled'):
+				return not p.stalled()
+			else:
+				return 1
+
+# ===========================================================================
+#						 HTTP Server Object
+# ===========================================================================
+
+class http_server (asyncore.dispatcher):
+
+	SERVER_IDENT = 'HTTP Server (V%s)' % VERSION_STRING
+
+	channel_class = http_channel
+
+	def __init__ (self, ip, port, resolver=None, logger_object=None):
+		self.ip = ip
+		self.port = port
+		asyncore.dispatcher.__init__ (self)
+		self.create_socket (socket.AF_INET, socket.SOCK_STREAM)
+
+		self.handlers = []
+
+		if not logger_object:
+			logger_object = logger.file_logger (sys.stdout)
+
+		self.set_reuse_addr()
+		self.bind ((ip, port))
+		self.listen (5)
+		host, port = self.socket.getsockname()
+		if not ip:
+			print 'Warning: computing default hostname'
+			self.server_name = socket.gethostbyaddr (
+				socket.gethostbyname (socket.gethostname())
+				)[0]
+		else:
+			self.server_name = socket.gethostbyaddr (ip)[0]
+		self.server_port = port
+		self.total_clients = counter()
+		self.total_requests = counter()
+		self.exceptions = counter()
+		self.bytes_out = counter()
+		self.bytes_in  = counter()
+
+		if not logger_object:
+			logger_object = logger.file_logger (sys.stdout)
+
+		if resolver:
+			self.logger = logger.resolving_logger (resolver, logger_object)
+		else:
+			self.logger = logger.unresolving_logger (logger_object)
+
+		sys.stdout.write (
+			'Medusa (V%s) started at %s'
+			'\n\tHostname: %s'
+			'\n\tPort:%d'
+			'\n' % (
+				VERSION_STRING,
+				time.ctime(time.time()),
+				self.server_name,
+				port,
+				)
+			)
+
+	def writable (self):
+		return 0
+
+	def handle_read (self):
+		pass
+
+	def readable (self):
+		return self.accepting
+
+	def handle_connect (self):
+		pass
+
+	def handle_accept (self):
+		self.total_clients.increment()
+		try:
+			conn, addr = self.accept()
+		except socket.error:
+			# linux: on rare occasions we get a bogus socket back from
+			# accept.  socketmodule.c:makesockaddr complains that the
+			# address family is unknown.  We don't want the whole server
+			# to shut down because of this.
+			sys.stderr.write ('warning: server accept() threw an exception\n')
+			return
+
+		self.channel_class (self, conn, addr)
+
+	def install_handler (self, handler, back=0):
+		if back:
+			self.handlers.append (handler)
+		else:
+			self.handlers.insert (0, handler)
+
+	def remove_handler (self, handler):
+		self.handlers.remove (handler)
+
+	def status (self):
+		def nice_bytes (n):
+			return string.join (status_handler.english_bytes (n))
+
+		handler_stats = filter (None, map (maybe_status, self.handlers))
+		
+		if self.total_clients:
+			ratio = float(self.total_requests.as_long()/self.total_clients.as_long())
+		else:
+			ratio = 0.0
+		
+		return producers.composite_producer (
+			fifo ([producers.lines_producer (
+				['<h2>%s</h2>'							% self.SERVER_IDENT,
+				'<br>Listening on: <b>Host:</b> %s'		% self.server_name,
+				'<b>Port:</b> %d'						% self.port,
+				 '<p><ul>'
+				 '<li>Total <b>Clients:</b> %s'			% self.total_clients,
+				 '<b>Requests:</b> %s'					% self.total_requests,
+				 '<b>Requests/Client:</b> %.1f'			% (ratio),
+				 '<li>Total <b>Bytes In:</b> %s'	% (nice_bytes (self.bytes_in.as_long())),
+				 '<b>Bytes Out:</b> %s'				% (nice_bytes (self.bytes_out.as_long())),
+				 '<li>Total <b>Exceptions:</b> %s'		% self.exceptions,
+				 '</ul><p>'
+				 '<b>Extension List</b><ul>',
+				 ])] + handler_stats + [producers.simple_producer('</ul>')]
+				  )
+			)
+
+def maybe_status (thing):
+	if hasattr (thing, 'status'):
+		return thing.status()
+	else:
+		return None
+
+CONNECTION = regex.compile ('Connection: \(.*\)', regex.casefold)
+
+# merge multi-line headers
+# [486dx2: ~500/sec]
+def join_headers (headers):
+	r = []
+	for i in range(len(headers)):
+		if headers[i][0] in ' \t':	
+			r[-1] = r[-1] + headers[i][1:]
+		else:
+			r.append (headers[i])
+	return r
+
+def get_header (head_reg, lines, group=1):
+	for line in lines:
+		if head_reg.match (line) == len(line):
+			return head_reg.group(group)
+	return ''
+
+REQUEST = regex.compile ('\([^ ]+\) \([^ ]+\)\(\( HTTP/\([0-9.]+\)\)$\|$\)')
+
+def crack_request (r):
+	if REQUEST.match (r) == len(r):
+		if REQUEST.group(3):
+			version = REQUEST.group(5)
+		else:
+			version = None
+		return string.lower (REQUEST.group (1)), REQUEST.group(2), version
+
+class fifo:
+	def __init__ (self, list=None):
+		if not list:
+			self.list = []
+		else:
+			self.list = list
+		
+	def __len__ (self):
+		return len(self.list)
+
+	def first (self):
+		return self.list[0]
+
+	def push_front (self, object):
+		self.list.insert (0, object)
+
+	def push (self, data):
+		self.list.append (data)
+
+	def pop (self):
+		if self.list:
+			result = self.list[0]
+			del self.list[0]
+			return (1, result)
+		else:
+			return (0, None)
+
+def compute_timezone_for_log ():
+	if time.daylight:
+		tz = time.altzone
+	else:
+		tz = time.timezone
+	if tz > 0:
+		neg = 1
+	else:
+		neg = 0
+		tz = -tz
+	h, rem = divmod (tz, 3600)
+	m, rem = divmod (rem, 60)
+	if neg:
+		return '-%02d%02d' % (h, m)
+	else:
+		return '+%02d%02d' % (h, m)
+
+# if you run this program over a TZ change boundary, this will be invalid.
+tz_for_log = compute_timezone_for_log()
+
+if __name__ == '__main__':
+	import sys
+	if len(sys.argv) < 2:
+		print 'usage: %s <root> <port>' % (sys.argv[0])
+	else:
+		import monitor
+		import filesys
+		import default_handler
+		import status_handler
+		import ftp_server
+		import chat_server
+		import resolver
+		import logger
+		rs = resolver.caching_resolver ('127.0.0.1')
+		lg = logger.file_logger (sys.stdout)
+		ms = monitor.secure_monitor_server ('fnord', '127.0.0.1', 9999)
+		fs = filesys.os_filesystem (sys.argv[1])
+		dh = default_handler.default_handler (fs)
+		hs = http_server ('', string.atoi (sys.argv[2]), rs, lg)
+		hs.install_handler (dh)
+		ftp = ftp_server.ftp_server (
+			ftp_server.dummy_authorizer(sys.argv[1]),
+			port=8021,
+			resolver=rs,
+			logger_object=lg
+			)
+		cs = chat_server.chat_server ('', 7777)
+		sh = status_handler.status_extension([hs,ms,ftp,cs,rs])
+		hs.install_handler (sh)
+		if ('-p' in sys.argv):
+			def profile_loop ():
+				try:
+					asyncore.loop()
+				except KeyboardInterrupt:
+					pass
+			import profile
+			profile.run ('profile_loop()', 'profile.out')
+		else:
+			asyncore.loop()

lib/python/ZServer/medusa/logger.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+import asynchat
+import socket
+import string
+
+#
+# three types of log:
+# 1) file
+#    with optional flushing.
+# 2) socket
+#    dump output directly to a socket connection. [how do we
+#    keep it open?]
+# 3) syslog
+#    log to syslog via tcp.  this is a per-line protocol.
+#
+
+#
+# The 'standard' interface to a logging object is simply
+# log_object.log (message)
+#
+
+# a file-like object that captures output, and
+# makes sure to flush it always...  this could
+# be connected to:
+#  o	stdio file
+#  o	low-level file
+#  o	socket channel
+#  o	syslog output...
+
+class file_logger:
+			
+	# pass this either a path or a file object.
+	def __init__ (self, file, flush=1, mode='wa'):
+		if type(file) == type(''):
+			if (file == '-'):
+				import sys
+				self.file = sys.stdout
+			else:
+				self.file = open (file, mode)
+		else:
+			self.file = file
+		self.do_flush = flush
+
+	def __repr__ (self):
+		return '<file logger: %s>' % self.file
+
+	def write (self, data):
+		self.file.write (data)
+		self.maybe_flush()
+		
+	def writeline (self, line):
+		self.file.writeline (line)
+		self.maybe_flush()
+		
+	def writelines (self, lines):
+		self.file.writelines (lines)
+		self.maybe_flush()
+
+	def maybe_flush (self):
+		if self.do_flush:
+			self.file.flush()
+
+	def flush (self):
+		self.file.flush()
+
+	def softspace (self, *args):
+		pass
+
+	def log (self, message):
+		if message[-1] not in ('\r', '\n'):
+			self.write (message + '\n')
+		else:
+			self.write (message)
+
+# syslog is a line-oriented log protocol - this class would be
+# appropriate for FTP or HTTP logs, but not for dumping stderr to.
+
+# TODO: a simple safety wrapper that will ensure that the line sent
+# to syslog is reasonable.
+
+# TODO: async version of syslog_client: now, log entries use blocking
+# send()
+
+import m_syslog
+syslog_logger = m_syslog.syslog_client
+
+class syslog_logger (m_syslog.syslog_client):
+	def __init__ (self, address, facility='user'):
+		m_syslog.syslog_client.__init__ (self, address)
+		self.facility = m_syslog.facility_names[facility]
+		self.address=address
+
+	def __repr__ (self):
+		return '<syslog logger address=%s>' % (repr(self.address))
+
+	def log (self, message):
+		m_syslog.syslog_client.log (
+			self,
+			message,
+			facility=self.facility,
+			priority=m_syslog.LOG_INFO
+			)
+
+# log to a stream socket, asynchronously
+
+class socket_logger (asynchat.async_chat):
+
+	def __init__ (self, address):
+
+		if type(address) == type(''):
+			self.create_socket (socket.AF_UNIX, socket.SOCK_STREAM)
+		else:
+			self.create_socket (socket.AF_INET, socket.SOCK_STREAM)
+
+		self.connect (address)
+		self.address = address
+		
+	def __repr__ (self):
+		return '<socket logger: address=%s>' % (self.address)
+
+	def log (self, message):
+		if message[-2:] != '\r\n':
+			self.socket.push (message + '\r\n')
+		else:
+			self.socket.push (message)
+
+# log to multiple places
+class multi_logger:
+	def __init__ (self, loggers):
+		self.loggers = loggers
+
+	def __repr__ (self):
+		return '<multi logger: %s>' % (repr(self.loggers))
+
+	def log (self, message):
+		for logger in self.loggers:
+			logger.log (message)
+
+class resolving_logger:
+	"""Feed (ip, message) combinations into this logger to get a
+	resolved hostname in front of the message.  The message will not
+	be logged until the PTR request finishes (or fails)."""
+
+	def __init__ (self, resolver, logger):
+		self.resolver = resolver
+		self.logger = logger
+
+	class logger_thunk:
+		def __init__ (self, message, logger):
+			self.message = message
+			self.logger = logger
+
+		def __call__ (self, host, ttl, answer):
+			if not answer:
+				answer = host
+			self.logger.log ('%s:%s' % (answer, self.message))
+
+	def log (self, ip, message):
+		self.resolver.resolve_ptr (
+			ip,
+			self.logger_thunk (
+				message,
+				self.logger
+				)
+			)
+
+class unresolving_logger:
+	"Just in case you don't want to resolve"
+	def __init__ (self, logger):
+		self.logger = logger
+
+	def log (self, ip, message):
+		self.logger.log ('%s:%s' % (ip, message))
+
+
+def strip_eol (line):
+	while line and line[-1] in '\r\n':
+		line = line[:-1]
+	return line
+
+class tail_logger:
+	"Keep track of the last <size> log messages"
+	def __init__ (self, logger, size=500):
+		self.size = size
+		self.logger = logger
+		self.messages = []
+
+	def log (self, message):
+		self.messages.append (strip_eol (message))
+		if len (self.messages) > self.size:
+			del self.messages[0]
+		self.logger.log (message)

lib/python/ZServer/medusa/m_syslog.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+# ======================================================================
+# Copyright 1997 by Sam Rushing
+# 
+#                         All Rights Reserved
+# 
+# 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
+# permission.
+# 
+# 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.
+# ======================================================================
+
+"""socket interface to unix syslog.
+On Unix, there are usually two ways of getting to syslog: via a
+local unix-domain socket, or via the TCP service.
+
+Usually "/dev/log" is the unix domain socket.  This may be different
+for other systems.
+
+>>> my_client = syslog_client ('/dev/log')
+
+Otherwise, just use the UDP version, port 514.
+
+>>> my_client = syslog_client (('my_log_host', 514))
+
+On win32, you will have to use the UDP version.  Note that
+you can use this to log to other hosts (and indeed, multiple
+hosts).
+
+This module is not a drop-in replacement for the python
+<syslog> extension module - the interface is different.
+
+Usage:
+
+>>> c = syslog_client()
+>>> c = syslog_client ('/strange/non_standard_log_location')
+>>> c = syslog_client (('other_host.com', 514))
+>>> c.log ('testing', facility='local0', priority='debug')
+
+"""
+
+# TODO: support named-pipe syslog.
+# [see ftp://sunsite.unc.edu/pub/Linux/system/Daemons/syslog-fifo.tar.z]
+
+# from <linux/sys/syslog.h>:
+# ===========================================================================
+# priorities/facilities are encoded into a single 32-bit quantity, where the
+# bottom 3 bits are the priority (0-7) and the top 28 bits are the facility
+# (0-big number).  Both the priorities and the facilities map roughly
+# one-to-one to strings in the syslogd(8) source code.  This mapping is
+# included in this file.
+#
+# priorities (these are ordered)
+
+LOG_EMERG		= 0		#  system is unusable 
+LOG_ALERT		= 1		#  action must be taken immediately 
+LOG_CRIT		= 2		#  critical conditions 
+LOG_ERR			= 3		#  error conditions 
+LOG_WARNING		= 4		#  warning conditions 
+LOG_NOTICE		= 5		#  normal but significant condition 
+LOG_INFO		= 6		#  informational 
+LOG_DEBUG		= 7		#  debug-level messages 
+
+#  facility codes 
+LOG_KERN		= 0		#  kernel messages 
+LOG_USER		= 1		#  random user-level messages 
+LOG_MAIL		= 2		#  mail system 
+LOG_DAEMON		= 3		#  system daemons 
+LOG_AUTH		= 4		#  security/authorization messages 
+LOG_SYSLOG		= 5		#  messages generated internally by syslogd 
+LOG_LPR			= 6		#  line printer subsystem 
+LOG_NEWS		= 7		#  network news subsystem 
+LOG_UUCP		= 8		#  UUCP subsystem 
+LOG_CRON		= 9		#  clock daemon 
+LOG_AUTHPRIV	= 10	#  security/authorization messages (private) 
+
+#  other codes through 15 reserved for system use 
+LOG_LOCAL0		= 16		#  reserved for local use 
+LOG_LOCAL1		= 17		#  reserved for local use 
+LOG_LOCAL2		= 18		#  reserved for local use 
+LOG_LOCAL3		= 19		#  reserved for local use 
+LOG_LOCAL4		= 20		#  reserved for local use 
+LOG_LOCAL5		= 21		#  reserved for local use 
+LOG_LOCAL6		= 22		#  reserved for local use 
+LOG_LOCAL7		= 23		#  reserved for local use 
+
+priority_names = {
+	"alert":	LOG_ALERT,
+	"crit":		LOG_CRIT,
+	"debug":	LOG_DEBUG,
+	"emerg":	LOG_EMERG,
+	"err":		LOG_ERR,
+	"error":	LOG_ERR,		#  DEPRECATED 
+	"info":		LOG_INFO,
+	"notice":	LOG_NOTICE,
+	"panic": 	LOG_EMERG,		#  DEPRECATED 
+	"warn":		LOG_WARNING,		#  DEPRECATED 
+	"warning":	LOG_WARNING,
+	}
+
+facility_names = {
+	"auth":		LOG_AUTH,
+	"authpriv":	LOG_AUTHPRIV,
+	"cron": 	LOG_CRON,
+	"daemon":	LOG_DAEMON,
+	"kern":		LOG_KERN,
+	"lpr":		LOG_LPR,
+	"mail":		LOG_MAIL,
+	"news":		LOG_NEWS,
+	"security":	LOG_AUTH,		#  DEPRECATED 
+	"syslog":	LOG_SYSLOG,
+	"user":		LOG_USER,
+	"uucp":		LOG_UUCP,
+	"local0":	LOG_LOCAL0,
+	"local1":	LOG_LOCAL1,
+	"local2":	LOG_LOCAL2,
+	"local3":	LOG_LOCAL3,
+	"local4":	LOG_LOCAL4,
+	"local5":	LOG_LOCAL5,
+	"local6":	LOG_LOCAL6,
+	"local7":	LOG_LOCAL7,
+	}
+
+import socket
+
+class syslog_client:
+	def __init__ (self, address='/dev/log'):
+		self.address = address
+		if type (address) == type(''):
+			self.socket = socket.socket (socket.AF_UNIX, socket.SOCK_STREAM)
+			self.socket.connect (address)
+			self.unix = 1
+		else:
+			self.socket = socket.socket (socket.AF_INET, socket.SOCK_DGRAM)
+			self.unix = 0
+
+	# curious: when talking to the unix-domain '/dev/log' socket, a
+	#   zero-terminator seems to be required.  this string is placed
+	#   into a class variable so that it can be overridden if
+	#   necessary.
+
+	log_format_string = '<%d>%s\000'
+
+	def log (self, message, facility=LOG_USER, priority=LOG_INFO):
+		message = self.log_format_string % (
+			self.encode_priority (facility, priority),
+			message
+			)
+		if self.unix:
+			self.socket.send (message)
+		else:
+			self.socket.sendto (message, self.address)
+
+	def encode_priority (self, facility, priority):
+		if type(facility) == type(''):
+			facility = facility_names[facility]
+		if type(priority) == type(''):
+			priority = priority_names[priority]			
+		return (facility<<3) | priority
+
+	def close (self):
+		if self.unix:
+			self.socket.close()
+

lib/python/ZServer/medusa/medusa_gif.py

+# -*- Mode: Python -*-
+
+# the medusa icon as a python source file.
+
+width = 97
+height = 61
+
+data = 'GIF89aa\000=\000\204\000\000\000\000\000\255\255\255\245\245\245ssskkkccc111)))\326\326\326!!!\316\316\316\300\300\300\204\204\000\224\224\224\214\214\214\200\200\200RRR\377\377\377JJJ\367\367\367BBB\347\347\347\000\204\000\020\020\020\265\265\265\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000!\371\004\001\000\000\021\000,\000\000\000\000a\000=\000\000\005\376`$\216di\236h\252\256l\353\276p,\317tm\337x\256\357|m\001@\240E\305\000\364\2164\206R)$\005\201\214\007r\012{X\255\312a\004\260\\>\026\3240\353)\224n\001W+X\334\373\231~\344.\303b\216\024\027x<\273\307\255G,rJiWN\014{S}k"?ti\013EdPQ\207G@_%\000\026yy\\\201\202\227\224<\221Fs$pOjWz\241<r@vO\236\231\233k\247M\2544\203F\177\235\236L#\247\256Z\270,\266BxJ[\276\256A]iE\304\305\262\273E\313\201\275i#\\\303\321\'h\203V\\\177\326\276\216\220P~\335\230_\264\013\342\275\344KF\233\360Q\212\352\246\000\367\274s\361\236\334\347T\341;\341\246\2202\177\3142\211`\242o\325@S\202\264\031\252\207\260\323\256\205\311\036\236\270\002\'\013\302\177\274H\010\324X\002\0176\212\037\376\321\360\032\226\207\244\2674(+^\202\346r\205J\0211\375\241Y#\256f\0127\315>\272\002\325\307g\012(\007\205\312#j\317(\012A\200\224.\241\003\346GS\247\033\245\344\264\366\015L\'PXQl]\266\263\243\232\260?\245\316\371\362\225\035\332\243J\273\332Q\263\357-D\241T\327\270\265\013W&\330\010u\371b\322IW0\214\261]\003\033Va\365Z#\207\213a\030k\2647\262\014p\354\024[n\321N\363\346\317\003\037P\000\235C\302\000\3228(\244\363YaA\005\022\255_\237@\260\000A\212\326\256qbp\321\332\266\011\334=T\023\010"!B\005\003A\010\224\020\220 H\002\337#\020 O\276E\357h\221\327\003\\\000b@v\004\351A.h\365\354\342B\002\011\257\025\\ \220\340\301\353\006\000\024\214\200pA\300\353\012\364\241k/\340\033C\202\003\000\310fZ\011\003V\240R\005\007\354\376\026A\000\000\360\'\202\177\024\004\210\003\000\305\215\360\000\000\015\220\240\332\203\027@\'\202\004\025VpA\000%\210x\321\206\032J\341\316\010\262\211H"l\333\341\200\200>"]P\002\212\011\010`\002\0066FP\200\001\'\024p]\004\027(8B\221\306]\000\201w>\002iB\001\007\340\260"v7J1\343(\257\020\251\243\011\242i\263\017\215\337\035\220\200\221\365m4d\015\016D\251\341iN\354\346Ng\253\200I\240\031\35609\245\2057\311I\302\2007t\231"&`\314\310\244\011e\226(\236\010w\212\300\234\011\012HX(\214\253\311@\001\233^\222pg{% \340\035\224&H\000\246\201\362\215`@\001"L\340\004\030\234\022\250\'\015(V:\302\235\030\240q\337\205\224\212h@\177\006\000\250\210\004\007\310\207\337\005\257-P\346\257\367]p\353\203\271\256:\203\236\211F\340\247\010\3329g\244\010\307*=A\000\203\260y\012\304s#\014\007D\207,N\007\304\265\027\021C\233\207%B\366[m\353\006\006\034j\360\306+\357\274a\204\000\000;'

lib/python/ZServer/medusa/mime_type_table.py

+# -*- Python -*-
+# Converted by ./convert_mime_type_table.py from:
+# /usr/src2/apache_1.2b6/conf/mime.types
+#
+content_type_map = \
+  {
+        'ai':  'application/postscript',
+       'aif':  'audio/x-aiff',
+      'aifc':  'audio/x-aiff',
+      'aiff':  'audio/x-aiff',
+        'au':  'audio/basic',
+       'avi':  'video/x-msvideo',
+     'bcpio':  'application/x-bcpio',
+       'bin':  'application/octet-stream',
+       'cdf':  'application/x-netcdf',
+     'class':  'application/octet-stream',
+      'cpio':  'application/x-cpio',
+       'cpt':  'application/mac-compactpro',
+       'csh':  'application/x-csh',
+       'dcr':  'application/x-director',
+       'dir':  'application/x-director',
+       'dms':  'application/octet-stream',
+       'doc':  'application/msword',
+       'dvi':  'application/x-dvi',
+       'dxr':  'application/x-director',
+       'eps':  'application/postscript',
+       'etx':  'text/x-setext',
+       'exe':  'application/octet-stream',
+       'gif':  'image/gif',
+      'gtar':  'application/x-gtar',
+        'gz':  'application/x-gzip',
+       'hdf':  'application/x-hdf',
+       'hqx':  'application/mac-binhex40',
+       'htm':  'text/html',
+      'html':  'text/html',
+       'ice':  'x-conference/x-cooltalk',
+       'ief':  'image/ief',
+       'jpe':  'image/jpeg',
+      'jpeg':  'image/jpeg',
+       'jpg':  'image/jpeg',
+       'kar':  'audio/midi',
+     'latex':  'application/x-latex',
+       'lha':  'application/octet-stream',
+       'lzh':  'application/octet-stream',
+       'man':  'application/x-troff-man',
+        'me':  'application/x-troff-me',
+       'mid':  'audio/midi',
+      'midi':  'audio/midi',
+       'mif':  'application/x-mif',
+       'mov':  'video/quicktime',
+     'movie':  'video/x-sgi-movie',
+       'mp2':  'audio/mpeg',
+       'mpe':  'video/mpeg',
+      'mpeg':  'video/mpeg',
+       'mpg':  'video/mpeg',
+      'mpga':  'audio/mpeg',
+       'mp3':  'audio/mpeg',
+        'ms':  'application/x-troff-ms',
+        'nc':  'application/x-netcdf',
+       'oda':  'application/oda',
+       'pbm':  'image/x-portable-bitmap',
+       'pdb':  'chemical/x-pdb',
+       'pdf':  'application/pdf',
+       'pgm':  'image/x-portable-graymap',
+       'png':  'image/png',
+       'pnm':  'image/x-portable-anymap',
+       'ppm':  'image/x-portable-pixmap',
+       'ppt':  'application/powerpoint',
+        'ps':  'application/postscript',
+        'qt':  'video/quicktime',
+        'ra':  'audio/x-realaudio',
+       'ram':  'audio/x-pn-realaudio',
+       'ras':  'image/x-cmu-raster',
+       'rgb':  'image/x-rgb',
+      'roff':  'application/x-troff',
+       'rpm':  'audio/x-pn-realaudio-plugin',
+       'rtf':  'application/rtf',
+       'rtx':  'text/richtext',
+       'sgm':  'text/x-sgml',
+      'sgml':  'text/x-sgml',
+        'sh':  'application/x-sh',
+      'shar':  'application/x-shar',
+       'sit':  'application/x-stuffit',
+       'skd':  'application/x-koan',
+       'skm':  'application/x-koan',
+       'skp':  'application/x-koan',
+       'skt':  'application/x-koan',
+       'snd':  'audio/basic',
+       'src':  'application/x-wais-source',
+   'sv4cpio':  'application/x-sv4cpio',
+    'sv4crc':  'application/x-sv4crc',
+         't':  'application/x-troff',
+       'tar':  'application/x-tar',
+       'tcl':  'application/x-tcl',
+       'tex':  'application/x-tex',
+      'texi':  'application/x-texinfo',
+   'texinfo':  'application/x-texinfo',
+       'tif':  'image/tiff',
+      'tiff':  'image/tiff',
+        'tr':  'application/x-troff',
+       'tsv':  'text/tab-separated-values',
+       'txt':  'text/plain',
+     'ustar':  'application/x-ustar',
+       'vcd':  'application/x-cdlink',
+      'vrml':  'x-world/x-vrml',
+       'wav':  'audio/x-wav',
+       'wrl':  'x-world/x-vrml',
+       'xbm':  'image/x-xbitmap',
+       'xpm':  'image/x-xpixmap',
+       'xwd':  'image/x-xwindowdump',
+       'xyz':  'chemical/x-pdb',
+       'zip':  'application/zip',
+  }

lib/python/ZServer/medusa/producers.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+RCS_ID = '$Id: producers.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+import string
+
+"""
+A collection of producers.
+Each producer implements a particular feature:  They can be combined
+in various ways to get interesting and useful behaviors.
+
+For example, you can feed dynamically-produced output into the compressing
+producer, then wrap this with the 'chunked' transfer-encoding producer.
+"""
+
+class simple_producer:
+	"producer for a string"
+	def __init__ (self, data, buffer_size=1024):
+		self.data = data
+		self.buffer_size = buffer_size
+
+	def more (self):
+		if len (self.data) > self.buffer_size:
+			result = self.data[:self.buffer_size]
+			self.data = self.data[self.buffer_size:]
+			return result
+		else:
+			result = self.data
+			self.data = ''
+			return result
+
+class scanning_producer:
+	"like simple_producer, but more efficient for large strings"
+	def __init__ (self, data, buffer_size=1024):
+		self.data = data
+		self.buffer_size = buffer_size
+		self.pos = 0
+
+	def more (self):
+		if self.pos < len(self.data):
+			lp = self.pos
+			rp = min (
+				len(self.data),
+				self.pos + self.buffer_size
+				)
+			result = self.data[lp:rp]
+			self.pos = self.pos + len(result)
+			return result
+		else:
+			return ''
+
+class lines_producer:
+	"producer for a list of lines"
+
+	def __init__ (self, lines):
+		self.lines = lines
+
+	def ready (self):
+		return len(self.lines)
+
+	def more (self):
+		if self.lines:
+			chunk = self.lines[:50]
+			self.lines = self.lines[50:]
+			return string.join (chunk, '\r\n') + '\r\n'
+		else:
+			return ''
+
+class file_producer:
+	"producer wrapper for file[-like] objects"
+
+	# match http_channel's outgoing buffer size
+	out_buffer_size = 1<<16
+
+	def __init__ (self, file):
+		self.done = 0
+		self.file = file
+
+	def more (self):
+		if self.done:
+			return ''
+		else:
+			data = self.file.read (self.out_buffer_size)
+			if not data:
+				self.file.close()
+				del self.file
+				self.done = 1
+				return ''
+			else:
+				return data
+
+# A simple output producer.  This one does not [yet] have
+# the safety feature builtin to the monitor channel:  runaway
+# output will not be caught.
+
+# don't try to print from within any of the methods
+# of this object.
+
+class output_producer:
+	"Acts like an output file; suitable for capturing sys.stdout"
+	def __init__ (self):
+		self.data = ''
+			
+	def write (self, data):
+		lines = string.splitfields (data, '\n')
+		data = string.join (lines, '\r\n')
+		self.data = self.data + data
+		
+	def writeline (self, line):
+		self.data = self.data + line + '\r\n'
+		
+	def writelines (self, lines):
+		self.data = self.data + string.joinfields (
+			lines,
+			'\r\n'
+			) + '\r\n'
+
+	def ready (self):
+		return (len (self.data) > 0)
+
+	def flush (self):
+		pass
+
+	def softspace (self, *args):
+		pass
+
+	def more (self):
+		if self.data:
+			result = self.data[:512]
+			self.data = self.data[512:]
+			return result
+		else:
+			return ''
+
+class composite_producer:
+	"combine a fifo of producers into one"
+	def __init__ (self, producers):
+		self.producers = producers
+
+	def more (self):
+		while len(self.producers):
+			p = self.producers.first()
+			d = p.more()
+			if d:
+				return d
+			else:
+				self.producers.pop()
+		else:
+			return ''
+
+
+class globbing_producer:
+	"""
+	'glob' the output from a producer into a particular buffer size.
+	helps reduce the number of calls to send().  [this appears to
+	gain about 30% performance on requests to a single channel]
+	"""
+
+	def __init__ (self, producer, buffer_size=1<<16):
+		self.producer = producer
+		self.buffer = ''
+		self.buffer_size = buffer_size
+
+	def more (self):
+		while len(self.buffer) < self.buffer_size:
+			data = self.producer.more()
+			if data:
+				self.buffer = self.buffer + data
+			else:
+				break
+		r = self.buffer
+		self.buffer = ''
+		return r
+
+
+class hooked_producer:
+	"""
+	A producer that will call <function> when it empties,.
+	with an argument of the number of bytes produced.  Useful
+	for logging/instrumentation purposes.
+	"""
+
+	def __init__ (self, producer, function):
+		self.producer = producer
+		self.function = function
+		self.bytes = 0
+
+	def more (self):
+		if self.producer:
+			result = self.producer.more()
+			if not result:
+				self.producer = None
+				self.function (self.bytes)
+			else:
+				self.bytes = self.bytes + len(result)
+			return result
+		else:
+			return ''
+
+# HTTP 1.1 emphasizes that an advertised Content-Length header MUST be
+# correct.  In the face of Strange Files, it is conceivable that
+# reading a 'file' may produce an amount of data not matching that
+# reported by os.stat() [text/binary mode issues, perhaps the file is
+# being appended to, etc..]  This makes the chunked encoding a True
+# Blessing, and it really ought to be used even with normal files.
+# How beautifully it blends with the concept of the producer.
+
+class chunked_producer:
+	"""A producer that implements the 'chunked' transfer coding for HTTP/1.1.
+	Here is a sample usage:
+		request['Transfer-Encoding'] = 'chunked'
+		request.push (
+			producers.chunked_producer (your_producer)
+			)
+		request.done()
+	"""
+
+	def __init__ (self, producer, footers=None):
+		self.producer = producer
+		self.footers = footers
+
+	def more (self):
+		if self.producer:
+			data = self.producer.more()
+			if data:
+				return '%x\r\n%s\r\n' % (len(data), data)
+			else:
+				self.producer = None
+				if self.footers:
+					return string.join (
+						['0'] + self.footers,
+						'\r\n'
+						) + '\r\n\r\n'
+				else:
+					return '0\r\n\r\n'
+		else:
+			return ''
+
+# Unfortunately this isn't very useful right now (Aug 97), because
+# apparently the browsers don't do on-the-fly decompression.  Which
+# is sad, because this could _really_ speed things up, especially for
+# low-bandwidth clients (i.e., most everyone).
+
+try:
+	import zlib
+except ImportError:
+	zlib = None
+
+class compressed_producer:
+	"""
+	Compress another producer on-the-fly, using ZLIB
+	[Unfortunately, none of the current browsers seem to support this]
+	"""
+
+	# Note: It's not very efficient to have the server repeatedly
+	# compressing your outgoing files: compress them ahead of time, or
+	# use a compress-once-and-store scheme.  However, if you have low
+	# bandwidth and low traffic, this may make more sense than
+	# maintaining your source files compressed.
+	#
+	# Can also be used for compressing dynamically-produced output.
+
+	def __init__ (self, producer, level=5):
+		self.producer = producer
+		self.compressor = zlib.compressobj (level)
+
+	def more (self):
+		if self.producer:
+			cdata = ''
+			# feed until we get some output
+			while not cdata:
+				data = self.producer.more()
+				if not data:
+					self.producer = None
+					return self.compressor.flush()
+				else:
+					cdata = self.compressor.compress (data)
+			return cdata
+		else:
+			return ''
+
+class escaping_producer:
+
+	"A producer that escapes a sequence of characters"
+	" Common usage: escaping the CRLF.CRLF sequence in SMTP, NNTP, etc..."
+
+	def __init__ (self, producer, esc_from='\r\n.', esc_to='\r\n..'):
+		self.producer = producer
+		self.esc_from = esc_from
+		self.esc_to = esc_to
+		self.buffer = ''
+		from asynchat import find_prefix_at_end
+		self.find_prefix_at_end = find_prefix_at_end
+
+	def more (self):
+		esc_from = self.esc_from
+		esc_to   = self.esc_to
+
+		buffer = self.buffer + self.producer.more()
+
+		if buffer:
+			buffer = string.replace (buffer, esc_from, esc_to)
+			i = self.find_prefix_at_end (buffer, esc_from)
+			if i:
+				# we found a prefix
+				self.buffer = buffer[-i:]
+				return buffer[:-i]
+			else:
+				# no prefix, return it all
+				self.buffer = ''
+				return buffer
+		else:
+			return buffer

lib/python/ZServer/medusa/resolver.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+#
+#	Author: Sam Rushing <rushing@nightmare.com>
+#
+
+RCS_ID =  '$Id: resolver.py,v 1.1 1999/01/09 03:17:32 amos Exp $'
+
+# Fast, low-overhead asynchronous name resolver.  uses 'pre-cooked'
+# DNS requests, unpacks only as much as it needs of the reply.
+
+# see rfc1035 for details
+
+import string
+
+VERSION = string.split(RCS_ID)[2]
+
+# header
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      ID                       |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |QR|   Opcode  |AA|TC|RD|RA|   Z    |   RCODE   |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    QDCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    ANCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    NSCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                    ARCOUNT                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+
+# question
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                                               |
+#    /                     QNAME                     /
+#    /                                               /
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     QTYPE                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     QCLASS                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+# build a DNS address request, _quickly_
+def fast_address_request (host, id=0):
+	return (
+		'%c%c' % (chr((id>>8)&0xff),chr(id&0xff))
+		+ '\001\000\000\001\000\000\000\000\000\000%s\000\000\001\000\001' % (
+			string.join (
+				map (
+					lambda part: '%c%s' % (chr(len(part)),part),
+					string.split (host, '.')
+					), ''
+				)
+			)
+		)
+
+def fast_ptr_request (host, id=0):
+	return (
+		'%c%c' % (chr((id>>8)&0xff),chr(id&0xff))
+		+ '\001\000\000\001\000\000\000\000\000\000%s\000\000\014\000\001' % (
+			string.join (
+				map (
+					lambda part: '%c%s' % (chr(len(part)),part),
+					string.split (host, '.')
+					), ''
+				)
+			)
+		)
+
+def unpack_name (r,pos):
+	n = []
+	while 1:
+		ll = ord(r[pos])
+		if (ll&0xc0):
+			# compression
+			pos = (ll&0x3f << 8) + (ord(r[pos+1]))
+		elif ll == 0:
+			break			
+		else:
+			pos = pos + 1
+			n.append (r[pos:pos+ll])
+			pos = pos + ll
+	return string.join (n,'.')
+
+def skip_name (r,pos):
+	s = pos
+	while 1:
+		ll = ord(r[pos])
+		if (ll&0xc0):
+			# compression
+			return pos + 2
+		elif ll == 0:
+			pos = pos + 1
+			break
+		else:
+			pos = pos + ll + 1
+	return pos
+
+def unpack_ttl (r,pos):
+	return reduce (
+		lambda x,y: (x<<8)|y,
+		map (ord, r[pos:pos+4])
+		)
+
+# resource record
+#                                    1  1  1  1  1  1
+#      0  1  2  3  4  5  6  7  8  9  0  1  2  3  4  5
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                                               |
+#    /                                               /
+#    /                      NAME                     /
+#    |                                               |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      TYPE                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                     CLASS                     |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                      TTL                      |
+#    |                                               |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+#    |                   RDLENGTH                    |
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--|
+#    /                     RDATA                     /
+#    /                                               /
+#    +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+
+def unpack_address_reply (r):
+	ancount = (ord(r[6])<<8) + (ord(r[7]))
+	# skip question, first name starts at 12,
+	# this is followed by QTYPE and QCLASS
+	pos = skip_name (r, 12) + 4
+	if ancount:
+		# we are looking very specifically for
+		# an answer with TYPE=A, CLASS=IN (\000\001\000\001)
+		for an in range(ancount):
+			pos = skip_name (r, pos)
+			if r[pos:pos+4] == '\000\001\000\001':
+				return (
+					unpack_ttl (r,pos+4),
+					'%d.%d.%d.%d' % tuple(map(ord,r[pos+10:pos+14]))
+					)
+			# skip over TYPE, CLASS, TTL, RDLENGTH, RDATA
+			pos = pos + 8
+			rdlength = (ord(r[pos])<<8) + (ord(r[pos+1]))
+			pos = pos + 2 + rdlength
+		return 0, None
+	else:
+		return 0, None
+
+def unpack_ptr_reply (r):
+	ancount = (ord(r[6])<<8) + (ord(r[7]))
+	# skip question, first name starts at 12,
+	# this is followed by QTYPE and QCLASS
+	pos = skip_name (r, 12) + 4
+	if ancount:
+		# we are looking very specifically for
+		# an answer with TYPE=PTR, CLASS=IN (\000\014\000\001)
+		for an in range(ancount):
+			pos = skip_name (r, pos)
+			if r[pos:pos+4] == '\000\014\000\001':
+				return (
+					unpack_ttl (r,pos+4),
+					unpack_name (r, pos+10)
+					)
+			# skip over TYPE, CLASS, TTL, RDLENGTH, RDATA
+			pos = pos + 8
+			rdlength = (ord(r[pos])<<8) + (ord(r[pos+1]))
+			pos = pos + 2 + rdlength
+		return 0, None
+	else:
+		return 0, None
+
+
+from counter import counter
+import asyncore
+import socket
+import sys
+
+# This is a UDP (datagram) resolver.
+
+#
+# It may be useful to implement a TCP resolver.  This would presumably
+# give us more reliable behavior when things get too busy.  A TCP
+# client would have to manage the connection carefully, since the
+# server is allowed to close it at will (the RFC recommends closing
+# after 2 minutes of idle time).
+#
+# Note also that the TCP client will have to prepend each request
+# with a 2-byte length indicator (see rfc1035).
+#
+
+class resolver (asyncore.dispatcher):
+	id = counter()
+	def __init__ (self, server='127.0.0.1'):
+		asyncore.dispatcher.__init__ (self)
+		self.create_socket (socket.AF_INET, socket.SOCK_DGRAM)
+		self.server = server
+		self.request_map = {}
+
+	def writable (self):
+		return 0
+
+	def log (self, *args):
+		pass
+
+	def handle_close (self):
+		print 'closing!'
+		self.close()
+
+	def get_id (self):
+		return (self.id.as_long() % (1<<16))
+
+	def resolve (self, host, callback):
+		self.socket.sendto (
+			fast_address_request (host, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, unpack_address_reply, callback
+		self.id.increment()
+
+	def resolve_ptr (self, host, callback):
+		ip = string.split (host, '.')
+		ip.reverse()
+		ip = string.join (ip, '.') + '.in-addr.arpa'
+		self.socket.sendto (
+			fast_ptr_request (ip, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, unpack_ptr_reply, callback
+		self.id.increment()
+
+	def handle_read (self):
+		reply, whence = self.socket.recvfrom (512)
+		# for security reasons we may want to double-check
+		# that <whence> is the server we sent the request to.
+		id = (ord(reply[0])<<8) + ord(reply[1])
+		if self.request_map.has_key (id):
+			host, unpack, callback = self.request_map[id]
+			del self.request_map[id]
+			ttl, answer = unpack (reply)
+			try:
+				callback (host, ttl, answer)
+			except:
+				t,v,tb = sys.exc_info()
+				(file,fun,line), tbinfo = asyncore.compact_traceback (t,v,tb)
+				print t,v
+				print tbinfo
+
+class rbl (resolver):
+
+	def resolve_maps (self, host, callback):
+		ip = string.split (host, '.')
+		ip.reverse()
+		ip = string.join (ip, '.') + '.rbl.maps.vix.com'
+		self.socket.sendto (
+			fast_ptr_request (ip, self.get_id()),
+			(self.server, 53)
+			)
+		self.request_map [self.get_id()] = host, self.check_reply, callback
+		self.id.increment()
+	
+	def check_reply (self, r):
+		# we only need to check RCODE.
+		rcode = (ord(r[3])&0xf)
+		print 'MAPS RBL; RCODE =%02x' % rcode
+		print repr(r)
+		return 0, rcode # (ttl, answer)
+
+import time
+
+class hooked_callback:
+	def __init__ (self, hook, callback):
+		self.hook, self.callback = hook, callback
+
+	def __call__ (self, *args):
+		apply (self.hook, args)
+		apply (self.callback, args)
+
+class caching_resolver (resolver):
+	"Cache DNS queries.  Will need to honor the TTL value in the replies"
+
+	def __init__ (*args):
+		apply (resolver.__init__, args)
+		self = args[0]
+		self.cache = {}
+		self.forward_requests = counter()
+		self.reverse_requests = counter()
+		self.cache_hits = counter()
+
+	def resolve (self, host, callback):
+		self.forward_requests.increment()
+		if self.cache.has_key (host):
+			when, ttl, answer = self.cache[host]
+			# ignore TTL for now
+			callback (host, ttl, answer)
+			self.cache_hits.increment()
+		else:
+			resolver.resolve (
+				self,
+				host,
+				hooked_callback (
+					self.callback_hook,
+					callback
+					)
+				)
+			
+	def resolve_ptr (self, host, callback):
+		self.reverse_requests.increment()
+		if self.cache.has_key (host):
+			when, ttl, answer = self.cache[host]
+			# ignore TTL for now
+			callback (host, ttl, answer)
+			self.cache_hits.increment()
+		else:
+			resolver.resolve_ptr (
+				self,
+				host,
+				hooked_callback (
+					self.callback_hook,
+					callback
+					)
+				)
+
+	def callback_hook (self, host, ttl, answer):
+		self.cache[host] = time.time(), ttl, answer
+
+	SERVER_IDENT = 'Caching DNS Resolver (V%s)' % VERSION
+
+	def status (self):
+		import status_handler
+		import producers
+		return producers.simple_producer (
+			'<h2>%s</h2>'					% self.SERVER_IDENT
+			+ '<br>Server: %s'				% self.server
+			+ '<br>Cache Entries: %d'		% len(self.cache)
+			+ '<br>Outstanding Requests: %d' % len(self.request_map)
+			+ '<br>Forward Requests: %s'	% self.forward_requests
+			+ '<br>Reverse Requests: %s'	% self.reverse_requests
+			+ '<br>Cache Hits: %s'			% self.cache_hits
+			)
+
+#test_reply = """\000\000\205\200\000\001\000\001\000\002\000\002\006squirl\011nightmare\003com\000\000\001\000\001\300\014\000\001\000\001\000\001Q\200\000\004\315\240\260\005\011nightmare\003com\000\000\002\000\001\000\001Q\200\000\002\300\014\3006\000\002\000\001\000\001Q\200\000\015\003ns1\003iag\003net\000\300\014\000\001\000\001\000\001Q\200\000\004\315\240\260\005\300]\000\001\000\001\000\000\350\227\000\004\314\033\322\005"""
+# def test_unpacker ():
+# 	print unpack_address_reply (test_reply)
+# 
+# import time
+# class timer:
+# 	def __init__ (self):
+# 		self.start = time.time()
+# 	def end (self):
+# 		return time.time() - self.start
+# 
+# # I get ~290 unpacks per second for the typical case, compared to ~48
+# # using dnslib directly.  also, that latter number does not include
+# # picking the actual data out.
+# 
+# def benchmark_unpacker():
+# 
+# 	r = range(1000)
+# 	t = timer()
+# 	for i in r:
+# 		unpack_address_reply (test_reply)
+# 	print '%.2f unpacks per second' % (1000.0 / t.end())
+
+if __name__ == '__main__':
+	import sys
+	if len(sys.argv) == 1:
+		print 'usage: %s [-r] [-s <server_IP>] host [host ...]' % sys.argv[0]
+		sys.exit(0)
+	elif ('-s' in sys.argv):
+		i = sys.argv.index('-s')
+		server = sys.argv[i+1]
+		del sys.argv[i:i+2]
+	else:
+		server = '127.0.0.1'
+
+	if ('-r' in sys.argv):
+		reverse = 1
+		i = sys.argv.index('-r')
+		del sys.argv[i]
+	else:
+		reverse = 0
+
+	if ('-m' in sys.argv):
+		maps = 1
+		sys.argv.remove ('-m')
+	else:
+		maps = 0
+
+	if maps:
+		r = rbl (server)
+	else:
+		r = caching_resolver(server)
+
+	count = len(sys.argv) - 1
+
+	def print_it (host, ttl, answer):
+		global count
+		print '%s: %s' % (host, answer)
+		count = count - 1
+		if not count:
+			r.close()
+
+	for host in sys.argv[1:]:
+		if reverse:
+			r.resolve_ptr (host, print_it)
+		elif maps:
+			r.resolve_maps (host, print_it)
+		else:
+			r.resolve (host, print_it)
+
+	# hooked asyncore.loop()
+	while asyncore.socket_map:
+		asyncore.poll (30.0)
+		print 'requests outstanding: %d' % len(r.request_map)

lib/python/ZServer/medusa/status_handler.py

+# -*- Mode: Python; tab-width: 4 -*-
+
+#			
+# medusa status extension
+#
+
+import string
+import time
+import regex
+
+import asyncore
+import http_server
+import medusa_gif
+import producers
+from counter import counter
+
+START_TIME = long(time.time())
+
+# split a uri
+# <path>;<params>?<query>#<fragment>
+path_regex = regex.compile (
+#        path        params        query       fragment
+	'\\([^;?#]*\\)\\(;[^?#]*\\)?\\(\\?[^#]*\)?\(#.*\)?'
+	)
+
+def split_path (path):
+	if path_regex.match (path) != len(path):
+		raise ValueError, "bad path"
+	else:
+		return map (lambda i,r=path_regex: r.group(i), range(1,5))
+
+class status_extension:
+	hit_counter = counter()
+
+	hyper_regex = regex.compile ('/status/object/\([0-9]+\)/.*')
+
+	def __init__ (self, objects, regexp='/status\(/.*\)?'):
+		self.objects = objects
+		self.regexp = regex.compile (regexp)
+		self.hyper_objects = []
+		for object in objects:
+			self.register_hyper_object (object)
+
+	def __repr__ (self):
+		return '<Status Extension (%s hits) at %x>' % (
+			self.hit_counter,
+			id(self)
+			)
+
+	def match (self, request):
+		[path, params, query, fragment] = split_path (request.uri)
+		return self.regexp.match (path) == len(path)
+
+	# Possible Targets:
+	# /status
+	# /status/channel_list
+	# /status/medusa.gif
+
+	# can we have 'clickable' objects?
+	# [yes, we can use id(x) and do a linear search]
+
+	# Dynamic producers:
+	# HTTP/1.0: we must close the channel, because it's dynamic output
+	# HTTP/1.1: we can use the chunked transfer-encoding, and leave
+	#   it open.
+
+	def handle_request (self, request):
+		[path, params, query, fragment] = split_path (request.uri)
+		self.hit_counter.increment()
+		if path == '/status':
+			up_time = string.join (english_time (long(time.time()) - START_TIME))
+			request['Content-Type'] = 'text/html'
+			request.push (
+				'<html>'
+				'<title>Medusa Status Reports</title>'
+				'<body bgcolor="#ffffff">'
+				'<h1>Medusa Status Reports</h1>'
+				'<b>Up:</b> %s' % up_time
+				)
+			for i in range(len(self.objects)):
+				request.push (self.objects[i].status())
+				request.push ('<hr>\r\n')
+			request.push (
+				'<p><a href="/status/channel_list">Channel List</a>'
+				'<hr>'
+				'<img src="/status/medusa.gif" align=right width=%d height=%d>' % (
+					medusa_gif.width,
+					medusa_gif.height
+					) +
+				'</body></html>'
+				)
+			request.done()
+
+		elif path == '/status/channel_list':
+			request['Content-Type'] = 'text/html'
+			request.push ('<html><body>')
+			request.push(channel_list_producer())
+			request.push (
+				'<hr>'
+				'<img src="/status/medusa.gif" align=right width=%d height=%d>' % (
+					medusa_gif.width,
+					medusa_gif.height
+					) +
+				'</body></html>'
+				)
+			request.done()
+
+		elif path == '/status/medusa.gif':
+			request['Content-Type'] = 'image/gif'
+			request['Content-Length'] = len(medusa_gif.data)
+			request.push (medusa_gif.data)
+			request.done()
+
+		elif path == '/status/close_zombies':
+			message = (
+				'<h2>Closing all zombie http client connections...</h2>'
+				'<p><a href="/status">Back to the status page</a>'
+				)
+			request['Content-Type'] = 'text/html'
+			request['Content-Length'] = len (message)
+			request.push (message)
+			now = int (time.time())
+			for channel in asyncore.socket_map.keys():
+				if channel.__class__ == http_server.http_channel:
+					if channel != request.channel:
+						if (now - channel.creation_time) > channel.zombie_timeout:
+							channel.close()
+			request.done()
+
+		# Emergency Debug Mode
+		# If a server is running away from you, don't KILL it!
+		# Move all the AF_INET server ports and perform an autopsy...
+		# [disabled by default to protect the innocent]
+		#elif path == '/status/emergency_debug':
+		elif 0:
+			request.push ('<html>Moving All Servers...</html>')
+			request.done()
+			for channel in asyncore.socket_map.keys():
+				if channel.accepting:
+					if type(channel.addr) is type(()):
+						ip, port = channel.addr
+						channel.socket.close()
+						channel.del_channel()
+						channel.addr = (ip, port+10000)
+						fam, typ = channel.family_and_type
+						channel.create_socket (fam, typ)
+						channel.set_reuse_addr()
+						channel.bind (channel.addr)
+						channel.listen(5)
+
+		elif self.hyper_regex.match (path) != -1:
+			oid = string.atoi (self.hyper_regex.group (1))
+			for object in self.hyper_objects:
+				if id (object) == oid:
+					if hasattr (object, 'hyper_respond'):
+						object.hyper_respond (self, path, request)
+		else:
+			request.error (404)
+			return
+
+	def status (self):
+		return producers.simple_producer (
+			'<li>Status Extension <b>Hits</b> : %s' % self.hit_counter
+			)
+
+	def register_hyper_object (self, object):
+		if not object in self.hyper_objects:
+			self.hyper_objects.append (object)
+
+import logger
+
+class logger_for_status (logger.tail_logger):
+
+	def status (self):
+		return 'Last %d log entries for: %s' % (
+			len (self.messages),
+			html_repr (self)
+			)
+
+	def hyper_respond (self, sh, path, request):
+		request['Content-Type'] = 'text/plain'
+		messages = self.messages[:]
+		messages.reverse()
+		request.push (lines_producer (messages))
+		request.done()
+
+class lines_producer:
+	def __init__ (self, lines):
+		self.lines = lines
+
+	def ready (self):
+		return len(self.lines)
+
+	def more (self):
+		if self.lines:
+			chunk = self.lines[:50]
+			self.lines = self.lines[50:]
+			return string.join (chunk, '\r\n') + '\r\n'
+		else:
+			return ''
+
+class channel_list_producer (lines_producer):
+	def __init__ (self):
+		channel_reprs = map (
+			lambda x: '&lt;' + repr(x)[1:-1] + '&gt;',
+			asyncore.socket_map.keys()
+			)
+		channel_reprs.sort()
+		lines_producer.__init__ (
+			self,
+			['<h1>Active Channel List</h1>',
+			 '<pre>'
+			 ] + channel_reprs + [
+				 '</pre>',
+				 '<p><a href="/status">Status Report</a>'
+				 ]
+			)
+
+
+# this really needs a full-blown quoter...
+def sanitize (s):
+	if '<' in s:
+		s = string.join (string.split (s, '<'), '&lt;')
+	if '>' in s:
+		s = string.join (string.split (s, '>'), '&gt;')
+	return s
+
+def html_repr (object):
+	so = sanitize (repr (object))
+	if hasattr (object, 'hyper_respond'):
+		return '<a href="/status/object/%d/">%s</a>' % (id (object), so)
+	else:
+		return so
+
+def html_reprs (list, front='', back=''):
+	reprs = map (
+		lambda x,f=front,b=back: '%s%s%s' % (f,x,b),
+		map (lambda x: sanitize (html_repr(x)), list)
+		)
+	reprs.sort()
+	return reprs
+
+# for example, tera, giga, mega, kilo
+# p_d (n, (1024, 1024, 1024, 1024))
+# smallest divider goes first - for example
+# minutes, hours, days
+# p_d (n, (60, 60, 24))
+
+def progressive_divide (n, parts):
+	result = []
+	for part in parts:
+		n, rem = divmod (n, part)
+		result.append (rem)
+	result.append (n)
+	return result
+
+# b,k,m,g,t
+def split_by_units (n, units, dividers, format_string):
+	divs = progressive_divide (n, dividers)
+	result = []
+	for i in range(len(units)):
+		if divs[i]:
+			result.append (format_string % (divs[i], units[i]))
+	result.reverse()
+	if not result:
+		return [format_string % (0, units[0])]
+	else:
+		return result
+
+def english_bytes (n):
+	return split_by_units (
+		n,
+		('','K','M','G','T'),
+		(1024, 1024, 1024, 1024, 1024),
+		'%d %sB'
+		)
+
+def english_time (n):
+	return split_by_units (
+		n,
+		('secs', 'mins', 'hours', 'days', 'weeks', 'years'),
+		(         60,     60,      24,     7,       52),
+		'%d %s'
+		)