Mercurial > hg
view tests/tinyproxy.py @ 37048:fc5e261915b9
wireproto: require POST for all HTTPv2 requests
Wire protocol version 1 transfers argument data via request
headers by default. This has historically caused problems because
servers institute limits on the length of individual HTTP headers
as well as the total size of all request headers. Mercurial servers
can advertise the maximum length of an individual header. But
there's no guarantee any intermediate HTTP agents will accept
headers up to that length.
In the existing wire protocol, server operators typically also
key off the HTTP request method to implement authentication.
For example, GET requests translate to read-only requests and
can be allowed. But read-write commands must use POST and require
authentication. This has typically worked because the only wire
protocol commands that use POST modify the repo (e.g. the
"unbundle" command).
There is an experimental feature to enable clients to transmit
argument data via POST request bodies. This is technically a
better and more robust solution. But we can't enable it by default
because of servers assuming POST means write access.
In version 2 of the wire protocol, the permissions of a request
are encoded in the URL. And with it being a new protocol in a new
URL space, we're not constrained by backwards compatibility
requirements.
This commit adopts the technically superior mechanism of using
HTTP request bodies to send argument data by requiring POST for
all commands. Strictly speaking, it may be possible to send
request bodies on GET requests. But my experience is that not all
HTTP stacks support this. POST pretty much always works. Using POST
for read-only operations does sacrifice some RESTful design
purity. But this API cares about practicality, not about being
in Roy T. Fielding's REST ivory tower.
There's a chance we may relax this restriction in the future. But
for now, I want to see how far we can get with a POST only API.
Differential Revision: https://phab.mercurial-scm.org/D2837
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Tue, 13 Mar 2018 11:57:43 -0700 |
parents | 88c1d13b637b |
children | 97e2442a4595 |
line wrap: on
line source
#!/usr/bin/env python from __future__ import absolute_import, print_function __doc__ = """Tiny HTTP Proxy. This module implements GET, HEAD, POST, PUT and DELETE methods on BaseHTTPServer, and behaves as an HTTP proxy. The CONNECT method is also implemented experimentally, but has not been tested yet. Any help will be greatly appreciated. SUZUKI Hisao """ __version__ = "0.2.1" import optparse import os import select import socket import sys from mercurial import util httpserver = util.httpserver socketserver = util.socketserver urlreq = util.urlreq if os.environ.get('HGIPV6', '0') == '1': family = socket.AF_INET6 else: family = socket.AF_INET class ProxyHandler (httpserver.basehttprequesthandler): __base = httpserver.basehttprequesthandler __base_handle = __base.handle server_version = "TinyHTTPProxy/" + __version__ rbufsize = 0 # self.rfile Be unbuffered def handle(self): (ip, port) = self.client_address allowed = getattr(self, 'allowed_clients', None) if allowed is not None and ip not in allowed: self.raw_requestline = self.rfile.readline() if self.parse_request(): self.send_error(403) else: self.__base_handle() def log_request(self, code='-', size='-'): xheaders = [h for h in self.headers.items() if h[0].startswith('x-')] self.log_message('"%s" %s %s%s', self.requestline, str(code), str(size), ''.join([' %s:%s' % h for h in sorted(xheaders)])) # Flush for Windows, so output isn't lost on TerminateProcess() sys.stdout.flush() sys.stderr.flush() def _connect_to(self, netloc, soc): i = netloc.find(':') if i >= 0: host_port = netloc[:i], int(netloc[i + 1:]) else: host_port = netloc, 80 print("\t" "connect to %s:%d" % host_port) try: soc.connect(host_port) except socket.error as arg: try: msg = arg[1] except (IndexError, TypeError): msg = arg self.send_error(404, msg) return 0 return 1 def do_CONNECT(self): soc = socket.socket(family, socket.SOCK_STREAM) try: if self._connect_to(self.path, soc): self.log_request(200) self.wfile.write(self.protocol_version + " 200 Connection established\r\n") self.wfile.write("Proxy-agent: %s\r\n" % self.version_string()) self.wfile.write("\r\n") self._read_write(soc, 300) finally: print("\t" "bye") soc.close() self.connection.close() def do_GET(self): (scm, netloc, path, params, query, fragment) = urlreq.urlparse( self.path, 'http') if scm != 'http' or fragment or not netloc: self.send_error(400, "bad url %s" % self.path) return soc = socket.socket(family, socket.SOCK_STREAM) try: if self._connect_to(netloc, soc): self.log_request() soc.send("%s %s %s\r\n" % ( self.command, urlreq.urlunparse(('', '', path, params, query, '')), self.request_version)) self.headers['Connection'] = 'close' del self.headers['Proxy-Connection'] for key_val in self.headers.items(): soc.send("%s: %s\r\n" % key_val) soc.send("\r\n") self._read_write(soc) finally: print("\t" "bye") soc.close() self.connection.close() def _read_write(self, soc, max_idling=20): iw = [self.connection, soc] ow = [] count = 0 while True: count += 1 (ins, _, exs) = select.select(iw, ow, iw, 3) if exs: break if ins: for i in ins: if i is soc: out = self.connection else: out = soc try: data = i.recv(8192) except socket.error: break if data: out.send(data) count = 0 else: print("\t" "idle", count) if count == max_idling: break do_HEAD = do_GET do_POST = do_GET do_PUT = do_GET do_DELETE = do_GET class ThreadingHTTPServer (socketserver.ThreadingMixIn, httpserver.httpserver): def __init__(self, *args, **kwargs): httpserver.httpserver.__init__(self, *args, **kwargs) a = open("proxy.pid", "w") a.write(str(os.getpid()) + "\n") a.close() def runserver(port=8000, bind=""): server_address = (bind, port) ProxyHandler.protocol_version = "HTTP/1.0" httpd = ThreadingHTTPServer(server_address, ProxyHandler) sa = httpd.socket.getsockname() print("Serving HTTP on", sa[0], "port", sa[1], "...") try: httpd.serve_forever() except KeyboardInterrupt: print("\nKeyboard interrupt received, exiting.") httpd.server_close() sys.exit(0) if __name__ == '__main__': argv = sys.argv if argv[1:] and argv[1] in ('-h', '--help'): print(argv[0], "[port [allowed_client_name ...]]") else: if argv[2:]: allowed = [] for name in argv[2:]: client = socket.gethostbyname(name) allowed.append(client) print("Accept: %s (%s)" % (client, name)) ProxyHandler.allowed_clients = allowed del argv[2:] else: print("Any clients will be served...") parser = optparse.OptionParser() parser.add_option('-b', '--bind', metavar='ADDRESS', help='Specify alternate bind address ' '[default: all interfaces]', default='') (options, args) = parser.parse_args() port = 8000 if len(args) == 1: port = int(args[0]) runserver(port, options.bind)