tests/tinyproxy.py

exchange: make clone bundles non-experimental and enabled by default

The clone bundles feature was introduced in Mercurial 3.6 behind an
experimental and disabled by default flag. The feature has been enabled
on hg.mozilla.org for a few months and has served many terabytes of
clones. Users have been encouraged to use the feature and reception
has been very positive (mainly due to faster clones as a result of
connecting to a CDN). I have heard no feedback about changing the
feature other than inquiries about when it will be enabled by default.
So, I think the feature is ready to be enabled by default.

This patch renames experimental.clonebundles to ui.clonebundles,
documents the option, and enables it by default. References to the
experimental state of clone bundles have been removed. The remaining
config option docs in clonebundles.py have been removed because they
are redudant with `hg help config`.

There are some oddities with behavior of clone bundles. Because clones
with clone bundles are effectively 2 `hg pull` operations, there may be
2 transactions. This could result in hooks running twice. If the
subsequent pull is aborted, it could result in partial rollback and an
incomplete clone. This behavior is a bit wonky and should probably
be documented. If this patch is accepted, I'll send a follow-up to
document it. I don't think this behavior should prevent the feature
being enabled by default. Reworking the clone mechanism to support
interrupted or multi-part clones feels like a major new feature and
something that when implemented can change the hook and rollback
semantics of clone bundles. Besides, partial clone is better than
full rollback and hooks running on initial clone are likely rare, so I
think the impact is minimal.

#!/usr/bin/env python

from __future__ import absolute_import

__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 BaseHTTPServer
import os
import select
import socket
import SocketServer
import urlparse

class ProxyHandler (BaseHTTPServer.BaseHTTPRequestHandler):
    __base = BaseHTTPServer.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)]))

    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(socket.AF_INET, 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) = urlparse.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(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(netloc, soc):
                self.log_request()
                soc.send("%s %s %s\r\n" % (
                    self.command,
                    urlparse.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,
                           BaseHTTPServer.HTTPServer):
    def __init__(self, *args, **kwargs):
        BaseHTTPServer.HTTPServer.__init__(self, *args, **kwargs)
        a = open("proxy.pid", "w")
        a.write(str(os.getpid()) + "\n")
        a.close()

if __name__ == '__main__':
    from sys import 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..."
        BaseHTTPServer.test(ProxyHandler, ThreadingHTTPServer)