url: use CONNECT for HTTPS connections through HTTP proxy (issue967)

urllib2 and httplib does not support using CONNECT proxy requests, but
only regular requests over the proxy. This does not work with HTTPS
requests as they typically require that the client issues a CONNECT to
the proxy to give a direct connection to the remote HTTPS server.

This is solved by duplicating some of the httplib functionality and
tying it together with the keepalive library such that a HTTPS
connection that need to be proxied can be proxied by letting a
connection be established to the proxy server and then subsequently
performing the normal request to the specified server through the
proxy server.

As it stands, the code also purports to support HTTPS proxies, i.e.
proxies that you connect to using SSL. These are extremely rare and
nothing is done to ensure that CONNECT requests can be made to these
as that would require multiple SSL handshakes. This use case is also
not supported by most other contemporary web tools like curl and
Firefox3.

mercurial/url.py

@@ -7,7 +7,7 b''
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
-import urllib, urllib2, urlparse, httplib, os, re
+import urllib, urllib2, urlparse, httplib, os, re, socket, cStringIO
 from i18n import _
 import keepalive, util
 
@@ -245,18 +245,165 b' def _gen_sendfile(connection):'
             connection.send(self, data)
     return _sendfile
 
+has_https = hasattr(urllib2, 'HTTPSHandler')
+if has_https:
+    try:
+        # avoid using deprecated/broken FakeSocket in python 2.6
+        import ssl
+        _ssl_wrap_socket = ssl.wrap_socket
+    except ImportError:
+        def _ssl_wrap_socket(sock, key_file, cert_file):
+            ssl = socket.ssl(sock, key_file, cert_file)
+            return httplib.FakeSocket(sock, ssl)
+
 class httpconnection(keepalive.HTTPConnection):
     # must be able to send big bundle as stream.
     send = _gen_sendfile(keepalive.HTTPConnection)
 
+    def _proxytunnel(self):
+        proxyheaders = dict(
+                [(x, self.headers[x]) for x in self.headers
+                 if x.lower().startswith('proxy-')])
+        self._set_hostport(self.host, self.port)
+        self.send('CONNECT %s:%d HTTP/1.0\r\n' % (self.realhost, self.realport))
+        for header in proxyheaders.iteritems():
+            self.send('%s: %s\r\n' % header)
+        self.send('\r\n')
+
+        # majority of the following code is duplicated from
+        # httplib.HTTPConnection as there are no adequate places to
+        # override functions to provide the needed functionality
+        res = self.response_class(self.sock,
+                                  strict=self.strict,
+                                  method=self._method)
+
+        while True:
+            version, status, reason = res._read_status()
+            if status != httplib.CONTINUE:
+                break
+            while True:
+                skip = res.fp.readline().strip()
+                if not skip:
+                    break
+        res.status = status
+        res.reason = reason.strip()
+
+        if res.status == 200:
+            while True:
+                line = res.fp.readline()
+                if line == '\r\n':
+                    break
+            return True
+
+        if version == 'HTTP/1.0':
+            res.version = 10
+        elif version.startswith('HTTP/1.'):
+            res.version = 11
+        elif version == 'HTTP/0.9':
+            res.version = 9
+        else:
+            raise httplib.UnknownProtocol(version)
+
+        if res.version == 9:
+            res.length = None
+            res.chunked = 0
+            res.will_close = 1
+            res.msg = httplib.HTTPMessage(cStringIO.StringIO())
+            return False
+
+        res.msg = httplib.HTTPMessage(res.fp)
+        res.msg.fp = None
+
+        # are we using the chunked-style of transfer encoding?
+        trenc = res.msg.getheader('transfer-encoding')
+        if trenc and trenc.lower() == "chunked":
+            res.chunked = 1
+            res.chunk_left = None
+        else:
+            res.chunked = 0
+
+        # will the connection close at the end of the response?
+        res.will_close = res._check_close()
+
+        # do we have a Content-Length?
+        # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked"
+        length = res.msg.getheader('content-length')
+        if length and not res.chunked:
+            try:
+                res.length = int(length)
+            except ValueError:
+                res.length = None
+            else:
+                if res.length < 0:  # ignore nonsensical negative lengths
+                    res.length = None
+        else:
+            res.length = None
+
+        # does the body have a fixed length? (of zero)
+        if (status == httplib.NO_CONTENT or status == httplib.NOT_MODIFIED or
+            100 <= status < 200 or # 1xx codes
+            res._method == 'HEAD'):
+            res.length = 0
+
+        # if the connection remains open, and we aren't using chunked, and
+        # a content-length was not provided, then assume that the connection
+        # WILL close.
+        if (not res.will_close and
+           not res.chunked and
+           res.length is None):
+            res.will_close = 1
+
+        self.proxyres = res
+
+        return False
+
+    def connect(self):
+        if has_https and self.realhost: # use CONNECT proxy
+            self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+            self.sock.connect((self.host, self.port))
+            if self._proxytunnel():
+                # we do not support client x509 certificates
+                self.sock = _ssl_wrap_socket(self.sock, None, None)
+        else:
+            keepalive.HTTPConnection.connect(self)
+
+    def getresponse(self):
+        proxyres = getattr(self, 'proxyres', None)
+        if proxyres:
+            if proxyres.will_close:
+                self.close()
+            self.proxyres = None
+            return proxyres
+        return keepalive.HTTPConnection.getresponse(self)
+
 class httphandler(keepalive.HTTPHandler):
     def http_open(self, req):
         return self.do_open(httpconnection, req)
 
+    def _start_transaction(self, h, req):
+        if req.get_selector() == req.get_full_url(): # has proxy
+            urlparts = urlparse.urlparse(req.get_selector())
+            if urlparts[0] == 'https': # only use CONNECT for HTTPS
+                if ':' in urlparts[1]:
+                    realhost, realport = urlparts[1].split(':')
+                else:
+                    realhost = urlparts[1]
+                    realport = 443
+
+                h.realhost = realhost
+                h.realport = realport
+                h.headers = req.headers.copy()
+                h.headers.update(self.parent.addheaders)
+                return keepalive.HTTPHandler._start_transaction(self, h, req)
+
+        h.realhost = None
+        h.realport = None
+        h.headers = None
+        return keepalive.HTTPHandler._start_transaction(self, h, req)
+
     def __del__(self):
         self.close_all()
 
-has_https = hasattr(urllib2, 'HTTPSHandler')
 if has_https:
     class httpsconnection(httplib.HTTPSConnection):
         response_class = keepalive.HTTPResponse