Merge pull request #158 from clue-labs/connect

Support CONNECT method

README.md

@@ -269,6 +269,27 @@ $http = new Server($socket, function (RequestInterface $request) {
 });
 ```
 
+Note that the server supports *any* request method (including custom and non-
+standard ones) and all request-target formats defined in the HTTP specs for each
+respective method.
+You can use `getMethod(): string` and `getRequestTarget(): string` to
+check this is an accepted request and may want to reject other requests with
+an appropriate error code, such as `400` (Bad Request) or `405` (Method Not
+Allowed).
+
+> The `CONNECT` method is useful in a tunneling setup (HTTPS proxy) and not
+  something most HTTP servers would want to care about.
+  Note that if you want to handle this method, the client MAY send a different
+  request-target than the `Host` header field (such as removing default ports)
+  and the request-target MUST take precendence when forwarding.
+  The HTTP specs define an opaque "tunneling mode" for this method and make no
+  use of the message body.
+  For consistency reasons, this library uses the message body of the request and
+  response for tunneled application data.
+  This implies that that a `2xx` (Successful) response to a `CONNECT` request
+  can in fact use a streaming response body for the tunneled application data.
+  See also [example #21](examples) for more details.
+
 ### Response
 
 The callback function passed to the constructor of the [Server](#server)
@@ -393,14 +414,25 @@ message body as per the HTTP specs.
 This means that your callback does not have to take special care of this and any
 response body will simply be ignored.
 
-Similarly, any response with a `1xx` (Informational) or `204` (No Content)
-status code will *not* include a `Content-Length` or `Transfer-Encoding`
-header as these do not apply to these messages.
+Similarly, any `2xx` (Successful) response to a `CONNECT` request, any response
+with a `1xx` (Informational) or `204` (No Content) status code will *not*
+include a `Content-Length` or `Transfer-Encoding` header as these do not apply
+to these messages.
 Note that a response to a `HEAD` request and any response with a `304` (Not
 Modified) status code MAY include these headers even though
 the message does not contain a response body, because these header would apply
 to the message if the same request would have used an (unconditional) `GET`.
 
+> The `CONNECT` method is useful in a tunneling setup (HTTPS proxy) and not
+  something most HTTP servers would want to care about.
+  The HTTP specs define an opaque "tunneling mode" for this method and make no
+  use of the message body.
+  For consistency reasons, this library uses the message body of the request and
+  response for tunneled application data.
+  This implies that that a `2xx` (Successful) response to a `CONNECT` request
+  can in fact use a streaming response body for the tunneled application data.
+  See also [example #21](examples) for more details.
+
 A `Date` header will be automatically added with the system date and time if none is given.
 You can add a custom `Date` header yourself like this:
 

composer.json

@@ -17,6 +17,7 @@
         }
     },
     "require-dev": {
-        "phpunit/phpunit": "^4.8.10||^5.0"
+        "phpunit/phpunit": "^4.8.10||^5.0",
+        "react/socket-client": "^0.6"
     }
 }

examples/21-connect-proxy.php

@@ -0,0 +1,77 @@
+<?php
+
+use React\EventLoop\Factory;
+use React\Socket\Server;
+use React\Http\Response;
+use Psr\Http\Message\RequestInterface;
+use React\SocketClient\TcpConnector;
+use React\SocketClient\ConnectionInterface;
+use React\SocketClient\DnsConnector;
+
+require __DIR__ . '/../vendor/autoload.php';
+
+$loop = Factory::create();
+$socket = new Server(isset($argv[1]) ? $argv[1] : '0.0.0.0:0', $loop);
+
+$resolver = new \React\Dns\Resolver\Factory();
+$resolver = $resolver->create('8.8.8.8', $loop);
+$connector = new DnsConnector(new TcpConnector($loop), $resolver);
+
+$server = new \React\Http\Server($socket, function (RequestInterface $request) use ($connector) {
+    if ($request->getMethod() !== 'CONNECT') {
+        return new Response(
+            405,
+            array('Content-Type' => 'text/plain', 'Allow' => 'CONNECT'),
+            'This is a HTTP CONNECT (secure HTTPS) proxy'
+        );
+    }
+
+    // pause consuming request body
+    $body = $request->getBody();
+    $body->pause();
+
+    $buffer = '';
+    $body->on('data', function ($chunk) use (&$buffer) {
+        $buffer .= $chunk;
+    });
+
+    // try to connect to given target host
+    $promise = $connector->connect($request->getRequestTarget())->then(
+        function (ConnectionInterface $remote) use ($body, &$buffer) {
+            // connection established => forward data
+            $body->pipe($remote);
+            $body->resume();
+
+            if ($buffer !== '') {
+                $remote->write($buffer);
+                $buffer = '';
+            }
+
+            return new Response(
+                200,
+                array(),
+                $remote
+            );
+        },
+        function ($e) {
+            return new Response(
+                502,
+                array('Content-Type' => 'text/plain'),
+                'Unable to connect: ' . $e->getMessage()
+            );
+        }
+    );
+
+    // cancel pending connection if request closes prematurely
+    $body->on('close', function () use ($promise) {
+        $promise->cancel();
+    });
+
+    return $promise;
+});
+
+//$server->on('error', 'printf');
+
+echo 'Listening on http://' . $socket->getAddress() . PHP_EOL;
+
+$loop->run();

src/RequestHeaderParser.php

@@ -55,18 +55,37 @@ private function parseRequest($data)
     {
         list($headers, $bodyBuffer) = explode("\r\n\r\n", $data, 2);
 
-        $asterisk = false;
+        $originalTarget = null;
         if (strpos($headers, 'OPTIONS * ') === 0) {
-            $asterisk = true;
+            $originalTarget = '*';
             $headers = 'OPTIONS / ' . substr($headers, 10);
+        } elseif (strpos($headers, 'CONNECT ') === 0) {
+            $parts = explode(' ', $headers, 3);
+            $uri = parse_url('tcp://' . $parts[1]);
+
+            // check this is a valid authority-form request-target (host:port)
+            if (isset($uri['scheme'], $uri['host'], $uri['port']) && count($uri) === 3) {
+                $originalTarget = $parts[1];
+                $parts[1] = '/';
+                $headers = implode(' ', $parts);
+            }
         }
 
         $request = g7\parse_request($headers);
 
-        if ($asterisk) {
+        // Do not assume this is HTTPS when this happens to be port 443
+        // detecting HTTPS is left up to the socket layer (TLS detection)
+        if ($request->getUri()->getScheme() === 'https') {
+            $request = $request->withUri(
+                $request->getUri()->withScheme('http')->withPort(443)
+            );
+        }
+
+        if ($originalTarget !== null) {
             $request = $request->withUri(
-                $request->getUri()->withPath('')
-            )->withRequestTarget('*');
+                $request->getUri()->withPath(''),
+                true
+            )->withRequestTarget($originalTarget);
         }
 
         return array($request, $bodyBuffer);

src/Server.php

@@ -199,7 +199,24 @@ public function handleRequest(ConnectionInterface $conn, RequestInterface $reque
 
         $contentLength = 0;
         $stream = new CloseProtectionStream($conn);
-        if ($request->hasHeader('Transfer-Encoding')) {
+        if ($request->getMethod() === 'CONNECT') {
+            // CONNECT method MUST use authority-form request target
+            $parts = parse_url('tcp://' . $request->getRequestTarget());
+            if (!isset($parts['scheme'], $parts['host'], $parts['port']) || count($parts) !== 3) {
+                $this->emit('error', array(new \InvalidArgumentException('CONNECT method MUST use authority-form request target')));
+                return $this->writeError($conn, 400);
+            }
+
+            // CONNECT uses undelimited body until connection closes
+            $request = $request->withoutHeader('Transfer-Encoding');
+            $request = $request->withoutHeader('Content-Length');
+            $contentLength = null;
+
+            // emit end event before the actual close event
+            $stream->on('close', function () use ($stream) {
+                $stream->emit('end');
+            });
+        } else if ($request->hasHeader('Transfer-Encoding')) {
 
             if (strtolower($request->getHeaderLine('Transfer-Encoding')) !== 'chunked') {
                 $this->emit('error', array(new \InvalidArgumentException('Only chunked-encoding is allowed for Transfer-Encoding')));
@@ -336,9 +353,9 @@ public function handleResponse(ConnectionInterface $connection, RequestInterface
             $response = $response->withHeader('Connection', 'close');
         }
 
-        // response code 1xx and 204 MUST NOT include Content-Length or Transfer-Encoding header
+        // 2xx response to CONNECT and 1xx and 204 MUST NOT include Content-Length or Transfer-Encoding header
         $code = $response->getStatusCode();
-        if (($code >= 100 && $code < 200) || $code === 204) {
+        if (($request->getMethod() === 'CONNECT' && $code >= 200 && $code < 300) || ($code >= 100 && $code < 200) || $code === 204) {
             $response = $response->withoutHeader('Content-Length')->withoutHeader('Transfer-Encoding');
         }