Support Upgrade header

README.md

@@ -24,6 +24,7 @@ Features:
     * request path, query string, fragment
     * message body
   * Defends against buffer overflow attacks.
+  * Upgrade support
 
 Usage
 -----
@@ -59,7 +60,9 @@ When data is received on the socket execute the parser and check for errors.
      */
     nparsed = http_parser_execute(parser, settings, buf, recved);
 
-    if (nparsed != recved) {
+    if (parser->upgrade) {
+      /* handle new protocol */
+    } else if (nparsed != recved) {
       /* Handle error. Usually just close the connection. */
     }
 
@@ -85,6 +88,34 @@ need to inspect the body. Decoding gzip is non-neglagable amount of
 processing (and requires making allocations). HTTP proxies using this
 parser, for example, would not want such a feature.
 
+The Special Problem of Upgrade
+------------------------------
+
+HTTP supports upgrading the connection to a different protocol. An
+increasingly common example of this is the Web Socket protocol which sends
+a request like
+
+        GET /demo HTTP/1.1
+        Upgrade: WebSocket
+        Connection: Upgrade
+        Host: example.com
+        Origin: http://example.com
+        WebSocket-Protocol: sample
+
+followed by non-HTTP data.
+
+(See http://tools.ietf.org/html/draft-hixie-thewebsocketprotocol-75 for more
+information the Web Socket protocol.)
+
+To support this, the parser will treat this as a normal HTTP message without a
+body. Issuing both on_headers_complete and on_message_complete callbacks. However
+http_parser_execute() may finish without parsing the entire supplied buffer.
+
+The user needs to check if parser->upgrade has been set to 1 after
+http_parser_execute() returns to determine if a premature exit was due to an
+upgrade or an error.
+
+
 Callbacks
 ---------
 

http_parser.c

@@ -78,6 +78,7 @@ do {                                                                 \
 #define CONNECTION "connection"
 #define CONTENT_LENGTH "content-length"
 #define TRANSFER_ENCODING "transfer-encoding"
+#define UPGRADE "upgrade"
 #define CHUNKED "chunked"
 #define KEEP_ALIVE "keep-alive"
 #define CLOSE "close"
@@ -207,10 +208,12 @@ enum header_states
   , h_matching_proxy_connection
   , h_matching_content_length
   , h_matching_transfer_encoding
+  , h_matching_upgrade
 
   , h_connection
   , h_content_length
   , h_transfer_encoding
+  , h_upgrade
 
   , h_matching_transfer_encoding_chunked
   , h_matching_connection_keep_alive
@@ -227,6 +230,7 @@ enum flags
   , F_CONNECTION_KEEP_ALIVE = 1 << 1
   , F_CONNECTION_CLOSE      = 1 << 2
   , F_TRAILING              = 1 << 3
+  , F_UPGRADE               = 1 << 4
   };
 
 
@@ -997,6 +1001,10 @@ size_t http_parser_execute (http_parser *parser,
             header_state = h_matching_transfer_encoding;
             break;
 
+          case 'u':
+            header_state = h_matching_upgrade;
+            break;
+
           default:
             header_state = h_general;
             break;
@@ -1086,9 +1094,22 @@ size_t http_parser_execute (http_parser *parser,
               }
               break;
 
+            /* upgrade */
+
+            case h_matching_upgrade:
+              index++;
+              if (index > sizeof(UPGRADE)-1
+                  || c != UPGRADE[index]) {
+                header_state = h_general;
+              } else if (index == sizeof(UPGRADE)-2) {
+                header_state = h_upgrade;
+              }
+              break;
+
             case h_connection:
             case h_content_length:
             case h_transfer_encoding:
+            case h_upgrade:
               if (ch != ' ') header_state = h_general;
               break;
 
@@ -1148,6 +1169,11 @@ size_t http_parser_execute (http_parser *parser,
         }
 
         switch (header_state) {
+          case h_upgrade:
+            parser->flags |= F_UPGRADE;
+            header_state = h_general;
+            break;
+
           case h_transfer_encoding:
             /* looking for 'Transfer-Encoding: chunked' */
             if ('c' == c) {
@@ -1298,8 +1324,16 @@ size_t http_parser_execute (http_parser *parser,
         parser->body_read = 0;
         nread = 0;
 
+        if (parser->flags & F_UPGRADE) parser->upgrade = 1;
+
         CALLBACK2(headers_complete);
 
+        // Exit, the rest of the connect is in a different protocol.
+        if (parser->flags & F_UPGRADE) {
+          CALLBACK2(message_complete);
+          return (p - data);
+        }
+
         if (parser->flags & F_CHUNKED) {
           /* chunked encoding - ignore Content-Length header */
           state = s_chunk_size_start;
@@ -1492,6 +1526,7 @@ http_parser_init (http_parser *parser, enum http_parser_type t)
   parser->type = t;
   parser->state = (t == HTTP_REQUEST ? s_start_req : s_start_res);
   parser->nread = 0;
+  parser->upgrade = 0;
 
   parser->header_field_mark = NULL;
   parser->header_value_mark = NULL;

http_parser.h

@@ -93,6 +93,13 @@ struct http_parser {
   unsigned short header_state;
   size_t index;
 
+  /* 1 = Upgrade header was present and the parser has exited because of that.
+   * 0 = No upgrade header present.
+   * Should be checked when http_parser_execute() returns in addition to
+   * error checking.
+   */
+  unsigned short upgrade;
+
   char flags;
 
   size_t nread;

test.c

@@ -52,6 +52,8 @@ struct message {
   char headers [MAX_HEADERS][2][MAX_ELEMENT_SIZE];
   int should_keep_alive;
 
+  int upgrade;
+
   unsigned short http_major;
   unsigned short http_minor;
 
@@ -456,6 +458,40 @@ const struct message requests[] =
   ,.body= ""
   }
 
+#define UPGRADE_REQUEST 16
+, {.name = "upgrade request"
+  ,.type= HTTP_REQUEST
+  ,.raw= "GET /demo HTTP/1.1\r\n"
+         "Host: example.com\r\n"
+         "Connection: Upgrade\r\n"
+         "Sec-WebSocket-Key2: 12998 5 Y3 1  .P00\r\n"
+         "Sec-WebSocket-Protocol: sample\r\n"
+         "Upgrade: WebSocket\r\n"
+         "Sec-WebSocket-Key1: 4 @1  46546xW%0l 1 5\r\n"
+         "Origin: http://example.com\r\n"
+         "\r\n"
+  ,.should_keep_alive= TRUE
+  ,.message_complete_on_eof= FALSE
+  ,.http_major= 1
+  ,.http_minor= 1
+  ,.method= HTTP_GET
+  ,.query_string= ""
+  ,.fragment= ""
+  ,.request_path= "/demo"
+  ,.request_url= "/demo"
+  ,.num_headers= 7
+  ,.upgrade=1
+  ,.headers= { { "Host", "example.com" }
+             , { "Connection", "Upgrade" }
+             , { "Sec-WebSocket-Key2", "12998 5 Y3 1  .P00" }
+             , { "Sec-WebSocket-Protocol", "sample" }
+             , { "Upgrade", "WebSocket" }
+             , { "Sec-WebSocket-Key1", "4 @1  46546xW%0l 1 5" }
+             , { "Origin", "http://example.com" }
+             }
+  ,.body= ""
+  }
+
 , {.name= NULL } /* sentinel */
 };
 
@@ -965,17 +1001,25 @@ test_message (const struct message *message)
   size_t read;
 
   read = parse(message->raw, strlen(message->raw));
+
+  if (message->upgrade && parser->upgrade) goto test;
+
   if (read != strlen(message->raw)) {
     print_error(message->raw, read);
     exit(1);
   }
 
   read = parse(NULL, 0);
+
+  if (message->upgrade && parser->upgrade) goto test;
+
   if (read != 0) {
     print_error(message->raw, read);
     exit(1);
   }
 
+test:
+
   if (num_messages != 1) {
     printf("\n*** num_messages != 1 after testing '%s' ***\n\n", message->name);
     exit(1);
@@ -1009,6 +1053,13 @@ out:
 void
 test_multiple3 (const struct message *r1, const struct message *r2, const struct message *r3)
 {
+  int message_count = 1;
+  if (!r1->upgrade) {
+    message_count++;
+    if (!r2->upgrade) message_count++;
+  }
+  int has_upgrade = (message_count < 3 || r3->upgrade);
+
   char total[ strlen(r1->raw)
             + strlen(r2->raw)
             + strlen(r3->raw)
@@ -1025,25 +1076,37 @@ test_multiple3 (const struct message *r1, const struct message *r2, const struct
   size_t read;
 
   read = parse(total, strlen(total));
+
+  if (has_upgrade && parser->upgrade) goto test;
+
   if (read != strlen(total)) {
     print_error(total, read);
     exit(1);
   }
 
   read = parse(NULL, 0);
+
+  if (has_upgrade && parser->upgrade) goto test;
+
   if (read != 0) {
     print_error(total, read);
     exit(1);
   }
 
-  if (3 != num_messages) {
+test:
+
+  if (message_count != num_messages) {
     fprintf(stderr, "\n\n*** Parser didn't see 3 messages only %d *** \n", num_messages);
     exit(1);
   }
 
   if (!message_eq(0, r1)) exit(1);
-  if (!message_eq(1, r2)) exit(1);
-  if (!message_eq(2, r3)) exit(1);
+  if (message_count > 1) {
+    if (!message_eq(1, r2)) exit(1);
+    if (message_count > 2) {
+      if (!message_eq(2, r3)) exit(1);
+    }
+  }
 
   parser_free();
 }