Updated bundled http-parser

Signed-off-by: Nikos Mavrogiannopoulos <n.mavrogiannopoulos@gmail.com>

src/http-parser/http_parser.c

@@ -18,11 +18,10 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
  * IN THE SOFTWARE.
  */
-#include <config.h>
 #include "http_parser.h"
 #include <assert.h>
 #include <stddef.h>
-#include <c-ctype.h>
+#include <ctype.h>
 #include <string.h>
 #include <limits.h>
 
@@ -382,7 +381,10 @@ enum header_states
   , h_transfer_encoding
   , h_upgrade
 
+  , h_matching_transfer_encoding_token_start
   , h_matching_transfer_encoding_chunked
+  , h_matching_transfer_encoding_token
+
   , h_matching_connection_token_start
   , h_matching_connection_keep_alive
   , h_matching_connection_close
@@ -651,6 +653,8 @@ size_t http_parser_execute (http_parser *parser,
   const char *status_mark = 0;
   enum state p_state = (enum state) parser->state;
   const unsigned int lenient = parser->lenient_http_headers;
+  const unsigned int allow_chunked_length = parser->allow_chunked_length;
+
   uint32_t nread = parser->nread;
 
   /* We're in an error state. Don't bother doing anything. */
@@ -729,6 +733,7 @@ reexecute:
         if (ch == CR || ch == LF)
           break;
         parser->flags = 0;
+        parser->uses_transfer_encoding = 0;
         parser->content_length = ULLONG_MAX;
 
         if (ch == 'H') {
@@ -766,6 +771,7 @@ reexecute:
         if (ch == CR || ch == LF)
           break;
         parser->flags = 0;
+        parser->uses_transfer_encoding = 0;
         parser->content_length = ULLONG_MAX;
 
         if (ch == 'H') {
@@ -923,6 +929,7 @@ reexecute:
         if (ch == CR || ch == LF)
           break;
         parser->flags = 0;
+        parser->uses_transfer_encoding = 0;
         parser->content_length = ULLONG_MAX;
 
         if (UNLIKELY(!IS_ALPHA(ch))) {
@@ -1336,6 +1343,7 @@ reexecute:
                 parser->header_state = h_general;
               } else if (parser->index == sizeof(TRANSFER_ENCODING)-2) {
                 parser->header_state = h_transfer_encoding;
+                parser->uses_transfer_encoding = 1;
               }
               break;
 
@@ -1417,10 +1425,14 @@ reexecute:
             if ('c' == c) {
               parser->header_state = h_matching_transfer_encoding_chunked;
             } else {
-              parser->header_state = h_general;
+              parser->header_state = h_matching_transfer_encoding_token;
             }
             break;
 
+          /* Multi-value `Transfer-Encoding` header */
+          case h_matching_transfer_encoding_token_start:
+            break;
+
           case h_content_length:
             if (UNLIKELY(!IS_NUM(ch))) {
               SET_ERRNO(HPE_INVALID_CONTENT_LENGTH);
@@ -1564,16 +1576,41 @@ reexecute:
               goto error;
 
             /* Transfer-Encoding: chunked */
+            case h_matching_transfer_encoding_token_start:
+              /* looking for 'Transfer-Encoding: chunked' */
+              if ('c' == c) {
+                h_state = h_matching_transfer_encoding_chunked;
+              } else if (STRICT_TOKEN(c)) {
+                /* TODO(indutny): similar code below does this, but why?
+                 * At the very least it seems to be inconsistent given that
+                 * h_matching_transfer_encoding_token does not check for
+                 * `STRICT_TOKEN`
+                 */
+                h_state = h_matching_transfer_encoding_token;
+              } else if (c == ' ' || c == '\t') {
+                /* Skip lws */
+              } else {
+                h_state = h_general;
+              }
+              break;
+
             case h_matching_transfer_encoding_chunked:
               parser->index++;
               if (parser->index > sizeof(CHUNKED)-1
                   || c != CHUNKED[parser->index]) {
-                h_state = h_general;
+                h_state = h_matching_transfer_encoding_token;
               } else if (parser->index == sizeof(CHUNKED)-2) {
                 h_state = h_transfer_encoding_chunked;
               }
               break;
 
+            case h_matching_transfer_encoding_token:
+              if (ch == ',') {
+                h_state = h_matching_transfer_encoding_token_start;
+                parser->index = 0;
+              }
+              break;
+
             case h_matching_connection_token_start:
               /* looking for 'Connection: keep-alive' */
               if (c == 'k') {
@@ -1632,7 +1669,7 @@ reexecute:
               break;
 
             case h_transfer_encoding_chunked:
-              if (ch != ' ') h_state = h_general;
+              if (ch != ' ') h_state = h_matching_transfer_encoding_token;
               break;
 
             case h_connection_keep_alive:
@@ -1766,12 +1803,22 @@ reexecute:
           REEXECUTE();
         }
 
-        /* Cannot use chunked encoding and a content-length header together
-           per the HTTP specification. */
-        if ((parser->flags & F_CHUNKED) &&
+        /* Cannot use transfer-encoding and a content-length header together
+           per the HTTP specification. (RFC 7230 Section 3.3.3) */
+        if ((parser->uses_transfer_encoding == 1) &&
             (parser->flags & F_CONTENTLENGTH)) {
-          SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH);
-          goto error;
+          /* Allow it for lenient parsing as long as `Transfer-Encoding` is
+           * not `chunked` or allow_length_with_encoding is set
+           */
+          if (parser->flags & F_CHUNKED) {
+            if (!allow_chunked_length) {
+              SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH);
+              goto error;
+            }
+          } else if (!lenient) {
+            SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH);
+            goto error;
+          }
         }
 
         UPDATE_STATE(s_headers_done);
@@ -1846,8 +1893,31 @@ reexecute:
           UPDATE_STATE(NEW_MESSAGE());
           CALLBACK_NOTIFY(message_complete);
         } else if (parser->flags & F_CHUNKED) {
-          /* chunked encoding - ignore Content-Length header */
+          /* chunked encoding - ignore Content-Length header,
+           * prepare for a chunk */
           UPDATE_STATE(s_chunk_size_start);
+        } else if (parser->uses_transfer_encoding == 1) {
+          if (parser->type == HTTP_REQUEST && !lenient) {
+            /* RFC 7230 3.3.3 */
+
+            /* If a Transfer-Encoding header field
+             * is present in a request and the chunked transfer coding is not
+             * the final encoding, the message body length cannot be determined
+             * reliably; the server MUST respond with the 400 (Bad Request)
+             * status code and then close the connection.
+             */
+            SET_ERRNO(HPE_INVALID_TRANSFER_ENCODING);
+            RETURN(p - data); /* Error */
+          } else {
+            /* RFC 7230 3.3.3 */
+
+            /* If a Transfer-Encoding header field is present in a response and
+             * the chunked transfer coding is not the final encoding, the
+             * message body length is determined by reading the connection until
+             * it is closed by the server.
+             */
+            UPDATE_STATE(s_body_identity_eof);
+          }
         } else {
           if (parser->content_length == 0) {
             /* Content-Length header given but zero: Content-Length: 0\r\n */
@@ -2101,6 +2171,12 @@ http_message_needs_eof (const http_parser *parser)
     return 0;
   }
 
+  /* RFC 7230 3.3.3, see `s_headers_almost_done` */
+  if ((parser->uses_transfer_encoding == 1) &&
+      (parser->flags & F_CHUNKED) == 0) {
+    return 1;
+  }
+
   if ((parser->flags & F_CHUNKED) || parser->content_length != ULLONG_MAX) {
     return 0;
   }
@@ -2448,7 +2524,7 @@ http_parser_parse_url(const char *buf, size_t buflen, int is_connect,
     end = buf + off + len;
 
     /* NOTE: The characters are already validated and are in the [0-9] range */
-    assert(off + len <= buflen && "Port number overflow");
+    assert((size_t) (off + len) <= buflen && "Port number overflow");
     v = 0;
     for (p = buf + off; p < end; p++) {
       v *= 10;

src/http-parser/http_parser.h

@@ -27,7 +27,7 @@ extern "C" {
 /* Also update SONAME in the Makefile whenever you change these. */
 #define HTTP_PARSER_VERSION_MAJOR 2
 #define HTTP_PARSER_VERSION_MINOR 9
-#define HTTP_PARSER_VERSION_PATCH 2
+#define HTTP_PARSER_VERSION_PATCH 4
 
 #include <stddef.h>
 #if defined(_WIN32) && !defined(__MINGW32__) && \
@@ -41,6 +41,8 @@ typedef __int32 int32_t;
 typedef unsigned __int32 uint32_t;
 typedef __int64 int64_t;
 typedef unsigned __int64 uint64_t;
+#elif (defined(__sun) || defined(__sun__)) && defined(__SunOS_5_9)
+#include <sys/inttypes.h>
 #else
 #include <stdint.h>
 #endif
@@ -275,7 +277,9 @@ enum flags
   XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\
   XX(STRICT, "strict mode assertion failed")                         \
   XX(PAUSED, "parser is paused")                                     \
-  XX(UNKNOWN, "an unknown error occurred")
+  XX(UNKNOWN, "an unknown error occurred")                           \
+  XX(INVALID_TRANSFER_ENCODING,                                      \
+     "request has invalid transfer-encoding")                        \
 
 
 /* Define HPE_* values for each errno value above */
@@ -293,14 +297,20 @@ enum http_errno {
 struct http_parser {
   /** PRIVATE **/
   unsigned int type : 2;         /* enum http_parser_type */
-  unsigned int flags : 8;        /* F_* values from 'flags' enum; semi-public */
+  unsigned int flags : 8;       /* F_* values from 'flags' enum; semi-public */
   unsigned int state : 7;        /* enum state from http_parser.c */
   unsigned int header_state : 7; /* enum header_state from http_parser.c */
-  unsigned int index : 7;        /* index into current matcher */
+  unsigned int index : 5;        /* index into current matcher */
+  unsigned int uses_transfer_encoding : 1; /* Transfer-Encoding header is present */
+  unsigned int allow_chunked_length : 1; /* Allow headers with both
+                                          * `Content-Length` and
+                                          * `Transfer-Encoding: chunked` set */
   unsigned int lenient_http_headers : 1;
 
   uint32_t nread;          /* # bytes read in various scenarios */
-  uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */
+  uint64_t content_length; /* # bytes in body. `(uint64_t) -1` (all bits one)
+                            * if no Content-Length header.
+                            */
 
   /** READ-ONLY **/
   unsigned short http_major;