X-Git-Url: https://git.m6w6.name/?p=m6w6%2Fext-http;a=blobdiff_plain;f=src%2Fphp_http_url.c;h=8352608982e4ab769dfeccbdea4ae01f47d58f1d;hp=4009add52fc369a78c1741b9c2d12a2466bc1516;hb=74e7358add4c74d212b91d23e8600ef3c10d081e;hpb=a38d5303f4d542ff6ccf152bf3b01641edbdf200

diff --git a/src/php_http_url.c b/src/php_http_url.c
index 4009add..8352608 100644
--- a/src/php_http_url.c
+++ b/src/php_http_url.c
@@ -1099,9 +1099,7 @@ static ZEND_RESULT_CODE parse_hostinfo(struct parse_state *state, const char *pt
 			state->buffer[state->offset++] = *ptr;
 			break;
 
-		case '!': case '$': case '&': case '\'': case '(': case ')': case '*':
-		case '+': case ',': case ';': case '=': /* sub-delims */
-		case '-': case '.': case '_': case '~': /* unreserved */
+		case '.':
 			if (port || !label) {
 				/* sort of a compromise, just ensure we don't end up
 				 * with a dot at the beginning or two consecutive dots
@@ -1116,6 +1114,21 @@ static ZEND_RESULT_CODE parse_hostinfo(struct parse_state *state, const char *pt
 			label = NULL;
 			break;
 
+		case '-':
+			if (!label) {
+				/* sort of a compromise, just ensure we don't end up
+				 * with a hyphen at the beginning
+				 */
+				php_error_docref(NULL TSRMLS_CC, E_WARNING,
+						"Failed to parse %s; unexpected '%c' at pos %u in '%s'",
+						port ? "port" : "host",
+						(unsigned char) *ptr, (unsigned) (ptr - tmp), tmp);
+				return FAILURE;
+			}
+			/* no break */
+		case '_': case '~': /* unreserved */
+		case '!': case '$': case '&': case '\'': case '(': case ')': case '*':
+		case '+': case ',': case ';': case '=': /* sub-delims */
 		case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
 		case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N':
 		case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U':
@@ -1468,7 +1481,7 @@ static const char *parse_scheme(struct parse_state *state)
 		case '7': case '8': case '9':
 		case '+': case '-': case '.':
 			if (state->ptr == tmp) {
-				return tmp;
+				goto softfail;
 			}
 			/* no break */
 		case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
@@ -1485,19 +1498,20 @@ static const char *parse_scheme(struct parse_state *state)
 
 		default:
 			if (!(mb = parse_mb(state, PARSE_SCHEME, state->ptr, state->end, tmp, 1))) {
-				/* soft fail; parse path next */
-				return tmp;
+				goto softfail;
 			}
 			state->ptr += mb - 1;
 		}
 	} while (++state->ptr != state->end);
 
+softfail:
+	state->offset = 0;
 	return state->ptr = tmp;
 }
 
 php_http_url_t *php_http_url_parse(const char *str, size_t len, unsigned flags)
 {
-	size_t maxlen = 3 * len;
+	size_t maxlen = 3 * len + 8 /* null bytes for all components */;
 	struct parse_state *state = ecalloc(1, sizeof(*state) + maxlen);
 
 	state->end = str + len;