Merge branch 'PHP-7.1'

Author: nikic

ext/standard/url.c

@@ -104,7 +104,7 @@ PHPAPI php_url *php_url_parse_ex(char const *str, size_t length)
 	ue = s + length;
 
 	/* parse scheme */
-	if ((e = memchr(s, ':', length)) && (e - s)) {
+	if ((e = memchr(s, ':', length)) && e != s) {
 		/* validate scheme */
 		p = s;
 		while (p < e) {
@@ -119,10 +119,10 @@ PHPAPI php_url *php_url_parse_ex(char const *str, size_t length)
 			p++;
 		}
 
-		if (*(e + 1) == '\0') { /* only scheme is available */
+		if (e + 1 == ue) { /* only scheme is available */
 			ret->scheme = estrndup(s, (e - s));
 			php_replace_controlchars_ex(ret->scheme, (e - s));
-			goto end;
+			return ret;
 		}
 
 		/*
@@ -134,90 +134,91 @@ PHPAPI php_url *php_url_parse_ex(char const *str, size_t length)
 			 * correctly parse things like a.com:80
 			 */
 			p = e + 1;
-			while (isdigit(*p)) {
+			while (p < ue && isdigit(*p)) {
 				p++;
 			}
 
-			if ((*p == '\0' || *p == '/') && (p - e) < 7) {
+			if ((p == ue || *p == '/') && (p - e) < 7) {
 				goto parse_port;
 			}
 
 			ret->scheme = estrndup(s, (e-s));
 			php_replace_controlchars_ex(ret->scheme, (e - s));
 
-			length -= ++e - s;
-			s = e;
+			s = e + 1;
 			goto just_path;
 		} else {
 			ret->scheme = estrndup(s, (e-s));
 			php_replace_controlchars_ex(ret->scheme, (e - s));
 
-			if (*(e+2) == '/') {
+			if (e + 2 < ue && *(e + 2) == '/') {
 				s = e + 3;
 				if (!strncasecmp("file", ret->scheme, sizeof("file"))) {
-					if (*(e + 3) == '/') {
+					if (e + 3 < ue && *(e + 3) == '/') {
 						/* support windows drive letters as in:
 						   file:///c:/somedir/file.txt
 						*/
-						if (*(e + 5) == ':') {
+						if (e + 5 < ue && *(e + 5) == ':') {
 							s = e + 4;
 						}
-						goto nohost;
+						goto just_path;
 					}
 				}
 			} else {
-				if (!strncasecmp("file", ret->scheme, sizeof("file"))) {
-					s = e + 1;
-					goto nohost;
-				} else {
-					length -= ++e - s;
-					s = e;
-					goto just_path;
-				}
+				s = e + 1;
+				goto just_path;
 			}
 		}
 	} else if (e) { /* no scheme; starts with colon: look for port */
 		parse_port:
 		p = e + 1;
 		pp = p;
 
-		while (pp-p < 6 && isdigit(*pp)) {
+		while (pp < ue && pp - p < 6 && isdigit(*pp)) {
 			pp++;
 		}
 
-		if (pp - p > 0 && pp - p < 6 && (*pp == '/' || *pp == '\0')) {
+		if (pp - p > 0 && pp - p < 6 && (pp == ue || *pp == '/')) {
 			zend_long port;
 			memcpy(port_buf, p, (pp - p));
 			port_buf[pp - p] = '\0';
 			port = ZEND_STRTOL(port_buf, NULL, 10);
 			if (port > 0 && port <= 65535) {
 				ret->port = (unsigned short) port;
-				if (*s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
+				if (s + 1 < ue && *s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
 				    s += 2;
 				}
 			} else {
 				if (ret->scheme) efree(ret->scheme);
 				efree(ret);
 				return NULL;
 			}
-		} else if (p == pp && *pp == '\0') {
+		} else if (p == pp && pp == ue) {
 			if (ret->scheme) efree(ret->scheme);
 			efree(ret);
 			return NULL;
-		} else if (*s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
+		} else if (s + 1 < ue && *s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
 			s += 2;
 		} else {
 			goto just_path;
 		}
-	} else if (*s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
+	} else if (s + 1 < ue && *s == '/' && *(s + 1) == '/') { /* relative-scheme URL */
 		s += 2;
 	} else {
-		just_path:
-		ue = s + length;
-		goto nohost;
+		goto just_path;
 	}
 
-	e = s + strcspn(s, "/?#");
+	/* Binary-safe strcspn(s, "/?#") */
+	e = ue;
+	if ((p = memchr(s, '/', e - s))) {
+		e = p;
+	}
+	if ((p = memchr(s, '?', e - s))) {
+		e = p;
+	}
+	if ((p = memchr(s, '#', e - s))) {
+		e = p;
+	}
 
 	/* check for login and password */
 	if ((p = zend_memrchr(s, '@', (e-s)))) {
@@ -237,18 +238,16 @@ PHPAPI php_url *php_url_parse_ex(char const *str, size_t length)
 	}
 
 	/* check for port */
-	if (*s == '[' && *(e-1) == ']') {
+	if (s < ue && *s == '[' && *(e-1) == ']') {
 		/* Short circuit portscan,
 		   we're dealing with an
 		   IPv6 embedded address */
-		p = s;
+		p = NULL;
 	} else {
-		/* memrchr is a GNU specific extension
-		   Emulate for wide compatibility */
-		for(p = e; p >= s && *p != ':'; p--);
+		p = zend_memrchr(s, ':', (e-s));
 	}
 
-	if (p >= s && *p == ':') {
+	if (p) {
 		if (!ret->port) {
 			p++;
 			if (e-p > 5) { /* port cannot be longer then 5 characters */
@@ -296,54 +295,34 @@ PHPAPI php_url *php_url_parse_ex(char const *str, size_t length)
 
 	s = e;
 
-	nohost:
-
-	if ((p = memchr(s, '?', (ue - s)))) {
-		pp = memchr(s, '#', (ue - s));
-
-		if (pp && pp < p) {
-			if (pp - s) {
-				ret->path = estrndup(s, (pp-s));
-				php_replace_controlchars_ex(ret->path, (pp - s));
-			}
-			p = pp;
-			goto label_parse;
-		}
+	just_path:
 
-		if (p - s) {
-			ret->path = estrndup(s, (p-s));
-			php_replace_controlchars_ex(ret->path, (p - s));
-		}
-
-		if (pp) {
-			if (pp - ++p) {
-				ret->query = estrndup(p, (pp-p));
-				php_replace_controlchars_ex(ret->query, (pp - p));
-			}
-			p = pp;
-			goto label_parse;
-		} else if (++p - ue) {
-			ret->query = estrndup(p, (ue-p));
-			php_replace_controlchars_ex(ret->query, (ue - p));
-		}
-	} else if ((p = memchr(s, '#', (ue - s)))) {
-		if (p - s) {
-			ret->path = estrndup(s, (p-s));
-			php_replace_controlchars_ex(ret->path, (p - s));
+	e = ue;
+	p = memchr(s, '#', (e - s));
+	if (p) {
+		p++;
+		if (p < e) {
+			ret->fragment = estrndup(p, (e - p));
+			php_replace_controlchars_ex(ret->fragment, (e - p));
 		}
+		e = p-1;
+	}
 
-		label_parse:
+	p = memchr(s, '?', (e - s));
+	if (p) {
 		p++;
-
-		if (ue - p) {
-			ret->fragment = estrndup(p, (ue-p));
-			php_replace_controlchars_ex(ret->fragment, (ue - p));
+		if (p < e) {
+			ret->query = estrndup(p, (e - p));
+			php_replace_controlchars_ex(ret->query, (e - p));
 		}
-	} else {
-		ret->path = estrndup(s, (ue-s));
-		php_replace_controlchars_ex(ret->path, (ue - s));
+		e = p-1;
 	}
-end:
+
+	if (s < e || s == ue) {
+		ret->path = estrndup(s, (e - s));
+		php_replace_controlchars_ex(ret->path, (e - s));
+	}
+
 	return ret;
 }
 /* }}} */