urlmatch: split host and port fields in `struct url_info`

The `url_info` structure contains information about a normalized URL
with the URL's components being represented by different fields. The
host and port part though are to be accessed by the same `host` field,
so that getting the host and/or port separately becomes more involved
than really necessary.

To make the port more readily accessible, split up the host and port
fields. Namely, the `host_len` will not include the port length anymore
and a new `port_off` field has been added which includes the offset to
the port, if available.

The only user of these fields is `url_normalize_1`. This change makes it
easier later on to treat host and port differently when introducing
globs for domains.

Signed-off-by: Patrick Steinhardt <patrick.steinhardt@elego.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

urlmatch.c

@@ -104,7 +104,7 @@ static char *url_normalize_1(const char *url, struct url_info *out_info, char al
 	struct strbuf norm;
 	size_t spanned;
 	size_t scheme_len, user_off=0, user_len=0, passwd_off=0, passwd_len=0;
-	size_t host_off=0, host_len=0, port_len=0, path_off, path_len, result_len;
+	size_t host_off=0, host_len=0, port_off=0, port_len=0, path_off, path_len, result_len;
 	const char *slash_ptr, *at_ptr, *colon_ptr, *path_start;
 	char *result;
 
@@ -263,6 +263,7 @@ static char *url_normalize_1(const char *url, struct url_info *out_info, char al
 				return NULL;
 			}
 			strbuf_addch(&norm, ':');
+			port_off = norm.len;
 			strbuf_add(&norm, url, slash_ptr - url);
 			port_len = slash_ptr - url;
 		}
@@ -270,7 +271,7 @@ static char *url_normalize_1(const char *url, struct url_info *out_info, char al
 		url = slash_ptr;
 	}
 	if (host_off)
-		host_len = norm.len - host_off;
+		host_len = norm.len - host_off - (port_len ? port_len + 1 : 0);
 
 
 	/*
@@ -378,6 +379,7 @@ static char *url_normalize_1(const char *url, struct url_info *out_info, char al
 		out_info->passwd_len = passwd_len;
 		out_info->host_off = host_off;
 		out_info->host_len = host_len;
+		out_info->port_off = port_off;
 		out_info->port_len = port_len;
 		out_info->path_off = path_off;
 		out_info->path_len = path_len;
@@ -464,11 +466,17 @@ static int match_urls(const struct url_info *url,
 		usermatched = 1;
 	}
 
-	/* check the host and port */
+	/* check the host */
 	if (url_prefix->host_len != url->host_len ||
 	    strncmp(url->url + url->host_off,
 		    url_prefix->url + url_prefix->host_off, url->host_len))
-		return 0; /* host names and/or ports do not match */
+		return 0; /* host names do not match */
+
+	/* check the port */
+	if (url_prefix->port_len != url->port_len ||
+	    strncmp(url->url + url->port_off,
+		    url_prefix->url + url_prefix->port_off, url->port_len))
+		return 0; /* ports do not match */
 
 	/* check the path */
 	pathmatchlen = url_match_prefix(

urlmatch.h

@@ -18,11 +18,12 @@ struct url_info {
 	size_t passwd_len;	/* length of passwd; if passwd_off != 0 but
 				   passwd_len == 0, an empty passwd was given */
 	size_t host_off;	/* offset into url to start of host name (0 => none) */
-	size_t host_len;	/* length of host name; this INCLUDES any ':portnum';
+	size_t host_len;	/* length of host name;
 				 * file urls may have host_len == 0 */
-	size_t port_len;	/* if a portnum is present (port_len != 0), it has
-				 * this length (excluding the leading ':') at the
-				 * end of the host name (always 0 for file urls) */
+	size_t port_off;	/* offset into url to start of port number (0 => none) */
+	size_t port_len;	/* if a portnum is present (port_off != 0), it has
+				 * this length (excluding the leading ':') starting
+				 * from port_off (always 0 for file urls) */
 	size_t path_off;	/* offset into url to the start of the url path;
 				 * this will always point to a '/' character
 				 * after the url has been normalized */