urlmatch: allow globbing for the URL host part

The URL matching function computes for two URLs whether they match not.
The match is performed by splitting up the URL into different parts and
then doing an exact comparison with the to-be-matched URL.

The main user of `urlmatch` is the configuration subsystem. It allows to
set certain configurations based on the URL which is being connected to
via keys like `http.<url>.*`. A common use case for this is to set
proxies for only some remotes which match the given URL. Unfortunately,
having exact matches for all parts of the URL can become quite tedious
in some setups. Imagine for example a corporate network where there are
dozens or even hundreds of subdomains, which would have to be configured
individually.

Allow users to write an asterisk '*' in place of any 'host' or
'subdomain' label as part of the host name.  For example,
"http.https://*.example.com.proxy" sets "http.proxy" for all direct
subdomains of "https://example.com", e.g. "https://foo.example.com", but
not "https://foo.bar.example.com".

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

1 files changed, 45 insertions, 4 deletions

diff --git a/urlmatch.c b/urlmatch.c
index 990a9de..4bbde92 100644
--- a/urlmatch.c
+++ b/urlmatch.c
@@ -63,6 +63,49 @@ static int append_normalized_escapes(struct strbuf *buf,
 	return 1;
 }
 
+static const char *end_of_token(const char *s, int c, size_t n)
+{
+	const char *next = memchr(s, c, n);
+	if (!next)
+		next = s + n;
+	return next;
+}
+
+static int match_host(const struct url_info *url_info,
+		      const struct url_info *pattern_info)
+{
+	const char *url = url_info->url + url_info->host_off;
+	const char *pat = pattern_info->url + pattern_info->host_off;
+	int url_len = url_info->host_len;
+	int pat_len = pattern_info->host_len;
+
+	while (url_len && pat_len) {
+		const char *url_next = end_of_token(url, '.', url_len);
+		const char *pat_next = end_of_token(pat, '.', pat_len);
+
+		if (pat_next == pat + 1 && pat[0] == '*')
+			/* wildcard matches anything */
+			;
+		else if ((pat_next - pat) == (url_next - url) &&
+			 !memcmp(url, pat, url_next - url))
+			/* the components are the same */
+			;
+		else
+			return 0; /* found an unmatch */
+
+		if (url_next < url + url_len)
+			url_next++;
+		url_len -= url_next - url;
+		url = url_next;
+		if (pat_next < pat + pat_len)
+			pat_next++;
+		pat_len -= pat_next - pat;
+		pat = pat_next;
+	}
+
+	return (!url_len && !pat_len);
+}
+
 static char *url_normalize_1(const char *url, struct url_info *out_info, char allow_globs)
 {
 	/*
@@ -467,9 +510,7 @@ static int match_urls(const struct url_info *url,
 	}
 
 	/* 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))
+	if (!match_host(url, url_prefix))
 		return 0; /* host names do not match */
 
 	/* check the port */
@@ -528,7 +569,7 @@ int urlmatch_config_entry(const char *var, const char *value, void *cb)
 		struct url_info norm_info;
 
 		config_url = xmemdupz(key, dot - key);
-		norm_url = url_normalize(config_url, &norm_info);
+		norm_url = url_normalize_1(config_url, &norm_info, 1);
 		free(config_url);
 		if (!norm_url)
 			return 0;