[PATCH 02/13] urlmatch: define url_parse function

From: Matheus Afonso Martins Moreira via GitGitGadget <gitgitgadget@gmail.com>
Date: Apr 28, 2024, 22:30 UTC
Message-ID: <13b81b8aa06cfd63a5fd9d1acbaf21a8b388ff47.1714343461.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1715.git.git.1714343461.gitgitgadget@gmail.com>

From: Matheus Afonso Martins Moreira <matheus@matheusmoreira.com>

Define general parsing function that supports all Git URLs including scp style URLs such as hostname:~user/repo. Has the same interface as the URL normalization function and uses the same data structures, facilitating its use. It's adapted from the algorithm used to process URLs in connect.c, so it should support the same inputs.

Signed-off-by: Matheus Afonso Martins Moreira <matheus@matheusmoreira.com>
---
 urlmatch.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 urlmatch.h |  1 +
 2 files changed, 91 insertions(+)

diff --git a/urlmatch.c b/urlmatch.c
index 1d0254abacb..5a442e31fa2 100644
--- a/urlmatch.c
+++ b/urlmatch.c
@@ -3,6 +3,7 @@
 #include "hex-ll.h"
 #include "strbuf.h"
 #include "urlmatch.h"
+#include "url.h"
 
 #define URL_ALPHA "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
 #define URL_DIGIT "0123456789"
@@ -438,6 +439,95 @@ char *url_normalize(const char *url, struct url_info *out_info)
 	return url_normalize_1(url, out_info, 0);
 }
 
+enum protocol {
+	PROTO_UNKNOWN = 0,
+	PROTO_LOCAL,
+	PROTO_FILE,
+	PROTO_SSH,
+	PROTO_GIT,
+};
+
+static enum protocol url_get_protocol(const char *name, size_t n)
+{
+	if (!strncmp(name, "ssh", n))
+		return PROTO_SSH;
+	if (!strncmp(name, "git", n))
+		return PROTO_GIT;
+	if (!strncmp(name, "git+ssh", n)) /* deprecated - do not use */
+		return PROTO_SSH;
+	if (!strncmp(name, "ssh+git", n)) /* deprecated - do not use */
+		return PROTO_SSH;
+	if (!strncmp(name, "file", n))
+		return PROTO_FILE;
+	return PROTO_UNKNOWN;
+}
+
+char *url_parse(const char *url_orig, struct url_info *out_info)
+{
+	struct strbuf url;
+	char *host, *separator;
+	char *detached, *normalized;
+	enum protocol protocol = PROTO_LOCAL;
+	struct url_info local_info;
+	struct url_info *info = out_info? out_info : &local_info;
+	bool scp_syntax = false;
+
+	if (is_url(url_orig)) {
+		url_orig = url_decode(url_orig);
+	} else {
+		url_orig = xstrdup(url_orig);
+	}
+
+	strbuf_init(&url, strlen(url_orig) + sizeof("ssh://"));
+	strbuf_addstr(&url, url_orig);
+
+	host = strstr(url.buf, "://");
+	if (host) {
+		protocol = url_get_protocol(url.buf, host - url.buf);
+		host += 3;
+	} else {
+		if (!url_is_local_not_ssh(url.buf)) {
+			scp_syntax = true;
+			protocol = PROTO_SSH;
+			strbuf_insertstr(&url, 0, "ssh://");
+			host = url.buf + 6;
+		}
+	}
+
+	/* path starts after ':' in scp style SSH URLs */
+	if (scp_syntax) {
+		separator = strchr(host, ':');
+		if (separator) {
+			if (separator[1] == '/')
+				strbuf_remove(&url, separator - url.buf, 1);
+			else
+				*separator = '/';
+		}
+	}
+
+	detached = strbuf_detach(&url, NULL);
+	normalized = url_normalize(detached, info);
+	free(detached);
+
+	if (!normalized) {
+		return NULL;
+	}
+
+	/* point path to ~ for URL's like this:
+	 *
+	 *     ssh://host.xz/~user/repo
+	 *     git://host.xz/~user/repo
+	 *     host.xz:~user/repo
+	 *
+	 */
+	if (protocol == PROTO_GIT || protocol == PROTO_SSH) {
+		if (normalized[info->path_off + 1] == '~')
+			info->path_off++;
+	}
+
+	return normalized;
+}
+
 static size_t url_match_prefix(const char *url,
 			       const char *url_prefix,
 			       size_t url_prefix_len)
diff --git a/urlmatch.h b/urlmatch.h
index 5ba85cea139..6b3ce428582 100644
--- a/urlmatch.h
+++ b/urlmatch.h
@@ -35,6 +35,7 @@ struct url_info {
 };
 
 char *url_normalize(const char *, struct url_info *);
+char *url_parse(const char *, struct url_info *);
 
 struct urlmatch_item {
 	size_t hostmatch_len;

-- 
gitgitgadget