[v2,43/44] bundle: detect hash algorithm when reading refs

Commit Message

brian m. carlson May 25, 2020, 7:59 p.m. UTC

Much like with the dumb HTTP transport, there isn't a way to explicitly
specify the hash algorithm when dealing with a bundle, so detect the
algorithm based on the length of the object IDs in the prerequisites and
ref advertisements.

Signed-off-by: brian m. carlson <[e-mail]>
---
 bundle.c    | 22 +++++++++++++++++++++-
 bundle.h    |  1 +
 transport.c | 10 ++++++++--
 3 files changed, 30 insertions(+), 3 deletions(-)

Patch

diff --git a/bundle.c b/bundle.c
index 99439e07a1..2a0d744d3f 100644
--- a/bundle.c
+++ b/bundle.c
@@ -23,6 +23,17 @@  static void add_to_ref_list(const struct object_id *oid, const char *name,
 	list->nr++;
 }
 
+static const struct git_hash_algo *detect_hash_algo(struct strbuf *buf)
+{
+	size_t len = strcspn(buf->buf, " \n");
+	int algo;
+
+	algo = hash_algo_by_length(len / 2);
+	if (algo == GIT_HASH_UNKNOWN)
+		return NULL;
+	return &hash_algos[algo];
+}
+
 static int parse_bundle_header(int fd, struct bundle_header *header,
 			       const char *report_path)
 {
@@ -52,12 +63,21 @@  static int parse_bundle_header(int fd, struct bundle_header *header,
 		}
 		strbuf_rtrim(&buf);
 
+		if (!header->hash_algo) {
+			header->hash_algo = detect_hash_algo(&buf);
+			if (!header->hash_algo) {
+				error(_("unknown hash algorithm length"));
+				status = -1;
+				break;
+			}
+		}
+
 		/*
 		 * Tip lines have object name, SP, and refname.
 		 * Prerequisites have object name that is optionally
 		 * followed by SP and subject line.
 		 */
-		if (parse_oid_hex(buf.buf, &oid, &p) ||
+		if (parse_oid_hex_algop(buf.buf, &oid, &p, header->hash_algo) ||
 		    (*p && !isspace(*p)) ||
 		    (!is_prereq && !*p)) {
 			if (report_path)
diff --git a/bundle.h b/bundle.h
index ceab0c7475..2dc9442024 100644
--- a/bundle.h
+++ b/bundle.h
@@ -15,6 +15,7 @@  struct ref_list {
 struct bundle_header {
 	struct ref_list prerequisites;
 	struct ref_list references;
+	const struct git_hash_algo *hash_algo;
 };
 
 int is_bundle(const char *path, int quiet);
diff --git a/transport.c b/transport.c
index b43d985f90..38a432be69 100644
--- a/transport.c
+++ b/transport.c
@@ -143,6 +143,9 @@  static struct ref *get_refs_from_bundle(struct transport *transport,
 	data->fd = read_bundle_header(transport->url, &data->header);
 	if (data->fd < 0)
 		die(_("could not read bundle '%s'"), transport->url);
+
+	transport->hash_algo = data->header.hash_algo;
+
 	for (i = 0; i < data->header.references.nr; i++) {
 		struct ref_list_entry *e = data->header.references.list + i;
 		struct ref *ref = alloc_ref(e->name);
@@ -157,11 +160,14 @@  static int fetch_refs_from_bundle(struct transport *transport,
 			       int nr_heads, struct ref **to_fetch)
 {
 	struct bundle_transport_data *data = transport->data;
+	int ret;
 
 	if (!data->get_refs_from_bundle_called)
 		get_refs_from_bundle(transport, 0, NULL);
-	return unbundle(the_repository, &data->header, data->fd,
-			transport->progress ? BUNDLE_VERBOSE : 0);
+	ret = unbundle(the_repository, &data->header, data->fd,
+			   transport->progress ? BUNDLE_VERBOSE : 0);
+	transport->hash_algo = data->header.hash_algo;
+	return ret;
 }
 
 static int close_bundle(struct transport *transport)