remote-curl: detect algorithm for dumb HTTP by size

When reading the info/refs file for a repository, we have no explicit
way to detect which hash algorithm is in use because the file doesn't
provide one. Detect the hash algorithm in use by the size of the first
object ID.

If we have an empty repository, we don't know what the hash algorithm is
on the remote side, so default to whatever the local side has
configured.  Without doing this, we cannot clone an empty repository
since we don't know its hash algorithm.  Test this case appropriately,
since we currently have no tests for cloning an empty repository with
the dumb HTTP protocol.

We anonymize the URL like elsewhere in the function in case the user has
decided to include a secret in the URL.

Signed-off-by: brian m. carlson <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: bk2204

remote-curl.c

@@ -252,6 +252,19 @@ static struct ref *parse_git_refs(struct discovery *heads, int for_push)
 	return list;
 }
 
+static const struct git_hash_algo *detect_hash_algo(struct discovery *heads)
+{
+	const char *p = memchr(heads->buf, '\t', heads->len);
+	int algo;
+	if (!p)
+		return the_hash_algo;
+
+	algo = hash_algo_by_length((p - heads->buf) / 2);
+	if (algo == GIT_HASH_UNKNOWN)
+		return NULL;
+	return &hash_algos[algo];
+}
+
 static struct ref *parse_info_refs(struct discovery *heads)
 {
 	char *data, *start, *mid;
@@ -262,6 +275,12 @@ static struct ref *parse_info_refs(struct discovery *heads)
 	struct ref *ref = NULL;
 	struct ref *last_ref = NULL;
 
+	options.hash_algo = detect_hash_algo(heads);
+	if (!options.hash_algo)
+		die("%sinfo/refs not valid: could not determine hash algorithm; "
+		    "is this a git repository?",
+		    transport_anonymize_url(url.buf));
+
 	data = heads->buf;
 	start = NULL;
 	mid = data;
@@ -272,13 +291,13 @@ static struct ref *parse_info_refs(struct discovery *heads)
 		if (data[i] == '\t')
 			mid = &data[i];
 		if (data[i] == '\n') {
-			if (mid - start != the_hash_algo->hexsz)
+			if (mid - start != options.hash_algo->hexsz)
 				die(_("%sinfo/refs not valid: is this a git repository?"),
 				    transport_anonymize_url(url.buf));
 			data[i] = 0;
 			ref_name = mid + 1;
 			ref = alloc_ref(ref_name);
-			get_oid_hex(start, &ref->old_oid);
+			get_oid_hex_algop(start, &ref->old_oid, options.hash_algo);
 			if (!refs)
 				refs = ref;
 			if (last_ref)

t/t5550-http-fetch-dumb.sh

@@ -50,6 +50,24 @@ test_expect_success 'create password-protected repository' '
 	       "$HTTPD_DOCUMENT_ROOT_PATH/auth/dumb/repo.git"
 '
 
+test_expect_success 'create empty remote repository' '
+	git init --bare "$HTTPD_DOCUMENT_ROOT_PATH/empty.git" &&
+	(cd "$HTTPD_DOCUMENT_ROOT_PATH/empty.git" &&
+	 mkdir -p hooks &&
+	 write_script "hooks/post-update" <<-\EOF &&
+	 exec git update-server-info
+	EOF
+	 hooks/post-update
+	)
+'
+
+test_expect_success 'empty dumb HTTP repository has default hash algorithm' '
+	test_when_finished "rm -fr clone-empty" &&
+	git clone $HTTPD_URL/dumb/empty.git clone-empty &&
+	git -C clone-empty rev-parse --show-object-format >empty-format &&
+	test "$(cat empty-format)" = "$(test_oid algo)"
+'
+
 setup_askpass_helper
 
 test_expect_success 'cloning password-protected repository can fail' '