Merge branch 'bc/sha-256-part-2'

SHA-256 migration work continues.

* bc/sha-256-part-2: (44 commits)
  remote-testgit: adapt for object-format
  bundle: detect hash algorithm when reading refs
  t5300: pass --object-format to git index-pack
  t5704: send object-format capability with SHA-256
  t5703: use object-format serve option
  t5702: offer an object-format capability in the test
  t/helper: initialize the repository for test-sha1-array
  remote-curl: avoid truncating refs with ls-remote
  t1050: pass algorithm to index-pack when outside repo
  builtin/index-pack: add option to specify hash algorithm
  remote-curl: detect algorithm for dumb HTTP by size
  builtin/ls-remote: initialize repository based on fetch
  t5500: make hash independent
  serve: advertise object-format capability for protocol v2
  connect: parse v2 refs with correct hash algorithm
  connect: pass full packet reader when parsing v2 refs
  Documentation/technical: document object-format for protocol v2
  t1302: expect repo format version 1 for SHA-256
  builtin/show-index: provide options to determine hash algo
  t5302: modernize test formatting
  ...

5 files changed, 56 insertions, 10 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index 2a8e3aaaed..e3519a8355 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -1220,6 +1220,15 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	refs = transport_get_remote_refs(transport, &ref_prefixes);
 
 	if (refs) {
+		int hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport));
+
+		/*
+		 * Now that we know what algorithm the remote side is using,
+		 * let's set ours to the same thing.
+		 */
+		initialize_repository_version(hash_algo);
+		repo_set_hash_algo(the_repository, hash_algo);
+
 		mapped_refs = wanted_peer_refs(refs, &remote->fetch);
 		/*
 		 * transport_get_remote_refs() may return refs with null sha-1
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index f176dd28c8..f865666db9 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -1555,13 +1555,9 @@ static void read_v2_anomalous_offsets(struct packed_git *p,
 {
 	const uint32_t *idx1, *idx2;
 	uint32_t i;
-	const uint32_t hashwords = the_hash_algo->rawsz / sizeof(uint32_t);
 
 	/* The address of the 4-byte offset table */
-	idx1 = (((const uint32_t *)p->index_data)
-		+ 2 /* 8-byte header */
-		+ 256 /* fan out */
-		+ hashwords * p->num_objects /* object ID table */
+	idx1 = (((const uint32_t *)((const uint8_t *)p->index_data + p->crc_offset))
 		+ p->num_objects /* CRC32 table */
 		);
 
@@ -1671,6 +1667,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	unsigned char pack_hash[GIT_MAX_RAWSZ];
 	unsigned foreign_nr = 1;	/* zero is a "good" value, assume bad */
 	int report_end_of_input = 0;
+	int hash_algo = 0;
 
 	/*
 	 * index-pack never needs to fetch missing objects except when
@@ -1764,6 +1761,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 					die(_("bad %s"), arg);
 			} else if (skip_prefix(arg, "--max-input-size=", &arg)) {
 				max_input_size = strtoumax(arg, NULL, 10);
+			} else if (skip_prefix(arg, "--object-format=", &arg)) {
+				hash_algo = hash_algo_by_name(arg);
+				if (hash_algo == GIT_HASH_UNKNOWN)
+					die(_("unknown hash algorithm '%s'"), arg);
+				repo_set_hash_algo(the_repository, hash_algo);
 			} else
 				usage(index_pack_usage);
 			continue;
@@ -1780,6 +1782,8 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 		die(_("--fix-thin cannot be used without --stdin"));
 	if (from_stdin && !startup_info->have_repository)
 		die(_("--stdin requires a git repository"));
+	if (from_stdin && hash_algo)
+		die(_("--object-format cannot be used with --stdin"));
 	if (!index_name && pack_name)
 		index_name = derive_filename(pack_name, "idx", &index_name_buf);
 
diff --git a/builtin/ls-remote.c b/builtin/ls-remote.c
index 6ef519514b..3a4dd12903 100644
--- a/builtin/ls-remote.c
+++ b/builtin/ls-remote.c
@@ -118,6 +118,10 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix)
 		transport->server_options = &server_options;
 
 	ref = transport_get_remote_refs(transport, &ref_prefixes);
+	if (ref) {
+		int hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport));
+		repo_set_hash_algo(the_repository, hash_algo);
+	}
 	if (transport_disconnect(transport)) {
 		UNLEAK(sorting);
 		return 1;
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index ea3d0f01af..d43663bb0a 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -249,6 +249,7 @@ static void show_ref(const char *path, const struct object_id *oid)
 			strbuf_addf(&cap, " push-cert=%s", push_cert_nonce);
 		if (advertise_push_options)
 			strbuf_addstr(&cap, " push-options");
+		strbuf_addf(&cap, " object-format=%s", the_hash_algo->name);
 		strbuf_addf(&cap, " agent=%s", git_user_agent_sanitized());
 		packet_write_fmt(1, "%s %s%c%s\n",
 			     oid_to_hex(oid), path, 0, cap.buf);
@@ -1624,6 +1625,8 @@ static struct command *read_head_info(struct packet_reader *reader,
 		linelen = strlen(reader->line);
 		if (linelen < reader->pktlen) {
 			const char *feature_list = reader->line + linelen + 1;
+			const char *hash = NULL;
+			int len = 0;
 			if (parse_feature_request(feature_list, "report-status"))
 				report_status = 1;
 			if (parse_feature_request(feature_list, "side-band-64k"))
@@ -1636,6 +1639,13 @@ static struct command *read_head_info(struct packet_reader *reader,
 			if (advertise_push_options
 			    && parse_feature_request(feature_list, "push-options"))
 				use_push_options = 1;
+			hash = parse_feature_value(feature_list, "object-format", &len, NULL);
+			if (!hash) {
+				hash = hash_algos[GIT_HASH_SHA1].name;
+				len = strlen(hash);
+			}
+			if (xstrncmpz(the_hash_algo->name, hash, len))
+				die("error: unsupported object format '%s'", hash);
 		}
 
 		if (!strcmp(reader->line, "push-cert")) {
diff --git a/builtin/show-index.c b/builtin/show-index.c
index 0826f6a5a2..8106b03a6b 100644
--- a/builtin/show-index.c
+++ b/builtin/show-index.c
@@ -1,9 +1,12 @@
 #include "builtin.h"
 #include "cache.h"
 #include "pack.h"
+#include "parse-options.h"
 
-static const char show_index_usage[] =
-"git show-index";
+static const char *const show_index_usage[] = {
+	"git show-index [--object-format=<hash-algorithm>]",
+	NULL
+};
 
 int cmd_show_index(int argc, const char **argv, const char *prefix)
 {
@@ -11,10 +14,26 @@ int cmd_show_index(int argc, const char **argv, const char *prefix)
 	unsigned nr;
 	unsigned int version;
 	static unsigned int top_index[256];
-	const unsigned hashsz = the_hash_algo->rawsz;
+	unsigned hashsz;
+	const char *hash_name = NULL;
+	int hash_algo;
+	const struct option show_index_options[] = {
+		OPT_STRING(0, "object-format", &hash_name, N_("hash-algorithm"),
+			   N_("specify the hash algorithm to use")),
+		OPT_END()
+	};
+
+	argc = parse_options(argc, argv, prefix, show_index_options, show_index_usage, 0);
+
+	if (hash_name) {
+		hash_algo = hash_algo_by_name(hash_name);
+		if (hash_algo == GIT_HASH_UNKNOWN)
+			die(_("Unknown hash algorithm"));
+		repo_set_hash_algo(the_repository, hash_algo);
+	}
+
+	hashsz = the_hash_algo->rawsz;
 
-	if (argc != 1)
-		usage(show_index_usage);
 	if (fread(top_index, 2 * 4, 1, stdin) != 1)
 		die("unable to read header");
 	if (top_index[0] == htonl(PACK_IDX_SIGNATURE)) {