All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: me@ttaylorr.com, gitster@pobox.com, l.s.r@web.de,
	szeder.dev@gmail.com, Chris Torek <chris.torek@gmail.com>,
	Derrick Stolee <stolee@gmail.com>,
	Derrick Stolee <derrickstolee@github.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v4 14/17] midx: use chunk-format read API
Date: Thu, 18 Feb 2021 14:07:36 +0000	[thread overview]
Message-ID: <64010031db0e44c8c040fa1a53f568574dd5a940.1613657259.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.848.v4.git.1613657259.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

Instead of parsing the table of contents directly, use the chunk-format
API methods read_table_of_contents() and pair_chunk(). In particular, we
can use the return value of pair_chunk() to generate an error when a
required chunk is missing.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 midx.c                      | 73 +++++++++++++------------------------
 t/t5319-multi-pack-index.sh |  6 +--
 2 files changed, 29 insertions(+), 50 deletions(-)

diff --git a/midx.c b/midx.c
index d2fd9c10feea..d7ea0d1375fa 100644
--- a/midx.c
+++ b/midx.c
@@ -28,7 +28,6 @@
 #define MIDX_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define MIDX_CHUNKID_OBJECTOFFSETS 0x4f4f4646 /* "OOFF" */
 #define MIDX_CHUNKID_LARGEOFFSETS 0x4c4f4646 /* "LOFF" */
-#define MIDX_CHUNKLOOKUP_WIDTH (sizeof(uint32_t) + sizeof(uint64_t))
 #define MIDX_CHUNK_FANOUT_SIZE (sizeof(uint32_t) * 256)
 #define MIDX_CHUNK_OFFSET_WIDTH (2 * sizeof(uint32_t))
 #define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
@@ -53,6 +52,19 @@ static char *get_midx_filename(const char *object_dir)
 	return xstrfmt("%s/pack/multi-pack-index", object_dir);
 }
 
+static int midx_read_oid_fanout(const unsigned char *chunk_start,
+				size_t chunk_size, void *data)
+{
+	struct multi_pack_index *m = data;
+	m->chunk_oid_fanout = (uint32_t *)chunk_start;
+
+	if (chunk_size != 4 * 256) {
+		error(_("multi-pack-index OID fanout is of the wrong size"));
+		return 1;
+	}
+	return 0;
+}
+
 struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local)
 {
 	struct multi_pack_index *m = NULL;
@@ -64,6 +76,7 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 	char *midx_name = get_midx_filename(object_dir);
 	uint32_t i;
 	const char *cur_pack_name;
+	struct chunkfile *cf = NULL;
 
 	fd = git_open(midx_name);
 
@@ -113,58 +126,23 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 
 	m->num_packs = get_be32(m->data + MIDX_BYTE_NUM_PACKS);
 
-	for (i = 0; i < m->num_chunks; i++) {
-		uint32_t chunk_id = get_be32(m->data + MIDX_HEADER_SIZE +
-					     MIDX_CHUNKLOOKUP_WIDTH * i);
-		uint64_t chunk_offset = get_be64(m->data + MIDX_HEADER_SIZE + 4 +
-						 MIDX_CHUNKLOOKUP_WIDTH * i);
-
-		if (chunk_offset >= m->data_len)
-			die(_("invalid chunk offset (too large)"));
-
-		switch (chunk_id) {
-			case MIDX_CHUNKID_PACKNAMES:
-				m->chunk_pack_names = m->data + chunk_offset;
-				break;
-
-			case MIDX_CHUNKID_OIDFANOUT:
-				m->chunk_oid_fanout = (uint32_t *)(m->data + chunk_offset);
-				break;
-
-			case MIDX_CHUNKID_OIDLOOKUP:
-				m->chunk_oid_lookup = m->data + chunk_offset;
-				break;
-
-			case MIDX_CHUNKID_OBJECTOFFSETS:
-				m->chunk_object_offsets = m->data + chunk_offset;
-				break;
-
-			case MIDX_CHUNKID_LARGEOFFSETS:
-				m->chunk_large_offsets = m->data + chunk_offset;
-				break;
-
-			case 0:
-				die(_("terminating multi-pack-index chunk id appears earlier than expected"));
-				break;
-
-			default:
-				/*
-				 * Do nothing on unrecognized chunks, allowing future
-				 * extensions to add optional chunks.
-				 */
-				break;
-		}
-	}
+	cf = init_chunkfile(NULL);
 
-	if (!m->chunk_pack_names)
+	if (read_table_of_contents(cf, m->data, midx_size,
+				   MIDX_HEADER_SIZE, m->num_chunks))
+		goto cleanup_fail;
+
+	if (pair_chunk(cf, MIDX_CHUNKID_PACKNAMES, &m->chunk_pack_names) == CHUNK_NOT_FOUND)
 		die(_("multi-pack-index missing required pack-name chunk"));
-	if (!m->chunk_oid_fanout)
+	if (read_chunk(cf, MIDX_CHUNKID_OIDFANOUT, midx_read_oid_fanout, m) == CHUNK_NOT_FOUND)
 		die(_("multi-pack-index missing required OID fanout chunk"));
-	if (!m->chunk_oid_lookup)
+	if (pair_chunk(cf, MIDX_CHUNKID_OIDLOOKUP, &m->chunk_oid_lookup) == CHUNK_NOT_FOUND)
 		die(_("multi-pack-index missing required OID lookup chunk"));
-	if (!m->chunk_object_offsets)
+	if (pair_chunk(cf, MIDX_CHUNKID_OBJECTOFFSETS, &m->chunk_object_offsets) == CHUNK_NOT_FOUND)
 		die(_("multi-pack-index missing required object offsets chunk"));
 
+	pair_chunk(cf, MIDX_CHUNKID_LARGEOFFSETS, &m->chunk_large_offsets);
+
 	m->num_objects = ntohl(m->chunk_oid_fanout[255]);
 
 	m->pack_names = xcalloc(m->num_packs, sizeof(*m->pack_names));
@@ -190,6 +168,7 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 cleanup_fail:
 	free(m);
 	free(midx_name);
+	free(cf);
 	if (midx_map)
 		munmap(midx_map, midx_size);
 	if (0 <= fd)
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index 297de502a94f..ad4e878b65b8 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -314,12 +314,12 @@ test_expect_success 'verify bad OID version' '
 
 test_expect_success 'verify truncated chunk count' '
 	corrupt_midx_and_verify $MIDX_BYTE_CHUNK_COUNT "\01" $objdir \
-		"missing required"
+		"final chunk has non-zero id"
 '
 
 test_expect_success 'verify extended chunk count' '
 	corrupt_midx_and_verify $MIDX_BYTE_CHUNK_COUNT "\07" $objdir \
-		"terminating multi-pack-index chunk id appears earlier than expected"
+		"terminating chunk id appears earlier than expected"
 '
 
 test_expect_success 'verify missing required chunk' '
@@ -329,7 +329,7 @@ test_expect_success 'verify missing required chunk' '
 
 test_expect_success 'verify invalid chunk offset' '
 	corrupt_midx_and_verify $MIDX_BYTE_CHUNK_OFFSET "\01" $objdir \
-		"invalid chunk offset (too large)"
+		"improper chunk offset(s)"
 '
 
 test_expect_success 'verify packnames out of order' '
-- 
gitgitgadget


  parent reply	other threads:[~2021-02-18 16:54 UTC|newest]

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-26 16:01 [PATCH 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27  1:53   ` Chris Torek
2021-01-27  2:36     ` Taylor Blau
2021-01-26 16:01 ` [PATCH 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-01-27  2:42   ` Taylor Blau
2021-01-27 13:49     ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27  2:47   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27  2:49   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-01-27  3:02   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 14/17] midx: " Derrick Stolee via GitGitGadget
2021-01-27  3:06   ` Taylor Blau
2021-01-27 13:50     ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-01-26 22:37 ` [PATCH 00/17] Refactor chunk-format into an API Junio C Hamano
2021-01-27  2:29 ` Taylor Blau
2021-01-27 15:01 ` [PATCH v2 " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-04 21:24     ` Junio C Hamano
2021-02-04 22:40       ` Junio C Hamano
2021-02-05 11:37       ` Derrick Stolee
2021-02-05 19:25         ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-04 22:59     ` Junio C Hamano
2021-02-05 11:42       ` Derrick Stolee
2021-01-27 15:01   ` [PATCH v2 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-04 23:40     ` Junio C Hamano
2021-02-05 12:19       ` Derrick Stolee
2021-02-05 19:37         ` Junio C Hamano
2021-02-08 22:26           ` Junio C Hamano
2021-02-09  1:33             ` Derrick Stolee
2021-02-09 20:47               ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 14/17] midx: " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05  0:00     ` Junio C Hamano
2021-02-05 10:59       ` Chris Torek
2021-02-05 20:41         ` Junio C Hamano
2021-02-06 20:35           ` Chris Torek
2021-02-05 12:30       ` Derrick Stolee
2021-02-05 19:42         ` Junio C Hamano
2021-02-07 19:50       ` SZEDER Gábor
2021-02-08  5:41         ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05  0:05     ` Junio C Hamano
2021-02-05 12:31       ` Derrick Stolee
2021-01-27 15:01   ` [PATCH v2 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-05  0:15     ` Junio C Hamano
2021-01-27 16:03   ` [PATCH v2 00/17] Refactor chunk-format into an API Taylor Blau
2021-02-05  2:08   ` Junio C Hamano
2021-02-05  2:27     ` Derrick Stolee
2021-02-05 14:30   ` [PATCH v3 " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-07 21:13       ` SZEDER Gábor
2021-02-08 13:44         ` Derrick Stolee
2021-02-11 19:43           ` SZEDER Gábor
2021-02-05 14:30     ` [PATCH v3 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-07 20:20       ` SZEDER Gábor
2021-02-08 13:35         ` Derrick Stolee
2021-02-05 14:30     ` [PATCH v3 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 14/17] midx: " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 14:07     ` [PATCH v4 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-24 16:52         ` SZEDER Gábor
2021-02-24 17:12           ` Taylor Blau
2021-02-24 17:52             ` Derrick Stolee
2021-02-24 19:44               ` Junio C Hamano
2021-02-18 14:07       ` [PATCH v4 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` Derrick Stolee via GitGitGadget [this message]
2021-02-18 14:07       ` [PATCH v4 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 21:47         ` Junio C Hamano
2021-02-19 12:42           ` Derrick Stolee

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=64010031db0e44c8c040fa1a53f568574dd5a940.1613657259.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=chris.torek@gmail.com \
    --cc=derrickstolee@github.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=l.s.r@web.de \
    --cc=me@ttaylorr.com \
    --cc=stolee@gmail.com \
    --cc=szeder.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.