git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Taylor Blau <me@ttaylorr.com>
To: git@vger.kernel.org
Cc: dstolee@microsoft.com, gitster@pobox.com, jrnieder@gmail.com,
	peff@peff.net
Subject: [PATCH v2 3/8] builtin/index-pack.c: write reverse indexes
Date: Wed, 13 Jan 2021 17:28:15 -0500	[thread overview]
Message-ID: <5b18ada61113faa9dc1de584366cb39b6a449ec6.1610576805.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1610576805.git.me@ttaylorr.com>

Teach 'git index-pack' to optionally write and verify reverse index with
'--[no-]rev-index', as well as respecting the 'pack.writeReverseIndex'
configuration option.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 Documentation/git-index-pack.txt | 20 ++++++---
 builtin/index-pack.c             | 64 +++++++++++++++++++++++-----
 t/t5325-reverse-index.sh         | 71 ++++++++++++++++++++++++++++++++
 3 files changed, 139 insertions(+), 16 deletions(-)
 create mode 100755 t/t5325-reverse-index.sh

diff --git a/Documentation/git-index-pack.txt b/Documentation/git-index-pack.txt
index af0c26232c..b65f380269 100644
--- a/Documentation/git-index-pack.txt
+++ b/Documentation/git-index-pack.txt
@@ -9,17 +9,18 @@ git-index-pack - Build pack index file for an existing packed archive
 SYNOPSIS
 --------
 [verse]
-'git index-pack' [-v] [-o <index-file>] <pack-file>
+'git index-pack' [-v] [-o <index-file>] [--[no-]rev-index] <pack-file>
 'git index-pack' --stdin [--fix-thin] [--keep] [-v] [-o <index-file>]
-                 [<pack-file>]
+		  [--[no-]rev-index] [<pack-file>]
 
 
 DESCRIPTION
 -----------
 Reads a packed archive (.pack) from the specified file, and
-builds a pack index file (.idx) for it.  The packed archive
-together with the pack index can then be placed in the
-objects/pack/ directory of a Git repository.
+builds a pack index file (.idx) for it. Optionally writes a
+reverse-index (.rev) for the specified pack. The packed
+archive together with the pack index can then be placed in
+the objects/pack/ directory of a Git repository.
 
 
 OPTIONS
@@ -33,7 +34,14 @@ OPTIONS
 	file is constructed from the name of packed archive
 	file by replacing .pack with .idx (and the program
 	fails if the name of packed archive does not end
-	with .pack).
+	with .pack). Incompatible with `--rev-index`.
+
+--[no-]rev-index::
+	When this flag is provided, generate a reverse index
+	(a `.rev` file) corresponding to the given pack. If
+	`--verify` is given, ensure that the existing
+	reverse index is correct. Takes precedence over
+	`pack.writeReverseIndex`.
 
 --stdin::
 	When this flag is provided, the pack is read from stdin
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 4b8d86e0ad..03408250b1 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -17,7 +17,7 @@
 #include "promisor-remote.h"
 
 static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
 
 struct object_entry {
 	struct pack_idx_entry idx;
@@ -1436,13 +1436,13 @@ static void fix_unresolved_deltas(struct hashfile *f)
 	free(sorted_by_pos);
 }
 
-static const char *derive_filename(const char *pack_name, const char *suffix,
-				   struct strbuf *buf)
+static const char *derive_filename(const char *pack_name, const char *strip,
+				   const char *suffix, struct strbuf *buf)
 {
 	size_t len;
-	if (!strip_suffix(pack_name, ".pack", &len))
-		die(_("packfile name '%s' does not end with '.pack'"),
-		    pack_name);
+	if (!strip_suffix(pack_name, strip, &len))
+		die(_("packfile name '%s' does not end with '%s'"),
+		    pack_name, strip);
 	strbuf_add(buf, pack_name, len);
 	strbuf_addch(buf, '.');
 	strbuf_addstr(buf, suffix);
@@ -1459,7 +1459,7 @@ static void write_special_file(const char *suffix, const char *msg,
 	int msg_len = strlen(msg);
 
 	if (pack_name)
-		filename = derive_filename(pack_name, suffix, &name_buf);
+		filename = derive_filename(pack_name, ".pack", suffix, &name_buf);
 	else
 		filename = odb_pack_name(&name_buf, hash, suffix);
 
@@ -1484,12 +1484,14 @@ static void write_special_file(const char *suffix, const char *msg,
 
 static void final(const char *final_pack_name, const char *curr_pack_name,
 		  const char *final_index_name, const char *curr_index_name,
+		  const char *final_rev_index_name, const char *curr_rev_index_name,
 		  const char *keep_msg, const char *promisor_msg,
 		  unsigned char *hash)
 {
 	const char *report = "pack";
 	struct strbuf pack_name = STRBUF_INIT;
 	struct strbuf index_name = STRBUF_INIT;
+	struct strbuf rev_index_name = STRBUF_INIT;
 	int err;
 
 	if (!from_stdin) {
@@ -1524,6 +1526,16 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 	} else
 		chmod(final_index_name, 0444);
 
+	if (curr_rev_index_name) {
+		if (final_rev_index_name != curr_rev_index_name) {
+			if (!final_rev_index_name)
+				final_rev_index_name = odb_pack_name(&rev_index_name, hash, "rev");
+			if (finalize_object_file(curr_rev_index_name, final_rev_index_name))
+				die(_("cannot store reverse index file"));
+		} else
+			chmod(final_rev_index_name, 0444);
+	}
+
 	if (do_fsck_object) {
 		struct packed_git *p;
 		p = add_packed_git(final_index_name, strlen(final_index_name), 0);
@@ -1553,6 +1565,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 		}
 	}
 
+	strbuf_release(&rev_index_name);
 	strbuf_release(&index_name);
 	strbuf_release(&pack_name);
 }
@@ -1578,6 +1591,12 @@ static int git_index_pack_config(const char *k, const char *v, void *cb)
 		}
 		return 0;
 	}
+	if (!strcmp(k, "pack.writereverseindex")) {
+		if (git_config_bool(k, v))
+			opts->flags |= WRITE_REV;
+		else
+			opts->flags &= ~WRITE_REV;
+	}
 	return git_default_config(k, v, cb);
 }
 
@@ -1695,12 +1714,14 @@ static void show_pack_info(int stat_only)
 
 int cmd_index_pack(int argc, const char **argv, const char *prefix)
 {
-	int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
+	int i, fix_thin_pack = 0, verify = 0, stat_only = 0, rev_index;
 	const char *curr_index;
-	const char *index_name = NULL, *pack_name = NULL;
+	const char *curr_rev_index = NULL;
+	const char *index_name = NULL, *pack_name = NULL, *rev_index_name = NULL;
 	const char *keep_msg = NULL;
 	const char *promisor_msg = NULL;
 	struct strbuf index_name_buf = STRBUF_INIT;
+	struct strbuf rev_index_name_buf = STRBUF_INIT;
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;
 	unsigned char pack_hash[GIT_MAX_RAWSZ];
@@ -1727,6 +1748,8 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (prefix && chdir(prefix))
 		die(_("Cannot come back to cwd"));
 
+	rev_index = !!(opts.flags & (WRITE_REV_VERIFY | WRITE_REV));
+
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 
@@ -1805,6 +1828,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				if (hash_algo == GIT_HASH_UNKNOWN)
 					die(_("unknown hash algorithm '%s'"), arg);
 				repo_set_hash_algo(the_repository, hash_algo);
+			} else if (!strcmp(arg, "--rev-index")) {
+				rev_index = 1;
+			} else if (!strcmp(arg, "--no-rev-index")) {
+				rev_index = 0;
 			} else
 				usage(index_pack_usage);
 			continue;
@@ -1824,7 +1851,16 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	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);
+		index_name = derive_filename(pack_name, ".pack", "idx", &index_name_buf);
+
+	opts.flags &= ~(WRITE_REV | WRITE_REV_VERIFY);
+	if (rev_index) {
+		opts.flags |= verify ? WRITE_REV_VERIFY : WRITE_REV;
+		if (index_name)
+			rev_index_name = derive_filename(index_name,
+							 ".idx", "rev",
+							 &rev_index_name_buf);
+	}
 
 	if (verify) {
 		if (!index_name)
@@ -1878,11 +1914,16 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	for (i = 0; i < nr_objects; i++)
 		idx_objects[i] = &objects[i].idx;
 	curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash);
+	if (rev_index)
+		curr_rev_index = write_rev_file(rev_index_name, idx_objects,
+						nr_objects, pack_hash,
+						opts.flags);
 	free(idx_objects);
 
 	if (!verify)
 		final(pack_name, curr_pack,
 		      index_name, curr_index,
+		      rev_index_name, curr_rev_index,
 		      keep_msg, promisor_msg,
 		      pack_hash);
 	else
@@ -1893,10 +1934,13 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 
 	free(objects);
 	strbuf_release(&index_name_buf);
+	strbuf_release(&rev_index_name_buf);
 	if (pack_name == NULL)
 		free((void *) curr_pack);
 	if (index_name == NULL)
 		free((void *) curr_index);
+	if (rev_index_name == NULL)
+		free((void *) curr_rev_index);
 
 	/*
 	 * Let the caller know this pack is not self contained
diff --git a/t/t5325-reverse-index.sh b/t/t5325-reverse-index.sh
new file mode 100755
index 0000000000..2dae213126
--- /dev/null
+++ b/t/t5325-reverse-index.sh
@@ -0,0 +1,71 @@
+#!/bin/sh
+
+test_description='on-disk reverse index'
+. ./test-lib.sh
+
+packdir=.git/objects/pack
+
+test_expect_success 'setup' '
+	test_commit base &&
+
+	pack=$(git pack-objects --all $packdir/pack) &&
+	rev=$packdir/pack-$pack.rev &&
+
+	test_path_is_missing $rev
+'
+
+test_index_pack () {
+	rm -f $rev &&
+	conf=$1 &&
+	shift &&
+	# remove the index since Windows won't overwrite an existing file
+	rm $packdir/pack-$pack.idx &&
+	git -c pack.writeReverseIndex=$conf index-pack "$@" \
+		$packdir/pack-$pack.pack
+}
+
+test_expect_success 'index-pack with pack.writeReverseIndex' '
+	test_index_pack "" &&
+	test_path_is_missing $rev &&
+
+	test_index_pack false &&
+	test_path_is_missing $rev &&
+
+	test_index_pack true &&
+	test_path_is_file $rev
+'
+
+test_expect_success 'index-pack with --[no-]rev-index' '
+	for conf in "" true false
+	do
+		test_index_pack "$conf" --rev-index &&
+		test_path_exists $rev &&
+
+		test_index_pack "$conf" --no-rev-index &&
+		test_path_is_missing $rev
+	done
+'
+
+test_expect_success 'index-pack can verify reverse indexes' '
+	test_when_finished "rm -f $rev" &&
+	test_index_pack true &&
+
+	test_path_is_file $rev &&
+	git index-pack --rev-index --verify $packdir/pack-$pack.pack &&
+
+	# Intentionally corrupt the reverse index.
+	chmod u+w $rev &&
+	printf "xxxx" | dd of=$rev bs=1 count=4 conv=notrunc &&
+
+	test_must_fail git index-pack --rev-index --verify \
+		$packdir/pack-$pack.pack 2>err &&
+	grep "validation error" err
+'
+
+test_expect_success 'index-pack infers reverse index name with -o' '
+	git index-pack --rev-index -o other.idx $packdir/pack-$pack.pack &&
+	test_path_is_file other.idx &&
+	test_path_is_file other.rev
+'
+
+test_done
-- 
2.30.0.138.g6d7191ea01


  parent reply	other threads:[~2021-01-14  2:28 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-08 18:19 [PATCH 0/8] pack-revindex: introduce on-disk '.rev' format Taylor Blau
2021-01-08 18:19 ` [PATCH 1/8] packfile: prepare for the existence of '*.rev' files Taylor Blau
2021-01-08 18:20 ` [PATCH 2/8] pack-write.c: prepare to write 'pack-*.rev' files Taylor Blau
2021-01-08 18:20 ` [PATCH 3/8] builtin/index-pack.c: write reverse indexes Taylor Blau
2021-01-08 18:20 ` [PATCH 4/8] builtin/pack-objects.c: respect 'pack.writeReverseIndex' Taylor Blau
2021-01-08 18:20 ` [PATCH 5/8] Documentation/config/pack.txt: advertise 'pack.writeReverseIndex' Taylor Blau
2021-01-08 18:20 ` [PATCH 6/8] t: prepare for GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-12 17:11   ` Ævar Arnfjörð Bjarmason
2021-01-12 18:40     ` Taylor Blau
2021-01-08 18:20 ` [PATCH 7/8] t: support GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-12 16:49   ` Derrick Stolee
2021-01-12 17:34     ` Taylor Blau
2021-01-12 17:18   ` Ævar Arnfjörð Bjarmason
2021-01-12 17:39     ` Derrick Stolee
2021-01-12 18:17       ` Taylor Blau
2021-01-08 18:20 ` [PATCH 8/8] pack-revindex: ensure that on-disk reverse indexes are given precedence Taylor Blau
2021-01-13 22:28 ` [PATCH v2 0/8] pack-revindex: introduce on-disk '.rev' format Taylor Blau
2021-01-13 22:28   ` [PATCH v2 1/8] packfile: prepare for the existence of '*.rev' files Taylor Blau
2021-01-14  7:22     ` Junio C Hamano
2021-01-14 12:07       ` Derrick Stolee
2021-01-14 19:57         ` Jeff King
2021-01-14 18:28       ` Taylor Blau
2021-01-14  7:26     ` Junio C Hamano
2021-01-14 18:13       ` Taylor Blau
2021-01-14 20:57         ` Junio C Hamano
2021-01-22 22:54     ` Jeff King
2021-01-25 17:44       ` Taylor Blau
2021-01-25 18:27         ` Jeff King
2021-01-25 19:04         ` Junio C Hamano
2021-01-25 19:23           ` Taylor Blau
2021-01-13 22:28   ` [PATCH v2 2/8] pack-write.c: prepare to write 'pack-*.rev' files Taylor Blau
2021-01-22 23:24     ` Jeff King
2021-01-25 19:15       ` Taylor Blau
2021-01-26 21:43         ` Jeff King
2021-01-13 22:28   ` Taylor Blau [this message]
2021-01-22 23:53     ` [PATCH v2 3/8] builtin/index-pack.c: write reverse indexes Jeff King
2021-01-25 20:03       ` Taylor Blau
2021-01-13 22:28   ` [PATCH v2 4/8] builtin/pack-objects.c: respect 'pack.writeReverseIndex' Taylor Blau
2021-01-22 23:57     ` Jeff King
2021-01-23  0:08       ` Jeff King
2021-01-25 20:21         ` Taylor Blau
2021-01-25 20:50           ` Jeff King
2021-01-13 22:28   ` [PATCH v2 5/8] Documentation/config/pack.txt: advertise 'pack.writeReverseIndex' Taylor Blau
2021-01-13 22:28   ` [PATCH v2 6/8] t: prepare for GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-13 22:28   ` [PATCH v2 7/8] t: support GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-13 22:28   ` [PATCH v2 8/8] pack-revindex: ensure that on-disk reverse indexes are given precedence Taylor Blau
2021-01-25 23:37 ` [PATCH v3 00/10] pack-revindex: introduce on-disk '.rev' format Taylor Blau
2021-01-25 23:37   ` [PATCH v3 01/10] packfile: prepare for the existence of '*.rev' files Taylor Blau
2021-01-29  0:27     ` Jeff King
2021-01-29  1:14       ` Taylor Blau
2021-01-30  8:39         ` Jeff King
2021-01-25 23:37   ` [PATCH v3 02/10] pack-write.c: prepare to write 'pack-*.rev' files Taylor Blau
2021-01-25 23:37   ` [PATCH v3 03/10] builtin/index-pack.c: allow stripping arbitrary extensions Taylor Blau
2021-01-29  0:28     ` Jeff King
2021-01-29  1:15       ` Taylor Blau
2021-01-25 23:37   ` [PATCH v3 04/10] builtin/index-pack.c: write reverse indexes Taylor Blau
2021-01-25 23:37   ` [PATCH v3 05/10] builtin/pack-objects.c: respect 'pack.writeReverseIndex' Taylor Blau
2021-01-25 23:37   ` [PATCH v3 06/10] Documentation/config/pack.txt: advertise 'pack.writeReverseIndex' Taylor Blau
2021-01-29  0:30     ` Jeff King
2021-01-29  1:17       ` Taylor Blau
2021-01-30  8:41         ` Jeff King
2021-01-25 23:37   ` [PATCH v3 07/10] t: prepare for GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-29  0:45     ` Jeff King
2021-01-29  1:09       ` Eric Sunshine
2021-01-29  1:21       ` Taylor Blau
2021-01-30  8:43         ` Jeff King
2021-01-29  2:42       ` Junio C Hamano
2021-01-25 23:37   ` [PATCH v3 08/10] t: support GIT_TEST_WRITE_REV_INDEX Taylor Blau
2021-01-29  0:47     ` Jeff King
2021-01-25 23:37   ` [PATCH v3 09/10] pack-revindex: ensure that on-disk reverse indexes are given precedence Taylor Blau
2021-01-29  0:53     ` Jeff King
2021-01-29  1:25       ` Taylor Blau
2021-01-30  8:46         ` Jeff King
2021-01-25 23:37   ` [PATCH v3 10/10] t5325: check both on-disk and in-memory reverse index Taylor Blau
2021-01-29  1:04     ` Jeff King
2021-01-29  1:05     ` Jeff King
2021-01-29  1:32       ` Taylor Blau
2021-01-30  8:47         ` Jeff King
2021-01-26  2:36   ` [PATCH v3 00/10] pack-revindex: introduce on-disk '.rev' format Junio C Hamano
2021-01-26  2:49     ` Taylor Blau
2021-01-29  1:06   ` Jeff King
2021-01-29  1:34     ` Taylor Blau

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

  List information: http://vger.kernel.org/majordomo-info.html

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

  git send-email \
    --in-reply-to=5b18ada61113faa9dc1de584366cb39b6a449ec6.1610576805.git.me@ttaylorr.com \
    --to=me@ttaylorr.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jrnieder@gmail.com \
    --cc=peff@peff.net \
    /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.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).