backfill: accept revision arguments

The existing implementation of 'git backfill' only includes downloading
missing blobs reachable from HEAD. Advanced uses may desire more general
commit limiting options, such as '--all' for all references, specifying a
commit range via negative references, or specifying a recency of use such as
with '--since=<date>'.

All of these options are available if we use setup_revisions() to parse the
unknown arguments with the revision machinery. This opens up a large number
of possibilities, only a small set of which are tested here.

For documentation, we avoid duplicating the option documentation and instead
link to the documentation of 'git rev-list'.

Note that these arguments currently allow specifying a pathspec, which
modifies the commit history checks but does not limit the paths used in the
backfill logic. This will be updated in a future change.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: derrickstolee

Documentation/git-backfill.adoc

@@ -63,9 +63,12 @@ OPTIONS
 	current sparse-checkout. If the sparse-checkout feature is enabled,
 	then `--sparse` is assumed and can be disabled with `--no-sparse`.
 
+You may also specify the commit limiting options from linkgit:git-rev-list[1].
+
 SEE ALSO
 --------
-linkgit:git-clone[1].
+linkgit:git-clone[1],
+linkgit:git-rev-list[1]
 
 GIT
 ---

builtin/backfill.c

@@ -35,6 +35,7 @@ struct backfill_context {
 	struct oid_array current_batch;
 	size_t min_batch_size;
 	int sparse;
+	struct rev_info revs;
 };
 
 static void backfill_context_clear(struct backfill_context *ctx)
@@ -79,7 +80,6 @@ static int fill_missing_blobs(const char *path UNUSED,
 
 static int do_backfill(struct backfill_context *ctx)
 {
-	struct rev_info revs;
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	int ret;
 
@@ -91,13 +91,14 @@ static int do_backfill(struct backfill_context *ctx)
 		}
 	}
 
-	repo_init_revisions(ctx->repo, &revs, "");
-	handle_revision_arg("HEAD", &revs, 0, 0);
+	/* Walk from HEAD if otherwise unspecified. */
+	if (!ctx->revs.pending.nr)
+		add_head_to_pending(&ctx->revs);
 
 	info.blobs = 1;
 	info.tags = info.commits = info.trees = 0;
 
-	info.revs = &revs;
+	info.revs = &ctx->revs;
 	info.path_fn = fill_missing_blobs;
 	info.path_fn_data = ctx;
 
@@ -108,7 +109,6 @@ static int do_backfill(struct backfill_context *ctx)
 		download_batch(ctx);
 
 	path_walk_info_clear(&info);
-	release_revisions(&revs);
 	return ret;
 }
 
@@ -120,6 +120,7 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 		.current_batch = OID_ARRAY_INIT,
 		.min_batch_size = 50000,
 		.sparse = 0,
+		.revs = REV_INFO_INIT,
 	};
 	struct option options[] = {
 		OPT_UNSIGNED(0, "min-batch-size", &ctx.min_batch_size,
@@ -134,7 +135,12 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 					 builtin_backfill_usage, options);
 
 	argc = parse_options(argc, argv, prefix, options, builtin_backfill_usage,
-			     0);
+			     PARSE_OPT_KEEP_UNKNOWN_OPT |
+			     PARSE_OPT_KEEP_ARGV0 |
+			     PARSE_OPT_KEEP_DASHDASH);
+
+	repo_init_revisions(repo, &ctx.revs, prefix);
+	argc = setup_revisions(argc, argv, &ctx.revs, NULL);
 
 	repo_config(repo, git_default_config, NULL);
 
@@ -143,5 +149,6 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 
 	result = do_backfill(&ctx);
 	backfill_context_clear(&ctx);
+	release_revisions(&ctx.revs);
 	return result;
 }

t/t5620-backfill.sh

@@ -224,6 +224,162 @@ test_expect_success 'backfill --sparse without cone mode (negative)' '
 	test_line_count = 12 missing
 '
 
+test_expect_success 'backfill with revision range' '
+	test_when_finished rm -rf backfill-revs &&
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-revs &&
+
+	# No blobs yet
+	git -C backfill-revs rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	git -C backfill-revs backfill HEAD~2..HEAD &&
+
+	# 30 objects downloaded.
+	git -C backfill-revs rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 18 missing
+'
+
+test_expect_success 'backfill with revisions over stdin' '
+	test_when_finished rm -rf backfill-revs &&
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-revs &&
+
+	# No blobs yet
+	git -C backfill-revs rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	cat >in <<-EOF &&
+	HEAD
+	^HEAD~2
+	EOF
+
+	git -C backfill-revs backfill --stdin <in &&
+
+	# 30 objects downloaded.
+	git -C backfill-revs rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 18 missing
+'
+
+test_expect_success 'backfill with prefix pathspec' '
+	test_when_finished rm -rf backfill-path &&
+	git clone --bare --filter=blob:none		        \
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-path &&
+
+	# No blobs yet
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# TODO: The pathspec should limit the downloaded blobs to
+	# only those matching the prefix "d/f", but currently all
+	# blobs are downloaded.
+	git -C backfill-path backfill HEAD -- d/f &&
+
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 0 missing
+'
+
+test_expect_success 'backfill with multiple pathspecs' '
+	test_when_finished rm -rf backfill-path &&
+	git clone --bare --filter=blob:none		        \
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-path &&
+
+	# No blobs yet
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# TODO: The pathspecs should limit the downloaded blobs to
+	# only those matching "d/f" or "a", but currently all blobs
+	# are downloaded.
+	git -C backfill-path backfill HEAD -- d/f a &&
+
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 0 missing
+'
+
+test_expect_success 'backfill with wildcard pathspec' '
+	test_when_finished rm -rf backfill-path &&
+	git clone --bare --filter=blob:none		        \
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-path &&
+
+	# No blobs yet
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# TODO: The wildcard pathspec should limit downloaded blobs,
+	# but currently all blobs are downloaded.
+	git -C backfill-path backfill HEAD -- "d/file.*.txt" &&
+
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 0 missing
+'
+
+test_expect_success 'backfill with --all' '
+	test_when_finished rm -rf backfill-all &&
+	git clone --no-checkout --filter=blob:none		\
+		"file://$(pwd)/srv-revs.bare" backfill-all &&
+
+	# All blobs from all refs are missing
+	git -C backfill-all rev-list --quiet --objects --all --missing=print >missing &&
+	test_line_count = 54 missing &&
+
+	# Backfill from HEAD gets main blobs only
+	git -C backfill-all backfill HEAD &&
+
+	# Other branch blobs still missing
+	git -C backfill-all rev-list --quiet --objects --all --missing=print >missing &&
+	test_line_count = 2 missing &&
+
+	# Backfill with --all gets everything
+	git -C backfill-all backfill --all &&
+
+	git -C backfill-all rev-list --quiet --objects --all --missing=print >missing &&
+	test_line_count = 0 missing
+'
+
+test_expect_success 'backfill with --first-parent' '
+	test_when_finished rm -rf backfill-fp &&
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main			\
+		"file://$(pwd)/srv-revs.bare" backfill-fp &&
+
+	git -C backfill-fp rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 52 missing &&
+
+	# --first-parent skips the side branch commits, so
+	# s/file.{1,2}.txt v1 blobs (only in side commit 1) are missed.
+	git -C backfill-fp backfill --first-parent HEAD &&
+
+	git -C backfill-fp rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 2 missing
+'
+
+test_expect_success 'backfill with --since' '
+	test_when_finished rm -rf backfill-since &&
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main			\
+		"file://$(pwd)/srv-revs.bare" backfill-since &&
+
+	git -C backfill-since rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 52 missing &&
+
+	# Use a cutoff between commits 4 and 5 (between v1 and v2
+	# iterations). Commits 5-8 still carry v1 of files 2-4 in
+	# their trees, but v1 of file.1.txt is only in commits 1-4.
+	SINCE=$(git -C backfill-since log --first-parent --reverse \
+		--format=%ct HEAD~1 | sed -n 5p) &&
+	git -C backfill-since backfill --since="@$((SINCE - 1))" HEAD &&
+
+	# 6 missing: v1 of file.1.txt in all 6 directories
+	git -C backfill-since rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 6 missing
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd