[PATCH v4 1/1] repo: add filtering options to "repo structure"

["Mark C. Chu-Carroll" <markchucarroll@fastmail.com>]

The current implementation of "git repo stucture" provides summary
information about everything in the repository - all of the
branches, remotes, tags, stashes, and notes. But sometimes
to properly diagnose a problem, it's useful to be able to
filter this information to get focused data about the specific
part of the repo that's exhibiting a problem.

Update "git repo structure" to use rev expressions
to filter the set of objects to be processed.

This implementation makes an awkward trade-off involving
"setup_revisions". In order to accept standard the standard
revs parameters, it uses `setup_revisions`, which does a ref
walk and populates the pending objects list that will be used
by "repo structure". But this ref walk doesn't count refs in the
way that "repo structure" requires, and because "setup_revisions"
doesn't support a custom callback for its ref-walk, that's not
changeable.

So in the cases where a user specifies revs, "repo structure" does
an initial ref-walk as part of "setup_revisions", and then a second
ref-walk in "count_references" in repo.c to count by reference type.
Further, if the user doesn't specify a revs parameter, "setup_revisions"
is not called, so the "count_references" walk needs to add objects
to the pending list. A parameter is added to "count_references"
to allow it to distinguish the cases where the pending
list is already populated from the case where it needs to
populate it.

Signed-off-by: Mark C. Chu-Carroll <markchucarroll@fastmail.com>
---
 Documentation/git-repo.adoc |  32 +++++-
 builtin/repo.c              |  32 ++++--
 t/t1901-repo-structure.sh   | 211 +++++++++++++++++++++++++++---------
 3 files changed, 210 insertions(+), 65 deletions(-)

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index ed7d80c690..67be7efd23 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -10,7 +10,7 @@ SYNOPSIS
 [synopsis]
 git repo info [--format=(lines|nul) | -z] [--all | <key>...]
 git repo info --keys [--format=(lines|nul) | -z]
-git repo structure [--format=(table|lines|nul) | -z]
+git repo structure [--format=(table|lines|nul) | -z] [<revs>...]
 
 DESCRIPTION
 -----------
@@ -56,7 +56,7 @@ supported:
 `nul`:::
 	Similar to `lines`, but using a _NUL_ character after each value.
 
-`structure [--format=(table|lines|nul) | -z]`::
+`structure [--format=(table|lines|nul) | -z] [<revs>...]`::
 	Retrieve statistics about the current repository structure. The
 	following kinds of information are reported:
 +
@@ -66,6 +66,12 @@ supported:
 * Total disk size of reachable objects by type
 * Largest reachable objects in the repository by type
 +
+The set of objects counted can be filtered by specifying a collection
+of revisions to select which objects will be counted. These parameters
+follow the same syntax as the parameters to similar commands like
+`git log`. If no includes are specified, then the include set is all
+reachable objects.
++
 The output format can be chosen through the flag `--format`. Three formats are
 supported:
 +
@@ -141,6 +147,28 @@ using the `nul` format:
 git repo info --format=nul layout.bare layout.shallow
 ------------
 
+* Generates information about storage usage in the repository:
++
+------------
+git repo structure
+------------
++
+
+* Generates information about storage usage in the repository omitting
+the branch "foo":
++
+------------
+git repo structure ^foo
+------------
++
+* Generates information about repository objects reachable from
+the references "x" and "y", but omitting anything that can
+only be reached on a path including "xchild":
++
+------------
+git repo structure x y ^xchild
+------------
++
 SEE ALSO
 --------
 linkgit:git-rev-parse[1]
diff --git a/builtin/repo.c b/builtin/repo.c
index 84e012f83f..081940a85c 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -27,7 +27,7 @@
 	"git repo info --keys [--format=(lines|nul) | -z]"
 
 #define REPO_STRUCTURE_USAGE \
-	"git repo structure [--format=(table|lines|nul) | -z]"
+	"git repo structure [--format=(table|lines|nul) | -z] [<revs>...]"
 
 static const char *const repo_usage[] = {
 	REPO_INFO_USAGE,
@@ -740,6 +740,7 @@ struct count_references_data {
 	struct ref_stats *stats;
 	struct rev_info *revs;
 	struct progress *progress;
+	bool add_to_pending;
 };
 
 static int count_references(const struct reference *ref, void *cb_data)
@@ -766,10 +767,12 @@ static int count_references(const struct reference *ref, void *cb_data)
 	}
 
 	/*
-	 * While iterating through references for counting, also add OIDs in
+	 * While iterating through references for counting, if we didn't already
+	 * populate the pending list in setup_revisions, also add OIDs in
 	 * preparation for the path walk.
 	 */
-	add_pending_oid(data->revs, NULL, ref->oid, 0);
+	if (data->add_to_pending)
+		add_pending_oid(data->revs, NULL, ref->oid, 0);
 
 	ref_count = get_total_reference_count(stats);
 	display_progress(data->progress, ref_count);
@@ -780,11 +783,13 @@ static int count_references(const struct reference *ref, void *cb_data)
 static void structure_count_references(struct ref_stats *stats,
 				       struct rev_info *revs,
 				       struct repository *repo,
-				       int show_progress)
+				       int show_progress,
+				       bool add_to_pending)
 {
 	struct count_references_data data = {
 		.stats = stats,
 		.revs = revs,
+		.add_to_pending = add_to_pending
 	};
 
 	if (show_progress)
@@ -935,6 +940,7 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
 	struct repo_structure stats = { 0 };
 	struct rev_info revs;
 	int show_progress = -1;
+	bool included_revision_args = false;
 	struct option options[] = {
 		OPT_CALLBACK_F(0, "format", &format, N_("format"),
 			       N_("output format"),
@@ -947,16 +953,20 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
 		OPT_END()
 	};
 
-	argc = parse_options(argc, argv, prefix, options, repo_structure_usage, 0);
-	if (argc)
-		usage(_("too many arguments"));
-
-	repo_init_revisions(repo, &revs, prefix);
-
+	argc = parse_options(argc, argv, prefix, options, repo_structure_usage,
+			     PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN_OPT);
 	if (show_progress < 0)
 		show_progress = isatty(2);
 
-	structure_count_references(&stats.refs, &revs, repo, show_progress);
+	repo_init_revisions(repo, &revs, prefix);
+	if (argc > 1) {
+		argc = setup_revisions(argc, argv, &revs, NULL);
+		included_revision_args = true;
+	}
+	if (argc > 1)
+		usage(_("too many arguments"));
+
+	structure_count_references(&stats.refs, &revs, repo, show_progress, !included_revision_args);
 	structure_count_objects(&stats.objects, &revs, repo, show_progress);
 
 	switch (format) {
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index 02cc2b594a..e35b46a277 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -21,58 +21,6 @@ object_type_disk_usage() {
 	fi
 }
 
-test_expect_success 'empty repository' '
-	test_when_finished "rm -rf repo" &&
-	git init repo &&
-	(
-		cd repo &&
-		cat >expect <<-\EOF &&
-		| Repository structure      | Value  |
-		| ------------------------- | ------ |
-		| * References              |        |
-		|   * Count                 |    0   |
-		|     * Branches            |    0   |
-		|     * Tags                |    0   |
-		|     * Remotes             |    0   |
-		|     * Others              |    0   |
-		|                           |        |
-		| * Reachable objects       |        |
-		|   * Count                 |    0   |
-		|     * Commits             |    0   |
-		|     * Trees               |    0   |
-		|     * Blobs               |    0   |
-		|     * Tags                |    0   |
-		|   * Inflated size         |    0 B |
-		|     * Commits             |    0 B |
-		|     * Trees               |    0 B |
-		|     * Blobs               |    0 B |
-		|     * Tags                |    0 B |
-		|   * Disk size             |    0 B |
-		|     * Commits             |    0 B |
-		|     * Trees               |    0 B |
-		|     * Blobs               |    0 B |
-		|     * Tags                |    0 B |
-		|                           |        |
-		| * Largest objects         |        |
-		|   * Commits               |        |
-		|     * Maximum size        |    0 B |
-		|     * Maximum parents     |    0   |
-		|   * Trees                 |        |
-		|     * Maximum size        |    0 B |
-		|     * Maximum entries     |    0   |
-		|   * Blobs                 |        |
-		|     * Maximum size        |    0 B |
-		|   * Tags                  |        |
-		|     * Maximum size        |    0 B |
-		EOF
-
-		git repo structure >out 2>err &&
-
-		test_cmp expect out &&
-		test_line_count = 0 err
-	)
-'
-
 test_expect_success SHA1 'repository with references and objects' '
 	test_when_finished "rm -rf repo" &&
 	git init repo &&
@@ -144,6 +92,165 @@ test_expect_success SHA1 'repository with references and objects' '
 	)
 '
 
+test_expect_success SHA1 'repository with branches' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 1005 &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+		git checkout -b grobble &&
+		test_commit_bulk --ref=refs/heads/grobble 20 &&
+		git checkout master &&
+		test_commit_bulk 20 &&
+		# Also creates a commit, tree, and blob.
+		git notes add -m foo &&
+		git repo structure --format=lines  >actual 2>actual-err &&
+		test_line_count = 0 actual-err &&
+		test_grep "objects.commits.inflated.size=231976" actual &&
+		test_grep "objects.commits.count=1046" actual &&
+		test_grep "objects.blobs.count=1006" actual &&
+		test_grep "objects.trees.count=1006" actual &&
+		test_grep "objects.trees.disk_size=284547" actual &&
+		test_grep "objects.blobs.disk_size=21022" actual &&
+		test_grep "objects.tags.disk_size=126" actual &&
+		test_line_count = 0 actual-err
+	)
+'
+
+test_expect_success SHA1 'filter by a positive rev' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 1005 &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+		git checkout -b grobble &&
+		test_commit_bulk --ref=refs/heads/grobble 20 &&
+		git checkout master &&
+		test_commit_bulk 20 &&
+		git notes add -m foo &&
+
+		git repo structure --format=lines grobble >actual 2>actual-err &&
+		test_grep "objects.commits.count=1025" actual &&
+		test_grep "objects.commits.disk_size=160455" actual &&
+		test_grep "objects.commits.inflated.size=227371" actual &&
+		test_grep "objects.blobs.count=1005" actual &&
+		test_grep "objects.blobs.disk_size=21003" actual &&
+		test_grep "objects.blobs.inflated_size=11958" actual &&
+		test_grep "objects.trees.count=1005" actual &&
+		test_grep "objects.trees.disk_size=284462" actual &&
+		test_grep "objects.trees.inflated_size=16578363" actual &&
+		test_grep "objects.tags.disk_size=0" actual &&
+		test_line_count = 0 actual-err
+	)
+'
+
+test_expect_success SHA1 'filter by both positive and negative revs' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 1005 &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+		git checkout -b grobble &&
+		test_commit_bulk --ref=refs/heads/grobble 20 &&
+		git checkout master &&
+		test_commit_bulk 20 &&
+		# Also creates a commit, tree, and blob.
+		git notes add -m foo &&
+		git repo structure --format=lines  >actual 2>actual-err &&
+		test_line_count = 0 actual-err &&
+
+		git repo structure --format=lines grobble ^master >actual 2>actual-err &&
+		test_grep "objects.commits.count=20" actual &&
+		test_grep "objects.commits.disk_size=3122" actual &&
+		test_grep "objects.commits.inflated.size=4411" actual &&
+		test_grep "objects.blobs.count=1005" actual &&
+		test_grep "objects.blobs.disk_size=21003" actual &&
+		test_grep "objects.blobs.inflated_size=11958" actual &&
+		test_grep "objects.trees.count=1" actual &&
+		test_grep "objects.trees.disk_size=53" actual &&
+		test_grep "objects.trees.inflated_size=33063" actual &&
+		test_grep "objects.tags.disk_size=0" actual &&
+		test_line_count = 0 actual-err
+	)
+'
+
+test_expect_success 'filter by object type' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 1005 &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+		git checkout -b grobble &&
+		test_commit_bulk --ref=refs/heads/grobble 20 &&
+		git checkout master &&
+		test_commit_bulk 20 &&
+		# Also creates a commit, tree, and blob.
+		git notes add -m foo &&
+		git repo structure --format=lines --objects --all --filter=object:type=blob >actual 2>actual-err &&
+		cp actual /tmp/test-actual-exclude-blob &&
+		test_grep "objects.commits.disk_size=0" actual &&
+		test_grep "objects.commits.max_size=0" actual &&
+		test_grep "objects.tags.disk_size=0" actual &&
+		test_grep "objects.tags.inflated_size=0" actual &&
+		test_grep "objects.trees.disk_size=0" actual &&
+		test_grep "objects.trees.inflated_size=0" actual &&
+		test_grep "objects.blobs.disk_size=21022" actual &&
+		test_grep "objects.blobs.count=1006" actual &&
+		test_grep "objects.blobs.disk_size=21022" actual &&
+		test_grep "objects.blobs.inflated_size=11962" actual &&
+		test_line_count = 0 actual-err
+	)
+'
+
+test_expect_success 'filter using by ref^{tree}' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 1005 &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+		git checkout -b grobble &&
+		test_commit_bulk --ref=refs/heads/grobble 20 &&
+		git checkout master &&
+		test_commit_bulk 20 &&
+		# Also creates a commit, tree, and blob.
+		git notes add -m foo &&
+		git repo structure --format=lines HEAD^{tree}  >actual 2>err &&
+		test_grep "objects.commits.count=0" actual &&
+		test_grep "objects.trees.count=1" actual &&
+		test_grep "objects.blobs.count=1005" actual &&
+		test_grep "objects.tags.count=0" actual &&
+		test_grep "objects.commits.inflated_size=0" actual &&
+		test_grep "objects.trees.inflated_size=33063" actual &&
+		test_grep "objects.blobs.inflated_size=11958" actual &&
+		test_grep "objects.tags.inflated_size=0" actual &&
+		test_grep "objects.commits.disk_size=0" actual &&
+		test_grep "objects.trees.disk_size=53" actual &&
+		test_grep "objects.blobs.disk_size=21003" actual &&
+		test_grep "objects.tags.disk_size=0" actual &&
+		test_line_count = 0 err
+	)
+'
+
 test_expect_success SHA1 'lines and nul format' '
 	test_when_finished "rm -rf repo" &&
 	git init repo &&
-- 
2.53.0