git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Jeff Hostetler via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: gitster@pobox.com, johannes.schindelin@gmx.de, peff@peff.net,
	ps@pks.im, me@ttaylorr.com, johncai86@gmail.com,
	newren@gmail.com, Derrick Stolee <stolee@gmail.com>,
	Jeff Hostetler <jeffhostetler@github.com>
Subject: [PATCH 10/30] survey: add command line opts to select references
Date: Tue, 10 Sep 2024 02:28:35 +0000	[thread overview]
Message-ID: <90986876381e4ccc10c5e191a3928407181e6a04.1725935335.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.1786.git.1725935335.gitgitgadget@gmail.com>

From: Jeff Hostetler <jeffhostetler@github.com>

By default we will scan all references in "refs/heads/", "refs/tags/"
and "refs/remotes/".

Add command line opts let the use ask for all refs or a subset of them
and to include a detached HEAD.

Signed-off-by: Jeff Hostetler <jeffhostetler@github.com>
Signed-off-by: Derrick Stolee <stolee@gmail.com>
---
 Documentation/git-survey.txt | 34 +++++++++++++
 builtin/survey.c             | 99 ++++++++++++++++++++++++++++++++++++
 2 files changed, 133 insertions(+)

diff --git a/Documentation/git-survey.txt b/Documentation/git-survey.txt
index cdd1ec4358b..c648ef704e3 100644
--- a/Documentation/git-survey.txt
+++ b/Documentation/git-survey.txt
@@ -19,12 +19,46 @@ As repositories grow to "monorepo" size, certain data shapes can cause
 performance problems.  `git-survey` attempts to measure and report on
 known problem areas.
 
+Ref Selection and Reachable Objects
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In this first analysis phase, `git survey` will iterate over the set of
+requested branches, tags, and other refs and treewalk over all of the
+reachable commits, trees, and blobs and generate various statistics.
+
 OPTIONS
 -------
 
 --progress::
 	Show progress.  This is automatically enabled when interactive.
 
+Ref Selection
+~~~~~~~~~~~~~
+
+The following options control the set of refs that `git survey` will examine.
+By default, `git survey` will look at tags, local branches, and remote refs.
+If any of the following options are given, the default set is cleared and
+only refs for the given options are added.
+
+--all-refs::
+	Use all refs.  This includes local branches, tags, remote refs,
+	notes, and stashes.  This option overrides all of the following.
+
+--branches::
+	Add local branches (`refs/heads/`) to the set.
+
+--tags::
+	Add tags (`refs/tags/`) to the set.
+
+--remotes::
+	Add remote branches (`refs/remote/`) to the set.
+
+--detached::
+	Add HEAD to the set.
+
+--other::
+	Add notes (`refs/notes/`) and stashes (`refs/stash/`) to the set.
+
 OUTPUT
 ------
 
diff --git a/builtin/survey.c b/builtin/survey.c
index 4cfd0f0293c..e0e844201de 100644
--- a/builtin/survey.c
+++ b/builtin/survey.c
@@ -7,19 +7,117 @@ static const char * const survey_usage[] = {
 	NULL,
 };
 
+struct survey_refs_wanted {
+	int want_all_refs; /* special override */
+
+	int want_branches;
+	int want_tags;
+	int want_remotes;
+	int want_detached;
+	int want_other; /* see FILTER_REFS_OTHERS -- refs/notes/, refs/stash/ */
+};
+
+/*
+ * The set of refs that we will search if the user doesn't select
+ * any on the command line.
+ */
+static struct survey_refs_wanted refs_if_unspecified = {
+	.want_all_refs = 0,
+
+	.want_branches = 1,
+	.want_tags = 1,
+	.want_remotes = 1,
+	.want_detached = 0,
+	.want_other = 0,
+};
+
 struct survey_opts {
 	int verbose;
 	int show_progress;
+	struct survey_refs_wanted refs;
 };
 
 static struct survey_opts survey_opts = {
 	.verbose = 0,
 	.show_progress = -1, /* defaults to isatty(2) */
+
+	.refs.want_all_refs = -1,
+
+	.refs.want_branches = -1, /* default these to undefined */
+	.refs.want_tags = -1,
+	.refs.want_remotes = -1,
+	.refs.want_detached = -1,
+	.refs.want_other = -1,
 };
 
+/*
+ * After parsing the command line arguments, figure out which refs we
+ * should scan.
+ *
+ * If ANY were given in positive sense, then we ONLY include them and
+ * do not use the builtin values.
+ */
+static void fixup_refs_wanted(void)
+{
+	struct survey_refs_wanted *rw = &survey_opts.refs;
+
+	/*
+	 * `--all-refs` overrides and enables everything.
+	 */
+	if (rw->want_all_refs == 1) {
+		rw->want_branches = 1;
+		rw->want_tags = 1;
+		rw->want_remotes = 1;
+		rw->want_detached = 1;
+		rw->want_other = 1;
+		return;
+	}
+
+	/*
+	 * If none of the `--<ref-type>` were given, we assume all
+	 * of the builtin unspecified values.
+	 */
+	if (rw->want_branches == -1 &&
+	    rw->want_tags == -1 &&
+	    rw->want_remotes == -1 &&
+	    rw->want_detached == -1 &&
+	    rw->want_other == -1) {
+		*rw = refs_if_unspecified;
+		return;
+	}
+
+	/*
+	 * Since we only allow positive boolean values on the command
+	 * line, we will only have true values where they specified
+	 * a `--<ref-type>`.
+	 *
+	 * So anything that still has an unspecified value should be
+	 * set to false.
+	 */
+	if (rw->want_branches == -1)
+		rw->want_branches = 0;
+	if (rw->want_tags == -1)
+		rw->want_tags = 0;
+	if (rw->want_remotes == -1)
+		rw->want_remotes = 0;
+	if (rw->want_detached == -1)
+		rw->want_detached = 0;
+	if (rw->want_other == -1)
+		rw->want_other = 0;
+}
+
 static struct option survey_options[] = {
 	OPT__VERBOSE(&survey_opts.verbose, N_("verbose output")),
 	OPT_BOOL(0, "progress", &survey_opts.show_progress, N_("show progress")),
+
+	OPT_BOOL_F(0, "all-refs", &survey_opts.refs.want_all_refs, N_("include all refs"),          PARSE_OPT_NONEG),
+
+	OPT_BOOL_F(0, "branches", &survey_opts.refs.want_branches, N_("include branches"),          PARSE_OPT_NONEG),
+	OPT_BOOL_F(0, "tags",     &survey_opts.refs.want_tags,     N_("include tags"),              PARSE_OPT_NONEG),
+	OPT_BOOL_F(0, "remotes",  &survey_opts.refs.want_remotes,  N_("include all remotes refs"),  PARSE_OPT_NONEG),
+	OPT_BOOL_F(0, "detached", &survey_opts.refs.want_detached, N_("include detached HEAD"),     PARSE_OPT_NONEG),
+	OPT_BOOL_F(0, "other",    &survey_opts.refs.want_other,    N_("include notes and stashes"), PARSE_OPT_NONEG),
+
 	OPT_END(),
 };
 
@@ -55,6 +153,7 @@ int cmd_survey(int argc, const char **argv, const char *prefix)
 
 	if (survey_opts.show_progress < 0)
 		survey_opts.show_progress = isatty(2);
+	fixup_refs_wanted();
 
 	return 0;
 }
-- 
gitgitgadget


  parent reply	other threads:[~2024-09-10  2:29 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-10  2:28 [PATCH 00/30] [RFC] Path-walk API and applications Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 01/30] path-walk: introduce an object walk by path Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 02/30] backfill: add builtin boilerplate Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 03/30] backfill: basic functionality and tests Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 04/30] backfill: add --batch-size=<n> option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 05/30] backfill: add --sparse option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 06/30] backfill: assume --sparse when sparse-checkout is enabled Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 07/30] path-walk: allow consumer to specify object types Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 08/30] path-walk: allow visiting tags Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 09/30] survey: stub in new experimental `git-survey` command Jeff Hostetler via GitGitGadget
2024-09-10  2:28 ` Jeff Hostetler via GitGitGadget [this message]
2024-09-10  2:28 ` [PATCH 11/30] survey: collect the set of requested refs Jeff Hostetler via GitGitGadget
2024-09-10  2:28 ` [PATCH 12/30] survey: start pretty printing data in table form Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 13/30] survey: add object count summary Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 14/30] survey: summarize total sizes by object type Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 15/30] survey: show progress during object walk Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 16/30] survey: add ability to track prioritized lists Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 17/30] survey: add report of "largest" paths Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 18/30] revision: create mark_trees_uninteresting_dense() Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 19/30] path-walk: add prune_all_uninteresting option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 20/30] pack-objects: add --path-walk option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 21/30] pack-objects: extract should_attempt_deltas() Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 22/30] pack-objects: introduce GIT_TEST_PACK_PATH_WALK Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 23/30] p5313: add size comparison test Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 24/30] repack: add --path-walk option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 25/30] pack-objects: enable --path-walk via config Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 26/30] scalar: enable path-walk during push " Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 27/30] pack-objects: add --full-name-hash option Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 28/30] test-name-hash: add helper to compute name-hash functions Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 29/30] p5314: add a size test for name-hash collisions Derrick Stolee via GitGitGadget
2024-09-10  2:28 ` [PATCH 30/30] pack-objects: output debug info about deltas Derrick Stolee via GitGitGadget
2024-09-11 21:32 ` [PATCH 00/30] [RFC] Path-walk API and applications Junio C Hamano
2024-09-17 10:41 ` Christian Couder
2024-09-18 23:18   ` Derrick Stolee
2024-09-22 18:37     ` Junio C Hamano
2024-09-23  1:22       ` Derrick Stolee
2024-09-23 16:56         ` Junio C Hamano
2024-09-22 21:08 ` Kristoffer Haugsbakk

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=90986876381e4ccc10c5e191a3928407181e6a04.1725935335.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jeffhostetler@github.com \
    --cc=johannes.schindelin@gmx.de \
    --cc=johncai86@gmail.com \
    --cc=me@ttaylorr.com \
    --cc=newren@gmail.com \
    --cc=peff@peff.net \
    --cc=ps@pks.im \
    --cc=stolee@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 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 NNTP newsgroup(s).