sparse-checkout: add 'clean' command

When users change their sparse-checkout definitions to add new
directories and remove old ones, there may be a few reasons why
directories no longer in scope remain (ignored or excluded files still
exist, Windows handles are still open, etc.). When these files still
exist, the sparse index feature notices that a tracked, but sparse,
directory still exists on disk and thus the index expands. This causes a
performance hit _and_ the advice printed isn't very helpful. Using 'git
clean' isn't enough (generally '-dfx' may be needed) but also this may
not be sufficient.

Add a new subcommand to 'git sparse-checkout' that removes these
tracked-but-sparse directories, including any excluded or ignored files
underneath. This is the most extreme method for doing this, but it works
when the sparse-checkout is in cone mode and is expected to rescope
based on directories, not files.

Be sure to add a --dry-run option so users can predict what will be
deleted. In general, output the directories that are being removed so
users can know what was removed.

Note that untracked directories within the sparse-checkout remain.
Further, directories that contain staged changes are not deleted. This
is a detail that is partly hidden by the implementation which relies on
collapsing the index to a sparse index in-memory and only deleting
directories that are listed as sparse in the index. If a staged change
exists, then that entry is not stored as a sparse tree entry and thus
remains on-disk until committed or reset.

Signed-off-by: Derrick Stolee <[email protected]>

Author: derrickstolee

Documentation/git-sparse-checkout.adoc

@@ -9,7 +9,7 @@ git-sparse-checkout - Reduce your working tree to a subset of tracked files
 SYNOPSIS
 --------
 [verse]
-'git sparse-checkout' (init | list | set | add | reapply | disable | check-rules) [<options>]
+'git sparse-checkout' (init | list | set | add | reapply | disable | check-rules | clean) [<options>]
 
 
 DESCRIPTION
@@ -111,6 +111,17 @@ flags, with the same meaning as the flags from the `set` command, in order
 to change which sparsity mode you are using without needing to also respecify
 all sparsity paths.
 
+'clean'::
+	Remove all files in tracked directories that are outside of the
+	sparse-checkout definition. This subcommand requires cone-mode
+	sparse-checkout to be sure that we know which directories are
+	both tracked and all contained paths are not in the sparse-checkout.
+	This command can be used to be sure the sparse index works
+	efficiently.
++
+The `clean` command can also take the `--dry-run` (`-n`) option to list
+the directories it would remove without performing any filesystem changes.
+
 'disable'::
 	Disable the `core.sparseCheckout` config setting, and restore the
 	working directory to include all files.

builtin/sparse-checkout.c

@@ -2,6 +2,7 @@
 #define DISABLE_SIGN_COMPARE_WARNINGS
 
 #include "builtin.h"
+#include "abspath.h"
 #include "config.h"
 #include "dir.h"
 #include "environment.h"
@@ -23,7 +24,7 @@
 static const char *empty_base = "";
 
 static char const * const builtin_sparse_checkout_usage[] = {
-	N_("git sparse-checkout (init | list | set | add | reapply | disable | check-rules) [<options>]"),
+	N_("git sparse-checkout (init | list | set | add | reapply | disable | check-rules | clean) [<options>]"),
 	NULL
 };
 
@@ -924,6 +925,73 @@ static int sparse_checkout_reapply(int argc, const char **argv,
 	return update_working_directory(repo, NULL);
 }
 
+static char const * const builtin_sparse_checkout_clean_usage[] = {
+	"git sparse-checkout clean [-n|--dry-run]",
+	NULL
+};
+
+static struct sparse_checkout_clean_opts {
+	int dry_run;
+} clean_opts;
+
+static const char *msg_remove = N_("Removing %s\n");
+static const char *msg_would_remove = N_("Would remove %s\n");
+
+static int sparse_checkout_clean(int argc, const char **argv,
+				   const char *prefix,
+				   struct repository *repo)
+{
+	struct strbuf full_path = STRBUF_INIT;
+	size_t worktree_len;
+	static struct option builtin_sparse_checkout_clean_options[] = {
+		OPT_BOOL('n', "dry-run", &clean_opts.dry_run,
+			 N_("list the directories that would be removed without making filesystem changes")),
+		OPT_END(),
+	};
+
+	setup_work_tree();
+	if (!repo->settings.sparse_checkout)
+		die(_("must be in a sparse-checkout to clean directories"));
+	if (!repo->settings.sparse_checkout_cone)
+		die(_("must be in a cone-mode sparse-checkout to clean directories"));
+
+	argc = parse_options(argc, argv, prefix,
+			     builtin_sparse_checkout_clean_options,
+			     builtin_sparse_checkout_clean_usage, 0);
+
+	if (repo_read_index(repo) < 0)
+		die(_("failed to read index"));
+
+	if (convert_to_sparse(repo->index, SPARSE_INDEX_MEMORY_ONLY))
+		die(_("failed to convert index to a sparse index"));
+
+	strbuf_addstr(&full_path, repo->worktree);
+	strbuf_addch(&full_path, '/');
+	worktree_len = full_path.len;
+
+	for (size_t i = 0; i < repo->index->cache_nr; i++) {
+		struct cache_entry *ce = repo->index->cache[i];
+		if (!S_ISSPARSEDIR(ce->ce_mode))
+			continue;
+		strbuf_setlen(&full_path, worktree_len);
+		strbuf_add(&full_path, ce->name, ce->ce_namelen);
+
+		if (!is_directory(full_path.buf))
+			continue;
+
+		if (!clean_opts.dry_run) {
+			printf(msg_remove, ce->name);
+			if (remove_dir_recursively(&full_path, 0))
+				warning_errno(_("failed to remove '%s'"), ce->name);
+		} else {
+			printf(msg_would_remove, ce->name);
+		}
+	}
+
+	strbuf_release(&full_path);
+	return 0;
+}
+
 static char const * const builtin_sparse_checkout_disable_usage[] = {
 	"git sparse-checkout disable",
 	NULL
@@ -1079,6 +1147,7 @@ int cmd_sparse_checkout(int argc,
 		OPT_SUBCOMMAND("set", &fn, sparse_checkout_set),
 		OPT_SUBCOMMAND("add", &fn, sparse_checkout_add),
 		OPT_SUBCOMMAND("reapply", &fn, sparse_checkout_reapply),
+		OPT_SUBCOMMAND("clean", &fn, sparse_checkout_clean),
 		OPT_SUBCOMMAND("disable", &fn, sparse_checkout_disable),
 		OPT_SUBCOMMAND("check-rules", &fn, sparse_checkout_check_rules),
 		OPT_END(),

t/t1091-sparse-checkout-builtin.sh

@@ -1050,5 +1050,62 @@ test_expect_success 'check-rules null termination' '
 	test_cmp expect actual
 '
 
+test_expect_success 'clean' '
+	git -C repo sparse-checkout set --cone deep/deeper1 &&
+	mkdir repo/deep/deeper2 repo/folder1 &&
+	touch repo/deep/deeper2/file &&
+	touch repo/folder1/file &&
+
+	cat >expect <<-\EOF &&
+	Would remove deep/deeper2/
+	Would remove folder1/
+	EOF
+
+	git -C repo sparse-checkout clean --dry-run >out &&
+	test_cmp expect out &&
+
+	test_path_exists repo/deep/deeper2 &&
+	test_path_exists repo/folder1 &&
+
+	cat >expect <<-\EOF &&
+	Removing deep/deeper2/
+	Removing folder1/
+	EOF
+
+	git -C repo sparse-checkout clean >out &&
+	test_cmp expect out &&
+
+	! test_path_exists repo/deep/deeper2 &&
+	! test_path_exists repo/folder1
+'
+
+test_expect_success 'clean with staged sparse change' '
+	git -C repo sparse-checkout set --cone deep/deeper1 &&
+	mkdir repo/deep/deeper2 repo/folder1 &&
+	touch repo/deep/deeper2/file &&
+	touch repo/folder1/file &&
+
+	git -C repo add --sparse folder1/file &&
+
+	cat >expect <<-\EOF &&
+	Would remove deep/deeper2/
+	EOF
+
+	git -C repo sparse-checkout clean --dry-run >out &&
+	test_cmp expect out &&
+
+	test_path_exists repo/deep/deeper2 &&
+	test_path_exists repo/folder1 &&
+
+	cat >expect <<-\EOF &&
+	Removing deep/deeper2/
+	EOF
+
+	git -C repo sparse-checkout clean >out &&
+	test_cmp expect out &&
+
+	! test_path_exists repo/deep/deeper2 &&
+	test_path_exists repo/folder1
+'
 
 test_done