[Sparse Index] Delete ignored files outside of cone

builtin/sparse-checkout.c

@@ -15,6 +15,7 @@
 #include "wt-status.h"
 #include "quote.h"
 #include "sparse-index.h"
+#include "run-command.h"
 
 static const char *empty_base = "";
 
@@ -100,6 +101,76 @@ static int sparse_checkout_list(int argc, const char **argv)
 	return 0;
 }
 
+static void clean_tracked_sparse_directories(struct repository *r)
+{
+	int i;
+	struct strvec args = STRVEC_INIT;
+
+	/*
+	 * If we are not using cone mode patterns, then we cannot
+	 * delete directories outside of the sparse cone.
+	 */
+	if (!r || !r->index || !r->index->sparse_checkout_patterns ||
+	    !r->index->sparse_checkout_patterns->use_cone_patterns)
+		return;
+	/*
+	 * NEEDSWORK: For now, only use this behavior when index.sparse
+	 * is enabled. We may want this behavior enabled whenever using
+	 * cone mode patterns.
+	 */
+	prepare_repo_settings(r);
+	if (!r->settings.sparse_index)
+		return;
+
+	strvec_pushl(&args, "clean", "-dfx", "--", NULL);
+
+	/*
+	 * Since we now depend on the sparse index to enable this
+	 * behavior, use it to our advantage. This process is more
+	 * complicated without it.
+	 */
+	convert_to_sparse(r->index);
+
+	for (i = 0; i < r->index->cache_nr; i++) {
+		struct cache_entry *ce = r->index->cache[i];
+
+		/*
+		 * Is this a sparse directory? If so, then definitely
+		 * include it. All contained content is outside of the
+		 * patterns.
+		 */
+		if (S_ISSPARSEDIR(ce->ce_mode) &&
+		    repo_file_exists(r, ce->name)) {
+			strvec_push(&args, ce->name);
+			continue;
+		}
+	}
+
+	/*
+	 * Only run if we found an existing sparse directory, otherwise
+	 * the clean will be across the entire worktree!
+	 */
+	if (args.nr > 3)
+		run_command_v_opt(args.v, RUN_GIT_CMD);
+
+	/*
+	 * The 'git clean -dfx -- <path> ...' command empties the
+	 * tracked directories outside of the sparse cone, but does not
+	 * delete the directories themselves. Remove them now.
+	 */
+	for (i = 3; i < args.nr; i++)
+		rmdir_or_warn(args.v[i]);
+
+	strvec_clear(&args);
+
+	/*
+	 * This is temporary: the sparse-checkout builtin is not
+	 * integrated with the sparse-index yet, so we need to keep
+	 * it full during the process.
+	 */
+	ensure_full_index(r->index);
+}
+
 static int update_working_directory(struct pattern_list *pl)
 {
 	enum update_sparsity_result result;
@@ -141,6 +212,8 @@ static int update_working_directory(struct pattern_list *pl)
 	else
 		rollback_lock_file(&lock_file);
 
+	clean_tracked_sparse_directories(r);
+
 	r->index->sparse_checkout_patterns = NULL;
 	return result;
 }
@@ -540,8 +613,11 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m)
 {
 	int result;
 	int changed_config = 0;
+	struct pattern_list *old_pl = xcalloc(1, sizeof(*old_pl));
 	struct pattern_list *pl = xcalloc(1, sizeof(*pl));
 
+	get_sparse_checkout_patterns(old_pl);
+
 	switch (m) {
 	case ADD:
 		if (core_sparse_checkout_cone)
@@ -567,7 +643,9 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m)
 		set_config(MODE_NO_PATTERNS);
 
 	clear_pattern_list(pl);
+	clear_pattern_list(old_pl);
 	free(pl);
+	free(old_pl);
 	return result;
 }
 

t/t1091-sparse-checkout-builtin.sh

@@ -642,4 +642,39 @@ test_expect_success MINGW 'cone mode replaces backslashes with slashes' '
 	check_files repo/deep a deeper1
 '
 
+test_expect_success 'cone mode clears ignored subdirectories' '
+	rm repo/.git/info/sparse-checkout &&
+
+	# NEEDSWORK: --sparse-index is required for now
+	git -C repo sparse-checkout init --cone --sparse-index &&
+	git -C repo sparse-checkout set deep/deeper1 &&
+
+	cat >repo/.gitignore <<-\EOF &&
+	obj/
+	*.o
+	EOF
+
+	git -C repo add .gitignore &&
+	git -C repo commit -m ".gitignore" &&
+
+	mkdir -p repo/obj repo/folder1/obj repo/deep/deeper2/obj &&
+	for file in folder1/obj/a obj/a folder1/file.o folder1.o \
+		    deep/deeper2/obj/a deep/deeper2/file.o file.o
+	do
+		echo ignored >repo/$file || return 1
+	done &&
+
+	git -C repo status --porcelain=v2 >out &&
+	test_must_be_empty out &&
+
+	git -C repo sparse-checkout reapply &&
+	test_path_is_missing repo/folder1 &&
+	test_path_is_missing repo/deep/deeper2 &&
+	test_path_is_dir repo/obj &&
+	test_path_is_file repo/file.o &&
+
+	git -C repo status --porcelain=v2 >out &&
+	test_must_be_empty out
+'
+
 test_done

t/t1092-sparse-checkout-compatibility.sh

@@ -42,6 +42,12 @@ test_expect_success 'setup' '
 		cp -r deep/deeper1/0 folder2 &&
 		echo >>folder1/0/0/0 &&
 		echo >>folder2/0/1 &&
+
+		cat >.gitignore <<-\EOF &&
+		obj/
+		*.o
+		EOF
+
 		git add . &&
 		git commit -m "initial commit" &&
 		git checkout -b base &&
@@ -62,6 +68,7 @@ test_expect_success 'setup' '
 		EOF
 		cp folder1/larger-content folder2/ &&
 		cp folder1/larger-content deep/deeper1/ &&
+
 		git add . &&
 		git commit -m "add interesting rename content" &&
 
@@ -587,6 +594,44 @@ test_expect_success 'sparse-index is not expanded' '
 	ensure_not_expanded add .
 '
 
+test_expect_success 'sparse-index is not expanded (with ignored files outside cone)' '
+	init_repos &&
+
+	write_script adjust_repo <<-\EOF &&
+	mkdir folder1 obj folder1/obj &&
+	echo ignored >folder1/obj/a &&
+	echo ignored >obj/a &&c
+	echo ignored >folder1/file.o &&
+	echo ignored >folder1.o
+	EOF
+
+	run_on_all ../adjust_repo &&
+	git -C sparse-index sparse-checkout reapply &&
+
+	ensure_not_expanded status &&
+	ensure_not_expanded commit --allow-empty -m empty &&
+	echo >>sparse-index/a &&
+	ensure_not_expanded commit -a -m a &&
+	echo >>sparse-index/a &&
+	ensure_not_expanded commit --include a -m a &&
+	echo >>sparse-index/deep/deeper1/a &&
+	ensure_not_expanded commit --include deep/deeper1/a -m deeper &&
+	ensure_not_expanded checkout rename-out-to-out &&
+	ensure_not_expanded checkout - &&
+	ensure_not_expanded switch rename-out-to-out &&
+	ensure_not_expanded switch - &&
+	git -C sparse-index reset --hard &&
+	ensure_not_expanded checkout rename-out-to-out -- deep/deeper1 &&
+	git -C sparse-index reset --hard &&
+	ensure_not_expanded restore -s rename-out-to-out -- deep/deeper1 &&
+	echo >>sparse-index/README.md &&
+	ensure_not_expanded add -A &&
+	echo >>sparse-index/extra.txt &&
+	ensure_not_expanded add extra.txt &&
+	echo >>sparse-index/untracked.txt &&
+	ensure_not_expanded add .
+'
+
 test_expect_success 'reset mixed and checkout orphan' '
 	init_repos &&
 

t/t7519-status-fsmonitor.sh

@@ -389,43 +389,47 @@ test_expect_success 'status succeeds after staging/unstaging' '
 # If "!" is supplied, then we verify that we do not call ensure_full_index
 # during a call to 'git status'. Otherwise, we verify that we _do_ call it.
 check_sparse_index_behavior () {
-	git status --porcelain=v2 >expect &&
-	git sparse-checkout init --cone --sparse-index &&
-	git sparse-checkout set dir1 dir2 &&
+	git -C full status --porcelain=v2 >expect &&
 	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
-		git status --porcelain=v2 >actual &&
+		git -C sparse status --porcelain=v2 >actual &&
 	test_region $1 index ensure_full_index trace2.txt &&
 	test_region fsm_hook query trace2.txt &&
 	test_cmp expect actual &&
-	rm trace2.txt &&
-	git sparse-checkout disable
+	rm trace2.txt
 }
 
 test_expect_success 'status succeeds with sparse index' '
-	git reset --hard &&
+	git clone . full &&
+	git clone . sparse &&
+	git -C sparse sparse-checkout init --cone --sparse-index &&
+	git -C sparse sparse-checkout set dir1 dir2 &&
 
-	test_config core.fsmonitor "$TEST_DIRECTORY/t7519/fsmonitor-all" &&
-	check_sparse_index_behavior ! &&
-
-	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+	write_script .git/hooks/fsmonitor-test <<-\EOF &&
 		printf "last_update_token\0"
 	EOF
-	git config core.fsmonitor .git/hooks/fsmonitor-test &&
+	git -C full config core.fsmonitor ../.git/hooks/fsmonitor-test &&
+	git -C sparse config core.fsmonitor ../.git/hooks/fsmonitor-test &&
 	check_sparse_index_behavior ! &&
 
-	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+	write_script .git/hooks/fsmonitor-test <<-\EOF &&
 		printf "last_update_token\0"
 		printf "dir1/modified\0"
 	EOF
 	check_sparse_index_behavior ! &&
 
-	cp -r dir1 dir1a &&
-	git add dir1a &&
-	git commit -m "add dir1a" &&
+	git -C sparse sparse-checkout add dir1a &&
+
+	for repo in full sparse
+	do
+		cp -r $repo/dir1 $repo/dir1a &&
+		git -C $repo add dir1a &&
+		git -C $repo commit -m "add dir1a" || return 1
+	done &&
+	git -C sparse sparse-checkout set dir1 dir2 &&
 
 	# This one modifies outside the sparse-checkout definition
 	# and hence we expect to expand the sparse-index.
-	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+	write_script .git/hooks/fsmonitor-test <<-\EOF &&
 		printf "last_update_token\0"
 		printf "dir1a/modified\0"
 	EOF

unpack-trees.c

@@ -1286,9 +1286,10 @@ static int sparse_dir_matches_path(const struct cache_entry *ce,
 static struct cache_entry *find_cache_entry(struct traverse_info *info,
 					    const struct name_entry *p)
 {
-	struct cache_entry *ce;
+	struct cache_entry *ce = NULL;
 	int pos = find_cache_pos(info, p->path, p->pathlen);
 	struct unpack_trees_options *o = info->data;
+	struct strbuf full_path = STRBUF_INIT;
 
 	if (0 <= pos)
 		return o->src_index->cache[pos];
@@ -1304,6 +1305,10 @@ static struct cache_entry *find_cache_entry(struct traverse_info *info,
 	if (pos < 0 || pos >= o->src_index->cache_nr)
 		return NULL;
 
+	strbuf_addstr(&full_path, info->traverse_path);
+	strbuf_add(&full_path, p->path, p->pathlen);
+	strbuf_addch(&full_path, '/');
+
 	/*
 	 * We might have multiple entries between 'pos' and
 	 * the actual sparse-directory entry, so start walking
@@ -1315,17 +1320,20 @@ static struct cache_entry *find_cache_entry(struct traverse_info *info,
 		/*
 		 * Have we walked too far?
 		 */
-		if (strncmp(ce->name, p->path, p->pathlen))
-			return NULL;
+		if (strncmp(ce->name, full_path.buf, full_path.len)) {
+			ce = NULL;
+			break;
+		}
 
 		if (S_ISSPARSEDIR(ce->ce_mode) &&
 		    sparse_dir_matches_path(ce, info, p))
-			return ce;
+			break;
 
 		pos--;
 	}
 
-	return NULL;
+	strbuf_release(&full_path);
+	return ce;
 }
 
 static void debug_path(struct traverse_info *info)