Sparse Index: latest integrations

Documentation/config/index.txt

@@ -1,3 +1,9 @@
+index.deleteSparseDirectories::
+	When enabled, the cone mode sparse-checkout feature will delete
+	directories that are outside of the sparse-checkout cone, unless
+	such a directory contains an untracked, non-ignored file. Defaults
+	to true.
+
 index.recordEndOfIndexEntries::
 	Specifies whether the index file should include an "End Of Index
 	Entry" section. This reduces index load time on multiprocessor

Documentation/git-sparse-checkout.txt

@@ -210,6 +210,16 @@ case-insensitive check. This corrects for case mismatched filenames in the
 'git sparse-checkout set' command to reflect the expected cone in the working
 directory.
 
+When changing the sparse-checkout patterns in cone mode, Git will inspect each
+tracked directory that is not within the sparse-checkout cone to see if it
+contains any untracked files. If all of those files are ignored due to the
+`.gitignore` patterns, then the directory will be deleted. If any of the
+untracked files within that directory is not ignored, then no deletions will
+occur within that directory and a warning message will appear. If these files
+are important, then reset your sparse-checkout definition so they are included,
+use `git add` and `git commit` to store them, then remove any remaining files
+manually to ensure Git can behave optimally.
+
 
 SUBMODULES
 ----------

attr.c

@@ -14,6 +14,7 @@
 #include "utf8.h"
 #include "quote.h"
 #include "thread-utils.h"
+#include "dir.h"
 
 const char git_attr__true[] = "(builtin)true";
 const char git_attr__false[] = "\0(builtin)false";
@@ -744,6 +745,19 @@ static struct attr_stack *read_attr_from_index(struct index_state *istate,
 	if (!istate)
 		return NULL;
 
+	/*
+	 * The .gitattributes file only applies to files within its
+	 * parent directory. In the case of cone-mode sparse-checkout,
+	 * the .gitattributes file is sparse if and only if all paths
+	 * within that directory are also sparse. Thus, don't load the
+	 * .gitattributes file since it will not matter.
+	 *
+	 * In the case of a sparse index, it is critical that we don't go
+	 * looking for a .gitattributes file, as the index will expand.
+	 */
+	if (!path_in_cone_modesparse_checkout(path, istate))
+		return NULL;
+
 	buf = read_blob_data_from_index(istate, path, NULL);
 	if (!buf)
 		return NULL;

builtin/add.c

@@ -144,8 +144,6 @@ static int renormalize_tracked_files(const struct pathspec *pathspec, int flags)
 {
 	int i, retval = 0;
 
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(&the_index);
 	for (i = 0; i < active_nr; i++) {
 		struct cache_entry *ce = active_cache[i];
 
@@ -198,7 +196,10 @@ static int refresh(int verbose, const struct pathspec *pathspec)
 		      _("Unstaged changes after refreshing the index:"));
 	for (i = 0; i < pathspec->nr; i++) {
 		if (!seen[i]) {
-			if (matches_skip_worktree(pathspec, i, &skip_worktree_seen)) {
+			const char *path = pathspec->items[i].original;
+
+			if (matches_skip_worktree(pathspec, i, &skip_worktree_seen) ||
+			    !path_in_sparse_checkout(path, &the_index)) {
 				string_list_append(&only_match_skip_worktree,
 						   pathspec->items[i].original);
 			} else {
@@ -532,6 +533,9 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 	add_new_files = !take_worktree_changes && !refresh_only && !add_renormalize;
 	require_pathspec = !(take_worktree_changes || (0 < addremove_explicit));
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
 
 	/*

builtin/merge.c

@@ -1276,6 +1276,9 @@ int cmd_merge(int argc, const char **argv, const char *prefix)
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage_with_options(builtin_merge_usage, builtin_merge_options);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	/*
 	 * Check if we are _not_ on a detached HEAD, i.e. if there is a
 	 * current branch.

builtin/rebase.c

@@ -559,6 +559,9 @@ int cmd_rebase__interactive(int argc, const char **argv, const char *prefix)
 	argc = parse_options(argc, argv, prefix, options,
 			builtin_rebase_interactive_usage, PARSE_OPT_KEEP_ARGV0);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	if (!is_null_oid(&squash_onto))
 		opts.squash_onto = &squash_onto;
 
@@ -1430,6 +1433,9 @@ int cmd_rebase(int argc, const char **argv, const char *prefix)
 		usage_with_options(builtin_rebase_usage,
 				   builtin_rebase_options);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	options.allow_empty_message = 1;
 	git_config(rebase_config, &options);
 	/* options.gpg_sign_opt will be either "-S" or NULL */

builtin/revert.c

@@ -136,6 +136,9 @@ static int run_sequencer(int argc, const char **argv, struct replay_opts *opts)
 			PARSE_OPT_KEEP_ARGV0 |
 			PARSE_OPT_KEEP_UNKNOWN);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	/* implies allow_empty */
 	if (opts->keep_redundant_commits)
 		opts->allow_empty = 1;

builtin/sparse-checkout.c

@@ -100,6 +100,106 @@ static int sparse_checkout_list(int argc, const char **argv)
 	return 0;
 }
 
+static void clean_tracked_sparse_directories(struct repository *r)
+{
+	int i, value, was_full = 0;
+	struct strbuf path = STRBUF_INIT;
+	size_t pathlen;
+	struct string_list_item *item;
+	struct string_list sparse_dirs = STRING_LIST_INIT_DUP;
+
+	/*
+	 * If we are not using cone mode patterns, then we cannot
+	 * delete directories outside of the sparse cone.
+	 */
+	if (!r || !r->index || !r->worktree)
+		return;
+	init_sparse_checkout_patterns(r->index);
+	if (!r->index->sparse_checkout_patterns ||
+	    !r->index->sparse_checkout_patterns->use_cone_patterns)
+		return;
+
+	/*
+	 * Users can disable this behavior.
+	 */
+	if (!repo_config_get_bool(r, "index.deletesparsedirectories", &value) &&
+	    !value)
+		return;
+
+	/*
+	 * Use the sparse index as a data structure to assist finding
+	 * directories that are safe to delete. This conversion to a
+	 * sparse index will not delete directories that contain
+	 * conflicted entries or submodules.
+	 */
+	if (!r->index->sparse_index) {
+		/*
+		 * If something, such as a merge conflict or other concern,
+		 * prevents us from converting to a sparse index, then do
+		 * not try deleting files.
+		 */
+		if (convert_to_sparse(r->index, SPARSE_INDEX_MEMORY_ONLY))
+			return;
+		was_full = 1;
+	}
+
+	strbuf_addstr(&path, r->worktree);
+	strbuf_complete(&path, '/');
+	pathlen = path.len;
+
+	/*
+	 * Collect directories that have gone out of scope but also
+	 * exist on disk, so there is some work to be done. We need to
+	 * store the entries in a list before exploring, since that might
+	 * expand the sparse-index again.
+	 */
+	for (i = 0; i < r->index->cache_nr; i++) {
+		struct cache_entry *ce = r->index->cache[i];
+
+		if (S_ISSPARSEDIR(ce->ce_mode) &&
+		    repo_file_exists(r, ce->name))
+			string_list_append(&sparse_dirs, ce->name);
+	}
+
+	for_each_string_list_item(item, &sparse_dirs) {
+		struct dir_struct dir = DIR_INIT;
+		struct pathspec p = { 0 };
+		struct strvec s = STRVEC_INIT;
+
+		strbuf_setlen(&path, pathlen);
+		strbuf_addstr(&path, item->string);
+
+		dir.flags |= DIR_SHOW_IGNORED_TOO;
+
+		setup_standard_excludes(&dir);
+		strvec_push(&s, path.buf);
+
+		parse_pathspec(&p, PATHSPEC_GLOB, 0, NULL, s.v);
+		fill_directory(&dir, r->index, &p);
+
+		if (dir.nr) {
+			warning(_("directory '%s' contains untracked files,"
+				  " but is not in the sparse-checkout cone"),
+				item->string);
+		} else if (remove_dir_recursively(&path, 0)) {
+			/*
+			 * Removal is "best effort". If something blocks
+			 * the deletion, then continue with a warning.
+			 */
+			warning(_("failed to remove directory '%s'"),
+				item->string);
+		}
+
+		dir_clear(&dir);
+	}
+
+	string_list_clear(&sparse_dirs, 0);
+	strbuf_release(&path);
+
+	if (was_full)
+		ensure_full_index(r->index);
+}
+
 static int update_working_directory(struct pattern_list *pl)
 {
 	enum update_sparsity_result result;
@@ -141,6 +241,8 @@ 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;
 }

diff.c

@@ -26,6 +26,7 @@
 #include "parse-options.h"
 #include "help.h"
 #include "promisor-remote.h"
+#include "dir.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -3900,6 +3901,13 @@ static int reuse_worktree_file(struct index_state *istate,
 	if (!FAST_WORKING_DIRECTORY && !want_file && has_object_pack(oid))
 		return 0;
 
+	/*
+	 * If this path does not match our sparse-checkout definition,
+	 * then the file will not be in the working directory.
+	 */
+	if (!path_in_sparse_checkout(name, istate))
+		return 0;
+
 	/*
 	 * Similarly, if we'd have to convert the file contents anyway, that
 	 * makes the optimization not worthwhile.

dir.c

@@ -1494,6 +1494,60 @@ enum pattern_match_result path_matches_pattern_list(
 	return result;
 }
 
+int init_sparse_checkout_patterns(struct index_state *istate)
+{
+	if (!core_apply_sparse_checkout ||
+	    istate->sparse_checkout_patterns)
+		return 0;
+
+	CALLOC_ARRAY(istate->sparse_checkout_patterns, 1);
+
+	if (get_sparse_checkout_patterns(istate->sparse_checkout_patterns) < 0) {
+		FREE_AND_NULL(istate->sparse_checkout_patterns);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int path_in_sparse_checkout_1(const char *path,
+				     struct index_state *istate,
+				     int require_cone_mode)
+{
+	const char *base;
+	int dtype = DT_REG;
+	init_sparse_checkout_patterns(istate);
+
+	/*
+	 * We default to accepting a path if there are no patterns or
+	 * they are of the wrong type.
+	 */
+	if (!istate->sparse_checkout_patterns ||
+	    (require_cone_mode &&
+	     !istate->sparse_checkout_patterns->use_cone_patterns))
+		return 1;
+
+
+
+	base = strrchr(path, '/');
+	return path_matches_pattern_list(path, strlen(path), base ? base + 1 : path,
+					 &dtype,
+					 istate->sparse_checkout_patterns,
+					 istate) > 0;
+}
+
+int path_in_sparse_checkout(const char *path,
+			    struct index_state *istate)
+{
+	return path_in_sparse_checkout_1(path, istate, 0);
+}
+
+int path_in_cone_modesparse_checkout(const char *path,
+				     struct index_state *istate)
+{
+	return path_in_sparse_checkout_1(path, istate, 1);
+}
+
 static struct path_pattern *last_matching_pattern_from_lists(
 		struct dir_struct *dir, struct index_state *istate,
 		const char *pathname, int pathlen,

dir.h

@@ -394,6 +394,14 @@ enum pattern_match_result path_matches_pattern_list(const char *pathname,
 				const char *basename, int *dtype,
 				struct pattern_list *pl,
 				struct index_state *istate);
+
+int init_sparse_checkout_patterns(struct index_state *state);
+
+int path_in_sparse_checkout(const char *path,
+			    struct index_state *istate);
+int path_in_cone_modesparse_checkout(const char *path,
+				     struct index_state *istate);
+
 struct dir_entry *dir_add_ignored(struct dir_struct *dir,
 				  struct index_state *istate,
 				  const char *pathname, int len);

merge-ort.c

@@ -4058,6 +4058,21 @@ static int record_conflicted_index_entries(struct merge_options *opt)
 	if (strmap_empty(&opt->priv->conflicted))
 		return 0;
 
+	/*
+	 * We are in a conflicted state. These conflicts might be inside
+	 * sparse-directory entries, so check if any entries are outside
+	 * of the sparse-checkout cone preemptively.
+	 *
+	 * We set original_cache_nr below, but that might change if
+	 * index_name_pos() calls ask for paths within sparse directories.
+	 */
+	strmap_for_each_entry(&opt->priv->conflicted, &iter, e) {
+		if (!path_in_sparse_checkout(e->key, index)) {
+			ensure_full_index(index);
+			break;
+		}
+	}
+
 	/* If any entries have skip_worktree set, we'll have to check 'em out */
 	state.force = 1;
 	state.quiet = 1;

merge-recursive.c

@@ -3750,6 +3750,9 @@ int merge_recursive(struct merge_options *opt,
 	assert(opt->ancestor == NULL ||
 	       !strcmp(opt->ancestor, "constructed merge base"));
 
+	prepare_repo_settings(opt->repo);
+	opt->repo->settings.command_requires_full_index = 1;
+
 	if (merge_start(opt, repo_get_commit_tree(opt->repo, h1)))
 		return -1;
 	clean = merge_recursive_internal(opt, h1, h2, merge_bases, result);

pathspec.c

@@ -37,8 +37,6 @@ void add_pathspec_matches_against_index(const struct pathspec *pathspec,
 			num_unmatched++;
 	if (!num_unmatched)
 		return;
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(istate);
 	for (i = 0; i < istate->cache_nr; i++) {
 		const struct cache_entry *ce = istate->cache[i];
 		if (sw_action == PS_IGNORE_SKIP_WORKTREE && ce_skip_worktree(ce))

read-cache.c

@@ -3111,7 +3111,7 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l
 	int ret;
 	int was_full = !istate->sparse_index;
 
-	ret = convert_to_sparse(istate);
+	ret = convert_to_sparse(istate, 0);
 
 	if (ret) {
 		warning(_("failed to convert to a sparse-index"));
@@ -3224,7 +3224,7 @@ static int write_shared_index(struct index_state *istate,
 	int ret, was_full = !istate->sparse_index;
 
 	move_cache_to_base_index(istate);
-	convert_to_sparse(istate);
+	convert_to_sparse(istate, 0);
 
 	trace2_region_enter_printf("index", "shared/do_write_index",
 				   the_repository, "%s", get_tempfile_path(*temp));