Merge pull request microsoft#417 from vdye/sparse-index/git-reset

Sparse index: `git reset`

builtin/reset.c

@@ -195,14 +195,43 @@ static int read_from_tree(const struct pathspec *pathspec,
 			  int intent_to_add)
 {
 	struct diff_options opt;
+	unsigned int i;
+	char *skip_worktree_seen = NULL;
 
 	memset(&opt, 0, sizeof(opt));
 	copy_pathspec(&opt.pathspec, pathspec);
 	opt.output_format = DIFF_FORMAT_CALLBACK;
 	opt.format_callback = update_index_from_diff;
 	opt.format_callback_data = &intent_to_add;
 	opt.flags.override_submodule_config = 1;
+	opt.flags.recursive = 1;
 	opt.repo = the_repository;
+	opt.change = diff_change;
+	opt.add_remove = diff_addremove;
+
+	/*
+	 * When pathspec is given for resetting a cone-mode sparse checkout, it may
+	 * identify entries that are nested in sparse directories, in which case the
+	 * index should be expanded. For the sake of efficiency, this check is
+	 * overly-cautious: anything with a wildcard or a magic prefix requires
+	 * expansion, as well as literal paths that aren't in the sparse checkout
+	 * definition AND don't match any directory in the index.
+	 */
+	if (pathspec->nr && the_index.sparse_index) {
+		if (pathspec->magic || pathspec->has_wildcard) {
+			ensure_full_index(&the_index);
+		} else {
+			for (i = 0; i < pathspec->nr; i++) {
+				if (!path_in_cone_modesparse_checkout(pathspec->items[i].original, &the_index) &&
+					!matches_skip_worktree(pathspec, i, &skip_worktree_seen)) {
+					ensure_full_index(&the_index);
+					break;
+				}
+			}
+		}
+	}
+
+	free(skip_worktree_seen);
 
 	if (do_diff_cache(tree_oid, &opt))
 		return 1;
@@ -281,9 +310,6 @@ static void parse_args(struct pathspec *pathspec,
 	}
 	*rev_ret = rev;
 
-	if (read_cache() < 0)
-		die(_("index file corrupt"));
-
 	parse_pathspec(pathspec, 0,
 		       PATHSPEC_PREFER_FULL |
 		       (patch_mode ? PATHSPEC_PREFIX_ORIGIN : 0),
@@ -440,6 +466,12 @@ int cmd_reset(int argc, const char **argv, const char *prefix)
 	if (intent_to_add && reset_type != MIXED)
 		die(_("-N can only be used with --mixed"));
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
+	if (read_cache() < 0)
+		die(_("index file corrupt"));
+
 	/* Soft reset does not touch the index file nor the working tree
 	 * at all, but requires them in a good order.  Other resets reset
 	 * the index file to the tree object we are switching to. */

cache-tree.c

@@ -802,13 +802,31 @@ int write_index_as_tree(struct object_id *oid, struct index_state *index_state,
 
 static void prime_cache_tree_rec(struct repository *r,
 				 struct cache_tree *it,
-				 struct tree *tree)
+				 struct tree *tree,
+				 struct strbuf *tree_path)
 {
+	struct strbuf subtree_path = STRBUF_INIT;
 	struct tree_desc desc;
 	struct name_entry entry;
 	int cnt;
 
 	oidcpy(&it->oid, &tree->object.oid);
+
+	/*
+	 * If this entry is outside the sparse-checkout cone, then it might be
+	 * a sparse directory entry. Check the index to ensure it is by looking
+	 * for an entry with the exact same name as the tree. If no matching sparse
+	 * entry is found, a staged or conflicted entry is preventing this
+	 * directory from collapsing to a sparse directory entry, so the cache
+	 * tree expansion should continue.
+	 */
+	if (r->index->sparse_index &&
+	    !path_in_cone_modesparse_checkout(tree_path->buf, r->index) &&
+	    index_name_pos(r->index, tree_path->buf, tree_path->len) >= 0) {
+		it->entry_count = 1;
+		return;
+	}
+
 	init_tree_desc(&desc, tree->buffer, tree->size);
 	cnt = 0;
 	while (tree_entry(&desc, &entry)) {
@@ -817,26 +835,38 @@ static void prime_cache_tree_rec(struct repository *r,
 		else {
 			struct cache_tree_sub *sub;
 			struct tree *subtree = lookup_tree(r, &entry.oid);
+
 			if (!subtree->object.parsed)
 				parse_tree(subtree);
 			sub = cache_tree_sub(it, entry.path);
 			sub->cache_tree = cache_tree();
-			prime_cache_tree_rec(r, sub->cache_tree, subtree);
+			strbuf_reset(&subtree_path);
+			strbuf_grow(&subtree_path, tree_path->len + entry.pathlen + 1);
+			strbuf_addbuf(&subtree_path, tree_path);
+			strbuf_add(&subtree_path, entry.path, entry.pathlen);
+			strbuf_addch(&subtree_path, '/');
+
+			prime_cache_tree_rec(r, sub->cache_tree, subtree, &subtree_path);
 			cnt += sub->cache_tree->entry_count;
 		}
 	}
 	it->entry_count = cnt;
+
+	strbuf_release(&subtree_path);
 }
 
 void prime_cache_tree(struct repository *r,
 		      struct index_state *istate,
 		      struct tree *tree)
 {
+	struct strbuf tree_path = STRBUF_INIT;
+
 	trace2_region_enter("cache-tree", "prime_cache_tree", r);
 	cache_tree_free(&istate->cache_tree);
 	istate->cache_tree = cache_tree();
 
-	prime_cache_tree_rec(r, istate->cache_tree, tree);
+	prime_cache_tree_rec(r, istate->cache_tree, tree, &tree_path);
+	strbuf_release(&tree_path);
 	istate->cache_changed |= CACHE_TREE_CHANGED;
 	trace2_region_leave("cache-tree", "prime_cache_tree", r);
 }

t/t1092-sparse-checkout-compatibility.sh

@@ -481,6 +481,113 @@ test_expect_success 'checkout and reset (mixed) [sparse]' '
 	test_sparse_match git reset update-folder2
 '
 
+# NEEDSWORK: with mixed reset, files with differences between HEAD and <commit>
+# will be added to the work tree even if outside the sparse checkout
+# definition, and even if the file is modified to a state of having no local
+# changes. The file is "re-ignored" if a hard reset is executed. We may want to
+# change this behavior in the future and enforce that files are not written
+# outside of the sparse checkout definition.
+test_expect_success 'checkout and mixed reset file tracking [sparse]' '
+	init_repos &&
+
+	test_all_match git checkout -b reset-test update-deep &&
+	test_all_match git reset update-folder1 &&
+	test_all_match git reset update-deep &&
+
+	# At this point, there are no changes in the working tree. However,
+	# folder1/a now exists locally (even though it is outside of the sparse
+	# paths).
+	run_on_sparse test_path_exists folder1 &&
+
+	run_on_all rm folder1/a &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset --hard update-deep &&
+	run_on_sparse test_path_is_missing folder1 &&
+	test_path_exists full-checkout/folder1
+'
+
+test_expect_success 'checkout and reset (merge)' '
+	init_repos &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+
+	test_all_match git checkout -b reset-test update-deep &&
+	run_on_all ../edit-contents a &&
+	test_all_match git reset --merge deepest &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset --hard update-deep &&
+	run_on_all ../edit-contents deep/a &&
+	test_all_match test_must_fail git reset --merge deepest
+'
+
+test_expect_success 'checkout and reset (keep)' '
+	init_repos &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+
+	test_all_match git checkout -b reset-test update-deep &&
+	run_on_all ../edit-contents a &&
+	test_all_match git reset --keep deepest &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset --hard update-deep &&
+	run_on_all ../edit-contents deep/a &&
+	test_all_match test_must_fail git reset --keep deepest
+'
+
+test_expect_success 'reset with pathspecs inside sparse definition' '
+	init_repos &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+
+	test_all_match git checkout -b reset-test update-deep &&
+	run_on_all ../edit-contents deep/a &&
+
+	test_all_match git reset base -- deep/a &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset base -- nonexistent-file &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset deepest -- deep &&
+	test_all_match git status --porcelain=v2
+'
+
+test_expect_success 'reset with sparse directory pathspec outside definition' '
+	init_repos &&
+
+	test_all_match git checkout -b reset-test update-deep &&
+	test_all_match git reset --hard update-folder1 &&
+	test_all_match git reset base -- folder1 &&
+	test_all_match git status --porcelain=v2
+'
+
+test_expect_success 'reset with pathspec match in sparse directory' '
+	init_repos &&
+
+	test_all_match git checkout -b reset-test update-deep &&
+	test_all_match git reset --hard update-folder1 &&
+	test_all_match git reset base -- folder1/a &&
+	test_all_match git status --porcelain=v2
+'
+
+test_expect_success 'reset with wildcard pathspec' '
+	init_repos &&
+
+	test_all_match git checkout -b reset-test update-deep &&
+	test_all_match git reset --hard update-folder1 &&
+	test_all_match git reset base -- */a &&
+	test_all_match git status --porcelain=v2
+'
+
 test_expect_success 'merge, cherry-pick, and rebase' '
 	init_repos &&
 
@@ -644,7 +751,7 @@ test_expect_success 'sparse-index is expanded and converted back' '
 	init_repos &&
 
 	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
-		git -C sparse-index -c core.fsmonitor="" reset --hard &&
+		git -C sparse-index -c core.fsmonitor="" read-tree -mu HEAD &&
 	test_region index convert_to_sparse trace2.txt &&
 	test_region index ensure_full_index trace2.txt
 '
@@ -681,9 +788,9 @@ test_expect_success 'sparse-index is not expanded' '
 	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 reset --hard &&
 	ensure_not_expanded checkout rename-out-to-out -- deep/deeper1 &&
-	git -C sparse-index reset --hard &&
+	ensure_not_expanded reset --hard &&
 	ensure_not_expanded restore -s rename-out-to-out -- deep/deeper1 &&
 
 	echo >>sparse-index/README.md &&
@@ -693,6 +800,28 @@ test_expect_success 'sparse-index is not expanded' '
 	echo >>sparse-index/untracked.txt &&
 	ensure_not_expanded add . &&
 
+	for ref in update-deep update-folder1 update-folder2 update-deep
+	do
+		echo >>sparse-index/README.md &&
+		ensure_not_expanded reset --mixed $ref
+		ensure_not_expanded reset --hard $ref
+	done &&
+
+	ensure_not_expanded reset --hard update-deep &&
+	ensure_not_expanded reset --keep base &&
+	ensure_not_expanded reset --merge update-deep &&
+
+	ensure_not_expanded reset base -- deep/a &&
+	ensure_not_expanded reset base -- nonexistent-file &&
+	ensure_not_expanded reset deepest -- deep &&
+
+	# Although folder1 is outside the sparse definition, it exists as a
+	# directory entry in the index, so it will be reset without needing to
+	# expand the full index.
+	ensure_not_expanded reset --hard update-folder1 &&
+	ensure_not_expanded reset base -- folder1 &&
+
+	ensure_not_expanded reset --hard update-deep &&
 	ensure_not_expanded checkout -f update-deep &&
 	(
 		sane_unset GIT_TEST_MERGE_ALGORITHM &&