reset: preserve skip-worktree bit in mixed reset

Change `update_index_from_diff` to set `skip-worktree` when applicable for
new index entries. When `git reset --mixed <tree-ish>` is run, entries in
the index with differences between the pre-reset HEAD and reset <tree-ish>
are identified and handled with `update_index_from_diff`. For each file, a
new cache entry in inserted into the index, created from the <tree-ish> side
of the reset (without changing the working tree). However, the newly-created
entry must have `skip-worktree` explicitly set in either of the following
scenarios:

1. the file is in the current index and has `skip-worktree` set
2. the file is not in the current index but is outside of a defined sparse
   checkout definition

Not setting the `skip-worktree` bit leads to likely-undesirable results for
a user. It causes `skip-worktree` settings to disappear on the
"diff"-containing files (but *only* the diff-containing files), leading to
those files now showing modifications in `git status`. For example, when
running `git reset --mixed` in a sparse checkout, some file entries outside
of sparse checkout could show up as deleted, despite the user never deleting
anything (and not wanting them on-disk anyway).

Additionally, add a test to `t7102` to ensure `skip-worktree` is preserved
in a basic `git reset --mixed` scenario and update a failure-documenting
test from 19a0acc (t1092: test interesting sparse-checkout scenarios,
2021-01-23) with new expected behavior.

Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Victoria Dye <vdye@github.com>

builtin/reset.c

@@ -28,7 +28,6 @@
 #include "strbuf.h"
 #include "quote.h"
 #include "dir.h"
-#include "entry.h"
 
 #define REFRESH_INDEX_DELAY_WARNING_IN_MS (2 * 1000)
 
@@ -138,45 +137,13 @@ static void update_index_from_diff(struct diff_queue_struct *q,
 		struct diff_options *opt, void *data)
 {
 	int i;
-	int pos;
 	int intent_to_add = *(int *)data;
 
 	for (i = 0; i < q->nr; i++) {
+		int pos;
 		struct diff_filespec *one = q->queue[i]->one;
-		struct diff_filespec *two = q->queue[i]->two;
-		int was_missing = !two->mode && is_null_oid(&two->oid);
 		int is_in_reset_tree = one->mode && !is_null_oid(&one->oid);
 		struct cache_entry *ce;
-		struct cache_entry *ceBefore;
-		struct checkout state = CHECKOUT_INIT;
-
-		/*
-		 * When using the sparse-checkout feature the cache entries that are
-		 * added here will not have the skip-worktree bit set.
-		 * Without this code there is data that is lost because the files that
-		 * would normally be in the working directory are not there and show as
-		 * deleted for the next status or in the case of added files just disappear.
-		 * We need to create the previous version of the files in the working
-		 * directory so that they will have the right content and the next
-		 * status call will show modified or untracked files correctly.
-		 */
-		if (core_apply_sparse_checkout && !file_exists(two->path))
-		{
-			pos = cache_name_pos(two->path, strlen(two->path));
-			if ((pos >= 0 && ce_skip_worktree(active_cache[pos])) && (is_in_reset_tree || !was_missing))
-			{
-				state.force = 1;
-				state.refresh_cache = 1;
-				state.istate = &the_index;
-				ceBefore = make_cache_entry(&the_index, two->mode, &two->oid, two->path,
-					0, 0);
-				if (!ceBefore)
-					die(_("make_cache_entry failed for path '%s'"),
-						two->path);
-
-				checkout_entry(ceBefore, &state, NULL, NULL);
-			}
-		}
 
 		if (!is_in_reset_tree && !intent_to_add) {
 			remove_file_from_cache(one->path);
@@ -185,6 +152,20 @@ static void update_index_from_diff(struct diff_queue_struct *q,
 
 		ce = make_cache_entry(&the_index, one->mode, &one->oid, one->path,
 				      0, 0);
+
+		/*
+		 * If the file 1) corresponds to an existing index entry with
+		 * skip-worktree set, or 2) does not exist in the index but is
+		 * outside the sparse checkout definition, add a skip-worktree bit
+		 * to the new index entry. Note that a sparse index will be expanded
+		 * if this entry is outside the sparse cone - this is necessary
+		 * to properly construct the reset sparse directory.
+		 */
+		pos = cache_name_pos(one->path, strlen(one->path));
+		if ((pos >= 0 && ce_skip_worktree(active_cache[pos])) ||
+		    (pos < 0 && !path_in_sparse_checkout(one->path, &the_index)))
+			ce->ce_flags |= CE_SKIP_WORKTREE;
+
 		if (!ce)
 			die(_("make_cache_entry failed for path '%s'"),
 			    one->path);

t/t1092-sparse-checkout-compatibility.sh

@@ -528,25 +528,17 @@ test_expect_success 'blame with pathspec outside sparse definition' '
 	test_sparse_match test_must_fail git blame deep/deeper2/deepest/a
 '
 
-# TODO: This behaves correctly in microsoft/git. Why?
 test_expect_success 'checkout and reset (mixed)' '
 	init_repos &&
 
 	test_all_match git checkout -b reset-test update-deep &&
 	test_all_match git reset deepest &&
-	test_all_match git reset update-folder1 &&
-	test_all_match git reset update-folder2
-'
-
-# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
-# in this scenario, but it shouldn't.
-test_expect_success 'checkout and reset (mixed) [sparse]' '
-	init_repos &&
 
-	test_sparse_match git checkout -b reset-test update-deep &&
-	test_sparse_match git reset deepest &&
+	# Because skip-worktree is preserved, resetting to update-folder1
+	# will show worktree changes for full-checkout that are not present
+	# in sparse-checkout or sparse-index.
 	test_sparse_match git reset update-folder1 &&
-	test_sparse_match git reset update-folder2
+	run_on_sparse test_path_is_missing folder1
 '
 
 # NEEDSWORK: with mixed reset, files with differences between HEAD and <commit>

t/t7102-reset.sh

@@ -472,6 +472,23 @@ test_expect_success '--mixed refreshes the index' '
 	test_cmp expect output
 '
 
+test_expect_success '--mixed preserves skip-worktree' '
+	echo 123 >>file2 &&
+	git add file2 &&
+	git update-index --skip-worktree file2 &&
+	git reset --mixed HEAD >output &&
+	test_must_be_empty output &&
+
+	cat >expect <<-\EOF &&
+	Unstaged changes after reset:
+	M	file2
+	EOF
+	git update-index --no-skip-worktree file2 &&
+	git add file2 &&
+	git reset --mixed HEAD >output &&
+	test_cmp expect output
+'
+
 test_expect_success 'resetting specific path that is unmerged' '
 	git rm --cached file2 &&
 	F1=$(git rev-parse HEAD:file1) &&