Merge branch 'vd/sparse-reset-checkout-fixes' into maint

Fixes to sparse index compatibility work for "reset" and "checkout"
commands.
source: <pull.1312.v3.git.1659985672.gitgitgadget@gmail.com>

* vd/sparse-reset-checkout-fixes:
  unpack-trees: unpack new trees as sparse directories
  cache.h: create 'index_name_pos_sparse()'
  oneway_diff: handle removed sparse directories
  checkout: fix nested sparse directory diff in sparse index

6 files changed, 141 insertions, 10 deletions

diff --git a/builtin/checkout.c b/builtin/checkout.c
index df3f1663d7..cdd96cd9c6 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -626,6 +626,7 @@ static void show_local_changes(struct object *head,
 	repo_init_revisions(the_repository, &rev, NULL);
 	rev.diffopt.flags = opts->flags;
 	rev.diffopt.output_format |= DIFF_FORMAT_NAME_STATUS;
+	rev.diffopt.flags.recursive = 1;
 	diff_setup_done(&rev.diffopt);
 	add_pending_object(&rev, head, NULL);
 	run_diff_index(&rev, 0);
diff --git a/cache.h b/cache.h
index ac5ab4ef9d..33fc8337c6 100644
--- a/cache.h
+++ b/cache.h
@@ -831,6 +831,15 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na
 int index_name_pos(struct index_state *, const char *name, int namelen);
 
 /*
+ * Like index_name_pos, returns the position of an entry of the given name in
+ * the index if one exists, otherwise returns a negative value where the negated
+ * value minus 1 is the position where the index entry would be inserted. Unlike
+ * index_name_pos, however, a sparse index is not expanded to find an entry
+ * inside a sparse directory.
+ */
+int index_name_pos_sparse(struct index_state *, const char *name, int namelen);
+
+/*
  * Determines whether an entry with the given name exists within the
  * given index. The return value is 1 if an exact match is found, otherwise
  * it is 0. Note that, unlike index_name_pos, this function does not expand
diff --git a/diff-lib.c b/diff-lib.c
index 7eb66a417a..2edea41a23 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -466,6 +466,11 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	 * Something removed from the tree?
 	 */
 	if (!idx) {
+		if (S_ISSPARSEDIR(tree->ce_mode)) {
+			diff_tree_oid(&tree->oid, NULL, tree->name, &revs->diffopt);
+			return;
+		}
+
 		diff_index_show_file(revs, "-", tree, &tree->oid, 1,
 				     tree->ce_mode, 0);
 		return;
diff --git a/read-cache.c b/read-cache.c
index 4de207752d..b09128b188 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -620,6 +620,11 @@ int index_name_pos(struct index_state *istate, const char *name, int namelen)
 	return index_name_stage_pos(istate, name, namelen, 0, EXPAND_SPARSE);
 }
 
+int index_name_pos_sparse(struct index_state *istate, const char *name, int namelen)
+{
+	return index_name_stage_pos(istate, name, namelen, 0, NO_EXPAND_SPARSE);
+}
+
 int index_entry_exists(struct index_state *istate, const char *name, int namelen)
 {
 	return index_name_stage_pos(istate, name, namelen, 0, NO_EXPAND_SPARSE) >= 0;
diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh
index f9f8c988bb..5dced39889 100755
--- a/t/t1092-sparse-checkout-compatibility.sh
+++ b/t/t1092-sparse-checkout-compatibility.sh
@@ -372,6 +372,14 @@ test_expect_success 'deep changes during checkout' '
 	test_all_match git checkout base
 '
 
+test_expect_success 'checkout with modified sparse directory' '
+	init_repos &&
+
+	test_all_match git checkout rename-in-to-out -- . &&
+	test_sparse_match git sparse-checkout reapply &&
+	test_all_match git checkout base
+'
+
 test_expect_success 'add outside sparse cone' '
 	init_repos &&
 
@@ -687,6 +695,23 @@ test_expect_success 'reset with wildcard pathspec' '
 	test_all_match git ls-files -s -- folder1
 '
 
+test_expect_success 'reset hard with removed sparse dir' '
+	init_repos &&
+
+	run_on_all git rm -r --sparse folder1 &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git reset --hard &&
+	test_all_match git status --porcelain=v2 &&
+
+	cat >expect <<-\EOF &&
+	folder1/
+	EOF
+
+	git -C sparse-index ls-files --sparse folder1 >out &&
+	test_cmp expect out
+'
+
 test_expect_success 'update-index modify outside sparse definition' '
 	init_repos &&
 
diff --git a/unpack-trees.c b/unpack-trees.c
index 8a454e03bf..90b92114be 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1070,6 +1070,67 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 }
 
 /*
+ * Determine whether the path specified by 'p' should be unpacked as a new
+ * sparse directory in a sparse index. A new sparse directory 'A/':
+ * - must be outside the sparse cone.
+ * - must not already be in the index (i.e., no index entry with name 'A/'
+ *   exists).
+ * - must not have any child entries in the index (i.e., no index entry
+ *   'A/<something>' exists).
+ * If 'p' meets the above requirements, return 1; otherwise, return 0.
+ */
+static int entry_is_new_sparse_dir(const struct traverse_info *info,
+				   const struct name_entry *p)
+{
+	int res, pos;
+	struct strbuf dirpath = STRBUF_INIT;
+	struct unpack_trees_options *o = info->data;
+
+	if (!S_ISDIR(p->mode))
+		return 0;
+
+	/*
+	 * If the path is inside the sparse cone, it can't be a sparse directory.
+	 */
+	strbuf_add(&dirpath, info->traverse_path, info->pathlen);
+	strbuf_add(&dirpath, p->path, p->pathlen);
+	strbuf_addch(&dirpath, '/');
+	if (path_in_cone_mode_sparse_checkout(dirpath.buf, o->src_index)) {
+		res = 0;
+		goto cleanup;
+	}
+
+	pos = index_name_pos_sparse(o->src_index, dirpath.buf, dirpath.len);
+	if (pos >= 0) {
+		/* Path is already in the index, not a new sparse dir */
+		res = 0;
+		goto cleanup;
+	}
+
+	/* Where would this sparse dir be inserted into the index? */
+	pos = -pos - 1;
+	if (pos >= o->src_index->cache_nr) {
+		/*
+		 * Sparse dir would be inserted at the end of the index, so we
+		 * know it has no child entries.
+		 */
+		res = 1;
+		goto cleanup;
+	}
+
+	/*
+	 * If the dir has child entries in the index, the first would be at the
+	 * position the sparse directory would be inserted. If the entry at this
+	 * position is inside the dir, not a new sparse dir.
+	 */
+	res = strncmp(o->src_index->cache[pos]->name, dirpath.buf, dirpath.len);
+
+cleanup:
+	strbuf_release(&dirpath);
+	return res;
+}
+
+/*
  * Note that traverse_by_cache_tree() duplicates some logic in this function
  * without actually calling it. If you change the logic here you may need to
  * check and change there as well.
@@ -1078,21 +1139,44 @@ static int unpack_single_entry(int n, unsigned long mask,
 			       unsigned long dirmask,
 			       struct cache_entry **src,
 			       const struct name_entry *names,
-			       const struct traverse_info *info)
+			       const struct traverse_info *info,
+			       int *is_new_sparse_dir)
 {
 	int i;
 	struct unpack_trees_options *o = info->data;
 	unsigned long conflicts = info->df_conflicts | dirmask;
+	const struct name_entry *p = names;
 
-	if (mask == dirmask && !src[0])
-		return 0;
+	*is_new_sparse_dir = 0;
+	if (mask == dirmask && !src[0]) {
+		/*
+		 * If we're not in a sparse index, we can't unpack a directory
+		 * without recursing into it, so we return.
+		 */
+		if (!o->src_index->sparse_index)
+			return 0;
+
+		/* Find first entry with a real name (we could use "mask" too) */
+		while (!p->mode)
+			p++;
+
+		/*
+		 * If the directory is completely missing from the index but
+		 * would otherwise be a sparse directory, we should unpack it.
+		 * If not, we'll return and continue recursively traversing the
+		 * tree.
+		 */
+		*is_new_sparse_dir = entry_is_new_sparse_dir(info, p);
+		if (!*is_new_sparse_dir)
+			return 0;
+	}
 
 	/*
-	 * When we have a sparse directory entry for src[0],
-	 * then this isn't necessarily a directory-file conflict.
+	 * When we are unpacking a sparse directory, then this isn't necessarily
+	 * a directory-file conflict.
 	 */
-	if (mask == dirmask && src[0] &&
-	    S_ISSPARSEDIR(src[0]->ce_mode))
+	if (mask == dirmask &&
+	    (*is_new_sparse_dir || (src[0] && S_ISSPARSEDIR(src[0]->ce_mode))))
 		conflicts = 0;
 
 	/*
@@ -1352,7 +1436,7 @@ static int unpack_sparse_callback(int n, unsigned long mask, unsigned long dirma
 {
 	struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
 	struct unpack_trees_options *o = info->data;
-	int ret;
+	int ret, is_new_sparse_dir;
 
 	assert(o->merge);
 
@@ -1376,7 +1460,7 @@ static int unpack_sparse_callback(int n, unsigned long mask, unsigned long dirma
 	 * "index" tree (i.e., names[0]) and adjust 'names', 'n', 'mask', and
 	 * 'dirmask' accordingly.
 	 */
-	ret = unpack_single_entry(n - 1, mask >> 1, dirmask >> 1, src, names + 1, info);
+	ret = unpack_single_entry(n - 1, mask >> 1, dirmask >> 1, src, names + 1, info, &is_new_sparse_dir);
 
 	if (src[0])
 		discard_cache_entry(src[0]);
@@ -1394,6 +1478,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 	struct cache_entry *src[MAX_UNPACK_TREES + 1] = { NULL, };
 	struct unpack_trees_options *o = info->data;
 	const struct name_entry *p = names;
+	int is_new_sparse_dir;
 
 	/* Find first entry with a real name (we could use "mask" too) */
 	while (!p->mode)
@@ -1440,7 +1525,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 		}
 	}
 
-	if (unpack_single_entry(n, mask, dirmask, src, names, info) < 0)
+	if (unpack_single_entry(n, mask, dirmask, src, names, info, &is_new_sparse_dir))
 		return -1;
 
 	if (o->merge && src[0]) {
@@ -1478,6 +1563,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 		}
 
 		if (!is_sparse_directory_entry(src[0], names, info) &&
+		    !is_new_sparse_dir &&
 		    traverse_trees_recursive(n, dirmask, mask & ~dirmask,
 						    names, info) < 0) {
 			return -1;