Merge branch 'sy/sparse-rm'

"git rm" has become more aware of the sparse-index feature.

* sy/sparse-rm:
  rm: integrate with sparse-index
  rm: expand the index only when necessary
  pathspec.h: move pathspec_needs_expanded_index() from reset.c to here
  t1092: add tests for `git-rm`

builtin/reset.c

@@ -174,88 +174,6 @@ static void update_index_from_diff(struct diff_queue_struct *q,
 	}
 }
 
-static int pathspec_needs_expanded_index(const struct pathspec *pathspec)
-{
-	unsigned int i, pos;
-	int res = 0;
-	char *skip_worktree_seen = NULL;
-
-	/*
-	 * When using a magic pathspec, assume for the sake of simplicity that
-	 * the index needs to be expanded to match all matchable files.
-	 */
-	if (pathspec->magic)
-		return 1;
-
-	for (i = 0; i < pathspec->nr; i++) {
-		struct pathspec_item item = pathspec->items[i];
-
-		/*
-		 * If the pathspec item has a wildcard, the index should be expanded
-		 * if the pathspec has the possibility of matching a subset of entries inside
-		 * of a sparse directory (but not the entire directory).
-		 *
-		 * If the pathspec item is a literal path, the index only needs to be expanded
-		 * if a) the pathspec isn't in the sparse checkout cone (to make sure we don't
-		 * expand for in-cone files) and b) it doesn't match any sparse directories
-		 * (since we can reset whole sparse directories without expanding them).
-		 */
-		if (item.nowildcard_len < item.len) {
-			/*
-			 * Special case: if the pattern is a path inside the cone
-			 * followed by only wildcards, the pattern cannot match
-			 * partial sparse directories, so we know we don't need to
-			 * expand the index.
-			 *
-			 * Examples:
-			 * - in-cone/foo***: doesn't need expanded index
-			 * - not-in-cone/bar*: may need expanded index
-			 * - **.c: may need expanded index
-			 */
-			if (strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len &&
-			    path_in_cone_mode_sparse_checkout(item.original, &the_index))
-				continue;
-
-			for (pos = 0; pos < active_nr; pos++) {
-				struct cache_entry *ce = active_cache[pos];
-
-				if (!S_ISSPARSEDIR(ce->ce_mode))
-					continue;
-
-				/*
-				 * If the pre-wildcard length is longer than the sparse
-				 * directory name and the sparse directory is the first
-				 * component of the pathspec, need to expand the index.
-				 */
-				if (item.nowildcard_len > ce_namelen(ce) &&
-				    !strncmp(item.original, ce->name, ce_namelen(ce))) {
-					res = 1;
-					break;
-				}
-
-				/*
-				 * If the pre-wildcard length is shorter than the sparse
-				 * directory and the pathspec does not match the whole
-				 * directory, need to expand the index.
-				 */
-				if (!strncmp(item.original, ce->name, item.nowildcard_len) &&
-				    wildmatch(item.original, ce->name, 0)) {
-					res = 1;
-					break;
-				}
-			}
-		} else if (!path_in_cone_mode_sparse_checkout(item.original, &the_index) &&
-			   !matches_skip_worktree(pathspec, i, &skip_worktree_seen))
-			res = 1;
-
-		if (res > 0)
-			break;
-	}
-
-	free(skip_worktree_seen);
-	return res;
-}
-
 static int read_from_tree(const struct pathspec *pathspec,
 			  struct object_id *tree_oid,
 			  int intent_to_add)
@@ -273,7 +191,7 @@ static int read_from_tree(const struct pathspec *pathspec,
 	opt.change = diff_change;
 	opt.add_remove = diff_addremove;
 
-	if (pathspec->nr && the_index.sparse_index && pathspec_needs_expanded_index(pathspec))
+	if (pathspec->nr && pathspec_needs_expanded_index(&the_index, pathspec))
 		ensure_full_index(&the_index);
 
 	if (do_diff_cache(tree_oid, &opt))

builtin/rm.c

@@ -287,6 +287,8 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 	if (!index_only)
 		setup_work_tree();
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
 	hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
 
 	if (read_cache() < 0)
@@ -296,8 +298,9 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 
 	seen = xcalloc(pathspec.nr, 1);
 
-	/* TODO: audit for interaction with sparse-index. */
+	if (pathspec_needs_expanded_index(&the_index, &pathspec))
 		ensure_full_index(&the_index);
+
 	for (i = 0; i < active_nr; i++) {
 		const struct cache_entry *ce = active_cache[i];
 

pathspec.c

@@ -759,3 +759,92 @@ int match_pathspec_attrs(struct index_state *istate,
 
 	return 1;
 }
+
+int pathspec_needs_expanded_index(struct index_state *istate,
+				  const struct pathspec *pathspec)
+{
+	unsigned int i, pos;
+	int res = 0;
+	char *skip_worktree_seen = NULL;
+
+	/*
+	 * If index is not sparse, no index expansion is needed.
+	 */
+	if (!istate->sparse_index)
+		return 0;
+
+	/*
+	 * When using a magic pathspec, assume for the sake of simplicity that
+	 * the index needs to be expanded to match all matchable files.
+	 */
+	if (pathspec->magic)
+		return 1;
+
+	for (i = 0; i < pathspec->nr; i++) {
+		struct pathspec_item item = pathspec->items[i];
+
+		/*
+		 * If the pathspec item has a wildcard, the index should be expanded
+		 * if the pathspec has the possibility of matching a subset of entries inside
+		 * of a sparse directory (but not the entire directory).
+		 *
+		 * If the pathspec item is a literal path, the index only needs to be expanded
+		 * if a) the pathspec isn't in the sparse checkout cone (to make sure we don't
+		 * expand for in-cone files) and b) it doesn't match any sparse directories
+		 * (since we can reset whole sparse directories without expanding them).
+		 */
+		if (item.nowildcard_len < item.len) {
+			/*
+			 * Special case: if the pattern is a path inside the cone
+			 * followed by only wildcards, the pattern cannot match
+			 * partial sparse directories, so we know we don't need to
+			 * expand the index.
+			 *
+			 * Examples:
+			 * - in-cone/foo***: doesn't need expanded index
+			 * - not-in-cone/bar*: may need expanded index
+			 * - **.c: may need expanded index
+			 */
+			if (strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len &&
+			    path_in_cone_mode_sparse_checkout(item.original, istate))
+				continue;
+
+			for (pos = 0; pos < istate->cache_nr; pos++) {
+				struct cache_entry *ce = istate->cache[pos];
+
+				if (!S_ISSPARSEDIR(ce->ce_mode))
+					continue;
+
+				/*
+				 * If the pre-wildcard length is longer than the sparse
+				 * directory name and the sparse directory is the first
+				 * component of the pathspec, need to expand the index.
+				 */
+				if (item.nowildcard_len > ce_namelen(ce) &&
+				    !strncmp(item.original, ce->name, ce_namelen(ce))) {
+					res = 1;
+					break;
+				}
+
+				/*
+				 * If the pre-wildcard length is shorter than the sparse
+				 * directory and the pathspec does not match the whole
+				 * directory, need to expand the index.
+				 */
+				if (!strncmp(item.original, ce->name, item.nowildcard_len) &&
+				    wildmatch(item.original, ce->name, 0)) {
+					res = 1;
+					break;
+				}
+			}
+		} else if (!path_in_cone_mode_sparse_checkout(item.original, istate) &&
+			   !matches_skip_worktree(pathspec, i, &skip_worktree_seen))
+			res = 1;
+
+		if (res > 0)
+			break;
+	}
+
+	free(skip_worktree_seen);
+	return res;
+}

pathspec.h

@@ -171,4 +171,16 @@ int match_pathspec_attrs(struct index_state *istate,
 			 const char *name, int namelen,
 			 const struct pathspec_item *item);
 
+/*
+ * Determine whether a pathspec will match only entire index entries (non-sparse
+ * files and/or entire sparse directories). If the pathspec has the potential to
+ * match partial contents of a sparse directory, return 1 to indicate the index
+ * should be expanded to match the  appropriate index entries.
+ *
+ * For the sake of simplicity, always return 1 if using a more complex "magic"
+ * pathspec.
+ */
+int pathspec_needs_expanded_index(struct index_state *istate,
+				  const struct pathspec *pathspec);
+
 #endif /* PATHSPEC_H */

t/perf/p2000-sparse-operations.sh

@@ -123,5 +123,6 @@ test_perf_on_all git blame $SPARSE_CONE/f3/a
 test_perf_on_all git read-tree -mu HEAD
 test_perf_on_all git checkout-index -f --all
 test_perf_on_all git update-index --add --remove $SPARSE_CONE/a
+test_perf_on_all "git rm -f $SPARSE_CONE/a && git checkout HEAD -- $SPARSE_CONE/a"
 
 test_done

t/t1092-sparse-checkout-compatibility.sh

@@ -937,7 +937,7 @@ test_expect_success 'read-tree --prefix' '
 	test_all_match git read-tree --prefix=deep/deeper1/deepest -u deepest &&
 	test_all_match git status --porcelain=v2 &&
 
-	test_all_match git rm -rf --sparse folder1/ &&
+	run_on_all git rm -rf --sparse folder1/ &&
 	test_all_match git read-tree --prefix=folder1/ -u update-folder1 &&
 	test_all_match git status --porcelain=v2 &&
 
@@ -1365,10 +1365,14 @@ ensure_not_expanded () {
 		shift &&
 		test_must_fail env \
 			GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \
-			git -C sparse-index "$@" || return 1
+			git -C sparse-index "$@" \
+			>sparse-index-out \
+			2>sparse-index-error || return 1
 	else
 		GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \
-			git -C sparse-index "$@" || return 1
+			git -C sparse-index "$@" \
+			>sparse-index-out \
+			2>sparse-index-error || return 1
 	fi &&
 	test_region ! index ensure_full_index trace2.txt
 }
@@ -1878,4 +1882,94 @@ test_expect_success 'mv directory from out-of-cone to in-cone' '
 	grep -e "H deep/0/1" actual
 '
 
+test_expect_success 'rm pathspec inside sparse definition' '
+	init_repos &&
+
+	test_all_match git rm deep/a &&
+	test_all_match git status --porcelain=v2 &&
+
+	# test wildcard
+	run_on_all git reset --hard &&
+	test_all_match git rm deep/* &&
+	test_all_match git status --porcelain=v2 &&
+
+	# test recursive rm
+	run_on_all git reset --hard &&
+	test_all_match git rm -r deep &&
+	test_all_match git status --porcelain=v2
+'
+
+test_expect_success 'rm pathspec outside sparse definition' '
+	init_repos &&
+
+	for file in folder1/a folder1/0/1
+	do
+		test_sparse_match test_must_fail git rm $file &&
+		test_sparse_match test_must_fail git rm --cached $file &&
+		test_sparse_match git rm --sparse $file &&
+		test_sparse_match git status --porcelain=v2
+	done &&
+
+	cat >folder1-full <<-EOF &&
+	rm ${SQ}folder1/0/0/0${SQ}
+	rm ${SQ}folder1/0/1${SQ}
+	rm ${SQ}folder1/a${SQ}
+	EOF
+
+	cat >folder1-sparse <<-EOF &&
+	rm ${SQ}folder1/${SQ}
+	EOF
+
+	# test wildcard
+	run_on_sparse git reset --hard &&
+	run_on_sparse git sparse-checkout reapply &&
+	test_sparse_match test_must_fail git rm folder1/* &&
+	run_on_sparse git rm --sparse folder1/* &&
+	test_cmp folder1-full sparse-checkout-out &&
+	test_cmp folder1-sparse sparse-index-out &&
+	test_sparse_match git status --porcelain=v2 &&
+
+	# test recursive rm
+	run_on_sparse git reset --hard &&
+	run_on_sparse git sparse-checkout reapply &&
+	test_sparse_match test_must_fail git rm --sparse folder1 &&
+	run_on_sparse git rm --sparse -r folder1 &&
+	test_cmp folder1-full sparse-checkout-out &&
+	test_cmp folder1-sparse sparse-index-out &&
+	test_sparse_match git status --porcelain=v2
+'
+
+test_expect_success 'rm pathspec expands index when necessary' '
+	init_repos &&
+
+	# in-cone pathspec (do not expand)
+	ensure_not_expanded rm "deep/deep*" &&
+	test_must_be_empty sparse-index-err &&
+
+	# out-of-cone pathspec (expand)
+	! ensure_not_expanded rm --sparse "folder1/a*" &&
+	test_must_be_empty sparse-index-err &&
+
+	# pathspec that should expand index
+	! ensure_not_expanded rm "*/a" &&
+	test_must_be_empty sparse-index-err &&
+
+	! ensure_not_expanded rm "**a" &&
+	test_must_be_empty sparse-index-err
+'
+
+test_expect_success 'sparse index is not expanded: rm' '
+	init_repos &&
+
+	ensure_not_expanded rm deep/a &&
+
+	# test in-cone wildcard
+	git -C sparse-index reset --hard &&
+	ensure_not_expanded rm deep/* &&
+
+	# test recursive rm
+	git -C sparse-index reset --hard &&
+	ensure_not_expanded rm -r deep
+'
+
 test_done