add, rm, mv: fix bug that prevents the update of non-sparse dirs

These three commands recently learned to avoid updating paths outside
the sparse checkout even if they are missing the SKIP_WORKTREE bit. This
is done using path_in_sparse_checkout(), which checks whether a given
path matches the current list of sparsity rules, similar to what
clear_ce_flags() does when we run "git sparse checkout init" or "git
sparse-checkout reapply". However, clear_ce_flags() uses a recursive
approach, applying the match results from parent directories on paths
that get the UNDECIDED result, whereas path_in_sparse_checkout() only
attempts to match the full path and immediately considers UNDECIDED as
NOT_MATCHED. This makes the function miss matches with leading
directories. For example, if the user has the sparsity patterns "!/a"
and "b/", add, rm, and mv will fail to update the path "a/b/c" and end
up displaying a warning about it being outside the sparse checkout even
though it isn't. This problem only occurs in full pattern mode as the
pattern matching functions never return UNDECIDED for cone mode.

To fix this, replicate the recursive behavior of clear_ce_flags() in
path_in_sparse_checkout(), falling back to the parent directory match
when a path gets the UNDECIDED result. (If this turns out to be too
expensive in some cases, we may want to later add some form of caching
to accelerate multiple queries within the same directory. This is not
implemented in this patch, though.) Also add two tests for each affected
command (add, rm, and mv) to check that they behave correctly with the
recursive pattern matching. The first test would previously fail without
this patch while the second already succeeded. It is added mostly to
make sure that we are not breaking the existing pattern matching for
directories that are really sparse, and also as a protection against any
future regressions.

Two other existing tests had to be changed as well: one test in t3602
checks that "git rm -r <dir>" won't remove sparse entries, but it didn't
allow the non-sparse entries inside <dir> to be removed. The other one,
in t7002, tested that "git mv" would correctly display a warning message
for sparse paths, but it accidentally expected the message to include
two non-sparse paths as well.

Signed-off-by: Matheus Tavares <[email protected]>
Acked-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: matheustavares

dir.c

@@ -1504,8 +1504,9 @@ 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;
+	enum pattern_match_result match = UNDECIDED;
+	const char *end, *slash;
 
 	/*
 	 * We default to accepting a path if there are no patterns or
@@ -1516,11 +1517,27 @@ static int path_in_sparse_checkout_1(const char *path,
 	     !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;
+	/*
+	 * If UNDECIDED, use the match from the parent dir (recursively), or
+	 * fall back to NOT_MATCHED at the topmost level. Note that cone mode
+	 * never returns UNDECIDED, so we will execute only one iteration in
+	 * this case.
+	 */
+	for (end = path + strlen(path);
+	     end > path && match == UNDECIDED;
+	     end = slash) {
+
+		for (slash = end - 1; slash > path && *slash != '/'; slash--)
+			; /* do nothing */
+
+		match = path_matches_pattern_list(path, end - path,
+				slash > path ? slash + 1 : path, &dtype,
+				istate->sparse_checkout_patterns, istate);
+
+		/* We are going to match the parent dir now */
+		dtype = DT_DIR;
+	}
+	return match > 0;
 }
 
 int path_in_sparse_checkout(const char *path,

t/t3602-rm-sparse-checkout.sh

@@ -40,14 +40,20 @@ done
 test_expect_success 'recursive rm does not remove sparse entries' '
 	git reset --hard &&
 	git sparse-checkout set sub/dir &&
-	test_must_fail git rm -r sub &&
-	git rm --sparse -r sub &&
+	git rm -r sub &&
 	git status --porcelain -uno >actual &&
 	cat >expected <<-\EOF &&
+	D  sub/dir/e
+	EOF
+	test_cmp expected actual &&
+
+	git rm --sparse -r sub &&
+	git status --porcelain -uno >actual2 &&
+	cat >expected2 <<-\EOF &&
 	D  sub/d
 	D  sub/dir/e
 	EOF
-	test_cmp expected actual
+	test_cmp expected2 actual2
 '
 
 test_expect_success 'recursive rm --sparse removes sparse entries' '
@@ -105,4 +111,29 @@ test_expect_success 'refuse to rm a non-skip-worktree path outside sparse cone'
 	test_path_is_missing b
 '
 
+test_expect_success 'can remove files from non-sparse dir' '
+	git reset --hard &&
+	git sparse-checkout disable &&
+	mkdir -p w x/y &&
+	test_commit w/f &&
+	test_commit x/y/f &&
+
+	git sparse-checkout set w !/x y/ &&
+	git rm w/f.t x/y/f.t 2>stderr &&
+	test_must_be_empty stderr
+'
+
+test_expect_success 'refuse to remove non-skip-worktree file from sparse dir' '
+	git reset --hard &&
+	git sparse-checkout disable &&
+	mkdir -p x/y/z &&
+	test_commit x/y/z/f &&
+	git sparse-checkout set !/x y/ !x/y/z &&
+
+	git update-index --no-skip-worktree x/y/z/f.t &&
+	test_must_fail git rm x/y/z/f.t 2>stderr &&
+	echo x/y/z/f.t | cat sparse_error_header - sparse_hint >expect &&
+	test_cmp expect stderr
+'
+
 test_done

t/t3705-add-sparse-checkout.sh

@@ -214,4 +214,21 @@ test_expect_success 'add allows sparse entries with --sparse' '
 	test_must_be_empty stderr
 '
 
+test_expect_success 'can add files from non-sparse dir' '
+	git sparse-checkout set w !/x y/ &&
+	mkdir -p w x/y &&
+	touch w/f x/y/f &&
+	git add w/f x/y/f 2>stderr &&
+	test_must_be_empty stderr
+'
+
+test_expect_success 'refuse to add non-skip-worktree file from sparse dir' '
+	git sparse-checkout set !/x y/ !x/y/z &&
+	mkdir -p x/y/z &&
+	touch x/y/z/f &&
+	test_must_fail git add x/y/z/f 2>stderr &&
+	echo x/y/z/f | cat sparse_error_header - sparse_hint >expect &&
+	test_cmp expect stderr
+'
+
 test_done

t/t7002-mv-sparse-checkout.sh

@@ -143,8 +143,6 @@ test_expect_success 'recursive mv refuses to move (possible) sparse' '
 	cat >>expect <<-\EOF &&
 	sub/d
 	sub2/d
-	sub/dir/e
-	sub2/dir/e
 	sub/dir2/e
 	sub2/dir2/e
 	EOF
@@ -186,4 +184,26 @@ test_expect_success 'recursive mv refuses to move sparse' '
 	git reset --hard HEAD~1
 '
 
+test_expect_success 'can move files to non-sparse dir' '
+	git reset --hard &&
+	git sparse-checkout init --no-cone &&
+	git sparse-checkout set a b c w !/x y/ &&
+	mkdir -p w x/y &&
+
+	git mv a w/new-a 2>stderr &&
+	git mv b x/y/new-b 2>stderr &&
+	test_must_be_empty stderr
+'
+
+test_expect_success 'refuse to move file to non-skip-worktree sparse path' '
+	git reset --hard &&
+	git sparse-checkout init --no-cone &&
+	git sparse-checkout set a !/x y/ !x/y/z &&
+	mkdir -p x/y/z &&
+
+	test_must_fail git mv a x/y/z/new-a 2>stderr &&
+	echo x/y/z/new-a | cat sparse_error_header - sparse_hint >expect &&
+	test_cmp expect stderr
+'
+
 test_done