sparse-checkout: properly match escaped characters

In cone mode, the sparse-checkout feature uses hashset containment
queries to match paths. Make this algorithm respect escaped asterisk
(*) and backslash (\) characters.

Create dup_and_filter_pattern() method to convert a pattern by
removing escape characters and dropping an optional "/*" at the end.
This method is available in dir.h as we will use it in
builtin/sparse-checkout.c in a later change.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 51 insertions, 7 deletions

diff --git a/dir.c b/dir.c
index 71d28331f3..7ac0920b71 100644
--- a/dir.c
+++ b/dir.c
@@ -630,6 +630,36 @@ int pl_hashmap_cmp(const void *unused_cmp_data,
 	return strncmp(ee1->pattern, ee2->pattern, min_len);
 }
 
+static char *dup_and_filter_pattern(const char *pattern)
+{
+	char *set, *read;
+	size_t count  = 0;
+	char *result = xstrdup(pattern);
+
+	set = result;
+	read = result;
+
+	while (*read) {
+		/* skip escape characters (once) */
+		if (*read == '\\')
+			read++;
+
+		*set = *read;
+
+		set++;
+		read++;
+		count++;
+	}
+	*set = 0;
+
+	if (count > 2 &&
+	    *(set - 1) == '*' &&
+	    *(set - 2) == '/')
+		*(set - 2) = 0;
+
+	return result;
+}
+
 static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
 {
 	struct pattern_entry *translated;
@@ -702,8 +732,7 @@ static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern
 			goto clear_hashmaps;
 		}
 
-		truncated = xstrdup(given->pattern);
-		truncated[given->patternlen - 2] = 0;
+		truncated = dup_and_filter_pattern(given->pattern);
 
 		translated = xmalloc(sizeof(struct pattern_entry));
 		translated->pattern = truncated;
@@ -737,7 +766,7 @@ static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern
 
 	translated = xmalloc(sizeof(struct pattern_entry));
 
-	translated->pattern = xstrdup(given->pattern);
+	translated->pattern = dup_and_filter_pattern(given->pattern);
 	translated->patternlen = given->patternlen;
 	hashmap_entry_init(&translated->ent,
 			   ignore_case ?
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index c732abeacd..9ea700896d 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -378,13 +378,28 @@ test_expect_success 'pattern-checks: contained glob characters' '
 	done
 '
 
-test_expect_success 'pattern-checks: escaped "*"' '
-	cat >repo/.git/info/sparse-checkout <<-\EOF &&
+test_expect_success BSLASHPSPEC 'pattern-checks: escaped "*"' '
+	git clone repo escaped &&
+	TREEOID=$(git -C escaped rev-parse HEAD:folder1) &&
+	NEWTREE=$(git -C escaped mktree <<-EOF
+	$(git -C escaped ls-tree HEAD)
+	040000 tree $TREEOID	zbad\\dir
+	040000 tree $TREEOID	zdoes*exist
+	EOF
+	) &&
+	COMMIT=$(git -C escaped commit-tree $NEWTREE -p HEAD) &&
+	git -C escaped reset --hard $COMMIT &&
+	check_files escaped "a deep folder1 folder2 zbad\\dir zdoes*exist" &&
+	git -C escaped sparse-checkout init --cone &&
+	cat >escaped/.git/info/sparse-checkout <<-\EOF &&
 	/*
 	!/*/
-	/does\*not\*exist/
+	/zbad\\dir/
+	!/zbad\\dir/*/
+	/zdoes\*not\*exist/
+	/zdoes\*exist/
 	EOF
-	check_read_tree_errors repo "a" ""
+	check_read_tree_errors escaped "a zbad\\dir zdoes*exist"
 '
 
 test_done