[v2,09/12] sparse-checkout: properly match escaped characters

Commit Message

Linus Arver via GitGitGadget Jan. 24, 2020, 9:19 p.m. UTC

From: Derrick Stolee <[e-mail]>

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 <[e-mail]>
---
 dir.c                              | 31 +++++++++++++++++++++++++++---
 dir.h                              |  1 +
 t/t1091-sparse-checkout-builtin.sh | 22 +++++++++++++++++----
 3 files changed, 47 insertions(+), 7 deletions(-)

Patch

diff --git a/dir.c b/dir.c
index 7cb78c8b87..6d8abc09c3 100644
--- a/dir.c
+++ b/dir.c
@@ -630,6 +630,32 @@  int pl_hashmap_cmp(const void *unused_cmp_data,
 	return strncmp(ee1->pattern, ee2->pattern, min_len);
 }
 
+char *dup_and_filter_pattern(const char *pattern)
+{
+	char *set, *read;
+	char *result = xstrdup(pattern);
+
+	set = result;
+	read = result;
+
+	while (*read) {
+		/* skip escape characters (once) */
+		if (*read == '\\')
+			read++;
+
+		*set = *read;
+
+		set++;
+		read++;
+	}
+	*set = 0;
+
+	if (*(read - 2) == '/' && *(read - 1) == '*')
+		*(read - 2) = 0;
+
+	return result;
+}
+
 static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
 {
 	struct pattern_entry *translated;
@@ -695,8 +721,7 @@  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;
@@ -730,7 +755,7 @@  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/dir.h b/dir.h
index 77a43dbf89..6dcd9d33e7 100644
--- a/dir.h
+++ b/dir.h
@@ -304,6 +304,7 @@  int pl_hashmap_cmp(const void *unused_cmp_data,
 		   const struct hashmap_entry *a,
 		   const struct hashmap_entry *b,
 		   const void *key);
+char *dup_and_filter_pattern(const char *pattern);
 int hashmap_contains_parent(struct hashmap *map,
 			    const char *path,
 			    struct strbuf *buffer);
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index 470900f6f4..0a21a5e15d 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -366,13 +366,27 @@  test_expect_success 'pattern-checks: starting "*"' '
 	check_read_tree_errors repo "a deep" "disabling cone pattern matching"
 '
 
-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/
+	/zdoes\*not\*exist/
+	/zdoes\*exist/
 	EOF
-	check_read_tree_errors repo "a" ""
+	check_read_tree_errors escaped "a zbad\\dir zdoes*exist"
 '
 
 test_done