You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@arrow.apache.org by ks...@apache.org on 2021/05/17 11:37:18 UTC
[arrow] 12/13: ARROW-12774 : [C++][Compute]
replace_substring_regex() creates invalid arrays => crash
This is an automated email from the ASF dual-hosted git repository.
kszucs pushed a commit to branch maint-4.0.x
in repository https://gitbox.apache.org/repos/asf/arrow.git
commit efdfb6dd45f221ab1124ed1b648c186c82301867
Author: niranda perera <ni...@gmail.com>
AuthorDate: Sat May 15 14:29:38 2021 +0800
ARROW-12774 : [C++][Compute] replace_substring_regex() creates invalid arrays => crash
fixing ARROW-12774
Closes #10320 from nirandaperera/ARROW-12774
Authored-by: niranda perera <ni...@gmail.com>
Signed-off-by: Yibo Cai <yi...@arm.com>
---
cpp/src/arrow/compute/kernels/scalar_string.cc | 2 +-
cpp/src/arrow/compute/kernels/scalar_string_test.cc | 8 ++++++++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/cpp/src/arrow/compute/kernels/scalar_string.cc b/cpp/src/arrow/compute/kernels/scalar_string.cc
index 82ae6fa..84a30c4 100644
--- a/cpp/src/arrow/compute/kernels/scalar_string.cc
+++ b/cpp/src/arrow/compute/kernels/scalar_string.cc
@@ -1329,7 +1329,7 @@ struct ReplaceSubString {
if (batch[0].kind() == Datum::ARRAY) {
// We already know how many strings we have, so we can use Reserve/UnsafeAppend
- KERNEL_RETURN_IF_ERROR(ctx, offset_builder.Reserve(batch[0].array()->length));
+ KERNEL_RETURN_IF_ERROR(ctx, offset_builder.Reserve(batch[0].array()->length + 1));
offset_builder.UnsafeAppend(0); // offsets start at 0
const ArrayData& input = *batch[0].array();
diff --git a/cpp/src/arrow/compute/kernels/scalar_string_test.cc b/cpp/src/arrow/compute/kernels/scalar_string_test.cc
index cb74b14..a59634b 100644
--- a/cpp/src/arrow/compute/kernels/scalar_string_test.cc
+++ b/cpp/src/arrow/compute/kernels/scalar_string_test.cc
@@ -499,6 +499,14 @@ TYPED_TEST(TestStringKernels, ReplaceSubstringRegex) {
ReplaceSubstringOptions options_regex2{"(a.a)", "aba\\1"};
this->CheckUnary("replace_substring_regex", R"(["aaaaaa"])", this->type(),
R"(["abaaaaabaaaa"])", &options_regex2);
+
+ // ARROW-12774
+ ReplaceSubstringOptions options_regex3{"X", "Y"};
+ this->CheckUnary("replace_substring_regex",
+ R"(["A","A","A","A","A","A","A","A","A","A","A","A","A","A","A","A"])",
+ this->type(),
+ R"(["A","A","A","A","A","A","A","A","A","A","A","A","A","A","A","A"])",
+ &options_regex3);
}
TYPED_TEST(TestStringKernels, ReplaceSubstringRegexLimited) {