ARROW-12774 : [C++][Compute] replace_substring_regex() creates invali…

…d arrays => crash fixing ARROW-12774 Closes #10320 from nirandaperera/ARROW-12774 Authored-by: niranda perera <[email protected]> Signed-off-by: Yibo Cai <[email protected]>
apache · May 15, 2021 · 068318f · 068318f
1 parent f47703e
commit 068318f
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/cpp/src/arrow/compute/kernels/scalar_string.cc b/cpp/src/arrow/compute/kernels/scalar_string.cc
@@ -1332,7 +1332,7 @@ struct ReplaceSubString {
 
     if (batch[0].kind() == Datum::ARRAY) {
       // We already know how many strings we have, so we can use Reserve/UnsafeAppend
-      RETURN_NOT_OK(offset_builder.Reserve(batch[0].array()->length));
+      RETURN_NOT_OK(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
@@ -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) {