Skip to content

GH-51156: [C++] Raise CapacityError instead of truncating binary values over 2 GiB #51158

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ngoldbaum wants to merge 1 commit into
base: main
Choose a base branch
from
+31 −0
Open

GH-51156: [C++] Raise CapacityError instead of truncating binary values over 2 GiB #51158

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions cpp/src/arrow/array/array_binary_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -946,6 +946,29 @@ TEST_F(TestChunkedBinaryBuilder, LargeElementCount) {
}
}

TEST(TestBinaryBuilder, LARGE_MEMORY_TEST(AppendOverflow)) {
const std::string value(static_cast<size_t>(1) << 31, 'x');

BinaryBuilder builder;
ASSERT_RAISES(CapacityError, builder.Append(std::string_view(value)));
ASSERT_OK(builder.Append("x"));
ASSERT_RAISES(CapacityError, builder.ExtendCurrent(std::string_view(value)));
ASSERT_OK_AND_ASSIGN(auto array, builder.Finish());
ASSERT_OK(array->ValidateFull());
ASSERT_EQ(1, array->length());
}

TEST_F(TestChunkedBinaryBuilder, LARGE_MEMORY_TEST(AppendOverflow)) {
Init(100);
const std::string value(static_cast<size_t>(1) << 31, 'x');

ASSERT_RAISES(CapacityError, builder_->Append(std::string_view(value)));
ArrayVector chunks;
ASSERT_OK(builder_->Finish(&chunks));
ASSERT_EQ(1, chunks.size());
ASSERT_EQ(0, chunks[0]->length());
}

TEST(TestChunkedStringBuilder, BasicOperation) {
const int chunksize = 100;
internal::ChunkedStringBuilder builder(chunksize);
Expand Down
8 changes: 8 additions & 0 deletions cpp/src/arrow/array/builder_binary.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,7 @@ class BaseBinaryBuilder
}

Status Append(std::string_view value) {
ARROW_RETURN_NOT_OK(ValidateOverflow(static_cast<int64_t>(value.size())));
return Append(value.data(), static_cast<offset_type>(value.size()));
}

Expand All @@ -100,6 +101,7 @@ class BaseBinaryBuilder
}

Status ExtendCurrent(std::string_view value) {
ARROW_RETURN_NOT_OK(ValidateOverflow(static_cast<int64_t>(value.size())));
return ExtendCurrent(reinterpret_cast<const uint8_t*>(value.data()),
static_cast<offset_type>(value.size()));
}
Expand Down Expand Up @@ -949,6 +951,12 @@ class ARROW_EXPORT ChunkedBinaryBuilder {
}

Status Append(std::string_view value) {
if (ARROW_PREDICT_FALSE(value.size() >
static_cast<size_t>(BinaryBuilder::memory_limit()))) {
return Status::CapacityError("array cannot contain more than ",
BinaryBuilder::memory_limit(), " bytes, have ",
value.size());
}
return Append(reinterpret_cast<const uint8_t*>(value.data()),
static_cast<int32_t>(value.size()));
}
Expand Down
Loading