Skip to content

GH-48691: [C++][Parquet] Write serializer may crash if the value buffer is empty #48692

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

Merged
wgtmac merged 4 commits into from
Jan 27, 2026
Merged

GH-48691: [C++][Parquet] Write serializer may crash if the value buffer is empty #48692

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
83aabed
[GH-48691][C++] Write serializer could be crash if the value buffer i…
boneanxs Dec 30, 2025
f65e58e
Address comment
boneanxs Jan 21, 2026
474ee19
Address comment
boneanxs Jan 22, 2026
080fb01
Address comment
boneanxs Jan 27, 2026
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
29 changes: 29 additions & 0 deletions cpp/src/parquet/arrow/arrow_reader_writer_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5889,5 +5889,34 @@ TEST(TestArrowReadWrite, OperationsOnClosedWriter) {
ASSERT_RAISES(Invalid, writer->WriteTable(*table, 1));
}

TEST(TestArrowReadWrite, AllNulls) {
auto schema = ::arrow::schema({::arrow::field("all_nulls", ::arrow::int8())});

constexpr int64_t length = 3;
ASSERT_OK_AND_ASSIGN(auto null_bitmap, ::arrow::AllocateEmptyBitmap(length));
auto array_data = ::arrow::ArrayData::Make(
::arrow::int8(), length, {null_bitmap, /*values=*/nullptr}, /*null_count=*/length);
auto array = ::arrow::MakeArray(array_data);
auto record_batch = ::arrow::RecordBatch::Make(schema, length, {array});

auto sink = CreateOutputStream();
ASSERT_OK_AND_ASSIGN(auto writer, parquet::arrow::FileWriter::Open(
*schema, ::arrow::default_memory_pool(), sink,
parquet::default_writer_properties(),
parquet::default_arrow_writer_properties()));
ASSERT_OK(writer->WriteRecordBatch(*record_batch));
ASSERT_OK(writer->Close());
ASSERT_OK_AND_ASSIGN(auto buffer, sink->Finish());

std::shared_ptr<::arrow::Table> read_table;
ASSERT_OK_AND_ASSIGN(auto reader,
parquet::arrow::OpenFile(std::make_shared<BufferReader>(buffer),
::arrow::default_memory_pool()));
ASSERT_OK(reader->ReadTable(&read_table));
auto expected_table = ::arrow::Table::Make(
schema, {::arrow::ArrayFromJSON(::arrow::int8(), R"([null, null, null])")});
ASSERT_TRUE(expected_table->Equals(*read_table));
}

} // namespace arrow
} // namespace parquet
7 changes: 6 additions & 1 deletion cpp/src/parquet/column_writer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2099,7 +2099,12 @@ Status TypedColumnWriterImpl<ParquetType>::WriteArrowSerialize(
PARQUET_THROW_NOT_OK(ctx->GetScratchData<ParquetCType>(array.length(), &buffer));

SerializeFunctor<ParquetType, ArrowType> functor;
RETURN_NOT_OK(functor.Serialize(checked_cast<const ArrayType&>(array), ctx, buffer));
// The value buffer could be empty if all values are nulls.
// The output buffer will then remain uninitialized, but that's ok since
// null value slots are not written in Parquet.
if (array.null_count() != array.length()) {
RETURN_NOT_OK(functor.Serialize(checked_cast<const ArrayType&>(array), ctx, buffer));
}
bool no_nulls =
this->descr()->schema_node()->is_required() || (array.null_count() == 0);
if (!maybe_parent_nulls && no_nulls) {
Expand Down
Loading