Skip to content

GH-46988: [C++][Parquet] Fix FLBA DecodeArrow multiply overflow #46991

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
mapleFU merged 2 commits into from
Jul 4, 2025
Merged

GH-46988: [C++][Parquet] Fix FLBA DecodeArrow multiply overflow #46991

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9eac1a1
GH-46988: [C++][Parquet] Fix FLBA DecodeArrow multiple overflow
mapleFU Jul 4, 2025
ef7f2a1
Apply suggestions
mapleFU Jul 4, 2025
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: 11 additions & 12 deletions cpp/src/parquet/decoder.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,6 +260,13 @@ auto DispatchArrowBinaryHelper(typename EncodingTraits<DType>::Accumulator* acc,
}
}

void CheckPageLargeEnough(int64_t remaining_bytes, int32_t value_width,
int64_t num_values) {
if (remaining_bytes < value_width * num_values) {
ParquetException::EofException();
}
}

// Internal decoder class hierarchy

class DecoderImpl : virtual public Decoder {
Expand Down Expand Up @@ -385,9 +392,7 @@ int PlainDecoder<DType>::DecodeArrow(

constexpr int value_size = static_cast<int>(sizeof(value_type));
int values_decoded = num_values - null_count;
if (ARROW_PREDICT_FALSE(this->len_ < value_size * values_decoded)) {
ParquetException::EofException();
}
CheckPageLargeEnough(this->len_, value_size, values_decoded);

const uint8_t* data = this->data_;

Expand Down Expand Up @@ -419,9 +424,7 @@ int PlainDecoder<DType>::DecodeArrow(

constexpr int value_size = static_cast<int>(sizeof(value_type));
int values_decoded = num_values - null_count;
if (ARROW_PREDICT_FALSE(this->len_ < value_size * values_decoded)) {
ParquetException::EofException();
}
CheckPageLargeEnough(this->len_, value_size, values_decoded);

const uint8_t* data = this->data_;

Expand Down Expand Up @@ -659,9 +662,7 @@ inline int PlainDecoder<FLBAType>::DecodeArrow(
typename EncodingTraits<FLBAType>::Accumulator* builder) {
const int byte_width = this->type_length_;
const int values_decoded = num_values - null_count;
if (ARROW_PREDICT_FALSE(len_ < byte_width * values_decoded)) {
ParquetException::EofException();
}
CheckPageLargeEnough(len_, byte_width, values_decoded);

PARQUET_THROW_NOT_OK(builder->Reserve(num_values));

Expand Down Expand Up @@ -691,9 +692,7 @@ inline int PlainDecoder<FLBAType>::DecodeArrow(
typename EncodingTraits<FLBAType>::DictAccumulator* builder) {
const int byte_width = this->type_length_;
const int values_decoded = num_values - null_count;
if (ARROW_PREDICT_FALSE(len_ < byte_width * values_decoded)) {
ParquetException::EofException();
}
CheckPageLargeEnough(len_, byte_width, values_decoded);

PARQUET_THROW_NOT_OK(builder->Reserve(num_values));
PARQUET_THROW_NOT_OK(
Expand Down
2 changes: 1 addition & 1 deletion testing
Open in desktop
Submodule testing updated 1 files
+ − data/parquet/fuzzing/clusterfuzz-testcase-minimized-parquet-arrow-fuzz-5843248142942208
Loading