Skip to content

GH-53518: [Parquet] Reject unsupported compression codecs #53522

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
pitrou merged 1 commit into from
Oct 13, 2026
Merged

GH-53518: [Parquet] Reject unsupported compression codecs #53522

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
21 changes: 21 additions & 0 deletions cpp/src/parquet/metadata_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,13 @@

#include "parquet/metadata.h"

#include <gmock/gmock.h>
#include <gtest/gtest.h>

#include <cstring>

#include "arrow/util/key_value_metadata.h"
#include "parquet/exception.h"
#include "parquet/file_reader.h"
#include "parquet/file_writer.h"
#include "parquet/schema.h"
Expand Down Expand Up @@ -344,6 +348,23 @@ void AssertColumnChunkMinMax(const FileMetaData& metadata,

} // namespace

TEST(Metadata, UnknownCompressionCodecThrows) {
format::FileMetaData thrift_metadata = SingleInt32MetadataWithStats();
auto metadata = ParseMetadata(SerializeMetadata(thrift_metadata));

auto& column_chunk = thrift_metadata.row_groups.at(0).columns.at(0);
const int32_t raw_codec = 8;
static_assert(sizeof(column_chunk.meta_data.codec) == sizeof(raw_codec));
std::memcpy(&column_chunk.meta_data.codec, &raw_codec, sizeof(raw_codec));

auto column = ColumnChunkMetaData::Make(&column_chunk, metadata->schema()->Column(0));

EXPECT_THROW_THAT([&]() { column->compression(); }, ParquetException,
::testing::Property(
&ParquetException::what,
::testing::HasSubstr("Unsupported compression codec value: 8")));
}

TEST(Metadata, UnknownColumnOrderIgnoresMinMax) {
format::FileMetaData thrift_metadata = SingleInt32MetadataWithStats();
// Simulate an unsupported ColumnOrder value: unknown union fields are skipped by
Expand Down
2 changes: 1 addition & 1 deletion cpp/src/parquet/thrift_internal.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@ inline typename Compression::type LoadEnumSafe(const format::CompressionCodec::t
const auto max_value =
static_cast<decltype(raw_value)>(format::CompressionCodec::LZ4_RAW);
if (raw_value < min_value || raw_value > max_value) {
return Compression::UNCOMPRESSED;
throw ParquetException("Unsupported compression codec value: ", raw_value);
}
return FromThriftUnsafe(*in);
}
Expand Down
Loading