pitrou commented on code in PR #40094:
URL: https://github.com/apache/arrow/pull/40094#discussion_r1494374171
##########
cpp/src/parquet/encoding.cc:
##########
@@ -3559,136 +3618,162 @@ class DeltaByteArrayFLBADecoder : public
DeltaByteArrayDecoderImpl<FLBAType>,
};
// ----------------------------------------------------------------------
-// BYTE_STREAM_SPLIT
+// BYTE_STREAM_SPLIT decoders
template <typename DType>
-class ByteStreamSplitDecoder : public DecoderImpl, virtual public
TypedDecoder<DType> {
+class ByteStreamSplitDecoderBase : public DecoderImpl,
+ virtual public TypedDecoder<DType> {
public:
using T = typename DType::c_type;
- explicit ByteStreamSplitDecoder(const ColumnDescriptor* descr);
- int Decode(T* buffer, int max_values) override;
+ ByteStreamSplitDecoderBase(const ColumnDescriptor* descr, int byte_width)
+ : DecoderImpl(descr, Encoding::BYTE_STREAM_SPLIT),
byte_width_(byte_width) {}
- int DecodeArrow(int num_values, int null_count, const uint8_t* valid_bits,
- int64_t valid_bits_offset,
- typename EncodingTraits<DType>::Accumulator* builder)
override;
+ void SetData(int num_values, const uint8_t* data, int len) override {
+ if (static_cast<int64_t>(num_values) * byte_width_ != len) {
+ throw ParquetException(
+ "Data size does not match number of values in BYTE_STREAM_SPLIT");
Review Comment:
Will do.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
