pitrou commented on a change in pull request #10627:
URL: https://github.com/apache/arrow/pull/10627#discussion_r691990798
##########
File path: cpp/src/parquet/encoding.cc
##########
@@ -2107,73 +2105,99 @@ class DeltaBitPackDecoder : public DecoderImpl, virtual
public TypedDecoder<DTyp
}
private:
- void InitBlock() {
- // The number of values per block.
- uint32_t block_size;
- if (!decoder_.GetVlqInt(&block_size)) ParquetException::EofException();
- if (!decoder_.GetVlqInt(&num_mini_blocks_))
ParquetException::EofException();
- if (!decoder_.GetVlqInt(&values_current_block_)) {
+ void InitHeader() {
+ if (!decoder_.GetVlqInt(&values_per_block_))
ParquetException::EofException();
+ if (!decoder_.GetVlqInt(&mini_blocks_per_block_))
ParquetException::EofException();
+ if (!decoder_.GetVlqInt(&total_value_count_)) {
ParquetException::EofException();
}
if (!decoder_.GetZigZagVlqInt(&last_value_))
ParquetException::EofException();
- delta_bit_widths_ = AllocateBuffer(pool_, num_mini_blocks_);
- uint8_t* bit_width_data = delta_bit_widths_->mutable_data();
+ delta_bit_widths_ = AllocateBuffer(pool_, mini_blocks_per_block_);
+ values_per_mini_block_ = values_per_block_ / mini_blocks_per_block_;
+ if (values_per_mini_block_ % 8 != 0) {
+ throw ParquetException("miniBlockSize must be multiple of 8, but it's " +
Review comment:
Well, we should follow the spec here, especially as `unpack64` assumes
the input length is a multiple of 32.
--
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]
