rok commented on code in PR #14191:
URL: https://github.com/apache/arrow/pull/14191#discussion_r986014746
##########
cpp/src/parquet/encoding.cc:
##########
@@ -2062,6 +2062,184 @@ class DictByteArrayDecoderImpl : public
DictDecoderImpl<ByteArrayType>,
}
};
+// ----------------------------------------------------------------------
+// DeltaBitPackEncoder
+
+template <typename DType>
+class DeltaBitPackEncoder : public EncoderImpl, virtual public
TypedEncoder<DType> {
+ public:
+ using T = typename DType::c_type;
+
+ explicit DeltaBitPackEncoder(const ColumnDescriptor* descr, MemoryPool* pool)
+ : EncoderImpl(descr, Encoding::DELTA_BINARY_PACKED, pool),
+ values_per_block_(128),
+ mini_blocks_per_block_(4),
+ values_per_mini_block_(values_per_block_ / mini_blocks_per_block_),
+ values_current_block_(0),
+ total_value_count_(0),
+ first_value_(0),
+ current_value_(0),
+ sink_(pool),
+ bits_buffer_(AllocateBuffer(pool, kInMemoryDefaultCapacity)),
+ bit_writer_(bits_buffer_->mutable_data(),
static_cast<int>(bits_buffer_->size())),
+ deltas_(std::vector<T>(values_per_block_)) {}
+
+ std::shared_ptr<Buffer> FlushValues() override;
+
+ int64_t EstimatedDataEncodedSize() override {
+ return 4 * sizeof(uint64_t) + sink_.length();
+ }
+
+ using TypedEncoder<DType>::Put;
+
+ void Put(const ::arrow::Array& values) override;
+
+ void Put(const T* buffer, int num_values) override;
+
+ void PutSpaced(const T* src, int num_values, const uint8_t* valid_bits,
+ int64_t valid_bits_offset) override {
+ ParquetException::NYI("put spaced");
+ }
+
+ protected:
+ const uint32_t values_per_block_;
+ const uint32_t mini_blocks_per_block_;
+ const uint32_t values_per_mini_block_;
+ uint32_t values_current_block_;
+ uint32_t total_value_count_;
+ T first_value_;
+ T current_value_;
+ ::arrow::BufferBuilder sink_;
+ std::shared_ptr<ResizableBuffer> bits_buffer_;
+ ::arrow::bit_util::BitWriter bit_writer_;
+ std::vector<T> deltas_;
+
+ private:
+ void FlushBlock();
+};
+
+template <typename DType>
+void DeltaBitPackEncoder<DType>::Put(const T* src, int num_values) {
+ if (num_values == 0) {
+ return;
+ }
+
+ uint32_t idx = 0;
+ if (total_value_count_ == 0) {
+ first_value_ = src[0];
+ current_value_ = first_value_;
+ idx = 1;
+ }
+ total_value_count_ += num_values;
+
+ int increment = total_value_count_ * sizeof(T);
+ if (ARROW_PREDICT_FALSE(sink_.capacity() + increment > sink_.capacity())) {
+ PARQUET_THROW_NOT_OK(sink_.Resize(increment, false));
+ }
+
+ while (idx < static_cast<uint32_t>(num_values)) {
+ T value = src[idx];
+ deltas_[values_current_block_] = value - current_value_;
+ current_value_ = value;
+ idx++;
+ values_current_block_++;
+ if (values_current_block_ == values_per_block_) {
+ FlushBlock();
+ }
+ }
+
+ if (values_current_block_ != 0) {
+ FlushBlock();
+ }
+}
+
+template <typename DType>
+void DeltaBitPackEncoder<DType>::FlushBlock() {
+ if (values_current_block_ == 0) {
+ return;
+ }
+
+ const auto min_delta =
+ static_cast<int64_t>(*std::min_element(deltas_.begin(), deltas_.end()));
Review Comment:
Changed to:
```
std::min_element(deltas_.begin(), deltas_.begin() + values_current_block_)
```
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
