Method DecodeArrow

cpp/src/parquet/decoder.cc:1876–1933

  }

  int DecodeArrow(int num_values, int null_count, const uint8_t* valid_bits,
                  int64_t valid_bits_offset,
                  typename EncodingTraits<BooleanType>::Accumulator* out) override {
    if (null_count == num_values) {
      PARQUET_THROW_NOT_OK(out->AppendNulls(null_count));
      return 0;
    }
    constexpr int kBatchSize = 1024;
    std::array<bool, kBatchSize> values;
    const int num_non_null_values = num_values - null_count;
    // Remaining non-null boolean values to read from decoder.
    // We decode from `decoder_` with maximum 1024 size batches.
    int num_remain_non_null_values = num_non_null_values;
    int current_index_in_batch = 0;
    int current_batch_size = 0;
    auto next_boolean_batch = [&]() {
      DCHECK_GT(num_remain_non_null_values, 0);
      DCHECK_EQ(current_index_in_batch, current_batch_size);
      current_batch_size = std::min(num_remain_non_null_values, kBatchSize);
      int decoded_count = decoder_->GetBatch(values.data(), current_batch_size);
      if (ARROW_PREDICT_FALSE(decoded_count != current_batch_size)) {
        // required values is more than values in decoder.
        ParquetException::EofException();
      }
      num_remain_non_null_values -= current_batch_size;
      current_index_in_batch = 0;
    };

    // Reserve all values including nulls first
    PARQUET_THROW_NOT_OK(out->Reserve(num_values));
    if (null_count == 0) {
      // Fast-path for not having nulls.
      do {
        next_boolean_batch();
        PARQUET_THROW_NOT_OK(
            out->AppendValues(values.begin(), values.begin() + current_batch_size));
        num_values -= current_batch_size;
        // set current_index_in_batch to current_batch_size means
        // the whole batch is totally consumed.
        current_index_in_batch = current_batch_size;
      } while (num_values > 0);
      return num_non_null_values;
    }
    auto next_value = [&]() -> bool {
      if (current_index_in_batch == current_batch_size) {
        next_boolean_batch();
        DCHECK_GT(current_batch_size, 0);
      }
      DCHECK_LT(current_index_in_batch, current_batch_size);
      bool value = values[current_index_in_batch];
      ++current_index_in_batch;
      return value;
    };
    VisitNullBitmapInline(
        valid_bits, valid_bits_offset, num_values, null_count,
        [&]() { out->UnsafeAppend(next_value()); }, [&]() { out->UnsafeAppendNull(); });
    return num_non_null_values;
  }