Method ReadBatch

cpp/src/parquet/column_reader.cc:1099–1138

template <typename DType>
int64_t TypedColumnReaderImpl<DType>::ReadBatch(int64_t batch_size, int16_t* def_levels,
                                                int16_t* rep_levels, T* values,
                                                int64_t* values_read) {
  // HasNext might invoke ReadNewPage until a data page with
  // `available_values_current_page() > 0` is found.
  if (!HasNext()) {
    *values_read = 0;
    return 0;
  }

  // TODO(wesm): keep reading data pages until batch_size is reached, or the
  // row group is finished
  int64_t num_def_levels = 0;
  // Number of non-null values to read within `num_def_levels`.
  int64_t non_null_values_to_read = 0;
  ReadLevels(batch_size, def_levels, rep_levels, &num_def_levels,
             &non_null_values_to_read);
  // Should not return more values than available in the current data page,
  // since currently, ReadLevels would only consume level from current
  // data page.
  if (ARROW_PREDICT_FALSE(num_def_levels > this->available_values_current_page())) {
    throw ParquetException(kErrorRepDefLevelNotMatchesNumValues);
  }
  if (non_null_values_to_read != 0) {
    *values_read = this->ReadValues(non_null_values_to_read, values);
  } else {
    *values_read = 0;
  }
  // Adjust total_values, since if max_def_level_ == 0, num_def_levels would
  // be 0 and `values_read` would adjust to `available_values_current_page()`.
  int64_t total_values = std::max<int64_t>(num_def_levels, *values_read);
  int64_t expected_values = std::min(batch_size, this->available_values_current_page());
  if (total_values == 0 && expected_values > 0) {
    std::stringstream ss;
    ss << "Read 0 values, expected " << expected_values;
    ParquetException::EofException(ss.str());
  }
  this->ConsumeBufferedValues(total_values);
  return total_values;
}

template <typename DType>
void TypedColumnReaderImpl<DType>::InitScratchForSkip() {