Method DecodeRowGroups

cpp/src/parquet/arrow/reader.cc:1272–1309

}

Future<std::shared_ptr<Table>> FileReaderImpl::DecodeRowGroups(
    std::shared_ptr<FileReaderImpl> self, const std::vector<int>& row_groups,
    const std::vector<int>& column_indices, ::arrow::internal::Executor* cpu_executor) {
  // `self` is used solely to keep `this` alive in an async context - but we use this
  // in a sync context too so use `this` over `self`
  std::vector<std::shared_ptr<ColumnReaderImpl>> readers;
  std::shared_ptr<::arrow::Schema> result_schema;
  RETURN_NOT_OK(GetFieldReaders(column_indices, row_groups, &readers, &result_schema));
  // OptionalParallelForAsync requires an executor
  if (!cpu_executor) cpu_executor = ::arrow::internal::GetCpuThreadPool();

  auto read_column = [row_groups, self, this](size_t i,
                                              std::shared_ptr<ColumnReaderImpl> reader)
      -> ::arrow::Result<std::shared_ptr<::arrow::ChunkedArray>> {
    std::shared_ptr<::arrow::ChunkedArray> column;
    RETURN_NOT_OK(ReadColumn(static_cast<int>(i), row_groups, reader.get(), &column));
    return column;
  };
  auto make_table = [result_schema, row_groups, self,
                     this](const ::arrow::ChunkedArrayVector& columns)
      -> ::arrow::Result<std::shared_ptr<Table>> {
    int64_t num_rows = 0;
    if (!columns.empty()) {
      num_rows = columns[0]->length();
    } else {
      for (int i : row_groups) {
        num_rows += parquet_reader()->metadata()->RowGroup(i)->num_rows();
      }
    }
    auto table = Table::Make(std::move(result_schema), columns, num_rows);
    RETURN_NOT_OK(table->Validate());
    return table;
  };
  return ::arrow::internal::OptionalParallelForAsync(reader_properties_.use_threads(),
                                                     std::move(readers), read_column,
                                                     cpu_executor)
      .Then(std::move(make_table));
}

std::shared_ptr<RowGroupReader> FileReaderImpl::RowGroup(int row_group_index) {
  return std::make_shared<RowGroupReaderImpl>(this, row_group_index);