parquet_io_utils.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 */
 
#pragma once
 
#include <cudf/io/datasource.hpp>
#include <cudf/io/text/byte_range_info.hpp>
 
#include <rmm/cuda_stream_view.hpp>
#include <rmm/device_buffer.hpp>
#include <rmm/resource_ref.hpp>
 
#include <cstddef>
#include <functional>
#include <future>
#include <tuple>
#include <vector>
 
namespace CUDF_EXPORT cudf {
namespace io::parquet {
 
using cudf::io::text::byte_range_info;
 
[[nodiscard]] std::size_t metadata_size_hint();
 
[[nodiscard]] std::unique_ptr<cudf::io::datasource::buffer> fetch_footer_to_host(
  cudf::io::datasource& datasource);
 
[[nodiscard]] std::vector<std::unique_ptr<cudf::io::datasource::buffer>> fetch_footers_to_host(
  cudf::host_span<std::reference_wrapper<cudf::io::datasource> const> datasources);
 
[[nodiscard]] std::unique_ptr<cudf::io::datasource::buffer> fetch_page_index_to_host(
  cudf::io::datasource& datasource, byte_range_info const page_index_bytes);
 
[[nodiscard]] std::vector<std::unique_ptr<cudf::io::datasource::buffer>> fetch_page_indexes_to_host(
  cudf::host_span<std::reference_wrapper<cudf::io::datasource> const> datasources,
  cudf::host_span<byte_range_info const> page_index_bytes_per_source);
 
std::tuple<std::vector<rmm::device_buffer>,
           std::vector<cudf::device_span<uint8_t const>>,
           std::future<void>>
fetch_byte_ranges_to_device_async(cudf::io::datasource& datasource,
                                  cudf::host_span<byte_range_info const> byte_ranges,
                                  rmm::cuda_stream_view stream,
                                  rmm::device_async_resource_ref mr);
 
std::tuple<std::vector<rmm::device_buffer>,
           std::vector<std::vector<cudf::device_span<uint8_t const>>>,
           std::future<void>>
fetch_byte_ranges_to_device_async(
  cudf::host_span<std::reference_wrapper<cudf::io::datasource> const> datasources,
  cudf::host_span<std::vector<byte_range_info> const> byte_ranges_per_source,
  rmm::cuda_stream_view stream,
  rmm::device_async_resource_ref mr);
  // end of group
}  // namespace io::parquet
}  // namespace CUDF_EXPORT cudf