minhash.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION.
 * SPDX-License-Identifier: Apache-2.0
 */
#pragma once
 
#include <cudf/column/column.hpp>
#include <cudf/hashing.hpp>
#include <cudf/lists/lists_column_view.hpp>
#include <cudf/scalar/scalar.hpp>
#include <cudf/strings/strings_column_view.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
#include <cudf/utilities/span.hpp>
 
namespace CUDF_EXPORT nvtext {
std::unique_ptr<cudf::column> minhash(
  cudf::strings_column_view const& input,
  uint32_t seed,
  cudf::device_span<uint32_t const> parameter_a,
  cudf::device_span<uint32_t const> parameter_b,
  cudf::size_type width,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<cudf::column> minhash64(
  cudf::strings_column_view const& input,
  uint64_t seed,
  cudf::device_span<uint64_t const> parameter_a,
  cudf::device_span<uint64_t const> parameter_b,
  cudf::size_type width,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<cudf::column> minhash_ngrams(
  cudf::lists_column_view const& input,
  cudf::size_type ngrams,
  uint32_t seed,
  cudf::device_span<uint32_t const> parameter_a,
  cudf::device_span<uint32_t const> parameter_b,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<cudf::column> minhash64_ngrams(
  cudf::lists_column_view const& input,
  cudf::size_type ngrams,
  uint64_t seed,
  cudf::device_span<uint64_t const> parameter_a,
  cudf::device_span<uint64_t const> parameter_b,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
  // end of group
}  // namespace CUDF_EXPORT nvtext