parquet.hpp

 
#pragma once
#include <cstddef>
#include <memory>
 
#include <cudf/ast/expressions.hpp>
#include <cudf/io/parquet.hpp>
#include <cudf/types.hpp>
 
#include <rapidsmpf/communicator/communicator.hpp>
#include <rapidsmpf/owning_wrapper.hpp>
#include <rapidsmpf/streaming/core/actor.hpp>
#include <rapidsmpf/streaming/core/channel.hpp>
#include <rapidsmpf/streaming/core/context.hpp>
 
namespace rapidsmpf::streaming {
 
struct Filter {
    rmm::cuda_stream_view stream;  
    cudf::ast::expression& filter;  
    OwningWrapper owner{};  
};
 
namespace actor {
Actor read_parquet(
    std::shared_ptr<Context> ctx,
    std::shared_ptr<Communicator> comm,
    std::shared_ptr<Channel> ch_out,
    std::size_t num_producers,
    cudf::io::parquet_reader_options options,
    // TODO: use byte count, not row count?
    cudf::size_type num_rows_per_chunk,
    std::unique_ptr<Filter> filter = nullptr
);
}  // namespace actor
}  // namespace rapidsmpf::streaming