com.nvidia.spark.rapids.ColumnarFileFormat.scala Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of rapids-4-spark_2.13 Show documentation

Creates the distribution package of the RAPIDS plugin for Apache Spark

There is a newer version: 24.10.1

/*
 * Copyright (c) 2019, NVIDIA CORPORATION.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.nvidia.spark.rapids

import org.apache.hadoop.mapreduce.Job

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.types.{DataType, StructType}

/**
 * Used to write columnar data to files.
 */
trait ColumnarFileFormat {
  /**
   * Prepares a write job and returns an [[ColumnarOutputWriterFactory]].  Client side job
   * preparation can be put here.  For example, user defined output committer can be configured here
   * by setting the output committer class in the conf of spark.sql.sources.outputCommitterClass.
   */
  def prepareWrite(
      sparkSession: SparkSession,
      job: Job,
      options: Map[String, String],
      dataSchema: StructType): ColumnarOutputWriterFactory

  /**
   * Returns whether this format supports the given `DataType` in the write path.
   * By default all data types are supported.
   */
  def supportDataType(dataType: DataType): Boolean = true
}