spark PythonUtils 源码

spark PythonUtils 代码

文件路径：/core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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 org.apache.spark.api.python

import java.io.File
import java.util.{List => JList}

import scala.collection.JavaConverters._
import scala.collection.mutable.ArrayBuffer

import org.apache.spark.SparkContext
import org.apache.spark.api.java.{JavaRDD, JavaSparkContext}

private[spark] object PythonUtils {
  val PY4J_ZIP_NAME = "py4j-0.10.9.7-src.zip"

  /** Get the PYTHONPATH for PySpark, either from SPARK_HOME, if it is set, or from our JAR */
  def sparkPythonPath: String = {
    val pythonPath = new ArrayBuffer[String]
    for (sparkHome <- sys.env.get("SPARK_HOME")) {
      pythonPath += Seq(sparkHome, "python", "lib", "pyspark.zip").mkString(File.separator)
      pythonPath +=
        Seq(sparkHome, "python", "lib", PY4J_ZIP_NAME).mkString(File.separator)
    }
    pythonPath ++= SparkContext.jarOfObject(this)
    pythonPath.mkString(File.pathSeparator)
  }

  /** Merge PYTHONPATHS with the appropriate separator. Ignores blank strings. */
  def mergePythonPaths(paths: String*): String = {
    paths.filter(_ != "").mkString(File.pathSeparator)
  }

  def generateRDDWithNull(sc: JavaSparkContext): JavaRDD[String] = {
    sc.parallelize(List("a", null, "b"))
  }

  /**
   * Convert list of T into seq of T (for calling API with varargs)
   */
  def toSeq[T](vs: JList[T]): Seq[T] = {
    vs.asScala.toSeq
  }

  /**
   * Convert list of T into a (Scala) List of T
   */
  def toList[T](vs: JList[T]): List[T] = {
    vs.asScala.toList
  }

  /**
   * Convert list of T into array of T (for calling API with array)
   */
  def toArray[T](vs: JList[T]): Array[T] = {
    vs.toArray().asInstanceOf[Array[T]]
  }

  /**
   * Convert java map of K, V into Map of K, V (for calling API with varargs)
   */
  def toScalaMap[K, V](jm: java.util.Map[K, V]): Map[K, V] = {
    jm.asScala.toMap
  }

  def isEncryptionEnabled(sc: JavaSparkContext): Boolean = {
    sc.conf.get(org.apache.spark.internal.config.IO_ENCRYPTION_ENABLED)
  }

  def getBroadcastThreshold(sc: JavaSparkContext): Long = {
    sc.conf.get(org.apache.spark.internal.config.BROADCAST_FOR_UDF_COMPRESSION_THRESHOLD)
  }

  def getPythonAuthSocketTimeout(sc: JavaSparkContext): Long = {
    sc.conf.get(org.apache.spark.internal.config.Python.PYTHON_AUTH_SOCKET_TIMEOUT)
  }

  def getSparkBufferSize(sc: JavaSparkContext): Int = {
    sc.conf.get(org.apache.spark.internal.config.BUFFER_SIZE)
  }
}

相关信息

spark 源码目录

相关文章

spark Py4JServer 源码

spark PythonGatewayServer 源码

spark PythonHadoopUtil 源码

spark PythonPartitioner 源码

spark PythonRDD 源码

spark PythonRunner 源码

spark PythonWorkerFactory 源码

spark SerDeUtil 源码

spark WriteInputFormatTestDataGenerator 源码