CC00032.spark——|Hadoop&Spark.V06|——|Spark.v06|sparkcore|RDD编程高阶&RDD分区器|-CSDN博客

一、RDD分区器

### --- 以下RDD分别是否有分区器，是什么类型的分区器

scala> val rdd1 = sc.textFile("/wcinput/wc.txt")
rdd1: org.apache.spark.rdd.RDD[String] = /wcinput/wc.txt MapPartitionsRDD[34] at textFile at <console>:24

scala> rdd1.partitioner
res33: Option[org.apache.spark.Partitioner] = None

scala> val rdd2 = rdd1.flatMap(_.split("\\s+"))
rdd2: org.apache.spark.rdd.RDD[String] = MapPartitionsRDD[35] at flatMap at <console>:25

scala> rdd2.partitioner
res34: Option[org.apache.spark.Partitioner] = None

scala> val rdd3 = rdd2.map((_, 1))
rdd3: org.apache.spark.rdd.RDD[(String, Int)] = MapPartitionsRDD[36] at map at <console>:25

scala> rdd3.partitioner
res35: Option[org.apache.spark.Partitioner] = None

scala> val rdd4 = rdd3.reduceByKey(_+_)
rdd4: org.apache.spark.rdd.RDD[(String, Int)] = ShuffledRDD[37] at reduceByKey at <console>:25

scala> rdd4.partitioner
res36: Option[org.apache.spark.Partitioner] = Some(org.apache.spark.HashPartitioner@2)

scala> val rdd5 = rdd4.sortByKey()
rdd5: org.apache.spark.rdd.RDD[(String, Int)] = ShuffledRDD[40] at sortByKey at <console>:25

scala> rdd5.partitioner
res37: Option[org.apache.spark.Partitioner] = Some(org.apache.spark.RangePartitioner@e44e9b0e)

~~~     # 只有Key-Value类型的RDD才可能有分区器，Value类型的RDD分区器的值是None。

Optionally, a Partitioner for key-value RDDs (e.g. to say that the RDD is hash-partitioned)

二、分区器的作用及分类

### --- 分区器的作用及分类：

~~~     在 PairRDD(key,value) 中，很多操作都是基于key的，系统会按照key对数据进行重组，
~~~     如groupbykey；
~~~     数据重组需要规则，最常见的就是基于 Hash 的分区，此外还有一种复杂的基于抽样Range 分区方法；

### --- HashPartitioner

~~~     HashPartitioner：最简单、最常用，也是默认提供的分区器。
~~~     对于给定的key，计算其hashCode，并除以分区的个数取余，
~~~     如果余数小于0，则用 余数+分区的个数，最后返回的值就是这个key所属的分区ID。
~~~     该分区方法可以保证key相同的数据出现在同一个分区中。
~~~     用户可通过partitionBy主动使用分区器，通过partitions参数指定想要分区的数量。

### --- 分区器实验示例

scala> val rdd1 = sc.makeRDD(1 to 100).map((_, 1))
rdd1: org.apache.spark.rdd.RDD[(Int, Int)] = MapPartitionsRDD[42] at map at <console>:24

scala> rdd1.getNumPartitions
res38: Int = 3

~~~     # 仅仅是将数据大致平均分成了若干份；rdd并没有分区器

scala> rdd2.glom.collect.foreach(x=>println(x.toBuffer))
ArrayBuffer(hadoop, mapreduce, yarn, hdfs, hadoop, mapreduce)
ArrayBuffer(mapreduce, yarn, yanqi, yanqi, yanqi)

scala> rdd1.partitioner
res40: Option[org.apache.spark.Partitioner] = None

~~~     # 主动使用 HashPartitioner

scala> val rdd2 = rdd1.partitionBy(new org.apache.spark.HashPartitioner(10))
rdd2: org.apache.spark.rdd.RDD[(Int, Int)] = ShuffledRDD[44] at partitionBy at <console>:26

scala> rdd2.glom.collect.foreach(x=>println(x.toBuffer))
ArrayBuffer((10,1), (20,1), (30,1), (40,1), (50,1), (60,1), (70,1), (80,1), (90,1), (100,1))
ArrayBuffer((71,1), (81,1), (91,1), (41,1), (51,1), (61,1), (1,1), (11,1), (21,1), (31,1))
ArrayBuffer((42,1), (52,1), (62,1), (72,1), (82,1), (92,1), (2,1), (12,1), (22,1), (32,1))
ArrayBuffer((3,1), (13,1), (23,1), (33,1), (43,1), (53,1), (63,1), (73,1), (83,1), (93,1))
ArrayBuffer((34,1), (44,1), (54,1), (64,1), (4,1), (14,1), (24,1), (74,1), (84,1), (94,1))
ArrayBuffer((5,1), (15,1), (25,1), (35,1), (45,1), (55,1), (65,1), (75,1), (85,1), (95,1))
ArrayBuffer((76,1), (86,1), (96,1), (36,1), (46,1), (56,1), (66,1), (6,1), (16,1), (26,1))
ArrayBuffer((37,1), (47,1), (57,1), (67,1), (77,1), (87,1), (97,1), (7,1), (17,1), (27,1))
ArrayBuffer((8,1), (18,1), (28,1), (38,1), (48,1), (58,1), (68,1), (78,1), (88,1), (98,1))
ArrayBuffer((39,1), (49,1), (59,1), (9,1), (19,1), (29,1), (69,1), (79,1), (89,1), (99,1))

~~~     # 主动使用 HashPartitioner

scala> val rdd3 = rdd1.partitionBy(new
     | org.apache.spark.RangePartitioner(10, rdd1))
rdd3: org.apache.spark.rdd.RDD[(Int, Int)] = ShuffledRDD[49] at partitionBy at <console>:25

scala> rdd3.glom.collect.foreach(x=>println(x.toBuffer))
ArrayBuffer((1,1), (2,1), (3,1), (4,1), (5,1), (6,1), (7,1), (8,1), (9,1), (10,1))
ArrayBuffer((11,1), (12,1), (13,1), (14,1), (15,1), (16,1), (17,1), (18,1), (19,1), (20,1))
ArrayBuffer((21,1), (22,1), (23,1), (24,1), (25,1), (26,1), (27,1), (28,1), (29,1), (30,1))
ArrayBuffer((34,1), (35,1), (36,1), (37,1), (38,1), (39,1), (40,1), (31,1), (32,1), (33,1))
ArrayBuffer((41,1), (42,1), (43,1), (44,1), (45,1), (46,1), (47,1), (48,1), (49,1), (50,1))
ArrayBuffer((51,1), (52,1), (53,1), (54,1), (55,1), (56,1), (57,1), (58,1), (59,1), (60,1))
ArrayBuffer((67,1), (68,1), (69,1), (70,1), (61,1), (62,1), (63,1), (64,1), (65,1), (66,1))
ArrayBuffer((71,1), (72,1), (73,1), (74,1), (75,1), (76,1), (77,1), (78,1), (79,1), (80,1))
ArrayBuffer((81,1), (82,1), (83,1), (84,1), (85,1), (86,1), (87,1), (88,1), (89,1), (90,1))
ArrayBuffer((91,1), (92,1), (93,1), (94,1), (95,1), (96,1), (97,1), (98,1), (99,1), (100,1))

三、spark算子设置HashPartitioner值

### --- Spark的很多算子都可以设置 HashPartitioner 的值：

~~~     # 源码提取说明：PairRDDFunctions.scala
~~~     # 301行
  /**
   * Merge the values for each key using an associative and commutative reduce function. This will
   * also perform the merging locally on each mapper before sending results to a reducer, similarly
   * to a "combiner" in MapReduce.
   */
  def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDD[(K, V)] = self.withScope {
    combineByKeyWithClassTag[V]((v: V) => v, func, func, partitioner)
  }

  /**
   * Merge the values for each key using an associative and commutative reduce function. This will
   * also perform the merging locally on each mapper before sending results to a reducer, similarly
   * to a "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
   */
  def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = self.withScope {
    reduceByKey(new HashPartitioner(numPartitions), func)
  }

四、RangePartitioner

### --- RangePartitioner

~~~     RangePartitioner：简单的说就是将一定范围内的数映射到某一个分区内。
~~~     在实现中，分界的算法尤为重要，用到了水塘抽样算法。sortByKey会使用RangePartitioner。

### --- 现在的问题：

~~~     在执行分区之前其实并不知道数据的分布情况，如果想知道数据分区就需要对数据进行采样；
~~~     Spark中RangePartitioner在对数据采样的过程中使用了水塘采样算法。
~~~     # 水塘采样：
~~~     从包含n个项目的集合S中选取k个样本，其中n为一很大或未知的数量，
~~~     尤其适用于不能把所有n个项目都存放到主内存的情况；
~~~     在采样的过程中执行了collect()操作，引发了Action操作。
~~~     自定义分区器：Spark允许用户通过自定义的Partitioner对象，灵活的来控制RDD的分区方式。

五、编程代码实验

### --- 实现自定义分区器按以下规则分区：

~~~     分区0 < 100
~~~     100 <= 分区1 < 200
~~~     200 <= 分区2 < 300
~~~     300 <= 分区3 < 400
~~~     ... ...
~~~     900 <= 分区9 < 1000

### --- 编程代码实现

package cn.yanqi.sparkcore

import org.apache.spark.rdd.RDD
import org.apache.spark.{Partitioner, SparkConf, SparkContext}

import scala.collection.immutable

class MyPartitioner(n: Int) extends Partitioner{
  // 有多少个分区数
  override def numPartitions: Int = n

  // 给定key，如果去分区
  override def getPartition(key: Any): Int = {
    val k = key.toString.toInt
    k / 100
  }
}

object UserDefinedPartitioner {
  def main(args: Array[String]): Unit = {
    // 创建SparkContext
    val conf = new SparkConf().setAppName(this.getClass.getCanonicalName.init).setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("WARN")

    // 业务逻辑
    val random = scala.util.Random
    val arr: immutable.IndexedSeq[Int] = (1 to 100).map(idx => random.nextInt(1000))
    val rdd1: RDD[(Int, Int)] = sc.makeRDD(arr).map((_, 1))
    rdd1.glom.collect.foreach(x => println(x.toBuffer))

    println("************************************************************************")
    val rdd2 = rdd1.partitionBy(new MyPartitioner(11))
    rdd2.glom.collect.foreach(x => println(x.toBuffer))

    // 关闭SparkContext
    sc.stop()
  }
}

### --- 编译打印

D:\JAVA\jdk1.8.0_231\bin\java.exe "-javaagent:D:\IntelliJIDEA\IntelliJ IDEA 2019.3.3\lib\idea_rt.jar=64715:D:\IntelliJIDEA\IntelliJ IDEA 2019.3.3\bin" -Dfile.encoding=UTF-8 -classpath D:\JAVA\jdk1.8.0_231\jre\lib\charsets.jar;D:\JAVA\jdk1.8.0_231\jre\lib\deploy.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\access-bridge-64.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\cldrdata.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\dnsns.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\jaccess.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\jfxrt.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\localedata.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\nashorn.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\sunec.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\sunjce_provider.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\sunmscapi.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\sunpkcs11.jar;D:\JAVA\jdk1.8.0_231\jre\lib\ext\zipfs.jar;D:\JAVA\jdk1.8.0_231\jre\lib\javaws.jar;D:\JAVA\jdk1.8.0_231\jre\lib\jce.jar;D:\JAVA\jdk1.8.0_231\jre\lib\jfr.jar;D:\JAVA\jdk1.8.0_231\jre\lib\jfxswt.jar;D:\JAVA\jdk1.8.0_231\jre\lib\jsse.jar;D:\JAVA\jdk1.8.0_231\jre\lib\management-agent.jar;D:\JAVA\jdk1.8.0_231\jre\lib\plugin.jar;D:\JAVA\jdk1.8.0_231\jre\lib\resources.jar;D:\JAVA\jdk1.8.0_231\jre\lib\rt.jar;E:\NO.Z.80000.Hadoop.spark\SparkBigData\target\classes;C:\Users\Administrator\.m2\repository\org\scala-lang\scala-library\2.12.10\scala-library-2.12.10.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-core_2.12\2.4.5\spark-core_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\com\thoughtworks\paranamer\paranamer\2.8\paranamer-2.8.jar;C:\Users\Administrator\.m2\repository\org\apache\avro\avro\1.8.2\avro-1.8.2.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-core-asl\1.9.13\jackson-core-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-compress\1.8.1\commons-compress-1.8.1.jar;C:\Users\Administrator\.m2\repository\org\tukaani\xz\1.5\xz-1.5.jar;C:\Users\Administrator\.m2\repository\org\apache\avro\avro-mapred\1.8.2\avro-mapred-1.8.2-hadoop2.jar;C:\Users\Administrator\.m2\repository\org\apache\avro\avro-ipc\1.8.2\avro-ipc-1.8.2.jar;C:\Users\Administrator\.m2\repository\com\twitter\chill_2.12\0.9.3\chill_2.12-0.9.3.jar;C:\Users\Administrator\.m2\repository\com\esotericsoftware\kryo-shaded\4.0.2\kryo-shaded-4.0.2.jar;C:\Users\Administrator\.m2\repository\com\esotericsoftware\minlog\1.3.0\minlog-1.3.0.jar;C:\Users\Administrator\.m2\repository\org\objenesis\objenesis\2.5.1\objenesis-2.5.1.jar;C:\Users\Administrator\.m2\repository\com\twitter\chill-java\0.9.3\chill-java-0.9.3.jar;C:\Users\Administrator\.m2\repository\org\apache\xbean\xbean-asm6-shaded\4.8\xbean-asm6-shaded-4.8.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-client\2.6.5\hadoop-client-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-common\2.6.5\hadoop-common-2.6.5.jar;C:\Users\Administrator\.m2\repository\xmlenc\xmlenc\0.52\xmlenc-0.52.jar;C:\Users\Administrator\.m2\repository\commons-collections\commons-collections\3.2.2\commons-collections-3.2.2.jar;C:\Users\Administrator\.m2\repository\commons-configuration\commons-configuration\1.6\commons-configuration-1.6.jar;C:\Users\Administrator\.m2\repository\commons-digester\commons-digester\1.8\commons-digester-1.8.jar;C:\Users\Administrator\.m2\repository\commons-beanutils\commons-beanutils\1.7.0\commons-beanutils-1.7.0.jar;C:\Users\Administrator\.m2\repository\com\google\code\gson\gson\2.2.4\gson-2.2.4.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-auth\2.6.5\hadoop-auth-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-kerberos-codec\2.0.0-M15\apacheds-kerberos-codec-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-i18n\2.0.0-M15\apacheds-i18n-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-asn1-api\1.0.0-M20\api-asn1-api-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-util\1.0.0-M20\api-util-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-client\2.6.0\curator-client-2.6.0.jar;C:\Users\Administrator\.m2\repository\org\htrace\htrace-core\3.0.4\htrace-core-3.0.4.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-hdfs\2.6.5\hadoop-hdfs-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\mortbay\jetty\jetty-util\6.1.26\jetty-util-6.1.26.jar;C:\Users\Administrator\.m2\repository\xerces\xercesImpl\2.9.1\xercesImpl-2.9.1.jar;C:\Users\Administrator\.m2\repository\xml-apis\xml-apis\1.3.04\xml-apis-1.3.04.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-app\2.6.5\hadoop-mapreduce-client-app-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-common\2.6.5\hadoop-mapreduce-client-common-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-client\2.6.5\hadoop-yarn-client-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-server-common\2.6.5\hadoop-yarn-server-common-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-shuffle\2.6.5\hadoop-mapreduce-client-shuffle-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-api\2.6.5\hadoop-yarn-api-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-core\2.6.5\hadoop-mapreduce-client-core-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-common\2.6.5\hadoop-yarn-common-2.6.5.jar;C:\Users\Administrator\.m2\repository\javax\xml\bind\jaxb-api\2.2.2\jaxb-api-2.2.2.jar;C:\Users\Administrator\.m2\repository\javax\xml\stream\stax-api\1.0-2\stax-api-1.0-2.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-jaxrs\1.9.13\jackson-jaxrs-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-xc\1.9.13\jackson-xc-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-jobclient\2.6.5\hadoop-mapreduce-client-jobclient-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-annotations\2.6.5\hadoop-annotations-2.6.5.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-launcher_2.12\2.4.5\spark-launcher_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-kvstore_2.12\2.4.5\spark-kvstore_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\fusesource\leveldbjni\leveldbjni-all\1.8\leveldbjni-all-1.8.jar;C:\Users\Administrator\.m2\repository\com\fasterxml\jackson\core\jackson-core\2.6.7\jackson-core-2.6.7.jar;C:\Users\Administrator\.m2\repository\com\fasterxml\jackson\core\jackson-annotations\2.6.7\jackson-annotations-2.6.7.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-network-common_2.12\2.4.5\spark-network-common_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-network-shuffle_2.12\2.4.5\spark-network-shuffle_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-unsafe_2.12\2.4.5\spark-unsafe_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\javax\activation\activation\1.1.1\activation-1.1.1.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-recipes\2.6.0\curator-recipes-2.6.0.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-framework\2.6.0\curator-framework-2.6.0.jar;C:\Users\Administrator\.m2\repository\com\google\guava\guava\16.0.1\guava-16.0.1.jar;C:\Users\Administrator\.m2\repository\org\apache\zookeeper\zookeeper\3.4.6\zookeeper-3.4.6.jar;C:\Users\Administrator\.m2\repository\javax\servlet\javax.servlet-api\3.1.0\javax.servlet-api-3.1.0.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-lang3\3.5\commons-lang3-3.5.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-math3\3.4.1\commons-math3-3.4.1.jar;C:\Users\Administrator\.m2\repository\com\google\code\findbugs\jsr305\1.3.9\jsr305-1.3.9.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-api\1.7.16\slf4j-api-1.7.16.jar;C:\Users\Administrator\.m2\repository\org\slf4j\jul-to-slf4j\1.7.16\jul-to-slf4j-1.7.16.jar;C:\Users\Administrator\.m2\repository\org\slf4j\jcl-over-slf4j\1.7.16\jcl-over-slf4j-1.7.16.jar;C:\Users\Administrator\.m2\repository\log4j\log4j\1.2.17\log4j-1.2.17.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-log4j12\1.7.16\slf4j-log4j12-1.7.16.jar;C:\Users\Administrator\.m2\repository\com\ning\compress-lzf\1.0.3\compress-lzf-1.0.3.jar;C:\Users\Administrator\.m2\repository\org\xerial\snappy\snappy-java\1.1.7.3\snappy-java-1.1.7.3.jar;C:\Users\Administrator\.m2\repository\org\lz4\lz4-java\1.4.0\lz4-java-1.4.0.jar;C:\Users\Administrator\.m2\repository\com\github\luben\zstd-jni\1.3.2-2\zstd-jni-1.3.2-2.jar;C:\Users\Administrator\.m2\repository\org\roaringbitmap\RoaringBitmap\0.7.45\RoaringBitmap-0.7.45.jar;C:\Users\Administrator\.m2\repository\org\roaringbitmap\shims\0.7.45\shims-0.7.45.jar;C:\Users\Administrator\.m2\repository\commons-net\commons-net\3.1\commons-net-3.1.jar;C:\Users\Administrator\.m2\repository\org\json4s\json4s-jackson_2.12\3.5.3\json4s-jackson_2.12-3.5.3.jar;C:\Users\Administrator\.m2\repository\org\json4s\json4s-core_2.12\3.5.3\json4s-core_2.12-3.5.3.jar;C:\Users\Administrator\.m2\repository\org\json4s\json4s-ast_2.12\3.5.3\json4s-ast_2.12-3.5.3.jar;C:\Users\Administrator\.m2\repository\org\json4s\json4s-scalap_2.12\3.5.3\json4s-scalap_2.12-3.5.3.jar;C:\Users\Administrator\.m2\repository\org\scala-lang\modules\scala-xml_2.12\1.0.6\scala-xml_2.12-1.0.6.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\core\jersey-client\2.22.2\jersey-client-2.22.2.jar;C:\Users\Administrator\.m2\repository\javax\ws\rs\javax.ws.rs-api\2.0.1\javax.ws.rs-api-2.0.1.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\hk2-api\2.4.0-b34\hk2-api-2.4.0-b34.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\hk2-utils\2.4.0-b34\hk2-utils-2.4.0-b34.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\external\aopalliance-repackaged\2.4.0-b34\aopalliance-repackaged-2.4.0-b34.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\external\javax.inject\2.4.0-b34\javax.inject-2.4.0-b34.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\hk2-locator\2.4.0-b34\hk2-locator-2.4.0-b34.jar;C:\Users\Administrator\.m2\repository\org\javassist\javassist\3.18.1-GA\javassist-3.18.1-GA.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\core\jersey-common\2.22.2\jersey-common-2.22.2.jar;C:\Users\Administrator\.m2\repository\javax\annotation\javax.annotation-api\1.2\javax.annotation-api-1.2.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\bundles\repackaged\jersey-guava\2.22.2\jersey-guava-2.22.2.jar;C:\Users\Administrator\.m2\repository\org\glassfish\hk2\osgi-resource-locator\1.0.1\osgi-resource-locator-1.0.1.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\core\jersey-server\2.22.2\jersey-server-2.22.2.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\media\jersey-media-jaxb\2.22.2\jersey-media-jaxb-2.22.2.jar;C:\Users\Administrator\.m2\repository\javax\validation\validation-api\1.1.0.Final\validation-api-1.1.0.Final.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\containers\jersey-container-servlet\2.22.2\jersey-container-servlet-2.22.2.jar;C:\Users\Administrator\.m2\repository\org\glassfish\jersey\containers\jersey-container-servlet-core\2.22.2\jersey-container-servlet-core-2.22.2.jar;C:\Users\Administrator\.m2\repository\io\netty\netty-all\4.1.42.Final\netty-all-4.1.42.Final.jar;C:\Users\Administrator\.m2\repository\io\netty\netty\3.9.9.Final\netty-3.9.9.Final.jar;C:\Users\Administrator\.m2\repository\com\clearspring\analytics\stream\2.7.0\stream-2.7.0.jar;C:\Users\Administrator\.m2\repository\io\dropwizard\metrics\metrics-core\3.1.5\metrics-core-3.1.5.jar;C:\Users\Administrator\.m2\repository\io\dropwizard\metrics\metrics-jvm\3.1.5\metrics-jvm-3.1.5.jar;C:\Users\Administrator\.m2\repository\io\dropwizard\metrics\metrics-json\3.1.5\metrics-json-3.1.5.jar;C:\Users\Administrator\.m2\repository\io\dropwizard\metrics\metrics-graphite\3.1.5\metrics-graphite-3.1.5.jar;C:\Users\Administrator\.m2\repository\com\fasterxml\jackson\core\jackson-databind\2.6.7.3\jackson-databind-2.6.7.3.jar;C:\Users\Administrator\.m2\repository\com\fasterxml\jackson\module\jackson-module-scala_2.12\2.6.7.1\jackson-module-scala_2.12-2.6.7.1.jar;C:\Users\Administrator\.m2\repository\org\scala-lang\scala-reflect\2.12.1\scala-reflect-2.12.1.jar;C:\Users\Administrator\.m2\repository\com\fasterxml\jackson\module\jackson-module-paranamer\2.7.9\jackson-module-paranamer-2.7.9.jar;C:\Users\Administrator\.m2\repository\org\apache\ivy\ivy\2.4.0\ivy-2.4.0.jar;C:\Users\Administrator\.m2\repository\oro\oro\2.0.8\oro-2.0.8.jar;C:\Users\Administrator\.m2\repository\net\razorvine\pyrolite\4.13\pyrolite-4.13.jar;C:\Users\Administrator\.m2\repository\net\sf\py4j\py4j\0.10.7\py4j-0.10.7.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-tags_2.12\2.4.5\spark-tags_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-crypto\1.0.0\commons-crypto-1.0.0.jar;C:\Users\Administrator\.m2\repository\org\spark-project\spark\unused\1.0.0\unused-1.0.0.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-sql_2.12\2.4.5\spark-sql_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\com\univocity\univocity-parsers\2.7.3\univocity-parsers-2.7.3.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-sketch_2.12\2.4.5\spark-sketch_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-catalyst_2.12\2.4.5\spark-catalyst_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\org\scala-lang\modules\scala-parser-combinators_2.12\1.1.0\scala-parser-combinators_2.12-1.1.0.jar;C:\Users\Administrator\.m2\repository\org\codehaus\janino\janino\3.0.9\janino-3.0.9.jar;C:\Users\Administrator\.m2\repository\org\codehaus\janino\commons-compiler\3.0.9\commons-compiler-3.0.9.jar;C:\Users\Administrator\.m2\repository\org\antlr\antlr4-runtime\4.7\antlr4-runtime-4.7.jar;C:\Users\Administrator\.m2\repository\org\apache\orc\orc-core\1.5.5\orc-core-1.5.5-nohive.jar;C:\Users\Administrator\.m2\repository\org\apache\orc\orc-shims\1.5.5\orc-shims-1.5.5.jar;C:\Users\Administrator\.m2\repository\com\google\protobuf\protobuf-java\2.5.0\protobuf-java-2.5.0.jar;C:\Users\Administrator\.m2\repository\commons-lang\commons-lang\2.6\commons-lang-2.6.jar;C:\Users\Administrator\.m2\repository\io\airlift\aircompressor\0.10\aircompressor-0.10.jar;C:\Users\Administrator\.m2\repository\org\apache\orc\orc-mapreduce\1.5.5\orc-mapreduce-1.5.5-nohive.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-column\1.10.1\parquet-column-1.10.1.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-common\1.10.1\parquet-common-1.10.1.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-encoding\1.10.1\parquet-encoding-1.10.1.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-hadoop\1.10.1\parquet-hadoop-1.10.1.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-format\2.4.0\parquet-format-2.4.0.jar;C:\Users\Administrator\.m2\repository\org\apache\parquet\parquet-jackson\1.10.1\parquet-jackson-1.10.1.jar;C:\Users\Administrator\.m2\repository\org\apache\arrow\arrow-vector\0.10.0\arrow-vector-0.10.0.jar;C:\Users\Administrator\.m2\repository\org\apache\arrow\arrow-format\0.10.0\arrow-format-0.10.0.jar;C:\Users\Administrator\.m2\repository\org\apache\arrow\arrow-memory\0.10.0\arrow-memory-0.10.0.jar;C:\Users\Administrator\.m2\repository\com\carrotsearch\hppc\0.7.2\hppc-0.7.2.jar;C:\Users\Administrator\.m2\repository\com\vlkan\flatbuffers\1.2.0-3f79e055\flatbuffers-1.2.0-3f79e055.jar;C:\Users\Administrator\.m2\repository\joda-time\joda-time\2.9.7\joda-time-2.9.7.jar;C:\Users\Administrator\.m2\repository\mysql\mysql-connector-java\5.1.44\mysql-connector-java-5.1.44.jar;C:\Users\Administrator\.m2\repository\org\apache\spark\spark-hive_2.12\2.4.5\spark-hive_2.12-2.4.5.jar;C:\Users\Administrator\.m2\repository\com\twitter\parquet-hadoop-bundle\1.6.0\parquet-hadoop-bundle-1.6.0.jar;C:\Users\Administrator\.m2\repository\org\spark-project\hive\hive-exec\1.2.1.spark2\hive-exec-1.2.1.spark2.jar;C:\Users\Administrator\.m2\repository\commons-io\commons-io\2.4\commons-io-2.4.jar;C:\Users\Administrator\.m2\repository\javolution\javolution\5.5.1\javolution-5.5.1.jar;C:\Users\Administrator\.m2\repository\log4j\apache-log4j-extras\1.2.17\apache-log4j-extras-1.2.17.jar;C:\Users\Administrator\.m2\repository\org\antlr\antlr-runtime\3.4\antlr-runtime-3.4.jar;C:\Users\Administrator\.m2\repository\org\antlr\stringtemplate\3.2.1\stringtemplate-3.2.1.jar;C:\Users\Administrator\.m2\repository\antlr\antlr\2.7.7\antlr-2.7.7.jar;C:\Users\Administrator\.m2\repository\org\antlr\ST4\4.0.4\ST4-4.0.4.jar;C:\Users\Administrator\.m2\repository\com\googlecode\javaewah\JavaEWAH\0.3.2\JavaEWAH-0.3.2.jar;C:\Users\Administrator\.m2\repository\org\iq80\snappy\snappy\0.2\snappy-0.2.jar;C:\Users\Administrator\.m2\repository\stax\stax-api\1.0.1\stax-api-1.0.1.jar;C:\Users\Administrator\.m2\repository\net\sf\opencsv\opencsv\2.3\opencsv-2.3.jar;C:\Users\Administrator\.m2\repository\org\spark-project\hive\hive-metastore\1.2.1.spark2\hive-metastore-1.2.1.spark2.jar;C:\Users\Administrator\.m2\repository\com\jolbox\bonecp\0.8.0.RELEASE\bonecp-0.8.0.RELEASE.jar;C:\Users\Administrator\.m2\repository\commons-cli\commons-cli\1.2\commons-cli-1.2.jar;C:\Users\Administrator\.m2\repository\commons-logging\commons-logging\1.1.3\commons-logging-1.1.3.jar;C:\Users\Administrator\.m2\repository\org\datanucleus\datanucleus-api-jdo\3.2.6\datanucleus-api-jdo-3.2.6.jar;C:\Users\Administrator\.m2\repository\org\datanucleus\datanucleus-rdbms\3.2.9\datanucleus-rdbms-3.2.9.jar;C:\Users\Administrator\.m2\repository\commons-pool\commons-pool\1.5.4\commons-pool-1.5.4.jar;C:\Users\Administrator\.m2\repository\commons-dbcp\commons-dbcp\1.4\commons-dbcp-1.4.jar;C:\Users\Administrator\.m2\repository\javax\jdo\jdo-api\3.0.1\jdo-api-3.0.1.jar;C:\Users\Administrator\.m2\repository\javax\transaction\jta\1.1\jta-1.1.jar;C:\Users\Administrator\.m2\repository\commons-httpclient\commons-httpclient\3.1\commons-httpclient-3.1.jar;C:\Users\Administrator\.m2\repository\org\apache\calcite\calcite-avatica\1.2.0-incubating\calcite-avatica-1.2.0-incubating.jar;C:\Users\Administrator\.m2\repository\org\apache\calcite\calcite-core\1.2.0-incubating\calcite-core-1.2.0-incubating.jar;C:\Users\Administrator\.m2\repository\org\apache\calcite\calcite-linq4j\1.2.0-incubating\calcite-linq4j-1.2.0-incubating.jar;C:\Users\Administrator\.m2\repository\net\hydromatic\eigenbase-properties\1.1.5\eigenbase-properties-1.1.5.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpclient\4.5.6\httpclient-4.5.6.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpcore\4.4.10\httpcore-4.4.10.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-mapper-asl\1.9.13\jackson-mapper-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\commons-codec\commons-codec\1.10\commons-codec-1.10.jar;C:\Users\Administrator\.m2\repository\org\jodd\jodd-core\3.5.2\jodd-core-3.5.2.jar;C:\Users\Administrator\.m2\repository\org\datanucleus\datanucleus-core\3.2.10\datanucleus-core-3.2.10.jar;C:\Users\Administrator\.m2\repository\org\apache\thrift\libthrift\0.9.3\libthrift-0.9.3.jar;C:\Users\Administrator\.m2\repository\org\apache\thrift\libfb303\0.9.3\libfb303-0.9.3.jar;C:\Users\Administrator\.m2\repository\org\apache\derby\derby\10.12.1.1\derby-10.12.1.1.jar cn.yanqi.sparkcore.UserDefinedPartitioner

ArrayBuffer((451,1), (594,1), (201,1), (643,1), (673,1), (625,1), (7,1), (721,1), (237,1), (874,1), (607,1), (705,1), (984,1), (912,1), (714,1), (342,1), (557,1), (344,1), (90,1), (882,1), (626,1), (561,1), (38,1), (62,1), (746,1))
ArrayBuffer((304,1), (134,1), (398,1), (185,1), (672,1), (800,1), (363,1), (619,1), (807,1), (445,1), (395,1), (673,1), (108,1), (860,1), (651,1), (753,1), (589,1), (328,1), (508,1), (273,1), (869,1), (688,1), (323,1), (663,1), (713,1))
ArrayBuffer((115,1), (947,1), (512,1), (603,1), (757,1), (941,1), (499,1), (248,1), (755,1), (871,1), (193,1), (981,1), (247,1), (435,1), (148,1), (247,1), (552,1), (350,1), (145,1), (159,1), (354,1), (313,1), (211,1), (291,1), (85,1))
ArrayBuffer((44,1), (285,1), (802,1), (828,1), (70,1), (204,1), (264,1), (805,1), (41,1), (655,1), (815,1), (792,1), (187,1), (140,1), (847,1), (197,1), (895,1), (536,1), (308,1), (743,1), (42,1), (610,1), (821,1), (967,1), (889,1))
************************************************************************
ArrayBuffer((7,1), (90,1), (38,1), (62,1), (85,1), (44,1), (70,1), (41,1), (42,1))
ArrayBuffer((134,1), (185,1), (108,1), (115,1), (193,1), (148,1), (145,1), (159,1), (187,1), (140,1), (197,1))
ArrayBuffer((201,1), (237,1), (273,1), (248,1), (247,1), (247,1), (211,1), (291,1), (285,1), (204,1), (264,1))
ArrayBuffer((342,1), (344,1), (304,1), (398,1), (363,1), (395,1), (328,1), (323,1), (350,1), (354,1), (313,1), (308,1))
ArrayBuffer((451,1), (445,1), (499,1), (435,1))
ArrayBuffer((594,1), (557,1), (561,1), (589,1), (508,1), (512,1), (552,1), (536,1))
ArrayBuffer((643,1), (673,1), (625,1), (607,1), (626,1), (672,1), (619,1), (673,1), (651,1), (688,1), (663,1), (603,1), (655,1), (610,1))
ArrayBuffer((721,1), (705,1), (714,1), (746,1), (753,1), (713,1), (757,1), (755,1), (792,1), (743,1))
ArrayBuffer((874,1), (882,1), (800,1), (807,1), (860,1), (869,1), (871,1), (802,1), (828,1), (805,1), (815,1), (847,1), (895,1), (821,1), (889,1))
ArrayBuffer((984,1), (912,1), (947,1), (941,1), (981,1), (967,1))
ArrayBuffer()

Process finished with exit code 0