spark JavaSparkHiveExample 源码

spark JavaSparkHiveExample 代码

文件路径：/examples/src/main/java/org/apache/spark/examples/sql/hive/JavaSparkHiveExample.java

/*
 * 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.examples.sql.hive;

// $example on:spark_hive$
import java.io.File;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;

import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
// $example off:spark_hive$

public class JavaSparkHiveExample {

  // $example on:spark_hive$
  public static class Record implements Serializable {
    private int key;
    private String value;

    public int getKey() {
      return key;
    }

    public void setKey(int key) {
      this.key = key;
    }

    public String getValue() {
      return value;
    }

    public void setValue(String value) {
      this.value = value;
    }
  }
  // $example off:spark_hive$

  public static void main(String[] args) {
    // $example on:spark_hive$
    // warehouseLocation points to the default location for managed databases and tables
    String warehouseLocation = new File("spark-warehouse").getAbsolutePath();
    SparkSession spark = SparkSession
      .builder()
      .appName("Java Spark Hive Example")
      .config("spark.sql.warehouse.dir", warehouseLocation)
      .enableHiveSupport()
      .getOrCreate();

    spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive");
    spark.sql("LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src");

    // Queries are expressed in HiveQL
    spark.sql("SELECT * FROM src").show();
    // +---+-------+
    // |key|  value|
    // +---+-------+
    // |238|val_238|
    // | 86| val_86|
    // |311|val_311|
    // ...

    // Aggregation queries are also supported.
    spark.sql("SELECT COUNT(*) FROM src").show();
    // +--------+
    // |count(1)|
    // +--------+
    // |    500 |
    // +--------+

    // The results of SQL queries are themselves DataFrames and support all normal functions.
    Dataset<Row> sqlDF = spark.sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key");

    // The items in DataFrames are of type Row, which lets you to access each column by ordinal.
    Dataset<String> stringsDS = sqlDF.map(
        (MapFunction<Row, String>) row -> "Key: " + row.get(0) + ", Value: " + row.get(1),
        Encoders.STRING());
    stringsDS.show();
    // +--------------------+
    // |               value|
    // +--------------------+
    // |Key: 0, Value: val_0|
    // |Key: 0, Value: val_0|
    // |Key: 0, Value: val_0|
    // ...

    // You can also use DataFrames to create temporary views within a SparkSession.
    List<Record> records = new ArrayList<>();
    for (int key = 1; key < 100; key++) {
      Record record = new Record();
      record.setKey(key);
      record.setValue("val_" + key);
      records.add(record);
    }
    Dataset<Row> recordsDF = spark.createDataFrame(records, Record.class);
    recordsDF.createOrReplaceTempView("records");

    // Queries can then join DataFrames data with data stored in Hive.
    spark.sql("SELECT * FROM records r JOIN src s ON r.key = s.key").show();
    // +---+------+---+------+
    // |key| value|key| value|
    // +---+------+---+------+
    // |  2| val_2|  2| val_2|
    // |  2| val_2|  2| val_2|
    // |  4| val_4|  4| val_4|
    // ...
    // $example off:spark_hive$

    spark.stop();
  }
}

相关信息

spark 源码目录

相关文章

spark ArrayWrappers 源码

spark InMemoryStore 源码

spark KVIndex 源码

spark KVStore 源码

spark KVStoreIterator 源码

spark KVStoreSerializer 源码

spark KVStoreView 源码

spark KVTypeInfo 源码

spark LevelDB 源码

spark LevelDBIterator 源码