aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/java/org/apache/spark/examples/sql/hive/JavaSparkHiveExample.java
blob: 76dd160d5568b20639b81e6ba7e7e28fb634240a (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
/*
 * 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.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 = "file:" + System.getProperty("user.dir") + "spark-warehouse";
    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)");
    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 DaraFrames are of type Row, which lets you to access each column by ordinal.
    Dataset<String> stringsDS = sqlDF.map(new MapFunction<Row, String>() {
      @Override
      public String call(Row row) throws Exception {
        return "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();
  }
}