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
|
/*
* 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.streaming;
import java.util.Arrays;
import java.util.Iterator;
import java.util.regex.Pattern;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.VoidFunction2;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.api.java.StorageLevels;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.Time;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
/**
* Use DataFrames and SQL to count words in UTF8 encoded, '\n' delimited text received from the
* network every second.
*
* Usage: JavaSqlNetworkWordCount <hostname> <port>
* <hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
*
* To run this on your local machine, you need to first run a Netcat server
* `$ nc -lk 9999`
* and then run the example
* `$ bin/run-example org.apache.spark.examples.streaming.JavaSqlNetworkWordCount localhost 9999`
*/
public final class JavaSqlNetworkWordCount {
private static final Pattern SPACE = Pattern.compile(" ");
public static void main(String[] args) throws Exception {
if (args.length < 2) {
System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
System.exit(1);
}
StreamingExamples.setStreamingLogLevels();
// Create the context with a 1 second batch size
SparkConf sparkConf = new SparkConf().setAppName("JavaSqlNetworkWordCount");
JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));
// Create a JavaReceiverInputDStream on target ip:port and count the
// words in input stream of \n delimited text (eg. generated by 'nc')
// Note that no duplication in storage level only for running locally.
// Replication necessary in distributed scenario for fault tolerance.
JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterator<String> call(String x) {
return Arrays.asList(SPACE.split(x)).iterator();
}
});
// Convert RDDs of the words DStream to DataFrame and run SQL query
words.foreachRDD(new VoidFunction2<JavaRDD<String>, Time>() {
@Override
public void call(JavaRDD<String> rdd, Time time) {
SparkSession spark = JavaSparkSessionSingleton.getInstance(rdd.context().getConf());
// Convert JavaRDD[String] to JavaRDD[bean class] to DataFrame
JavaRDD<JavaRecord> rowRDD = rdd.map(new Function<String, JavaRecord>() {
@Override
public JavaRecord call(String word) {
JavaRecord record = new JavaRecord();
record.setWord(word);
return record;
}
});
Dataset<Row> wordsDataFrame = spark.createDataFrame(rowRDD, JavaRecord.class);
// Creates a temporary view using the DataFrame
wordsDataFrame.createOrReplaceTempView("words");
// Do word count on table using SQL and print it
Dataset<Row> wordCountsDataFrame =
spark.sql("select word, count(*) as total from words group by word");
System.out.println("========= " + time + "=========");
wordCountsDataFrame.show();
}
});
ssc.start();
ssc.awaitTermination();
}
}
/** Lazily instantiated singleton instance of SparkSession */
class JavaSparkSessionSingleton {
private static transient SparkSession instance = null;
public static SparkSession getInstance(SparkConf sparkConf) {
if (instance == null) {
instance = SparkSession
.builder()
.config(sparkConf)
.getOrCreate();
}
return instance;
}
}
|
