This repository has been archived by the owner on Feb 16, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 198
/
MQTTStreamWordCount.scala
73 lines (60 loc) · 2.37 KB
/
MQTTStreamWordCount.scala
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
/*
* 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.bahir.examples.sql.streaming.mqtt
import java.sql.Timestamp
import org.apache.spark.sql.SparkSession
/**
* Counts words in UTF8 encoded, '\n' delimited text received from MQTT Server.
*
* Usage: MQTTStreamWordCount <brokerUrl> <topic>
* <brokerUrl> and <topic> describe the MQTT server that Structured Streaming
* would connect to receive data.
*
* To run this on your local machine, a MQTT Server should be up and running.
*
*/
object MQTTStreamWordCount {
def main(args: Array[String]) {
if (args.length < 2) {
System.err.println("Usage: MQTTStreamWordCount <brokerUrl> <topic>") // scalastyle:off println
System.exit(1)
}
val brokerUrl = args(0)
val topic = args(1)
val spark = SparkSession
.builder
.appName("MQTTStreamWordCount")
.master("local[4]")
.getOrCreate()
import spark.implicits._
// Create DataFrame representing the stream of input lines from connection to mqtt server
val lines = spark.readStream
.format("org.apache.bahir.sql.streaming.mqtt.MQTTStreamSourceProvider")
.option("topic", topic).option("persistence", "memory")
.load(brokerUrl).selectExpr("CAST(payload AS STRING)").as[String]
// Split the lines into words
val words = lines.flatMap(_.split(" "))
// Generate running word count
val wordCounts = words.groupBy("value").count()
// Start running the query that prints the running counts to the console
val query = wordCounts.writeStream
.outputMode("complete")
.format("console")
.start()
query.awaitTermination()
}
}