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
|
#
# 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.
#
"""
A sample wordcount with MqttStream stream
Usage: mqtt_wordcount.py <broker url> <topic>
To run this in your local machine, you need to setup a MQTT broker and publisher first,
Mosquitto is one of the open source MQTT Brokers, see
http://mosquitto.org/
Eclipse paho project provides number of clients and utilities for working with MQTT, see
http://www.eclipse.org/paho/#getting-started
and then run the example
`$ bin/spark-submit --jars \
external/mqtt-assembly/target/scala-*/spark-streaming-mqtt-assembly-*.jar \
examples/src/main/python/streaming/mqtt_wordcount.py \
tcp://localhost:1883 foo`
"""
import sys
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.streaming.mqtt import MQTTUtils
if __name__ == "__main__":
if len(sys.argv) != 3:
print >> sys.stderr, "Usage: mqtt_wordcount.py <broker url> <topic>"
exit(-1)
sc = SparkContext(appName="PythonStreamingMQTTWordCount")
ssc = StreamingContext(sc, 1)
brokerUrl = sys.argv[1]
topic = sys.argv[2]
lines = MQTTUtils.createStream(ssc, brokerUrl, topic)
counts = lines.flatMap(lambda line: line.split(" ")) \
.map(lambda word: (word, 1)) \
.reduceByKey(lambda a, b: a+b)
counts.pprint()
ssc.start()
ssc.awaitTermination()
|