blob: 32d63c52c9191a20de865e944eaf118ee6448b94 (
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
|
#
# 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.
#
"""
Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
Usage: structured_network_wordcount.py <hostname> <port>
<hostname> and <port> describe the TCP server that Structured 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/spark-submit examples/src/main/python/sql/streaming/structured_network_wordcount.py
localhost 9999`
"""
from __future__ import print_function
import sys
from pyspark.sql import SparkSession
from pyspark.sql.functions import explode
from pyspark.sql.functions import split
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: structured_network_wordcount.py <hostname> <port>", file=sys.stderr)
exit(-1)
host = sys.argv[1]
port = int(sys.argv[2])
spark = SparkSession\
.builder\
.appName("StructuredNetworkWordCount")\
.getOrCreate()
# Create DataFrame representing the stream of input lines from connection to host:port
lines = spark\
.readStream\
.format('socket')\
.option('host', host)\
.option('port', port)\
.load()
# Split the lines into words
words = lines.select(
explode(
split(lines.value, ' ')
).alias('word')
)
# Generate running word count
wordCounts = words.groupBy('word').count()
# Start running the query that prints the running counts to the console
query = wordCounts\
.writeStream\
.outputMode('complete')\
.format('console')\
.start()
query.awaitTermination()
|