python/streaming/hdfs_wordcount.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019  Counts words in new text files created in the given directory
0020  Usage: hdfs_wordcount.py <directory>
0021    <directory> is the directory that Spark Streaming will use to find and read new text files.
0022
0023  To run this on your local machine on directory `localdir`, run this example
0024     $ bin/spark-submit examples/src/main/python/streaming/hdfs_wordcount.py localdir
0025
0026  Then create a text file in `localdir` and the words in the file will get counted.
0027 """
0028 from __future__ import print_function
0029
0030 import sys
0031
0032 from pyspark import SparkContext
0033 from pyspark.streaming import StreamingContext
0034
0035 if __name__ == "__main__":
0036     if len(sys.argv) != 2:
0037         print("Usage: hdfs_wordcount.py <directory>", file=sys.stderr)
0038         sys.exit(-1)
0039
0040     sc = SparkContext(appName="PythonStreamingHDFSWordCount")
0041     ssc = StreamingContext(sc, 1)
0042
0043     lines = ssc.textFileStream(sys.argv[1])
0044     counts = lines.flatMap(lambda line: line.split(" "))\
0045                   .map(lambda x: (x, 1))\
0046                   .reduceByKey(lambda a, b: a+b)
0047     counts.pprint()
0048
0049     ssc.start()
0050     ssc.awaitTermination()