/*
* 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.
*/// scalastyle:off printlnpackage org.apache.spark.examples.streaming
import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.{Seconds, StreamingContext}/**
* Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
*
* Usage: NetworkWordCount <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.NetworkWordCount localhost 9999`
*/
object NetworkWordCount {
def main(args: Array[String]){if(args.length <2){
System.err.println("Usage: NetworkWordCount <hostname> <port>")
System.exit(1)}
StreamingExamples.setStreamingLogLevels()// Create the context with a 1 second batch size
val sparkConf =newSparkConf().setAppName("NetworkWordCount")
val ssc =newStreamingContext(sparkConf,Seconds(1))// Create a socket stream 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.
val lines = ssc.socketTextStream(args(0),args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER)
val words = lines.flatMap(_.split(" "))
val wordCounts = words.map(x =>(x,1)).reduceByKey(_ + _)
wordCounts.print()
ssc.start()
ssc.awaitTermination()}}// scalastyle:on println
import org.apache.spark.streaming.{Seconds, StreamingContext}
val ssc =newStreamingContext(sc,Seconds(1))
val lines = ssc.socketTextStream("hadoop000",9999)
val words = lines.flatMap(_.split(" "))
val wordCounts = words.map(x =>(x,1)).reduceByKey(_ + _)
wordCounts.print()
ssc.start()
ssc.awaitTermination()