Switch branches/tags
Find file Copy path
83 lines (70 sloc) 2.96 KB
* 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
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* See the License for the specific language governing permissions and
* limitations under the License.
package org.apache.flink.streaming.scala.examples.socket
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time
* Implements a streaming windowed version of the "WordCount" program.
* This program connects to a server socket and reads strings from the socket.
* The easiest way to try this out is to open a text sever (at port 12345)
* using the ''netcat'' tool via
* {{{
* nc -l 12345
* }}}
* and run this example with the hostname and the port as arguments..
object SocketWindowWordCount {
/** Main program method */
def main(args: Array[String]) : Unit = {
// the host and the port to connect to
var hostname: String = "localhost"
var port: Int = 0
try {
val params = ParameterTool.fromArgs(args)
hostname = if (params.has("hostname")) params.get("hostname") else "localhost"
port = params.getInt("port")
} catch {
case e: Exception => {
System.err.println("No port specified. Please run 'SocketWindowWordCount " +
"--hostname <hostname> --port <port>', where hostname (localhost by default) and port " +
"is the address of the text server")
System.err.println("To start a simple text server, run 'netcat -l <port>' " +
"and type the input text into the command line")
// get the execution environment
val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
// get input data by connecting to the socket
val text: DataStream[String] = env.socketTextStream(hostname, port, '\n')
// parse the data, group it, window it, and aggregate the counts
val windowCounts = text
.flatMap { w => w.split("\\s") }
.map { w => WordWithCount(w, 1) }
// print the results with a single thread, rather than in parallel
env.execute("Socket Window WordCount")
/** Data type for words with count */
case class WordWithCount(word: String, count: Long)