/** * 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. */ package org.apache.flink.streaming.examples.java8.wordcount; import java.util.Arrays; import org.apache.flink.api.java.tuple.Tuple2; import org.apache.flink.examples.java.wordcount.util.WordCountData; import org.apache.flink.streaming.api.datastream.DataStream; import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; import org.apache.flink.util.Collector; /** * Implements the streaming "WordCount" program that computes a simple word occurrences * over text files. * * <p> * The input is a plain text file with lines separated by newline characters. * * <p> * Usage: <code>WordCount <text path> <result path></code><br> * If no parameters are provided, the program is run with default data from {@link WordCountData}. * * <p> * This example shows how to: * <ul> * <li>write a compact Flink Streaming program with Java 8 Lambda Expressions. * </ul> * */ public class WordCount { // ************************************************************************* // PROGRAM // ************************************************************************* public static void main(String[] args) throws Exception { if(!parseParameters(args)) { return; } // set up the execution environment final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); // get input data DataStream<String> text = getTextDataStream(env); DataStream<Tuple2<String, Integer>> counts = // normalize and split each line text.map(line -> line.toLowerCase().split("\\W+")) // convert splitted line in pairs (2-tuples) containing: (word,1) .flatMap((String[] tokens, Collector<Tuple2<String, Integer>> out) -> { // emit the pairs with non-zero-length words Arrays.stream(tokens) .filter(t -> t.length() > 0) .forEach(t -> out.collect(new Tuple2<>(t, 1))); }) // group by the tuple field "0" and sum up tuple field "1" .keyBy(0) .sum(1); // emit result if(fileOutput) { counts.writeAsCsv(outputPath); } else { counts.print(); } // execute program env.execute("Streaming WordCount Example"); } // ************************************************************************* // UTIL METHODS // ************************************************************************* private static boolean fileOutput = false; private static String textPath; private static String outputPath; private static boolean parseParameters(String[] args) { if(args.length > 0) { // parse input arguments fileOutput = true; if(args.length == 2) { textPath = args[0]; outputPath = args[1]; } else { System.err.println("Usage: WordCount <text path> <result path>"); return false; } } else { System.out.println("Executing WordCount example with built-in default data."); System.out.println(" Provide parameters to read input data from a file."); System.out.println(" Usage: WordCount <text path> <result path>"); } return true; } private static DataStream<String> getTextDataStream(StreamExecutionEnvironment env) { if (fileOutput) { // read the text file from given input path return env.readTextFile(textPath); } else { // get default test text data return env.fromElements(WordCountData.WORDS); } } }