/*
* 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 com.house.flink.wordcount;import org.apache.flink.api.common.functions.FlatMapFunction;import org.apache.flink.api.java.tuple.Tuple2;import org.apache.flink.streaming.api.datastream.DataStream;import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;import org.apache.flink.util.Collector;publicclassWordCount{publicstaticvoidmain(String[] args)throws Exception {final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStream<String> text = env.readTextFile("/Users/haozhang/env/bigdata/**");
DataStream<Tuple2<String, Integer>> counts =
text.flatMap(newTokenizer()).keyBy(0).sum(1);
counts.print();
env.execute("Streaming WordCount");}// *************************************************************************// USER FUNCTIONS
//*************************************************************************/**
* Implements the string tokenizer that splits sentences into words as a
* user-defined FlatMapFunction. The function takes a line (String) and
* splits it into multiple pairs in the form of "(word,1)" ({@code Tuple2<String,
* Integer>}).
*/publicstaticfinalclassTokenizerimplementsFlatMapFunction<String, Tuple2<String, Integer>>{@OverridepublicvoidflatMap(String value, Collector<Tuple2<String, Integer>> out){// normalize and split the line
String[] tokens = value.toLowerCase().split("\\W+");// emit the pairsfor(String token : tokens){if(token.length()>0){
out.collect(newTuple2<>(token,1));}}}}}