
package cn.edu.hgu.flink;
 
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.operators.Order;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
 
/**
 * 使用Flink中的DataSet实现单词计数
*/
public class WordCount {
    public static void main(String[] args) throws Exception {
    //1·准备环境-env
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    //2·准备数据-source
        DataSet<String> lineDS = env.fromElements("flink hadoop java hbase",
                "hadoop flink 0","hadoop hbase flink");
    //3·处理数据-transformation
//        3.1 将每一行数据切分成一个一个的单词，组成一个集合
        DataSet<String> wordDS = lineDS.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String s, Collector<String> collector) throws Exception {
                //参数 s 就是一行行的数据再将每一行切分成一个个的单词
                String[] words = s.split(" ");
                // 将切分的单词收集起来，发到集合中去
                for (String word:words){
                    collector.collect(word);
                }
            }
        });
//        3.2对集合中的每一个单词记为1，成为一个三元组集合
        DataSet<Tuple2<String,Integer>> wordAndOneDS = wordDS.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String s) throws Exception {
                // 此处的s就是进来的一个个单词，再跟一组成一个二元组返回

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/喵喵爱编程/article/detail/1007949