spark jdk8 单词统计示例

在github上有spark-java8 实例地址：

https://github.com/ypriverol/spark-java8

https://github.com/ihr/java8-spark

学些java8 Lambda Expressions 的可以参考下，同时自己也做下比较。

java8 代码实例

/* 
 * 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.east.spark.stream;  
  
import java.util.Arrays;  
import java.util.List;  
import java.util.regex.Pattern;  
  
import org.apache.spark.api.java.JavaPairRDD;  
import org.apache.spark.api.java.JavaRDD;  
import org.apache.spark.sql.SparkSession;  
  
import scala.Tuple2;  
  
public final class JavaWordCount2 {  
    private static final Pattern SPACE = Pattern.compile(" ");  
  
    public static void main(String[] args) throws Exception {  
  
        args = new String[] { "D:/tmp/spark/test.txt" };  
  
        if (args.length < 1) {  
            System.err.println("Usage: JavaWordCount <file>");  
            System.exit(1);  
        }  
  
        SparkSession spark = SparkSession.builder().appName("JavaWordCount").master("local").getOrCreate();  
  
        // SparkConf conf = new  
        // SparkConf().setAppName("ingini-spark-java8").setMaster("local");  
  
        JavaRDD<String> lines = spark.read().textFile(args[0]).javaRDD();  
  
        JavaRDD<String> words = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());  
  
        JavaPairRDD<String, Integer> counts = words.mapToPair(w -> new Tuple2<String, Integer>(w, 1))  
                .reduceByKey((x, y) -> x + y);  
        // counts.collect();  
  
        List<Tuple2<String, Integer>> output = counts.collect();  
        for (Tuple2<?, ?> tuple : output) {  
            System.out.println(tuple._1() + ":== " + tuple._2());  
        }  
  
        spark.stop();  
    }  
}  

更简洁的写法：

JavaRDD<String> lines = sc.textFile("src/main/resources/a.txt");
        JavaPairRDD<String, Integer> counts = lines.flatMap(line -> Arrays.asList(line.split(REGEX)))
                .mapToPair(word -> new Tuple2(word, 1))
                .reduceByKey((x, y) -> (Integer) x + (Integer) y)
                .sortByKey();
        
        counts.foreach(stringIntegerTuple2 ->System.out.println( stringIntegerTuple2._1+":"+stringIntegerTuple2._2));