昨天安装完成,起床后抄了个简单的单词计数,单机版运行成功,从Java和Scala两种语言比较来看,Scala在做Spark开发的时候确实要简练很多:
/**
* Created by tsq on 2016-07-17.
*/
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;
import java.util.Arrays;
import java.util.List;
import java.util.regex.Pattern;
public class wordCount {
private static final Pattern SPACE = Pattern.compile(" ");
public static void main(String[] args) throws Exception
{
/*var conf= new SparkConf().setMaster("local").setAppName("wordCount")
var sc= new SparkContext(conf)
var data = sc.textFile("d://word.txt")
data.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).collect().foreach(println)*/
SparkConf sparkConf = new SparkConf().setMaster("local").setAppName("wordCount");
JavaSparkContext ctx = new JavaSparkContext(sparkConf);
JavaRDD<String> lines = ctx.textFile("d://word.txt", 1);
JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String s) {
return Arrays.asList(SPACE.split(s));
}
});
JavaPairRDD<String, Integer> ones = words.mapToPair(new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) {
if(s.contentEquals("good"))
{
return new Tuple2<String, Integer>(s, 1);
}
if(s.contentEquals("spark"))
{
return new Tuple2<String, Integer>(s, 1);
}
return new Tuple2<String, Integer>("other", 1);
}
});
JavaPairRDD<String, Integer> counts = ones.reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
List<Tuple2<String, Integer>> output = counts.collect();
for (Tuple2<?, ?> tuple : output) {
System.out.println(tuple._1() + "=> " + tuple._2());
}
ctx.stop();
}
}
注意:main函数的注释部分使用Scala语言写的。
需要注意的是,如果是单机版的,要运行的话一定要添加红色部分代码:
SparkConf sparkConf = new SparkConf().setMaster("local").setAppName("wordCount");
但如果要在集群中运行,红色部分的代码就应该除掉。
下一步,安装cywin,测试一下集群下的Spark.