1. 程式人生 > >spark讀hdfs檔案實現wordcount並將結果存回hdfs

spark讀hdfs檔案實現wordcount並將結果存回hdfs

package iie.udps.example.operator.spark;

import scala.Tuple2;

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.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import java.util.Arrays;
import java.util.regex.Pattern;

/**
 * 利用Spark框架讀取HDFS檔案,實現WordCount示例
 * 
 * 執行命令:spark-submit --class iie.hadoop.hcatalog.TextFileSparkTest --master
 * yarn-cluster /tmp/sparkTest.jar hdfs://192.168.8.101/test/words
 * hdfs://192.168.8.101/test/spark/out
 * 
 * @author xiaodongfang
 *
 */
public final class TextFileSparkTest {
	private static final Pattern SPACE = Pattern.compile(" ");

	@SuppressWarnings("serial")
	public static void main(String[] args) throws Exception {

		if (args.length < 2) {
			System.err.println("Usage: JavaWordCount <file>");
			System.exit(1);
		}
		String inputSparkFile = args[0];
		String outputSparkFile = args[1];

		SparkConf sparkConf = new SparkConf().setAppName("SparkWordCount");
		JavaSparkContext ctx = new JavaSparkContext(sparkConf);
		JavaRDD<String> lines = ctx.textFile(inputSparkFile, 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) {
						return new Tuple2<String, Integer>(s, 1);
					}
				});
		

		JavaPairRDD<String, Integer> counts = ones
				.reduceByKey(new Function2<Integer, Integer, Integer>() {
					@Override
					public Integer call(Integer i1, Integer i2) {
						return i1 + i2;
					}
				});

		counts.map(new Function<Tuple2<String, Integer>, String>() {
			@Override
			public String call(Tuple2<String, Integer> arg0) throws Exception {
				return arg0._1.toUpperCase() + ": " + arg0._2;
			}
		}).saveAsTextFile(outputSparkFile);

		ctx.stop();
	}
}