sparkはhdfsファイルを読んでwodcountを実現して、結果をhdfsに保存します。

作者のブログはブログ園に移転しました。http://www.cnblogs.com/xiaodf/

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;

/**
 *   Spark    HDFS  ，  WordCount  
 * 
 *     ：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 ");
			System.exit(1);
		}
		String inputSparkFile = args[0];
		String outputSparkFile = args[1];

		SparkConf sparkConf = new SparkConf().setAppName("SparkWordCount");
		JavaSparkContext ctx = new JavaSparkContext(sparkConf);
		JavaRDD lines = ctx.textFile(inputSparkFile, 1);
		JavaRDD words = lines
				.flatMap(new FlatMapFunction() {
					@Override
					public Iterable call(String s) {
						return Arrays.asList(SPACE.split(s));
					}
				});

		JavaPairRDD ones = words
				.mapToPair(new PairFunction() {

					@Override
					public Tuple2 call(String s) {
						return new Tuple2(s, 1);
					}
				});
		

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

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

		ctx.stop();
	}
}