Spark wordcount
package com.chinatelecom.hadoop;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 final> private static final Pattern SPACE = Pattern.compile(" ");
public static void main(String[] args) throws Exception {
if (args.length < 1) {
System.err.println("Usage: SparkWordCount ");
System.exit(1);
}
SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount");
JavaSparkContext ctx = new JavaSparkContext(sparkConf);
JavaRDD lines = ctx.textFile(args, 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;
}
});
List output = counts.collect();
for (Tuple2 tuple : output) {
System.out.println(tuple._1() + ": " + tuple._2());
}
System.exit(0);
}
}
spark-submit --master spark://NameNode34:7077 --name JavaWordCountByLCS --class com.chinatelecom.hadoop.SparkWordCount --executor-memory 1G --total-executor-cores 2 /opt/spark.jar hdfs://NameNode34:9000/input
spark-submit --help
查看所有参数说明
页:
[1]