/** * Copyright 2015 Nabarun Mondal * Licensed 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 * <p> * http://www.apache.org/licenses/LICENSE-2.0 * <p> * 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.noga.njexl.spark; import com.noga.njexl.lang.JexlContext; import com.noga.njexl.lang.JexlEngine; import com.noga.njexl.lang.Script; import com.noga.njexl.spark.impl.ScalaInteract; 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.Map; /** * A Main class to have command line interface, if need be. * Created by noga on 15/04/15. */ public class Main { private static final FlatMapFunction<String, String> WORDS_EXTRACTOR = new FlatMapFunction<String, String>() { @Override public Iterable<String> call(String s) throws Exception { return Arrays.asList(s.split(" ")); } }; private static final PairFunction<String, String, Integer> WORDS_MAPPER = new PairFunction<String, String, Integer>() { @Override public Tuple2<String, Integer> call(String s) throws Exception { return new Tuple2<String, Integer>(s, 1); } }; private static final Function2<Integer, Integer, Integer> WORDS_REDUCER = new Function2<Integer, Integer, Integer>() { @Override public Integer call(Integer a, Integer b) throws Exception { return a + b; } }; private Main() { } public static void ain(String[] args) { String inputFileName = "samples/big.txt" ; String outputDirName = "output" ; SparkConf conf = new SparkConf().setAppName("org.sparkexample.WordCount").setMaster("local"); JavaSparkContext context = new JavaSparkContext(conf); JavaRDD<String> file = context.textFile(inputFileName); JavaRDD<String> words = file.flatMap(WORDS_EXTRACTOR); JavaPairRDD<String, Integer> pairs = words.mapToPair(WORDS_MAPPER); JavaPairRDD<String, Integer> counter = pairs.reduceByKey(WORDS_REDUCER); counter.saveAsTextFile(outputDirName); } public static Object executeScript(String script) throws Exception { JexlContext context = com.noga.njexl.lang.Main.getContext(); Map map = com.noga.njexl.lang.Main.getFunction(context); map.put("spark", XSpark.class ); context.set( ScalaInteract.MY_NAME , ScalaInteract.class ); JexlEngine engine = com.noga.njexl.lang.Main.getJexl( context ); engine.setFunctions( map ); Script s = engine.importScript(script); return s.execute(context); } public static void main(String[] args) throws Exception { executeScript(args[0]); } }