eu.stratosphere.example.java.wordcount.WordCount Maven / Gradle / Ivy

Go to download
/***********************************************************************************************************************
 *
 * Copyright (C) 2010-2013 by the Stratosphere project (http://stratosphere.eu)
 *
 * 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
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * 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 eu.stratosphere.example.java.wordcount;

import eu.stratosphere.api.java.DataSet;
import eu.stratosphere.api.java.ExecutionEnvironment;
import eu.stratosphere.api.java.aggregation.Aggregations;
import eu.stratosphere.api.java.functions.FlatMapFunction;
import eu.stratosphere.api.java.tuple.Tuple2;
import eu.stratosphere.example.java.wordcount.util.WordCountData;
import eu.stratosphere.util.Collector;

/**
 * Implements the "WordCount" program that computes a simple word occurrence histogram
 * over text files. 
 * 
 * 
 * The input is a plain text file with lines separated by newline characters.
 * 
 * 

 * This example shows how to:
 * 

 * write a simple Stratosphere program.
 * 
use Tuple data types.
 * 
write and use user-defined functions. 
 * 
 * 
 */
@SuppressWarnings("serial")
public class WordCount {
	
	// *************************************************************************
	//     PROGRAM
	// *************************************************************************
	
	public static void main(String[] args) throws Exception {
		
		parseParameters(args);
		
		// set up the execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		
		// get input data
		DataSet text = getTextDataSet(env);
		
		DataSet> counts = 
				// split up the lines in pairs (2-tuples) containing: (word,1)
				text.flatMap(new Tokenizer())
				// group by the tuple field "0" and sum up tuple field "1"
				.groupBy(0)
				.aggregate(Aggregations.SUM, 1);

		// emit result
		if(fileOutput) {
			counts.writeAsCsv(outputPath, "\n", " ");
		} else {
			counts.print();
		}
		
		// execute program
		env.execute("WordCount Example");
	}
	
	// *************************************************************************
	//     USER FUNCTIONS
	// *************************************************************************
	
	/**
	 * Implements the string tokenizer that splits sentences into words as a user-defined
	 * FlatMapFunction. The function takes a line (String) and splits it into 
	 * multiple pairs in the form of "(word,1)" (Tuple2).
	 */
	public static final class Tokenizer extends FlatMapFunction> {

		@Override
		public void flatMap(String value, Collector> out) {
			// normalize and split the line
			String[] tokens = value.toLowerCase().split("\\W+");
			
			// emit the pairs
			for (String token : tokens) {
				if (token.length() > 0) {
					out.collect(new Tuple2(token, 1));
				}
			}
		}
	}
	
	// *************************************************************************
	//     UTIL METHODS
	// *************************************************************************
	
	private static boolean fileOutput = false;
	private static String textPath;
	private static String outputPath;
	
	private static void parseParameters(String[] args) {
		
		if(args.length > 0) {
			// parse input arguments
			fileOutput = true;
			if(args.length == 2) {
				textPath = args[0];
				outputPath = args[1];
			} else {
				System.err.println("Usage: WordCount  ");
				System.exit(1);
			}
		} else {
			System.out.println("Executing WordCount example with built-in default data.");
			System.out.println("  Provide parameters to read input data from a file.");
			System.out.println("  Usage: WordCount  ");
		}
	}
	
	private static DataSet getTextDataSet(ExecutionEnvironment env) {
		if(fileOutput) {
			// read the text file from given input path
			return env.readTextFile(textPath);
		} else {
			// get default test text data
			return WordCountData.getDefaultTextLineDataSet(env);
		}
	}
}