运行hadoop的WordCount程序

最新推荐文章于 2025-05-13 09:13:51 发布

samwalt

最新推荐文章于 2025-05-13 09:13:51 发布

阅读量103

点赞数

CC 4.0 BY-SA版权

分类专栏： hadoop 文章标签： Hadoop Apache

本文链接：https://blog.youkuaiyun.com/samwalt/article/details/83914110

hadoop 专栏收录该内容

8 篇文章

订阅专栏

本文介绍了一个使用Hadoop实现的词频统计程序，通过MapReduce框架处理大量文本数据，实现单词计数的功能。该程序包括Mapper和Reducer两个阶段，Mapper阶段负责将文本拆分为单词并给出初步计数，Reducer阶段则汇总所有中间结果，输出最终的单词及其出现次数。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

源代码

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {

	public static class MapClass extends MapReduceBase implements
			Mapper<LongWritable, Text, Text, IntWritable> {

		private final static IntWritable one = new IntWritable(1);
		private Text word = new Text();

		public void map(LongWritable key, Text value,
				OutputCollector<Text, IntWritable> output, Reporter reporter)
				throws IOException {
			String line = value.toString();
			StringTokenizer itr = new StringTokenizer(line);
			while (itr.hasMoreTokens()) {
				word.set(itr.nextToken());
				output.collect(word, one);
			}
		}
	}

	/**
	 * A reducer class that just emits the sum of the input values.
	 */
	public static class Reduce extends MapReduceBase implements
			Reducer<Text, IntWritable, Text, IntWritable> {

		public void reduce(Text key, Iterator<IntWritable> values,
				OutputCollector<Text, IntWritable> output, Reporter reporter)
				throws IOException {
			int sum = 0;
			while (values.hasNext()) {
				sum += values.next().get();
			}
			output.collect(key, new IntWritable(sum));
		}
	}

	static int printUsage() {
		System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
		ToolRunner.printGenericCommandUsage(System.out);
		return -1;
	}

	/**
	 * The main driver for word count map/reduce program. Invoke this method to
	 * submit the map/reduce job.
	 *
	 * @throws IOException
	 *             When there is communication problems with the job tracker.
	 */
	public int run(String[] args) throws Exception {
		JobConf conf = new JobConf(getConf(), WordCount.class);
		conf.setJobName("wordcount");

		// the keys are words (strings)
		conf.setOutputKeyClass(Text.class);
		// the values are counts (ints)
		conf.setOutputValueClass(IntWritable.class);

		conf.setMapperClass(MapClass.class);
		conf.setCombinerClass(Reduce.class);
		conf.setReducerClass(Reduce.class);

		List<String> other_args = new ArrayList<String>();
		for (int i = 0; i < args.length; ++i) {
			try {
				if ("-m".equals(args[i])) {
					conf.setNumMapTasks(Integer.parseInt(args[++i]));
				} else if ("-r".equals(args[i])) {
					conf.setNumReduceTasks(Integer.parseInt(args[++i]));
				} else {
					other_args.add(args[i]);
				}
			} catch (NumberFormatException except) {
				System.out.println("ERROR: Integer expected instead of "
						+ args[i]);
				return printUsage();
			} catch (ArrayIndexOutOfBoundsException except) {
				System.out.println("ERROR: Required parameter missing from "
						+ args[i - 1]);
				return printUsage();
			}
		}

		// Make sure there are exactly 2 parameters left.
		if (other_args.size() != 2) {
			System.out.println("ERROR: Wrong number of parameters: "
					+ other_args.size() + " instead of 2.");
			return printUsage();
		}
		FileInputFormat.setInputPaths(conf, other_args.get(0));
		FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

		JobClient.runJob(conf);
		return 0;
	}

	public static void main(String[] args) throws Exception {
		int res = ToolRunner.run(new Configuration(), new WordCount(), args);
		System.exit(res);
	}

}

hadoop配置成伪分布模式。本机上新建一个目录，如：~/code/hadoop/WordCount，编译WordCount.java。

javac -classpath /usr/local/hadoop-0.20.2/hadoop-0.20.2-core.jar WordCount.java

编译后生成三个class文件，WordCount.class，WordCount$Map.class，WordCount$Reduce.class。
打包成jar文件，

jar -cvf WordCount.jar *.class

新建input1.txt和input2.txt文件，输入一些单词。

在hdfs上新建目录，上传输入文件

hadoop fs -mkdir /tmp/input
hadoop fs -put input1.txt /tmp/input/
hadoop fs -put input2.txt /tmp/input/

运行程序

hadoop jar WordCount.jar WordCount /tmp/input /tmp/output