1

我最近安装了新的 Hadoop 2.2。我之前写过一个简单的 Word Count MapReduce 程序，它曾经在 CDH4 上轻松工作。org.apache.hadoop.mapreduce但是现在，我对所有进口都有问题。有人可以告诉我要导出哪个 jar 来修复这些导入吗？代码如下，以防有人需要指出我需要进行的更改以确保它在 Hadoop 2.2 中运行。

import java.io.IOException;
import java.lang.InterruptedException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

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.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MapRWordCount {
    private final static IntWritable ONE = new IntWritable(1);
    private final static Pattern WORD = Pattern.compile("\\w+");

    public static class WordCountMapper 
            extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final Text word = new Text();

        @Override
        public void map(LongWritable key, Text value, Context context) 
                throws IOException, InterruptedException {

            String valueString = value.toString();
            Matcher matcher = WORD.matcher(valueString);
            while (matcher.find()) {
                word.set(matcher.group().toLowerCase());
                context.write(word, ONE);
            }
        }
    }

    public static class WordCountReducer 
            extends Reducer<Text, IntWritable, Text, IntWritable> {
        private final IntWritable totalCount = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) 
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();
            }
            totalCount.set(sum);
            context.write(key, totalCount);
        }
    }

    public static void main(String[] args) 
            throws IOException, ClassNotFoundException, InterruptedException {

        if (args.length != 2) {
            System.err.println("Usage: MapRWordCount <input_path> <output_path>");
            System.exit(-1);
        }

        Job job = new Job();
        job.setJarByClass(MapRWordCount.class);
        job.setJobName("MapReduce Word Count");

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.setMapperClass(WordCountMapper.class);
        job.setCombinerClass(WordCountReducer.class);
        job.setReducerClass(WordCountReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}
4

4 回答 4

3

我在以下位置找到了 JAR：

$HADOOP_HOME/share/hadoop/common/hadoop-common-2.2.0.jar
$HADOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.2.0.jar
于 2013-10-17T21:16:17.740 回答
3

在 maven 中，我必须将以下内容添加到 pom.xml 中，然后干净地构建以便能够在 Java 中找到 Mapper 和 Reducer 类：

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.2.0</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-core</artifactId>
    <version>2.2.0</version>
</dependency>

现在以下不会引发错误：

import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
于 2014-01-15T01:00:21.570 回答
1

如果您只是在 Hadoop 2.2 中寻找适当 JAR 的位置，请查看share/hadoop/{common,hdfs,mapreduce}. 您会发现以您要查找的文件结尾的文件-2.2.0.jar。

这应该与 CDH4 中的相同，除非您安装了匹配 Hadoop 1.x 结构的“MR1”版本。

于 2013-10-17T20:28:15.917 回答
-1

使用此链接查找您需要的任何 JAR 文件

下载它们，右键单击您的项目转到构建路径 > 配置构建路径 > 添加外部 JAR

于 2013-10-17T20:37:19.000 回答