二、实验内容与步骤(过程及数据记录): (1) 先在Eclipse中创建“WordCount”MapReduce项目。 (2) 在项目中创建一个新的Java文件命名为“WordCountTest.java”。 (3)在Java文件中输入下列代码: import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCountTest {
public WordCountTest() {
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
if(otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "word count test");
job.setJarByClass(WordCountTest.class);
job.setMapperClass(WordCountTest.TokenizerMapper.class);
job.setCombinerClass(WordCountTest.IntSumReducer.class);
job.setReducerClass(WordCountTest.IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
for(int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true)?0:1);
}
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public IntSumReducer() {
}
public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable,
Text, IntWritable>.Context context) throws IOException, InterruptedException {
int sum = 0;
IntWritable val;
for(Iterator itr = values.iterator(); itr.hasNext(); sum += val.get()) {
val = (IntWritable)itr.next();
}
this.result.set(sum);
context.write(key, this.result);
}
}
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
private static final IntWritable one = new IntWritable(1);
private Text word = new Text();
public TokenizerMapper() {
}
public void map(Object key, Text value, Mapper<Object, Text,
Text, IntWritable>.Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while(itr.hasMoreTokens()) {
this.word.set(itr.nextToken());
context.write(this.word, one);
}
}
}
} (4) Hadoop配置文件添加到“WordCount” MapReduce项目。 [hfut@master ~]$ cp ~/hadoop-3.2.2/etc/hadoop/log4j.properties ~/workspace/MyWordCount/src (5) 通过Eclipse运行“MyWordCount” MapReduce项目。 (6) 在eclipse上能如果能够成功运行,将这个项目打包成一个jar包保存到Hadoop里的myapp文件夹中。 (7) 在Hadoop上运行这个程序。 运行结果如图所示: |