Hadoop应用引用第三方jar的几种方式（二）
package com.hadoop.examples;import java.io.IOException;
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;
import com.hadoop.hdfs.OperateHDFS;
public class WordCount {
public static class TokenizerMapper extends
Mapper {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
//它什么都不做，就是为了测试引入第三方jar的，如果找不到，肯定就会报ClassNotFound异常
OperateHDFS s = new OperateHDFS();
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer extends
Reducer {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
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[...] ");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
/**
* 其实我是做过测试的，把这个目录写成本地目录也可以的，
* 就是第三种方式，不使用libjars命令加载，而是采用程序动态加载
* 但是这样的话，就只能在固定的机器上执行命令，运行程序了，和第三种方式一样
*/
//只有做第四种方式的时候，才需要把它打开，前三种方式，需要把它注释掉
//job.addFileToClassPath(new Path("hdfs://192.168.3.57:8020/user/lxy/lib/OperateHDFS.jar"));
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs));
}
FileOutputFormat.setOutputPath(job, new Path(
otherArgs));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
页:
[1]