package com.delhi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class UppercaseDriver extends Configured implements Tool {
public int run(String[] args) throws Exception{
if(args.length !=2){
System.out.printf("Two parameters are required- <input dir> <output dir>n");
return -1;}
Configuration conf = new Configuration();
Job job=Job.getInstance(conf);
job.setJobName("uppercase");
job.setJarByClass(UppercaseDriver.class);
job.setMapperClass(UpperCaseMapper.class);
job.setReducerClass(UpperCaseReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
//job.setNumReduceTasks(1);
boolean success = job.waitForCompletion(true);
return success ?0:1;
}
public static void main(String[] args) throws Exception {
int exitcode = ToolRunner.run(new UppercaseDriver(), args);
System.exit(exitcode);
}
}
这是驱动程序。减速器在mapreduce wordcount程序中没有被驱动程序调用
接下来就是减速程序:
package com.delhi;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class UpperCaseReduce extends Reducer< Text,LongWritable, Text, LongWritable>{
public void reduce(Text key, Iterable<LongWritable> value,
org.apache.hadoop.mapreduce.Reducer.Context context)
throws IOException, InterruptedException {
int sum=0;
System.out.println("how +++++++++++++++++" + key);
for(LongWritable st: value){
sum = (int) (sum + st.get());
}
System.out.println("how +++++++++++++++++" + key);
context.write(key, new LongWritable(sum));
}
}
接下来就是映射器程序:
package com.delhi;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class UpperCaseMapper extends Mapper<Object, Text, Text, LongWritable>{
@Override
protected void map(Object key, Text value,
org.apache.hadoop.mapreduce.Mapper.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String arr[] = line.split(" ");
System.out.println("hello++++++++++++++++++++++++++++");
for(String st: arr){
//context.write(new Text(st.toUpperCase().trim()),new LongWritable(1));
context.write(new Text(st),new LongWritable(1));
}
}
}
从已经存在的解决方案,我发现了,在这类问题outputkeyclass和outputvalueclass的应与减速机。我认为我采取妥善妥善的部分。我的情况@Override for reduce不起作用。我正在使用hadoop 7.2.3。我也尝试使用修剪功能。问题是wordcount不会发生。我只给我“单词1”,输出文件中的任何单词。 我从不同的问题开始,我就这样结束了。请帮助我。 谢谢。
确实很难设法解决你的问题。你有错误吗?减速机是否在运转?问一个问题,并明确你遇到的问题。 –
感谢您的回复。我得到这样的输出:1 1个 文件1个 文件1 文件1 1 是1 为1 为1 所以,简单的字计数不working.My问题是为什么?我认为减速机不工作。 – Angshusuri
请编辑问题以使其更具可读性。从问题开始,然后发布代码,然后添加您希望的任何细节。添加您以前的评论作为问题的一部分。 – vefthym