Hadoop JobConf 类已弃用，需要更新示例

Question

我正在编写 hadoop 程序，我真的不想玩弃用的类。我在网上的任何地方都找不到更新的程序

org.apache.hadoop.conf.Configuration

类代替

org.apache.hadoop.mapred.JobConf

类。

   public static void main(String[] args) throws Exception {
     JobConf conf = new JobConf(Test.class);
     conf.setJobName("TESST");

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

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

     conf.setInputFormat(TextInputFormat.class);
     conf.setOutputFormat(TextOutputFormat.class);

     FileInputFormat.setInputPaths(conf, new Path(args[0]));
     FileOutputFormat.setOutputPath(conf, new Path(args[1]));

     JobClient.runJob(conf);
   }

这就是我的 main() 的样子。可以请任何人为我提供更新的功能。

Answer 1

这是经典的 WordCount 示例。您会注意到可能没有必要的其他导入的语气，阅读代码您会弄清楚哪个是哪个。

有什么不同？我正在使用工具接口(interface)和 GenericOptionParser 来解析作业命令 a.k.a:hadoop jar ....

在映射器中，您会注意到一个正在运行的东西。您可以去掉它，它通常在您为 Map 方法提供代码时默认调用。我把它放在那里是为了向您提供可以进一步控制映射阶段的信息。这都是使用新的 API。希望对你有帮助。任何其他问题，让我知道!

import java.io.IOException;
import java.util.*;

import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;

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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.util.GenericOptionsParser;

public class Inception extends Configured implements Tool{

 public static class Map extends 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, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        StringTokenizer tokenizer = new StringTokenizer(line);
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            context.write(word, one);
        }
    }

  public void run (Context context) throws IOException, InterruptedException {
        setup(context);
        while (context.nextKeyValue()) {
              map(context.getCurrentKey(), context.getCurrentValue(), context);
            }
        cleanup(context);
  }
 }

 public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {

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

public int run(String[] args) throws Exception {

    Job job = Job.getInstance(new Configuration());

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

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

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

    job.setJarByClass(WordCount.class);

    job.submit();
    return 0;
    }

 public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    ToolRunner.run(new WordCount(), otherArgs);
 }
}