Question

我正在编写hadoop程序，我真的不想玩弃用的类。在线任何地方我无法找到更新的程序

org.apache.hadoop.conf.Configuration

类

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。可以请任何人都能为我提供更新的功能。

Answer 1

这是经典的WordCount示例。您会注意到其他可能没有必要的输入音，阅读您将找出哪些代码。

有什么不同？我正在使用Tool接口和GenericOptionParser来解析作业命令a.k.a：hadoop jar ....

在映射器中你会注意到一个运行的东西。您可以摆脱它，当您提供Map方法的代码时，它通常默认调用。我把它放在那里给你的信息，你可以进一步控制映射阶段。这都是使用新的API。希望对你有帮助。还有其他任何问题，请告诉我们！

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);
 }
}

Answer 2

同样以经典 WordCount 为例：

org.apache.hadoop.mapred.JobConf已过时，在新版本中我们使用Configuration和Job来实现。

请使用org.apache.hadoop.mapreduce.lib.*（这是新的API）而不是org.apache.hadoop.mapred.TextInputFormat（它已经过时了）。

Mapper和Reducer并不是什么新鲜事，请参阅main功能，它包含相对整体的配置，可以根据您的具体要求随时更改。

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

class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
  private Text outputKey;
  private IntWritable outputVal;

  @Override
  public void setup(Context context) {
    outputKey = new Text();
    outputVal = new IntWritable(1);
  }

  @Override
  public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
    StringTokenizer stk = new StringTokenizer(value.toString());
    while(stk.hasMoreTokens()) {
      outputKey.set(stk.nextToken());
      context.write(outputKey, outputVal);
    }
  }
}

class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
  private IntWritable result;

  @Override
  public void setup(Context context) {
    result = new IntWritable();
  }

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

public class WordCount {
  public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = new Configuration();
    if(args.length != 2) {
      System.err.println("Usage: <in> <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "Word Count");

    // set jar
    job.setJarByClass(WordCount.class);

    // set Mapper, Combiner, Reducer
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);

    /* Optional, set customer defined Partioner:
     * job.setPartitionerClass(MyPartioner.class);
     */

    // set output key
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    // set input and output path
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    // by default, Hadoop use TextInputFormat and TextOutputFormat
    // any customer defined input and output class must implement InputFormat/OutputFormat interface
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

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

不推荐使用Hadoop JobConf类，需要更新示例

2 个答案: