Hadoop JobConf 类已弃用，需要更新示例

Question

我正在编写 hadoop 程序，我真的不想使用已弃用的类。 在网上的任何地方我都找不到更新的程序

org.apache.hadoop.conf.Configuration

配置类 插入的

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。 请任何人都可以为我提供更新的功能。

Answer 1

这是经典的 WordCount 示例。您会注意到其他导入的语气可能不是必需的，阅读代码您就会弄清楚哪个是哪个。

有什么不同？我正在使用 Tool 界面和 GenericOptionParser 来解析作业命令，又名：hadoop jar ...。

在映射器中，您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，通常会默认调用它。我把它放在那里是为了给您提供可以进一步控制映射阶段的信息。这一切都是使用新的API。我希望你觉得它有用。如有其他问题，请告诉我！

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

还以经典的 WordCount 为例：

org.apache.hadoop.mapred.JobConf 是旧的，在新版本中我们使用 Configuration< /code> 和 Job 来实现。

请使用org.apache.hadoop.mapreduce.lib.*（它是新的API）而不是org.apache.hadoop.mapred.TextInputFormat（它是旧的）。

Mapper和Reducer没什么新鲜的，请看main函数，它包含了比较全面的配置，您可以根据您的具体需求随意更改它们。

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);
  }
}