java - 在java程序中编译错误以使用hadoop计算文件中的单词

Question

我的 Java 版本:

➜  test git:(dev) ✗ java -version
java version "1.8.0_131"
Java(TM) SE Runtime Environment (build 1.8.0_131-b11)
Java HotSpot(TM) 64-Bit Server VM (build 25.131-b11, mixed mode)

我正在尝试运行以下简单的 java 程序，该程序使用 hadoop map reduce from here 提供文件中的字数统计.以下是完整的java代码:

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

public class WordCount extends Configured implements Tool {
   private final static LongWritable ONE = new LongWritable(1L);

// Mapper Class, Counts words in each line. For each line, break the line into words and emits them as (word, 1)

public static class MapClass extends MapReduceBase implements 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,
   OutputCollector<text, intwritable> output,
   Reporter reporter) throws IOException {

  String line = value.toString();
  StringTokenizer itr = new StringTokenizer(line);
  while (itr.hasMoreTokens()) {
    word.set(itr.nextToken());
     output.collect(word, one);
   }
 }
}

// Reducer class that just emits the sum of the input values.

public static class Reduce extends MapReduceBase implements Reducer< Text, IntWritable, Text, IntWritable > {
public void reduce(Text key, Iterator values,
 OutputCollector<text, intwritable=""> output,
 Reporter reporter) throws IOException {
      int sum = 0;
      while (values.hasNext()) {
        sum += values.next().get();
      }
      output.collect(key, new IntWritable(sum));
    }
  }

static int printUsage() {
System.out.println("wordcount [-m #mappers ] [-r #reducers] input_file output_file");
    ToolRunner.printGenericCommandUsage(System.out);
    return -1;
  }

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

    JobConf conf = new JobConf(getConf(), WordCount.class);
    conf.setJobName("wordcount");

// the keys are words (strings)
   conf.setOutputKeyClass(Text.class);
// the values are counts (ints)
   conf.setOutputValueClass(IntWritable.class);

   conf.setMapperClass(MapClass.class);
// Here we set the combiner!!!!
   conf.setCombinerClass(Reduce.class);
   conf.setReducerClass(Reduce.class);

  List other_args = new ArrayList();
   for(int i=0; i < args.length; ++i) {
     try {
        if ("-m".equals(args[i])) {
conf.setNumMapTasks(Integer.parseInt(args[++i]));
        } else if ("-r".equals(args[i])) {
conf.setNumReduceTasks(Integer.parseInt(args[++i]));
        } else {
          other_args.add(args[i]);
        }
      } catch (NumberFormatException except) {
        System.out.println("ERROR: Integer expected instead of " + args[i]);
        return printUsage();
      } catch (ArrayIndexOutOfBoundsException except) {
        System.out.println("ERROR: Required parameter missing from " +
            args[i-1]);
        return printUsage();
      }
    }
// Make sure there are exactly 2 parameters left.
   if (other_args.size() != 2) {
      System.out.println("ERROR: Wrong number of parameters: " +
          other_args.size() + " instead of 2.");
      return printUsage();
    }
    FileInputFormat.setInputPaths(conf, other_args.get(0));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

    JobClient.runJob(conf);
    return 0;
  }

public static void main(String[] args) throws Exception {
    int res = ToolRunner.run(new Configuration(), new WordCount(), args);
    System.exit(res);
  }
}

但是在上面代码的下面部分:

// Reducer class that just emits the sum of the input values.

public static class Reduce extends MapReduceBase implements Reducer< Text, IntWritable, Text, IntWritable > {
public void reduce(Text key, Iterator values,
 OutputCollector<text, intwritable=""> output,
 Reporter reporter) throws IOException {
      int sum = 0;
      while (values.hasNext()) {
        sum += values.next().get();
      }
      output.collect(key, new IntWritable(sum));
    }
  }

我收到以下编译错误:

➜ test git:(dev) ✗ javac WordCount.java WordCount.java:43: error: > expected OutputCollector output, ^

WordCount.java:43: error: ')' expected OutputCollector output, ^

WordCount.java:43: error: ';' expected OutputCollector output, ^

WordCount.java:43: error: expected OutputCollector output, ^

WordCount.java:44: error: ';' expected Reporter reporter) throws IOException { ^

WordCount.java:44: error: expected Reporter reporter) throws IOException { ^ WordCount.java:44: error: illegal start of type Reporter reporter) throws IOException { ^

WordCount.java:44: error: ';' expected Reporter reporter) throws IOException { ^

8 errors

我确定这是一些非常基本的错误，但无法弄清楚。

Answer 1

我不确定这是什么，但它不完全是 Java。例如:

OutputCollector<text, intwritable="">

text 和 intwrtiable 不是类型。那应该是 Text 和 IntWritable。那里的默认分配对我来说完全是个谜。 Java 不支持默认泛型，即使支持，我也不确定在此上下文中空白字符串的含义。