Hadoop java交叉編譯

系統：ubuntu 14.04
HADOOP VERSION: 2.6.0 32bits

在裝好hadoop並且開啓dfs和yarn以後，用JPS檢查能看到一下六個進程：

14779 DataNode
15322 NodeManager
14657 NameNode
15194 ResourceManager
17656 Jps
14979 SecondaryNameNode

接下來我們需要運行WordCout項目來驗證是否安裝正確。
WordCount.java：

package org.apache.hadoop.mapred;

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

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.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * This is an example Hadoop Map/Reduce application.
 * It reads the text input files, breaks each line into words
 * and counts them. The output is a locally sorted list of words and the 
 * count of how often they occurred.
 *
 * To run: bin/hadoop jar build/hadoop-examples.jar wordcount
 *            [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i> <i>out-dir</i> 
 */
public class WordCount extends Configured implements Tool {

  /**
   * Counts the words in each line.
   * For each line of input, break the line into words and emit them as
   * (<b>word</b>, <b>1</b>).
   */
  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);
      }
    }
  }

  /**
   * A 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<IntWritable> 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 <maps>] [-r <reduces>] <input> <output>");
    ToolRunner.printGenericCommandUsage(System.out);
    return -1;
  }

  /**
   * The main driver for word count map/reduce program.
   * Invoke this method to submit the map/reduce job.
   * @throws IOException When there is communication problems with the 
   *                     job tracker.
   */
  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);        
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    List<String> other_args = new ArrayList<String>();
    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);
  }

}

顯然直接直接使用javac命令編譯因爲沒有hadoop的jar包是會報很多錯的。
查了一些資料，發現因爲hadoop版本不同各種jar包的位置略有不同。
在hadoop2.6.0的安裝包裏面仔細查找可以發現需要的jar包都在hadoop-2.6.0/share/hadoop的各級子目錄下面：

root@fd-ubuntu:/usr/hadoop/hadoop-2.6.0/share/hadoop# ls
common  hdfs  httpfs  kms  mapreduce  tools  yarn

於是我們可以首先在/etc/profile最後一行加入一個遞歸搜索此目錄下jar文件的環境變量，source之後註銷才能全局生效。

for X in `find ${HADOOP_DEV_HOME}/share/hadoop -type f`
do
    HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:${X}
done

然後編寫生成WordCount.jar的makefile：

jj = javac

WordCount.jar:org
    jar -cvf WordCount.jar org

org: WordCount.java
    $(jj) -cp $(HADOOP_CLASSPATH) WordCount.java -d .

clear:
    rm -rf org WordCount.jar

按照以上步驟就可以生成WordCount的可執行JAR，再放入HDFS執行即可。

hadoop jar WordCount.jar org.apache.nutch.WordCount input output