[Mapreduce]eclipse下写wordcount「建议收藏」

上传两个文件到hdfs上的input目录下

代码例如以下：

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.output.FileOutputFormat;

public class wordcount {

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    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 static void main(String[] args) throws Exception {
      Configuration conf = new Configuration();
      Job job = Job.getInstance(conf, "word count");
      job.setJarByClass(wordcount.class);
      job.setMapperClass(TokenizerMapper.class);
      job.setCombinerClass(IntSumReducer.class);
      job.setReducerClass(IntSumReducer.class);
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(IntWritable.class);
      FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/input"));               //这里直接指定了文件路径.在run configuration下指定也行。但没配置好
      FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output1"));
      System.exit(job.waitForCompletion(true) ?
 0 : 1);    }  }

注：eclipse下初次执行wordcount可能会有log4j警告。能够在src下建立名为log4j.properties的文件，就可以消除警告，内容例如以下：

log4j.rootLogger=INFO,Console
 
log4j.appender.Console=org.apache.log4j.ConsoleAppender
log4j.appender.Console.Target=System.out
log4j.appender.Console.Threshold=DEBUG
log4j.appender.Console.layout=org.apache.log4j.PatternLayout
log4j.appender.Console.layout.ConversionPattern=[%d]%l%5p:%m%n
 
log4j.appender.DebugFile=org.apache.log4j.RollingFileAppender
log4j.appender.DebugFile.File=../log/debugFile.log
#log4j.appender.DebugFile.File=debugFile.log
log4j.appender.DebugFile.Append=true
log4j.appender.DebugFile.Threshold=DEBUG
log4j.appender.DebugFile.layout=org.apache.log4j.PatternLayout
log4j.appender.DebugFile.layout.ConversionPattern=[%d]%l%5p:%m%n
log4j.appender.DebugFile.MaxFileSize=20MB
log4j.appender.DebugFile.MaxBackupIndex=10
 
log4j.logger.com.ibatis=DEBUG
log4j.logger.com.ibatis.common.jdbc.SimpleDataSource=DEBUG
log4j.logger.com.ibatis.common.jdbc.ScriptRunner=DEBUG
log4j.logger.com.ibatis.sqlmap.engine.impl.SqlMapClientDelegate=DEBUG
 
log4j.logger.java.sql=DEBUG
log4j.logger.java.sql.Connection = INFO
log4j.logger.java.sql.Statement = DEBUG
log4j.logger.java.sql.PreparedStatement = DEBUG
log4j.logger.java.sql.ResultSet = DEBUG
 
log4j.logger.com.yuetao=DEBUG