MapReduce实现（一）

package searchResult;
/** 
 * map函数
 * 输出键：搜索词...
 * 输出值：对应搜索结果数...+搜索时间...
 */
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class SearchResultMap extends Mapper<Object, Text, Text, Text>{
	
	public void map(Object key, Text value, Context context)
			throws IOException, InterruptedException{
		
		String line = value.toString();
		String[] str= line.split("\t");
		
		//判断条件：...
		if (str[15].equals("XXX")  && str[17].compareTo("-1")!=0){
			context.write(new Text(str[17]),new Text(str[9]+"\t"+str[10]));
		}
	}

}

package searchResult;

import java.io.IOException;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/** 
 * reduce函数
 * 输出键:搜索词...
 * 输出键：对应搜索结果数...
 */ 
public class SearchResultReduce extends Reducer<Text,Text,Text,Text>{
	
	public void reduce(Text key, Iterable<Text> values, Context context)
			throws IOException, InterruptedException {
		
		String time = "20010101 00:00:00";
		String result = "";
		java.text.DateFormat df = new java.text.SimpleDateFormat("yyyyMMdd HH:mm:ss");//search_time格式
		
		for (Text val : values){
			String line2 = val.toString();
			String[] str2 = line2.split("\t");
			//时间类型转换
			java.util.Calendar c1 = java.util.Calendar.getInstance();
			java.util.Calendar c2 = java.util.Calendar.getInstance();
			try{
				c1.setTime(df.parse(time));
				c2.setTime(df.parse(str2[1]));
			}catch(java.text.ParseException e){
				System.err.println("start_time格式不正确");
			}
			//判断条件
			if(c1.compareTo(c2)<0){
				time=str2[1];
				result = str2[0];
			}
		}
		context.write(key, new Text(result));
	}

}

package searchResult;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
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.GenericOptionsParser;

import com.SearchProject;
import com.SearchProject.SearchProjectMapper;
import com.SearchProject.SearchProjectReducer;

public class SearchResultDriver {
	public static void main(String[] args) throws Exception, InterruptedException {

		Configuration conf = new Configuration();
	    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();   
	    if (otherArgs.length != 2) {  
	      System.err.println("Usage: search project <in> <out>");  
	      System.exit(2);  
	    }  
	    Job job = new Job(conf, "searchResult:" + args[1]);  
	    job.setJarByClass(SearchProject.class);
	    
	    job.setMapperClass(SearchProjectMapper.class);//mapper   
	    job.setReducerClass(SearchProjectReducer.class);//reducer  
	    
	     
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
	    job.setOutputKeyClass(Text.class);
	    job.setOutputValueClass(Text.class);
	     
        job.setInputFormatClass(TextInputFormat.class);   
        job.setOutputFormatClass(TextOutputFormat.class);  
        
        Path outpath = new Path(args[1]);
        FileSystem hdfs = outpath.getFileSystem(conf);
        if (hdfs.exists(outpath)) {
        	hdfs.delete(outpath, true);
        }
	    
	    FileInputFormat.addInputPath(job, new Path(args[0]));//输入hdfs路径  
	    FileOutputFormat.setOutputPath(job, new Path(args[1]));//输出hdfs路径 
	    System.exit(job.waitForCompletion(true) ? 0 : 1);//等待完成退出.  
	  }  	

}

PS:已做部分修改