MapReduce_MaxValue

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration; 
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path; 
import org.apache.hadoop.io.LongWritable; 
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; 
import org.apache.hadoop.util.Tool; 
import org.apache.hadoop.util.ToolRunner; 

//求最大值 
public class MaxValue extends Configured implements Tool { 
    private static final String INPUT_PATH = "hdfs://h201:9000/user/hadoop/input_maxvalue";
    private static final String OUTPUT_PATH = "hdfs://h201:9000/user/hadoop/output";
    public static class MapClass extends Mapper<LongWritable, Text, IntWritable, IntWritable> { 
        private int maxNum = 0; 
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { 
            String[] str = value.toString().split(" "); 
            try {// 对于非数字字符我们忽略掉
                for(int i=0;i<str.length;i++){
                    int temp = Integer.parseInt(str[i]); 
                    if (temp > maxNum) { 
                        maxNum = temp; 
                    }
                }
            } catch (NumberFormatException e) { 
            } 
        } 

        @Override 
    protected void cleanup(Context context) throws IOException, InterruptedException { 
            context.write(new IntWritable(maxNum), new IntWritable(maxNum)); 
        } 
    } 

    public static class Reduce extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable> { 
        private int maxNum = 0; 
        public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { 
            for (IntWritable val : values) { 
                if ( val.get() > maxNum) { 
                    maxNum = val.get(); 
                } 
            } 
        } 

        @Override 
        protected void cleanup(Context context) throws IOException, InterruptedException { 
            context.write(new IntWritable(maxNum), new IntWritable(maxNum)); 
        } 
    } 

    public int run(String[] args) throws Exception { 
        Configuration conf = getConf(); 
        conf.set("mapred.jar","mv.jar");
        final FileSystem fileSystem = FileSystem.get(new URI(OUTPUT_PATH), conf);//读路径信息
        fileSystem.delete(new Path(OUTPUT_PATH), true);//删除路径信息 输出路径不能存在
        Job job = new Job(conf, "MaxNum"); 
        job.setJarByClass(MaxValue.class); 
        FileInputFormat.setInputPaths(job, INPUT_PATH); 
        FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH)); 
        job.setMapperClass(MapClass.class); 
        job.setCombinerClass(Reduce.class); 
        job.setReducerClass(Reduce.class); 
        job.setInputFormatClass(TextInputFormat.class); 
        job.setOutputFormatClass(TextOutputFormat.class); 
        job.setOutputKeyClass(IntWritable.class); 
        job.setOutputValueClass(IntWritable.class); 
        System.exit(job.waitForCompletion(true) ? 0 : 1); 
        return 0; 
    } 

    public static void main(String[] args) throws Exception { 
        long start = System.nanoTime(); 
        int res = ToolRunner.run(new Configuration(), new MaxValue(), args); 
        System.out.println(System.nanoTime()-start); 
        System.exit(res); 
    } 
}

*************
setup()，此方法被MapReduce框架仅且执行一次，在执行Map任务前，进行相关变量或者资源的集中初始化工作。若是将资源初始化工作放在方法map()中，导致Mapper任务在解析每一行输入时都会进行资源初始化工作，导致重复，程序运行效率不高！

cleanup(),此方法被MapReduce框架仅且执行一次，在执行完毕Map任务后，进行相关变量或资源的释放工作。若是将释放资源工作放入方法map()中，也会导致Mapper任务在解析、处理每一行文本后释放资源，而且在下一行文本解析前还要重复初始化，导致反复重复，程序运行效率不高！
*************