hadoop程序在MyEclipse中打jar时要注意的事项

1. 首先你的类得extends Configured implements Tool，并且实现tool的run方法。
2. 下面我把代码贴出来，如图

3. package cmd;
   
   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.Text;
   import org.apache.hadoop.mapreduce.Job;
   import org.apache.hadoop.mapreduce.Mapper;
   import org.apache.hadoop.mapreduce.Mapper.Context;
   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.mapreduce.lib.partition.HashPartitioner;
   import org.apache.hadoop.util.Tool;
   import org.apache.hadoop.util.ToolRunner;
   
   
   public class WordCountApp extends Configured implements Tool{
   	
   	public static String FILE_PATH="";
   	public static String OUT_PATH="";
   	
   	
   	@Override
   	public int run(String[] args) throws Exception {
   		FILE_PATH = args[0];
   		OUT_PATH = args[1];
   		
   		Job job = new Job(new Configuration(), WordCountApp.class.getSimpleName());
   		job.setJarByClass(WordCountApp.class);
   		
   		
   		final Configuration conf = new Configuration();
   		final FileSystem fileSystem = FileSystem.get(new URI(OUT_PATH), conf);
   		if(fileSystem.exists(new Path(OUT_PATH))){
   			fileSystem.delete(new Path(OUT_PATH), true);
   		}
   		//1.1从哪里读取数据
   		FileInputFormat.setInputPaths(job, FILE_PATH);
   		//把每一行数据解析成一个键值对
   		job.setInputFormatClass(TextInputFormat.class);
   		
   		//1.2自定义函数
   		job.setMapperClass(MyMapReduce.class);
   		job.setMapOutputKeyClass(Text.class);
   		job.setPartitionerClass(HashPartitioner.class);
   		
   		//1.3分区
   		job.setPartitionerClass(HashPartitioner.class);
   		job.setNumReduceTasks(1);
   		
   		//1.4排序，分组
   		//1.5归约
   		
   		//2.1框架自己完成
   		//2.2自定义reduce函数
   		job.setReducerClass(MyReduce.class);
   		job.setOutputKeyClass(Text.class);
   		job.setOutputValueClass(LongWritable.class);
   		
   		//2.3写入hdfs中去
   		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
   		
   		job.setOutputFormatClass(TextOutputFormat.class);
   		
   		job.waitForCompletion(true);
   		return 0;
   	}
   	
   	public static void main(String[] args) throws Exception {
   		ToolRunner.run(new WordCountApp(), args);
   	}
   	
   	static class MyMapReduce extends Mapper<LongWritable, Text, Text, LongWritable>{
   		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
   				String line = value.toString();
   				String[] splits = line.split("\t");
   					for(String word:splits){
   						context.write(new Text(word),new LongWritable(1));
   					}
   				}
   	}
   	
   	
   	static class MyReduce extends Reducer<Text, LongWritable, Text, LongWritable>{
   		 protected void reduce(Text key, Iterable<LongWritable> values, Context context
                    ) throws IOException, InterruptedException {
   			 long sum = 0L;
   			for(LongWritable value: values) {
   				sum+=value.get();
   			}
   			context.write(key, new LongWritable(sum));
   		 }
   	}
   
   
   }
   

   最后在完成后不要忘记 job.setJarByClass(WordCountApp.class);写这一句代码，负责会报错找不到类。
4. 然后把这段代码打成jar包放到linux系统下，利用Hadoop的命令上传到hdfs系统中。
5. 最后操作命令hadoop jar 打包的包名.jar  读取文件路径  输入的文件路径