hadoop做的一个简单grep程序，可从文档中提取包含某些字符串的行

复制代码 代码如下:

/*

* 一个简单grep程序，可从文档中提取包含莫些字符串的行

*/

public class grep extends Configured implements Tool{

public static class grepMap extends Mapper<LongWritable, Text, Text,NullWritable>{

public void map(LongWritable line,Text value,Context context) throws IOException, InterruptedException{

//通过Configuration获取参数

String str = context.getConfiguration().get("grep");

if(value.toString().contains(str)){

context.write(value, NullWritable.get());

}

}

}

@Override

public int run(String[] args) throws Exception {

if(args.length!=3){

System.out.println("ERROR");

System.exit(1);

}

Configuration configuration = getConf();

//传递参数

configuration.set("grep", args[2]);

Job job = new Job(configuration,"grep");

job.setJarByClass(grep.class);

job.setMapperClass(grepMap.class);

job.setNumReduceTasks(0);

job.setMapOutputKeyClass(Text.class);

job.setOutputValueClass(NullWritable.class);

Path in = new Path(args[0]);

Path out = new Path(args[1]);

FileSystem fileSystem = out.getFileSystem(configuration);

if(fileSystem.exists(out))

fileSystem.delete(out, true);

FileInputFormat.addInputPath(job, in);

FileOutputFormat.setOutputPath(job, out);

System.exit(job.waitForCompletion(true)?0:1);

return 0;

}