04使用api读取hdfs文件内容

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URI;
import java.net.URISyntaxException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.junit.Before;
import org.junit.Test;



public class Read {
	
FileSystem fs = null;
@Before
public void init() throws Exception {
	Configuration conf = new Configuration();
	conf.set("dfs.replication", "2");
	conf.set("dfs.blocksize", "128m");
	fs.get(new URI("hdfs://hadoop1:9000"), conf, "root");
}

/*
 * 读取hdfs中的文件内容
 */
@Test
public void testReadDate() throws Exception {
	FSDataInputStream in = fs.open(new Path("/name.txt"));		
	BufferedReader br = new BufferedReader(new InputStreamReader(in, "utf-8"));
	
	String line = null;
	while((line=br.readLine()) != null) {
		System.out.println(line);
	}
	
	in.close();
	fs.close();
}



/*
 * 读取hdfs中指定偏移量范围内的内容
 */
@Test
public void testReadSeekDate() throws Exception {
	FSDataInputStream in = fs.open(new Path("/name.txt"));
	//将读取的起始位置进行指定
	in.seek(12);
	//读取16个字节
	byte[] buf = new byte[16];
	System.out.println(new String(buf));
	
	in.close();
	fs.close();
}

}