基於JAVA的HDFS文件操作(擴展實驗2)
一、先啓動Hadoop
./sbin/start-dfs.sh
出現以下界面說明啓動成功
二、編程實現一個類“MyFSDataInputStream”,該類繼承“org.apache.hadoop.fs.FSDataInputStream”,要求如下:實現按行讀取HDFS中指定文件的方法“readLine()”,如果讀到文件末尾,則返回空,否則返回文件一行的文本。
1.代碼如下:
package test2;
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 java.io.*;
public class MyFSDataInputStream extends FSDataInputStream {
public MyFSDataInputStream(InputStream in) {
super(in);
}
/**
*實現按行讀取
*每次讀入一個字符,遇到"n"結束,返回一行內容
*/
public static String readline(BufferedReader br) throws IOException {
char[] data = new char[1024];
int read = -1;
int off = 0; //循環執行時,br每次會從上- -次讀取結束的位置繼續讀取,因此該函數裏,off每次都從0開始
while ( (read = br.read(data, off, 1)) != -1 ) {
if (String.valueOf(data[off]).equals("\n") ) {
off += 1;
break;
}
off += 1;
}
if (off> 0) {
return String.valueOf( data);
} else {
return null;
}
}
/**
*讀取文件內容
*/
public static void cat(Configuration conf, String remoteFilePath) throws IOException {
FileSystem fs = FileSystem.get(conf);
Path remotePath = new Path(remoteFilePath);
FSDataInputStream in = fs.open(remotePath);
BufferedReader br = new BufferedReader(new InputStreamReader(in));
String line = null;
while ( (line = MyFSDataInputStream.readline(br)) != null ) {
System.out.println(line);
}
br.close();
in.close();
fs.close();
}
/**
*主函數
*/
public static void main(String[] args) {
Configuration conf = new Configuration();
conf.set(" fs.default.name", "hdfs://localhost:9000");
String remoteFilePath = "/user/hadoop/file/text.txt"; // HDFS路徑
try {
MyFSDataInputStream.cat(conf,remoteFilePath);
} catch (Exception e) {
e.printStackTrace();
}
}
}
2.運行結果:
三、查看Java幫助手冊或其它資料,用”java.net.URL”和“org.apache.hadoop.fs.FsURLStreamHandlerFactory”編程完成輸出HDFS中指定文件的文本到終端中。
1.代碼如下:
package test2;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import java.io.*;
import java.net.URL;
public class HDFSApi {
static {
URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
}
/**
* 主函數
*/
public static void main(String[] args) throws Exception {
String remoteFilePath = "hdfs://localhost:9000/user/hadoop/file/text.txt"; // HDFS 文件
InputStream in = null;
try {
/* 通過 URL 對象打開數據流,從中讀取數據 */
in = new URL(remoteFilePath).openStream();
IOUtils.copyBytes(in, System.out, 4096, false);
} finally {
IOUtils.closeStream(in);
}
}
}
運行結果: