通过JAVA直接读取HDFS中的时候,一定会用到FSDataInputStream类,通过FSDataInputStream以流的形式从HDFS读数据代码如下:
import java.io.IOException;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
public class FileReadFromHdfs {
public static void main(String[] args) {
try {
String dsf = "hdfs://hadoop1:9000/tmp/wordcount/kkk.txt";
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(dsf),conf);
FSDataInputStream hdfsInStream = fs.open(new Path(dsf));
byte[] ioBuffer = new byte[1024];
int readLen = hdfsInStream.read(ioBuffer);
while(readLen!=-1)
{
System.out.write(ioBuffer, 0, readLen);
readLen = hdfsInStream.read(ioBuffer);
}
hdfsInStream.close();
fs.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}