Hadoop learning-- getting file system status through API-- day04

Import java.io.ByteArrayOutputStream

Import java.io.InputStream

Import java.net.URL

Import org.apache.hadoop.conf.Configuration

Import org.apache.hadoop.fs.BlockLocation

Import org.apache.hadoop.fs.FSDataInputStream

Import org.apache.hadoop.fs.FileStatus

Import org.apache.hadoop.fs.FileSystem

Import org.apache.hadoop.fs.FsUrlStreamHandlerFactory

Import org.apache.hadoop.fs.Path

Import org.apache.hadoop.io.IOUtils

Import org.junit.Test

/ * *

* Test the API of the hadoop file system

* @ author Administrator

*

, /

Public class readfilestatus {

/ * *

* read HDFS file data through filesystem object API

*

* @ author Administrator

*

* 1. Create a configuration object. Note that if some parameters are involved, you need to write and specify it in the src directory.

* 2. Using the get method of filesystem to get the filesystem object, there are three get methods (key)

* 3. Use the open method of filesystem to open a data input stream, which requires the parameter transfer of a path object (key).

* 4. Using ioutils tool class to realize the output of files

*

*

*

, /

@ Test

Public void read () throws Exception {

/ / create configuration objects, which have a default loading order, first from core-default.xml to the files in the src directory, here

/ / We have given

Configuration conf = new Configuration ()

/ / you can add the specified profile manually

/ / conf.addResource ("my-core-site.xml")

/ / the distributed file system fs is created through the configuration object of conf. By default, it is the local file system if no file is specified.

FileSystem fs = FileSystem.get (conf)

/ / define a string of URL

String file = "hdfs://hadoop01/user/hadoop/data2/demo.txt"

/ / construct a path object from a string of URL, which is actually the address of the file

Path path = new Path (file)

/ / get the status of the files under the specified path

FileStatus st = fs.getFileStatus (path)

System.out.println ("st.getBlockSize () =" + st.getBlockSize ())

System.out.println ("st.getAccessTime () =" + st.getAccessTime ())

System.out.println ("st.getGroup () =" + st.getGroup ())

System.out.println ("st.getLen () =" + st.getLen ())

System.out.println ("st.getModificationTime () =" + st.getModificationTime ())

System.out.println ("st.getOwner () =" + st.getOwner ())

System.out.println ("st.getReplication () =" + st.getReplication ())

System.out.println ("st.getClass () =" + st.getClass ())

System.out.println ("st.getPath () =" + st.getPath ())

System.out.println ("st.getPermission () =" + st.getPermission ())

System.out.println ("-")

/ / System.out.println ("st.getSymlink () =" + st.getSymlink ())

/ / get the collection of block location information for the specified file status

/ / start the entire file from 0 bytes to the full-length bytes of the entire file

BlockLocation [] locations = fs.getFileBlockLocations (st, 0, st.getLen ())

For (BlockLocation block: locations) {

System.out.println (block.getLength ())

System.out.println (block.getOffset ())

System.out.println (block.getCachedHosts ())

System.out.println (block.getHosts ())

System.out.println (block.getNames ())

System.out.println (block.getTopologyPaths ())

}

}

}