How to use Combinefileinputformat to import Netflix data set into HBase

Package com.mr.test;  
      
Import java.io.IOException;  
Import org.apache.hadoop.io.BytesWritable;  
Import org.apache.hadoop.io.LongWritable;  
Import Org.apache.hadoop.mapreduce.InputSplit;  
Import Org.apache.hadoop.mapreduce.RecordReader;  
Import Org.apache.hadoop.mapreduce.TaskAttemptContext;  
Import Org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat;  
Import Org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader;  
      
Import Org.apache.hadoop.mapreduce.lib.input.CombineFileSplit;  
      
    public class Combinesmallfileinputformat extends Combinefileinputformat<longwritable, byteswritable> { @Override public recordreader<longwritable, byteswritable> Createrecordreader (Inputsplit split, Taskattemptcontext context) throws IOException {Combinefilesplit combinefilesplit = (combinefilesplit) s  
        Plit; Combinefilerecordreader<longwritable, byteswritable> recordreader = new combinefilerecordreader<Longwritable, byteswritable> (combinefilesplit, context, combinesmallfilerecordreader.class);  
        try {recordreader.initialize (combinefilesplit, context); The catch (Interruptedexception e) {new RuntimeException ("Error to initialize Combinesmallfilerecordreader.")  
        );  
    return recordreader; }  
      
}

Package com.mr.test;  
      
Import java.io.IOException;  
Import Org.apache.hadoop.fs.Path;  
Import org.apache.hadoop.io.BytesWritable;  
Import org.apache.hadoop.io.LongWritable;  
Import Org.apache.hadoop.mapreduce.InputSplit;  
Import Org.apache.hadoop.mapreduce.RecordReader;  
Import Org.apache.hadoop.mapreduce.TaskAttemptContext;  
Import Org.apache.hadoop.mapreduce.lib.input.CombineFileSplit;  
Import Org.apache.hadoop.mapreduce.lib.input.FileSplit;  
      
Import Org.apache.hadoop.mapreduce.lib.input.LineRecordReader; public class Combinesmallfilerecordreader extends Recordreader<longwritable, byteswritable> {private C  
    Ombinefilesplit Combinefilesplit;  
    Private Linerecordreader Linerecordreader = new Linerecordreader ();  
    Private path[] paths;  
    private int totallength;  
    private int currentindex;  
    private float currentprogress = 0;  
    Private Longwritable Currentkey; Private byteswritable CurrentValue = new BYTESWRItable (); Public Combinesmallfilerecordreader (Combinefilesplit combinefilesplit, Taskattemptcontext context, Integer index)  
        Throws IOException {super ();  
        This.combinefilesplit = Combinefilesplit; This.currentindex = index; The small file block currently being processed is indexed in Combinefilesplit} @Override public void Initialize (Inputsplit split, Taskatt Emptcontext context) throws IOException, interruptedexception {this.combinefilesplit = (combinefilesplit) split  
        ; Handles a small file block in Combinefilesplit, because using Linerecordreader, you need to construct a Filesplit object before you can read the data filesplit filesplit = new Fil Esplit (Combinefilesplit.getpath (Currentindex), Combinefilesplit.getoffset (Currentindex),  
        Combinefilesplit.getlength (Currentindex), combinefilesplit.getlocations ());  
      
        Linerecordreader.initialize (filesplit, context);  
        This.paths = Combinefilesplit.getpaths ();  
        Totallength = Paths.length; Context.getconfiguration (). Set ("Map.input.file.name", Combinefilesplit.getpath (Currentindex). GetName ()); @Override public longwritable Getcurrentkey () throws IOException, interruptedexception {Curr  
        Entkey = Linerecordreader.getcurrentkey ();  
    return currentkey; } <strong><span style= "color: #ff0000;" > @Override public byteswritable getcurrentvalue () throws IOException, interruptedexception {System.ou  
        T.println ("Linerecordreader:" +linerecordreader.getcurrentvalue (). toString ());  
        byte[] content = Linerecordreader.getcurrentvalue (). toString (). GetBytes ();  
        System.out.println ("Content:" +new String (content));  
        CurrentValue = new Byteswritable ();  
        Currentvalue.set (content, 0, content.length);  
        System.out.println ("CurrentValue:" +new String (Currentvalue.getbytes ()));  
    return currentvalue; }</span></strong> public static void Main (String args[]) {byteswritable CV = new byteswritable ();  
        String str1 = "1234567";  
        String str2 = "123450";  
        Cv.set (Str1.getbytes (), 0, Str1.getbytes (). length);  
              
        System.out.println (New String (Cv.getbytes ()));  
              
        Cv.setcapacity (0);  
        Cv.set (Str2.getbytes (), 0, Str2.getbytes (). length);  
    System.out.println (New String (Cv.getbytes ())); @Override public boolean Nextkeyvalue () throws IOException, interruptedexception {if (currentindex  
        >= 0 && Currentindex < totallength) {return linerecordreader.nextkeyvalue ();  
        else {return false; @Override public float getprogress () throws IOException {if Currentindex >= 0 &A  
            mp;& Currentindex < totallength) {currentprogress = (float) currentindex/totallength;  
        return currentprogress; Return to currentProgress;  
    @Override public void Close () throws IOException {linerecordreader.close (); }  
}

More Wonderful content: http://www.bianceng.cnhttp://www.bianceng.cn/database/extra/