New API multi-file input

/**
* Licensed to the Apache Software Foundation (ASF) under one
* Or more contributor license agreements. See the notice file
* Distributed with this work for additional information
* Regarding copyright ownership. The ASF licenses this file
* To you under the Apache license, version 2.0 (
* "License"); you may not use this file except T in compliance
* With the license. You may obtain a copy of the license
*
* Http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* Distributed under the license is distributed on an "as is" basis,
* Without warranties or conditions of any kind, either express or implied.
* See the license for the specific language governing permissions and
* Limitations under the license.
*/

Package org. Apache. hadoop. examples;

Import java. Io. ioexception;
Import java. util. stringtokenizer;

Import org. Apache. hadoop. conf. configured;
Import org. Apache. hadoop. fs. path;
Import org. Apache. hadoop. Io. longwritable;
Import org. Apache. hadoop. Io. text;
Import org. Apache. hadoop. mapreduce. job;
Import org. Apache. hadoop. mapreduce. mapper;
Import org. Apache. hadoop. mapreduce. Lib. Input. multipleinputs;
Import org. Apache. hadoop. mapreduce. Lib. Input. textinputformat;
Import org. Apache. hadoop. mapreduce. Lib. Output. fileoutputformat;
Import org. Apache. hadoop. util. tool;
Import org. Apache. hadoop. util. toolrunner;

/**
* Newmultifilewordcount is an example to demonstrate the usage
* Multipleinputs. This examples counts the occurrences of words in
* Text files under the given input directory.
*/
Public class newmultifilewordcount extends configured implements tool {
/**
* This mapper is similar to the one in {@ link hadooptest. mapclass }.
*/
Public static class mapclass extends mapper <longwritable, text, text, longwritable> {

Private Final Static longwritable one = new longwritable (1 );
Private text word = new text ();

Public void map (longwritable key, text value, context) throws ioexception, interruptedexception {
String line = value. tostring ();
Stringtokenizer itr = new stringtokenizer (line );
While (itr. hasmoretokens ()){
Word. Set (itr. nexttoken ());
Context. Write (word, one );
}
}
}

Private void printusage (){
System. Out. println ("Usage: multifilewc <input_dir> <output> ");
}

Public int run (string [] ARGs) throws exception {

If (ARGs. Length <2 ){
Printusage ();
Return 1;
}

Job job = new job (getconf ());
Job. setjobname ("multifilewordcount ");
Job. setjarbyclass (newmultifilewordcount. Class );
// The keys are words (strings)
Job. setoutputkeyclass (text. Class );
// The values are counts (ints)
Job. setoutputvalueclass (longwritable. Class );

// Use the wordcount CER
Job. setcombinerclass (longsumreducer. Class );
Job. setreducerclass (longsumreducer. Class );

Multipleinputs. addinputpath (job, new path (ARGs [0]), textinputformat. Class, mapclass. Class );

Multipleinputs. addinputpath (job, new path (ARGs [0]), textinputformat. Class, mapclass. Class );
Fileoutputformat. setoutputpath (job, new path (ARGs [1]);

System. Exit (job. waitforcompletion (true )? 0: 1 );

Return 0;
}

Public static void main (string [] ARGs) throws exception {
Int ret = toolrunner. Run (New newmultifilewordcount (), argS );
System. Exit (RET );
}

}

If the error occurs, please advise me !!!