All Downloads are FREE. Search and download functionalities are using the official Maven repository.

ml.shifu.guagua.io.GuaguaRecordReader Maven / Gradle / Ivy

There is a newer version: 0.7.10
Show newest version
/*
 * Copyright [2013-2014] eBay Software Foundation
 *  
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *    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 ml.shifu.guagua.io;

import java.io.IOException;

import ml.shifu.guagua.worker.AbstractWorkerComputable;

/**
 * {@link GuaguaRecordReader} is used for consistent interface to iterate data through FileSplit provided. The typical
 * implementation is HDFS implementation in guagua-mapreduce.
 * 
 * 

* To use it, one should set implementation in {@link AbstractWorkerComputable}. * * @param * key type for each record * @param * value type for each record */ public interface GuaguaRecordReader { /** * Initialize file split for user to create relative reader instance. */ void initialize(GuaguaFileSplit split) throws IOException; /** * Cursor shift to next and set current key value. */ boolean nextKeyValue() throws IOException; /** * Tmp we only support LongWritable key for byte offset in each line, follow LineRecordReader in hadoop. */ KEY getCurrentKey(); /** * Tmp we only support Text value for whole content in each line, follow LineRecordReader in hadoop. */ VALUE getCurrentValue(); /** * Close resources at last, for example file descriptors. Should be called in finally segment. */ void close() throws IOException; }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy