/*
* 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 (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 org.apache.hadoop.io.compress;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
/**
* Specification of a stream-based 'compressor' which can be
* plugged into a {@link CompressionOutputStream} to compress data.
* This is modelled after {@link java.util.zip.Deflater}
*
*/
public interface Compressor {
/**
* Sets input data for compression.
* This should be called whenever #needsInput() returns
* <code>true</code> indicating that more input data is required.
*
* @param b Input data
* @param off Start offset
* @param len Length
*/
//通过setInput()接收数据到内部缓存区 可以多次调用该方法
public void setInput(byte[] b, int off, int len);
/**
* Returns true if the input data buffer is empty and
* #setInput() should be called to provide more input.
*
* @return <code>true</code> if the input data buffer is empty and
* #setInput() should be called in order to provide more input.
*/
//返回false表示内部缓存已经满了 此时必须通过compress()方法获取压缩后的数据
public boolean needsInput();
/**
* Sets preset dictionary for compression. A preset dictionary
* is used when the history buffer can be predetermined.
*
* @param b Dictionary data bytes
* @param off Start offset
* @param len Length
*/
public void setDictionary(byte[] b, int off, int len);
/**
* Return number of uncompressed bytes input so far.
*/
//获得compressor()输入没有压缩字节的总数
public long getBytesRead();
/**
* Return number of compressed bytes output so far.
*/
//输出压缩自己的总数
public long getBytesWritten();
/**
* When called, indicates that compression should end
* with the current contents of the input buffer.
*/
//调用finish()就开始压缩
public void finish();
/**
* Returns true if the end of the compressed
* data output stream has been reached.
* @return <code>true</code> if the end of the compressed
* data output stream has been reached.
*/
//判断压缩器里是不是还有没有压缩的数据
public boolean finished();
/**
* Fills specified buffer with compressed data. Returns actual number
* of bytes of compressed data. A return value of 0 indicates that
* needsInput() should be called in order to determine if more input
* data is required.
*
* @param b Buffer for the compressed data
* @param off Start offset of the data
* @param len Size of the buffer
* @return The actual number of bytes of compressed data.
*/
public int compress(byte[] b, int off, int len) throws IOException;
/**
* Resets compressor so that a new set of input data can be processed.
*/
//用与重置压缩器 以处理新的输入数据集合
public void reset();
/**
* Closes the compressor and discards any unprocessed input.
*/
//关闭解压缩器并放弃所有没有处理的输入
public void end();
/**
* Prepare the compressor to be used in a new stream with settings defined in
* the given Configuration
*
* @param conf Configuration from which new setting are fetched
*/
//更进一步允许使用hadoop的配置系统 重新配置压缩器
public void reinit(Configuration conf);
}