bytechunk.java

Tomcat 4.1与WebServer集成组件的源代码包.

/*
 * ====================================================================
 *
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 1999 The Apache Software Foundation.  All rights 
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer. 
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution, if
 *    any, must include the following acknowlegement:  
 *       "This product includes software developed by the 
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowlegement may appear in the software itself,
 *    if and wherever such third-party acknowlegements normally appear.
 *
 * 4. The names "The Jakarta Project", "Tomcat", and "Apache Software
 *    Foundation" must not be used to endorse or promote products derived
 *    from this software without prior written permission. For written 
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache"
 *    nor may "Apache" appear in their names without prior written
 *    permission of the Apache Group.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 * [Additional notices, if required by prior licensing conditions]
 *
 */ 

package org.apache.tomcat.util.buf;

import java.text.*;
import java.util.*;
import java.io.Serializable;
import java.io.IOException;

/*
 * In a server it is very important to be able to operate on
 * the original byte[] without converting everything to chars.
 * Some protocols are ASCII only, and some allow different
 * non-UNICODE encodings. The encoding is not known beforehand,
 * and can even change during the execution of the protocol.
 * ( for example a multipart message may have parts with different
 *  encoding )
 *
 * For HTTP it is not very clear how the encoding of RequestURI
 * and mime values can be determined, but it is a great advantage
 * to be able to parse the request without converting to string.
 */


/**
 * This class is used to represent a chunk of bytes, and
 * utilities to manipulate byte[].
 *
 * The buffer can be modified and used for both input and output.
 *
 * @author [e-mail]
 * @author James Todd [[e-mail]]
 * @author Costin Manolache
 * @author Remy Maucherat
 */
public final class ByteChunk implements Cloneable, Serializable {

    // Input interface, used when the buffer is emptied.
    public static interface ByteInputChannel {
        /** 
         * Read new bytes ( usually the internal conversion buffer ).
         * The implementation is allowed to ignore the parameters, 
         * and mutate the chunk if it wishes to implement its own buffering.
         */
        public int realReadBytes(byte cbuf[], int off, int len)
            throws IOException;
    }
    // Output interface, used when the buffer is filled.
    public static interface ByteOutputChannel {
        /** 
         * Send the bytes ( usually the internal conversion buffer ).
         * Expect 8k output if the buffer is full.
         */
        public void realWriteBytes(byte cbuf[], int off, int len)
            throws IOException;
    }

    // --------------------

    /** Default encoding used to convert to strings. It should be UTF8,
	as most standards seem to converge, but the servlet API requires
	8859_1, and this object is used mostly for servlets. 
    */
    public static final String DEFAULT_CHARACTER_ENCODING="ISO-8859-1";
        
    // byte[]
    private byte[] buff;

    private int start=0;
    private int end;

    private String enc;

    private boolean isSet=false; // XXX

    // How much can it grow, when data is added
    private int limit=-1;

    private ByteInputChannel in = null;
    private ByteOutputChannel out = null;

    private boolean isOutput=false;
    
    /**
     * Creates a new, uninitialized ByteChunk object.
     */
    public ByteChunk() {
    }

    public ByteChunk( int initial ) {
	allocate( initial, -1 );
    }

    //--------------------
        public ByteChunk getClone() {
	try {
	    return (ByteChunk)this.clone();
	} catch( Exception ex) {
	    return null;
	}
    }

    public boolean isNull() {
	return ! isSet; // buff==null;
    }
    
    /**
     * Resets the message buff to an uninitialized state.
     */
    public void recycle() {
	//	buff = null;
	enc=null;
	start=0;
	end=0;
	isSet=false;
    }

    public void reset() {
	buff=null;
    }

    // -------------------- Setup --------------------

    public void allocate( int initial, int limit  ) {
	isOutput=true;
	if( buff==null || buff.length < initial ) {
	    buff=new byte[initial];
	}    
	this.limit=limit;
	start=0;
	end=0;
	isSet=true;
    }

    /**
     * Sets the message bytes to the specified subarray of bytes.
     * 
     * @param b the ascii bytes
     * @param off the start offset of the bytes
     * @param len the length of the bytes
     */
    public void setBytes(byte[] b, int off, int len) {
	buff = b;
	start = off;
	end = start+ len;
	isSet=true;
    }

    public void setEncoding( String enc ) {
	this.enc=enc;
    }

    /**
     * Returns the message bytes.
     */
    public byte[] getBytes() {
	return getBuffer();
    }

    /**
     * Returns the message bytes.
     */
    public byte[] getBuffer() {
	return buff;
    }

    /**
     * Returns the start offset of the bytes.
     * For output this is the end of the buffer.
     */
    public int getStart() {
	return start;
    }

    public int getOffset() {
	return getStart();
    }

    public void setOffset(int off) {
        if (end < off ) end=off;
	start=off;
    }

    /**
     * Returns the length of the bytes.
     * XXX need to clean this up
     */
    public int getLength() {
	return end-start;
    }

    /** Maximum amount of data in this buffer.
     *
     *  If -1 or not set, the buffer will grow undefinitely.
     *  Can be smaller than the current buffer size ( which will not shrink ).
     *  When the limit is reached, the buffer will be flushed ( if out is set )
     *  or throw exception.
     */
    public void setLimit(int limit) {
	this.limit=limit;
    }
    
    public int getLimit() {
	return limit;
    }

    /**
     * When the buffer is empty, read the data from the input channel.
     */
    public void setByteInputChannel(ByteInputChannel in) {
        this.in = in;
    }

    /** When the buffer is full, write the data to the output channel.
     * 	Also used when large amount of data is appended.
     *
     *  If not set, the buffer will grow to the limit.
     */
    public void setByteOutputChannel(ByteOutputChannel out) {
	this.out=out;
    }

    public int getEnd() {
	return end;
    }

    public void setEnd( int i ) {
	end=i;
    }

    // -------------------- Adding data to the buffer --------------------
    public void append( char c )
	throws IOException
    {
	append( (byte)c);
    }

    public void append( byte b )
	throws IOException
    {
	makeSpace( 1 );

	// couldn't make space
	if( limit >0 && end >= limit ) {
	    flushBuffer();
	}
	buff[end++]=b;
    }

    public void append( ByteChunk src )
	throws IOException
    {
	append( src.getBytes(), src.getStart(), src.getLength());
    }

    /** Add data to the buffer
     */
    public void append( byte src[], int off, int len )
	throws IOException
    {
	// will grow, up to limit
	makeSpace( len );

	// if we don't have limit: makeSpace can grow as it wants
	if( limit < 0 ) {
	    // assert: makeSpace made enough space
	    System.arraycopy( src, off, buff, end, len );
	    end+=len;
	    return;
	}

	// if we have limit and we're below
	if( len <= limit - end ) {
	    // makeSpace will grow the buffer to the limit,
	    // so we have space
	    System.arraycopy( src, off, buff, end, len );
	    end+=len;
	    return;
	}

	// need more space than we can afford, need to flush
	// buffer

	// the buffer is already at ( or bigger than ) limit

	// Optimization:
	// If len-avail < length ( i.e. after we fill the buffer with
	// what we can, the remaining will fit in the buffer ) we'll just
	// copy the first part, flush, then copy the second part - 1 write
	// and still have some space for more. We'll still have 2 writes, but
	// we write more on the first.

	if( len + end < 2 * limit ) {
	    /* If the request length exceeds the size of the output buffer,
	       flush the output buffer and then write the data directly.
	       We can't avoid 2 writes, but we can write more on the second
	    */
	    int avail=limit-end;
	    System.arraycopy(src, off, buff, end, avail);
	    end += avail;

	    flushBuffer();

	    System.arraycopy(src, off+avail, buff, end, len - avail);
	    end+= len - avail;

	} else {	// len > buf.length + avail
	    // long write - flush the buffer and write the rest
	    // directly from source
	    flushBuffer();
	    
	    out.realWriteBytes( src, off, len );
	}
    }


    // -------------------- Removing data from the buffer --------------------

    public int substract()
        throws IOException {

        if ((end - start) == 0) {
            if (in == null)
                return -1;
            int n = in.realReadBytes( buff, 0, buff.length );
            if (n < 0)
                return -1;
        }

        return (buff[start++] & 0xFF);

    }

    public int substract(ByteChunk src)
        throws IOException {

        if ((end - start) == 0) {
            if (in == null)
                return -1;
            int n = in.realReadBytes( buff, 0, buff.length );
            if (n < 0)
                return -1;
        }