base64.cpp

IBM的解析xml的工具Xerces的源代码

/*
 * Copyright 2001,2004 The Apache 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.
 */

/*
 * $Log: Base64.cpp,v $
 * Revision 1.15  2004/09/08 13:56:21  peiyongz
 * Apache License Version 2.0
 *
 * Revision 1.14  2004/08/17 21:10:33  peiyongz
 * fix bug in getting CanRep from decode()
 *
 * Revision 1.13  2004/08/11 16:47:32  peiyongz
 * Decoding and getCanRep
 *
 * Revision 1.12  2004/06/24 15:00:37  peiyongz
 * Schema-Errata: E2-54 new specs for base64
 *
 * Revision 1.11  2003/12/17 00:18:35  cargilld
 * Update to memory management so that the static memory manager (one used to call Initialize) is only for static data.
 *
 * Revision 1.10  2003/05/20 22:10:02  peiyongz
 * To differentiate external/internal memory
 *
 * Revision 1.8  2003/01/27 21:15:56  peiyongz
 * only zero or one space allowed in between B64 character.
 *
 * Revision 1.7  2002/12/20 22:10:20  tng
 * XML 1.1
 *
 * Revision 1.6  2002/11/25 18:14:35  peiyongz
 * Schema Errata: E2-9 Base64
 *
 * Revision 1.5  2002/11/04 15:22:03  tng
 * C++ Namespace Support.
 *
 * Revision 1.4  2002/03/19 17:01:20  peiyongz
 * Fix to Bug#7243 Base64 encoding is not working.
 *
 * Revision 1.3  2002/02/18 16:07:38  peiyongz
 * fix: "i" redefined on line 428 reported by compilers on some UNIX platforms
 *
 * Revision 1.2  2002/02/15 21:36:56  peiyongz
 * Interface redefined for conversion in XMLByte
 *
 * Revision 1.1.1.1  2002/02/01 22:22:09  peiyongz
 * sane_include
 *
 * Revision 1.6  2001/10/15 19:42:16  knoaman
 * Null-terminate base64Alphabet.
 *
 * Revision 1.5  2001/10/10 19:14:08  peiyongz
 * Patch from Petr Gotthard : encode() provided and some other changes
 *
 * Revision 1.4  2001/06/07 20:55:20  tng
 * Fix no newline at the end warning.  By Pei Yong Zhang.
 *
 * Revision 1.3  2001/05/28 21:11:16  tng
 * Schema: Various DatatypeValidator fix.  By Pei Yong Zhang
 *
 * Revision 1.2  2001/05/16 19:01:04  tng
 * Schema: Typo fix in Base64
 *
 * Revision 1.1  2001/05/16 15:25:36  tng
 * Schema: Add Base64 and HexBin.  By Pei Yong Zhang.
 *
 */

// ---------------------------------------------------------------------------
//  Includes
// ---------------------------------------------------------------------------
#include <xercesc/util/Base64.hpp>
#include <xercesc/util/XMLString.hpp>
#include <xercesc/util/Janitor.hpp>
#include <xercesc/internal/XMLReader.hpp>

XERCES_CPP_NAMESPACE_BEGIN

// ---------------------------------------------------------------------------
//  constants
// ---------------------------------------------------------------------------
static const int BASELENGTH = 255;
static const int FOURBYTE   = 4;

// ---------------------------------------------------------------------------
//  class data member
// ---------------------------------------------------------------------------

// the base64 alphabet according to definition in RFC 2045
const XMLByte Base64::base64Alphabet[] = {
    chLatin_A, chLatin_B, chLatin_C, chLatin_D, chLatin_E,
    chLatin_F, chLatin_G, chLatin_H, chLatin_I, chLatin_J,
    chLatin_K, chLatin_L, chLatin_M, chLatin_N, chLatin_O,
    chLatin_P, chLatin_Q, chLatin_R, chLatin_S, chLatin_T,
    chLatin_U, chLatin_V, chLatin_W, chLatin_X, chLatin_Y, chLatin_Z,
	chLatin_a, chLatin_b, chLatin_c, chLatin_d, chLatin_e,
	chLatin_f, chLatin_g, chLatin_h, chLatin_i, chLatin_j,
	chLatin_k, chLatin_l, chLatin_m, chLatin_n, chLatin_o,
	chLatin_p, chLatin_q, chLatin_r, chLatin_s, chLatin_t,
	chLatin_u, chLatin_v, chLatin_w, chLatin_x, chLatin_y, chLatin_z,
	chDigit_0, chDigit_1, chDigit_2, chDigit_3, chDigit_4,
	chDigit_5, chDigit_6, chDigit_7, chDigit_8, chDigit_9,
	chPlus, chForwardSlash, chNull
};

XMLByte Base64::base64Inverse[BASELENGTH];

const XMLByte Base64::base64Padding = chEqual;

bool Base64::isInitialized = false;

/***
 *
 * Memory Management Issue:
 *
 * . For memory allocated for result returned to caller (external memory), 
 *   the plugged memory manager is used if it is provided, otherwise global 
 *   new used to retain the pre-memory-manager behaviour.
 *
 * . For memory allocated for temperary buffer (internal memory), 
 *   XMLPlatformUtils::fgMemoryManager is used.
 *
 */

static inline void* getExternalMemory(MemoryManager* const allocator
                                    , unsigned int const   sizeToAllocate)
{
   return allocator ? allocator->allocate(sizeToAllocate)
       : ::operator new(sizeToAllocate);
}

static inline void* getInternalMemory(unsigned int const   sizeToAllocate)
{
    return XMLPlatformUtils::fgMemoryManager->allocate(sizeToAllocate);
}

/***
 * internal memory is deallocated by janitorArray
 */ 
static inline void returnExternalMemory(MemoryManager* const allocator
                                      , void*                buffer)
{
    allocator ? allocator->deallocate(buffer)
        : ::operator delete(buffer);
}

/**
 *     E2-9
 *
 *     Canonical-base64Binary ::= (B64line* B64lastline)?
 *
 *      B64line ::= B64x15 B64x15 B64x15 B64x15 B64x15 B64 #xA
 *                  76 Base64 characters followed by newline
 *
 *      B64x15  ::= B64 B64 B64 B64 B64
 *                  B64 B64 B64 B64 B64
 *                  B64 B64 B64 B64 B64
 *
 *      B64lastline ::= B64x4? B64x4? B64x4? B64x4?
 *                      B64x4? B64x4? B64x4? B64x4?
 *                      B64x4? B64x4? B64x4? B64x4?
 *                      B64x4? B64x4? B64x4? B64x4?
 *                      B64x4? B64x4?
 *                      (B64x4 | (B64 B64 B16 '=') | (B64 B04 '=='))
 *                      #xA
 *
 *      B64x4   ::= B64 B64 B64 B64
 *      B04     ::= [AQgw]
 *      B16     ::= [AEIMQUYcgkosw048]
*/

// number of quadruplets per one line ( must be >1 and <19 )
const unsigned int Base64::quadsPerLine = 15;

XMLByte* Base64::encode(const XMLByte* const inputData
                      , const unsigned int   inputLength
                      , unsigned int*        outputLength                      
                      , MemoryManager* const memMgr)
{
    if (!isInitialized)
        init();

    if (!inputData || !outputLength)
        return 0;

    int quadrupletCount = ( inputLength + 2 ) / 3;
    if (quadrupletCount == 0)
        return 0;

    // number of rows in encoded stream ( including the last one )
    int lineCount = ( quadrupletCount + quadsPerLine-1 ) / quadsPerLine;

    //
    // convert the triplet(s) to quadruplet(s)
    //
    XMLByte  b1, b2, b3, b4;  // base64 binary codes ( 0..63 )

    unsigned int inputIndex = 0;
    unsigned int outputIndex = 0;
    XMLByte *encodedData = (XMLByte*) getExternalMemory(memMgr, (quadrupletCount*FOURBYTE+lineCount+1) * sizeof(XMLByte));

    //
    // Process all quadruplet(s) except the last
    //
    int quad = 1;
    for (; quad <= quadrupletCount-1; quad++ )
    {
        // read triplet from the input stream
        split1stOctet( inputData[ inputIndex++ ], b1, b2 );
        split2ndOctet( inputData[ inputIndex++ ], b2, b3 );
        split3rdOctet( inputData[ inputIndex++ ], b3, b4 );

        // write quadruplet to the output stream
        encodedData[ outputIndex++ ] = base64Alphabet[ b1 ];
        encodedData[ outputIndex++ ] = base64Alphabet[ b2 ];
        encodedData[ outputIndex++ ] = base64Alphabet[ b3 ];
        encodedData[ outputIndex++ ] = base64Alphabet[ b4 ];

        if (( quad % quadsPerLine ) == 0 )
            encodedData[ outputIndex++ ] = chLF;
    }

    //
    // process the last Quadruplet
    //
    // first octet is present always, process it
    split1stOctet( inputData[ inputIndex++ ], b1, b2 );
    encodedData[ outputIndex++ ] = base64Alphabet[ b1 ];

    if( inputIndex < inputLength )
    {
        // second octet is present, process it
        split2ndOctet( inputData[ inputIndex++ ], b2, b3 );
        encodedData[ outputIndex++ ] = base64Alphabet[ b2 ];

        if( inputIndex < inputLength )