base64.cpp

IBM的解析xml的工具Xerces的源代码

        {
            // third octet present, process it
            // no PAD e.g. 3cQl
            split3rdOctet( inputData[ inputIndex++ ], b3, b4 );
            encodedData[ outputIndex++ ] = base64Alphabet[ b3 ];
            encodedData[ outputIndex++ ] = base64Alphabet[ b4 ];
        }
        else
        {
            // third octet not present
            // one PAD e.g. 3cQ=
            encodedData[ outputIndex++ ] = base64Alphabet[ b3 ];
            encodedData[ outputIndex++ ] = base64Padding;
        }
    }
    else
    {
        // second octet not present
        // two PADs e.g. 3c==
        encodedData[ outputIndex++ ] = base64Alphabet[ b2 ];
        encodedData[ outputIndex++ ] = base64Padding;
        encodedData[ outputIndex++ ] = base64Padding;
    }

    // write out end of the last line
    encodedData[ outputIndex++ ] = chLF;
    // write out end of string
    encodedData[ outputIndex ] = 0;

    *outputLength = outputIndex;

    return encodedData;
}

//
// delete the buffer allocated by decode() if
// decoding is successfully done.
//
// In previous version, we use XMLString::strLen(decodedData)
// to get the length, this will fail for test case containing
// consequtive "A", such "AAFF", or "ab56AA56". Instead of
// returning 3/6, we have 0 and 3, indicating that "AA", after
// decoded, is interpreted as <null> by the strLen().
//
// Since decode() has track of length of the decoded data, we
// will get this length from decode(), instead of strLen().
//
int Base64::getDataLength(const XMLCh*         const inputData
                        ,       MemoryManager* const manager
                        ,       Conformance          conform )

{
    unsigned int    retLen = 0;
    XMLCh* decodedData = decode(inputData, &retLen, manager, conform);

    if ( !decodedData )
        return -1;
    else
    {
        returnExternalMemory(manager, decodedData);
        return retLen;
    }
}

XMLByte* Base64::decode(const XMLByte*       const  inputData
                      ,       unsigned int*         decodedLength
                      ,       MemoryManager* const  memMgr
                      ,       Conformance           conform )
{
    XMLByte* canRepInByte = 0;
    XMLByte* retStr = decode(
                              inputData
                            , decodedLength
                            , canRepInByte
                            , memMgr
                            , conform);

    /***
     * Release the canRepData
     */ 
    if (retStr)
        returnExternalMemory(memMgr, canRepInByte);

    return retStr;
}

XMLCh* Base64::decode(const XMLCh*         const   inputData
                    ,       unsigned int*          decodedLen
                    ,       MemoryManager* const   memMgr
                    ,       Conformance            conform )
{
	if (!inputData)
		return 0;

    /***
     *  Move input data to a XMLByte buffer
     */
	unsigned int srcLen = XMLString::stringLen(inputData);
    XMLByte *dataInByte = (XMLByte*) getExternalMemory(memMgr, (srcLen+1) * sizeof(XMLByte));
    ArrayJanitor<XMLByte> janFill(dataInByte, memMgr ? memMgr : XMLPlatformUtils::fgMemoryManager);

    for (unsigned int i = 0; i < srcLen; i++)
		dataInByte[i] = (XMLByte)inputData[i];

	dataInByte[srcLen] = 0;

    /***
     * Forward to the actual decoding method to do the decoding
     */
	*decodedLen = 0;
	XMLByte *DecodedBuf = decode(dataInByte, decodedLen, memMgr, conform);

	if (!DecodedBuf)
		return 0;

    /***
     * Move decoded data to a XMLCh buffer to return
     */
    XMLCh *toRet = (XMLCh*) getExternalMemory(memMgr, (*decodedLen+1) * sizeof(XMLCh));
               
    for (unsigned int j = 0; j < *decodedLen; j++)
		toRet[j] = (XMLCh)DecodedBuf[j];

	toRet[*decodedLen] = 0;

    /***
     * Release the memory allocated in the actual decoding method
     */ 
    returnExternalMemory(memMgr, DecodedBuf);

    return toRet;
}

/***
* E2-54
*
* Canonical-base64Binary ::= (B64 B64 B64 B64)*((B64 B64 B16 '=')|(B64 B04 '=='))? 
* B04                    ::= [AQgw]
* B16                    ::= [AEIMQUYcgkosw048]
* B64                    ::= [A-Za-z0-9+/] 
*
***/
XMLCh* Base64::getCanonicalRepresentation(const XMLCh*         const   inputData
                                        ,       MemoryManager* const   memMgr
                                        ,       Conformance            conform)
    
{
	if (!inputData || !*inputData) 
		return 0;

    /***
     *  Move input data to a XMLByte buffer
     */
	unsigned int srcLen = XMLString::stringLen(inputData);
    XMLByte *dataInByte = (XMLByte*) getExternalMemory(memMgr, (srcLen+1) * sizeof(XMLByte));
    ArrayJanitor<XMLByte> janFill(dataInByte, memMgr ? memMgr : XMLPlatformUtils::fgMemoryManager);

    for (unsigned int i = 0; i < srcLen; i++)
		dataInByte[i] = (XMLByte)inputData[i];

	dataInByte[srcLen] = 0;

    /***
     * Forward to the actual decoding method to do the decoding
     */
	unsigned int decodedLength = 0;
    XMLByte*     canRepInByte = 0;
    XMLByte*     retStr = decode(
                              dataInByte
                            , &decodedLength
                            , canRepInByte
                            , memMgr
                            , conform);

    if (!retStr)
        return 0;

    /***
     * Move canonical representation to a XMLCh buffer to return
     */
    unsigned int canRepLen = XMLString::stringLen((char*)canRepInByte);
    XMLCh *canRepData = (XMLCh*) getExternalMemory(memMgr, (canRepLen + 1) * sizeof(XMLCh));
               
    for (unsigned int j = 0; j < canRepLen; j++)
		canRepData[j] = (XMLCh)canRepInByte[j];

	canRepData[canRepLen] = 0;

    /***
     * Release the memory allocated in the actual decoding method
     */ 
    returnExternalMemory(memMgr, retStr);
    returnExternalMemory(memMgr, canRepInByte);

    return canRepData;
}
// -----------------------------------------------------------------------
//  Helper methods
// -----------------------------------------------------------------------

//
// return 0(null) if invalid data found.
// return the buffer containning decoded data otherwise
// the caller is responsible for the de-allocation of the
// buffer returned.
//
// temporary data, rawInputData, is ALWAYS released by this function.
//

/***
 *     E2-9
 *
 *     Base64Binary ::= S? B64quartet* B64final?
 *
 *     B64quartet   ::= B64 S? B64 S? B64 S? B64 S?
 *
 *     B64final     ::= B64 S? B04 S? '=' S? '=' S?
 *                    | B64 S? B64 S? B16 S? '=' S?
 *
 *     B04          ::= [AQgw]
 *     B16          ::= [AEIMQUYcgkosw048]
 *     B64          ::= [A-Za-z0-9+/]
 *
 *
 *     E2-54
 *
 *     Base64Binary  ::=  ((B64S B64S B64S B64S)*
 *                         ((B64S B64S B64S B64) |
 *                          (B64S B64S B16S '=') |
 *                          (B64S B04S '=' #x20? '=')))?
 *
 *     B64S         ::= B64 #x20?
 *     B16S         ::= B16 #x20?
 *     B04S         ::= B04 #x20?
 *
 *
 *     Note that this grammar requires the number of non-whitespace characters 
 *     in the lexical form to be a multiple of four, and for equals signs to 
 *     appear only at the end of the lexical form; strings which do not meet these 
 *     constraints are not legal lexical forms of base64Binary because they 
 *     cannot successfully be decoded by base64 decoders.
 * 
 *     Note: 
 *     The above definition of the lexical space is more restrictive than that given 
 *     in [RFC 2045] as regards whitespace -- this is not an issue in practice. Any 
 *     string compatible with the RFC can occur in an element or attribute validated 
 *     by this type, because the 穡hiteSpace