cpl_string.cpp

用于读取TAB、MIF、SHP文件的类

 * or to write within a text stream but in a form that can be
 * reconstitued to it's original form.  The escaping will even preserve
 * zero bytes allowing preservation of raw binary data.
 *
 * CPLES_BackslashQuotable(0): This scheme turns a binary string into 
 * a form suitable to be placed within double quotes as a string constant.
 * The backslash, quote, '\0' and newline characters are all escaped in 
 * the usual C style. 
 *
 * CPLES_XML(1): This scheme converts the '<', '<' and '&' characters into
 * their XML/HTML equivelent (&gt;, &lt; and &amp;) making a string safe
 * to embed as CDATA within an XML element.  The '\0' is not escaped and 
 * should not be included in the input.
 *
 * CPLES_URL(2): Everything except alphanumerics and the underscore are 
 * converted to a percent followed by a two digit hex encoding of the character
 * (leading zero supplied if needed).  This is the mechanism used for encoding
 * values to be passed in URLs.
 *
 * CPLES_SQL(3): All single quotes are replaced with two single quotes.  
 * Suitable for use when constructing literal values for SQL commands where
 * the literal will be enclosed in single quotes.
 *
 * CPLES_CSV(4): If the values contains commas, double quotes, or newlines it 
 * placed in double quotes, and double quotes in the value are doubled.
 * Suitable for use when constructing field values for .csv files.  Note that
 * CPLUnescapeString() currently does not support this format, only 
 * CPLEscapeString().  See cpl_csv.cpp for csv parsing support.
 *
 * @param pszInput the string to escape.  
 * @param nLength The number of bytes of data to preserve.  If this is -1
 * the strlen(pszString) function will be used to compute the length.
 * @param nScheme the encoding scheme to use.  
 *
 * @return an escaped, zero terminated string that should be freed with 
 * CPLFree() when no longer needed.
 */

char *CPLEscapeString( const char *pszInput, int nLength, 
                       int nScheme )

{
    char        *pszOutput;
    char        *pszShortOutput;

    if( nLength == -1 )
        nLength = strlen(pszInput);

    pszOutput = (char *) CPLMalloc( nLength * 6 + 1 );
    
    if( nScheme == CPLES_BackslashQuotable )
    {
        int iOut = 0, iIn;

        for( iIn = 0; iIn < nLength; iIn++ )
        {
            if( pszInput[iIn] == '\0' )
            {
                pszOutput[iOut++] = '\\';
                pszOutput[iOut++] = '0';
            }
            else if( pszInput[iIn] == '\n' )
            {
                pszOutput[iOut++] = '\\';
                pszOutput[iOut++] = 'n';
            }
            else if( pszInput[iIn] == '"' )
            {
                pszOutput[iOut++] = '\\';
                pszOutput[iOut++] = '\"';
            }
            else if( pszInput[iIn] == '\\' )
            {
                pszOutput[iOut++] = '\\';
                pszOutput[iOut++] = '\\';
            }
            else
                pszOutput[iOut++] = pszInput[iIn];
        }
        pszOutput[iOut] = '\0';
    }
    else if( nScheme == CPLES_URL ) /* Untested at implementation */
    {
        int iOut = 0, iIn;

        for( iIn = 0; iIn < nLength; iIn++ )
        {
            if( (pszInput[iIn] >= 'a' && pszInput[iIn] <= 'z')
                || (pszInput[iIn] >= 'A' && pszInput[iIn] <= 'Z')
                || (pszInput[iIn] >= '0' && pszInput[iIn] <= '9')
                || pszInput[iIn] == '_' )
            {
                pszOutput[iOut++] = pszInput[iIn];
            }
            else
            {
                sprintf( pszOutput, "%%%02X", pszInput[iIn] );
                iOut += 3;
            }
        }
        pszOutput[iOut] = '\0';
    }
    else if( nScheme == CPLES_XML )
    {
        int iOut = 0, iIn;

        for( iIn = 0; iIn < nLength; iIn++ )
        {
            if( pszInput[iIn] == '<' )
            {
                pszOutput[iOut++] = '&';
                pszOutput[iOut++] = 'l';
                pszOutput[iOut++] = 't';
                pszOutput[iOut++] = ';';
            }
            else if( pszInput[iIn] == '>' )
            {
                pszOutput[iOut++] = '&';
                pszOutput[iOut++] = 'g';
                pszOutput[iOut++] = 't';
                pszOutput[iOut++] = ';';
            }
            else if( pszInput[iIn] == '&' )
            {
                pszOutput[iOut++] = '&';
                pszOutput[iOut++] = 'a';
                pszOutput[iOut++] = 'm';
                pszOutput[iOut++] = 'p';
                pszOutput[iOut++] = ';';
            }
            else if( pszInput[iIn] == '"' )
            {
                pszOutput[iOut++] = '&';
                pszOutput[iOut++] = 'q';
                pszOutput[iOut++] = 'u';
                pszOutput[iOut++] = 'o';
                pszOutput[iOut++] = 't';
                pszOutput[iOut++] = ';';
            }
            else
                pszOutput[iOut++] = pszInput[iIn];
        }
        pszOutput[iOut] = '\0';
    }
    else if( nScheme == CPLES_SQL )
    {
        int iOut = 0, iIn;

        for( iIn = 0; iIn < nLength; iIn++ )
        {
            if( pszInput[iIn] == '\'' )
            {
                pszOutput[iOut++] = '\'';
                pszOutput[iOut++] = '\'';
            }
            else
                pszOutput[iOut++] = pszInput[iIn];
        }
        pszOutput[iOut] = '\0';
    }
    else if( nScheme == CPLES_CSV )
    {
        if( strchr( pszInput, '\"' ) == NULL
            && strchr( pszInput, ',') == NULL
            && strchr( pszInput, 10) == NULL 
            && strchr( pszInput, 13) == NULL )
        {
            strcpy( pszOutput, pszInput );
        }
        else
        {
            int iOut = 1, iIn;

            pszOutput[0] = '\"';

            for( iIn = 0; iIn < nLength; iIn++ )
            {
                if( pszInput[iIn] == '\"' )
                {
                    pszOutput[iOut++] = '\"';
                    pszOutput[iOut++] = '\"';
                }
                else if( pszInput[iIn] == 13 )
                    /* drop DOS LF's in strings. */;
                else
                    pszOutput[iOut++] = pszInput[iIn];
            }
            pszOutput[iOut++] = '\"';
            pszOutput[iOut++] = '\0';
        }
    }
    else
    {
        pszOutput[0] = '\0';
        CPLError( CE_Failure, CPLE_AppDefined, 
                  "Undefined escaping scheme (%d) in CPLEscapeString()",
                  nScheme );
    }

    pszShortOutput = CPLStrdup( pszOutput );
    CPLFree( pszOutput );

    return pszShortOutput;
}

/************************************************************************/
/*                         CPLUnescapeString()                          */
/************************************************************************/

/**
 * Unescape a string.
 *
 * This function does the opposite of CPLEscapeString().  Given a string
 * with special values escaped according to some scheme, it will return a
 * new copy of the string returned to it's original form. 
 *
 * @param pszInput the input string.  This is a zero terminated string.
 * @param pnLength location to return the length of the unescaped string, 
 * which may in some cases include embedded '\0' characters.
 * @param nScheme the escaped scheme to undo (see CPLEscapeString() for a
 * list). 
 * 
 * @return a copy of the unescaped string that should be freed by the 
 * application using CPLFree() when no longer needed.
 */

char *CPLUnescapeString( const char *pszInput, int *pnLength, int nScheme )

{
    char *pszOutput;
    int iOut=0, iIn;

    pszOutput = (char *) CPLMalloc(strlen(pszInput)+1);
    pszOutput[0] = '\0';

    if( nScheme == CPLES_XML )
    {
        for( iIn = 0; pszInput[iIn] != '\0'; iIn++ )
        {
            if( EQUALN(pszInput+iIn,"&lt;",4) )
            {
                pszOutput[iOut++] = '<';
                iIn += 3;
            }
            else if( EQUALN(pszInput+iIn,"&gt;",4) )
            {
                pszOutput[iOut++] = '>';
                iIn += 3;
            }
            else if( EQUALN(pszInput+iIn,"&amp;",5) )
            {
                pszOutput[iOut++] = '&';
                iIn += 4;
            }
            else if( EQUALN(pszInput+iIn,"&quot;",6) )
            {
                pszOutput[iOut++] = '"';
                iIn += 5;
            }
            else
            {
                pszOutput[iOut++] = pszInput[iIn];
            }
        }
    }
    else if( nScheme == CPLES_URL )
    {
        for( iIn = 0; pszInput[iIn] != '\0'; iIn++ )
        {
            if( pszInput[iIn] == '%' 
                && pszInput[iIn+1] != '\0' 
                && pszInput[iIn+2] != '\0' )
            {
                int nHexChar = 0;

                if( pszInput[iIn+1] >= 'A' && pszInput[iIn+1] <= 'F' )
                    nHexChar += 16 * (pszInput[iIn+1] - 'A' + 10);
                else if( pszInput[iIn+1] >= 'a' && pszInput[iIn+1] <= 'f' )
                    nHexChar += 16 * (pszInput[iIn+1] - 'a' + 10);
                else if( pszInput[iIn+1] >= '0' && pszInput[iIn+1] <= '9' )
                    nHexChar += 16 * (pszInput[iIn+1] - '0');
                else
                    CPLDebug( "CPL", 
                              "Error unescaping CPLES_URL text, percent not "
                              "followed by two hex digits." );
                    
                if( pszInput[iIn+2] >= 'A' && pszInput[iIn+2] <= 'F' )
                    nHexChar += pszInput[iIn+2] - 'A' + 10;
                else if( pszInput[iIn+2] >= 'a' && pszInput[iIn+2] <= 'f' )
                    nHexChar += pszInput[iIn+2] - 'a' + 10;
                else if( pszInput[iIn+2] >= '0' && pszInput[iIn+2] <= '9' )
                    nHexChar += pszInput[iIn+2] - '0';
                else
                    CPLDebug( "CPL", 
                              "Error unescaping CPLES_URL text, percent not "
                              "followed by two hex digits." );

                pszOutput[iOut++] = (char) nHexChar;
                iIn += 2;
            }
            else if( pszInput[iIn] == '+' )
            {
                pszOutput[iOut++] = ' ';
            }   
            else
            {
                pszOutput[iOut++] = pszInput[iIn];
            }
        }
    }
    else if( nScheme == CPLES_SQL )
    {
        for( iIn = 0; pszInput[iIn] != '\0'; iIn++ )
        {
            if( pszInput[iIn] == '\'' && pszInput[iIn+1] == '\'' )
            {
                iIn++;
                pszOutput[iOut++] = pszInput[iIn];
            }
            else
            {
                pszOutput[iOut++] = pszInput[iIn];
            }
        }
    }
    else /* if( nScheme == CPLES_BackslashQuoteable ) */
    {
        for( iIn = 0; pszInput[iIn] != '\0'; iIn++ )
        {
            if( pszInput[iIn] == '\\' )
            {
                iIn++;
                if( pszInput[iIn] == 'n' )
                    pszOutput[iOut++] = '\n';
                else if( pszInput[iIn] == '0' )
                    pszOutput[iOut++] = '\0';
                else 
                    pszOutput[iOut++] = pszInput[iIn];
            }
            else
            {
                pszOutput[iOut++] = pszInput[iIn];
            }
        }
    }

    pszOutput[iOut] = '\0';

    if( pnLength != NULL )
        *pnLength = iOut;

    return pszOutput;
}

/************************************************************************/
/*                           CPLBinaryToHex()                           */
/************************************************************************/

/**
 * Binary to hexadecimal translation.
 *
 * @param nBytes number of bytes of binary data in pabyData.
 * @param pabyData array of data bytes to translate. 
 * 
 * @return hexadecimal translation, zero terminated.  Free with CPLFree().
 */

char *CPLBinaryToHex( int nBytes, const GByte *pabyData )

{
    char *pszHex = (char *) CPLMalloc(nBytes * 2 + 1 );
    int i;
    static const char achHex[] = "0123456789ABCDEF";

    pszHex[nBytes*2] = '\0';

    for( i = 0; i < nBytes; i++ )
    {
        int nLow = pabyData[i] & 0x0f;
        int nHigh = (pabyData[i] & 0xf0) >> 4;

        pszHex[i*2] = achHex[nHigh];
        pszHex[i*2+1] = achHex[nLow];
    }

    return pszHex;
}


/************************************************************************/
/*                           CPLHexToBinary()                           */
/************************************************************************/

/**
 * Hexadecimal to binary translation
 *
 * @param 

*/

GByte *CPLHexToBinary( const char *pszHex, int *pnBytes )

{
    int     iSrc = 0, iDst = 0;
    size_t  nHexLen = strlen(pszHex);

    GByte *pabyWKB;

    pabyWKB = (GByte *) CPLMalloc(nHexLen / 2 + 2);

    while( pszHex[iSrc] != '\0' )
    {
        if( pszHex[iSrc] >= '0' && pszHex[iSrc] <= '9' )
            pabyWKB[iDst] = pszHex[iSrc] - '0';
        else if( pszHex[iSrc] >= 'A' && pszHex[iSrc] <= 'F' )
            pabyWKB[iDst] = pszHex[iSrc] - 'A' + 10;
        else if( pszHex[iSrc] >= 'a' && pszHex[iSrc] <= 'f' )
            pabyWKB[iDst] = pszHex[iSrc] - 'a' + 10;
        else 
            break;

        pabyWKB[iDst] *= 16;

        iSrc++;

        if( pszHex[iSrc] >= '0' && pszHex[iSrc] <= '9' )
            pabyWKB[iDst] += pszHex[iSrc] - '0';
        else if( pszHex[iSrc] >= 'A' && pszHex[iSrc] <= 'F' )
            pabyWKB[iDst] += pszHex[iSrc] - 'A' + 10;
        else if( pszHex[iSrc] >= 'a' && pszHex[iSrc] <= 'f' )
            pabyWKB[iDst] += pszHex[iSrc] - 'a' + 10;
        else
            break;

        iSrc++;
        iDst++;
    }
    
    pabyWKB[iDst] = 0;
    *pnBytes = iDst;

    return pabyWKB;
}