Function ms_Tcl_UtfToUniChar

maptclutf.c:224–311

(str, chPtr)

 */
 
static int
ms_Tcl_UtfToUniChar(str, chPtr)
    register const char *str;    /* The UTF-8 string. */
    register Tcl_UniChar *chPtr; /* Filled with the Tcl_UniChar represented
                                  * by the UTF-8 string. */
{
    register int byte;
    int entitylgth;

    /*check if the string is an html entity (eg { or Ī)*/
    if((entitylgth=msGetUnicodeEntity(str, chPtr))>0)
        return entitylgth;
    
    /*
     * Unroll 1 to 3 byte UTF-8 sequences, use loop to handle longer ones.
     */

    byte = *((unsigned char *) str);
    if (byte < 0xC0) {
        /*
         * Handles properly formed UTF-8 characters between 0x01 and 0x7F.
         * Also treats \0 and naked trail bytes 0x80 to 0xBF as valid
         * characters representing themselves.
         */

        *chPtr = (Tcl_UniChar) byte;
        return 1;
    } else if (byte < 0xE0) {
        if ((str[1] & 0xC0) == 0x80) {
            /*
             * Two-byte-character lead-byte followed by a trail-byte.
             */

            *chPtr = (Tcl_UniChar) (((byte & 0x1F) << 6) | (str[1] & 0x3F));
            return 2;
        }
        /*
         * A two-byte-character lead-byte not followed by trail-byte
         * represents itself.
         */

        *chPtr = (Tcl_UniChar) byte;
        return 1;
    } else if (byte < 0xF0) {
        if (((str[1] & 0xC0) == 0x80) && ((str[2] & 0xC0) == 0x80)) {
            /*
             * Three-byte-character lead byte followed by two trail bytes.
             */

            *chPtr = (Tcl_UniChar) (((byte & 0x0F) << 12) 
                                    | ((str[1] & 0x3F) << 6) | (str[2] & 0x3F));
            return 3;
        }
        /*
         * A three-byte-character lead-byte not followed by two trail-bytes
         * represents itself.
         */