1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,1,1,1,1,1,1,1,1,1,1,1
};

static const unsigned char complete[256] = {
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,1,1,1,1,1,1,1,1,1,1,1
};

/*
 *---------------------------------------------------------------------------
 *
 * TclUtfCount --
 *
 *	Find the number of bytes in the Utf character "ch".

int
Tcl_UtfCharComplete(
    const char *src,		/* String to check if first few bytes contain
				 * a complete UTF-8 character. */
    size_t length)			/* Length of above string in bytes. */
{
    return length >= complete[(unsigned char)*src];
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_NumUtfChars --
 *

}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfPrev --
 *
 *	The aim of this routine is to provide a way to move backward
 *	through a UTF-8 string. The caller is expected to pass non-NULL
 *	pointer arguments start and src. start points to the beginning
 *	of a string, and src >= start points to a location within (or just
 *	past the end) of the string. This routine always returns a
 *	pointer within the string (>= start).  When (src == start), it
 *	returns start. When (src > start), it returns a pointer (< src)
 *	and (>= src - TCL_UTF_MAX).  Subject to these constraints, the
 *	routine returns a pointer to the earliest byte in the string that
 *	starts a character when characters are read starting at start and
 *	that character might include the byte src[-1]. The routine will
 *	examine only those bytes in the range that might be returned.
 *	It will not examine the byte *src, and because of that cannot 
 *	determine for certain in all circumstances whether the character
 *	that begins with the returned pointer will or will not include
 *	the byte src[-1]. In the scenario, where src points to the end of
 *	a buffer being filled, the returned pointer point to either the
 *	final complete character in the string or to the earliest byte
 *	that might start an incomplete character waiting for more bytes to
 *	complete.
 *
 *	Because this routine always returns a value < src until the point
 *	it is forced to return start, it is useful as a backward iterator
 *	through a string that will always make progress and always be
 *	prevented from running past the beginning of the string.
 *
 *	In a string where all characters are complete and properly formed,
 *	and the value of src points to the first byte of a character, 
 *	repeated Tcl_UtfPrev calls will step to the starting bytes of
 *	characters, one character at a time. Within those limitations,
 *	Tcl_UtfPrev and Tcl_UtfNext are inverses. If either condition cannot
 *	be met, Tcl_UtfPrev and Tcl_UtfNext may not function as inverses and
 *	the caller will have to take greater care.
 *
 * Results:
 *	A pointer to the start of a character in the string as described


 *	above.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfPrev(
    const char *src,		/* A location in a UTF-8 string. */
    const char *start)		/* Pointer to the beginning of the string */

{
    const char *look;
    int i, byte;

    look = --src;
    for (i = 0; i < 4; i++) {
	if (look < start) {
	    if (src < start) {
		src = start;
	    }
	    break;
	}
	byte = *((unsigned char *) look);
	if (byte < 0x80) {
	    break;
	}
	if (byte >= 0xC0) {
	    if (totalBytes[byte] <= i) {
		break;
	    }
	    return look;
	}
	look--;
    }
    return src;
}


    /*
     * If the character is within the first 127 characters, just use the
     * standard C function, otherwise consult the Unicode table.
     */

    if (ch < 0x80) {
	return TclIsSpaceProcM((char) ch);
    } else if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    } else if (ch == 0x0085 || ch == 0x180E || ch == 0x200B
	    || ch == 0x202F || ch == 0x2060 || ch == 0xFEFF) {
	return 1;
    } else {
	return ((SPACE_BITS >> GetCategory(ch)) & 1);