Tcl Source Code

\fBTcl_UtfToLower\fR(\fIstr\fR)
.sp
int
\fBTcl_UtfToTitle\fR(\fIstr\fR)
.SH ARGUMENTS
.AS char *str in/out
.AP int ch in
The Unicode character to be converted.
.AP char *str in/out
Pointer to UTF-8 string to be converted in place.
.BE

.SH DESCRIPTION
.PP
The first three routines convert the case of individual Unicode characters:

.AS int ch
.AP int ch in
The character to be examined.
.BE

.SH DESCRIPTION
.PP
All of the routines described examine Unicode characters and return a
boolean value. A non-zero return value means that the character does
belong to the character class associated with the called routine. The
rest of this document just describes the character classes associated
with the various routines.

.SH "CHARACTER CLASSES"
.PP

\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR)
.SH ARGUMENTS
.AS "const Tcl_UniChar" *uniPattern in/out
.AP char *buf out
Buffer in which the UTF-8 representation of the Tcl_UniChar is stored.  At most
\fBTCL_UTF_MAX\fR bytes are stored in the buffer.
.AP int ch in
The Unicode character to be converted or examined.
.AP Tcl_UniChar *chPtr out
Filled with the Tcl_UniChar represented by the head of the UTF-8 string.
.AP "const char" *src in
Pointer to a UTF-8 string.
.AP "const char" *cs in
Pointer to a UTF-8 string.
.AP "const char" *ct in

typedef int (Tcl_NRPostProc) (ClientData data[], Tcl_Interp *interp,
				int result);

/*
 *----------------------------------------------------------------------------
 * The following constant is used to test for older versions of Tcl in the
 * stubs tables. If TCL_UTF_MAX>4 use a different value.
 */

#define TCL_STUB_MAGIC		((int) 0xFCA3BACF + (TCL_UTF_MAX>4))

/*
 * The following function is required to be defined in all stubs aware
 * extensions. The function is actually implemented in the stub library, not
 * the main Tcl library, although there is a trivial implementation in the
 * main library in case an extension is statically linked into an application.
 */

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }

int
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX == 4
	int len = 1;
#endif

    while (index-- >= 0) {
#if TCL_UTF_MAX == 4
	src += (len = TclUtfToUniChar(src, &ch));
#else
	src += TclUtfToUniChar(src, &ch);
#endif
    }
    fullchar = ch;
#if TCL_UTF_MAX == 4
     if (!len) {
	/* If last Tcl_UniChar was an upper surrogate, combine with lower surrogate */
	(void)TclUtfToUniChar(src, &ch);
	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
    }
#endif
    return fullchar;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfAtIndex --
 *

const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;

    while (index-- > 0) {

	src += TclUtfToUniChar(src, &ch);
    }
    return src;
}

/*
 *---------------------------------------------------------------------------