Diff
Not logged in

Differences From Artifact [f956e30ce4]:

To Artifact [077dcce582]:


328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
 *	The caller must ensure that the source buffer is long enough that this
 *	routine does not run off the end and dereference non-existent memory
 *	looking for trail bytes. If the source buffer is known to be '\0'
 *	terminated, this cannot happen. Otherwise, the caller should call
 *	Tcl_UtfCharComplete() before calling this routine to ensure that
 *	enough bytes remain in the string.
 *
 *	Special handling of Surrogate pairs is handled as follows:
 *	For any UTF-8 string containing a character outside of the BMP, the
 *	first call to this function will fill *chPtr with the high surrogate
 *	and generate a return value of 1. Calling Tcl_UtfToUniChar again
 *	will produce the low surrogate and a return value of 3. Because *chPtr
 *	is used to remember whether the high surrogate is already produced, it
 *	is recommended to initialize the variable it points to as 0 before
 *	the first call to Tcl_UtfToUniChar is done.







|







328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
 *	The caller must ensure that the source buffer is long enough that this
 *	routine does not run off the end and dereference non-existent memory
 *	looking for trail bytes. If the source buffer is known to be '\0'
 *	terminated, this cannot happen. Otherwise, the caller should call
 *	Tcl_UtfCharComplete() before calling this routine to ensure that
 *	enough bytes remain in the string.
 *
 *	If TCL_UTF_MAX <= 4, special handling of Surrogate pairs is done:
 *	For any UTF-8 string containing a character outside of the BMP, the
 *	first call to this function will fill *chPtr with the high surrogate
 *	and generate a return value of 1. Calling Tcl_UtfToUniChar again
 *	will produce the low surrogate and a return value of 3. Because *chPtr
 *	is used to remember whether the high surrogate is already produced, it
 *	is recommended to initialize the variable it points to as 0 before
 *	the first call to Tcl_UtfToUniChar is done.
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}







|







784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((fullchar != ch) && (find >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}







|







832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((fullchar != ch) && (find >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}