585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
|
int
Tcl_NumUtfChars(
register const char *src, /* The UTF-8 string to measure. */
int length) /* The length of the string in bytes, or -1
* for strlen(string). */
{
register int i = 0;
/*
* The separate implementations are faster.
*
* Since this is a time-sensitive function, we also do the check for the
* single-byte char case specially.
*/
if (length < 0) {
while ((*src != '\0') && (i < INT_MAX)) {
src = TclUtfNext(src);
i++;
}
} else {
register const char *endPtr = src + length - TCL_UTF_MAX;
while (src < endPtr) {
src = TclUtfNext(src);
i++;
}
endPtr += TCL_UTF_MAX;
while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) {
src = TclUtfNext(src);
i++;
}
if (src < endPtr) {
i += endPtr - src;
}
}
return i;
}
|
>
|
|
>
|
|
>
|
|
>
|
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
|
int
Tcl_NumUtfChars(
register const char *src, /* The UTF-8 string to measure. */
int length) /* The length of the string in bytes, or -1
* for strlen(string). */
{
const char *next;
register int i = 0;
/*
* The separate implementations are faster.
*
* Since this is a time-sensitive function, we also do the check for the
* single-byte char case specially.
*/
if (length < 0) {
while ((*src != '\0') && (i < INT_MAX)) {
next = TclUtfNext(src);
i += 1 + ((next - src) > 3);
src = next;
}
} else {
register const char *endPtr = src + length - TCL_UTF_MAX;
while (src < endPtr) {
next = TclUtfNext(src);
i += 1 + ((next - src) > 3);
src = next;
}
endPtr += TCL_UTF_MAX;
while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) {
next = TclUtfNext(src);
i += 1 + ((next - src) > 3);
src = next;
}
if (src < endPtr) {
i += endPtr - src;
}
}
return i;
}
|
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
|
*/
const char *
Tcl_UtfAtIndex(
register const char *src, /* The UTF-8 string. */
register int index) /* The position of the desired character. */
{
#if 0
/* The Tcl 8.6 implementation */
Tcl_UniChar ch = 0;
int len = 0;
len = TclUtfToUniChar(src, &ch);
src += len;
}
#if TCL_UTF_MAX == 4
if ((ch >= 0xD800) && (len < 3)) {
/* Index points at character following high Surrogate */
src = TclUtfToUniChar(src, &ch);
}
#endif
return src;
#else
/* The Tcl 8.5 implementation */
while (index > 0) {
index--;
src = TclUtfNext(src); /* NOTE: counts each valid byte sequence
* as one character, maybe including those
* that will get stored as two UCS-2 units
* in the UTF-16 encoding. */
}
return src;
#endif
|
<
<
<
<
<
|
<
|
<
<
>
>
>
>
>
|
<
|
<
|
<
<
<
<
<
<
<
<
<
|
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
|
*/
const char *
Tcl_UtfAtIndex(
register const char *src, /* The UTF-8 string. */
register int index) /* The position of the desired character. */
{
while (index-- > 0) {
const char *next = TclUtfNext(src);
/*
* 4-byte sequences generate two UCS-2 code units in the
* UTF-16 representation, so in the current indexing scheme
* we need to account for an extra index (total of two).
*/
index -= ((next - src) > 3);
src = next;
}
return src;
}
/*
*---------------------------------------------------------------------------
*
* Tcl_UtfBackslash --
*
|