Diff
Not logged in

Differences From Artifact [0c6eb3b4a5]:

To Artifact [b86e29514a]:


84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
TclUtfCount(
    int ch)			/* The Unicode character whose size is returned. */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {







|







84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

size_t
TclUtfCount(
    int ch)			/* The Unicode character whose size is returned. */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
571
572
573
574
575
576
577

578
579
580
581
582
583
584
585
 */

const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{

    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if (!len) {







>
|







571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
 */

const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    size_t len;
    int fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if (!len) {
617
618
619
620
621
622
623

624
625
626
627
628
629
630
631
 */

const char *
Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{

    int len, fullchar;
    Tcl_UniChar find = 0;
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;







>
|







618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
 */

const char *
Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    size_t len;
    int fullchar;
    Tcl_UniChar find = 0;
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
 */

const char *
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    int len = TclUtfToUniChar(src, &ch);

#if TCL_UTF_MAX <= 4
    if (len == 0) {
      len = TclUtfToUniChar(src, &ch);
    }
#endif
    return src + len;







|







668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
 */

const char *
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    size_t len = TclUtfToUniChar(src, &ch);

#if TCL_UTF_MAX <= 4
    if (len == 0) {
      len = TclUtfToUniChar(src, &ch);
    }
#endif
    return src + len;
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX <= 4
	int len = 1;
#endif

    src += TclUtfToUniChar(src, &ch);
    while (index--) {
#if TCL_UTF_MAX <= 4
	src += (len = TclUtfToUniChar(src, &ch));
#else







|







753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX <= 4
	size_t len = 1;
#endif

    src += TclUtfToUniChar(src, &ch);
    while (index--) {
#if TCL_UTF_MAX <= 4
	src += (len = TclUtfToUniChar(src, &ch));
#else
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
#if TCL_UTF_MAX <= 4
    int len = 1;
#endif

    if (index != TCL_AUTO_LENGTH) {
	while (index--) {
#if TCL_UTF_MAX <= 4
	    src += (len = TclUtfToUniChar(src, &ch));
#else







|







801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
#if TCL_UTF_MAX <= 4
    size_t len = 1;
#endif

    if (index != TCL_AUTO_LENGTH) {
	while (index--) {
#if TCL_UTF_MAX <= 4
	    src += (len = TclUtfToUniChar(src, &ch));
#else
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int upChar;
    char *src, *dst;
    int bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {







|







899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int upChar;
    char *src, *dst;
    size_t bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the upper case
	 * char to dst if its size is <= the original char.
	 */

	if ((bytes < TclUtfCount(upChar)) || ((upChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';







|







926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the upper case
	 * char to dst if its size is <= the original char.
	 */

	if ((bytes < TclUtfCount(upChar)) || ((upChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int lowChar;
    char *src, *dst;
    int bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {







|







962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int lowChar;
    char *src, *dst;
    size_t bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the lower case
	 * char to dst if its size is <= the original char.
	 */

	if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';







|







989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the lower case
	 * char to dst if its size is <= the original char.
	 */

	if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int titleChar, lowChar;
    char *src, *dst;
    int bytes;

    /*
     * Capitalize the first character and then lowercase the rest of the
     * characters until we get to a null.
     */

    src = dst = str;







|







1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int titleChar, lowChar;
    char *src, *dst;
    size_t bytes;

    /*
     * Capitalize the first character and then lowercase the rest of the
     * characters until we get to a null.
     */

    src = dst = str;
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	titleChar = Tcl_UniCharToTitle(titleChar);

	if ((bytes < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {







|







1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	titleChar = Tcl_UniCharToTitle(titleChar);

	if ((bytes < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
#endif
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';







|







1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
#endif
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';