Tcl Source Code

Changes On Branch tip-389
Login
Bounty program for improvements to Tcl and certain Tcl packages.

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Changes In Branch tip-389 Excluding Merge-Ins

This is equivalent to a diff from 82ddedafd7 to 1997a15ffd

2018-04-20
10:16
TIP #389 implementation. check-in: e109760b1c user: jan.nijtmans tags: core-8-branch
2018-04-17
21:49
Slightly better unmatched-surrogates handling. Unmatched High surrogates will still be silently remo... Closed-Leaf check-in: 1997a15ffd user: jan.nijtmans tags: tip-389
14:39
merge 8.6 check-in: f21a25950c user: dgp tags: core-8-branch
2018-04-16
14:46
merge 8.7 check-in: a1f6233f04 user: dgp tags: tip-491
13:41
merge 8.7 check-in: 0b2e37e7c2 user: dgp tags: trunk
2018-04-13
09:36
Fix documentation for [encoding convertfrom] check-in: 3e9c686cde user: gahr tags: encoding-doc-fixes
09:24
Create new branch named "encoding-doc-fixes" Closed-Leaf check-in: 3a78bbe617 user: gahr tags: mistake
2018-04-11
16:17
merge 8.7 check-in: fdf9328219 user: dgp tags: tip-389
12:45
merge 8.7 check-in: 43e01830a9 user: dgp tags: tip-421
2018-04-07
17:12
merge 8.7 check-in: 1d2e0cde7b user: dgp tags: tip-502
17:07
merge 8.7 check-in: faf8c0b052 user: dgp tags: tip-445
17:07
merge 8.6 check-in: 82ddedafd7 user: dgp tags: core-8-branch
16:56
merge 8.5 check-in: 0d32dfc5f0 user: dgp tags: core-8-6-branch
2018-04-05
17:22
Plug memleak in [format] applied to bignums. check-in: 225c752bdc user: dgp tags: core-8-branch

Changes to doc/StringObj.3.

33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
.sp
Tcl_UniChar *
\fBTcl_GetUnicodeFromObj\fR(\fIobjPtr, lengthPtr\fR)
.sp
Tcl_UniChar *
\fBTcl_GetUnicode\fR(\fIobjPtr\fR)
.sp
Tcl_UniChar
\fBTcl_GetUniChar\fR(\fIobjPtr, index\fR)
.sp
int
\fBTcl_GetCharLength\fR(\fIobjPtr\fR)
.sp
Tcl_Obj *
\fBTcl_GetRange\fR(\fIobjPtr, first, last\fR)






|







33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
.sp
Tcl_UniChar *
\fBTcl_GetUnicodeFromObj\fR(\fIobjPtr, lengthPtr\fR)
.sp
Tcl_UniChar *
\fBTcl_GetUnicode\fR(\fIobjPtr\fR)
.sp
int
\fBTcl_GetUniChar\fR(\fIobjPtr, index\fR)
.sp
int
\fBTcl_GetCharLength\fR(\fIobjPtr\fR)
.sp
Tcl_Obj *
\fBTcl_GetRange\fR(\fIobjPtr, first, last\fR)
200
201
202
203
204
205
206
207

208
209
210
211
212
213
214
\fIlengthPtr\fR if it is non-NULL.  The storage referenced by the returned
byte pointer is owned by the value manager and should not be modified by
the caller.  The procedure \fBTcl_GetUnicode\fR is used in the common case
where the caller does not need the length of the unicode string
representation.
.PP
\fBTcl_GetUniChar\fR returns the \fIindex\fR'th character in the
value's Unicode representation.

.PP
\fBTcl_GetRange\fR returns a newly created value comprised of the
characters between \fIfirst\fR and \fIlast\fR (inclusive) in the
value's Unicode representation.  If the value's Unicode
representation is invalid, the Unicode representation is regenerated
from the value's string representation.
.PP






|
>







200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
\fIlengthPtr\fR if it is non-NULL.  The storage referenced by the returned
byte pointer is owned by the value manager and should not be modified by
the caller.  The procedure \fBTcl_GetUnicode\fR is used in the common case
where the caller does not need the length of the unicode string
representation.
.PP
\fBTcl_GetUniChar\fR returns the \fIindex\fR'th character in the
value's Unicode representation. If the index is out of range or
it references a low surrogate preceded by a high surrogate, it returns -1;
.PP
\fBTcl_GetRange\fR returns a newly created value comprised of the
characters between \fIfirst\fR and \fIlast\fR (inclusive) in the
value's Unicode representation.  If the value's Unicode
representation is invalid, the Unicode representation is regenerated
from the value's string representation.
.PP

Changes to doc/ToUpper.3.

9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
.BS
.SH NAME
Tcl_UniCharToUpper, Tcl_UniCharToLower, Tcl_UniCharToTitle, Tcl_UtfToUpper, Tcl_UtfToLower, Tcl_UtfToTitle \- routines for manipulating the case of Unicode characters and UTF-8 strings
.SH SYNOPSIS
.nf
\fB#include <tcl.h>\fR
.sp
Tcl_UniChar
\fBTcl_UniCharToUpper\fR(\fIch\fR)
.sp
Tcl_UniChar
\fBTcl_UniCharToLower\fR(\fIch\fR)
.sp
Tcl_UniChar
\fBTcl_UniCharToTitle\fR(\fIch\fR)
.sp
int
\fBTcl_UtfToUpper\fR(\fIstr\fR)
.sp
int
\fBTcl_UtfToLower\fR(\fIstr\fR)






|


|


|







9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
.BS
.SH NAME
Tcl_UniCharToUpper, Tcl_UniCharToLower, Tcl_UniCharToTitle, Tcl_UtfToUpper, Tcl_UtfToLower, Tcl_UtfToTitle \- routines for manipulating the case of Unicode characters and UTF-8 strings
.SH SYNOPSIS
.nf
\fB#include <tcl.h>\fR
.sp
int
\fBTcl_UniCharToUpper\fR(\fIch\fR)
.sp
int
\fBTcl_UniCharToLower\fR(\fIch\fR)
.sp
int
\fBTcl_UniCharToTitle\fR(\fIch\fR)
.sp
int
\fBTcl_UtfToUpper\fR(\fIstr\fR)
.sp
int
\fBTcl_UtfToLower\fR(\fIstr\fR)

Changes to doc/Utf.3.

59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
.sp
const char *
\fBTcl_UtfNext\fR(\fIsrc\fR)
.sp
const char *
\fBTcl_UtfPrev\fR(\fIsrc, start\fR)
.sp
Tcl_UniChar
\fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR)
.sp
const char *
\fBTcl_UtfAtIndex\fR(\fIsrc, index\fR)
.sp
int
\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR)






|







59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
.sp
const char *
\fBTcl_UtfNext\fR(\fIsrc\fR)
.sp
const char *
\fBTcl_UtfPrev\fR(\fIsrc, start\fR)
.sp
int
\fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR)
.sp
const char *
\fBTcl_UtfAtIndex\fR(\fIsrc, index\fR)
.sp
int
\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR)
136
137
138
139
140
141
142



143
144
145
146
147
148
149
.PP
\fBTcl_UtfToUniChar\fR reads one UTF-8 character starting at \fIsrc\fR
and stores it as a Tcl_UniChar in \fI*chPtr\fR.  The return value is the
number of bytes read from \fIsrc\fR.  The caller must ensure that the
source buffer is long enough such that this routine does not run off the
end and dereference non-existent or random memory; if the source buffer
is known to be null-terminated, this will not happen.  If the input is



not in proper UTF-8 format, \fBTcl_UtfToUniChar\fR will store the first
byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x0000 and
0x00ff and return 1.
.PP
\fBTcl_UniCharToUtfDString\fR converts the given Unicode string
to UTF-8, storing the result in a previously initialized \fBTcl_DString\fR.
You must specify \fIuniLength\fR, the length of the given Unicode string.






>
>
>







136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
.PP
\fBTcl_UtfToUniChar\fR reads one UTF-8 character starting at \fIsrc\fR
and stores it as a Tcl_UniChar in \fI*chPtr\fR.  The return value is the
number of bytes read from \fIsrc\fR.  The caller must ensure that the
source buffer is long enough such that this routine does not run off the
end and dereference non-existent or random memory; if the source buffer
is known to be null-terminated, this will not happen.  If the input is
a byte in the range 0x80 - 0x9F, \fBTcl_UtfToUniChar\fR assumes the
cp1252 encoding, stores the corresponding Tcl_UniChar in \fI*chPtr\fR
and returns 1. If the input is otherwise
not in proper UTF-8 format, \fBTcl_UtfToUniChar\fR will store the first
byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x0000 and
0x00ff and return 1.
.PP
\fBTcl_UniCharToUtfDString\fR converts the given Unicode string
to UTF-8, storing the result in a previously initialized \fBTcl_DString\fR.
You must specify \fIuniLength\fR, the length of the given Unicode string.

Changes to generic/tcl.decls.

1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
    void Tcl_ThreadAlert(Tcl_ThreadId threadId)
}
declare 319 {
    void Tcl_ThreadQueueEvent(Tcl_ThreadId threadId, Tcl_Event *evPtr,
	    Tcl_QueuePosition position)
}
declare 320 {
    Tcl_UniChar Tcl_UniCharAtIndex(const char *src, int index)
}
declare 321 {
    Tcl_UniChar Tcl_UniCharToLower(int ch)
}
declare 322 {
    Tcl_UniChar Tcl_UniCharToTitle(int ch)
}
declare 323 {
    Tcl_UniChar Tcl_UniCharToUpper(int ch)
}
declare 324 {
    int Tcl_UniCharToUtf(int ch, char *buf)
}
declare 325 {
    const char *Tcl_UtfAtIndex(const char *src, int index)
}






|


|


|


|







1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
    void Tcl_ThreadAlert(Tcl_ThreadId threadId)
}
declare 319 {
    void Tcl_ThreadQueueEvent(Tcl_ThreadId threadId, Tcl_Event *evPtr,
	    Tcl_QueuePosition position)
}
declare 320 {
    int Tcl_UniCharAtIndex(const char *src, int index)
}
declare 321 {
    int Tcl_UniCharToLower(int ch)
}
declare 322 {
    int Tcl_UniCharToTitle(int ch)
}
declare 323 {
    int Tcl_UniCharToUpper(int ch)
}
declare 324 {
    int Tcl_UniCharToUtf(int ch, char *buf)
}
declare 325 {
    const char *Tcl_UtfAtIndex(const char *src, int index)
}
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
    void Tcl_SetUnicodeObj(Tcl_Obj *objPtr, const Tcl_UniChar *unicode,
	    int numChars)
}
declare 380 {
    int Tcl_GetCharLength(Tcl_Obj *objPtr)
}
declare 381 {
    Tcl_UniChar Tcl_GetUniChar(Tcl_Obj *objPtr, int index)
}
declare 382 {
    Tcl_UniChar *Tcl_GetUnicode(Tcl_Obj *objPtr)
}
declare 383 {
    Tcl_Obj *Tcl_GetRange(Tcl_Obj *objPtr, int first, int last)
}






|







1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
    void Tcl_SetUnicodeObj(Tcl_Obj *objPtr, const Tcl_UniChar *unicode,
	    int numChars)
}
declare 380 {
    int Tcl_GetCharLength(Tcl_Obj *objPtr)
}
declare 381 {
    int Tcl_GetUniChar(Tcl_Obj *objPtr, int index)
}
declare 382 {
    Tcl_UniChar *Tcl_GetUnicode(Tcl_Obj *objPtr)
}
declare 383 {
    Tcl_Obj *Tcl_GetRange(Tcl_Obj *objPtr, int first, int last)
}

Changes to generic/tcl.h.

2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
 * 4, then Tcl_UniChar must be 2-bytes in size (UCS-2) (the default). If 6,
 * then Tcl_UniChar must be 4-bytes in size (UCS-4). At this time UCS-2 mode
 * is the default and recommended mode. UCS-4 is experimental and not
 * recommended. It works for the core, but most extensions expect UCS-2.
 */

#ifndef TCL_UTF_MAX
#define TCL_UTF_MAX		3
#endif

/*
 * This represents a Unicode character. Any changes to this should also be
 * reflected in regcustom.h.
 */







|







2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
 * 4, then Tcl_UniChar must be 2-bytes in size (UCS-2) (the default). If 6,
 * then Tcl_UniChar must be 4-bytes in size (UCS-4). At this time UCS-2 mode
 * is the default and recommended mode. UCS-4 is experimental and not
 * recommended. It works for the core, but most extensions expect UCS-2.
 */

#ifndef TCL_UTF_MAX
#define TCL_UTF_MAX		4
#endif

/*
 * This represents a Unicode character. Any changes to this should also be
 * reflected in regcustom.h.
 */

2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
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.
 */

#define TCL_STUB_MAGIC		((int) 0xFCA3BACF)

/*
 * 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.
 */






|


|







2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
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.
 */

Changes to generic/tclCmdMZ.c.

1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431




1432
1433
1434
1435
1436
1437
1438
    if (objc != 3) {
	Tcl_WrongNumArgs(interp, 1, objv, "string charIndex");
	return TCL_ERROR;
    }

    /*
     * Get the char length to calulate what 'end' means.
     */

    length = Tcl_GetCharLength(objv[1]);
    if (TclGetIntForIndexM(interp, objv[2], length-1, &index) != TCL_OK) {
	return TCL_ERROR;
    }

    if ((index >= 0) && (index < length)) {
	Tcl_UniChar ch = Tcl_GetUniChar(objv[1], index);





	/*
	 * If we have a ByteArray object, we're careful to generate a new
	 * bytearray for a result.
	 */

	if (TclIsPureByteArray(objv[1])) {






|








|
>
>
>
>







1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
    if (objc != 3) {
	Tcl_WrongNumArgs(interp, 1, objv, "string charIndex");
	return TCL_ERROR;
    }

    /*
     * Get the char length to calculate what 'end' means.
     */

    length = Tcl_GetCharLength(objv[1]);
    if (TclGetIntForIndexM(interp, objv[2], length-1, &index) != TCL_OK) {
	return TCL_ERROR;
    }

    if ((index >= 0) && (index < length)) {
	int ch = Tcl_GetUniChar(objv[1], index);

	if (ch == -1) {
	    return TCL_OK;
	}

	/*
	 * If we have a ByteArray object, we're careful to generate a new
	 * bytearray for a result.
	 */

	if (TclIsPureByteArray(objv[1])) {

Changes to generic/tclDecls.h.

958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
				int flags);
/* 318 */
EXTERN void		Tcl_ThreadAlert(Tcl_ThreadId threadId);
/* 319 */
EXTERN void		Tcl_ThreadQueueEvent(Tcl_ThreadId threadId,
				Tcl_Event *evPtr, Tcl_QueuePosition position);
/* 320 */
EXTERN Tcl_UniChar	Tcl_UniCharAtIndex(const char *src, int index);
/* 321 */
EXTERN Tcl_UniChar	Tcl_UniCharToLower(int ch);
/* 322 */
EXTERN Tcl_UniChar	Tcl_UniCharToTitle(int ch);
/* 323 */
EXTERN Tcl_UniChar	Tcl_UniCharToUpper(int ch);
/* 324 */
EXTERN int		Tcl_UniCharToUtf(int ch, char *buf);
/* 325 */
EXTERN const char *	Tcl_UtfAtIndex(const char *src, int index);
/* 326 */
EXTERN int		Tcl_UtfCharComplete(const char *src, int length);
/* 327 */






|

|

|

|







958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
				int flags);
/* 318 */
EXTERN void		Tcl_ThreadAlert(Tcl_ThreadId threadId);
/* 319 */
EXTERN void		Tcl_ThreadQueueEvent(Tcl_ThreadId threadId,
				Tcl_Event *evPtr, Tcl_QueuePosition position);
/* 320 */
EXTERN int		Tcl_UniCharAtIndex(const char *src, int index);
/* 321 */
EXTERN int		Tcl_UniCharToLower(int ch);
/* 322 */
EXTERN int		Tcl_UniCharToTitle(int ch);
/* 323 */
EXTERN int		Tcl_UniCharToUpper(int ch);
/* 324 */
EXTERN int		Tcl_UniCharToUtf(int ch, char *buf);
/* 325 */
EXTERN const char *	Tcl_UtfAtIndex(const char *src, int index);
/* 326 */
EXTERN int		Tcl_UtfCharComplete(const char *src, int length);
/* 327 */
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
				int numChars);
/* 379 */
EXTERN void		Tcl_SetUnicodeObj(Tcl_Obj *objPtr,
				const Tcl_UniChar *unicode, int numChars);
/* 380 */
EXTERN int		Tcl_GetCharLength(Tcl_Obj *objPtr);
/* 381 */
EXTERN Tcl_UniChar	Tcl_GetUniChar(Tcl_Obj *objPtr, int index);
/* 382 */
EXTERN Tcl_UniChar *	Tcl_GetUnicode(Tcl_Obj *objPtr);
/* 383 */
EXTERN Tcl_Obj *	Tcl_GetRange(Tcl_Obj *objPtr, int first, int last);
/* 384 */
EXTERN void		Tcl_AppendUnicodeToObj(Tcl_Obj *objPtr,
				const Tcl_UniChar *unicode, int length);






|







1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
				int numChars);
/* 379 */
EXTERN void		Tcl_SetUnicodeObj(Tcl_Obj *objPtr,
				const Tcl_UniChar *unicode, int numChars);
/* 380 */
EXTERN int		Tcl_GetCharLength(Tcl_Obj *objPtr);
/* 381 */
EXTERN int		Tcl_GetUniChar(Tcl_Obj *objPtr, int index);
/* 382 */
EXTERN Tcl_UniChar *	Tcl_GetUnicode(Tcl_Obj *objPtr);
/* 383 */
EXTERN Tcl_Obj *	Tcl_GetRange(Tcl_Obj *objPtr, int first, int last);
/* 384 */
EXTERN void		Tcl_AppendUnicodeToObj(Tcl_Obj *objPtr,
				const Tcl_UniChar *unicode, int length);
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
    int (*tcl_ReadChars) (Tcl_Channel channel, Tcl_Obj *objPtr, int charsToRead, int appendFlag); /* 313 */
    void (*tcl_RestoreResult) (Tcl_Interp *interp, Tcl_SavedResult *statePtr); /* 314 */
    void (*tcl_SaveResult) (Tcl_Interp *interp, Tcl_SavedResult *statePtr); /* 315 */
    int (*tcl_SetSystemEncoding) (Tcl_Interp *interp, const char *name); /* 316 */
    Tcl_Obj * (*tcl_SetVar2Ex) (Tcl_Interp *interp, const char *part1, const char *part2, Tcl_Obj *newValuePtr, int flags); /* 317 */
    void (*tcl_ThreadAlert) (Tcl_ThreadId threadId); /* 318 */
    void (*tcl_ThreadQueueEvent) (Tcl_ThreadId threadId, Tcl_Event *evPtr, Tcl_QueuePosition position); /* 319 */
    Tcl_UniChar (*tcl_UniCharAtIndex) (const char *src, int index); /* 320 */
    Tcl_UniChar (*tcl_UniCharToLower) (int ch); /* 321 */
    Tcl_UniChar (*tcl_UniCharToTitle) (int ch); /* 322 */
    Tcl_UniChar (*tcl_UniCharToUpper) (int ch); /* 323 */
    int (*tcl_UniCharToUtf) (int ch, char *buf); /* 324 */
    const char * (*tcl_UtfAtIndex) (const char *src, int index); /* 325 */
    int (*tcl_UtfCharComplete) (const char *src, int length); /* 326 */
    int (*tcl_UtfBackslash) (const char *src, int *readPtr, char *dst); /* 327 */
    const char * (*tcl_UtfFindFirst) (const char *src, int ch); /* 328 */
    const char * (*tcl_UtfFindLast) (const char *src, int ch); /* 329 */
    const char * (*tcl_UtfNext) (const char *src); /* 330 */






|
|
|
|







2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
    int (*tcl_ReadChars) (Tcl_Channel channel, Tcl_Obj *objPtr, int charsToRead, int appendFlag); /* 313 */
    void (*tcl_RestoreResult) (Tcl_Interp *interp, Tcl_SavedResult *statePtr); /* 314 */
    void (*tcl_SaveResult) (Tcl_Interp *interp, Tcl_SavedResult *statePtr); /* 315 */
    int (*tcl_SetSystemEncoding) (Tcl_Interp *interp, const char *name); /* 316 */
    Tcl_Obj * (*tcl_SetVar2Ex) (Tcl_Interp *interp, const char *part1, const char *part2, Tcl_Obj *newValuePtr, int flags); /* 317 */
    void (*tcl_ThreadAlert) (Tcl_ThreadId threadId); /* 318 */
    void (*tcl_ThreadQueueEvent) (Tcl_ThreadId threadId, Tcl_Event *evPtr, Tcl_QueuePosition position); /* 319 */
    int (*tcl_UniCharAtIndex) (const char *src, int index); /* 320 */
    int (*tcl_UniCharToLower) (int ch); /* 321 */
    int (*tcl_UniCharToTitle) (int ch); /* 322 */
    int (*tcl_UniCharToUpper) (int ch); /* 323 */
    int (*tcl_UniCharToUtf) (int ch, char *buf); /* 324 */
    const char * (*tcl_UtfAtIndex) (const char *src, int index); /* 325 */
    int (*tcl_UtfCharComplete) (const char *src, int length); /* 326 */
    int (*tcl_UtfBackslash) (const char *src, int *readPtr, char *dst); /* 327 */
    const char * (*tcl_UtfFindFirst) (const char *src, int ch); /* 328 */
    const char * (*tcl_UtfFindLast) (const char *src, int ch); /* 329 */
    const char * (*tcl_UtfNext) (const char *src); /* 330 */
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
    int (*tcl_UniCharIsPrint) (int ch); /* 374 */
    int (*tcl_UniCharIsPunct) (int ch); /* 375 */
    int (*tcl_RegExpExecObj) (Tcl_Interp *interp, Tcl_RegExp regexp, Tcl_Obj *textObj, int offset, int nmatches, int flags); /* 376 */
    void (*tcl_RegExpGetInfo) (Tcl_RegExp regexp, Tcl_RegExpInfo *infoPtr); /* 377 */
    Tcl_Obj * (*tcl_NewUnicodeObj) (const Tcl_UniChar *unicode, int numChars); /* 378 */
    void (*tcl_SetUnicodeObj) (Tcl_Obj *objPtr, const Tcl_UniChar *unicode, int numChars); /* 379 */
    int (*tcl_GetCharLength) (Tcl_Obj *objPtr); /* 380 */
    Tcl_UniChar (*tcl_GetUniChar) (Tcl_Obj *objPtr, int index); /* 381 */
    Tcl_UniChar * (*tcl_GetUnicode) (Tcl_Obj *objPtr); /* 382 */
    Tcl_Obj * (*tcl_GetRange) (Tcl_Obj *objPtr, int first, int last); /* 383 */
    void (*tcl_AppendUnicodeToObj) (Tcl_Obj *objPtr, const Tcl_UniChar *unicode, int length); /* 384 */
    int (*tcl_RegExpMatchObj) (Tcl_Interp *interp, Tcl_Obj *textObj, Tcl_Obj *patternObj); /* 385 */
    void (*tcl_SetNotifier) (Tcl_NotifierProcs *notifierProcPtr); /* 386 */
    Tcl_Mutex * (*tcl_GetAllocMutex) (void); /* 387 */
    int (*tcl_GetChannelNames) (Tcl_Interp *interp); /* 388 */






|







2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
    int (*tcl_UniCharIsPrint) (int ch); /* 374 */
    int (*tcl_UniCharIsPunct) (int ch); /* 375 */
    int (*tcl_RegExpExecObj) (Tcl_Interp *interp, Tcl_RegExp regexp, Tcl_Obj *textObj, int offset, int nmatches, int flags); /* 376 */
    void (*tcl_RegExpGetInfo) (Tcl_RegExp regexp, Tcl_RegExpInfo *infoPtr); /* 377 */
    Tcl_Obj * (*tcl_NewUnicodeObj) (const Tcl_UniChar *unicode, int numChars); /* 378 */
    void (*tcl_SetUnicodeObj) (Tcl_Obj *objPtr, const Tcl_UniChar *unicode, int numChars); /* 379 */
    int (*tcl_GetCharLength) (Tcl_Obj *objPtr); /* 380 */
    int (*tcl_GetUniChar) (Tcl_Obj *objPtr, int index); /* 381 */
    Tcl_UniChar * (*tcl_GetUnicode) (Tcl_Obj *objPtr); /* 382 */
    Tcl_Obj * (*tcl_GetRange) (Tcl_Obj *objPtr, int first, int last); /* 383 */
    void (*tcl_AppendUnicodeToObj) (Tcl_Obj *objPtr, const Tcl_UniChar *unicode, int length); /* 384 */
    int (*tcl_RegExpMatchObj) (Tcl_Interp *interp, Tcl_Obj *textObj, Tcl_Obj *patternObj); /* 385 */
    void (*tcl_SetNotifier) (Tcl_NotifierProcs *notifierProcPtr); /* 386 */
    Tcl_Mutex * (*tcl_GetAllocMutex) (void); /* 387 */
    int (*tcl_GetChannelNames) (Tcl_Interp *interp); /* 388 */

Changes to generic/tclExecute.c.

5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && length == valuePtr->length) {
	    objResultPtr = Tcl_NewStringObj((const char *)
		    valuePtr->bytes+index, 1);
	} else {
	    char buf[TCL_UTF_MAX];
	    Tcl_UniChar ch = Tcl_GetUniChar(valuePtr, index);

	    /*
	     * This could be: Tcl_NewUnicodeObj((const Tcl_UniChar *)&ch, 1)
	     * but creating the object as a string seems to be faster in
	     * practical use.
	     */

	    length = Tcl_UniCharToUtf(ch, buf);
	    objResultPtr = Tcl_NewStringObj(buf, length);
	}

	TRACE_APPEND(("\"%s\"\n", O2S(objResultPtr)));
	NEXT_INST_F(1, 2, 1);

    case INST_STR_RANGE:






|







|







5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && length == valuePtr->length) {
	    objResultPtr = Tcl_NewStringObj((const char *)
		    valuePtr->bytes+index, 1);
	} else {
	    char buf[TCL_UTF_MAX];
	    int ch = Tcl_GetUniChar(valuePtr, index);

	    /*
	     * This could be: Tcl_NewUnicodeObj((const Tcl_UniChar *)&ch, 1)
	     * but creating the object as a string seems to be faster in
	     * practical use.
	     */

	    length = (ch != -1) ? Tcl_UniCharToUtf(ch, buf) : 0;
	    objResultPtr = Tcl_NewStringObj(buf, length);
	}

	TRACE_APPEND(("\"%s\"\n", O2S(objResultPtr)));
	NEXT_INST_F(1, 2, 1);

    case INST_STR_RANGE:

Changes to generic/tclStringObj.c.

456
457
458
459
460
461
462
463

464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481





482
483
484
485
486
487
488
489


490

491
492
493
494
495
496
497
498
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_GetUniChar --
 *
 *	Get the index'th Unicode character from the String object. The index

 *	is assumed to be in the appropriate range.
 *
 * Results:
 *	Returns the index'th Unicode character in the Object.
 *
 * Side effects:
 *	Fills unichar with the index'th Unicode character.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_GetUniChar(
    Tcl_Obj *objPtr,		/* The object to get the Unicode charater
				 * from. */
    int index)			/* Get the index'th Unicode character. */
{
    String *stringPtr;






    /*
     * Optimize the case where we're really dealing with a bytearray object
     * we don't need to convert to a string to perform the indexing operation.
     */

    if (TclIsPureByteArray(objPtr)) {
	unsigned char *bytes = Tcl_GetByteArrayFromObj(objPtr, NULL);




	return (Tcl_UniChar) bytes[index];
    }

    /*
     * OK, need to work with the object as a string.
     */

    SetStringFromAny(NULL, objPtr);






|
>
|










|






>
>
>
>
>







|
>
>
|
>
|







456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_GetUniChar --
 *
 *	Get the index'th Unicode character from the String object. If index
 *	is out of range or it references a low surrogate preceded by a high
 *	surrogate, the result = -1;
 *
 * Results:
 *	Returns the index'th Unicode character in the Object.
 *
 * Side effects:
 *	Fills unichar with the index'th Unicode character.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_GetUniChar(
    Tcl_Obj *objPtr,		/* The object to get the Unicode charater
				 * from. */
    int index)			/* Get the index'th Unicode character. */
{
    String *stringPtr;
    int ch, length;

    if (index < 0) {
	return -1;
    }

    /*
     * Optimize the case where we're really dealing with a bytearray object
     * we don't need to convert to a string to perform the indexing operation.
     */

    if (TclIsPureByteArray(objPtr)) {
	unsigned char *bytes = Tcl_GetByteArrayFromObj(objPtr, &length);
	if (index >= length) {
		return -1;
	}

	return (int) bytes[index];
    }

    /*
     * OK, need to work with the object as a string.
     */

    SetStringFromAny(NULL, objPtr);
508
509
510
511
512
513
514




515















516
517
518
519
520
521
522
	}
	if (stringPtr->numChars == objPtr->length) {
	    return (Tcl_UniChar) objPtr->bytes[index];
	}
	FillUnicodeRep(objPtr);
	stringPtr = GET_STRING(objPtr);
    }




    return stringPtr->unicode[index];















}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_GetUnicode --
 *






>
>
>
>
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
	}
	if (stringPtr->numChars == objPtr->length) {
	    return (Tcl_UniChar) objPtr->bytes[index];
	}
	FillUnicodeRep(objPtr);
	stringPtr = GET_STRING(objPtr);
    }

    if (index >= stringPtr->numChars) {
	return -1;
    }
	ch = stringPtr->unicode[index];
#if TCL_UTF_MAX == 4
	/* See: bug [11ae2be95dac9417] */
	if ((ch&0xF800) == 0xD800) {
	    if (ch&0x400) {
		if ((index > 0) && ((stringPtr->unicode[index-1]&0xFC00) == 0xD800)) {
		    ch = -1; /* low surrogate preceded by high surrogate */
		}
	    } else if ((++index < stringPtr->numChars)
		    && ((stringPtr->unicode[index]&0xFC00) == 0xDC00)) {
		/* high surrogate followed by low surrogate */
		ch = (((ch & 0x3FF) << 10) | (stringPtr->unicode[index] & 0x3FF)) + 0x10000;
	    }
	}
#endif
    return ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_GetUnicode --
 *
608
609
610
611
612
613
614

615



616
617
618
619
620
621
622


623



624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642






643
644
645
646
647
648
649
650
651
652
653
654
655
656


657



658
659
660
661
662
663
664
Tcl_GetRange(
    Tcl_Obj *objPtr,		/* The Tcl object to find the range of. */
    int first,			/* First index of the range. */
    int last)			/* Last index of the range. */
{
    Tcl_Obj *newObjPtr;		/* The Tcl object to find the range of. */
    String *stringPtr;





    /*
     * Optimize the case where we're really dealing with a bytearray object
     * we don't need to convert to a string to perform the substring operation.
     */

    if (TclIsPureByteArray(objPtr)) {
	unsigned char *bytes = Tcl_GetByteArrayFromObj(objPtr, NULL);






	return Tcl_NewByteArrayObj(bytes+first, last-first+1);
    }

    /*
     * OK, need to work with the object as a string.
     */

    SetStringFromAny(NULL, objPtr);
    stringPtr = GET_STRING(objPtr);

    if (stringPtr->hasUnicode == 0) {
	/*
	 * If numChars is unknown, compute it.
	 */

	if (stringPtr->numChars == -1) {
	    TclNumUtfChars(stringPtr->numChars, objPtr->bytes, objPtr->length);
	}
	if (stringPtr->numChars == objPtr->length) {






	    newObjPtr = Tcl_NewStringObj(objPtr->bytes + first, last-first+1);

	    /*
	     * Since we know the char length of the result, store it.
	     */

	    SetStringFromAny(NULL, newObjPtr);
	    stringPtr = GET_STRING(newObjPtr);
	    stringPtr->numChars = newObjPtr->length;
	    return newObjPtr;
	}
	FillUnicodeRep(objPtr);
	stringPtr = GET_STRING(objPtr);
    }






#if TCL_UTF_MAX == 4
	/* See: bug [11ae2be95dac9417] */
	if ((first>0) && ((stringPtr->unicode[first]&0xFC00) == 0xDC00)
		&& ((stringPtr->unicode[first-1]&0xFC00) == 0xD800)) {
	    ++first;
	}
	if ((last+1<stringPtr->numChars) && ((stringPtr->unicode[last+1]&0xFC00) == 0xDC00)






>

>
>
>






|
>
>
|
>
>
>



















>
>
>
>
>
>














>
>
|
>
>
>







636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
Tcl_GetRange(
    Tcl_Obj *objPtr,		/* The Tcl object to find the range of. */
    int first,			/* First index of the range. */
    int last)			/* Last index of the range. */
{
    Tcl_Obj *newObjPtr;		/* The Tcl object to find the range of. */
    String *stringPtr;
    int length;

    if (first < 0) {
	first = 0;
	}
    /*
     * Optimize the case where we're really dealing with a bytearray object
     * we don't need to convert to a string to perform the substring operation.
     */

    if (TclIsPureByteArray(objPtr)) {
	unsigned char *bytes = Tcl_GetByteArrayFromObj(objPtr, &length);
	if (last >= length) {
	    last = length - 1;
	}
	if (last < first) {
	    return Tcl_NewObj();
	}
	return Tcl_NewByteArrayObj(bytes+first, last-first+1);
    }

    /*
     * OK, need to work with the object as a string.
     */

    SetStringFromAny(NULL, objPtr);
    stringPtr = GET_STRING(objPtr);

    if (stringPtr->hasUnicode == 0) {
	/*
	 * If numChars is unknown, compute it.
	 */

	if (stringPtr->numChars == -1) {
	    TclNumUtfChars(stringPtr->numChars, objPtr->bytes, objPtr->length);
	}
	if (stringPtr->numChars == objPtr->length) {
	    if (last >= stringPtr->numChars) {
		last = stringPtr->numChars - 1;
	    }
	    if (last < first) {
		return Tcl_NewObj();
	    }
	    newObjPtr = Tcl_NewStringObj(objPtr->bytes + first, last-first+1);

	    /*
	     * Since we know the char length of the result, store it.
	     */

	    SetStringFromAny(NULL, newObjPtr);
	    stringPtr = GET_STRING(newObjPtr);
	    stringPtr->numChars = newObjPtr->length;
	    return newObjPtr;
	}
	FillUnicodeRep(objPtr);
	stringPtr = GET_STRING(objPtr);
    }
	if (last > stringPtr->numChars) {
	    last = stringPtr->numChars;
	}
	if (last < first) {
	    return Tcl_NewObj();
	}
#if TCL_UTF_MAX == 4
	/* See: bug [11ae2be95dac9417] */
	if ((first>0) && ((stringPtr->unicode[first]&0xFC00) == 0xDC00)
		&& ((stringPtr->unicode[first-1]&0xFC00) == 0xD800)) {
	    ++first;
	}
	if ((last+1<stringPtr->numChars) && ((stringPtr->unicode[last+1]&0xFC00) == 0xDC00)

Changes to generic/tclUtf.c.

144
145
146
147
148
149
150



151
152
153


154
155
156


157
158
159
160
161
162
163
164
165
166
	    return 2;
	}
	if (ch <= 0xFFFF) {
#if TCL_UTF_MAX == 4
	    if ((ch & 0xF800) == 0xD800) {
		if (ch & 0x0400) {
		    /* Low surrogate */



		    buf[3] = (char) ((ch | 0x80) & 0xBF);
		    buf[2] |= (char) (((ch >> 6) | 0x80) & 0x8F);
		    return 4;


		} else {
		    /* High surrogate */
		    ch += 0x40;


		    buf[2] = (char) (((ch << 4) | 0x80) & 0xB0);
		    buf[1] = (char) (((ch >> 2) | 0x80) & 0xBF);
		    buf[0] = (char) (((ch >> 8) | 0xF0) & 0xF7);
		    return 0;
		}
	    }
#endif
	    goto three;
	}







>
>
>
|
|
|
>
>



>
>
|
|
|







144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
	    return 2;
	}
	if (ch <= 0xFFFF) {
#if TCL_UTF_MAX == 4
	    if ((ch & 0xF800) == 0xD800) {
		if (ch & 0x0400) {
		    /* Low surrogate */
		    if (((buf[0] & 0xF8) == 0xF0) && ((buf[1] & 0xC0) == 0x80)
			    && ((buf[2] & 0xCF) == 0)) {
			/* Previous Tcl_UniChar was a High surrogate, so combine */
			buf[3] = (char) ((ch & 0x3F) | 0x80);
			buf[2] |= (char) (((ch >> 6) & 0x0F) | 0x80);
			return 4;
		    }
		    /* Previous Tcl_UniChar was not a High surrogate, so just output */
		} else {
		    /* High surrogate */
		    ch += 0x40;
		    /* Fill buffer with specific 3-byte (invalid) byte combination,
		       so following Low surrogate can recognize it and combine */
		    buf[2] = (char) ((ch << 4) & 0x30);
		    buf[1] = (char) (((ch >> 2) & 0x3F) | 0x80);
		    buf[0] = (char) (((ch >> 8) & 0x07) | 0xF0);
		    return 0;
		}
	    }
#endif
	    goto three;
	}

263
264
265
266
267
268
269







270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287


288
289
290



291

292
293
294
295
296
297
298
 *	number of bytes from the UTF-8 string that were consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */








int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{
    register int byte;

    /*
     * Unroll 1 to 3 (or 4) byte UTF-8 sequences.
     */

    byte = *((unsigned char *) src);
    if (byte < 0xC0) {
	/*
	 * Handles properly formed UTF-8 characters between 0x01 and 0x7F.
	 * Also treats \0 and naked trail bytes 0x80 to 0xBF as valid


	 * characters representing themselves.
	 */




	*chPtr = (Tcl_UniChar) byte;

	return 1;
    } else if (byte < 0xE0) {
	if ((src[1] & 0xC0) == 0x80) {
	    /*
	     * Two-byte-character lead-byte followed by a trail-byte.
	     */







>
>
>
>
>
>
>

















|
>
>



>
>
>
|
>







270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
 *	number of bytes from the UTF-8 string that were consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

static const unsigned short cp1252[32] = {
  0x20ac,   0x81, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
  0x02C6, 0x2030, 0x0160, 0x2039, 0x0152,   0x8D, 0x017D,   0x8F,
    0x90, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
   0x2DC, 0x2122, 0x0161, 0x203A, 0x0153,   0x9D, 0x017E, 0x0178
};

int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{
    register int byte;

    /*
     * Unroll 1 to 3 (or 4) byte UTF-8 sequences.
     */

    byte = *((unsigned char *) src);
    if (byte < 0xC0) {
	/*
	 * Handles properly formed UTF-8 characters between 0x01 and 0x7F.
	 * Treats naked trail bytes 0x80 to 0x9F as valid characters from
	 * the cp1252 table. See: <https://en.wikipedia.org/wiki/UTF-8>
	 * Also treats \0 and other naked trail bytes 0xA0 to 0xBF as valid
	 * characters representing themselves.
	 */

	if ((unsigned)(byte-0x80) < (unsigned) 0x20) {
	    *chPtr = (Tcl_UniChar) cp1252[byte-0x80];
	} else {
	    *chPtr = (Tcl_UniChar) byte;
	}
	return 1;
    } else if (byte < 0xE0) {
	if ((src[1] & 0xC0) == 0x80) {
	    /*
	     * Two-byte-character lead-byte followed by a trail-byte.
	     */

713
714
715
716
717
718
719
720
721
722
723
724
725




726
727



728

729








730
731
732
733
734
735
736
737
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

Tcl_UniChar
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;





    while (index-- >= 0) {



	src += TclUtfToUniChar(src, &ch);

    }








    return ch;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfAtIndex --
 *






|





>
>
>
>


>
>
>

>

>
>
>
>
>
>
>
>
|







733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

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 --
 *
831
832
833
834
835
836
837
838

839
840
841
842
843
844
845
846
847
848







849
850
851
852
853
854
855
856
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, upChar;

    char *src, *dst;
    int bytes;

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);







	upChar = Tcl_UniCharToUpper(ch);

	/*
	 * 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.
	 */







|
>










>
>
>
>
>
>
>
|







867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
 *----------------------------------------------------------------------
 */

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) {
	bytes = TclUtfToUniChar(src, &ch);
	upChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    upChar = (((upChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	upChar = Tcl_UniCharToUpper(upChar);

	/*
	 * 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.
	 */

884
885
886
887
888
889
890
891

892
893
894
895
896
897
898
899
900
901







902
903
904
905
906
907
908
909
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, lowChar;

    char *src, *dst;
    int bytes;

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);







	lowChar = Tcl_UniCharToLower(ch);

	/*
	 * 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.
	 */







|
>










>
>
>
>
>
>
>
|







928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
 *----------------------------------------------------------------------
 */

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) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	lowChar = Tcl_UniCharToLower(lowChar);

	/*
	 * 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.
	 */

938
939
940
941
942
943
944
945

946
947
948
949
950
951
952
953
954
955
956
957







958
959
960
961
962
963
964
965
966
967
968
969







970
971
972
973
974
975
976
977
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, 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;

    if (*src) {
	bytes = TclUtfToUniChar(src, &ch);







	titleChar = Tcl_UniCharToTitle(ch);

	if (bytes < TclUtfCount(titleChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);







	lowChar = Tcl_UniCharToLower(ch);

	if (bytes < TclUtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}






|
>












>
>
>
>
>
>
>
|











>
>
>
>
>
>
>
|







990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
 *----------------------------------------------------------------------
 */

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;

    if (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	titleChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	titleChar = Tcl_UniCharToTitle(titleChar);

	if (bytes < TclUtfCount(titleChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	lowChar = Tcl_UniCharToLower(lowChar);

	if (bytes < TclUtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258

1259
1260
1261
1262
1263

1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286

1287
1288
1289
1290
1291

1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314

1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326

1327
1328
1329
1330
1331
1332
1333
1334
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToUpper(
    int ch)			/* Unicode character to convert. */
{

    int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x04) {
	ch -= GetDelta(info);
    }

    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToLower --
 *
 *	Compute the lowercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the lowercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToLower(
    int ch)			/* Unicode character to convert. */
{

    int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x02) {
	ch += GetDelta(info);
    }

    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToTitle --
 *
 *	Compute the titlecase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the titlecase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToTitle(
    int ch)			/* Unicode character to convert. */
{

    int info = GetUniCharInfo(ch);
    int mode = GetCaseType(info);

    if (mode & 0x1) {
	/*
	 * Subtract or add one depending on the original case.
	 */

	ch += ((mode & 0x4) ? -1 : 1);
    } else if (mode == 0x4) {
	ch -= GetDelta(info);
    }

    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharLen --
 *






|



>
|

|
|
|
>
|


















|



>
|

|
|
|
>
|


















|



>
|
|

|
|
|
|

|
|
|
|
>
|







1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharToUpper(
    int ch)			/* Unicode character to convert. */
{
    if (!UNICODE_OUT_OF_RANGE(ch)) {
	int info = GetUniCharInfo(ch);

	if (GetCaseType(info) & 0x04) {
	    ch -= GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToLower --
 *
 *	Compute the lowercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the lowercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharToLower(
    int ch)			/* Unicode character to convert. */
{
    if (!UNICODE_OUT_OF_RANGE(ch)) {
	int info = GetUniCharInfo(ch);

	if (GetCaseType(info) & 0x02) {
	    ch += GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToTitle --
 *
 *	Compute the titlecase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the titlecase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharToTitle(
    int ch)			/* Unicode character to convert. */
{
    if (!UNICODE_OUT_OF_RANGE(ch)) {
	int info = GetUniCharInfo(ch);
	int mode = GetCaseType(info);

	if (mode & 0x1) {
	    /*
	     * Subtract or add one depending on the original case.
	     */

	    ch += ((mode & 0x4) ? -1 : 1);
	} else if (mode == 0x4) {
	    ch -= GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharLen --
 *

Changes to tests/string.test.

483
484
485
486
487
488
489



490
491
492
493
494
495
496
} -match glob -result {1 {*invalid octal number*}}
test string-5.19.$noComp {string index, bytearray object out of bounds} {
    run {string index [binary format I* {0x50515253 0x52}] -1}
} {}
test string-5.20.$noComp {string index, bytearray object out of bounds} {
    run {string index [binary format I* {0x50515253 0x52}] 20}
} {}





proc largest_int {} {
    # This will give us what the largest valid int on this machine is,
    # so we can test for overflow properly below on >32 bit systems
    set int 1
    set exp 7; # assume we get at least 8 bits






>
>
>







483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
} -match glob -result {1 {*invalid octal number*}}
test string-5.19.$noComp {string index, bytearray object out of bounds} {
    run {string index [binary format I* {0x50515253 0x52}] -1}
} {}
test string-5.20.$noComp {string index, bytearray object out of bounds} {
    run {string index [binary format I* {0x50515253 0x52}] 20}
} {}
test string-5.21 {string index, surrogates, bug [11ae2be95dac9417]} fullutf {
    list [string index a\U100000b 1] [string index a\U100000b 2] [string index a\U100000b 3]
} [list \U100000 {} b]


proc largest_int {} {
    # This will give us what the largest valid int on this machine is,
    # so we can test for overflow properly below on >32 bit systems
    set int 1
    set exp 7; # assume we get at least 8 bits