Tcl Source Code

Check-in [149309017e]
Login
Bounty program for improvements to Tcl and certain Tcl packages.
Tcl 2019 Conference, Houston/TX, US, Nov 4-8
Send your abstracts to [email protected]
or submit via the online form by Sep 9.

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

Overview
Comment:merge 8.7
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: 149309017ec0ee10d142c8a74e7e07653c484b56a6b093c491970d8573e44aee
User & Date: jan.nijtmans 2018-04-20 10:18:29
Context
2018-04-20
16:55
merge 8.7 check-in: 03e1985393 user: dgp tags: trunk
10:18
merge 8.7 check-in: 149309017e user: jan.nijtmans tags: trunk
10:16
TIP #389 implementation. check-in: e109760b1c user: jan.nijtmans tags: core-8-branch
2018-04-19
02:51
merge 8.7 check-in: efebbf0517 user: dgp tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to doc/StringObj.3.

33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
...
197
198
199
200
201
202
203
204

205
206
207
208
209
210
211
.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)
................................................................................
\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






|







 







|
>







33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
...
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
.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)
................................................................................
\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
...
136
137
138
139
140
141
142



143
144
145
146
147
148
149
.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)
................................................................................
.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.






|







 







>
>
>







59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
...
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
.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)
................................................................................
.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.

1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
....
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
    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)
}
................................................................................
    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)
}






|


|


|


|







 







|







1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
....
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
    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)
}
................................................................................
    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.

1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
....
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
 * 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.
 */

................................................................................

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.
 */






|







 







|


|







1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
....
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
 * 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.
 */

................................................................................

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.

487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
....
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
....
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
1443
1444
1445
1446
1447
1448
1449
1450
....
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
    Tcl_Obj *const objv[])	/* Argument objects. */
{
    int idx, result, cflags, all, wlen, wsublen, numMatches, offset;
    int start, end, subStart, subEnd, match, command, numParts;
    Tcl_RegExp regExpr;
    Tcl_RegExpInfo info;
    Tcl_Obj *resultPtr, *subPtr, *objPtr, *startIndex = NULL;
    Tcl_UniChar ch, *wsrc, *wfirstChar, *wstring, *wsubspec, *wend;

    static const char *const options[] = {
	"-all",		"-command",	"-expanded",	"-line",
	"-linestop",	"-lineanchor",	"-nocase",	"-start",
	"--",		NULL
    };
    enum options {
................................................................................
	Tcl_InitHashTable(&charReuseTable, TCL_ONE_WORD_KEYS);

	for ( ; stringPtr < end; stringPtr += len) {
		int fullchar;
	    len = TclUtfToUniChar(stringPtr, &ch);
	    fullchar = ch;

#if TCL_UTF_MAX == 4
	    if (!len) {
		len += TclUtfToUniChar(stringPtr, &ch);
		fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	    }
#endif

	    /*
................................................................................

    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])) {
	    unsigned char uch = (unsigned char) ch;

	    Tcl_SetObjResult(interp, Tcl_NewByteArrayObj(&uch, 1));
	} else {
	    char buf[TCL_UTF_MAX];

	    length = Tcl_UniCharToUtf(ch, buf);
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, length));
	}
    }
    return TCL_OK;
}
................................................................................
	    goto str_is_done;
	}
	end = string1 + length1;
	for (; string1 < end; string1 += length2, failat++) {
	    int fullchar;
	    length2 = TclUtfToUniChar(string1, &ch);
	    fullchar = ch;
#if TCL_UTF_MAX == 4
	    if (!length2) {
	    	length2 = TclUtfToUniChar(string1, &ch);
	    	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	    }
#endif
	    if (!chcomp(fullchar)) {
		result = 0;






|







 







|







 







|








|
>
>
>
>











|







 







|







487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
....
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
....
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
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
....
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
    Tcl_Obj *const objv[])	/* Argument objects. */
{
    int idx, result, cflags, all, wlen, wsublen, numMatches, offset;
    int start, end, subStart, subEnd, match, command, numParts;
    Tcl_RegExp regExpr;
    Tcl_RegExpInfo info;
    Tcl_Obj *resultPtr, *subPtr, *objPtr, *startIndex = NULL;
    Tcl_UniChar ch, *wsrc, *wfirstChar, *wstring, *wsubspec = 0, *wend;

    static const char *const options[] = {
	"-all",		"-command",	"-expanded",	"-line",
	"-linestop",	"-lineanchor",	"-nocase",	"-start",
	"--",		NULL
    };
    enum options {
................................................................................
	Tcl_InitHashTable(&charReuseTable, TCL_ONE_WORD_KEYS);

	for ( ; stringPtr < end; stringPtr += len) {
		int fullchar;
	    len = TclUtfToUniChar(stringPtr, &ch);
	    fullchar = ch;

#if TCL_UTF_MAX <= 4
	    if (!len) {
		len += TclUtfToUniChar(stringPtr, &ch);
		fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	    }
#endif

	    /*
................................................................................

    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])) {
	    unsigned char uch = (unsigned char) ch;

	    Tcl_SetObjResult(interp, Tcl_NewByteArrayObj(&uch, 1));
	} else {
	    char buf[4];

	    length = Tcl_UniCharToUtf(ch, buf);
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, length));
	}
    }
    return TCL_OK;
}
................................................................................
	    goto str_is_done;
	}
	end = string1 + length1;
	for (; string1 < end; string1 += length2, failat++) {
	    int fullchar;
	    length2 = TclUtfToUniChar(string1, &ch);
	    fullchar = ch;
#if TCL_UTF_MAX <= 4
	    if (!length2) {
	    	length2 = TclUtfToUniChar(string1, &ch);
	    	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	    }
#endif
	    if (!chcomp(fullchar)) {
		result = 0;

Changes to generic/tclDecls.h.

921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
....
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
....
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
....
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
				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 */
................................................................................
				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);
................................................................................
    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 */
................................................................................
    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 */






|

|

|

|







 







|







 







|
|
|
|







 







|







921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
....
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
....
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
....
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
				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 */
................................................................................
				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);
................................................................................
    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 */
................................................................................
    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.

5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
	} else if (TclIsPureByteArray(valuePtr)) {
	    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:






|
|







|







5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
	} else if (TclIsPureByteArray(valuePtr)) {
	    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[4];
	    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
...
508
509
510
511
512
513
514




515















516
517
518
519
520
521
522
...
608
609
610
611
612
613
614

615



616
617
618
619
620
621
622


623



624
625
626
627
628
629
630
...
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
....
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
}
 
/*
 *----------------------------------------------------------------------
 *
 * 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);
................................................................................
	}
	if (stringPtr->numChars == objPtr->length) {
	    return (Tcl_UniChar) objPtr->bytes[index];
	}
	FillUnicodeRep(objPtr);
	stringPtr = GET_STRING(objPtr);
    }




    return stringPtr->unicode[index];















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

................................................................................
	 * 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)
		&& ((stringPtr->unicode[last]&0xFC00) == 0xD800)) {
................................................................................
		    numChars = precision;
		    Tcl_IncrRefCount(segment);
		    allocSegment = 1;
		}
	    }
	    break;
	case 'c': {
	    char buf[TCL_UTF_MAX];
	    int code, length;

	    if (TclGetIntFromObj(interp, segment, &code) != TCL_OK) {
		goto error;
	    }
	    length = Tcl_UniCharToUtf(code, buf);
	    segment = Tcl_NewStringObj(buf, length);






|
|
>










|






>
>
>
>
>







|
>
>
|
>
|







 







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







 







>

>
>
>






|
>
>
|
>
>
>







 







>
>
>
>
>
>







 







>
>
|
>
>
>
|







 







|







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
...
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
...
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
...
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
713
....
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
}
 
/*
 *----------------------------------------------------------------------
 *
 * 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);
................................................................................
	}
	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 --
 *
................................................................................
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.
     */

................................................................................
	 * 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)
		&& ((stringPtr->unicode[last]&0xFC00) == 0xD800)) {
................................................................................
		    numChars = precision;
		    Tcl_IncrRefCount(segment);
		    allocSegment = 1;
		}
	    }
	    break;
	case 'c': {
	    char buf[4];
	    int code, length;

	    if (TclGetIntFromObj(interp, segment, &code) != TCL_OK) {
		goto error;
	    }
	    length = Tcl_UniCharToUtf(code, buf);
	    segment = Tcl_NewStringObj(buf, length);

Changes to generic/tclUtf.c.

94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
...
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
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
174
175
176
177
178
179
180
181
182
...
263
264
265
266
267
268
269







270
271
272
273
274
275
276
...
280
281
282
283
284
285
286
287


288
289
290



291

292
293
294
295
296
297
298
...
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
...
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
...
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
...
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
...
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
...
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
...
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
...
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
....
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
....
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
....
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
....
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
....
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258

1259
1260
1261
1262
1263
1264


1265
1266
1267
1268
1269
1270
1271
....
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286

1287
1288
1289
1290
1291
1292


1293
1294
1295
1296
1297
1298
1299
....
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
....
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
....
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
....
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
....
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
....
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
....
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
....
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
....
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
....
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
....
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
....
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
	return 2;
    }
#if TCL_UTF_MAX > 3
    if (((unsigned)(ch - 0x10000) <= 0xFFFFF)) {
	return 4;
    }
#endif
    return 3;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharToUtf --
................................................................................
int
Tcl_UniCharToUtf(
    int ch,			/* The Tcl_UniChar to be stored in the
				 * buffer. */
    char *buf)			/* Buffer in which the UTF-8 representation of
				 * the Tcl_UniChar is stored. Buffer must be
				 * large enough to hold the UTF-8 character
				 * (at most TCL_UTF_MAX bytes). */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	buf[0] = (char) ch;
	return 1;
    }
    if (ch >= 0) {
	if (ch <= 0x7FF) {
	    buf[1] = (char) ((ch | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 6) | 0xC0);
	    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;
	}

#if TCL_UTF_MAX > 3
	if (ch <= 0x10FFFF) {
	    buf[3] = (char) ((ch | 0x80) & 0xBF);
	    buf[2] = (char) (((ch >> 6) | 0x80) & 0xBF);
	    buf[1] = (char) (((ch >> 12) | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 18) | 0xF0);
	    return 4;
	}
#endif
    }

    ch = 0xFFFD;
three:
    buf[2] = (char) ((ch | 0x80) & 0xBF);
    buf[1] = (char) (((ch >> 6) | 0x80) & 0xBF);
    buf[0] = (char) ((ch >> 12) | 0xE0);
................................................................................
 *	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. */
{
................................................................................
     * 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.
	     */

................................................................................
	 */
    }
    else if (byte < 0xF8) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
	    /*
	     * Four-byte-character lead byte followed by three trail bytes.
	     */
#if TCL_UTF_MAX == 3
	    byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)) - 0x10000;
	    if (byte & 0x100000) {
		/* out of range, < 0x10000 or > 0x10ffff */
	    } else {
		/* produce replacement character, and advance source pointer */
		*chPtr = (Tcl_UniChar) 0xFFFD;
		return 4;
	    }
#elif TCL_UTF_MAX == 4
	    Tcl_UniChar surrogate;

	    byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)) - 0x10000;
	    surrogate = (Tcl_UniChar) (0xD800 + (byte >> 10));
	    if (byte & 0x100000) {
		/* out of range, < 0x10000 or > 0x10ffff */
................................................................................
{
    int len, fullchar;
    Tcl_UniChar find = 0;

    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;
................................................................................
    Tcl_UniChar find = 0;
    const char *last;

    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;
................................................................................
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;
}
 
................................................................................
 *
 * 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 --
 *
................................................................................
 *----------------------------------------------------------------------
 */

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.
	 */

................................................................................
 *----------------------------------------------------------------------
 */

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.
	 */

................................................................................
 *----------------------------------------------------------------------
 */

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);
	}
................................................................................
	 * only when both strings are of at least n chars long (no need for \0
	 * check)
	 */

	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
	 * n must be interpreted as chars, not bytes.
	 * This should be called only when both strings are of
	 * at least n chars long (no need for \0 check)
	 */
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (*cs && *ct) {
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (*cs && *ct) {
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
 *
 * 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 --
 *
................................................................................
 *
 * 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 --
 *
................................................................................
 *
 * 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 --
 *
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlnum(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (((ALPHA_BITS | DIGIT_BITS) >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsAlpha --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlpha(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((ALPHA_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsControl --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsControl(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	if ((ch == 0xE0001) || ((ch >= 0xE0020) && (ch <= 0xE007f))) {
	    return 1;
	}
	if ((ch >= 0xF0000) && ((ch & 0xFFFF) <= 0xFFFD)) {
	    return 1;
	}
	return 0;
    }
#endif
    return ((CONTROL_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsDigit --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsDigit(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == DECIMAL_DIGIT_NUMBER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsGraph --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsGraph(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }
#endif
    return ((GRAPH_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsLower --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsLower(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == LOWERCASE_LETTER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPrint --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPrint(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }
#endif
    return (((GRAPH_BITS|SPACE_BITS) >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPunct --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPunct(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((PUNCT_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsSpace --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsSpace(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    /* Ignore upper 11 bits. */
    ch &= 0x1FFFFF;
#else
    /* Ignore upper 16 bits. */
    ch &= 0xFFFF;
#endif

    /*
     * If the character is within the first 127 characters, just use the
     * standard C function, otherwise consult the Unicode table.
     */

    if (ch < 0x80) {
	return TclIsSpaceProc((char) ch);
#if TCL_UTF_MAX > 3
    } else if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
#endif
    } else if (ch == 0x0085 || ch == 0x180E || ch == 0x200B
	    || ch == 0x202F || ch == 0x2060 || ch == 0xFEFF) {
	return 1;
    } else {
	return ((SPACE_BITS >> GetCategory(ch)) & 1);
    }
}
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsUpper(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == UPPERCASE_LETTER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsWordChar --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsWordChar(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((WORD_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharCaseMatch --






<



<







 







|












<



>
>
>
|
|
|
>
>



>
>
|
|
|



<


<
<







<







 







>
>
>
>
>
>
>







 







|
>
>



>
>
>
|
>







 







|
<
<
<
<
<
<
<
<
<
<







 







|







 







|







 







|







 







|





>
>
>
>


>
>
>

>

>
>
>
>
>
>
>
>
|







 







|
>










>
>
>
>
>
>
>
|







 







|
>










>
>
>
>
>
>
>
|







 







>
|












>
>
>
>
>
>
>
|











>
>
>
>
>
>
>
|







 







|







 







|







 







|







 







|







 







|



>
|

|
|
|
<
>
>







 







|



>
|

|
|
|
<
>
>







 







|



>
|
|

|
|
|
|

|
|
|
|
<
>
>







 







<



<







 







<



<







 







<










<







 







<



<







 







<




<







 







<



<







 







<




<







 







<



<







 







<


<
<
<
<








<


<







 







<



<







 







<



<







94
95
96
97
98
99
100

101
102
103

104
105
106
107
108
109
110
...
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
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
174
175

176
177
178
179
180
181
182
...
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
...
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
...
338
339
340
341
342
343
344
345










346
347
348
349
350
351
352
...
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
...
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
...
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
...
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
...
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
...
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
...
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
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
....
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
....
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
....
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
....
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
....
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
....
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
....
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
....
1510
1511
1512
1513
1514
1515
1516

1517
1518
1519

1520
1521
1522
1523
1524
1525
1526
....
1536
1537
1538
1539
1540
1541
1542

1543
1544
1545

1546
1547
1548
1549
1550
1551
1552
....
1562
1563
1564
1565
1566
1567
1568

1569
1570
1571
1572
1573
1574
1575
1576
1577
1578

1579
1580
1581
1582
1583
1584
1585
....
1595
1596
1597
1598
1599
1600
1601

1602
1603
1604

1605
1606
1607
1608
1609
1610
1611
....
1621
1622
1623
1624
1625
1626
1627

1628
1629
1630
1631

1632
1633
1634
1635
1636
1637
1638
....
1648
1649
1650
1651
1652
1653
1654

1655
1656
1657

1658
1659
1660
1661
1662
1663
1664
....
1674
1675
1676
1677
1678
1679
1680

1681
1682
1683
1684

1685
1686
1687
1688
1689
1690
1691
....
1701
1702
1703
1704
1705
1706
1707

1708
1709
1710

1711
1712
1713
1714
1715
1716
1717
....
1727
1728
1729
1730
1731
1732
1733

1734
1735




1736
1737
1738
1739
1740
1741
1742
1743

1744
1745

1746
1747
1748
1749
1750
1751
1752
....
1767
1768
1769
1770
1771
1772
1773

1774
1775
1776

1777
1778
1779
1780
1781
1782
1783
....
1793
1794
1795
1796
1797
1798
1799

1800
1801
1802

1803
1804
1805
1806
1807
1808
1809
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
	return 2;
    }

    if (((unsigned)(ch - 0x10000) <= 0xFFFFF)) {
	return 4;
    }

    return 3;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharToUtf --
................................................................................
int
Tcl_UniCharToUtf(
    int ch,			/* The Tcl_UniChar to be stored in the
				 * buffer. */
    char *buf)			/* Buffer in which the UTF-8 representation of
				 * the Tcl_UniChar is stored. Buffer must be
				 * large enough to hold the UTF-8 character
				 * (at most 4 bytes). */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	buf[0] = (char) ch;
	return 1;
    }
    if (ch >= 0) {
	if (ch <= 0x7FF) {
	    buf[1] = (char) ((ch | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 6) | 0xC0);
	    return 2;
	}
	if (ch <= 0xFFFF) {

	    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;
		}
	    }

	    goto three;
	}


	if (ch <= 0x10FFFF) {
	    buf[3] = (char) ((ch | 0x80) & 0xBF);
	    buf[2] = (char) (((ch >> 6) | 0x80) & 0xBF);
	    buf[1] = (char) (((ch >> 12) | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 18) | 0xF0);
	    return 4;
	}

    }

    ch = 0xFFFD;
three:
    buf[2] = (char) ((ch | 0x80) & 0xBF);
    buf[1] = (char) (((ch >> 6) | 0x80) & 0xBF);
    buf[0] = (char) ((ch >> 12) | 0xE0);
................................................................................
 *	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. */
{
................................................................................
     * 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.
	     */

................................................................................
	 */
    }
    else if (byte < 0xF8) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
	    /*
	     * Four-byte-character lead byte followed by three trail bytes.
	     */
#if TCL_UTF_MAX <= 4










	    Tcl_UniChar surrogate;

	    byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)) - 0x10000;
	    surrogate = (Tcl_UniChar) (0xD800 + (byte >> 10));
	    if (byte & 0x100000) {
		/* out of range, < 0x10000 or > 0x10ffff */
................................................................................
{
    int len, fullchar;
    Tcl_UniChar find = 0;

    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;
................................................................................
    Tcl_UniChar find = 0;
    const char *last;

    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;
................................................................................
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;
}
 
................................................................................
 *
 * 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 --
 *
................................................................................
 *----------------------------------------------------------------------
 */

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.
	 */

................................................................................
 *----------------------------------------------------------------------
 */

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.
	 */

................................................................................
 *----------------------------------------------------------------------
 */

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);
	}
................................................................................
	 * only when both strings are of at least n chars long (no need for \0
	 * check)
	 */

	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX <= 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
	 * n must be interpreted as chars, not bytes.
	 * This should be called only when both strings are of
	 * at least n chars long (no need for \0 check)
	 */
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX <= 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (*cs && *ct) {
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX <= 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (*cs && *ct) {
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX <= 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
................................................................................
 *
 * 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 --
 *
................................................................................
 *
 * 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 --
 *
................................................................................
 *
 * 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 --
 *
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlnum(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return (((ALPHA_BITS | DIGIT_BITS) >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsAlpha --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlpha(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return ((ALPHA_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsControl --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsControl(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	if ((ch == 0xE0001) || ((ch >= 0xE0020) && (ch <= 0xE007f))) {
	    return 1;
	}
	if ((ch >= 0xF0000) && ((ch & 0xFFFF) <= 0xFFFD)) {
	    return 1;
	}
	return 0;
    }

    return ((CONTROL_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsDigit --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsDigit(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return (GetCategory(ch) == DECIMAL_DIGIT_NUMBER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsGraph --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsGraph(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }

    return ((GRAPH_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsLower --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsLower(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return (GetCategory(ch) == LOWERCASE_LETTER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPrint --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPrint(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }

    return (((GRAPH_BITS|SPACE_BITS) >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPunct --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPunct(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return ((PUNCT_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsSpace --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsSpace(
    int ch)			/* Unicode character to test. */
{

    /* Ignore upper 11 bits. */
    ch &= 0x1FFFFF;





    /*
     * If the character is within the first 127 characters, just use the
     * standard C function, otherwise consult the Unicode table.
     */

    if (ch < 0x80) {
	return TclIsSpaceProc((char) ch);

    } else if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;

    } else if (ch == 0x0085 || ch == 0x180E || ch == 0x200B
	    || ch == 0x202F || ch == 0x2060 || ch == 0xFEFF) {
	return 1;
    } else {
	return ((SPACE_BITS >> GetCategory(ch)) & 1);
    }
}
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsUpper(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return (GetCategory(ch) == UPPERCASE_LETTER);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsWordChar --
................................................................................
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsWordChar(
    int ch)			/* Unicode character to test. */
{

    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }

    return ((WORD_BITS >> GetCategory(ch)) & 1);
}
 
/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharCaseMatch --

Changes to tests/msgcat.test.

1313
1314
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
    } -body {
	::msgcat::mcn [namespace current]::bar con1
    } -result con1bar

 
    interp bgerror {} $bgerrorsaved

    # Tests msgcat-15.*: [mcutil]

    test msgcat-15.5 {mcutil - no argument} -body {
	mcutil
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil subcommand ?arg ...?"}

    test msgcat-15.6 {mcutil - wrong argument} -body {
	mcutil junk
    } -returnCodes 1\
    -result {unknown subcommand "junk": must be getpreferences, or getsystemlocale}
    
    test msgcat-15.7 {mcutil - partial argument} -body {
	mcutil getsystem
    } -returnCodes 1\
    -result {unknown subcommand "getsystem": must be getpreferences, or getsystemlocale}
    
    test msgcat-15.8 {mcutil getpreferences - no argument} -body {
	mcutil getpreferences
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil getpreferences locale"}
    
    test msgcat-15.9 {mcutil getpreferences - DE_de} -body {
	mcutil getpreferences DE_de
    } -result {de_de de {}}
    
    test msgcat-15.10 {mcutil getsystemlocale - wrong argument} -body {
	mcutil getsystemlocale DE_de
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil getsystemlocale"}
    
    # The result is system dependent
    # So just test if it runs
    # The environment variable version was test with test 0.x
    test msgcat-15.11 {mcutil getsystemlocale} -body {
	mcutil getsystemlocale
	set ok ok
    } -result {ok}
    
    
    cleanupTests
}
namespace delete ::msgcat::test
return

# Local Variables:
# mode: tcl
# End:






|

|




|




|




|




|



|







|













1313
1314
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
    } -body {
	::msgcat::mcn [namespace current]::bar con1
    } -result con1bar

 
    interp bgerror {} $bgerrorsaved

    # Tests msgcat-18.*: [mcutil]

    test msgcat-18.1 {mcutil - no argument} -body {
	mcutil
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil subcommand ?arg ...?"}

    test msgcat-18.2 {mcutil - wrong argument} -body {
	mcutil junk
    } -returnCodes 1\
    -result {unknown subcommand "junk": must be getpreferences, or getsystemlocale}
    
    test msgcat-18.3 {mcutil - partial argument} -body {
	mcutil getsystem
    } -returnCodes 1\
    -result {unknown subcommand "getsystem": must be getpreferences, or getsystemlocale}
    
    test msgcat-18.4 {mcutil getpreferences - no argument} -body {
	mcutil getpreferences
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil getpreferences locale"}
    
    test msgcat-18.5 {mcutil getpreferences - DE_de} -body {
	mcutil getpreferences DE_de
    } -result {de_de de {}}
    
    test msgcat-18.6 {mcutil getsystemlocale - wrong argument} -body {
	mcutil getsystemlocale DE_de
    } -returnCodes 1\
    -result {wrong # args: should be "mcutil getsystemlocale"}
    
    # The result is system dependent
    # So just test if it runs
    # The environment variable version was test with test 0.x
    test msgcat-18.7 {mcutil getsystemlocale} -body {
	mcutil getsystemlocale
	set ok ok
    } -result {ok}
    
    
    cleanupTests
}
namespace delete ::msgcat::test
return

# Local Variables:
# mode: tcl
# End:

Changes to tests/string.test.

483
484
485
486
487
488
489



490
491
492
493
494
495
496
} -match glob -result {1 {*}}
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 {*}}
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