Tcl Source Code

Check-in [e4e3193004]
Login

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

Overview
Comment:merge trunk
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | dgp-refactor
Files: files | file ages | folders
SHA3-256: e4e31930042a9d5b1a85d1569b1bdfb08128ce42d603dd91d57b1c676a243063
User & Date: dgp 2019-02-28 20:35:06.215
Context
2019-03-08
15:09
merge trunk check-in: 2886da4545 user: dgp tags: dgp-refactor
2019-02-28
20:35
merge trunk check-in: e4e3193004 user: dgp tags: dgp-refactor
2019-02-27
21:58
Merge 8.7 check-in: 727e74f081 user: jan.nijtmans tags: trunk
2019-02-25
16:04
merge trunk check-in: 7fd2df44ff user: dgp tags: dgp-refactor
Changes
Unified Diff Ignore Whitespace Patch
Changes to .travis.yml.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
sudo: false
language: c

matrix:
  include:
    - os: linux
      dist: trusty
      compiler: clang
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: clang
      env:
        - CFGOPT=--disable-shared
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc
      env:
        - CFGOPT=--disable-shared
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc-4.9
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-4.9
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc-5
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-5
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc-6
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-6
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: trusty
      compiler: gcc-7
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-7






|




|





|




|





|










|










|










|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
sudo: false
language: c

matrix:
  include:
    - os: linux
      dist: xenial
      compiler: clang
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: clang
      env:
        - CFGOPT=--disable-shared
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc
      env:
        - CFGOPT=--disable-shared
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc-4.9
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-4.9
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc-5
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-5
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc-6
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-6
      env:
        - BUILD_DIR=unix
    - os: linux
      dist: xenial
      compiler: gcc-7
      addons:
        apt:
          sources:
            - ubuntu-toolchain-r-test
          packages:
            - g++-7
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
        - NO_DIRECT_CONFIGURE=1
    - os: osx
      osx_image: xcode9
      env:
        - BUILD_DIR=macosx
        - NO_DIRECT_CONFIGURE=1
    - os: osx
      osx_image: xcode10
      env:
        - BUILD_DIR=macosx
        - NO_DIRECT_CONFIGURE=1
### C builds not currently supported on Windows instances
#    - os: windows
#      env:
#        - BUILD_DIR=win
### ... so proxy with a Mingw cross-compile
# Test with mingw-w64 (32 bit)
    - os: linux
      dist: trusty
      compiler: i686-w64-mingw32-gcc
      addons:
        apt:
          packages:
            - gcc-mingw-w64-base
            - binutils-mingw-w64-i686
            - gcc-mingw-w64-i686
            - gcc-mingw-w64
            - gcc-multilib
            - wine
      env:
        - BUILD_DIR=win
        - CFGOPT=--host=i686-w64-mingw32
        - NO_DIRECT_TEST=1
# Test with mingw-w64 (64 bit)
    - os: linux
      dist: trusty
      compiler: x86_64-w64-mingw32-gcc
      addons:
        apt:
          packages:
            - gcc-mingw-w64-base
            - binutils-mingw-w64-x86-64
            - gcc-mingw-w64-x86-64







|










|
















|







80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
        - NO_DIRECT_CONFIGURE=1
    - os: osx
      osx_image: xcode9
      env:
        - BUILD_DIR=macosx
        - NO_DIRECT_CONFIGURE=1
    - os: osx
      osx_image: xcode10.2
      env:
        - BUILD_DIR=macosx
        - NO_DIRECT_CONFIGURE=1
### C builds not currently supported on Windows instances
#    - os: windows
#      env:
#        - BUILD_DIR=win
### ... so proxy with a Mingw cross-compile
# Test with mingw-w64 (32 bit)
    - os: linux
      dist: xenial
      compiler: i686-w64-mingw32-gcc
      addons:
        apt:
          packages:
            - gcc-mingw-w64-base
            - binutils-mingw-w64-i686
            - gcc-mingw-w64-i686
            - gcc-mingw-w64
            - gcc-multilib
            - wine
      env:
        - BUILD_DIR=win
        - CFGOPT=--host=i686-w64-mingw32
        - NO_DIRECT_TEST=1
# Test with mingw-w64 (64 bit)
    - os: linux
      dist: xenial
      compiler: x86_64-w64-mingw32-gcc
      addons:
        apt:
          packages:
            - gcc-mingw-w64-base
            - binutils-mingw-w64-x86-64
            - gcc-mingw-w64-x86-64
Changes to generic/tclBasic.c.
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151

    if (objc != 2) {
	MathFuncWrongNumArgs(interp, 2, objc, objv);
	return TCL_ERROR;
    }
    if (Tcl_GetDoubleFromObj(interp, objv[1], &dResult) != TCL_OK) {
#ifdef ACCEPT_NAN
	if (objv[1]->typePtr == &tclDoubleType) {
	    Tcl_SetObjResult(interp, objv[1]);
	    return TCL_OK;
	}
#endif
	return TCL_ERROR;
    }
    Tcl_SetObjResult(interp, Tcl_NewDoubleObj(dResult));







|







7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151

    if (objc != 2) {
	MathFuncWrongNumArgs(interp, 2, objc, objv);
	return TCL_ERROR;
    }
    if (Tcl_GetDoubleFromObj(interp, objv[1], &dResult) != TCL_OK) {
#ifdef ACCEPT_NAN
	if (TclHasIntRep(objv[1], &tclDoubleType)) {
	    Tcl_SetObjResult(interp, objv[1]);
	    return TCL_OK;
	}
#endif
	return TCL_ERROR;
    }
    Tcl_SetObjResult(interp, Tcl_NewDoubleObj(dResult));
Changes to generic/tclBinary.c.
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
#define SET_BYTEARRAY(irPtr, baPtr) \
		(irPtr)->twoPtrValue.ptr1 = (baPtr)

int
TclIsPureByteArray(
    Tcl_Obj * objPtr)
{
    return objPtr->typePtr == &properByteArrayType;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_NewByteArrayObj --
 *







|







287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
#define SET_BYTEARRAY(irPtr, baPtr) \
		(irPtr)->twoPtrValue.ptr1 = (baPtr)

int
TclIsPureByteArray(
    Tcl_Obj * objPtr)
{
    return TclHasIntRep(objPtr, &properByteArrayType);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_NewByteArrayObj --
 *
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
    int improper = 0;
    const char *src, *srcEnd;
    unsigned char *dst;
    Tcl_UniChar ch = 0;
    ByteArray *byteArrayPtr;
    Tcl_ObjIntRep ir;

    if (objPtr->typePtr == &properByteArrayType) {
	return TCL_OK;
    }
    if (objPtr->typePtr == &tclByteArrayType) {
	return TCL_OK;
    }

    src = TclGetStringFromObj(objPtr, &length);
    srcEnd = src + length;

    byteArrayPtr = Tcl_Alloc(BYTEARRAY_SIZE(length));







|


|







550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
    int improper = 0;
    const char *src, *srcEnd;
    unsigned char *dst;
    Tcl_UniChar ch = 0;
    ByteArray *byteArrayPtr;
    Tcl_ObjIntRep ir;

    if (TclHasIntRep(objPtr, &properByteArrayType)) {
	return TCL_OK;
    }
    if (TclHasIntRep(objPtr, &tclByteArrayType)) {
	return TCL_OK;
    }

    src = TclGetStringFromObj(objPtr, &length);
    srcEnd = src + length;

    byteArrayPtr = Tcl_Alloc(BYTEARRAY_SIZE(length));
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

    srcArrayPtr = GET_BYTEARRAY(TclFetchIntRep(srcPtr, &tclByteArrayType));
    length = srcArrayPtr->used;

    copyArrayPtr = ckalloc(BYTEARRAY_SIZE(length));
    copyArrayPtr->used = length;
    copyArrayPtr->allocated = length;
    memcpy(copyArrayPtr->bytes, srcArrayPtr->bytes, (size_t) length);

    SET_BYTEARRAY(&ir, copyArrayPtr);
    Tcl_StoreIntRep(copyPtr, &tclByteArrayType, &ir);
}

static void
DupProperByteArrayInternalRep(
    Tcl_Obj *srcPtr,		/* Object with internal rep to copy. */
    Tcl_Obj *copyPtr)		/* Object with internal rep to set. */
{
    unsigned int length;
    ByteArray *srcArrayPtr, *copyArrayPtr;
    Tcl_ObjIntRep ir;

    srcArrayPtr = GET_BYTEARRAY(TclFetchIntRep(srcPtr, &properByteArrayType));
    length = srcArrayPtr->used;

    copyArrayPtr = Tcl_Alloc(BYTEARRAY_SIZE(length));
    copyArrayPtr->used = length;
    copyArrayPtr->allocated = length;
    memcpy(copyArrayPtr->bytes, srcArrayPtr->bytes, (size_t) length);

    SET_BYTEARRAY(&ir, copyArrayPtr);
    Tcl_StoreIntRep(copyPtr, &properByteArrayType, &ir);
}

/*
 *----------------------------------------------------------------------







|




















|







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

    srcArrayPtr = GET_BYTEARRAY(TclFetchIntRep(srcPtr, &tclByteArrayType));
    length = srcArrayPtr->used;

    copyArrayPtr = ckalloc(BYTEARRAY_SIZE(length));
    copyArrayPtr->used = length;
    copyArrayPtr->allocated = length;
    memcpy(copyArrayPtr->bytes, srcArrayPtr->bytes, length);

    SET_BYTEARRAY(&ir, copyArrayPtr);
    Tcl_StoreIntRep(copyPtr, &tclByteArrayType, &ir);
}

static void
DupProperByteArrayInternalRep(
    Tcl_Obj *srcPtr,		/* Object with internal rep to copy. */
    Tcl_Obj *copyPtr)		/* Object with internal rep to set. */
{
    unsigned int length;
    ByteArray *srcArrayPtr, *copyArrayPtr;
    Tcl_ObjIntRep ir;

    srcArrayPtr = GET_BYTEARRAY(TclFetchIntRep(srcPtr, &properByteArrayType));
    length = srcArrayPtr->used;

    copyArrayPtr = Tcl_Alloc(BYTEARRAY_SIZE(length));
    copyArrayPtr->used = length;
    copyArrayPtr->allocated = length;
    memcpy(copyArrayPtr->bytes, srcArrayPtr->bytes, length);

    SET_BYTEARRAY(&ir, copyArrayPtr);
    Tcl_StoreIntRep(copyPtr, &properByteArrayType, &ir);
}

/*
 *----------------------------------------------------------------------
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
 badIndex:
    errorString = "not enough arguments for all format specifiers";
    goto error;

 badField:
    {
	Tcl_UniChar ch = 0;
	char buf[TCL_UTF_MAX + 1];

	TclUtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }







|







1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
 badIndex:
    errorString = "not enough arguments for all format specifiers";
    goto error;

 badField:
    {
	Tcl_UniChar ch = 0;
	char buf[TCL_UTF_MAX + 1] = "";

	TclUtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
 badIndex:
    errorString = "not enough arguments for all format specifiers";
    goto error;

 badField:
    {
	Tcl_UniChar ch = 0;
	char buf[TCL_UTF_MAX + 1];

	TclUtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }







|







1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
 badIndex:
    errorString = "not enough arguments for all format specifiers";
    goto error;

 badField:
    {
	Tcl_UniChar ch = 0;
	char buf[TCL_UTF_MAX + 1] = "";

	TclUtfToUniChar(errorString, &ch);
	buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
	Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		"bad field specifier \"%s\"", buf));
	return TCL_ERROR;
    }
Changes to generic/tclClock.c.
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
    }

    /*
     * fields.seconds could be an unsigned number that overflowed. Make sure
     * that it isn't.
     */

    if (objv[1]->typePtr == &tclBignumType) {
	Tcl_SetObjResult(interp, literals[LIT_INTEGER_VALUE_TOO_LARGE]);
	return TCL_ERROR;
    }

    /*
     * Convert UTC time to local.
     */







|







448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
    }

    /*
     * fields.seconds could be an unsigned number that overflowed. Make sure
     * that it isn't.
     */

    if (TclHasIntRep(objv[1], &tclBignumType)) {
	Tcl_SetObjResult(interp, literals[LIT_INTEGER_VALUE_TOO_LARGE]);
	return TCL_ERROR;
    }

    /*
     * Convert UTC time to local.
     */
Changes to generic/tclCmdMZ.c.
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234

	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

	    /*
	     * Assume Tcl_UniChar is an integral type...
	     */







|
|







1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234

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

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

	    /*
	     * Assume Tcl_UniChar is an integral type...
	     */
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
	 */

	if (TclIsPureByteArray(objv[1])) {
	    unsigned char uch = (unsigned char) ch;

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

	    end = Tcl_UniCharToUtf(ch, buf);
	    if (!end) {
		end = Tcl_UniCharToUtf(-1, buf);
	    }
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, end));
	}
    }
    return TCL_OK;
}








|


|
|







1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
	 */

	if (TclIsPureByteArray(objv[1])) {
	    unsigned char uch = (unsigned char) ch;

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

	    end = Tcl_UniCharToUtf(ch, buf);
	    if ((ch >= 0xD800) && (end < 3)) {
		end += Tcl_UniCharToUtf(-1, buf + end);
	    }
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, end));
	}
    }
    return TCL_OK;
}

1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
	}
	break;
    }
    case STR_IS_DIGIT:
	chcomp = Tcl_UniCharIsDigit;
	break;
    case STR_IS_DOUBLE: {
	if ((objPtr->typePtr == &tclDoubleType) ||
		(objPtr->typePtr == &tclIntType) ||
		(objPtr->typePtr == &tclBignumType)) {
	    break;
	}
	string1 = TclGetStringFromObj(objPtr, &length1);
	if (length1 == 0) {
	    if (strict) {
		result = 0;
	    }







|
|
|







1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
	}
	break;
    }
    case STR_IS_DIGIT:
	chcomp = Tcl_UniCharIsDigit;
	break;
    case STR_IS_DOUBLE: {
	if (TclHasIntRep(objPtr, &tclDoubleType) ||
		TclHasIntRep(objPtr, &tclIntType) ||
		TclHasIntRep(objPtr, &tclBignumType)) {
	    break;
	}
	string1 = TclGetStringFromObj(objPtr, &length1);
	if (length1 == 0) {
	    if (strict) {
		result = 0;
	    }
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
	break;
    }
    case STR_IS_GRAPH:
	chcomp = Tcl_UniCharIsGraph;
	break;
    case STR_IS_INT:
    case STR_IS_ENTIER:
	if ((objPtr->typePtr == &tclIntType) ||
		(objPtr->typePtr == &tclBignumType)) {
	    break;
	}
	string1 = TclGetStringFromObj(objPtr, &length1);
	if (length1 == 0) {
	    if (strict) {
		result = 0;
	    }







|
|







1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
	break;
    }
    case STR_IS_GRAPH:
	chcomp = Tcl_UniCharIsGraph;
	break;
    case STR_IS_INT:
    case STR_IS_ENTIER:
	if (TclHasIntRep(objPtr, &tclIntType) ||
		TclHasIntRep(objPtr, &tclBignumType)) {
	    break;
	}
	string1 = TclGetStringFromObj(objPtr, &length1);
	if (length1 == 0) {
	    if (strict) {
		result = 0;
	    }
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
	}
	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;
		break;
	    }







|
|







1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
	}
	end = string1 + length1;
	for (; string1 < end; string1 += length2, failat++) {
	    int fullchar;
	    length2 = TclUtfToUniChar(string1, &ch);
	    fullchar = ch;
#if TCL_UTF_MAX <= 4
	    if ((ch >= 0xD800) && (length2 < 3)) {
	    	length2 += TclUtfToUniChar(string1 + length2, &ch);
	    	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	    }
#endif
	    if (!chcomp(fullchar)) {
		result = 0;
		break;
	    }
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967

    /*
     * This test is tricky, but has to be that way or you get other strange
     * inconsistencies (see test string-10.20.1 for illustration why!)
     */

    if (!TclHasStringRep(objv[objc-2])
	    && (objv[objc-2]->typePtr == &tclDictType)){
	int i, done;
	Tcl_DictSearch search;

	/*
	 * We know the type exactly, so all dict operations will succeed for
	 * sure. This shortens this code quite a bit.
	 */







|







1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967

    /*
     * This test is tricky, but has to be that way or you get other strange
     * inconsistencies (see test string-10.20.1 for illustration why!)
     */

    if (!TclHasStringRep(objv[objc-2])
	    && TclHasIntRep(objv[objc-2], &tclDictType)){
	int i, done;
	Tcl_DictSearch search;

	/*
	 * We know the type exactly, so all dict operations will succeed for
	 * sure. This shortens this code quite a bit.
	 */
Changes to generic/tclCompCmdsSZ.c.
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
	count++;
    }

    for (endTokenPtr = tokenPtr + parse.numTokens;
	    tokenPtr < endTokenPtr; tokenPtr = TokenAfter(tokenPtr)) {
	size_t length;
	int literal, catchRange, breakJump;
	char buf[TCL_UTF_MAX];
	JumpFixup startFixup, okFixup, returnFixup, breakFixup;
	JumpFixup continueFixup, otherFixup, endFixup;

	switch (tokenPtr->type) {
	case TCL_TOKEN_TEXT:
	    literal = TclRegisterLiteral(envPtr,
		    tokenPtr->start, tokenPtr->size, 0);







|







1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
	count++;
    }

    for (endTokenPtr = tokenPtr + parse.numTokens;
	    tokenPtr < endTokenPtr; tokenPtr = TokenAfter(tokenPtr)) {
	size_t length;
	int literal, catchRange, breakJump;
	char buf[TCL_UTF_MAX] = "";
	JumpFixup startFixup, okFixup, returnFixup, breakFixup;
	JumpFixup continueFixup, otherFixup, endFixup;

	switch (tokenPtr->type) {
	case TCL_TOKEN_TEXT:
	    literal = TclRegisterLiteral(envPtr,
		    tokenPtr->start, tokenPtr->size, 0);
Changes to generic/tclCompile.c.
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
	    if (tempPtr != NULL) {
		Tcl_AppendToObj(tempPtr, tokenPtr->start, tokenPtr->size);
	    }
	    break;

	case TCL_TOKEN_BS:
	    if (tempPtr != NULL) {
		char utfBuf[TCL_UTF_MAX];
		size_t length = TclParseBackslash(tokenPtr->start,
			tokenPtr->size, NULL, utfBuf);

		Tcl_AppendToObj(tempPtr, utfBuf, length);
	    }
	    break;








|







1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
	    if (tempPtr != NULL) {
		Tcl_AppendToObj(tempPtr, tokenPtr->start, tokenPtr->size);
	    }
	    break;

	case TCL_TOKEN_BS:
	    if (tempPtr != NULL) {
		char utfBuf[TCL_UTF_MAX] = "";
		size_t length = TclParseBackslash(tokenPtr->start,
			tokenPtr->size, NULL, utfBuf);

		Tcl_AppendToObj(tempPtr, utfBuf, length);
	    }
	    break;

2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
				 * compile. */
    size_t count,		/* Number of tokens to consider at tokenPtr.
				 * Must be at least 1. */
    CompileEnv *envPtr)		/* Holds the resulting instructions. */
{
    Tcl_DString textBuffer;	/* Holds concatenated chars from adjacent
				 * TCL_TOKEN_TEXT, TCL_TOKEN_BS tokens. */
    char buffer[TCL_UTF_MAX];
    int numObjsToConcat, adjust;
    size_t i, length;
    unsigned char *entryCodeNext = envPtr->codeNext;
#define NUM_STATIC_POS 20
    int isLiteral, maxNumCL, numCL;
    int *clPosition = NULL;
    int depth = TclGetStackDepth(envPtr);







|







2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
				 * compile. */
    size_t count,		/* Number of tokens to consider at tokenPtr.
				 * Must be at least 1. */
    CompileEnv *envPtr)		/* Holds the resulting instructions. */
{
    Tcl_DString textBuffer;	/* Holds concatenated chars from adjacent
				 * TCL_TOKEN_TEXT, TCL_TOKEN_BS tokens. */
    char buffer[TCL_UTF_MAX] = "";
    int numObjsToConcat, adjust;
    size_t i, length;
    unsigned char *entryCodeNext = envPtr->codeNext;
#define NUM_STATIC_POS 20
    int isLiteral, maxNumCL, numCL;
    int *clPosition = NULL;
    int depth = TclGetStackDepth(envPtr);
Changes to generic/tclDictObj.c.
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623

    /*
     * Since lists and dictionaries have very closely-related string
     * representations (i.e. the same parsing code) we can safely special-case
     * the conversion from lists to dictionaries.
     */

    if (objPtr->typePtr == &tclListType) {
	int objc, i;
	Tcl_Obj **objv;

	/* Cannot fail, we already know the Tcl_ObjType is "list". */
	TclListObjGetElements(NULL, objPtr, &objc, &objv);
	if (objc & 1) {
	    goto missingValue;







|







609
610
611
612
613
614
615
616
617
618
619
620
621
622
623

    /*
     * Since lists and dictionaries have very closely-related string
     * representations (i.e. the same parsing code) we can safely special-case
     * the conversion from lists to dictionaries.
     */

    if (TclHasIntRep(objPtr, &tclListType)) {
	int objc, i;
	Tcl_Obj **objv;

	/* Cannot fail, we already know the Tcl_ObjType is "list". */
	TclListObjGetElements(NULL, objPtr, &objc, &objv);
	if (objc & 1) {
	    goto missingValue;
Changes to generic/tclDisassemble.c.
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
	 */

	if (objc != 3) {
	    Tcl_WrongNumArgs(interp, 2, objv, "script");
	    return TCL_ERROR;
	}

	if ((objv[2]->typePtr != &tclByteCodeType) && (TCL_OK
		!= TclSetByteCodeFromAny(interp, objv[2], NULL, NULL))) {
	    return TCL_ERROR;
	}
	codeObjPtr = objv[2];
	break;

    case DISAS_CLASS_CONSTRUCTOR:







|







1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
	 */

	if (objc != 3) {
	    Tcl_WrongNumArgs(interp, 2, objv, "script");
	    return TCL_ERROR;
	}

	if (!TclHasIntRep(objv[2], &tclByteCodeType) && (TCL_OK
		!= TclSetByteCodeFromAny(interp, objv[2], NULL, NULL))) {
	    return TCL_ERROR;
	}
	codeObjPtr = objv[2];
	break;

    case DISAS_CLASS_CONSTRUCTOR:
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
	    return TCL_ERROR;
	}

	/*
	 * Compile if necessary.
	 */

	if (procPtr->bodyPtr->typePtr != &tclByteCodeType) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */








|







1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
	    return TCL_ERROR;
	}

	/*
	 * Compile if necessary.
	 */

	if (!TclHasIntRep(procPtr->bodyPtr, &tclByteCodeType)) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */

1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
	    return TCL_ERROR;
	}

	/*
	 * Compile if necessary.
	 */

	if (procPtr->bodyPtr->typePtr != &tclByteCodeType) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */








|







1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
	    return TCL_ERROR;
	}

	/*
	 * Compile if necessary.
	 */

	if (!TclHasIntRep(procPtr->bodyPtr, &tclByteCodeType)) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */

1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
	if (procPtr == NULL) {
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(
		    "body not available for this kind of method", -1));
	    Tcl_SetErrorCode(interp, "TCL", "OPERATION", "DISASSEMBLE",
		    "METHODTYPE", NULL);
	    return TCL_ERROR;
	}
	if (procPtr->bodyPtr->typePtr != &tclByteCodeType) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */








|







1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
	if (procPtr == NULL) {
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(
		    "body not available for this kind of method", -1));
	    Tcl_SetErrorCode(interp, "TCL", "OPERATION", "DISASSEMBLE",
		    "METHODTYPE", NULL);
	    return TCL_ERROR;
	}
	if (!TclHasIntRep(procPtr->bodyPtr, &tclByteCodeType)) {
	    Command cmd;

	    /*
	     * Yes, this is ugly, but we need to pass the namespace in to the
	     * compiler in two places.
	     */

Changes to generic/tclEncoding.c.
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
	    src += 1;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	} else {
	    int len = TclUtfToUniChar(src, chPtr);
	    src += len;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
#if TCL_UTF_MAX <= 4
	    if (!len) {
		src += TclUtfToUniChar(src, chPtr);
		dst += Tcl_UniCharToUtf(*chPtr, dst);
	    }
#endif
	}
    }

    *srcReadPtr = src - srcStart;







|
|







2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
	    src += 1;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	} else {
	    int len = TclUtfToUniChar(src, chPtr);
	    src += len;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
#if TCL_UTF_MAX <= 4
	    if ((*chPtr >= 0xD800) && (len < 3)) {
		src += TclUtfToUniChar(src + len, chPtr);
		dst += Tcl_UniCharToUtf(*chPtr, dst);
	    }
#endif
	}
    }

    *srcReadPtr = src - srcStart;
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962

	/*
	 * Check for illegal characters.
	 */

	if (ch > 0xff
#if TCL_UTF_MAX <= 4
		|| !len
#endif
		) {
	    if (flags & TCL_ENCODING_STOPONERROR) {
		result = TCL_CONVERT_UNKNOWN;
		break;
	    }
#if TCL_UTF_MAX <= 4
	    if (!len) len = 4;
#endif
	    /*
	     * Plunge on, using '?' as a fallback character.
	     */

	    ch = (Tcl_UniChar) '?';
	}







|







|







2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962

	/*
	 * Check for illegal characters.
	 */

	if (ch > 0xff
#if TCL_UTF_MAX <= 4
		|| ((ch >= 0xD800) && (len < 3))
#endif
		) {
	    if (flags & TCL_ENCODING_STOPONERROR) {
		result = TCL_CONVERT_UNKNOWN;
		break;
	    }
#if TCL_UTF_MAX <= 4
	    if ((ch >= 0xD800) && (len < 3)) len = 4;
#endif
	    /*
	     * Plunge on, using '?' as a fallback character.
	     */

	    ch = (Tcl_UniChar) '?';
	}
Changes to generic/tclExecute.c.
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
	TRACE(("\"%.30s\" \"%.30s\" => ", O2S(valuePtr), O2S(value2Ptr)));

	/*
	 * Extract the desired list element.
	 */

	if ((TclListObjGetElements(interp, valuePtr, &objc, &objv) == TCL_OK)
		&& (value2Ptr->typePtr != &tclListType)
		&& (TclGetIntForIndexM(NULL, value2Ptr, objc-1,
			&index) == TCL_OK)) {
	    TclDecrRefCount(value2Ptr);
	    tosPtr--;
	    pcAdjustment = 1;
	    goto lindexFastPath;
	}







|







4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
	TRACE(("\"%.30s\" \"%.30s\" => ", O2S(valuePtr), O2S(value2Ptr)));

	/*
	 * Extract the desired list element.
	 */

	if ((TclListObjGetElements(interp, valuePtr, &objc, &objv) == TCL_OK)
		&& !TclHasIntRep(value2Ptr, &tclListType)
		&& (TclGetIntForIndexM(NULL, value2Ptr, objc-1,
			&index) == TCL_OK)) {
	    TclDecrRefCount(value2Ptr);
	    tosPtr--;
	    pcAdjustment = 1;
	    goto lindexFastPath;
	}
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
	} else if (TclIsPureByteArray(valuePtr)) {
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && slength == 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.
	     */
	    if (ch == -1) {
		objResultPtr = Tcl_NewObj();
	    } else {
		slength = Tcl_UniCharToUtf(ch, buf);
		if (!slength) {
		    slength = Tcl_UniCharToUtf(-1, buf);
		}
		objResultPtr = Tcl_NewStringObj(buf, slength);
	    }
	}

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







|











|
|







5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
	} else if (TclIsPureByteArray(valuePtr)) {
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && slength == 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.
	     */
	    if (ch == -1) {
		objResultPtr = Tcl_NewObj();
	    } else {
		slength = Tcl_UniCharToUtf(ch, buf);
		if ((ch >= 0xD800) && (slength < 3)) {
		    slength += Tcl_UniCharToUtf(-1, buf + slength);
		}
		objResultPtr = Tcl_NewStringObj(buf, slength);
	    }
	}

	TRACE_APPEND(("\"%s\"\n", O2S(objResultPtr)));
	NEXT_INST_F(1, 2, 1);
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
	    TclNewObj(statePtr);
	    ir.twoPtrValue.ptr1 = searchPtr;
	    ir.twoPtrValue.ptr2 = dictPtr;
	    Tcl_StoreIntRep(statePtr, &dictIteratorType, &ir);
	}
	varPtr = LOCAL(opnd);
	if (varPtr->value.objPtr) {
	    if (varPtr->value.objPtr->typePtr == &dictIteratorType) {
		Tcl_Panic("mis-issued dictFirst!");
	    }
	    TclDecrRefCount(varPtr->value.objPtr);
	}
	varPtr->value.objPtr = statePtr;
	Tcl_IncrRefCount(statePtr);
	goto pushDictIteratorResult;







|







6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
	    TclNewObj(statePtr);
	    ir.twoPtrValue.ptr1 = searchPtr;
	    ir.twoPtrValue.ptr2 = dictPtr;
	    Tcl_StoreIntRep(statePtr, &dictIteratorType, &ir);
	}
	varPtr = LOCAL(opnd);
	if (varPtr->value.objPtr) {
	    if (TclHasIntRep(varPtr->value.objPtr, &dictIteratorType)) {
		Tcl_Panic("mis-issued dictFirst!");
	    }
	    TclDecrRefCount(varPtr->value.objPtr);
	}
	varPtr->value.objPtr = statePtr;
	Tcl_IncrRefCount(statePtr);
	goto pushDictIteratorResult;
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
    objBytesIfUnshared = 0.0;
    strBytesIfUnshared = 0.0;
    strBytesSharedMultX = 0.0;
    strBytesSharedOnce = 0.0;
    for (i = 0;  i < globalTablePtr->numBuckets;  i++) {
	for (entryPtr = globalTablePtr->buckets[i];  entryPtr != NULL;
		entryPtr = entryPtr->nextPtr) {
	    if (entryPtr->objPtr->typePtr == &tclByteCodeType) {
		numByteCodeLits++;
	    }
	    (void) TclGetStringFromObj(entryPtr->objPtr, &length);
	    refCountSum += entryPtr->refCount;
	    objBytesIfUnshared += (entryPtr->refCount * sizeof(Tcl_Obj));
	    strBytesIfUnshared += (entryPtr->refCount * (length+1));
	    if (entryPtr->refCount > 1) {







|







9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
    objBytesIfUnshared = 0.0;
    strBytesIfUnshared = 0.0;
    strBytesSharedMultX = 0.0;
    strBytesSharedOnce = 0.0;
    for (i = 0;  i < globalTablePtr->numBuckets;  i++) {
	for (entryPtr = globalTablePtr->buckets[i];  entryPtr != NULL;
		entryPtr = entryPtr->nextPtr) {
	    if (TclHasIntRep(entryPtr->objPtr, &tclByteCodeType)) {
		numByteCodeLits++;
	    }
	    (void) TclGetStringFromObj(entryPtr->objPtr, &length);
	    refCountSum += entryPtr->refCount;
	    objBytesIfUnshared += (entryPtr->refCount * sizeof(Tcl_Obj));
	    strBytesIfUnshared += (entryPtr->refCount * (length+1));
	    if (entryPtr->refCount > 1) {
Changes to generic/tclFileName.c.
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
 *---------------------------------------------------------------------------
 */

unsigned
Tcl_GetFSDeviceFromStat(
    const Tcl_StatBuf *statPtr)
{
    return (unsigned) statPtr->st_dev;
}

unsigned
Tcl_GetFSInodeFromStat(
    const Tcl_StatBuf *statPtr)
{
    return (unsigned) statPtr->st_ino;
}

unsigned
Tcl_GetModeFromStat(
    const Tcl_StatBuf *statPtr)
{
    return (unsigned) statPtr->st_mode;
}

int
Tcl_GetLinkCountFromStat(
    const Tcl_StatBuf *statPtr)
{
    return (int)statPtr->st_nlink;







|






|






|







2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
 *---------------------------------------------------------------------------
 */

unsigned
Tcl_GetFSDeviceFromStat(
    const Tcl_StatBuf *statPtr)
{
    return statPtr->st_dev;
}

unsigned
Tcl_GetFSInodeFromStat(
    const Tcl_StatBuf *statPtr)
{
    return statPtr->st_ino;
}

unsigned
Tcl_GetModeFromStat(
    const Tcl_StatBuf *statPtr)
{
    return statPtr->st_mode;
}

int
Tcl_GetLinkCountFromStat(
    const Tcl_StatBuf *statPtr)
{
    return (int)statPtr->st_nlink;
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
}

unsigned
Tcl_GetBlockSizeFromStat(
    const Tcl_StatBuf *statPtr)
{
#ifdef HAVE_STRUCT_STAT_ST_BLKSIZE
    return (unsigned) statPtr->st_blksize;
#else
    /*
     * Not a great guess, but will do...
     */

    return GUESSED_BLOCK_SIZE;
#endif







|







2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
}

unsigned
Tcl_GetBlockSizeFromStat(
    const Tcl_StatBuf *statPtr)
{
#ifdef HAVE_STRUCT_STAT_ST_BLKSIZE
    return statPtr->st_blksize;
#else
    /*
     * Not a great guess, but will do...
     */

    return GUESSED_BLOCK_SIZE;
#endif
Changes to generic/tclInt.h.
4677
4678
4679
4680
4681
4682
4683


4684
4685
4686
4687
4688
4689
4690
4691
4692
 * MODULE_SCOPE int	TclIsPureByteArray(Tcl_Obj *objPtr);
 *----------------------------------------------------------------
 */

MODULE_SCOPE int	TclIsPureByteArray(Tcl_Obj *objPtr);
#define TclIsPureDict(objPtr) \
	(((objPtr)->bytes==NULL) && ((objPtr)->typePtr==&tclDictType))


#define TclFetchIntRep(objPtr, type) \
	(((objPtr)->typePtr == type) ? &((objPtr)->internalRep) : NULL)


/*
 *----------------------------------------------------------------
 * Macro used by the Tcl core to compare Unicode strings. On big-endian
 * systems we can use the more efficient memcmp, but this would not be
 * lexically correct on little-endian systems. The ANSI C "prototype" for







>
>

|







4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
 * MODULE_SCOPE int	TclIsPureByteArray(Tcl_Obj *objPtr);
 *----------------------------------------------------------------
 */

MODULE_SCOPE int	TclIsPureByteArray(Tcl_Obj *objPtr);
#define TclIsPureDict(objPtr) \
	(((objPtr)->bytes==NULL) && ((objPtr)->typePtr==&tclDictType))
#define TclHasIntRep(objPtr, type) \
	((objPtr)->typePtr == (type)) 
#define TclFetchIntRep(objPtr, type) \
	(TclHasIntRep((objPtr), (type)) ? &((objPtr)->internalRep) : NULL)


/*
 *----------------------------------------------------------------
 * Macro used by the Tcl core to compare Unicode strings. On big-endian
 * systems we can use the more efficient memcmp, but this would not be
 * lexically correct on little-endian systems. The ANSI C "prototype" for
Changes to generic/tclListObj.c.
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
     * Dictionaries are a special case; they have a string representation such
     * that *all* valid dictionaries are valid lists. Hence we can convert
     * more directly. Only do this when there's no existing string rep; if
     * there is, it is the string rep that's authoritative (because it could
     * describe duplicate keys).
     */

    if (!TclHasStringRep(objPtr) && (objPtr->typePtr == &tclDictType)) {
	Tcl_Obj *keyPtr, *valuePtr;
	Tcl_DictSearch search;
	int done, size;

	/*
	 * Create the new list representation. Note that we do not need to do
	 * anything with the string representation as the transformation (and







|







1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
     * Dictionaries are a special case; they have a string representation such
     * that *all* valid dictionaries are valid lists. Hence we can convert
     * more directly. Only do this when there's no existing string rep; if
     * there is, it is the string rep that's authoritative (because it could
     * describe duplicate keys).
     */

    if (!TclHasStringRep(objPtr) && TclHasIntRep(objPtr, &tclDictType)) {
	Tcl_Obj *keyPtr, *valuePtr;
	Tcl_DictSearch search;
	int done, size;

	/*
	 * Create the new list representation. Note that we do not need to do
	 * anything with the string representation as the transformation (and
Changes to generic/tclParse.c.
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
				 * written. At most TCL_UTF_MAX bytes will be
				 * written there. */
{
    register const char *p = src+1;
    Tcl_UniChar unichar = 0;
    int result;
    size_t count;
    char buf[TCL_UTF_MAX];

    if (numBytes == 0) {
	if (readPtr != NULL) {
	    *readPtr = 0;
	}
	return 0;
    }







|







1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
				 * written. At most TCL_UTF_MAX bytes will be
				 * written there. */
{
    register const char *p = src+1;
    Tcl_UniChar unichar = 0;
    int result;
    size_t count;
    char buf[TCL_UTF_MAX] = "";

    if (numBytes == 0) {
	if (readPtr != NULL) {
	    *readPtr = 0;
	}
	return 0;
    }
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
    }

  done:
    if (readPtr != NULL) {
	*readPtr = count;
    }
    count = Tcl_UniCharToUtf(result, dst);
    if (!count) {
	/* Special case for handling high surrogates. */
	count = Tcl_UniCharToUtf(-1, dst);
    }
    return count;
}

/*
 *----------------------------------------------------------------------
 *







|

|







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

  done:
    if (readPtr != NULL) {
	*readPtr = count;
    }
    count = Tcl_UniCharToUtf(result, dst);
    if ((result >= 0xD800) && (count < 3)) {
	/* Special case for handling high surrogates. */
	count += Tcl_UniCharToUtf(-1, dst + count);
    }
    return count;
}

/*
 *----------------------------------------------------------------------
 *
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597

    adjust = 0;
    result = NULL;
    for (; count>0 && code==TCL_OK ; count--, tokenPtr++) {
	Tcl_Obj *appendObj = NULL;
	const char *append = NULL;
	int appendByteLength = 0;
	char utfCharBytes[TCL_UTF_MAX];

	switch (tokenPtr->type) {
	case TCL_TOKEN_TEXT:
	    append = tokenPtr->start;
	    appendByteLength = tokenPtr->size;
	    break;








|







2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597

    adjust = 0;
    result = NULL;
    for (; count>0 && code==TCL_OK ; count--, tokenPtr++) {
	Tcl_Obj *appendObj = NULL;
	const char *append = NULL;
	int appendByteLength = 0;
	char utfCharBytes[TCL_UTF_MAX] = "";

	switch (tokenPtr->type) {
	case TCL_TOKEN_TEXT:
	    append = tokenPtr->start;
	    appendByteLength = tokenPtr->size;
	    break;

Changes to generic/tclPathObj.c.
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572

Tcl_Obj *
TclPathPart(
    Tcl_Interp *interp,		/* Used for error reporting */
    Tcl_Obj *pathPtr,		/* Path to take dirname of */
    Tcl_PathPart portion)	/* Requested portion of name */
{
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    if (irPtr) {
	FsPath *fsPathPtr = PATHOBJ(pathPtr);

	if (PATHFLAGS(pathPtr) != 0) {
	    switch (portion) {
	    case TCL_PATH_DIRNAME: {
		/*
		 * Check if the joined-on bit has any directory delimiters in







|
<
<







556
557
558
559
560
561
562
563


564
565
566
567
568
569
570

Tcl_Obj *
TclPathPart(
    Tcl_Interp *interp,		/* Used for error reporting */
    Tcl_Obj *pathPtr,		/* Path to take dirname of */
    Tcl_PathPart portion)	/* Requested portion of name */
{
    if (TclHasIntRep(pathPtr, &fsPathType)) {


	FsPath *fsPathPtr = PATHOBJ(pathPtr);

	if (PATHFLAGS(pathPtr) != 0) {
	    switch (portion) {
	    case TCL_PATH_DIRNAME: {
		/*
		 * Check if the joined-on bit has any directory delimiters in
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
int
Tcl_FSConvertToPathType(
    Tcl_Interp *interp,		/* Interpreter in which to store error message
				 * (if necessary). */
    Tcl_Obj *pathPtr)		/* Object to convert to a valid, current path
				 * type. */
{
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    /*
     * While it is bad practice to examine an object's type directly, this is
     * actually the best thing to do here. The reason is that if we are
     * converting this object to FsPath type for the first time, we don't need
     * to worry whether the 'cwd' has changed. On the other hand, if this
     * object is already of FsPath type, and is a relative path, we do have to
     * worry about the cwd. If the cwd has changed, we must recompute the
     * path.
     */

    if (irPtr) {
	if (TclFSEpochOk(PATHOBJ(pathPtr)->filesystemEpoch)) {
	    return TCL_OK;
	}

	TclGetString(pathPtr);
	Tcl_StoreIntRep(pathPtr, &fsPathType, NULL);
    }







<
<










|







1151
1152
1153
1154
1155
1156
1157


1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
int
Tcl_FSConvertToPathType(
    Tcl_Interp *interp,		/* Interpreter in which to store error message
				 * (if necessary). */
    Tcl_Obj *pathPtr)		/* Object to convert to a valid, current path
				 * type. */
{


    /*
     * While it is bad practice to examine an object's type directly, this is
     * actually the best thing to do here. The reason is that if we are
     * converting this object to FsPath type for the first time, we don't need
     * to worry whether the 'cwd' has changed. On the other hand, if this
     * object is already of FsPath type, and is a relative path, we do have to
     * worry about the cwd. If the cwd has changed, we must recompute the
     * path.
     */

    if (TclHasIntRep(pathPtr, &fsPathType)) {
	if (TclFSEpochOk(PATHOBJ(pathPtr)->filesystemEpoch)) {
	    return TCL_OK;
	}

	TclGetString(pathPtr);
	Tcl_StoreIntRep(pathPtr, &fsPathType, NULL);
    }
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492

static int
MakePathFromNormalized(
    Tcl_Interp *interp,		/* Used for error reporting if not NULL. */
    Tcl_Obj *pathPtr)		/* The object to convert. */
{
    FsPath *fsPathPtr;
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    if (irPtr) {
	return TCL_OK;
    }

    fsPathPtr = Tcl_Alloc(sizeof(FsPath));

    /*
     * It's a pure normalized absolute path.







<

|







1472
1473
1474
1475
1476
1477
1478

1479
1480
1481
1482
1483
1484
1485
1486
1487

static int
MakePathFromNormalized(
    Tcl_Interp *interp,		/* Used for error reporting if not NULL. */
    Tcl_Obj *pathPtr)		/* The object to convert. */
{
    FsPath *fsPathPtr;


    if (TclHasIntRep(pathPtr, &fsPathType)) {
	return TCL_OK;
    }

    fsPathPtr = Tcl_Alloc(sizeof(FsPath));

    /*
     * It's a pure normalized absolute path.
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099

int
TclFSEnsureEpochOk(
    Tcl_Obj *pathPtr,
    const Tcl_Filesystem **fsPtrPtr)
{
    FsPath *srcFsPathPtr;
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    if (irPtr == NULL) {
	return TCL_OK;
    }

    srcFsPathPtr = PATHOBJ(pathPtr);

    /*
     * Check if the filesystem has changed in some way since this object's







<

|







2078
2079
2080
2081
2082
2083
2084

2085
2086
2087
2088
2089
2090
2091
2092
2093

int
TclFSEnsureEpochOk(
    Tcl_Obj *pathPtr,
    const Tcl_Filesystem **fsPtrPtr)
{
    FsPath *srcFsPathPtr;


    if (!TclHasIntRep(pathPtr, &fsPathType)) {
	return TCL_OK;
    }

    srcFsPathPtr = PATHOBJ(pathPtr);

    /*
     * Check if the filesystem has changed in some way since this object's
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
void
TclFSSetPathDetails(
    Tcl_Obj *pathPtr,
    const Tcl_Filesystem *fsPtr,
    ClientData clientData)
{
    FsPath *srcFsPathPtr;
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);;

    /*
     * Make sure pathPtr is of the correct type.
     */

    if (irPtr == NULL) {
	if (SetFsPathFromAny(NULL, pathPtr) != TCL_OK) {
	    return;
	}
    }

    srcFsPathPtr = PATHOBJ(pathPtr);
    srcFsPathPtr->fsPtr = fsPtr;







<





|







2136
2137
2138
2139
2140
2141
2142

2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
void
TclFSSetPathDetails(
    Tcl_Obj *pathPtr,
    const Tcl_Filesystem *fsPtr,
    ClientData clientData)
{
    FsPath *srcFsPathPtr;


    /*
     * Make sure pathPtr is of the correct type.
     */

    if (!TclHasIntRep(pathPtr, &fsPathType)) {
	if (SetFsPathFromAny(NULL, pathPtr) != TCL_OK) {
	    return;
	}
    }

    srcFsPathPtr = PATHOBJ(pathPtr);
    srcFsPathPtr->fsPtr = fsPtr;
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
    Tcl_Interp *interp,		/* Used for error reporting if not NULL. */
    Tcl_Obj *pathPtr)		/* The object to convert. */
{
    size_t len;
    FsPath *fsPathPtr;
    Tcl_Obj *transPtr;
    char *name;
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    if (irPtr) {
	return TCL_OK;
    }

    /*
     * First step is to translate the filename. This is similar to
     * Tcl_TranslateFilename, but shouldn't convert everything to windows
     * backslashes on that platform. The current implementation of this piece







<

|







2240
2241
2242
2243
2244
2245
2246

2247
2248
2249
2250
2251
2252
2253
2254
2255
    Tcl_Interp *interp,		/* Used for error reporting if not NULL. */
    Tcl_Obj *pathPtr)		/* The object to convert. */
{
    size_t len;
    FsPath *fsPathPtr;
    Tcl_Obj *transPtr;
    char *name;


    if (TclHasIntRep(pathPtr, &fsPathType)) {
	return TCL_OK;
    }

    /*
     * First step is to translate the filename. This is similar to
     * Tcl_TranslateFilename, but shouldn't convert everything to windows
     * backslashes on that platform. The current implementation of this piece
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
 */

int
TclNativePathInFilesystem(
    Tcl_Obj *pathPtr,
    ClientData *clientDataPtr)
{
    Tcl_ObjIntRep *irPtr = TclFetchIntRep(pathPtr, &fsPathType);

    /*
     * A special case is required to handle the empty path "". This is a valid
     * path (i.e. the user should be able to do 'file exists ""' without
     * throwing an error), but equally the path doesn't exist. Those are the
     * semantics of Tcl (at present anyway), so we have to abide by them here.
     */

    if (irPtr) {
	if (pathPtr->bytes != NULL && pathPtr->bytes[0] == '\0') {
	    /*
	     * We reject the empty path "".
	     */

	    return -1;
	}







<
<







|







2548
2549
2550
2551
2552
2553
2554


2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
 */

int
TclNativePathInFilesystem(
    Tcl_Obj *pathPtr,
    ClientData *clientDataPtr)
{


    /*
     * A special case is required to handle the empty path "". This is a valid
     * path (i.e. the user should be able to do 'file exists ""' without
     * throwing an error), but equally the path doesn't exist. Those are the
     * semantics of Tcl (at present anyway), so we have to abide by them here.
     */

    if (TclHasIntRep(pathPtr, &fsPathType)) {
	if (pathPtr->bytes != NULL && pathPtr->bytes[0] == '\0') {
	    /*
	     * We reject the empty path "".
	     */

	    return -1;
	}
Changes to generic/tclScan.c.
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
				 * required. */
{
    int gotXpg, gotSequential, value, i, flags;
    char *end;
    Tcl_UniChar ch = 0;
    int objIndex, xpgSize, nspace = numVars;
    int *nassign = TclStackAlloc(interp, nspace * sizeof(int));
    char buf[TCL_UTF_MAX+1];
    Tcl_Obj *errorMsg;		/* Place to build an error messages. Note that
				 * these are messy operations because we do
				 * not want to use the formatting engine;
				 * we're inside there! */

    /*
     * Initialize an array that records the number of times a variable is







|







257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
				 * required. */
{
    int gotXpg, gotSequential, value, i, flags;
    char *end;
    Tcl_UniChar ch = 0;
    int objIndex, xpgSize, nspace = numVars;
    int *nassign = TclStackAlloc(interp, nspace * sizeof(int));
    char buf[TCL_UTF_MAX+1] = "";
    Tcl_Obj *errorMsg;		/* Place to build an error messages. Note that
				 * these are messy operations because we do
				 * not want to use the formatting engine;
				 * we're inside there! */

    /*
     * Initialize an array that records the number of times a variable is
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
	    /*
	     * Scan a single Unicode character.
	     */

	    offset = TclUtfToUniChar(string, &sch);
	    i = (int)sch;
#if TCL_UTF_MAX == 4
	    if (!offset) {
		offset = TclUtfToUniChar(string, &sch);
		i = (((i<<10) & 0x0FFC00) + 0x10000) + (sch & 0x3FF);
	    }
#endif
	    string += offset;
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewWideIntObj(i);
		Tcl_IncrRefCount(objPtr);







|
|







878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
	    /*
	     * Scan a single Unicode character.
	     */

	    offset = TclUtfToUniChar(string, &sch);
	    i = (int)sch;
#if TCL_UTF_MAX == 4
	    if (((sch & 0xFC00) == 0xD800) && (offset < 3)) {
		offset += TclUtfToUniChar(string+offset, &sch);
		i = (((i<<10) & 0x0FFC00) + 0x10000) + (sch & 0x3FF);
	    }
#endif
	    string += offset;
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewWideIntObj(i);
		Tcl_IncrRefCount(objPtr);
Changes to generic/tclStringObj.c.
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
	    char buf[4];
	    int code, length;

	    if (TclGetIntFromObj(interp, segment, &code) != TCL_OK) {
		goto error;
	    }
	    length = Tcl_UniCharToUtf(code, buf);
	    if (!length) {
		/* Special case for handling high surrogates. */
		length = Tcl_UniCharToUtf(-1, buf);
	    }
	    segment = Tcl_NewStringObj(buf, length);
	    Tcl_IncrRefCount(segment);
	    allocSegment = 1;
	    break;
	}








|

|







1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
	    char buf[4];
	    int code, length;

	    if (TclGetIntFromObj(interp, segment, &code) != TCL_OK) {
		goto error;
	    }
	    length = Tcl_UniCharToUtf(code, buf);
	    if ((code >= 0xD800) && (length < 3)) {
		/* Special case for handling high surrogates. */
		length += Tcl_UniCharToUtf(-1, buf + length);
	    }
	    segment = Tcl_NewStringObj(buf, length);
	    Tcl_IncrRefCount(segment);
	    allocSegment = 1;
	    break;
	}

Changes to generic/tclUtf.c.
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
183
184
185
186
187
188
	    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;
	}
    } else if (ch == -1) {
	if (((buf[0] & 0xF8) == 0xF0) && ((buf[1] & 0xC0) == 0x80)
		&& ((buf[2] & 0xCF) == 0)) {
	    ch = 0xD7C0 + ((buf[0] & 0x07) << 8) + ((buf[1] & 0x3F) << 2)
		    + ((buf[2] & 0x30) >> 4);



	    goto three;
	}
    }

    ch = 0xFFFD;
three:
    buf[2] = (char) ((ch | 0x80) & 0xBF);
    buf[1] = (char) (((ch >> 6) | 0x80) & 0xBF);







|
<
|
|
|
|

|




|



|












|
|
|
|
>
>
>
|







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
183
184
185
186
187
188
189
190
	    buf[0] = (char) ((ch >> 6) | 0xC0);
	    return 2;
	}
	if (ch <= 0xFFFF) {
	    if ((ch & 0xF800) == 0xD800) {
		if (ch & 0x0400) {
		    /* Low surrogate */
		    if (((buf[0] & 0xC0) == 0x80) && ((buf[1] & 0xCF) == 0)) {

			/* Previous Tcl_UniChar was a high surrogate, so combine */
			buf[2] = (char) ((ch & 0x3F) | 0x80);
			buf[1] |= (char) (((ch >> 6) & 0x0F) | 0x80);
			return 3;
		    }
		    /* 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 1;
		}
	    }
	    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;
	}
    } else if (ch == -1) {
	if (((buf[0] & 0xC0) == 0x80) && ((buf[1] & 0xCF) == 0)
		&& ((buf[-1] & 0xF8) == 0xF0)) {
	    ch = 0xD7C0 + ((buf[-1] & 0x07) << 8) + ((buf[0] & 0x3F) << 2)
		    + ((buf[1] & 0x30) >> 4);
	    buf[1] = (char) ((ch | 0x80) & 0xBF);
	    buf[0] = (char) (((ch >> 6) | 0x80) & 0xBF);
	    buf[-1] = (char) ((ch >> 12) | 0xE0);
	    return 2;
	}
    }

    ch = 0xFFFD;
three:
    buf[2] = (char) ((ch | 0x80) & 0xBF);
    buf[1] = (char) (((ch >> 6) | 0x80) & 0xBF);
234
235
236
237
238
239
240



241
242
243
244
245
246
247
    for (w = uniStr; w < wEnd; ) {
	if (!len && ((*w & 0xFC00) != 0xDC00)) {
	    /* Special case for handling high surrogates. */
	    p += Tcl_UniCharToUtf(-1, p);
	}
	len = Tcl_UniCharToUtf(*w, p);
	p += len;



	w++;
    }
    if (!len) {
	/* Special case for handling high surrogates. */
	p += Tcl_UniCharToUtf(-1, p);
    }
    Tcl_DStringSetLength(dsPtr, oldLength + (p - string));







>
>
>







236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
    for (w = uniStr; w < wEnd; ) {
	if (!len && ((*w & 0xFC00) != 0xDC00)) {
	    /* Special case for handling high surrogates. */
	    p += Tcl_UniCharToUtf(-1, p);
	}
	len = Tcl_UniCharToUtf(*w, p);
	p += len;
	if ((*w >= 0xD800) && (len < 3)) {
	    len = 0; /* Indication that high surrogate was found */
	}
	w++;
    }
    if (!len) {
	/* Special case for handling high surrogates. */
	p += Tcl_UniCharToUtf(-1, p);
    }
    Tcl_DStringSetLength(dsPtr, oldLength + (p - string));
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
319
320
321
322
323
324
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
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400

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.
	     */

	    *chPtr = (Tcl_UniChar) (((byte & 0x1F) << 6) | (src[1] & 0x3F));
	    if ((unsigned)(*chPtr - 1) >= (UNICODE_SELF - 1)) {
		return 2;
	    }
	}

	/*
	 * A two-byte-character lead-byte not followed by trail-byte
	 * represents itself.
	 */
    } else if (byte < 0xF0) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80)) {
	    /*
	     * Three-byte-character lead byte followed by two trail bytes.
	     */

	    *chPtr = (Tcl_UniChar) (((byte & 0x0F) << 12)
		    | ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
	    if (*chPtr > 0x7FF) {
		return 3;
	    }
	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
    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 */
	    } else if (*chPtr != surrogate) {
		/* produce high surrogate, but don't advance source pointer */
		*chPtr = surrogate;
		return 0;
	    } else {
		/* produce low surrogate, and advance source pointer */
		*chPtr = (Tcl_UniChar) (0xDC00 | (byte & 0x3FF));
		return 4;
	    }
#else
	    *chPtr = (Tcl_UniChar) (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
	    if ((unsigned)(*chPtr - 0x10000) <= 0xFFFFF) {
		return 4;
	    }
#endif
	}

	/*
	 * A four-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --







|


|












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

|








|















|

















|
<
<
|
<
|

<
<
<
<

|
|
|


|

|











|







298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
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
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381


382

383
384




385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412

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. */
{
    Tcl_UniChar byte;

    /*
     * Unroll 1 to 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 TCL_UTF_MAX <= 4
	/* If *chPtr contains a high surrogate (produced by a previous
	 * Tcl_UtfToUniChar() call) and the next 3 bytes are UTF-8 continuation
	 * bytes, then we must produce a follow-up low surrogate. We only
	 * do that if the high surrogate matches the bits we encounter.
	 */
	if ((byte >= 0x80)
		&& (((((byte - 0x10) << 2) & 0xFC) | 0xD800) == (*chPtr & 0xFCFC))
		&& ((src[1] & 0xF0) == (((*chPtr << 4) & 0x30) | 0x80))
		&& ((src[2] & 0xC0) == 0x80)) {
	    *chPtr = ((src[1] & 0x0F) << 6) + (src[2] & 0x3F) + 0xDC00;
	    return 3;
	}
#endif
	if (byte-0x80 < 0x20) {
	    *chPtr = cp1252[byte-0x80];
	} else {
	    *chPtr = byte;
	}
	return 1;
    } else if (byte < 0xE0) {
	if ((src[1] & 0xC0) == 0x80) {
	    /*
	     * Two-byte-character lead-byte followed by a trail-byte.
	     */

	    *chPtr = (((byte & 0x1F) << 6) | (src[1] & 0x3F));
	    if ((unsigned)(*chPtr - 1) >= (UNICODE_SELF - 1)) {
		return 2;
	    }
	}

	/*
	 * A two-byte-character lead-byte not followed by trail-byte
	 * represents itself.
	 */
    } else if (byte < 0xF0) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80)) {
	    /*
	     * Three-byte-character lead byte followed by two trail bytes.
	     */

	    *chPtr = (((byte & 0x0F) << 12)
		    | ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
	    if (*chPtr > 0x7FF) {
		return 3;
	    }
	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
    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 high = (((byte & 0x07) << 8) | ((src[1] & 0x3F) << 2)


		    | ((src[2] & 0x3F) >> 4)) - 0x40;

	    if (high >= 0x400) {
		/* out of range, < 0x10000 or > 0x10ffff */




	    } else {
		/* produce high surrogate, advance source pointer */
		*chPtr = 0xD800 + high;
		return 1;
	    }
#else
	    *chPtr = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
	    if ((*chPtr - 0x10000) <= 0xFFFFF) {
		return 4;
	    }
#endif
	}

	/*
	 * A four-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }

    *chPtr = byte;
    return 1;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
	p += TclUtfToUniChar(p, &ch);
	*w++ = ch;
    }
    end += 4;
    while (p < end) {
	if (Tcl_UtfCharComplete(p, end-p)) {
	    p += TclUtfToUniChar(p, &ch);
	} else if ((unsigned)((UCHAR(*p)-0x80)) < (unsigned) 0x20) {
	    ch = (Tcl_UniChar) cp1252[UCHAR(*p++)-0x80];
	} else {
	    ch = UCHAR(*p++);
	}
	*w++ = ch;
    }
    *w = '\0';
    Tcl_DStringSetLength(dsPtr,







|
|







459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
	p += TclUtfToUniChar(p, &ch);
	*w++ = ch;
    }
    end += 4;
    while (p < end) {
	if (Tcl_UtfCharComplete(p, end-p)) {
	    p += TclUtfToUniChar(p, &ch);
	} else if (((UCHAR(*p)-0x80)) < 0x20) {
	    ch = cp1252[UCHAR(*p++)-0x80];
	} else {
	    ch = UCHAR(*p++);
	}
	*w++ = ch;
    }
    *w = '\0';
    Tcl_DStringSetLength(dsPtr,
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
    int 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;
	}
	if (*src == '\0') {







|
|







591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
    int fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
	if (*src == '\0') {
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
    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;
	}
	if (*src == '\0') {







|
|







640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {
	    len += TclUtfToUniChar(src + len, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}
	if (*src == '\0') {
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    size_t len = TclUtfToUniChar(src, &ch);

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







|
|







683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    size_t len = TclUtfToUniChar(src, &ch);

#if TCL_UTF_MAX <= 4
    if ((ch >= 0xD800) && (len < 3)) {
	len += TclUtfToUniChar(src + len, &ch);
    }
#endif
    return src + len;
}

/*
 *---------------------------------------------------------------------------
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX <= 4
	size_t len = 1;
#endif

    src += TclUtfToUniChar(src, &ch);
    while (index--) {
#if TCL_UTF_MAX <= 4
	src += (len = TclUtfToUniChar(src, &ch));
#else
	src += TclUtfToUniChar(src, &ch);
#endif
    }
    fullchar = ch;
#if TCL_UTF_MAX <= 4
     if (!len) {
	/* If last Tcl_UniChar was a high surrogate, combine with low surrogate */
	(void)TclUtfToUniChar(src, &ch);
	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
    }
#endif
    return fullchar;
}







|












|







765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX <= 4
	size_t len = 0;
#endif

    src += TclUtfToUniChar(src, &ch);
    while (index--) {
#if TCL_UTF_MAX <= 4
	src += (len = TclUtfToUniChar(src, &ch));
#else
	src += TclUtfToUniChar(src, &ch);
#endif
    }
    fullchar = ch;
#if TCL_UTF_MAX <= 4
    if ((ch >= 0xD800) && (len < 3)) {
	/* If last Tcl_UniChar was a high surrogate, combine with low surrogate */
	(void)TclUtfToUniChar(src, &ch);
	fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
    }
#endif
    return fullchar;
}
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
#if TCL_UTF_MAX <= 4
    size_t len = 1;
#endif

    if (index != TCL_AUTO_LENGTH) {
	while (index--) {
#if TCL_UTF_MAX <= 4
	    src += (len = TclUtfToUniChar(src, &ch));
#else
	    src += TclUtfToUniChar(src, &ch);
#endif
	}
#if TCL_UTF_MAX <= 4
	if (!len) {
	    /* Index points at character following High Surrogate */
	    src += TclUtfToUniChar(src, &ch);
	}
#endif
    }
    return src;
}

/*
 *---------------------------------------------------------------------------







|











|
|
|
|







813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register size_t index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
#if TCL_UTF_MAX <= 4
    size_t len = 0;
#endif

    if (index != TCL_AUTO_LENGTH) {
	while (index--) {
#if TCL_UTF_MAX <= 4
	    src += (len = TclUtfToUniChar(src, &ch));
#else
	    src += TclUtfToUniChar(src, &ch);
#endif
	}
#if TCL_UTF_MAX <= 4
    if ((ch >= 0xD800) && (len < 3)) {
	/* Index points at character following high Surrogate */
	src += TclUtfToUniChar(src, &ch);
    }
#endif
    }
    return src;
}

/*
 *---------------------------------------------------------------------------
899
900
901
902
903
904
905
906
907
908
909
910
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
945
int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int upChar;
    char *src, *dst;
    size_t bytes;

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	upChar = ch;
#if TCL_UTF_MAX <= 4
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    upChar = (((upChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	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.
	 */

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







|







|


|
<
|












|
|
|



|







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
945
946
947
948
949
950
951
952
953
954
955
956
int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int upChar;
    char *src, *dst;
    size_t len;

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	upChar = ch;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {

	    len += TclUtfToUniChar(src + len, &ch);
	    /* Combine surrogates */
	    upChar = (((upChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	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.
	 */

	if ((len < TclUtfCount(upChar)) || ((upChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int lowChar;
    char *src, *dst;
    size_t bytes;

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
#if TCL_UTF_MAX <= 4
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	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.
	 */

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







|







|


|
<
|












|
|
|



|







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

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	lowChar = ch;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {

	    len += TclUtfToUniChar(src + len, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	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.
	 */

	if ((len < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int titleChar, lowChar;
    char *src, *dst;
    size_t bytes;

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

    src = dst = str;

    if (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	titleChar = ch;
#if TCL_UTF_MAX <= 4
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	titleChar = Tcl_UniCharToTitle(titleChar);

	if ((bytes < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
#if TCL_UTF_MAX <= 4
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

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







|









|


|
<
|






|
|
|



|


|


|
<
|









|
|
|



|







1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056

1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076

1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0;
    int titleChar, lowChar;
    char *src, *dst;
    size_t len;

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

    src = dst = str;

    if (*src) {
	len = TclUtfToUniChar(src, &ch);
	titleChar = ch;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {

	    len += TclUtfToUniChar(src + len, &ch);
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	titleChar = Tcl_UniCharToTitle(titleChar);

	if ((len < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += len;
    }
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	lowChar = ch;
#if TCL_UTF_MAX <= 4
	if ((ch >= 0xD800) && (len < 3)) {

	    len += TclUtfToUniChar(src + len, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if ((len < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
Changes to generic/tclZipfs.c.
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
 *	This cache is never cleared.
 *
 *-------------------------------------------------------------------------
 */

#ifdef _WIN32
#define LIBRARY_SIZE	    64

static inline int
WCharToUtf(
    const WCHAR *wSrc,
    char *dst)
{
    char *start = dst;

    while (*wSrc != '\0') {
	dst += Tcl_UniCharToUtf(*wSrc, dst);
	wSrc++;
    }
    *dst = '\0';
    return (int) (dst - start);
}
#endif /* _WIN32 */

Tcl_Obj *
TclZipfs_TclLibrary(void)
{
    Tcl_Obj *vfsInitScript;
    int found;







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







3145
3146
3147
3148
3149
3150
3151















3152
3153
3154
3155
3156
3157
3158
 *	This cache is never cleared.
 *
 *-------------------------------------------------------------------------
 */

#ifdef _WIN32
#define LIBRARY_SIZE	    64















#endif /* _WIN32 */

Tcl_Obj *
TclZipfs_TclLibrary(void)
{
    Tcl_Obj *vfsInitScript;
    int found;
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
    /*
     * Look for the library file system within the DLL/shared library.  Note
     * that we must mount the zip file and dll before releasing to search.
     */

#if defined(_WIN32)
    hModule = TclWinGetTclInstance();
    if (GetModuleFileNameW(hModule, wName, MAX_PATH) == 0) {
	GetModuleFileNameA(hModule, dllName, MAX_PATH);
    } else {
	WCharToUtf(wName, dllName);
    }

    if (ZipfsAppHookFindTclInit(dllName) == TCL_OK) {
	return Tcl_NewStringObj(zipfs_literal_tcl_library, -1);
    }
#elif /* !_WIN32 && */ defined(CFG_RUNTIME_DLLFILE)
    if (ZipfsAppHookFindTclInit(
	    CFG_RUNTIME_LIBDIR "/" CFG_RUNTIME_DLLFILE) == TCL_OK) {







|
<
<
|
<







3188
3189
3190
3191
3192
3193
3194
3195


3196

3197
3198
3199
3200
3201
3202
3203
    /*
     * Look for the library file system within the DLL/shared library.  Note
     * that we must mount the zip file and dll before releasing to search.
     */

#if defined(_WIN32)
    hModule = TclWinGetTclInstance();
    GetModuleFileNameW(hModule, wName, MAX_PATH);


    WideCharToMultiByte(CP_UTF8, 0, wName, -1, dllName, sizeof(dllName), NULL, NULL);


    if (ZipfsAppHookFindTclInit(dllName) == TCL_OK) {
	return Tcl_NewStringObj(zipfs_literal_tcl_library, -1);
    }
#elif /* !_WIN32 && */ defined(CFG_RUNTIME_DLLFILE)
    if (ZipfsAppHookFindTclInit(
	    CFG_RUNTIME_LIBDIR "/" CFG_RUNTIME_DLLFILE) == TCL_OK) {
Changes to win/tclWin32Dll.c.
568
569
570
571
572
573
574




575
576
577
578
579
580
581
    for (w = (TCHAR *)string; w < wEnd; ) {
	if (!blen && ((*w & 0xFC00) != 0xDC00)) {
	    /* Special case for handling high surrogates. */
	    p += Tcl_UniCharToUtf(-1, p);
	}
	blen = Tcl_UniCharToUtf(*w, p);
	p += blen;




	w++;
    }
    if (!blen) {
	/* Special case for handling high surrogates. */
	p += Tcl_UniCharToUtf(-1, p);
    }
    Tcl_DStringSetLength(dsPtr, oldLength + (p - result));







>
>
>
>







568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
    for (w = (TCHAR *)string; w < wEnd; ) {
	if (!blen && ((*w & 0xFC00) != 0xDC00)) {
	    /* Special case for handling high surrogates. */
	    p += Tcl_UniCharToUtf(-1, p);
	}
	blen = Tcl_UniCharToUtf(*w, p);
	p += blen;
	if ((*w >= 0xD800) && (blen < 3)) {
	    /* Indication that high surrogate is handled */
	    blen = 0;
	}
	w++;
    }
    if (!blen) {
	/* Special case for handling high surrogates. */
	p += Tcl_UniCharToUtf(-1, p);
    }
    Tcl_DStringSetLength(dsPtr, oldLength + (p - result));