Tcl Source Code

Check-in [6d946ddf77]
Login

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

Overview
Comment:merge trunk
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | tip-389-impl
Files: files | file ages | folders
SHA1: 6d946ddf7771ae9b14c5ea1d7f151fd4dd56b0b0
User & Date: jan.nijtmans 2017-05-29 15:38:04
Context
2017-05-31
12:51
merge trunk check-in: f07a85fee0 user: jan.nijtmans tags: tip-389-impl
2017-05-29
15:38
merge trunk check-in: 6d946ddf77 user: jan.nijtmans tags: tip-389-impl
13:14
merge core-8-6-branch check-in: a9965b7335 user: jan.nijtmans tags: trunk
2017-05-23
14:57
merge trunk check-in: 9430d4c198 user: jan.nijtmans tags: tip-389-impl
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to generic/tclBinary.c.

547
548
549
550
551
552
553
554
555
556
557
558
559
560
561

    src = TclGetString(objPtr);
    length = objPtr->length;
    srcEnd = src + length;

    byteArrayPtr = ckalloc(BYTEARRAY_SIZE(length));
    for (dst = byteArrayPtr->bytes; src < srcEnd; ) {
	src += Tcl_UtfToUniChar(src, &ch);
	improper = improper || (ch > 255);
	*dst++ = UCHAR(ch);
    }

    byteArrayPtr->used = dst - byteArrayPtr->bytes;
    byteArrayPtr->allocated = length;








|







547
548
549
550
551
552
553
554
555
556
557
558
559
560
561

    src = TclGetString(objPtr);
    length = objPtr->length;
    srcEnd = src + length;

    byteArrayPtr = ckalloc(BYTEARRAY_SIZE(length));
    for (dst = byteArrayPtr->bytes; src < srcEnd; ) {
	src += TclUtfToUniChar(src, &ch);
	improper = improper || (ch > 255);
	*dst++ = UCHAR(ch);
    }

    byteArrayPtr->used = dst - byteArrayPtr->bytes;
    byteArrayPtr->allocated = length;

1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
    goto error;

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

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

 error:







|







1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
    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;
    }

 error:
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
    goto error;

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

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

 error:







|







1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
    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;
    }

 error:

Changes to generic/tclCmdIL.c.

4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
	/*
	 * Convert character to Unicode for comparison purposes. If either
	 * string is at the terminating null, do a byte-wise comparison and
	 * bail out immediately.
	 */

	if ((*left != '\0') && (*right != '\0')) {
	    left += Tcl_UtfToUniChar(left, &uniLeft);
	    right += Tcl_UtfToUniChar(right, &uniRight);

	    /*
	     * Convert both chars to lower for the comparison, because
	     * dictionary sorts are case insensitve. Covert to lower, not
	     * upper, so chars between Z and a will sort before A (where most
	     * other interesting punctuations occur).
	     */







|
|







4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
	/*
	 * Convert character to Unicode for comparison purposes. If either
	 * string is at the terminating null, do a byte-wise comparison and
	 * bail out immediately.
	 */

	if ((*left != '\0') && (*right != '\0')) {
	    left += TclUtfToUniChar(left, &uniLeft);
	    right += TclUtfToUniChar(right, &uniRight);

	    /*
	     * Convert both chars to lower for the comparison, because
	     * dictionary sorts are case insensitve. Covert to lower, not
	     * upper, so chars between Z and a will sort before A (where most
	     * other interesting punctuations occur).
	     */

Changes to generic/tclCompExpr.c.

2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
     * We reject leading underscores in bareword.  No sensible reason why.
     * Might be inspired by reserved identifier rules in C, which of course
     * have no direct relevance here.
     */

    if (!TclIsBareword(*start) || *start == '_') {
	if (Tcl_UtfCharComplete(start, numBytes)) {
	    scanned = Tcl_UtfToUniChar(start, &ch);
	} else {
	    char utfBytes[TCL_UTF_MAX];

	    memcpy(utfBytes, start, (size_t) numBytes);
	    utfBytes[numBytes] = '\0';
	    scanned = Tcl_UtfToUniChar(utfBytes, &ch);
	}
	*lexemePtr = INVALID;
	Tcl_DecrRefCount(literal);
	return scanned;
    }
    end = start;
    while (numBytes && TclIsBareword(*end)) {







|





|







2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
     * We reject leading underscores in bareword.  No sensible reason why.
     * Might be inspired by reserved identifier rules in C, which of course
     * have no direct relevance here.
     */

    if (!TclIsBareword(*start) || *start == '_') {
	if (Tcl_UtfCharComplete(start, numBytes)) {
	    scanned = TclUtfToUniChar(start, &ch);
	} else {
	    char utfBytes[TCL_UTF_MAX];

	    memcpy(utfBytes, start, (size_t) numBytes);
	    utfBytes[numBytes] = '\0';
	    scanned = TclUtfToUniChar(utfBytes, &ch);
	}
	*lexemePtr = INVALID;
	Tcl_DecrRefCount(literal);
	return scanned;
    }
    end = start;
    while (numBytes && TclIsBareword(*end)) {

Changes to generic/tclEncoding.c.

2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
	     * Convert 0xc080 to real nulls when we are in output mode.
	     */

	    *dst++ = 0;
	    src += 2;
	} else if (!Tcl_UtfCharComplete(src, srcEnd - src)) {
	    /*
	     * Always check before using Tcl_UtfToUniChar. Not doing can so
	     * cause it run beyond the endof the buffer! If we happen such an
	     * incomplete char its byts are made to represent themselves.
	     */

		*chPtr = (unsigned char) *src;
	    src += 1;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	} else {
	    int n = Tcl_UtfToUniChar(src, chPtr);
	    src += n;
	    if (!n) numChars--;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	}
    }

    *srcReadPtr = src - srcStart;







|








|







2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
	     * Convert 0xc080 to real nulls when we are in output mode.
	     */

	    *dst++ = 0;
	    src += 2;
	} else if (!Tcl_UtfCharComplete(src, srcEnd - src)) {
	    /*
	     * Always check before using TclUtfToUniChar. Not doing can so
	     * cause it run beyond the endof the buffer! If we happen such an
	     * incomplete char its byts are made to represent themselves.
	     */

		*chPtr = (unsigned char) *src;
	    src += 1;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	} else {
	    int n = TclUtfToUniChar(src, chPtr);
	    src += n;
	    if (!n) numChars--;
	    dst += Tcl_UniCharToUtf(*chPtr, dst);
	}
    }

    *srcReadPtr = src - srcStart;

Changes to generic/tclLoad.c.

332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
#ifdef __CYGWIN__
		if ((pkgGuess[0] == 'c') && (pkgGuess[1] == 'y')
			&& (pkgGuess[2] == 'g')) {
		    pkgGuess += 3;
		}
#endif /* __CYGWIN__ */
		for (p = pkgGuess; *p != 0; p += offset) {
		    offset = Tcl_UtfToUniChar(p, &ch);
		    if ((ch > 0x100)
			    || !(isalpha(UCHAR(ch)) /* INTL: ISO only */
				    || (UCHAR(ch) == '_'))) {
			break;
		    }
		}
		if (p == pkgGuess) {







|







332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
#ifdef __CYGWIN__
		if ((pkgGuess[0] == 'c') && (pkgGuess[1] == 'y')
			&& (pkgGuess[2] == 'g')) {
		    pkgGuess += 3;
		}
#endif /* __CYGWIN__ */
		for (p = pkgGuess; *p != 0; p += offset) {
		    offset = TclUtfToUniChar(p, &ch);
		    if ((ch > 0x100)
			    || !(isalpha(UCHAR(ch)) /* INTL: ISO only */
				    || (UCHAR(ch) == '_'))) {
			break;
		    }
		}
		if (p == pkgGuess) {

Changes to generic/tclParse.c.

959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
	 * We have to convert here in case the user has put a backslash in
	 * front of a multi-byte utf-8 character. While this means nothing
	 * special, we shouldn't break up a correct utf-8 character. [Bug
	 * #217987] test subst-3.2
	 */

	if (Tcl_UtfCharComplete(p, numBytes - 1)) {
	    count = Tcl_UtfToUniChar(p, &unichar) + 1;	/* +1 for '\' */
	} else {
	    char utfBytes[TCL_UTF_MAX];

	    memcpy(utfBytes, p, (size_t) (numBytes - 1));
	    utfBytes[numBytes - 1] = '\0';
	    count = Tcl_UtfToUniChar(utfBytes, &unichar) + 1;
	}
	result = unichar;
	break;
    }

  done:
    if (readPtr != NULL) {







|





|







959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
	 * We have to convert here in case the user has put a backslash in
	 * front of a multi-byte utf-8 character. While this means nothing
	 * special, we shouldn't break up a correct utf-8 character. [Bug
	 * #217987] test subst-3.2
	 */

	if (Tcl_UtfCharComplete(p, numBytes - 1)) {
	    count = TclUtfToUniChar(p, &unichar) + 1;	/* +1 for '\' */
	} else {
	    char utfBytes[TCL_UTF_MAX];

	    memcpy(utfBytes, p, (size_t) (numBytes - 1));
	    utfBytes[numBytes - 1] = '\0';
	    count = TclUtfToUniChar(utfBytes, &unichar) + 1;
	}
	result = unichar;
	break;
    }

  done:
    if (readPtr != NULL) {

Changes to generic/tclPkg.c.

220
221
222
223
224
225
226

227
228
229
230
231
232
233
    entry = Tcl_FirstHashEntry(&pkgFiles->table, &search);
    while (entry) {
	Tcl_Obj *obj = (Tcl_Obj *)Tcl_GetHashValue(entry);
	Tcl_DecrRefCount(obj);
	entry = Tcl_NextHashEntry(&search);
    }
    Tcl_DeleteHashTable(&pkgFiles->table);

    return;
}

void *TclInitPkgFiles(Tcl_Interp *interp)
{
    /* If assocdata "tclPkgFiles" doesn't exist yet, create it */
    PkgFiles *pkgFiles = Tcl_GetAssocData(interp, "tclPkgFiles", NULL);







>







220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
    entry = Tcl_FirstHashEntry(&pkgFiles->table, &search);
    while (entry) {
	Tcl_Obj *obj = (Tcl_Obj *)Tcl_GetHashValue(entry);
	Tcl_DecrRefCount(obj);
	entry = Tcl_NextHashEntry(&search);
    }
    Tcl_DeleteHashTable(&pkgFiles->table);
    ckfree(pkgFiles);
    return;
}

void *TclInitPkgFiles(Tcl_Interp *interp)
{
    /* If assocdata "tclPkgFiles" doesn't exist yet, create it */
    PkgFiles *pkgFiles = Tcl_GetAssocData(interp, "tclPkgFiles", NULL);

Changes to generic/tclScan.c.

74
75
76
77
78
79
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
123
124
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
{
    Tcl_UniChar ch = 0, start;
    int offset, nranges;
    const char *end;

    memset(cset, 0, sizeof(CharSet));

    offset = Tcl_UtfToUniChar(format, &ch);
    if (ch == '^') {
	cset->exclude = 1;
	format += offset;
	offset = Tcl_UtfToUniChar(format, &ch);
    }
    end = format + offset;

    /*
     * Find the close bracket so we can overallocate the set.
     */

    if (ch == ']') {
	end += Tcl_UtfToUniChar(end, &ch);
    }
    nranges = 0;
    while (ch != ']') {
	if (ch == '-') {
	    nranges++;
	}
	end += Tcl_UtfToUniChar(end, &ch);
    }

    cset->chars = ckalloc(sizeof(Tcl_UniChar) * (end - format - 1));
    if (nranges > 0) {
	cset->ranges = ckalloc(sizeof(struct Range) * nranges);
    } else {
	cset->ranges = NULL;
    }

    /*
     * Now build the character set.
     */

    cset->nchars = cset->nranges = 0;
    format += Tcl_UtfToUniChar(format, &ch);
    start = ch;
    if (ch == ']' || ch == '-') {
	cset->chars[cset->nchars++] = ch;
	format += Tcl_UtfToUniChar(format, &ch);
    }
    while (ch != ']') {
	if (*format == '-') {
	    /*
	     * This may be the first character of a range, so don't add it
	     * yet.
	     */

	    start = ch;
	} else if (ch == '-') {
	    /*
	     * Check to see if this is the last character in the set, in which
	     * case it is not a range and we should add the previous character
	     * as well as the dash.
	     */

	    if (*format == ']') {
		cset->chars[cset->nchars++] = start;
		cset->chars[cset->nchars++] = ch;
	    } else {
		format += Tcl_UtfToUniChar(format, &ch);

		/*
		 * Check to see if the range is in reverse order.
		 */

		if (start < ch) {
		    cset->ranges[cset->nranges].start = start;
		    cset->ranges[cset->nranges].end = ch;
		} else {
		    cset->ranges[cset->nranges].start = ch;
		    cset->ranges[cset->nranges].end = start;
		}
		cset->nranges++;
	    }
	} else {
	    cset->chars[cset->nchars++] = ch;
	}
	format += Tcl_UtfToUniChar(format, &ch);
    }
    return format;
}

/*
 *----------------------------------------------------------------------
 *







|



|








|






|














|



|




















|

















|







74
75
76
77
78
79
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
123
124
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
{
    Tcl_UniChar ch = 0, start;
    int offset, nranges;
    const char *end;

    memset(cset, 0, sizeof(CharSet));

    offset = TclUtfToUniChar(format, &ch);
    if (ch == '^') {
	cset->exclude = 1;
	format += offset;
	offset = TclUtfToUniChar(format, &ch);
    }
    end = format + offset;

    /*
     * Find the close bracket so we can overallocate the set.
     */

    if (ch == ']') {
	end += TclUtfToUniChar(end, &ch);
    }
    nranges = 0;
    while (ch != ']') {
	if (ch == '-') {
	    nranges++;
	}
	end += TclUtfToUniChar(end, &ch);
    }

    cset->chars = ckalloc(sizeof(Tcl_UniChar) * (end - format - 1));
    if (nranges > 0) {
	cset->ranges = ckalloc(sizeof(struct Range) * nranges);
    } else {
	cset->ranges = NULL;
    }

    /*
     * Now build the character set.
     */

    cset->nchars = cset->nranges = 0;
    format += TclUtfToUniChar(format, &ch);
    start = ch;
    if (ch == ']' || ch == '-') {
	cset->chars[cset->nchars++] = ch;
	format += TclUtfToUniChar(format, &ch);
    }
    while (ch != ']') {
	if (*format == '-') {
	    /*
	     * This may be the first character of a range, so don't add it
	     * yet.
	     */

	    start = ch;
	} else if (ch == '-') {
	    /*
	     * Check to see if this is the last character in the set, in which
	     * case it is not a range and we should add the previous character
	     * as well as the dash.
	     */

	    if (*format == ']') {
		cset->chars[cset->nchars++] = start;
		cset->chars[cset->nchars++] = ch;
	    } else {
		format += TclUtfToUniChar(format, &ch);

		/*
		 * Check to see if the range is in reverse order.
		 */

		if (start < ch) {
		    cset->ranges[cset->nranges].start = start;
		    cset->ranges[cset->nranges].end = ch;
		} else {
		    cset->ranges[cset->nranges].start = ch;
		    cset->ranges[cset->nranges].end = start;
		}
		cset->nranges++;
	    }
	} else {
	    cset->chars[cset->nchars++] = ch;
	}
	format += TclUtfToUniChar(format, &ch);
    }
    return format;
}

/*
 *----------------------------------------------------------------------
 *
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
    for (i = 0; i < nspace; i++) {
	nassign[i] = 0;
    }

    xpgSize = objIndex = gotXpg = gotSequential = 0;

    while (*format != '\0') {
	format += Tcl_UtfToUniChar(format, &ch);

	flags = 0;

	if (ch != '%') {
	    continue;
	}
	format += Tcl_UtfToUniChar(format, &ch);
	if (ch == '%') {
	    continue;
	}
	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += Tcl_UtfToUniChar(format, &ch);
	    goto xpgCheckDone;
	}

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    /*
	     * Check for an XPG3-style %n$ specification. Note: there must
	     * not be a mixture of XPG3 specs and non-XPG3 specs in the same
	     * format string.
	     */

	    value = strtoul(format-1, &end, 10);	/* INTL: "C" locale. */
	    if (*end != '$') {
		goto notXpg;
	    }
	    format = end+1;
	    format += Tcl_UtfToUniChar(format, &ch);
	    gotXpg = 1;
	    if (gotSequential) {
		goto mixedXPG;
	    }
	    objIndex = value - 1;
	    if ((objIndex < 0) || (numVars && (objIndex >= numVars))) {
		goto badIndex;







|






|





|















|







275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
    for (i = 0; i < nspace; i++) {
	nassign[i] = 0;
    }

    xpgSize = objIndex = gotXpg = gotSequential = 0;

    while (*format != '\0') {
	format += TclUtfToUniChar(format, &ch);

	flags = 0;

	if (ch != '%') {
	    continue;
	}
	format += TclUtfToUniChar(format, &ch);
	if (ch == '%') {
	    continue;
	}
	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += TclUtfToUniChar(format, &ch);
	    goto xpgCheckDone;
	}

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    /*
	     * Check for an XPG3-style %n$ specification. Note: there must
	     * not be a mixture of XPG3 specs and non-XPG3 specs in the same
	     * format string.
	     */

	    value = strtoul(format-1, &end, 10);	/* INTL: "C" locale. */
	    if (*end != '$') {
		goto notXpg;
	    }
	    format = end+1;
	    format += TclUtfToUniChar(format, &ch);
	    gotXpg = 1;
	    if (gotSequential) {
		goto mixedXPG;
	    }
	    objIndex = value - 1;
	    if ((objIndex < 0) || (numVars && (objIndex >= numVars))) {
		goto badIndex;
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
	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    value = strtoul(format-1, (char **) &format, 10);	/* INTL: "C" locale. */
	    flags |= SCAN_WIDTH;
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += Tcl_UtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	case 'h':
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	if (!(flags & SCAN_SUPPRESS) && numVars && (objIndex >= numVars)) {
	    goto badIndex;
	}

	/*







|











|





|







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
	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    value = strtoul(format-1, (char **) &format, 10);	/* INTL: "C" locale. */
	    flags |= SCAN_WIDTH;
	    format += TclUtfToUniChar(format, &ch);
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += TclUtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	case 'h':
	    format += TclUtfToUniChar(format, &ch);
	}

	if (!(flags & SCAN_SUPPRESS) && numVars && (objIndex >= numVars)) {
	    goto badIndex;
	}

	/*
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
	case '[':
	    if (flags & (SCAN_LONGER|SCAN_BIG)) {
		goto invalidFieldSize;
	    }
	    if (*format == '\0') {
		goto badSet;
	    }
	    format += Tcl_UtfToUniChar(format, &ch);
	    if (ch == '^') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    if (ch == ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    while (ch != ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    break;
	badSet:
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(
		    "unmatched [ in format string", -1));
	    Tcl_SetErrorCode(interp, "TCL", "FORMAT", "BRACKET", NULL);
	    goto error;







|




|





|





|







430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
	case '[':
	    if (flags & (SCAN_LONGER|SCAN_BIG)) {
		goto invalidFieldSize;
	    }
	    if (*format == '\0') {
		goto badSet;
	    }
	    format += TclUtfToUniChar(format, &ch);
	    if (ch == '^') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += TclUtfToUniChar(format, &ch);
	    }
	    if (ch == ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += TclUtfToUniChar(format, &ch);
	    }
	    while (ch != ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += TclUtfToUniChar(format, &ch);
	    }
	    break;
	badSet:
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(
		    "unmatched [ in format string", -1));
	    Tcl_SetErrorCode(interp, "TCL", "FORMAT", "BRACKET", NULL);
	    goto error;
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
     * mismatch.
     */

    objIndex = 0;
    nconversions = 0;
    while (*format != '\0') {
	int parseFlag = TCL_PARSE_NO_WHITESPACE;
	format += Tcl_UtfToUniChar(format, &ch);

	flags = 0;

	/*
	 * If we see whitespace in the format, skip whitespace in the string.
	 */

	if (Tcl_UniCharIsSpace(ch)) {
	    offset = Tcl_UtfToUniChar(string, &sch);
	    while (Tcl_UniCharIsSpace(sch)) {
		if (*string == '\0') {
		    goto done;
		}
		string += offset;
		offset = Tcl_UtfToUniChar(string, &sch);
	    }
	    continue;
	}

	if (ch != '%') {
	literal:
	    if (*string == '\0') {
		underflow = 1;
		goto done;
	    }
	    string += Tcl_UtfToUniChar(string, &sch);
	    if (ch != sch) {
		goto done;
	    }
	    continue;
	}

	format += Tcl_UtfToUniChar(format, &ch);
	if (ch == '%') {
	    goto literal;
	}

	/*
	 * Check for assignment suppression ('*') or an XPG3-style assignment
	 * ('%n$').
	 */

	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += Tcl_UtfToUniChar(format, &ch);
	} else if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    char *formatEnd;
	    value = strtoul(format-1, &formatEnd, 10);/* INTL: "C" locale. */
	    if (*formatEnd == '$') {
		format = formatEnd+1;
		format += Tcl_UtfToUniChar(format, &ch);
		objIndex = (int) value - 1;
	    }
	}

	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    width = (int) strtoul(format-1, (char **) &format, 10);/* INTL: "C" locale. */
	    format += Tcl_UtfToUniChar(format, &ch);
	} else {
	    width = 0;
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += Tcl_UtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	    /*
	     * Fall through so we skip to the next character.
	     */
	case 'h':
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	/*
	 * Handle the various field types.
	 */

	switch (ch) {







|








|





|










|






|











|





|










|













|








|







626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
     * mismatch.
     */

    objIndex = 0;
    nconversions = 0;
    while (*format != '\0') {
	int parseFlag = TCL_PARSE_NO_WHITESPACE;
	format += TclUtfToUniChar(format, &ch);

	flags = 0;

	/*
	 * If we see whitespace in the format, skip whitespace in the string.
	 */

	if (Tcl_UniCharIsSpace(ch)) {
	    offset = TclUtfToUniChar(string, &sch);
	    while (Tcl_UniCharIsSpace(sch)) {
		if (*string == '\0') {
		    goto done;
		}
		string += offset;
		offset = TclUtfToUniChar(string, &sch);
	    }
	    continue;
	}

	if (ch != '%') {
	literal:
	    if (*string == '\0') {
		underflow = 1;
		goto done;
	    }
	    string += TclUtfToUniChar(string, &sch);
	    if (ch != sch) {
		goto done;
	    }
	    continue;
	}

	format += TclUtfToUniChar(format, &ch);
	if (ch == '%') {
	    goto literal;
	}

	/*
	 * Check for assignment suppression ('*') or an XPG3-style assignment
	 * ('%n$').
	 */

	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += TclUtfToUniChar(format, &ch);
	} else if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    char *formatEnd;
	    value = strtoul(format-1, &formatEnd, 10);/* INTL: "C" locale. */
	    if (*formatEnd == '$') {
		format = formatEnd+1;
		format += TclUtfToUniChar(format, &ch);
		objIndex = (int) value - 1;
	    }
	}

	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    width = (int) strtoul(format-1, (char **) &format, 10);/* INTL: "C" locale. */
	    format += TclUtfToUniChar(format, &ch);
	} else {
	    width = 0;
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += TclUtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	    /*
	     * Fall through so we skip to the next character.
	     */
	case 'h':
	    format += TclUtfToUniChar(format, &ch);
	}

	/*
	 * Handle the various field types.
	 */

	switch (ch) {
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
	/*
	 * Skip any leading whitespace at the beginning of a field unless the
	 * format suppresses this behavior.
	 */

	if (!(flags & SCAN_NOSKIP)) {
	    while (*string != '\0') {
		offset = Tcl_UtfToUniChar(string, &sch);
		if (!Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		string += offset;
	    }
	    if (*string == '\0') {
		underflow = 1;







|







795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
	/*
	 * Skip any leading whitespace at the beginning of a field unless the
	 * format suppresses this behavior.
	 */

	if (!(flags & SCAN_NOSKIP)) {
	    while (*string != '\0') {
		offset = TclUtfToUniChar(string, &sch);
		if (!Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		string += offset;
	    }
	    if (*string == '\0') {
		underflow = 1;
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
	     */

	    if (width == 0) {
		width = ~0;
	    }
	    end = string;
	    while (*end != '\0') {
		offset = Tcl_UtfToUniChar(end, &sch);
		if (Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}







|







822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
	     */

	    if (width == 0) {
		width = ~0;
	    }
	    end = string;
	    while (*end != '\0') {
		offset = TclUtfToUniChar(end, &sch);
		if (Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
	    if (width == 0) {
		width = ~0;
	    }
	    end = string;

	    format = BuildCharSet(&cset, format);
	    while (*end != '\0') {
		offset = Tcl_UtfToUniChar(end, &sch);
		if (!CharInSet(&cset, (int)sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}







|







850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
	    if (width == 0) {
		width = ~0;
	    }
	    end = string;

	    format = BuildCharSet(&cset, format);
	    while (*end != '\0') {
		offset = TclUtfToUniChar(end, &sch);
		if (!CharInSet(&cset, (int)sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
	    break;
	}
	case 'c':
	    /*
	     * Scan a single Unicode character.
	     */

	    offset = Tcl_UtfToUniChar(string, &sch);
	    i = (int)sch;
	    if (!offset) {
		offset = Tcl_UtfToUniChar(string, &sch);
		i = (((i<<10) & 0x0FFC00) + 0x10000) + (sch & 0x3FF);
	    }
	    string += offset;
	    if (!(flags & SCAN_SUPPRESS)) {







|







881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
	    break;
	}
	case 'c':
	    /*
	     * Scan a single Unicode character.
	     */

	    offset = TclUtfToUniChar(string, &sch);
	    i = (int)sch;
	    if (!offset) {
		offset = Tcl_UtfToUniChar(string, &sch);
		i = (((i<<10) & 0x0FFC00) + 0x10000) + (sch & 0x3FF);
	    }
	    string += offset;
	    if (!(flags & SCAN_SUPPRESS)) {

Changes to generic/tclStringObj.c.

1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
	int gotMinus = 0, gotHash = 0, gotZero = 0, gotSpace = 0, gotPlus = 0;
	int width, gotPrecision, precision, sawFlag, useShort = 0, useBig = 0;
#ifndef TCL_WIDE_INT_IS_LONG
	int useWide = 0;
#endif
	int newXpg, numChars, allocSegment = 0, segmentLimit, segmentNumBytes;
	Tcl_Obj *segment;
	int step = Tcl_UtfToUniChar(format, &ch);

	format += step;
	if (ch != '%') {
	    numBytes += step;
	    continue;
	}
	if (numBytes) {







|







1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
	int gotMinus = 0, gotHash = 0, gotZero = 0, gotSpace = 0, gotPlus = 0;
	int width, gotPrecision, precision, sawFlag, useShort = 0, useBig = 0;
#ifndef TCL_WIDE_INT_IS_LONG
	int useWide = 0;
#endif
	int newXpg, numChars, allocSegment = 0, segmentLimit, segmentNumBytes;
	Tcl_Obj *segment;
	int step = TclUtfToUniChar(format, &ch);

	format += step;
	if (ch != '%') {
	    numBytes += step;
	    continue;
	}
	if (numBytes) {
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743

	/*
	 * Saw a % : process the format specifier.
	 *
	 * Step 0. Handle special case of escaped format marker (i.e., %%).
	 */

	step = Tcl_UtfToUniChar(format, &ch);
	if (ch == '%') {
	    span = format;
	    numBytes = step;
	    format += step;
	    continue;
	}

	/*
	 * Step 1. XPG3 position specifier
	 */

	newXpg = 0;
	if (isdigit(UCHAR(ch))) {
	    int position = strtoul(format, &end, 10);

	    if (*end == '$') {
		newXpg = 1;
		objIndex = position - 1;
		format = end + 1;
		step = Tcl_UtfToUniChar(format, &ch);
	    }
	}
	if (newXpg) {
	    if (gotSequential) {
		msg = mixedXPG;
		errCode = "MIXEDSPECTYPES";
		goto errorMsg;







|



















|







1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743

	/*
	 * Saw a % : process the format specifier.
	 *
	 * Step 0. Handle special case of escaped format marker (i.e., %%).
	 */

	step = TclUtfToUniChar(format, &ch);
	if (ch == '%') {
	    span = format;
	    numBytes = step;
	    format += step;
	    continue;
	}

	/*
	 * Step 1. XPG3 position specifier
	 */

	newXpg = 0;
	if (isdigit(UCHAR(ch))) {
	    int position = strtoul(format, &end, 10);

	    if (*end == '$') {
		newXpg = 1;
		objIndex = position - 1;
		format = end + 1;
		step = TclUtfToUniChar(format, &ch);
	    }
	}
	if (newXpg) {
	    if (gotSequential) {
		msg = mixedXPG;
		errCode = "MIXEDSPECTYPES";
		goto errorMsg;
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
		gotPlus = 1;
		break;
	    default:
		sawFlag = 0;
	    }
	    if (sawFlag) {
		format += step;
		step = Tcl_UtfToUniChar(format, &ch);
	    }
	} while (sawFlag);

	/*
	 * Step 3. Minimum field width.
	 */

	width = 0;
	if (isdigit(UCHAR(ch))) {
	    width = strtoul(format, &end, 10);
	    format = end;
	    step = Tcl_UtfToUniChar(format, &ch);
	} else if (ch == '*') {
	    if (objIndex >= objc - 1) {
		msg = badIndex[gotXpg];
		errCode = gotXpg ? "INDEXRANGE" : "FIELDVARMISMATCH";
		goto errorMsg;
	    }
	    if (TclGetIntFromObj(interp, objv[objIndex], &width) != TCL_OK) {
		goto error;
	    }
	    if (width < 0) {
		width = -width;
		gotMinus = 1;
	    }
	    objIndex++;
	    format += step;
	    step = Tcl_UtfToUniChar(format, &ch);
	}
	if (width > limit) {
	    msg = overflow;
	    errCode = "OVERFLOW";
	    goto errorMsg;
	}

	/*
	 * Step 4. Precision.
	 */

	gotPrecision = precision = 0;
	if (ch == '.') {
	    gotPrecision = 1;
	    format += step;
	    step = Tcl_UtfToUniChar(format, &ch);
	}
	if (isdigit(UCHAR(ch))) {
	    precision = strtoul(format, &end, 10);
	    format = end;
	    step = Tcl_UtfToUniChar(format, &ch);
	} else if (ch == '*') {
	    if (objIndex >= objc - 1) {
		msg = badIndex[gotXpg];
		errCode = gotXpg ? "INDEXRANGE" : "FIELDVARMISMATCH";
		goto errorMsg;
	    }
	    if (TclGetIntFromObj(interp, objv[objIndex], &precision)
		    != TCL_OK) {
		goto error;
	    }

	    /*
	     * TODO: Check this truncation logic.
	     */

	    if (precision < 0) {
		precision = 0;
	    }
	    objIndex++;
	    format += step;
	    step = Tcl_UtfToUniChar(format, &ch);
	}

	/*
	 * Step 5. Length modifier.
	 */

	if (ch == 'h') {
	    useShort = 1;
	    format += step;
	    step = Tcl_UtfToUniChar(format, &ch);
	} else if (ch == 'l') {
	    format += step;
	    step = Tcl_UtfToUniChar(format, &ch);
	    if (ch == 'l') {
		useBig = 1;
		format += step;
		step = Tcl_UtfToUniChar(format, &ch);
#ifndef TCL_WIDE_INT_IS_LONG
	    } else {
		useWide = 1;
#endif
	    }
	} else if (ch == 'I') {
	    if ((format[1] == '6') && (format[2] == '4')) {







|











|















|















|




|




















|









|


|



|







1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
		gotPlus = 1;
		break;
	    default:
		sawFlag = 0;
	    }
	    if (sawFlag) {
		format += step;
		step = TclUtfToUniChar(format, &ch);
	    }
	} while (sawFlag);

	/*
	 * Step 3. Minimum field width.
	 */

	width = 0;
	if (isdigit(UCHAR(ch))) {
	    width = strtoul(format, &end, 10);
	    format = end;
	    step = TclUtfToUniChar(format, &ch);
	} else if (ch == '*') {
	    if (objIndex >= objc - 1) {
		msg = badIndex[gotXpg];
		errCode = gotXpg ? "INDEXRANGE" : "FIELDVARMISMATCH";
		goto errorMsg;
	    }
	    if (TclGetIntFromObj(interp, objv[objIndex], &width) != TCL_OK) {
		goto error;
	    }
	    if (width < 0) {
		width = -width;
		gotMinus = 1;
	    }
	    objIndex++;
	    format += step;
	    step = TclUtfToUniChar(format, &ch);
	}
	if (width > limit) {
	    msg = overflow;
	    errCode = "OVERFLOW";
	    goto errorMsg;
	}

	/*
	 * Step 4. Precision.
	 */

	gotPrecision = precision = 0;
	if (ch == '.') {
	    gotPrecision = 1;
	    format += step;
	    step = TclUtfToUniChar(format, &ch);
	}
	if (isdigit(UCHAR(ch))) {
	    precision = strtoul(format, &end, 10);
	    format = end;
	    step = TclUtfToUniChar(format, &ch);
	} else if (ch == '*') {
	    if (objIndex >= objc - 1) {
		msg = badIndex[gotXpg];
		errCode = gotXpg ? "INDEXRANGE" : "FIELDVARMISMATCH";
		goto errorMsg;
	    }
	    if (TclGetIntFromObj(interp, objv[objIndex], &precision)
		    != TCL_OK) {
		goto error;
	    }

	    /*
	     * TODO: Check this truncation logic.
	     */

	    if (precision < 0) {
		precision = 0;
	    }
	    objIndex++;
	    format += step;
	    step = TclUtfToUniChar(format, &ch);
	}

	/*
	 * Step 5. Length modifier.
	 */

	if (ch == 'h') {
	    useShort = 1;
	    format += step;
	    step = TclUtfToUniChar(format, &ch);
	} else if (ch == 'l') {
	    format += step;
	    step = TclUtfToUniChar(format, &ch);
	    if (ch == 'l') {
		useBig = 1;
		format += step;
		step = TclUtfToUniChar(format, &ch);
#ifndef TCL_WIDE_INT_IS_LONG
	    } else {
		useWide = 1;
#endif
	    }
	} else if (ch == 'I') {
	    if ((format[1] == '6') && (format[2] == '4')) {
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429

	    while (bytesLeft) {
		/*
		 * NOTE: We know that the from buffer is NUL-terminated.
		 * It's part of the contract for objPtr->bytes values.
		 * Thus, we can skip calling Tcl_UtfCharComplete() here.
		 */
		int bytesInChar = Tcl_UtfToUniChar(from, &ch);

		ReverseBytes((unsigned char *)to, (unsigned char *)from,
			bytesInChar);
		to += bytesInChar;
		from += bytesInChar;
		bytesLeft -= bytesInChar;
		charCount++;







|







3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429

	    while (bytesLeft) {
		/*
		 * NOTE: We know that the from buffer is NUL-terminated.
		 * It's part of the contract for objPtr->bytes values.
		 * Thus, we can skip calling Tcl_UtfCharComplete() here.
		 */
		int bytesInChar = TclUtfToUniChar(from, &ch);

		ReverseBytes((unsigned char *)to, (unsigned char *)from,
			bytesInChar);
		to += bytesInChar;
		from += bytesInChar;
		bytesLeft -= bytesInChar;
		charCount++;

Changes to generic/tclUtf.c.

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
    } 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));

	    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));

	    return 3;

	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
#if TCL_UTF_MAX > 3
    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.
	     */


















	    *chPtr = (Tcl_UniChar) (((byte & 0x0E) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));

	    return 4;


	}

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







>
|
>














>
|
>













>
>

>
>
>
>
>
>
>
>
>
>
>
>
>
>
>


>
|
>
>







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
    } 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 ((*chPtr == 0) || (*chPtr <= 0x3ff) && (*chPtr > 0x7f)) {
		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 <= 0xffff) && (*chPtr > 0x3ff)) {
		return 3;
	    }
	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
#if TCL_UTF_MAX > 3
    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 = 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 & 0x0E) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
	    if ((*chPtr <= 0x10ffff) && (*chPtr > 0xffff)) {
		return 4;
	    }
#endif
	}

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

Changes to win/tclWinPipe.c.

1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
	if (arg[0] == '\0') {
	    quote = 1;
	} else {
	    int count;
	    Tcl_UniChar ch;

	    for (start = arg; *start != '\0'; start += count) {
		count = Tcl_UtfToUniChar(start, &ch);
		if (Tcl_UniCharIsSpace(ch)) {	/* INTL: ISO space. */
		    quote = 1;
		    break;
		}
	    }
	}
	if (quote) {







|







1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
	if (arg[0] == '\0') {
	    quote = 1;
	} else {
	    int count;
	    Tcl_UniChar ch;

	    for (start = arg; *start != '\0'; start += count) {
		count = TclUtfToUniChar(start, &ch);
		if (Tcl_UniCharIsSpace(ch)) {	/* INTL: ISO space. */
		    quote = 1;
		    break;
		}
	    }
	}
	if (quote) {