Tcl Source Code

Check-in [9e1984c250]
Login
Bounty program for improvements to Tcl and certain Tcl packages.

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

Overview
Comment:Backport [bd94500678e837d7] from 8.7, preventing endless loops in UTF-8 conversions when handling surrogates. Only effective when compiling with -DTCL_UTF_MAX=4|6 (default: 3). Meant for benefit of Androwish.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core-8-6-branch
Files: files | file ages | folders
SHA3-256: 9e1984c250d1a859bc607d362dc55ae9cfdced6a9c140f5269fe230309fda35d
User & Date: jan.nijtmans 2019-03-02 16:04:59
References
2019-11-13
09:21 Ticket [d433c0e0ad] TCL_UTF_MAX == 4 problems status still Pending with 3 other changes artifact: 3ed9242a56 user: jan.nijtmans
Context
2019-03-02
16:35
Fix some "scan.test" test-cases when TCL_UTF_MAX=4. Wrongly resolved merge-conflict in previous che... check-in: 8d1ff82057 user: jan.nijtmans tags: core-8-6-branch
16:08
Merge 8.6 (one forgotten adaptation of surrogate handling, only compiled on Cygwin) check-in: 4f781560c5 user: jan.nijtmans tags: core-8-branch
16:04
Backport [bd94500678e837d7] from 8.7, preventing endless loops in UTF-8 conversions when handling su... check-in: 9e1984c250 user: jan.nijtmans tags: core-8-6-branch
2019-03-01
20:11
Update all internal tables to Unicode 12.0 check-in: 88da1b0307 user: jan.nijtmans tags: core-8-6-branch
2019-02-27
21:29
Fix [bd94500678e837d7]: SEGFAULT by conversion of unicode (out of BMP) to byte-array check-in: efe8f3e6b0 user: jan.nijtmans tags: core-8-branch
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to generic/tclBinary.c.

1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
....
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
 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;
    }
................................................................................
 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;
    }






|







 







|







1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
....
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
 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;
    }
................................................................................
 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/tclCmdMZ.c.

1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
....
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430





1431
1432
1433
1434
1435
1436
1437
....
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
....
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
....
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
....
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
....
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
	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...
	     */
................................................................................
	 */

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

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

	    length = Tcl_UniCharToUtf(ch, buf);





	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, length));
	}
    }
    return TCL_OK;
}
 
/*
................................................................................
	}
	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;
	    }
................................................................................
	return TCL_ERROR;
    }

    if (objc == 4) {
	const char *string = TclGetStringFromObj(objv[1], &length2);

	if ((length2 > 1) &&
		strncmp(string, "-nocase", (size_t) length2) == 0) {
	    nocase = 1;
	} else {
	    Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		    "bad option \"%s\": must be -nocase", string));
	    Tcl_SetErrorCode(interp, "TCL", "LOOKUP", "INDEX", "option",
		    string, NULL);
	    return TCL_ERROR;
................................................................................
    }

    if (objc == 4) {
	int length;
	const char *string = TclGetStringFromObj(objv[1], &length);

	if ((length > 1) &&
	    strncmp(string, "-nocase", (size_t) length) == 0) {
	    nocase = TCL_MATCH_NOCASE;
	} else {
	    Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		    "bad option \"%s\": must be -nocase", string));
	    Tcl_SetErrorCode(interp, "TCL", "LOOKUP", "INDEX", "option",
		    string, NULL);
	    return TCL_ERROR;
................................................................................
	Tcl_WrongNumArgs(interp, 1, objv,
		"?-nocase? ?-length int? string1 string2");
	return TCL_ERROR;
    }

    for (i = 1; i < objc-2; i++) {
	string2 = TclGetStringFromObj(objv[i], &length2);
	if ((length2 > 1) && !strncmp(string2, "-nocase", (size_t)length2)) {
	    nocase = 1;
	} else if ((length2 > 1)
		&& !strncmp(string2, "-length", (size_t)length2)) {
	    if (i+1 >= objc-2) {
		goto str_cmp_args;
	    }
	    i++;
	    if (TclGetIntFromObj(interp, objv[i], &reqlength) != TCL_OK) {
		return TCL_ERROR;
	    }
................................................................................
	Tcl_WrongNumArgs(interp, 1, objv,
		"?-nocase? ?-length int? string1 string2");
	return TCL_ERROR;
    }

    for (i = 1; i < objc-2; i++) {
	string = TclGetStringFromObj(objv[i], &length);
	if ((length > 1) && !strncmp(string, "-nocase", (size_t)length)) {
	    *nocase = 1;
	} else if ((length > 1)
		&& !strncmp(string, "-length", (size_t)length)) {
	    if (i+1 >= objc-2) {
		goto str_cmp_args;
	    }
	    i++;
	    if (TclGetIntFromObj(interp, objv[i], reqlength) != TCL_OK) {
		return TCL_ERROR;
	    }






|
|







 







|


>
>
>
>
>







 







|
|







 







|







 







|







 







|


|







 







|


|







1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
....
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
....
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
....
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
....
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
....
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
....
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
	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...
	     */
................................................................................
	 */

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

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

	    length = Tcl_UniCharToUtf(ch, buf);
#if TCL_UTF_MAX > 3
	    if ((ch >= 0xD800) && (length < 3)) {
		length += Tcl_UniCharToUtf(-1, buf + length);
	    }
#endif
	    Tcl_SetObjResult(interp, Tcl_NewStringObj(buf, length));
	}
    }
    return TCL_OK;
}
 
/*
................................................................................
	}
	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;
	    }
................................................................................
	return TCL_ERROR;
    }

    if (objc == 4) {
	const char *string = TclGetStringFromObj(objv[1], &length2);

	if ((length2 > 1) &&
		strncmp(string, "-nocase", length2) == 0) {
	    nocase = 1;
	} else {
	    Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		    "bad option \"%s\": must be -nocase", string));
	    Tcl_SetErrorCode(interp, "TCL", "LOOKUP", "INDEX", "option",
		    string, NULL);
	    return TCL_ERROR;
................................................................................
    }

    if (objc == 4) {
	int length;
	const char *string = TclGetStringFromObj(objv[1], &length);

	if ((length > 1) &&
	    strncmp(string, "-nocase", length) == 0) {
	    nocase = TCL_MATCH_NOCASE;
	} else {
	    Tcl_SetObjResult(interp, Tcl_ObjPrintf(
		    "bad option \"%s\": must be -nocase", string));
	    Tcl_SetErrorCode(interp, "TCL", "LOOKUP", "INDEX", "option",
		    string, NULL);
	    return TCL_ERROR;
................................................................................
	Tcl_WrongNumArgs(interp, 1, objv,
		"?-nocase? ?-length int? string1 string2");
	return TCL_ERROR;
    }

    for (i = 1; i < objc-2; i++) {
	string2 = TclGetStringFromObj(objv[i], &length2);
	if ((length2 > 1) && !strncmp(string2, "-nocase", length2)) {
	    nocase = 1;
	} else if ((length2 > 1)
		&& !strncmp(string2, "-length", length2)) {
	    if (i+1 >= objc-2) {
		goto str_cmp_args;
	    }
	    i++;
	    if (TclGetIntFromObj(interp, objv[i], &reqlength) != TCL_OK) {
		return TCL_ERROR;
	    }
................................................................................
	Tcl_WrongNumArgs(interp, 1, objv,
		"?-nocase? ?-length int? string1 string2");
	return TCL_ERROR;
    }

    for (i = 1; i < objc-2; i++) {
	string = TclGetStringFromObj(objv[i], &length);
	if ((length > 1) && !strncmp(string, "-nocase", length)) {
	    *nocase = 1;
	} else if ((length > 1)
		&& !strncmp(string, "-length", length)) {
	    if (i+1 >= objc-2) {
		goto str_cmp_args;
	    }
	    i++;
	    if (TclGetIntFromObj(interp, objv[i], reqlength) != TCL_OK) {
		return TCL_ERROR;
	    }

Changes to generic/tclCompCmdsSZ.c.

1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
	PUSH("");
	count++;
    }

    for (endTokenPtr = tokenPtr + parse.numTokens;
	    tokenPtr < endTokenPtr; tokenPtr = TokenAfter(tokenPtr)) {
	int length, 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 = TclRegisterNewLiteral(envPtr,
		    tokenPtr->start, tokenPtr->size);






|







1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
	PUSH("");
	count++;
    }

    for (endTokenPtr = tokenPtr + parse.numTokens;
	    tokenPtr < endTokenPtr; tokenPtr = TokenAfter(tokenPtr)) {
	int length, 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 = TclRegisterNewLiteral(envPtr,
		    tokenPtr->start, tokenPtr->size);

Changes to generic/tclCompile.c.

1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
....
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
	    if (tempPtr != NULL) {
		Tcl_AppendToObj(tempPtr, tokenPtr->start, tokenPtr->size);
	    }
	    break;

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

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

................................................................................
				 * compile. */
    int 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 i, numObjsToConcat, length, adjust;
    unsigned char *entryCodeNext = envPtr->codeNext;
#define NUM_STATIC_POS 20
    int isLiteral, maxNumCL, numCL;
    int *clPosition = NULL;
    int depth = TclGetStackDepth(envPtr);







|







 







|







1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
....
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
	    if (tempPtr != NULL) {
		Tcl_AppendToObj(tempPtr, tokenPtr->start, tokenPtr->size);
	    }
	    break;

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

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

................................................................................
				 * compile. */
    int 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 i, numObjsToConcat, length, adjust;
    unsigned char *entryCodeNext = envPtr->codeNext;
#define NUM_STATIC_POS 20
    int isLiteral, maxNumCL, numCL;
    int *clPosition = NULL;
    int depth = TclGetStackDepth(envPtr);

Changes to generic/tclEncoding.c.

2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
....
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
....
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
	    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;
................................................................................

	/*
	 * 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) '?';
................................................................................
		     */

		    state = oldState;
		    result = TCL_CONVERT_NOSPACE;
		    break;
		}
		memcpy(dst, subTablePtr->sequence,
			(size_t) subTablePtr->sequenceLen);
		dst += subTablePtr->sequenceLen;
	    }
	}

	if (tablePrefixBytes[(word >> 8)] != 0) {
	    if (dst + 1 > dstEnd) {
		result = TCL_CONVERT_NOSPACE;






|
|







 







|







|







 







|







2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
....
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
....
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
	    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;
................................................................................

	/*
	 * 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) '?';
................................................................................
		     */

		    state = oldState;
		    result = TCL_CONVERT_NOSPACE;
		    break;
		}
		memcpy(dst, subTablePtr->sequence,
			subTablePtr->sequenceLen);
		dst += subTablePtr->sequenceLen;
	    }
	}

	if (tablePrefixBytes[(word >> 8)] != 0) {
	    if (dst + 1 > dstEnd) {
		result = TCL_CONVERT_NOSPACE;

Changes to generic/tclExecute.c.

5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
	} else if (TclIsPureByteArray(valuePtr)) {
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && length == valuePtr->length) {
	    objResultPtr = Tcl_NewStringObj((const char *)
		    valuePtr->bytes+index, 1);
	} else {
	    char buf[TCL_UTF_MAX];
	    Tcl_UniChar ch = Tcl_GetUniChar(valuePtr, index);

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






|







5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
	} else if (TclIsPureByteArray(valuePtr)) {
	    objResultPtr = Tcl_NewByteArrayObj(
		    Tcl_GetByteArrayFromObj(valuePtr, NULL)+index, 1);
	} else if (valuePtr->bytes && length == valuePtr->length) {
	    objResultPtr = Tcl_NewStringObj((const char *)
		    valuePtr->bytes+index, 1);
	} else {
	    char buf[TCL_UTF_MAX] = "";
	    Tcl_UniChar ch = Tcl_GetUniChar(valuePtr, index);

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

Changes to generic/tclParse.c.

840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
...
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
....
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
				 * written. At most TCL_UTF_MAX bytes will be
				 * written there. */
{
    register const char *p = src+1;
    Tcl_UniChar unichar = 0;
    int result;
    int count;
    char buf[TCL_UTF_MAX];

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

  done:
    if (readPtr != NULL) {
	*readPtr = count;
    }
    count = Tcl_UniCharToUtf(result, dst);
#if TCL_UTF_MAX > 3
    if (!count) {
	count = Tcl_UniCharToUtf(-1, dst);
    }
#endif
    return count;
}
 
/*
 *----------------------------------------------------------------------
................................................................................

    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;







|







 







|
|







 







|







840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
...
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
....
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
				 * written. At most TCL_UTF_MAX bytes will be
				 * written there. */
{
    register const char *p = src+1;
    Tcl_UniChar unichar = 0;
    int result;
    int count;
    char buf[TCL_UTF_MAX] = "";

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

  done:
    if (readPtr != NULL) {
	*readPtr = count;
    }
    count = Tcl_UniCharToUtf(result, dst);
#if TCL_UTF_MAX > 3
     if ((result >= 0xD800) && (count < 3)) {
	count += Tcl_UniCharToUtf(-1, dst + count);
    }
#endif
    return count;
}
 
/*
 *----------------------------------------------------------------------
................................................................................

    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/tclScan.c.

256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
...
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
				 * 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
................................................................................
	     * Scan a single Unicode character.
	     */

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






|







 







|







256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
...
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
				 * 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
................................................................................
	     * 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_NewIntObj(i);
		Tcl_IncrRefCount(objPtr);

Changes to generic/tclStringObj.c.

1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
....
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
	    int code, length;

	    if (TclGetIntFromObj(interp, segment, &code) != TCL_OK) {
		goto error;
	    }
	    length = Tcl_UniCharToUtf(code, buf);
#if TCL_UTF_MAX > 3
	    if (!length) {
		/* Special case for handling high surrogates. */
		length = Tcl_UniCharToUtf(-1, buf);
	    }
#endif
	    segment = Tcl_NewStringObj(buf, length);
	    Tcl_IncrRefCount(segment);
	    allocSegment = 1;
	    break;
	}
................................................................................
    if (size > stringPtr->allocated) {
	GrowStringBuffer(objPtr, size, 1);
    }

  copyBytes:
    dst = objPtr->bytes + origLength;
    for (i = 0; i < numChars; i++) {
	dst += Tcl_UniCharToUtf((int) unicode[i], dst);
    }
    *dst = '\0';
    objPtr->length = dst - objPtr->bytes;
    return numChars;
}
 
/*






|

|







 







|







1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
....
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
	    int code, length;

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

  copyBytes:
    dst = objPtr->bytes + origLength;
    for (i = 0; i < numChars; i++) {
	dst += Tcl_UniCharToUtf(unicode[i], dst);
    }
    *dst = '\0';
    objPtr->length = dst - objPtr->bytes;
    return numChars;
}
 
/*

Changes to generic/tclStubInit.c.

283
284
285
286
287
288
289




290
291
292
293
294
295
296
    for (w = (wchar_t *)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));






>
>
>
>







283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
    for (w = (wchar_t *)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));

Changes to generic/tclUtf.c.

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
...
186
187
188
189
190
191
192
193
194
195
196
197



198
199
200
201
202
203
204
...
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
...
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
...
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
...
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
...
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
...
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
...
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
...
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
...
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
957
...
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
	    return 2;
	}
	if (ch <= 0xFFFF) {
#if TCL_UTF_MAX > 3
	    if ((ch & 0xF800) == 0xD800) {
		if (ch & 0x0400) {
		    /* Low surrogate */
		    if (((buf[0] & 0xF8) == 0xF0) && ((buf[1] & 0xC0) == 0x80)
			    && ((buf[2] & 0xCF) == 0)) {
			/* Previous Tcl_UniChar was a High surrogate, so combine */
			buf[3] = (char) ((ch & 0x3F) | 0x80);
			buf[2] |= (char) (((ch >> 6) & 0x0F) | 0x80);
			return 4;
		    }
		    /* Previous Tcl_UniChar was not a High surrogate, so just output */
		} else {
		    /* High surrogate */
		    ch += 0x40;
		    /* Fill buffer with specific 3-byte (invalid) byte combination,
		       so following Low surrogate can recognize it and combine */
		    buf[2] = (char) ((ch << 4) & 0x30);
		    buf[1] = (char) (((ch >> 2) & 0x3F) | 0x80);
		    buf[0] = (char) (((ch >> 8) & 0x07) | 0xF0);
		    return 0;
		}
	    }
#endif
	    goto three;
	}

#if TCL_UTF_MAX > 3
................................................................................
	    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;



	}
#endif
    }

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

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

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

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















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

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

	/*
................................................................................
#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 = (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.
	 */
    }
#endif

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}
 
/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
................................................................................
    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
	if (*src == '\0') {
................................................................................
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}
	if (*src == '\0') {
................................................................................
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    int len = TclUtfToUniChar(src, &ch);

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

const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int len = 1;

    while (index-- > 0) {
	len = TclUtfToUniChar(src, &ch);
	src += len;
    }
#if TCL_UTF_MAX == 4
     if (!len) {
	/* Index points at character following High Surrogate */
	src += TclUtfToUniChar(src, &ch);
    }
#endif
    return src;
}
 
/*
................................................................................

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

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

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

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the upper case
	 * char to dst if its size is <= the original char.
	 */

	if (bytes < UtfCount(upChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------
................................................................................

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

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

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

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the lower case
	 * char to dst if its size is <= the original char.
	 */

	if (bytes < UtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------
................................................................................

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

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

    src = dst = str;

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

	if (bytes < UtfCount(titleChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if (bytes < UtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------






|
<
|
|
|
|

|




|



|







 







|
|
|
|
|
>
>
>







 







|













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







|







 







|







 







<
<
|
|
<
<
>

<
<
<
<

|
<
>
|


|

|












|







 







|
|







 







|
|







 







|
|







 







|






|
|







 







|







|








|
|
|



|







 







|







|








|
|
|



|







 







|









|


|
|
|



|


|






|
|
|



|







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
...
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
...
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
...
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
...
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
...
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
...
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
...
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
...
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
...
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
...
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
...
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
	    return 2;
	}
	if (ch <= 0xFFFF) {
#if TCL_UTF_MAX > 3
	    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;
		}
	    }
#endif
	    goto three;
	}

#if TCL_UTF_MAX > 3
................................................................................
	    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;
	}
#endif
    }

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

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

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

#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
	*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
................................................................................
	 */
    } 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;
	    }
	}

	/*
................................................................................
#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 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.
	 */
    }
#endif

    *chPtr = byte;
    return 1;
}
 
/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
................................................................................
    int len, 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') {
................................................................................
    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') {
................................................................................
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    int len = TclUtfToUniChar(src, &ch);

#if TCL_UTF_MAX == 4
    if ((ch >= 0xD800) && (len < 3)) {
	len += TclUtfToUniChar(src + len, &ch);
    }
#endif
    return src + len;
}
 
/*
 *---------------------------------------------------------------------------
................................................................................

const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int len = 0;

    while (index-- > 0) {
	len = TclUtfToUniChar(src, &ch);
	src += len;
    }
#if TCL_UTF_MAX == 4
    if ((ch >= 0xD800) && (len < 3)) {
	/* Index points at character following high Surrogate */
	src += TclUtfToUniChar(src, &ch);
    }
#endif
    return src;
}
 
/*
................................................................................

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

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	upChar = Tcl_UniCharToUpper(ch);

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the upper case
	 * char to dst if its size is <= the original char.
	 */

	if (len < UtfCount(upChar)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------
................................................................................

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

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	lowChar = Tcl_UniCharToLower(ch);

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the lower case
	 * char to dst if its size is <= the original char.
	 */

	if (len < UtfCount(lowChar)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------
................................................................................

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

	if (len < UtfCount(titleChar)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += len;
    }
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if (len < UtfCount(lowChar)) {
	    memcpy(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += len;
    }
    *dst = '\0';
    return (dst - str);
}
 
/*
 *----------------------------------------------------------------------

Changes to generic/tclUtil.c.

1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
char
Tcl_Backslash(
    const char *src,		/* Points to the backslash character of a
				 * backslash sequence. */
    int *readPtr)		/* Fill in with number of characters read from
				 * src, unless NULL. */
{
    char buf[TCL_UTF_MAX];
    Tcl_UniChar ch = 0;

    Tcl_UtfBackslash(src, readPtr, buf);
    TclUtfToUniChar(buf, &ch);
    return (char) ch;
}
 






|







1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
char
Tcl_Backslash(
    const char *src,		/* Points to the backslash character of a
				 * backslash sequence. */
    int *readPtr)		/* Fill in with number of characters read from
				 * src, unless NULL. */
{
    char buf[TCL_UTF_MAX] = "";
    Tcl_UniChar ch = 0;

    Tcl_UtfBackslash(src, readPtr, buf);
    TclUtfToUniChar(buf, &ch);
    return (char) ch;
}
 

Changes to win/tclWin32Dll.c.

644
645
646
647
648
649
650




651
652
653
654
655
656
657
    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));






>
>
>
>







644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
    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));