summaryrefslogtreecommitdiffstats
path: root/generic/tclUtf.c
diff options
context:
space:
mode:
Diffstat (limited to 'generic/tclUtf.c')
-rw-r--r--generic/tclUtf.c299
1 files changed, 192 insertions, 107 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c
index b33bf5f..10e78bd 100644
--- a/generic/tclUtf.c
+++ b/generic/tclUtf.c
@@ -68,24 +68,14 @@ static const unsigned char totalBytes[256] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
-#if TCL_UTF_MAX > 3
4,4,4,4,4,4,4,4,
-#else
- 1,1,1,1,1,1,1,1,
-#endif
1,1,1,1,1,1,1,1
};
-
-/*
- * Functions used only in this module.
- */
-
-static int UtfCount(int ch);
/*
*---------------------------------------------------------------------------
*
- * UtfCount --
+ * TclUtfCount --
*
* Find the number of bytes in the Utf character "ch".
*
@@ -98,8 +88,8 @@ static int UtfCount(int ch);
*---------------------------------------------------------------------------
*/
-static inline int
-UtfCount(
+int
+TclUtfCount(
int ch) /* The Unicode character whose size is returned. */
{
if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
@@ -108,11 +98,9 @@ UtfCount(
if (ch <= 0x7FF) {
return 2;
}
-#if TCL_UTF_MAX > 3
if (((unsigned)(ch - 0x10000) <= 0xFFFFF)) {
return 4;
}
-#endif
return 3;
}
@@ -141,7 +129,7 @@ Tcl_UniCharToUtf(
char *buf) /* Buffer in which the UTF-8 representation of
* the Tcl_UniChar is stored. Buffer must be
* large enough to hold the UTF-8 character
- * (at most TCL_UTF_MAX bytes). */
+ * (at most 4 bytes). */
{
if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
buf[0] = (char) ch;
@@ -154,7 +142,6 @@ Tcl_UniCharToUtf(
return 2;
}
if (ch <= 0xFFFF) {
-#if TCL_UTF_MAX > 3
if ((ch & 0xF800) == 0xD800) {
if (ch & 0x0400) {
/* Low surrogate */
@@ -177,11 +164,8 @@ Tcl_UniCharToUtf(
return 0;
}
}
-#endif
goto three;
}
-
-#if TCL_UTF_MAX > 3
if (ch <= 0x10FFFF) {
buf[3] = (char) ((ch | 0x80) & 0xBF);
buf[2] = (char) (((ch >> 6) | 0x80) & 0xBF);
@@ -196,7 +180,6 @@ Tcl_UniCharToUtf(
+ ((buf[2] & 0x30) >> 4);
goto three;
}
-#endif
}
ch = 0xFFFD;
@@ -235,23 +218,31 @@ Tcl_UniCharToUtfDString(
{
const Tcl_UniChar *w, *wEnd;
char *p, *string;
- int oldLength;
+ int oldLength, len = 1;
/*
- * UTF-8 string length in bytes will be <= Unicode string length *
- * TCL_UTF_MAX.
+ * UTF-8 string length in bytes will be <= Unicode string length * 4.
*/
oldLength = Tcl_DStringLength(dsPtr);
- Tcl_DStringSetLength(dsPtr, oldLength + (uniLength + 1) * TCL_UTF_MAX);
+ Tcl_DStringSetLength(dsPtr, oldLength + (uniLength + 1) * 4);
string = Tcl_DStringValue(dsPtr) + oldLength;
p = string;
wEnd = uniStr + uniLength;
for (w = uniStr; w < wEnd; ) {
- p += Tcl_UniCharToUtf(*w, p);
+ if (!len && ((*w & 0xFC00) != 0xDC00)) {
+ /* Special case for handling high surrogates. */
+ p += Tcl_UniCharToUtf(-1, p);
+ }
+ len = Tcl_UniCharToUtf(*w, p);
+ p += len;
w++;
}
+ if (!len) {
+ /* Special case for handling high surrogates. */
+ p += Tcl_UniCharToUtf(-1, p);
+ }
Tcl_DStringSetLength(dsPtr, oldLength + (p - string));
return string;
@@ -292,6 +283,13 @@ Tcl_UniCharToUtfDString(
*---------------------------------------------------------------------------
*/
+static const unsigned short cp1252[32] = {
+ 0x20ac, 0x81, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+ 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x8D, 0x017D, 0x8F,
+ 0x90, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+ 0x2DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x9D, 0x017E, 0x0178
+};
+
int
Tcl_UtfToUniChar(
register const char *src, /* The UTF-8 string. */
@@ -308,11 +306,17 @@ Tcl_UtfToUniChar(
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
+ * Treats naked trail bytes 0x80 to 0x9F as valid characters from
+ * the cp1252 table. See: <https://en.wikipedia.org/wiki/UTF-8>
+ * Also treats \0 and other naked trail bytes 0xA0 to 0xBF as valid
* characters representing themselves.
*/
- *chPtr = (Tcl_UniChar) byte;
+ if ((unsigned)(byte-0x80) < (unsigned) 0x20) {
+ *chPtr = (Tcl_UniChar) cp1252[byte-0x80];
+ } else {
+ *chPtr = (Tcl_UniChar) byte;
+ }
return 1;
} else if (byte < 0xE0) {
if ((src[1] & 0xC0) == 0x80) {
@@ -348,13 +352,12 @@ Tcl_UtfToUniChar(
* 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
+#if TCL_UTF_MAX <= 4
Tcl_UniChar surrogate;
byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
@@ -385,7 +388,6 @@ Tcl_UtfToUniChar(
* represents itself.
*/
}
-#endif
*chPtr = (Tcl_UniChar) byte;
return 1;
@@ -439,15 +441,17 @@ Tcl_UtfToUniCharDString(
w = wString;
p = src;
- end = src + length - TCL_UTF_MAX;
+ end = src + length - 4;
while (p < end) {
p += TclUtfToUniChar(p, &ch);
*w++ = ch;
}
- end += TCL_UTF_MAX;
+ end += 4;
while (p < end) {
if (Tcl_UtfCharComplete(p, end-p)) {
p += TclUtfToUniChar(p, &ch);
+ } else if ((unsigned)((UCHAR(*p)-0x80)) < (unsigned) 0x20) {
+ ch = (Tcl_UniChar) cp1252[UCHAR(*p++)-0x80];
} else {
ch = UCHAR(*p++);
}
@@ -455,7 +459,7 @@ Tcl_UtfToUniCharDString(
}
*w = '\0';
Tcl_DStringSetLength(dsPtr,
- (oldLength + ((char *) w - (char *) wString)));
+ oldLength + ((char *) w - (char *) wString));
return wString;
}
@@ -529,13 +533,13 @@ Tcl_NumUtfChars(
}
if (i < 0) i = INT_MAX; /* Bug [2738427] */
} else {
- register const char *endPtr = src + length - TCL_UTF_MAX;
+ register const char *endPtr = src + length - 4;
while (src < endPtr) {
src += TclUtfToUniChar(src, &ch);
i++;
}
- endPtr += TCL_UTF_MAX;
+ endPtr += 4;
while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) {
src += TclUtfToUniChar(src, &ch);
i++;
@@ -577,7 +581,7 @@ Tcl_UtfFindFirst(
while (1) {
len = TclUtfToUniChar(src, &find);
fullchar = find;
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
if (!len) {
len += TclUtfToUniChar(src, &find);
fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
@@ -625,7 +629,7 @@ Tcl_UtfFindLast(
while (1) {
len = TclUtfToUniChar(src, &find);
fullchar = find;
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
if (!len) {
len += TclUtfToUniChar(src, &find);
fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
@@ -668,7 +672,7 @@ Tcl_UtfNext(
Tcl_UniChar ch = 0;
int len = TclUtfToUniChar(src, &ch);
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
if (len == 0) {
len = TclUtfToUniChar(src, &ch);
}
@@ -707,7 +711,7 @@ Tcl_UtfPrev(
int i, byte;
look = --src;
- for (i = 0; i < TCL_UTF_MAX; i++) {
+ for (i = 0; i < 4; i++) {
if (look < start) {
if (src < start) {
src = start;
@@ -743,17 +747,33 @@ Tcl_UtfPrev(
*---------------------------------------------------------------------------
*/
-Tcl_UniChar
+int
Tcl_UniCharAtIndex(
register const char *src, /* The UTF-8 string to dereference. */
register int index) /* The position of the desired character. */
{
Tcl_UniChar ch = 0;
+ int fullchar = 0;
+#if TCL_UTF_MAX <= 4
+ int len = 1;
+#endif
while (index-- >= 0) {
+#if TCL_UTF_MAX <= 4
+ src += (len = TclUtfToUniChar(src, &ch));
+#else
src += TclUtfToUniChar(src, &ch);
+#endif
}
- return ch;
+ fullchar = ch;
+#if TCL_UTF_MAX <= 4
+ if (!len) {
+ /* If last Tcl_UniChar was a high surrogate, combine with low surrogate */
+ (void)TclUtfToUniChar(src, &ch);
+ fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
+ }
+#endif
+ return fullchar;
}
/*
@@ -762,7 +782,9 @@ Tcl_UniCharAtIndex(
* Tcl_UtfAtIndex --
*
* Returns a pointer to the specified character (not byte) position in
- * the UTF-8 string.
+ * the UTF-8 string. If TCL_UTF_MAX <= 4, characters > U+FFFF count as
+ * 2 positions, but then the pointer should never be placed between
+ * the two positions.
*
* Results:
* As above.
@@ -785,7 +807,7 @@ Tcl_UtfAtIndex(
len = TclUtfToUniChar(src, &ch);
src += len;
}
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
if (!len) {
/* Index points at character following High Surrogate */
src += TclUtfToUniChar(src, &ch);
@@ -869,7 +891,8 @@ int
Tcl_UtfToUpper(
char *str) /* String to convert in place. */
{
- Tcl_UniChar ch = 0, upChar;
+ Tcl_UniChar ch = 0;
+ int upChar;
char *src, *dst;
int bytes;
@@ -880,7 +903,16 @@ Tcl_UtfToUpper(
src = dst = str;
while (*src) {
bytes = TclUtfToUniChar(src, &ch);
- upChar = Tcl_UniCharToUpper(ch);
+ upChar = ch;
+#if TCL_UTF_MAX <= 4
+ if (!bytes) {
+ /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
+ bytes = TclUtfToUniChar(src, &ch);
+ /* Combine surrogates */
+ upChar = (((upChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
+ }
+#endif
+ upChar = Tcl_UniCharToUpper(upChar);
/*
* To keep badly formed Utf strings from getting inflated by the
@@ -888,7 +920,7 @@ Tcl_UtfToUpper(
* char to dst if its size is <= the original char.
*/
- if (bytes < UtfCount(upChar)) {
+ if ((bytes < TclUtfCount(upChar)) || ((upChar & 0xF800) == 0xD800)) {
memcpy(dst, src, (size_t) bytes);
dst += bytes;
} else {
@@ -922,7 +954,8 @@ int
Tcl_UtfToLower(
char *str) /* String to convert in place. */
{
- Tcl_UniChar ch = 0, lowChar;
+ Tcl_UniChar ch = 0;
+ int lowChar;
char *src, *dst;
int bytes;
@@ -933,7 +966,16 @@ Tcl_UtfToLower(
src = dst = str;
while (*src) {
bytes = TclUtfToUniChar(src, &ch);
- lowChar = Tcl_UniCharToLower(ch);
+ lowChar = ch;
+#if TCL_UTF_MAX <= 4
+ if (!bytes) {
+ /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
+ bytes = TclUtfToUniChar(src, &ch);
+ /* Combine surrogates */
+ lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
+ }
+#endif
+ lowChar = Tcl_UniCharToLower(lowChar);
/*
* To keep badly formed Utf strings from getting inflated by the
@@ -941,7 +983,7 @@ Tcl_UtfToLower(
* char to dst if its size is <= the original char.
*/
- if (bytes < UtfCount(lowChar)) {
+ if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
memcpy(dst, src, (size_t) bytes);
dst += bytes;
} else {
@@ -976,7 +1018,8 @@ int
Tcl_UtfToTitle(
char *str) /* String to convert in place. */
{
- Tcl_UniChar ch = 0, titleChar, lowChar;
+ Tcl_UniChar ch = 0;
+ int titleChar, lowChar;
char *src, *dst;
int bytes;
@@ -989,9 +1032,18 @@ Tcl_UtfToTitle(
if (*src) {
bytes = TclUtfToUniChar(src, &ch);
- titleChar = Tcl_UniCharToTitle(ch);
+ titleChar = ch;
+#if TCL_UTF_MAX <= 4
+ if (!bytes) {
+ /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
+ bytes = TclUtfToUniChar(src, &ch);
+ /* Combine surrogates */
+ titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
+ }
+#endif
+ titleChar = Tcl_UniCharToTitle(titleChar);
- if (bytes < UtfCount(titleChar)) {
+ if ((bytes < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
memcpy(dst, src, (size_t) bytes);
dst += bytes;
} else {
@@ -1002,12 +1054,20 @@ Tcl_UtfToTitle(
while (*src) {
bytes = TclUtfToUniChar(src, &ch);
lowChar = ch;
+#if TCL_UTF_MAX <= 4
+ if (!bytes) {
+ /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
+ bytes = TclUtfToUniChar(src, &ch);
+ /* Combine surrogates */
+ lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
+ }
+#endif
/* Special exception for Georgian Asomtavruli chars, no titlecase. */
if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
lowChar = Tcl_UniCharToLower(lowChar);
}
- if (bytes < UtfCount(lowChar)) {
+ if ((bytes < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
memcpy(dst, src, (size_t) bytes);
dst += bytes;
} else {
@@ -1107,7 +1167,7 @@ Tcl_UtfNcmp(
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
@@ -1158,7 +1218,7 @@ Tcl_UtfNcasecmp(
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
@@ -1177,6 +1237,52 @@ Tcl_UtfNcasecmp(
}
return 0;
}
+
+/*
+ *----------------------------------------------------------------------
+ *
+ * Tcl_UtfCmp --
+ *
+ * Compare UTF chars of string cs to string ct case sensitively.
+ * Replacement for strcmp in Tcl core, in places where UTF-8 should
+ * be handled.
+ *
+ * Results:
+ * Return <0 if cs < ct, 0 if cs == ct, or >0 if cs > ct.
+ *
+ * Side effects:
+ * None.
+ *
+ *----------------------------------------------------------------------
+ */
+
+int
+TclUtfCmp(
+ const char *cs, /* UTF string to compare to ct. */
+ const char *ct) /* UTF string cs is compared to. */
+{
+ Tcl_UniChar ch1 = 0, ch2 = 0;
+
+ while (*cs && *ct) {
+ cs += TclUtfToUniChar(cs, &ch1);
+ ct += TclUtfToUniChar(ct, &ch2);
+ if (ch1 != ch2) {
+#if TCL_UTF_MAX <= 4
+ /* Surrogates always report higher than non-surrogates */
+ if (((ch1 & 0xFC00) == 0xD800)) {
+ if ((ch2 & 0xFC00) != 0xD800) {
+ return ch1;
+ }
+ } else if ((ch2 & 0xFC00) == 0xD800) {
+ return -ch2;
+ }
+#endif
+ return ch1 - ch2;
+ }
+ }
+ return UCHAR(*cs) - UCHAR(*ct);
+}
+
/*
*----------------------------------------------------------------------
@@ -1207,7 +1313,7 @@ TclUtfCasecmp(
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
-#if TCL_UTF_MAX == 4
+#if TCL_UTF_MAX <= 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
@@ -1244,16 +1350,18 @@ TclUtfCasecmp(
*----------------------------------------------------------------------
*/
-Tcl_UniChar
+int
Tcl_UniCharToUpper(
int ch) /* Unicode character to convert. */
{
- int info = GetUniCharInfo(ch);
+ if (!UNICODE_OUT_OF_RANGE(ch)) {
+ int info = GetUniCharInfo(ch);
- if (GetCaseType(info) & 0x04) {
- ch -= GetDelta(info);
+ if (GetCaseType(info) & 0x04) {
+ ch -= GetDelta(info);
+ }
}
- return (Tcl_UniChar) ch;
+ return ch & 0x1FFFFF;
}
/*
@@ -1272,17 +1380,19 @@ Tcl_UniCharToUpper(
*----------------------------------------------------------------------
*/
-Tcl_UniChar
+int
Tcl_UniCharToLower(
int ch) /* Unicode character to convert. */
{
- int info = GetUniCharInfo(ch);
- int mode = GetCaseType(info);
+ if (!UNICODE_OUT_OF_RANGE(ch)) {
+ int info = GetUniCharInfo(ch);
+ int mode = GetCaseType(info);
- if ((mode & 0x02) && (mode != 0x7)) {
- ch += GetDelta(info);
+ if ((mode & 0x02) && (mode != 0x7)) {
+ ch += GetDelta(info);
+ }
}
- return (Tcl_UniChar) ch;
+ return ch & 0x1FFFFF;
}
/*
@@ -1301,25 +1411,27 @@ Tcl_UniCharToLower(
*----------------------------------------------------------------------
*/
-Tcl_UniChar
+int
Tcl_UniCharToTitle(
int ch) /* Unicode character to convert. */
{
- int info = GetUniCharInfo(ch);
- int mode = GetCaseType(info);
+ if (!UNICODE_OUT_OF_RANGE(ch)) {
+ int info = GetUniCharInfo(ch);
+ int mode = GetCaseType(info);
- if (mode & 0x1) {
- /*
- * Subtract or add one depending on the original case.
- */
+ if (mode & 0x1) {
+ /*
+ * Subtract or add one depending on the original case.
+ */
- if (mode != 0x7) {
- ch += ((mode & 0x4) ? -1 : 1);
+ if (mode != 0x7) {
+ ch += ((mode & 0x4) ? -1 : 1);
+ }
+ } else if (mode == 0x4) {
+ ch -= GetDelta(info);
}
- } else if (mode == 0x4) {
- ch -= GetDelta(info);
}
- return (Tcl_UniChar) ch;
+ return ch & 0x1FFFFF;
}
/*
@@ -1453,11 +1565,9 @@ int
Tcl_UniCharIsAlnum(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return (((ALPHA_BITS | DIGIT_BITS) >> GetCategory(ch)) & 1);
}
@@ -1481,11 +1591,9 @@ int
Tcl_UniCharIsAlpha(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return ((ALPHA_BITS >> GetCategory(ch)) & 1);
}
@@ -1509,7 +1617,6 @@ int
Tcl_UniCharIsControl(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
ch &= 0x1FFFFF;
if ((ch == 0xE0001) || ((ch >= 0xE0020) && (ch <= 0xE007f))) {
@@ -1520,7 +1627,6 @@ Tcl_UniCharIsControl(
}
return 0;
}
-#endif
return ((CONTROL_BITS >> GetCategory(ch)) & 1);
}
@@ -1544,11 +1650,9 @@ int
Tcl_UniCharIsDigit(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return (GetCategory(ch) == DECIMAL_DIGIT_NUMBER);
}
@@ -1572,12 +1676,10 @@ int
Tcl_UniCharIsGraph(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
ch &= 0x1FFFFF;
return (ch >= 0xE0100) && (ch <= 0xE01EF);
}
-#endif
return ((GRAPH_BITS >> GetCategory(ch)) & 1);
}
@@ -1601,11 +1703,9 @@ int
Tcl_UniCharIsLower(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return (GetCategory(ch) == LOWERCASE_LETTER);
}
@@ -1629,12 +1729,10 @@ int
Tcl_UniCharIsPrint(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
ch &= 0x1FFFFF;
return (ch >= 0xE0100) && (ch <= 0xE01EF);
}
-#endif
return (((GRAPH_BITS|SPACE_BITS) >> GetCategory(ch)) & 1);
}
@@ -1658,11 +1756,9 @@ int
Tcl_UniCharIsPunct(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return ((PUNCT_BITS >> GetCategory(ch)) & 1);
}
@@ -1686,13 +1782,8 @@ int
Tcl_UniCharIsSpace(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
/* Ignore upper 11 bits. */
ch &= 0x1FFFFF;
-#else
- /* Ignore upper 16 bits. */
- ch &= 0xFFFF;
-#endif
/*
* If the character is within the first 127 characters, just use the
@@ -1701,10 +1792,8 @@ Tcl_UniCharIsSpace(
if (ch < 0x80) {
return TclIsSpaceProc((char) ch);
-#if TCL_UTF_MAX > 3
} else if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
-#endif
} else if (ch == 0x0085 || ch == 0x180E || ch == 0x200B
|| ch == 0x202F || ch == 0x2060 || ch == 0xFEFF) {
return 1;
@@ -1733,11 +1822,9 @@ int
Tcl_UniCharIsUpper(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return (GetCategory(ch) == UPPERCASE_LETTER);
}
@@ -1761,11 +1848,9 @@ int
Tcl_UniCharIsWordChar(
int ch) /* Unicode character to test. */
{
-#if TCL_UTF_MAX > 3
if (UNICODE_OUT_OF_RANGE(ch)) {
return 0;
}
-#endif
return ((WORD_BITS >> GetCategory(ch)) & 1);
}
generated by cgit v0.12 at 2024-11-16 08:09:57 (GMT)