summaryrefslogtreecommitdiffstats
path: root/generic/tclUtf.c
diff options
context:
space:
mode:
Diffstat (limited to 'generic/tclUtf.c')
-rw-r--r--generic/tclUtf.c198
1 files changed, 87 insertions, 111 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c
index e5497a4..16acab2 100644
--- a/generic/tclUtf.c
+++ b/generic/tclUtf.c
@@ -7,6 +7,8 @@
*
* See the file "license.terms" for information on usage and redistribution of
* this file, and for a DISCLAIMER OF ALL WARRANTIES.
+ *
+ * RCS: @(#) $Id: tclUtf.c,v 1.39 2009/02/11 15:28:59 dgp Exp $
*/
#include "tclInt.h"
@@ -26,27 +28,28 @@
#define ALPHA_BITS ((1 << UPPERCASE_LETTER) | (1 << LOWERCASE_LETTER) \
| (1 << TITLECASE_LETTER) | (1 << MODIFIER_LETTER) | (1<<OTHER_LETTER))
-#define CONTROL_BITS ((1 << CONTROL) | (1 << FORMAT) | (1 << PRIVATE_USE))
-
#define DIGIT_BITS (1 << DECIMAL_DIGIT_NUMBER)
#define SPACE_BITS ((1 << SPACE_SEPARATOR) | (1 << LINE_SEPARATOR) \
| (1 << PARAGRAPH_SEPARATOR))
-#define WORD_BITS (ALPHA_BITS | DIGIT_BITS | (1 << CONNECTOR_PUNCTUATION))
-
-#define PUNCT_BITS ((1 << CONNECTOR_PUNCTUATION) | \
- (1 << DASH_PUNCTUATION) | (1 << OPEN_PUNCTUATION) | \
- (1 << CLOSE_PUNCTUATION) | (1 << INITIAL_QUOTE_PUNCTUATION) | \
- (1 << FINAL_QUOTE_PUNCTUATION) | (1 << OTHER_PUNCTUATION))
+#define CONNECTOR_BITS (1 << CONNECTOR_PUNCTUATION)
-#define GRAPH_BITS (WORD_BITS | PUNCT_BITS | \
+#define PRINT_BITS (ALPHA_BITS | DIGIT_BITS | SPACE_BITS | \
(1 << NON_SPACING_MARK) | (1 << ENCLOSING_MARK) | \
(1 << COMBINING_SPACING_MARK) | (1 << LETTER_NUMBER) | \
- (1 << OTHER_NUMBER) | \
+ (1 << OTHER_NUMBER) | (1 << CONNECTOR_PUNCTUATION) | \
+ (1 << DASH_PUNCTUATION) | (1 << OPEN_PUNCTUATION) | \
+ (1 << CLOSE_PUNCTUATION) | (1 << INITIAL_QUOTE_PUNCTUATION) | \
+ (1 << FINAL_QUOTE_PUNCTUATION) | (1 << OTHER_PUNCTUATION) | \
(1 << MATH_SYMBOL) | (1 << CURRENCY_SYMBOL) | \
(1 << MODIFIER_SYMBOL) | (1 << OTHER_SYMBOL))
+#define PUNCT_BITS ((1 << CONNECTOR_PUNCTUATION) | \
+ (1 << DASH_PUNCTUATION) | (1 << OPEN_PUNCTUATION) | \
+ (1 << CLOSE_PUNCTUATION) | (1 << INITIAL_QUOTE_PUNCTUATION) | \
+ (1 << FINAL_QUOTE_PUNCTUATION) | (1 << OTHER_PUNCTUATION))
+
/*
* Unicode characters less than this value are represented by themselves in
* UTF-8 strings.
@@ -59,7 +62,7 @@
* UTF-8.
*/
-static CONST unsigned char totalBytes[256] = {
+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,
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,
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,
@@ -231,13 +234,13 @@ Tcl_UniCharToUtf(
char *
Tcl_UniCharToUtfDString(
- CONST Tcl_UniChar *uniStr, /* Unicode string to convert to UTF-8. */
+ const Tcl_UniChar *uniStr, /* Unicode string to convert to UTF-8. */
int uniLength, /* Length of Unicode string in Tcl_UniChars
* (must be >= 0). */
Tcl_DString *dsPtr) /* UTF-8 representation of string is appended
* to this previously initialized DString. */
{
- CONST Tcl_UniChar *w, *wEnd;
+ const Tcl_UniChar *w, *wEnd;
char *p, *string;
int oldLength;
@@ -289,7 +292,7 @@ Tcl_UniCharToUtfDString(
int
Tcl_UtfToUniChar(
- register CONST char *src, /* The UTF-8 string. */
+ register const char *src, /* The UTF-8 string. */
register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
* the UTF-8 string. */
{
@@ -393,7 +396,7 @@ Tcl_UtfToUniChar(
Tcl_UniChar *
Tcl_UtfToUniCharDString(
- CONST char *src, /* UTF-8 string to convert to Unicode. */
+ const char *src, /* UTF-8 string to convert to Unicode. */
int length, /* Length of UTF-8 string in bytes, or -1 for
* strlen(). */
Tcl_DString *dsPtr) /* Unicode representation of string is
@@ -401,7 +404,7 @@ Tcl_UtfToUniCharDString(
* DString. */
{
Tcl_UniChar *w, *wString;
- CONST char *p, *end;
+ const char *p, *end;
int oldLength;
if (length < 0) {
@@ -414,6 +417,7 @@ Tcl_UtfToUniCharDString(
*/
oldLength = Tcl_DStringLength(dsPtr);
+/* TODO: fix overreach! */
Tcl_DStringSetLength(dsPtr,
(int) ((oldLength + length + 1) * sizeof(Tcl_UniChar)));
wString = (Tcl_UniChar *) (Tcl_DStringValue(dsPtr) + oldLength);
@@ -452,7 +456,7 @@ Tcl_UtfToUniCharDString(
int
Tcl_UtfCharComplete(
- CONST char *src, /* String to check if first few bytes contain
+ const char *src, /* String to check if first few bytes contain
* a complete UTF-8 character. */
int length) /* Length of above string in bytes. */
{
@@ -482,7 +486,7 @@ Tcl_UtfCharComplete(
int
Tcl_NumUtfChars(
- register CONST char *src, /* The UTF-8 string to measure. */
+ register const char *src, /* The UTF-8 string to measure. */
int length) /* The length of the string in bytes, or -1
* for strlen(string). */
{
@@ -540,9 +544,9 @@ Tcl_NumUtfChars(
*---------------------------------------------------------------------------
*/
-CONST char *
+const char *
Tcl_UtfFindFirst(
- CONST char *src, /* The UTF-8 string to be searched. */
+ const char *src, /* The UTF-8 string to be searched. */
int ch) /* The Tcl_UniChar to search for. */
{
int len;
@@ -579,14 +583,14 @@ Tcl_UtfFindFirst(
*---------------------------------------------------------------------------
*/
-CONST char *
+const char *
Tcl_UtfFindLast(
- CONST char *src, /* The UTF-8 string to be searched. */
+ const char *src, /* The UTF-8 string to be searched. */
int ch) /* The Tcl_UniChar to search for. */
{
int len;
Tcl_UniChar find;
- CONST char *last;
+ const char *last;
last = NULL;
while (1) {
@@ -621,9 +625,9 @@ Tcl_UtfFindLast(
*---------------------------------------------------------------------------
*/
-CONST char *
+const char *
Tcl_UtfNext(
- CONST char *src) /* The current location in the string. */
+ const char *src) /* The current location in the string. */
{
Tcl_UniChar ch;
@@ -651,13 +655,13 @@ Tcl_UtfNext(
*---------------------------------------------------------------------------
*/
-CONST char *
+const char *
Tcl_UtfPrev(
- CONST char *src, /* The current location in the string. */
- CONST char *start) /* Pointer to the beginning of the string, to
+ const char *src, /* The current location in the string. */
+ const char *start) /* Pointer to the beginning of the string, to
* avoid going backwards too far. */
{
- CONST char *look;
+ const char *look;
int i, byte;
src--;
@@ -700,7 +704,7 @@ Tcl_UtfPrev(
Tcl_UniChar
Tcl_UniCharAtIndex(
- register CONST char *src, /* The UTF-8 string to dereference. */
+ register const char *src, /* The UTF-8 string to dereference. */
register int index) /* The position of the desired character. */
{
Tcl_UniChar ch;
@@ -729,9 +733,9 @@ Tcl_UniCharAtIndex(
*---------------------------------------------------------------------------
*/
-CONST char *
+const char *
Tcl_UtfAtIndex(
- register CONST char *src, /* The UTF-8 string. */
+ register const char *src, /* The UTF-8 string. */
register int index) /* The position of the desired character. */
{
Tcl_UniChar ch;
@@ -771,7 +775,7 @@ Tcl_UtfAtIndex(
int
Tcl_UtfBackslash(
- CONST char *src, /* Points to the backslash character of a
+ 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. */
@@ -983,8 +987,8 @@ Tcl_UtfToTitle(
int
TclpUtfNcmp2(
- CONST char *cs, /* UTF string to compare to ct. */
- CONST char *ct, /* UTF string cs is compared to. */
+ const char *cs, /* UTF string to compare to ct. */
+ const char *ct, /* UTF string cs is compared to. */
unsigned long numBytes) /* Number of *bytes* to compare. */
{
/*
@@ -1030,8 +1034,8 @@ TclpUtfNcmp2(
int
Tcl_UtfNcmp(
- CONST char *cs, /* UTF string to compare to ct. */
- CONST char *ct, /* UTF string cs is compared to. */
+ const char *cs, /* UTF string to compare to ct. */
+ const char *ct, /* UTF string cs is compared to. */
unsigned long numChars) /* Number of UTF chars to compare. */
{
Tcl_UniChar ch1, ch2;
@@ -1078,8 +1082,8 @@ Tcl_UtfNcmp(
int
Tcl_UtfNcasecmp(
- CONST char *cs, /* UTF string to compare to ct. */
- CONST char *ct, /* UTF string cs is compared to. */
+ const char *cs, /* UTF string to compare to ct. */
+ const char *ct, /* UTF string cs is compared to. */
unsigned long numChars) /* Number of UTF chars to compare. */
{
Tcl_UniChar ch1, ch2;
@@ -1105,46 +1109,6 @@ Tcl_UtfNcasecmp(
/*
*----------------------------------------------------------------------
*
- * Tcl_UtfNcasecmp --
- *
- * Compare UTF chars of string cs to string ct case insensitively.
- * Replacement for strcasecmp 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
-TclUtfCasecmp(
- CONST char *cs, /* UTF string to compare to ct. */
- CONST char *ct) /* UTF string cs is compared to. */
-{
- while (*cs && *ct) {
- Tcl_UniChar ch1, ch2;
-
- cs += TclUtfToUniChar(cs, &ch1);
- ct += TclUtfToUniChar(ct, &ch2);
- if (ch1 != ch2) {
- ch1 = Tcl_UniCharToLower(ch1);
- ch2 = Tcl_UniCharToLower(ch2);
- if (ch1 != ch2) {
- return ch1 - ch2;
- }
- }
- }
- return UCHAR(*cs) - UCHAR(*ct);
-}
-
-
-/*
- *----------------------------------------------------------------------
- *
* Tcl_UniCharToUpper --
*
* Compute the uppercase equivalent of the given Unicode character.
@@ -1165,9 +1129,10 @@ Tcl_UniCharToUpper(
int info = GetUniCharInfo(ch);
if (GetCaseType(info) & 0x04) {
- ch -= GetDelta(info);
+ return (Tcl_UniChar) (ch - GetDelta(info));
+ } else {
+ return ch;
}
- return (Tcl_UniChar) ch;
}
/*
@@ -1193,9 +1158,10 @@ Tcl_UniCharToLower(
int info = GetUniCharInfo(ch);
if (GetCaseType(info) & 0x02) {
- ch += GetDelta(info);
+ return (Tcl_UniChar) (ch + GetDelta(info));
+ } else {
+ return ch;
}
- return (Tcl_UniChar) ch;
}
/*
@@ -1226,11 +1192,12 @@ Tcl_UniCharToTitle(
* Subtract or add one depending on the original case.
*/
- ch += ((mode & 0x4) ? -1 : 1);
+ return (Tcl_UniChar) (ch + ((mode & 0x4) ? -1 : 1));
} else if (mode == 0x4) {
- ch -= GetDelta(info);
+ return (Tcl_UniChar) (ch - GetDelta(info));
+ } else {
+ return ch;
}
- return (Tcl_UniChar) ch;
}
/*
@@ -1252,7 +1219,7 @@ Tcl_UniCharToTitle(
int
Tcl_UniCharLen(
- CONST Tcl_UniChar *uniStr) /* Unicode string to find length of. */
+ const Tcl_UniChar *uniStr) /* Unicode string to find length of. */
{
int len = 0;
@@ -1282,8 +1249,8 @@ Tcl_UniCharLen(
int
Tcl_UniCharNcmp(
- CONST Tcl_UniChar *ucs, /* Unicode string to compare to uct. */
- CONST Tcl_UniChar *uct, /* Unicode string ucs is compared to. */
+ const Tcl_UniChar *ucs, /* Unicode string to compare to uct. */
+ const Tcl_UniChar *uct, /* Unicode string ucs is compared to. */
unsigned long numChars) /* Number of unichars to compare. */
{
#ifdef WORDS_BIGENDIAN
@@ -1327,8 +1294,8 @@ Tcl_UniCharNcmp(
int
Tcl_UniCharNcasecmp(
- CONST Tcl_UniChar *ucs, /* Unicode string to compare to uct. */
- CONST Tcl_UniChar *uct, /* Unicode string ucs is compared to. */
+ const Tcl_UniChar *ucs, /* Unicode string to compare to uct. */
+ const Tcl_UniChar *uct, /* Unicode string ucs is compared to. */
unsigned long numChars) /* Number of unichars to compare. */
{
for ( ; numChars != 0; numChars--, ucs++, uct++) {
@@ -1364,7 +1331,9 @@ int
Tcl_UniCharIsAlnum(
int ch) /* Unicode character to test. */
{
- return (((ALPHA_BITS | DIGIT_BITS) >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+
+ return (((ALPHA_BITS | DIGIT_BITS) >> category) & 1);
}
/*
@@ -1387,7 +1356,8 @@ int
Tcl_UniCharIsAlpha(
int ch) /* Unicode character to test. */
{
- return ((ALPHA_BITS >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+ return ((ALPHA_BITS >> category) & 1);
}
/*
@@ -1410,7 +1380,7 @@ int
Tcl_UniCharIsControl(
int ch) /* Unicode character to test. */
{
- return ((CONTROL_BITS >> GetCategory(ch)) & 1);
+ return ((GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK) == CONTROL);
}
/*
@@ -1433,7 +1403,7 @@ int
Tcl_UniCharIsDigit(
int ch) /* Unicode character to test. */
{
- return (GetCategory(ch) == DECIMAL_DIGIT_NUMBER);
+ return (GetUniCharInfo(ch)&UNICODE_CATEGORY_MASK) == DECIMAL_DIGIT_NUMBER;
}
/*
@@ -1456,7 +1426,8 @@ int
Tcl_UniCharIsGraph(
int ch) /* Unicode character to test. */
{
- return ((GRAPH_BITS >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+ return (((PRINT_BITS >> category) & 1) && ((unsigned char) ch != ' '));
}
/*
@@ -1479,7 +1450,7 @@ int
Tcl_UniCharIsLower(
int ch) /* Unicode character to test. */
{
- return (GetCategory(ch) == LOWERCASE_LETTER);
+ return ((GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK) == LOWERCASE_LETTER);
}
/*
@@ -1502,7 +1473,8 @@ int
Tcl_UniCharIsPrint(
int ch) /* Unicode character to test. */
{
- return (((GRAPH_BITS|SPACE_BITS) >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+ return ((PRINT_BITS >> category) & 1);
}
/*
@@ -1525,7 +1497,8 @@ int
Tcl_UniCharIsPunct(
int ch) /* Unicode character to test. */
{
- return ((PUNCT_BITS >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+ return ((PUNCT_BITS >> category) & 1);
}
/*
@@ -1548,17 +1521,18 @@ int
Tcl_UniCharIsSpace(
int ch) /* Unicode character to test. */
{
+ register int category;
+
/*
* If the character is within the first 127 characters, just use the
* standard C function, otherwise consult the Unicode table.
*/
- if (((Tcl_UniChar) ch) < ((Tcl_UniChar) 0x80)) {
- return TclIsSpaceProc((char) ch);
- } else if ((Tcl_UniChar) ch == 0x180e || (Tcl_UniChar) ch == 0x202f) {
- return 1;
+ if (ch < 0x80) {
+ return isspace(UCHAR(ch)); /* INTL: ISO space */
} else {
- return ((SPACE_BITS >> GetCategory(ch)) & 1);
+ category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+ return ((SPACE_BITS >> category) & 1);
}
}
@@ -1582,7 +1556,7 @@ int
Tcl_UniCharIsUpper(
int ch) /* Unicode character to test. */
{
- return (GetCategory(ch) == UPPERCASE_LETTER);
+ return ((GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK) == UPPERCASE_LETTER);
}
/*
@@ -1605,7 +1579,9 @@ int
Tcl_UniCharIsWordChar(
int ch) /* Unicode character to test. */
{
- return ((WORD_BITS >> GetCategory(ch)) & 1);
+ register int category = (GetUniCharInfo(ch) & UNICODE_CATEGORY_MASK);
+
+ return (((ALPHA_BITS | DIGIT_BITS | CONNECTOR_BITS) >> category) & 1);
}
/*
@@ -1633,8 +1609,8 @@ Tcl_UniCharIsWordChar(
int
Tcl_UniCharCaseMatch(
- CONST Tcl_UniChar *uniStr, /* Unicode String. */
- CONST Tcl_UniChar *uniPattern,
+ const Tcl_UniChar *uniStr, /* Unicode String. */
+ const Tcl_UniChar *uniPattern,
/* Pattern, which may contain special
* characters. */
int nocase) /* 0 for case sensitive, 1 for insensitive */
@@ -1821,14 +1797,14 @@ Tcl_UniCharCaseMatch(
int
TclUniCharMatch(
- CONST Tcl_UniChar *string, /* Unicode String. */
+ const Tcl_UniChar *string, /* Unicode String. */
int strLen, /* Length of String */
- CONST Tcl_UniChar *pattern, /* Pattern, which may contain special
+ const Tcl_UniChar *pattern, /* Pattern, which may contain special
* characters. */
int ptnLen, /* Length of Pattern */
int nocase) /* 0 for case sensitive, 1 for insensitive */
{
- CONST Tcl_UniChar *stringEnd, *patternEnd;
+ const Tcl_UniChar *stringEnd, *patternEnd;
Tcl_UniChar p;
stringEnd = string + strLen;
generated by cgit v0.12 at 2025-04-29 20:41:06 (GMT)