summaryrefslogtreecommitdiffstats
path: root/generic/tclUtf.c
diff options
context:
space:
mode:
Diffstat (limited to 'generic/tclUtf.c')
-rw-r--r--generic/tclUtf.c44
1 files changed, 42 insertions, 2 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c
index 18a82f7..15529c7 100644
--- a/generic/tclUtf.c
+++ b/generic/tclUtf.c
@@ -1106,6 +1106,46 @@ 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.
@@ -1515,10 +1555,10 @@ Tcl_UniCharIsSpace(
*/
if (((Tcl_UniChar) ch) < ((Tcl_UniChar) 0x80)) {
- return isspace(UCHAR(ch)); /* INTL: ISO space */
+ return TclIsSpaceProc((char) ch);
} else if ((Tcl_UniChar) ch == 0x0085 || (Tcl_UniChar) ch == 0x180e
|| (Tcl_UniChar) ch == 0x200b || (Tcl_UniChar) ch == 0x2060
- || (Tcl_UniChar) ch == 0xfeff) {
+ || (Tcl_UniChar) ch == 0x202f || (Tcl_UniChar) ch == 0xfeff) {
return 1;
} else {
return ((SPACE_BITS >> GetCategory(ch)) & 1);