* generic/tclStringObj.c: Rewrites of the routines

        Tcl_GetCharLength, Tcl_GetUniChar, Tcl_GetUnicodeFromObj,
        Tcl_GetRange, and TclStringObjReverse to use the new macro, and
        to more simply and clearly split the cases depending on whether
        a valid unicode rep is present or needs to be created.

        * generic/tclInt.h:     New macro TclNumUtfChars meant to be a faster
        replacement for a full Tcl_NumUtfChars() call when the string has all
        single-byte characters.

1 files changed, 26 insertions, 1 deletions

diff --git a/generic/tclInt.h b/generic/tclInt.h
index dba84fb..3de0ea2 100644
--- a/generic/tclInt.h
+++ b/generic/tclInt.h
@@ -15,7 +15,7 @@
  * See the file "license.terms" for information on usage and redistribution of
  * this file, and for a DISCLAIMER OF ALL WARRANTIES.
  *
- * RCS: @(#) $Id: tclInt.h,v 1.416 2009/02/03 18:48:25 dkf Exp $
+ * RCS: @(#) $Id: tclInt.h,v 1.417 2009/02/13 03:22:52 dgp Exp $
  */
 
 #ifndef _TCLINT
@@ -3805,6 +3805,31 @@ MODULE_SCOPE void	TclDbInitNewObj(Tcl_Obj *objPtr);
 
 /*
  *----------------------------------------------------------------
+ * Macro counterpart of the Tcl_NumUtfChars() function.  To be used
+ * in speed-sensitive points where it pays to avoid a function call
+ * in the common case of counting along a string of all one-byte characters.
+ * The ANSI C "prototype" for this macro is:
+ *
+ * MODULE_SCOPE void	TclNumUtfChars(int numChars, const char *bytes,
+ *				int numBytes);
+ *----------------------------------------------------------------
+ */
+
+#define TclNumUtfChars(numChars, bytes, numBytes) \
+    do { \
+	int count, i = (numBytes); \
+	unsigned char *str = (unsigned char *) (bytes); \
+	while (i && (*str < 0xC0)) { i--; str++; } \
+	count = (numBytes) - i; \
+	if (i) { \
+	    count += Tcl_NumUtfChars((bytes) + count, i); \
+	} \
+	(numChars) = count; \
+    } while (0);
+
+
+/*
+ *----------------------------------------------------------------
  * Macro used by the Tcl core to compare Unicode strings. On big-endian
  * systems we can use the more efficient memcmp, but this would not be
  * lexically correct on little-endian systems. The ANSI C "prototype" for