* generic/tclUtil.c: Corrected [Bug 411825] and other bugs in

        TclNeedSpace() where non-breaking space (\u00A0) and backslash-escaped
        spaces were handled incorrectly.
        * tests/util.test:      Added new tests util-8.[2-6].

1 files changed, 36 insertions, 25 deletions

diff --git a/generic/tclUtil.c b/generic/tclUtil.c
index fd58235..d939496 100644
--- a/generic/tclUtil.c
+++ b/generic/tclUtil.c
@@ -11,7 +11,7 @@
  * See the file "license.terms" for information on usage and redistribution
  * of this file, and for a DISCLAIMER OF ALL WARRANTIES.
  *
- *  RCS: @(#) $Id: tclUtil.c,v 1.40 2003/08/27 19:55:50 dgp Exp $
+ *  RCS: @(#) $Id: tclUtil.c,v 1.41 2003/08/27 20:29:36 dgp Exp $
  */
 
 #include "tclInt.h"
@@ -2001,42 +2001,53 @@ TclNeedSpace(start, end)
     CONST char *end;		/* End of string (place where space will
 				 * be added, if appropriate). */
 {
-    Tcl_UniChar ch;
-
     /*
      * A space is needed unless either
      * (a) we're at the start of the string, or
-     * (b) the trailing characters of the string consist of one or more
-     *     open curly braces preceded by a space or extending back to
-     *     the beginning of the string.
-     * (c) the trailing characters of the string consist of a space
-     *	   preceded by a character other than backslash.
      */
-
     if (end == start) {
 	return 0;
     }
+
+    /*
+     * (b) we're at the start of a nested list-element, quoted with an
+     *     open curly brace; we can be nested arbitrarily deep, so long
+     *     as the first curly brace starts an element, so backtrack over
+     *     open curly braces that are trailing characters of the string; and
+     */
+
     end = Tcl_UtfPrev(end, start);
-    if (*end != '{') {
-	Tcl_UtfToUniChar(end, &ch);
-	/*
-	 * Direct char comparison on next line is safe as it is with
-	 * a character in the ASCII subset, and so single-byte in UTF8.
-	 */
-	if (Tcl_UniCharIsSpace(ch) && ((end == start) || (end[-1] != '\\'))) {
-	    return 0;
-	}
-	return 1;
-    }
-    do {
+    while (*end == '{') {
 	if (end == start) {
 	    return 0;
 	}
 	end = Tcl_UtfPrev(end, start);
-    } while (*end == '{');
-    Tcl_UtfToUniChar(end, &ch);
-    if (Tcl_UniCharIsSpace(ch)) {
-	return 0;
+    }
+
+    /*
+     * (c) the trailing character of the string is already a list-element
+     *     separator (according to TclFindElement); that is, one of these
+     *     characters:
+     *     	\u0009	\t	TAB
+     *     	\u000A	\n	NEWLINE
+     *     	\u000B	\v	VERTICAL TAB
+     *     	\u000C	\f	FORM FEED
+     *     	\u000D	\r	CARRIAGE RETURN
+     *     	\u0020		SPACE
+     *     with the condition that the penultimate character is not a
+     *     backslash.
+     */
+
+    switch (*end) {
+	case ' ':
+        case '\f':
+        case '\n':
+        case '\r':
+        case '\t':
+        case '\v':
+	    if ((end == start) || (end[-1] != '\\')) {
+		return 0;
+	    }
     }
     return 1;
 }