Merge 8.6. Fix documentation for \Uhhhhhhhh escape sequences > U+FFFF, which are no longer "reserved for the future": It's already working in 8.7.

2 files changed, 6 insertions, 3 deletions

diff --git a/doc/Tcl.n b/doc/Tcl.n
index 0eb51b9..48a3488 100644
--- a/doc/Tcl.n
+++ b/doc/Tcl.n
@@ -223,7 +223,10 @@ before this range overflows, or when the maximum of eight digits
 is reached.  The upper bits of the Unicode character will be 0.
 .RS
 .PP
-The range U+010000\(enU+10FFFD is reserved for the future.
+The range U+00D800\(enU+00DFFF is reserved for surrogates, which
+are illegal on its own. Therefore, such sequences will result in
+the replacement character U+FFFD. Surrogate pairs should be
+encoded as single \e\fBU\fIhhhhhhhh\fR character.
 .RE
 .PP
 Backslash substitution is not performed on words enclosed in braces,
diff --git a/tests/utf.test b/tests/utf.test
index fdbc4e1..c3be5ba 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -79,8 +79,8 @@ test utf-1.11 {Tcl_UniCharToUtf: 3 byte sequence, low surrogate} testbytestring
 test utf-1.12 {Tcl_UniCharToUtf: 4 byte sequence, high/low surrogate} {pairsTo4bytes testbytestring} {
     expr {"\uD842\uDC42" eq [testbytestring \xF0\xA0\xA1\x82]}
 } 1
-test utf-1.13 {Tcl_UniCharToUtf: Invalid surrogate} {Uesc testbytestring} {
-    expr {"\UD842" eq [testbytestring \xEF\xBF\xBD]}
+test utf-1.13 {Tcl_UniCharToUtf: Invalid surrogate} Uesc {
+    expr {"\UD842" eq "\uD842"}
 } 1
 
 test utf-2.1 {Tcl_UtfToUniChar: low ascii} {