commit 59b26d84b64510158e23d80eba077b844b7e0b04
author Richard Smith <richard-llvm@metafoo.co.uk> Wed Jun 13 05:41:29 2012 +0000
committer Richard Smith <richard-llvm@metafoo.co.uk> Wed Jun 13 05:41:29 2012 +0000
tree 0005117b8e6556da67dbcb0d17546d0c5607b3f1
parent df9ef1bc8c3780307ab2ed81bf5e31c23310b936

Fix off-by-one error in UTF-16 encoding: don't try to use a surrogate pair for U+FFFF.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@158391 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Lex/LiteralSupport.cpp

diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp
index 2930d6a..9b0bc70 100644
--- a/lib/Lex/LiteralSupport.cpp
+++ b/lib/Lex/LiteralSupport.cpp
@@ -322,7 +322,7 @@
     // using reinterpret_cast.
     UTF16 *ResultPtr = reinterpret_cast<UTF16*>(ResultBuf);
 
-    if (UcnVal < (UTF32)0xFFFF) {
+    if (UcnVal <= (UTF32)0xFFFF) {
       *ResultPtr = UcnVal;
       ResultBuf += 2;
       return;

test/Lexer/char-literal.cpp

diff --git a/test/Lexer/char-literal.cpp b/test/Lexer/char-literal.cpp
index 5dc5360..8556d46 100644
--- a/test/Lexer/char-literal.cpp
+++ b/test/Lexer/char-literal.cpp
@@ -22,3 +22,6 @@
 
 char32_t n = U'ab'; // expected-error {{Unicode character literals may not contain multiple characters}}
 char16_t o = '👽'; // expected-error {{character too large for enclosing character literal type}}
+
+char16_t p[2] = u"\U0000FFFF";
+char16_t q[2] = u"\U00010000"; // expected-error {{too long}}