[Clang] Fix a crash when encountering an ill-formed delimited UCN.

\u<DIGIT>{...} was incorrectly parsed as a valid UCN instead
of emitting a diagnostic, causing an assertion failure.

Reviewed By: tahonermann

Differential Revision: https://reviews.llvm.org/D139889

diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp
index 2f21f7b..ce48e7d 100644 (file)
--- a/clang/lib/Lex/Lexer.cpp
+++ b/clang/lib/Lex/Lexer.cpp
@@ -3286,7 +3286,7 @@ llvm::Optional<uint32_t> Lexer::tryReadNumericUCN(const char *&StartPtr,
   uint32_t CodePoint = 0;
   while (Count != NumHexDigits || Delimited) {
     char C = getCharAndSize(CurPtr, CharSize);
-    if (!Delimited && C == '{') {
+    if (!Delimited && Count == 0 && C == '{') {
       Delimited = true;
       CurPtr += CharSize;
       continue;

diff --git a/clang/test/Preprocessor/ucn-pp-identifier.c b/clang/test/Preprocessor/ucn-pp-identifier.c
index 8d30a6a..c47ed21 100644 (file)
--- a/clang/test/Preprocessor/ucn-pp-identifier.c
+++ b/clang/test/Preprocessor/ucn-pp-identifier.c
@@ -117,6 +117,7 @@ C 1
 // CHECK-NEXT: {{^                   u}}
 
 #define \u{}           // expected-warning {{empty delimited universal character name; treating as '\' 'u' '{' '}'}} expected-error {{macro name must be an identifier}}
+#define \u1{123}       // expected-warning {{incomplete universal character name; treating as '\' followed by identifier}} expected-error {{macro name must be an identifier}}
 #define \u{123456789}  // expected-error {{hex escape sequence out of range}} expected-error {{macro name must be an identifier}}
 #define \u{            // expected-warning {{incomplete delimited universal character name; treating as '\' 'u' '{' identifier}} expected-error {{macro name must be an identifier}}
 #define \u{fgh}        // expected-warning {{incomplete delimited universal character name; treating as '\' 'u' '{' identifier}} expected-error {{macro name must be an identifier}}