From 20afc2977cd0a6bacbe6218a633cd59a24463e2f Mon Sep 17 00:00:00 2001 From: Jordan Rose Date: Wed, 30 Jan 2013 19:21:12 +0000 Subject: [PATCH] Fix r173881 to properly skip invalid UTF-8 characters in raw lexing and -E. This caused hangs as we processed the same invalid byte over and over. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@173959 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Lex/Lexer.cpp | 1 + test/Lexer/utf8-invalid.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/lib/Lex/Lexer.cpp b/lib/Lex/Lexer.cpp index 6a918d6a3a..4b5a3135c3 100644 --- a/lib/Lex/Lexer.cpp +++ b/lib/Lex/Lexer.cpp @@ -3538,6 +3538,7 @@ LexNextToken: return LexUnicode(Result, CodePoint, CurPtr); if (isLexingRawMode() || PP->isPreprocessedOutput()) { + ++CurPtr; Kind = tok::unknown; break; } diff --git a/test/Lexer/utf8-invalid.c b/test/Lexer/utf8-invalid.c index c4dd318e78..f9d2b59a6b 100644 --- a/test/Lexer/utf8-invalid.c +++ b/test/Lexer/utf8-invalid.c @@ -1,6 +1,12 @@ // RUN: %clang_cc1 -fsyntax-only -verify %s +// RUN: %clang_cc1 -E %s -o /dev/null // Note: this file contains invalid UTF-8 before the variable name in the // next line. Please do not fix! extern int ‚x; // expected-error{{source file is not valid UTF-8}} + +#if 0 +// Don't warn about bad UTF-8 in raw lexing mode. +extern int ‚x; +#endif -- 2.50.1