Skip Unicode character expansion in assembly files

Summary: When using the C preprocessor with assembly files, either with a
capital `S` file extension, or with `-xassembler-with-cpp`, the Unicode escape
sequence `\u` is ignored. The `\u` pattern can be used for expanding a macro
argument that starts with `u`.

Author: Salman Arif <salman.arif@arm.com>

Reviewers: rengolin, olista01

Reviewed By: olista01

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D31765

llvm-svn: 299754

clang/lib/Lex/Lexer.cpp

@@ -3603,17 +3603,19 @@ LexNextToken:
 
   // UCNs (C99 6.4.3, C++11 [lex.charset]p2)
   case '\\':
-    if (uint32_t CodePoint = tryReadUCN(CurPtr, BufferPtr, &Result)) {
-      if (CheckUnicodeWhitespace(Result, CodePoint, CurPtr)) {
-        if (SkipWhitespace(Result, CurPtr, TokAtPhysicalStartOfLine))
-          return true; // KeepWhitespaceMode
+    if (!LangOpts.AsmPreprocessor) {
+      if (uint32_t CodePoint = tryReadUCN(CurPtr, BufferPtr, &Result)) {
+        if (CheckUnicodeWhitespace(Result, CodePoint, CurPtr)) {
+          if (SkipWhitespace(Result, CurPtr, TokAtPhysicalStartOfLine))
+            return true; // KeepWhitespaceMode
 
-        // We only saw whitespace, so just try again with this lexer.
-        // (We manually eliminate the tail call to avoid recursion.)
-        goto LexNextToken;
+          // We only saw whitespace, so just try again with this lexer.
+          // (We manually eliminate the tail call to avoid recursion.)
+          goto LexNextToken;
+        }
+
+        return LexUnicode(Result, CodePoint, CurPtr);
       }
-
-      return LexUnicode(Result, CodePoint, CurPtr);
     }
 
     Kind = tok::unknown;

clang/test/Lexer/asm-preproc-no-unicode.s

@@ -0,0 +1,8 @@
+// RUN: %clang -E -xassembler-with-cpp %s -o - 2>&1 | FileCheck %s
+
+// CHECK-NOT: warning: \u used with no following hex digits
+// CHECK: .word \u
+
+    .macro foo, u
+        .word \u
+    .endm