[MC] Lex CRLF as one token

This will prevent doubling of line endings when parsing assembly and
emitting assembly.

Otherwise we'd parse the directive, consume the end of statement, hit
the next end of statement, and emit a fresh newline.

llvm-svn: 315943

1 files changed, 9 insertions, 1 deletions

diff --git a/llvm/lib/MC/MCParser/AsmLexer.cpp b/llvm/lib/MC/MCParser/AsmLexer.cpp
index e9123b9d714..b83b6d3dcf6 100644
--- a/llvm/lib/MC/MCParser/AsmLexer.cpp
+++ b/llvm/lib/MC/MCParser/AsmLexer.cpp
@@ -606,8 +606,16 @@ AsmToken AsmLexer::LexToken() {
       return LexToken(); // Ignore whitespace.
     else
       return AsmToken(AsmToken::Space, StringRef(TokStart, CurPtr - TokStart));
+  case '\r': {
+    IsAtStartOfLine = true;
+    IsAtStartOfStatement = true;
+    // If this is a CR followed by LF, treat that as one token.
+    if (CurPtr != CurBuf.end() && *CurPtr == '\n')
+      ++CurPtr;
+    return AsmToken(AsmToken::EndOfStatement,
+                    StringRef(TokStart, CurPtr - TokStart));
+  }
   case '\n':
-  case '\r':
     IsAtStartOfLine = true;
     IsAtStartOfStatement = true;
     return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));