[PATCH] MC: AsmLexer: handle multi-character CommentStrings correctly

[Janne Grunau]

added explicit tests with single '#' comments for x86 darwin. A couple of existing tests will catch incorrect parsing of single '#' comments too though.

http://reviews.llvm.org/D4597

Files:
  include/llvm/MC/MCParser/AsmLexer.h
  lib/MC/MCParser/AsmLexer.cpp
  test/MC/AArch64/single-slash.s
  test/MC/AsmParser/comments-x86-darwin.s

Index: include/llvm/MC/MCParser/AsmLexer.h
===================================================================
--- include/llvm/MC/MCParser/AsmLexer.h
+++ include/llvm/MC/MCParser/AsmLexer.h
@@ -49,7 +49,7 @@
 
   const AsmToken peekTok(bool ShouldSkipSpace = true) override;
 
-  bool isAtStartOfComment(char Char);
+  bool isAtStartOfComment(const char *Ptr);
   bool isAtStatementSeparator(const char *Ptr);
 
   const MCAsmInfo &getMAI() const { return MAI; }
Index: lib/MC/MCParser/AsmLexer.cpp
===================================================================
--- lib/MC/MCParser/AsmLexer.cpp
+++ lib/MC/MCParser/AsmLexer.cpp
@@ -417,7 +417,7 @@
 StringRef AsmLexer::LexUntilEndOfStatement() {
   TokStart = CurPtr;
 
-  while (!isAtStartOfComment(*CurPtr) &&    // Start of line comment.
+  while (!isAtStartOfComment(CurPtr) &&     // Start of line comment.
          !isAtStatementSeparator(CurPtr) && // End of statement marker.
          *CurPtr != '\n' && *CurPtr != '\r' &&
          (*CurPtr != 0 || CurPtr != CurBuf.end())) {
@@ -458,9 +458,16 @@
   return Token;
 }
 
-bool AsmLexer::isAtStartOfComment(char Char) {
-  // FIXME: This won't work for multi-character comment indicators like "//".
-  return Char == *MAI.getCommentString();
+bool AsmLexer::isAtStartOfComment(const char *Ptr) {
+  const char *CommentString = MAI.getCommentString();
+
+  if (CommentString[1] == '\0')
+    return  CommentString[0] == Ptr[0];
+
+  if (CommentString[1] == '#')
+      // FIXME: special case for the bogus comment string in X86MCAsmInfoDarwin
+    return CommentString[0] == Ptr[0];
+  return strncmp(Ptr, CommentString, strlen(CommentString)) == 0;
 }
 
 bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
@@ -473,7 +480,7 @@
   // This always consumes at least one character.
   int CurChar = getNextChar();
 
-  if (isAtStartOfComment(CurChar)) {
+  if (isAtStartOfComment(TokStart)) {
     // If this comment starts with a '#', then return the Hash token and let
     // the assembler parser see if it can be parsed as a cpp line filename
     // comment. We do this only if we are at the start of a line.
Index: test/MC/AArch64/single-slash.s
===================================================================
--- /dev/null
+++ test/MC/AArch64/single-slash.s
@@ -0,0 +1,6 @@
+// RUN: llvm-mc -triple aarch64-none-linux-gnu < %s | FileCheck %s
+
+// Test that a single slash is not mistaken as the start of comment.
+
+//CHECK: movz    x0, #0x10
+    movz x0, #(32 / 2)
Index: test/MC/AsmParser/comments-x86-darwin.s
===================================================================
--- /dev/null
+++ test/MC/AsmParser/comments-x86-darwin.s
@@ -0,0 +1,14 @@
+// RUN: llvm-mc -triple x86_64-apple-darwin %s 2>&1 | FileCheck %s
+# ensure that single '#' comments are worink as expected on x86 darwin
+.align 3            # test single hash after align
+// CHECK: .align 3
+foo:                # single hash should be ignored as comment
+// CHECK-LABEL: foo:
+    movl %esp, %ebp # same after an instruction
+// CHECK: movl %esp, %ebp
+#   movl %esp, %ebp ## start of the line
+// CHECK-NOT: movl %esp, %ebp
+    # movl %esp, %ebp ## not quite start of the line
+// CHECK-NOT: movl %esp, %ebp
+bar:
+// CHECK-LABEL: bar:
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D4597.12175.patch
Type: text/x-patch
Size: 3244 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20140804/84eedad2/attachment.bin>