MC: AsmLexer: handle multi-character CommentStrings correctly

As X86MCAsmInfoDarwin uses '##' as CommentString although a single '#' starts a
comment a workaround for this special case is added.

Fixes divisions in constant expressions for the AArch64 assembler and other
targets which use '//' as CommentString.

Patch by Janne Grunau!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215615 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/MC/MCParser/AsmLexer.h b/include/llvm/MC/MCParser/AsmLexer.h
index 0b550ba627e958e8f87fb41086abb133d28991c9..a9a30f172071271324e4aeecc44004462d99de03 100644 (file)
--- a/include/llvm/MC/MCParser/AsmLexer.h
+++ b/include/llvm/MC/MCParser/AsmLexer.h
@@ -49,7 +49,7 @@ public:
 
   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; }

diff --git a/lib/MC/MCParser/AsmLexer.cpp b/lib/MC/MCParser/AsmLexer.cpp
index 145ad4a5612348a835e4eec13f396116c60da862..5c8ec669ee86805b97b67ce67f2b6290c5eea741 100644 (file)
--- a/lib/MC/MCParser/AsmLexer.cpp
+++ b/lib/MC/MCParser/AsmLexer.cpp
@@ -417,7 +417,7 @@ AsmToken AsmLexer::LexQuote() {
 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 +458,17 @@ const AsmToken AsmLexer::peekTok(bool ShouldSkipSpace) {
   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];
+
+  // FIXME: special case for the bogus "##" comment string in X86MCAsmInfoDarwin
+  if (CommentString[1] == '#')
+    return CommentString[0] == Ptr[0];
+
+  return strncmp(Ptr, CommentString, strlen(CommentString)) == 0;
 }
 
 bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
@@ -473,7 +481,7 @@ AsmToken AsmLexer::LexToken() {
   // 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.

diff --git a/test/MC/AArch64/single-slash.s b/test/MC/AArch64/single-slash.s
new file mode 100644 (file)
index 0000000..c4c266c
--- /dev/null
+++ b/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)

diff --git a/test/MC/AsmParser/comments-x86-darwin.s b/test/MC/AsmParser/comments-x86-darwin.s
new file mode 100644 (file)
index 0000000..e201f48
--- /dev/null
+++ b/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: