Add a comment consumer mechanism to MCAsmLexer

[olista01]

Summary

This allows clients to register an AsmCommentConsumer with the MCAsmLexer, which receives a callback each time a comment is parsed.

[niravd]

LGTM

include/llvm/MC/MCParser/MCAsmLexer.h

public:
 
   APInt getAPIntVal() const {
     assert((Kind == Integer || Kind == BigNum) &&
            "This token isn't an integer!");
     return IntVal;
   }
 };
 
+/// A callback class which is notified of each comment in an assembly file as
+/// it is lexed.
+class AsmCommentConsumer {
+public:
+  virtual ~AsmCommentConsumer() {};
+
+  /// Callback function for when a comment is lexed. Loc is the start of the
+  /// comment text (excluding the comment-start marker). CommentText is the text
+  /// of the comment, excluding the comment start and end markers, and the
+  /// newline for single-line comments.
+  virtual void HandleComment(SMLoc Loc, StringRef CommentText) = 0;
+};
+
+
 /// Generic assembler lexer interface, for use by target specific assembly
 /// lexers.
 class MCAsmLexer {
   /// The current token, stored in the base class for faster access.
   SmallVector<AsmToken, 1> CurTok;
 
   /// The location and description of the current error
   SMLoc ErrLoc;
   std::string Err;
 
   MCAsmLexer(const MCAsmLexer &) = delete;
   void operator=(const MCAsmLexer &) = delete;
 protected: // Can only create subclasses.
   const char *TokStart;
   bool SkipSpace;
   bool AllowAtInIdentifier;
   bool IsAtStartOfStatement;
+  AsmCommentConsumer *CommentConsumer;
 
   MCAsmLexer();
 
   virtual AsmToken LexToken() = 0;
 
   void SetError(SMLoc errLoc, const std::string &err) {
     ErrLoc = errLoc;
     Err = err;
public:
   /// Check if the current token has kind \p K.
   bool isNot(AsmToken::TokenKind K) const { return getTok().isNot(K); }
 
   /// Set whether spaces should be ignored by the lexer
   void setSkipSpace(bool val) { SkipSpace = val; }
 
   bool getAllowAtInIdentifier() { return AllowAtInIdentifier; }
   void setAllowAtInIdentifier(bool v) { AllowAtInIdentifier = v; }
+
+  void setCommentConsumer(AsmCommentConsumer *CommentConsumer) {
+    this->CommentConsumer = CommentConsumer;
+  }
 };
 
 } // End llvm namespace
 
 #endif

lib/MC/MCParser/AsmLexer.cpp

case '/':
     return LexLineComment();
   default:
     IsAtStartOfStatement = false;
     return AsmToken(AsmToken::Slash, StringRef(TokStart, 1));
   }
 
   // C Style comment.
   ++CurPtr;  // skip the star.
+  const char *CommentTextStart = CurPtr;
   while (CurPtr != CurBuf.end()) {
     switch (*CurPtr++) {
     case '*':
       // End of the comment?
       if (*CurPtr != '/')
         break;
+      // If we have a CommentConsumer, notify it about the comment.
+      if (CommentConsumer) {
+        CommentConsumer->HandleComment(
+            SMLoc::getFromPointer(CommentTextStart),
+            StringRef(CommentTextStart, CurPtr - 1 - CommentTextStart));
+      }
       ++CurPtr;   // End the */.
       return AsmToken(AsmToken::Comment,
                       StringRef(TokStart, CurPtr - TokStart));
     }
   }
   return ReturnError(TokStart, "unterminated comment");
 }
 
 /// LexLineComment: Comment: #[^\n]*
 ///                        : //[^\n]*
 AsmToken AsmLexer::LexLineComment() {
   // Mark This as an end of statement with a body of the
   // comment. While it would be nicer to leave this two tokens,
   // backwards compatability with TargetParsers makes keeping this in this form
   // better.
+  const char *CommentTextStart = CurPtr;
   int CurChar = getNextChar();
   while (CurChar != '\n' && CurChar != '\r' && CurChar != EOF)
     CurChar = getNextChar();
 
+  // If we have a CommentConsumer, notify it about the comment.
+  if (CommentConsumer) {
+    CommentConsumer->HandleComment(
+        SMLoc::getFromPointer(CommentTextStart),
+        StringRef(CommentTextStart, CurPtr - 1 - CommentTextStart));
+  }
+
   IsAtStartOfLine = true;
   // This is a whole line comment. leave newline
   if (IsAtStartOfStatement)
     return AsmToken(AsmToken::EndOfStatement,
                     StringRef(TokStart, CurPtr - TokStart));
   IsAtStartOfStatement = true;
 
   return AsmToken(AsmToken::EndOfStatement,

lib/MC/MCParser/MCAsmLexer.cpp

 //===-- MCAsmLexer.cpp - Abstract Asm Lexer Interface ---------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/Support/SourceMgr.h"
 
 using namespace llvm;
 
 MCAsmLexer::MCAsmLexer()
-    : TokStart(nullptr), SkipSpace(true), IsAtStartOfStatement(true) {
+    : TokStart(nullptr), SkipSpace(true), IsAtStartOfStatement(true),
+      CommentConsumer(nullptr) {
   CurTok.emplace_back(AsmToken::Space, StringRef());
 }
 
 MCAsmLexer::~MCAsmLexer() {
 }
 
 SMLoc MCAsmLexer::getLoc() const {
   return SMLoc::getFromPointer(TokStart);