Allow peeking forward several tokens with MCAsmLexer

[Benjamin Kramer via llvm-commits]

> On 15.08.2015, at 16:23, Dylan McKay via llvm-commits <llvm-commits at lists.llvm.org> wrote:
> 
> From b7094fa637ffd59b10776e0a4bbf7f8c04235306 Mon Sep 17 00:00:00 2001
> From: Dylan McKay <dylanmckay34 at gmail.com>
> Date: Sun, 16 Aug 2015 02:09:05 +1200
> Subject: [PATCH] Extend MCAsmLexer so that it can peek forward several tokens
> 
> This commit adds a virtual `peekTokens()` function to `MCAsmLexer`
> which can peek forward an arbitrary number of tokens.
> 
> It also makes the `peekTok()` method call `peekTokens()` method, but
> only requesting one token.
> 
> The idea is to better support targets which more more ambiguous
> assembly syntaxes.
> ---
>  include/llvm/MC/MCParser/AsmLexer.h   |  3 ++-
>  include/llvm/MC/MCParser/MCAsmLexer.h | 13 ++++++++++++-
>  lib/MC/MCParser/AsmLexer.cpp          | 16 +++++++++++++---
>  3 files changed, 27 insertions(+), 5 deletions(-)
> 
> diff --git a/include/llvm/MC/MCParser/AsmLexer.h b/include/llvm/MC/MCParser/AsmLexer.h
> index 62d39b2..77023e4 100644
> --- a/include/llvm/MC/MCParser/AsmLexer.h
> +++ b/include/llvm/MC/MCParser/AsmLexer.h
> @@ -47,7 +47,8 @@ public:
>    StringRef LexUntilEndOfStatement() override;
>    StringRef LexUntilEndOfLine();
>  
> -  const AsmToken peekTok(bool ShouldSkipSpace = true) override;
> +  size_t peekTokens(AsmToken *Buf, size_t Size,
> +                    bool ShouldSkipSpace = true) override;

This could be a MutableArrayRef<AsmToken> instead of a pointer+size pair.

>  
>    bool isAtStartOfComment(const char *Ptr);
>    bool isAtStatementSeparator(const char *Ptr);
> diff --git a/include/llvm/MC/MCParser/MCAsmLexer.h b/include/llvm/MC/MCParser/MCAsmLexer.h
> index 71f15b3..fb9d32d 100644
> --- a/include/llvm/MC/MCParser/MCAsmLexer.h
> +++ b/include/llvm/MC/MCParser/MCAsmLexer.h
> @@ -162,7 +162,18 @@ public:
>    }
>  
>    /// Look ahead at the next token to be lexed.
> -  virtual const AsmToken peekTok(bool ShouldSkipSpace = true) = 0;
> +  const AsmToken peekTok(bool ShouldSkipSpace = true) {
> +    AsmToken Buf;
> +
> +    size_t ReadCount = peekTokens(&Buf, 1, ShouldSkipSpace);
> +    assert(ReadCount == 1);

Add (void)ReadCount; here to avoid unused variable warnings when assertions are disabled.

> +
> +    return Buf;
> +  }
> +
> +  /// Look ahead an arbitrary number of tokens.
> +  virtual size_t peekTokens(AsmToken *Buf, size_t Size,
> +                            bool ShouldSkipSpace = true) = 0;
>  
>    /// Get the current error location
>    const SMLoc &getErrLoc() {
> diff --git a/lib/MC/MCParser/AsmLexer.cpp b/lib/MC/MCParser/AsmLexer.cpp
> index b983d99..fcedb42 100644
> --- a/lib/MC/MCParser/AsmLexer.cpp
> +++ b/lib/MC/MCParser/AsmLexer.cpp
> @@ -436,7 +436,8 @@ StringRef AsmLexer::LexUntilEndOfLine() {
>    return StringRef(TokStart, CurPtr-TokStart);
>  }
>  
> -const AsmToken AsmLexer::peekTok(bool ShouldSkipSpace) {
> +size_t AsmLexer::peekTokens(AsmToken *Buf, size_t Size,
> +                         bool ShouldSkipSpace) {
>    const char *SavedTokStart = TokStart;
>    const char *SavedCurPtr = CurPtr;
>    bool SavedAtStartOfLine = isAtStartOfLine;
> @@ -446,8 +447,17 @@ const AsmToken AsmLexer::peekTok(bool ShouldSkipSpace) {
>    SMLoc SavedErrLoc = getErrLoc();
>  
>    SkipSpace = ShouldSkipSpace;
> -  AsmToken Token = LexToken();
>  
> +  size_t ReadCount;
> +  for(ReadCount = 0; ReadCount<Size; ++ReadCount) {
> +    AsmToken Token = LexToken();
> +
> +    Buf[ReadCount] = Token;
> +
> +    if(Token.is(AsmToken::Eof))
> +        break;
> +
> +  }

This hunk has funky identation. clang-format?

Patch looks good when my comments are fixed.

- Ben

>    SetError(SavedErrLoc, SavedErr);
>  
>    SkipSpace = SavedSkipSpace;
> @@ -455,7 +465,7 @@ const AsmToken AsmLexer::peekTok(bool ShouldSkipSpace) {
>    CurPtr = SavedCurPtr;
>    TokStart = SavedTokStart;
>  
> -  return Token;
> +  return ReadCount;
>  }
>  
>  bool AsmLexer::isAtStartOfComment(const char *Ptr) {
> -- 
> 2.4.4
>