Reimplement the old and horrible bison parser for .ll files with a nice

and clean recursive descent parser.

This change has a couple of ramifications:
1. The parser code is about 400 lines shorter (in what we maintain, not
   including what is autogenerated).
2. The code should be significantly faster than the old code because we 
   don't have to work around bison's poor handling of datatypes with 
   ctors/dtors.  This also makes the code much more resistant to memory 
   leaks.
3. We now get caret diagnostics from the .ll parser, woo.
4. The actual diagnostics emited from the parser are completely different
   so a bunch of testcases had to be updated.
5. I now disallow "%ty = type opaque %ty = type i32".  There was no good
   reason to support this, it was just an accident of the old 
   implementation.  I have no reason to think that anyone is actually using
   this.
6. The syntax for sticking a global variable has changed to make it 
   unambiguous.  I don't think anyone is depending on this since only clang
   supports this and it is not solid yet, so I'm not worried about anything
   breaking.
7. This gets rid of the last use of bison, and along with it the .cvs files.
   I'll prune this from the makefiles as a subsequent commit.

There are a few minor cleanups that can be done after this commit (suggestions
welcome!) but this passes dejagnu testing and is ready for its time in the
limelight.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61558 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 46 insertions, 17 deletions

diff --git a/lib/AsmParser/LLLexer.h b/lib/AsmParser/LLLexer.h
index 8b44b14cb74..45001815e75 100644
--- a/lib/AsmParser/LLLexer.h
+++ b/lib/AsmParser/LLLexer.h
@@ -14,43 +14,72 @@
 #ifndef LIB_ASMPARSER_LLLEXER_H
 #define LIB_ASMPARSER_LLLEXER_H
 
+#include "LLToken.h"
+#include "llvm/ADT/APSInt.h"
+#include "llvm/ADT/APFloat.h"
+
 #include <vector>
 #include <string>
 #include <iosfwd>
 
 namespace llvm {
   class MemoryBuffer;
+  class Type;
+  class ParseError;
   
   class LLLexer {
     const char *CurPtr;
-    unsigned CurLineNo;
     MemoryBuffer *CurBuf;
-    
+    ParseError &ErrorInfo;
+
+    // Information about the current token.
     const char *TokStart;
+    lltok::Kind CurKind;
+    std::string StrVal;
+    unsigned UIntVal;
+    const Type *TyVal;
+    APFloat APFloatVal;
+    APSInt  APSIntVal;
     
     std::string TheError;
   public:
-    explicit LLLexer(MemoryBuffer *StartBuf);
+    explicit LLLexer(MemoryBuffer *StartBuf, ParseError &);
     ~LLLexer() {}
 
-    const char *getTokStart() const { return TokStart; }
-    unsigned getTokLength() const { return CurPtr-TokStart; }
-    unsigned getLineNo() const { return CurLineNo; }
-    std::string getFilename() const;
-    int LexToken();
-    
-    const std::string getError() const { return TheError; }
+    lltok::Kind Lex() {
+      return CurKind = LexToken();
+    }
+
+    typedef const char* LocTy;
+    LocTy getLoc() const { return TokStart; }
+    lltok::Kind getKind() const { return CurKind; }
+    const std::string getStrVal() const { return StrVal; }
+    const Type *getTyVal() const { return TyVal; }
+    unsigned getUIntVal() const { return UIntVal; }
+    const APSInt &getAPSIntVal() const { return APSIntVal; }
+    const APFloat &getAPFloatVal() const { return APFloatVal; }
+
     
+    bool Error(LocTy L, const std::string &Msg) const;
+    bool Error(const std::string &Msg) const { return Error(CurPtr, Msg); }
+    std::string getFilename() const;
+        
   private:
+    lltok::Kind LexToken();
+
     int getNextChar();
     void SkipLineComment();
-    int LexIdentifier();
-    int LexDigitOrNegative();
-    int LexPositive();
-    int LexAt();
-    int LexPercent();
-    int LexQuote();
-    int Lex0x();
+    lltok::Kind LexIdentifier();
+    lltok::Kind LexDigitOrNegative();
+    lltok::Kind LexPositive();
+    lltok::Kind LexAt();
+    lltok::Kind LexPercent();
+    lltok::Kind LexQuote();
+    lltok::Kind Lex0x();
+    
+    uint64_t atoull(const char *Buffer, const char *End);
+    uint64_t HexIntToVal(const char *Buffer, const char *End);
+    void HexToIntPair(const char *Buffer, const char *End, uint64_t Pair[2]);
   };
 } // end namespace llvm