implement enough of a lexer to get through Olden/health/Output/health.llc.s

without errors.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73855 91177308-0d34-0410-b5e6-96231b3b80d8

tools/llvm-mc/AsmLexer.cpp

@@ -14,6 +14,7 @@
 #include "AsmLexer.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Support/MemoryBuffer.h"
+#include <cerrno>
 using namespace llvm;
 
 AsmLexer::AsmLexer(SourceMgr &SM) : SrcMgr(SM) {
@@ -23,6 +24,10 @@ AsmLexer::AsmLexer(SourceMgr &SM) : SrcMgr(SM) {
   TokStart = 0;
 }
 
+SMLoc AsmLexer::getLoc() const {
+  return SMLoc::getFromPointer(TokStart);
+}
+
 void AsmLexer::PrintError(const char *Loc, const std::string &Msg) const {
   SrcMgr.PrintError(SMLoc::getFromPointer(Loc), Msg);
 }
@@ -31,6 +36,13 @@ void AsmLexer::PrintError(SMLoc Loc, const std::string &Msg) const {
   SrcMgr.PrintError(Loc, Msg);
 }
 
+/// ReturnError - Set the error to the specified string at the specified
+/// location.  This is defined to always return asmtok::Error.
+asmtok::TokKind AsmLexer::ReturnError(const char *Loc, const std::string &Msg) {
+  PrintError(Loc, Msg);
+  return asmtok::Error;
+}
+
 int AsmLexer::getNextChar() {
   char CurChar = *CurPtr++;
   switch (CurChar) {
@@ -59,6 +71,129 @@ int AsmLexer::getNextChar() {
   }
 }
 
+/// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
+asmtok::TokKind AsmLexer::LexIdentifier() {
+  while (isalnum(*CurPtr) || *CurPtr == '_' || *CurPtr == '$' ||
+         *CurPtr == '.' || *CurPtr == '@')
+    ++CurPtr;
+  CurStrVal.assign(TokStart, CurPtr);   // Skip %
+  return asmtok::Identifier;
+}
+
+/// LexPercent: Register: %[a-zA-Z0-9]+
+asmtok::TokKind AsmLexer::LexPercent() {
+  if (!isalnum(*CurPtr))
+    return asmtok::Error;  // Must have at least one character.
+  while (isalnum(*CurPtr))
+    ++CurPtr;
+  CurStrVal.assign(TokStart, CurPtr);   // Skip %
+  return asmtok::Register;
+}
+
+/// LexSlash: Slash: /
+///           C-Style Comment: /* ... */
+asmtok::TokKind AsmLexer::LexSlash() {
+  if (*CurPtr != '*')
+    return asmtok::Slash;
+
+  // C Style comment.
+  ++CurPtr;  // skip the star.
+  while (1) {
+    int CurChar = getNextChar();
+    switch (CurChar) {
+    case EOF:
+      PrintError(TokStart, "Unterminated comment!");
+      return asmtok::Error;
+    case '*':
+      // End of the comment?
+      if (CurPtr[0] != '/') break;
+      
+      ++CurPtr;   // End the */.
+      return LexToken();
+    }
+  }
+}
+
+/// LexHash: Comment: #[^\n]*
+asmtok::TokKind AsmLexer::LexHash() {
+  int CurChar = getNextChar();
+  while (CurChar != '\n' && CurChar != '\n' && CurChar != EOF)
+    CurChar = getNextChar();
+  
+  if (CurChar == EOF)
+    return asmtok::Eof;
+  return asmtok::EndOfStatement;
+}
+
+
+/// LexDigit: First character is [0-9].
+///   Local Label: [0-9][:]
+///   Forward/Backward Label: [0-9][fb]
+///   Binary integer: 0b[01]+
+///   Octal integer: 0[0-7]+
+///   Hex integer: 0x[0-9a-fA-F]+
+///   Decimal integer: [1-9][0-9]*
+/// TODO: FP literal.
+asmtok::TokKind AsmLexer::LexDigit() {
+  if (*CurPtr == ':')
+    return asmtok::Error;  // FIXME LOCAL LABEL.
+  if (*CurPtr == 'f' || *CurPtr == 'b')
+    return asmtok::Error;  // FIXME FORWARD/BACKWARD LABEL.
+  
+  // Decimal integer: [1-9][0-9]*
+  if (CurPtr[-1] != '0') {
+    while (isdigit(*CurPtr))
+      ++CurPtr;
+    CurIntVal = strtoll(TokStart, 0, 10);
+    return asmtok::IntVal;
+  }
+  
+  if (*CurPtr == 'b') {
+    ++CurPtr;
+    const char *NumStart = CurPtr;
+    while (CurPtr[0] == '0' || CurPtr[0] == '1')
+      ++CurPtr;
+    
+    // Requires at least one binary digit.
+    if (CurPtr == NumStart)
+      return ReturnError(CurPtr-2, "Invalid binary number");
+    CurIntVal = strtoll(NumStart, 0, 2);
+    return asmtok::IntVal;
+  }
+ 
+  if (*CurPtr == 'x') {
+    ++CurPtr;
+    const char *NumStart = CurPtr;
+    while (isxdigit(CurPtr[0]))
+      ++CurPtr;
+    
+    // Requires at least one hex digit.
+    if (CurPtr == NumStart)
+      return ReturnError(CurPtr-2, "Invalid hexadecimal number");
+    
+    errno = 0;
+    CurIntVal = strtoll(NumStart, 0, 16);
+    if (errno == EINVAL)
+      return ReturnError(CurPtr-2, "Invalid hexadecimal number");
+    if (errno == ERANGE) {
+      errno = 0;
+      CurIntVal = (int64_t)strtoull(NumStart, 0, 16);
+      if (errno == EINVAL)
+        return ReturnError(CurPtr-2, "Invalid hexadecimal number");
+      if (errno == ERANGE)
+        return ReturnError(CurPtr-2, "Hexadecimal number out of range");
+    }
+    return asmtok::IntVal;
+  }
+  
+  // Must be an octal number, it starts with 0.
+  while (*CurPtr >= '0' && *CurPtr <= '7')
+    ++CurPtr;
+  CurIntVal = strtoll(TokStart, 0, 8);
+  return asmtok::IntVal;
+}
+
+
 asmtok::TokKind AsmLexer::LexToken() {
   TokStart = CurPtr;
   // This always consumes at least one character.
@@ -66,9 +201,9 @@ asmtok::TokKind AsmLexer::LexToken() {
   
   switch (CurChar) {
   default:
-    // Handle letters: [a-zA-Z_]
-//    if (isalpha(CurChar) || CurChar == '_' || CurChar == '#')
-//      return LexIdentifier();
+    // Handle identifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
+    if (isalpha(CurChar) || CurChar == '_' || CurChar == '.')
+      return LexIdentifier();
     
     // Unknown character, emit an error.
     return asmtok::Error;
@@ -76,12 +211,29 @@ asmtok::TokKind AsmLexer::LexToken() {
   case 0:
   case ' ':
   case '\t':
-  case '\n':
-  case '\r':
     // Ignore whitespace.
     return LexToken();
+  case '\n': // FALL THROUGH.
+  case '\r': // FALL THROUGH.
+  case ';': return asmtok::EndOfStatement;
   case ':': return asmtok::Colon;
   case '+': return asmtok::Plus;
   case '-': return asmtok::Minus;
+  case '(': return asmtok::LParen;
+  case ')': return asmtok::RParen;
+  case '*': return asmtok::Star;
+  case ',': return asmtok::Comma;
+  case '$': return asmtok::Dollar;
+  case '%': return LexPercent();
+  case '/': return LexSlash();
+  case '#': return LexHash();
+  case '0': case '1': case '2': case '3': case '4':
+  case '5': case '6': case '7': case '8': case '9':
+    return LexDigit();
+      
+  // TODO: Quoted identifiers (objc methods etc)
+  // local labels: [0-9][:]
+  // Forward/backward labels: [0-9][fb]
+  // Integers, fp constants, character constants.
   }
 }

tools/llvm-mc/AsmLexer.h

@@ -29,12 +29,16 @@ namespace asmtok {
     Eof, Error,
 
     Identifier,
+    Register,
     IntVal,
     
-    
+    EndOfStatement,
     Colon,
     Plus,
-    Minus
+    Minus,
+    Slash,    // '/'
+    LParen, RParen,
+    Star, Comma, Dollar
   };
 }
 
@@ -66,7 +70,7 @@ public:
   asmtok::TokKind getKind() const { return CurKind; }
   
   const std::string &getCurStrVal() const {
-    assert(CurKind == asmtok::Identifier &&
+    assert((CurKind == asmtok::Identifier || CurKind == asmtok::Register) &&
            "This token doesn't have a string value");
     return CurStrVal;
   }
@@ -82,9 +86,15 @@ public:
   
 private:
   int getNextChar();
+  asmtok::TokKind ReturnError(const char *Loc, const std::string &Msg);
 
   /// LexToken - Read the next token and return its code.
   asmtok::TokKind LexToken();
+  asmtok::TokKind LexIdentifier();
+  asmtok::TokKind LexPercent();
+  asmtok::TokKind LexSlash();
+  asmtok::TokKind LexHash();
+  asmtok::TokKind LexDigit();
 };
   
 } // end namespace llvm

tools/llvm-mc/llvm-mc.cpp

@@ -72,17 +72,29 @@ static int AssembleInput(const char *ProgName) {
   asmtok::TokKind Tok = Lexer.Lex();
   while (Tok != asmtok::Eof) {
     switch (Tok) {
-    default: outs() << "<<unknown token>>\n"; break;
-    case asmtok::Error: outs() << "<<error>>\n"; break;
+    default: Lexer.PrintError(Lexer.getLoc(), "driver: unknown token"); break;
+    case asmtok::Error:
+      Lexer.PrintError(Lexer.getLoc(), "error, bad token");
+      break;
     case asmtok::Identifier:
       outs() << "identifier: " << Lexer.getCurStrVal() << '\n';
       break;
+    case asmtok::Register:
+      outs() << "register: " << Lexer.getCurStrVal() << '\n';
+      break;
     case asmtok::IntVal:
       outs() << "int: " << Lexer.getCurIntVal() << '\n';
       break;
+    case asmtok::EndOfStatement: outs() << "EndOfStatement\n"; break;
     case asmtok::Colon:  outs() << "Colon\n"; break;
     case asmtok::Plus:   outs() << "Plus\n"; break;
     case asmtok::Minus:  outs() << "Minus\n"; break;
+    case asmtok::Slash:  outs() << "Slash\n"; break;
+    case asmtok::LParen: outs() << "LParen\n"; break;
+    case asmtok::RParen: outs() << "RParen\n"; break;
+    case asmtok::Star:   outs() << "Star\n"; break;
+    case asmtok::Comma:  outs() << "Comma\n"; break;
+    case asmtok::Dollar: outs() << "Dollar\n"; break;
     }
     
     Tok = Lexer.Lex();