Disambiguate Numbers and Identifiers

Use lookahead to determine whether a number is really a number or is
part of something forming an identifier.  This won't come into play
until the paste operator is recognized as a unique token.

llvm-svn: 142513

1 files changed, 37 insertions, 1 deletions

diff --git a/llvm/lib/TableGen/TGLexer.cpp b/llvm/lib/TableGen/TGLexer.cpp
index c1b00b66ef5..3262121ee8d 100644
--- a/llvm/lib/TableGen/TGLexer.cpp
+++ b/llvm/lib/TableGen/TGLexer.cpp
@@ -132,8 +132,44 @@ tgtok::TokKind TGLexer::LexToken() {
     return LexToken();
   case '-': case '+':
   case '0': case '1': case '2': case '3': case '4': case '5': case '6':
-  case '7': case '8': case '9':  
+  case '7': case '8': case '9': {
+    int NextChar = 0;
+    if (isdigit(CurChar)) {
+      // Allow identifiers to start with a number if it is followed by
+      // an identifier.  This can happen with paste operations like
+      // foo#8i.
+      int i = 0;
+      do {
+        NextChar = peekNextChar(i++);
+      } while (isdigit(NextChar));
+
+      if (NextChar == 'x' || NextChar == 'b') {
+        // If this is [0-9]b[01] or [0-9]x[0-9A-fa-f] this is most
+        // likely a number.
+        int NextNextChar = peekNextChar(i);
+        switch (NextNextChar) {
+        default:
+          break;
+        case '0': case '1': 
+          if (NextChar == 'b')
+            return LexNumber();
+          // Fallthrough
+        case '2': case '3': case '4': case '5':
+        case '6': case '7': case '8': case '9':
+        case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
+        case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
+          if (NextChar == 'x')
+            return LexNumber();
+          break;
+        }
+      }
+    }
+
+    if (isalpha(NextChar) || NextChar == '_')
+      return LexIdentifier();
+
     return LexNumber();
+  }
   case '"': return LexString();
   case '$': return LexVarName();
   case '[': return LexBracket();