X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTableGen%2FTGLexer.cpp;h=63b85842d6a9e68910ecd32eb78be621abbb1ed7;hb=a19abeb7abaa80b946c593164a08c3d230183a95;hp=8c1b4290548de11577138afb7d30f658978a1f45;hpb=a1b1b79be15c4b79a4282f148085ebad1cf877ca;p=oota-llvm.git

diff --git a/lib/TableGen/TGLexer.cpp b/lib/TableGen/TGLexer.cpp
index 8c1b4290548..63b85842d6a 100644
--- a/lib/TableGen/TGLexer.cpp
+++ b/lib/TableGen/TGLexer.cpp
@@ -12,24 +12,25 @@
 //===----------------------------------------------------------------------===//
 
 #include "TGLexer.h"
-#include "llvm/TableGen/Error.h"
-#include "llvm/Support/SourceMgr.h"
-#include "llvm/Support/MemoryBuffer.h"
-#include "llvm/Config/config.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/ADT/Twine.h"
+#include "llvm/Config/config.h" // for strtoull()/strtoll() define
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/SourceMgr.h"
+#include "llvm/TableGen/Error.h"
 #include <cctype>
+#include <cerrno>
 #include <cstdio>
 #include <cstdlib>
 #include <cstring>
-#include <cerrno>
+
 using namespace llvm;
 
 TGLexer::TGLexer(SourceMgr &SM) : SrcMgr(SM) {
-  CurBuffer = 0;
-  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
-  CurPtr = CurBuf->getBufferStart();
-  TokStart = 0;
+  CurBuffer = SrcMgr.getMainFileID();
+  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer)->getBuffer();
+  CurPtr = CurBuf.begin();
+  TokStart = nullptr;
 }
 
 SMLoc TGLexer::getLoc() const {
@@ -51,7 +52,7 @@ int TGLexer::getNextChar() {
   case 0: {
     // A nul character in the stream is either the end of the current buffer or
     // a random nul in the file.  Disambiguate that here.
-    if (CurPtr-1 != CurBuf->getBufferEnd())
+    if (CurPtr-1 != CurBuf.end())
       return 0;  // Just whitespace.
     
     // If this is the end of an included file, pop the parent file off the
@@ -59,7 +60,7 @@ int TGLexer::getNextChar() {
     SMLoc ParentIncludeLoc = SrcMgr.getParentIncludeLoc(CurBuffer);
     if (ParentIncludeLoc != SMLoc()) {
       CurBuffer = SrcMgr.FindBufferContainingLoc(ParentIncludeLoc);
-      CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
+      CurBuf = SrcMgr.getMemoryBuffer(CurBuffer)->getBuffer();
       CurPtr = ParentIncludeLoc.getPointer();
       return getNextChar();
     }
@@ -80,6 +81,10 @@ int TGLexer::getNextChar() {
   }  
 }
 
+int TGLexer::peekNextChar(int Index) {
+  return *(CurPtr + Index);
+}
+
 tgtok::TokKind TGLexer::LexToken() {
   TokStart = CurPtr;
   // This always consumes at least one character.
@@ -87,10 +92,10 @@ tgtok::TokKind TGLexer::LexToken() {
 
   switch (CurChar) {
   default:
-    // Handle letters: [a-zA-Z_#]
-    if (isalpha(CurChar) || CurChar == '_' || CurChar == '#')
+    // Handle letters: [a-zA-Z_]
+    if (isalpha(CurChar) || CurChar == '_')
       return LexIdentifier();
-      
+
     // Unknown character, emit an error.
     return ReturnError(TokStart, "Unexpected character");
   case EOF: return tgtok::Eof;
@@ -107,6 +112,7 @@ tgtok::TokKind TGLexer::LexToken() {
   case ')': return tgtok::r_paren;
   case '=': return tgtok::equal;
   case '?': return tgtok::question;
+  case '#': return tgtok::paste;
       
   case 0:
   case ' ':
@@ -128,8 +134,44 @@ 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();
@@ -145,7 +187,7 @@ tgtok::TokKind TGLexer::LexString() {
   
   while (*CurPtr != '"') {
     // If we hit the end of the buffer, report an error.
-    if (*CurPtr == 0 && CurPtr == CurBuf->getBufferEnd())
+    if (*CurPtr == 0 && CurPtr == CurBuf.end())
       return ReturnError(StrStart, "End of file in string literal");
     
     if (*CurPtr == '\n' || *CurPtr == '\r')
@@ -178,7 +220,7 @@ tgtok::TokKind TGLexer::LexString() {
 
     // If we hit the end of the buffer, report an error.
     case '\0':
-      if (CurPtr == CurBuf->getBufferEnd())
+      if (CurPtr == CurBuf.end())
         return ReturnError(StrStart, "End of file in string literal");
       // FALL THROUGH
     default:
@@ -210,8 +252,7 @@ tgtok::TokKind TGLexer::LexIdentifier() {
   const char *IdentStart = TokStart;
 
   // Match the rest of the identifier regex: [0-9a-zA-Z_#]*
-  while (isalpha(*CurPtr) || isdigit(*CurPtr) || *CurPtr == '_' ||
-         *CurPtr == '#')
+  while (isalpha(*CurPtr) || isdigit(*CurPtr) || *CurPtr == '_')
     ++CurPtr;
 
   // Check to see if this identifier is a keyword.
@@ -232,6 +273,7 @@ tgtok::TokKind TGLexer::LexIdentifier() {
     .Case("dag", tgtok::Dag)
     .Case("class", tgtok::Class)
     .Case("def", tgtok::Def)
+    .Case("foreach", tgtok::Foreach)
     .Case("defm", tgtok::Defm)
     .Case("multiclass", tgtok::MultiClass)
     .Case("field", tgtok::Field)
@@ -262,15 +304,23 @@ bool TGLexer::LexInclude() {
   
   CurBuffer = SrcMgr.AddIncludeFile(Filename, SMLoc::getFromPointer(CurPtr),
                                     IncludedFile);
-  if (CurBuffer == -1) {
+  if (!CurBuffer) {
     PrintError(getLoc(), "Could not find include file '" + Filename + "'");
     return true;
   }
   
-  Dependencies.push_back(IncludedFile);
+  DependenciesMapTy::const_iterator Found = Dependencies.find(IncludedFile);
+  if (Found != Dependencies.end()) {
+    PrintError(getLoc(),
+               "File '" + IncludedFile + "' has already been included.");
+    SrcMgr.PrintMessage(Found->second, SourceMgr::DK_Note,
+                        "previously included here");
+    return true;
+  }
+  Dependencies.insert(std::make_pair(IncludedFile, getLoc()));
   // Save the line number and lex buffer of the includer.
-  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
-  CurPtr = CurBuf->getBufferStart();
+  CurBuf = SrcMgr.getMemoryBuffer(CurBuffer)->getBuffer();
+  CurPtr = CurBuf.begin();
   return false;
 }
 
@@ -283,7 +333,7 @@ void TGLexer::SkipBCPLComment() {
       return;  // Newline is end of comment.
     case 0:
       // If this is the end of the buffer, end the comment.
-      if (CurPtr == CurBuf->getBufferEnd())
+      if (CurPtr == CurBuf.end())
         return;
       break;
     }
@@ -339,12 +389,12 @@ tgtok::TokKind TGLexer::LexNumber() {
         return ReturnError(TokStart, "Invalid hexadecimal number");
 
       errno = 0;
-      CurIntVal = strtoll(NumStart, 0, 16);
+      CurIntVal = strtoll(NumStart, nullptr, 16);
       if (errno == EINVAL)
         return ReturnError(TokStart, "Invalid hexadecimal number");
       if (errno == ERANGE) {
         errno = 0;
-        CurIntVal = (int64_t)strtoull(NumStart, 0, 16);
+        CurIntVal = (int64_t)strtoull(NumStart, nullptr, 16);
         if (errno == EINVAL)
           return ReturnError(TokStart, "Invalid hexadecimal number");
         if (errno == ERANGE)
@@ -360,8 +410,8 @@ tgtok::TokKind TGLexer::LexNumber() {
       // Requires at least one binary digit.
       if (CurPtr == NumStart)
         return ReturnError(CurPtr-2, "Invalid binary number");
-      CurIntVal = strtoll(NumStart, 0, 2);
-      return tgtok::IntVal;
+      CurIntVal = strtoll(NumStart, nullptr, 2);
+      return tgtok::BinaryIntVal;
     }
   }
 
@@ -375,7 +425,7 @@ tgtok::TokKind TGLexer::LexNumber() {
   
   while (isdigit(CurPtr[0]))
     ++CurPtr;
-  CurIntVal = strtoll(TokStart, 0, 10);
+  CurIntVal = strtoll(TokStart, nullptr, 10);
   return tgtok::IntVal;
 }
 
@@ -420,6 +470,8 @@ tgtok::TokKind TGLexer::LexExclaim() {
     .Case("head", tgtok::XHead)
     .Case("tail", tgtok::XTail)
     .Case("con", tgtok::XConcat)
+    .Case("add", tgtok::XADD)
+    .Case("and", tgtok::XAND)
     .Case("shl", tgtok::XSHL)
     .Case("sra", tgtok::XSRA)
     .Case("srl", tgtok::XSRL)
@@ -427,6 +479,7 @@ tgtok::TokKind TGLexer::LexExclaim() {
     .Case("empty", tgtok::XEmpty)
     .Case("subst", tgtok::XSubst)
     .Case("foreach", tgtok::XForEach)
+    .Case("listconcat", tgtok::XListConcat)
     .Case("strconcat", tgtok::XStrConcat)
     .Default(tgtok::Error);