Add static cast to unsigned char whenever a character classification function is called with a signed char argument, in order to avoid assertions in Windows Debug configuration.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175006 91177308-0d34-0410-b5e6-96231b3b80d8

lib/AsmParser/LLLexer.cpp

@@ -119,7 +119,9 @@ static void UnEscapeLexed(std::string &Str) {
       if (BIn < EndBuffer-1 && BIn[1] == '\\') {
         *BOut++ = '\\'; // Two \ becomes one
         BIn += 2;
-      } else if (BIn < EndBuffer-2 && isxdigit(BIn[1]) && isxdigit(BIn[2])) {
+      } else if (BIn < EndBuffer-2 &&
+                 isxdigit(static_cast<unsigned char>(BIn[1])) &&
+                 isxdigit(static_cast<unsigned char>(BIn[2]))) {
         *BOut = hexDigitValue(BIn[1]) * 16 + hexDigitValue(BIn[2]);
         BIn += 3;                           // Skip over handled chars
         ++BOut;
@@ -135,7 +137,8 @@ static void UnEscapeLexed(std::string &Str) {
 
 /// isLabelChar - Return true for [-a-zA-Z$._0-9].
 static bool isLabelChar(char C) {
-  return isalnum(C) || C == '-' || C == '$' || C == '.' || C == '_';
+  return isalnum(static_cast<unsigned char>(C)) || C == '-' || C == '$' ||
+         C == '.' || C == '_';
 }
 
 
@@ -188,7 +191,7 @@ lltok::Kind LLLexer::LexToken() {
   switch (CurChar) {
   default:
     // Handle letters: [a-zA-Z_]
-    if (isalpha(CurChar) || CurChar == '_')
+    if (isalpha(static_cast<unsigned char>(CurChar)) || CurChar == '_')
       return LexIdentifier();
 
     return lltok::Error;
@@ -282,8 +285,8 @@ lltok::Kind LLLexer::LexAt() {
     return lltok::GlobalVar;
 
   // Handle GlobalVarID: @[0-9]+
-  if (isdigit(CurPtr[0])) {
+  if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
-    for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+    for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
       /*empty*/;
 
     uint64_t Val = atoull(TokStart+1, CurPtr);
@@ -317,10 +320,12 @@ lltok::Kind LLLexer::ReadString(lltok::Kind kind) {
 /// ReadVarName - Read the rest of a token containing a variable name.
 bool LLLexer::ReadVarName() {
   const char *NameStart = CurPtr;
-  if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+  if (isalpha(static_cast<unsigned char>(CurPtr[0])) ||
+      CurPtr[0] == '-' || CurPtr[0] == '$' ||
       CurPtr[0] == '.' || CurPtr[0] == '_') {
     ++CurPtr;
-    while (isalnum(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+    while (isalnum(static_cast<unsigned char>(CurPtr[0])) ||
+           CurPtr[0] == '-' || CurPtr[0] == '$' ||
            CurPtr[0] == '.' || CurPtr[0] == '_')
       ++CurPtr;
 
@@ -346,8 +351,8 @@ lltok::Kind LLLexer::LexPercent() {
     return lltok::LocalVar;
 
   // Handle LocalVarID: %[0-9]+
-  if (isdigit(CurPtr[0])) {
+  if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
-    for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+    for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
       /*empty*/;
 
     uint64_t Val = atoull(TokStart+1, CurPtr);
@@ -381,10 +386,12 @@ lltok::Kind LLLexer::LexQuote() {
 ///    !
 lltok::Kind LLLexer::LexExclaim() {
   // Lex a metadata name as a MetadataVar.
-  if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+  if (isalpha(static_cast<unsigned char>(CurPtr[0])) ||
+      CurPtr[0] == '-' || CurPtr[0] == '$' ||
       CurPtr[0] == '.' || CurPtr[0] == '_' || CurPtr[0] == '\\') {
     ++CurPtr;
-    while (isalnum(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+    while (isalnum(static_cast<unsigned char>(CurPtr[0])) ||
+           CurPtr[0] == '-' || CurPtr[0] == '$' ||
            CurPtr[0] == '.' || CurPtr[0] == '_' || CurPtr[0] == '\\')
       ++CurPtr;
 
@@ -399,8 +406,8 @@ lltok::Kind LLLexer::LexExclaim() {
 ///    AttrGrpID ::= #[0-9]+
 lltok::Kind LLLexer::LexHash() {
   // Handle AttrGrpID: #[0-9]+
-  if (isdigit(CurPtr[0])) {
+  if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
-    for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+    for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
       /*empty*/;
 
     uint64_t Val = atoull(TokStart+1, CurPtr);
@@ -425,8 +432,11 @@ lltok::Kind LLLexer::LexIdentifier() {
 
   for (; isLabelChar(*CurPtr); ++CurPtr) {
     // If we decide this is an integer, remember the end of the sequence.
-    if (!IntEnd && !isdigit(*CurPtr)) IntEnd = CurPtr;
+    if (!IntEnd && !isdigit(static_cast<unsigned char>(*CurPtr)))
-    if (!KeywordEnd && !isalnum(*CurPtr) && *CurPtr != '_') KeywordEnd = CurPtr;
+      IntEnd = CurPtr;
+    if (!KeywordEnd && !isalnum(static_cast<unsigned char>(*CurPtr)) &&
+        *CurPtr != '_')
+      KeywordEnd = CurPtr;
   }
 
   // If we stopped due to a colon, this really is a label.
@@ -676,7 +686,8 @@ lltok::Kind LLLexer::LexIdentifier() {
   // Check for [us]0x[0-9A-Fa-f]+ which are Hexadecimal constant generated by
   // the CFE to avoid forcing it to deal with 64-bit numbers.
   if ((TokStart[0] == 'u' || TokStart[0] == 's') &&
-      TokStart[1] == '0' && TokStart[2] == 'x' && isxdigit(TokStart[3])) {
+      TokStart[1] == '0' && TokStart[2] == 'x' &&
+      isxdigit(static_cast<unsigned char>(TokStart[3]))) {
     int len = CurPtr-TokStart-3;
     uint32_t bits = len * 4;
     APInt Tmp(bits, StringRef(TokStart+3, len), 16);
@@ -716,13 +727,13 @@ lltok::Kind LLLexer::Lex0x() {
     Kind = 'J';
   }
 
-  if (!isxdigit(CurPtr[0])) {
+  if (!isxdigit(static_cast<unsigned char>(CurPtr[0]))) {
     // Bad token, return it as an error.
     CurPtr = TokStart+1;
     return lltok::Error;
   }
 
-  while (isxdigit(CurPtr[0]))
+  while (isxdigit(static_cast<unsigned char>(CurPtr[0])))
     ++CurPtr;
 
   if (Kind == 'J') {
@@ -769,7 +780,8 @@ lltok::Kind LLLexer::Lex0x() {
 ///    HexPPC128Constant 0xM[0-9A-Fa-f]+
 lltok::Kind LLLexer::LexDigitOrNegative() {
   // If the letter after the negative is not a number, this is probably a label.
-  if (!isdigit(TokStart[0]) && !isdigit(CurPtr[0])) {
+  if (!isdigit(static_cast<unsigned char>(TokStart[0])) &&
+      !isdigit(static_cast<unsigned char>(CurPtr[0]))) {
     // Okay, this is not a number after the -, it's probably a label.
     if (const char *End = isLabelTail(CurPtr)) {
       StrVal.assign(TokStart, End-1);
@@ -783,7 +795,7 @@ lltok::Kind LLLexer::LexDigitOrNegative() {
   // At this point, it is either a label, int or fp constant.
 
   // Skip digits, we have at least one.
-  for (; isdigit(CurPtr[0]); ++CurPtr)
+  for (; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
     /*empty*/;
 
   // Check to see if this really is a label afterall, e.g. "-1:".
@@ -820,13 +832,14 @@ lltok::Kind LLLexer::LexDigitOrNegative() {
   ++CurPtr;
 
   // Skip over [0-9]*([eE][-+]?[0-9]+)?
-  while (isdigit(CurPtr[0])) ++CurPtr;
+  while (isdigit(static_cast<unsigned char>(CurPtr[0]))) ++CurPtr;
 
   if (CurPtr[0] == 'e' || CurPtr[0] == 'E') {
-    if (isdigit(CurPtr[1]) ||
+    if (isdigit(static_cast<unsigned char>(CurPtr[1])) ||
-        ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+        ((CurPtr[1] == '-' || CurPtr[1] == '+') &&
+          isdigit(static_cast<unsigned char>(CurPtr[2])))) {
       CurPtr += 2;
-      while (isdigit(CurPtr[0])) ++CurPtr;
+      while (isdigit(static_cast<unsigned char>(CurPtr[0]))) ++CurPtr;
     }
   }
 
@@ -838,11 +851,11 @@ lltok::Kind LLLexer::LexDigitOrNegative() {
 lltok::Kind LLLexer::LexPositive() {
   // If the letter after the negative is a number, this is probably not a
   // label.
-  if (!isdigit(CurPtr[0]))
+  if (!isdigit(static_cast<unsigned char>(CurPtr[0])))
     return lltok::Error;
 
   // Skip digits.
-  for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+  for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
     /*empty*/;
 
   // At this point, we need a '.'.
@@ -854,13 +867,14 @@ lltok::Kind LLLexer::LexPositive() {
   ++CurPtr;
 
   // Skip over [0-9]*([eE][-+]?[0-9]+)?
-  while (isdigit(CurPtr[0])) ++CurPtr;
+  while (isdigit(static_cast<unsigned char>(CurPtr[0]))) ++CurPtr;
 
   if (CurPtr[0] == 'e' || CurPtr[0] == 'E') {
-    if (isdigit(CurPtr[1]) ||
+    if (isdigit(static_cast<unsigned char>(CurPtr[1])) ||
-        ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+        ((CurPtr[1] == '-' || CurPtr[1] == '+') &&
+        isdigit(static_cast<unsigned char>(CurPtr[2])))) {
       CurPtr += 2;
-      while (isdigit(CurPtr[0])) ++CurPtr;
+      while (isdigit(static_cast<unsigned char>(CurPtr[0]))) ++CurPtr;
     }
   }
 

lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -2038,7 +2038,7 @@ getRegForInlineAsmConstraint(const std::string &Constraint,
 /// a matching constraint like "4".
 bool TargetLowering::AsmOperandInfo::isMatchingInputConstraint() const {
   assert(!ConstraintCode.empty() && "No known constraint!");
-  return isdigit(ConstraintCode[0]);
+  return isdigit(static_cast<unsigned char>(ConstraintCode[0]));
 }
 
 /// getMatchedOperand - If this is an input matching constraint, this method

lib/CodeGen/TargetInstrInfo.cpp

@@ -80,7 +80,7 @@ unsigned TargetInstrInfo::getInlineAsmLength(const char *Str,
     if (*Str == '\n' || strncmp(Str, MAI.getSeparatorString(),
                                 strlen(MAI.getSeparatorString())) == 0)
       atInsnStart = true;
-    if (atInsnStart && !std::isspace(*Str)) {
+    if (atInsnStart && !std::isspace(static_cast<unsigned char>(*Str))) {
       Length += MAI.getMaxInstLength();
       atInsnStart = false;
     }

lib/IR/AsmWriter.cpp

@@ -117,7 +117,7 @@ static void PrintLLVMName(raw_ostream &OS, StringRef Name, PrefixType Prefix) {
   }
 
   // Scan the name to see if it needs quotes first.
-  bool NeedsQuotes = isdigit(Name[0]);
+  bool NeedsQuotes = isdigit(static_cast<unsigned char>(Name[0]));
   if (!NeedsQuotes) {
     for (unsigned i = 0, e = Name.size(); i != e; ++i) {
       // By making this unsigned, the value passed in to isalnum will always be
@@ -125,7 +125,8 @@ static void PrintLLVMName(raw_ostream &OS, StringRef Name, PrefixType Prefix) {
       // its implementation will assert.  This situation can arise when dealing
       // with UTF-8 multibyte characters.
       unsigned char C = Name[i];
-      if (!isalnum(C) && C != '-' && C != '.' && C != '_') {
+      if (!isalnum(static_cast<unsigned char>(C)) && C != '-' && C != '.' &&
+          C != '_') {
         NeedsQuotes = true;
         break;
       }
@@ -1392,14 +1393,16 @@ void AssemblyWriter::printNamedMDNode(const NamedMDNode *NMD) {
   if (Name.empty()) {
     Out << "<empty name> ";
   } else {
-    if (isalpha(Name[0]) || Name[0] == '-' || Name[0] == '$' ||
+    if (isalpha(static_cast<unsigned char>(Name[0])) ||
+        Name[0] == '-' || Name[0] == '$' ||
         Name[0] == '.' || Name[0] == '_')
       Out << Name[0];
     else
       Out << '\\' << hexdigit(Name[0] >> 4) << hexdigit(Name[0] & 0x0F);
     for (unsigned i = 1, e = Name.size(); i != e; ++i) {
       unsigned char C = Name[i];
-      if (isalnum(C) || C == '-' || C == '$' || C == '.' || C == '_')
+      if (isalnum(static_cast<unsigned char>(C)) || C == '-' || C == '$' ||
+          C == '.' || C == '_')
         Out << C;
       else
         Out << '\\' << hexdigit(C >> 4) << hexdigit(C & 0x0F);

lib/IR/InlineAsm.cpp

@@ -151,10 +151,10 @@ bool InlineAsm::ConstraintInfo::Parse(StringRef Str,
       if (ConstraintEnd == E) return true;  // "{foo"
       pCodes->push_back(std::string(I, ConstraintEnd+1));
       I = ConstraintEnd+1;
-    } else if (isdigit(*I)) {     // Matching Constraint
+    } else if (isdigit(static_cast<unsigned char>(*I))) { // Matching Constraint
       // Maximal munch numbers.
       StringRef::iterator NumStart = I;
-      while (I != E && isdigit(*I))
+      while (I != E && isdigit(static_cast<unsigned char>(*I)))
         ++I;
       pCodes->push_back(std::string(NumStart, I));
       unsigned N = atoi(pCodes->back().c_str());

lib/IR/LLVMContext.cpp

@@ -130,12 +130,13 @@ static bool isValidName(StringRef MDName) {
   if (MDName.empty())
     return false;
 
-  if (!std::isalpha(MDName[0]))
+  if (!std::isalpha(static_cast<unsigned char>(MDName[0])))
     return false;
 
   for (StringRef::iterator I = MDName.begin() + 1, E = MDName.end(); I != E;
        ++I) {
-    if (!std::isalnum(*I) && *I != '_' && *I != '-' && *I != '.')
+    if (!std::isalnum(static_cast<unsigned char>(*I)) && *I != '_' &&
+        *I != '-' && *I != '.')
       return false;
   }
   return true;

lib/Linker/LinkModules.cpp

@@ -606,7 +606,8 @@ void ModuleLinker::computeTypeMapping() {
     // Check to see if there is a dot in the name followed by a digit.
     size_t DotPos = ST->getName().rfind('.');
     if (DotPos == 0 || DotPos == StringRef::npos ||
-        ST->getName().back() == '.' || !isdigit(ST->getName()[DotPos+1]))
+        ST->getName().back() == '.' ||
+        !isdigit(static_cast<unsigned char>(ST->getName()[DotPos+1])))
       continue;
     
     // Check to see if the destination module has a struct with the prefix name.

lib/MC/MCParser/AsmParser.cpp

@@ -1622,7 +1622,8 @@ void AsmParser::DiagHandler(const SMDiagnostic &Diag, void *Context) {
 // we can't do that. AsmLexer.cpp should probably be changed to handle
 // '@' as a special case when needed.
 static bool isIdentifierChar(char c) {
-  return isalnum(c) || c == '_' || c == '$' || c == '.';
+  return isalnum(static_cast<unsigned char>(c)) || c == '_' || c == '$' ||
+         c == '.';
 }
 
 bool AsmParser::expandMacro(raw_svector_ostream &OS, StringRef Body,
@@ -1646,7 +1647,8 @@ bool AsmParser::expandMacro(raw_svector_ostream &OS, StringRef Body,
           continue;
 
         char Next = Body[Pos + 1];
-        if (Next == '$' || Next == 'n' || isdigit(Next))
+        if (Next == '$' || Next == 'n' ||
+            isdigit(static_cast<unsigned char>(Next)))
           break;
       } else {
         // This macro has parameters, look for \foo, \bar, etc.
@@ -3094,7 +3096,8 @@ void AsmParser::CheckForBadMacro(SMLoc DirectiveLoc, StringRef Name,
       if (Body[Pos] != '$' || Pos + 1 == End)
         continue;
       char Next = Body[Pos + 1];
-      if (Next == '$' || Next == 'n' || isdigit(Next))
+      if (Next == '$' || Next == 'n' ||
+          isdigit(static_cast<unsigned char>(Next)))
         break;
     }
 

lib/MC/MCSectionMachO.cpp

@@ -165,9 +165,9 @@ bool MCSectionMachO::isVirtualSection() const {
 
 /// StripSpaces - This removes leading and trailing spaces from the StringRef.
 static void StripSpaces(StringRef &Str) {
-  while (!Str.empty() && isspace(Str[0]))
+  while (!Str.empty() && isspace(static_cast<unsigned char>(Str[0])))
     Str = Str.substr(1);
-  while (!Str.empty() && isspace(Str.back()))
+  while (!Str.empty() && isspace(static_cast<unsigned char>(Str.back())))
     Str = Str.substr(0, Str.size()-1);
 }
 

lib/Object/COFFObjectFile.cpp

@@ -267,7 +267,7 @@ error_code COFFObjectFile::getSymbolNMTypeChar(DataRefImpl Symb,
   }
 
   if (symb->StorageClass == COFF::IMAGE_SYM_CLASS_EXTERNAL)
-    ret = ::toupper(ret);
+    ret = ::toupper(static_cast<unsigned char>(ret));
 
   Result = ret;
   return object_error::success;

lib/Object/MachOObjectFile.cpp

@@ -273,7 +273,7 @@ error_code MachOObjectFile::getSymbolNMTypeChar(DataRefImpl DRI,
   }
 
   if (Flags & (macho::STF_External | macho::STF_PrivateExtern))
-    Char = toupper(Char);
+    Char = toupper(static_cast<unsigned char>(Char));
   Result = Char;
   return object_error::success;
 }

lib/Support/FileUtilities.cpp

@@ -87,9 +87,9 @@ static bool CompareNumbers(const char *&F1P, const char *&F2P,
 
   // If one of the positions is at a space and the other isn't, chomp up 'til
   // the end of the space.
-  while (isspace(*F1P) && F1P != F1End)
+  while (isspace(static_cast<unsigned char>(*F1P)) && F1P != F1End)
     ++F1P;
-  while (isspace(*F2P) && F2P != F2End)
+  while (isspace(static_cast<unsigned char>(*F2P)) && F2P != F2End)
     ++F2P;
 
   // If we stop on numbers, compare their difference.

lib/Support/PathV2.cpp

@@ -44,7 +44,8 @@ namespace {
 
 #ifdef LLVM_ON_WIN32
     // C:
-    if (path.size() >= 2 && std::isalpha(path[0]) && path[1] == ':')
+    if (path.size() >= 2 && std::isalpha(static_cast<unsigned char>(path[0])) &&
+        path[1] == ':')
       return path.substr(0, 2);
 #endif
 

lib/Support/Windows/Path.inc

@@ -82,7 +82,7 @@ Path::isValid() const {
   pos = path.rfind(':',len);
   size_t rootslash = 0;
   if (pos != std::string::npos) {
-    if (pos != 1 || !isalpha(path[0]) || len < 3)
+    if (pos != 1 || !isalpha(static_cast<unsigned char>(path[0])) || len < 3)
       return false;
       rootslash = 2;
   }

lib/Support/raw_ostream.cpp

@@ -241,7 +241,8 @@ raw_ostream &raw_ostream::operator<<(double N) {
       if (cs == '+' || cs == '-') {
         int c1 = buf[len - 2];
         int c0 = buf[len - 1];
-        if (isdigit(c1) && isdigit(c0)) {
+        if (isdigit(static_cast<unsigned char>(c1)) &&
+            isdigit(static_cast<unsigned char>(c0))) {
           // Trim leading '0': "...e+012" -> "...e+12\0"
           buf[len - 3] = c1;
           buf[len - 2] = c0;

tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp

@@ -450,7 +450,7 @@ static bool ParseBlock(BitstreamCursor &Stream, unsigned BlockID,
         outs() << " blob data = ";
         bool BlobIsPrintable = true;
         for (unsigned i = 0, e = Blob.size(); i != e; ++i)
-          if (!isprint(Blob[i])) {
+          if (!isprint(static_cast<unsigned char>(Blob[i]))) {
             BlobIsPrintable = false;
             break;
           }

tools/llvm-objdump/llvm-objdump.cpp

@@ -481,7 +481,7 @@ static void PrintSectionContents(const ObjectFile *o) {
       // Print ascii.
       outs() << "  ";
       for (std::size_t i = 0; i < 16 && addr + i < end; ++i) {
-        if (std::isprint(Contents[addr + i] & 0xFF))
+        if (std::isprint(static_cast<unsigned char>(Contents[addr + i]) & 0xFF))
           outs() << Contents[addr + i];
         else
           outs() << ".";

utils/FileCheck/FileCheck.cpp

@@ -242,7 +242,7 @@ bool Pattern::ParsePattern(StringRef PatternStr, SourceMgr &SM,
       }
 
       // Name can't start with a digit.
-      if (isdigit(Name[0])) {
+      if (isdigit(static_cast<unsigned char>(Name[0]))) {
         SM.PrintMessage(SMLoc::getFromPointer(Name.data()), SourceMgr::DK_Error,
                         "invalid name in named regex");
         return true;