#include "LLLexer.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/Twine.h"
-#include "llvm/Assembly/Parser.h"
+#include "llvm/AsmParser/Parser.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/LLVMContext.h"
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;
/// 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 == '$' ||
+ C == '.' || C == '_';
}
switch (CurChar) {
default:
// Handle letters: [a-zA-Z_]
- if (isalpha(CurChar) || CurChar == '_')
+ if (isalpha(static_cast<unsigned char>(CurChar)) || CurChar == '_')
return LexIdentifier();
return lltok::Error;
if (CurChar == '"') {
StrVal.assign(TokStart+2, CurPtr-1);
UnEscapeLexed(StrVal);
+ if (StringRef(StrVal).find_first_of(0) != StringRef::npos) {
+ Error("Null bytes are not allowed in names");
+ return lltok::Error;
+ }
return lltok::GlobalVar;
}
}
return lltok::GlobalVar;
// Handle GlobalVarID: @[0-9]+
- if (isdigit(CurPtr[0])) {
- for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
+ for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
/*empty*/;
uint64_t Val = atoull(TokStart+1, CurPtr);
/// ReadVarName - Read the rest of a token containing a variable name.
bool LLLexer::ReadVarName() {
const char *NameStart = CurPtr;
- if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ 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] == '$' ||
CurPtr[0] == '.' || CurPtr[0] == '_')
++CurPtr;
return lltok::LocalVar;
// Handle LocalVarID: %[0-9]+
- if (isdigit(CurPtr[0])) {
- for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
+ for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
/*empty*/;
uint64_t Val = atoull(TokStart+1, CurPtr);
/// !
lltok::Kind LLLexer::LexExclaim() {
// Lex a metadata name as a MetadataVar.
- if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ 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;
/// AttrGrpID ::= #[0-9]+
lltok::Kind LLLexer::LexHash() {
// Handle AttrGrpID: #[0-9]+
- if (isdigit(CurPtr[0])) {
- for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
+ for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
/*empty*/;
uint64_t Val = atoull(TokStart+1, CurPtr);
for (; isLabelChar(*CurPtr); ++CurPtr) {
// If we decide this is an integer, remember the end of the sequence.
- if (!IntEnd && !isdigit(*CurPtr)) IntEnd = CurPtr;
- if (!KeywordEnd && !isalnum(*CurPtr) && *CurPtr != '_') KeywordEnd = CurPtr;
+ if (!IntEnd && !isdigit(static_cast<unsigned char>(*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.
KEYWORD(private);
KEYWORD(linker_private);
KEYWORD(linker_private_weak);
- KEYWORD(linker_private_weak_def_auto); // FIXME: For backwards compatibility.
KEYWORD(internal);
KEYWORD(available_externally);
KEYWORD(linkonce);
KEYWORD(linkonce_odr);
- KEYWORD(linkonce_odr_auto_hide);
KEYWORD(weak);
KEYWORD(weak_odr);
KEYWORD(appending);
KEYWORD(alignstack);
KEYWORD(inteldialect);
KEYWORD(gc);
+ KEYWORD(prefix);
KEYWORD(ccc);
KEYWORD(fastcc);
KEYWORD(x86_stdcallcc);
KEYWORD(x86_fastcallcc);
KEYWORD(x86_thiscallcc);
+ KEYWORD(x86_cdeclmethodcc);
KEYWORD(arm_apcscc);
KEYWORD(arm_aapcscc);
KEYWORD(arm_aapcs_vfpcc);
KEYWORD(spir_kernel);
KEYWORD(spir_func);
KEYWORD(intel_ocl_bicc);
+ KEYWORD(x86_64_sysvcc);
+ KEYWORD(x86_64_win64cc);
+ KEYWORD(webkit_jscc);
+ KEYWORD(anyregcc);
+ KEYWORD(preserve_mostcc);
+ KEYWORD(preserve_allcc);
KEYWORD(cc);
KEYWORD(c);
KEYWORD(attributes);
- KEYWORD(address_safety);
KEYWORD(alwaysinline);
+ KEYWORD(builtin);
KEYWORD(byval);
+ KEYWORD(inalloca);
+ KEYWORD(cold);
KEYWORD(inlinehint);
KEYWORD(inreg);
KEYWORD(minsize);
KEYWORD(naked);
KEYWORD(nest);
KEYWORD(noalias);
+ KEYWORD(nobuiltin);
KEYWORD(nocapture);
KEYWORD(noduplicate);
KEYWORD(noimplicitfloat);
KEYWORD(noredzone);
KEYWORD(noreturn);
KEYWORD(nounwind);
+ KEYWORD(optnone);
KEYWORD(optsize);
KEYWORD(readnone);
KEYWORD(readonly);
+ KEYWORD(returned);
KEYWORD(returns_twice);
KEYWORD(signext);
KEYWORD(sret);
KEYWORD(ssp);
KEYWORD(sspreq);
KEYWORD(sspstrong);
+ KEYWORD(sanitize_address);
+ KEYWORD(sanitize_thread);
+ KEYWORD(sanitize_memory);
KEYWORD(uwtable);
KEYWORD(zeroext);
INSTKEYWORD(inttoptr, IntToPtr);
INSTKEYWORD(ptrtoint, PtrToInt);
INSTKEYWORD(bitcast, BitCast);
+ INSTKEYWORD(addrspacecast, AddrSpaceCast);
INSTKEYWORD(select, Select);
INSTKEYWORD(va_arg, VAArg);
INSTKEYWORD(ret, Ret);
// 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);
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') {
/// 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);
// 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:".
++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]) ||
- ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+ if (isdigit(static_cast<unsigned char>(CurPtr[1])) ||
+ ((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;
}
}
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 '.'.
++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]) ||
- ((CurPtr[1] == '-' || CurPtr[1] == '+') && isdigit(CurPtr[2]))) {
+ if (isdigit(static_cast<unsigned char>(CurPtr[1])) ||
+ ((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;
}
}