//===----------------------------------------------------------------------===//
#include "LLLexer.h"
-#include "llvm/DerivedTypes.h"
-#include "llvm/Instruction.h"
-#include "llvm/LLVMContext.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"
#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Support/raw_ostream.h"
#include <cctype>
return true;
}
+void LLLexer::Warning(LocTy WarningLoc, const Twine &Msg) const {
+ SM.PrintMessage(WarningLoc, SourceMgr::DK_Warning, Msg);
+}
+
//===----------------------------------------------------------------------===//
// Helper functions.
//===----------------------------------------------------------------------===//
return Result;
}
-static char parseHexChar(char C) {
- if (C >= '0' && C <= '9')
- return C-'0';
- if (C >= 'A' && C <= 'F')
- return C-'A'+10;
- if (C >= 'a' && C <= 'f')
- return C-'a'+10;
- return 0;
-}
-
uint64_t LLLexer::HexIntToVal(const char *Buffer, const char *End) {
uint64_t Result = 0;
for (; Buffer != End; ++Buffer) {
uint64_t OldRes = Result;
Result *= 16;
- Result += parseHexChar(*Buffer);
+ Result += hexDigitValue(*Buffer);
if (Result < OldRes) { // Uh, oh, overflow detected!!!
Error("constant bigger than 64 bits detected!");
void LLLexer::HexToIntPair(const char *Buffer, const char *End,
uint64_t Pair[2]) {
Pair[0] = 0;
- for (int i=0; i<16; i++, Buffer++) {
- assert(Buffer != End);
- Pair[0] *= 16;
- Pair[0] += parseHexChar(*Buffer);
+ if (End - Buffer >= 16) {
+ for (int i = 0; i < 16; i++, Buffer++) {
+ assert(Buffer != End);
+ Pair[0] *= 16;
+ Pair[0] += hexDigitValue(*Buffer);
+ }
}
Pair[1] = 0;
- for (int i=0; i<16 && Buffer != End; i++, Buffer++) {
+ for (int i = 0; i < 16 && Buffer != End; i++, Buffer++) {
Pair[1] *= 16;
- Pair[1] += parseHexChar(*Buffer);
+ Pair[1] += hexDigitValue(*Buffer);
}
if (Buffer != End)
Error("constant bigger than 128 bits detected!");
for (int i=0; i<4 && Buffer != End; i++, Buffer++) {
assert(Buffer != End);
Pair[1] *= 16;
- Pair[1] += parseHexChar(*Buffer);
+ Pair[1] += hexDigitValue(*Buffer);
}
Pair[0] = 0;
- for (int i=0; i<16; i++, Buffer++) {
+ for (int i = 0; i < 16 && Buffer != End; i++, Buffer++) {
Pair[0] *= 16;
- Pair[0] += parseHexChar(*Buffer);
+ Pair[0] += hexDigitValue(*Buffer);
}
if (Buffer != End)
Error("constant bigger than 128 bits detected!");
if (BIn < EndBuffer-1 && BIn[1] == '\\') {
*BOut++ = '\\'; // Two \ becomes one
BIn += 2;
- } else if (BIn < EndBuffer-2 && isxdigit(BIn[1]) && isxdigit(BIn[2])) {
- *BOut = parseHexChar(BIn[1]) * 16 + parseHexChar(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;
} else {
/// 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 == '$' ||
+ C == '.' || C == '_';
}
static const char *isLabelTail(const char *CurPtr) {
while (1) {
if (CurPtr[0] == ':') return CurPtr+1;
- if (!isLabelChar(CurPtr[0])) return 0;
+ if (!isLabelChar(CurPtr[0])) return nullptr;
++CurPtr;
}
}
// Lexer definition.
//===----------------------------------------------------------------------===//
-LLLexer::LLLexer(MemoryBuffer *StartBuf, SourceMgr &sm, SMDiagnostic &Err,
+LLLexer::LLLexer(StringRef StartBuf, SourceMgr &sm, SMDiagnostic &Err,
LLVMContext &C)
: CurBuf(StartBuf), ErrorInfo(Err), SM(sm), Context(C), APFloatVal(0.0) {
- CurPtr = CurBuf->getBufferStart();
-}
-
-std::string LLLexer::getFilename() const {
- return CurBuf->getBufferIdentifier();
+ CurPtr = CurBuf.begin();
}
int LLLexer::getNextChar() {
case 0:
// A nul character in the stream is either the end of the current buffer or
// a random nul in the file. Disambiguate that here.
- if (CurPtr-1 != CurBuf->getBufferEnd())
+ if (CurPtr-1 != CurBuf.end())
return 0; // Just whitespace.
// Otherwise, return end of file.
switch (CurChar) {
default:
// Handle letters: [a-zA-Z_]
- if (isalpha(CurChar) || CurChar == '_')
+ if (isalpha(static_cast<unsigned char>(CurChar)) || CurChar == '_')
return LexIdentifier();
return lltok::Error;
return LexToken();
case '+': return LexPositive();
case '@': return LexAt();
+ case '$': return LexDollar();
case '%': return LexPercent();
case '"': return LexQuote();
case '.':
return lltok::dotdotdot;
}
return lltok::Error;
- case '$':
- if (const char *Ptr = isLabelTail(CurPtr)) {
- CurPtr = Ptr;
- StrVal.assign(TokStart, CurPtr-1);
- return lltok::LabelStr;
- }
- return lltok::Error;
case ';':
SkipLineComment();
return LexToken();
case '!': return LexExclaim();
+ case '#': return LexHash();
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case '-':
case ')': return lltok::rparen;
case ',': return lltok::comma;
case '*': return lltok::star;
- case '\\': return lltok::backslash;
+ case '|': return lltok::bar;
}
}
}
}
-/// LexAt - Lex all tokens that start with an @ character:
+/// Lex all tokens that start with an @ character.
/// GlobalVar @\"[^\"]*\"
/// GlobalVar @[-a-zA-Z$._][-a-zA-Z$._0-9]*
/// GlobalVarID @[0-9]+
lltok::Kind LLLexer::LexAt() {
- // Handle AtStringConstant: @\"[^\"]*\"
+ return LexVar(lltok::GlobalVar, lltok::GlobalID);
+}
+
+lltok::Kind LLLexer::LexDollar() {
+ if (const char *Ptr = isLabelTail(TokStart)) {
+ CurPtr = Ptr;
+ StrVal.assign(TokStart, CurPtr - 1);
+ return lltok::LabelStr;
+ }
+
+ // Handle DollarStringConstant: $\"[^\"]*\"
if (CurPtr[0] == '"') {
++CurPtr;
int CurChar = getNextChar();
if (CurChar == EOF) {
- Error("end of file in global variable name");
+ Error("end of file in COMDAT variable name");
return lltok::Error;
}
if (CurChar == '"') {
- StrVal.assign(TokStart+2, CurPtr-1);
+ StrVal.assign(TokStart + 2, CurPtr - 1);
UnEscapeLexed(StrVal);
- return lltok::GlobalVar;
+ if (StringRef(StrVal).find_first_of(0) != StringRef::npos) {
+ Error("Null bytes are not allowed in names");
+ return lltok::Error;
+ }
+ return lltok::ComdatVar;
}
}
}
- // Handle GlobalVarName: @[-a-zA-Z$._][-a-zA-Z$._0-9]*
+ // Handle ComdatVarName: $[-a-zA-Z$._][-a-zA-Z$._0-9]*
if (ReadVarName())
- return lltok::GlobalVar;
-
- // Handle GlobalVarID: @[0-9]+
- if (isdigit(CurPtr[0])) {
- for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
- /*empty*/;
-
- uint64_t Val = atoull(TokStart+1, CurPtr);
- if ((unsigned)Val != Val)
- Error("invalid value number (too large)!");
- UIntVal = unsigned(Val);
- return lltok::GlobalID;
- }
+ return lltok::ComdatVar;
return lltok::Error;
}
/// ReadVarName - Read the rest of a token containing a variable name.
bool LLLexer::ReadVarName() {
const char *NameStart = CurPtr;
- if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ 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] == '$' ||
CurPtr[0] == '.' || CurPtr[0] == '_')
++CurPtr;
return false;
}
-/// LexPercent - Lex all tokens that start with a % character:
-/// LocalVar ::= %\"[^\"]*\"
-/// LocalVar ::= %[-a-zA-Z$._][-a-zA-Z$._0-9]*
-/// LocalVarID ::= %[0-9]+
-lltok::Kind LLLexer::LexPercent() {
- // Handle LocalVarName: %\"[^\"]*\"
+lltok::Kind LLLexer::LexVar(lltok::Kind Var, lltok::Kind VarID) {
+ // Handle StringConstant: \"[^\"]*\"
if (CurPtr[0] == '"') {
++CurPtr;
- return ReadString(lltok::LocalVar);
+
+ while (1) {
+ int CurChar = getNextChar();
+
+ if (CurChar == EOF) {
+ Error("end of file in global variable name");
+ return lltok::Error;
+ }
+ if (CurChar == '"') {
+ StrVal.assign(TokStart+2, CurPtr-1);
+ UnEscapeLexed(StrVal);
+ if (StringRef(StrVal).find_first_of(0) != StringRef::npos) {
+ Error("Null bytes are not allowed in names");
+ return lltok::Error;
+ }
+ return Var;
+ }
+ }
}
- // Handle LocalVarName: %[-a-zA-Z$._][-a-zA-Z$._0-9]*
+ // Handle VarName: [-a-zA-Z$._][-a-zA-Z$._0-9]*
if (ReadVarName())
- return lltok::LocalVar;
+ return Var;
- // Handle LocalVarID: %[0-9]+
- if (isdigit(CurPtr[0])) {
- for (++CurPtr; isdigit(CurPtr[0]); ++CurPtr)
+ // Handle VarID: [0-9]+
+ if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
+ for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
/*empty*/;
uint64_t Val = atoull(TokStart+1, CurPtr);
if ((unsigned)Val != Val)
Error("invalid value number (too large)!");
UIntVal = unsigned(Val);
- return lltok::LocalVarID;
+ return VarID;
}
-
return lltok::Error;
}
-/// LexQuote - Lex all tokens that start with a " character:
+/// Lex all tokens that start with a % character.
+/// LocalVar ::= %\"[^\"]*\"
+/// LocalVar ::= %[-a-zA-Z$._][-a-zA-Z$._0-9]*
+/// LocalVarID ::= %[0-9]+
+lltok::Kind LLLexer::LexPercent() {
+ return LexVar(lltok::LocalVar, lltok::LocalVarID);
+}
+
+/// Lex all tokens that start with a " character.
/// QuoteLabel "[^"]+":
/// StringConstant "[^"]*"
lltok::Kind LLLexer::LexQuote() {
if (CurPtr[0] == ':') {
++CurPtr;
- kind = lltok::LabelStr;
+ if (StringRef(StrVal).find_first_of(0) != StringRef::npos) {
+ Error("Null bytes are not allowed in names");
+ kind = lltok::Error;
+ } else {
+ kind = lltok::LabelStr;
+ }
}
return kind;
}
-/// LexExclaim:
+/// Lex all tokens that start with a ! character.
/// !foo
/// !
lltok::Kind LLLexer::LexExclaim() {
// Lex a metadata name as a MetadataVar.
- if (isalpha(CurPtr[0]) || CurPtr[0] == '-' || CurPtr[0] == '$' ||
+ 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] == '$' ||
CurPtr[0] == '.' || CurPtr[0] == '_' || CurPtr[0] == '\\')
++CurPtr;
}
return lltok::exclaim;
}
-
-/// LexIdentifier: Handle several related productions:
+
+/// Lex all tokens that start with a # character.
+/// AttrGrpID ::= #[0-9]+
+lltok::Kind LLLexer::LexHash() {
+ // Handle AttrGrpID: #[0-9]+
+ if (isdigit(static_cast<unsigned char>(CurPtr[0]))) {
+ for (++CurPtr; isdigit(static_cast<unsigned char>(CurPtr[0])); ++CurPtr)
+ /*empty*/;
+
+ uint64_t Val = atoull(TokStart+1, CurPtr);
+ if ((unsigned)Val != Val)
+ Error("invalid value number (too large)!");
+ UIntVal = unsigned(Val);
+ return lltok::AttrGrpID;
+ }
+
+ return lltok::Error;
+}
+
+/// Lex a label, integer type, keyword, or hexadecimal integer constant.
/// Label [-a-zA-Z$._0-9]+:
/// IntegerType i[0-9]+
/// Keyword sdiv, float, ...
/// HexIntConstant [us]0x[0-9A-Fa-f]+
lltok::Kind LLLexer::LexIdentifier() {
const char *StartChar = CurPtr;
- const char *IntEnd = CurPtr[-1] == 'i' ? 0 : StartChar;
- const char *KeywordEnd = 0;
+ const char *IntEnd = CurPtr[-1] == 'i' ? nullptr : StartChar;
+ const char *KeywordEnd = nullptr;
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.
// Otherwise, this wasn't a label. If this was valid as an integer type,
// return it.
- if (IntEnd == 0) IntEnd = CurPtr;
+ if (!IntEnd) IntEnd = CurPtr;
if (IntEnd != StartChar) {
CurPtr = IntEnd;
uint64_t NumBits = atoull(StartChar, CurPtr);
}
// Otherwise, this was a letter sequence. See which keyword this is.
- if (KeywordEnd == 0) KeywordEnd = CurPtr;
+ if (!KeywordEnd) KeywordEnd = CurPtr;
CurPtr = KeywordEnd;
--StartChar;
- unsigned Len = CurPtr-StartChar;
-#define KEYWORD(STR) \
- if (Len == strlen(#STR) && !memcmp(StartChar, #STR, strlen(#STR))) \
- return lltok::kw_##STR;
+ StringRef Keyword(StartChar, CurPtr - StartChar);
+#define KEYWORD(STR) \
+ do { \
+ if (Keyword == #STR) \
+ return lltok::kw_##STR; \
+ } while (0)
KEYWORD(true); KEYWORD(false);
KEYWORD(declare); KEYWORD(define);
KEYWORD(global); KEYWORD(constant);
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); // Use as a linkage, and a modifier for "cmpxchg".
KEYWORD(weak_odr);
KEYWORD(appending);
KEYWORD(dllimport);
KEYWORD(hidden);
KEYWORD(protected);
KEYWORD(unnamed_addr);
+ KEYWORD(externally_initialized);
KEYWORD(extern_weak);
KEYWORD(external);
KEYWORD(thread_local);
KEYWORD(zeroinitializer);
KEYWORD(undef);
KEYWORD(null);
+ KEYWORD(none);
KEYWORD(to);
+ KEYWORD(caller);
+ KEYWORD(within);
+ KEYWORD(from);
KEYWORD(tail);
+ KEYWORD(musttail);
+ KEYWORD(notail);
KEYWORD(target);
KEYWORD(triple);
KEYWORD(unwind);
- KEYWORD(deplibs);
+ KEYWORD(deplibs); // FIXME: Remove in 4.0.
KEYWORD(datalayout);
KEYWORD(volatile);
KEYWORD(atomic);
KEYWORD(seq_cst);
KEYWORD(singlethread);
+ KEYWORD(nnan);
+ KEYWORD(ninf);
+ KEYWORD(nsz);
+ KEYWORD(arcp);
+ KEYWORD(fast);
KEYWORD(nuw);
KEYWORD(nsw);
KEYWORD(exact);
KEYWORD(alignstack);
KEYWORD(inteldialect);
KEYWORD(gc);
+ KEYWORD(prefix);
+ KEYWORD(prologue);
KEYWORD(ccc);
KEYWORD(fastcc);
KEYWORD(x86_stdcallcc);
KEYWORD(x86_fastcallcc);
KEYWORD(x86_thiscallcc);
+ KEYWORD(x86_vectorcallcc);
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(ghccc);
+ KEYWORD(x86_intrcc);
+ KEYWORD(hhvmcc);
+ KEYWORD(hhvm_ccc);
+ KEYWORD(cxx_fast_tlscc);
KEYWORD(cc);
KEYWORD(c);
- KEYWORD(signext);
- KEYWORD(zeroext);
+ KEYWORD(attributes);
+
+ KEYWORD(alwaysinline);
+ KEYWORD(argmemonly);
+ KEYWORD(builtin);
+ KEYWORD(byval);
+ KEYWORD(inalloca);
+ KEYWORD(cold);
+ KEYWORD(convergent);
+ KEYWORD(dereferenceable);
+ KEYWORD(dereferenceable_or_null);
+ KEYWORD(inaccessiblememonly);
+ KEYWORD(inaccessiblemem_or_argmemonly);
+ KEYWORD(inlinehint);
KEYWORD(inreg);
- KEYWORD(sret);
- KEYWORD(nounwind);
- KEYWORD(noreturn);
+ KEYWORD(jumptable);
+ KEYWORD(minsize);
+ KEYWORD(naked);
+ KEYWORD(nest);
KEYWORD(noalias);
+ KEYWORD(nobuiltin);
KEYWORD(nocapture);
- KEYWORD(byval);
- KEYWORD(nest);
+ KEYWORD(noduplicate);
+ KEYWORD(noimplicitfloat);
+ KEYWORD(noinline);
+ KEYWORD(norecurse);
+ KEYWORD(nonlazybind);
+ KEYWORD(nonnull);
+ KEYWORD(noredzone);
+ KEYWORD(noreturn);
+ KEYWORD(nounwind);
+ KEYWORD(optnone);
+ KEYWORD(optsize);
KEYWORD(readnone);
KEYWORD(readonly);
- KEYWORD(uwtable);
+ KEYWORD(returned);
KEYWORD(returns_twice);
-
- KEYWORD(inlinehint);
- KEYWORD(noinline);
- KEYWORD(alwaysinline);
- KEYWORD(optsize);
+ KEYWORD(signext);
+ KEYWORD(sret);
KEYWORD(ssp);
KEYWORD(sspreq);
- KEYWORD(noredzone);
- KEYWORD(noimplicitfloat);
- KEYWORD(naked);
- KEYWORD(nonlazybind);
- KEYWORD(address_safety);
- KEYWORD(minsize);
+ KEYWORD(sspstrong);
+ KEYWORD(safestack);
+ KEYWORD(sanitize_address);
+ KEYWORD(sanitize_thread);
+ KEYWORD(sanitize_memory);
+ KEYWORD(uwtable);
+ KEYWORD(zeroext);
KEYWORD(type);
KEYWORD(opaque);
+ KEYWORD(comdat);
+
+ // Comdat types
+ KEYWORD(any);
+ KEYWORD(exactmatch);
+ KEYWORD(largest);
+ KEYWORD(noduplicates);
+ KEYWORD(samesize);
+
KEYWORD(eq); KEYWORD(ne); KEYWORD(slt); KEYWORD(sgt); KEYWORD(sle);
KEYWORD(sge); KEYWORD(ult); KEYWORD(ugt); KEYWORD(ule); KEYWORD(uge);
KEYWORD(oeq); KEYWORD(one); KEYWORD(olt); KEYWORD(ogt); KEYWORD(ole);
KEYWORD(x);
KEYWORD(blockaddress);
+ // Metadata types.
+ KEYWORD(distinct);
+
+ // Use-list order directives.
+ KEYWORD(uselistorder);
+ KEYWORD(uselistorder_bb);
+
KEYWORD(personality);
KEYWORD(cleanup);
KEYWORD(catch);
#undef KEYWORD
// Keywords for types.
-#define TYPEKEYWORD(STR, LLVMTY) \
- if (Len == strlen(STR) && !memcmp(StartChar, STR, strlen(STR))) { \
- TyVal = LLVMTY; return lltok::Type; }
+#define TYPEKEYWORD(STR, LLVMTY) \
+ do { \
+ if (Keyword == STR) { \
+ TyVal = LLVMTY; \
+ return lltok::Type; \
+ } \
+ } while (false)
TYPEKEYWORD("void", Type::getVoidTy(Context));
TYPEKEYWORD("half", Type::getHalfTy(Context));
TYPEKEYWORD("float", Type::getFloatTy(Context));
TYPEKEYWORD("label", Type::getLabelTy(Context));
TYPEKEYWORD("metadata", Type::getMetadataTy(Context));
TYPEKEYWORD("x86_mmx", Type::getX86_MMXTy(Context));
+ TYPEKEYWORD("token", Type::getTokenTy(Context));
#undef TYPEKEYWORD
// Keywords for instructions.
-#define INSTKEYWORD(STR, Enum) \
- if (Len == strlen(#STR) && !memcmp(StartChar, #STR, strlen(#STR))) { \
- UIntVal = Instruction::Enum; return lltok::kw_##STR; }
+#define INSTKEYWORD(STR, Enum) \
+ do { \
+ if (Keyword == #STR) { \
+ UIntVal = Instruction::Enum; \
+ return lltok::kw_##STR; \
+ } \
+ } while (false)
INSTKEYWORD(add, Add); INSTKEYWORD(fadd, FAdd);
INSTKEYWORD(sub, Sub); INSTKEYWORD(fsub, FSub);
INSTKEYWORD(inttoptr, IntToPtr);
INSTKEYWORD(ptrtoint, PtrToInt);
INSTKEYWORD(bitcast, BitCast);
+ INSTKEYWORD(addrspacecast, AddrSpaceCast);
INSTKEYWORD(select, Select);
INSTKEYWORD(va_arg, VAArg);
INSTKEYWORD(ret, Ret);
INSTKEYWORD(extractvalue, ExtractValue);
INSTKEYWORD(insertvalue, InsertValue);
INSTKEYWORD(landingpad, LandingPad);
+ INSTKEYWORD(cleanupret, CleanupRet);
+ INSTKEYWORD(catchret, CatchRet);
+ INSTKEYWORD(catchswitch, CatchSwitch);
+ INSTKEYWORD(catchpad, CatchPad);
+ INSTKEYWORD(cleanuppad, CleanupPad);
#undef INSTKEYWORD
+#define DWKEYWORD(TYPE, TOKEN) \
+ do { \
+ if (Keyword.startswith("DW_" #TYPE "_")) { \
+ StrVal.assign(Keyword.begin(), Keyword.end()); \
+ return lltok::TOKEN; \
+ } \
+ } while (false)
+ DWKEYWORD(TAG, DwarfTag);
+ DWKEYWORD(ATE, DwarfAttEncoding);
+ DWKEYWORD(VIRTUALITY, DwarfVirtuality);
+ DWKEYWORD(LANG, DwarfLang);
+ DWKEYWORD(OP, DwarfOp);
+ DWKEYWORD(MACINFO, DwarfMacinfo);
+#undef DWKEYWORD
+
+ if (Keyword.startswith("DIFlag")) {
+ StrVal.assign(Keyword.begin(), Keyword.end());
+ return lltok::DIFlag;
+ }
+
// 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);
+ StringRef HexStr(TokStart + 3, len);
+ if (!std::all_of(HexStr.begin(), HexStr.end(), isxdigit)) {
+ // Bad token, return it as an error.
+ CurPtr = TokStart+3;
+ return lltok::Error;
+ }
+ APInt Tmp(bits, HexStr, 16);
uint32_t activeBits = Tmp.getActiveBits();
if (activeBits > 0 && activeBits < bits)
Tmp = Tmp.trunc(activeBits);
return lltok::Error;
}
-
-/// Lex0x: Handle productions that start with 0x, knowing that it matches and
-/// that this is not a label:
+/// Lex all tokens that start with a 0x prefix, knowing they match and are not
+/// labels.
/// HexFPConstant 0x[0-9A-Fa-f]+
/// HexFP80Constant 0xK[0-9A-Fa-f]+
/// HexFP128Constant 0xL[0-9A-Fa-f]+
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') {
case 'K':
// F80HexFPConstant - x87 long double in hexadecimal format (10 bytes)
FP80HexToIntPair(TokStart+3, CurPtr, Pair);
- APFloatVal = APFloat(APInt(80, Pair));
+ APFloatVal = APFloat(APFloat::x87DoubleExtended, APInt(80, Pair));
return lltok::APFloat;
case 'L':
// F128HexFPConstant - IEEE 128-bit in hexadecimal format (16 bytes)
HexToIntPair(TokStart+3, CurPtr, Pair);
- APFloatVal = APFloat(APInt(128, Pair), true);
+ APFloatVal = APFloat(APFloat::IEEEquad, APInt(128, Pair));
return lltok::APFloat;
case 'M':
// PPC128HexFPConstant - PowerPC 128-bit in hexadecimal format (16 bytes)
HexToIntPair(TokStart+3, CurPtr, Pair);
- APFloatVal = APFloat(APInt(128, Pair));
+ APFloatVal = APFloat(APFloat::PPCDoubleDouble, APInt(128, Pair));
return lltok::APFloat;
case 'H':
- APFloatVal = APFloat(APInt(16,HexIntToVal(TokStart+3, CurPtr)));
+ APFloatVal = APFloat(APFloat::IEEEhalf,
+ APInt(16,HexIntToVal(TokStart+3, CurPtr)));
return lltok::APFloat;
}
}
-/// LexIdentifier: Handle several related productions:
+/// Lex tokens for a label or a numeric constant, possibly starting with -.
/// Label [-a-zA-Z$._0-9]+:
/// NInteger -[0-9]+
/// FPConstant [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
/// 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:".
if (CurPtr[0] != '.') {
if (TokStart[0] == '0' && TokStart[1] == 'x')
return Lex0x();
- unsigned Len = CurPtr-TokStart;
- uint32_t numBits = ((Len * 64) / 19) + 2;
- APInt Tmp(numBits, StringRef(TokStart, Len), 10);
- if (TokStart[0] == '-') {
- uint32_t minBits = Tmp.getMinSignedBits();
- if (minBits > 0 && minBits < numBits)
- Tmp = Tmp.trunc(minBits);
- APSIntVal = APSInt(Tmp, false);
- } else {
- uint32_t activeBits = Tmp.getActiveBits();
- if (activeBits > 0 && activeBits < numBits)
- Tmp = Tmp.trunc(activeBits);
- APSIntVal = APSInt(Tmp, true);
- }
+ APSIntVal = APSInt(StringRef(TokStart, CurPtr - TokStart));
return lltok::APSInt;
}
++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;
}
}
return lltok::APFloat;
}
+/// Lex a floating point constant starting with +.
/// FPConstant [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
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;
}
}
projects / oota-llvm.git / blobdiff