#include "llvm/MC/MCParser/AsmLexer.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/SMLoc.h"
#include <cctype>
#include <cerrno>
#include <cstdio>
#include <cstdlib>
using namespace llvm;
AsmLexer::AsmLexer(const MCAsmInfo &MAI) : MAI(MAI) {
CurPtr = nullptr;
isAtStartOfLine = true;
AllowAtInIdentifier = !StringRef(MAI.getCommentString()).startswith("@");
}
AsmLexer::~AsmLexer() {
}
void AsmLexer::setBuffer(StringRef Buf, const char *ptr) {
CurBuf = Buf;
if (ptr)
CurPtr = ptr;
else
CurPtr = CurBuf.begin();
TokStart = nullptr;
}
AsmToken AsmLexer::ReturnError(const char *Loc, const std::string &Msg) {
SetError(SMLoc::getFromPointer(Loc), Msg);
return AsmToken(AsmToken::Error, StringRef(Loc, 0));
}
int AsmLexer::getNextChar() {
char CurChar = *CurPtr++;
switch (CurChar) {
default:
return (unsigned char)CurChar;
case 0:
if (CurPtr - 1 != CurBuf.end())
return 0;
--CurPtr; return EOF;
}
}
AsmToken AsmLexer::LexFloatLiteral() {
while (isdigit(*CurPtr))
++CurPtr;
if (*CurPtr == 'e' || *CurPtr == 'E') {
++CurPtr;
if (*CurPtr == '-' || *CurPtr == '+')
++CurPtr;
while (isdigit(*CurPtr))
++CurPtr;
}
return AsmToken(AsmToken::Real,
StringRef(TokStart, CurPtr - TokStart));
}
AsmToken AsmLexer::LexHexFloatLiteral(bool NoIntDigits) {
assert((*CurPtr == 'p' || *CurPtr == 'P' || *CurPtr == '.') &&
"unexpected parse state in floating hex");
bool NoFracDigits = true;
if (*CurPtr == '.') {
++CurPtr;
const char *FracStart = CurPtr;
while (isxdigit(*CurPtr))
++CurPtr;
NoFracDigits = CurPtr == FracStart;
}
if (NoIntDigits && NoFracDigits)
return ReturnError(TokStart, "invalid hexadecimal floating-point constant: "
"expected at least one significand digit");
if (*CurPtr != 'p' && *CurPtr != 'P')
return ReturnError(TokStart, "invalid hexadecimal floating-point constant: "
"expected exponent part 'p'");
++CurPtr;
if (*CurPtr == '+' || *CurPtr == '-')
++CurPtr;
const char *ExpStart = CurPtr;
while (isdigit(*CurPtr))
++CurPtr;
if (CurPtr == ExpStart)
return ReturnError(TokStart, "invalid hexadecimal floating-point constant: "
"expected at least one exponent digit");
return AsmToken(AsmToken::Real, StringRef(TokStart, CurPtr - TokStart));
}
static bool IsIdentifierChar(char c, bool AllowAt) {
return isalnum(c) || c == '_' || c == '$' || c == '.' ||
(c == '@' && AllowAt) || c == '?';
}
AsmToken AsmLexer::LexIdentifier() {
if (CurPtr[-1] == '.' && isdigit(*CurPtr)) {
while (isdigit(*CurPtr))
++CurPtr;
if (*CurPtr == 'e' || *CurPtr == 'E' ||
!IsIdentifierChar(*CurPtr, AllowAtInIdentifier))
return LexFloatLiteral();
}
while (IsIdentifierChar(*CurPtr, AllowAtInIdentifier))
++CurPtr;
if (CurPtr == TokStart+1 && TokStart[0] == '.')
return AsmToken(AsmToken::Dot, StringRef(TokStart, 1));
return AsmToken(AsmToken::Identifier, StringRef(TokStart, CurPtr - TokStart));
}
AsmToken AsmLexer::LexSlash() {
switch (*CurPtr) {
case '*': break; case '/': return ++CurPtr, LexLineComment();
default: return AsmToken(AsmToken::Slash, StringRef(CurPtr-1, 1));
}
++CurPtr; while (1) {
int CurChar = getNextChar();
switch (CurChar) {
case EOF:
return ReturnError(TokStart, "unterminated comment");
case '*':
if (CurPtr[0] != '/') break;
++CurPtr; return LexToken();
}
}
}
AsmToken AsmLexer::LexLineComment() {
int CurChar = getNextChar();
while (CurChar != '\n' && CurChar != '\r' && CurChar != EOF)
CurChar = getNextChar();
if (CurChar == EOF)
return AsmToken(AsmToken::Eof, StringRef(TokStart, 0));
return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 0));
}
static void SkipIgnoredIntegerSuffix(const char *&CurPtr) {
if (CurPtr[0] == 'U')
++CurPtr;
if (CurPtr[0] == 'L')
++CurPtr;
if (CurPtr[0] == 'L')
++CurPtr;
}
static unsigned doLookAhead(const char *&CurPtr, unsigned DefaultRadix) {
const char *FirstHex = nullptr;
const char *LookAhead = CurPtr;
while (1) {
if (isdigit(*LookAhead)) {
++LookAhead;
} else if (isxdigit(*LookAhead)) {
if (!FirstHex)
FirstHex = LookAhead;
++LookAhead;
} else {
break;
}
}
bool isHex = *LookAhead == 'h' || *LookAhead == 'H';
CurPtr = isHex || !FirstHex ? LookAhead : FirstHex;
if (isHex)
return 16;
return DefaultRadix;
}
static AsmToken intToken(StringRef Ref, APInt &Value)
{
if (Value.isIntN(64))
return AsmToken(AsmToken::Integer, Ref, Value);
return AsmToken(AsmToken::BigNum, Ref, Value);
}
AsmToken AsmLexer::LexDigit() {
if (CurPtr[-1] != '0' || CurPtr[0] == '.') {
unsigned Radix = doLookAhead(CurPtr, 10);
bool isHex = Radix == 16;
if (!isHex && (*CurPtr == '.' || *CurPtr == 'e')) {
++CurPtr;
return LexFloatLiteral();
}
StringRef Result(TokStart, CurPtr - TokStart);
APInt Value(128, 0, true);
if (Result.getAsInteger(Radix, Value))
return ReturnError(TokStart, !isHex ? "invalid decimal number" :
"invalid hexdecimal number");
if (Radix == 2 || Radix == 16)
++CurPtr;
SkipIgnoredIntegerSuffix(CurPtr);
return intToken(Result, Value);
}
if (*CurPtr == 'b') {
++CurPtr;
if (!isdigit(CurPtr[0])) {
--CurPtr;
StringRef Result(TokStart, CurPtr - TokStart);
return AsmToken(AsmToken::Integer, Result, 0);
}
const char *NumStart = CurPtr;
while (CurPtr[0] == '0' || CurPtr[0] == '1')
++CurPtr;
if (CurPtr == NumStart)
return ReturnError(TokStart, "invalid binary number");
StringRef Result(TokStart, CurPtr - TokStart);
APInt Value(128, 0, true);
if (Result.substr(2).getAsInteger(2, Value))
return ReturnError(TokStart, "invalid binary number");
SkipIgnoredIntegerSuffix(CurPtr);
return intToken(Result, Value);
}
if (*CurPtr == 'x') {
++CurPtr;
const char *NumStart = CurPtr;
while (isxdigit(CurPtr[0]))
++CurPtr;
if (CurPtr[0] == '.' || CurPtr[0] == 'p' || CurPtr[0] == 'P')
return LexHexFloatLiteral(NumStart == CurPtr);
if (CurPtr == NumStart)
return ReturnError(CurPtr-2, "invalid hexadecimal number");
APInt Result(128, 0);
if (StringRef(TokStart, CurPtr - TokStart).getAsInteger(0, Result))
return ReturnError(TokStart, "invalid hexadecimal number");
if (*CurPtr == 'h' || *CurPtr == 'H')
++CurPtr;
SkipIgnoredIntegerSuffix(CurPtr);
return intToken(StringRef(TokStart, CurPtr - TokStart), Result);
}
APInt Value(128, 0, true);
unsigned Radix = doLookAhead(CurPtr, 8);
bool isHex = Radix == 16;
StringRef Result(TokStart, CurPtr - TokStart);
if (Result.getAsInteger(Radix, Value))
return ReturnError(TokStart, !isHex ? "invalid octal number" :
"invalid hexdecimal number");
if (Radix == 16)
++CurPtr;
SkipIgnoredIntegerSuffix(CurPtr);
return intToken(Result, Value);
}
AsmToken AsmLexer::LexSingleQuote() {
int CurChar = getNextChar();
if (CurChar == '\\')
CurChar = getNextChar();
if (CurChar == EOF)
return ReturnError(TokStart, "unterminated single quote");
CurChar = getNextChar();
if (CurChar != '\'')
return ReturnError(TokStart, "single quote way too long");
StringRef Res = StringRef(TokStart,CurPtr - TokStart);
long long Value;
if (Res.startswith("\'\\")) {
char theChar = Res[2];
switch (theChar) {
default: Value = theChar; break;
case '\'': Value = '\''; break;
case 't': Value = '\t'; break;
case 'n': Value = '\n'; break;
case 'b': Value = '\b'; break;
}
} else
Value = TokStart[1];
return AsmToken(AsmToken::Integer, Res, Value);
}
AsmToken AsmLexer::LexQuote() {
int CurChar = getNextChar();
while (CurChar != '"') {
if (CurChar == '\\') {
CurChar = getNextChar();
}
if (CurChar == EOF)
return ReturnError(TokStart, "unterminated string constant");
CurChar = getNextChar();
}
return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart));
}
StringRef AsmLexer::LexUntilEndOfStatement() {
TokStart = CurPtr;
while (!isAtStartOfComment(CurPtr) && !isAtStatementSeparator(CurPtr) && *CurPtr != '\n' && *CurPtr != '\r' &&
(*CurPtr != 0 || CurPtr != CurBuf.end())) {
++CurPtr;
}
return StringRef(TokStart, CurPtr-TokStart);
}
StringRef AsmLexer::LexUntilEndOfLine() {
TokStart = CurPtr;
while (*CurPtr != '\n' && *CurPtr != '\r' &&
(*CurPtr != 0 || CurPtr != CurBuf.end())) {
++CurPtr;
}
return StringRef(TokStart, CurPtr-TokStart);
}
size_t AsmLexer::peekTokens(MutableArrayRef<AsmToken> Buf,
bool ShouldSkipSpace) {
const char *SavedTokStart = TokStart;
const char *SavedCurPtr = CurPtr;
bool SavedAtStartOfLine = isAtStartOfLine;
bool SavedSkipSpace = SkipSpace;
std::string SavedErr = getErr();
SMLoc SavedErrLoc = getErrLoc();
SkipSpace = ShouldSkipSpace;
size_t ReadCount;
for (ReadCount = 0; ReadCount < Buf.size(); ++ReadCount) {
AsmToken Token = LexToken();
Buf[ReadCount] = Token;
if (Token.is(AsmToken::Eof))
break;
}
SetError(SavedErrLoc, SavedErr);
SkipSpace = SavedSkipSpace;
isAtStartOfLine = SavedAtStartOfLine;
CurPtr = SavedCurPtr;
TokStart = SavedTokStart;
return ReadCount;
}
bool AsmLexer::isAtStartOfComment(const char *Ptr) {
const char *CommentString = MAI.getCommentString();
if (CommentString[1] == '\0')
return CommentString[0] == Ptr[0];
if (CommentString[1] == '#')
return CommentString[0] == Ptr[0];
return strncmp(Ptr, CommentString, strlen(CommentString)) == 0;
}
bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
return strncmp(Ptr, MAI.getSeparatorString(),
strlen(MAI.getSeparatorString())) == 0;
}
AsmToken AsmLexer::LexToken() {
TokStart = CurPtr;
int CurChar = getNextChar();
if (isAtStartOfComment(TokStart)) {
if (CurChar == '#' && isAtStartOfLine)
return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
isAtStartOfLine = true;
return LexLineComment();
}
if (isAtStatementSeparator(TokStart)) {
CurPtr += strlen(MAI.getSeparatorString()) - 1;
return AsmToken(AsmToken::EndOfStatement,
StringRef(TokStart, strlen(MAI.getSeparatorString())));
}
if (CurChar == EOF && !isAtStartOfLine) {
isAtStartOfLine = true;
return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
}
isAtStartOfLine = false;
switch (CurChar) {
default:
if (isalpha(CurChar) || CurChar == '_' || CurChar == '.')
return LexIdentifier();
return ReturnError(TokStart, "invalid character in input");
case EOF: return AsmToken(AsmToken::Eof, StringRef(TokStart, 0));
case 0:
case ' ':
case '\t':
if (SkipSpace) {
return LexToken();
} else {
int len = 1;
while (*CurPtr==' ' || *CurPtr=='\t') {
CurPtr++;
len++;
}
return AsmToken(AsmToken::Space, StringRef(TokStart, len));
}
case '\n': case '\r':
isAtStartOfLine = true;
return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1));
case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1));
case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1));
case '~': return AsmToken(AsmToken::Tilde, StringRef(TokStart, 1));
case '(': return AsmToken(AsmToken::LParen, StringRef(TokStart, 1));
case ')': return AsmToken(AsmToken::RParen, StringRef(TokStart, 1));
case '[': return AsmToken(AsmToken::LBrac, StringRef(TokStart, 1));
case ']': return AsmToken(AsmToken::RBrac, StringRef(TokStart, 1));
case '{': return AsmToken(AsmToken::LCurly, StringRef(TokStart, 1));
case '}': return AsmToken(AsmToken::RCurly, StringRef(TokStart, 1));
case '*': return AsmToken(AsmToken::Star, StringRef(TokStart, 1));
case ',': return AsmToken(AsmToken::Comma, StringRef(TokStart, 1));
case '$': return AsmToken(AsmToken::Dollar, StringRef(TokStart, 1));
case '@': return AsmToken(AsmToken::At, StringRef(TokStart, 1));
case '\\': return AsmToken(AsmToken::BackSlash, StringRef(TokStart, 1));
case '=':
if (*CurPtr == '=')
return ++CurPtr, AsmToken(AsmToken::EqualEqual, StringRef(TokStart, 2));
return AsmToken(AsmToken::Equal, StringRef(TokStart, 1));
case '|':
if (*CurPtr == '|')
return ++CurPtr, AsmToken(AsmToken::PipePipe, StringRef(TokStart, 2));
return AsmToken(AsmToken::Pipe, StringRef(TokStart, 1));
case '^': return AsmToken(AsmToken::Caret, StringRef(TokStart, 1));
case '&':
if (*CurPtr == '&')
return ++CurPtr, AsmToken(AsmToken::AmpAmp, StringRef(TokStart, 2));
return AsmToken(AsmToken::Amp, StringRef(TokStart, 1));
case '!':
if (*CurPtr == '=')
return ++CurPtr, AsmToken(AsmToken::ExclaimEqual, StringRef(TokStart, 2));
return AsmToken(AsmToken::Exclaim, StringRef(TokStart, 1));
case '%': return AsmToken(AsmToken::Percent, StringRef(TokStart, 1));
case '/': return LexSlash();
case '#': return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
case '\'': return LexSingleQuote();
case '"': return LexQuote();
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
return LexDigit();
case '<':
switch (*CurPtr) {
case '<': return ++CurPtr, AsmToken(AsmToken::LessLess,
StringRef(TokStart, 2));
case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual,
StringRef(TokStart, 2));
case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater,
StringRef(TokStart, 2));
default: return AsmToken(AsmToken::Less, StringRef(TokStart, 1));
}
case '>':
switch (*CurPtr) {
case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater,
StringRef(TokStart, 2));
case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual,
StringRef(TokStart, 2));
default: return AsmToken(AsmToken::Greater, StringRef(TokStart, 1));
}
}
}