llvm/llvm/lib/AsmParser/LLLexer.cpp

//===- LLLexer.cpp - Lexer for .ll Files ----------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// Implement the Lexer for .ll files.
//
//===----------------------------------------------------------------------===//

#include "llvm/AsmParser/LLLexer.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/Twine.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/SourceMgr.h"
#include <cassert>
#include <cctype>
#include <cstdio>

usingnamespacellvm;

bool LLLexer::Error(LocTy ErrorLoc, const Twine &Msg) const { … }

void LLLexer::Warning(LocTy WarningLoc, const Twine &Msg) const { … }

//===----------------------------------------------------------------------===//
// Helper functions.
//===----------------------------------------------------------------------===//

// atoull - Convert an ascii string of decimal digits into the unsigned long
// long representation... this does not have to do input error checking,
// because we know that the input will be matched by a suitable regex...
//
uint64_t LLLexer::atoull(const char *Buffer, const char *End) { … }

uint64_t LLLexer::HexIntToVal(const char *Buffer, const char *End) { … }

void LLLexer::HexToIntPair(const char *Buffer, const char *End,
                           uint64_t Pair[2]) { … }

/// FP80HexToIntPair - translate an 80 bit FP80 number (20 hexits) into
/// { low64, high16 } as usual for an APInt.
void LLLexer::FP80HexToIntPair(const char *Buffer, const char *End,
                           uint64_t Pair[2]) { … }

// UnEscapeLexed - Run through the specified buffer and change \xx codes to the
// appropriate character.
static void UnEscapeLexed(std::string &Str) { … }

/// isLabelChar - Return true for [-a-zA-Z$._0-9].
static bool isLabelChar(char C) { … }

/// isLabelTail - Return true if this pointer points to a valid end of a label.
static const char *isLabelTail(const char *CurPtr) { … }

//===----------------------------------------------------------------------===//
// Lexer definition.
//===----------------------------------------------------------------------===//

LLLexer::LLLexer(StringRef StartBuf, SourceMgr &SM, SMDiagnostic &Err,
                 LLVMContext &C)
    : … { … }

int LLLexer::getNextChar() { … }

lltok::Kind LLLexer::LexToken() { … }

void LLLexer::SkipLineComment() { … }

/// 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() { … }

lltok::Kind LLLexer::LexDollar() { … }

/// ReadString - Read a string until the closing quote.
lltok::Kind LLLexer::ReadString(lltok::Kind kind) { … }

/// ReadVarName - Read the rest of a token containing a variable name.
bool LLLexer::ReadVarName() { … }

// Lex an ID: [0-9]+. On success, the ID is stored in UIntVal and Token is
// returned, otherwise the Error token is returned.
lltok::Kind LLLexer::LexUIntID(lltok::Kind Token) { … }

lltok::Kind LLLexer::LexVar(lltok::Kind Var, lltok::Kind VarID) { … }

/// 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() { … }

/// Lex all tokens that start with a " character.
///   QuoteLabel        "[^"]+":
///   StringConstant    "[^"]*"
lltok::Kind LLLexer::LexQuote() { … }

/// Lex all tokens that start with a ! character.
///    !foo
///    !
lltok::Kind LLLexer::LexExclaim() { … }

/// Lex all tokens that start with a ^ character.
///    SummaryID ::= ^[0-9]+
lltok::Kind LLLexer::LexCaret() { … }

/// Lex all tokens that start with a # character.
///    AttrGrpID ::= #[0-9]+
///    Hash ::= #
lltok::Kind LLLexer::LexHash() { … }

/// 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() { … }

/// 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]+
///    HexPPC128Constant 0xM[0-9A-Fa-f]+
///    HexHalfConstant   0xH[0-9A-Fa-f]+
///    HexBFloatConstant 0xR[0-9A-Fa-f]+
lltok::Kind LLLexer::Lex0x() { … }

/// 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]+)?
///    PInteger          [0-9]+
///    HexFPConstant     0x[0-9A-Fa-f]+
///    HexFP80Constant   0xK[0-9A-Fa-f]+
///    HexFP128Constant  0xL[0-9A-Fa-f]+
///    HexPPC128Constant 0xM[0-9A-Fa-f]+
lltok::Kind LLLexer::LexDigitOrNegative() { … }

/// Lex a floating point constant starting with +.
///    FPConstant  [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
lltok::Kind LLLexer::LexPositive() { … }