LiteralSupport.h

Go to the documentation of this file.

//===--- LiteralSupport.h ---------------------------------------*- C++ -*-===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file defines the NumericLiteralParser, CharLiteralParser, and
// StringLiteralParser interfaces.
//
//===----------------------------------------------------------------------===//
 
#ifndef LLVM_CLANG_LEX_LITERALSUPPORT_H
#define LLVM_CLANG_LEX_LITERALSUPPORT_H
 
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/LLVM.h"
#include "clang/Basic/TokenKinds.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/DataTypes.h"
 
namespace clang {
 
class DiagnosticsEngine;
class Preprocessor;
class Token;
class SourceLocation;
class TargetInfo;
class SourceManager;
class LangOptions;
 
/// Copy characters from Input to Buf, expanding any UCNs.
void expandUCNs(SmallVectorImpl<char> &Buf, StringRef Input);
 
/// Return true if the token corresponds to a function local predefined macro,
/// which expands to a string literal, that can be concatenated with other
/// string literals (only in Microsoft mode).
bool isFunctionLocalStringLiteralMacro(tok::TokenKind K, const LangOptions &LO);
 
/// Return true if the token is a string literal, or a function local
/// predefined macro, which expands to a string literal.
bool tokenIsLikeStringLiteral(const Token &Tok, const LangOptions &LO);
 
/// NumericLiteralParser - This performs strict semantic analysis of the content
/// of a ppnumber, classifying it as either integer, floating, or erroneous,
/// determines the radix of the value and can convert it to a useful value.
class NumericLiteralParser {
  const SourceManager &SM;
  const LangOptions &LangOpts;
  DiagnosticsEngine &Diags;
 
  const char *const ThisTokBegin;
  const char *const ThisTokEnd;
  const char *DigitsBegin, *SuffixBegin; // markers
  const char *s; // cursor
 
  unsigned radix;
 
  bool saw_exponent, saw_period, saw_ud_suffix, saw_fixed_point_suffix;
 
  SmallString<32> UDSuffixBuf;
 
public:
  NumericLiteralParser(StringRef TokSpelling, SourceLocation TokLoc,
                       const SourceManager &SM, const LangOptions &LangOpts,
                       const TargetInfo &Target, DiagnosticsEngine &Diags);
  bool hadError : 1;
  bool isUnsigned : 1;
  bool isLong : 1;          // This is *not* set for long long.
  bool isLongLong : 1;
  bool isSizeT : 1;         // 1z, 1uz (C++23)
  bool isHalf : 1;          // 1.0h
  bool isFloat : 1;         // 1.0f
  bool isImaginary : 1;     // 1.0i
  bool isFloat16 : 1;       // 1.0f16
  bool isFloat128 : 1;      // 1.0q
  bool isFract : 1;         // 1.0hr/r/lr/uhr/ur/ulr
  bool isAccum : 1;         // 1.0hk/k/lk/uhk/uk/ulk
  bool isBitInt : 1;        // 1wb, 1uwb (C23) or 1__wb, 1__uwb (Clang extension in C++
                            // mode)
  uint8_t MicrosoftInteger; // Microsoft suffix extension i8, i16, i32, or i64.
 
 
  bool isFixedPointLiteral() const {
    return (saw_period || saw_exponent) && saw_fixed_point_suffix;
  }
 
  bool isIntegerLiteral() const {
    return !saw_period && !saw_exponent && !isFixedPointLiteral();
  }
  bool isFloatingLiteral() const {
    return (saw_period || saw_exponent) && !isFixedPointLiteral();
  }
 
  bool hasUDSuffix() const {
    return saw_ud_suffix;
  }
  StringRef getUDSuffix() const {
    assert(saw_ud_suffix);
    return UDSuffixBuf;
  }
  unsigned getUDSuffixOffset() const {
    assert(saw_ud_suffix);
    return SuffixBegin - ThisTokBegin;
  }
 
  static bool isValidUDSuffix(const LangOptions &LangOpts, StringRef Suffix);
 
  unsigned getRadix() const { return radix; }
 
  /// GetIntegerValue - Convert this numeric literal value to an APInt that
  /// matches Val's input width.  If there is an overflow (i.e., if the unsigned
  /// value read is larger than the APInt's bits will hold), set Val to the low
  /// bits of the result and return true.  Otherwise, return false.
  bool GetIntegerValue(llvm::APInt &Val);
 
  /// Convert this numeric literal to a floating value, using the specified
  /// APFloat fltSemantics (specifying float, double, etc) and rounding mode.
  llvm::APFloat::opStatus GetFloatValue(llvm::APFloat &Result,
                                        llvm::RoundingMode RM);
 
  /// GetFixedPointValue - Convert this numeric literal value into a
  /// scaled integer that represents this value. Returns true if an overflow
  /// occurred when calculating the integral part of the scaled integer or
  /// calculating the digit sequence of the exponent.
  bool GetFixedPointValue(llvm::APInt &StoreVal, unsigned Scale);
 
  /// Get the digits that comprise the literal. This excludes any prefix or
  /// suffix associated with the literal.
  StringRef getLiteralDigits() const {
    assert(!hadError && "cannot reliably get the literal digits with an error");
    return StringRef(DigitsBegin, SuffixBegin - DigitsBegin);
  }
 
private:
 
  void ParseNumberStartingWithZero(SourceLocation TokLoc);
  void ParseDecimalOrOctalCommon(SourceLocation TokLoc);
 
  static bool isDigitSeparator(char C) { return C == '\''; }
 
  /// Determine whether the sequence of characters [Start, End) contains
  /// any real digits (not digit separators).
  bool containsDigits(const char *Start, const char *End) {
    return Start != End && (Start + 1 != End || !isDigitSeparator(Start[0]));
  }
 
  enum CheckSeparatorKind { CSK_BeforeDigits, CSK_AfterDigits };
 
  /// Ensure that we don't have a digit separator here.
  void checkSeparator(SourceLocation TokLoc, const char *Pos,
                      CheckSeparatorKind IsAfterDigits);
 
  /// SkipHexDigits - Read and skip over any hex digits, up to End.
  /// Return a pointer to the first non-hex digit or End.
  const char *SkipHexDigits(const char *ptr) {
    while (ptr != ThisTokEnd && (isHexDigit(*ptr) || isDigitSeparator(*ptr)))
      ptr++;
    return ptr;
  }
 
  /// SkipOctalDigits - Read and skip over any octal digits, up to End.
  /// Return a pointer to the first non-hex digit or End.
  const char *SkipOctalDigits(const char *ptr) {
    while (ptr != ThisTokEnd &&
           ((*ptr >= '0' && *ptr <= '7') || isDigitSeparator(*ptr)))
      ptr++;
    return ptr;
  }
 
  /// SkipDigits - Read and skip over any digits, up to End.
  /// Return a pointer to the first non-hex digit or End.
  const char *SkipDigits(const char *ptr) {
    while (ptr != ThisTokEnd && (isDigit(*ptr) || isDigitSeparator(*ptr)))
      ptr++;
    return ptr;
  }
 
  /// SkipBinaryDigits - Read and skip over any binary digits, up to End.
  /// Return a pointer to the first non-binary digit or End.
  const char *SkipBinaryDigits(const char *ptr) {
    while (ptr != ThisTokEnd &&
           (*ptr == '0' || *ptr == '1' || isDigitSeparator(*ptr)))
      ptr++;
    return ptr;
  }
 
};
 
/// CharLiteralParser - Perform interpretation and semantic analysis of a
/// character literal.
class CharLiteralParser {