reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
  188
  189
  190
  191
  192
  193
  194
  195
  196
  197
  198
  199
  200
  201
  202
  203
  204
  205
  206
  207
  208
  209
  210
  211
  212
  213
  214
  215
  216
  217
  218
  219
  220
  221
  222
  223
  224
  225
  226
  227
  228
  229
  230
  231
  232
  233
  234
  235
  236
  237
  238
  239
  240
  241
  242
  243
  244
  245
  246
  247
  248
  249
  250
  251
  252
  253
  254
  255
  256
  257
  258
  259
  260
  261
  262
  263
  264
  265
  266
  267
  268
  269
  270
  271
  272
  273
  274
  275
  276
  277
  278
  279
  280
  281
  282
  283
  284
//===--- 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);

/// 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 {
  Preprocessor &PP; // needed for diagnostics

  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,
                       Preprocessor &PP);
  bool hadError : 1;
  bool isUnsigned : 1;
  bool isLong : 1;          // This is *not* set for long long.
  bool isLongLong : 1;
  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
  uint8_t MicrosoftInteger; // Microsoft suffix extension i8, i16, i32, or i64.

  bool isFract : 1;         // 1.0hr/r/lr/uhr/ur/ulr
  bool isAccum : 1;         // 1.0hk/k/lk/uhk/uk/ulk

  bool isFixedPointLiteral() const { return 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);

  /// GetFloatValue - Convert this numeric literal to a floating value, using
  /// the specified APFloat fltSemantics (specifying float, double, etc).
  /// The optional bool isExact (passed-by-reference) has its value
  /// set to true if the returned APFloat can represent the number in the
  /// literal exactly, and false otherwise.
  llvm::APFloat::opStatus GetFloatValue(llvm::APFloat &Result);

  /// 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);

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 {
  uint64_t Value;
  tok::TokenKind Kind;
  bool IsMultiChar;
  bool HadError;
  SmallString<32> UDSuffixBuf;
  unsigned UDSuffixOffset;
public:
  CharLiteralParser(const char *begin, const char *end,
                    SourceLocation Loc, Preprocessor &PP,
                    tok::TokenKind kind);

  bool hadError() const { return HadError; }
  bool isAscii() const { return Kind == tok::char_constant; }
  bool isWide() const { return Kind == tok::wide_char_constant; }
  bool isUTF8() const { return Kind == tok::utf8_char_constant; }
  bool isUTF16() const { return Kind == tok::utf16_char_constant; }
  bool isUTF32() const { return Kind == tok::utf32_char_constant; }
  bool isMultiChar() const { return IsMultiChar; }
  uint64_t getValue() const { return Value; }
  StringRef getUDSuffix() const { return UDSuffixBuf; }
  unsigned getUDSuffixOffset() const {
    assert(!UDSuffixBuf.empty() && "no ud-suffix");
    return UDSuffixOffset;
  }
};

/// StringLiteralParser - This decodes string escape characters and performs
/// wide string analysis and Translation Phase #6 (concatenation of string
/// literals) (C99 5.1.1.2p1).
class StringLiteralParser {
  const SourceManager &SM;
  const LangOptions &Features;
  const TargetInfo &Target;
  DiagnosticsEngine *Diags;

  unsigned MaxTokenLength;
  unsigned SizeBound;
  unsigned CharByteWidth;
  tok::TokenKind Kind;
  SmallString<512> ResultBuf;
  char *ResultPtr; // cursor
  SmallString<32> UDSuffixBuf;
  unsigned UDSuffixToken;
  unsigned UDSuffixOffset;
public:
  StringLiteralParser(ArrayRef<Token> StringToks,
                      Preprocessor &PP, bool Complain = true);
  StringLiteralParser(ArrayRef<Token> StringToks,
                      const SourceManager &sm, const LangOptions &features,
                      const TargetInfo &target,
                      DiagnosticsEngine *diags = nullptr)
    : SM(sm), Features(features), Target(target), Diags(diags),
      MaxTokenLength(0), SizeBound(0), CharByteWidth(0), Kind(tok::unknown),
      ResultPtr(ResultBuf.data()), hadError(false), Pascal(false) {
    init(StringToks);
  }


  bool hadError;
  bool Pascal;

  StringRef GetString() const {
    return StringRef(ResultBuf.data(), GetStringLength());
  }
  unsigned GetStringLength() const { return ResultPtr-ResultBuf.data(); }

  unsigned GetNumStringChars() const {
    return GetStringLength() / CharByteWidth;
  }
  /// getOffsetOfStringByte - This function returns the offset of the
  /// specified byte of the string data represented by Token.  This handles
  /// advancing over escape sequences in the string.
  ///
  /// If the Diagnostics pointer is non-null, then this will do semantic
  /// checking of the string literal and emit errors and warnings.
  unsigned getOffsetOfStringByte(const Token &TheTok, unsigned ByteNo) const;

  bool isAscii() const { return Kind == tok::string_literal; }
  bool isWide() const { return Kind == tok::wide_string_literal; }
  bool isUTF8() const { return Kind == tok::utf8_string_literal; }
  bool isUTF16() const { return Kind == tok::utf16_string_literal; }
  bool isUTF32() const { return Kind == tok::utf32_string_literal; }
  bool isPascal() const { return Pascal; }

  StringRef getUDSuffix() const { return UDSuffixBuf; }

  /// Get the index of a token containing a ud-suffix.
  unsigned getUDSuffixToken() const {
    assert(!UDSuffixBuf.empty() && "no ud-suffix");
    return UDSuffixToken;
  }
  /// Get the spelling offset of the first byte of the ud-suffix.
  unsigned getUDSuffixOffset() const {
    assert(!UDSuffixBuf.empty() && "no ud-suffix");
    return UDSuffixOffset;
  }

  static bool isValidUDSuffix(const LangOptions &LangOpts, StringRef Suffix);

private:
  void init(ArrayRef<Token> StringToks);
  bool CopyStringFragment(const Token &Tok, const char *TokBegin,
                          StringRef Fragment);
  void DiagnoseLexingError(SourceLocation Loc);
};

}  // end namespace clang

#endif