path: root/lib/Lex/LiteralSupport.cpp

//===--- LiteralSupport.cpp - Code to parse and process literals ----------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the NumericLiteralParser, CharLiteralParser, and
// StringLiteralParser interfaces.
//
//===----------------------------------------------------------------------===//

#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Basic/TargetInfo.h"
#include "llvm/ADT/StringExtras.h"
using namespace clang;

/// HexDigitValue - Return the value of the specified hex digit, or -1 if it's
/// not valid.
static int HexDigitValue(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 -1;
}

static unsigned getCharWidth(tok::TokenKind kind, const TargetInfo &Target) {
  switch (kind) {
  default: assert(0 && "Unknown token type!");
  case tok::char_constant:
  case tok::string_literal:
  case tok::utf8_string_literal:
    return Target.getCharWidth();
  case tok::wide_char_constant:
  case tok::wide_string_literal:
    return Target.getWCharWidth();
  case tok::utf16_char_constant:
  case tok::utf16_string_literal:
    return Target.getChar16Width();
  case tok::utf32_char_constant:
  case tok::utf32_string_literal:
    return Target.getChar32Width();
  }
}

/// ProcessCharEscape - Parse a standard C escape sequence, which can occur in
/// either a character or a string literal.
static unsigned ProcessCharEscape(const char *&ThisTokBuf,
                                  const char *ThisTokEnd, bool &HadError,
                                  FullSourceLoc Loc, unsigned CharWidth,
                                  Diagnostic *Diags) {
  // Skip the '\' char.
  ++ThisTokBuf;

  // We know that this character can't be off the end of the buffer, because
  // that would have been \", which would not have been the end of string.
  unsigned ResultChar = *ThisTokBuf++;
  switch (ResultChar) {
  // These map to themselves.
  case '\\': case '\'': case '"': case '?': break;

    // These have fixed mappings.
  case 'a':
    // TODO: K&R: the meaning of '\\a' is different in traditional C
    ResultChar = 7;
    break;
  case 'b':
    ResultChar = 8;
    break;
  case 'e':
    if (Diags)
      Diags->Report(Loc, diag::ext_nonstandard_escape) << "e";
    ResultChar = 27;
    break;
  case 'E':
    if (Diags)
      Diags->Report(Loc, diag::ext_nonstandard_escape) << "E";
    ResultChar = 27;
    break;
  case 'f':
    ResultChar = 12;
    break;
  case 'n':
    ResultChar = 10;
    break;
  case 'r':
    ResultChar = 13;
    break;
  case 't':
    ResultChar = 9;
    break;
  case 'v':
    ResultChar = 11;
    break;