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;
}

/// 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,
                                  SourceLocation Loc, bool IsWide,
                                  Preprocessor &PP) {
  // 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':
    PP.Diag(Loc, diag::ext_nonstandard_escape) << "e";
    ResultChar = 27;
    break;
  case 'E':
    PP.Diag(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;
  case 'x': { // Hex escape.
    ResultChar = 0;
    if (ThisTokBuf == ThisTokEnd || !isxdigit(*ThisTokBuf)) {
      PP.Diag(Loc, diag::err_hex_escape_no_digits);
      HadError = 1;
      break;
    }
    
    // Hex escapes are a maximal series of hex digits.
    bool Overflow = false;
    for (; ThisTokBuf != ThisTokEnd; ++ThisTokBuf) {
      int CharVal = HexDigitValue(ThisTokBuf[0]);
      if (CharVal == -1) break;
      // About to shift out a digit?
      Overflow |= (ResultChar & 0xF0000000) ? true : false;
      ResultChar <<= 4;
      ResultChar |= CharVal;
    }

    // See if any bits will be truncated when evaluated as a character.
    unsigned CharWidth = PP.getTargetInfo().getCharWidth(IsWide);
                       
    if (CharWidth != 32 && (ResultChar >> CharWidth) != 0) {
      Overflow = true;
      ResultChar &= ~0U >> (32-CharWidth);
    }
    
    // Check for overflow.
    if (Overflow)   // Too many digits to fit in
      PP.Diag(Loc, diag::warn_hex_escape_too_large);
    break;
  }
  case '0': case '1': case '2': case '3':
  case '4': case '5': case '6': case '7': {
    // Octal escapes.
    --ThisTokBuf;
    ResultChar = 0;

    // Octal escapes are a series of octal digits with maximum length 3.
    // "\0123" is a two digit sequence equal to "\012" "3".
    unsigned NumDigits = 0;
    do {
      ResultChar <<= 3;
      ResultChar |= *ThisTokBuf++ - '0';
      ++NumDigits;
    } while (ThisTokBuf != ThisTokEnd && NumDigits < 3 &&
             ThisTokBuf[0] >= '0' && ThisTokBuf[0] <= '7');
    
    // Check for overflow.  Reject '\777', but not L'\777'.
    unsigned CharWidth = PP.getTargetInfo().getCharWidth(IsWide);
                       
    if (CharWidth != 32 && (ResultChar >> CharWidth) != 0) {
      PP.Diag(Loc, diag::warn_octal_escape_too_large);
      ResultChar &= ~0U >> (32-CharWidth);
    }
    break;
  }
    
    // Otherwise, these are not valid escapes.
  case '(': case '{':