DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (dcc6d7a0dc00)

VCS Links

Line Code
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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

//----------------------------------------------------------------------
// Global functions and data [declaration]
#include "nsUnicodeToUTF8.h"
#include "mozilla/CheckedInt.h"

NS_IMPL_ISUPPORTS(nsUnicodeToUTF8, nsIUnicodeEncoder)

//----------------------------------------------------------------------
// nsUnicodeToUTF8 class [implementation]

NS_IMETHODIMP nsUnicodeToUTF8::GetMaxLength(const char16_t* aSrc,
                                            int32_t aSrcLength,
                                            int32_t* aDestLength)
{
  MOZ_ASSERT(aDestLength);

  // aSrc is interpreted as UTF16, 3 is normally enough.
  // But when previous buffer only contains part of the surrogate pair, we
  // need to complete it here. If the first word in following buffer is not
  // in valid surrogate range, we need to convert the remaining of last buffer
  // to 3 bytes.
  mozilla::CheckedInt32 length = aSrcLength;
  length *= 3;
  length += 3;

  if (!length.isValid()) {
    return NS_ERROR_OUT_OF_MEMORY;
  }

  *aDestLength = length.value();
  return NS_OK;
}

NS_IMETHODIMP nsUnicodeToUTF8::Convert(const char16_t* aSrc,
                                       int32_t* aSrcLength,
                                       char* aDest,
                                       int32_t* aDestLength)
{
  const char16_t* src = aSrc;
  const char16_t* srcEnd = aSrc + *aSrcLength;
  char* dest = aDest;
  int32_t destLen = *aDestLength;
  uint32_t n;

  //complete remaining of last conversion
  if (mHighSurrogate) {
    if (src < srcEnd) {
      *aDestLength = 0;
      return NS_OK_UENC_MOREINPUT;
    }
    if (*aDestLength < 4) {
      *aSrcLength = 0;
      *aDestLength = 0;
      return NS_OK_UENC_MOREOUTPUT;
    }
    if (*src < (char16_t)0xdc00 || *src > (char16_t)0xdfff) { //not a pair
      *dest++ = (char)0xef; //replacement character
      *dest++ = (char)0xbf;
      *dest++ = (char)0xbd;
      destLen -= 3;
    } else { 
      n = ((mHighSurrogate - (char16_t)0xd800) << 10) + 
              (*src - (char16_t)0xdc00) + 0x10000;
      *dest++ = (char)0xf0 | (n >> 18);
      *dest++ = (char)0x80 | ((n >> 12) & 0x3f);
      *dest++ = (char)0x80 | ((n >> 6) & 0x3f);
      *dest++ = (char)0x80 | (n & 0x3f);
      ++src;
      destLen -= 4;
    }
    mHighSurrogate = 0;
  }

  while (src < srcEnd) {
    if ( *src <= 0x007f) {
      if (destLen < 1)
        goto error_more_output;
      *dest++ = (char)*src;
      --destLen;
    } else if (*src <= 0x07ff) {
      if (destLen < 2)
        goto error_more_output;
      *dest++ = (char)0xc0 | (*src >> 6);
      *dest++ = (char)0x80 | (*src & 0x003f);
      destLen -= 2;
    } else if (*src >= (char16_t)0xd800 && *src <= (char16_t)0xdfff) {
      if (*src >= (char16_t)0xdc00) { //not a pair
        if (destLen < 3)
          goto error_more_output;
        *dest++ = (char)0xef; //replacement character
        *dest++ = (char)0xbf;
        *dest++ = (char)0xbd;
        destLen -= 3;
        ++src;
        continue;
      }
      if ((src+1) >= srcEnd) {
        //we need another surrogate to complete this unicode char
        mHighSurrogate = *src;
        *aDestLength = dest - aDest;
        return NS_OK_UENC_MOREINPUT;
      }
      //handle surrogate
      if (destLen < 4)
        goto error_more_output;
      if (*(src+1) < (char16_t)0xdc00 || *(src+1) > 0xdfff) { //not a pair
        *dest++ = (char)0xef; //replacement character
        *dest++ = (char)0xbf;
        *dest++ = (char)0xbd;
        destLen -= 3;
      } else {
        n = ((*src - (char16_t)0xd800) << 10) + (*(src+1) - (char16_t)0xdc00) + (uint32_t)0x10000;
        *dest++ = (char)0xf0 | (n >> 18);
        *dest++ = (char)0x80 | ((n >> 12) & 0x3f);
        *dest++ = (char)0x80 | ((n >> 6) & 0x3f);
        *dest++ = (char)0x80 | (n & 0x3f);
        destLen -= 4;
        ++src;
      }
    } else { 
      if (destLen < 3)
        goto error_more_output;
      //treat rest of the character as BMP
      *dest++ = (char)0xe0 | (*src >> 12);
      *dest++ = (char)0x80 | ((*src >> 6) & 0x003f);
      *dest++ = (char)0x80 | (*src & 0x003f);
      destLen -= 3;
    }
    ++src;
  }

  *aDestLength = dest - aDest;
  return NS_OK;

error_more_output:
  *aSrcLength = src - aSrc;
  *aDestLength = dest - aDest;
  return NS_OK_UENC_MOREOUTPUT;
}

NS_IMETHODIMP nsUnicodeToUTF8::Finish(char * aDest, int32_t * aDestLength)
{
  char * dest = aDest;

  if (mHighSurrogate) {
    if (*aDestLength < 3) {
      *aDestLength = 0;
      return NS_OK_UENC_MOREOUTPUT;
    }
    *dest++ = (char)0xef; //replacement character
    *dest++ = (char)0xbf;
    *dest++ = (char)0xbd;
    mHighSurrogate = 0;
    *aDestLength = 3;
    return NS_OK;
  } 

  *aDestLength  = 0;
  return NS_OK;
}