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

Untracked file

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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
 * Version: NPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Netscape Public License
 * Version 1.1 (the "License"); you may not use this file except in
 * compliance with the License. You may obtain a copy of the License at
 * http://www.mozilla.org/NPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the
 * License.
 *
 * The Original Code is Mozilla Communicator client code.
 *
 * The Initial Developer of the Original Code is 
 * Netscape Communications Corporation.
 * Portions created by the Initial Developer are Copyright (C) 1998
 * the Initial Developer. All Rights Reserved.
 *
 * Contributor(s):
 *
 *
 * Alternatively, the contents of this file may be used under the terms of
 * either the GNU General Public License Version 2 or later (the "GPL"), or
 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
 * in which case the provisions of the GPL or the LGPL are applicable instead
 * of those above. If you wish to allow use of your version of this file only
 * under the terms of either the GPL or the LGPL, and not to allow others to
 * use your version of this file under the terms of the NPL, indicate your
 * decision by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL or the LGPL. If you do not delete
 * the provisions above, a recipient may use your version of this file under
 * the terms of any one of the NPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */

#include "nsUCConstructors.h"
#include "nsUCS2BEToUnicode.h"
#include "nsUCvLatinDll.h"
#include <string.h>
#include "prtypes.h"

// XXX : illegal surrogate code points are just passed through !!
static nsresult
UTF16ConvertToUnicode(PRUint8& aState, PRUint8& aData, const char * aSrc,
                      PRInt32 * aSrcLength, PRUnichar * aDest,
                      PRInt32 * aDestLength)
{
  const char* src = aSrc;
  const char* srcEnd = aSrc + *aSrcLength;
  PRUnichar* dest = aDest;
  PRUnichar* destEnd = aDest + *aDestLength;

  if(2 == aState) // first time called
  {
    NS_ASSERTION(*aSrcLength >= 2, "Too few bytes in input");

    // Eliminate BOM (0xFEFF). Note that different endian case is taken care of
    // in |Convert| of LE and BE converters. Here, we only have to
    // deal with the same endian case. That is, 0xFFFE (byte-swapped BOM) is
    // illegal.
    if(0xFEFF == *((PRUnichar*)src)) {
      src+=2;
    } else if(0xFFFE == *((PRUnichar*)src)) {
      *aSrcLength=0;
      *aDestLength=0;
      return NS_ERROR_ILLEGAL_INPUT;
    }  
    aState=0;
  }

  PRInt32 copybytes;

  if((1 == aState) && (src < srcEnd))
  {
    if(dest >= destEnd)
      goto error;

    char tmpbuf[2];

    // the 1st byte of a 16-bit code unit was stored in |aData| in the previous
    // run while the 2nd byte has to come from |*src|. We just have to copy
    // 'byte-by-byte'. Byte-swapping, if necessary, will be done in |Convert| of
    // LE and BE converters.
    PRUnichar * up = (PRUnichar*) &tmpbuf[0];
    tmpbuf[0]= aData;
    tmpbuf[1]= *src++;
    *dest++ = *up;
  }
  
  copybytes = (destEnd-dest)*2;
  // if |srcEnd-src| is odd, we copy one fewer bytes.
  if(copybytes > (~1 & (srcEnd - src)))
      copybytes = ~1 & (srcEnd - src);
  memcpy(dest,src,copybytes);
  src +=copybytes;
  dest +=(copybytes/2);
  if(srcEnd == src)  { // srcLength was even.
     aState = 0;
  } else if(1 == (srcEnd - src) ) { // srcLength was odd. 
     aState = 1;
     aData  = *src++;  // store the lead byte of a 16-bit unit for the next run.
  } else  {
     goto error;
  }
  
  *aDestLength = dest - aDest;
  *aSrcLength =  src  - aSrc; 
  return NS_OK;

error:
  *aDestLength = dest - aDest;
  *aSrcLength =  src  - aSrc; 
  return  NS_OK_UDEC_MOREOUTPUT;
}

static void
SwapBytes(PRUnichar *aDest, PRInt32 aLen)
{
  for (PRUnichar *p = aDest; aLen > 0; ++p, --aLen)
     *p = ((*p & 0xff) << 8) | ((*p >> 8) & 0xff);
}

NS_IMETHODIMP
nsUTF16ToUnicodeBase::Reset()
{
  mState = 2;
  mData = 0;
  return NS_OK;
}

NS_IMETHODIMP
nsUTF16ToUnicodeBase::GetMaxLength(const char * aSrc, PRInt32 aSrcLength, 
                                   PRInt32 * aDestLength)
{
  // the left-over byte of the previous run has to be taken into account.
  *aDestLength = (aSrcLength + ((1 == mState) ? 1 : 0)) / 2;
  return NS_OK;
}


NS_IMETHODIMP
nsUTF16BEToUnicode::Convert(const char * aSrc, PRInt32 * aSrcLength,
                            PRUnichar * aDest, PRInt32 * aDestLength)
{
#ifdef IS_LITTLE_ENDIAN
    // Remove the BOM if we're little-endian. The 'same endian' case with the
    // leading BOM will be taken care of by |UTF16ConvertToUnicode|.
    if(2 == mState) // Called for the first time.
    {
      NS_ASSERTION(*aSrcLength >= 2, "Too few bytes in input");
      if(0xFFFE == *((PRUnichar*)aSrc)) {
        // eliminate BOM (on LE machines, BE BOM is 0xFFFE)
        aSrc+=2;
        *aSrcLength-=2;
      } else if(0xFEFF == *((PRUnichar*)aSrc)) {
        *aSrcLength=0;
        *aDestLength=0;
        return NS_ERROR_ILLEGAL_INPUT;
      }  
      mState=0;
    }
#endif

  nsresult rv = UTF16ConvertToUnicode(mState, mData, aSrc, aSrcLength,
                                      aDest, aDestLength);

#ifdef IS_LITTLE_ENDIAN
  SwapBytes(aDest, *aDestLength);
#endif
  return rv;
}

NS_IMETHODIMP
nsUTF16LEToUnicode::Convert(const char * aSrc, PRInt32 * aSrcLength,
                            PRUnichar * aDest, PRInt32 * aDestLength)
{
#ifdef IS_BIG_ENDIAN
    // Remove the BOM if we're big-endian. The 'same endian' case with the
    // leading BOM will be taken care of by |UTF16ConvertToUnicode|.
    if(2 == mState) // first time called
    {
      NS_ASSERTION(*aSrcLength >= 2, "Too few bytes in input");
      if(0xFFFE == *((PRUnichar*)aSrc)) {
        // eliminate BOM (on BE machines, LE BOM is 0xFFFE)
        aSrc+=2;
        *aSrcLength-=2;
      } else if(0xFEFF == *((PRUnichar*)aSrc)) {
        *aSrcLength=0;
        *aDestLength=0;
        return NS_ERROR_ILLEGAL_INPUT;
      }  
      mState=0;
    }
#endif
    
  nsresult rv = UTF16ConvertToUnicode(mState, mData, aSrc, aSrcLength, aDest,
                                      aDestLength);

#ifdef IS_BIG_ENDIAN
  SwapBytes(aDest, *aDestLength);
#endif
  return rv;
}

NS_IMETHODIMP
nsUTF16ToUnicode::Reset()
{
  mEndian = kUnknown;
  mFoundBOM = PR_FALSE;
  return nsUTF16ToUnicodeBase::Reset();
}

NS_IMETHODIMP
nsUTF16ToUnicode::Convert(const char * aSrc, PRInt32 * aSrcLength,
                          PRUnichar * aDest, PRInt32 * aDestLength)
{
    if(2 == mState) // first time called
    {
      NS_ASSERTION(*aSrcLength >= 2, "Too few bytes in input");

      // check if BOM (0xFEFF) is at the beginning, remove it if found, and
      // set mEndian accordingly.
      if(0xFF == PRUint8(aSrc[0]) && 0xFE == PRUint8(aSrc[1])) {
        aSrc += 2;
        *aSrcLength -= 2;
        mState = 0;
        mEndian = kLittleEndian;
        mFoundBOM = PR_TRUE;
      }
      else if(0xFE == PRUint8(aSrc[0]) && 0xFF == PRUint8(aSrc[1])) {
        aSrc += 2;
        *aSrcLength -= 2;
        mState = 0;
        mEndian = kBigEndian;
        mFoundBOM = PR_TRUE;
      }
      // BOM is not found, but we can use a simple heuristic to determine
      // the endianness. Assume the first character is [U+0001, U+00FF].
      // Not always valid, but it's very likely to hold for html/xml/css. 
      else if(!aSrc[0] && aSrc[1]) {  // 0x00 0xhh (hh != 00)
        mState = 0;                   
        mEndian = kBigEndian;
      }
      else if(aSrc[0] && !aSrc[1]) {  // 0xhh 0x00 (hh != 00)
        mState = 0;
        mEndian = kLittleEndian;
      }
      else { // Neither BOM nor 'plausible' byte patterns at the beginning.
             // Just assume it's BE (per Unicode standard)
             // and let the garbage show up in the browser. (security concern?)
             // (bug 246194)
        mState = 0;   
        mEndian = kBigEndian;
      }
    }
    
    nsresult rv = UTF16ConvertToUnicode(mState, mData, aSrc, aSrcLength, aDest,
                                        aDestLength);

#ifdef IS_BIG_ENDIAN
    if (mEndian == kLittleEndian)
#elif defined(IS_LITTLE_ENDIAN)
    if (mEndian == kBigEndian)
#else
    #error "Unknown endianness"
#endif
      SwapBytes(aDest, *aDestLength);

    // If BOM is not found and we're to return NS_OK, signal that BOM
    // is not found. Otherwise, return |rv| from |UTF16ConvertToUnicode|
    return (rv == NS_OK && !mFoundBOM) ? NS_OK_UDEC_NOBOMFOUND : rv;
}