intl/uconv/ucvlatin/nsUnicodeToUTF32.cpp

   1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* vim:expandtab:shiftwidth=2:tabstop=2:
   3  */
   4 /* ***** BEGIN LICENSE BLOCK *****
   5  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   6  *
   7  * The contents of this file are subject to the Mozilla Public License Version
   8  * 1.1 (the "License"); you may not use this file except in compliance with
   9  * the License. You may obtain a copy of the License at
  10  * http://www.mozilla.org/MPL/
  11  *
  12  * Software distributed under the License is distributed on an "AS IS" basis,
  13  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  14  * for the specific language governing rights and limitations under the
  15  * License.
  16  *
  17  * The Original Code is Mozilla Communicator client code.
  18  *
  19  * The Initial Developer of the Original Code is
  20  * Netscape Communications Corporation.
  21  * Portions created by the Initial Developer are Copyright (C) 1998
  22  * the Initial Developer. All Rights Reserved.
  23  *
  24  * Contributor(s):
  25  *   Jungshik Shin <jshin@mailaps.org>
  26  *
  27  * Alternatively, the contents of this file may be used under the terms of
  28  * either of the GNU General Public License Version 2 or later (the "GPL"),
  29  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  30  * in which case the provisions of the GPL or the LGPL are applicable instead
  31  * of those above. If you wish to allow use of your version of this file only
  32  * under the terms of either the GPL or the LGPL, and not to allow others to
  33  * use your version of this file under the terms of the MPL, indicate your
  34  * decision by deleting the provisions above and replace them with the notice
  35  * and other provisions required by the GPL or the LGPL. If you do not delete
  36  * the provisions above, a recipient may use your version of this file under
  37  * the terms of any one of the MPL, the GPL or the LGPL.
  38  *
  39  * ***** END LICENSE BLOCK ***** */
  40
  41 #include <string.h>
  42 #include "nsUCSupport.h"
  43 #include "nsUnicodeToUTF32.h"
  44
  45 #ifdef IS_BIG_ENDIAN
  46 #define UCS4_TO_LE_STRING(u, s)           \
  47   PR_BEGIN_MACRO                          \
  48     s[3] = PRUint8(((u) >> 24) & 0xffL);  \
  49     s[2] = PRUint8(((u) >> 16) & 0xffL);  \
  50     s[1] = PRUint8(((u) >> 8) & 0xffL);   \
  51     s[0] = PRUint8((u) & 0xffL);          \
  52   PR_END_MACRO
  53 #else
  54 #define UCS4_TO_LE_STRING(u, s)           \
  55   PR_BEGIN_MACRO                          \
  56     *((PRUint32*)(s)) = (u);              \
  57   PR_END_MACRO
  58 #endif
  59
  60 #ifdef IS_BIG_ENDIAN
  61 #define UCS4_TO_BE_STRING(u, s)           \
  62   PR_BEGIN_MACRO                          \
  63     *((PRUint32*)(s)) = (u);              \
  64   PR_END_MACRO
  65 #else
  66 #define UCS4_TO_BE_STRING(u, s)           \
  67   PR_BEGIN_MACRO                          \
  68     s[0] = PRUint8(((u) >> 24) & 0xffL);  \
  69     s[1] = PRUint8(((u) >> 16) & 0xffL);  \
  70     s[2] = PRUint8(((u) >> 8) & 0xffL);   \
  71     s[3] = PRUint8((u) & 0xffL);          \
  72   PR_END_MACRO
  73 #endif
  74
  75 //----------------------------------------------------------------------
  76 // Static functions common to nsUnicodeToUTF32LE and nsUnicodeToUTF32BE
  77
  78 static nsresult ConvertCommon(const PRUnichar * aSrc,
  79                               PRInt32 * aSrcLength,
  80                               char * aDest,
  81                               PRInt32 * aDestLength,
  82                               PRUnichar * aHighSurrogate,
  83                               PRBool aIsLE)
  84 {
  85   const PRUnichar * src = aSrc;
  86   const PRUnichar * srcEnd = aSrc + *aSrcLength;
  87   char * dest = aDest;
  88   const char * destEnd = aDest + *aDestLength;
  89   PRUint32 ucs4;
  90
  91
  92   // left-over high surroage code point from the prev. run.
  93   if (*aHighSurrogate)
  94   {
  95     if (! *aSrcLength)
  96     {
  97       *aDestLength = 0;
  98       return NS_OK_UENC_MOREINPUT;
  99     }
 100     if (*aDestLength < 4)
 101     {
 102       *aSrcLength = 0;
 103       *aDestLength = 0;
 104       return NS_OK_UENC_MOREOUTPUT;
 105     }
 106     if ((*src & 0xfc00) != 0xdc00) // Not a low surrogate codepoint. Unpaird.
 107       ucs4 = PRUint32(*aHighSurrogate);
 108     else
 109       ucs4 = (((*aHighSurrogate & 0x3ffL) << 10) | (*src & 0x3ffL)) + 0x10000;
 110
 111     ++src;
 112     if (aIsLE)
 113       UCS4_TO_LE_STRING(ucs4, dest);
 114     else
 115       UCS4_TO_BE_STRING(ucs4, dest);
 116     dest += 4;
 117     *aHighSurrogate = 0;
 118   }
 119
 120   while (src < srcEnd) {
 121     // regular codepoint or an unpaired low surrogate
 122     if ((src[0] & 0xfc00) != 0xd800)
 123     {
 124       if (destEnd - dest < 4)
 125         goto error_more_output;
 126       ucs4 = PRUint32(src[0]);
 127     }
 128     else  // high surrogate
 129     {
 130       if ((src+1) >= srcEnd) {
 131         //we need another surrogate to complete this unicode char
 132         *aHighSurrogate = src[0];
 133         *aDestLength = dest - aDest;
 134         return NS_OK_UENC_MOREINPUT;
 135       }
 136       //handle surrogate
 137       if (destEnd - dest < 4)
 138         goto error_more_output;
 139       if ((src[1] & 0xfc00) != 0xdc00)  // unpaired
 140         ucs4 = PRUint32(src[0]);
 141       else
 142       {  // convert surrogate pair to UCS4
 143         ucs4 = (((src[0] & 0x3ffL) << 10) | (src[1] & 0x3ffL)) + 0x10000;
 144         *aHighSurrogate = 0;
 145         ++src;
 146       }
 147     }
 148     if (aIsLE)
 149       UCS4_TO_LE_STRING(ucs4, dest);
 150     else
 151       UCS4_TO_BE_STRING(ucs4, dest);
 152     dest += 4;
 153     ++src;
 154   }
 155
 156   *aDestLength = dest - aDest;
 157   return NS_OK;
 158
 159 error_more_output:
 160   *aSrcLength = src - aSrc;
 161   *aDestLength = dest - aDest;
 162   return NS_OK_UENC_MOREOUTPUT;
 163
 164 }
 165
 166 static nsresult FinishCommon(char * aDest,
 167                              PRInt32 * aDestLength,
 168                              PRUnichar * aHighSurrogate,
 169                              PRBool aIsLE)
 170 {
 171   char * dest = aDest;
 172
 173   if (*aHighSurrogate) {
 174     if (*aDestLength < 4) {
 175       *aDestLength = 0;
 176       return NS_OK_UENC_MOREOUTPUT;
 177     }
 178     PRUint32 high = PRUint32(*aHighSurrogate);
 179     if (aIsLE)
 180       UCS4_TO_LE_STRING(high, dest);
 181     else
 182       UCS4_TO_BE_STRING(high, dest);
 183     *aHighSurrogate = 0;
 184     *aDestLength = 4;
 185     return NS_OK;
 186   }
 187
 188   *aDestLength  = 0;
 189   return NS_OK;
 190 }
 191
 192
 193
 194 //----------------------------------------------------------------------
 195 // Class nsUnicodeToUTF32 [implementation]
 196
 197 NS_IMPL_ISUPPORTS1(nsUnicodeToUTF32, nsIUnicodeEncoder)
 198
 199
 200 //----------------------------------------------------------------------
 201 // Subclassing of nsIUnicodeEncoder class [implementation]
 202
 203 NS_IMETHODIMP nsUnicodeToUTF32::GetMaxLength(const PRUnichar * aSrc,
 204                                             PRInt32 aSrcLength,
 205                                             PRInt32 * aDestLength)
 206 {
 207   *aDestLength = aSrcLength * 4;
 208   return NS_OK;
 209 }
 210
 211 NS_IMETHODIMP nsUnicodeToUTF32::FillInfo(PRUint32 *aInfo)
 212 {
 213   memset(aInfo, 0xFF, (0x10000L >> 3));
 214   return NS_OK;
 215 }
 216
 217
 218 //----------------------------------------------------------------------
 219 // Class nsUnicodeToUTF32BE [implementation]
 220
 221 //----------------------------------------------------------------------
 222 // Subclassing of nsUnicodeToUTF32 class [implementation]
 223
 224
 225 NS_IMETHODIMP nsUnicodeToUTF32BE::Convert(const PRUnichar * aSrc,
 226                                           PRInt32 * aSrcLength,
 227                                           char * aDest,
 228                                           PRInt32 * aDestLength)
 229 {
 230   return ConvertCommon(aSrc, aSrcLength, aDest, aDestLength,
 231                        &mHighSurrogate, PR_FALSE);
 232 }
 233
 234 NS_IMETHODIMP nsUnicodeToUTF32BE::Finish(char * aDest,
 235                                          PRInt32 * aDestLength)
 236 {
 237   return FinishCommon(aDest, aDestLength, &mHighSurrogate, PR_FALSE);
 238 }
 239
 240
 241 //----------------------------------------------------------------------
 242 // Class nsUnicodeToUTF32LE [implementation]
 243
 244 //----------------------------------------------------------------------
 245 // Subclassing of nsUnicodeToUTF32 class [implementation]
 246
 247
 248 NS_IMETHODIMP nsUnicodeToUTF32LE::Convert(const PRUnichar * aSrc,
 249                                           PRInt32 * aSrcLength,
 250                                           char * aDest,
 251                                           PRInt32 * aDestLength)
 252 {
 253   return ConvertCommon(aSrc, aSrcLength, aDest, aDestLength,
 254                        &mHighSurrogate, PR_TRUE);
 255 }
 256
 257 NS_IMETHODIMP nsUnicodeToUTF32LE::Finish(char * aDest,
 258                                          PRInt32 * aDestLength)
 259 {
 260   return FinishCommon(aDest, aDestLength, &mHighSurrogate, PR_TRUE);
 261 }
 262