lib/ucs4.h

   1 /*
   2  * Copyright (C) 1999-2001, 2008, 2011, 2016 Free Software Foundation, Inc.
   3  * This file is part of the GNU LIBICONV Library.
   4  *
   5  * The GNU LIBICONV Library is free software; you can redistribute it
   6  * and/or modify it under the terms of the GNU Lesser General Public
   7  * License as published by the Free Software Foundation; either version 2.1
   8  * of the License, or (at your option) any later version.
   9  *
  10  * The GNU LIBICONV Library is distributed in the hope that it will be
  11  * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13  * Lesser General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU Lesser General Public
  16  * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
  17  * If not, see <https://www.gnu.org/licenses/>.
  18  */
  19
  20 /*
  21  * UCS-4
  22  */
  23
  24 /* Here we accept FFFE0000/0000FEFF marks as endianness indicators everywhere
  25    in the stream, not just at the beginning. The default is big-endian. */
  26 /* The state is 0 if big-endian, 1 if little-endian. */
  27 static int
  28 ucs4_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, size_t n)
  29 {
  30   state_t state = conv->istate;
  31   int count = 0;
  32   for (; n >= 4 && count <= RET_COUNT_MAX && count <= INT_MAX-4;) {
  33     ucs4_t wc = (state
  34                   ? s[0] + (s[1] << 8) + (s[2] << 16) + (s[3] << 24)
  35                   : (s[0] << 24) + (s[1] << 16) + (s[2] << 8) + s[3]);
  36     if (wc == 0x0000feff) {
  37     } else if (wc == 0xfffe0000u) {
  38       state ^= 1;
  39     } else if (wc <= 0x7fffffff) {
  40       *pwc = wc;
  41       conv->istate = state;
  42       return count+4;
  43     } else {
  44       conv->istate = state;
  45       return RET_SHIFT_ILSEQ(count);
  46     }
  47     s += 4; n -= 4; count += 4;
  48   }
  49   conv->istate = state;
  50   return RET_TOOFEW(count);
  51 }
  52
  53 /* But we output UCS-4 in big-endian order, without byte-order mark. */
  54 static int
  55 ucs4_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n)
  56 {
  57   if (wc <= 0x7fffffff) {
  58     if (n >= 4) {
  59       r[0] = (unsigned char) (wc >> 24);
  60       r[1] = (unsigned char) (wc >> 16);
  61       r[2] = (unsigned char) (wc >> 8);
  62       r[3] = (unsigned char) wc;
  63       return 4;
  64     } else
  65       return RET_TOOSMALL;
  66   } else
  67     return RET_ILUNI;
  68 }