Return to ucs2.h CVS log

Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / libiconv / lib

libiconv

    1: /*
    2:  * Copyright (C) 1999-2001, 2008 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 Library General Public
    7:  * License as published by the Free Software Foundation; either version 2
    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:  * Library General Public License for more details.
   14:  *
   15:  * You should have received a copy of the GNU Library General Public
   16:  * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
   17:  * If not, write to the Free Software Foundation, Inc., 51 Franklin Street,
   18:  * Fifth Floor, Boston, MA 02110-1301, USA.
   19:  */
   20: 
   21: /*
   22:  * UCS-2
   23:  */
   24: 
   25: /* Here we accept FFFE/FEFF marks as endianness indicators everywhere
   26:    in the stream, not just at the beginning. The default is big-endian. */
   27: /* The state is 0 if big-endian, 1 if little-endian. */
   28: static int
   29: ucs2_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
   30: {
   31:   state_t state = conv->istate;
   32:   int count = 0;
   33:   for (; n >= 2;) {
   34:     ucs4_t wc = (state ? s[0] + (s[1] << 8) : (s[0] << 8) + s[1]);
   35:     s += 2; n -= 2; count += 2;
   36:     if (wc == 0xfeff) {
   37:     } else if (wc == 0xfffe) {
   38:       state ^= 1;
   39:     } else if (wc >= 0xd800 && wc < 0xe000) {
   40:       conv->istate = state;
   41:       return RET_SHIFT_ILSEQ(count);
   42:     } else {
   43:       *pwc = wc;
   44:       conv->istate = state;
   45:       return count;
   46:     }
   47:   }
   48:   conv->istate = state;
   49:   return RET_TOOFEW(count);
   50: }
   51: 
   52: /* But we output UCS-2 in big-endian order, without byte-order mark. */
   53: /* RFC 2152 says:
   54:    "ISO/IEC 10646-1:1993(E) specifies that when characters the UCS-2 form are
   55:     serialized as octets, that the most significant octet appear first." */
   56: static int
   57: ucs2_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, int n)
   58: {
   59:   if (wc < 0x10000 && wc != 0xfffe && !(wc >= 0xd800 && wc < 0xe000)) {
   60:     if (n >= 2) {
   61:       r[0] = (unsigned char) (wc >> 8);
   62:       r[1] = (unsigned char) wc;
   63:       return 2;
   64:     } else
   65:       return RET_TOOSMALL;
   66:   } else
   67:     return RET_ILUNI;
   68: }