2 * Copyright (C) 1999-2001 Free Software Foundation, Inc.
3 * This file is part of the GNU LIBICONV Library.
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.
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.
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., 59 Temple Place -
18 * Suite 330, Boston, MA 02111-1307, USA.
25 /* Specification: Unicode 3.1 Standard Annex #19 */
27 /* Here we accept FFFE0000/0000FEFF marks as endianness indicators
28 everywhere in the stream, not just at the beginning. (This is contrary
29 to what #19 D36c specifies, but it allows concatenation of byte
30 sequences to work flawlessly, while disagreeing with #19 behaviour
31 only for strings containing U+FEFF characters, which is quite rare.)
32 The default is big-endian. */
33 /* The state is 0 if big-endian, 1 if little-endian. */
35 utf32_mbtowc (conv_t conv
, ucs4_t
*pwc
, const unsigned char *s
, int n
)
37 state_t state
= conv
->istate
;
41 ? s
[0] + (s
[1] << 8) + (s
[2] << 16) + (s
[3] << 24)
42 : (s
[0] << 24) + (s
[1] << 16) + (s
[2] << 8) + s
[3]);
44 if (wc
== 0x0000feff) {
45 } else if (wc
== 0xfffe0000u
) {
48 if (wc
< 0x110000 && !(wc
>= 0xd800 && wc
< 0xe000)) {
58 return RET_TOOFEW(count
);
61 /* We output UTF-32 in big-endian order, with byte-order mark. */
62 /* The state is 0 at the beginning, 1 after the BOM has been written. */
64 utf32_wctomb (conv_t conv
, unsigned char *r
, ucs4_t wc
, int n
)
66 if (wc
< 0x110000 && !(wc
>= 0xd800 && wc
< 0xe000)) {
74 r
+= 4; n
-= 4; count
+= 4;
81 r
[1] = (unsigned char) (wc
>> 16);
82 r
[2] = (unsigned char) (wc
>> 8);
83 r
[3] = (unsigned char) wc
;