| 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 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, see <http://www.gnu.org/licenses/>. |
| 18 |
*/ |
| 19 |
|
| 20 |
/* |
| 21 |
* UCS-2 |
| 22 |
*/ |
| 23 |
|
| 24 |
/* Here we accept FFFE/FEFF 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 |
ucs2_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 >= 2 && count <= RET_COUNT_MAX && count <= INT_MAX-2;) { |
| 33 |
ucs4_t wc = (state ? s[0] + (s[1] << 8) : (s[0] << 8) + s[1]); |
| 34 |
if (wc == 0xfeff) { |
| 35 |
} else if (wc == 0xfffe) { |
| 36 |
state ^= 1; |
| 37 |
} else if (wc >= 0xd800 && wc < 0xe000) { |
| 38 |
conv->istate = state; |
| 39 |
return RET_SHIFT_ILSEQ(count); |
| 40 |
} else { |
| 41 |
*pwc = wc; |
| 42 |
conv->istate = state; |
| 43 |
return count+2; |
| 44 |
} |
| 45 |
s += 2; n -= 2; count += 2; |
| 46 |
} |
| 47 |
conv->istate = state; |
| 48 |
return RET_TOOFEW(count); |
| 49 |
} |
| 50 |
|
| 51 |
/* But we output UCS-2 in big-endian order, without byte-order mark. */ |
| 52 |
/* RFC 2152 says: |
| 53 |
"ISO/IEC 10646-1:1993(E) specifies that when characters the UCS-2 form are |
| 54 |
serialized as octets, that the most significant octet appear first." */ |
| 55 |
static int |
| 56 |
ucs2_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n) |
| 57 |
{ |
| 58 |
if (wc < 0x10000 && wc != 0xfffe && !(wc >= 0xd800 && wc < 0xe000)) { |
| 59 |
if (n >= 2) { |
| 60 |
r[0] = (unsigned char) (wc >> 8); |
| 61 |
r[1] = (unsigned char) wc; |
| 62 |
return 2; |
| 63 |
} else |
| 64 |
return RET_TOOSMALL; |
| 65 |
} else |
| 66 |
return RET_ILUNI; |
| 67 |
} |