lyx_mirror/3rdparty/libiconv/1.15/lib/utf8.h
Uwe Stöhr cf214f8263 libiconv: upgrade to version 1.15
- libiconv 1.15 was released in February this year
- I opened a thread to discuss if this should also be done for the lyX 2.3 branch on the list
2017-09-10 14:46:37 +02:00

99 lines
2.9 KiB
C

/*
* Copyright (C) 1999-2001, 2004, 2016 Free Software Foundation, Inc.
* This file is part of the GNU LIBICONV Library.
*
* The GNU LIBICONV Library is free software; you can redistribute it
* and/or modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* The GNU LIBICONV Library is distributed in the hope that it will be
* useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public
* License along with the GNU LIBICONV Library; see the file COPYING.LIB.
* If not, see <http://www.gnu.org/licenses/>.
*/
/*
* UTF-8
*/
/* Specification: RFC 3629 */
static int
utf8_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, size_t n)
{
unsigned char c = s[0];
if (c < 0x80) {
*pwc = c;
return 1;
} else if (c < 0xc2) {
return RET_ILSEQ;
} else if (c < 0xe0) {
if (n < 2)
return RET_TOOFEW(0);
if (!((s[1] ^ 0x80) < 0x40))
return RET_ILSEQ;
*pwc = ((ucs4_t) (c & 0x1f) << 6)
| (ucs4_t) (s[1] ^ 0x80);
return 2;
} else if (c < 0xf0) {
if (n < 3)
return RET_TOOFEW(0);
if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (c >= 0xe1 || s[1] >= 0xa0)
&& (c != 0xed || s[1] < 0xa0)))
return RET_ILSEQ;
*pwc = ((ucs4_t) (c & 0x0f) << 12)
| ((ucs4_t) (s[1] ^ 0x80) << 6)
| (ucs4_t) (s[2] ^ 0x80);
return 3;
} else if (c < 0xf8 && sizeof(ucs4_t)*8 >= 32) {
if (n < 4)
return RET_TOOFEW(0);
if (!((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (s[3] ^ 0x80) < 0x40
&& (c >= 0xf1 || s[1] >= 0x90)
&& (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))))
return RET_ILSEQ;
*pwc = ((ucs4_t) (c & 0x07) << 18)
| ((ucs4_t) (s[1] ^ 0x80) << 12)
| ((ucs4_t) (s[2] ^ 0x80) << 6)
| (ucs4_t) (s[3] ^ 0x80);
return 4;
} else
return RET_ILSEQ;
}
static int
utf8_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n) /* n == 0 is acceptable */
{
int count;
if (wc < 0x80)
count = 1;
else if (wc < 0x800)
count = 2;
else if (wc < 0x10000) {
if (wc < 0xd800 || wc >= 0xe000)
count = 3;
else
return RET_ILUNI;
} else if (wc < 0x110000)
count = 4;
else
return RET_ILUNI;
if (n < count)
return RET_TOOSMALL;
switch (count) { /* note: code falls through cases! */
case 4: r[3] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x10000;
case 3: r[2] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x800;
case 2: r[1] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0xc0;
case 1: r[0] = wc;
}
return count;
}