| 1 |
9 |
jlechner |
/* Routine to translate from Japanese characters to Unicode */
|
| 2 |
|
|
|
| 3 |
|
|
/* Copyright (c) 2002 Red Hat Incorporated.
|
| 4 |
|
|
All rights reserved.
|
| 5 |
|
|
|
| 6 |
|
|
Redistribution and use in source and binary forms, with or without
|
| 7 |
|
|
modification, are permitted provided that the following conditions are met:
|
| 8 |
|
|
|
| 9 |
|
|
Redistributions of source code must retain the above copyright
|
| 10 |
|
|
notice, this list of conditions and the following disclaimer.
|
| 11 |
|
|
|
| 12 |
|
|
Redistributions in binary form must reproduce the above copyright
|
| 13 |
|
|
notice, this list of conditions and the following disclaimer in the
|
| 14 |
|
|
documentation and/or other materials provided with the distribution.
|
| 15 |
|
|
|
| 16 |
|
|
The name of Red Hat Incorporated may not be used to endorse
|
| 17 |
|
|
or promote products derived from this software without specific
|
| 18 |
|
|
prior written permission.
|
| 19 |
|
|
|
| 20 |
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
| 21 |
|
|
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
| 22 |
|
|
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
| 23 |
|
|
ARE DISCLAIMED. IN NO EVENT SHALL RED HAT INCORPORATED BE LIABLE FOR ANY
|
| 24 |
|
|
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
| 25 |
|
|
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
| 26 |
|
|
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
| 27 |
|
|
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
| 28 |
|
|
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
| 29 |
|
|
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
| 30 |
|
|
*/
|
| 31 |
|
|
|
| 32 |
|
|
#include <newlib.h>
|
| 33 |
|
|
|
| 34 |
|
|
#ifdef _MB_CAPABLE
|
| 35 |
|
|
|
| 36 |
|
|
#include <_ansi.h>
|
| 37 |
|
|
#include <wctype.h>
|
| 38 |
|
|
#include "local.h"
|
| 39 |
|
|
#include "jp2uc.h"
|
| 40 |
|
|
|
| 41 |
|
|
wint_t
|
| 42 |
|
|
_DEFUN (__jp2uc, (c, type), wint_t c _AND int type)
|
| 43 |
|
|
{
|
| 44 |
|
|
int index, adj;
|
| 45 |
|
|
unsigned char byte1, byte2;
|
| 46 |
|
|
wint_t ret;
|
| 47 |
|
|
|
| 48 |
|
|
/* we actually use tables of EUCJP to Unicode. For JIS, we simply
|
| 49 |
|
|
note that EUCJP is essentially JIS with the top bits on in each
|
| 50 |
|
|
byte and translate to EUCJP. For SJIS, we do a translation to EUCJP before
|
| 51 |
|
|
accessing the tables. */
|
| 52 |
|
|
switch (type)
|
| 53 |
|
|
{
|
| 54 |
|
|
case JP_JIS:
|
| 55 |
|
|
byte1 = (c >> 8) + 0x80;
|
| 56 |
|
|
byte2 = (c & 0xff) + 0x80;
|
| 57 |
|
|
break;
|
| 58 |
|
|
case JP_EUCJP:
|
| 59 |
|
|
byte1 = (c >> 8);
|
| 60 |
|
|
byte2 = (c & 0xff);
|
| 61 |
|
|
break;
|
| 62 |
|
|
case JP_SJIS:
|
| 63 |
|
|
byte1 = c >> 8;
|
| 64 |
|
|
byte2 = c & 0xff;
|
| 65 |
|
|
if (byte2 <= 0x9e)
|
| 66 |
|
|
{
|
| 67 |
|
|
adj = 0xa1 - 0x22;
|
| 68 |
|
|
byte2 = (byte2 - 31) + 0xa1;
|
| 69 |
|
|
}
|
| 70 |
|
|
else
|
| 71 |
|
|
{
|
| 72 |
|
|
adj = 0xa1 - 0x21;
|
| 73 |
|
|
byte2 = (byte2 - 126) + 0xa1;
|
| 74 |
|
|
}
|
| 75 |
|
|
if (byte1 <= 0x9f)
|
| 76 |
|
|
byte1 = ((byte1 - 112) << 1) + adj;
|
| 77 |
|
|
else
|
| 78 |
|
|
byte1 = ((byte1 - 176) << 1) + adj;
|
| 79 |
|
|
break;
|
| 80 |
|
|
default:
|
| 81 |
|
|
return WEOF;
|
| 82 |
|
|
}
|
| 83 |
|
|
|
| 84 |
|
|
/* find conversion in jp2uc arrays */
|
| 85 |
|
|
|
| 86 |
|
|
/* handle larger ranges first */
|
| 87 |
|
|
if (byte1 >= 0xb0 && byte1 <= 0xcf && c <= 0xcfd3)
|
| 88 |
|
|
{
|
| 89 |
|
|
index = (byte1 - 0xb0) * 0xfe + (byte2 - 0xa1);
|
| 90 |
|
|
return b02cf[index];
|
| 91 |
|
|
}
|
| 92 |
|
|
else if (byte1 >= 0xd0 && byte1 <= 0xf4 && c <= 0xf4a6)
|
| 93 |
|
|
{
|
| 94 |
|
|
index = (byte1 - 0xd0) * 0xfe + (byte2 - 0xa1);
|
| 95 |
|
|
return d02f4[index];
|
| 96 |
|
|
}
|
| 97 |
|
|
|
| 98 |
|
|
/* handle smaller ranges here */
|
| 99 |
|
|
switch (byte1)
|
| 100 |
|
|
{
|
| 101 |
|
|
case 0xA1:
|
| 102 |
|
|
return (wint_t)a1[byte2 - 0xa1];
|
| 103 |
|
|
case 0xA2:
|
| 104 |
|
|
ret = a2[byte2 - 0xa1];
|
| 105 |
|
|
if (ret != 0)
|
| 106 |
|
|
return (wint_t)ret;
|
| 107 |
|
|
break;
|
| 108 |
|
|
case 0xA3:
|
| 109 |
|
|
if (a3[byte2 - 0xa1])
|
| 110 |
|
|
return (wint_t)(0xff00 + (byte2 - 0xa0));
|
| 111 |
|
|
break;
|
| 112 |
|
|
case 0xA4:
|
| 113 |
|
|
if (byte2 <= 0xf3)
|
| 114 |
|
|
return (wint_t)(0x3000 + (byte2 - 0x60));
|
| 115 |
|
|
break;
|
| 116 |
|
|
case 0xA5:
|
| 117 |
|
|
if (byte2 <= 0xf6)
|
| 118 |
|
|
return (wint_t)(0x3000 + byte2);
|
| 119 |
|
|
break;
|
| 120 |
|
|
case 0xA6:
|
| 121 |
|
|
ret = 0;
|
| 122 |
|
|
if (byte2 <= 0xd8)
|
| 123 |
|
|
ret = (wint_t)a6[byte2 - 0xa1];
|
| 124 |
|
|
if (ret != 0)
|
| 125 |
|
|
return ret;
|
| 126 |
|
|
break;
|
| 127 |
|
|
case 0xA7:
|
| 128 |
|
|
ret = 0;
|
| 129 |
|
|
if (byte2 <= 0xf1)
|
| 130 |
|
|
ret = (wint_t)a7[byte2 - 0xa1];
|
| 131 |
|
|
if (ret != 0)
|
| 132 |
|
|
return ret;
|
| 133 |
|
|
break;
|
| 134 |
|
|
case 0xA8:
|
| 135 |
|
|
if (byte2 <= 0xc0)
|
| 136 |
|
|
return (wint_t)a8[byte2 - 0xa1];
|
| 137 |
|
|
break;
|
| 138 |
|
|
default:
|
| 139 |
|
|
return WEOF;
|
| 140 |
|
|
}
|
| 141 |
|
|
|
| 142 |
|
|
return WEOF;
|
| 143 |
|
|
}
|
| 144 |
|
|
|
| 145 |
|
|
#endif /* _MB_CAPABLE */
|
