| 1 |
/*************************************************
|
| 2 |
* libucp - Unicode Property Table handler *
|
| 3 |
*************************************************/
|
| 4 |
|
| 5 |
/* Copyright (c) University of Cambridge 2004 */
|
| 6 |
|
| 7 |
/* This little library provides a fast way of obtaining the basic Unicode
|
| 8 |
properties of a character, using a compact binary tree that occupies less than
|
| 9 |
100K bytes.
|
| 10 |
|
| 11 |
-----------------------------------------------------------------------------
|
| 12 |
Redistribution and use in source and binary forms, with or without
|
| 13 |
modification, are permitted provided that the following conditions are met:
|
| 14 |
|
| 15 |
* Redistributions of source code must retain the above copyright notice,
|
| 16 |
this list of conditions and the following disclaimer.
|
| 17 |
|
| 18 |
* Redistributions in binary form must reproduce the above copyright
|
| 19 |
notice, this list of conditions and the following disclaimer in the
|
| 20 |
documentation and/or other materials provided with the distribution.
|
| 21 |
|
| 22 |
* Neither the name of the University of Cambridge nor the names of its
|
| 23 |
contributors may be used to endorse or promote products derived from
|
| 24 |
this software without specific prior written permission.
|
| 25 |
|
| 26 |
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
| 27 |
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
| 28 |
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
| 29 |
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
| 30 |
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
| 31 |
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
| 32 |
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
| 33 |
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
| 34 |
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
| 35 |
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
| 36 |
POSSIBILITY OF SUCH DAMAGE.
|
| 37 |
-----------------------------------------------------------------------------
|
| 38 |
*/
|
| 39 |
|
| 40 |
|
| 41 |
#include "ucp.h" /* Exported interface */
|
| 42 |
#include "ucpinternal.h" /* Internal table details */
|
| 43 |
#include "ucptable.c" /* The table itself */
|
| 44 |
|
| 45 |
|
| 46 |
/* In some environments, external functions have to be preceded by some magic.
|
| 47 |
In my world (Unix), they do not. Use a macro to deal with this. */
|
| 48 |
|
| 49 |
#ifndef EXPORT
|
| 50 |
#define EXPORT
|
| 51 |
#endif
|
| 52 |
|
| 53 |
|
| 54 |
|
| 55 |
/*************************************************
|
| 56 |
* Search table and return data *
|
| 57 |
*************************************************/
|
| 58 |
|
| 59 |
/* Two values are returned: the category is ucp_C, ucp_L, etc. The detailed
|
| 60 |
character type is ucp_Lu, ucp_Nd, etc.
|
| 61 |
|
| 62 |
Arguments:
|
| 63 |
c the character value
|
| 64 |
type_ptr the detailed character type is returned here
|
| 65 |
case_ptr for letters, the opposite case is returned here, if there
|
| 66 |
is one, else zero
|
| 67 |
|
| 68 |
Returns: the character type category or -1 if not found
|
| 69 |
*/
|
| 70 |
|
| 71 |
EXPORT int
|
| 72 |
ucp_findchar(const int c, int *type_ptr, int *case_ptr)
|
| 73 |
{
|
| 74 |
cnode *node = ucp_table;
|
| 75 |
register int cc = c;
|
| 76 |
int case_offset;
|
| 77 |
|
| 78 |
for (;;)
|
| 79 |
{
|
| 80 |
register int d = node->f1 | ((node->f0 & f0_chhmask) << 16);
|
| 81 |
if (cc == d) break;
|
| 82 |
if (cc < d)
|
| 83 |
{
|
| 84 |
if ((node->f0 & f0_leftexists) == 0) return -1;
|
| 85 |
node ++;
|
| 86 |
}
|
| 87 |
else
|
| 88 |
{
|
| 89 |
register int roffset = (node->f2 & f2_rightmask) >> f2_rightshift;
|
| 90 |
if (roffset == 0) return -1;
|
| 91 |
node += 1 << (roffset - 1);
|
| 92 |
}
|
| 93 |
}
|
| 94 |
|
| 95 |
switch ((*type_ptr = ((node->f0 & f0_typemask) >> f0_typeshift)))
|
| 96 |
{
|
| 97 |
case ucp_Cc:
|
| 98 |
case ucp_Cf:
|
| 99 |
case ucp_Cn:
|
| 100 |
case ucp_Co:
|
| 101 |
case ucp_Cs:
|
| 102 |
return ucp_C;
|
| 103 |
break;
|
| 104 |
|
| 105 |
case ucp_Ll:
|
| 106 |
case ucp_Lu:
|
| 107 |
case_offset = node->f2 & f2_casemask;
|
| 108 |
if ((case_offset & 0x0100) != 0) case_offset |= 0xfffff000;
|
| 109 |
*case_ptr = (case_offset == 0)? 0 : cc + case_offset;
|
| 110 |
return ucp_L;
|
| 111 |
|
| 112 |
case ucp_Lm:
|
| 113 |
case ucp_Lo:
|
| 114 |
case ucp_Lt:
|
| 115 |
*case_ptr = 0;
|
| 116 |
return ucp_L;
|
| 117 |
break;
|
| 118 |
|
| 119 |
case ucp_Mc:
|
| 120 |
case ucp_Me:
|
| 121 |
case ucp_Mn:
|
| 122 |
return ucp_M;
|
| 123 |
break;
|
| 124 |
|
| 125 |
case ucp_Nd:
|
| 126 |
case ucp_Nl:
|
| 127 |
case ucp_No:
|
| 128 |
return ucp_N;
|
| 129 |
break;
|
| 130 |
|
| 131 |
case ucp_Pc:
|
| 132 |
case ucp_Pd:
|
| 133 |
case ucp_Pe:
|
| 134 |
case ucp_Pf:
|
| 135 |
case ucp_Pi:
|
| 136 |
case ucp_Ps:
|
| 137 |
case ucp_Po:
|
| 138 |
return ucp_P;
|
| 139 |
break;
|
| 140 |
|
| 141 |
case ucp_Sc:
|
| 142 |
case ucp_Sk:
|
| 143 |
case ucp_Sm:
|
| 144 |
case ucp_So:
|
| 145 |
return ucp_S;
|
| 146 |
break;
|
| 147 |
|
| 148 |
case ucp_Zl:
|
| 149 |
case ucp_Zp:
|
| 150 |
case ucp_Zs:
|
| 151 |
return ucp_Z;
|
| 152 |
break;
|
| 153 |
|
| 154 |
default: /* "Should never happen" */
|
| 155 |
return -1;
|
| 156 |
break;
|
| 157 |
}
|
| 158 |
}
|
| 159 |
|
| 160 |
/* End of ucp_findchar.c */
|