1 /**********************************************************************
2 iso8859_6.c - Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5 * Copyright (c) 2002-2007 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
6 * All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 */
29
30 #include "regenc.h"
31
32 #define ENC_IS_ISO_8859_6_CTYPE(code,ctype) \
33 ((EncISO_8859_6_CtypeTable[code] & CTYPE_TO_BIT(ctype)) != 0)
34
35 static const unsigned short EncISO_8859_6_CtypeTable[256] = {
36 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008,
37 0x4008, 0x420c, 0x4209, 0x4208, 0x4208, 0x4208, 0x4008, 0x4008,
38 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008,
39 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008,
40 0x4284, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0,
41 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0,
42 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0,
43 0x78b0, 0x78b0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0,
44 0x41a0, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x74a2,
45 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2,
46 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2,
47 0x74a2, 0x74a2, 0x74a2, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x51a0,
48 0x41a0, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x70e2,
49 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2,
50 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2,
51 0x70e2, 0x70e2, 0x70e2, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x4008,
52 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
53 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
54 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
55 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
56 0x0284, 0x0000, 0x0000, 0x0000, 0x00a0, 0x0000, 0x0000, 0x0000,
57 0x0000, 0x0000, 0x0000, 0x0000, 0x01a0, 0x01a0, 0x0000, 0x0000,
58 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
59 0x0000, 0x0000, 0x0000, 0x01a0, 0x0000, 0x0000, 0x0000, 0x01a0,
60 0x0000, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2,
61 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2,
62 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2,
63 0x30a2, 0x30a2, 0x30a2, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
64 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2,
65 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2, 0x30a2,
66 0x30a2, 0x30a2, 0x30a2, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
67 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000
68 };
69
70 static int
is_code_ctype(OnigCodePoint code,unsigned int ctype)71 is_code_ctype(OnigCodePoint code, unsigned int ctype)
72 {
73 if (code < 256)
74 return ENC_IS_ISO_8859_6_CTYPE(code, ctype);
75 else
76 return FALSE;
77 }
78
79 OnigEncodingType OnigEncodingISO_8859_6 = {
80 onigenc_single_byte_mbc_enc_len,
81 "ISO-8859-6", /* name */
82 1, /* max enc length */
83 1, /* min enc length */
84 onigenc_is_mbc_newline_0x0a,
85 onigenc_single_byte_mbc_to_code,
86 onigenc_single_byte_code_to_mbclen,
87 onigenc_single_byte_code_to_mbc,
88 onigenc_ascii_mbc_case_fold,
89 onigenc_ascii_apply_all_case_fold,
90 onigenc_ascii_get_case_fold_codes_by_str,
91 onigenc_minimum_property_name_to_ctype,
92 is_code_ctype,
93 onigenc_not_support_get_ctype_code_range,
94 onigenc_single_byte_left_adjust_char_head,
95 onigenc_always_true_is_allowed_reverse_match
96 };
97
