1 : /**********************************************************************
2 : iso8859_8.c - Oniguruma (regular expression library)
3 : **********************************************************************/
4 : /*-
5 : * Copyright (c) 2002-2004 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_8_CTYPE(code,ctype) \
33 : ((EncISO_8859_8_CtypeTable[code] & ctype) != 0)
34 :
35 : static const unsigned short EncISO_8859_8_CtypeTable[256] = {
36 : 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
37 : 0x2008, 0x220c, 0x2209, 0x2208, 0x2208, 0x2208, 0x2008, 0x2008,
38 : 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
39 : 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
40 : 0x2284, 0x21a0, 0x21a0, 0x21a0, 0x20a0, 0x21a0, 0x21a0, 0x21a0,
41 : 0x21a0, 0x21a0, 0x21a0, 0x20a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0,
42 : 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0,
43 : 0x38b0, 0x38b0, 0x21a0, 0x21a0, 0x20a0, 0x20a0, 0x20a0, 0x21a0,
44 : 0x21a0, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x34a2,
45 : 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2,
46 : 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2,
47 : 0x34a2, 0x34a2, 0x34a2, 0x21a0, 0x21a0, 0x21a0, 0x20a0, 0x31a0,
48 : 0x20a0, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x30e2,
49 : 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
50 : 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
51 : 0x30e2, 0x30e2, 0x30e2, 0x21a0, 0x20a0, 0x21a0, 0x20a0, 0x2008,
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, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0,
57 : 0x00a0, 0x00a0, 0x00a0, 0x01a0, 0x00a0, 0x01a0, 0x00a0, 0x00a0,
58 : 0x00a0, 0x00a0, 0x10a0, 0x10a0, 0x00a0, 0x10e2, 0x00a0, 0x01a0,
59 : 0x00a0, 0x10a0, 0x00a0, 0x01a0, 0x10a0, 0x10a0, 0x10a0, 0x0000,
60 : 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
61 : 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
62 : 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
63 : 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x01a0,
64 : 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2,
65 : 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2,
66 : 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2, 0x10a2,
67 : 0x10a2, 0x10a2, 0x10a2, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000
68 : };
69 :
70 : static int
71 : iso_8859_8_is_code_ctype(OnigCodePoint code, unsigned int ctype)
72 0 : {
73 0 : if (code < 256)
74 0 : return ENC_IS_ISO_8859_8_CTYPE(code, ctype);
75 : else
76 0 : return FALSE;
77 : }
78 :
79 : OnigEncodingType OnigEncodingISO_8859_8 = {
80 : onigenc_single_byte_mbc_enc_len,
81 : "ISO-8859-8", /* name */
82 : 1, /* max enc length */
83 : 1, /* min enc length */
84 : ( ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE ),
85 : {
86 : (OnigCodePoint )'\\' /* esc */
87 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
88 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
89 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
90 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
91 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
92 : },
93 : onigenc_is_mbc_newline_0x0a,
94 : onigenc_single_byte_mbc_to_code,
95 : onigenc_single_byte_code_to_mbclen,
96 : onigenc_single_byte_code_to_mbc,
97 : onigenc_ascii_mbc_to_normalize,
98 : onigenc_ascii_is_mbc_ambiguous,
99 : onigenc_ascii_get_all_pair_ambig_codes,
100 : onigenc_nothing_get_all_comp_ambig_codes,
101 : iso_8859_8_is_code_ctype,
102 : onigenc_not_support_get_ctype_code_range,
103 : onigenc_single_byte_left_adjust_char_head,
104 : onigenc_always_true_is_allowed_reverse_match
105 : };
|
