1
/**********************************************************************
2
utf32_le.c - Oniguruma (regular expression library)
3
**********************************************************************/
5
* Copyright (c) 2002-2005 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
8
* Redistribution and use in source and binary forms, with or without
9
* modification, are permitted provided that the following conditions
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.
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
33
utf32le_mbc_enc_len(const UChar* p)
39
utf32le_is_mbc_newline(const UChar* p, const UChar* end)
42
if (*p == 0x0a && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0)
49
utf32le_mbc_to_code(const UChar* p, const UChar* end)
51
return (OnigCodePoint )(((p[3] * 256 + p[2]) * 256 + p[1]) * 256 + p[0]);
55
utf32le_code_to_mbclen(OnigCodePoint code)
61
utf32le_code_to_mbc(OnigCodePoint code, UChar *buf)
65
*p++ = (UChar ) (code & 0xff);
66
*p++ = (UChar )((code & 0xff00) >> 8);
67
*p++ = (UChar )((code & 0xff0000) >>16);
68
*p++ = (UChar )((code & 0xff000000) >>24);
73
utf32le_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
78
if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
80
(flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0 &&
81
((*p == 's' && *(p+4) == 's') ||
82
((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
83
(*p == 'S' && *(p+4) == 'S'))) &&
84
*(p+5) == 0 && *(p+6) == 0 && *(p+7) == 0) {
93
if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
94
ONIGENC_IS_MBC_ASCII(p)) ||
95
((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
96
!ONIGENC_IS_MBC_ASCII(p))) {
97
*lower++ = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
107
return 4; /* return byte length of converted char to lower */
113
for (i = 0; i < len; i++) {
118
return len; /* return byte length of converted char to lower */
123
utf32le_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
125
const UChar* p = *pp;
129
if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
132
if ((flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0) {
134
((*p == 's' && *(p+4) == 's') ||
135
((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
136
(*p == 'S' && *(p+4) == 'S'))) &&
137
*(p+5) == 0 && *(p+6) == 0 && *(p+7) == 0) {
141
else if (*p == 0xdf) {
146
if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
147
ONIGENC_IS_MBC_ASCII(p)) ||
148
((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
149
!ONIGENC_IS_MBC_ASCII(p))) {
151
v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
152
(ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
153
if ((v | ONIGENC_CTYPE_LOWER) != 0) {
154
/* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
155
if (c >= 0xaa && c <= 0xba)
160
return (v != 0 ? TRUE : FALSE);
168
utf32le_left_adjust_char_head(const UChar* start, const UChar* s)
172
if (s <= start) return (UChar* )s;
174
rem = (s - start) % 4;
175
return (UChar* )(s - rem);
178
OnigEncodingType OnigEncodingUTF32_LE = {
180
"UTF-32LE", /* name */
181
4, /* max byte length */
182
4, /* min byte length */
183
(ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
184
ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE |
185
ONIGENC_AMBIGUOUS_MATCH_COMPOUND),
187
(OnigCodePoint )'\\' /* esc */
188
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
189
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
190
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
191
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
192
, (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
194
utf32le_is_mbc_newline,
196
utf32le_code_to_mbclen,
198
utf32le_mbc_to_normalize,
199
utf32le_is_mbc_ambiguous,
200
onigenc_iso_8859_1_get_all_pair_ambig_codes,
201
onigenc_ess_tsett_get_all_comp_ambig_codes,
202
onigenc_unicode_is_code_ctype,
203
onigenc_unicode_get_ctype_code_range,
204
utf32le_left_adjust_char_head,
205
onigenc_always_false_is_allowed_reverse_match