1 /**********************************************************************
2 utf32_le.c - Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5 * Copyright (c) 2002-2020 K.Kosako
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 static int
utf32le_mbc_enc_len(const UChar * p ARG_UNUSED)33 utf32le_mbc_enc_len(const UChar* p ARG_UNUSED)
34 {
35 return 4;
36 }
37
38 static int
is_valid_mbc_string(const UChar * s,const UChar * end)39 is_valid_mbc_string(const UChar* s, const UChar* end)
40 {
41 return onigenc_length_check_is_valid_mbc_string(ONIG_ENCODING_UTF32_LE, s, end);
42 }
43
44 static int
utf32le_is_mbc_newline(const UChar * p,const UChar * end)45 utf32le_is_mbc_newline(const UChar* p, const UChar* end)
46 {
47 if (p + 3 < end) {
48 if (*p == NEWLINE_CODE && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0)
49 return 1;
50 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
51 if ((
52 #ifndef USE_CRNL_AS_LINE_TERMINATOR
53 *p == 0x0d ||
54 #endif
55 *p == 0x85)
56 && *(p+1) == 0x00 && (p+2) == 0x00 && *(p+3) == 0x00)
57 return 1;
58
59 if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28)
60 && *(p+2) == 0x00 && *(p+3) == 0x00)
61 return 1;
62 #endif
63 }
64 return 0;
65 }
66
67 static OnigCodePoint
utf32le_mbc_to_code(const UChar * p,const UChar * end ARG_UNUSED)68 utf32le_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
69 {
70 OnigCodePoint code;
71
72 code = (OnigCodePoint )((((p[3] & 0x7f) * 256 + p[2]) * 256 + p[1]) * 256 + p[0]);
73 return code;
74 }
75
76 static int
utf32le_code_to_mbclen(OnigCodePoint code ARG_UNUSED)77 utf32le_code_to_mbclen(OnigCodePoint code ARG_UNUSED)
78 {
79 return 4;
80 }
81
82 static int
utf32le_code_to_mbc(OnigCodePoint code,UChar * buf)83 utf32le_code_to_mbc(OnigCodePoint code, UChar *buf)
84 {
85 UChar* p = buf;
86
87 *p++ = (UChar ) (code & 0xff);
88 *p++ = (UChar )((code & 0xff00) >> 8);
89 *p++ = (UChar )((code & 0xff0000) >>16);
90 *p++ = (UChar )((code & 0xff000000) >>24);
91 return 4;
92 }
93
94 static int
utf32le_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)95 utf32le_mbc_case_fold(OnigCaseFoldType flag,
96 const UChar** pp, const UChar* end, UChar* fold)
97 {
98 const UChar* p = *pp;
99
100 if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
101 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
102 if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
103 if (*p == 0x49) {
104 *fold++ = 0x31;
105 *fold++ = 0x01;
106 }
107 }
108 else {
109 #endif
110 *fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
111 *fold++ = 0;
112 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
113 }
114 #endif
115
116 *fold++ = 0;
117 *fold = 0;
118 *pp += 4;
119 return 4;
120 }
121 else
122 return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF32_LE, flag, pp, end,
123 fold);
124 }
125
126 static UChar*
utf32le_left_adjust_char_head(const UChar * start,const UChar * s)127 utf32le_left_adjust_char_head(const UChar* start, const UChar* s)
128 {
129 int rem;
130
131 if (s <= start) return (UChar* )s;
132
133 rem = (s - start) % 4;
134 return (UChar* )(s - rem);
135 }
136
137 static int
utf32le_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])138 utf32le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
139 const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
140 {
141 return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF32_LE,
142 flag, p, end, items);
143 }
144
145 OnigEncodingType OnigEncodingUTF32_LE = {
146 utf32le_mbc_enc_len,
147 "UTF-32LE", /* name */
148 4, /* max enc length */
149 4, /* min enc length */
150 utf32le_is_mbc_newline,
151 utf32le_mbc_to_code,
152 utf32le_code_to_mbclen,
153 utf32le_code_to_mbc,
154 utf32le_mbc_case_fold,
155 onigenc_unicode_apply_all_case_fold,
156 utf32le_get_case_fold_codes_by_str,
157 onigenc_unicode_property_name_to_ctype,
158 onigenc_unicode_is_code_ctype,
159 onigenc_utf16_32_get_ctype_code_range,
160 utf32le_left_adjust_char_head,
161 onigenc_always_false_is_allowed_reverse_match,
162 NULL, /* init */
163 NULL, /* is_initialized */
164 is_valid_mbc_string,
165 ENC_FLAG_UNICODE|ENC_FLAG_SKIP_OFFSET_1,
166 0, 0
167 };
168