1 /**********************************************************************
2   utf32_be.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
utf32be_mbc_enc_len(const UChar * p ARG_UNUSED)33 utf32be_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_BE, s, end);
42 }
43 
44 static int
utf32be_is_mbc_newline(const UChar * p,const UChar * end)45 utf32be_is_mbc_newline(const UChar* p, const UChar* end)
46 {
47   if (p + 3 < end) {
48     if (*(p+3) == NEWLINE_CODE && *(p+2) == 0 && *(p+1) == 0 && *p == 0)
49       return 1;
50 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
51     if ((
52 #ifndef USE_CRNL_AS_LINE_TERMINATOR
53          *(p+3) == 0x0d ||
54 #endif
55          *(p+3) == 0x85)
56         && *(p+2) == 0 && *(p+1) == 0 && *p == 0x00)
57       return 1;
58 
59     if (*(p+2) == 0x20 && (*(p+3) == 0x29 || *(p+3) == 0x28)
60         && *(p+1) == 0 && *p == 0)
61       return 1;
62 #endif
63   }
64   return 0;
65 }
66 
67 static OnigCodePoint
utf32be_mbc_to_code(const UChar * p,const UChar * end ARG_UNUSED)68 utf32be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
69 {
70   OnigCodePoint code;
71 
72   code = (OnigCodePoint )((((p[0] & 0x7f) * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
73   return code;
74 }
75 
76 static int
utf32be_code_to_mbclen(OnigCodePoint code ARG_UNUSED)77 utf32be_code_to_mbclen(OnigCodePoint code ARG_UNUSED)
78 {
79   return 4;
80 }
81 
82 static int
utf32be_code_to_mbc(OnigCodePoint code,UChar * buf)83 utf32be_code_to_mbc(OnigCodePoint code, UChar *buf)
84 {
85   UChar* p = buf;
86 
87   *p++ = (UChar )((code & 0xff000000) >>24);
88   *p++ = (UChar )((code & 0xff0000)   >>16);
89   *p++ = (UChar )((code & 0xff00)     >> 8);
90   *p++ = (UChar ) (code & 0xff);
91   return 4;
92 }
93 
94 static int
utf32be_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)95 utf32be_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+3)) && *(p+2) == 0 && *(p+1) == 0 && *p == 0) {
101     *fold++ = 0;
102     *fold++ = 0;
103 
104 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
105     if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
106       if (*(p+3) == 0x49) {
107         *fold++ = 0x01;
108         *fold   = 0x31;
109         (*pp) += 4;
110         return 4;
111       }
112     }
113 #endif
114 
115     *fold++ = 0;
116     *fold   = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*(p+3));
117     *pp += 4;
118     return 4;
119   }
120   else
121     return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF32_BE, flag, pp, end,
122                                          fold);
123 }
124 
125 static UChar*
utf32be_left_adjust_char_head(const UChar * start,const UChar * s)126 utf32be_left_adjust_char_head(const UChar* start, const UChar* s)
127 {
128   int rem;
129 
130   if (s <= start) return (UChar* )s;
131 
132   rem = (s - start) % 4;
133   return (UChar* )(s - rem);
134 }
135 
136 static int
utf32be_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])137 utf32be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
138     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
139 {
140   return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF32_BE,
141                                                     flag, p, end, items);
142 }
143 
144 OnigEncodingType OnigEncodingUTF32_BE = {
145   utf32be_mbc_enc_len,
146   "UTF-32BE",   /* name */
147   4,            /* max enc length */
148   4,            /* min enc length */
149   utf32be_is_mbc_newline,
150   utf32be_mbc_to_code,
151   utf32be_code_to_mbclen,
152   utf32be_code_to_mbc,
153   utf32be_mbc_case_fold,
154   onigenc_unicode_apply_all_case_fold,
155   utf32be_get_case_fold_codes_by_str,
156   onigenc_unicode_property_name_to_ctype,
157   onigenc_unicode_is_code_ctype,
158   onigenc_utf16_32_get_ctype_code_range,
159   utf32be_left_adjust_char_head,
160   onigenc_always_false_is_allowed_reverse_match,
161   NULL, /* init */
162   NULL, /* is_initialized */
163   is_valid_mbc_string,
164   ENC_FLAG_UNICODE|ENC_FLAG_SKIP_OFFSET_4,
165   0, 0
166 };
167