1 /**********************************************************************
2 utf32_be.c - Oniguruma (regular expression library)
3 **********************************************************************/
5 * Copyright (c) 2002-2016 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 utf32be_mbc_enc_len(const UChar* p ARG_UNUSED)
39 is_valid_mbc_string(const UChar* s, const UChar* end)
41 return onigenc_length_check_is_valid_mbc_string(ONIG_ENCODING_UTF32_BE, s, end);
45 utf32be_is_mbc_newline(const UChar* p, const UChar* end)
48 if (*(p+3) == 0x0a && *(p+2) == 0 && *(p+1) == 0 && *p == 0)
50 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
52 #ifndef USE_CRNL_AS_LINE_TERMINATOR
56 && *(p+2) == 0 && *(p+1) == 0 && *p == 0x00)
59 if (*(p+2) == 0x20 && (*(p+3) == 0x29 || *(p+3) == 0x28)
60 && *(p+1) == 0 && *p == 0)
68 utf32be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
70 return (OnigCodePoint )(((p[0] * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
74 utf32be_code_to_mbclen(OnigCodePoint code ARG_UNUSED)
80 utf32be_code_to_mbc(OnigCodePoint code, UChar *buf)
84 *p++ = (UChar )((code & 0xff000000) >>24);
85 *p++ = (UChar )((code & 0xff0000) >>16);
86 *p++ = (UChar )((code & 0xff00) >> 8);
87 *p++ = (UChar ) (code & 0xff);
92 utf32be_mbc_case_fold(OnigCaseFoldType flag,
93 const UChar** pp, const UChar* end, UChar* fold)
97 if (ONIGENC_IS_ASCII_CODE(*(p+3)) && *(p+2) == 0 && *(p+1) == 0 && *p == 0) {
101 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
102 if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
103 if (*(p+3) == 0x49) {
113 *fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*(p+3));
118 return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF32_BE, flag, pp, end,
124 utf32be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
126 const UChar* p = *pp;
130 if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
134 if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
139 v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
140 (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
141 if ((v | BIT_CTYPE_LOWER) != 0) {
142 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
143 if (c >= 0xaa && c <= 0xba)
148 return (v != 0 ? TRUE : FALSE);
156 utf32be_left_adjust_char_head(const UChar* start, const UChar* s)
160 if (s <= start) return (UChar* )s;
162 rem = (s - start) % 4;
163 return (UChar* )(s - rem);
167 utf32be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
168 const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
170 return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF32_BE,
171 flag, p, end, items);
174 OnigEncodingType OnigEncodingUTF32_BE = {
176 "UTF-32BE", /* name */
177 4, /* max byte length */
178 4, /* min byte length */
179 utf32be_is_mbc_newline,
181 utf32be_code_to_mbclen,
183 utf32be_mbc_case_fold,
184 onigenc_unicode_apply_all_case_fold,
185 utf32be_get_case_fold_codes_by_str,
186 onigenc_unicode_property_name_to_ctype,
187 onigenc_unicode_is_code_ctype,
188 onigenc_utf16_32_get_ctype_code_range,
189 utf32be_left_adjust_char_head,
190 onigenc_always_false_is_allowed_reverse_match,
192 NULL, /* is_initialized */