xref: /PHP-7.2/ext/mbstring/oniguruma/src/utf32_le.c (revision 0ae2f95b)
1 /**********************************************************************
2   utf32_le.c -  Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5  * Copyright (c) 2002-2016  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 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 == 0x0a && *(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   if (end - p < 4) return 0;
71   return (OnigCodePoint )(((p[3] * 256 + p[2]) * 256 + p[1]) * 256 + p[0]);
72 }
73 
74 static int
utf32le_code_to_mbclen(OnigCodePoint code ARG_UNUSED)75 utf32le_code_to_mbclen(OnigCodePoint code ARG_UNUSED)
76 {
77   return 4;
78 }
79 
80 static int
utf32le_code_to_mbc(OnigCodePoint code,UChar * buf)81 utf32le_code_to_mbc(OnigCodePoint code, UChar *buf)
82 {
83   UChar* p = buf;
84 
85   *p++ = (UChar ) (code & 0xff);
86   *p++ = (UChar )((code & 0xff00)     >> 8);
87   *p++ = (UChar )((code & 0xff0000)   >>16);
88   *p++ = (UChar )((code & 0xff000000) >>24);
89   return 4;
90 }
91 
92 static int
utf32le_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)93 utf32le_mbc_case_fold(OnigCaseFoldType flag,
94 		      const UChar** pp, const UChar* end, UChar* fold)
95 {
96   const UChar* p = *pp;
97 
98   if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
99 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
100     if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
101       if (*p == 0x49) {
102         *fold++ = 0x31;
103         *fold++ = 0x01;
104       }
105     }
106     else {
107 #endif
108       *fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
109       *fold++ = 0;
110 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
111     }
112 #endif
113 
114     *fold++ = 0;
115     *fold   = 0;
116     *pp += 4;
117     return 4;
118   }
119   else
120     return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF32_LE, flag, pp, end,
121                                          fold);
122 }
123 
124 #if 0
125 static int
126 utf32le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
127 {
128   const UChar* p = *pp;
129 
130   (*pp) += 4;
131 
132   if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
133     int c, v;
134 
135     if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
136       return TRUE;
137     }
138 
139     c = *p;
140     v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
141                        (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
142     if ((v | BIT_CTYPE_LOWER) != 0) {
143       /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
144       if (c >= 0xaa && c <= 0xba)
145         return FALSE;
146       else
147         return TRUE;
148     }
149     return (v != 0 ? TRUE : FALSE);
150   }
151 
152   return FALSE;
153 }
154 #endif
155 
156 static UChar*
utf32le_left_adjust_char_head(const UChar * start,const UChar * s)157 utf32le_left_adjust_char_head(const UChar* start, const UChar* s)
158 {
159   int rem;
160 
161   if (s <= start) return (UChar* )s;
162 
163   rem = (s - start) % 4;
164   return (UChar* )(s - rem);
165 }
166 
167 static int
utf32le_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])168 utf32le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
169     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
170 {
171   return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF32_LE,
172 						    flag, p, end, items);
173 }
174 
175 OnigEncodingType OnigEncodingUTF32_LE = {
176   utf32le_mbc_enc_len,
177   "UTF-32LE",   /* name */
178   4,            /* max byte length */
179   4,            /* min byte length */
180   utf32le_is_mbc_newline,
181   utf32le_mbc_to_code,
182   utf32le_code_to_mbclen,
183   utf32le_code_to_mbc,
184   utf32le_mbc_case_fold,
185   onigenc_unicode_apply_all_case_fold,
186   utf32le_get_case_fold_codes_by_str,
187   onigenc_unicode_property_name_to_ctype,
188   onigenc_unicode_is_code_ctype,
189   onigenc_utf16_32_get_ctype_code_range,
190   utf32le_left_adjust_char_head,
191   onigenc_always_false_is_allowed_reverse_match,
192   NULL, /* init */
193   NULL, /* is_initialized */
194   is_valid_mbc_string
195 };
196