xref: /PHP-5.4/ext/mbstring/oniguruma/enc/utf32_le.c (revision 6284ef11)
1 /**********************************************************************
2   utf32_le.c -  Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5  * Copyright (c) 2002-2006  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)33 utf32le_mbc_enc_len(const UChar* p)
34 {
35   return 4;
36 }
37 
38 static int
utf32le_is_mbc_newline(const UChar * p,const UChar * end)39 utf32le_is_mbc_newline(const UChar* p, const UChar* end)
40 {
41   if (p + 3 < end) {
42     if (*p == 0x0a && *(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0)
43       return 1;
44 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
45     if ((*p == 0x0d || *p == 0x85) && *(p+1) == 0x00
46 	&& (p+2) == 0x00 && *(p+3) == 0x00)
47       return 1;
48     if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28)
49 	&& *(p+2) == 0x00 && *(p+3) == 0x00)
50       return 1;
51 #endif
52   }
53   return 0;
54 }
55 
56 static OnigCodePoint
utf32le_mbc_to_code(const UChar * p,const UChar * end)57 utf32le_mbc_to_code(const UChar* p, const UChar* end)
58 {
59   return (OnigCodePoint )(((p[3] * 256 + p[2]) * 256 + p[1]) * 256 + p[0]);
60 }
61 
62 static int
utf32le_code_to_mbclen(OnigCodePoint code)63 utf32le_code_to_mbclen(OnigCodePoint code)
64 {
65   return 4;
66 }
67 
68 static int
utf32le_code_to_mbc(OnigCodePoint code,UChar * buf)69 utf32le_code_to_mbc(OnigCodePoint code, UChar *buf)
70 {
71   UChar* p = buf;
72 
73   *p++ = (UChar ) (code & 0xff);
74   *p++ = (UChar )((code & 0xff00)     >> 8);
75   *p++ = (UChar )((code & 0xff0000)   >>16);
76   *p++ = (UChar )((code & 0xff000000) >>24);
77   return 4;
78 }
79 
80 static int
utf32le_mbc_to_normalize(OnigAmbigType flag,const UChar ** pp,const UChar * end,UChar * lower)81 utf32le_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
82                          UChar* lower)
83 {
84   const UChar* p = *pp;
85 
86   if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
87     if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
88 	 ONIGENC_IS_MBC_ASCII(p)) ||
89 	((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
90 	 !ONIGENC_IS_MBC_ASCII(p))) {
91       *lower++ = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
92     }
93     else {
94       *lower++ = *p;
95     }
96     *lower++ = '\0';
97     *lower++ = '\0';
98     *lower   = '\0';
99 
100     (*pp) += 4;
101     return 4;  /* return byte length of converted char to lower */
102   }
103   else {
104     int len = 4;
105     if (lower != p) {
106       int i;
107       for (i = 0; i < len; i++) {
108 	*lower++ = *p++;
109       }
110     }
111     (*pp) += len;
112     return len; /* return byte length of converted char to lower */
113   }
114 }
115 
116 static int
utf32le_is_mbc_ambiguous(OnigAmbigType flag,const UChar ** pp,const UChar * end)117 utf32le_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
118 {
119   const UChar* p = *pp;
120 
121   (*pp) += 4;
122 
123   if (*(p+1) == 0 && *(p+2) == 0 && *(p+3) == 0) {
124     int c, v;
125 
126     if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
127 	 ONIGENC_IS_MBC_ASCII(p)) ||
128 	((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
129 	 !ONIGENC_IS_MBC_ASCII(p))) {
130       c = *p;
131       v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
132                        (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
133       if ((v | ONIGENC_CTYPE_LOWER) != 0) {
134         /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
135         if (c >= 0xaa && c <= 0xba)
136           return FALSE;
137         else
138           return TRUE;
139       }
140       return (v != 0 ? TRUE : FALSE);
141     }
142   }
143 
144   return FALSE;
145 }
146 
147 static UChar*
utf32le_left_adjust_char_head(const UChar * start,const UChar * s)148 utf32le_left_adjust_char_head(const UChar* start, const UChar* s)
149 {
150   int rem;
151 
152   if (s <= start) return (UChar* )s;
153 
154   rem = (s - start) % 4;
155   return (UChar* )(s - rem);
156 }
157 
158 OnigEncodingType OnigEncodingUTF32_LE = {
159   utf32le_mbc_enc_len,
160   "UTF-32LE",   /* name */
161   4,            /* max byte length */
162   4,            /* min byte length */
163   (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
164    ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
165   {
166       (OnigCodePoint )'\\'                       /* esc */
167     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.'  */
168     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*'  */
169     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
170     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
171     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
172   },
173   utf32le_is_mbc_newline,
174   utf32le_mbc_to_code,
175   utf32le_code_to_mbclen,
176   utf32le_code_to_mbc,
177   utf32le_mbc_to_normalize,
178   utf32le_is_mbc_ambiguous,
179   onigenc_iso_8859_1_get_all_pair_ambig_codes,
180   onigenc_ess_tsett_get_all_comp_ambig_codes,
181   onigenc_unicode_is_code_ctype,
182   onigenc_unicode_get_ctype_code_range,
183   utf32le_left_adjust_char_head,
184   onigenc_always_false_is_allowed_reverse_match
185 };
186