xref: /PHP-5.3/ext/mbstring/oniguruma/enc/iso8859_9.c (revision 7aab46a2)
1 /**********************************************************************
2   iso8859_9.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 #define ENC_ISO_8859_9_TO_LOWER_CASE(c) EncISO_8859_9_ToLowerCaseTable[c]
33 #define ENC_IS_ISO_8859_9_CTYPE(code,ctype) \
34   ((EncISO_8859_9_CtypeTable[code] & ctype) != 0)
35 
36 static const UChar EncISO_8859_9_ToLowerCaseTable[256] = {
37   '\000', '\001', '\002', '\003', '\004', '\005', '\006', '\007',
38   '\010', '\011', '\012', '\013', '\014', '\015', '\016', '\017',
39   '\020', '\021', '\022', '\023', '\024', '\025', '\026', '\027',
40   '\030', '\031', '\032', '\033', '\034', '\035', '\036', '\037',
41   '\040', '\041', '\042', '\043', '\044', '\045', '\046', '\047',
42   '\050', '\051', '\052', '\053', '\054', '\055', '\056', '\057',
43   '\060', '\061', '\062', '\063', '\064', '\065', '\066', '\067',
44   '\070', '\071', '\072', '\073', '\074', '\075', '\076', '\077',
45   '\100', '\141', '\142', '\143', '\144', '\145', '\146', '\147',
46   '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157',
47   '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167',
48   '\170', '\171', '\172', '\133', '\134', '\135', '\136', '\137',
49   '\140', '\141', '\142', '\143', '\144', '\145', '\146', '\147',
50   '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157',
51   '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167',
52   '\170', '\171', '\172', '\173', '\174', '\175', '\176', '\177',
53   '\200', '\201', '\202', '\203', '\204', '\205', '\206', '\207',
54   '\210', '\211', '\212', '\213', '\214', '\215', '\216', '\217',
55   '\220', '\221', '\222', '\223', '\224', '\225', '\226', '\227',
56   '\230', '\231', '\232', '\233', '\234', '\235', '\236', '\237',
57   '\240', '\241', '\242', '\243', '\244', '\245', '\246', '\247',
58   '\250', '\251', '\252', '\253', '\254', '\255', '\256', '\257',
59   '\260', '\261', '\262', '\263', '\264', '\265', '\266', '\267',
60   '\270', '\271', '\272', '\273', '\274', '\275', '\276', '\277',
61   '\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
62   '\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
63   '\360', '\361', '\362', '\363', '\364', '\365', '\366', '\327',
64   '\370', '\371', '\372', '\373', '\374', '\335', '\376', '\337',
65   '\340', '\341', '\342', '\343', '\344', '\345', '\346', '\347',
66   '\350', '\351', '\352', '\353', '\354', '\355', '\356', '\357',
67   '\360', '\361', '\362', '\363', '\364', '\365', '\366', '\367',
68   '\370', '\371', '\372', '\373', '\374', '\375', '\376', '\377'
69 };
70 
71 static const unsigned short EncISO_8859_9_CtypeTable[256] = {
72   0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
73   0x2008, 0x220c, 0x2209, 0x2208, 0x2208, 0x2208, 0x2008, 0x2008,
74   0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
75   0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008, 0x2008,
76   0x2284, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0,
77   0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0,
78   0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0, 0x38b0,
79   0x38b0, 0x38b0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x21a0,
80   0x21a0, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x3ca2, 0x34a2,
81   0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2,
82   0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2,
83   0x34a2, 0x34a2, 0x34a2, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x31a0,
84   0x21a0, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x38e2, 0x30e2,
85   0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
86   0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2,
87   0x30e2, 0x30e2, 0x30e2, 0x21a0, 0x21a0, 0x21a0, 0x21a0, 0x2008,
88   0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
89   0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
90   0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
91   0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008, 0x0008,
92   0x0284, 0x01a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0,
93   0x00a0, 0x00a0, 0x10e2, 0x01a0, 0x00a0, 0x01a0, 0x00a0, 0x00a0,
94   0x00a0, 0x00a0, 0x10a0, 0x10a0, 0x00a0, 0x10e2, 0x00a0, 0x01a0,
95   0x00a0, 0x10a0, 0x10e2, 0x01a0, 0x10a0, 0x10a0, 0x10a0, 0x01a0,
96   0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2,
97   0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2,
98   0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x00a0,
99   0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x14a2, 0x10e2,
100   0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2,
101   0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2,
102   0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x00a0,
103   0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2
104 };
105 
106 static int
iso_8859_9_mbc_to_normalize(OnigAmbigType flag,const UChar ** pp,const UChar * end,UChar * lower)107 iso_8859_9_mbc_to_normalize(OnigAmbigType flag,
108                             const UChar** pp, const UChar* end, UChar* lower)
109 {
110   const UChar* p = *pp;
111 
112   if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
113        ONIGENC_IS_MBC_ASCII(p)) ||
114       ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
115        !ONIGENC_IS_MBC_ASCII(p))) {
116     *lower = ENC_ISO_8859_9_TO_LOWER_CASE(*p);
117   }
118   else {
119     *lower = *p;
120   }
121   (*pp)++;
122   return 1; /* return byte length of converted char to lower */
123 }
124 
125 static int
iso_8859_9_is_mbc_ambiguous(OnigAmbigType flag,const UChar ** pp,const UChar * end)126 iso_8859_9_is_mbc_ambiguous(OnigAmbigType flag,
127 			    const UChar** pp, const UChar* end)
128 {
129   const UChar* p = *pp;
130 
131   (*pp)++;
132   if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
133        ONIGENC_IS_MBC_ASCII(p)) ||
134       ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
135        !ONIGENC_IS_MBC_ASCII(p))) {
136     int v = (EncISO_8859_9_CtypeTable[*p] &
137              (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
138 
139     if ((v | ONIGENC_CTYPE_LOWER) != 0) {
140       /* 0xdf etc..  are lower case letter, but can't convert. */
141       if (*p == 0xdf || (*p >= 0xaa && *p <= 0xba))
142         return FALSE;
143       else
144         return TRUE;
145     }
146 
147     return (v != 0 ? TRUE : FALSE);
148   }
149   return FALSE;
150 }
151 
152 static int
iso_8859_9_is_code_ctype(OnigCodePoint code,unsigned int ctype)153 iso_8859_9_is_code_ctype(OnigCodePoint code, unsigned int ctype)
154 {
155   if (code < 256)
156     return ENC_IS_ISO_8859_9_CTYPE(code, ctype);
157   else
158     return FALSE;
159 }
160 
161 static int
iso_8859_9_get_all_pair_ambig_codes(OnigAmbigType flag,const OnigPairAmbigCodes ** ccs)162 iso_8859_9_get_all_pair_ambig_codes(OnigAmbigType flag,
163                                     const OnigPairAmbigCodes** ccs)
164 {
165   static const OnigPairAmbigCodes cc[] = {
166     { 0xc0, 0xe0 },
167     { 0xc1, 0xe1 },
168     { 0xc2, 0xe2 },
169     { 0xc3, 0xe3 },
170     { 0xc4, 0xe4 },
171     { 0xc5, 0xe5 },
172     { 0xc6, 0xe6 },
173     { 0xc7, 0xe7 },
174     { 0xc8, 0xe8 },
175     { 0xc9, 0xe9 },
176     { 0xca, 0xea },
177     { 0xcb, 0xeb },
178     { 0xcc, 0xec },
179     { 0xcd, 0xed },
180     { 0xce, 0xee },
181     { 0xcf, 0xef },
182 
183     { 0xd0, 0xf0 },
184     { 0xd1, 0xf1 },
185     { 0xd2, 0xf2 },
186     { 0xd3, 0xf3 },
187     { 0xd4, 0xf4 },
188     { 0xd5, 0xf5 },
189     { 0xd6, 0xf6 },
190     { 0xd8, 0xf8 },
191     { 0xd9, 0xf9 },
192     { 0xda, 0xfa },
193     { 0xdb, 0xfb },
194     { 0xdc, 0xfc },
195     { 0xdd, 0xfd },
196     { 0xde, 0xfe },
197 
198     { 0xe0, 0xc0 },
199     { 0xe1, 0xc1 },
200     { 0xe2, 0xc2 },
201     { 0xe3, 0xc3 },
202     { 0xe4, 0xc4 },
203     { 0xe5, 0xc5 },
204     { 0xe6, 0xc6 },
205     { 0xe7, 0xc7 },
206     { 0xe8, 0xc8 },
207     { 0xe9, 0xc9 },
208     { 0xea, 0xca },
209     { 0xeb, 0xcb },
210     { 0xec, 0xcc },
211     { 0xed, 0xcd },
212     { 0xee, 0xce },
213     { 0xef, 0xcf },
214 
215     { 0xf0, 0xd0 },
216     { 0xf1, 0xd1 },
217     { 0xf2, 0xd2 },
218     { 0xf3, 0xd3 },
219     { 0xf4, 0xd4 },
220     { 0xf5, 0xd5 },
221     { 0xf6, 0xd6 },
222     { 0xf8, 0xd8 },
223     { 0xf9, 0xd9 },
224     { 0xfa, 0xda },
225     { 0xfb, 0xdb },
226     { 0xfc, 0xdc },
227     { 0xfd, 0xdd },
228     { 0xfe, 0xde }
229   };
230 
231   if (flag == ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) {
232     *ccs = OnigAsciiPairAmbigCodes;
233     return 52;
234   }
235   if (flag == ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) {
236     *ccs = cc;
237     return sizeof(cc) / sizeof(OnigPairAmbigCodes);
238   }
239   else
240     return 0;
241 }
242 
243 OnigEncodingType OnigEncodingISO_8859_9 = {
244   onigenc_single_byte_mbc_enc_len,
245   "ISO-8859-9",  /* name */
246   1,             /* max enc length */
247   1,             /* min enc length */
248   (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
249    ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
250   {
251       (OnigCodePoint )'\\'                       /* esc */
252     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.'  */
253     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*'  */
254     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
255     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
256     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
257   },
258   onigenc_is_mbc_newline_0x0a,
259   onigenc_single_byte_mbc_to_code,
260   onigenc_single_byte_code_to_mbclen,
261   onigenc_single_byte_code_to_mbc,
262   iso_8859_9_mbc_to_normalize,
263   iso_8859_9_is_mbc_ambiguous,
264   iso_8859_9_get_all_pair_ambig_codes,
265   onigenc_ess_tsett_get_all_comp_ambig_codes,
266   iso_8859_9_is_code_ctype,
267   onigenc_not_support_get_ctype_code_range,
268   onigenc_single_byte_left_adjust_char_head,
269   onigenc_always_true_is_allowed_reverse_match
270 };
271