1 /**********************************************************************
2   iso8859_16.c -  Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5  * Copyright (c) 2002-2007  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_16_TO_LOWER_CASE(c) EncISO_8859_16_ToLowerCaseTable[c]
33 #define ENC_IS_ISO_8859_16_CTYPE(code,ctype) \
34   ((EncISO_8859_16_CtypeTable[code] & ctype) != 0)
35 
36 static const UChar EncISO_8859_16_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', '\242', '\242', '\263', '\245', '\245', '\250', '\247',
58   '\250', '\251', '\272', '\253', '\256', '\255', '\256', '\277',
59   '\260', '\261', '\271', '\263', '\270', '\265', '\266', '\267',
60   '\270', '\271', '\272', '\273', '\275', '\275', '\377', '\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', '\367',
64   '\370', '\371', '\372', '\373', '\374', '\375', '\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_16_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, 0x14a2, 0x10e2, 0x14a2, 0x00a0, 0x01a0, 0x14a2, 0x00a0,
93   0x10e2, 0x00a0, 0x14a2, 0x01a0, 0x14a2, 0x01a0, 0x10e2, 0x14a2,
94   0x00a0, 0x00a0, 0x14a2, 0x10e2, 0x14a2, 0x01a0, 0x00a0, 0x01a0,
95   0x10e2, 0x10e2, 0x10e2, 0x01a0, 0x14a2, 0x10e2, 0x14a2, 0x10e2,
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, 0x14a2,
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, 0x10e2,
103   0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2, 0x10e2
104 };
105 
106 static int
mbc_to_normalize(OnigAmbigType flag,const UChar ** pp,const UChar * end,UChar * lower)107 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_16_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
is_mbc_ambiguous(OnigAmbigType flag,const UChar ** pp,const UChar * end)126 is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
127 {
128   const UChar* p = *pp;
129 
130   (*pp)++;
131   if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
132        ONIGENC_IS_MBC_ASCII(p)) ||
133       ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
134        !ONIGENC_IS_MBC_ASCII(p))) {
135     int v = (EncISO_8859_16_CtypeTable[*p] &
136              (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
137 
138     if ((v | ONIGENC_CTYPE_LOWER) != 0) {
139       /* 0xdf is lower case letter, but can't convert. */
140       if (*p == 0xdf)
141         return FALSE;
142       else
143         return TRUE;
144     }
145 
146     return (v != 0 ? TRUE : FALSE);
147   }
148   return FALSE;
149 }
150 
151 static int
is_code_ctype(OnigCodePoint code,unsigned int ctype)152 is_code_ctype(OnigCodePoint code, unsigned int ctype)
153 {
154   if (code < 256)
155     return ENC_IS_ISO_8859_16_CTYPE(code, ctype);
156   else
157     return FALSE;
158 }
159 
160 static int
get_all_pair_ambig_codes(OnigAmbigType flag,const OnigPairAmbigCodes ** ccs)161 get_all_pair_ambig_codes(OnigAmbigType flag, const OnigPairAmbigCodes** ccs)
162 {
163   static const OnigPairAmbigCodes cc[] = {
164    { 0xa1, 0xa2 },
165    { 0xa2, 0xa1 },
166    { 0xa3, 0xb3 },
167    { 0xa6, 0xa8 },
168    { 0xa8, 0xa6 },
169    { 0xaa, 0xba },
170    { 0xac, 0xae },
171    { 0xae, 0xac },
172    { 0xaf, 0xbf },
173 
174    { 0xb2, 0xb9 },
175    { 0xb3, 0xa3 },
176    { 0xb4, 0xb8 },
177    { 0xb8, 0xb4 },
178    { 0xb9, 0xb2 },
179    { 0xba, 0xaa },
180    { 0xbc, 0xbd },
181    { 0xbd, 0xbc },
182    { 0xbe, 0xff },
183    { 0xbf, 0xaf },
184 
185    { 0xc0, 0xe0 },
186    { 0xc1, 0xe1 },
187    { 0xc2, 0xe2 },
188    { 0xc3, 0xe3 },
189    { 0xc4, 0xe4 },
190    { 0xc5, 0xe5 },
191    { 0xc6, 0xe6 },
192    { 0xc7, 0xe7 },
193    { 0xc8, 0xe8 },
194    { 0xc9, 0xe9 },
195    { 0xca, 0xea },
196    { 0xcb, 0xeb },
197    { 0xcc, 0xec },
198    { 0xcd, 0xed },
199    { 0xce, 0xee },
200    { 0xcf, 0xef },
201 
202    { 0xd0, 0xf0 },
203    { 0xd1, 0xf1 },
204    { 0xd2, 0xf2 },
205    { 0xd3, 0xf3 },
206    { 0xd4, 0xf4 },
207    { 0xd5, 0xf5 },
208    { 0xd6, 0xf6 },
209    { 0xd7, 0xf7 },
210    { 0xd8, 0xf8 },
211    { 0xd9, 0xf9 },
212    { 0xda, 0xfa },
213    { 0xdb, 0xfb },
214    { 0xdc, 0xfc },
215    { 0xdd, 0xfd },
216    { 0xde, 0xfe },
217 
218    { 0xe0, 0xc0 },
219    { 0xe1, 0xc1 },
220    { 0xe2, 0xc2 },
221    { 0xe3, 0xc3 },
222    { 0xe4, 0xc4 },
223    { 0xe5, 0xc5 },
224    { 0xe6, 0xc6 },
225    { 0xe7, 0xc7 },
226    { 0xe8, 0xc8 },
227    { 0xe9, 0xc9 },
228    { 0xea, 0xca },
229    { 0xeb, 0xcb },
230    { 0xec, 0xcc },
231    { 0xed, 0xcd },
232    { 0xee, 0xce },
233    { 0xef, 0xcf },
234 
235    { 0xf0, 0xd0 },
236    { 0xf1, 0xd1 },
237    { 0xf2, 0xd2 },
238    { 0xf3, 0xd3 },
239    { 0xf4, 0xd4 },
240    { 0xf5, 0xd5 },
241    { 0xf6, 0xd6 },
242    { 0xf7, 0xd7 },
243    { 0xf8, 0xd8 },
244    { 0xf9, 0xd9 },
245    { 0xfa, 0xda },
246    { 0xfb, 0xdb },
247    { 0xfc, 0xdc },
248    { 0xfd, 0xdd },
249    { 0xfe, 0xde },
250    { 0xff, 0xbe }
251   };
252 
253   if (flag == ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) {
254     *ccs = OnigAsciiPairAmbigCodes;
255     return 52;
256   }
257   if (flag == ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) {
258     *ccs = cc;
259     return sizeof(cc) / sizeof(OnigPairAmbigCodes);
260   }
261   else
262     return 0;
263 }
264 
265 OnigEncodingType OnigEncodingISO_8859_16 = {
266   onigenc_single_byte_mbc_enc_len,
267   "ISO-8859-16",  /* name */
268   1,             /* max enc length */
269   1,             /* min enc length */
270   (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
271    ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
272   {
273       (OnigCodePoint )'\\'                       /* esc */
274     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.'  */
275     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*'  */
276     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
277     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
278     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
279   },
280   onigenc_is_mbc_newline_0x0a,
281   onigenc_single_byte_mbc_to_code,
282   onigenc_single_byte_code_to_mbclen,
283   onigenc_single_byte_code_to_mbc,
284   mbc_to_normalize,
285   is_mbc_ambiguous,
286   get_all_pair_ambig_codes,
287   onigenc_ess_tsett_get_all_comp_ambig_codes,
288   is_code_ctype,
289   onigenc_not_support_get_ctype_code_range,
290   onigenc_single_byte_left_adjust_char_head,
291   onigenc_always_true_is_allowed_reverse_match
292 };
293