1 |
/*************************************************
|
2 |
* Perl-Compatible Regular Expressions *
|
3 |
*************************************************/
|
4 |
|
5 |
/* PCRE is a library of functions to support regular expressions whose syntax
|
6 |
and semantics are as close as possible to those of the Perl 5 language.
|
7 |
|
8 |
Written by Philip Hazel
|
9 |
Copyright (c) 1997-2007 University of Cambridge
|
10 |
|
11 |
-----------------------------------------------------------------------------
|
12 |
Redistribution and use in source and binary forms, with or without
|
13 |
modification, are permitted provided that the following conditions are met:
|
14 |
|
15 |
* Redistributions of source code must retain the above copyright notice,
|
16 |
this list of conditions and the following disclaimer.
|
17 |
|
18 |
* Redistributions in binary form must reproduce the above copyright
|
19 |
notice, this list of conditions and the following disclaimer in the
|
20 |
documentation and/or other materials provided with the distribution.
|
21 |
|
22 |
* Neither the name of the University of Cambridge nor the names of its
|
23 |
contributors may be used to endorse or promote products derived from
|
24 |
this software without specific prior written permission.
|
25 |
|
26 |
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
27 |
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
28 |
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
29 |
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
30 |
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
31 |
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
32 |
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
33 |
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
34 |
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
35 |
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
36 |
POSSIBILITY OF SUCH DAMAGE.
|
37 |
-----------------------------------------------------------------------------
|
38 |
*/
|
39 |
|
40 |
|
41 |
/* This module contains some fixed tables that are used by more than one of the
|
42 |
PCRE code modules. The tables are also #included by the pcretest program, which
|
43 |
uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
|
44 |
clashes with the library. */
|
45 |
|
46 |
|
47 |
#ifdef HAVE_CONFIG_H
|
48 |
#include "config.h"
|
49 |
#endif
|
50 |
|
51 |
#include "pcre_internal.h"
|
52 |
|
53 |
|
54 |
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
|
55 |
the definition is next to the definition of the opcodes in pcre_internal.h. */
|
56 |
|
57 |
const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
|
58 |
|
59 |
|
60 |
|
61 |
/*************************************************
|
62 |
* Tables for UTF-8 support *
|
63 |
*************************************************/
|
64 |
|
65 |
/* These are the breakpoints for different numbers of bytes in a UTF-8
|
66 |
character. */
|
67 |
|
68 |
#ifdef SUPPORT_UTF8
|
69 |
|
70 |
const int _pcre_utf8_table1[] =
|
71 |
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
|
72 |
|
73 |
const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);
|
74 |
|
75 |
/* These are the indicator bits and the mask for the data bits to set in the
|
76 |
first byte of a character, indexed by the number of additional bytes. */
|
77 |
|
78 |
const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
|
79 |
const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
|
80 |
|
81 |
/* Table of the number of extra bytes, indexed by the first byte masked with
|
82 |
0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
|
83 |
|
84 |
const uschar _pcre_utf8_table4[] = {
|
85 |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
86 |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
87 |
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
|
88 |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
|
89 |
|
90 |
/* The pcre_utt[] table below translates Unicode property names into type and
|
91 |
code values. It is searched by binary chop, so must be in collating sequence of
|
92 |
name. Originally, the table contained pointers to the name strings in the first
|
93 |
field of each entry. However, that leads to a large number of relocations when
|
94 |
a shared library is dynamically loaded. A significant reduction is made by
|
95 |
putting all the names into a single, large string and then using offsets in the
|
96 |
table itself. Maintenance is more error-prone, but frequent changes to this
|
97 |
data is unlikely. */
|
98 |
|
99 |
const char _pcre_utt_names[] =
|
100 |
"Any\0"
|
101 |
"Arabic\0"
|
102 |
"Armenian\0"
|
103 |
"Balinese\0"
|
104 |
"Bengali\0"
|
105 |
"Bopomofo\0"
|
106 |
"Braille\0"
|
107 |
"Buginese\0"
|
108 |
"Buhid\0"
|
109 |
"C\0"
|
110 |
"Canadian_Aboriginal\0"
|
111 |
"Cc\0"
|
112 |
"Cf\0"
|
113 |
"Cherokee\0"
|
114 |
"Cn\0"
|
115 |
"Co\0"
|
116 |
"Common\0"
|
117 |
"Coptic\0"
|
118 |
"Cs\0"
|
119 |
"Cuneiform\0"
|
120 |
"Cypriot\0"
|
121 |
"Cyrillic\0"
|
122 |
"Deseret\0"
|
123 |
"Devanagari\0"
|
124 |
"Ethiopic\0"
|
125 |
"Georgian\0"
|
126 |
"Glagolitic\0"
|
127 |
"Gothic\0"
|
128 |
"Greek\0"
|
129 |
"Gujarati\0"
|
130 |
"Gurmukhi\0"
|
131 |
"Han\0"
|
132 |
"Hangul\0"
|
133 |
"Hanunoo\0"
|
134 |
"Hebrew\0"
|
135 |
"Hiragana\0"
|
136 |
"Inherited\0"
|
137 |
"Kannada\0"
|
138 |
"Katakana\0"
|
139 |
"Kharoshthi\0"
|
140 |
"Khmer\0"
|
141 |
"L\0"
|
142 |
"L&\0"
|
143 |
"Lao\0"
|
144 |
"Latin\0"
|
145 |
"Limbu\0"
|
146 |
"Linear_B\0"
|
147 |
"Ll\0"
|
148 |
"Lm\0"
|
149 |
"Lo\0"
|
150 |
"Lt\0"
|
151 |
"Lu\0"
|
152 |
"M\0"
|
153 |
"Malayalam\0"
|
154 |
"Mc\0"
|
155 |
"Me\0"
|
156 |
"Mn\0"
|
157 |
"Mongolian\0"
|
158 |
"Myanmar\0"
|
159 |
"N\0"
|
160 |
"Nd\0"
|
161 |
"New_Tai_Lue\0"
|
162 |
"Nko\0"
|
163 |
"Nl\0"
|
164 |
"No\0"
|
165 |
"Ogham\0"
|
166 |
"Old_Italic\0"
|
167 |
"Old_Persian\0"
|
168 |
"Oriya\0"
|
169 |
"Osmanya\0"
|
170 |
"P\0"
|
171 |
"Pc\0"
|
172 |
"Pd\0"
|
173 |
"Pe\0"
|
174 |
"Pf\0"
|
175 |
"Phags_Pa\0"
|
176 |
"Phoenician\0"
|
177 |
"Pi\0"
|
178 |
"Po\0"
|
179 |
"Ps\0"
|
180 |
"Runic\0"
|
181 |
"S\0"
|
182 |
"Sc\0"
|
183 |
"Shavian\0"
|
184 |
"Sinhala\0"
|
185 |
"Sk\0"
|
186 |
"Sm\0"
|
187 |
"So\0"
|
188 |
"Syloti_Nagri\0"
|
189 |
"Syriac\0"
|
190 |
"Tagalog\0"
|
191 |
"Tagbanwa\0"
|
192 |
"Tai_Le\0"
|
193 |
"Tamil\0"
|
194 |
"Telugu\0"
|
195 |
"Thaana\0"
|
196 |
"Thai\0"
|
197 |
"Tibetan\0"
|
198 |
"Tifinagh\0"
|
199 |
"Ugaritic\0"
|
200 |
"Yi\0"
|
201 |
"Z\0"
|
202 |
"Zl\0"
|
203 |
"Zp\0"
|
204 |
"Zs\0";
|
205 |
|
206 |
const ucp_type_table _pcre_utt[] = {
|
207 |
{ 0, PT_ANY, 0 },
|
208 |
{ 4, PT_SC, ucp_Arabic },
|
209 |
{ 11, PT_SC, ucp_Armenian },
|
210 |
{ 20, PT_SC, ucp_Balinese },
|
211 |
{ 29, PT_SC, ucp_Bengali },
|
212 |
{ 37, PT_SC, ucp_Bopomofo },
|
213 |
{ 46, PT_SC, ucp_Braille },
|
214 |
{ 54, PT_SC, ucp_Buginese },
|
215 |
{ 63, PT_SC, ucp_Buhid },
|
216 |
{ 69, PT_GC, ucp_C },
|
217 |
{ 71, PT_SC, ucp_Canadian_Aboriginal },
|
218 |
{ 91, PT_PC, ucp_Cc },
|
219 |
{ 94, PT_PC, ucp_Cf },
|
220 |
{ 97, PT_SC, ucp_Cherokee },
|
221 |
{ 106, PT_PC, ucp_Cn },
|
222 |
{ 109, PT_PC, ucp_Co },
|
223 |
{ 112, PT_SC, ucp_Common },
|
224 |
{ 119, PT_SC, ucp_Coptic },
|
225 |
{ 126, PT_PC, ucp_Cs },
|
226 |
{ 129, PT_SC, ucp_Cuneiform },
|
227 |
{ 139, PT_SC, ucp_Cypriot },
|
228 |
{ 147, PT_SC, ucp_Cyrillic },
|
229 |
{ 156, PT_SC, ucp_Deseret },
|
230 |
{ 164, PT_SC, ucp_Devanagari },
|
231 |
{ 175, PT_SC, ucp_Ethiopic },
|
232 |
{ 184, PT_SC, ucp_Georgian },
|
233 |
{ 193, PT_SC, ucp_Glagolitic },
|
234 |
{ 204, PT_SC, ucp_Gothic },
|
235 |
{ 211, PT_SC, ucp_Greek },
|
236 |
{ 217, PT_SC, ucp_Gujarati },
|
237 |
{ 226, PT_SC, ucp_Gurmukhi },
|
238 |
{ 235, PT_SC, ucp_Han },
|
239 |
{ 239, PT_SC, ucp_Hangul },
|
240 |
{ 246, PT_SC, ucp_Hanunoo },
|
241 |
{ 254, PT_SC, ucp_Hebrew },
|
242 |
{ 261, PT_SC, ucp_Hiragana },
|
243 |
{ 270, PT_SC, ucp_Inherited },
|
244 |
{ 280, PT_SC, ucp_Kannada },
|
245 |
{ 288, PT_SC, ucp_Katakana },
|
246 |
{ 297, PT_SC, ucp_Kharoshthi },
|
247 |
{ 308, PT_SC, ucp_Khmer },
|
248 |
{ 314, PT_GC, ucp_L },
|
249 |
{ 316, PT_LAMP, 0 },
|
250 |
{ 319, PT_SC, ucp_Lao },
|
251 |
{ 323, PT_SC, ucp_Latin },
|
252 |
{ 329, PT_SC, ucp_Limbu },
|
253 |
{ 335, PT_SC, ucp_Linear_B },
|
254 |
{ 344, PT_PC, ucp_Ll },
|
255 |
{ 347, PT_PC, ucp_Lm },
|
256 |
{ 350, PT_PC, ucp_Lo },
|
257 |
{ 353, PT_PC, ucp_Lt },
|
258 |
{ 356, PT_PC, ucp_Lu },
|
259 |
{ 359, PT_GC, ucp_M },
|
260 |
{ 361, PT_SC, ucp_Malayalam },
|
261 |
{ 371, PT_PC, ucp_Mc },
|
262 |
{ 374, PT_PC, ucp_Me },
|
263 |
{ 377, PT_PC, ucp_Mn },
|
264 |
{ 380, PT_SC, ucp_Mongolian },
|
265 |
{ 390, PT_SC, ucp_Myanmar },
|
266 |
{ 398, PT_GC, ucp_N },
|
267 |
{ 400, PT_PC, ucp_Nd },
|
268 |
{ 403, PT_SC, ucp_New_Tai_Lue },
|
269 |
{ 415, PT_SC, ucp_Nko },
|
270 |
{ 419, PT_PC, ucp_Nl },
|
271 |
{ 422, PT_PC, ucp_No },
|
272 |
{ 425, PT_SC, ucp_Ogham },
|
273 |
{ 431, PT_SC, ucp_Old_Italic },
|
274 |
{ 442, PT_SC, ucp_Old_Persian },
|
275 |
{ 454, PT_SC, ucp_Oriya },
|
276 |
{ 460, PT_SC, ucp_Osmanya },
|
277 |
{ 468, PT_GC, ucp_P },
|
278 |
{ 470, PT_PC, ucp_Pc },
|
279 |
{ 473, PT_PC, ucp_Pd },
|
280 |
{ 476, PT_PC, ucp_Pe },
|
281 |
{ 479, PT_PC, ucp_Pf },
|
282 |
{ 482, PT_SC, ucp_Phags_Pa },
|
283 |
{ 491, PT_SC, ucp_Phoenician },
|
284 |
{ 502, PT_PC, ucp_Pi },
|
285 |
{ 505, PT_PC, ucp_Po },
|
286 |
{ 508, PT_PC, ucp_Ps },
|
287 |
{ 511, PT_SC, ucp_Runic },
|
288 |
{ 517, PT_GC, ucp_S },
|
289 |
{ 519, PT_PC, ucp_Sc },
|
290 |
{ 522, PT_SC, ucp_Shavian },
|
291 |
{ 530, PT_SC, ucp_Sinhala },
|
292 |
{ 538, PT_PC, ucp_Sk },
|
293 |
{ 541, PT_PC, ucp_Sm },
|
294 |
{ 544, PT_PC, ucp_So },
|
295 |
{ 547, PT_SC, ucp_Syloti_Nagri },
|
296 |
{ 560, PT_SC, ucp_Syriac },
|
297 |
{ 567, PT_SC, ucp_Tagalog },
|
298 |
{ 575, PT_SC, ucp_Tagbanwa },
|
299 |
{ 584, PT_SC, ucp_Tai_Le },
|
300 |
{ 591, PT_SC, ucp_Tamil },
|
301 |
{ 597, PT_SC, ucp_Telugu },
|
302 |
{ 604, PT_SC, ucp_Thaana },
|
303 |
{ 611, PT_SC, ucp_Thai },
|
304 |
{ 616, PT_SC, ucp_Tibetan },
|
305 |
{ 624, PT_SC, ucp_Tifinagh },
|
306 |
{ 633, PT_SC, ucp_Ugaritic },
|
307 |
{ 642, PT_SC, ucp_Yi },
|
308 |
{ 645, PT_GC, ucp_Z },
|
309 |
{ 647, PT_PC, ucp_Zl },
|
310 |
{ 650, PT_PC, ucp_Zp },
|
311 |
{ 653, PT_PC, ucp_Zs }
|
312 |
};
|
313 |
|
314 |
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
|
315 |
|
316 |
#endif /* SUPPORT_UTF8 */
|
317 |
|
318 |
/* End of pcre_tables.c */
|