1 |
– |
/* $Id$ */ |
2 |
– |
|
1 |
|
/************************************************* |
2 |
|
* Perl-Compatible Regular Expressions * |
3 |
|
*************************************************/ |
6 |
|
and semantics are as close as possible to those of the Perl 5 language. |
7 |
|
|
8 |
|
Written by Philip Hazel |
9 |
< |
Copyright (c) 1997-2005 University of Cambridge |
9 |
> |
Copyright (c) 1997-2009 University of Cambridge |
10 |
|
|
11 |
|
----------------------------------------------------------------------------- |
12 |
|
Redistribution and use in source and binary forms, with or without |
39 |
|
|
40 |
|
|
41 |
|
/* This module contains some fixed tables that are used by more than one of the |
42 |
< |
PCRE code modules. */ |
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 |
|
#include "pcre_internal.h" |
48 |
|
|
49 |
|
|
50 |
|
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that |
51 |
< |
the definition is next to the definition of the opcodes in internal.h. */ |
51 |
> |
the definition is next to the definition of the opcodes in pcre_internal.h. */ |
52 |
|
|
53 |
|
const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; |
54 |
|
|
55 |
+ |
|
56 |
+ |
|
57 |
+ |
/************************************************* |
58 |
+ |
* Tables for UTF-8 support * |
59 |
+ |
*************************************************/ |
60 |
+ |
|
61 |
+ |
/* These are the breakpoints for different numbers of bytes in a UTF-8 |
62 |
+ |
character. */ |
63 |
+ |
|
64 |
+ |
#ifdef SUPPORT_UTF8 |
65 |
+ |
|
66 |
+ |
const int _pcre_utf8_table1[] = |
67 |
+ |
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; |
68 |
+ |
|
69 |
+ |
const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int); |
70 |
+ |
|
71 |
+ |
/* These are the indicator bits and the mask for the data bits to set in the |
72 |
+ |
first byte of a character, indexed by the number of additional bytes. */ |
73 |
+ |
|
74 |
+ |
const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; |
75 |
+ |
const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; |
76 |
+ |
|
77 |
+ |
/* Table of the number of extra bytes, indexed by the first byte masked with |
78 |
+ |
0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ |
79 |
+ |
|
80 |
+ |
const uschar _pcre_utf8_table4[] = { |
81 |
+ |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, |
82 |
+ |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, |
83 |
+ |
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, |
84 |
+ |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; |
85 |
+ |
|
86 |
+ |
/* Table to translate from particular type value to the general value. */ |
87 |
+ |
|
88 |
+ |
const int _pcre_ucp_gentype[] = { |
89 |
+ |
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ |
90 |
+ |
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ |
91 |
+ |
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ |
92 |
+ |
ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ |
93 |
+ |
ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ |
94 |
+ |
ucp_P, ucp_P, /* Ps, Po */ |
95 |
+ |
ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ |
96 |
+ |
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ |
97 |
+ |
}; |
98 |
+ |
|
99 |
+ |
/* The pcre_utt[] table below translates Unicode property names into type and |
100 |
+ |
code values. It is searched by binary chop, so must be in collating sequence of |
101 |
+ |
name. Originally, the table contained pointers to the name strings in the first |
102 |
+ |
field of each entry. However, that leads to a large number of relocations when |
103 |
+ |
a shared library is dynamically loaded. A significant reduction is made by |
104 |
+ |
putting all the names into a single, large string and then using offsets in the |
105 |
+ |
table itself. Maintenance is more error-prone, but frequent changes to this |
106 |
+ |
data are unlikely. |
107 |
+ |
|
108 |
+ |
July 2008: There is now a script called maint/GenerateUtt.py that can be used |
109 |
+ |
to generate this data instead of maintaining it entirely by hand. |
110 |
+ |
|
111 |
+ |
The script was updated in March 2009 to generate a new EBCDIC-compliant |
112 |
+ |
version. Like all other character and string literals that are compared against |
113 |
+ |
the regular expression pattern, we must use STR_ macros instead of literal |
114 |
+ |
strings to make sure that UTF-8 support works on EBCDIC platforms. */ |
115 |
+ |
|
116 |
+ |
#define STRING_Any0 STR_A STR_n STR_y "\0" |
117 |
+ |
#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" |
118 |
+ |
#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" |
119 |
+ |
#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" |
120 |
+ |
#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" |
121 |
+ |
#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" |
122 |
+ |
#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" |
123 |
+ |
#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" |
124 |
+ |
#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" |
125 |
+ |
#define STRING_C0 STR_C "\0" |
126 |
+ |
#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" |
127 |
+ |
#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" |
128 |
+ |
#define STRING_Cc0 STR_C STR_c "\0" |
129 |
+ |
#define STRING_Cf0 STR_C STR_f "\0" |
130 |
+ |
#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" |
131 |
+ |
#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" |
132 |
+ |
#define STRING_Cn0 STR_C STR_n "\0" |
133 |
+ |
#define STRING_Co0 STR_C STR_o "\0" |
134 |
+ |
#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" |
135 |
+ |
#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" |
136 |
+ |
#define STRING_Cs0 STR_C STR_s "\0" |
137 |
+ |
#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" |
138 |
+ |
#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" |
139 |
+ |
#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" |
140 |
+ |
#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" |
141 |
+ |
#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" |
142 |
+ |
#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" |
143 |
+ |
#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" |
144 |
+ |
#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" |
145 |
+ |
#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" |
146 |
+ |
#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" |
147 |
+ |
#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" |
148 |
+ |
#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" |
149 |
+ |
#define STRING_Han0 STR_H STR_a STR_n "\0" |
150 |
+ |
#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" |
151 |
+ |
#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" |
152 |
+ |
#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" |
153 |
+ |
#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" |
154 |
+ |
#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" |
155 |
+ |
#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" |
156 |
+ |
#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" |
157 |
+ |
#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" |
158 |
+ |
#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" |
159 |
+ |
#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" |
160 |
+ |
#define STRING_L0 STR_L "\0" |
161 |
+ |
#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" |
162 |
+ |
#define STRING_Lao0 STR_L STR_a STR_o "\0" |
163 |
+ |
#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" |
164 |
+ |
#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" |
165 |
+ |
#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" |
166 |
+ |
#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" |
167 |
+ |
#define STRING_Ll0 STR_L STR_l "\0" |
168 |
+ |
#define STRING_Lm0 STR_L STR_m "\0" |
169 |
+ |
#define STRING_Lo0 STR_L STR_o "\0" |
170 |
+ |
#define STRING_Lt0 STR_L STR_t "\0" |
171 |
+ |
#define STRING_Lu0 STR_L STR_u "\0" |
172 |
+ |
#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" |
173 |
+ |
#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" |
174 |
+ |
#define STRING_M0 STR_M "\0" |
175 |
+ |
#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" |
176 |
+ |
#define STRING_Mc0 STR_M STR_c "\0" |
177 |
+ |
#define STRING_Me0 STR_M STR_e "\0" |
178 |
+ |
#define STRING_Mn0 STR_M STR_n "\0" |
179 |
+ |
#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" |
180 |
+ |
#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" |
181 |
+ |
#define STRING_N0 STR_N "\0" |
182 |
+ |
#define STRING_Nd0 STR_N STR_d "\0" |
183 |
+ |
#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" |
184 |
+ |
#define STRING_Nko0 STR_N STR_k STR_o "\0" |
185 |
+ |
#define STRING_Nl0 STR_N STR_l "\0" |
186 |
+ |
#define STRING_No0 STR_N STR_o "\0" |
187 |
+ |
#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" |
188 |
+ |
#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" |
189 |
+ |
#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" |
190 |
+ |
#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" |
191 |
+ |
#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" |
192 |
+ |
#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" |
193 |
+ |
#define STRING_P0 STR_P "\0" |
194 |
+ |
#define STRING_Pc0 STR_P STR_c "\0" |
195 |
+ |
#define STRING_Pd0 STR_P STR_d "\0" |
196 |
+ |
#define STRING_Pe0 STR_P STR_e "\0" |
197 |
+ |
#define STRING_Pf0 STR_P STR_f "\0" |
198 |
+ |
#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" |
199 |
+ |
#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" |
200 |
+ |
#define STRING_Pi0 STR_P STR_i "\0" |
201 |
+ |
#define STRING_Po0 STR_P STR_o "\0" |
202 |
+ |
#define STRING_Ps0 STR_P STR_s "\0" |
203 |
+ |
#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" |
204 |
+ |
#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" |
205 |
+ |
#define STRING_S0 STR_S "\0" |
206 |
+ |
#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" |
207 |
+ |
#define STRING_Sc0 STR_S STR_c "\0" |
208 |
+ |
#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" |
209 |
+ |
#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" |
210 |
+ |
#define STRING_Sk0 STR_S STR_k "\0" |
211 |
+ |
#define STRING_Sm0 STR_S STR_m "\0" |
212 |
+ |
#define STRING_So0 STR_S STR_o "\0" |
213 |
+ |
#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" |
214 |
+ |
#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" |
215 |
+ |
#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" |
216 |
+ |
#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" |
217 |
+ |
#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" |
218 |
+ |
#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" |
219 |
+ |
#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" |
220 |
+ |
#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" |
221 |
+ |
#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" |
222 |
+ |
#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" |
223 |
+ |
#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" |
224 |
+ |
#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" |
225 |
+ |
#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" |
226 |
+ |
#define STRING_Vai0 STR_V STR_a STR_i "\0" |
227 |
+ |
#define STRING_Yi0 STR_Y STR_i "\0" |
228 |
+ |
#define STRING_Z0 STR_Z "\0" |
229 |
+ |
#define STRING_Zl0 STR_Z STR_l "\0" |
230 |
+ |
#define STRING_Zp0 STR_Z STR_p "\0" |
231 |
+ |
#define STRING_Zs0 STR_Z STR_s "\0" |
232 |
+ |
|
233 |
+ |
const char _pcre_utt_names[] = |
234 |
+ |
STRING_Any0 |
235 |
+ |
STRING_Arabic0 |
236 |
+ |
STRING_Armenian0 |
237 |
+ |
STRING_Balinese0 |
238 |
+ |
STRING_Bengali0 |
239 |
+ |
STRING_Bopomofo0 |
240 |
+ |
STRING_Braille0 |
241 |
+ |
STRING_Buginese0 |
242 |
+ |
STRING_Buhid0 |
243 |
+ |
STRING_C0 |
244 |
+ |
STRING_Canadian_Aboriginal0 |
245 |
+ |
STRING_Carian0 |
246 |
+ |
STRING_Cc0 |
247 |
+ |
STRING_Cf0 |
248 |
+ |
STRING_Cham0 |
249 |
+ |
STRING_Cherokee0 |
250 |
+ |
STRING_Cn0 |
251 |
+ |
STRING_Co0 |
252 |
+ |
STRING_Common0 |
253 |
+ |
STRING_Coptic0 |
254 |
+ |
STRING_Cs0 |
255 |
+ |
STRING_Cuneiform0 |
256 |
+ |
STRING_Cypriot0 |
257 |
+ |
STRING_Cyrillic0 |
258 |
+ |
STRING_Deseret0 |
259 |
+ |
STRING_Devanagari0 |
260 |
+ |
STRING_Ethiopic0 |
261 |
+ |
STRING_Georgian0 |
262 |
+ |
STRING_Glagolitic0 |
263 |
+ |
STRING_Gothic0 |
264 |
+ |
STRING_Greek0 |
265 |
+ |
STRING_Gujarati0 |
266 |
+ |
STRING_Gurmukhi0 |
267 |
+ |
STRING_Han0 |
268 |
+ |
STRING_Hangul0 |
269 |
+ |
STRING_Hanunoo0 |
270 |
+ |
STRING_Hebrew0 |
271 |
+ |
STRING_Hiragana0 |
272 |
+ |
STRING_Inherited0 |
273 |
+ |
STRING_Kannada0 |
274 |
+ |
STRING_Katakana0 |
275 |
+ |
STRING_Kayah_Li0 |
276 |
+ |
STRING_Kharoshthi0 |
277 |
+ |
STRING_Khmer0 |
278 |
+ |
STRING_L0 |
279 |
+ |
STRING_L_AMPERSAND0 |
280 |
+ |
STRING_Lao0 |
281 |
+ |
STRING_Latin0 |
282 |
+ |
STRING_Lepcha0 |
283 |
+ |
STRING_Limbu0 |
284 |
+ |
STRING_Linear_B0 |
285 |
+ |
STRING_Ll0 |
286 |
+ |
STRING_Lm0 |
287 |
+ |
STRING_Lo0 |
288 |
+ |
STRING_Lt0 |
289 |
+ |
STRING_Lu0 |
290 |
+ |
STRING_Lycian0 |
291 |
+ |
STRING_Lydian0 |
292 |
+ |
STRING_M0 |
293 |
+ |
STRING_Malayalam0 |
294 |
+ |
STRING_Mc0 |
295 |
+ |
STRING_Me0 |
296 |
+ |
STRING_Mn0 |
297 |
+ |
STRING_Mongolian0 |
298 |
+ |
STRING_Myanmar0 |
299 |
+ |
STRING_N0 |
300 |
+ |
STRING_Nd0 |
301 |
+ |
STRING_New_Tai_Lue0 |
302 |
+ |
STRING_Nko0 |
303 |
+ |
STRING_Nl0 |
304 |
+ |
STRING_No0 |
305 |
+ |
STRING_Ogham0 |
306 |
+ |
STRING_Ol_Chiki0 |
307 |
+ |
STRING_Old_Italic0 |
308 |
+ |
STRING_Old_Persian0 |
309 |
+ |
STRING_Oriya0 |
310 |
+ |
STRING_Osmanya0 |
311 |
+ |
STRING_P0 |
312 |
+ |
STRING_Pc0 |
313 |
+ |
STRING_Pd0 |
314 |
+ |
STRING_Pe0 |
315 |
+ |
STRING_Pf0 |
316 |
+ |
STRING_Phags_Pa0 |
317 |
+ |
STRING_Phoenician0 |
318 |
+ |
STRING_Pi0 |
319 |
+ |
STRING_Po0 |
320 |
+ |
STRING_Ps0 |
321 |
+ |
STRING_Rejang0 |
322 |
+ |
STRING_Runic0 |
323 |
+ |
STRING_S0 |
324 |
+ |
STRING_Saurashtra0 |
325 |
+ |
STRING_Sc0 |
326 |
+ |
STRING_Shavian0 |
327 |
+ |
STRING_Sinhala0 |
328 |
+ |
STRING_Sk0 |
329 |
+ |
STRING_Sm0 |
330 |
+ |
STRING_So0 |
331 |
+ |
STRING_Sundanese0 |
332 |
+ |
STRING_Syloti_Nagri0 |
333 |
+ |
STRING_Syriac0 |
334 |
+ |
STRING_Tagalog0 |
335 |
+ |
STRING_Tagbanwa0 |
336 |
+ |
STRING_Tai_Le0 |
337 |
+ |
STRING_Tamil0 |
338 |
+ |
STRING_Telugu0 |
339 |
+ |
STRING_Thaana0 |
340 |
+ |
STRING_Thai0 |
341 |
+ |
STRING_Tibetan0 |
342 |
+ |
STRING_Tifinagh0 |
343 |
+ |
STRING_Ugaritic0 |
344 |
+ |
STRING_Vai0 |
345 |
+ |
STRING_Yi0 |
346 |
+ |
STRING_Z0 |
347 |
+ |
STRING_Zl0 |
348 |
+ |
STRING_Zp0 |
349 |
+ |
STRING_Zs0; |
350 |
+ |
|
351 |
+ |
const ucp_type_table _pcre_utt[] = { |
352 |
+ |
{ 0, PT_ANY, 0 }, |
353 |
+ |
{ 4, PT_SC, ucp_Arabic }, |
354 |
+ |
{ 11, PT_SC, ucp_Armenian }, |
355 |
+ |
{ 20, PT_SC, ucp_Balinese }, |
356 |
+ |
{ 29, PT_SC, ucp_Bengali }, |
357 |
+ |
{ 37, PT_SC, ucp_Bopomofo }, |
358 |
+ |
{ 46, PT_SC, ucp_Braille }, |
359 |
+ |
{ 54, PT_SC, ucp_Buginese }, |
360 |
+ |
{ 63, PT_SC, ucp_Buhid }, |
361 |
+ |
{ 69, PT_GC, ucp_C }, |
362 |
+ |
{ 71, PT_SC, ucp_Canadian_Aboriginal }, |
363 |
+ |
{ 91, PT_SC, ucp_Carian }, |
364 |
+ |
{ 98, PT_PC, ucp_Cc }, |
365 |
+ |
{ 101, PT_PC, ucp_Cf }, |
366 |
+ |
{ 104, PT_SC, ucp_Cham }, |
367 |
+ |
{ 109, PT_SC, ucp_Cherokee }, |
368 |
+ |
{ 118, PT_PC, ucp_Cn }, |
369 |
+ |
{ 121, PT_PC, ucp_Co }, |
370 |
+ |
{ 124, PT_SC, ucp_Common }, |
371 |
+ |
{ 131, PT_SC, ucp_Coptic }, |
372 |
+ |
{ 138, PT_PC, ucp_Cs }, |
373 |
+ |
{ 141, PT_SC, ucp_Cuneiform }, |
374 |
+ |
{ 151, PT_SC, ucp_Cypriot }, |
375 |
+ |
{ 159, PT_SC, ucp_Cyrillic }, |
376 |
+ |
{ 168, PT_SC, ucp_Deseret }, |
377 |
+ |
{ 176, PT_SC, ucp_Devanagari }, |
378 |
+ |
{ 187, PT_SC, ucp_Ethiopic }, |
379 |
+ |
{ 196, PT_SC, ucp_Georgian }, |
380 |
+ |
{ 205, PT_SC, ucp_Glagolitic }, |
381 |
+ |
{ 216, PT_SC, ucp_Gothic }, |
382 |
+ |
{ 223, PT_SC, ucp_Greek }, |
383 |
+ |
{ 229, PT_SC, ucp_Gujarati }, |
384 |
+ |
{ 238, PT_SC, ucp_Gurmukhi }, |
385 |
+ |
{ 247, PT_SC, ucp_Han }, |
386 |
+ |
{ 251, PT_SC, ucp_Hangul }, |
387 |
+ |
{ 258, PT_SC, ucp_Hanunoo }, |
388 |
+ |
{ 266, PT_SC, ucp_Hebrew }, |
389 |
+ |
{ 273, PT_SC, ucp_Hiragana }, |
390 |
+ |
{ 282, PT_SC, ucp_Inherited }, |
391 |
+ |
{ 292, PT_SC, ucp_Kannada }, |
392 |
+ |
{ 300, PT_SC, ucp_Katakana }, |
393 |
+ |
{ 309, PT_SC, ucp_Kayah_Li }, |
394 |
+ |
{ 318, PT_SC, ucp_Kharoshthi }, |
395 |
+ |
{ 329, PT_SC, ucp_Khmer }, |
396 |
+ |
{ 335, PT_GC, ucp_L }, |
397 |
+ |
{ 337, PT_LAMP, 0 }, |
398 |
+ |
{ 340, PT_SC, ucp_Lao }, |
399 |
+ |
{ 344, PT_SC, ucp_Latin }, |
400 |
+ |
{ 350, PT_SC, ucp_Lepcha }, |
401 |
+ |
{ 357, PT_SC, ucp_Limbu }, |
402 |
+ |
{ 363, PT_SC, ucp_Linear_B }, |
403 |
+ |
{ 372, PT_PC, ucp_Ll }, |
404 |
+ |
{ 375, PT_PC, ucp_Lm }, |
405 |
+ |
{ 378, PT_PC, ucp_Lo }, |
406 |
+ |
{ 381, PT_PC, ucp_Lt }, |
407 |
+ |
{ 384, PT_PC, ucp_Lu }, |
408 |
+ |
{ 387, PT_SC, ucp_Lycian }, |
409 |
+ |
{ 394, PT_SC, ucp_Lydian }, |
410 |
+ |
{ 401, PT_GC, ucp_M }, |
411 |
+ |
{ 403, PT_SC, ucp_Malayalam }, |
412 |
+ |
{ 413, PT_PC, ucp_Mc }, |
413 |
+ |
{ 416, PT_PC, ucp_Me }, |
414 |
+ |
{ 419, PT_PC, ucp_Mn }, |
415 |
+ |
{ 422, PT_SC, ucp_Mongolian }, |
416 |
+ |
{ 432, PT_SC, ucp_Myanmar }, |
417 |
+ |
{ 440, PT_GC, ucp_N }, |
418 |
+ |
{ 442, PT_PC, ucp_Nd }, |
419 |
+ |
{ 445, PT_SC, ucp_New_Tai_Lue }, |
420 |
+ |
{ 457, PT_SC, ucp_Nko }, |
421 |
+ |
{ 461, PT_PC, ucp_Nl }, |
422 |
+ |
{ 464, PT_PC, ucp_No }, |
423 |
+ |
{ 467, PT_SC, ucp_Ogham }, |
424 |
+ |
{ 473, PT_SC, ucp_Ol_Chiki }, |
425 |
+ |
{ 482, PT_SC, ucp_Old_Italic }, |
426 |
+ |
{ 493, PT_SC, ucp_Old_Persian }, |
427 |
+ |
{ 505, PT_SC, ucp_Oriya }, |
428 |
+ |
{ 511, PT_SC, ucp_Osmanya }, |
429 |
+ |
{ 519, PT_GC, ucp_P }, |
430 |
+ |
{ 521, PT_PC, ucp_Pc }, |
431 |
+ |
{ 524, PT_PC, ucp_Pd }, |
432 |
+ |
{ 527, PT_PC, ucp_Pe }, |
433 |
+ |
{ 530, PT_PC, ucp_Pf }, |
434 |
+ |
{ 533, PT_SC, ucp_Phags_Pa }, |
435 |
+ |
{ 542, PT_SC, ucp_Phoenician }, |
436 |
+ |
{ 553, PT_PC, ucp_Pi }, |
437 |
+ |
{ 556, PT_PC, ucp_Po }, |
438 |
+ |
{ 559, PT_PC, ucp_Ps }, |
439 |
+ |
{ 562, PT_SC, ucp_Rejang }, |
440 |
+ |
{ 569, PT_SC, ucp_Runic }, |
441 |
+ |
{ 575, PT_GC, ucp_S }, |
442 |
+ |
{ 577, PT_SC, ucp_Saurashtra }, |
443 |
+ |
{ 588, PT_PC, ucp_Sc }, |
444 |
+ |
{ 591, PT_SC, ucp_Shavian }, |
445 |
+ |
{ 599, PT_SC, ucp_Sinhala }, |
446 |
+ |
{ 607, PT_PC, ucp_Sk }, |
447 |
+ |
{ 610, PT_PC, ucp_Sm }, |
448 |
+ |
{ 613, PT_PC, ucp_So }, |
449 |
+ |
{ 616, PT_SC, ucp_Sundanese }, |
450 |
+ |
{ 626, PT_SC, ucp_Syloti_Nagri }, |
451 |
+ |
{ 639, PT_SC, ucp_Syriac }, |
452 |
+ |
{ 646, PT_SC, ucp_Tagalog }, |
453 |
+ |
{ 654, PT_SC, ucp_Tagbanwa }, |
454 |
+ |
{ 663, PT_SC, ucp_Tai_Le }, |
455 |
+ |
{ 670, PT_SC, ucp_Tamil }, |
456 |
+ |
{ 676, PT_SC, ucp_Telugu }, |
457 |
+ |
{ 683, PT_SC, ucp_Thaana }, |
458 |
+ |
{ 690, PT_SC, ucp_Thai }, |
459 |
+ |
{ 695, PT_SC, ucp_Tibetan }, |
460 |
+ |
{ 703, PT_SC, ucp_Tifinagh }, |
461 |
+ |
{ 712, PT_SC, ucp_Ugaritic }, |
462 |
+ |
{ 721, PT_SC, ucp_Vai }, |
463 |
+ |
{ 725, PT_SC, ucp_Yi }, |
464 |
+ |
{ 728, PT_GC, ucp_Z }, |
465 |
+ |
{ 730, PT_PC, ucp_Zl }, |
466 |
+ |
{ 733, PT_PC, ucp_Zp }, |
467 |
+ |
{ 736, PT_PC, ucp_Zs } |
468 |
+ |
}; |
469 |
+ |
|
470 |
+ |
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); |
471 |
+ |
|
472 |
+ |
#endif /* SUPPORT_UTF8 */ |
473 |
+ |
|
474 |
|
/* End of pcre_tables.c */ |