Annotation of win32/pcre/pcre_tables.c, revision 1.3
1.1 misha 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
1.3 ! misha 9: Copyright (c) 1997-2009 University of Cambridge
1.1 misha 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:
1.2 misha 90: /* Table to translate from particular type value to the general value. */
91:
92: const int _pcre_ucp_gentype[] = {
93: ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
94: ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
95: ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
96: ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
97: ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
98: ucp_P, ucp_P, /* Ps, Po */
99: ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
100: ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
101: };
102:
1.1 misha 103: /* The pcre_utt[] table below translates Unicode property names into type and
104: code values. It is searched by binary chop, so must be in collating sequence of
105: name. Originally, the table contained pointers to the name strings in the first
106: field of each entry. However, that leads to a large number of relocations when
107: a shared library is dynamically loaded. A significant reduction is made by
108: putting all the names into a single, large string and then using offsets in the
109: table itself. Maintenance is more error-prone, but frequent changes to this
1.2 misha 110: data are unlikely.
111:
1.3 ! misha 112: July 2008: There is now a script called maint/GenerateUtt.py that can be used
! 113: to generate this data instead of maintaining it entirely by hand.
! 114:
! 115: The script was updated in March 2009 to generate a new EBCDIC-compliant
! 116: version. Like all other character and string literals that are compared against
! 117: the regular expression pattern, we must use STR_ macros instead of literal
! 118: strings to make sure that UTF-8 support works on EBCDIC platforms. */
! 119:
! 120: #define STRING_Any0 STR_A STR_n STR_y "\0"
! 121: #define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
! 122: #define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
! 123: #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
! 124: #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
! 125: #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
! 126: #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
! 127: #define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
! 128: #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
! 129: #define STRING_C0 STR_C "\0"
! 130: #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"
! 131: #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
! 132: #define STRING_Cc0 STR_C STR_c "\0"
! 133: #define STRING_Cf0 STR_C STR_f "\0"
! 134: #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
! 135: #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
! 136: #define STRING_Cn0 STR_C STR_n "\0"
! 137: #define STRING_Co0 STR_C STR_o "\0"
! 138: #define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
! 139: #define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
! 140: #define STRING_Cs0 STR_C STR_s "\0"
! 141: #define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
! 142: #define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
! 143: #define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
! 144: #define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
! 145: #define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
! 146: #define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
! 147: #define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
! 148: #define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
! 149: #define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
! 150: #define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
! 151: #define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
! 152: #define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
! 153: #define STRING_Han0 STR_H STR_a STR_n "\0"
! 154: #define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
! 155: #define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
! 156: #define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
! 157: #define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
! 158: #define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
! 159: #define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
! 160: #define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
! 161: #define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
! 162: #define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
! 163: #define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
! 164: #define STRING_L0 STR_L "\0"
! 165: #define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
! 166: #define STRING_Lao0 STR_L STR_a STR_o "\0"
! 167: #define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
! 168: #define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
! 169: #define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
! 170: #define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
! 171: #define STRING_Ll0 STR_L STR_l "\0"
! 172: #define STRING_Lm0 STR_L STR_m "\0"
! 173: #define STRING_Lo0 STR_L STR_o "\0"
! 174: #define STRING_Lt0 STR_L STR_t "\0"
! 175: #define STRING_Lu0 STR_L STR_u "\0"
! 176: #define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
! 177: #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
! 178: #define STRING_M0 STR_M "\0"
! 179: #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
! 180: #define STRING_Mc0 STR_M STR_c "\0"
! 181: #define STRING_Me0 STR_M STR_e "\0"
! 182: #define STRING_Mn0 STR_M STR_n "\0"
! 183: #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
! 184: #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
! 185: #define STRING_N0 STR_N "\0"
! 186: #define STRING_Nd0 STR_N STR_d "\0"
! 187: #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"
! 188: #define STRING_Nko0 STR_N STR_k STR_o "\0"
! 189: #define STRING_Nl0 STR_N STR_l "\0"
! 190: #define STRING_No0 STR_N STR_o "\0"
! 191: #define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
! 192: #define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
! 193: #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"
! 194: #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"
! 195: #define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
! 196: #define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
! 197: #define STRING_P0 STR_P "\0"
! 198: #define STRING_Pc0 STR_P STR_c "\0"
! 199: #define STRING_Pd0 STR_P STR_d "\0"
! 200: #define STRING_Pe0 STR_P STR_e "\0"
! 201: #define STRING_Pf0 STR_P STR_f "\0"
! 202: #define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
! 203: #define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
! 204: #define STRING_Pi0 STR_P STR_i "\0"
! 205: #define STRING_Po0 STR_P STR_o "\0"
! 206: #define STRING_Ps0 STR_P STR_s "\0"
! 207: #define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
! 208: #define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
! 209: #define STRING_S0 STR_S "\0"
! 210: #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
! 211: #define STRING_Sc0 STR_S STR_c "\0"
! 212: #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
! 213: #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
! 214: #define STRING_Sk0 STR_S STR_k "\0"
! 215: #define STRING_Sm0 STR_S STR_m "\0"
! 216: #define STRING_So0 STR_S STR_o "\0"
! 217: #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
! 218: #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"
! 219: #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
! 220: #define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
! 221: #define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
! 222: #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
! 223: #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
! 224: #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
! 225: #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
! 226: #define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
! 227: #define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
! 228: #define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
! 229: #define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
! 230: #define STRING_Vai0 STR_V STR_a STR_i "\0"
! 231: #define STRING_Yi0 STR_Y STR_i "\0"
! 232: #define STRING_Z0 STR_Z "\0"
! 233: #define STRING_Zl0 STR_Z STR_l "\0"
! 234: #define STRING_Zp0 STR_Z STR_p "\0"
! 235: #define STRING_Zs0 STR_Z STR_s "\0"
1.1 misha 236:
237: const char _pcre_utt_names[] =
1.3 ! misha 238: STRING_Any0
! 239: STRING_Arabic0
! 240: STRING_Armenian0
! 241: STRING_Balinese0
! 242: STRING_Bengali0
! 243: STRING_Bopomofo0
! 244: STRING_Braille0
! 245: STRING_Buginese0
! 246: STRING_Buhid0
! 247: STRING_C0
! 248: STRING_Canadian_Aboriginal0
! 249: STRING_Carian0
! 250: STRING_Cc0
! 251: STRING_Cf0
! 252: STRING_Cham0
! 253: STRING_Cherokee0
! 254: STRING_Cn0
! 255: STRING_Co0
! 256: STRING_Common0
! 257: STRING_Coptic0
! 258: STRING_Cs0
! 259: STRING_Cuneiform0
! 260: STRING_Cypriot0
! 261: STRING_Cyrillic0
! 262: STRING_Deseret0
! 263: STRING_Devanagari0
! 264: STRING_Ethiopic0
! 265: STRING_Georgian0
! 266: STRING_Glagolitic0
! 267: STRING_Gothic0
! 268: STRING_Greek0
! 269: STRING_Gujarati0
! 270: STRING_Gurmukhi0
! 271: STRING_Han0
! 272: STRING_Hangul0
! 273: STRING_Hanunoo0
! 274: STRING_Hebrew0
! 275: STRING_Hiragana0
! 276: STRING_Inherited0
! 277: STRING_Kannada0
! 278: STRING_Katakana0
! 279: STRING_Kayah_Li0
! 280: STRING_Kharoshthi0
! 281: STRING_Khmer0
! 282: STRING_L0
! 283: STRING_L_AMPERSAND0
! 284: STRING_Lao0
! 285: STRING_Latin0
! 286: STRING_Lepcha0
! 287: STRING_Limbu0
! 288: STRING_Linear_B0
! 289: STRING_Ll0
! 290: STRING_Lm0
! 291: STRING_Lo0
! 292: STRING_Lt0
! 293: STRING_Lu0
! 294: STRING_Lycian0
! 295: STRING_Lydian0
! 296: STRING_M0
! 297: STRING_Malayalam0
! 298: STRING_Mc0
! 299: STRING_Me0
! 300: STRING_Mn0
! 301: STRING_Mongolian0
! 302: STRING_Myanmar0
! 303: STRING_N0
! 304: STRING_Nd0
! 305: STRING_New_Tai_Lue0
! 306: STRING_Nko0
! 307: STRING_Nl0
! 308: STRING_No0
! 309: STRING_Ogham0
! 310: STRING_Ol_Chiki0
! 311: STRING_Old_Italic0
! 312: STRING_Old_Persian0
! 313: STRING_Oriya0
! 314: STRING_Osmanya0
! 315: STRING_P0
! 316: STRING_Pc0
! 317: STRING_Pd0
! 318: STRING_Pe0
! 319: STRING_Pf0
! 320: STRING_Phags_Pa0
! 321: STRING_Phoenician0
! 322: STRING_Pi0
! 323: STRING_Po0
! 324: STRING_Ps0
! 325: STRING_Rejang0
! 326: STRING_Runic0
! 327: STRING_S0
! 328: STRING_Saurashtra0
! 329: STRING_Sc0
! 330: STRING_Shavian0
! 331: STRING_Sinhala0
! 332: STRING_Sk0
! 333: STRING_Sm0
! 334: STRING_So0
! 335: STRING_Sundanese0
! 336: STRING_Syloti_Nagri0
! 337: STRING_Syriac0
! 338: STRING_Tagalog0
! 339: STRING_Tagbanwa0
! 340: STRING_Tai_Le0
! 341: STRING_Tamil0
! 342: STRING_Telugu0
! 343: STRING_Thaana0
! 344: STRING_Thai0
! 345: STRING_Tibetan0
! 346: STRING_Tifinagh0
! 347: STRING_Ugaritic0
! 348: STRING_Vai0
! 349: STRING_Yi0
! 350: STRING_Z0
! 351: STRING_Zl0
! 352: STRING_Zp0
! 353: STRING_Zs0;
1.1 misha 354:
355: const ucp_type_table _pcre_utt[] = {
1.2 misha 356: { 0, PT_ANY, 0 },
357: { 4, PT_SC, ucp_Arabic },
358: { 11, PT_SC, ucp_Armenian },
359: { 20, PT_SC, ucp_Balinese },
360: { 29, PT_SC, ucp_Bengali },
361: { 37, PT_SC, ucp_Bopomofo },
362: { 46, PT_SC, ucp_Braille },
363: { 54, PT_SC, ucp_Buginese },
364: { 63, PT_SC, ucp_Buhid },
365: { 69, PT_GC, ucp_C },
366: { 71, PT_SC, ucp_Canadian_Aboriginal },
367: { 91, PT_SC, ucp_Carian },
368: { 98, PT_PC, ucp_Cc },
369: { 101, PT_PC, ucp_Cf },
370: { 104, PT_SC, ucp_Cham },
371: { 109, PT_SC, ucp_Cherokee },
372: { 118, PT_PC, ucp_Cn },
373: { 121, PT_PC, ucp_Co },
374: { 124, PT_SC, ucp_Common },
375: { 131, PT_SC, ucp_Coptic },
376: { 138, PT_PC, ucp_Cs },
377: { 141, PT_SC, ucp_Cuneiform },
378: { 151, PT_SC, ucp_Cypriot },
379: { 159, PT_SC, ucp_Cyrillic },
380: { 168, PT_SC, ucp_Deseret },
381: { 176, PT_SC, ucp_Devanagari },
382: { 187, PT_SC, ucp_Ethiopic },
383: { 196, PT_SC, ucp_Georgian },
384: { 205, PT_SC, ucp_Glagolitic },
385: { 216, PT_SC, ucp_Gothic },
386: { 223, PT_SC, ucp_Greek },
387: { 229, PT_SC, ucp_Gujarati },
388: { 238, PT_SC, ucp_Gurmukhi },
389: { 247, PT_SC, ucp_Han },
390: { 251, PT_SC, ucp_Hangul },
391: { 258, PT_SC, ucp_Hanunoo },
392: { 266, PT_SC, ucp_Hebrew },
393: { 273, PT_SC, ucp_Hiragana },
394: { 282, PT_SC, ucp_Inherited },
395: { 292, PT_SC, ucp_Kannada },
396: { 300, PT_SC, ucp_Katakana },
397: { 309, PT_SC, ucp_Kayah_Li },
398: { 318, PT_SC, ucp_Kharoshthi },
399: { 329, PT_SC, ucp_Khmer },
400: { 335, PT_GC, ucp_L },
401: { 337, PT_LAMP, 0 },
402: { 340, PT_SC, ucp_Lao },
403: { 344, PT_SC, ucp_Latin },
404: { 350, PT_SC, ucp_Lepcha },
405: { 357, PT_SC, ucp_Limbu },
406: { 363, PT_SC, ucp_Linear_B },
407: { 372, PT_PC, ucp_Ll },
408: { 375, PT_PC, ucp_Lm },
409: { 378, PT_PC, ucp_Lo },
410: { 381, PT_PC, ucp_Lt },
411: { 384, PT_PC, ucp_Lu },
412: { 387, PT_SC, ucp_Lycian },
413: { 394, PT_SC, ucp_Lydian },
414: { 401, PT_GC, ucp_M },
415: { 403, PT_SC, ucp_Malayalam },
416: { 413, PT_PC, ucp_Mc },
417: { 416, PT_PC, ucp_Me },
418: { 419, PT_PC, ucp_Mn },
419: { 422, PT_SC, ucp_Mongolian },
420: { 432, PT_SC, ucp_Myanmar },
421: { 440, PT_GC, ucp_N },
422: { 442, PT_PC, ucp_Nd },
423: { 445, PT_SC, ucp_New_Tai_Lue },
424: { 457, PT_SC, ucp_Nko },
425: { 461, PT_PC, ucp_Nl },
426: { 464, PT_PC, ucp_No },
427: { 467, PT_SC, ucp_Ogham },
428: { 473, PT_SC, ucp_Ol_Chiki },
429: { 482, PT_SC, ucp_Old_Italic },
430: { 493, PT_SC, ucp_Old_Persian },
431: { 505, PT_SC, ucp_Oriya },
432: { 511, PT_SC, ucp_Osmanya },
433: { 519, PT_GC, ucp_P },
434: { 521, PT_PC, ucp_Pc },
435: { 524, PT_PC, ucp_Pd },
436: { 527, PT_PC, ucp_Pe },
437: { 530, PT_PC, ucp_Pf },
438: { 533, PT_SC, ucp_Phags_Pa },
439: { 542, PT_SC, ucp_Phoenician },
440: { 553, PT_PC, ucp_Pi },
441: { 556, PT_PC, ucp_Po },
442: { 559, PT_PC, ucp_Ps },
443: { 562, PT_SC, ucp_Rejang },
444: { 569, PT_SC, ucp_Runic },
445: { 575, PT_GC, ucp_S },
446: { 577, PT_SC, ucp_Saurashtra },
447: { 588, PT_PC, ucp_Sc },
448: { 591, PT_SC, ucp_Shavian },
449: { 599, PT_SC, ucp_Sinhala },
450: { 607, PT_PC, ucp_Sk },
451: { 610, PT_PC, ucp_Sm },
452: { 613, PT_PC, ucp_So },
453: { 616, PT_SC, ucp_Sundanese },
454: { 626, PT_SC, ucp_Syloti_Nagri },
455: { 639, PT_SC, ucp_Syriac },
456: { 646, PT_SC, ucp_Tagalog },
457: { 654, PT_SC, ucp_Tagbanwa },
458: { 663, PT_SC, ucp_Tai_Le },
459: { 670, PT_SC, ucp_Tamil },
460: { 676, PT_SC, ucp_Telugu },
461: { 683, PT_SC, ucp_Thaana },
462: { 690, PT_SC, ucp_Thai },
463: { 695, PT_SC, ucp_Tibetan },
464: { 703, PT_SC, ucp_Tifinagh },
465: { 712, PT_SC, ucp_Ugaritic },
466: { 721, PT_SC, ucp_Vai },
467: { 725, PT_SC, ucp_Yi },
468: { 728, PT_GC, ucp_Z },
469: { 730, PT_PC, ucp_Zl },
470: { 733, PT_PC, ucp_Zp },
471: { 736, PT_PC, ucp_Zs }
1.1 misha 472: };
473:
474: const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
475:
476: #endif /* SUPPORT_UTF8 */
477:
478: /* End of pcre_tables.c */
E-mail:
![[BACK]](/cvsweb/icons/back.gif){kind=icon}
Return to pcre_tables.c CVS log ![[TXT]](/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvsweb/icons/dir.gif){kind=icon}
Up to [parser3project] / win32 / pcre