diff options
Diffstat (limited to 'ext/pcre/pcrelib/pcre_tables.c')
| -rw-r--r-- | ext/pcre/pcrelib/pcre_tables.c | 340 |
1 files changed, 197 insertions, 143 deletions
diff --git a/ext/pcre/pcrelib/pcre_tables.c b/ext/pcre/pcrelib/pcre_tables.c index 4dfcbc6f9d..2f605f5fa1 100644 --- a/ext/pcre/pcrelib/pcre_tables.c +++ b/ext/pcre/pcrelib/pcre_tables.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge + Copyright (c) 1997-2012 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -37,6 +37,7 @@ POSSIBILITY OF SUCH DAMAGE. ----------------------------------------------------------------------------- */ +#ifndef PCRE_INCLUDED /* This module contains some fixed tables that are used by more than one of the PCRE code modules. The tables are also #included by the pcretest program, which @@ -48,11 +49,12 @@ clashes with the library. */ #include "pcre_internal.h" +#endif /* PCRE_INCLUDED */ /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that the definition is next to the definition of the opcodes in pcre_internal.h. */ -const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; +const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; @@ -63,31 +65,38 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; /* These are the breakpoints for different numbers of bytes in a UTF-8 character. */ -#ifdef SUPPORT_UTF8 +#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ + || (defined PCRE_INCLUDED && defined SUPPORT_PCRE16) -const int _pcre_utf8_table1[] = +/* These tables are also required by pcretest in 16 bit mode. */ + +const int PRIV(utf8_table1)[] = { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; -const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int); +const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int); /* These are the indicator bits and the mask for the data bits to set in the first byte of a character, indexed by the number of additional bytes. */ -const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; -const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; +const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; +const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; /* Table of the number of extra bytes, indexed by the first byte masked with 0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ -const uschar _pcre_utf8_table4[] = { +const pcre_uint8 PRIV(utf8_table4)[] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; +#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/ + +#ifdef SUPPORT_UTF + /* Table to translate from particular type value to the general value. */ -const int _pcre_ucp_gentype[] = { +const int PRIV(ucp_gentype)[] = { ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ @@ -98,6 +107,21 @@ const int _pcre_ucp_gentype[] = { ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ }; +#ifdef SUPPORT_JIT +/* This table reverses PRIV(ucp_gentype). We can save the cost +of a memory load. */ + +const int PRIV(ucp_typerange)[] = { + ucp_Cc, ucp_Cs, + ucp_Ll, ucp_Lu, + ucp_Mc, ucp_Mn, + ucp_Nd, ucp_No, + ucp_Pc, ucp_Ps, + ucp_Sc, ucp_So, + ucp_Zl, ucp_Zs, +}; +#endif /* SUPPORT_JIT */ + /* The pcre_utt[] table below translates Unicode property names into type and code values. It is searched by binary chop, so must be in collating sequence of name. Originally, the table contained pointers to the name strings in the first @@ -108,7 +132,7 @@ table itself. Maintenance is more error-prone, but frequent changes to this data are unlikely. July 2008: There is now a script called maint/GenerateUtt.py that can be used -to generate this data instead of maintaining it entirely by hand. +to generate this data automatically instead of maintaining it by hand. The script was updated in March 2009 to generate a new EBCDIC-compliant version. Like all other character and string literals that are compared against @@ -121,8 +145,10 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0" #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" #define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0" +#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0" #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" +#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0" #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" #define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" @@ -131,6 +157,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" #define STRING_Cc0 STR_C STR_c "\0" #define STRING_Cf0 STR_C STR_f "\0" +#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0" #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" #define STRING_Cn0 STR_C STR_n "\0" @@ -184,9 +211,13 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" #define STRING_M0 STR_M "\0" #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" +#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0" #define STRING_Mc0 STR_M STR_c "\0" #define STRING_Me0 STR_M STR_e "\0" #define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0" +#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0" +#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0" +#define STRING_Miao0 STR_M STR_i STR_a STR_o "\0" #define STRING_Mn0 STR_M STR_n "\0" #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" @@ -220,11 +251,13 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0" #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" #define STRING_Sc0 STR_S STR_c "\0" +#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0" #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" #define STRING_Sk0 STR_S STR_k "\0" #define STRING_Sm0 STR_S STR_m "\0" #define STRING_So0 STR_S STR_o "\0" +#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0" #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" #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" #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" @@ -233,6 +266,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" #define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0" #define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0" +#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0" #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" @@ -251,15 +285,17 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */ #define STRING_Zp0 STR_Z STR_p "\0" #define STRING_Zs0 STR_Z STR_s "\0" -const char _pcre_utt_names[] = +const char PRIV(utt_names)[] = STRING_Any0 STRING_Arabic0 STRING_Armenian0 STRING_Avestan0 STRING_Balinese0 STRING_Bamum0 + STRING_Batak0 STRING_Bengali0 STRING_Bopomofo0 + STRING_Brahmi0 STRING_Braille0 STRING_Buginese0 STRING_Buhid0 @@ -268,6 +304,7 @@ const char _pcre_utt_names[] = STRING_Carian0 STRING_Cc0 STRING_Cf0 + STRING_Chakma0 STRING_Cham0 STRING_Cherokee0 STRING_Cn0 @@ -321,9 +358,13 @@ const char _pcre_utt_names[] = STRING_Lydian0 STRING_M0 STRING_Malayalam0 + STRING_Mandaic0 STRING_Mc0 STRING_Me0 STRING_Meetei_Mayek0 + STRING_Meroitic_Cursive0 + STRING_Meroitic_Hieroglyphs0 + STRING_Miao0 STRING_Mn0 STRING_Mongolian0 STRING_Myanmar0 @@ -357,11 +398,13 @@ const char _pcre_utt_names[] = STRING_Samaritan0 STRING_Saurashtra0 STRING_Sc0 + STRING_Sharada0 STRING_Shavian0 STRING_Sinhala0 STRING_Sk0 STRING_Sm0 STRING_So0 + STRING_Sora_Sompeng0 STRING_Sundanese0 STRING_Syloti_Nagri0 STRING_Syriac0 @@ -370,6 +413,7 @@ const char _pcre_utt_names[] = STRING_Tai_Le0 STRING_Tai_Tham0 STRING_Tai_Viet0 + STRING_Takri0 STRING_Tamil0 STRING_Telugu0 STRING_Thaana0 @@ -388,146 +432,156 @@ const char _pcre_utt_names[] = STRING_Zp0 STRING_Zs0; -const ucp_type_table _pcre_utt[] = { +const ucp_type_table PRIV(utt)[] = { { 0, PT_ANY, 0 }, { 4, PT_SC, ucp_Arabic }, { 11, PT_SC, ucp_Armenian }, { 20, PT_SC, ucp_Avestan }, { 28, PT_SC, ucp_Balinese }, { 37, PT_SC, ucp_Bamum }, - { 43, PT_SC, ucp_Bengali }, - { 51, PT_SC, ucp_Bopomofo }, - { 60, PT_SC, ucp_Braille }, - { 68, PT_SC, ucp_Buginese }, - { 77, PT_SC, ucp_Buhid }, - { 83, PT_GC, ucp_C }, - { 85, PT_SC, ucp_Canadian_Aboriginal }, - { 105, PT_SC, ucp_Carian }, - { 112, PT_PC, ucp_Cc }, - { 115, PT_PC, ucp_Cf }, - { 118, PT_SC, ucp_Cham }, - { 123, PT_SC, ucp_Cherokee }, - { 132, PT_PC, ucp_Cn }, - { 135, PT_PC, ucp_Co }, - { 138, PT_SC, ucp_Common }, - { 145, PT_SC, ucp_Coptic }, - { 152, PT_PC, ucp_Cs }, - { 155, PT_SC, ucp_Cuneiform }, - { 165, PT_SC, ucp_Cypriot }, - { 173, PT_SC, ucp_Cyrillic }, - { 182, PT_SC, ucp_Deseret }, - { 190, PT_SC, ucp_Devanagari }, - { 201, PT_SC, ucp_Egyptian_Hieroglyphs }, - { 222, PT_SC, ucp_Ethiopic }, - { 231, PT_SC, ucp_Georgian }, - { 240, PT_SC, ucp_Glagolitic }, - { 251, PT_SC, ucp_Gothic }, - { 258, PT_SC, ucp_Greek }, - { 264, PT_SC, ucp_Gujarati }, - { 273, PT_SC, ucp_Gurmukhi }, - { 282, PT_SC, ucp_Han }, - { 286, PT_SC, ucp_Hangul }, - { 293, PT_SC, ucp_Hanunoo }, - { 301, PT_SC, ucp_Hebrew }, - { 308, PT_SC, ucp_Hiragana }, - { 317, PT_SC, ucp_Imperial_Aramaic }, - { 334, PT_SC, ucp_Inherited }, - { 344, PT_SC, ucp_Inscriptional_Pahlavi }, - { 366, PT_SC, ucp_Inscriptional_Parthian }, - { 389, PT_SC, ucp_Javanese }, - { 398, PT_SC, ucp_Kaithi }, - { 405, PT_SC, ucp_Kannada }, - { 413, PT_SC, ucp_Katakana }, - { 422, PT_SC, ucp_Kayah_Li }, - { 431, PT_SC, ucp_Kharoshthi }, - { 442, PT_SC, ucp_Khmer }, - { 448, PT_GC, ucp_L }, - { 450, PT_LAMP, 0 }, - { 453, PT_SC, ucp_Lao }, - { 457, PT_SC, ucp_Latin }, - { 463, PT_SC, ucp_Lepcha }, - { 470, PT_SC, ucp_Limbu }, - { 476, PT_SC, ucp_Linear_B }, - { 485, PT_SC, ucp_Lisu }, - { 490, PT_PC, ucp_Ll }, - { 493, PT_PC, ucp_Lm }, - { 496, PT_PC, ucp_Lo }, - { 499, PT_PC, ucp_Lt }, - { 502, PT_PC, ucp_Lu }, - { 505, PT_SC, ucp_Lycian }, - { 512, PT_SC, ucp_Lydian }, - { 519, PT_GC, ucp_M }, - { 521, PT_SC, ucp_Malayalam }, - { 531, PT_PC, ucp_Mc }, - { 534, PT_PC, ucp_Me }, - { 537, PT_SC, ucp_Meetei_Mayek }, - { 550, PT_PC, ucp_Mn }, - { 553, PT_SC, ucp_Mongolian }, - { 563, PT_SC, ucp_Myanmar }, - { 571, PT_GC, ucp_N }, - { 573, PT_PC, ucp_Nd }, - { 576, PT_SC, ucp_New_Tai_Lue }, - { 588, PT_SC, ucp_Nko }, - { 592, PT_PC, ucp_Nl }, - { 595, PT_PC, ucp_No }, - { 598, PT_SC, ucp_Ogham }, - { 604, PT_SC, ucp_Ol_Chiki }, - { 613, PT_SC, ucp_Old_Italic }, - { 624, PT_SC, ucp_Old_Persian }, - { 636, PT_SC, ucp_Old_South_Arabian }, - { 654, PT_SC, ucp_Old_Turkic }, - { 665, PT_SC, ucp_Oriya }, - { 671, PT_SC, ucp_Osmanya }, - { 679, PT_GC, ucp_P }, - { 681, PT_PC, ucp_Pc }, - { 684, PT_PC, ucp_Pd }, - { 687, PT_PC, ucp_Pe }, - { 690, PT_PC, ucp_Pf }, - { 693, PT_SC, ucp_Phags_Pa }, - { 702, PT_SC, ucp_Phoenician }, - { 713, PT_PC, ucp_Pi }, - { 716, PT_PC, ucp_Po }, - { 719, PT_PC, ucp_Ps }, - { 722, PT_SC, ucp_Rejang }, - { 729, PT_SC, ucp_Runic }, - { 735, PT_GC, ucp_S }, - { 737, PT_SC, ucp_Samaritan }, - { 747, PT_SC, ucp_Saurashtra }, - { 758, PT_PC, ucp_Sc }, - { 761, PT_SC, ucp_Shavian }, - { 769, PT_SC, ucp_Sinhala }, - { 777, PT_PC, ucp_Sk }, - { 780, PT_PC, ucp_Sm }, - { 783, PT_PC, ucp_So }, - { 786, PT_SC, ucp_Sundanese }, - { 796, PT_SC, ucp_Syloti_Nagri }, - { 809, PT_SC, ucp_Syriac }, - { 816, PT_SC, ucp_Tagalog }, - { 824, PT_SC, ucp_Tagbanwa }, - { 833, PT_SC, ucp_Tai_Le }, - { 840, PT_SC, ucp_Tai_Tham }, - { 849, PT_SC, ucp_Tai_Viet }, - { 858, PT_SC, ucp_Tamil }, - { 864, PT_SC, ucp_Telugu }, - { 871, PT_SC, ucp_Thaana }, - { 878, PT_SC, ucp_Thai }, - { 883, PT_SC, ucp_Tibetan }, - { 891, PT_SC, ucp_Tifinagh }, - { 900, PT_SC, ucp_Ugaritic }, - { 909, PT_SC, ucp_Vai }, - { 913, PT_ALNUM, 0 }, - { 917, PT_PXSPACE, 0 }, - { 921, PT_SPACE, 0 }, - { 925, PT_WORD, 0 }, - { 929, PT_SC, ucp_Yi }, - { 932, PT_GC, ucp_Z }, - { 934, PT_PC, ucp_Zl }, - { 937, PT_PC, ucp_Zp }, - { 940, PT_PC, ucp_Zs } + { 43, PT_SC, ucp_Batak }, + { 49, PT_SC, ucp_Bengali }, + { 57, PT_SC, ucp_Bopomofo }, + { 66, PT_SC, ucp_Brahmi }, + { 73, PT_SC, ucp_Braille }, + { 81, PT_SC, ucp_Buginese }, + { 90, PT_SC, ucp_Buhid }, + { 96, PT_GC, ucp_C }, + { 98, PT_SC, ucp_Canadian_Aboriginal }, + { 118, PT_SC, ucp_Carian }, + { 125, PT_PC, ucp_Cc }, + { 128, PT_PC, ucp_Cf }, + { 131, PT_SC, ucp_Chakma }, + { 138, PT_SC, ucp_Cham }, + { 143, PT_SC, ucp_Cherokee }, + { 152, PT_PC, ucp_Cn }, + { 155, PT_PC, ucp_Co }, + { 158, PT_SC, ucp_Common }, + { 165, PT_SC, ucp_Coptic }, + { 172, PT_PC, ucp_Cs }, + { 175, PT_SC, ucp_Cuneiform }, + { 185, PT_SC, ucp_Cypriot }, + { 193, PT_SC, ucp_Cyrillic }, + { 202, PT_SC, ucp_Deseret }, + { 210, PT_SC, ucp_Devanagari }, + { 221, PT_SC, ucp_Egyptian_Hieroglyphs }, + { 242, PT_SC, ucp_Ethiopic }, + { 251, PT_SC, ucp_Georgian }, + { 260, PT_SC, ucp_Glagolitic }, + { 271, PT_SC, ucp_Gothic }, + { 278, PT_SC, ucp_Greek }, + { 284, PT_SC, ucp_Gujarati }, + { 293, PT_SC, ucp_Gurmukhi }, + { 302, PT_SC, ucp_Han }, + { 306, PT_SC, ucp_Hangul }, + { 313, PT_SC, ucp_Hanunoo }, + { 321, PT_SC, ucp_Hebrew }, + { 328, PT_SC, ucp_Hiragana }, + { 337, PT_SC, ucp_Imperial_Aramaic }, + { 354, PT_SC, ucp_Inherited }, + { 364, PT_SC, ucp_Inscriptional_Pahlavi }, + { 386, PT_SC, ucp_Inscriptional_Parthian }, + { 409, PT_SC, ucp_Javanese }, + { 418, PT_SC, ucp_Kaithi }, + { 425, PT_SC, ucp_Kannada }, + { 433, PT_SC, ucp_Katakana }, + { 442, PT_SC, ucp_Kayah_Li }, + { 451, PT_SC, ucp_Kharoshthi }, + { 462, PT_SC, ucp_Khmer }, + { 468, PT_GC, ucp_L }, + { 470, PT_LAMP, 0 }, + { 473, PT_SC, ucp_Lao }, + { 477, PT_SC, ucp_Latin }, + { 483, PT_SC, ucp_Lepcha }, + { 490, PT_SC, ucp_Limbu }, + { 496, PT_SC, ucp_Linear_B }, + { 505, PT_SC, ucp_Lisu }, + { 510, PT_PC, ucp_Ll }, + { 513, PT_PC, ucp_Lm }, + { 516, PT_PC, ucp_Lo }, + { 519, PT_PC, ucp_Lt }, + { 522, PT_PC, ucp_Lu }, + { 525, PT_SC, ucp_Lycian }, + { 532, PT_SC, ucp_Lydian }, + { 539, PT_GC, ucp_M }, + { 541, PT_SC, ucp_Malayalam }, + { 551, PT_SC, ucp_Mandaic }, + { 559, PT_PC, ucp_Mc }, + { 562, PT_PC, ucp_Me }, + { 565, PT_SC, ucp_Meetei_Mayek }, + { 578, PT_SC, ucp_Meroitic_Cursive }, + { 595, PT_SC, ucp_Meroitic_Hieroglyphs }, + { 616, PT_SC, ucp_Miao }, + { 621, PT_PC, ucp_Mn }, + { 624, PT_SC, ucp_Mongolian }, + { 634, PT_SC, ucp_Myanmar }, + { 642, PT_GC, ucp_N }, + { 644, PT_PC, ucp_Nd }, + { 647, PT_SC, ucp_New_Tai_Lue }, + { 659, PT_SC, ucp_Nko }, + { 663, PT_PC, ucp_Nl }, + { 666, PT_PC, ucp_No }, + { 669, PT_SC, ucp_Ogham }, + { 675, PT_SC, ucp_Ol_Chiki }, + { 684, PT_SC, ucp_Old_Italic }, + { 695, PT_SC, ucp_Old_Persian }, + { 707, PT_SC, ucp_Old_South_Arabian }, + { 725, PT_SC, ucp_Old_Turkic }, + { 736, PT_SC, ucp_Oriya }, + { 742, PT_SC, ucp_Osmanya }, + { 750, PT_GC, ucp_P }, + { 752, PT_PC, ucp_Pc }, + { 755, PT_PC, ucp_Pd }, + { 758, PT_PC, ucp_Pe }, + { 761, PT_PC, ucp_Pf }, + { 764, PT_SC, ucp_Phags_Pa }, + { 773, PT_SC, ucp_Phoenician }, + { 784, PT_PC, ucp_Pi }, + { 787, PT_PC, ucp_Po }, + { 790, PT_PC, ucp_Ps }, + { 793, PT_SC, ucp_Rejang }, + { 800, PT_SC, ucp_Runic }, + { 806, PT_GC, ucp_S }, + { 808, PT_SC, ucp_Samaritan }, + { 818, PT_SC, ucp_Saurashtra }, + { 829, PT_PC, ucp_Sc }, + { 832, PT_SC, ucp_Sharada }, + { 840, PT_SC, ucp_Shavian }, + { 848, PT_SC, ucp_Sinhala }, + { 856, PT_PC, ucp_Sk }, + { 859, PT_PC, ucp_Sm }, + { 862, PT_PC, ucp_So }, + { 865, PT_SC, ucp_Sora_Sompeng }, + { 878, PT_SC, ucp_Sundanese }, + { 888, PT_SC, ucp_Syloti_Nagri }, + { 901, PT_SC, ucp_Syriac }, + { 908, PT_SC, ucp_Tagalog }, + { 916, PT_SC, ucp_Tagbanwa }, + { 925, PT_SC, ucp_Tai_Le }, + { 932, PT_SC, ucp_Tai_Tham }, + { 941, PT_SC, ucp_Tai_Viet }, + { 950, PT_SC, ucp_Takri }, + { 956, PT_SC, ucp_Tamil }, + { 962, PT_SC, ucp_Telugu }, + { 969, PT_SC, ucp_Thaana }, + { 976, PT_SC, ucp_Thai }, + { 981, PT_SC, ucp_Tibetan }, + { 989, PT_SC, ucp_Tifinagh }, + { 998, PT_SC, ucp_Ugaritic }, + { 1007, PT_SC, ucp_Vai }, + { 1011, PT_ALNUM, 0 }, + { 1015, PT_PXSPACE, 0 }, + { 1019, PT_SPACE, 0 }, + { 1023, PT_WORD, 0 }, + { 1027, PT_SC, ucp_Yi }, + { 1030, PT_GC, ucp_Z }, + { 1032, PT_PC, ucp_Zl }, + { 1035, PT_PC, ucp_Zp }, + { 1038, PT_PC, ucp_Zs } }; -const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); +const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table); -#endif /* SUPPORT_UTF8 */ +#endif /* SUPPORT_UTF */ /* End of pcre_tables.c */ |