version 1.1, 2012/02/21 23:05:51
|
version 1.1.1.3, 2012/10/09 09:19:17
|
Line 6
|
Line 6
|
and semantics are as close as possible to those of the Perl 5 language. |
and semantics are as close as possible to those of the Perl 5 language. |
|
|
Written by Philip Hazel |
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 |
Redistribution and use in source and binary forms, with or without |
Line 37 POSSIBILITY OF SUCH DAMAGE.
|
Line 37 POSSIBILITY OF SUCH DAMAGE.
|
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
*/ |
*/ |
|
|
|
#ifndef PCRE_INCLUDED |
|
|
/* This module contains some fixed tables that are used by more than one of the |
/* 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 |
PCRE code modules. The tables are also #included by the pcretest program, which |
Line 50 clashes with the library. */
|
Line 51 clashes with the library. */
|
|
|
#include "pcre_internal.h" |
#include "pcre_internal.h" |
|
|
|
#endif /* PCRE_INCLUDED */ |
|
|
/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that |
/* 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. */ |
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 }; |
|
|
|
|
|
|
Line 65 const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
|
Line 67 const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
|
/* These are the breakpoints for different numbers of bytes in a UTF-8 |
/* These are the breakpoints for different numbers of bytes in a UTF-8 |
character. */ |
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}; |
{ 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 |
/* 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. */ |
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 PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; |
const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; | 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 |
/* 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. */ |
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, |
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, |
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 }; |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; |
|
|
#ifdef SUPPORT_JIT | #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/ |
/* Full table of the number of extra bytes when the | |
character code is greater or equal than 0xc0. | |
See _pcre_utf8_table4 above. */ | |
|
|
const uschar _pcre_utf8_char_sizes[] = { | #ifdef SUPPORT_UTF |
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, | |
3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4, | |
}; | |
#endif | |
|
|
/* Table to translate from particular type value to the general value. */ |
/* 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_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_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ |
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ |
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ |
Line 114 const int _pcre_ucp_gentype[] = {
|
Line 110 const int _pcre_ucp_gentype[] = {
|
}; |
}; |
|
|
#ifdef SUPPORT_JIT |
#ifdef SUPPORT_JIT |
/* This table reverses _pcre_ucp_gentype. We can save the cost | /* This table reverses PRIV(ucp_gentype). We can save the cost |
of a memory load. */ |
of a memory load. */ |
|
|
const int _pcre_ucp_typerange[] = { | const int PRIV(ucp_typerange)[] = { |
ucp_Cc, ucp_Cs, |
ucp_Cc, ucp_Cs, |
ucp_Ll, ucp_Lu, |
ucp_Ll, ucp_Lu, |
ucp_Mc, ucp_Mn, |
ucp_Mc, ucp_Mn, |
Line 126 const int _pcre_ucp_typerange[] = {
|
Line 122 const int _pcre_ucp_typerange[] = {
|
ucp_Sc, ucp_So, |
ucp_Sc, ucp_So, |
ucp_Zl, ucp_Zs, |
ucp_Zl, ucp_Zs, |
}; |
}; |
#endif | #endif /* SUPPORT_JIT */ |
|
|
/* The pcre_utt[] table below translates Unicode property names into type and |
/* 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 |
code values. It is searched by binary chop, so must be in collating sequence of |
Line 163 strings to make sure that UTF-8 support works on EBCDI
|
Line 159 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" |
#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_Cc0 STR_C STR_c "\0" |
#define STRING_Cf0 STR_C STR_f "\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_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_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" |
#define STRING_Cn0 STR_C STR_n "\0" |
Line 220 strings to make sure that UTF-8 support works on EBCDI
|
Line 217 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Mc0 STR_M STR_c "\0" |
#define STRING_Mc0 STR_M STR_c "\0" |
#define STRING_Me0 STR_M STR_e "\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_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_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_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" |
#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" |
Line 253 strings to make sure that UTF-8 support works on EBCDI
|
Line 253 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0" |
#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_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_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_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_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_Sk0 STR_S STR_k "\0" |
#define STRING_Sm0 STR_S STR_m "\0" |
#define STRING_Sm0 STR_S STR_m "\0" |
#define STRING_So0 STR_S STR_o "\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_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_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" |
#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" |
Line 266 strings to make sure that UTF-8 support works on EBCDI
|
Line 268 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" |
#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_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_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_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_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" |
#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" |
Line 284 strings to make sure that UTF-8 support works on EBCDI
|
Line 287 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Zp0 STR_Z STR_p "\0" |
#define STRING_Zp0 STR_Z STR_p "\0" |
#define STRING_Zs0 STR_Z STR_s "\0" |
#define STRING_Zs0 STR_Z STR_s "\0" |
|
|
const char _pcre_utt_names[] = | const char PRIV(utt_names)[] = |
STRING_Any0 |
STRING_Any0 |
STRING_Arabic0 |
STRING_Arabic0 |
STRING_Armenian0 |
STRING_Armenian0 |
Line 303 const char _pcre_utt_names[] =
|
Line 306 const char _pcre_utt_names[] =
|
STRING_Carian0 |
STRING_Carian0 |
STRING_Cc0 |
STRING_Cc0 |
STRING_Cf0 |
STRING_Cf0 |
|
STRING_Chakma0 |
STRING_Cham0 |
STRING_Cham0 |
STRING_Cherokee0 |
STRING_Cherokee0 |
STRING_Cn0 |
STRING_Cn0 |
Line 360 const char _pcre_utt_names[] =
|
Line 364 const char _pcre_utt_names[] =
|
STRING_Mc0 |
STRING_Mc0 |
STRING_Me0 |
STRING_Me0 |
STRING_Meetei_Mayek0 |
STRING_Meetei_Mayek0 |
|
STRING_Meroitic_Cursive0 |
|
STRING_Meroitic_Hieroglyphs0 |
|
STRING_Miao0 |
STRING_Mn0 |
STRING_Mn0 |
STRING_Mongolian0 |
STRING_Mongolian0 |
STRING_Myanmar0 |
STRING_Myanmar0 |
Line 393 const char _pcre_utt_names[] =
|
Line 400 const char _pcre_utt_names[] =
|
STRING_Samaritan0 |
STRING_Samaritan0 |
STRING_Saurashtra0 |
STRING_Saurashtra0 |
STRING_Sc0 |
STRING_Sc0 |
|
STRING_Sharada0 |
STRING_Shavian0 |
STRING_Shavian0 |
STRING_Sinhala0 |
STRING_Sinhala0 |
STRING_Sk0 |
STRING_Sk0 |
STRING_Sm0 |
STRING_Sm0 |
STRING_So0 |
STRING_So0 |
|
STRING_Sora_Sompeng0 |
STRING_Sundanese0 |
STRING_Sundanese0 |
STRING_Syloti_Nagri0 |
STRING_Syloti_Nagri0 |
STRING_Syriac0 |
STRING_Syriac0 |
Line 406 const char _pcre_utt_names[] =
|
Line 415 const char _pcre_utt_names[] =
|
STRING_Tai_Le0 |
STRING_Tai_Le0 |
STRING_Tai_Tham0 |
STRING_Tai_Tham0 |
STRING_Tai_Viet0 |
STRING_Tai_Viet0 |
|
STRING_Takri0 |
STRING_Tamil0 |
STRING_Tamil0 |
STRING_Telugu0 |
STRING_Telugu0 |
STRING_Thaana0 |
STRING_Thaana0 |
Line 424 const char _pcre_utt_names[] =
|
Line 434 const char _pcre_utt_names[] =
|
STRING_Zp0 |
STRING_Zp0 |
STRING_Zs0; |
STRING_Zs0; |
|
|
const ucp_type_table _pcre_utt[] = { | const ucp_type_table PRIV(utt)[] = { |
{ 0, PT_ANY, 0 }, |
{ 0, PT_ANY, 0 }, |
{ 4, PT_SC, ucp_Arabic }, |
{ 4, PT_SC, ucp_Arabic }, |
{ 11, PT_SC, ucp_Armenian }, |
{ 11, PT_SC, ucp_Armenian }, |
Line 443 const ucp_type_table _pcre_utt[] = {
|
Line 453 const ucp_type_table _pcre_utt[] = {
|
{ 118, PT_SC, ucp_Carian }, |
{ 118, PT_SC, ucp_Carian }, |
{ 125, PT_PC, ucp_Cc }, |
{ 125, PT_PC, ucp_Cc }, |
{ 128, PT_PC, ucp_Cf }, |
{ 128, PT_PC, ucp_Cf }, |
{ 131, PT_SC, ucp_Cham }, | { 131, PT_SC, ucp_Chakma }, |
{ 136, PT_SC, ucp_Cherokee }, | { 138, PT_SC, ucp_Cham }, |
{ 145, PT_PC, ucp_Cn }, | { 143, PT_SC, ucp_Cherokee }, |
{ 148, PT_PC, ucp_Co }, | { 152, PT_PC, ucp_Cn }, |
{ 151, PT_SC, ucp_Common }, | { 155, PT_PC, ucp_Co }, |
{ 158, PT_SC, ucp_Coptic }, | { 158, PT_SC, ucp_Common }, |
{ 165, PT_PC, ucp_Cs }, | { 165, PT_SC, ucp_Coptic }, |
{ 168, PT_SC, ucp_Cuneiform }, | { 172, PT_PC, ucp_Cs }, |
{ 178, PT_SC, ucp_Cypriot }, | { 175, PT_SC, ucp_Cuneiform }, |
{ 186, PT_SC, ucp_Cyrillic }, | { 185, PT_SC, ucp_Cypriot }, |
{ 195, PT_SC, ucp_Deseret }, | { 193, PT_SC, ucp_Cyrillic }, |
{ 203, PT_SC, ucp_Devanagari }, | { 202, PT_SC, ucp_Deseret }, |
{ 214, PT_SC, ucp_Egyptian_Hieroglyphs }, | { 210, PT_SC, ucp_Devanagari }, |
{ 235, PT_SC, ucp_Ethiopic }, | { 221, PT_SC, ucp_Egyptian_Hieroglyphs }, |
{ 244, PT_SC, ucp_Georgian }, | { 242, PT_SC, ucp_Ethiopic }, |
{ 253, PT_SC, ucp_Glagolitic }, | { 251, PT_SC, ucp_Georgian }, |
{ 264, PT_SC, ucp_Gothic }, | { 260, PT_SC, ucp_Glagolitic }, |
{ 271, PT_SC, ucp_Greek }, | { 271, PT_SC, ucp_Gothic }, |
{ 277, PT_SC, ucp_Gujarati }, | { 278, PT_SC, ucp_Greek }, |
{ 286, PT_SC, ucp_Gurmukhi }, | { 284, PT_SC, ucp_Gujarati }, |
{ 295, PT_SC, ucp_Han }, | { 293, PT_SC, ucp_Gurmukhi }, |
{ 299, PT_SC, ucp_Hangul }, | { 302, PT_SC, ucp_Han }, |
{ 306, PT_SC, ucp_Hanunoo }, | { 306, PT_SC, ucp_Hangul }, |
{ 314, PT_SC, ucp_Hebrew }, | { 313, PT_SC, ucp_Hanunoo }, |
{ 321, PT_SC, ucp_Hiragana }, | { 321, PT_SC, ucp_Hebrew }, |
{ 330, PT_SC, ucp_Imperial_Aramaic }, | { 328, PT_SC, ucp_Hiragana }, |
{ 347, PT_SC, ucp_Inherited }, | { 337, PT_SC, ucp_Imperial_Aramaic }, |
{ 357, PT_SC, ucp_Inscriptional_Pahlavi }, | { 354, PT_SC, ucp_Inherited }, |
{ 379, PT_SC, ucp_Inscriptional_Parthian }, | { 364, PT_SC, ucp_Inscriptional_Pahlavi }, |
{ 402, PT_SC, ucp_Javanese }, | { 386, PT_SC, ucp_Inscriptional_Parthian }, |
{ 411, PT_SC, ucp_Kaithi }, | { 409, PT_SC, ucp_Javanese }, |
{ 418, PT_SC, ucp_Kannada }, | { 418, PT_SC, ucp_Kaithi }, |
{ 426, PT_SC, ucp_Katakana }, | { 425, PT_SC, ucp_Kannada }, |
{ 435, PT_SC, ucp_Kayah_Li }, | { 433, PT_SC, ucp_Katakana }, |
{ 444, PT_SC, ucp_Kharoshthi }, | { 442, PT_SC, ucp_Kayah_Li }, |
{ 455, PT_SC, ucp_Khmer }, | { 451, PT_SC, ucp_Kharoshthi }, |
{ 461, PT_GC, ucp_L }, | { 462, PT_SC, ucp_Khmer }, |
{ 463, PT_LAMP, 0 }, | { 468, PT_GC, ucp_L }, |
{ 466, PT_SC, ucp_Lao }, | { 470, PT_LAMP, 0 }, |
{ 470, PT_SC, ucp_Latin }, | { 473, PT_SC, ucp_Lao }, |
{ 476, PT_SC, ucp_Lepcha }, | { 477, PT_SC, ucp_Latin }, |
{ 483, PT_SC, ucp_Limbu }, | { 483, PT_SC, ucp_Lepcha }, |
{ 489, PT_SC, ucp_Linear_B }, | { 490, PT_SC, ucp_Limbu }, |
{ 498, PT_SC, ucp_Lisu }, | { 496, PT_SC, ucp_Linear_B }, |
{ 503, PT_PC, ucp_Ll }, | { 505, PT_SC, ucp_Lisu }, |
{ 506, PT_PC, ucp_Lm }, | { 510, PT_PC, ucp_Ll }, |
{ 509, PT_PC, ucp_Lo }, | { 513, PT_PC, ucp_Lm }, |
{ 512, PT_PC, ucp_Lt }, | { 516, PT_PC, ucp_Lo }, |
{ 515, PT_PC, ucp_Lu }, | { 519, PT_PC, ucp_Lt }, |
{ 518, PT_SC, ucp_Lycian }, | { 522, PT_PC, ucp_Lu }, |
{ 525, PT_SC, ucp_Lydian }, | { 525, PT_SC, ucp_Lycian }, |
{ 532, PT_GC, ucp_M }, | { 532, PT_SC, ucp_Lydian }, |
{ 534, PT_SC, ucp_Malayalam }, | { 539, PT_GC, ucp_M }, |
{ 544, PT_SC, ucp_Mandaic }, | { 541, PT_SC, ucp_Malayalam }, |
{ 552, PT_PC, ucp_Mc }, | { 551, PT_SC, ucp_Mandaic }, |
{ 555, PT_PC, ucp_Me }, | { 559, PT_PC, ucp_Mc }, |
{ 558, PT_SC, ucp_Meetei_Mayek }, | { 562, PT_PC, ucp_Me }, |
{ 571, PT_PC, ucp_Mn }, | { 565, PT_SC, ucp_Meetei_Mayek }, |
{ 574, PT_SC, ucp_Mongolian }, | { 578, PT_SC, ucp_Meroitic_Cursive }, |
{ 584, PT_SC, ucp_Myanmar }, | { 595, PT_SC, ucp_Meroitic_Hieroglyphs }, |
{ 592, PT_GC, ucp_N }, | { 616, PT_SC, ucp_Miao }, |
{ 594, PT_PC, ucp_Nd }, | { 621, PT_PC, ucp_Mn }, |
{ 597, PT_SC, ucp_New_Tai_Lue }, | { 624, PT_SC, ucp_Mongolian }, |
{ 609, PT_SC, ucp_Nko }, | { 634, PT_SC, ucp_Myanmar }, |
{ 613, PT_PC, ucp_Nl }, | { 642, PT_GC, ucp_N }, |
{ 616, PT_PC, ucp_No }, | { 644, PT_PC, ucp_Nd }, |
{ 619, PT_SC, ucp_Ogham }, | { 647, PT_SC, ucp_New_Tai_Lue }, |
{ 625, PT_SC, ucp_Ol_Chiki }, | { 659, PT_SC, ucp_Nko }, |
{ 634, PT_SC, ucp_Old_Italic }, | { 663, PT_PC, ucp_Nl }, |
{ 645, PT_SC, ucp_Old_Persian }, | { 666, PT_PC, ucp_No }, |
{ 657, PT_SC, ucp_Old_South_Arabian }, | { 669, PT_SC, ucp_Ogham }, |
{ 675, PT_SC, ucp_Old_Turkic }, | { 675, PT_SC, ucp_Ol_Chiki }, |
{ 686, PT_SC, ucp_Oriya }, | { 684, PT_SC, ucp_Old_Italic }, |
{ 692, PT_SC, ucp_Osmanya }, | { 695, PT_SC, ucp_Old_Persian }, |
{ 700, PT_GC, ucp_P }, | { 707, PT_SC, ucp_Old_South_Arabian }, |
{ 702, PT_PC, ucp_Pc }, | { 725, PT_SC, ucp_Old_Turkic }, |
{ 705, PT_PC, ucp_Pd }, | { 736, PT_SC, ucp_Oriya }, |
{ 708, PT_PC, ucp_Pe }, | { 742, PT_SC, ucp_Osmanya }, |
{ 711, PT_PC, ucp_Pf }, | { 750, PT_GC, ucp_P }, |
{ 714, PT_SC, ucp_Phags_Pa }, | { 752, PT_PC, ucp_Pc }, |
{ 723, PT_SC, ucp_Phoenician }, | { 755, PT_PC, ucp_Pd }, |
{ 734, PT_PC, ucp_Pi }, | { 758, PT_PC, ucp_Pe }, |
{ 737, PT_PC, ucp_Po }, | { 761, PT_PC, ucp_Pf }, |
{ 740, PT_PC, ucp_Ps }, | { 764, PT_SC, ucp_Phags_Pa }, |
{ 743, PT_SC, ucp_Rejang }, | { 773, PT_SC, ucp_Phoenician }, |
{ 750, PT_SC, ucp_Runic }, | { 784, PT_PC, ucp_Pi }, |
{ 756, PT_GC, ucp_S }, | { 787, PT_PC, ucp_Po }, |
{ 758, PT_SC, ucp_Samaritan }, | { 790, PT_PC, ucp_Ps }, |
{ 768, PT_SC, ucp_Saurashtra }, | { 793, PT_SC, ucp_Rejang }, |
{ 779, PT_PC, ucp_Sc }, | { 800, PT_SC, ucp_Runic }, |
{ 782, PT_SC, ucp_Shavian }, | { 806, PT_GC, ucp_S }, |
{ 790, PT_SC, ucp_Sinhala }, | { 808, PT_SC, ucp_Samaritan }, |
{ 798, PT_PC, ucp_Sk }, | { 818, PT_SC, ucp_Saurashtra }, |
{ 801, PT_PC, ucp_Sm }, | { 829, PT_PC, ucp_Sc }, |
{ 804, PT_PC, ucp_So }, | { 832, PT_SC, ucp_Sharada }, |
{ 807, PT_SC, ucp_Sundanese }, | { 840, PT_SC, ucp_Shavian }, |
{ 817, PT_SC, ucp_Syloti_Nagri }, | { 848, PT_SC, ucp_Sinhala }, |
{ 830, PT_SC, ucp_Syriac }, | { 856, PT_PC, ucp_Sk }, |
{ 837, PT_SC, ucp_Tagalog }, | { 859, PT_PC, ucp_Sm }, |
{ 845, PT_SC, ucp_Tagbanwa }, | { 862, PT_PC, ucp_So }, |
{ 854, PT_SC, ucp_Tai_Le }, | { 865, PT_SC, ucp_Sora_Sompeng }, |
{ 861, PT_SC, ucp_Tai_Tham }, | { 878, PT_SC, ucp_Sundanese }, |
{ 870, PT_SC, ucp_Tai_Viet }, | { 888, PT_SC, ucp_Syloti_Nagri }, |
{ 879, PT_SC, ucp_Tamil }, | { 901, PT_SC, ucp_Syriac }, |
{ 885, PT_SC, ucp_Telugu }, | { 908, PT_SC, ucp_Tagalog }, |
{ 892, PT_SC, ucp_Thaana }, | { 916, PT_SC, ucp_Tagbanwa }, |
{ 899, PT_SC, ucp_Thai }, | { 925, PT_SC, ucp_Tai_Le }, |
{ 904, PT_SC, ucp_Tibetan }, | { 932, PT_SC, ucp_Tai_Tham }, |
{ 912, PT_SC, ucp_Tifinagh }, | { 941, PT_SC, ucp_Tai_Viet }, |
{ 921, PT_SC, ucp_Ugaritic }, | { 950, PT_SC, ucp_Takri }, |
{ 930, PT_SC, ucp_Vai }, | { 956, PT_SC, ucp_Tamil }, |
{ 934, PT_ALNUM, 0 }, | { 962, PT_SC, ucp_Telugu }, |
{ 938, PT_PXSPACE, 0 }, | { 969, PT_SC, ucp_Thaana }, |
{ 942, PT_SPACE, 0 }, | { 976, PT_SC, ucp_Thai }, |
{ 946, PT_WORD, 0 }, | { 981, PT_SC, ucp_Tibetan }, |
{ 950, PT_SC, ucp_Yi }, | { 989, PT_SC, ucp_Tifinagh }, |
{ 953, PT_GC, ucp_Z }, | { 998, PT_SC, ucp_Ugaritic }, |
{ 955, PT_PC, ucp_Zl }, | { 1007, PT_SC, ucp_Vai }, |
{ 958, PT_PC, ucp_Zp }, | { 1011, PT_ALNUM, 0 }, |
{ 961, PT_PC, ucp_Zs } | { 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 */ |
/* End of pcre_tables.c */ |