/[pcre]/code/trunk/pcre_tables.c

Diff of /code/trunk/pcre_tables.c

Parent Directory | Revision Log | View Patch Patch

-revision 592 by ph10,
Sat Apr 30 17:37:37 2011 UTC
+revision 836 by ph10,
Wed Dec 28 17:16:11 2011 UTC
 Line 6
  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
 Line 37 
 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
-Line 50 
 clashes with the library. */
+Line 51 
 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 };
-Line 65 
 const uschar _pcre_OP_lengths[] = { OP_L
+Line 67 
 const uschar _pcre_OP_lengths[] = { OP_L
  /* 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 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
 x3f. 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,
 ,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
 ,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 */
-Line 100 
 const int _pcre_ucp_gentype[] = {
+Line 109 
 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
-Line 256 
 strings to make sure that UTF-8 support
+Line 280 
 strings to make sure that UTF-8 support
  #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
-Line 396 
 const char _pcre_utt_names[] =
+Line 420 
 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_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_Cham },
    { 136, PT_SC, ucp_Cherokee },
    { 145, PT_PC, ucp_Cn },
    { 148, PT_PC, ucp_Co },
    { 151, PT_SC, ucp_Common },
    { 158, PT_SC, ucp_Coptic },
    { 165, PT_PC, ucp_Cs },
    { 168, PT_SC, ucp_Cuneiform },
    { 178, PT_SC, ucp_Cypriot },
    { 186, PT_SC, ucp_Cyrillic },
    { 195, PT_SC, ucp_Deseret },
    { 203, PT_SC, ucp_Devanagari },
    { 214, PT_SC, ucp_Egyptian_Hieroglyphs },
    { 235, PT_SC, ucp_Ethiopic },
    { 244, PT_SC, ucp_Georgian },
    { 253, PT_SC, ucp_Glagolitic },
    { 264, PT_SC, ucp_Gothic },
    { 271, PT_SC, ucp_Greek },
    { 277, PT_SC, ucp_Gujarati },
    { 286, PT_SC, ucp_Gurmukhi },
    { 295, PT_SC, ucp_Han },
    { 299, PT_SC, ucp_Hangul },
    { 306, PT_SC, ucp_Hanunoo },
    { 314, PT_SC, ucp_Hebrew },
    { 321, PT_SC, ucp_Hiragana },
    { 330, PT_SC, ucp_Imperial_Aramaic },
    { 347, PT_SC, ucp_Inherited },
    { 357, PT_SC, ucp_Inscriptional_Pahlavi },
    { 379, PT_SC, ucp_Inscriptional_Parthian },
    { 402, PT_SC, ucp_Javanese },
    { 411, PT_SC, ucp_Kaithi },
    { 418, PT_SC, ucp_Kannada },
    { 426, PT_SC, ucp_Katakana },
    { 435, PT_SC, ucp_Kayah_Li },
    { 444, PT_SC, ucp_Kharoshthi },
    { 455, PT_SC, ucp_Khmer },
    { 461, PT_GC, ucp_L },
    { 463, PT_LAMP, 0 },
    { 466, PT_SC, ucp_Lao },
    { 470, PT_SC, ucp_Latin },
    { 476, PT_SC, ucp_Lepcha },
    { 483, PT_SC, ucp_Limbu },
    { 489, PT_SC, ucp_Linear_B },
    { 498, PT_SC, ucp_Lisu },
    { 503, PT_PC, ucp_Ll },
    { 506, PT_PC, ucp_Lm },
    { 509, PT_PC, ucp_Lo },
    { 512, PT_PC, ucp_Lt },
    { 515, PT_PC, ucp_Lu },
    { 518, PT_SC, ucp_Lycian },
    { 525, PT_SC, ucp_Lydian },
    { 532, PT_GC, ucp_M },
    { 534, PT_SC, ucp_Malayalam },
    { 544, PT_SC, ucp_Mandaic },
    { 552, PT_PC, ucp_Mc },
    { 555, PT_PC, ucp_Me },
    { 558, PT_SC, ucp_Meetei_Mayek },
    { 571, PT_PC, ucp_Mn },
    { 574, PT_SC, ucp_Mongolian },
    { 584, PT_SC, ucp_Myanmar },
    { 592, PT_GC, ucp_N },
    { 594, PT_PC, ucp_Nd },
    { 597, PT_SC, ucp_New_Tai_Lue },
    { 609, PT_SC, ucp_Nko },
    { 613, PT_PC, ucp_Nl },
    { 616, PT_PC, ucp_No },
    { 619, PT_SC, ucp_Ogham },
    { 625, PT_SC, ucp_Ol_Chiki },
    { 634, PT_SC, ucp_Old_Italic },
    { 645, PT_SC, ucp_Old_Persian },
    { 657, PT_SC, ucp_Old_South_Arabian },
    { 675, PT_SC, ucp_Old_Turkic },
    { 686, PT_SC, ucp_Oriya },
    { 692, PT_SC, ucp_Osmanya },
    { 700, PT_GC, ucp_P },
    { 702, PT_PC, ucp_Pc },
    { 705, PT_PC, ucp_Pd },
    { 708, PT_PC, ucp_Pe },
    { 711, PT_PC, ucp_Pf },
    { 714, PT_SC, ucp_Phags_Pa },
    { 723, PT_SC, ucp_Phoenician },
    { 734, PT_PC, ucp_Pi },
    { 737, PT_PC, ucp_Po },
    { 740, PT_PC, ucp_Ps },
    { 743, PT_SC, ucp_Rejang },
    { 750, PT_SC, ucp_Runic },
    { 756, PT_GC, ucp_S },
    { 758, PT_SC, ucp_Samaritan },
    { 768, PT_SC, ucp_Saurashtra },
    { 779, PT_PC, ucp_Sc },
    { 782, PT_SC, ucp_Shavian },
    { 790, PT_SC, ucp_Sinhala },
    { 798, PT_PC, ucp_Sk },
    { 801, PT_PC, ucp_Sm },
    { 804, PT_PC, ucp_So },
    { 807, PT_SC, ucp_Sundanese },
    { 817, PT_SC, ucp_Syloti_Nagri },
    { 830, PT_SC, ucp_Syriac },
    { 837, PT_SC, ucp_Tagalog },
    { 845, PT_SC, ucp_Tagbanwa },
    { 854, PT_SC, ucp_Tai_Le },
    { 861, PT_SC, ucp_Tai_Tham },
    { 870, PT_SC, ucp_Tai_Viet },
    { 879, PT_SC, ucp_Tamil },
    { 885, PT_SC, ucp_Telugu },
    { 892, PT_SC, ucp_Thaana },
    { 899, PT_SC, ucp_Thai },
    { 904, PT_SC, ucp_Tibetan },
    { 912, PT_SC, ucp_Tifinagh },
    { 921, PT_SC, ucp_Ugaritic },
    { 930, PT_SC, ucp_Vai },
    { 934, PT_ALNUM, 0 },
    { 938, PT_PXSPACE, 0 },
    { 942, PT_SPACE, 0 },
    { 946, PT_WORD, 0 },
    { 950, PT_SC, ucp_Yi },
    { 953, PT_GC, ucp_Z },
    { 955, PT_PC, ucp_Zl },
    { 958, PT_PC, ucp_Zp },
    { 961, 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 */

 Legend:



Removed from v.592
 


changed lines


 
Added in v.836
 Legend:



Removed from v.592
 


changed lines


 
Added in v.836
-Removed from v.592
+Added in v.836

webmaster@exim.org	ViewVC Help
Powered by ViewVC 1.1.12