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

Diff of /code/trunk/pcre_tables.c

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 236 by ph10, Tue Sep 11 12:57:06 2007 UTC revision 975 by ph10, Sat Jun 2 11:03:06 2012 UTC
# Line 6  Line 6 
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.
7    
8                         Written by Philip Hazel                         Written by Philip Hazel
9             Copyright (c) 1997-2007 University of Cambridge             Copyright (c) 1997-2012 University of Cambridge
10    
11  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
12  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.
37  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
38  */  */
39    
40    #ifndef PCRE_INCLUDED
41    
42  /* 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
43  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. */
51    
52  #include "pcre_internal.h"  #include "pcre_internal.h"
53    
54    #endif /* PCRE_INCLUDED */
55    
56  /* 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
57  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. */
58    
59  const uschar _pcre_OP_lengths[] = { OP_LENGTHS };  const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
60    
61    
62    
# Line 65  const uschar _pcre_OP_lengths[] = { OP_L Line 67  const uschar _pcre_OP_lengths[] = { OP_L
67  /* 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
68  character. */  character. */
69    
70  #ifdef SUPPORT_UTF8  #if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
71      || (defined PCRE_INCLUDED && defined SUPPORT_PCRE16)
72    
73  const int _pcre_utf8_table1[] =  /* These tables are also required by pcretest in 16 bit mode. */
74    
75    const int PRIV(utf8_table1)[] =
76    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
77    
78  const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);  const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
79    
80  /* 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
81  first byte of a character, indexed by the number of additional bytes. */  first byte of a character, indexed by the number of additional bytes. */
82    
83  const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};  const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
84  const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};  const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
85    
86  /* 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
87  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. */
88    
89  const uschar _pcre_utf8_table4[] = {  const pcre_uint8 PRIV(utf8_table4)[] = {
90    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,
91    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,
92    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,
93    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 };
94    
95  /* This table translates Unicode property names into type and code values. It  #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/
96  is searched by binary chop, so must be in collating sequence of name. */  
97    #ifdef SUPPORT_UTF
98    
99    /* Table to translate from particular type value to the general value. */
100    
101    const int PRIV(ucp_gentype)[] = {
102      ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
103      ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
104      ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
105      ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
106      ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
107      ucp_P, ucp_P,                       /* Ps, Po */
108      ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
109      ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
110    };
111    
112    #ifdef SUPPORT_JIT
113    /* This table reverses PRIV(ucp_gentype). We can save the cost
114    of a memory load. */
115    
116    const int PRIV(ucp_typerange)[] = {
117      ucp_Cc, ucp_Cs,
118      ucp_Ll, ucp_Lu,
119      ucp_Mc, ucp_Mn,
120      ucp_Nd, ucp_No,
121      ucp_Pc, ucp_Ps,
122      ucp_Sc, ucp_So,
123      ucp_Zl, ucp_Zs,
124    };
125    #endif /* SUPPORT_JIT */
126    
127  const ucp_type_table _pcre_utt[] = {  /* The pcre_utt[] table below translates Unicode property names into type and
128    { "Any",                 PT_ANY,  0 },  code values. It is searched by binary chop, so must be in collating sequence of
129    { "Arabic",              PT_SC,   ucp_Arabic },  name. Originally, the table contained pointers to the name strings in the first
130    { "Armenian",            PT_SC,   ucp_Armenian },  field of each entry. However, that leads to a large number of relocations when
131    { "Balinese",            PT_SC,   ucp_Balinese },  a shared library is dynamically loaded. A significant reduction is made by
132    { "Bengali",             PT_SC,   ucp_Bengali },  putting all the names into a single, large string and then using offsets in the
133    { "Bopomofo",            PT_SC,   ucp_Bopomofo },  table itself. Maintenance is more error-prone, but frequent changes to this
134    { "Braille",             PT_SC,   ucp_Braille },  data are unlikely.
135    { "Buginese",            PT_SC,   ucp_Buginese },  
136    { "Buhid",               PT_SC,   ucp_Buhid },  July 2008: There is now a script called maint/GenerateUtt.py that can be used
137    { "C",                   PT_GC,   ucp_C },  to generate this data automatically instead of maintaining it by hand.
138    { "Canadian_Aboriginal", PT_SC,   ucp_Canadian_Aboriginal },  
139    { "Cc",                  PT_PC,   ucp_Cc },  The script was updated in March 2009 to generate a new EBCDIC-compliant
140    { "Cf",                  PT_PC,   ucp_Cf },  version. Like all other character and string literals that are compared against
141    { "Cherokee",            PT_SC,   ucp_Cherokee },  the regular expression pattern, we must use STR_ macros instead of literal
142    { "Cn",                  PT_PC,   ucp_Cn },  strings to make sure that UTF-8 support works on EBCDIC platforms. */
143    { "Co",                  PT_PC,   ucp_Co },  
144    { "Common",              PT_SC,   ucp_Common },  #define STRING_Any0 STR_A STR_n STR_y "\0"
145    { "Coptic",              PT_SC,   ucp_Coptic },  #define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
146    { "Cs",                  PT_PC,   ucp_Cs },  #define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
147    { "Cuneiform",           PT_SC,   ucp_Cuneiform },  #define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
148    { "Cypriot",             PT_SC,   ucp_Cypriot },  #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
149    { "Cyrillic",            PT_SC,   ucp_Cyrillic },  #define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
150    { "Deseret",             PT_SC,   ucp_Deseret },  #define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
151    { "Devanagari",          PT_SC,   ucp_Devanagari },  #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
152    { "Ethiopic",            PT_SC,   ucp_Ethiopic },  #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
153    { "Georgian",            PT_SC,   ucp_Georgian },  #define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
154    { "Glagolitic",          PT_SC,   ucp_Glagolitic },  #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
155    { "Gothic",              PT_SC,   ucp_Gothic },  #define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
156    { "Greek",               PT_SC,   ucp_Greek },  #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
157    { "Gujarati",            PT_SC,   ucp_Gujarati },  #define STRING_C0 STR_C "\0"
158    { "Gurmukhi",            PT_SC,   ucp_Gurmukhi },  #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"
159    { "Han",                 PT_SC,   ucp_Han },  #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
160    { "Hangul",              PT_SC,   ucp_Hangul },  #define STRING_Cc0 STR_C STR_c "\0"
161    { "Hanunoo",             PT_SC,   ucp_Hanunoo },  #define STRING_Cf0 STR_C STR_f "\0"
162    { "Hebrew",              PT_SC,   ucp_Hebrew },  #define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
163    { "Hiragana",            PT_SC,   ucp_Hiragana },  #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
164    { "Inherited",           PT_SC,   ucp_Inherited },  #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
165    { "Kannada",             PT_SC,   ucp_Kannada },  #define STRING_Cn0 STR_C STR_n "\0"
166    { "Katakana",            PT_SC,   ucp_Katakana },  #define STRING_Co0 STR_C STR_o "\0"
167    { "Kharoshthi",          PT_SC,   ucp_Kharoshthi },  #define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
168    { "Khmer",               PT_SC,   ucp_Khmer },  #define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
169    { "L",                   PT_GC,   ucp_L },  #define STRING_Cs0 STR_C STR_s "\0"
170    { "L&",                  PT_LAMP, 0 },  #define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
171    { "Lao",                 PT_SC,   ucp_Lao },  #define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
172    { "Latin",               PT_SC,   ucp_Latin },  #define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
173    { "Limbu",               PT_SC,   ucp_Limbu },  #define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
174    { "Linear_B",            PT_SC,   ucp_Linear_B },  #define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
175    { "Ll",                  PT_PC,   ucp_Ll },  #define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n 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"
176    { "Lm",                  PT_PC,   ucp_Lm },  #define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
177    { "Lo",                  PT_PC,   ucp_Lo },  #define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
178    { "Lt",                  PT_PC,   ucp_Lt },  #define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
179    { "Lu",                  PT_PC,   ucp_Lu },  #define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
180    { "M",                   PT_GC,   ucp_M },  #define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
181    { "Malayalam",           PT_SC,   ucp_Malayalam },  #define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
182    { "Mc",                  PT_PC,   ucp_Mc },  #define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
183    { "Me",                  PT_PC,   ucp_Me },  #define STRING_Han0 STR_H STR_a STR_n "\0"
184    { "Mn",                  PT_PC,   ucp_Mn },  #define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
185    { "Mongolian",           PT_SC,   ucp_Mongolian },  #define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
186    { "Myanmar",             PT_SC,   ucp_Myanmar },  #define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
187    { "N",                   PT_GC,   ucp_N },  #define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
188    { "Nd",                  PT_PC,   ucp_Nd },  #define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
189    { "New_Tai_Lue",         PT_SC,   ucp_New_Tai_Lue },  #define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
190    { "Nko",                 PT_SC,   ucp_Nko },  #define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
191    { "Nl",                  PT_PC,   ucp_Nl },  #define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0"
192    { "No",                  PT_PC,   ucp_No },  #define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
193    { "Ogham",               PT_SC,   ucp_Ogham },  #define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
194    { "Old_Italic",          PT_SC,   ucp_Old_Italic },  #define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
195    { "Old_Persian",         PT_SC,   ucp_Old_Persian },  #define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
196    { "Oriya",               PT_SC,   ucp_Oriya },  #define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
197    { "Osmanya",             PT_SC,   ucp_Osmanya },  #define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
198    { "P",                   PT_GC,   ucp_P },  #define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
199    { "Pc",                  PT_PC,   ucp_Pc },  #define STRING_L0 STR_L "\0"
200    { "Pd",                  PT_PC,   ucp_Pd },  #define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
201    { "Pe",                  PT_PC,   ucp_Pe },  #define STRING_Lao0 STR_L STR_a STR_o "\0"
202    { "Pf",                  PT_PC,   ucp_Pf },  #define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
203    { "Phags_Pa",            PT_SC,   ucp_Phags_Pa },  #define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
204    { "Phoenician",          PT_SC,   ucp_Phoenician },  #define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
205    { "Pi",                  PT_PC,   ucp_Pi },  #define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
206    { "Po",                  PT_PC,   ucp_Po },  #define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
207    { "Ps",                  PT_PC,   ucp_Ps },  #define STRING_Ll0 STR_L STR_l "\0"
208    { "Runic",               PT_SC,   ucp_Runic },  #define STRING_Lm0 STR_L STR_m "\0"
209    { "S",                   PT_GC,   ucp_S },  #define STRING_Lo0 STR_L STR_o "\0"
210    { "Sc",                  PT_PC,   ucp_Sc },  #define STRING_Lt0 STR_L STR_t "\0"
211    { "Shavian",             PT_SC,   ucp_Shavian },  #define STRING_Lu0 STR_L STR_u "\0"
212    { "Sinhala",             PT_SC,   ucp_Sinhala },  #define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
213    { "Sk",                  PT_PC,   ucp_Sk },  #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
214    { "Sm",                  PT_PC,   ucp_Sm },  #define STRING_M0 STR_M "\0"
215    { "So",                  PT_PC,   ucp_So },  #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
216    { "Syloti_Nagri",        PT_SC,   ucp_Syloti_Nagri },  #define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
217    { "Syriac",              PT_SC,   ucp_Syriac },  #define STRING_Mc0 STR_M STR_c "\0"
218    { "Tagalog",             PT_SC,   ucp_Tagalog },  #define STRING_Me0 STR_M STR_e "\0"
219    { "Tagbanwa",            PT_SC,   ucp_Tagbanwa },  #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"
220    { "Tai_Le",              PT_SC,   ucp_Tai_Le },  #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"
221    { "Tamil",               PT_SC,   ucp_Tamil },  #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"
222    { "Telugu",              PT_SC,   ucp_Telugu },  #define STRING_Miao0 STR_M STR_i STR_a STR_o "\0"
223    { "Thaana",              PT_SC,   ucp_Thaana },  #define STRING_Mn0 STR_M STR_n "\0"
224    { "Thai",                PT_SC,   ucp_Thai },  #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
225    { "Tibetan",             PT_SC,   ucp_Tibetan },  #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
226    { "Tifinagh",            PT_SC,   ucp_Tifinagh },  #define STRING_N0 STR_N "\0"
227    { "Ugaritic",            PT_SC,   ucp_Ugaritic },  #define STRING_Nd0 STR_N STR_d "\0"
228    { "Yi",                  PT_SC,   ucp_Yi },  #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"
229    { "Z",                   PT_GC,   ucp_Z },  #define STRING_Nko0 STR_N STR_k STR_o "\0"
230    { "Zl",                  PT_PC,   ucp_Zl },  #define STRING_Nl0 STR_N STR_l "\0"
231    { "Zp",                  PT_PC,   ucp_Zp },  #define STRING_No0 STR_N STR_o "\0"
232    { "Zs",                  PT_PC,   ucp_Zs }  #define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
233    #define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
234    #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"
235    #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"
236    #define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
237    #define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
238    #define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
239    #define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
240    #define STRING_P0 STR_P "\0"
241    #define STRING_Pc0 STR_P STR_c "\0"
242    #define STRING_Pd0 STR_P STR_d "\0"
243    #define STRING_Pe0 STR_P STR_e "\0"
244    #define STRING_Pf0 STR_P STR_f "\0"
245    #define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
246    #define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
247    #define STRING_Pi0 STR_P STR_i "\0"
248    #define STRING_Po0 STR_P STR_o "\0"
249    #define STRING_Ps0 STR_P STR_s "\0"
250    #define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
251    #define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
252    #define STRING_S0 STR_S "\0"
253    #define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
254    #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
255    #define STRING_Sc0 STR_S STR_c "\0"
256    #define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
257    #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
258    #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
259    #define STRING_Sk0 STR_S STR_k "\0"
260    #define STRING_Sm0 STR_S STR_m "\0"
261    #define STRING_So0 STR_S STR_o "\0"
262    #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"
263    #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
264    #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"
265    #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
266    #define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
267    #define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
268    #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
269    #define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
270    #define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
271    #define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
272    #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
273    #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
274    #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
275    #define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
276    #define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
277    #define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
278    #define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
279    #define STRING_Vai0 STR_V STR_a STR_i "\0"
280    #define STRING_Xan0 STR_X STR_a STR_n "\0"
281    #define STRING_Xps0 STR_X STR_p STR_s "\0"
282    #define STRING_Xsp0 STR_X STR_s STR_p "\0"
283    #define STRING_Xwd0 STR_X STR_w STR_d "\0"
284    #define STRING_Yi0 STR_Y STR_i "\0"
285    #define STRING_Z0 STR_Z "\0"
286    #define STRING_Zl0 STR_Z STR_l "\0"
287    #define STRING_Zp0 STR_Z STR_p "\0"
288    #define STRING_Zs0 STR_Z STR_s "\0"
289    
290    const char PRIV(utt_names)[] =
291      STRING_Any0
292      STRING_Arabic0
293      STRING_Armenian0
294      STRING_Avestan0
295      STRING_Balinese0
296      STRING_Bamum0
297      STRING_Batak0
298      STRING_Bengali0
299      STRING_Bopomofo0
300      STRING_Brahmi0
301      STRING_Braille0
302      STRING_Buginese0
303      STRING_Buhid0
304      STRING_C0
305      STRING_Canadian_Aboriginal0
306      STRING_Carian0
307      STRING_Cc0
308      STRING_Cf0
309      STRING_Chakma0
310      STRING_Cham0
311      STRING_Cherokee0
312      STRING_Cn0
313      STRING_Co0
314      STRING_Common0
315      STRING_Coptic0
316      STRING_Cs0
317      STRING_Cuneiform0
318      STRING_Cypriot0
319      STRING_Cyrillic0
320      STRING_Deseret0
321      STRING_Devanagari0
322      STRING_Egyptian_Hieroglyphs0
323      STRING_Ethiopic0
324      STRING_Georgian0
325      STRING_Glagolitic0
326      STRING_Gothic0
327      STRING_Greek0
328      STRING_Gujarati0
329      STRING_Gurmukhi0
330      STRING_Han0
331      STRING_Hangul0
332      STRING_Hanunoo0
333      STRING_Hebrew0
334      STRING_Hiragana0
335      STRING_Imperial_Aramaic0
336      STRING_Inherited0
337      STRING_Inscriptional_Pahlavi0
338      STRING_Inscriptional_Parthian0
339      STRING_Javanese0
340      STRING_Kaithi0
341      STRING_Kannada0
342      STRING_Katakana0
343      STRING_Kayah_Li0
344      STRING_Kharoshthi0
345      STRING_Khmer0
346      STRING_L0
347      STRING_L_AMPERSAND0
348      STRING_Lao0
349      STRING_Latin0
350      STRING_Lepcha0
351      STRING_Limbu0
352      STRING_Linear_B0
353      STRING_Lisu0
354      STRING_Ll0
355      STRING_Lm0
356      STRING_Lo0
357      STRING_Lt0
358      STRING_Lu0
359      STRING_Lycian0
360      STRING_Lydian0
361      STRING_M0
362      STRING_Malayalam0
363      STRING_Mandaic0
364      STRING_Mc0
365      STRING_Me0
366      STRING_Meetei_Mayek0
367      STRING_Meroitic_Cursive0
368      STRING_Meroitic_Hieroglyphs0
369      STRING_Miao0
370      STRING_Mn0
371      STRING_Mongolian0
372      STRING_Myanmar0
373      STRING_N0
374      STRING_Nd0
375      STRING_New_Tai_Lue0
376      STRING_Nko0
377      STRING_Nl0
378      STRING_No0
379      STRING_Ogham0
380      STRING_Ol_Chiki0
381      STRING_Old_Italic0
382      STRING_Old_Persian0
383      STRING_Old_South_Arabian0
384      STRING_Old_Turkic0
385      STRING_Oriya0
386      STRING_Osmanya0
387      STRING_P0
388      STRING_Pc0
389      STRING_Pd0
390      STRING_Pe0
391      STRING_Pf0
392      STRING_Phags_Pa0
393      STRING_Phoenician0
394      STRING_Pi0
395      STRING_Po0
396      STRING_Ps0
397      STRING_Rejang0
398      STRING_Runic0
399      STRING_S0
400      STRING_Samaritan0
401      STRING_Saurashtra0
402      STRING_Sc0
403      STRING_Sharada0
404      STRING_Shavian0
405      STRING_Sinhala0
406      STRING_Sk0
407      STRING_Sm0
408      STRING_So0
409      STRING_Sora_Sompeng0
410      STRING_Sundanese0
411      STRING_Syloti_Nagri0
412      STRING_Syriac0
413      STRING_Tagalog0
414      STRING_Tagbanwa0
415      STRING_Tai_Le0
416      STRING_Tai_Tham0
417      STRING_Tai_Viet0
418      STRING_Takri0
419      STRING_Tamil0
420      STRING_Telugu0
421      STRING_Thaana0
422      STRING_Thai0
423      STRING_Tibetan0
424      STRING_Tifinagh0
425      STRING_Ugaritic0
426      STRING_Vai0
427      STRING_Xan0
428      STRING_Xps0
429      STRING_Xsp0
430      STRING_Xwd0
431      STRING_Yi0
432      STRING_Z0
433      STRING_Zl0
434      STRING_Zp0
435      STRING_Zs0;
436    
437    const ucp_type_table PRIV(utt)[] = {
438      {   0, PT_ANY, 0 },
439      {   4, PT_SC, ucp_Arabic },
440      {  11, PT_SC, ucp_Armenian },
441      {  20, PT_SC, ucp_Avestan },
442      {  28, PT_SC, ucp_Balinese },
443      {  37, PT_SC, ucp_Bamum },
444      {  43, PT_SC, ucp_Batak },
445      {  49, PT_SC, ucp_Bengali },
446      {  57, PT_SC, ucp_Bopomofo },
447      {  66, PT_SC, ucp_Brahmi },
448      {  73, PT_SC, ucp_Braille },
449      {  81, PT_SC, ucp_Buginese },
450      {  90, PT_SC, ucp_Buhid },
451      {  96, PT_GC, ucp_C },
452      {  98, PT_SC, ucp_Canadian_Aboriginal },
453      { 118, PT_SC, ucp_Carian },
454      { 125, PT_PC, ucp_Cc },
455      { 128, PT_PC, ucp_Cf },
456      { 131, PT_SC, ucp_Chakma },
457      { 138, PT_SC, ucp_Cham },
458      { 143, PT_SC, ucp_Cherokee },
459      { 152, PT_PC, ucp_Cn },
460      { 155, PT_PC, ucp_Co },
461      { 158, PT_SC, ucp_Common },
462      { 165, PT_SC, ucp_Coptic },
463      { 172, PT_PC, ucp_Cs },
464      { 175, PT_SC, ucp_Cuneiform },
465      { 185, PT_SC, ucp_Cypriot },
466      { 193, PT_SC, ucp_Cyrillic },
467      { 202, PT_SC, ucp_Deseret },
468      { 210, PT_SC, ucp_Devanagari },
469      { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
470      { 242, PT_SC, ucp_Ethiopic },
471      { 251, PT_SC, ucp_Georgian },
472      { 260, PT_SC, ucp_Glagolitic },
473      { 271, PT_SC, ucp_Gothic },
474      { 278, PT_SC, ucp_Greek },
475      { 284, PT_SC, ucp_Gujarati },
476      { 293, PT_SC, ucp_Gurmukhi },
477      { 302, PT_SC, ucp_Han },
478      { 306, PT_SC, ucp_Hangul },
479      { 313, PT_SC, ucp_Hanunoo },
480      { 321, PT_SC, ucp_Hebrew },
481      { 328, PT_SC, ucp_Hiragana },
482      { 337, PT_SC, ucp_Imperial_Aramaic },
483      { 354, PT_SC, ucp_Inherited },
484      { 364, PT_SC, ucp_Inscriptional_Pahlavi },
485      { 386, PT_SC, ucp_Inscriptional_Parthian },
486      { 409, PT_SC, ucp_Javanese },
487      { 418, PT_SC, ucp_Kaithi },
488      { 425, PT_SC, ucp_Kannada },
489      { 433, PT_SC, ucp_Katakana },
490      { 442, PT_SC, ucp_Kayah_Li },
491      { 451, PT_SC, ucp_Kharoshthi },
492      { 462, PT_SC, ucp_Khmer },
493      { 468, PT_GC, ucp_L },
494      { 470, PT_LAMP, 0 },
495      { 473, PT_SC, ucp_Lao },
496      { 477, PT_SC, ucp_Latin },
497      { 483, PT_SC, ucp_Lepcha },
498      { 490, PT_SC, ucp_Limbu },
499      { 496, PT_SC, ucp_Linear_B },
500      { 505, PT_SC, ucp_Lisu },
501      { 510, PT_PC, ucp_Ll },
502      { 513, PT_PC, ucp_Lm },
503      { 516, PT_PC, ucp_Lo },
504      { 519, PT_PC, ucp_Lt },
505      { 522, PT_PC, ucp_Lu },
506      { 525, PT_SC, ucp_Lycian },
507      { 532, PT_SC, ucp_Lydian },
508      { 539, PT_GC, ucp_M },
509      { 541, PT_SC, ucp_Malayalam },
510      { 551, PT_SC, ucp_Mandaic },
511      { 559, PT_PC, ucp_Mc },
512      { 562, PT_PC, ucp_Me },
513      { 565, PT_SC, ucp_Meetei_Mayek },
514      { 578, PT_SC, ucp_Meroitic_Cursive },
515      { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
516      { 616, PT_SC, ucp_Miao },
517      { 621, PT_PC, ucp_Mn },
518      { 624, PT_SC, ucp_Mongolian },
519      { 634, PT_SC, ucp_Myanmar },
520      { 642, PT_GC, ucp_N },
521      { 644, PT_PC, ucp_Nd },
522      { 647, PT_SC, ucp_New_Tai_Lue },
523      { 659, PT_SC, ucp_Nko },
524      { 663, PT_PC, ucp_Nl },
525      { 666, PT_PC, ucp_No },
526      { 669, PT_SC, ucp_Ogham },
527      { 675, PT_SC, ucp_Ol_Chiki },
528      { 684, PT_SC, ucp_Old_Italic },
529      { 695, PT_SC, ucp_Old_Persian },
530      { 707, PT_SC, ucp_Old_South_Arabian },
531      { 725, PT_SC, ucp_Old_Turkic },
532      { 736, PT_SC, ucp_Oriya },
533      { 742, PT_SC, ucp_Osmanya },
534      { 750, PT_GC, ucp_P },
535      { 752, PT_PC, ucp_Pc },
536      { 755, PT_PC, ucp_Pd },
537      { 758, PT_PC, ucp_Pe },
538      { 761, PT_PC, ucp_Pf },
539      { 764, PT_SC, ucp_Phags_Pa },
540      { 773, PT_SC, ucp_Phoenician },
541      { 784, PT_PC, ucp_Pi },
542      { 787, PT_PC, ucp_Po },
543      { 790, PT_PC, ucp_Ps },
544      { 793, PT_SC, ucp_Rejang },
545      { 800, PT_SC, ucp_Runic },
546      { 806, PT_GC, ucp_S },
547      { 808, PT_SC, ucp_Samaritan },
548      { 818, PT_SC, ucp_Saurashtra },
549      { 829, PT_PC, ucp_Sc },
550      { 832, PT_SC, ucp_Sharada },
551      { 840, PT_SC, ucp_Shavian },
552      { 848, PT_SC, ucp_Sinhala },
553      { 856, PT_PC, ucp_Sk },
554      { 859, PT_PC, ucp_Sm },
555      { 862, PT_PC, ucp_So },
556      { 865, PT_SC, ucp_Sora_Sompeng },
557      { 878, PT_SC, ucp_Sundanese },
558      { 888, PT_SC, ucp_Syloti_Nagri },
559      { 901, PT_SC, ucp_Syriac },
560      { 908, PT_SC, ucp_Tagalog },
561      { 916, PT_SC, ucp_Tagbanwa },
562      { 925, PT_SC, ucp_Tai_Le },
563      { 932, PT_SC, ucp_Tai_Tham },
564      { 941, PT_SC, ucp_Tai_Viet },
565      { 950, PT_SC, ucp_Takri },
566      { 956, PT_SC, ucp_Tamil },
567      { 962, PT_SC, ucp_Telugu },
568      { 969, PT_SC, ucp_Thaana },
569      { 976, PT_SC, ucp_Thai },
570      { 981, PT_SC, ucp_Tibetan },
571      { 989, PT_SC, ucp_Tifinagh },
572      { 998, PT_SC, ucp_Ugaritic },
573      { 1007, PT_SC, ucp_Vai },
574      { 1011, PT_ALNUM, 0 },
575      { 1015, PT_PXSPACE, 0 },
576      { 1019, PT_SPACE, 0 },
577      { 1023, PT_WORD, 0 },
578      { 1027, PT_SC, ucp_Yi },
579      { 1030, PT_GC, ucp_Z },
580      { 1032, PT_PC, ucp_Zl },
581      { 1035, PT_PC, ucp_Zp },
582      { 1038, PT_PC, ucp_Zs }
583  };  };
584    
585  const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);  const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
586    
587  #endif  /* SUPPORT_UTF8 */  #endif /* SUPPORT_UTF */
588    
589  /* End of pcre_tables.c */  /* End of pcre_tables.c */

Legend:
Removed from v.236  
changed lines
  Added in v.975

  ViewVC Help
Powered by ViewVC 1.1.5