/[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 93 by nigel, Sat Feb 24 21:41:42 2007 UTC revision 1128 by chpe, Thu Oct 18 18:35:08 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) 1997-2006 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 44  uses macros to change their names from _ Line 45  uses macros to change their names from _
45  clashes with the library. */  clashes with the library. */
46    
47    
48    #ifdef HAVE_CONFIG_H
49    #include "config.h"
50    #endif
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    /* Tables of horizontal and vertical whitespace characters, suitable for
62    adding to classes. */
63    
64    const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST };
65    const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST };
66    
67    
68    
# Line 61  const uschar _pcre_OP_lengths[] = { OP_L Line 73  const uschar _pcre_OP_lengths[] = { OP_L
73  /* 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
74  character. */  character. */
75    
76  const int _pcre_utf8_table1[] =  #if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
77      || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32))
78    
79    /* These tables are also required by pcretest in 16- or 32-bit mode. */
80    
81    const int PRIV(utf8_table1)[] =
82    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
83    
84  const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);  const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
85    
86  /* 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
87  first byte of a character, indexed by the number of additional bytes. */  first byte of a character, indexed by the number of additional bytes. */
88    
89  const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};  const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
90  const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};  const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
91    
92  /* 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
93  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. */
94    
95  const uschar _pcre_utf8_table4[] = {  const pcre_uint8 PRIV(utf8_table4)[] = {
96    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,
97    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,
98    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,
99    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 };
100    
101  /* This table translates Unicode property names into type and code values. It  #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/
102  is searched by binary chop, so must be in collating sequence of name. */  
103    #ifdef SUPPORT_UTF
104    
105    /* Table to translate from particular type value to the general value. */
106    
107  const ucp_type_table _pcre_utt[] = {  const pcre_uint32 PRIV(ucp_gentype)[] = {
108    { "Any",                 PT_ANY,  0 },    ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
109    { "Arabic",              PT_SC,   ucp_Arabic },    ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
110    { "Armenian",            PT_SC,   ucp_Armenian },    ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
111    { "Balinese",            PT_SC,   ucp_Balinese },    ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
112    { "Bengali",             PT_SC,   ucp_Bengali },    ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
113    { "Bopomofo",            PT_SC,   ucp_Bopomofo },    ucp_P, ucp_P,                       /* Ps, Po */
114    { "Braille",             PT_SC,   ucp_Braille },    ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
115    { "Buginese",            PT_SC,   ucp_Buginese },    ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
   { "Buhid",               PT_SC,   ucp_Buhid },  
   { "C",                   PT_GC,   ucp_C },  
   { "Canadian_Aboriginal", PT_SC,   ucp_Canadian_Aboriginal },  
   { "Cc",                  PT_PC,   ucp_Cc },  
   { "Cf",                  PT_PC,   ucp_Cf },  
   { "Cherokee",            PT_SC,   ucp_Cherokee },  
   { "Cn",                  PT_PC,   ucp_Cn },  
   { "Co",                  PT_PC,   ucp_Co },  
   { "Common",              PT_SC,   ucp_Common },  
   { "Coptic",              PT_SC,   ucp_Coptic },  
   { "Cs",                  PT_PC,   ucp_Cs },  
   { "Cuneiform",           PT_SC,   ucp_Cuneiform },  
   { "Cypriot",             PT_SC,   ucp_Cypriot },  
   { "Cyrillic",            PT_SC,   ucp_Cyrillic },  
   { "Deseret",             PT_SC,   ucp_Deseret },  
   { "Devanagari",          PT_SC,   ucp_Devanagari },  
   { "Ethiopic",            PT_SC,   ucp_Ethiopic },  
   { "Georgian",            PT_SC,   ucp_Georgian },  
   { "Glagolitic",          PT_SC,   ucp_Glagolitic },  
   { "Gothic",              PT_SC,   ucp_Gothic },  
   { "Greek",               PT_SC,   ucp_Greek },  
   { "Gujarati",            PT_SC,   ucp_Gujarati },  
   { "Gurmukhi",            PT_SC,   ucp_Gurmukhi },  
   { "Han",                 PT_SC,   ucp_Han },  
   { "Hangul",              PT_SC,   ucp_Hangul },  
   { "Hanunoo",             PT_SC,   ucp_Hanunoo },  
   { "Hebrew",              PT_SC,   ucp_Hebrew },  
   { "Hiragana",            PT_SC,   ucp_Hiragana },  
   { "Inherited",           PT_SC,   ucp_Inherited },  
   { "Kannada",             PT_SC,   ucp_Kannada },  
   { "Katakana",            PT_SC,   ucp_Katakana },  
   { "Kharoshthi",          PT_SC,   ucp_Kharoshthi },  
   { "Khmer",               PT_SC,   ucp_Khmer },  
   { "L",                   PT_GC,   ucp_L },  
   { "L&",                  PT_LAMP, 0 },  
   { "Lao",                 PT_SC,   ucp_Lao },  
   { "Latin",               PT_SC,   ucp_Latin },  
   { "Limbu",               PT_SC,   ucp_Limbu },  
   { "Linear_B",            PT_SC,   ucp_Linear_B },  
   { "Ll",                  PT_PC,   ucp_Ll },  
   { "Lm",                  PT_PC,   ucp_Lm },  
   { "Lo",                  PT_PC,   ucp_Lo },  
   { "Lt",                  PT_PC,   ucp_Lt },  
   { "Lu",                  PT_PC,   ucp_Lu },  
   { "M",                   PT_GC,   ucp_M },  
   { "Malayalam",           PT_SC,   ucp_Malayalam },  
   { "Mc",                  PT_PC,   ucp_Mc },  
   { "Me",                  PT_PC,   ucp_Me },  
   { "Mn",                  PT_PC,   ucp_Mn },  
   { "Mongolian",           PT_SC,   ucp_Mongolian },  
   { "Myanmar",             PT_SC,   ucp_Myanmar },  
   { "N",                   PT_GC,   ucp_N },  
   { "Nd",                  PT_PC,   ucp_Nd },  
   { "New_Tai_Lue",         PT_SC,   ucp_New_Tai_Lue },  
   { "Nko",                 PT_SC,   ucp_Nko },  
   { "Nl",                  PT_PC,   ucp_Nl },  
   { "No",                  PT_PC,   ucp_No },  
   { "Ogham",               PT_SC,   ucp_Ogham },  
   { "Old_Italic",          PT_SC,   ucp_Old_Italic },  
   { "Old_Persian",         PT_SC,   ucp_Old_Persian },  
   { "Oriya",               PT_SC,   ucp_Oriya },  
   { "Osmanya",             PT_SC,   ucp_Osmanya },  
   { "P",                   PT_GC,   ucp_P },  
   { "Pc",                  PT_PC,   ucp_Pc },  
   { "Pd",                  PT_PC,   ucp_Pd },  
   { "Pe",                  PT_PC,   ucp_Pe },  
   { "Pf",                  PT_PC,   ucp_Pf },  
   { "Phags_Pa",            PT_SC,   ucp_Phags_Pa },  
   { "Phoenician",          PT_SC,   ucp_Phoenician },  
   { "Pi",                  PT_PC,   ucp_Pi },  
   { "Po",                  PT_PC,   ucp_Po },  
   { "Ps",                  PT_PC,   ucp_Ps },  
   { "Runic",               PT_SC,   ucp_Runic },  
   { "S",                   PT_GC,   ucp_S },  
   { "Sc",                  PT_PC,   ucp_Sc },  
   { "Shavian",             PT_SC,   ucp_Shavian },  
   { "Sinhala",             PT_SC,   ucp_Sinhala },  
   { "Sk",                  PT_PC,   ucp_Sk },  
   { "Sm",                  PT_PC,   ucp_Sm },  
   { "So",                  PT_PC,   ucp_So },  
   { "Syloti_Nagri",        PT_SC,   ucp_Syloti_Nagri },  
   { "Syriac",              PT_SC,   ucp_Syriac },  
   { "Tagalog",             PT_SC,   ucp_Tagalog },  
   { "Tagbanwa",            PT_SC,   ucp_Tagbanwa },  
   { "Tai_Le",              PT_SC,   ucp_Tai_Le },  
   { "Tamil",               PT_SC,   ucp_Tamil },  
   { "Telugu",              PT_SC,   ucp_Telugu },  
   { "Thaana",              PT_SC,   ucp_Thaana },  
   { "Thai",                PT_SC,   ucp_Thai },  
   { "Tibetan",             PT_SC,   ucp_Tibetan },  
   { "Tifinagh",            PT_SC,   ucp_Tifinagh },  
   { "Ugaritic",            PT_SC,   ucp_Ugaritic },  
   { "Yi",                  PT_SC,   ucp_Yi },  
   { "Z",                   PT_GC,   ucp_Z },  
   { "Zl",                  PT_PC,   ucp_Zl },  
   { "Zp",                  PT_PC,   ucp_Zp },  
   { "Zs",                  PT_PC,   ucp_Zs }  
116  };  };
117    
118  const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);  /* This table encodes the rules for finding the end of an extended grapheme
119    cluster. Every code point has a grapheme break property which is one of the
120    ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the
121    properties of two adjacent code points. The left property selects a word from
122    the table, and the right property selects a bit from that word like this:
123    
124      ucp_gbtable[left-property] & (1 << right-property)
125    
126    The value is non-zero if a grapheme break is NOT permitted between the relevant
127    two code points. The breaking rules are as follows:
128    
129    1. Break at the start and end of text (pretty obviously).
130    
131    2. Do not break between a CR and LF; otherwise, break before and   after
132       controls.
133    
134    3. Do not break Hangul syllable sequences, the rules for which are:
135    
136        L may be followed by L, V, LV or LVT
137        LV or V may be followed by V or T
138        LVT or T may be followed by T
139    
140    4. Do not break before extending characters.
141    
142    The next two rules are only for extended grapheme clusters (but that's what we
143    are implementing).
144    
145    5. Do not break before SpacingMarks.
146    
147    6. Do not break after Prepend characters.
148    
149    7. Otherwise, break everywhere.
150    */
151    
152    const pcre_uint32 PRIV(ucp_gbtable[]) = {
153       (1<<ucp_gbLF),                                           /*  0 CR */
154       0,                                                       /*  1 LF */
155       0,                                                       /*  2 Control */
156       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  3 Extend */
157       (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)|                    /*  4 Prepend */
158         (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|
159         (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)|
160         (1<<ucp_gbLVT)|(1<<ucp_gbOther),
161    
162       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  5 SpacingMark */
163       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|   /*  6 L */
164         (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT),
165    
166       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  7 V */
167         (1<<ucp_gbT),
168    
169       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /*  8 T */
170       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  9 LV */
171         (1<<ucp_gbT),
172    
173       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /* 10 LVT */
174       (1<<ucp_gbRegionalIndicator),                            /* 11 RegionalIndicator */
175       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)                 /* 12 Other */
176    };
177    
178    #ifdef SUPPORT_JIT
179    /* This table reverses PRIV(ucp_gentype). We can save the cost
180    of a memory load. */
181    
182    const int PRIV(ucp_typerange)[] = {
183      ucp_Cc, ucp_Cs,
184      ucp_Ll, ucp_Lu,
185      ucp_Mc, ucp_Mn,
186      ucp_Nd, ucp_No,
187      ucp_Pc, ucp_Ps,
188      ucp_Sc, ucp_So,
189      ucp_Zl, ucp_Zs,
190    };
191    #endif /* SUPPORT_JIT */
192    
193    /* The pcre_utt[] table below translates Unicode property names into type and
194    code values. It is searched by binary chop, so must be in collating sequence of
195    name. Originally, the table contained pointers to the name strings in the first
196    field of each entry. However, that leads to a large number of relocations when
197    a shared library is dynamically loaded. A significant reduction is made by
198    putting all the names into a single, large string and then using offsets in the
199    table itself. Maintenance is more error-prone, but frequent changes to this
200    data are unlikely.
201    
202    July 2008: There is now a script called maint/GenerateUtt.py that can be used
203    to generate this data automatically instead of maintaining it by hand.
204    
205    The script was updated in March 2009 to generate a new EBCDIC-compliant
206    version. Like all other character and string literals that are compared against
207    the regular expression pattern, we must use STR_ macros instead of literal
208    strings to make sure that UTF-8 support works on EBCDIC platforms. */
209    
210    #define STRING_Any0 STR_A STR_n STR_y "\0"
211    #define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
212    #define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
213    #define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
214    #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
215    #define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
216    #define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
217    #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
218    #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
219    #define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
220    #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
221    #define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
222    #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
223    #define STRING_C0 STR_C "\0"
224    #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"
225    #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
226    #define STRING_Cc0 STR_C STR_c "\0"
227    #define STRING_Cf0 STR_C STR_f "\0"
228    #define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
229    #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
230    #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
231    #define STRING_Cn0 STR_C STR_n "\0"
232    #define STRING_Co0 STR_C STR_o "\0"
233    #define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
234    #define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
235    #define STRING_Cs0 STR_C STR_s "\0"
236    #define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
237    #define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
238    #define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
239    #define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
240    #define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
241    #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"
242    #define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
243    #define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
244    #define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
245    #define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
246    #define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
247    #define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
248    #define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
249    #define STRING_Han0 STR_H STR_a STR_n "\0"
250    #define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
251    #define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
252    #define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
253    #define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
254    #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"
255    #define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
256    #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"
257    #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"
258    #define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
259    #define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
260    #define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
261    #define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
262    #define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
263    #define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
264    #define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
265    #define STRING_L0 STR_L "\0"
266    #define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
267    #define STRING_Lao0 STR_L STR_a STR_o "\0"
268    #define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
269    #define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
270    #define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
271    #define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
272    #define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
273    #define STRING_Ll0 STR_L STR_l "\0"
274    #define STRING_Lm0 STR_L STR_m "\0"
275    #define STRING_Lo0 STR_L STR_o "\0"
276    #define STRING_Lt0 STR_L STR_t "\0"
277    #define STRING_Lu0 STR_L STR_u "\0"
278    #define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
279    #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
280    #define STRING_M0 STR_M "\0"
281    #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
282    #define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
283    #define STRING_Mc0 STR_M STR_c "\0"
284    #define STRING_Me0 STR_M STR_e "\0"
285    #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"
286    #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"
287    #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"
288    #define STRING_Miao0 STR_M STR_i STR_a STR_o "\0"
289    #define STRING_Mn0 STR_M STR_n "\0"
290    #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
291    #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
292    #define STRING_N0 STR_N "\0"
293    #define STRING_Nd0 STR_N STR_d "\0"
294    #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"
295    #define STRING_Nko0 STR_N STR_k STR_o "\0"
296    #define STRING_Nl0 STR_N STR_l "\0"
297    #define STRING_No0 STR_N STR_o "\0"
298    #define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
299    #define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
300    #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"
301    #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"
302    #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"
303    #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"
304    #define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
305    #define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
306    #define STRING_P0 STR_P "\0"
307    #define STRING_Pc0 STR_P STR_c "\0"
308    #define STRING_Pd0 STR_P STR_d "\0"
309    #define STRING_Pe0 STR_P STR_e "\0"
310    #define STRING_Pf0 STR_P STR_f "\0"
311    #define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
312    #define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
313    #define STRING_Pi0 STR_P STR_i "\0"
314    #define STRING_Po0 STR_P STR_o "\0"
315    #define STRING_Ps0 STR_P STR_s "\0"
316    #define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
317    #define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
318    #define STRING_S0 STR_S "\0"
319    #define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
320    #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
321    #define STRING_Sc0 STR_S STR_c "\0"
322    #define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
323    #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
324    #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
325    #define STRING_Sk0 STR_S STR_k "\0"
326    #define STRING_Sm0 STR_S STR_m "\0"
327    #define STRING_So0 STR_S STR_o "\0"
328    #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"
329    #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
330    #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"
331    #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
332    #define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
333    #define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
334    #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
335    #define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
336    #define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
337    #define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
338    #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
339    #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
340    #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
341    #define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
342    #define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
343    #define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
344    #define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
345    #define STRING_Vai0 STR_V STR_a STR_i "\0"
346    #define STRING_Xan0 STR_X STR_a STR_n "\0"
347    #define STRING_Xps0 STR_X STR_p STR_s "\0"
348    #define STRING_Xsp0 STR_X STR_s STR_p "\0"
349    #define STRING_Xwd0 STR_X STR_w STR_d "\0"
350    #define STRING_Yi0 STR_Y STR_i "\0"
351    #define STRING_Z0 STR_Z "\0"
352    #define STRING_Zl0 STR_Z STR_l "\0"
353    #define STRING_Zp0 STR_Z STR_p "\0"
354    #define STRING_Zs0 STR_Z STR_s "\0"
355    
356    const char PRIV(utt_names)[] =
357      STRING_Any0
358      STRING_Arabic0
359      STRING_Armenian0
360      STRING_Avestan0
361      STRING_Balinese0
362      STRING_Bamum0
363      STRING_Batak0
364      STRING_Bengali0
365      STRING_Bopomofo0
366      STRING_Brahmi0
367      STRING_Braille0
368      STRING_Buginese0
369      STRING_Buhid0
370      STRING_C0
371      STRING_Canadian_Aboriginal0
372      STRING_Carian0
373      STRING_Cc0
374      STRING_Cf0
375      STRING_Chakma0
376      STRING_Cham0
377      STRING_Cherokee0
378      STRING_Cn0
379      STRING_Co0
380      STRING_Common0
381      STRING_Coptic0
382      STRING_Cs0
383      STRING_Cuneiform0
384      STRING_Cypriot0
385      STRING_Cyrillic0
386      STRING_Deseret0
387      STRING_Devanagari0
388      STRING_Egyptian_Hieroglyphs0
389      STRING_Ethiopic0
390      STRING_Georgian0
391      STRING_Glagolitic0
392      STRING_Gothic0
393      STRING_Greek0
394      STRING_Gujarati0
395      STRING_Gurmukhi0
396      STRING_Han0
397      STRING_Hangul0
398      STRING_Hanunoo0
399      STRING_Hebrew0
400      STRING_Hiragana0
401      STRING_Imperial_Aramaic0
402      STRING_Inherited0
403      STRING_Inscriptional_Pahlavi0
404      STRING_Inscriptional_Parthian0
405      STRING_Javanese0
406      STRING_Kaithi0
407      STRING_Kannada0
408      STRING_Katakana0
409      STRING_Kayah_Li0
410      STRING_Kharoshthi0
411      STRING_Khmer0
412      STRING_L0
413      STRING_L_AMPERSAND0
414      STRING_Lao0
415      STRING_Latin0
416      STRING_Lepcha0
417      STRING_Limbu0
418      STRING_Linear_B0
419      STRING_Lisu0
420      STRING_Ll0
421      STRING_Lm0
422      STRING_Lo0
423      STRING_Lt0
424      STRING_Lu0
425      STRING_Lycian0
426      STRING_Lydian0
427      STRING_M0
428      STRING_Malayalam0
429      STRING_Mandaic0
430      STRING_Mc0
431      STRING_Me0
432      STRING_Meetei_Mayek0
433      STRING_Meroitic_Cursive0
434      STRING_Meroitic_Hieroglyphs0
435      STRING_Miao0
436      STRING_Mn0
437      STRING_Mongolian0
438      STRING_Myanmar0
439      STRING_N0
440      STRING_Nd0
441      STRING_New_Tai_Lue0
442      STRING_Nko0
443      STRING_Nl0
444      STRING_No0
445      STRING_Ogham0
446      STRING_Ol_Chiki0
447      STRING_Old_Italic0
448      STRING_Old_Persian0
449      STRING_Old_South_Arabian0
450      STRING_Old_Turkic0
451      STRING_Oriya0
452      STRING_Osmanya0
453      STRING_P0
454      STRING_Pc0
455      STRING_Pd0
456      STRING_Pe0
457      STRING_Pf0
458      STRING_Phags_Pa0
459      STRING_Phoenician0
460      STRING_Pi0
461      STRING_Po0
462      STRING_Ps0
463      STRING_Rejang0
464      STRING_Runic0
465      STRING_S0
466      STRING_Samaritan0
467      STRING_Saurashtra0
468      STRING_Sc0
469      STRING_Sharada0
470      STRING_Shavian0
471      STRING_Sinhala0
472      STRING_Sk0
473      STRING_Sm0
474      STRING_So0
475      STRING_Sora_Sompeng0
476      STRING_Sundanese0
477      STRING_Syloti_Nagri0
478      STRING_Syriac0
479      STRING_Tagalog0
480      STRING_Tagbanwa0
481      STRING_Tai_Le0
482      STRING_Tai_Tham0
483      STRING_Tai_Viet0
484      STRING_Takri0
485      STRING_Tamil0
486      STRING_Telugu0
487      STRING_Thaana0
488      STRING_Thai0
489      STRING_Tibetan0
490      STRING_Tifinagh0
491      STRING_Ugaritic0
492      STRING_Vai0
493      STRING_Xan0
494      STRING_Xps0
495      STRING_Xsp0
496      STRING_Xwd0
497      STRING_Yi0
498      STRING_Z0
499      STRING_Zl0
500      STRING_Zp0
501      STRING_Zs0;
502    
503    const ucp_type_table PRIV(utt)[] = {
504      {   0, PT_ANY, 0 },
505      {   4, PT_SC, ucp_Arabic },
506      {  11, PT_SC, ucp_Armenian },
507      {  20, PT_SC, ucp_Avestan },
508      {  28, PT_SC, ucp_Balinese },
509      {  37, PT_SC, ucp_Bamum },
510      {  43, PT_SC, ucp_Batak },
511      {  49, PT_SC, ucp_Bengali },
512      {  57, PT_SC, ucp_Bopomofo },
513      {  66, PT_SC, ucp_Brahmi },
514      {  73, PT_SC, ucp_Braille },
515      {  81, PT_SC, ucp_Buginese },
516      {  90, PT_SC, ucp_Buhid },
517      {  96, PT_GC, ucp_C },
518      {  98, PT_SC, ucp_Canadian_Aboriginal },
519      { 118, PT_SC, ucp_Carian },
520      { 125, PT_PC, ucp_Cc },
521      { 128, PT_PC, ucp_Cf },
522      { 131, PT_SC, ucp_Chakma },
523      { 138, PT_SC, ucp_Cham },
524      { 143, PT_SC, ucp_Cherokee },
525      { 152, PT_PC, ucp_Cn },
526      { 155, PT_PC, ucp_Co },
527      { 158, PT_SC, ucp_Common },
528      { 165, PT_SC, ucp_Coptic },
529      { 172, PT_PC, ucp_Cs },
530      { 175, PT_SC, ucp_Cuneiform },
531      { 185, PT_SC, ucp_Cypriot },
532      { 193, PT_SC, ucp_Cyrillic },
533      { 202, PT_SC, ucp_Deseret },
534      { 210, PT_SC, ucp_Devanagari },
535      { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
536      { 242, PT_SC, ucp_Ethiopic },
537      { 251, PT_SC, ucp_Georgian },
538      { 260, PT_SC, ucp_Glagolitic },
539      { 271, PT_SC, ucp_Gothic },
540      { 278, PT_SC, ucp_Greek },
541      { 284, PT_SC, ucp_Gujarati },
542      { 293, PT_SC, ucp_Gurmukhi },
543      { 302, PT_SC, ucp_Han },
544      { 306, PT_SC, ucp_Hangul },
545      { 313, PT_SC, ucp_Hanunoo },
546      { 321, PT_SC, ucp_Hebrew },
547      { 328, PT_SC, ucp_Hiragana },
548      { 337, PT_SC, ucp_Imperial_Aramaic },
549      { 354, PT_SC, ucp_Inherited },
550      { 364, PT_SC, ucp_Inscriptional_Pahlavi },
551      { 386, PT_SC, ucp_Inscriptional_Parthian },
552      { 409, PT_SC, ucp_Javanese },
553      { 418, PT_SC, ucp_Kaithi },
554      { 425, PT_SC, ucp_Kannada },
555      { 433, PT_SC, ucp_Katakana },
556      { 442, PT_SC, ucp_Kayah_Li },
557      { 451, PT_SC, ucp_Kharoshthi },
558      { 462, PT_SC, ucp_Khmer },
559      { 468, PT_GC, ucp_L },
560      { 470, PT_LAMP, 0 },
561      { 473, PT_SC, ucp_Lao },
562      { 477, PT_SC, ucp_Latin },
563      { 483, PT_SC, ucp_Lepcha },
564      { 490, PT_SC, ucp_Limbu },
565      { 496, PT_SC, ucp_Linear_B },
566      { 505, PT_SC, ucp_Lisu },
567      { 510, PT_PC, ucp_Ll },
568      { 513, PT_PC, ucp_Lm },
569      { 516, PT_PC, ucp_Lo },
570      { 519, PT_PC, ucp_Lt },
571      { 522, PT_PC, ucp_Lu },
572      { 525, PT_SC, ucp_Lycian },
573      { 532, PT_SC, ucp_Lydian },
574      { 539, PT_GC, ucp_M },
575      { 541, PT_SC, ucp_Malayalam },
576      { 551, PT_SC, ucp_Mandaic },
577      { 559, PT_PC, ucp_Mc },
578      { 562, PT_PC, ucp_Me },
579      { 565, PT_SC, ucp_Meetei_Mayek },
580      { 578, PT_SC, ucp_Meroitic_Cursive },
581      { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
582      { 616, PT_SC, ucp_Miao },
583      { 621, PT_PC, ucp_Mn },
584      { 624, PT_SC, ucp_Mongolian },
585      { 634, PT_SC, ucp_Myanmar },
586      { 642, PT_GC, ucp_N },
587      { 644, PT_PC, ucp_Nd },
588      { 647, PT_SC, ucp_New_Tai_Lue },
589      { 659, PT_SC, ucp_Nko },
590      { 663, PT_PC, ucp_Nl },
591      { 666, PT_PC, ucp_No },
592      { 669, PT_SC, ucp_Ogham },
593      { 675, PT_SC, ucp_Ol_Chiki },
594      { 684, PT_SC, ucp_Old_Italic },
595      { 695, PT_SC, ucp_Old_Persian },
596      { 707, PT_SC, ucp_Old_South_Arabian },
597      { 725, PT_SC, ucp_Old_Turkic },
598      { 736, PT_SC, ucp_Oriya },
599      { 742, PT_SC, ucp_Osmanya },
600      { 750, PT_GC, ucp_P },
601      { 752, PT_PC, ucp_Pc },
602      { 755, PT_PC, ucp_Pd },
603      { 758, PT_PC, ucp_Pe },
604      { 761, PT_PC, ucp_Pf },
605      { 764, PT_SC, ucp_Phags_Pa },
606      { 773, PT_SC, ucp_Phoenician },
607      { 784, PT_PC, ucp_Pi },
608      { 787, PT_PC, ucp_Po },
609      { 790, PT_PC, ucp_Ps },
610      { 793, PT_SC, ucp_Rejang },
611      { 800, PT_SC, ucp_Runic },
612      { 806, PT_GC, ucp_S },
613      { 808, PT_SC, ucp_Samaritan },
614      { 818, PT_SC, ucp_Saurashtra },
615      { 829, PT_PC, ucp_Sc },
616      { 832, PT_SC, ucp_Sharada },
617      { 840, PT_SC, ucp_Shavian },
618      { 848, PT_SC, ucp_Sinhala },
619      { 856, PT_PC, ucp_Sk },
620      { 859, PT_PC, ucp_Sm },
621      { 862, PT_PC, ucp_So },
622      { 865, PT_SC, ucp_Sora_Sompeng },
623      { 878, PT_SC, ucp_Sundanese },
624      { 888, PT_SC, ucp_Syloti_Nagri },
625      { 901, PT_SC, ucp_Syriac },
626      { 908, PT_SC, ucp_Tagalog },
627      { 916, PT_SC, ucp_Tagbanwa },
628      { 925, PT_SC, ucp_Tai_Le },
629      { 932, PT_SC, ucp_Tai_Tham },
630      { 941, PT_SC, ucp_Tai_Viet },
631      { 950, PT_SC, ucp_Takri },
632      { 956, PT_SC, ucp_Tamil },
633      { 962, PT_SC, ucp_Telugu },
634      { 969, PT_SC, ucp_Thaana },
635      { 976, PT_SC, ucp_Thai },
636      { 981, PT_SC, ucp_Tibetan },
637      { 989, PT_SC, ucp_Tifinagh },
638      { 998, PT_SC, ucp_Ugaritic },
639      { 1007, PT_SC, ucp_Vai },
640      { 1011, PT_ALNUM, 0 },
641      { 1015, PT_PXSPACE, 0 },
642      { 1019, PT_SPACE, 0 },
643      { 1023, PT_WORD, 0 },
644      { 1027, PT_SC, ucp_Yi },
645      { 1030, PT_GC, ucp_Z },
646      { 1032, PT_PC, ucp_Zl },
647      { 1035, PT_PC, ucp_Zp },
648      { 1038, PT_PC, ucp_Zs }
649    };
650    
651    const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
652    
653    #endif /* SUPPORT_UTF */
654    
655  /* End of pcre_tables.c */  /* End of pcre_tables.c */

Legend:
Removed from v.93  
changed lines
  Added in v.1128

  ViewVC Help
Powered by ViewVC 1.1.5