/[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 491 by ph10, Mon Mar 1 17:45:08 2010 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) 1997-2009 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    /* 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 65  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  #ifdef SUPPORT_UTF8  #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 _pcre_utf8_table1[] =  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    #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/
102    
103    #ifdef SUPPORT_UTF
104    
105  /* Table to translate from particular type value to the general value. */  /* Table to translate from particular type value to the general value. */
106    
107  const int _pcre_ucp_gentype[] = {  const pcre_uint32 PRIV(ucp_gentype)[] = {
108    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 */
109    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 */
110    ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */    ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
# Line 100  const int _pcre_ucp_gentype[] = { Line 115  const int _pcre_ucp_gentype[] = {
115    ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */    ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
116  };  };
117    
118    /* 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  /* 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  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  name. Originally, the table contained pointers to the name strings in the first
# Line 110  table itself. Maintenance is more error- Line 200  table itself. Maintenance is more error-
200  data are unlikely.  data are unlikely.
201    
202  July 2008: There is now a script called maint/GenerateUtt.py that can be used  July 2008: There is now a script called maint/GenerateUtt.py that can be used
203  to generate this data instead of maintaining it entirely by hand.  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  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  version. Like all other character and string literals that are compared against
# Line 123  strings to make sure that UTF-8 support Line 213  strings to make sure that UTF-8 support
213  #define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"  #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"  #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"  #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"  #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"  #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"  #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"  #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"  #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
# Line 133  strings to make sure that UTF-8 support Line 225  strings to make sure that UTF-8 support
225  #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"
226  #define STRING_Cc0 STR_C STR_c "\0"  #define STRING_Cc0 STR_C STR_c "\0"
227  #define STRING_Cf0 STR_C STR_f "\0"  #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"  #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"  #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"  #define STRING_Cn0 STR_C STR_n "\0"
# Line 186  strings to make sure that UTF-8 support Line 279  strings to make sure that UTF-8 support
279  #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"  #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
280  #define STRING_M0 STR_M "\0"  #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"  #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"  #define STRING_Mc0 STR_M STR_c "\0"
284  #define STRING_Me0 STR_M STR_e "\0"  #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"  #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"  #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"  #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"  #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
# Line 222  strings to make sure that UTF-8 support Line 319  strings to make sure that UTF-8 support
319  #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"
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"  #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"  #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"  #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"  #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"  #define STRING_Sk0 STR_S STR_k "\0"
326  #define STRING_Sm0 STR_S STR_m "\0"  #define STRING_Sm0 STR_S STR_m "\0"
327  #define STRING_So0 STR_S STR_o "\0"  #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"  #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"  #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"  #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
# Line 235  strings to make sure that UTF-8 support Line 334  strings to make sure that UTF-8 support
334  #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"
335  #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"
336  #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"
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"  #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"  #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"  #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
# Line 243  strings to make sure that UTF-8 support Line 343  strings to make sure that UTF-8 support
343  #define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"  #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"  #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"  #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"  #define STRING_Yi0 STR_Y STR_i "\0"
351  #define STRING_Z0 STR_Z "\0"  #define STRING_Z0 STR_Z "\0"
352  #define STRING_Zl0 STR_Z STR_l "\0"  #define STRING_Zl0 STR_Z STR_l "\0"
353  #define STRING_Zp0 STR_Z STR_p "\0"  #define STRING_Zp0 STR_Z STR_p "\0"
354  #define STRING_Zs0 STR_Z STR_s "\0"  #define STRING_Zs0 STR_Z STR_s "\0"
355    
356  const char _pcre_utt_names[] =  const char PRIV(utt_names)[] =
357    STRING_Any0    STRING_Any0
358    STRING_Arabic0    STRING_Arabic0
359    STRING_Armenian0    STRING_Armenian0
360    STRING_Avestan0    STRING_Avestan0
361    STRING_Balinese0    STRING_Balinese0
362    STRING_Bamum0    STRING_Bamum0
363      STRING_Batak0
364    STRING_Bengali0    STRING_Bengali0
365    STRING_Bopomofo0    STRING_Bopomofo0
366      STRING_Brahmi0
367    STRING_Braille0    STRING_Braille0
368    STRING_Buginese0    STRING_Buginese0
369    STRING_Buhid0    STRING_Buhid0
# Line 266  const char _pcre_utt_names[] = Line 372  const char _pcre_utt_names[] =
372    STRING_Carian0    STRING_Carian0
373    STRING_Cc0    STRING_Cc0
374    STRING_Cf0    STRING_Cf0
375      STRING_Chakma0
376    STRING_Cham0    STRING_Cham0
377    STRING_Cherokee0    STRING_Cherokee0
378    STRING_Cn0    STRING_Cn0
# Line 319  const char _pcre_utt_names[] = Line 426  const char _pcre_utt_names[] =
426    STRING_Lydian0    STRING_Lydian0
427    STRING_M0    STRING_M0
428    STRING_Malayalam0    STRING_Malayalam0
429      STRING_Mandaic0
430    STRING_Mc0    STRING_Mc0
431    STRING_Me0    STRING_Me0
432    STRING_Meetei_Mayek0    STRING_Meetei_Mayek0
433      STRING_Meroitic_Cursive0
434      STRING_Meroitic_Hieroglyphs0
435      STRING_Miao0
436    STRING_Mn0    STRING_Mn0
437    STRING_Mongolian0    STRING_Mongolian0
438    STRING_Myanmar0    STRING_Myanmar0
# Line 355  const char _pcre_utt_names[] = Line 466  const char _pcre_utt_names[] =
466    STRING_Samaritan0    STRING_Samaritan0
467    STRING_Saurashtra0    STRING_Saurashtra0
468    STRING_Sc0    STRING_Sc0
469      STRING_Sharada0
470    STRING_Shavian0    STRING_Shavian0
471    STRING_Sinhala0    STRING_Sinhala0
472    STRING_Sk0    STRING_Sk0
473    STRING_Sm0    STRING_Sm0
474    STRING_So0    STRING_So0
475      STRING_Sora_Sompeng0
476    STRING_Sundanese0    STRING_Sundanese0
477    STRING_Syloti_Nagri0    STRING_Syloti_Nagri0
478    STRING_Syriac0    STRING_Syriac0
# Line 368  const char _pcre_utt_names[] = Line 481  const char _pcre_utt_names[] =
481    STRING_Tai_Le0    STRING_Tai_Le0
482    STRING_Tai_Tham0    STRING_Tai_Tham0
483    STRING_Tai_Viet0    STRING_Tai_Viet0
484      STRING_Takri0
485    STRING_Tamil0    STRING_Tamil0
486    STRING_Telugu0    STRING_Telugu0
487    STRING_Thaana0    STRING_Thaana0
# Line 376  const char _pcre_utt_names[] = Line 490  const char _pcre_utt_names[] =
490    STRING_Tifinagh0    STRING_Tifinagh0
491    STRING_Ugaritic0    STRING_Ugaritic0
492    STRING_Vai0    STRING_Vai0
493      STRING_Xan0
494      STRING_Xps0
495      STRING_Xsp0
496      STRING_Xwd0
497    STRING_Yi0    STRING_Yi0
498    STRING_Z0    STRING_Z0
499    STRING_Zl0    STRING_Zl0
500    STRING_Zp0    STRING_Zp0
501    STRING_Zs0;    STRING_Zs0;
502    
503  const ucp_type_table _pcre_utt[] = {  const ucp_type_table PRIV(utt)[] = {
504    {   0, PT_ANY, 0 },    {   0, PT_ANY, 0 },
505    {   4, PT_SC, ucp_Arabic },    {   4, PT_SC, ucp_Arabic },
506    {  11, PT_SC, ucp_Armenian },    {  11, PT_SC, ucp_Armenian },
507    {  20, PT_SC, ucp_Avestan },    {  20, PT_SC, ucp_Avestan },
508    {  28, PT_SC, ucp_Balinese },    {  28, PT_SC, ucp_Balinese },
509    {  37, PT_SC, ucp_Bamum },    {  37, PT_SC, ucp_Bamum },
510    {  43, PT_SC, ucp_Bengali },    {  43, PT_SC, ucp_Batak },
511    {  51, PT_SC, ucp_Bopomofo },    {  49, PT_SC, ucp_Bengali },
512    {  60, PT_SC, ucp_Braille },    {  57, PT_SC, ucp_Bopomofo },
513    {  68, PT_SC, ucp_Buginese },    {  66, PT_SC, ucp_Brahmi },
514    {  77, PT_SC, ucp_Buhid },    {  73, PT_SC, ucp_Braille },
515    {  83, PT_GC, ucp_C },    {  81, PT_SC, ucp_Buginese },
516    {  85, PT_SC, ucp_Canadian_Aboriginal },    {  90, PT_SC, ucp_Buhid },
517    { 105, PT_SC, ucp_Carian },    {  96, PT_GC, ucp_C },
518    { 112, PT_PC, ucp_Cc },    {  98, PT_SC, ucp_Canadian_Aboriginal },
519    { 115, PT_PC, ucp_Cf },    { 118, PT_SC, ucp_Carian },
520    { 118, PT_SC, ucp_Cham },    { 125, PT_PC, ucp_Cc },
521    { 123, PT_SC, ucp_Cherokee },    { 128, PT_PC, ucp_Cf },
522    { 132, PT_PC, ucp_Cn },    { 131, PT_SC, ucp_Chakma },
523    { 135, PT_PC, ucp_Co },    { 138, PT_SC, ucp_Cham },
524    { 138, PT_SC, ucp_Common },    { 143, PT_SC, ucp_Cherokee },
525    { 145, PT_SC, ucp_Coptic },    { 152, PT_PC, ucp_Cn },
526    { 152, PT_PC, ucp_Cs },    { 155, PT_PC, ucp_Co },
527    { 155, PT_SC, ucp_Cuneiform },    { 158, PT_SC, ucp_Common },
528    { 165, PT_SC, ucp_Cypriot },    { 165, PT_SC, ucp_Coptic },
529    { 173, PT_SC, ucp_Cyrillic },    { 172, PT_PC, ucp_Cs },
530    { 182, PT_SC, ucp_Deseret },    { 175, PT_SC, ucp_Cuneiform },
531    { 190, PT_SC, ucp_Devanagari },    { 185, PT_SC, ucp_Cypriot },
532    { 201, PT_SC, ucp_Egyptian_Hieroglyphs },    { 193, PT_SC, ucp_Cyrillic },
533    { 222, PT_SC, ucp_Ethiopic },    { 202, PT_SC, ucp_Deseret },
534    { 231, PT_SC, ucp_Georgian },    { 210, PT_SC, ucp_Devanagari },
535    { 240, PT_SC, ucp_Glagolitic },    { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
536    { 251, PT_SC, ucp_Gothic },    { 242, PT_SC, ucp_Ethiopic },
537    { 258, PT_SC, ucp_Greek },    { 251, PT_SC, ucp_Georgian },
538    { 264, PT_SC, ucp_Gujarati },    { 260, PT_SC, ucp_Glagolitic },
539    { 273, PT_SC, ucp_Gurmukhi },    { 271, PT_SC, ucp_Gothic },
540    { 282, PT_SC, ucp_Han },    { 278, PT_SC, ucp_Greek },
541    { 286, PT_SC, ucp_Hangul },    { 284, PT_SC, ucp_Gujarati },
542    { 293, PT_SC, ucp_Hanunoo },    { 293, PT_SC, ucp_Gurmukhi },
543    { 301, PT_SC, ucp_Hebrew },    { 302, PT_SC, ucp_Han },
544    { 308, PT_SC, ucp_Hiragana },    { 306, PT_SC, ucp_Hangul },
545    { 317, PT_SC, ucp_Imperial_Aramaic },    { 313, PT_SC, ucp_Hanunoo },
546    { 334, PT_SC, ucp_Inherited },    { 321, PT_SC, ucp_Hebrew },
547    { 344, PT_SC, ucp_Inscriptional_Pahlavi },    { 328, PT_SC, ucp_Hiragana },
548    { 366, PT_SC, ucp_Inscriptional_Parthian },    { 337, PT_SC, ucp_Imperial_Aramaic },
549    { 389, PT_SC, ucp_Javanese },    { 354, PT_SC, ucp_Inherited },
550    { 398, PT_SC, ucp_Kaithi },    { 364, PT_SC, ucp_Inscriptional_Pahlavi },
551    { 405, PT_SC, ucp_Kannada },    { 386, PT_SC, ucp_Inscriptional_Parthian },
552    { 413, PT_SC, ucp_Katakana },    { 409, PT_SC, ucp_Javanese },
553    { 422, PT_SC, ucp_Kayah_Li },    { 418, PT_SC, ucp_Kaithi },
554    { 431, PT_SC, ucp_Kharoshthi },    { 425, PT_SC, ucp_Kannada },
555    { 442, PT_SC, ucp_Khmer },    { 433, PT_SC, ucp_Katakana },
556    { 448, PT_GC, ucp_L },    { 442, PT_SC, ucp_Kayah_Li },
557    { 450, PT_LAMP, 0 },    { 451, PT_SC, ucp_Kharoshthi },
558    { 453, PT_SC, ucp_Lao },    { 462, PT_SC, ucp_Khmer },
559    { 457, PT_SC, ucp_Latin },    { 468, PT_GC, ucp_L },
560    { 463, PT_SC, ucp_Lepcha },    { 470, PT_LAMP, 0 },
561    { 470, PT_SC, ucp_Limbu },    { 473, PT_SC, ucp_Lao },
562    { 476, PT_SC, ucp_Linear_B },    { 477, PT_SC, ucp_Latin },
563    { 485, PT_SC, ucp_Lisu },    { 483, PT_SC, ucp_Lepcha },
564    { 490, PT_PC, ucp_Ll },    { 490, PT_SC, ucp_Limbu },
565    { 493, PT_PC, ucp_Lm },    { 496, PT_SC, ucp_Linear_B },
566    { 496, PT_PC, ucp_Lo },    { 505, PT_SC, ucp_Lisu },
567    { 499, PT_PC, ucp_Lt },    { 510, PT_PC, ucp_Ll },
568    { 502, PT_PC, ucp_Lu },    { 513, PT_PC, ucp_Lm },
569    { 505, PT_SC, ucp_Lycian },    { 516, PT_PC, ucp_Lo },
570    { 512, PT_SC, ucp_Lydian },    { 519, PT_PC, ucp_Lt },
571    { 519, PT_GC, ucp_M },    { 522, PT_PC, ucp_Lu },
572    { 521, PT_SC, ucp_Malayalam },    { 525, PT_SC, ucp_Lycian },
573    { 531, PT_PC, ucp_Mc },    { 532, PT_SC, ucp_Lydian },
574    { 534, PT_PC, ucp_Me },    { 539, PT_GC, ucp_M },
575    { 537, PT_SC, ucp_Meetei_Mayek },    { 541, PT_SC, ucp_Malayalam },
576    { 550, PT_PC, ucp_Mn },    { 551, PT_SC, ucp_Mandaic },
577    { 553, PT_SC, ucp_Mongolian },    { 559, PT_PC, ucp_Mc },
578    { 563, PT_SC, ucp_Myanmar },    { 562, PT_PC, ucp_Me },
579    { 571, PT_GC, ucp_N },    { 565, PT_SC, ucp_Meetei_Mayek },
580    { 573, PT_PC, ucp_Nd },    { 578, PT_SC, ucp_Meroitic_Cursive },
581    { 576, PT_SC, ucp_New_Tai_Lue },    { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
582    { 588, PT_SC, ucp_Nko },    { 616, PT_SC, ucp_Miao },
583    { 592, PT_PC, ucp_Nl },    { 621, PT_PC, ucp_Mn },
584    { 595, PT_PC, ucp_No },    { 624, PT_SC, ucp_Mongolian },
585    { 598, PT_SC, ucp_Ogham },    { 634, PT_SC, ucp_Myanmar },
586    { 604, PT_SC, ucp_Ol_Chiki },    { 642, PT_GC, ucp_N },
587    { 613, PT_SC, ucp_Old_Italic },    { 644, PT_PC, ucp_Nd },
588    { 624, PT_SC, ucp_Old_Persian },    { 647, PT_SC, ucp_New_Tai_Lue },
589    { 636, PT_SC, ucp_Old_South_Arabian },    { 659, PT_SC, ucp_Nko },
590    { 654, PT_SC, ucp_Old_Turkic },    { 663, PT_PC, ucp_Nl },
591    { 665, PT_SC, ucp_Oriya },    { 666, PT_PC, ucp_No },
592    { 671, PT_SC, ucp_Osmanya },    { 669, PT_SC, ucp_Ogham },
593    { 679, PT_GC, ucp_P },    { 675, PT_SC, ucp_Ol_Chiki },
594    { 681, PT_PC, ucp_Pc },    { 684, PT_SC, ucp_Old_Italic },
595    { 684, PT_PC, ucp_Pd },    { 695, PT_SC, ucp_Old_Persian },
596    { 687, PT_PC, ucp_Pe },    { 707, PT_SC, ucp_Old_South_Arabian },
597    { 690, PT_PC, ucp_Pf },    { 725, PT_SC, ucp_Old_Turkic },
598    { 693, PT_SC, ucp_Phags_Pa },    { 736, PT_SC, ucp_Oriya },
599    { 702, PT_SC, ucp_Phoenician },    { 742, PT_SC, ucp_Osmanya },
600    { 713, PT_PC, ucp_Pi },    { 750, PT_GC, ucp_P },
601    { 716, PT_PC, ucp_Po },    { 752, PT_PC, ucp_Pc },
602    { 719, PT_PC, ucp_Ps },    { 755, PT_PC, ucp_Pd },
603    { 722, PT_SC, ucp_Rejang },    { 758, PT_PC, ucp_Pe },
604    { 729, PT_SC, ucp_Runic },    { 761, PT_PC, ucp_Pf },
605    { 735, PT_GC, ucp_S },    { 764, PT_SC, ucp_Phags_Pa },
606    { 737, PT_SC, ucp_Samaritan },    { 773, PT_SC, ucp_Phoenician },
607    { 747, PT_SC, ucp_Saurashtra },    { 784, PT_PC, ucp_Pi },
608    { 758, PT_PC, ucp_Sc },    { 787, PT_PC, ucp_Po },
609    { 761, PT_SC, ucp_Shavian },    { 790, PT_PC, ucp_Ps },
610    { 769, PT_SC, ucp_Sinhala },    { 793, PT_SC, ucp_Rejang },
611    { 777, PT_PC, ucp_Sk },    { 800, PT_SC, ucp_Runic },
612    { 780, PT_PC, ucp_Sm },    { 806, PT_GC, ucp_S },
613    { 783, PT_PC, ucp_So },    { 808, PT_SC, ucp_Samaritan },
614    { 786, PT_SC, ucp_Sundanese },    { 818, PT_SC, ucp_Saurashtra },
615    { 796, PT_SC, ucp_Syloti_Nagri },    { 829, PT_PC, ucp_Sc },
616    { 809, PT_SC, ucp_Syriac },    { 832, PT_SC, ucp_Sharada },
617    { 816, PT_SC, ucp_Tagalog },    { 840, PT_SC, ucp_Shavian },
618    { 824, PT_SC, ucp_Tagbanwa },    { 848, PT_SC, ucp_Sinhala },
619    { 833, PT_SC, ucp_Tai_Le },    { 856, PT_PC, ucp_Sk },
620    { 840, PT_SC, ucp_Tai_Tham },    { 859, PT_PC, ucp_Sm },
621    { 849, PT_SC, ucp_Tai_Viet },    { 862, PT_PC, ucp_So },
622    { 858, PT_SC, ucp_Tamil },    { 865, PT_SC, ucp_Sora_Sompeng },
623    { 864, PT_SC, ucp_Telugu },    { 878, PT_SC, ucp_Sundanese },
624    { 871, PT_SC, ucp_Thaana },    { 888, PT_SC, ucp_Syloti_Nagri },
625    { 878, PT_SC, ucp_Thai },    { 901, PT_SC, ucp_Syriac },
626    { 883, PT_SC, ucp_Tibetan },    { 908, PT_SC, ucp_Tagalog },
627    { 891, PT_SC, ucp_Tifinagh },    { 916, PT_SC, ucp_Tagbanwa },
628    { 900, PT_SC, ucp_Ugaritic },    { 925, PT_SC, ucp_Tai_Le },
629    { 909, PT_SC, ucp_Vai },    { 932, PT_SC, ucp_Tai_Tham },
630    { 913, PT_SC, ucp_Yi },    { 941, PT_SC, ucp_Tai_Viet },
631    { 916, PT_GC, ucp_Z },    { 950, PT_SC, ucp_Takri },
632    { 918, PT_PC, ucp_Zl },    { 956, PT_SC, ucp_Tamil },
633    { 921, PT_PC, ucp_Zp },    { 962, PT_SC, ucp_Telugu },
634    { 924, PT_PC, ucp_Zs }    { 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 _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);  const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
652    
653  #endif  /* SUPPORT_UTF8 */  #endif /* SUPPORT_UTF */
654    
655  /* End of pcre_tables.c */  /* End of pcre_tables.c */

Legend:
Removed from v.491  
changed lines
  Added in v.1128

  ViewVC Help
Powered by ViewVC 1.1.5