/[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 85 by nigel, Sat Feb 24 21:41:13 2007 UTC revision 351 by ph10, Fri Jul 4 18:27:16 2008 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) 1997-2005 University of Cambridge             Copyright (c) 1997-2008 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 44  uses macros to change their names from _ Line 44  uses macros to change their names from _
44  clashes with the library. */  clashes with the library. */
45    
46    
47    #ifdef HAVE_CONFIG_H
48    #include "config.h"
49    #endif
50    
51  #include "pcre_internal.h"  #include "pcre_internal.h"
52    
53    
54  /* 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
55  the definition is next to the definition of the opcodes in internal.h. */  the definition is next to the definition of the opcodes in pcre_internal.h. */
56    
57  const uschar _pcre_OP_lengths[] = { OP_LENGTHS };  const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
58    
# Line 61  const uschar _pcre_OP_lengths[] = { OP_L Line 65  const uschar _pcre_OP_lengths[] = { OP_L
65  /* 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
66  character. */  character. */
67    
68    #ifdef SUPPORT_UTF8
69    
70  const int _pcre_utf8_table1[] =  const int _pcre_utf8_table1[] =
71    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
72    
# Line 72  first byte of a character, indexed by th Line 78  first byte of a character, indexed by th
78  const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};  const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
79  const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};  const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
80    
81  /* Table of the number of extra characters, indexed by the first character  /* Table of the number of extra bytes, indexed by the first byte masked with
82  masked with 0x3f. The highest number for a valid UTF-8 character is in fact  0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
 0x3d. */  
83    
84  const uschar _pcre_utf8_table4[] = {  const uschar _pcre_utf8_table4[] = {
85    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,
# Line 82  const uschar _pcre_utf8_table4[] = { Line 87  const uschar _pcre_utf8_table4[] = {
87    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,
88    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 };
89    
90  /* This table translates Unicode property names into code values for the  /* Table to translate from particular type value to the general value. */
91  ucp_findchar() function. */  
92    const int _pcre_ucp_gentype[] = {
93      ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
94      ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
95      ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
96      ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
97      ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
98      ucp_P, ucp_P,                       /* Ps, Po */
99      ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
100      ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
101    };
102    
103    /* The pcre_utt[] table below translates Unicode property names into type and
104    code values. It is searched by binary chop, so must be in collating sequence of
105    name. Originally, the table contained pointers to the name strings in the first
106    field of each entry. However, that leads to a large number of relocations when
107    a shared library is dynamically loaded. A significant reduction is made by
108    putting all the names into a single, large string and then using offsets in the
109    table itself. Maintenance is more error-prone, but frequent changes to this
110    data are unlikely.
111    
112    July 2008: There is now a script called maint/GenerateUtt.py which can be used
113    to generate this data instead of maintaining it entirely by hand. */
114    
115    const char _pcre_utt_names[] =
116      "Any\0"
117      "Arabic\0"
118      "Armenian\0"
119      "Balinese\0"
120      "Bengali\0"
121      "Bopomofo\0"
122      "Braille\0"
123      "Buginese\0"
124      "Buhid\0"
125      "C\0"
126      "Canadian_Aboriginal\0"
127      "Carian\0"
128      "Cc\0"
129      "Cf\0"
130      "Cham\0"
131      "Cherokee\0"
132      "Cn\0"
133      "Co\0"
134      "Common\0"
135      "Coptic\0"
136      "Cs\0"
137      "Cuneiform\0"
138      "Cypriot\0"
139      "Cyrillic\0"
140      "Deseret\0"
141      "Devanagari\0"
142      "Ethiopic\0"
143      "Georgian\0"
144      "Glagolitic\0"
145      "Gothic\0"
146      "Greek\0"
147      "Gujarati\0"
148      "Gurmukhi\0"
149      "Han\0"
150      "Hangul\0"
151      "Hanunoo\0"
152      "Hebrew\0"
153      "Hiragana\0"
154      "Inherited\0"
155      "Kannada\0"
156      "Katakana\0"
157      "Kayah_Li\0"
158      "Kharoshthi\0"
159      "Khmer\0"
160      "L\0"
161      "L&\0"
162      "Lao\0"
163      "Latin\0"
164      "Lepcha\0"
165      "Limbu\0"
166      "Linear_B\0"
167      "Ll\0"
168      "Lm\0"
169      "Lo\0"
170      "Lt\0"
171      "Lu\0"
172      "Lycian\0"
173      "Lydian\0"
174      "M\0"
175      "Malayalam\0"
176      "Mc\0"
177      "Me\0"
178      "Mn\0"
179      "Mongolian\0"
180      "Myanmar\0"
181      "N\0"
182      "Nd\0"
183      "New_Tai_Lue\0"
184      "Nko\0"
185      "Nl\0"
186      "No\0"
187      "Ogham\0"
188      "Ol_Chiki\0"
189      "Old_Italic\0"
190      "Old_Persian\0"
191      "Oriya\0"
192      "Osmanya\0"
193      "P\0"
194      "Pc\0"
195      "Pd\0"
196      "Pe\0"
197      "Pf\0"
198      "Phags_Pa\0"
199      "Phoenician\0"
200      "Pi\0"
201      "Po\0"
202      "Ps\0"
203      "Rejang\0"
204      "Runic\0"
205      "S\0"
206      "Saurashtra\0"
207      "Sc\0"
208      "Shavian\0"
209      "Sinhala\0"
210      "Sk\0"
211      "Sm\0"
212      "So\0"
213      "Sundanese\0"
214      "Syloti_Nagri\0"
215      "Syriac\0"
216      "Tagalog\0"
217      "Tagbanwa\0"
218      "Tai_Le\0"
219      "Tamil\0"
220      "Telugu\0"
221      "Thaana\0"
222      "Thai\0"
223      "Tibetan\0"
224      "Tifinagh\0"
225      "Ugaritic\0"
226      "Vai\0"
227      "Yi\0"
228      "Z\0"
229      "Zl\0"
230      "Zp\0"
231      "Zs\0";
232    
233  const ucp_type_table _pcre_utt[] = {  const ucp_type_table _pcre_utt[] = {
234    { "C",  128 + ucp_C },    {   0, PT_ANY, 0 },
235    { "Cc", ucp_Cc },    {   4, PT_SC, ucp_Arabic },
236    { "Cf", ucp_Cf },    {  11, PT_SC, ucp_Armenian },
237    { "Cn", ucp_Cn },    {  20, PT_SC, ucp_Balinese },
238    { "Co", ucp_Co },    {  29, PT_SC, ucp_Bengali },
239    { "Cs", ucp_Cs },    {  37, PT_SC, ucp_Bopomofo },
240    { "L",  128 + ucp_L },    {  46, PT_SC, ucp_Braille },
241    { "Ll", ucp_Ll },    {  54, PT_SC, ucp_Buginese },
242    { "Lm", ucp_Lm },    {  63, PT_SC, ucp_Buhid },
243    { "Lo", ucp_Lo },    {  69, PT_GC, ucp_C },
244    { "Lt", ucp_Lt },    {  71, PT_SC, ucp_Canadian_Aboriginal },
245    { "Lu", ucp_Lu },    {  91, PT_SC, ucp_Carian },
246    { "M",  128 + ucp_M },    {  98, PT_PC, ucp_Cc },
247    { "Mc", ucp_Mc },    { 101, PT_PC, ucp_Cf },
248    { "Me", ucp_Me },    { 104, PT_SC, ucp_Cham },
249    { "Mn", ucp_Mn },    { 109, PT_SC, ucp_Cherokee },
250    { "N",  128 + ucp_N },    { 118, PT_PC, ucp_Cn },
251    { "Nd", ucp_Nd },    { 121, PT_PC, ucp_Co },
252    { "Nl", ucp_Nl },    { 124, PT_SC, ucp_Common },
253    { "No", ucp_No },    { 131, PT_SC, ucp_Coptic },
254    { "P",  128 + ucp_P },    { 138, PT_PC, ucp_Cs },
255    { "Pc", ucp_Pc },    { 141, PT_SC, ucp_Cuneiform },
256    { "Pd", ucp_Pd },    { 151, PT_SC, ucp_Cypriot },
257    { "Pe", ucp_Pe },    { 159, PT_SC, ucp_Cyrillic },
258    { "Pf", ucp_Pf },    { 168, PT_SC, ucp_Deseret },
259    { "Pi", ucp_Pi },    { 176, PT_SC, ucp_Devanagari },
260    { "Po", ucp_Po },    { 187, PT_SC, ucp_Ethiopic },
261    { "Ps", ucp_Ps },    { 196, PT_SC, ucp_Georgian },
262    { "S",  128 + ucp_S },    { 205, PT_SC, ucp_Glagolitic },
263    { "Sc", ucp_Sc },    { 216, PT_SC, ucp_Gothic },
264    { "Sk", ucp_Sk },    { 223, PT_SC, ucp_Greek },
265    { "Sm", ucp_Sm },    { 229, PT_SC, ucp_Gujarati },
266    { "So", ucp_So },    { 238, PT_SC, ucp_Gurmukhi },
267    { "Z",  128 + ucp_Z },    { 247, PT_SC, ucp_Han },
268    { "Zl", ucp_Zl },    { 251, PT_SC, ucp_Hangul },
269    { "Zp", ucp_Zp },    { 258, PT_SC, ucp_Hanunoo },
270    { "Zs", ucp_Zs }    { 266, PT_SC, ucp_Hebrew },
271      { 273, PT_SC, ucp_Hiragana },
272      { 282, PT_SC, ucp_Inherited },
273      { 292, PT_SC, ucp_Kannada },
274      { 300, PT_SC, ucp_Katakana },
275      { 309, PT_SC, ucp_Kayah_Li },
276      { 318, PT_SC, ucp_Kharoshthi },
277      { 329, PT_SC, ucp_Khmer },
278      { 335, PT_GC, ucp_L },
279      { 337, PT_LAMP, 0 },
280      { 340, PT_SC, ucp_Lao },
281      { 344, PT_SC, ucp_Latin },
282      { 350, PT_SC, ucp_Lepcha },
283      { 357, PT_SC, ucp_Limbu },
284      { 363, PT_SC, ucp_Linear_B },
285      { 372, PT_PC, ucp_Ll },
286      { 375, PT_PC, ucp_Lm },
287      { 378, PT_PC, ucp_Lo },
288      { 381, PT_PC, ucp_Lt },
289      { 384, PT_PC, ucp_Lu },
290      { 387, PT_SC, ucp_Lycian },
291      { 394, PT_SC, ucp_Lydian },
292      { 401, PT_GC, ucp_M },
293      { 403, PT_SC, ucp_Malayalam },
294      { 413, PT_PC, ucp_Mc },
295      { 416, PT_PC, ucp_Me },
296      { 419, PT_PC, ucp_Mn },
297      { 422, PT_SC, ucp_Mongolian },
298      { 432, PT_SC, ucp_Myanmar },
299      { 440, PT_GC, ucp_N },
300      { 442, PT_PC, ucp_Nd },
301      { 445, PT_SC, ucp_New_Tai_Lue },
302      { 457, PT_SC, ucp_Nko },
303      { 461, PT_PC, ucp_Nl },
304      { 464, PT_PC, ucp_No },
305      { 467, PT_SC, ucp_Ogham },
306      { 473, PT_SC, ucp_Ol_Chiki },
307      { 482, PT_SC, ucp_Old_Italic },
308      { 493, PT_SC, ucp_Old_Persian },
309      { 505, PT_SC, ucp_Oriya },
310      { 511, PT_SC, ucp_Osmanya },
311      { 519, PT_GC, ucp_P },
312      { 521, PT_PC, ucp_Pc },
313      { 524, PT_PC, ucp_Pd },
314      { 527, PT_PC, ucp_Pe },
315      { 530, PT_PC, ucp_Pf },
316      { 533, PT_SC, ucp_Phags_Pa },
317      { 542, PT_SC, ucp_Phoenician },
318      { 553, PT_PC, ucp_Pi },
319      { 556, PT_PC, ucp_Po },
320      { 559, PT_PC, ucp_Ps },
321      { 562, PT_SC, ucp_Rejang },
322      { 569, PT_SC, ucp_Runic },
323      { 575, PT_GC, ucp_S },
324      { 577, PT_SC, ucp_Saurashtra },
325      { 588, PT_PC, ucp_Sc },
326      { 591, PT_SC, ucp_Shavian },
327      { 599, PT_SC, ucp_Sinhala },
328      { 607, PT_PC, ucp_Sk },
329      { 610, PT_PC, ucp_Sm },
330      { 613, PT_PC, ucp_So },
331      { 616, PT_SC, ucp_Sundanese },
332      { 626, PT_SC, ucp_Syloti_Nagri },
333      { 639, PT_SC, ucp_Syriac },
334      { 646, PT_SC, ucp_Tagalog },
335      { 654, PT_SC, ucp_Tagbanwa },
336      { 663, PT_SC, ucp_Tai_Le },
337      { 670, PT_SC, ucp_Tamil },
338      { 676, PT_SC, ucp_Telugu },
339      { 683, PT_SC, ucp_Thaana },
340      { 690, PT_SC, ucp_Thai },
341      { 695, PT_SC, ucp_Tibetan },
342      { 703, PT_SC, ucp_Tifinagh },
343      { 712, PT_SC, ucp_Ugaritic },
344      { 721, PT_SC, ucp_Vai },
345      { 725, PT_SC, ucp_Yi },
346      { 728, PT_GC, ucp_Z },
347      { 730, PT_PC, ucp_Zl },
348      { 733, PT_PC, ucp_Zp },
349      { 736, PT_PC, ucp_Zs }
350  };  };
351    
352  const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);  const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
353    
354    #endif  /* SUPPORT_UTF8 */
355    
356  /* End of pcre_tables.c */  /* End of pcre_tables.c */

Legend:
Removed from v.85  
changed lines
  Added in v.351

webmaster@exim.org
ViewVC Help
Powered by ViewVC 1.1.12