1 | /* Copyright (c) 2000-2007 MySQL AB |
2 | Copyright (c) 2009-2011, Monty Program Ab |
3 | Use is subject to license terms. |
4 | |
5 | This program is free software; you can redistribute it and/or modify |
6 | it under the terms of the GNU General Public License as published by |
7 | the Free Software Foundation; version 2 of the License. |
8 | |
9 | This program is distributed in the hope that it will be useful, |
10 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
12 | GNU General Public License for more details. |
13 | |
14 | You should have received a copy of the GNU General Public License |
15 | along with this program; if not, write to the Free Software |
16 | Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ |
17 | |
18 | /* File strings/ctype-czech.c for MySQL. |
19 | |
20 | This file implements the Czech sorting for the MySQL database |
21 | server (www.mysql.com). Due to some complicated rules the |
22 | Czech language has for sorting strings, a more complex |
23 | solution was needed than the one-to-one conversion table. To |
24 | note a few, here is an example of a Czech sorting sequence: |
25 | |
26 | co < hlaska < hláska < hlava < chlapec < krtek |
27 | |
28 | It because some of the rules are: double char 'ch' is sorted |
29 | between 'h' and 'i'. Accented character 'á' (a with acute) is |
30 | sorted after 'a' and before 'b', but only if the word is |
31 | otherwise the same. However, because 's' is sorted before 'v' |
32 | in hlava, the accentness of 'á' is overridden. There are many |
33 | more rules. |
34 | |
35 | This file defines functions my_strxfrm and my_strcoll for |
36 | C-like zero terminated strings and my_strnxfrm and my_strnncoll |
37 | for strings where the length comes as an parameter. Also |
38 | defined here you will find function my_like_range that returns |
39 | index range strings for LIKE expression and the |
40 | MY_STRXFRM_MULTIPLY set to value 4 -- this is the ratio the |
41 | strings grows during my_strxfrm. The algorithm has four |
42 | passes, that's why we need four times more space for expanded |
43 | string. |
44 | |
45 | This file also contains the ISO-Latin-2 definitions of |
46 | characters. |
47 | |
48 | Author: (c) 1997--1998 Jan Pazdziora, adelton@fi.muni.cz |
49 | Jan Pazdziora has a shared copyright for this code |
50 | |
51 | The original of this file can also be found at |
52 | http://www.fi.muni.cz/~adelton/l10n/ |
53 | |
54 | Bug reports and suggestions are always welcome. |
55 | */ |
56 | |
57 | /* |
58 | * This comment is parsed by configure to create ctype.c, |
59 | * so don't change it unless you know what you are doing. |
60 | * |
61 | * .configure. strxfrm_multiply_czech=4 |
62 | */ |
63 | |
64 | #define SKIP_TRAILING_SPACES 1 |
65 | |
66 | #define REAL_MYSQL |
67 | |
68 | #ifdef REAL_MYSQL |
69 | |
70 | #include "strings_def.h" |
71 | #include <m_ctype.h> |
72 | |
73 | #else |
74 | |
75 | #include <stdio.h> |
76 | #define uchar unsigned char |
77 | |
78 | #endif |
79 | |
80 | #ifdef HAVE_CHARSET_latin2 |
81 | |
82 | /* |
83 | These are four tables for four passes of the algorithm. Please see |
84 | below for what are the "special values" |
85 | */ |
86 | |
87 | static const uchar *const CZ_SORT_TABLE[] = { |
88 | (uchar*) "\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\043\044\045\046\047\050\051\052\053\054\000\000\000\000\000\000\000\003\004\377\007\010\011\012\013\015\016\017\020\022\023\024\025\026\027\031\033\034\035\036\037\040\041\000\000\000\000\000\000\003\004\377\007\010\011\012\013\015\016\017\020\022\023\024\025\026\027\031\033\034\035\036\037\040\041\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\003\000\021\000\020\032\000\000\032\032\033\042\000\042\042\000\003\000\021\000\020\032\000\000\032\032\033\042\000\042\042\027\003\003\003\003\020\006\006\006\010\010\010\010\015\015\007\007\023\023\024\024\024\024\000\030\034\034\034\034\040\033\000\027\003\003\003\003\020\006\006\006\010\010\010\010\015\015\007\007\023\023\024\024\024\024\000\030\034\034\034\034\040\033\000" , |
89 | (uchar*) "\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\106\107\110\111\112\113\114\115\116\117\000\000\000\000\000\000\000\003\011\377\016\021\026\027\030\032\035\036\037\043\044\047\054\055\056\061\065\070\075\076\077\100\102\000\000\000\000\000\000\003\011\377\016\021\026\027\030\032\035\036\037\043\044\047\054\055\056\061\065\070\075\076\077\100\102\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\010\000\042\000\041\063\000\000\062\064\066\104\000\103\105\000\010\000\042\000\041\063\000\000\062\064\066\104\000\103\105\057\004\005\007\006\040\014\015\013\022\025\024\023\033\034\017\020\046\045\050\051\053\052\000\060\072\071\074\073\101\067\000\057\004\005\007\006\040\014\015\013\022\025\024\023\033\034\017\020\046\045\050\051\053\052\000\060\072\071\074\073\101\067\000" , |
90 | (uchar*) "\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\002\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\212\213\214\215\216\217\220\221\222\223\000\000\000\000\000\000\000\004\020\377\032\040\052\054\056\063\071\073\075\105\107\115\127\131\133\141\151\157\171\173\175\177\203\000\000\000\000\000\000\003\017\377\031\037\051\053\055\062\070\072\074\104\106\114\126\130\132\140\150\156\170\172\174\176\202\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\000\016\000\103\000\101\145\000\000\143\147\153\207\000\205\211\000\015\000\102\000\100\144\000\000\142\146\152\206\000\204\210\135\006\010\014\012\077\026\030\024\042\050\046\044\065\067\034\036\113\111\117\121\125\123\000\137\163\161\167\165\201\155\000\134\005\007\013\011\076\025\027\023\041\047\045\043\064\066\033\035\112\110\116\120\124\122\000\136\162\160\166\164\200\154\000" , |
91 | (uchar*) "\264\265\266\267\270\271\272\273\274\002\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\002\230\232\253\324\252\251\234\240\241\261\260\225\262\224\235\212\213\214\215\216\217\220\221\222\223\231\226\244\257\245\227\250\004\020\377\032\040\052\054\056\063\071\073\075\105\107\115\127\131\133\141\151\157\171\173\175\177\203\242\237\243\254\255\233\003\017\377\031\037\051\053\055\062\070\072\074\104\106\114\126\130\132\140\150\156\170\172\174\176\202\246\236\247\256\325\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\326\016\327\103\330\101\145\331\332\143\147\153\207\333\205\211\334\015\335\102\336\100\144\337\340\142\146\152\206\341\204\210\135\006\010\014\012\077\026\030\024\042\050\046\044\065\067\034\036\113\111\117\121\125\123\263\137\163\161\167\165\201\155\342\134\005\007\013\011\076\025\027\023\041\047\045\043\064\066\033\035\112\110\116\120\124\122\343\136\162\160\166\164\200\154\344" , |
92 | }; |
93 | |
94 | /* |
95 | These define the valuse for the double chars that need to be |
96 | sorted as they were single characters -- in Czech these are |
97 | 'ch', 'Ch' and 'CH'. |
98 | */ |
99 | |
100 | struct wordvalue |
101 | { |
102 | const char * word; |
103 | const uchar *outvalue; |
104 | }; |
105 | static const struct wordvalue doubles[] = { |
106 | { "ch" , (const uchar*) "\014\031\057\057" }, |
107 | { "Ch" , (const uchar*) "\014\031\060\060" }, |
108 | { "CH" , (const uchar*) "\014\031\061\061" }, |
109 | { "c" , (const uchar*) "\005\012\021\021" }, |
110 | { "C" , (const uchar*) "\005\012\022\022" }, |
111 | }; |
112 | |
113 | /* |
114 | Unformal description of the algorithm: |
115 | |
116 | We walk the string left to right. |
117 | |
118 | The end of the string is either passed as parameter, or is |
119 | *p == 0. This is hidden in the IS_END macro. |
120 | |
121 | In the first two passes, we compare word by word. So we make |
122 | first and second pass on the first word, first and second pass |
123 | on the second word, etc. If we come to the end of the string |
124 | during the first pass, we need to jump to the last word of the |
125 | second pass. |
126 | |
127 | End of pass is marked with value 1 on the output. |
128 | |
129 | For each character, we read it's value from the table. |
130 | |
131 | If the value is ignore (0), we go straight to the next character. |
132 | |
133 | If the value is space/end of word (2) and we are in the first |
134 | or second pass, we skip all characters having value 0 -- 2 and |
135 | switch the passwd. |
136 | |
137 | If it's the compose character (255), we check if the double |
138 | exists behind it, find its value. |
139 | |
140 | We append 0 to the end. |
141 | --- |
142 | Neformální popis algoritmu: |
143 | |
144 | Procházíme řetězec zleva doprava. |
145 | |
146 | Konec řetězce je předán buď jako parametr, nebo je to *p == 0. |
147 | Toto je ošetřeno makrem IS_END. |
148 | |
149 | Pokud jsme došli na konec řetězce při průchodu 0, nejdeme na |
150 | začátek, ale na uloženou pozici, protože první a druhý průchod |
151 | běží současně. |
152 | |
153 | Konec vstupu (průchodu) označíme na výstupu hodnotou 1. |
154 | |
155 | Pro každý znak řetězce načteme hodnotu z třídící tabulky. |
156 | |
157 | Jde-li o hodnotu ignorovat (0), skočíme ihned na další znak.. |
158 | |
159 | Jde-li o hodnotu konec slova (2) a je to průchod 0 nebo 1, |
160 | přeskočíme všechny další 0 -- 2 a prohodíme průchody. |
161 | |
162 | Jde-li o kompozitní znak (255), otestujeme, zda následuje |
163 | správný do dvojice, dohledáme správnou hodnotu. |
164 | |
165 | Na konci připojíme znak 0 |
166 | */ |
167 | |
168 | #define ADD_TO_RESULT(dest, len, totlen, value) \ |
169 | { if ((totlen) < (len)) { dest[totlen++]= value; } } |
170 | #define IS_END(p, src, len) (((char *)p - (char *)src) >= (len)) |
171 | |
172 | #define NEXT_CMP_VALUE(src, p, store, pass, value, len) \ |
173 | while (1) \ |
174 | { \ |
175 | if (IS_END(p, src, len)) \ |
176 | { \ |
177 | /* when we are at the end of string */ \ |
178 | /* return either 0 for end of string */ \ |
179 | /* or 1 for end of pass */ \ |
180 | value= 0; \ |
181 | if (pass != 3) \ |
182 | { \ |
183 | p= (pass++ == 0) ? store : src; \ |
184 | value = 1; \ |
185 | } \ |
186 | break; \ |
187 | } \ |
188 | /* not at end of string */ \ |
189 | value = CZ_SORT_TABLE[pass][*p]; \ |
190 | if (value == 0) \ |
191 | { p++; continue; } /* ignore value */ \ |
192 | if (value == 2) /* space */ \ |
193 | { \ |
194 | const uchar *tmp; \ |
195 | const uchar *runner = ++p; \ |
196 | while (!(IS_END(runner, src, len)) && (CZ_SORT_TABLE[pass][*runner] == 2)) \ |
197 | runner++; /* skip all spaces */ \ |
198 | if (IS_END(runner, src, len) && SKIP_TRAILING_SPACES) \ |
199 | p = runner; \ |
200 | if ((pass <= 2) && !(IS_END(runner, src, len))) \ |
201 | p = runner; \ |
202 | if (IS_END(p, src, len)) \ |
203 | continue; \ |
204 | /* we switch passes */ \ |
205 | if (pass > 1) \ |
206 | break; \ |
207 | tmp = p; \ |
208 | pass= 1-pass; \ |
209 | p = store; store = tmp; \ |
210 | break; \ |
211 | } \ |
212 | if (value == 255) \ |
213 | { \ |
214 | int i; \ |
215 | for (i = 0; i < (int) sizeof(doubles); i++) \ |
216 | { \ |
217 | const char * pattern = doubles[i].word; \ |
218 | const char * q = (const char *) p; \ |
219 | int j = 0; \ |
220 | while (pattern[j]) \ |
221 | { \ |
222 | if (IS_END(q, src, len) || (*q != pattern[j])) \ |
223 | break; \ |
224 | j++; q++; \ |
225 | } \ |
226 | if (!(pattern[j])) \ |
227 | { \ |
228 | value = (int)(doubles[i].outvalue[pass]); \ |
229 | p= (const uchar *) q - 1; \ |
230 | break; \ |
231 | } \ |
232 | } \ |
233 | } \ |
234 | p++; \ |
235 | break; \ |
236 | } |
237 | |
238 | /* |
239 | Function strnncoll, actually strcoll, with Czech sorting, which expect |
240 | the length of the strings being specified |
241 | */ |
242 | |
243 | static int my_strnncoll_czech(CHARSET_INFO *cs __attribute__((unused)), |
244 | const uchar *s1, size_t len1, |
245 | const uchar *s2, size_t len2, |
246 | my_bool s2_is_prefix) |
247 | { |
248 | int v1, v2; |
249 | const uchar *p1, * p2, * store1, * store2; |
250 | int pass1 = 0, pass2 = 0; |
251 | |
252 | if (s2_is_prefix && len1 > len2) |
253 | len1=len2; |
254 | |
255 | p1 = s1; p2 = s2; |
256 | store1 = s1; store2 = s2; |
257 | |
258 | do |
259 | { |
260 | int diff; |
261 | NEXT_CMP_VALUE(s1, p1, store1, pass1, v1, (int)len1); |
262 | NEXT_CMP_VALUE(s2, p2, store2, pass2, v2, (int)len2); |
263 | if ((diff = v1 - v2)) |
264 | return diff; |
265 | } |
266 | while (v1); |
267 | return 0; |
268 | } |
269 | |
270 | |
271 | |
272 | /* |
273 | TODO: Fix this one to compare strings as they are done in ctype-simple1 |
274 | */ |
275 | |
276 | static |
277 | int my_strnncollsp_czech(CHARSET_INFO * cs, |
278 | const uchar *s, size_t slen, |
279 | const uchar *t, size_t tlen) |
280 | { |
281 | for ( ; slen && s[slen-1] == ' ' ; slen--); |
282 | for ( ; tlen && t[tlen-1] == ' ' ; tlen--); |
283 | return my_strnncoll_czech(cs,s,slen,t,tlen,0); |
284 | } |
285 | |
286 | |
287 | /* |
288 | Returns the number of bytes required for strnxfrm(). |
289 | */ |
290 | static size_t |
291 | my_strnxfrmlen_czech(CHARSET_INFO *cs |
292 | __attribute__((unused)), size_t len) |
293 | { |
294 | return len * 4 + 4; |
295 | } |
296 | |
297 | |
298 | /* |
299 | Function strnxfrm, actually strxfrm, with Czech sorting, which expect |
300 | the length of the strings being specified |
301 | */ |
302 | |
303 | static size_t |
304 | my_strnxfrm_czech(CHARSET_INFO *cs __attribute__((unused)), |
305 | uchar *dest, size_t len, |
306 | uint nweights_arg __attribute__((unused)), |
307 | const uchar *src, size_t srclen, uint flags) |
308 | { |
309 | int value; |
310 | const uchar *p, * store; |
311 | int pass = 0; |
312 | size_t totlen = 0; |
313 | p = src; store = src; |
314 | |
315 | if (!(flags & 0x0F)) /* All levels by default */ |
316 | flags|= 0x0F; |
317 | |
318 | do |
319 | { |
320 | int add= (1 << pass) & flags; /* If this level is needed */ |
321 | NEXT_CMP_VALUE(src, p, store, pass, value, (int)srclen); |
322 | if (add) |
323 | ADD_TO_RESULT(dest, len, totlen, value); |
324 | } |
325 | while (value); |
326 | if ((flags & MY_STRXFRM_PAD_TO_MAXLEN) && len > totlen) |
327 | { |
328 | memset(dest + totlen, ' ', len - totlen); |
329 | totlen= len; |
330 | } |
331 | return totlen; |
332 | } |
333 | |
334 | #undef IS_END |
335 | |
336 | |
337 | /* |
338 | Neformální popis algoritmu: |
339 | |
340 | procházíme řetězec zleva doprava |
341 | konec řetězce poznáme podle *p == 0 |
342 | pokud jsme došli na konec řetězce při průchodu 0, nejdeme na |
343 | začátek, ale na uloženou pozici, protože první a druhý |
344 | průchod běží současně |
345 | konec vstupu (průchodu) označíme na výstupu hodnotou 1 |
346 | |
347 | načteme hodnotu z třídící tabulky |
348 | jde-li o hodnotu ignorovat (0), skočíme na další průchod |
349 | jde-li o hodnotu konec slova (2) a je to průchod 0 nebo 1, |
350 | přeskočíme všechny další 0 -- 2 a prohodíme |
351 | průchody |
352 | jde-li o kompozitní znak (255), otestujeme, zda následuje |
353 | správný do dvojice, dohledáme správnou hodnotu |
354 | |
355 | na konci připojíme znak 0 |
356 | */ |
357 | |
358 | |
359 | /* |
360 | ** Calculate min_str and max_str that ranges a LIKE string. |
361 | ** Arguments: |
362 | ** ptr Pointer to LIKE string. |
363 | ** ptr_length Length of LIKE string. |
364 | ** escape Escape character in LIKE. (Normally '\'). |
365 | ** All escape characters should be removed from min_str and max_str |
366 | ** res_length Length of min_str and max_str. |
367 | ** min_str Smallest case sensitive string that ranges LIKE. |
368 | ** Should be space padded to res_length. |
369 | ** max_str Largest case sensitive string that ranges LIKE. |
370 | ** Normally padded with the biggest character sort value. |
371 | ** |
372 | ** The function should return 0 if ok and 1 if the LIKE string can't be |
373 | ** optimized ! |
374 | */ |
375 | |
376 | #ifdef REAL_MYSQL |
377 | |
378 | #define min_sort_char ' ' |
379 | #define max_sort_char '9' |
380 | |
381 | #define EXAMPLE |
382 | |
383 | static my_bool my_like_range_czech(CHARSET_INFO *cs __attribute__((unused)), |
384 | const char *ptr,size_t ptr_length, |
385 | pbool escape, pbool w_one, pbool w_many, |
386 | size_t res_length, char *min_str, |
387 | char *max_str, |
388 | size_t *min_length,size_t *max_length) |
389 | { |
390 | #ifdef EXAMPLE |
391 | uchar value; |
392 | const char *end=ptr+ptr_length; |
393 | char *min_org=min_str; |
394 | char *min_end=min_str+res_length; |
395 | |
396 | for (; ptr != end && min_str != min_end ; ptr++) |
397 | { |
398 | if (*ptr == w_one) /* '_' in SQL */ |
399 | { break; } |
400 | if (*ptr == w_many) /* '%' in SQL */ |
401 | { break; } |
402 | |
403 | if (*ptr == escape && ptr+1 != end) |
404 | { ptr++; } /* Skip escape */ |
405 | |
406 | value = CZ_SORT_TABLE[0][(int) (uchar) *ptr]; |
407 | |
408 | if (value == 0) /* Ignore in the first pass */ |
409 | { continue; } |
410 | if (value <= 2) /* End of pass or end of string */ |
411 | { break; } |
412 | if (value == 255) /* Double char too compicated */ |
413 | { break; } |
414 | |
415 | *min_str++= *max_str++ = *ptr; |
416 | } |
417 | |
418 | if (cs->state & MY_CS_BINSORT) |
419 | *min_length= (size_t) (min_str - min_org); |
420 | else |
421 | { |
422 | /* 'a\0\0... is the smallest possible string */ |
423 | *min_length= res_length; |
424 | } |
425 | /* a\ff\ff... is the biggest possible string */ |
426 | *max_length= res_length; |
427 | |
428 | while (min_str != min_end) |
429 | { |
430 | *min_str++ = min_sort_char; /* Because of key compression */ |
431 | *max_str++ = max_sort_char; |
432 | } |
433 | return 0; |
434 | #else |
435 | return 1; |
436 | #endif |
437 | } |
438 | |
439 | #endif |
440 | |
441 | #ifdef REAL_MYSQL |
442 | /* This is a latin2 file */ |
443 | |
444 | /* |
445 | * File generated by cset |
446 | * (C) Abandoned 1997 Zarko Mocnik <zarko.mocnik@dem.si> |
447 | * |
448 | * definition table reworked by Jaromir Dolecek <dolecek@ics.muni.cz> |
449 | */ |
450 | #include "strings_def.h" |
451 | |
452 | static const uchar ctype_czech[257] = { |
453 | 0, |
454 | 32, 32, 32, 32, 32, 32, 32, 32, 32, 40, 40, 40, 40, 40, 32, 32, |
455 | 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, |
456 | 72, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, |
457 | 132,132,132,132,132,132,132,132,132,132, 16, 16, 16, 16, 16, 16, |
458 | 16,129,129,129,129,129,129, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
459 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 16, 16, 16, 16, 16, |
460 | 16,130,130,130,130,130,130, 2, 2, 2, 2, 2, 2, 2, 2, 2, |
461 | 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 16, 16, 16, 16, 32, |
462 | 32, 32, 32, 32, 32, 32, 32, 32, 40, 40, 40, 40, 40, 32, 32, 32, |
463 | 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 72, |
464 | 1, 16, 1, 16, 1, 1, 16, 0, 0, 1, 1, 1, 1, 16, 1, 1, |
465 | 16, 2, 16, 2, 16, 2, 2, 16, 16, 2, 2, 2, 2, 16, 2, 2, |
466 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, |
467 | 16, 1, 1, 1, 1, 1, 1, 16, 1, 1, 1, 1, 1, 1, 1, 16, |
468 | 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, |
469 | 2, 2, 2, 2, 2, 2, 2, 16, 2, 2, 2, 2, 2, 2, 2, 16, |
470 | }; |
471 | |
472 | static const uchar to_lower_czech[] = { |
473 | 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, |
474 | 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, |
475 | 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, |
476 | 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, |
477 | 64, 97, 98, 99,100,101,102,103,104,105,106,107,108,109,110,111, |
478 | 112,113,114,115,116,117,118,119,120,121,122, 91, 92, 93, 94, 95, |
479 | 96, 97, 98, 99,100,101,102,103,104,105,106,107,108,109,110,111, |
480 | 112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127, |
481 | 128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143, |
482 | 144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159, |
483 | 177,161,179,163,181,182,166,167,168,185,186,187,188,173,190,191, |
484 | 176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191, |
485 | 224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239, |
486 | 208,241,242,243,244,245,246,215,248,249,250,251,252,253,254,223, |
487 | 224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239, |
488 | 240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255, |
489 | }; |
490 | |
491 | static const uchar to_upper_czech[] = { |
492 | 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, |
493 | 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, |
494 | 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, |
495 | 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, |
496 | 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, |
497 | 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, |
498 | 96, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, |
499 | 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90,123,124,125,126,127, |
500 | 128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143, |
501 | 144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159, |
502 | 160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175, |
503 | 176,160,178,162,180,164,165,183,184,169,170,171,172,189,174,175, |
504 | 192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207, |
505 | 208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223, |
506 | 192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207, |
507 | 240,209,210,211,212,213,214,247,216,217,218,219,220,221,222,255, |
508 | }; |
509 | |
510 | static const uchar sort_order_czech[] = { |
511 | 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, |
512 | 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, |
513 | 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, |
514 | 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, |
515 | 64, 65, 71, 72, 76, 78, 83, 84, 85, 86, 90, 91, 92, 96, 97,100, |
516 | 105,106,107,110,114,117,122,123,124,125,127,131,132,133,134,135, |
517 | 136, 65, 71, 72, 76, 78, 83, 84, 85, 86, 90, 91, 92, 96, 97,100, |
518 | 105,106,107,110,114,117,122,123,124,125,127,137,138,139,140, 0, |
519 | 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, |
520 | 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,255, |
521 | 66,255, 93,255, 94,111,255,255,255,112,113,115,128,255,129,130, |
522 | 255, 66,255, 93,255, 94,111,255,255,112,113,115,128,255,129,130, |
523 | 108, 67, 68, 69, 70, 95, 73, 75, 74, 79, 81, 82, 80, 89, 87, 77, |
524 | 255, 98, 99,101,102,103,104,255,109,119,118,120,121,126,116,255, |
525 | 108, 67, 68, 69, 70, 95, 73, 75, 74, 79, 81, 82, 80, 89, 88, 77, |
526 | 255, 98, 99,101,102,103,104,255,109,119,118,120,121,126,116,255, |
527 | }; |
528 | |
529 | static const uint16 tab_8859_2_uni[256]={ |
530 | 0,0x0001,0x0002,0x0003,0x0004,0x0005,0x0006,0x0007, |
531 | 0x0008,0x0009,0x000A,0x000B,0x000C,0x000D,0x000E,0x000F, |
532 | 0x0010,0x0011,0x0012,0x0013,0x0014,0x0015,0x0016,0x0017, |
533 | 0x0018,0x0019,0x001A,0x001B,0x001C,0x001D,0x001E,0x001F, |
534 | 0x0020,0x0021,0x0022,0x0023,0x0024,0x0025,0x0026,0x0027, |
535 | 0x0028,0x0029,0x002A,0x002B,0x002C,0x002D,0x002E,0x002F, |
536 | 0x0030,0x0031,0x0032,0x0033,0x0034,0x0035,0x0036,0x0037, |
537 | 0x0038,0x0039,0x003A,0x003B,0x003C,0x003D,0x003E,0x003F, |
538 | 0x0040,0x0041,0x0042,0x0043,0x0044,0x0045,0x0046,0x0047, |
539 | 0x0048,0x0049,0x004A,0x004B,0x004C,0x004D,0x004E,0x004F, |
540 | 0x0050,0x0051,0x0052,0x0053,0x0054,0x0055,0x0056,0x0057, |
541 | 0x0058,0x0059,0x005A,0x005B,0x005C,0x005D,0x005E,0x005F, |
542 | 0x0060,0x0061,0x0062,0x0063,0x0064,0x0065,0x0066,0x0067, |
543 | 0x0068,0x0069,0x006A,0x006B,0x006C,0x006D,0x006E,0x006F, |
544 | 0x0070,0x0071,0x0072,0x0073,0x0074,0x0075,0x0076,0x0077, |
545 | 0x0078,0x0079,0x007A,0x007B,0x007C,0x007D,0x007E, 0, |
546 | 0, 0, 0, 0, 0, 0, 0, 0, |
547 | 0, 0, 0, 0, 0, 0, 0, 0, |
548 | 0, 0, 0, 0, 0, 0, 0, 0, |
549 | 0, 0, 0, 0, 0, 0, 0, 0, |
550 | 0x00A0,0x0104,0x02D8,0x0141,0x00A4,0x013D,0x015A,0x00A7, |
551 | 0x00A8,0x0160,0x015E,0x0164,0x0179,0x00AD,0x017D,0x017B, |
552 | 0x00B0,0x0105,0x02DB,0x0142,0x00B4,0x013E,0x015B,0x02C7, |
553 | 0x00B8,0x0161,0x015F,0x0165,0x017A,0x02DD,0x017E,0x017C, |
554 | 0x0154,0x00C1,0x00C2,0x0102,0x00C4,0x0139,0x0106,0x00C7, |
555 | 0x010C,0x00C9,0x0118,0x00CB,0x011A,0x00CD,0x00CE,0x010E, |
556 | 0x0110,0x0143,0x0147,0x00D3,0x00D4,0x0150,0x00D6,0x00D7, |
557 | 0x0158,0x016E,0x00DA,0x0170,0x00DC,0x00DD,0x0162,0x00DF, |
558 | 0x0155,0x00E1,0x00E2,0x0103,0x00E4,0x013A,0x0107,0x00E7, |
559 | 0x010D,0x00E9,0x0119,0x00EB,0x011B,0x00ED,0x00EE,0x010F, |
560 | 0x0111,0x0144,0x0148,0x00F3,0x00F4,0x0151,0x00F6,0x00F7, |
561 | 0x0159,0x016F,0x00FA,0x0171,0x00FC,0x00FD,0x0163,0x02D9 |
562 | }; |
563 | |
564 | |
565 | /* 0000-00FD , 254 chars */ |
566 | static const uchar tab_uni_8859_2_plane00[]={ |
567 | 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F, |
568 | 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0x1A,0x1B,0x1C,0x1D,0x1E,0x1F, |
569 | 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,0x28,0x29,0x2A,0x2B,0x2C,0x2D,0x2E,0x2F, |
570 | 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F, |
571 | 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0x4A,0x4B,0x4C,0x4D,0x4E,0x4F, |
572 | 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5A,0x5B,0x5C,0x5D,0x5E,0x5F, |
573 | 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F, |
574 | 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7A,0x7B,0x7C,0x7D,0x7E,0x00, |
575 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, |
576 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, |
577 | 0xA0,0x00,0x00,0x00,0xA4,0x00,0x00,0xA7,0xA8,0x00,0x00,0x00,0x00,0xAD,0x00,0x00, |
578 | 0xB0,0x00,0x00,0x00,0xB4,0x00,0x00,0x00,0xB8,0x00,0x00,0x00,0x00,0x00,0x00,0x00, |
579 | 0x00,0xC1,0xC2,0x00,0xC4,0x00,0x00,0xC7,0x00,0xC9,0x00,0xCB,0x00,0xCD,0xCE,0x00, |
580 | 0x00,0x00,0x00,0xD3,0xD4,0x00,0xD6,0xD7,0x00,0x00,0xDA,0x00,0xDC,0xDD,0x00,0xDF, |
581 | 0x00,0xE1,0xE2,0x00,0xE4,0x00,0x00,0xE7,0x00,0xE9,0x00,0xEB,0x00,0xED,0xEE,0x00, |
582 | 0x00,0x00,0x00,0xF3,0xF4,0x00,0xF6,0xF7,0x00,0x00,0xFA,0x00,0xFC,0xFD}; |
583 | |
584 | /* 0102-017E , 125 chars */ |
585 | static const uchar tab_uni_8859_2_plane01[]={ |
586 | 0xC3,0xE3,0xA1,0xB1,0xC6,0xE6,0x00,0x00,0x00,0x00,0xC8,0xE8,0xCF,0xEF,0xD0,0xF0, |
587 | 0x00,0x00,0x00,0x00,0x00,0x00,0xCA,0xEA,0xCC,0xEC,0x00,0x00,0x00,0x00,0x00,0x00, |
588 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, |
589 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xC5,0xE5,0x00,0x00,0xA5,0xB5,0x00,0x00,0xA3, |
590 | 0xB3,0xD1,0xF1,0x00,0x00,0xD2,0xF2,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xD5,0xF5, |
591 | 0x00,0x00,0xC0,0xE0,0x00,0x00,0xD8,0xF8,0xA6,0xB6,0x00,0x00,0xAA,0xBA,0xA9,0xB9, |
592 | 0xDE,0xFE,0xAB,0xBB,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xD9,0xF9,0xDB,0xFB, |
593 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xAC,0xBC,0xAF,0xBF,0xAE,0xBE}; |
594 | |
595 | /* 02C7-02DD , 23 chars */ |
596 | static const uchar tab_uni_8859_2_plane02[]={ |
597 | 0xB7,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, |
598 | 0x00,0xA2,0xFF,0x00,0xB2,0x00,0xBD}; |
599 | |
600 | static MY_UNI_IDX idx_uni_8859_2[]={ |
601 | {0x0000,0x00FD,tab_uni_8859_2_plane00}, |
602 | {0x0102,0x017E,tab_uni_8859_2_plane01}, |
603 | {0x02C7,0x02DD,tab_uni_8859_2_plane02}, |
604 | {0,0,NULL} |
605 | }; |
606 | |
607 | |
608 | static MY_COLLATION_HANDLER my_collation_latin2_czech_ci_handler = |
609 | { |
610 | NULL, /* init */ |
611 | my_strnncoll_czech, |
612 | my_strnncollsp_czech, |
613 | my_strnxfrm_czech, |
614 | my_strnxfrmlen_czech, |
615 | my_like_range_czech, |
616 | my_wildcmp_bin, |
617 | my_strcasecmp_8bit, |
618 | my_instr_simple, |
619 | my_hash_sort_simple, |
620 | my_propagate_simple |
621 | }; |
622 | |
623 | struct charset_info_st my_charset_latin2_czech_ci = |
624 | { |
625 | 2,0,0, /* number */ |
626 | MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_CSSORT| |
627 | MY_CS_STRNXFRM_BAD_NWEIGHTS|MY_CS_NON1TO1, /* state */ |
628 | "latin2" , /* cs name */ |
629 | "latin2_czech_cs" , /* name */ |
630 | "" , /* comment */ |
631 | NULL, /* tailoring */ |
632 | ctype_czech, |
633 | to_lower_czech, |
634 | to_upper_czech, |
635 | sort_order_czech, |
636 | NULL, /* uca */ |
637 | tab_8859_2_uni, /* tab_to_uni */ |
638 | idx_uni_8859_2, /* tab_from_uni */ |
639 | &my_unicase_default,/* caseinfo */ |
640 | NULL, /* state_map */ |
641 | NULL, /* ident_map */ |
642 | 4, /* strxfrm_multiply */ |
643 | 1, /* caseup_multiply */ |
644 | 1, /* casedn_multiply */ |
645 | 1, /* mbminlen */ |
646 | 1, /* mbmaxlen */ |
647 | 0, /* min_sort_char */ |
648 | 0, /* max_sort_char */ |
649 | ' ', /* pad char */ |
650 | 0, /* escape_with_backslash_is_dangerous */ |
651 | 4, /* levels_for_order */ |
652 | &my_charset_8bit_handler, |
653 | &my_collation_latin2_czech_ci_handler |
654 | }; |
655 | |
656 | |
657 | #endif |
658 | |
659 | #endif |
660 | |