CharsetMapping.java
54.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
/*
Copyright (c) 2002, 2016, Oracle and/or its affiliates. All rights reserved.
The MySQL Connector/J is licensed under the terms of the GPLv2
<http://www.gnu.org/licenses/old-licenses/gpl-2.0.html>, like most MySQL Connectors.
There are special exceptions to the terms and conditions of the GPLv2 as it is applied to
this software, see the FOSS License Exception
<http://www.mysql.com/about/legal/licensing/foss-exception.html>.
This program is free software; you can redistribute it and/or modify it under the terms
of the GNU General Public License as published by the Free Software Foundation; version 2
of the License.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU General Public License for more details.
You should have received a copy of the GNU General Public License along with this
program; if not, write to the Free Software Foundation, Inc., 51 Franklin St, Fifth
Floor, Boston, MA 02110-1301 USA
*/
package com.mysql.jdbc;
import java.nio.charset.Charset;
import java.sql.SQLException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.Set;
import java.util.TreeMap;
/**
* Mapping between MySQL charset names and Java charset names. I've investigated placing these in a .properties file, but unfortunately under most appservers
* this complicates configuration because the security policy needs to be changed by the user to allow the driver to read them :(
*/
public class CharsetMapping {
public static final int MAP_SIZE = 255; // Size of static maps
public static final String[] COLLATION_INDEX_TO_COLLATION_NAME;
public static final MysqlCharset[] COLLATION_INDEX_TO_CHARSET;
public static final Map<String, MysqlCharset> CHARSET_NAME_TO_CHARSET;
public static final Map<String, Integer> CHARSET_NAME_TO_COLLATION_INDEX;
private static final Map<String, List<MysqlCharset>> JAVA_ENCODING_UC_TO_MYSQL_CHARSET;
private static final Set<String> MULTIBYTE_ENCODINGS;
private static final Map<String, String> ERROR_MESSAGE_FILE_TO_MYSQL_CHARSET;
private static final Set<String> ESCAPE_ENCODINGS;
public static final Set<Integer> UTF8MB4_INDEXES;
private static final String MYSQL_CHARSET_NAME_armscii8 = "armscii8";
private static final String MYSQL_CHARSET_NAME_ascii = "ascii";
private static final String MYSQL_CHARSET_NAME_big5 = "big5";
private static final String MYSQL_CHARSET_NAME_binary = "binary";
private static final String MYSQL_CHARSET_NAME_cp1250 = "cp1250";
private static final String MYSQL_CHARSET_NAME_cp1251 = "cp1251";
private static final String MYSQL_CHARSET_NAME_cp1256 = "cp1256";
private static final String MYSQL_CHARSET_NAME_cp1257 = "cp1257";
private static final String MYSQL_CHARSET_NAME_cp850 = "cp850";
private static final String MYSQL_CHARSET_NAME_cp852 = "cp852";
private static final String MYSQL_CHARSET_NAME_cp866 = "cp866";
private static final String MYSQL_CHARSET_NAME_cp932 = "cp932";
private static final String MYSQL_CHARSET_NAME_dec8 = "dec8";
private static final String MYSQL_CHARSET_NAME_eucjpms = "eucjpms";
private static final String MYSQL_CHARSET_NAME_euckr = "euckr";
private static final String MYSQL_CHARSET_NAME_gb18030 = "gb18030";
private static final String MYSQL_CHARSET_NAME_gb2312 = "gb2312";
private static final String MYSQL_CHARSET_NAME_gbk = "gbk";
private static final String MYSQL_CHARSET_NAME_geostd8 = "geostd8";
private static final String MYSQL_CHARSET_NAME_greek = "greek";
private static final String MYSQL_CHARSET_NAME_hebrew = "hebrew";
private static final String MYSQL_CHARSET_NAME_hp8 = "hp8";
private static final String MYSQL_CHARSET_NAME_keybcs2 = "keybcs2";
private static final String MYSQL_CHARSET_NAME_koi8r = "koi8r";
private static final String MYSQL_CHARSET_NAME_koi8u = "koi8u";
private static final String MYSQL_CHARSET_NAME_latin1 = "latin1";
private static final String MYSQL_CHARSET_NAME_latin2 = "latin2";
private static final String MYSQL_CHARSET_NAME_latin5 = "latin5";
private static final String MYSQL_CHARSET_NAME_latin7 = "latin7";
private static final String MYSQL_CHARSET_NAME_macce = "macce";
private static final String MYSQL_CHARSET_NAME_macroman = "macroman";
private static final String MYSQL_CHARSET_NAME_sjis = "sjis";
private static final String MYSQL_CHARSET_NAME_swe7 = "swe7";
private static final String MYSQL_CHARSET_NAME_tis620 = "tis620";
private static final String MYSQL_CHARSET_NAME_ucs2 = "ucs2";
private static final String MYSQL_CHARSET_NAME_ujis = "ujis";
private static final String MYSQL_CHARSET_NAME_utf16 = "utf16";
private static final String MYSQL_CHARSET_NAME_utf16le = "utf16le";
private static final String MYSQL_CHARSET_NAME_utf32 = "utf32";
private static final String MYSQL_CHARSET_NAME_utf8 = "utf8";
private static final String MYSQL_CHARSET_NAME_utf8mb4 = "utf8mb4";
private static final String MYSQL_4_0_CHARSET_NAME_cp1251cias = "cp1251cias";
private static final String MYSQL_4_0_CHARSET_NAME_cp1251csas = "cp1251csas";
private static final String MYSQL_4_0_CHARSET_NAME_croat = "croat"; // 4.1 => 27 latin2 latin2_croatian_ci
private static final String MYSQL_4_0_CHARSET_NAME_czech = "czech"; // 4.1 => 2 latin2 latin2_czech_ci
private static final String MYSQL_4_0_CHARSET_NAME_danish = "danish"; // 4.1 => 15 latin1 latin1_danish_ci
private static final String MYSQL_4_0_CHARSET_NAME_dos = "dos"; // 4.1 => 4 cp850 cp850_general_ci
private static final String MYSQL_4_0_CHARSET_NAME_estonia = "estonia"; // 4.1 => 20 latin7 latin7_estonian_ci
private static final String MYSQL_4_0_CHARSET_NAME_euc_kr = "euc_kr"; // 4.1 => 19 euckr euckr_korean_ci
private static final String MYSQL_4_0_CHARSET_NAME_german1 = "german1"; // 4.1 => 5 latin1 latin1_german1_ci
private static final String MYSQL_4_0_CHARSET_NAME_hungarian = "hungarian"; // 4.1 => 21 latin2 latin2_hungarian_ci
private static final String MYSQL_4_0_CHARSET_NAME_koi8_ru = "koi8_ru"; // 4.1 => 7 koi8r koi8r_general_ci
private static final String MYSQL_4_0_CHARSET_NAME_koi8_ukr = "koi8_ukr"; // 4.1 => 22 koi8u koi8u_ukrainian_ci
private static final String MYSQL_4_0_CHARSET_NAME_latin1_de = "latin1_de"; // 4.1 => 31 latin1 latin1_german2_ci
private static final String MYSQL_4_0_CHARSET_NAME_latvian = "latvian";
private static final String MYSQL_4_0_CHARSET_NAME_latvian1 = "latvian1";
private static final String MYSQL_4_0_CHARSET_NAME_usa7 = "usa7"; // 4.1 => 11 ascii ascii_general_ci
private static final String MYSQL_4_0_CHARSET_NAME_win1250 = "win1250"; // 4.1 => 26 cp1250 cp1250_general_ci
private static final String MYSQL_4_0_CHARSET_NAME_win1251 = "win1251"; // 4.1 => 17 (removed)
private static final String MYSQL_4_0_CHARSET_NAME_win1251ukr = "win1251ukr"; // 4.1 => 23 cp1251 cp1251_ukrainian_ci
private static final String NOT_USED = MYSQL_CHARSET_NAME_latin1; // punting for not-used character sets
public static final int MYSQL_COLLATION_INDEX_utf8 = 33;
public static final int MYSQL_COLLATION_INDEX_binary = 63;
private static int numberOfEncodingsConfigured = 0;
static {
// complete list of mysql character sets and their corresponding java encoding names
MysqlCharset[] charset = new MysqlCharset[] { new MysqlCharset(MYSQL_4_0_CHARSET_NAME_usa7, 1, 0, new String[] { "US-ASCII" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_ascii, 1, 0, new String[] { "US-ASCII", "ASCII" }),
new MysqlCharset(MYSQL_CHARSET_NAME_big5, 2, 0, new String[] { "Big5" }),
new MysqlCharset(MYSQL_CHARSET_NAME_gbk, 2, 0, new String[] { "GBK" }),
new MysqlCharset(MYSQL_CHARSET_NAME_sjis, 2, 0, new String[] { "SHIFT_JIS", "Cp943", "WINDOWS-31J" }), // SJIS is alias for SHIFT_JIS, Cp943 is rather a cp932 but we map it to sjis for years
new MysqlCharset(MYSQL_CHARSET_NAME_cp932, 2, 1, new String[] { "WINDOWS-31J" }), // MS932 is alias for WINDOWS-31J
new MysqlCharset(MYSQL_CHARSET_NAME_gb2312, 2, 0, new String[] { "GB2312" }),
new MysqlCharset(MYSQL_CHARSET_NAME_ujis, 3, 0, new String[] { "EUC_JP" }),
new MysqlCharset(MYSQL_CHARSET_NAME_eucjpms, 3, 0, new String[] { "EUC_JP_Solaris" }, 5, 0, 3), // "EUC_JP_Solaris = >5.0.3 eucjpms,"
new MysqlCharset(MYSQL_CHARSET_NAME_gb18030, 4, 0, new String[] { "GB18030" }, 5, 7, 4),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_euc_kr, 2, 0, new String[] { "EUC_KR" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_euckr, 2, 0, new String[] { "EUC-KR" }),
new MysqlCharset(MYSQL_CHARSET_NAME_latin1, 1, 1, new String[] { "Cp1252", "ISO8859_1" }),
new MysqlCharset(MYSQL_CHARSET_NAME_swe7, 1, 0, new String[] { "Cp1252" }), // new mapping, Cp1252 ?
new MysqlCharset(MYSQL_CHARSET_NAME_hp8, 1, 0, new String[] { "Cp1252" }), // new mapping, Cp1252 ?
new MysqlCharset(MYSQL_CHARSET_NAME_dec8, 1, 0, new String[] { "Cp1252" }), // new mapping, Cp1252 ?
new MysqlCharset(MYSQL_CHARSET_NAME_armscii8, 1, 0, new String[] { "Cp1252" }), // new mapping, Cp1252 ?
new MysqlCharset(MYSQL_CHARSET_NAME_geostd8, 1, 0, new String[] { "Cp1252" }), // new mapping, Cp1252 ?
new MysqlCharset(MYSQL_CHARSET_NAME_latin2, 1, 0, new String[] { "ISO8859_2" }), // latin2 is an alias
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_czech, 1, 0, new String[] { "ISO8859_2" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_hungarian, 1, 0, new String[] { "ISO8859_2" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_croat, 1, 0, new String[] { "ISO8859_2" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_greek, 1, 0, new String[] { "ISO8859_7", "greek" }),
new MysqlCharset(MYSQL_CHARSET_NAME_latin7, 1, 0, new String[] { "ISO-8859-13" }), // was ISO8859_7, that's incorrect; also + "LATIN7 = latin7," is wrong java encoding name
new MysqlCharset(MYSQL_CHARSET_NAME_hebrew, 1, 0, new String[] { "ISO8859_8" }), // hebrew is an alias
new MysqlCharset(MYSQL_CHARSET_NAME_latin5, 1, 0, new String[] { "ISO8859_9" }), // LATIN5 is an alias
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_latvian, 1, 0, new String[] { "ISO8859_13" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_latvian1, 1, 0, new String[] { "ISO8859_13" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_estonia, 1, 1, new String[] { "ISO8859_13" }, 4, 0), //, "ISO8859_13"); // punting for "estonia";
new MysqlCharset(MYSQL_CHARSET_NAME_cp850, 1, 0, new String[] { "Cp850", "Cp437" }),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_dos, 1, 0, new String[] { "Cp850", "Cp437" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_cp852, 1, 0, new String[] { "Cp852" }),
new MysqlCharset(MYSQL_CHARSET_NAME_keybcs2, 1, 0, new String[] { "Cp852" }), // new, Kamenicky encoding usually known as Cp895 but there is no official cp895 specification; close to Cp852, see http://ftp.muni.cz/pub/localization/charsets/cs-encodings-faq
new MysqlCharset(MYSQL_CHARSET_NAME_cp866, 1, 0, new String[] { "Cp866" }),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_koi8_ru, 1, 0, new String[] { "KOI8_R" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_koi8r, 1, 1, new String[] { "KOI8_R" }),
new MysqlCharset(MYSQL_CHARSET_NAME_koi8u, 1, 0, new String[] { "KOI8_R" }),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_koi8_ukr, 1, 0, new String[] { "KOI8_R" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_tis620, 1, 0, new String[] { "TIS620" }),
new MysqlCharset(MYSQL_CHARSET_NAME_cp1250, 1, 0, new String[] { "Cp1250" }),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_win1250, 1, 0, new String[] { "Cp1250" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_cp1251, 1, 1, new String[] { "Cp1251" }),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_win1251, 1, 0, new String[] { "Cp1251" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_cp1251cias, 1, 0, new String[] { "Cp1251" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_cp1251csas, 1, 0, new String[] { "Cp1251" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_win1251ukr, 1, 0, new String[] { "Cp1251" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_cp1256, 1, 0, new String[] { "Cp1256" }),
new MysqlCharset(MYSQL_CHARSET_NAME_cp1257, 1, 0, new String[] { "Cp1257" }),
new MysqlCharset(MYSQL_CHARSET_NAME_macroman, 1, 0, new String[] { "MacRoman" }),
new MysqlCharset(MYSQL_CHARSET_NAME_macce, 1, 0, new String[] { "MacCentralEurope" }),
new MysqlCharset(MYSQL_CHARSET_NAME_utf8, 3, 1, new String[] { "UTF-8" }),
new MysqlCharset(MYSQL_CHARSET_NAME_utf8mb4, 4, 0, new String[] { "UTF-8" }), // "UTF-8 = *> 5.5.2 utf8mb4,"
new MysqlCharset(MYSQL_CHARSET_NAME_ucs2, 2, 0, new String[] { "UnicodeBig" }),
new MysqlCharset(MYSQL_CHARSET_NAME_binary, 1, 1, new String[] { "ISO8859_1" }), // US-ASCII ?
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_latin1_de, 1, 0, new String[] { "ISO8859_1" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_german1, 1, 0, new String[] { "ISO8859_1" }, 4, 0),
new MysqlCharset(MYSQL_4_0_CHARSET_NAME_danish, 1, 0, new String[] { "ISO8859_1" }, 4, 0),
new MysqlCharset(MYSQL_CHARSET_NAME_utf16, 4, 0, new String[] { "UTF-16" }),
new MysqlCharset(MYSQL_CHARSET_NAME_utf16le, 4, 0, new String[] { "UTF-16LE" }),
new MysqlCharset(MYSQL_CHARSET_NAME_utf32, 4, 0, new String[] { "UTF-32" })
};
HashMap<String, MysqlCharset> charsetNameToMysqlCharsetMap = new HashMap<String, MysqlCharset>();
HashMap<String, List<MysqlCharset>> javaUcToMysqlCharsetMap = new HashMap<String, List<MysqlCharset>>();
Set<String> tempMultibyteEncodings = new HashSet<String>(); // Character sets that we can't convert ourselves.
Set<String> tempEscapeEncodings = new HashSet<String>(); // Eastern Unicode character sets which require escaping
for (int i = 0; i < charset.length; i++) {
String charsetName = charset[i].charsetName;
charsetNameToMysqlCharsetMap.put(charsetName, charset[i]);
numberOfEncodingsConfigured += charset[i].javaEncodingsUc.size();
for (String encUC : charset[i].javaEncodingsUc) {
// fill javaUcToMysqlCharsetMap
List<MysqlCharset> charsets = javaUcToMysqlCharsetMap.get(encUC);
if (charsets == null) {
charsets = new ArrayList<MysqlCharset>();
javaUcToMysqlCharsetMap.put(encUC, charsets);
}
charsets.add(charset[i]);
// fill multi-byte charsets
if (charset[i].mblen > 1) {
tempMultibyteEncodings.add(encUC);
}
}
// fill EscapeEasternUnicode charsets
// TODO maybe needs more charsets, MS932 eg?
if (charsetName.equals(MYSQL_CHARSET_NAME_big5) || charsetName.equals(MYSQL_CHARSET_NAME_gbk) || charsetName.equals(MYSQL_CHARSET_NAME_sjis)) {
tempEscapeEncodings.addAll(charset[i].javaEncodingsUc);
}
}
CHARSET_NAME_TO_CHARSET = Collections.unmodifiableMap(charsetNameToMysqlCharsetMap);
JAVA_ENCODING_UC_TO_MYSQL_CHARSET = Collections.unmodifiableMap(javaUcToMysqlCharsetMap);
MULTIBYTE_ENCODINGS = Collections.unmodifiableSet(tempMultibyteEncodings);
ESCAPE_ENCODINGS = Collections.unmodifiableSet(tempEscapeEncodings);
// complete list of mysql collations and their corresponding character sets each element of collation[1]..collation[MAP_SIZE-1] must not be null
Collation[] collation = new Collation[MAP_SIZE];
collation[1] = new Collation(1, "big5_chinese_ci", 1, MYSQL_CHARSET_NAME_big5);
collation[84] = new Collation(84, "big5_bin", 0, MYSQL_CHARSET_NAME_big5);
collation[2] = new Collation(2, "latin2_czech_cs", 0, MYSQL_CHARSET_NAME_latin2);
collation[9] = new Collation(9, "latin2_general_ci", 1, MYSQL_CHARSET_NAME_latin2);
collation[21] = new Collation(21, "latin2_hungarian_ci", 0, MYSQL_CHARSET_NAME_latin2);
collation[27] = new Collation(27, "latin2_croatian_ci", 0, MYSQL_CHARSET_NAME_latin2);
collation[77] = new Collation(77, "latin2_bin", 0, MYSQL_CHARSET_NAME_latin2);
collation[4] = new Collation(4, "cp850_general_ci", 1, MYSQL_CHARSET_NAME_cp850);
collation[80] = new Collation(80, "cp850_bin", 0, MYSQL_CHARSET_NAME_cp850);
collation[5] = new Collation(5, "latin1_german1_ci", 1, MYSQL_CHARSET_NAME_latin1);
collation[8] = new Collation(8, "latin1_swedish_ci", 0, MYSQL_CHARSET_NAME_latin1);
collation[15] = new Collation(15, "latin1_danish_ci", 0, MYSQL_CHARSET_NAME_latin1);
collation[31] = new Collation(31, "latin1_german2_ci", 0, MYSQL_CHARSET_NAME_latin1);
collation[47] = new Collation(47, "latin1_bin", 0, MYSQL_CHARSET_NAME_latin1);
collation[48] = new Collation(48, "latin1_general_ci", 0, MYSQL_CHARSET_NAME_latin1);
collation[49] = new Collation(49, "latin1_general_cs", 0, MYSQL_CHARSET_NAME_latin1);
collation[76] = new Collation(76, "not_implemented", 0, NOT_USED);
collation[94] = new Collation(94, "latin1_spanish_ci", 0, MYSQL_CHARSET_NAME_latin1);
collation[100] = new Collation(100, "not_implemented", 0, NOT_USED);
collation[125] = new Collation(125, "not_implemented", 0, NOT_USED);
collation[126] = new Collation(126, "not_implemented", 0, NOT_USED);
collation[127] = new Collation(127, "not_implemented", 0, NOT_USED);
collation[152] = new Collation(152, "not_implemented", 0, NOT_USED);
collation[153] = new Collation(153, "not_implemented", 0, NOT_USED);
collation[154] = new Collation(154, "not_implemented", 0, NOT_USED);
collation[155] = new Collation(155, "not_implemented", 0, NOT_USED);
collation[156] = new Collation(156, "not_implemented", 0, NOT_USED);
collation[157] = new Collation(157, "not_implemented", 0, NOT_USED);
collation[158] = new Collation(158, "not_implemented", 0, NOT_USED);
collation[184] = new Collation(184, "not_implemented", 0, NOT_USED);
collation[185] = new Collation(185, "not_implemented", 0, NOT_USED);
collation[186] = new Collation(186, "not_implemented", 0, NOT_USED);
collation[187] = new Collation(187, "not_implemented", 0, NOT_USED);
collation[188] = new Collation(188, "not_implemented", 0, NOT_USED);
collation[189] = new Collation(189, "not_implemented", 0, NOT_USED);
collation[190] = new Collation(190, "not_implemented", 0, NOT_USED);
collation[191] = new Collation(191, "not_implemented", 0, NOT_USED);
collation[216] = new Collation(216, "not_implemented", 0, NOT_USED);
collation[217] = new Collation(217, "not_implemented", 0, NOT_USED);
collation[218] = new Collation(218, "not_implemented", 0, NOT_USED);
collation[219] = new Collation(219, "not_implemented", 0, NOT_USED);
collation[220] = new Collation(220, "not_implemented", 0, NOT_USED);
collation[221] = new Collation(221, "not_implemented", 0, NOT_USED);
collation[222] = new Collation(222, "not_implemented", 0, NOT_USED);
collation[248] = new Collation(248, "gb18030_chinese_ci", 1, MYSQL_CHARSET_NAME_gb18030);
collation[249] = new Collation(249, "gb18030_bin", 0, MYSQL_CHARSET_NAME_gb18030);
collation[250] = new Collation(250, "gb18030_unicode_520_ci", 0, MYSQL_CHARSET_NAME_gb18030);
collation[251] = new Collation(251, "not_implemented", 0, NOT_USED);
collation[252] = new Collation(252, "not_implemented", 0, NOT_USED);
collation[253] = new Collation(253, "not_implemented", 0, NOT_USED);
collation[254] = new Collation(254, "not_implemented", 0, NOT_USED);
collation[10] = new Collation(10, "swe7_swedish_ci", 0, MYSQL_CHARSET_NAME_swe7);
collation[82] = new Collation(82, "swe7_bin", 0, MYSQL_CHARSET_NAME_swe7);
collation[6] = new Collation(6, "hp8_english_ci", 0, MYSQL_CHARSET_NAME_hp8);
collation[72] = new Collation(72, "hp8_bin", 0, MYSQL_CHARSET_NAME_hp8);
collation[3] = new Collation(3, "dec8_swedish_ci", 0, MYSQL_CHARSET_NAME_dec8);
collation[69] = new Collation(69, "dec8_bin", 0, MYSQL_CHARSET_NAME_dec8);
collation[32] = new Collation(32, "armscii8_general_ci", 0, MYSQL_CHARSET_NAME_armscii8);
collation[64] = new Collation(64, "armscii8_bin", 0, MYSQL_CHARSET_NAME_armscii8);
collation[92] = new Collation(92, "geostd8_general_ci", 0, MYSQL_CHARSET_NAME_geostd8);
collation[93] = new Collation(93, "geostd8_bin", 0, MYSQL_CHARSET_NAME_geostd8);
collation[7] = new Collation(7, "koi8r_general_ci", 0, MYSQL_CHARSET_NAME_koi8r);
collation[74] = new Collation(74, "koi8r_bin", 0, MYSQL_CHARSET_NAME_koi8r);
collation[11] = new Collation(11, "ascii_general_ci", 0, MYSQL_CHARSET_NAME_ascii);
collation[65] = new Collation(65, "ascii_bin", 0, MYSQL_CHARSET_NAME_ascii);
collation[12] = new Collation(12, "ujis_japanese_ci", 0, MYSQL_CHARSET_NAME_ujis);
collation[91] = new Collation(91, "ujis_bin", 0, MYSQL_CHARSET_NAME_ujis);
collation[13] = new Collation(13, "sjis_japanese_ci", 0, MYSQL_CHARSET_NAME_sjis);
collation[14] = new Collation(14, "cp1251_bulgarian_ci", 0, MYSQL_CHARSET_NAME_cp1251);
collation[16] = new Collation(16, "hebrew_general_ci", 0, MYSQL_CHARSET_NAME_hebrew);
collation[17] = new Collation(17, "latin1_german1_ci", 0, MYSQL_4_0_CHARSET_NAME_win1251); // removed since 4.1
collation[18] = new Collation(18, "tis620_thai_ci", 0, MYSQL_CHARSET_NAME_tis620);
collation[19] = new Collation(19, "euckr_korean_ci", 0, MYSQL_CHARSET_NAME_euckr);
collation[20] = new Collation(20, "latin7_estonian_cs", 0, MYSQL_CHARSET_NAME_latin7);
collation[22] = new Collation(22, "koi8u_general_ci", 0, MYSQL_CHARSET_NAME_koi8u);
collation[23] = new Collation(23, "cp1251_ukrainian_ci", 0, MYSQL_CHARSET_NAME_cp1251);
collation[24] = new Collation(24, "gb2312_chinese_ci", 0, MYSQL_CHARSET_NAME_gb2312);
collation[25] = new Collation(25, "greek_general_ci", 0, MYSQL_CHARSET_NAME_greek);
collation[26] = new Collation(26, "cp1250_general_ci", 1, MYSQL_CHARSET_NAME_cp1250);
collation[28] = new Collation(28, "gbk_chinese_ci", 1, MYSQL_CHARSET_NAME_gbk);
collation[29] = new Collation(29, "cp1257_lithuanian_ci", 0, MYSQL_CHARSET_NAME_cp1257);
collation[30] = new Collation(30, "latin5_turkish_ci", 1, MYSQL_CHARSET_NAME_latin5);
collation[33] = new Collation(33, "utf8_general_ci", 1, MYSQL_CHARSET_NAME_utf8);
collation[34] = new Collation(34, "cp1250_czech_cs", 0, MYSQL_CHARSET_NAME_cp1250);
collation[35] = new Collation(35, "ucs2_general_ci", 1, MYSQL_CHARSET_NAME_ucs2);
collation[36] = new Collation(36, "cp866_general_ci", 1, MYSQL_CHARSET_NAME_cp866);
collation[37] = new Collation(37, "keybcs2_general_ci", 1, MYSQL_CHARSET_NAME_keybcs2);
collation[38] = new Collation(38, "macce_general_ci", 1, MYSQL_CHARSET_NAME_macce);
collation[39] = new Collation(39, "macroman_general_ci", 1, MYSQL_CHARSET_NAME_macroman);
collation[40] = new Collation(40, "cp852_general_ci", 1, MYSQL_CHARSET_NAME_cp852);
collation[41] = new Collation(41, "latin7_general_ci", 1, MYSQL_CHARSET_NAME_latin7);
collation[42] = new Collation(42, "latin7_general_cs", 0, MYSQL_CHARSET_NAME_latin7);
collation[43] = new Collation(43, "macce_bin", 0, MYSQL_CHARSET_NAME_macce);
collation[44] = new Collation(44, "cp1250_croatian_ci", 0, MYSQL_CHARSET_NAME_cp1250);
collation[45] = new Collation(45, "utf8mb4_general_ci", 1, MYSQL_CHARSET_NAME_utf8mb4);
collation[46] = new Collation(46, "utf8mb4_bin", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[50] = new Collation(50, "cp1251_bin", 0, MYSQL_CHARSET_NAME_cp1251);
collation[51] = new Collation(51, "cp1251_general_ci", 1, MYSQL_CHARSET_NAME_cp1251);
collation[52] = new Collation(52, "cp1251_general_cs", 0, MYSQL_CHARSET_NAME_cp1251);
collation[53] = new Collation(53, "macroman_bin", 0, MYSQL_CHARSET_NAME_macroman);
collation[54] = new Collation(54, "utf16_general_ci", 1, MYSQL_CHARSET_NAME_utf16);
collation[55] = new Collation(55, "utf16_bin", 0, MYSQL_CHARSET_NAME_utf16);
collation[56] = new Collation(56, "utf16le_general_ci", 1, MYSQL_CHARSET_NAME_utf16le);
collation[57] = new Collation(57, "cp1256_general_ci", 1, MYSQL_CHARSET_NAME_cp1256);
collation[58] = new Collation(58, "cp1257_bin", 0, MYSQL_CHARSET_NAME_cp1257);
collation[59] = new Collation(59, "cp1257_general_ci", 1, MYSQL_CHARSET_NAME_cp1257);
collation[60] = new Collation(60, "utf32_general_ci", 1, MYSQL_CHARSET_NAME_utf32);
collation[61] = new Collation(61, "utf32_bin", 0, MYSQL_CHARSET_NAME_utf32);
collation[62] = new Collation(62, "utf16le_bin", 0, MYSQL_CHARSET_NAME_utf16le);
collation[63] = new Collation(63, "binary", 1, MYSQL_CHARSET_NAME_binary);
collation[66] = new Collation(66, "cp1250_bin", 0, MYSQL_CHARSET_NAME_cp1250);
collation[67] = new Collation(67, "cp1256_bin", 0, MYSQL_CHARSET_NAME_cp1256);
collation[68] = new Collation(68, "cp866_bin", 0, MYSQL_CHARSET_NAME_cp866);
collation[70] = new Collation(70, "greek_bin", 0, MYSQL_CHARSET_NAME_greek);
collation[71] = new Collation(71, "hebrew_bin", 0, MYSQL_CHARSET_NAME_hebrew);
collation[73] = new Collation(73, "keybcs2_bin", 0, MYSQL_CHARSET_NAME_keybcs2);
collation[75] = new Collation(75, "koi8u_bin", 0, MYSQL_CHARSET_NAME_koi8u);
collation[78] = new Collation(78, "latin5_bin", 0, MYSQL_CHARSET_NAME_latin5);
collation[79] = new Collation(79, "latin7_bin", 0, MYSQL_CHARSET_NAME_latin7);
collation[81] = new Collation(81, "cp852_bin", 0, MYSQL_CHARSET_NAME_cp852);
collation[83] = new Collation(83, "utf8_bin", 0, MYSQL_CHARSET_NAME_utf8);
collation[85] = new Collation(85, "euckr_bin", 0, MYSQL_CHARSET_NAME_euckr);
collation[86] = new Collation(86, "gb2312_bin", 0, MYSQL_CHARSET_NAME_gb2312);
collation[87] = new Collation(87, "gbk_bin", 0, MYSQL_CHARSET_NAME_gbk);
collation[88] = new Collation(88, "sjis_bin", 0, MYSQL_CHARSET_NAME_sjis);
collation[89] = new Collation(89, "tis620_bin", 0, MYSQL_CHARSET_NAME_tis620);
collation[90] = new Collation(90, "ucs2_bin", 0, MYSQL_CHARSET_NAME_ucs2);
collation[95] = new Collation(95, "cp932_japanese_ci", 1, MYSQL_CHARSET_NAME_cp932);
collation[96] = new Collation(96, "cp932_bin", 0, MYSQL_CHARSET_NAME_cp932);
collation[97] = new Collation(97, "eucjpms_japanese_ci", 1, MYSQL_CHARSET_NAME_eucjpms);
collation[98] = new Collation(98, "eucjpms_bin", 0, MYSQL_CHARSET_NAME_eucjpms);
collation[99] = new Collation(99, "cp1250_polish_ci", 0, MYSQL_CHARSET_NAME_cp1250);
collation[101] = new Collation(101, "utf16_unicode_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[102] = new Collation(102, "utf16_icelandic_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[103] = new Collation(103, "utf16_latvian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[104] = new Collation(104, "utf16_romanian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[105] = new Collation(105, "utf16_slovenian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[106] = new Collation(106, "utf16_polish_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[107] = new Collation(107, "utf16_estonian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[108] = new Collation(108, "utf16_spanish_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[109] = new Collation(109, "utf16_swedish_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[110] = new Collation(110, "utf16_turkish_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[111] = new Collation(111, "utf16_czech_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[112] = new Collation(112, "utf16_danish_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[113] = new Collation(113, "utf16_lithuanian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[114] = new Collation(114, "utf16_slovak_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[115] = new Collation(115, "utf16_spanish2_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[116] = new Collation(116, "utf16_roman_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[117] = new Collation(117, "utf16_persian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[118] = new Collation(118, "utf16_esperanto_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[119] = new Collation(119, "utf16_hungarian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[120] = new Collation(120, "utf16_sinhala_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[121] = new Collation(121, "utf16_german2_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[122] = new Collation(122, "utf16_croatian_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[123] = new Collation(123, "utf16_unicode_520_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[124] = new Collation(124, "utf16_vietnamese_ci", 0, MYSQL_CHARSET_NAME_utf16);
collation[128] = new Collation(128, "ucs2_unicode_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[129] = new Collation(129, "ucs2_icelandic_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[130] = new Collation(130, "ucs2_latvian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[131] = new Collation(131, "ucs2_romanian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[132] = new Collation(132, "ucs2_slovenian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[133] = new Collation(133, "ucs2_polish_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[134] = new Collation(134, "ucs2_estonian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[135] = new Collation(135, "ucs2_spanish_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[136] = new Collation(136, "ucs2_swedish_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[137] = new Collation(137, "ucs2_turkish_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[138] = new Collation(138, "ucs2_czech_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[139] = new Collation(139, "ucs2_danish_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[140] = new Collation(140, "ucs2_lithuanian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[141] = new Collation(141, "ucs2_slovak_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[142] = new Collation(142, "ucs2_spanish2_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[143] = new Collation(143, "ucs2_roman_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[144] = new Collation(144, "ucs2_persian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[145] = new Collation(145, "ucs2_esperanto_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[146] = new Collation(146, "ucs2_hungarian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[147] = new Collation(147, "ucs2_sinhala_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[148] = new Collation(148, "ucs2_german2_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[149] = new Collation(149, "ucs2_croatian_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[150] = new Collation(150, "ucs2_unicode_520_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[151] = new Collation(151, "ucs2_vietnamese_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[159] = new Collation(159, "ucs2_general_mysql500_ci", 0, MYSQL_CHARSET_NAME_ucs2);
collation[160] = new Collation(160, "utf32_unicode_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[161] = new Collation(161, "utf32_icelandic_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[162] = new Collation(162, "utf32_latvian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[163] = new Collation(163, "utf32_romanian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[164] = new Collation(164, "utf32_slovenian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[165] = new Collation(165, "utf32_polish_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[166] = new Collation(166, "utf32_estonian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[167] = new Collation(167, "utf32_spanish_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[168] = new Collation(168, "utf32_swedish_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[169] = new Collation(169, "utf32_turkish_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[170] = new Collation(170, "utf32_czech_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[171] = new Collation(171, "utf32_danish_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[172] = new Collation(172, "utf32_lithuanian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[173] = new Collation(173, "utf32_slovak_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[174] = new Collation(174, "utf32_spanish2_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[175] = new Collation(175, "utf32_roman_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[176] = new Collation(176, "utf32_persian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[177] = new Collation(177, "utf32_esperanto_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[178] = new Collation(178, "utf32_hungarian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[179] = new Collation(179, "utf32_sinhala_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[180] = new Collation(180, "utf32_german2_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[181] = new Collation(181, "utf32_croatian_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[182] = new Collation(182, "utf32_unicode_520_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[183] = new Collation(183, "utf32_vietnamese_ci", 0, MYSQL_CHARSET_NAME_utf32);
collation[192] = new Collation(192, "utf8_unicode_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[193] = new Collation(193, "utf8_icelandic_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[194] = new Collation(194, "utf8_latvian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[195] = new Collation(195, "utf8_romanian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[196] = new Collation(196, "utf8_slovenian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[197] = new Collation(197, "utf8_polish_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[198] = new Collation(198, "utf8_estonian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[199] = new Collation(199, "utf8_spanish_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[200] = new Collation(200, "utf8_swedish_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[201] = new Collation(201, "utf8_turkish_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[202] = new Collation(202, "utf8_czech_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[203] = new Collation(203, "utf8_danish_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[204] = new Collation(204, "utf8_lithuanian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[205] = new Collation(205, "utf8_slovak_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[206] = new Collation(206, "utf8_spanish2_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[207] = new Collation(207, "utf8_roman_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[208] = new Collation(208, "utf8_persian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[209] = new Collation(209, "utf8_esperanto_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[210] = new Collation(210, "utf8_hungarian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[211] = new Collation(211, "utf8_sinhala_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[212] = new Collation(212, "utf8_german2_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[213] = new Collation(213, "utf8_croatian_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[214] = new Collation(214, "utf8_unicode_520_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[215] = new Collation(215, "utf8_vietnamese_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[223] = new Collation(223, "utf8_general_mysql500_ci", 0, MYSQL_CHARSET_NAME_utf8);
collation[224] = new Collation(224, "utf8mb4_unicode_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[225] = new Collation(225, "utf8mb4_icelandic_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[226] = new Collation(226, "utf8mb4_latvian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[227] = new Collation(227, "utf8mb4_romanian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[228] = new Collation(228, "utf8mb4_slovenian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[229] = new Collation(229, "utf8mb4_polish_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[230] = new Collation(230, "utf8mb4_estonian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[231] = new Collation(231, "utf8mb4_spanish_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[232] = new Collation(232, "utf8mb4_swedish_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[233] = new Collation(233, "utf8mb4_turkish_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[234] = new Collation(234, "utf8mb4_czech_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[235] = new Collation(235, "utf8mb4_danish_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[236] = new Collation(236, "utf8mb4_lithuanian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[237] = new Collation(237, "utf8mb4_slovak_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[238] = new Collation(238, "utf8mb4_spanish2_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[239] = new Collation(239, "utf8mb4_roman_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[240] = new Collation(240, "utf8mb4_persian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[241] = new Collation(241, "utf8mb4_esperanto_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[242] = new Collation(242, "utf8mb4_hungarian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[243] = new Collation(243, "utf8mb4_sinhala_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[244] = new Collation(244, "utf8mb4_german2_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[245] = new Collation(245, "utf8mb4_croatian_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[246] = new Collation(246, "utf8mb4_unicode_520_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
collation[247] = new Collation(247, "utf8mb4_vietnamese_ci", 0, MYSQL_CHARSET_NAME_utf8mb4);
COLLATION_INDEX_TO_COLLATION_NAME = new String[MAP_SIZE];
COLLATION_INDEX_TO_CHARSET = new MysqlCharset[MAP_SIZE];
Map<String, Integer> charsetNameToCollationIndexMap = new TreeMap<String, Integer>();
Map<String, Integer> charsetNameToCollationPriorityMap = new TreeMap<String, Integer>();
Set<Integer> tempUTF8MB4Indexes = new HashSet<Integer>();
for (int i = 1; i < MAP_SIZE; i++) {
COLLATION_INDEX_TO_COLLATION_NAME[i] = collation[i].collationName;
COLLATION_INDEX_TO_CHARSET[i] = collation[i].mysqlCharset;
String charsetName = collation[i].mysqlCharset.charsetName;
if (!charsetNameToCollationIndexMap.containsKey(charsetName) || charsetNameToCollationPriorityMap.get(charsetName) < collation[i].priority) {
charsetNameToCollationIndexMap.put(charsetName, i);
charsetNameToCollationPriorityMap.put(charsetName, collation[i].priority);
}
// Filling indexes of utf8mb4 collations
if (charsetName.equals(MYSQL_CHARSET_NAME_utf8mb4)) {
tempUTF8MB4Indexes.add(i);
}
}
// Sanity check
for (int i = 1; i < MAP_SIZE; i++) {
if (COLLATION_INDEX_TO_COLLATION_NAME[i] == null) {
throw new RuntimeException("Assertion failure: No mapping from charset index " + i + " to a mysql collation");
}
if (COLLATION_INDEX_TO_COLLATION_NAME[i] == null) {
throw new RuntimeException("Assertion failure: No mapping from charset index " + i + " to a Java character set");
}
}
CHARSET_NAME_TO_COLLATION_INDEX = Collections.unmodifiableMap(charsetNameToCollationIndexMap);
UTF8MB4_INDEXES = Collections.unmodifiableSet(tempUTF8MB4Indexes);
/**
* Charsets for error messages for servers < 5.5
*/
Map<String, String> tempMap = new HashMap<String, String>();
tempMap.put("czech", "latin2");
tempMap.put("danish", "latin1");
tempMap.put("dutch", "latin1");
tempMap.put("english", "latin1");
tempMap.put("estonian", "latin7");
tempMap.put("french", "latin1");
tempMap.put("german", "latin1");
tempMap.put("greek", "greek");
tempMap.put("hungarian", "latin2");
tempMap.put("italian", "latin1");
tempMap.put("japanese", "ujis");
tempMap.put("japanese-sjis", "sjis");
tempMap.put("korean", "euckr");
tempMap.put("norwegian", "latin1");
tempMap.put("norwegian-ny", "latin1");
tempMap.put("polish", "latin2");
tempMap.put("portuguese", "latin1");
tempMap.put("romanian", "latin2");
tempMap.put("russian", "koi8r");
tempMap.put("serbian", "cp1250");
tempMap.put("slovak", "latin2");
tempMap.put("spanish", "latin1");
tempMap.put("swedish", "latin1");
tempMap.put("ukrainian", "koi8u");
ERROR_MESSAGE_FILE_TO_MYSQL_CHARSET = Collections.unmodifiableMap(tempMap);
}
public final static String getMysqlCharsetForJavaEncoding(String javaEncoding, Connection conn) throws SQLException {
try {
List<MysqlCharset> mysqlCharsets = CharsetMapping.JAVA_ENCODING_UC_TO_MYSQL_CHARSET.get(javaEncoding.toUpperCase(Locale.ENGLISH));
if (mysqlCharsets != null) {
Iterator<MysqlCharset> iter = mysqlCharsets.iterator();
MysqlCharset versionedProp = null;
while (iter.hasNext()) {
MysqlCharset charset = iter.next();
if (conn == null) {
// Take the first one we get
return charset.charsetName;
}
if (versionedProp == null || versionedProp.major < charset.major || versionedProp.minor < charset.minor
|| versionedProp.subminor < charset.subminor || versionedProp.priority < charset.priority) {
if (charset.isOkayForVersion(conn)) {
versionedProp = charset;
}
}
}
if (versionedProp != null) {
return versionedProp.charsetName;
}
}
return null;
} catch (SQLException ex) {
throw ex;
} catch (RuntimeException ex) {
SQLException sqlEx = SQLError.createSQLException(ex.toString(), SQLError.SQL_STATE_ILLEGAL_ARGUMENT, null);
sqlEx.initCause(ex);
throw sqlEx;
}
}
public static int getCollationIndexForJavaEncoding(String javaEncoding, java.sql.Connection conn) throws SQLException {
String charsetName = getMysqlCharsetForJavaEncoding(javaEncoding, (Connection) conn);
if (charsetName != null) {
Integer ci = CHARSET_NAME_TO_COLLATION_INDEX.get(charsetName);
if (ci != null) {
return ci.intValue();
}
}
return 0;
}
public static String getMysqlCharsetNameForCollationIndex(Integer collationIndex) {
if (collationIndex != null && collationIndex > 0 && collationIndex < MAP_SIZE) {
return COLLATION_INDEX_TO_CHARSET[collationIndex].charsetName;
}
return null;
}
/**
* MySQL charset could map to several Java encodings.
* So here we choose the one according to next rules:
* <li>if there is no static mapping for this charset then return javaEncoding value as is because this
* could be a custom charset for example
* <li>if static mapping exists and javaEncoding equals to one of Java encoding canonical names or aliases available
* for this mapping then javaEncoding value as is; this is required when result should match to connection encoding, for example if connection encoding is
* Cp943 we must avoid getting SHIFT_JIS for sjis mysql charset
* <li>if static mapping exists and javaEncoding doesn't match any Java encoding canonical
* names or aliases available for this mapping then return default Java encoding (the first in mapping list)
*
* @param mysqlCharsetName
* @param javaEncoding
*/
public static String getJavaEncodingForMysqlCharset(String mysqlCharsetName, String javaEncoding) {
String res = javaEncoding;
MysqlCharset cs = CHARSET_NAME_TO_CHARSET.get(mysqlCharsetName);
if (cs != null) {
res = cs.getMatchingJavaEncoding(javaEncoding);
}
return res;
}
public static String getJavaEncodingForMysqlCharset(String mysqlCharsetName) {
return getJavaEncodingForMysqlCharset(mysqlCharsetName, null);
}
public static String getJavaEncodingForCollationIndex(Integer collationIndex, String javaEncoding) {
if (collationIndex != null && collationIndex > 0 && collationIndex < MAP_SIZE) {
MysqlCharset cs = COLLATION_INDEX_TO_CHARSET[collationIndex];
return cs.getMatchingJavaEncoding(javaEncoding);
}
return null;
}
public static String getJavaEncodingForCollationIndex(Integer collationIndex) {
return getJavaEncodingForCollationIndex(collationIndex, null);
}
final static int getNumberOfCharsetsConfigured() {
return numberOfEncodingsConfigured;
}
/**
* Returns the character encoding for error messages returned from the
* server. Doesn't return useful values other than Cp1252 until the driver
* has gone through initialization phase and determined server configuration,
* as not enough information is available to make an intelligent decision
* until then.
*
* @param conn
* the connection to the MySQL server
* @return the Java encoding name that error messages use
* @throws SQLException
* if determination of the character encoding fails
*/
final static String getCharacterEncodingForErrorMessages(ConnectionImpl conn) throws SQLException {
// As of MySQL 5.5, the server constructs error messages using UTF-8 and returns them to clients in the character set specified by the
// character_set_results system variable.
if (conn.versionMeetsMinimum(5, 5, 0)) {
String errorMessageCharsetName = conn.getServerVariable(ConnectionImpl.JDBC_LOCAL_CHARACTER_SET_RESULTS);
if (errorMessageCharsetName != null) {
String javaEncoding = getJavaEncodingForMysqlCharset(errorMessageCharsetName);
if (javaEncoding != null) {
return javaEncoding;
}
}
return "UTF-8";
}
String errorMessageFile = conn.getServerVariable("language");
if (errorMessageFile == null || errorMessageFile.length() == 0) {
// punt
return "Cp1252";
}
int endWithoutSlash = errorMessageFile.length();
if (errorMessageFile.endsWith("/") || errorMessageFile.endsWith("\\")) {
endWithoutSlash--;
}
int lastSlashIndex = errorMessageFile.lastIndexOf('/', endWithoutSlash - 1);
if (lastSlashIndex == -1) {
lastSlashIndex = errorMessageFile.lastIndexOf('\\', endWithoutSlash - 1);
}
if (lastSlashIndex == -1) {
lastSlashIndex = 0;
}
if (lastSlashIndex == endWithoutSlash || endWithoutSlash < lastSlashIndex) {
// punt
return "Cp1252";
}
errorMessageFile = errorMessageFile.substring(lastSlashIndex + 1, endWithoutSlash);
String errorMessageEncodingMysql = ERROR_MESSAGE_FILE_TO_MYSQL_CHARSET.get(errorMessageFile);
if (errorMessageEncodingMysql == null) {
// punt
return "Cp1252";
}
String javaEncoding = getJavaEncodingForMysqlCharset(errorMessageEncodingMysql);
if (javaEncoding == null) {
// punt
return "Cp1252";
}
return javaEncoding;
}
final static boolean requiresEscapeEasternUnicode(String javaEncodingName) {
return ESCAPE_ENCODINGS.contains(javaEncodingName.toUpperCase(Locale.ENGLISH));
}
/**
* Character sets that we can't convert ourselves.
*
* @param javaEncodingName
*/
final public static boolean isMultibyteCharset(String javaEncodingName) {
return MULTIBYTE_ENCODINGS.contains(javaEncodingName.toUpperCase(Locale.ENGLISH));
}
public static int getMblen(String charsetName) {
if (charsetName != null) {
MysqlCharset cs = CHARSET_NAME_TO_CHARSET.get(charsetName);
if (cs != null) {
return cs.mblen;
}
}
return 0;
}
}
class MysqlCharset {
public final String charsetName;
public final int mblen;
public final int priority;
public final List<String> javaEncodingsUc = new ArrayList<String>();
public int major = 4;
public int minor = 1;
public int subminor = 0;
/**
* Constructs MysqlCharset object
*
* @param charsetName
* MySQL charset name
* @param mblen
* Max number of bytes per character
* @param priority
* MysqlCharset with highest lever of this param will be used for Java encoding --> Mysql charsets conversion.
* @param javaEncodings
* List of Java encodings corresponding to this MySQL charset; the first name in list is the default for mysql --> java data conversion
*/
public MysqlCharset(String charsetName, int mblen, int priority, String[] javaEncodings) {
this.charsetName = charsetName;
this.mblen = mblen;
this.priority = priority;
for (int i = 0; i < javaEncodings.length; i++) {
String encoding = javaEncodings[i];
try {
Charset cs = Charset.forName(encoding);
addEncodingMapping(cs.name());
Set<String> als = cs.aliases();
Iterator<String> ali = als.iterator();
while (ali.hasNext()) {
addEncodingMapping(ali.next());
}
} catch (Exception e) {
// if there is no support of this charset in JVM it's still possible to use our converter for 1-byte charsets
if (mblen == 1) {
addEncodingMapping(encoding);
}
}
}
if (this.javaEncodingsUc.size() == 0) {
if (mblen > 1) {
addEncodingMapping("UTF-8");
} else {
addEncodingMapping("Cp1252");
}
}
}
private void addEncodingMapping(String encoding) {
String encodingUc = encoding.toUpperCase(Locale.ENGLISH);
if (!this.javaEncodingsUc.contains(encodingUc)) {
this.javaEncodingsUc.add(encodingUc);
}
}
public MysqlCharset(String charsetName, int mblen, int priority, String[] javaEncodings, int major, int minor) {
this(charsetName, mblen, priority, javaEncodings);
this.major = major;
this.minor = minor;
}
public MysqlCharset(String charsetName, int mblen, int priority, String[] javaEncodings, int major, int minor, int subminor) {
this(charsetName, mblen, priority, javaEncodings);
this.major = major;
this.minor = minor;
this.subminor = subminor;
}
@Override
public String toString() {
StringBuilder asString = new StringBuilder();
asString.append("[");
asString.append("charsetName=");
asString.append(this.charsetName);
asString.append(",mblen=");
asString.append(this.mblen);
// asString.append(",javaEncoding=");
// asString.append(this.javaEncodings.toString());
asString.append("]");
return asString.toString();
}
boolean isOkayForVersion(Connection conn) throws SQLException {
return conn.versionMeetsMinimum(this.major, this.minor, this.subminor);
}
/**
* If javaEncoding parameter value is one of available java encodings for this charset
* then returns javaEncoding value as is. Otherwise returns first available java encoding name.
*
* @param javaEncoding
* @throws SQLException
*/
String getMatchingJavaEncoding(String javaEncoding) {
if (javaEncoding != null && this.javaEncodingsUc.contains(javaEncoding.toUpperCase(Locale.ENGLISH))) {
return javaEncoding;
}
return this.javaEncodingsUc.get(0);
}
}
class Collation {
public final int index;
public final String collationName;
public final int priority;
public final MysqlCharset mysqlCharset;
public Collation(int index, String collationName, int priority, String charsetName) {
this.index = index;
this.collationName = collationName;
this.priority = priority;
this.mysqlCharset = CharsetMapping.CHARSET_NAME_TO_CHARSET.get(charsetName);
}
@Override
public String toString() {
StringBuilder asString = new StringBuilder();
asString.append("[");
asString.append("index=");
asString.append(this.index);
asString.append(",collationName=");
asString.append(this.collationName);
asString.append(",charsetName=");
asString.append(this.mysqlCharset.charsetName);
asString.append(",javaCharsetName=");
asString.append(this.mysqlCharset.getMatchingJavaEncoding(null));
asString.append("]");
return asString.toString();
}
}