summaryrefslogtreecommitdiff
path: root/mysql/strings/ctype-simple.c
blob: 953eb75c66f67a9d04b79dd08327fb8c07b2e98d (plain)
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
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
/* Copyright (c) 2002, 2016, Oracle and/or its affiliates. All rights reserved.

   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 */

#include <my_global.h>
#include "m_string.h"
#include "m_ctype.h"
#include "my_sys.h"  /* Needed for MY_ERRNO_ERANGE */
#include <errno.h>

#include "stdarg.h"

/*
  Returns the number of bytes required for strnxfrm().
*/

size_t my_strnxfrmlen_simple(const CHARSET_INFO *cs, size_t len)
{
  return len * (cs->strxfrm_multiply ? cs->strxfrm_multiply : 1);
}


/*
  Converts a string into its sort key.
  
  SYNOPSIS
     my_strnxfrm_xxx()
     
  IMPLEMENTATION
     
     The my_strxfrm_xxx() function transforms a string pointed to by
     'src' with length 'srclen' according to the charset+collation 
     pair 'cs' and copies the result key into 'dest'.
     
     Comparing two strings using memcmp() after my_strnxfrm_xxx()
     is equal to comparing two original strings with my_strnncollsp_xxx().
     
     Not more than 'dstlen' bytes are written into 'dst'.
     To garantee that the whole string is transformed, 'dstlen' must be
     at least srclen*cs->strnxfrm_multiply bytes long. Otherwise,
     consequent memcmp() may return a non-accurate result.
     
     If the source string is too short to fill whole 'dstlen' bytes,
     then the 'dest' string is padded up to 'dstlen', ensuring that:
     
       "a"  == "a "
       "a\0" < "a"
       "a\0" < "a "
     
     my_strnxfrm_simple() is implemented for 8bit charsets and
     simple collations with one-to-one string->key transformation.
     
     See also implementations for various charsets/collations in  
     other ctype-xxx.c files.
     
  RETURN
  
    Target len 'dstlen'.
  
*/


size_t
my_strnxfrm_simple(const CHARSET_INFO *cs,
                   uchar *dst, size_t dstlen, uint nweights,
                   const uchar *src, size_t srclen, uint flags)
{
  const uchar *map= cs->sort_order;
  uchar *d0= dst;
  const uchar *end;
  const uchar *remainder;
  size_t frmlen;
  if ((frmlen= MY_MIN(dstlen, nweights)) > srclen)
    frmlen= srclen;
  end= src + frmlen;

  // Do the first few bytes.
  remainder= src + (frmlen % 8);
  for (; src < remainder;)
    *dst++= map[*src++];

  // Unroll loop for rest of string.
  for (; src < end;)
  {
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
    *dst++= map[*src++];
  }
  return my_strxfrm_pad_desc_and_reverse(cs, d0, dst, d0 + dstlen,
                                         (uint)(nweights - frmlen), flags, 0);
}


int my_strnncoll_simple(const CHARSET_INFO * cs, const uchar *s, size_t slen,
                        const uchar *t, size_t tlen,
                        my_bool t_is_prefix)
{
  size_t len = ( slen > tlen ) ? tlen : slen;
  const uchar *map= cs->sort_order;
  if (t_is_prefix && slen > tlen)
    slen=tlen;
  while (len--)
  {
    if (map[*s++] != map[*t++])
      return ((int) map[s[-1]] - (int) map[t[-1]]);
  }
  /*
    We can't use (slen - tlen) here as the result may be outside of the
    precision of a signed int
  */
  return slen > tlen ? 1 : slen < tlen ? -1 : 0 ;
}


/*
  Compare strings, discarding end space

  SYNOPSIS
    my_strnncollsp_simple()
    cs			character set handler
    a			First string to compare
    a_length		Length of 'a'
    b			Second string to compare
    b_length		Length of 'b'
    diff_if_only_endspace_difference
		        Set to 1 if the strings should be regarded as different
                        if they only difference in end space

  IMPLEMENTATION
    If one string is shorter as the other, then we space extend the other
    so that the strings have equal length.

    This will ensure that the following things hold:

    "a"  == "a "
    "a\0" < "a"
    "a\0" < "a "

  RETURN
    < 0	 a <  b
    = 0	 a == b
    > 0	 a > b
*/

int my_strnncollsp_simple(const CHARSET_INFO *cs, const uchar *a,
                          size_t a_length, const uchar *b, size_t b_length,
                          my_bool diff_if_only_endspace_difference)
{
  const uchar *map= cs->sort_order, *end;
  size_t length;
  int res;

#ifndef VARCHAR_WITH_DIFF_ENDSPACE_ARE_DIFFERENT_FOR_UNIQUE
  diff_if_only_endspace_difference= 0;
#endif

  end= a + (length= MY_MIN(a_length, b_length));
  while (a < end)
  {
    if (map[*a++] != map[*b++])
      return ((int) map[a[-1]] - (int) map[b[-1]]);
  }
  res= 0;
  if (a_length != b_length)
  {
    int swap= 1;
    if (diff_if_only_endspace_difference)
      res= 1;                                   /* Assume 'a' is bigger */
    /*
      Check the next not space character of the longer key. If it's < ' ',
      then it's smaller than the other key.
    */
    if (a_length < b_length)
    {
      /* put shorter key in s */
      a_length= b_length;
      a= b;
      swap= -1;                                 /* swap sign of result */
      res= -res;
    }
    for (end= a + a_length-length; a < end ; a++)
    {
      if (map[*a] != map[' '])
	return (map[*a] < map[' ']) ? -swap : swap;
    }
  }
  return res;
}


size_t my_caseup_str_8bit(const CHARSET_INFO *cs,char *str)
{
  const uchar *map= cs->to_upper;
  char *str_orig= str;
  while ((*str= (char) map[(uchar) *str]) != 0)
    str++;
  return (size_t) (str - str_orig);
}


size_t my_casedn_str_8bit(const CHARSET_INFO *cs,char *str)
{
  const uchar *map= cs->to_lower;
  char *str_orig= str;
  while ((*str= (char) map[(uchar) *str]) != 0)
    str++;
  return (size_t) (str - str_orig);
}


size_t my_caseup_8bit(const CHARSET_INFO *cs, char *src, size_t srclen,
                      char *dst MY_ATTRIBUTE((unused)),
                      size_t dstlen MY_ATTRIBUTE((unused)))
{
  char *end= src + srclen;
  const uchar *map= cs->to_upper;
  DBUG_ASSERT(src == dst && srclen == dstlen);
  for ( ; src != end ; src++)
    *src= (char) map[(uchar) *src];
  return srclen;
}


size_t my_casedn_8bit(const CHARSET_INFO *cs, char *src, size_t srclen,
                      char *dst MY_ATTRIBUTE((unused)),
                      size_t dstlen MY_ATTRIBUTE((unused)))
{
  char *end= src + srclen;
  const uchar *map=cs->to_lower;
  DBUG_ASSERT(src == dst && srclen == dstlen);
  for ( ; src != end ; src++)
    *src= (char) map[(uchar) *src];
  return srclen;
}

int my_strcasecmp_8bit(const CHARSET_INFO *cs,const char *s, const char *t)
{
  const uchar *map=cs->to_upper;
  while (map[(uchar) *s] == map[(uchar) *t++])
    if (!*s++) return 0;
  return ((int) map[(uchar) s[0]] - (int) map[(uchar) t[-1]]);
}


int my_mb_wc_8bit(const CHARSET_INFO *cs,my_wc_t *wc,
		  const uchar *str,
		  const uchar *end MY_ATTRIBUTE((unused)))
{
  if (str >= end)
    return MY_CS_TOOSMALL;
  
  *wc=cs->tab_to_uni[*str];
  return (!wc[0] && str[0]) ? -1 : 1;
}

int my_wc_mb_8bit(const CHARSET_INFO *cs,my_wc_t wc,
		  uchar *str,
		  uchar *end)
{
  const MY_UNI_IDX *idx;

  if (str >= end)
    return MY_CS_TOOSMALL;

  for (idx=cs->tab_from_uni; idx->tab ; idx++)
  {
    if (idx->from <= wc && idx->to >= wc)
    {
      str[0]= idx->tab[wc - idx->from];
      return (!str[0] && wc) ? MY_CS_ILUNI : 1;
    }
  }
  return MY_CS_ILUNI;
}


/* 
   We can't use vsprintf here as it's not guaranteed to return
   the length on all operating systems.
   This function is also not called in a safe environment, so the
   end buffer must be checked.
*/

size_t my_snprintf_8bit(const CHARSET_INFO *cs  MY_ATTRIBUTE((unused)),
                        char* to, size_t n  MY_ATTRIBUTE((unused)),
		     const char* fmt, ...)
{
  va_list args;
  size_t result;
  va_start(args,fmt);
  result= my_vsnprintf(to, n, fmt, args);
  va_end(args);
  return result;
}


void my_hash_sort_simple(const CHARSET_INFO *cs,
			 const uchar *key, size_t len,
			 ulong *nr1, ulong *nr2)
{
  const uchar *sort_order=cs->sort_order;
  const uchar *end;
  ulong tmp1;
  ulong tmp2;

  /*
    Remove end space. We have to do this to be able to compare
    'A ' and 'A' as identical
  */
  end= skip_trailing_space(key, len);

  tmp1= *nr1;
  tmp2= *nr2;

  for (; key < (uchar*) end ; key++)
  {
    tmp1^=(ulong) ((((uint) tmp1 & 63) + tmp2) *
                   ((uint) sort_order[(uint) *key])) + (tmp1 << 8);
    tmp2+=3;
  }

  *nr1= tmp1;
  *nr2= tmp2;
}


long my_strntol_8bit(const CHARSET_INFO *cs,
		     const char *nptr, size_t l, int base,
		     char **endptr, int *err)
{
  int negative;
  uint32 cutoff;
  uint cutlim;
  uint32 i;
  const char *s;
  uchar c;
  const char *save, *e;
  int overflow;

  *err= 0;				/* Initialize error indicator */

  s = nptr;
  e = nptr+l;
  
  for ( ; s<e && my_isspace(cs, *s) ; s++);
  
  if (s == e)
  {
    goto noconv;
  }
  
  /* Check for a sign.	*/
  if (*s == '-')
  {
    negative = 1;
    ++s;
  }
  else if (*s == '+')
  {
    negative = 0;
    ++s;
  }
  else
    negative = 0;

  save = s;
  cutoff = ((uint32)~0L) / (uint32) base;
  cutlim = (uint) (((uint32)~0L) % (uint32) base);

  overflow = 0;
  i = 0;
  for (c = *s; s != e; c = *++s)
  {
    if (c>='0' && c<='9')
      c -= '0';
    else if (c>='A' && c<='Z')
      c = c - 'A' + 10;
    else if (c>='a' && c<='z')
      c = c - 'a' + 10;
    else
      break;
    if (c >= base)
      break;
    if (i > cutoff || (i == cutoff && c > cutlim))
      overflow = 1;
    else
    {
      i *= (uint32) base;
      i += c;
    }
  }
  
  if (s == save)
    goto noconv;
  
  if (endptr != NULL)
    *endptr = (char *) s;
  
  if (negative)
  {
    if (i  > (uint32) INT_MIN32)
      overflow = 1;
  }
  else if (i > INT_MAX32)
    overflow = 1;
  
  if (overflow)
  {
    err[0]= ERANGE;
    return negative ? INT_MIN32 : INT_MAX32;
  }
  
  return (negative ? -((long) i) : (long) i);

noconv:
  err[0]= EDOM;
  if (endptr != NULL)
    *endptr = (char *) nptr;
  return 0L;
}


ulong my_strntoul_8bit(const CHARSET_INFO *cs,
		       const char *nptr, size_t l, int base,
		       char **endptr, int *err)
{
  int negative;
  uint32 cutoff;
  uint cutlim;
  uint32 i;
  const char *s;
  uchar c;
  const char *save, *e;
  int overflow;

  *err= 0;				/* Initialize error indicator */

  s = nptr;
  e = nptr+l;
  
  for( ; s<e && my_isspace(cs, *s); s++);
  
  if (s==e)
  {
    goto noconv;
  }

  if (*s == '-')
  {
    negative = 1;
    ++s;
  }
  else if (*s == '+')
  {
    negative = 0;
    ++s;
  }
  else
    negative = 0;

  save = s;
  cutoff = ((uint32)~0L) / (uint32) base;
  cutlim = (uint) (((uint32)~0L) % (uint32) base);
  overflow = 0;
  i = 0;
  
  for (c = *s; s != e; c = *++s)
  {
    if (c>='0' && c<='9')
      c -= '0';
    else if (c>='A' && c<='Z')
      c = c - 'A' + 10;
    else if (c>='a' && c<='z')
      c = c - 'a' + 10;
    else
      break;
    if (c >= base)
      break;
    if (i > cutoff || (i == cutoff && c > cutlim))
      overflow = 1;
    else
    {
      i *= (uint32) base;
      i += c;
    }
  }

  if (s == save)
    goto noconv;

  if (endptr != NULL)
    *endptr = (char *) s;

  if (overflow)
  {
    err[0]= ERANGE;
    return (~(uint32) 0);
  }
  
  return (negative ? -((long) i) : (long) i);
  
noconv:
  err[0]= EDOM;
  if (endptr != NULL)
    *endptr = (char *) nptr;
  return 0L;
}


longlong my_strntoll_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
			  const char *nptr, size_t l, int base,
			  char **endptr,int *err)
{
  int negative;
  ulonglong cutoff;
  uint cutlim;
  ulonglong i;
  const char *s, *e;
  const char *save;
  int overflow;

  *err= 0;				/* Initialize error indicator */

  s = nptr;
  e = nptr+l;

  for(; s<e && my_isspace(cs,*s); s++);

  if (s == e)
  {
    goto noconv;
  }

  if (*s == '-')
  {
    negative = 1;
    ++s;
  }
  else if (*s == '+')
  {
    negative = 0;
    ++s;
  }
  else
    negative = 0;

  save = s;

  cutoff = (~(ulonglong) 0) / (unsigned long int) base;
  cutlim = (uint) ((~(ulonglong) 0) % (unsigned long int) base);

  overflow = 0;
  i = 0;
  for ( ; s != e; s++)
  {
    uchar c= *s;
    if (c>='0' && c<='9')
      c -= '0';
    else if (c>='A' && c<='Z')
      c = c - 'A' + 10;
    else if (c>='a' && c<='z')
      c = c - 'a' + 10;
    else
      break;
    if (c >= base)
      break;
    if (i > cutoff || (i == cutoff && c > cutlim))
      overflow = 1;
    else
    {
      i *= (ulonglong) base;
      i += c;
    }
  }

  if (s == save)
    goto noconv;

  if (endptr != NULL)
    *endptr = (char *) s;

  if (negative)
  {
    if (i  > (ulonglong) LLONG_MIN)
      overflow = 1;
  }
  else if (i > (ulonglong) LLONG_MAX)
    overflow = 1;

  if (overflow)
  {
    err[0]= ERANGE;
    return negative ? LLONG_MIN : LLONG_MAX;
  }

  return (negative ? -((longlong) i) : (longlong) i);

noconv:
  err[0]= EDOM;
  if (endptr != NULL)
    *endptr = (char *) nptr;
  return 0L;
}


ulonglong my_strntoull_8bit(const CHARSET_INFO *cs,
			   const char *nptr, size_t l, int base,
			   char **endptr, int *err)
{
  int negative;
  ulonglong cutoff;
  uint cutlim;
  ulonglong i;
  const char *s, *e;
  const char *save;
  int overflow;

  *err= 0;				/* Initialize error indicator */

  s = nptr;
  e = nptr+l;

  for(; s<e && my_isspace(cs,*s); s++);

  if (s == e)
  {
    goto noconv;
  }

  if (*s == '-')
  {
    negative = 1;
    ++s;
  }
  else if (*s == '+')
  {
    negative = 0;
    ++s;
  }
  else
    negative = 0;

  save = s;

  cutoff = (~(ulonglong) 0) / (unsigned long int) base;
  cutlim = (uint) ((~(ulonglong) 0) % (unsigned long int) base);

  overflow = 0;
  i = 0;
  for ( ; s != e; s++)
  {
    uchar c= *s;

    if (c>='0' && c<='9')
      c -= '0';
    else if (c>='A' && c<='Z')
      c = c - 'A' + 10;
    else if (c>='a' && c<='z')
      c = c - 'a' + 10;
    else
      break;
    if (c >= base)
      break;
    if (i > cutoff || (i == cutoff && c > cutlim))
      overflow = 1;
    else
    {
      i *= (ulonglong) base;
      i += c;
    }
  }

  if (s == save)
    goto noconv;

  if (endptr != NULL)
    *endptr = (char *) s;

  if (overflow)
  {
    err[0]= ERANGE;
    return (~(ulonglong) 0);
  }

  return (negative ? -((longlong) i) : (longlong) i);

noconv:
  err[0]= EDOM;
  if (endptr != NULL)
    *endptr = (char *) nptr;
  return 0L;
}


/*
  Read double from string

  SYNOPSIS:
    my_strntod_8bit()
    cs		Character set information
    str		String to convert to double
    length	Optional length for string.
    end		result pointer to end of converted string
    err		Error number if failed conversion
    
  NOTES:
    If length is not INT_MAX32 or str[length] != 0 then the given str must
    be writeable
    If length == INT_MAX32 the str must be \0 terminated.

    It's implemented this way to save a buffer allocation and a memory copy.

  RETURN
    Value of number in string
*/


double my_strntod_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
		       char *str, size_t length,
		       char **end, int *err)
{
  if (length == INT_MAX32)
    length= 65535;                          /* Should be big enough */
  *end= str + length;
  return my_strtod(str, end, err);
}


/*
  This is a fast version optimized for the case of radix 10 / -10

  Assume len >= 1
*/

size_t my_long10_to_str_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                             char *dst, size_t len, int radix, long int val)
{
  char buffer[66];
  char *p, *e;
  long int new_val;
  uint sign=0;
  unsigned long int uval = (unsigned long int) val;

  e = p = &buffer[sizeof(buffer)-1];
  *p= 0;
  
  if (radix < 0)
  {
    if (val < 0)
    {
      /* Avoid integer overflow in (-val) for LLONG_MIN (BUG#31799). */
      uval= (unsigned long int)0 - uval;
      *dst++= '-';
      len--;
      sign= 1;
    }
  }
  
  new_val = (long) (uval / 10);
  *--p    = '0'+ (char) (uval - (unsigned long) new_val * 10);
  val     = new_val;
  
  while (val != 0)
  {
    new_val=val/10;
    *--p = '0' + (char) (val-new_val*10);
    val= new_val;
  }
  
  len= MY_MIN(len, (size_t) (e-p));
  memcpy(dst, p, len);
  return len+sign;
}


size_t my_longlong10_to_str_8bit(const CHARSET_INFO *cs
                                 MY_ATTRIBUTE((unused)),
                                 char *dst, size_t len, int radix,
                                 longlong val)
{
  char buffer[65];
  char *p, *e;
  long long_val;
  uint sign= 0;
  ulonglong uval = (ulonglong)val;
  
  if (radix < 0)
  {
    if (val < 0)
    {
      /* Avoid integer overflow in (-val) for LLONG_MIN (BUG#31799). */
      uval = (ulonglong)0 - uval;
      *dst++= '-';
      len--;
      sign= 1;
    }
  }
  
  e = p = &buffer[sizeof(buffer)-1];
  *p= 0;
  
  if (uval == 0)
  {
    *--p= '0';
    len= 1;
    goto cnv;
  }
  
  while (uval > (ulonglong) LONG_MAX)
  {
    ulonglong quo= uval/(uint) 10;
    uint rem= (uint) (uval- quo* (uint) 10);
    *--p = '0' + rem;
    uval= quo;
  }
  
  long_val= (long) uval;
  while (long_val != 0)
  {
    long quo= long_val/10;
    *--p = (char) ('0' + (long_val - quo*10));
    long_val= quo;
  }
  
  len= MY_MIN(len, (size_t) (e-p));
cnv:
  memcpy(dst, p, len);
  return len+sign;
}


/*
** Compare string against string with wildcard
**	0 if matched
**	-1 if not matched with wildcard
**	 1 if matched with wildcard
*/

#define likeconv(s,A) (uchar) (s)->sort_order[(uchar) (A)]
#define INC_PTR(cs,A,B) (A)++

static
int my_wildcmp_8bit_impl(const CHARSET_INFO *cs,
                         const char *str,const char *str_end,
                         const char *wildstr,const char *wildend,
                         int escape, int w_one, int w_many, int recurse_level)
{
  int result= -1;			/* Not found, using wildcards */

  if (my_string_stack_guard && my_string_stack_guard(recurse_level))
    return 1;
  while (wildstr != wildend)
  {
    while (*wildstr != w_many && *wildstr != w_one)
    {
      if (*wildstr == escape && wildstr+1 != wildend)
	wildstr++;

      if (str == str_end || likeconv(cs,*wildstr++) != likeconv(cs,*str++))
	return(1);				/* No match */
      if (wildstr == wildend)
	return(str != str_end);		/* Match if both are at end */
      result=1;					/* Found an anchor char     */
    }
    if (*wildstr == w_one)
    {
      do
      {
	if (str == str_end)			/* Skip one char if possible */
	  return(result);
	INC_PTR(cs,str,str_end);
      } while (++wildstr < wildend && *wildstr == w_one);
      if (wildstr == wildend)
	break;
    }
    if (*wildstr == w_many)
    {						/* Found w_many */
      uchar cmp;
      
      wildstr++;
      /* Remove any '%' and '_' from the wild search string */
      for (; wildstr != wildend ; wildstr++)
      {
	if (*wildstr == w_many)
	  continue;
	if (*wildstr == w_one)
	{
	  if (str == str_end)
	    return(-1);
	  INC_PTR(cs,str,str_end);
	  continue;
	}
	break;					/* Not a wild character */
      }
      if (wildstr == wildend)
	return(0);				/* Ok if w_many is last */
      if (str == str_end)
	return(-1);
      
      if ((cmp= *wildstr) == escape && wildstr+1 != wildend)
	cmp= *++wildstr;

      INC_PTR(cs,wildstr,wildend);	/* This is compared trough cmp */
      cmp=likeconv(cs,cmp);
      do
      {
	while (str != str_end && (uchar) likeconv(cs,*str) != cmp)
	  str++;
	if (str++ == str_end) return(-1);
	{
	  int tmp=my_wildcmp_8bit_impl(cs,str,str_end,
                                       wildstr,wildend,escape,w_one,
                                       w_many, recurse_level + 1);
	  if (tmp <= 0)
	    return(tmp);
	}
      } while (str != str_end && wildstr[0] != w_many);
      return(-1);
    }
  }
  return(str != str_end ? 1 : 0);
}

int my_wildcmp_8bit(const CHARSET_INFO *cs,
                    const char *str,const char *str_end,
                    const char *wildstr,const char *wildend,
                    int escape, int w_one, int w_many)
{
  return my_wildcmp_8bit_impl(cs, str, str_end,
                              wildstr, wildend,
                              escape, w_one, w_many, 1);
}


/*
** Calculate min_str and max_str that ranges a LIKE string.
** Arguments:
** ptr		Pointer to LIKE string.
** ptr_length	Length of LIKE string.
** escape	Escape character in LIKE.  (Normally '\').
**		All escape characters should be removed from min_str and max_str
** res_length	Length of min_str and max_str.
** min_str	Smallest case sensitive string that ranges LIKE.
**		Should be space padded to res_length.
** max_str	Largest case sensitive string that ranges LIKE.
**		Normally padded with the biggest character sort value.
**
** The function should return 0 if ok and 1 if the LIKE string can't be
** optimized !
*/

my_bool my_like_range_simple(const CHARSET_INFO *cs,
			     const char *ptr, size_t ptr_length,
			     pbool escape, pbool w_one, pbool w_many,
			     size_t res_length,
			     char *min_str,char *max_str,
			     size_t *min_length, size_t *max_length)
{
  const char *end= ptr + ptr_length;
  char *min_org=min_str;
  char *min_end=min_str+res_length;
  size_t charlen= res_length / cs->mbmaxlen;

  for (; ptr != end && min_str != min_end && charlen > 0 ; ptr++, charlen--)
  {
    if (*ptr == escape && ptr+1 != end)
    {
      ptr++;					/* Skip escape */
      *min_str++= *max_str++ = *ptr;
      continue;
    }
    if (*ptr == w_one)				/* '_' in SQL */
    {
      *min_str++='\0';				/* This should be min char */
      *max_str++= (char) cs->max_sort_char;
      continue;
    }
    if (*ptr == w_many)				/* '%' in SQL */
    {
      /* Calculate length of keys */
      *min_length= ((cs->state & MY_CS_BINSORT) ?
                    (size_t) (min_str - min_org) :
                    res_length);
      *max_length= res_length;
      do
      {
	*min_str++= 0;
	*max_str++= (char) cs->max_sort_char;
      } while (min_str != min_end);
      return 0;
    }
    *min_str++= *max_str++ = *ptr;
  }

 *min_length= *max_length = (size_t) (min_str - min_org);
  while (min_str != min_end)
    *min_str++= *max_str++ = ' ';      /* Because if key compression */
  return 0;
}


size_t my_scan_8bit(const CHARSET_INFO *cs, const char *str, const char *end,
                    int sq)
{
  const char *str0= str;
  switch (sq)
  {
  case MY_SEQ_INTTAIL:
    if (*str == '.')
    {
      for(str++ ; str != end && *str == '0' ; str++);
      return (size_t) (str - str0);
    }
    return 0;

  case MY_SEQ_SPACES:
    for ( ; str < end ; str++)
    {
      if (!my_isspace(cs,*str))
        break;
    }
    return (size_t) (str - str0);
  default:
    return 0;
  }
}


void my_fill_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
		   char *s, size_t l, int fill)
{
  memset(s, fill, l);
}


size_t my_numchars_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
		      const char *b, const char *e)
{
  return (size_t) (e - b);
}


size_t my_numcells_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                        const char *b, const char *e)
{
  return (size_t) (e - b);
}


size_t my_charpos_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                       const char *b  MY_ATTRIBUTE((unused)),
                       const char *e  MY_ATTRIBUTE((unused)),
                       size_t pos)
{
  return pos;
}


size_t my_well_formed_len_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                               const char *start, const char *end,
                               size_t nchars, int *error)
{
  size_t nbytes= (size_t) (end-start);
  *error= 0;
  return MY_MIN(nbytes, nchars);
}


size_t my_lengthsp_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                        const char *ptr, size_t length)
{
  const char *end;
  end= (const char *) skip_trailing_space((const uchar *)ptr, length);
  return (size_t) (end-ptr);
}


uint my_instr_simple(const CHARSET_INFO *cs,
                     const char *b, size_t b_length, 
                     const char *s, size_t s_length,
                     my_match_t *match, uint nmatch)
{
  const uchar *str, *search, *end, *search_end;
  
  if (s_length <= b_length)
  {
    if (!s_length)
    {
      if (nmatch)
      {
        match->beg= 0;
        match->end= 0;
        match->mb_len= 0;
      }
      return 1;		/* Empty string is always found */
    }
    
    str= (const uchar*) b;
    search= (const uchar*) s;
    end= (const uchar*) b+b_length-s_length+1;
    search_end= (const uchar*) s + s_length;
    
skip:
    while (str != end)
    {
      if (cs->sort_order[*str++] == cs->sort_order[*search])
      {
	const uchar *i,*j;
	
	i= str; 
	j= search+1;
	
	while (j != search_end)
	  if (cs->sort_order[*i++] != cs->sort_order[*j++]) 
            goto skip;
        
	if (nmatch > 0)
	{
	  match[0].beg= 0;
	  match[0].end= (uint) (str- (const uchar*)b-1);
	  match[0].mb_len= match[0].end;
	  
	  if (nmatch > 1)
	  {
	    match[1].beg= match[0].end;
	    match[1].end= match[0].end + (uint)s_length;
	    match[1].mb_len= match[1].end-match[1].beg;
	  }
	}
	return 2;
      }
    }
  }
  return 0;
}

size_t my_well_formed_len_ascii(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                                const char *start, const char *end,
                                size_t nchars, int *error)
{
  /**
    @todo: Currently return warning on invalid character.
           Return error in future release.
  */
  const char* oldstart = start;
  *error= 0;
  while (start < end)
  {
    if ((*start & 0x80) != 0)
    {
      *error = 1;
      break;
    }
    start++;
  }
  return MY_MIN((size_t)(end - oldstart), nchars);
}

typedef struct
{
  int		nchars;
  MY_UNI_IDX	uidx;
} uni_idx;

#define PLANE_SIZE	0x100
#define PLANE_NUM	0x100
#define PLANE_NUMBER(x)	(((x)>>8) % PLANE_NUM)

static int pcmp(const void * f, const void * s)
{
  const uni_idx *F= (const uni_idx*) f;
  const uni_idx *S= (const uni_idx*) s;
  int res;

  if (!(res=((S->nchars)-(F->nchars))))
    res=((F->uidx.from)-(S->uidx.to));
  return res;
}

static my_bool
create_fromuni(CHARSET_INFO *cs,
               MY_CHARSET_LOADER *loader)
{
  uni_idx	idx[PLANE_NUM];
  int		i,n;
  MY_UNI_IDX	*tab_from_uni;

  /*
    Check that Unicode map is loaded.
    It can be not loaded when the collation is
    listed in Index.xml but not specified
    in the character set specific XML file.
  */
  if (!cs->tab_to_uni)
    return TRUE;
  
  /* Clear plane statistics */
  memset(idx, 0, sizeof(idx));
  
  /* Count number of characters in each plane */
  for (i=0; i< 0x100; i++)
  {
    uint16 wc=cs->tab_to_uni[i];
    int pl= PLANE_NUMBER(wc);
    
    if (wc || !i)
    {
      if (!idx[pl].nchars)
      {
        idx[pl].uidx.from=wc;
        idx[pl].uidx.to=wc;
      }else
      {
        idx[pl].uidx.from=wc<idx[pl].uidx.from?wc:idx[pl].uidx.from;
        idx[pl].uidx.to=wc>idx[pl].uidx.to?wc:idx[pl].uidx.to;
      }
      idx[pl].nchars++;
    }
  }
  
  /* Sort planes in descending order */
  qsort(&idx,PLANE_NUM,sizeof(uni_idx),&pcmp);

  for (i=0; i < PLANE_NUM; i++)
  {
    int ch,numchars;
    uchar *tab;

    /* Skip empty plane */
    if (!idx[i].nchars)
      break;

    numchars=idx[i].uidx.to-idx[i].uidx.from+1;
    if (!(idx[i].uidx.tab= tab= (uchar *)
                                (loader->once_alloc)
                                  (numchars * sizeof(*idx[i].uidx.tab))))
      return TRUE;

    memset(tab, 0, numchars*sizeof(*idx[i].uidx.tab));

    for (ch=1; ch < PLANE_SIZE; ch++)
    {
      uint16 wc=cs->tab_to_uni[ch];
      if (wc >= idx[i].uidx.from && wc <= idx[i].uidx.to && wc)
      {
        int ofs= wc - idx[i].uidx.from;
        /*
          Character sets like armscii8 may have two code points for
          one character. When converting from UNICODE back to
          armscii8, select the lowest one, which is in the ASCII
          range.
        */
        if (tab[ofs] == '\0')
          tab[ofs]= ch;
      }
    }
  }

  /* Allocate and fill reverse table for each plane */
  n=i;
  if (!(cs->tab_from_uni= tab_from_uni= (MY_UNI_IDX *)
                                        (loader->once_alloc)
                                          (sizeof(MY_UNI_IDX) * (n + 1))))
    return TRUE;

  for (i=0; i< n; i++)
    tab_from_uni[i]= idx[i].uidx;

  /* Set end-of-list marker */
  memset(&tab_from_uni[i], 0, sizeof(MY_UNI_IDX));
  return FALSE;
}

static my_bool
my_cset_init_8bit(CHARSET_INFO *cs, MY_CHARSET_LOADER *loader)
{
  cs->caseup_multiply= 1;
  cs->casedn_multiply= 1;
  cs->pad_char= ' ';
  return create_fromuni(cs, loader);
}

static void set_max_sort_char(CHARSET_INFO *cs)
{
  uchar max_char;
  uint  i;
  
  if (!cs->sort_order)
    return;
  
  max_char=cs->sort_order[(uchar) cs->max_sort_char];
  for (i= 0; i < 256; i++)
  {
    if ((uchar) cs->sort_order[i] > max_char)
    {
      max_char=(uchar) cs->sort_order[i];
      cs->max_sort_char= i;
    }
  }
}

static my_bool
my_coll_init_simple(CHARSET_INFO *cs,
                    MY_CHARSET_LOADER *loader MY_ATTRIBUTE((unused)))
{
  set_max_sort_char(cs);
  return FALSE;
}


longlong my_strtoll10_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                           const char *nptr, char **endptr, int *error)
{
  return my_strtoll10(nptr, endptr, error);
}


int my_mb_ctype_8bit(const CHARSET_INFO *cs, int *ctype,
                   const uchar *s, const uchar *e)
{
  if (s >= e)
  {
    *ctype= 0;
    return MY_CS_TOOSMALL;
  }
  *ctype= cs->ctype[*s + 1];
  return 1;
}


#define CUTOFF  (ULLONG_MAX / 10)
#define CUTLIM  (ULLONG_MAX % 10)
#define DIGITS_IN_ULONGLONG 20

static ulonglong d10[DIGITS_IN_ULONGLONG]=
{
  1,
  10,
  100,
  1000,
  10000,
  100000,
  1000000,
  10000000,
  100000000,
  1000000000,
  10000000000ULL,
  100000000000ULL,
  1000000000000ULL,
  10000000000000ULL,
  100000000000000ULL,
  1000000000000000ULL,
  10000000000000000ULL,
  100000000000000000ULL,
  1000000000000000000ULL,
  10000000000000000000ULL
};


/*

  Convert a string to unsigned long long integer value
  with rounding.
  
  SYNOPSYS
    my_strntoull10_8bit()
      cs              in      pointer to character set
      str             in      pointer to the string to be converted
      length          in      string length
      unsigned_flag   in      whether the number is unsigned
      endptr          out     pointer to the stop character
      error           out     returned error code

  DESCRIPTION
    This function takes the decimal representation of integer number
    from string str and converts it to an signed or unsigned
    long long integer value.
    Space characters and tab are ignored.
    A sign character might precede the digit characters.
    The number may have any number of pre-zero digits.
    The number may have decimal point and exponent.
    Rounding is always done in "away from zero" style:
      0.5  ->   1
     -0.5  ->  -1

    The function stops reading the string str after "length" bytes
    or at the first character that is not a part of correct number syntax:

    <signed numeric literal> ::=
      [ <sign> ] <exact numeric literal> [ E [ <sign> ] <unsigned integer> ]

    <exact numeric literal> ::=
                        <unsigned integer> [ <period> [ <unsigned integer> ] ]
                      | <period> <unsigned integer>
    <unsigned integer>   ::= <digit>...
     
  RETURN VALUES
    Value of string as a signed/unsigned longlong integer

    endptr cannot be NULL. The function will store the end pointer
    to the stop character here.

    The error parameter contains information how things went:
    0	     ok
    ERANGE   If the the value of the converted number is out of range
    In this case the return value is:
    - ULLONG_MAX if unsigned_flag and the number was too big
    - 0 if unsigned_flag and the number was negative
    - LLONG_MAX if no unsigned_flag and the number is too big
    - LLONG_MIN if no unsigned_flag and the number it too big negative
    
    EDOM If the string didn't contain any digits.
    In this case the return value is 0.
*/

ulonglong
my_strntoull10rnd_8bit(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                       const char *str, size_t length, int unsigned_flag,
                       char **endptr, int *error)
{
  const char *dot, *end9, *beg, *end= str + length;
  ulonglong ull;
  ulong ul;
  uchar ch;
  int shift= 0, digits= 0, negative, addon;

  /* Skip leading spaces and tabs */
  for ( ; str < end && (*str == ' ' || *str == '\t') ; str++);

  if (str >= end)
    goto ret_edom;

  if ((negative= (*str == '-')) || *str=='+') /* optional sign */
  {
    if (++str == end)
      goto ret_edom;
  }

  beg= str;
  end9= (str + 9) > end ? end : (str + 9);
  /* Accumulate small number into ulong, for performance purposes */
  for (ul= 0 ; str < end9 && (ch= (uchar) (*str - '0')) < 10; str++)
  {
    ul= ul * 10 + ch;
  }
  
  if (str >= end) /* Small number without dots and expanents */
  {
    *endptr= (char*) str;
    if (negative)
    {
      if (unsigned_flag)
      {
        *error= ul ? MY_ERRNO_ERANGE : 0;
        return 0;
      }
      else
      {
        *error= 0;
        return (ulonglong) (longlong) -(long) ul;
      }
    }
    else
    {
      *error=0;
      return (ulonglong) ul;
    }
  }
  
  digits= (int)(str - beg);

  /* Continue to accumulate into ulonglong */
  for (dot= NULL, ull= ul; str < end; str++)
  {
    if ((ch= (uchar) (*str - '0')) < 10)
    {
      if (ull < CUTOFF || (ull == CUTOFF && ch <= CUTLIM))
      {
        ull= ull * 10 + ch;
        digits++;
        continue;
      }
      /*
        Adding the next digit would overflow.
        Remember the next digit in "addon", for rounding.
        Scan all digits with an optional single dot.
      */
      if (ull == CUTOFF)
      {
        ull= ULLONG_MAX;
        addon= 1;
        str++;
      }
      else
        addon= (*str >= '5');
      if (!dot)
      {
        for ( ; str < end && (ch= (uchar) (*str - '0')) < 10; shift++, str++);
        if (str < end && *str == '.')
        {
          str++;
          for ( ; str < end && (ch= (uchar) (*str - '0')) < 10; str++);
        }
      }
      else
      {
        shift= (int)(dot - str);
        for ( ; str < end && (ch= (uchar) (*str - '0')) < 10; str++);
      }
      goto exp;
    }
    
    if (*str == '.')
    {
      if (dot)
      {
        /* The second dot character */
        addon= 0;
        goto exp;
      }
      else
      {
        dot= str + 1;
      }
      continue;
    }
    
    /* Unknown character, exit the loop */
    break; 
  }
  shift= dot ? (int)(dot - str) : 0; /* Right shift */
  addon= 0;

exp:    /* [ E [ <sign> ] <unsigned integer> ] */

  if (!digits)
  {
    str= beg;
    goto ret_edom;
  }
  
  if (str < end && (*str == 'e' || *str == 'E'))
  {
    str++;
    if (str < end)
    {
      int negative_exp, exponent;
      if ((negative_exp= (*str == '-')) || *str=='+')
      {
        if (++str == end)
          goto ret_sign;
      }
      for (exponent= 0 ;
           str < end && (ch= (uchar) (*str - '0')) < 10;
           str++)
      {
        exponent= exponent * 10 + ch;
      }
      shift+= negative_exp ? -exponent : exponent;
    }
  }
  
  if (shift == 0) /* No shift, check addon digit */
  {
    if (addon)
    {
      if (ull == ULLONG_MAX)
        goto ret_too_big;
      ull++;
    }
    goto ret_sign;
  }

  if (shift < 0) /* Right shift */
  {
    ulonglong d, r;
    
    if (-shift >= DIGITS_IN_ULONGLONG)
      goto ret_zero; /* Exponent is a big negative number, return 0 */
    
    d= d10[-shift];
    r= (ull % d) * 2;
    ull /= d;
    if (r >= d)
      ull++;
    goto ret_sign;
  }

  if (shift > DIGITS_IN_ULONGLONG) /* Huge left shift */
  {
    if (!ull)
      goto ret_sign;
    goto ret_too_big;
  }

  for ( ; shift > 0; shift--, ull*= 10) /* Left shift */
  {
    if (ull > CUTOFF)
      goto ret_too_big; /* Overflow, number too big */
  }

ret_sign:
  *endptr= (char*) str;

  if (!unsigned_flag)
  {
    if (negative)
    {
      if (ull > (ulonglong) LLONG_MIN)
      {
        *error= MY_ERRNO_ERANGE;
        return (ulonglong) LLONG_MIN;
      }
      *error= 0;
      return (ulonglong) -(longlong) ull;
    }
    else
    {
      if (ull > (ulonglong) LLONG_MAX)
      {
        *error= MY_ERRNO_ERANGE;
        return (ulonglong) LLONG_MAX;
      }
      *error= 0;
      return ull;
    }
  }

  /* Unsigned number */
  if (negative && ull)
  {
    *error= MY_ERRNO_ERANGE;
    return 0;
  }
  *error= 0;
  return ull;

ret_zero:
  *endptr= (char*) str;
  *error= 0;
  return 0;

ret_edom:
  *endptr= (char*) str;
  *error= MY_ERRNO_EDOM;
  return 0;
  
ret_too_big:
  *endptr= (char*) str;
  *error= MY_ERRNO_ERANGE;
  return unsigned_flag ?
         ULLONG_MAX :
         negative ? (ulonglong) LLONG_MIN : (ulonglong) LLONG_MAX;
}


/*
  Check if a constant can be propagated

  SYNOPSIS:
    my_propagate_simple()
    cs		Character set information
    str		String to convert to double
    length	Optional length for string.
    
  NOTES:
   Takes the string in the given charset and check
   if it can be safely propagated in the optimizer.
   
   create table t1 (
     s char(5) character set latin1 collate latin1_german2_ci);
   insert into t1 values (0xf6); -- o-umlaut
   select * from t1 where length(s)=1 and s='oe';

   The above query should return one row.
   We cannot convert this query into:
   select * from t1 where length('oe')=1 and s='oe';
   
   Currently we don't check the constant itself,
   and decide not to propagate a constant
   just if the collation itself allows tricky things
   like expansions and contractions. In the future
   we can write a more sophisticated functions to
   check the constants. For example, 'oa' can always
   be safety propagated in German2 because unlike 
   'oe' it does not have any special meaning.

  RETURN
    1 if constant can be safely propagated
    0 if it is not safe to propagate the constant
*/



my_bool my_propagate_simple(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                            const uchar *str MY_ATTRIBUTE((unused)),
                            size_t length MY_ATTRIBUTE((unused)))
{
  return 1;
}


my_bool my_propagate_complex(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
                             const uchar *str MY_ATTRIBUTE((unused)),
                             size_t length MY_ATTRIBUTE((unused)))
{
  return 0;
}


/*
  Normalize strxfrm flags

  SYNOPSIS:
    my_strxfrm_flag_normalize()
    flags    - non-normalized flags
    nlevels  - number of levels
    
  NOTES:
    If levels are omitted, then 1-maximum is assumed.
    If any level number is greater than the maximum,
    it is treated as the maximum.

  RETURN
    normalized flags
*/

uint my_strxfrm_flag_normalize(uint flags, uint maximum)
{
  DBUG_ASSERT(maximum >= 1 && maximum <= MY_STRXFRM_NLEVELS);
  
  /* If levels are omitted, then 1-maximum is assumed*/
  if (!(flags & MY_STRXFRM_LEVEL_ALL))
  {
    static uint def_level_flags[]= {0, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F };
    uint flag_pad= flags &
                   (MY_STRXFRM_PAD_WITH_SPACE | MY_STRXFRM_PAD_TO_MAXLEN);
    flags= def_level_flags[maximum] | flag_pad;
  }
  else
  {
    uint i;
    uint flag_lev= flags & MY_STRXFRM_LEVEL_ALL;
    uint flag_dsc= (flags >> MY_STRXFRM_DESC_SHIFT) & MY_STRXFRM_LEVEL_ALL;
    uint flag_rev= (flags >> MY_STRXFRM_REVERSE_SHIFT) & MY_STRXFRM_LEVEL_ALL;
    uint flag_pad= flags &
                   (MY_STRXFRM_PAD_WITH_SPACE | MY_STRXFRM_PAD_TO_MAXLEN);

    /*
      If any level number is greater than the maximum,
      it is treated as the maximum.
    */
    for (maximum--, flags= 0, i= 0; i < MY_STRXFRM_NLEVELS; i++)
    {
      uint src_bit= 1 << i;
      if (flag_lev & src_bit)
      {
        uint dst_bit= 1 << MY_MIN(i, maximum);
        flags|= dst_bit;
        flags|= (flag_dsc & dst_bit) << MY_STRXFRM_DESC_SHIFT;
        flags|= (flag_rev & dst_bit) << MY_STRXFRM_REVERSE_SHIFT;
      }
    }
    flags|= flag_pad;
  }
  
  return flags;
}


/*
  Apply DESC and REVERSE collation rules.

  SYNOPSIS:
    my_strxfrm_desc_and_reverse()
    str      - pointer to string
    strend   - end of string
    flags    - flags
    level    - which level, starting from 0.
    
  NOTES:
    Apply DESC or REVERSE or both flags.
    
    If DESC flag is given, then the weights
    come out NOTed or negated for that level.
    
    If REVERSE flags is given, then the weights come out in
    reverse order for that level, that is, starting with
    the last character and ending with the first character.
    
    If nether DESC nor REVERSE flags are give,
    the string is not changed.
    
*/
void
my_strxfrm_desc_and_reverse(uchar *str, uchar *strend,
                            uint flags, uint level)
{
  if (flags & (MY_STRXFRM_DESC_LEVEL1 << level))
  {
    if (flags & (MY_STRXFRM_REVERSE_LEVEL1 << level))
    {
      for (strend--; str <= strend;)
      {
        uchar tmp= *str;
        *str++= ~*strend;
        *strend--= ~tmp;
      }
    }
    else
    {
      for (; str < strend; str++)
        *str= ~*str;
    }
  }
  else if (flags & (MY_STRXFRM_REVERSE_LEVEL1 << level))
  {
    for (strend--; str < strend;)
    {
      uchar tmp= *str;
      *str++= *strend;
      *strend--= tmp;
    }
  }
}


size_t
my_strxfrm_pad_desc_and_reverse(const CHARSET_INFO *cs,
                                uchar *str, uchar *frmend, uchar *strend,
                                uint nweights, uint flags, uint level)
{
  if (nweights && frmend < strend && (flags & MY_STRXFRM_PAD_WITH_SPACE))
  {
    uint fill_length= MY_MIN((uint) (strend - frmend), nweights * cs->mbminlen);
    cs->cset->fill(cs, (char*) frmend, fill_length, cs->pad_char);
    frmend+= fill_length;
  }
  my_strxfrm_desc_and_reverse(str, frmend, flags, level);
  if ((flags & MY_STRXFRM_PAD_TO_MAXLEN) && frmend < strend)
  {
    size_t fill_length= strend - frmend;
    cs->cset->fill(cs, (char*) frmend, fill_length, cs->pad_char);
    frmend= strend;
  }
  return frmend - str;
}


MY_CHARSET_HANDLER my_charset_8bit_handler=
{
    my_cset_init_8bit,
    NULL,			/* ismbchar      */
    my_mbcharlen_8bit,		/* mbcharlen     */
    my_numchars_8bit,
    my_charpos_8bit,
    my_well_formed_len_8bit,
    my_lengthsp_8bit,
    my_numcells_8bit,
    my_mb_wc_8bit,
    my_wc_mb_8bit,
    my_mb_ctype_8bit,
    my_caseup_str_8bit,
    my_casedn_str_8bit,
    my_caseup_8bit,
    my_casedn_8bit,
    my_snprintf_8bit,
    my_long10_to_str_8bit,
    my_longlong10_to_str_8bit,
    my_fill_8bit,
    my_strntol_8bit,
    my_strntoul_8bit,
    my_strntoll_8bit,
    my_strntoull_8bit,
    my_strntod_8bit,
    my_strtoll10_8bit,
    my_strntoull10rnd_8bit,
    my_scan_8bit
};

MY_CHARSET_HANDLER my_charset_ascii_handler=
{
    my_cset_init_8bit,
    NULL,                /* ismbchar      */
    my_mbcharlen_8bit,   /* mbcharlen     */
    my_numchars_8bit,
    my_charpos_8bit,
    my_well_formed_len_ascii,
    my_lengthsp_8bit,
    my_numcells_8bit,
    my_mb_wc_8bit,
    my_wc_mb_8bit,
    my_mb_ctype_8bit,
    my_caseup_str_8bit,
    my_casedn_str_8bit,
    my_caseup_8bit,
    my_casedn_8bit,
    my_snprintf_8bit,
    my_long10_to_str_8bit,
    my_longlong10_to_str_8bit,
    my_fill_8bit,
    my_strntol_8bit,
    my_strntoul_8bit,
    my_strntoll_8bit,
    my_strntoull_8bit,
    my_strntod_8bit,
    my_strtoll10_8bit,
    my_strntoull10rnd_8bit,
    my_scan_8bit
};

MY_COLLATION_HANDLER my_collation_8bit_simple_ci_handler =
{
    my_coll_init_simple,	/* init */
    my_strnncoll_simple,
    my_strnncollsp_simple,
    my_strnxfrm_simple,
    my_strnxfrmlen_simple,
    my_like_range_simple,
    my_wildcmp_8bit,
    my_strcasecmp_8bit,
    my_instr_simple,
    my_hash_sort_simple,
    my_propagate_simple
};