mariadb/strings/ctype-latin1.c
Alexander Barkov 6075f12c65 MDEV-31071 Refactor case folding data types in Unicode collations
This is a non-functional change. It changes the way how case folding data
and weight data (for simple Unicode collations) are stored:

- Removing data types MY_UNICASE_CHARACTER, MY_UNICASE_INFO
- Using data types MY_CASEFOLD_CHARACTER, MY_CASEFOLD_INFO instead.

This patch changes simple Unicode collations in a similar way
how MDEV-30695 previously changed Asian collations.

No new MTR tests are needed. The underlying code is thoroughly
covered by a number of ctype_*_ws.test and ctype_*_casefold.test
files, which were added recently as a preparation
for this change.

Old and new Unicode data layout
-------------------------------

Case folding data is now stored in separate tables
consisting of MY_CASEFOLD_CHARACTER elements with two members:

    typedef struct casefold_info_char_t
    {
      uint32 toupper;
      uint32 tolower;
    } MY_CASEFOLD_CHARACTER;

while weight data (for simple non-UCA collations xxx_general_ci
and xxx_general_mysql500_ci) is stored in separate arrays of
uint16 elements.

Before this change case folding data and simple weight data were
stored together, in tables of the following elements with three members:

    typedef struct unicase_info_char_st
    {
      uint32 toupper;
      uint32 tolower;
      uint32 sort;          /* weights for simple collations */
    } MY_UNICASE_CHARACTER;

This data format was redundant, because weights (the "sort" member) were
needed only for these two simple Unicode collations:
- xxx_general_ci
- xxx_general_mysql500_ci

Adding case folding information for Unicode-14.0.0 using the old
format would waste memory without purpose.

Detailed changes
----------------
- Changing the underlying data types as described above

- Including unidata-dump.c into the sources.
  This program was earlier used to dump UnicodeData.txt
  (e.g. https://www.unicode.org/Public/14.0.0/ucd/UnicodeData.txt)
  into MySQL / MariaDB source files.
  It was originally written in 2002, but has not been distributed yet
  together with MySQL / MariaDB sources.

- Removing the old format Unicode data earlier dumped from UnicodeData.txt
  (versions 3.0.0 and 5.2.0) from ctype-utf8.c.
  Adding Unicode data in the new format into separate header files,
  to maintain the code easier:

    - ctype-unicode300-casefold.h
    - ctype-unicode300-casefold-tr.h
    - ctype-unicode300-general_ci.h
    - ctype-unicode300-general_mysql500_ci.h
    - ctype-unicode520-casefold.h

- Adding a new file ctype-unidata.c as an aggregator for
  the header files listed above.
2023-04-18 11:29:25 +04:00

839 lines
31 KiB
C

/* Copyright (c) 2000, 2003-2007 MySQL AB, 2009 Sun Microsystems, Inc.
Copyright (c) 2009-2011, Monty Program Ab
Use is subject to license terms.
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 02110-1335 USA */
#include "strings_def.h"
#include <m_ctype.h>
#include "ctype-simple.h"
const char charset_name_latin1[]= "latin1";
#define charset_name_latin1_length sizeof(charset_name_latin1)-1
static const uchar ctype_latin1[] = {
0,
32, 32, 32, 32, 32, 32, 32, 32, 32, 40, 40, 40, 40, 40, 32, 32,
32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32,
72, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
132,132,132,132,132,132,132,132,132,132, 16, 16, 16, 16, 16, 16,
16,129,129,129,129,129,129, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 16, 16, 16, 16, 16,
16,130,130,130,130,130,130, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 16, 16, 16, 16, 32,
16, 0, 16, 2, 16, 16, 16, 16, 16, 16, 1, 16, 1, 0, 1, 0,
0, 16, 16, 16, 16, 16, 16, 16, 16, 16, 2, 16, 2, 0, 2, 1,
72, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 16, 1, 1, 1, 1, 1, 1, 1, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 16, 2, 2, 2, 2, 2, 2, 2, 2
};
static const uchar to_lower_latin1[] = {
0, 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, 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, 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,
224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,
240,241,242,243,244,245,246,215,248,249,250,251,252,253,254,223,
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
};
static const uchar to_upper_latin1[] = {
0, 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, 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, 90,123,124,125,126,127,
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,
192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,
208,209,210,211,212,213,214,247,216,217,218,219,220,221,222,255
};
static const uchar sort_order_latin1[] = {
0, 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, 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, 90,123,124,125,126,127,
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,
65, 65, 65, 65, 92, 91, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79, 93,215,216, 85, 85, 85, 89, 89,222,223,
65, 65, 65, 65, 92, 91, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79, 93,247,216, 85, 85, 85, 89, 89,222,255
};
/*
WL#1494 notes:
We'll use cp1252 instead of iso-8859-1.
cp1252 contains printable characters in the range 0x80-0x9F.
In ISO 8859-1, these code points have no associated printable
characters. Therefore, by converting from CP1252 to ISO 8859-1,
one would lose the euro (for instance). Since most people are
unaware of the difference, and since we don't really want a
"Windows ANSI" to differ from a "Unix ANSI", we will:
- continue to pretend the latin1 character set is ISO 8859-1
- actually allow the storage of euro etc. so it's actually cp1252
Also we'll map these five undefined cp1252 character:
0x81, 0x8D, 0x8F, 0x90, 0x9D
into corresponding control characters:
U+0081, U+008D, U+008F, U+0090, U+009D.
like ISO-8859-1 does. Otherwise, loading "mysqldump"
output doesn't reproduce these undefined characters.
*/
static unsigned const short cs_to_uni[256]={
0x0000,0x0001,0x0002,0x0003,0x0004,0x0005,0x0006,0x0007,
0x0008,0x0009,0x000A,0x000B,0x000C,0x000D,0x000E,0x000F,
0x0010,0x0011,0x0012,0x0013,0x0014,0x0015,0x0016,0x0017,
0x0018,0x0019,0x001A,0x001B,0x001C,0x001D,0x001E,0x001F,
0x0020,0x0021,0x0022,0x0023,0x0024,0x0025,0x0026,0x0027,
0x0028,0x0029,0x002A,0x002B,0x002C,0x002D,0x002E,0x002F,
0x0030,0x0031,0x0032,0x0033,0x0034,0x0035,0x0036,0x0037,
0x0038,0x0039,0x003A,0x003B,0x003C,0x003D,0x003E,0x003F,
0x0040,0x0041,0x0042,0x0043,0x0044,0x0045,0x0046,0x0047,
0x0048,0x0049,0x004A,0x004B,0x004C,0x004D,0x004E,0x004F,
0x0050,0x0051,0x0052,0x0053,0x0054,0x0055,0x0056,0x0057,
0x0058,0x0059,0x005A,0x005B,0x005C,0x005D,0x005E,0x005F,
0x0060,0x0061,0x0062,0x0063,0x0064,0x0065,0x0066,0x0067,
0x0068,0x0069,0x006A,0x006B,0x006C,0x006D,0x006E,0x006F,
0x0070,0x0071,0x0072,0x0073,0x0074,0x0075,0x0076,0x0077,
0x0078,0x0079,0x007A,0x007B,0x007C,0x007D,0x007E,0x007F,
0x20AC,0x0081,0x201A,0x0192,0x201E,0x2026,0x2020,0x2021,
0x02C6,0x2030,0x0160,0x2039,0x0152,0x008D,0x017D,0x008F,
0x0090,0x2018,0x2019,0x201C,0x201D,0x2022,0x2013,0x2014,
0x02DC,0x2122,0x0161,0x203A,0x0153,0x009D,0x017E,0x0178,
0x00A0,0x00A1,0x00A2,0x00A3,0x00A4,0x00A5,0x00A6,0x00A7,
0x00A8,0x00A9,0x00AA,0x00AB,0x00AC,0x00AD,0x00AE,0x00AF,
0x00B0,0x00B1,0x00B2,0x00B3,0x00B4,0x00B5,0x00B6,0x00B7,
0x00B8,0x00B9,0x00BA,0x00BB,0x00BC,0x00BD,0x00BE,0x00BF,
0x00C0,0x00C1,0x00C2,0x00C3,0x00C4,0x00C5,0x00C6,0x00C7,
0x00C8,0x00C9,0x00CA,0x00CB,0x00CC,0x00CD,0x00CE,0x00CF,
0x00D0,0x00D1,0x00D2,0x00D3,0x00D4,0x00D5,0x00D6,0x00D7,
0x00D8,0x00D9,0x00DA,0x00DB,0x00DC,0x00DD,0x00DE,0x00DF,
0x00E0,0x00E1,0x00E2,0x00E3,0x00E4,0x00E5,0x00E6,0x00E7,
0x00E8,0x00E9,0x00EA,0x00EB,0x00EC,0x00ED,0x00EE,0x00EF,
0x00F0,0x00F1,0x00F2,0x00F3,0x00F4,0x00F5,0x00F6,0x00F7,
0x00F8,0x00F9,0x00FA,0x00FB,0x00FC,0x00FD,0x00FE,0x00FF
};
static const uchar pl00[256]={
0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
0x08,0x09,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,
0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,
0x18,0x19,0x1A,0x1B,0x1C,0x1D,0x1E,0x1F,
0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,
0x28,0x29,0x2A,0x2B,0x2C,0x2D,0x2E,0x2F,
0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,
0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F,
0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47,
0x48,0x49,0x4A,0x4B,0x4C,0x4D,0x4E,0x4F,
0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57,
0x58,0x59,0x5A,0x5B,0x5C,0x5D,0x5E,0x5F,
0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,
0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F,
0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,
0x78,0x79,0x7A,0x7B,0x7C,0x7D,0x7E,0x7F,
0x00,0x81,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x8D,0x00,0x8F,
0x90,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x9D,0x00,0x00,
0xA0,0xA1,0xA2,0xA3,0xA4,0xA5,0xA6,0xA7,
0xA8,0xA9,0xAA,0xAB,0xAC,0xAD,0xAE,0xAF,
0xB0,0xB1,0xB2,0xB3,0xB4,0xB5,0xB6,0xB7,
0xB8,0xB9,0xBA,0xBB,0xBC,0xBD,0xBE,0xBF,
0xC0,0xC1,0xC2,0xC3,0xC4,0xC5,0xC6,0xC7,
0xC8,0xC9,0xCA,0xCB,0xCC,0xCD,0xCE,0xCF,
0xD0,0xD1,0xD2,0xD3,0xD4,0xD5,0xD6,0xD7,
0xD8,0xD9,0xDA,0xDB,0xDC,0xDD,0xDE,0xDF,
0xE0,0xE1,0xE2,0xE3,0xE4,0xE5,0xE6,0xE7,
0xE8,0xE9,0xEA,0xEB,0xEC,0xED,0xEE,0xEF,
0xF0,0xF1,0xF2,0xF3,0xF4,0xF5,0xF6,0xF7,
0xF8,0xF9,0xFA,0xFB,0xFC,0xFD,0xFE,0xFF
};
static const uchar pl01[256]={
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x8C,0x9C,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x8A,0x9A,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x9F,0x00,0x00,0x00,0x00,0x8E,0x9E,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x83,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
};
static const uchar pl02[256]={
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x88,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x98,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
};
static const uchar pl20[256]={
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x96,0x97,0x00,0x00,0x00,
0x91,0x92,0x82,0x00,0x93,0x94,0x84,0x00,
0x86,0x87,0x95,0x00,0x00,0x00,0x85,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x89,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x8B,0x9B,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x80,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
};
static const uchar pl21[256]={
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x99,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
};
static const uchar *const uni_to_cs[256]={
pl00,pl01,pl02,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
pl20,pl21,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,
NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL
};
static
int my_mb_wc_latin1(CHARSET_INFO *cs __attribute__((unused)),
my_wc_t *wc,
const uchar *str,
const uchar *end __attribute__((unused)))
{
if (str >= end)
return MY_CS_TOOSMALL;
/*
There are no unassigned characters in latin1.
Every code point in latin1 is mapped to some Unicode code point.
We can always return 1, no needs to check the value of cs_to_uni[*str].
*/
*wc= cs_to_uni[*str];
DBUG_ASSERT(wc[0] || !str[0]);
return 1;
}
static
int my_wc_mb_latin1(CHARSET_INFO *cs __attribute__((unused)),
my_wc_t wc,
uchar *str,
uchar *end __attribute__((unused)))
{
const uchar *pl;
if (str >= end)
return MY_CS_TOOSMALL;
if (wc > 0xFFFF)
return MY_CS_ILUNI;
pl= uni_to_cs[wc >> 8];
str[0]= pl ? pl[wc & 0xFF] : '\0';
return (!str[0] && wc) ? MY_CS_ILUNI : 1;
}
static MY_CHARSET_HANDLER my_charset_handler=
{
NULL, /* init */
my_numchars_8bit,
my_charpos_8bit,
my_lengthsp_8bit,
my_numcells_8bit,
my_mb_wc_latin1,
my_wc_mb_latin1,
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_charlen_8bit,
my_well_formed_char_length_8bit,
my_copy_8bit,
my_wc_mb_bin, /* native_to_mb */
my_wc_to_printable_generic,
my_casefold_multiply_1,
my_casefold_multiply_1
};
struct charset_info_st my_charset_latin1=
{
8,0,0, /* number */
MY_CS_COMPILED | MY_CS_PRIMARY, /* state */
{ charset_name_latin1, charset_name_latin1_length }, /* cs_name */
{ STRING_WITH_LEN("latin1_swedish_ci") }, /* name */
"", /* comment */
NULL, /* tailoring */
ctype_latin1,
to_lower_latin1,
to_upper_latin1,
sort_order_latin1,
NULL, /* uca */
cs_to_uni, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* casefold */
NULL, /* state_map */
NULL, /* ident_map */
1, /* strxfrm_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
255, /* max_sort_char */
' ', /* pad char */
0, /* escape_with_backslash_is_dangerous */
MY_CS_COLL_LEVELS_S1,
&my_charset_handler,
&my_collation_8bit_simple_ci_handler
};
struct charset_info_st my_charset_latin1_nopad=
{
MY_NOPAD_ID(8),0,0, /* number */
MY_CS_COMPILED | MY_CS_NOPAD, /* state */
{ charset_name_latin1, charset_name_latin1_length }, /* cs_name */
{ STRING_WITH_LEN("latin1_swedish_nopad_ci") }, /* name */
"", /* comment */
NULL, /* tailoring */
ctype_latin1,
to_lower_latin1,
to_upper_latin1,
sort_order_latin1,
NULL, /* uca */
cs_to_uni, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* casefold */
NULL, /* state_map */
NULL, /* ident_map */
1, /* strxfrm_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
255, /* max_sort_char */
' ', /* pad char */
0, /* escape_with_backslash_is_dangerous */
MY_CS_COLL_LEVELS_S1,
&my_charset_handler,
&my_collation_8bit_simple_nopad_ci_handler
};
/*
* This file is the latin1 character set with German sorting
*
* The modern sort order is used, where:
*
* 'ä' -> "ae"
* 'ö' -> "oe"
* 'ü' -> "ue"
* 'ß' -> "ss"
*/
/*
* This is a simple latin1 mapping table, which maps all accented
* characters to their non-accented equivalents. Note: in this
* table, 'ä' is mapped to 'A', 'ÿ' is mapped to 'Y', etc. - all
* accented characters except the following are treated the same way.
* Ü, ü, Ö, ö, Ä, ä
*/
static const uchar sort_order_latin1_de[] = {
0, 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, 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, 90,123,124,125,126,127,
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,
65, 65, 65, 65,196, 65, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79,214,215,216, 85, 85, 85,220, 89,222,223,
65, 65, 65, 65,196, 65, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79,214,247,216, 85, 85, 85,220, 89,222, 89
};
/*
same as sort_order_latin_de, but maps ALL accented chars to unaccented ones
*/
static const uchar combo1map[]={
0, 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, 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, 90,123,124,125,126,127,
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,
65, 65, 65, 65, 65, 65, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79, 79,215,216, 85, 85, 85, 85, 89,222, 83,
65, 65, 65, 65, 65, 65, 92, 67, 69, 69, 69, 69, 73, 73, 73, 73,
68, 78, 79, 79, 79, 79, 79,247,216, 85, 85, 85, 85, 89,222, 89
};
static const uchar combo2map[]={
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,69, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0,69, 0, 0, 0, 0, 0,69, 0, 0,83, 0, 0, 0, 0,69, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,69, 0, 0, 0, 0, 0,69, 0, 0, 0, 0
};
/*
Some notes about the following comparison rules:
By definition, my_strnncoll_latin_de must works exactly as if had called
my_strnxfrm_latin_de() on both strings and compared the result strings.
This means that:
Ä must also matches ÁE and Aè, because my_strxn_frm_latin_de() will convert
both to AE.
The other option would be to not do any accent removal in
sort_order_latin_de[] at all
*/
static int my_strnncoll_latin1_de(CHARSET_INFO *cs __attribute__((unused)),
const uchar *a, size_t a_length,
const uchar *b, size_t b_length,
my_bool b_is_prefix)
{
const uchar *a_end= a + a_length;
const uchar *b_end= b + b_length;
uchar a_char, a_extend= 0, b_char, b_extend= 0;
while ((a < a_end || a_extend) && (b < b_end || b_extend))
{
if (a_extend)
{
a_char=a_extend; a_extend=0;
}
else
{
a_extend=combo2map[*a];
a_char=combo1map[*a++];
}
if (b_extend)
{
b_char=b_extend; b_extend=0;
}
else
{
b_extend=combo2map[*b];
b_char=combo1map[*b++];
}
if (a_char != b_char)
return (int) a_char - (int) b_char;
}
/*
A simple test of string lengths won't work -- we test to see
which string ran out first
*/
return ((a < a_end || a_extend) ? (b_is_prefix ? 0 : 1) :
(b < b_end || b_extend) ? -1 : 0);
}
static int my_strnncollsp_latin1_de(CHARSET_INFO *cs __attribute__((unused)),
const uchar *a, size_t a_length,
const uchar *b, size_t b_length)
{
const uchar *a_end= a + a_length, *b_end= b + b_length;
uchar a_char, a_extend= 0, b_char, b_extend= 0;
while ((a < a_end || a_extend) && (b < b_end || b_extend))
{
if (a_extend)
{
a_char=a_extend;
a_extend= 0;
}
else
{
a_extend= combo2map[*a];
a_char= combo1map[*a++];
}
if (b_extend)
{
b_char= b_extend;
b_extend= 0;
}
else
{
b_extend= combo2map[*b];
b_char= combo1map[*b++];
}
if (a_char != b_char)
return (int) a_char - (int) b_char;
}
/* Check if double character last */
if (a_extend)
return 1;
if (b_extend)
return -1;
if (a < a_end)
return my_strnncollsp_padspace_bin(a, a_end - a);
if (b < b_end)
return -my_strnncollsp_padspace_bin(b, b_end - b);
return 0;
}
static size_t
my_strnxfrm_latin1_de(CHARSET_INFO *cs,
uchar *dst, size_t dstlen, uint nweights,
const uchar* src, size_t srclen, uint flags)
{
uchar *de= dst + dstlen;
const uchar *se= src + srclen;
uchar *d0= dst;
for ( ; src < se && dst < de && nweights; src++, nweights--)
{
uchar chr= combo1map[*src];
*dst++= chr;
if ((chr= combo2map[*src]) && dst < de && nweights > 1)
{
*dst++= chr;
nweights--;
}
}
return my_strxfrm_pad_desc_and_reverse(cs, d0, dst, de, nweights, flags, 0);
}
void my_hash_sort_latin1_de(CHARSET_INFO *cs __attribute__((unused)),
const uchar *key, size_t len,
ulong *nr1, ulong *nr2)
{
const uchar *end;
register ulong m1= *nr1, m2= *nr2;
/*
Remove end space. We have to do this to be able to compare
'AE' and 'Ä' as identical
*/
end= skip_trailing_space(key, len);
for (; key < end ; key++)
{
uint X= (uint) combo1map[(uint) *key];
MY_HASH_ADD(m1, m2, X);
if ((X= combo2map[*key]))
{
MY_HASH_ADD(m1, m2, X);
}
}
*nr1= m1;
*nr2= m2;
}
static MY_COLLATION_HANDLER my_collation_german2_ci_handler=
{
NULL, /* init */
my_strnncoll_latin1_de,
my_strnncollsp_latin1_de,
my_strnncollsp_nchars_generic_8bit,
my_strnxfrm_latin1_de,
my_strnxfrmlen_simple,
my_like_range_simple,
my_wildcmp_8bit,
my_strcasecmp_8bit,
my_instr_simple,
my_hash_sort_latin1_de,
my_propagate_complex,
my_min_str_8bit_simple,
my_max_str_8bit_simple,
my_ci_get_id_generic,
my_ci_get_collation_name_generic
};
struct charset_info_st my_charset_latin1_german2_ci=
{
31,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_NON1TO1, /* state */
{ charset_name_latin1, charset_name_latin1_length}, /* cs_name */
{ STRING_WITH_LEN("latin1_german2_ci") }, /* name */
"", /* comment */
NULL, /* tailoring */
ctype_latin1,
to_lower_latin1,
to_upper_latin1,
sort_order_latin1_de,
NULL, /* uca */
cs_to_uni, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* casefold */
NULL, /* state_map */
NULL, /* ident_map */
2, /* strxfrm_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
247, /* max_sort_char */
' ', /* pad char */
0, /* escape_with_backslash_is_dangerous */
MY_CS_COLL_LEVELS_S1,
&my_charset_handler,
&my_collation_german2_ci_handler
};
struct charset_info_st my_charset_latin1_bin=
{
47,0,0, /* number */
MY_CS_COMPILED|MY_CS_BINSORT, /* state */
{ charset_name_latin1, charset_name_latin1_length}, /* cs_name */
{ STRING_WITH_LEN("latin1_bin") }, /* name */
"", /* comment */
NULL, /* tailoring */
ctype_latin1,
to_lower_latin1,
to_upper_latin1,
NULL, /* sort_order */
NULL, /* uca */
cs_to_uni, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* casefold */
NULL, /* state_map */
NULL, /* ident_map */
1, /* strxfrm_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
255, /* max_sort_char */
' ', /* pad char */
0, /* escape_with_backslash_is_dangerous */
MY_CS_COLL_LEVELS_S1,
&my_charset_handler,
&my_collation_8bit_bin_handler
};
struct charset_info_st my_charset_latin1_nopad_bin=
{
MY_NOPAD_ID(47),0,0, /* number */
MY_CS_COMPILED|MY_CS_BINSORT|MY_CS_NOPAD,/* state */
{ charset_name_latin1, charset_name_latin1_length}, /* cs_name */
{ STRING_WITH_LEN("latin1_nopad_bin") }, /* name */
"", /* comment */
NULL, /* tailoring */
ctype_latin1,
to_lower_latin1,
to_upper_latin1,
NULL, /* sort_order */
NULL, /* uca */
cs_to_uni, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* casefold */
NULL, /* state_map */
NULL, /* ident_map */
1, /* strxfrm_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
255, /* max_sort_char */
' ', /* pad char */
0, /* escape_with_backslash_is_dangerous */
MY_CS_COLL_LEVELS_S1,
&my_charset_handler,
&my_collation_8bit_nopad_bin_handler
};