mirror/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-01-15 19:42:28 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions
mariadb/strings/ctype-uca1400.h

254 lines
7.9 KiB
C
Raw Normal View History

MDEV-27009 Add UCA-14.0.0 collations - Adding implicit weight handling for Unicode-14.0.0 1. Adding separate functions for different Unicode versions - my_uca_520_implicit_weight_primary() It calculates implicit weights according to the old algorithm that we used to dump Unicode-5.2.0 weights. - my_uca_1400_implicit_weight_primary() It calculates implicit weights according to https://unicode.org/reports/tr10/#Values_For_Base_Table as of November 2021, Unicode version 14.0.0. 2. Adding the "@version" line recognition when dumping allkeys.txt. Implicit weights are dumped according to @version. 3. Dumping the scanned version as a "#define" 4. Removing dumping MY_UCA_NPAGES, MY_UCA_NCHARS, MY_UCA_CMASK, MY_UCA_PSHIFT, as they are defined in ctype-uca.c. Removing dumping of "main()", it's not needed. The intent is to generate an *.h file which can be put directly to the MariaDB source tree. 5. Adding a structure MY_DUCET. It now contains weights for single characters and version related members. Later we'll add contractions and logical positions in here.
2021-11-24 12:11:49 +01:00
#ifndef CTYPE_UCA_1400_H
#define CTYPE_UCA_1400_H
/* Copyright (c) 2021, MariaDB
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public
License as published by the Free Software Foundation; version 2
of the License.
This library 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with this library; if not, write to the Free
Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
MA 02110-1335 USA */
/*
17000..187FF; Tangut [6144]
18800..18AFF; Tangut Components [768]
18D00..18D7F; Tangut Supplement [128]
*/
static inline my_bool
my_uca_1400_is_assigned_tangut(my_wc_t code)
{
return (code >= 0x17000 && code <= 0x187FF) ||
(code >= 0x18800 && code <= 0x18AFF) ||
(code >= 0x18D00 && code <= 0x18D7F);
}
static inline MY_UCA_IMPLICIT_WEIGHT
my_uca_1400_implicit_weight_primary_tangut(my_wc_t code)
{
MY_UCA_IMPLICIT_WEIGHT res;
res.weight[0]= 0xFB00;
res.weight[1]= (uint16) (code - 0x17000) | 0x8000;
return res;
}
/*
1B170..1B2FF; Nushu [400]
*/
static inline my_bool
my_uca_1400_is_assigned_nushu(my_wc_t code)
{
return code >= 0x1B170 && code <= 0x1B2FF;
}
static inline MY_UCA_IMPLICIT_WEIGHT
my_uca_1400_implicit_weight_primary_nushu(my_wc_t code)
{
MY_UCA_IMPLICIT_WEIGHT res;
res.weight[0]= 0xFB01;
res.weight[1]= (uint16) (code - 0x1B170) | 0x8000;
return res;
}
/*
18B00..18CFF; Khitan Small Script [512]
*/
static inline my_bool
my_uca_1400_is_assigned_khitan_small_script(my_wc_t code)
{
return code >= 0x18B00 && code <= 0x18CFF;
}
static inline MY_UCA_IMPLICIT_WEIGHT
my_uca_1400_implicit_weight_primary_khitan(my_wc_t code)
{
MY_UCA_IMPLICIT_WEIGHT res;
res.weight[0]= 0xFB02;
res.weight[1]= (uint16) (code - 0x18B00) | 0x8000;
return res;
}
/*
Unified_Ideograph=True AND
((Block=CJK_Unified_Ideograph) OR (Block=CJK_Compatibility_Ideographs))
https://www.unicode.org/Public/14.0.0/ucd/Blocks.txt
4E00..9FFF; CJK Unified Ideographs
F900..FAFF; CJK Compatibility Ideographs
https://www.unicode.org/Public/14.0.0/ucd/PropList.txt
4E00..9FFF ; Unified_Ideograph # Lo [20992] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FFF
FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F
FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11
FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14
FA1F ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA1F
FA21 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA21
FA23..FA24 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
*/
static inline my_bool
my_uca_1400_is_core_han_unified_ideograph(my_wc_t code)
{
return (code >= 0x4E00 && code <= 0x9FFF) ||
(code >= 0xFA0E && code <= 0xFA0F) ||
(code == 0xFA11) ||
(code >= 0xFA13 && code <= 0xFA14) ||
(code == 0xFA1F) ||
(code == 0xFA21) ||
(code >= 0xFA23 && code <= 0xFA24) ||
(code >= 0xFA27 && code <= 0xFA29);
}
/*
(Unified_Ideograph=True AND NOT
((Block=CJK_Unified_Ideograph) OR (Block=CJK_Compatibility_Ideographs))
https://www.unicode.org/Public/14.0.0/ucd/Blocks.txt
3400..4DBF; CJK Unified Ideographs Extension A
20000..2A6DF; CJK Unified Ideographs Extension B
2A700..2B73F; CJK Unified Ideographs Extension C
2B740..2B81F; CJK Unified Ideographs Extension D
2B820..2CEAF; CJK Unified Ideographs Extension E
2CEB0..2EBEF; CJK Unified Ideographs Extension F
30000..3134F; CJK Unified Ideographs Extension G
https://www.unicode.org/Public/14.0.0/ucd/PropList.txt
3400..4DBF ; Unified_Ideograph # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF
20000..2A6DF ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
2A700..2B738 ; Unified_Ideograph # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
30000..3134A ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
*/
static inline my_bool
my_uca_1400_is_other_han_unified_ideograph(my_wc_t code)
{
return (code >= 0x3400 && code <= 0x4DBF) ||
(code >= 0x20000 && code <= 0x2A6DF) ||
(code >= 0x2A700 && code <= 0x2B738) ||
(code >= 0x2B740 && code <= 0x2B81D) ||
(code >= 0x2B820 && code <= 0x2CEA1) ||
(code >= 0x2CEB0 && code <= 0x2EBE0) ||
(code >= 0x30000 && code <= 0x3134A);
}
/*
See section "Computing Implicit Weights" in
https://unicode.org/reports/tr10/#Values_For_Base_Table
*/
static inline MY_UCA_IMPLICIT_WEIGHT
my_uca_1400_implicit_weight_primary(my_wc_t code)
{
if (my_uca_1400_is_core_han_unified_ideograph(code))
return my_uca_implicit_weight_primary_default(0xFB40, code);
if (my_uca_1400_is_other_han_unified_ideograph(code))
return my_uca_implicit_weight_primary_default(0xFB80, code);
if (my_uca_1400_is_assigned_tangut(code))
return my_uca_1400_implicit_weight_primary_tangut(code);
if (my_uca_1400_is_assigned_nushu(code))
return my_uca_1400_implicit_weight_primary_nushu(code);
if (my_uca_1400_is_assigned_khitan_small_script(code))
return my_uca_1400_implicit_weight_primary_khitan(code);
/* Unassigned - Any other code point */
return my_uca_implicit_weight_primary_default(0xFBC0, code);
}
MDEV-27009 Add UCA-14.0.0 collations - Added one neutral and 22 tailored (language specific) collations based on Unicode Collation Algorithm version 14.0.0. Collations were added for Unicode character sets utf8mb3, utf8mb4, ucs2, utf16, utf32. Every tailoring was added with four accent and case sensitivity flag combinations, e.g: * utf8mb4_uca1400_swedish_as_cs * utf8mb4_uca1400_swedish_as_ci * utf8mb4_uca1400_swedish_ai_cs * utf8mb4_uca1400_swedish_ai_ci and their _nopad_ variants: * utf8mb4_uca1400_swedish_nopad_as_cs * utf8mb4_uca1400_swedish_nopad_as_ci * utf8mb4_uca1400_swedish_nopad_ai_cs * utf8mb4_uca1400_swedish_nopad_ai_ci - Introducing a conception of contextually typed named collations: CREATE DATABASE db1 CHARACTER SET utf8mb4; CREATE TABLE db1.t1 (a CHAR(10) COLLATE uca1400_as_ci); The idea is that there is no a need to specify the character set prefix in the new collation names. It's enough to type just the suffix "uca1400_as_ci". The character set is taken from the context. In the above example script the context character set is utf8mb4. So the CREATE TABLE will make a column with the collation utf8mb4_uca1400_as_ci. Short collations names can be used in any parts of the SQL syntax where the COLLATE clause is understood. - New collations are displayed only one time (without character set combinations) by these statements: SELECT * FROM INFORMATION_SCHEMA.COLLATIONS; SHOW COLLATION; For example, all these collations: - utf8mb3_uca1400_swedish_as_ci - utf8mb4_uca1400_swedish_as_ci - ucs2_uca1400_swedish_as_ci - utf16_uca1400_swedish_as_ci - utf32_uca1400_swedish_as_ci have just one entry in INFORMATION_SCHEMA.COLLATIONS and SHOW COLLATION, with COLLATION_NAME equal to "uca1400_swedish_as_ci", which is the suffix without the character set name: SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.COLLATIONS WHERE COLLATION_NAME LIKE '%uca1400_swedish_as_ci'; +-----------------------+ | COLLATION_NAME | +-----------------------+ | uca1400_swedish_as_ci | +-----------------------+ Note, the behaviour of old collations did not change. Non-unicode collations (e.g. latin1_swedish_ci) and old UCA-4.0.0 collations (e.g. utf8mb4_unicode_ci) are still displayed with the character set prefix, as before. - The structure of the table INFORMATION_SCHEMA.COLLATIONS was changed. The NOT NULL constraint was removed from these columns: - CHARACTER_SET_NAME - ID - IS_DEFAULT and from the corresponding columns in SHOW COLLATION. For example: SELECT COLLATION_NAME, CHARACTER_SET_NAME, ID, IS_DEFAULT FROM INFORMATION_SCHEMA.COLLATIONS WHERE COLLATION_NAME LIKE '%uca1400_swedish_as_ci'; +-----------------------+--------------------+------+------------+ | COLLATION_NAME | CHARACTER_SET_NAME | ID | IS_DEFAULT | +-----------------------+--------------------+------+------------+ | uca1400_swedish_as_ci | NULL | NULL | NULL | +-----------------------+--------------------+------+------------+ The NULL value in these columns now means that the collation is applicable to multiple character sets. The behavioir of old collations did not change. Make sure your client programs can handle NULL values in these columns. - The structure of the table INFORMATION_SCHEMA.COLLATION_CHARACTER_SET_APPLICABILITY was changed. Three new NOT NULL columns were added: - FULL_COLLATION_NAME - ID - IS_DEFAULT New collations have multiple entries in COLLATION_CHARACTER_SET_APPLICABILITY. The column COLLATION_NAME contains the collation name without the character set prefix. The column FULL_COLLATION_NAME contains the collation name with the character set prefix. Old collations have full collation name in both FULL_COLLATION_NAME and COLLATION_NAME. SELECT COLLATION_NAME, FULL_COLLATION_NAME, CHARACTER_SET_NAME, ID, IS_DEFAULT FROM INFORMATION_SCHEMA.COLLATION_CHARACTER_SET_APPLICABILITY WHERE FULL_COLLATION_NAME RLIKE '^(utf8mb4|latin1).*swedish.*ci$'; +-----------------------------+-------------------------------------+--------------------+------+------------+ | COLLATION_NAME | FULL_COLLATION_NAME | CHARACTER_SET_NAME | ID | IS_DEFAULT | +-----------------------------+-------------------------------------+--------------------+------+------------+ | latin1_swedish_ci | latin1_swedish_ci | latin1 | 8 | Yes | | latin1_swedish_nopad_ci | latin1_swedish_nopad_ci | latin1 | 1032 | | | utf8mb4_swedish_ci | utf8mb4_swedish_ci | utf8mb4 | 232 | | | uca1400_swedish_ai_ci | utf8mb4_uca1400_swedish_ai_ci | utf8mb4 | 2368 | | | uca1400_swedish_as_ci | utf8mb4_uca1400_swedish_as_ci | utf8mb4 | 2370 | | | uca1400_swedish_nopad_ai_ci | utf8mb4_uca1400_swedish_nopad_ai_ci | utf8mb4 | 2372 | | | uca1400_swedish_nopad_as_ci | utf8mb4_uca1400_swedish_nopad_as_ci | utf8mb4 | 2374 | | +-----------------------------+-------------------------------------+--------------------+------+------------+ - Other INFORMATION_SCHEMA queries: SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.COLUMNS; SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.PARAMETERS; SELECT TABLE_COLLATION FROM INFORMATION_SCHEMA.TABLES; SELECT DEFAULT_COLLATION_NAME FROM INFORMATION_SCHEMA.SCHEMATA; SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.ROUTINES; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.EVENTS; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.EVENTS; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.ROUTINES; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.ROUTINES; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.TRIGGERS; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.TRIGGERS; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.VIEWS; display full collation names, including character sets prefix, for all collations, including new collations. Corresponding SHOW commands also display full collation names in collation related columns: SHOW CREATE TABLE t1; SHOW CREATE DATABASE db1; SHOW TABLE STATUS; SHOW CREATE FUNCTION f1; SHOW CREATE PROCEDURE p1; SHOW CREATE EVENT ev1; SHOW CREATE TRIGGER tr1; SHOW CREATE VIEW; These INFORMATION_SCHEMA queries and SHOW statements may change in the future, to display show collation names.
2021-11-28 13:55:15 +01:00
#define MY_UCA1400_COLLATION_ID_POSSIBLE_MIN 2048
#define MY_UCA1400_COLLATION_ID_POSSIBLE_MAX 4095
static inline my_bool
my_collation_id_is_uca1400(uint id)
{
return (my_bool) (id >= MY_UCA1400_COLLATION_ID_POSSIBLE_MIN &&
id <= MY_UCA1400_COLLATION_ID_POSSIBLE_MAX);
}
/*
UCA1400 collation ID:
1000 0000 0000 0x800 2048
1111 1111 1111 0xFFF 4095
1ccc tttt tPST
c - charset ID (utf8mb3=0, utf8mb4=1, ucs2=2, utf16=3, utf32=4)
p - PAD/NO PAD
S - secondary level is enabled
T - tertiary level is enabled
*/
static inline my_cs_encoding_t
my_uca1400_collation_id_to_charset_id(uint id)
{
return (my_cs_encoding_t) ((id >> 8) & 0x07);
}
static inline uint
my_uca1400_collation_id_to_tailoring_id(uint id)
{
return (id >> 3) & 0x1F;
}
static inline my_bool
my_uca1400_collation_id_to_nopad_flag(uint id)
{
return (my_bool) ((id >> 2) & 0x01);
}
static inline my_bool
my_uca1400_collation_id_to_secondary_level_flag(uint id)
{
return (my_bool) ((id >> 1) & 0x01);
}
static inline my_bool
my_uca1400_collation_id_to_tertiary_level_flag(uint id)
{
return (my_bool) ((id >> 0) & 0x01);
}
uint
my_uca1400_make_builtin_collation_id(my_cs_encoding_t charset_id,
uint tailoring_id,
my_bool nopad,
my_bool secondary_level,
my_bool tertiary_level);
my_bool
my_uca1400_collation_definition_init(MY_CHARSET_LOADER *loader,
struct charset_info_st *dst,
uint collation_id);
#define MY_UCA1400_COLLATION_DEFINITION_COUNT 26
MDEV-20912 Add support for utf8mb4_0900_* collations in MariaDB Server This is done by mapping most of the existing MySQL unicode 0900 collations to MariadB 1400 unicode collations. The assumption is that 1400 is a super set of 0900 for all practical purposes. I also added a new function 'compare_collations()' and changed most code to use this instead of comparing character sets directly. This enables one to seamlessly mix-and-match the corresponding 0900 and 1400 sets. Field comparision and alter table treats the character sets as identical. All MySQL 8.0 0900 collations are supported except: - utf8mb4_ja_0900_as_cs - utf8mb4_ja_0900_as_cs_ks - utf8mb4_ru_0900_as_cs - utf8mb4_zh_0900_as_cs These do not have corresponding entries in the MariadB 01400 collations. Other things: - Added COMMENT colum to information_schema.collations. For utf8mb4_0900 colletions it contains the corresponding alias collation.
2024-12-15 14:57:53 +01:00
my_bool mysql_utf8mb4_0900_collation_definitions_add();
MDEV-27009 Add UCA-14.0.0 collations - Added one neutral and 22 tailored (language specific) collations based on Unicode Collation Algorithm version 14.0.0. Collations were added for Unicode character sets utf8mb3, utf8mb4, ucs2, utf16, utf32. Every tailoring was added with four accent and case sensitivity flag combinations, e.g: * utf8mb4_uca1400_swedish_as_cs * utf8mb4_uca1400_swedish_as_ci * utf8mb4_uca1400_swedish_ai_cs * utf8mb4_uca1400_swedish_ai_ci and their _nopad_ variants: * utf8mb4_uca1400_swedish_nopad_as_cs * utf8mb4_uca1400_swedish_nopad_as_ci * utf8mb4_uca1400_swedish_nopad_ai_cs * utf8mb4_uca1400_swedish_nopad_ai_ci - Introducing a conception of contextually typed named collations: CREATE DATABASE db1 CHARACTER SET utf8mb4; CREATE TABLE db1.t1 (a CHAR(10) COLLATE uca1400_as_ci); The idea is that there is no a need to specify the character set prefix in the new collation names. It's enough to type just the suffix "uca1400_as_ci". The character set is taken from the context. In the above example script the context character set is utf8mb4. So the CREATE TABLE will make a column with the collation utf8mb4_uca1400_as_ci. Short collations names can be used in any parts of the SQL syntax where the COLLATE clause is understood. - New collations are displayed only one time (without character set combinations) by these statements: SELECT * FROM INFORMATION_SCHEMA.COLLATIONS; SHOW COLLATION; For example, all these collations: - utf8mb3_uca1400_swedish_as_ci - utf8mb4_uca1400_swedish_as_ci - ucs2_uca1400_swedish_as_ci - utf16_uca1400_swedish_as_ci - utf32_uca1400_swedish_as_ci have just one entry in INFORMATION_SCHEMA.COLLATIONS and SHOW COLLATION, with COLLATION_NAME equal to "uca1400_swedish_as_ci", which is the suffix without the character set name: SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.COLLATIONS WHERE COLLATION_NAME LIKE '%uca1400_swedish_as_ci'; +-----------------------+ | COLLATION_NAME | +-----------------------+ | uca1400_swedish_as_ci | +-----------------------+ Note, the behaviour of old collations did not change. Non-unicode collations (e.g. latin1_swedish_ci) and old UCA-4.0.0 collations (e.g. utf8mb4_unicode_ci) are still displayed with the character set prefix, as before. - The structure of the table INFORMATION_SCHEMA.COLLATIONS was changed. The NOT NULL constraint was removed from these columns: - CHARACTER_SET_NAME - ID - IS_DEFAULT and from the corresponding columns in SHOW COLLATION. For example: SELECT COLLATION_NAME, CHARACTER_SET_NAME, ID, IS_DEFAULT FROM INFORMATION_SCHEMA.COLLATIONS WHERE COLLATION_NAME LIKE '%uca1400_swedish_as_ci'; +-----------------------+--------------------+------+------------+ | COLLATION_NAME | CHARACTER_SET_NAME | ID | IS_DEFAULT | +-----------------------+--------------------+------+------------+ | uca1400_swedish_as_ci | NULL | NULL | NULL | +-----------------------+--------------------+------+------------+ The NULL value in these columns now means that the collation is applicable to multiple character sets. The behavioir of old collations did not change. Make sure your client programs can handle NULL values in these columns. - The structure of the table INFORMATION_SCHEMA.COLLATION_CHARACTER_SET_APPLICABILITY was changed. Three new NOT NULL columns were added: - FULL_COLLATION_NAME - ID - IS_DEFAULT New collations have multiple entries in COLLATION_CHARACTER_SET_APPLICABILITY. The column COLLATION_NAME contains the collation name without the character set prefix. The column FULL_COLLATION_NAME contains the collation name with the character set prefix. Old collations have full collation name in both FULL_COLLATION_NAME and COLLATION_NAME. SELECT COLLATION_NAME, FULL_COLLATION_NAME, CHARACTER_SET_NAME, ID, IS_DEFAULT FROM INFORMATION_SCHEMA.COLLATION_CHARACTER_SET_APPLICABILITY WHERE FULL_COLLATION_NAME RLIKE '^(utf8mb4|latin1).*swedish.*ci$'; +-----------------------------+-------------------------------------+--------------------+------+------------+ | COLLATION_NAME | FULL_COLLATION_NAME | CHARACTER_SET_NAME | ID | IS_DEFAULT | +-----------------------------+-------------------------------------+--------------------+------+------------+ | latin1_swedish_ci | latin1_swedish_ci | latin1 | 8 | Yes | | latin1_swedish_nopad_ci | latin1_swedish_nopad_ci | latin1 | 1032 | | | utf8mb4_swedish_ci | utf8mb4_swedish_ci | utf8mb4 | 232 | | | uca1400_swedish_ai_ci | utf8mb4_uca1400_swedish_ai_ci | utf8mb4 | 2368 | | | uca1400_swedish_as_ci | utf8mb4_uca1400_swedish_as_ci | utf8mb4 | 2370 | | | uca1400_swedish_nopad_ai_ci | utf8mb4_uca1400_swedish_nopad_ai_ci | utf8mb4 | 2372 | | | uca1400_swedish_nopad_as_ci | utf8mb4_uca1400_swedish_nopad_as_ci | utf8mb4 | 2374 | | +-----------------------------+-------------------------------------+--------------------+------+------------+ - Other INFORMATION_SCHEMA queries: SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.COLUMNS; SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.PARAMETERS; SELECT TABLE_COLLATION FROM INFORMATION_SCHEMA.TABLES; SELECT DEFAULT_COLLATION_NAME FROM INFORMATION_SCHEMA.SCHEMATA; SELECT COLLATION_NAME FROM INFORMATION_SCHEMA.ROUTINES; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.EVENTS; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.EVENTS; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.ROUTINES; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.ROUTINES; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.TRIGGERS; SELECT DATABASE_COLLATION FROM INFORMATION_SCHEMA.TRIGGERS; SELECT COLLATION_CONNECTION FROM INFORMATION_SCHEMA.VIEWS; display full collation names, including character sets prefix, for all collations, including new collations. Corresponding SHOW commands also display full collation names in collation related columns: SHOW CREATE TABLE t1; SHOW CREATE DATABASE db1; SHOW TABLE STATUS; SHOW CREATE FUNCTION f1; SHOW CREATE PROCEDURE p1; SHOW CREATE EVENT ev1; SHOW CREATE TRIGGER tr1; SHOW CREATE VIEW; These INFORMATION_SCHEMA queries and SHOW statements may change in the future, to display show collation names.
2021-11-28 13:55:15 +01:00
MDEV-27009 Add UCA-14.0.0 collations - Adding implicit weight handling for Unicode-14.0.0 1. Adding separate functions for different Unicode versions - my_uca_520_implicit_weight_primary() It calculates implicit weights according to the old algorithm that we used to dump Unicode-5.2.0 weights. - my_uca_1400_implicit_weight_primary() It calculates implicit weights according to https://unicode.org/reports/tr10/#Values_For_Base_Table as of November 2021, Unicode version 14.0.0. 2. Adding the "@version" line recognition when dumping allkeys.txt. Implicit weights are dumped according to @version. 3. Dumping the scanned version as a "#define" 4. Removing dumping MY_UCA_NPAGES, MY_UCA_NCHARS, MY_UCA_CMASK, MY_UCA_PSHIFT, as they are defined in ctype-uca.c. Removing dumping of "main()", it's not needed. The intent is to generate an *.h file which can be put directly to the MariaDB source tree. 5. Adding a structure MY_DUCET. It now contains weights for single characters and version related members. Later we'll add contractions and logical positions in here.
2021-11-24 12:11:49 +01:00
#endif /* CTYPE_UCA_1400_H */
Reference in a new issue Copy permalink