2014-08-02 21:26:16 +02:00
|
|
|
# Copyright (c) 2006, 2014, Oracle and/or its affiliates
|
2006-12-31 02:29:11 +01:00
|
|
|
#
|
|
|
|
|
# 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
|
2019-05-11 20:29:06 +02:00
|
|
|
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1335 USA
|
2006-12-31 02:29:11 +01:00
|
|
|
|
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
|
|
|
INCLUDE_DIRECTORIES(
|
|
|
|
|
${CMAKE_SOURCE_DIR}/include
|
|
|
|
|
${CMAKE_BINARY_DIR}/strings
|
|
|
|
|
)
|
CMakeLists.txt (many), win/README, mysql_manifest.cmake, configure.js:
Additional changes for bug#29903
- Changed to do embedded build part as normal build, when
WITH_EMBEDDED_SERVER is set.
- Allow both normal and debug build with embedded.
- Build static embedded library by pointing out all source and compile
it all, i.e. not building libraries from libraries, not portable.
- Let embedded use generated files from the "sql" directory, added
dependencies to make sure built before embedded.
- Mark library "dbug" in TARGET_LINK_LIBRARIES() with "debug", so only
linked in when debug target is used.
- Removed change of target name with "mysqld${MYSQLD_EXE_SUFFIX}", as
others can't depend on it, not defined at configure time. Instead
set the output file name.
- Created work around for bug in CMake 2.4.6 and output names, to
set the "mysqld<suffix>.pdb" name to the same base name.
- Set the correct manifest "name" (patch by iggy)
CMakeLists.txt:
Changes for embedded and Windows
libmysql/CMakeLists.txt:
Changes for embedded and Windows
libmysqld/CMakeLists.txt:
Changes for embedded and Windows
libmysqld/examples/CMakeLists.txt:
Changes for embedded and Windows
mysys/CMakeLists.txt:
Changes for embedded and Windows
regex/CMakeLists.txt:
Changes for embedded and Windows
server-tools/instance-manager/CMakeLists.txt:
Changes for embedded and Windows
sql/CMakeLists.txt:
Changes for embedded and Windows
storage/archive/CMakeLists.txt:
Changes for embedded and Windows
storage/blackhole/CMakeLists.txt:
Changes for embedded and Windows
storage/csv/CMakeLists.txt:
Changes for embedded and Windows
storage/example/CMakeLists.txt:
Changes for embedded and Windows
storage/federated/CMakeLists.txt:
Changes for embedded and Windows
storage/heap/CMakeLists.txt:
Changes for embedded and Windows
storage/innobase/CMakeLists.txt:
Changes for embedded and Windows
storage/myisam/CMakeLists.txt:
Changes for embedded and Windows
storage/myisammrg/CMakeLists.txt:
Changes for embedded and Windows
strings/CMakeLists.txt:
Changes for embedded and Windows
vio/CMakeLists.txt:
Changes for embedded and Windows
win/README:
Changes for embedded and Windows
win/configure.js:
Changes for embedded and Windows
win/mysql_manifest.cmake:
Changes for embedded and Windows
2007-08-06 23:16:01 +02:00
|
|
|
|
2010-07-25 19:30:18 +02:00
|
|
|
SET(STRINGS_SOURCES bchange.c bmove_upp.c ctype-big5.c ctype-bin.c ctype-cp932.c
|
2006-01-31 14:52:16 +01:00
|
|
|
ctype-czech.c ctype-euc_kr.c ctype-eucjpms.c ctype-extra.c ctype-gb2312.c ctype-gbk.c
|
|
|
|
|
ctype-latin1.c ctype-mb.c ctype-simple.c ctype-sjis.c ctype-tis620.c ctype-uca.c
|
2009-12-22 17:23:13 +01:00
|
|
|
ctype-ucs2.c ctype-ujis.c ctype-utf8.c ctype-win1250ch.c ctype.c decimal.c dtoa.c int2str.c
|
2023-02-24 16:22:32 +01:00
|
|
|
ctype-unidata.c
|
2010-07-23 22:17:14 +02:00
|
|
|
is_prefix.c llstr.c longlong2str.c my_strtoll10.c my_vsnprintf.c
|
2017-12-18 14:15:48 +01:00
|
|
|
str2int.c strcend.c strend.c strfill.c strmake.c strmov.c strnmov.c
|
2010-07-25 19:30:18 +02:00
|
|
|
strxmov.c strxnmov.c xml.c
|
2010-11-25 18:17:28 +01:00
|
|
|
strmov_overlapp.c
|
2021-07-02 07:59:56 +02:00
|
|
|
my_strchr.c strcont.c strappend.c json_lib.c json_normalize.c)
|
2010-01-14 19:42:28 +01:00
|
|
|
|
2010-07-25 19:30:18 +02:00
|
|
|
IF(NOT HAVE_STRNLEN)
|
2015-06-14 15:51:34 +02:00
|
|
|
# OSX below 10.7 did not have strnlen
|
2010-07-25 19:30:18 +02:00
|
|
|
SET(STRINGS_SOURCES ${STRINGS_SOURCES} strnlen.c)
|
|
|
|
|
ENDIF()
|
2010-01-14 19:42:28 +01:00
|
|
|
# Avoid dependencies on perschema data defined in mysys
|
|
|
|
|
ADD_DEFINITIONS(-DDISABLE_MYSQL_THREAD_H)
|
2009-11-25 02:11:01 +01:00
|
|
|
ADD_CONVENIENCE_LIBRARY(strings ${STRINGS_SOURCES})
|
2020-05-04 14:17:06 +02:00
|
|
|
TARGET_LINK_LIBRARIES(strings dbug mysys)
|
|
|
|
|
MAYBE_DISABLE_IPO(strings)
|
2013-10-02 13:04:07 +02:00
|
|
|
ADD_EXECUTABLE(conf_to_src EXCLUDE_FROM_ALL conf_to_src.c)
|
2018-01-05 19:22:57 +01:00
|
|
|
SET_TARGET_PROPERTIES(conf_to_src PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD TRUE)
|
|
|
|
|
TARGET_LINK_LIBRARIES(conf_to_src mysys strings)
|
2021-11-23 13:33:08 +01:00
|
|
|
|
2023-02-21 11:04:45 +01:00
|
|
|
IF(NOT CMAKE_CROSSCOMPILING OR DEFINED CMAKE_CROSSCOMPILING_EMULATOR)
|
|
|
|
|
ADD_EXECUTABLE(uca-dump uca-dump.c)
|
|
|
|
|
ENDIF()
|
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
|
|
|
|
|
|
|
|
ADD_CUSTOM_COMMAND(
|
|
|
|
|
OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/ctype-uca1400data.h
|
|
|
|
|
COMMAND uca-dump --name-prefix=uca1400 --levels=3 ${PROJECT_SOURCE_DIR}/mysql-test/std_data/unicode/allkeys1400.txt > ctype-uca1400data.h
|
|
|
|
|
DEPENDS uca-dump
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
ADD_CUSTOM_TARGET(
|
|
|
|
|
GenUnicodeDataSource
|
|
|
|
|
DEPENDS
|
|
|
|
|
${CMAKE_CURRENT_BINARY_DIR}/ctype-uca1400data.h
|
|
|
|
|
)
|
|
|
|
|
ADD_DEPENDENCIES(strings GenUnicodeDataSource)
|