diff options
author | Alexander Barkov <bar@mariadb.com> | 2021-11-28 16:55:15 +0400 |
---|---|---|
committer | Oleksandr Byelkin <sanja@mariadb.com> | 2022-08-10 15:04:24 +0200 |
commit | 133446828c9dcb484476e4b3598af0d63d056a6e (patch) | |
tree | cf511dbe61a84c1eed97250dc8f92fe7798a098d /sql/lex_charset.cc | |
parent | 6bc10f8026e691444f0d2e857a5d0de4b88fa11f (diff) | |
download | mariadb-git-133446828c9dcb484476e4b3598af0d63d056a6e.tar.gz |
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.
Diffstat (limited to 'sql/lex_charset.cc')
-rw-r--r-- | sql/lex_charset.cc | 113 |
1 files changed, 94 insertions, 19 deletions
diff --git a/sql/lex_charset.cc b/sql/lex_charset.cc index b83d175307f..cfb74a0bf04 100644 --- a/sql/lex_charset.cc +++ b/sql/lex_charset.cc @@ -45,7 +45,7 @@ raise_ER_CONFLICTING_DECLARATIONS(const char *clause1, const char *name2, bool reverse_order) { - char def[MY_CS_NAME_SIZE * 2]; + char def[MY_CS_CHARACTER_SET_NAME_SIZE * 2]; my_snprintf(def, sizeof(def), "%s (%s)", name1, name1_part2); raise_ER_CONFLICTING_DECLARATIONS(clause1, def, clause2, name2, @@ -127,19 +127,43 @@ Lex_exact_collation:: raise_if_conflicts_with_context_collation(const Lex_context_collation &cl, bool reverse_order) const { - if (cl.is_contextually_typed_collate_default() && - !(m_ci->state & MY_CS_PRIMARY)) + if (cl.is_contextually_typed_collate_default()) { - raise_ER_CONFLICTING_DECLARATIONS("COLLATE ", m_ci->coll_name.str, - "COLLATE ", "DEFAULT", reverse_order); - return true; + if (!(m_ci->state & MY_CS_PRIMARY)) + { + raise_ER_CONFLICTING_DECLARATIONS("COLLATE ", m_ci->coll_name.str, + "COLLATE ", "DEFAULT", reverse_order); + return true; + } + return false; } - if (cl.is_contextually_typed_binary_style() && - !(m_ci->state & MY_CS_BINSORT)) + if (cl.is_contextually_typed_binary_style()) { - raise_ER_CONFLICTING_DECLARATIONS("COLLATE ", m_ci->coll_name.str, - "", "BINARY", reverse_order); + if (!(m_ci->state & MY_CS_BINSORT)) + { + raise_ER_CONFLICTING_DECLARATIONS("COLLATE ", m_ci->coll_name.str, + "", "BINARY", reverse_order); + return true; + } + return false; + } + + DBUG_ASSERT(!strncmp(cl.charset_info()->coll_name.str, + STRING_WITH_LEN("utf8mb4_uca1400_"))); + + Charset_loader_server loader; + CHARSET_INFO *ci= loader.get_exact_collation_by_context_name( + m_ci, + cl.collation_name_context_suffix().str, + MYF(0)); + if (m_ci != ci) + { + raise_ER_CONFLICTING_DECLARATIONS("COLLATE ", + m_ci->coll_name.str, + "COLLATE ", + cl.collation_name_for_show().str, + reverse_order); return true; } return false; @@ -153,9 +177,16 @@ Lex_context_collation::raise_if_not_equal(const Lex_context_collation &cl) const Only equal context collations are possible here so far: - Column grammar only supports BINARY, but does not support COLLATE DEFAULT - DB/Table grammar only support COLLATE DEFAULT - But we'll have different collations here - uca140 is coming soon. */ - DBUG_ASSERT(m_ci == cl.m_ci); + if (m_ci != cl.m_ci) + { + my_error(ER_CONFLICTING_DECLARATIONS, MYF(0), + is_contextually_typed_binary_style() ? "" : "COLLATE ", + collation_name_for_show().str, + cl.is_contextually_typed_binary_style() ? "" : "COLLATE ", + cl.collation_name_for_show().str); + return true; + } return false; } @@ -193,12 +224,16 @@ bool Lex_exact_charset_opt_extended_collate:: return false; } - /* - A non-binary and non-default contextually typed collation. - We don't have such yet - the parser cannot produce this. - But we have "uca1400_as_ci" coming soon. - */ - DBUG_ASSERT(0); + DBUG_ASSERT(!strncmp(cl.charset_info()->coll_name.str, + STRING_WITH_LEN("utf8mb4_uca1400_"))); + + CHARSET_INFO *ci= Charset_loader_server(). + get_exact_collation_by_context_name_or_error(m_ci, + cl.charset_info()->coll_name.str + 8, MYF(0)); + if (!ci) + return true; + m_ci= ci; + m_with_collate= true; return false; } @@ -244,7 +279,7 @@ bool Lex_extended_collation_st:: CONTEXT + EXACT CHAR(10) COLLATE DEFAULT .. COLLATE latin1_swedish_ci CHAR(10) BINARY .. COLLATE latin1_bin - CHAR(10) COLLATE uca1400_as_ci .. COLLATE latin1_bin - coming soon + CHAR(10) COLLATE uca1400_as_ci .. COLLATE latin1_bin */ if (rhs.raise_if_conflicts_with_context_collation( Lex_context_collation(m_ci), true)) @@ -320,6 +355,38 @@ bool Lex_extended_collation_st::merge(const Lex_extended_collation_st &rhs) } +LEX_CSTRING Lex_context_collation::collation_name_for_show() const +{ + if (is_contextually_typed_collate_default()) + return LEX_CSTRING({STRING_WITH_LEN("DEFAULT")}); + if (is_contextually_typed_binary_style()) + return LEX_CSTRING({STRING_WITH_LEN("BINARY")}); + return collation_name_context_suffix(); +} + + +bool Lex_extended_collation_st::set_by_name(const char *name, myf my_flags) +{ + Charset_loader_server loader; + CHARSET_INFO *cs; + + if (!strncasecmp(name, STRING_WITH_LEN("uca1400_"))) + { + if (!(cs= loader.get_context_collation_or_error(name, my_flags))) + return true; + + *this= Lex_extended_collation(Lex_context_collation(cs)); + return false; + } + + if (!(cs= loader.get_exact_collation_or_error(name, my_flags))) + return true; + + *this= Lex_extended_collation(Lex_exact_collation(cs)); + return false; +} + + /** find a collation with binary comparison rules */ CHARSET_INFO *Lex_exact_charset_opt_extended_collate::find_bin_collation() const @@ -499,6 +566,14 @@ bool Lex_exact_charset_opt_extended_collate:: // CHARACTER SET latin1 [COLLATE latin1_bin] .. COLLATE latin1_bin if (m_with_collate) return Lex_exact_collation(m_ci).raise_if_not_equal(cl); + return merge_exact_collation_override(cl); +} + + +bool Lex_exact_charset_opt_extended_collate:: + merge_exact_collation_override(const Lex_exact_collation &cl) +{ + // CHARACTER SET latin1 [COLLATE latin1_bin] .. COLLATE latin1_bin if (raise_if_not_applicable(cl)) return true; *this= Lex_exact_charset_opt_extended_collate(cl); |