mirror of
https://github.com/MariaDB/server.git
synced 2025-11-27 05:41:41 +03:00
e056efdd6c
1. In case of system-versioned table add row_end into FTS_DOC_ID index
in fts_create_common_tables() and innobase_create_key_defs().
fts_n_uniq() returns 1 or 2 depending on whether the table is
system-versioned.
After this patch recreate of FTS_DOC_ID index is required for
existing system-versioned tables. If you see this message in error
log or server warnings: "InnoDB: Table db/t1 contains 2 indexes
inside InnoDB, which is different from the number of indexes 1
defined in the MariaDB" use this command to fix the table:
ALTER TABLE db.t1 FORCE;
2. Fix duplicate history for secondary unique index like it was done
in MDEV-23644 for clustered index (932ec586aa). In case of
existing history row which conflicts with currently inseted row we
check in row_ins_scan_sec_index_for_duplicate() whether that row
was inserted as part of current transaction. In that case we
indicate with DB_FOREIGN_DUPLICATE_KEY that new history row is not
needed and should be silently skipped.
3. Some parts of MDEV-21138 (7410ff436e) reverted. Skipping of
FTS_DOC_ID index for history rows made problems with purge
system. Now this is fixed differently by p.2.
4. wait_all_purged.inc checks that we didn't affect non-history rows
so they are deleted and purged correctly.
Additional FTS fixes
fts_init_get_doc_id(): exclude history rows from max_doc_id
calculation. fts_init_get_doc_id() callback is used only for crash
recovery.
fts_add_doc_by_id(): set max value for row_end field.
fts_read_stopword(): stopwords table can be system-versioned too. We
now read stopwords only for current data.
row_insert_for_mysql(): exclude history rows from doc_id validation.
row_merge_read_clustered_index(): exclude history_rows from doc_id
processing.
fts_load_user_stopword(): for versioned table retrieve row_end field
and skip history rows. For non-versioned table we retrieve 'value'
field twice (just for uniformity).
FTS tests for System Versioning now include maybe_versioning.inc which
adds 3 combinations:
'vers' for debug build sets sysvers_force and
sysvers_hide. sysvers_force makes every created table
system-versioned, sysvers_hide hides WITH SYSTEM VERSIONING
for SHOW CREATE.
Note: basic.test, stopword.test and versioning.test do not
require debug for 'vers' combination. This is controlled by
$modify_create_table in maybe_versioning.inc and these
tests run WITH SYSTEM VERSIONING explicitly which allows to
test 'vers' combination on non-debug builds.
'vers_trx' like 'vers' sets sysvers_force_trx and sysvers_hide. That
tests FTS with trx_id-based System Versioning.
'orig' works like before: no System Versioning is added, no debug is
required.
Upgrade/downgrade test for System Versioning is done by
innodb_fts.versioning. It has 2 combinations:
'prepare' makes binaries in std_data (requires old server and OLD_BINDIR).
It tests upgrade/downgrade against old server as well.
'upgrade' tests upgrade against binaries in std_data.
Cleanups:
Removed innodb-fts-stopword.test as it duplicates stopword.test
262 lines
7.9 KiB
Plaintext
262 lines
7.9 KiB
Plaintext
--source include/have_innodb.inc
|
|
--source include/maybe_versioning.inc
|
|
|
|
# This is the DDL function tests for innodb FTS
|
|
# Functional testing with FTS proximity search using '@'
|
|
# and try search default words
|
|
|
|
--disable_warnings
|
|
drop table if exists t1;
|
|
--enable_warnings
|
|
|
|
--disable_query_log
|
|
let $innodb_file_per_table_orig = `select @@innodb_file_per_table`;
|
|
--enable_query_log
|
|
|
|
# Create FTS table
|
|
CREATE TABLE t1 (
|
|
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
|
|
a VARCHAR(200),
|
|
b TEXT
|
|
) ENGINE= InnoDB;
|
|
|
|
# Create the FTS index again
|
|
CREATE FULLTEXT INDEX idx on t1 (a,b);
|
|
|
|
# Insert rows
|
|
INSERT INTO t1 (a,b) VALUES
|
|
('MySQL from Tutorial','DBMS stands for DataBase ...') ,
|
|
('when To Use MySQL Well','After that you went through a ...'),
|
|
('where will Optimizing MySQL','what In this tutorial we will show ...');
|
|
|
|
# Try to Search default stopword from innodb, "where", "will", "what"
|
|
# and "when" are all stopwords
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST ("where will");
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST ("when");
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST ("what" WITH QUERY EXPANSION);
|
|
|
|
# boolean No result expected
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST("whe*" IN BOOLEAN MODE);
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST("+what +will" IN BOOLEAN MODE);
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST("+from" IN BOOLEAN MODE);
|
|
SELECT * FROM t1 WHERE MATCH(a,b) AGAINST("+where +(show what)" IN BOOLEAN MODE);
|
|
|
|
# no result expected. Words are filtered out as stopwords
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"where will"@6' IN BOOLEAN MODE);
|
|
|
|
# no result expected
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"where will"@9' IN BOOLEAN MODE);
|
|
|
|
# insert record with @ character which is used in proximity search
|
|
INSERT INTO t1 (a,b) VALUES
|
|
('MySQL Tutorial','request docteam@oraclehelp.com ...') ,
|
|
('Trial version','query performace @1255 minute on 2.1Hz Memory 2GB...') ,
|
|
('when To Use MySQL Well','for free faq mail@xyz.com ...');
|
|
# proximity search with @ charcter
|
|
|
|
# We don't need more than one word in proximity search. Single word
|
|
# treated as single word search
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"request"@10' IN BOOLEAN MODE);
|
|
|
|
# If the distance is 0, it is treated as "phrase search"
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"Trial version"@0' IN BOOLEAN MODE);
|
|
|
|
# @ is word seperator
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"request docteam@oraclehelp.com"@10' IN BOOLEAN MODE);
|
|
|
|
# This should not return any document
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"1255 minute"@1' IN BOOLEAN MODE);
|
|
|
|
# This should return the first document. That is "1255" and "minutes" are
|
|
# in a two-word range (adjacent)
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"1255 minute"@2' IN BOOLEAN MODE);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"1255"@10' IN BOOLEAN MODE);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('1255' WITH QUERY EXPANSION);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"request docteam"@2' IN BOOLEAN MODE);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"1255 minute"' IN BOOLEAN MODE);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('request docteam@oraclehelp.com');
|
|
|
|
# Test across fields search
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"MySQL request"@3' IN BOOLEAN MODE);
|
|
|
|
# Two words are in 10 words range
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"Trial memory"@10' IN BOOLEAN MODE);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"Trial memory"@9' IN BOOLEAN MODE);
|
|
|
|
DROP TABLE t1;
|
|
|
|
# test on utf8 encoded proximity search
|
|
CREATE TABLE t1 (
|
|
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
|
|
a VARCHAR(200),
|
|
b TEXT
|
|
) CHARACTER SET = UTF8, ENGINE= InnoDB;
|
|
|
|
INSERT INTO t1 (a,b) VALUES
|
|
('MySQL from Tutorial','DBMS stands for DataBase ...') ,
|
|
('when To Use MySQL Well','After that you went through a ...'),
|
|
('where will Optimizing MySQL','what In this tutorial we will show ...');
|
|
|
|
CREATE FULLTEXT INDEX idx on t1 (a,b);
|
|
|
|
INSERT INTO t1 (a,b) VALUES
|
|
('MySQL Tutorial','request docteam@oraclehelp.com ...') ,
|
|
('Trial version','query performace @1255 minute on 2.1Hz Memory 2GB...'),
|
|
('when To Use MySQL Well','for free faq mail@xyz.com ...');
|
|
|
|
# Should have 2 rows. Note proximity search does require words in order
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"mysql use"@2' IN BOOLEAN MODE);
|
|
|
|
# Should return 0 row
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"mysql use"@1' IN BOOLEAN MODE);
|
|
|
|
INSERT INTO t1 (a,b) VALUES ('XYZ, long blob', repeat("a", 9000));
|
|
|
|
INSERT IGNORE INTO t1 (a,b) VALUES (repeat("b", 9000), 'XYZ, long blob');
|
|
|
|
# 2 rows match
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"xyz blob"@3' IN BOOLEAN MODE);
|
|
|
|
DROP TABLE t1;
|
|
|
|
set global innodb_file_per_table=1;
|
|
|
|
# Test fts with externally stored long column
|
|
CREATE TABLE t1 (
|
|
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
|
|
a TEXT,
|
|
b TEXT,
|
|
c TEXT
|
|
) CHARACTER SET = UTF8, ROW_FORMAT=DYNAMIC, ENGINE= InnoDB;
|
|
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("b", 19000), 'XYZ, long text', 'very long blob');
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("b", 19000), 'XYZ, very little long blob very much blob', 'very long blob');
|
|
|
|
# Note 租车 is count as one word
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("b", 19000),"very 租车 供 blob","new 供需分析information");
|
|
CREATE FULLTEXT INDEX idx on t1 (a,b,c);
|
|
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("x", 19000), 'new, long text', 'very new blob');
|
|
INSERT INTO t1 (a,b,c) VALUES ('interesting, long text', repeat("x", 19000), 'very very good new blob');
|
|
|
|
# 3 rows should match
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very blob"@3' IN BOOLEAN MODE);
|
|
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very long blob"@0' IN BOOLEAN MODE);
|
|
|
|
# 4 rows should match
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very blob"@4' IN BOOLEAN MODE);
|
|
|
|
# 1 row should match
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"interesting blob"@9' IN BOOLEAN MODE);
|
|
|
|
# should have 3 rows
|
|
SELECT COUNT(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"interesting blob"@9 "very long blob"@0' IN BOOLEAN MODE);
|
|
|
|
# should have 3 rows
|
|
SELECT COUNT(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very blob"@4 - "interesting blob"@9' IN BOOLEAN MODE);
|
|
|
|
DROP TABLE t1;
|
|
|
|
CREATE TABLE t1 (
|
|
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
|
|
a VARCHAR(200),
|
|
b TEXT
|
|
) CHARACTER SET = UTF8, ENGINE= InnoDB;
|
|
|
|
# Space and special characters are not counted as word
|
|
INSERT INTO t1 (a,b) VALUES
|
|
('MySQL from Tutorial','DBMS stands for + DataBase ...');
|
|
|
|
CREATE FULLTEXT INDEX idx on t1 (a,b);
|
|
|
|
SELECT * FROM t1
|
|
WHERE MATCH (a,b)
|
|
AGAINST ('"stands database"@3' IN BOOLEAN MODE);
|
|
|
|
DROP TABLE t1;
|
|
|
|
# Test fts with externally stored long column
|
|
CREATE TABLE t1 (
|
|
id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
|
|
a TEXT,
|
|
b TEXT,
|
|
c TEXT
|
|
) CHARACTER SET = UTF8, ROW_FORMAT=DYNAMIC, ENGINE= InnoDB;
|
|
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("b", 19000), 'XYZ, long text', 'very long blob');
|
|
INSERT INTO t1 (a,b,c) VALUES ('XYZ, 租车 very little long blob very much blob', repeat("b", 19000), 'very long but smaller blob');
|
|
|
|
CREATE FULLTEXT INDEX idx on t1 (a,b,c);
|
|
|
|
DELETE FROM t1;
|
|
|
|
INSERT INTO t1 (a,b,c) VALUES (repeat("b", 19000), 'XYZ, long text', 'very long blob');
|
|
INSERT INTO t1 (a,b,c) VALUES ('XYZ, 租车 very little long blob is a very much longer blob', repeat("b", 19000), 'this is very long but smaller blob');
|
|
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very blob"@4' IN BOOLEAN MODE);
|
|
|
|
SELECT count(*) FROM t1
|
|
WHERE MATCH (a,b,c)
|
|
AGAINST ('"very blob"@3' IN BOOLEAN MODE);
|
|
|
|
DROP TABLE t1;
|
|
|
|
eval SET GLOBAL innodb_file_per_table=$innodb_file_per_table_orig;
|