194 lines
7.6 KiB
Plaintext
194 lines
7.6 KiB
Plaintext
call mtr.add_suppression("unknown variable 'loose_mecab_rc_file");
|
|
call mtr.add_suppression("Fulltext index charset 'big5' doesn't match mecab charset");
|
|
call mtr.add_suppression("Mecab: createModel.* failed: param.cpp");
|
|
call mtr.add_suppression("Plugin 'mecab' init function returned error");
|
|
SHOW STATUS LIKE 'mecab_charset';
|
|
Variable_name Value
|
|
mecab_charset utf8
|
|
SET NAMES utf8;
|
|
Warnings:
|
|
Warning 3719 'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.
|
|
CREATE TABLE page (
|
|
page_id int(8) unsigned NOT NULL AUTO_INCREMENT,
|
|
page_title varchar(255) CHARACTER SET utf8 NOT NULL DEFAULT '',
|
|
PRIMARY KEY (page_id),
|
|
FULLTEXT KEY page_title (page_title) WITH PARSER mecab
|
|
) ENGINE=InnoDB;
|
|
Warnings:
|
|
Warning 1681 Integer display width is deprecated and will be removed in a future release.
|
|
Warning 3719 'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.
|
|
INSERT INTO page VALUES
|
|
(1,'レモナ'),
|
|
(2,'SDレモナ'),
|
|
(3,'レモナ'),
|
|
(4,'データベース管理システム'),
|
|
(5,'キム'),
|
|
(6,'鉄道100電車'),
|
|
(7,'100'),
|
|
(8,'ラフィタ・カスティージョ'),
|
|
(9,'ツル科_(Sibley)'),
|
|
(10,'ツル'),
|
|
(11,'鉄道');
|
|
SET GLOBAL innodb_ft_aux_table="test/page";
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_CACHE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
100 7 8 2 7 6
|
|
100 7 8 2 8 0
|
|
sd 3 3 1 3 0
|
|
sibley 10 10 1 10 11
|
|
_( 10 10 1 10 9
|
|
キム 6 6 1 6 0
|
|
システム 5 5 1 5 24
|
|
ツル 10 11 2 10 0
|
|
ツル 10 11 2 11 0
|
|
データベース 5 5 1 5 0
|
|
ラフィタ・カスティージョ 9 9 1 9 0
|
|
レモナ 3 4 2 3 2
|
|
レモナ 3 4 2 4 0
|
|
管理 5 5 1 5 18
|
|
鉄道 7 12 2 7 0
|
|
鉄道 7 12 2 12 0
|
|
電車 7 7 1 7 9
|
|
レモナ 2 2 1 2 0
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_TABLE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
SHOW CREATE TABLE page;
|
|
Table Create Table
|
|
page CREATE TABLE `page` (
|
|
`page_id` int(8) unsigned NOT NULL AUTO_INCREMENT,
|
|
`page_title` varchar(255) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL DEFAULT '',
|
|
PRIMARY KEY (`page_id`),
|
|
FULLTEXT KEY `page_title` (`page_title`) /*!50100 WITH PARSER `mecab` */
|
|
) ENGINE=InnoDB AUTO_INCREMENT=12 DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("レモナ" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
1 レモナ
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("キムショウカン" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("100" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
6 鉄道100電車
|
|
7 100
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("ツル*" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
9 ツル科_(Sibley)
|
|
10 ツル
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("ラフィタ・カスティージョ");
|
|
page_id page_title
|
|
8 ラフィタ・カスティージョ
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("ラフィタ・カスティージョ" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("+ラフィタ・カスティージョ +データベース" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("+ラフィタ・カスティージョ +(データベース)" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("-ラフィタ・カスティージョ +(データベース)" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
4 データベース管理システム
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("ラフィタ・カスティージョ 鉄道" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
6 鉄道100電車
|
|
11 鉄道
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("<ラフィタ・カスティージョ >鉄道" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
6 鉄道100電車
|
|
11 鉄道
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('鉄道');
|
|
page_id page_title
|
|
6 鉄道100電車
|
|
11 鉄道
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('鉄道' WITH QUERY EXPANSION);
|
|
page_id page_title
|
|
6 鉄道100電車
|
|
7 100
|
|
11 鉄道
|
|
ALTER TABLE page add column c1 varchar(100) CHARACTER SET utf8 DEFAULT 'レモナ';
|
|
Warnings:
|
|
Warning 3719 'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.
|
|
ALTER TABLE page ADD FULLTEXT INDEX idx1 (page_title,c1) WITH PARSER mecab;
|
|
SELECT * FROM page WHERE MATCH(page_title,c1) AGAINST('レモナ');
|
|
page_id page_title c1
|
|
1 レモナ レモナ
|
|
2 SDレモナ レモナ
|
|
3 レモナ レモナ
|
|
4 データベース管理システム レモナ
|
|
5 キム レモナ
|
|
6 鉄道100電車 レモナ
|
|
7 100 レモナ
|
|
8 ラフィタ・カスティージョ レモナ
|
|
9 ツル科_(Sibley) レモナ
|
|
10 ツル レモナ
|
|
11 鉄道 レモナ
|
|
SELECT * FROM page WHERE MATCH(page_title,c1) AGAINST('-レモナ' IN BOOLEAN MODE);
|
|
page_id page_title c1
|
|
DROP TABLE page;
|
|
CREATE TABLE page (
|
|
page_id int(8) unsigned NOT NULL AUTO_INCREMENT,
|
|
page_title varchar(255) CHARACTER SET big5 NOT NULL DEFAULT '',
|
|
PRIMARY KEY (page_id)
|
|
)ENGINE=InnoDB;
|
|
Warnings:
|
|
Warning 1681 Integer display width is deprecated and will be removed in a future release.
|
|
INSERT INTO page VALUES (1,'日本');
|
|
CREATE FULLTEXT INDEX ft_idx ON page(page_title) WITH PARSER mecab;
|
|
Warnings:
|
|
Warning 124 InnoDB rebuilding table to add column FTS_DOC_ID
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_CACHE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_TABLE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
INSERT INTO page VALUES (2,'日本');
|
|
ERROR HY000: Fulltext index charset 'big5' doesn't match mecab charset 'utf8'.
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('日本');
|
|
ERROR HY000: Fulltext index charset 'big5' doesn't match mecab charset 'utf8'.
|
|
DROP TABLE page;
|
|
SET NAMES utf8mb4;
|
|
CREATE TABLE page (
|
|
page_id int(8) unsigned NOT NULL AUTO_INCREMENT,
|
|
page_title varchar(255) CHARACTER SET utf8mb4 NOT NULL DEFAULT '',
|
|
PRIMARY KEY (page_id),
|
|
FULLTEXT KEY page_title (page_title) WITH PARSER mecab
|
|
) ENGINE=InnoDB;
|
|
Warnings:
|
|
Warning 1681 Integer display width is deprecated and will be removed in a future release.
|
|
INSERT INTO page VALUES
|
|
(1,'😃レモナ'),
|
|
(2,'鉄道😄'),
|
|
(3,'鉄道😊100電車');
|
|
SET GLOBAL innodb_ft_aux_table="test/page";
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_CACHE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
100 4 4 1 4 10
|
|
レモナ 2 2 1 2 4
|
|
鉄道 3 4 2 3 0
|
|
鉄道 3 4 2 4 0
|
|
電車 4 4 1 4 13
|
|
SELECT * FROM INFORMATION_SCHEMA.INNODB_FT_INDEX_TABLE;
|
|
WORD FIRST_DOC_ID LAST_DOC_ID DOC_COUNT DOC_ID POSITION
|
|
SHOW CREATE TABLE page;
|
|
Table Create Table
|
|
page CREATE TABLE `page` (
|
|
`page_id` int(8) unsigned NOT NULL AUTO_INCREMENT,
|
|
`page_title` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL DEFAULT '',
|
|
PRIMARY KEY (`page_id`),
|
|
FULLTEXT KEY `page_title` (`page_title`) /*!50100 WITH PARSER `mecab` */
|
|
) ENGINE=InnoDB AUTO_INCREMENT=4 DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST("レモナ" IN BOOLEAN MODE);
|
|
page_id page_title
|
|
1 😃レモナ
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('鉄道');
|
|
page_id page_title
|
|
2 鉄道😄
|
|
3 鉄道😊100電車
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('鉄道😄');
|
|
page_id page_title
|
|
2 鉄道😄
|
|
3 鉄道😊100電車
|
|
SELECT * FROM page WHERE MATCH(page_title) AGAINST('鉄道' WITH QUERY EXPANSION);
|
|
page_id page_title
|
|
3 鉄道😊100電車
|
|
2 鉄道😄
|
|
DROP TABLE page;
|
|
SET GLOBAL innodb_ft_aux_table=default;
|
|
UNINSTALL PLUGIN mecab;
|