我有一个电影数据库,其中包含有关名为 Yes, We're Open 的电影的信息。
在搜索数据库时,我遇到了一个问题,其中搜索“是的,我们是开放的”返回另一个标题,其中包含“我们是”和“开放”但在其描述中没有“是”字样,即使我要求布尔模式下的所有单词(即“是的,我们打开”'+yes +we\'re +open'
在作为查询发送之前被翻译)。
我认为这是因为“是”在内置的停用词列表中。但是,当我设置ft_stopword_file = ""
,重新启动 mysql,然后repair table [tablename] quick
我正在搜索的表时,我在搜索“是的,我们已打开”时没有得到任何结果。我在下面包含了我的 my.cnf。这是 MySQL 版本 5.0.22。有任何想法吗?
[mysqld]
query-cache-type = 1
query-cache-size = 8M
max_allowed_packet=500M
ft_min_word_len=2
ft_stopword_file = ""
[myisamchk]
ft_min_word_len=2
set-variable=local-infile=0
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
# Default to using old password format for compatibility with mysql 3.x
# clients (those using the mysqlclient10 compatibility package).
# old_passwords=1
skip-bdb
set-variable = innodb_buffer_pool_size=2M
set-variable = innodb_additional_mem_pool_size=500K
set-variable = innodb_log_buffer_size=500K
set-variable = innodb_thread_concurrency=2
[mysql.server]
user=mysql
basedir=/var/lib
[mysqld_safe]
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
skip-bdb
set-variable = innodb_buffer_pool_size=2M
set-variable = innodb_additional_mem_pool_size=500K
set-variable = innodb_log_buffer_size=500K
set-variable = innodb_thread_concurrency=2
编辑:以下是一些示例查询:
#1 - 内置停用词文件
mysql> SHOW VARIABLES LIKE 'ft_%';
+--------------------------+----------------+
| Variable_name | Value |
+--------------------------+----------------+
| ft_boolean_syntax | + -><()~*:""&| |
| ft_max_word_len | 84 |
| ft_min_word_len | 2 |
| ft_query_expansion_limit | 20 |
| ft_stopword_file | (built-in) |
+--------------------------+----------------+
5 rows in set (0.00 sec)
mysql> SELECT title, MATCH(title,description,genre,country) AGAINST (' +yes +we\'re +open' IN BOOLEAN MODE) as title_description_genre_country_score FROM `films` WHERE MATCH(title,description,genre,country) AGAINST (' +yes +we\'re +open' IN BOOLEAN MODE) AND `hidden` <> '1' ORDER BY `title_description_genre_country_score` DESC ;
+-----------------+---------------------------------------+
| title | title_description_genre_country_score |
+-----------------+---------------------------------------+
| Yes, We?re Open | 1 |
| Present/Future | 1 |
+-----------------+---------------------------------------+
2 rows in set (0.00 sec)
....然后编辑my.cnf,添加ft_stopword_file=""
.....
#2 没有停用词文件
mysql> SHOW VARIABLES LIKE 'ft_%';
+--------------------------+----------------+
| Variable_name | Value |
+--------------------------+----------------+
| ft_boolean_syntax | + -><()~*:""&| |
| ft_max_word_len | 84 |
| ft_min_word_len | 2 |
| ft_query_expansion_limit | 20 |
| ft_stopword_file | |
+--------------------------+----------------+
5 rows in set (0.00 sec)
mysql> REPAIR TABLE `films` QUICK;
+-------------------------+--------+----------+----------+
| Table | Op | Msg_type | Msg_text |
+-------------------------+--------+----------+----------+
| db.films | repair | status | OK |
+-------------------------+--------+----------+----------+
1 row in set (0.14 sec)
mysql> SELECT title, MATCH(title,description,genre,country) AGAINST (' +yes +we\'re +open' IN BOOLEAN MODE) as title_description_genre_country_score FROM `films` WHERE MATCH(title,description,genre,country) AGAINST (' +yes +we\'re +open' IN BOOLEAN MODE) AND `hidden` <> '1' ORDER BY `title_description_genre_country_score` DESC ;
Empty set (0.00 sec)
编辑#2:创建表:
mysql> SHOW CREATE TABLE db.films\G;
*************************** 1. row ***************************
Table: films
Create Table: CREATE TABLE `films` (
`id` varchar(8) NOT NULL default '',
`title` varchar(255) default NULL,
`hidden` tinyint(1) default '0',
`featured` tinyint(1) default NULL,
`type` varchar(255) default NULL,
`subtype` varchar(255) default NULL,
`summary` text,
`description` text,
`image_url` varchar(255) default NULL,
`trailer_url` varchar(255) default NULL,
`slug` varchar(255) default NULL,
`category` varchar(255) default NULL,
`parent` varchar(255) default NULL,
`related` varchar(255) default NULL,
`sponsor` varchar(255) default NULL,
`genre` varchar(255) default NULL,
`country` varchar(255) default NULL,
`copresenters` varchar(255) default NULL,
`original_title` varchar(255) default NULL,
`director` varchar(255) default NULL,
`executive_producer` varchar(255) default NULL,
`producer` varchar(255) default NULL,
`cinematographer` varchar(255) default NULL,
`writer` varchar(255) default NULL,
`editor` varchar(255) default NULL,
`sound` varchar(255) default NULL,
`cast` varchar(255) default NULL,
`language` varchar(255) default NULL,
`trt` varchar(255) default NULL,
`year` varchar(255) default NULL,
`subtitles` varchar(255) default NULL,
`format` varchar(255) default NULL,
`color` varchar(255) default NULL,
`premiere_status` varchar(255) default NULL,
PRIMARY KEY (`id`),
KEY `id` (`id`),
KEY `type` (`type`),
KEY `subtype` (`subtype`),
KEY `slug` (`slug`),
KEY `category` (`category`),
KEY `parent` (`parent`),
KEY `hidden` (`hidden`),
KEY `featured` (`featured`),
KEY `copresenters` (`copresenters`),
KEY `original_title` (`original_title`),
KEY `director` (`director`),
KEY `executive_producer` (`executive_producer`),
KEY `producer` (`producer`),
KEY `cinematographer` (`cinematographer`),
KEY `writer` (`writer`),
KEY `editor` (`editor`),
KEY `sound` (`sound`),
KEY `cast` (`cast`),
KEY `language` (`language`),
KEY `trt` (`trt`),
KEY `year` (`year`),
KEY `subtitles` (`subtitles`),
KEY `format` (`format`),
KEY `color` (`color`),
KEY `premiere_status` (`premiere_status`),
FULLTEXT KEY `title` (`title`),
FULLTEXT KEY `summary` (`summary`),
FULLTEXT KEY `description` (`description`),
FULLTEXT KEY `genre` (`genre`),
FULLTEXT KEY `country` (`country`),
FULLTEXT KEY `title,description` (`title`,`description`),
FULLTEXT KEY `title,description,genre,country` (`title`,`description`,`genre`,`country`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8
1 row in set (0.00 sec)