MySQL全文索引实现简单版搜索引擎实例代码

SELECT * FROM information_schema.INNODB_FT_DEFAULT_STOPWORD;

+-------+ 
| value | 
+-------+ 
| a   | 
| about | 
| an  | 
| are  | 
| as  | 
| at  | 
| be  | 
| by  | 
| com  | 
| de  | 
| en  | 
| for  | 
| from | 

SET GLOBAL sync_binlog=100;
SET GLOBAL innodb_flush_log_at_trx_commit=2;

CREATE TABLE `article` (
 `id` bigint(10) NOT NULL,
 `url` varchar(1024) CHARACTER SET latin1 NOT NULL DEFAULT '',
 `title` varchar(256) NOT NULL DEFAULT '',
 `source` varchar(32) DEFAULT '' COMMENT '真实来源',
 `keywords` varchar(32) DEFAULT NULL,
 `publish_time` timestamp NULL DEFAULT NULL,
 PRIMARY KEY (`id`),
 KEY `title_idx` (`title`)
) ENGINE=InnoDB

先把测试数据进行解压
tar -zxf mydumper_dump_article.tar.gz
time myloader -u $user -p $passwd -S $socket -t 32 -d /datas/dump_article -v 3

SELECT COUNT(*) FROM `article`;
+----------+
| COUNT(*) |
+----------+
| 10000000 |
+----------+
1 row in set (7.85 sec)

SELECT   table_name,  CONCAT(FORMAT(SUM(data_length) / 1024 / 1024,2),'M') AS dbdata_size,  CONCAT(FORMAT(SUM(index_length) / 1024 / 1024,2),'M') AS dbindex_size,  CONCAT(FORMAT(SUM(data_length + index_length) / 1024 / 1024 / 1024,2),'G') AS `db_size(G)`,  AVG_ROW_LENGTH,table_rows,update_time FROM  information_schema.tables WHERE table_schema = DATABASE() and table_name='article';
+------------+-------------+--------------+------------+----------------+------------+---------------------+
| table_name | dbdata_size | dbindex_size | db_size(G) | AVG_ROW_LENGTH | table_rows | update_time     |
+------------+-------------+--------------+------------+----------------+------------+---------------------+
| article  | 3,710.00M  | 1,003.00M  | 4.60G   |      414 |  9388739 | 2019-07-05 15:31:37 |
+------------+-------------+--------------+------------+----------------+------------+---------------------+

select keywords from article limit 10;
+-------------------------------------------------+
| keywords                    |
+-------------------------------------------------+
| NULL                      |
| NULL                      |
| ,婚姻,爱情                   |
| 发型,偏分,化妆,时尚               |
| 小A,                      |
| ,服装搭配,女性,时尚               |
| 漂亮,女性                    |
| 情人节,东莞,女性                |
| 皮肤,护肤,护肤,食品营养,美容,养生        |
| 三里屯,北京,时尚                |
+-------------------------------------------------+

select count(*) from article where keywords like '%时尚%';
+----------+
| count(*) |
+----------+
|   163 |
+----------+
1 row in set (7.56 sec)

[mysqld]
innodb_ft_min_token_size=2

USE mysql;
CREATE TABLE my_stopwords(VALUE VARCHAR(30)) ENGINE = INNODB;
INSERT INTO my_stopwords(VALUE) VALUE (',');
SET GLOBAL innodb_ft_server_stopword_table = 'mysql/my_stopwords';

SHOW GLOBAL VARIABLES WHERE Variable_name IN('innodb_ft_min_token_size','innodb_ft_server_stopword_table');
+---------------------------------+--------------------+
| Variable_name          | Value       |
+---------------------------------+--------------------+
| innodb_ft_min_token_size    | 2         |
| innodb_ft_server_stopword_table | mysql/my_stopwords |
+---------------------------------+--------------------+

alter table article add fulltext index idx_full_keyword(keywords);
* [ ] Query OK, 0 rows affected, 1 warning (1 min 27.92 sec)
* [ ] Records: 0 Duplicates: 0 Warnings: 1

df -h
Filesystem      Size Used Avail Use% Mounted on
/dev/vda1       7.8G 6.3G 1.2G 85% /
tmpfs         1.9G   0 1.9G  0% /dev/shm
/dev/mapper/vg_opt-lvol0
            19G  12G 5.7G 68% /datas

会创建原表大小的临时文件
 8.6K Jul 5 16:19 #sql-5250_3533.frm
 4.4G Jul 5 16:20 #sql-ib117-1768830977.ibd


alter table article add fulltext index idx_full_keyword(keywords);
ERROR 1114 (HY000): The table 'article' is full

select count(*) from article where match(keywords) against('%时尚%');
+----------+
| count(*) |
+----------+
|   163 |
+----------+
1 row in set (0.05 sec)

表示完全匹配 "三里屯,北京" 的记录数
select count(*) from article where match(keywords) against('+三里屯,北京' in boolean mode);
+----------+
| count(*) |
+----------+
|    1 |
+----------+
1 row in set (0.06 sec)

表示匹配“三里屯” 或者 “北京”的记录数
select count(*) from article where match(keywords) against('三里屯,北京');
+----------+
| count(*) |
+----------+
|    8 |
+----------+
1 row in set (0.06 sec)

select title from article limit 10;
+------------------------------------------------------------------------------+
| title                                    |
+------------------------------------------------------------------------------+
| worth IT                                  |
|Launchpad 江南皮革厂小show                         |
|Raw 幕后罕见一刻 “疯子”被抬回后台                      |
|Raw:公子大骂老爸你就是个绿茶 公子以一打四                 |
|四组30平米精装小户型，海量图片，附户型图                  |
|夜店女王性感烟熏猫眼妆                           |
|大秀哥重摔“巨石”强森                            |
|少女时代 崔秀英 服饰科普 林允儿 黄美英 金泰妍 郑秀晶            |                       
|德阳户外踏青，花田自助烧烤                         |
+------------------------------------------------------------------------------+

alter table article add fulltext index ft_index_title(title) with parser ngram;
Query OK, 0 rows affected (3 min 29.22 sec)
Records: 0 Duplicates: 0 Warnings: 0

select count(*) from article where title like '%户外%';
+----------+
| count(*) |
+----------+
|  22058 |
+----------+
1 row in set (8.60 sec)

select count(*) from article where title like '%后台%';
+----------+
| count(*) |
+----------+
|   1142 |
+----------+

select count(*) from article where match(title) against('户外');
+----------+
| count(*) |
+----------+
|  22058 |
+----------+
1 row in set (0.07 sec)

select count(*) from article where title like '%后台%';
+----------+
| count(*) |
+----------+
|   1142 |
+----------+
1 row in set (8.31 sec)

普通搜索，实际中出现该关键词的记录数为6
select count(*) from article where title like '%公子大%';
+----------+
| count(*) |
+----------+
|    6 |
+----------+
1 row in set (8.40 sec)

全文搜索，出现关键字的记录数为9443
select count(*) from article where match(title) against('公子大');
+----------+
| count(*) |
+----------+
|   9443 |
+----------+
1 row in set (0.06 sec)

实际出现该关键字的记录数为1
select count(*) from article where title like '%花田自助%';
+----------+
| count(*) |
+----------+
|    1 |
+----------+
1 row in set (8.33 sec)

全文搜索出现该关键词的记录数为3202
select count(*) from article where match(title) against('花田自助');
+----------+
| count(*) |
+----------+
|   3202 |
+----------+
1 row in set (0.06 sec)