SPHINX使用说明

+------------------------------------+
1.创建配置文件：
+------------------------------------+
cd /usr/local/webserver/sphinx/coreseek/etc
vi sphinx.conf

+------------------------------------+
2.输入以下内容：
+------------------------------------+
source test_doc_source
{
    type                = mysql
    sql_host            = localhost
    sql_user            = root
    sql_pass            = 123456
    sql_db                = test
    sql_port            = 3306    # optional, default is 3306
    sql_sock            = /tmp/mysql.sock
    sql_query_pre            = SET NAMES utf8
    sql_query            = \
        SELECT id, group_id, UNIX_TIMESTAMP(date_added) AS date_added, title, content \
        FROM documents
    sql_attr_uint            = group_id
    sql_attr_timestamp        = date_added
    sql_query_info            = SELECT * FROM documents WHERE id=$id
}

index test_doc_index
{
    source            = test_doc_source
    path        = /usr/local/webserver/sphinx/coreseek/var/data/test_doc_index
    docinfo            = extern
    charset_type        = zh_cn.utf-8
    mlock            = 0
    morphology        = none
    min_word_len        = 1
    html_strip        = 0
    charset_dictpath    = /usr/local/webserver/sphinx/mmseg3/etc/
    ngram_len        = 0
}

indexer
{
    mem_limit        = 32M
}

searchd
{
    port            = 9312
    log            = /usr/local/webserver/sphinx/coreseek/var/log/searchd.log
    query_log        = /usr/local/webserver/sphinx/coreseek/var/log/query.log
    read_timeout        = 5
    max_children        = 30
    pid_file        = /usr/local/webserver/sphinx/coreseek/var/log/searchd.pid
    max_matches        = 1000
    seamless_rotate        = 1
    preopen_indexes        = 0
    unlink_old        = 1
}

+------------------------------------+
3.向test数据库中创建测试表：
+------------------------------------+
DROP TABLE IF EXISTS test.documents;

CREATE TABLE `documents` (
  `id` int(10) NOT NULL auto_increment,
  `group_id` int(10) NOT NULL,
  `group_id2` int(10) NOT NULL,
  `date_added` datetime NOT NULL,
  `title` varchar(255) NOT NULL,
  `content` text NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;

REPLACE INTO test.documents ( id, group_id, group_id2, date_added, title, content ) VALUES
    ( 1, 1, 5, NOW(), 'test one', 'this is my test document number one. also checking search within phrases.' ),
    ( 2, 1, 6, NOW(), 'test two', 'this is my test document number two' ),
    ( 3, 2, 7, NOW(), 'another doc', 'this is another group' ),
    ( 4, 2, 8, NOW(), 'doc number four', 'this is to test groups' );

DROP TABLE IF EXISTS test.tags;

CREATE TABLE `tags` (
  `docid` int(11) NOT NULL,
  `tagid` int(11) NOT NULL,
  UNIQUE KEY `docid` (`docid`,`tagid`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

INSERT INTO test.tags VALUES
    (1,1), (1,3), (1,5), (1,7),
    (2,6), (2,4), (2,2),
    (3,15),
    (4,7), (4,40);

+------------------------------------+
3.创建索引：
+------------------------------------+
/usr/local/webserver/sphinx/coreseek/bin/indexer -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf --all
# --all 表示创建所有的索引，也可以是具体索引的名词
/usr/local/webserver/sphinx/coreseek/bin/indexer -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf test_doc_index

#索引文件存放位置
/usr/local/webserver/sphinx/coreseek/var/data

+------------------------------------+
4.测试：
+------------------------------------+
/usr/local/webserver/sphinx/coreseek/bin/search -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf number

+------------------------------------+
5.过滤查询：
+------------------------------------+
/usr/local/webserver/sphinx/coreseek/bin/search -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf number --filter group_id 2

+------------------------------------+
5.测试中文：
+------------------------------------+
INSERT INTO `test`.`documents` (`id`, `group_id`, `group_id2`, `date_added`, `title`, `content`) VALUES
(NULL, '2', '3', '2011-02-01 00:37:12', '研究生的故事', '研究生自主创业'),
(NULL, '1', '1', '2011-01-28 00:38:22', '研究', '为了创业而研究生命科学');

#更新索引
/usr/local/webserver/sphinx/coreseek/bin/indexer -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf test_doc_index

#查询
/usr/local/webserver/sphinx/coreseek/bin/search -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf 研究

#如果用PHP代码访问Sphinx，需要先启动守护进程
/usr/local/webserver/sphinx/coreseek/bin/searchd -c /usr/local/webserver/sphinx/coreseek/etc/sphinx.conf

#创建SPHINX引擎表
CREATE TABLE sph_document1
(
    id          INTEGER UNSIGNED NOT NULL,
    weight      INTEGER NOT NULL,
    query       VARCHAR(3072) NOT NULL,
    group_id    INTEGER,
    INDEX(query)
) ENGINE=SPHINX CONNECTION="sphinx://192.168.1.100:9312/test_doc_index";

CREATE TABLE `documents` (
  `id` int(10) NOT NULL auto_increment,
  `group_id` int(10) NOT NULL,
  `group_id2` int(10) NOT NULL,
  `date_added` datetime NOT NULL,
  `title` varchar(255) NOT NULL,
  `content` text NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;

SELECT doc.id, doc.title, doc.content FROM sph_document1 AS sph JOIN documents AS doc ON sph.id = doc.id AND sph.query = 'number';