10.Solr4.10.3数据导入(DIH全量增量同步Mysql数据)

create database solr;

use solr;

DROP TABLE IF EXISTS student;

CREATE TABLE student (

id char(10) NOT NULL,

stu_name varchar(50) DEFAULT NULL,

stu_sex int(1) DEFAULT NULL,

stu_address varchar(200) DEFAULT NULL,

updateTime timestamp NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,

isDeleted int(1) DEFAULT 0,

PRIMARY KEY (id)

) ENGINE=InnoDB DEFAULT CHARSET=utf8;

INSERT INTO student VALUES (‘1000000001‘, ‘李莉‘, 0, ‘上海市中山路‘,default,default);

INSERT INTO student VALUES (‘1000000002‘, ‘Tom‘, 1, ‘NewYork‘,default,default);

INSERT INTO student VALUES (‘1000000003‘, ‘张小贝‘, 0, ‘江西省泰和县中山路‘,default,default);

INSERT INTO student VALUES (‘1000000004‘, ‘鲍勃‘, 1, ‘北京市海淀区知春路‘,default,default);

INSERT INTO student VALUES (‘1000000005‘, ‘Tim‘, 0, ‘Paris‘,default,default);

select * from student;

<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">

<lst name="defaults">

<str name="config">data-config.xml</str>

</lst>

</requestHandler>

<?xml version="1.0" encoding="UTF-8"?>

<dataConfig>

<dataSource type="JdbcDataSource" driver="com.mysql.jdbc.Driver" url="jdbc:mysql://192.168.137.168:3306/solr" user="root" password="root" batchSize="-1" />

<document name="testDoc">

<entity name="student" pk="id"

query="select * from student">

<field column="id" name="id"/>

<field column="stu_name" name="stu_name"/>

<field column="stu_sex" name="stu_sex"/>

<field column="stu_address" name="stu_address"/>

</entity>

</document>

</dataConfig>

<field name="stu_name" type="text_ik" indexed="true" stored="true" multiValued="false" /> 

<field name="stu_sex" type="int" indexed="true" stored="true" multiValued="false" /> 

<field name="stu_address" type="text_ik" indexed="true" stored="true" multiValued="false" />

<?xml version="1.0" encoding="UTF-8"?>

<dataConfig>

<dataSource type="JdbcDataSource" driver="com.mysql.jdbc.Driver" url="jdbc:mysql://192.168.137.168:3306/solr" user="root" password="root" batchSize="-1" />

<document name="testDoc">

<entity name="student" pk="id"

query="select * from student limit ${dataimporter.request.length} offset ${dataimporter.request.offset}">

<field column="id" name="id"/>

<field column="stu_name" name="stu_name"/>

<field column="stu_sex" name="stu_sex"/>

<field column="stu_address" name="stu_address"/>

</entity>

</document>

</dataConfig>

<?xml version="1.0" encoding="UTF-8"?>

<dataConfig>

<dataSource type="JdbcDataSource" driver="com.mysql.jdbc.Driver" url="jdbc:mysql://192.168.137.168:3306/solr" user="root" password="root" batchSize="-1" />

<document name="testDoc">

<entity name="student" pk="id"

query="select * from student where isDeleted=0"

deltaImportQuery="select * from student where id=‘${dih.delta.id}‘"

deltaQuery="select id from student where updateTime> ‘${dataimporter.last_index_time}‘ and isDeleted=0"

deletedPkQuery="select id from student where isDeleted=1">

<field column="id" name="id"/>

<field column="stu_name" name="stu_name"/>

<field column="stu_sex" name="stu_sex"/>

<field column="stu_address" name="stu_address"/>

</entity>

</document>

</dataConfig>

update student set stu_name="jerry" where id = ‘1000000005‘;

update student set isDeleted=1 where id = ‘1000000004‘;

INSERT INTO student VALUES (‘1000000006‘, ‘Tim11‘, 0, ‘Paris‘,default,default);

<listener>

<listener-class>

org.apache.solr.handler.dataimport.scheduler.ApplicationListener

</listener-class>

</listener>

#################################################

# #

# dataimport scheduler properties #

# #

#################################################

# to sync or not to sync

# 1 - active; anything else - inactive

syncEnabled=1

# which cores to schedule

# in a multi-core environment you can decide which cores you want syncronized

# leave empty or comment it out if using single-core deployment

# syncCores=game,resource

syncCores=collection1

# solr server name or IP address

# [defaults to localhost if empty]

server=192.168.137.168

# solr server port

# [defaults to 80 if empty]

port=8080

# application name/context

# [defaults to current ServletContextListener‘s context (app) name]

webapp=solr

# URLparams [mandatory]

# remainder of URL

#http://localhost:8983/solr/collection1/dataimport?command=delta-import&clean=false&commit=true

params=/dataimport?command=delta-import&clean=false&commit=true

# schedule interval

# number of minutes between two runs

# [defaults to 30 if empty]

interval=1

# 重做索引的时间间隔，单位分钟，默认7200，即1天; 

# 为空,为0,或者注释掉:表示永不重做索引

reBuildIndexInterval=2

# 重做索引的参数

reBuildIndexParams=/dataimport?command=full-import&clean=true&commit=true

# 重做索引时间间隔的计时开始时间，第一次真正执行的时间=reBuildIndexBeginTime+reBuildIndexInterval*60*1000；

# 两种格式：2012-04-11 03:10:00 或者 03:10:00，后一种会自动补全日期部分为服务启动时的日期

reBuildIndexBeginTime=03:10:00