I am trying to setup my SOLR to import documents from my SQL file. I have found this which should go in the data-config:
<dataConfig>
<dataSource driver="org.postgresql.Driver" url="jdbc:postgresql://localhost:5432/wikipedia" user="wikipedia" password="secret" />
<document>
<entity name="page" query="SELECT page_id, page_title from page">
<field column="page_id" name="id" />
<field column="page_title" name="name" />
<entity name="revision" query="select rev_id from revision where rev_page=${page.page_id}">
<entity name="pagecontent" query="select old_text from pagecontent where old_id=${revision.rev_id}">
<field column="old_text" name="text" />
</entity>
</entity>
</entity>
</document>
</dataConfig>
In my case, my schema looks like this:
CREATE TABLE country (
id integer NOT NULL PRIMARY KEY AUTO_INCREMENT,
name varchar(255) NOT NULL
)
;
CREATE TABLE location (
id integer NOT NULL PRIMARY KEY AUTO_INCREMENT,
name varchar(255) NOT NULL,
coordinate varchar(255) NOT NULL,
country_id integer NOT NULL REFERENCES country (id)
)
;
CREATE TABLE item (
id integer NOT NULL PRIMARY KEY AUTO_INCREMENT,
title varchar(60) NOT NULL,
description varchar(900) NOT NULL,
date datetime NOT NULL,
source varchar(255) NOT NULL,
link varchar(255) NOT NULL,
location_id integer NOT NULL REFERENCES location (id)
)
;
If I want to import the following fields into Solr:
id
title
description
date
source
link
location(name)
location(co-ordinates)
Can someone please help me on my way to change the example data-config to use my data. What I am confused about are when to use "entity" and when to use "field column".
You can do it two ways eg :-
Create a Simple SQL query with Join between Item and Location
<document name="items">
<entity name="item" query="SELECT A.ID, A.TITLE, A.DESCRIPTION, A.DATE, A.SOURCE, B.COORDINATE , C.NAME FROM ITEM A, LOCATION B, COUNTRY C WHERE A.LOCATION_ID = B.ID AND B.COUNTRY_ID = C.ID">
<field column="ID" name="id" />
<field column="TITLE" name="title" />
<field column="DESCRIPTION" name="description" />
<field column="DATE" name="date" />
<field column="SOURCE" name="source" />
<field column="COORDINATE" name="coordinate" />
</entity>
</document>
Using subentities :-
<document name="items">
<entity name="item" query="SELECT A.ID, A.TITLE, A.DESCRIPTION, A.DATE, A.SOURCE, B.COORDINATE , C.NAME FROM ITEM A, LOCATION B, COUNTRY C WHERE A.LOCATION_ID = B.ID AND B.COUNTRY_ID = C.ID">
<field column="ID" name="id" />
<field column="TITLE" name="title" />
<field column="description" name="description" />
<field column="DATE" name="date" />
<field column="SOURCE" name="source" />
<entity name="location" query="select coordinate from location where id='${item.ID}'">
<field name="coordinate" column="coordinate" />
</entity>
</entity>
</document>
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.