Indexing using Data Import Handler

• For full import: Create the following dataconfig.xml to define mapping of database table columns to Solr:

  <dataconfig> 
      <datasource driver="org.hsqldb.jdbcDriver" url="jdbc:mysql:/temp/example/ex" user="user" 
                  password="user"/> 
      <document name="products"> 
          <entity name="item" query="select * from item"> 
              <field column="ID" name="id"/> 
              <field column="NAME" name="name"/> 
          </entity> 
      </document> 
  </dataconfig>

• For delta import: Create the following dataconfig.xml:

  <dataconfig> 
      <dataSource 
      driver="com.mysql.jdbc.Driver" "jdbc:mysql:/temp/example/ex" user="user" password="password" /> 
      <document name="rrr"> 
      <entity name="item" pk="ID" query="select             ID,NAME,PRICE,WEIGHT,last_modified  from item" 
              deltaimportquery="select ID,NAME,PRICE,WEIGHT,last_modified from item where ID='${dataimporter.delta.id}'" 
              deltaquery="select id from item where last_modified > '${dataimporter.last index_time}'"> 
          <field column="ID" name="uid"/> 
          <field column="NAME" name="name_t"/> 
          <field column="PRICE" name="price_f"/> 
          <field column="WEIGHT" name="weight_d"/> 
          <entity name="feature" pk="ITEM_ID" 
                  query="select description as         features from feature where item_id='${item.ID}'"> 
              <field name="features_t" column="features"/> 
          </entity> 
          <entity name="item_category" pk="ITEM_ID, CATEGORY_ID" 
                  query="select CATEGORY_ID from item_category where ITEM_ID='${item.ID}'"> 
              <entity name="category" pk="ID" 
                      query="select description as cat from category where id = '${item_category.CATEGORY_ID}'"> 
                  <field column="cat" n a m 
                         e="cat t"/> 
              </entity> 
          </entity> 
      </entity> 
  </dataconfig>

• Ensure that last_modified is the column name of the table that you index and the column has time stamp.

• Unless you have this column mapped, partial import fails.

• The latest timestamp is created in the dataimport.properties available in the collection location.

<!-- 
  <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler"> 
    <lst name="defaults"> 
      <str name="config">data-config.xml</str> 
    </lst> 
  </requestHandler> 
  -->