Solr 数值溢出

Question

我在使用 DataImportHandler 的 SOLR 上遇到问题，我正在与 oracle 10g 数据库建立连接，我需要导入 1.6 亿条记录，但是当 solr 达到大约 6000 万条时，他抛出异常并中断导入：

java.sql.SQLException: Overflow Numérico
at oracle.jdbc.driver.NumberCommonAccessor.throwOverflow(NumberCommonAccessor.java:4381)
at oracle.jdbc.driver.NumberCommonAccessor.getBigDecimal(NumberCommonAccessor.java:2509)
at oracle.jdbc.driver.NumberCommonAccessor.getObject(NumberCommonAccessor.java:3247)
at oracle.jdbc.driver.T4CNumberAccessor.getObject(T4CNumberAccessor.java:313)
at oracle.jdbc.driver.OracleResultSetImpl.getObject(OracleResultSetImpl.java:1108)
at oracle.jdbc.driver.OracleResultSet.getObject(OracleResultSet.java:462)
at org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.getARow(JdbcDataSource.java:320)
at org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.access0(JdbcDataSource.java:258)
at org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.next(JdbcDataSource.java:298)
at org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.next(JdbcDataSource.java:290)
at org.apache.solr.handler.dataimport.EntityProcessorBase.getNext(EntityProcessorBase.java:133)
at org.apache.solr.handler.dataimport.SqlEntityProcessor.nextRow(SqlEntityProcessor.java:75)
at org.apache.solr.handler.dataimport.EntityProcessorWrapper.nextRow(EntityProcessorWrapper.java:243)
at org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:476)
at org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:415)
at org.apache.solr.handler.dataimport.DocBuilder.doFullDump(DocBuilder.java:330)
at org.apache.solr.handler.dataimport.DocBuilder.execute(DocBuilder.java:232)
at org.apache.solr.handler.dataimport.DataImporter.doFullImport(DataImporter.java:416)
at org.apache.solr.handler.dataimport.DataImporter.runCmd(DataImporter.java:480)
at org.apache.solr.handler.dataimport.DataImporter.run(DataImporter.java:461)

配置如下：

数据-config.xml

<dataConfig>
<dataSource 
    name="DataSourceProduction"
    type="JdbcDataSource"
    driver="oracle.jdbc.driver.OracleDriver"
    url="xxxxxxxxxxxxxxxxxxxx"
    user="xxxxx"
    password="xxxxx"
    batchSize="100"
/>

<document>

    <entity
        dataSource="DataSourceProduction"
        name="maestroObjectValue"
        pk="id"

        query="SELECT VAL.ID, VAL.OBJECT_VARIANT_ID, VAL.CHARACTERISTIC_ID, VAL.CHARACTERISTIC_VALUE_ID, VAL.VALUE_STRING, VAL.VALUE_NUMBER, VAL.TYPE, VAL.CD_ITEM_EEM, VAL.SEQUENCE, VAL.VALUE_FORMATTED FROM OBJECT_VALUE VAL"

    ><!-- END -->

        <field column="ID" name="ID" /> 
        <field column="OBJECT_VARIANT_ID" name="OBJECT_VARIANT_ID" />
        <field column="CHARACTERISTIC_ID" name="CHARACTERISTIC_ID" />
        <field column="CHARACTERISTIC_VALUE_ID" name="CHARACTERISTIC_VALUE_ID" />
        <field column="VALUE_STRING" name="VALUE_STRING" />
        <field column="VALUE_NUMBER" name="VALUE_NUMBER" />
        <field column="TYPE" name="TYPE" />
        <field column="CD_ITEM_EEM" name="CD_ITEM_EEM" />
        <field column="SEQUENCE" name="SEQUENCE" />
        <field column="VALUE_FORMATTED" name="VALUE_FORMATTED" />

        <entity 
            dataSource="DataSourceProduction"
            name="maestroObjectVariant"
            pk="id"

            query="SELECT OV.OBJECT_HEADER_ID, OV.OBJECT_TYPE_ID FROM OBJECT_VARIANT OV WHERE OV.ID = '${maestroObjectValue.OBJECT_VARIANT_ID}'"
        ><!-- END -->
            <field column="OBJECT_HEADER_ID" name="OBJECT_HEADER_ID" />
            <field column="OBJECT_TYPE_ID" name="OBJECT_TYPE_ID" />             
        </entity>


    </entity>

</document>

schema.xml

<?xml version="1.0" encoding="UTF-8" ?><schema name="objectValue" version="1.5">


<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="ID" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 

<!-- catchall field, containing all other searchable text fields (implemented
    via copyField further on in this schema  -->
<field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>


<field name="OBJECT_VARIANT_ID"         type="long" indexed="true" stored="true" multiValued="false"/>
<field name="CHARACTERISTIC_ID"         type="long" indexed="true" stored="true" multiValued="false"/>
<field name="CHARACTERISTIC_VALUE_ID"   type="long" indexed="true" stored="true" multiValued="false"/>
<field name="VALUE_STRING"              type="string" indexed="true" stored="true" multiValued="false"/>
<field name="VALUE_NUMBER"              type="double" indexed="true" stored="true" multiValued="false"/>
<field name="TYPE"                      type="int" indexed="true" stored="true" multiValued="false"/>
<field name="CD_ITEM_EEM"               type="string" indexed="true" stored="true" multiValued="false"/>
<field name="SEQUENCE"                  type="int" indexed="true" stored="true" multiValued="false"/>
<field name="VALUE_FORMATTED"           type="string" indexed="true" stored="true" multiValued="false"/>
<field name="OBJECT_HEADER_ID"          type="long" indexed="true" stored="true" multiValued="false"/>
<field name="OBJECT_TYPE_ID"            type="long" indexed="true" stored="true" multiValued="false"/>


<uniqueKey>ID</uniqueKey>


<fieldType name="string" class="solr.StrField" />
<fieldType name="int" class="solr.TrieIntField" />
<fieldType name="long" class="solr.TrieLongField" />
<fieldType name="double" class="solr.TrieDoubleField" />
<fieldType name="text_general" class="solr.TextField" />

Answer 1

尝试将 onError="skip" 添加到您的实体标签。

SOLR DIH 文档：Schema for the data config

onError : (abort|skip|continue) . The default value is 'abort' . 'skip' skips the current document. 'continue' continues as if the error did not happen.

Solr 数值溢出

Solr Numeric Overflow

java

oracle

solr

dataimporthandler