dse search apache uima integration
我在CentOS 7.3.1611(Core)上安装了DSE 5.1,并安装了solr 6.0.1。 UIMA在eclipse中为我的annotator项目配置。dse search apache uima integration
我下面Solr的文档: https://wiki.apache.org/solr/Solr4UIMA
与UIMA创建的项目有一个简单的注释来获得个人的名字,已经从UIMA的CAS可视化调试工作正常。这个jar已经创建并复制到了solr lib目录(DSE_HOME/solr/lib)中,这里也是uima集成的solr(SOLR_HOME/contrib/uima/lib,SOLR_HOME/contrib/uima/lucene-lib ,SOLR_HOME/dist/solr-uima-version)。
在卡桑德拉创建我的表是:
CREATE TABLE uima_solr.person_annotator (
id int PRIMARY KEY,
apellido text,
nombre text,
nombrecompleto text,
solr_query text,
uimaname set<text>
Solr的核心使用模式:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<schema name="autoSolrSchema" version="1.5">
<types>
<fieldType class="org.apache.solr.schema.TextField" name="TextField">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType class="org.apache.solr.schema.TrieIntField" name="TrieIntField"/>
</types>
<fields>
<field indexed="true" multiValued="false" name="nombrecompleto" stored="true" type="TextField"/>
<field indexed="true" multiValued="false" name="apellido" stored="true" type="TextField"/>
<field indexed="true" multiValued="false" name="nombre" stored="true" type="TextField"/>
<field docValues="true" indexed="true" multiValued="false" name="id" stored="true" type="TrieIntField"/>
<field indexed="true" multiValued="false" name="all" stored="false" type="TextField"/>
<field indexed="true" multiValued="true" name="uimaname" stored="true" type="TextField"/>
</fields>
<uniqueKey>id</uniqueKey>
<defaultSearchField>all</defaultSearchField>
<copyField source="nombrecompleto" dest="all"/>
<copyField source="apellido" dest="all"/>
<copyField source="nombre" dest="all"/>
</schema>
而且solr_config如下:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<config>
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<luceneMatchVersion>LUCENE_6_0_0</luceneMatchVersion>
<dseTypeMappingVersion>2</dseTypeMappingVersion>
<directoryFactory class="solr.StandardDirectoryFactory" name="DirectoryFactory"/>
<indexConfig>
<rt>false</rt>
<useCompoundFile>false</useCompoundFile>
<ramBufferSizeMB>512</ramBufferSizeMB>
<mergeFactor>10</mergeFactor>
<reopenReaders>true</reopenReaders>
<deletionPolicy class="solr.SolrDeletionPolicy">
<str name="maxCommitsToKeep">1</str>
<str name="maxOptimizedCommitsToKeep">0</str>
</deletionPolicy>
<infoStream file="INFOSTREAM.txt">false</infoStream>
</indexConfig>
<jmx/>
<updateHandler class="solr.DirectUpdateHandler2">
<autoSoftCommit>
<maxTime>10000</maxTime>
</autoSoftCommit>
</updateHandler>
<query>
<maxBooleanClauses>1024</maxBooleanClauses>
<filterCache class="solr.SolrFilterCache" highWaterMarkMB="256" lowWaterMarkMB="128"/>
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<useColdSearcher>true</useColdSearcher>
<maxWarmingSearchers>16</maxWarmingSearchers>
</query>
<requestDispatcher handleSelect="true">
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000"/>
<httpCaching never304="true"/>
</requestDispatcher>
<requestHandler class="solr.SearchHandler" default="true" name="search">
<lst name="defaults">
<int name="rows">10</int>
</lst>
</requestHandler>
<requestHandler class="com.datastax.bdp.search.solr.handler.component.CqlSearchHandler" name="solr_query">
<lst name="defaults">
<int name="rows">10</int>
</lst>
</requestHandler>
<!--<requestHandler class="solr.UpdateRequestHandler" name="/update"/>-->
<requestHandler class="solr.UpdateRequestHandler" name="/update/csv" startup="lazy"/>
<requestHandler class="solr.UpdateRequestHandler" name="/update/json" startup="lazy"/>
<requestHandler class="solr.FieldAnalysisRequestHandler" name="/analysis/field" startup="lazy"/>
<requestHandler class="solr.DocumentAnalysisRequestHandler" name="/analysis/document" startup="lazy"/>
<requestHandler class="solr.admin.AdminHandlers" name="/admin/"/>
<requestHandler class="solr.PingRequestHandler" name="/admin/ping">
<lst name="invariants">
<str name="qt">search</str>
<str name="q">solrpingquery</str>
</lst>
<lst name="defaults">
<str name="echoParams">all</str>
</lst>
</requestHandler>
<requestHandler class="solr.DumpRequestHandler" name="/debug/dump">
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="echoHandler">true</str>
</lst>
</requestHandler>
<admin>
<defaultQuery>*:*</defaultQuery>
</admin>
<updateRequestProcessorChain default="true" name="uima">
<processor class="org.apache.solr.uima.processor.UIMAUpdateRequestProcessorFactory">
<lst name="uimaConfig">
<lst name="runtimeParameters"></lst>
<!-- Under $SOLR_HOME/solr/example-->
<str name="analysisEngine">desc/descPersonAnnotator.xml</str>
<bool name="ignoreErrors">false</bool>
<lst name="analyzeFields">
<bool name="merge">false</bool>
<arr name="fields">
<str>nombrecompleto</str>
</arr>
</lst>
<lst name="fieldMappings">
<lst name="type">
<str name="name">org.apache.uima.annotator.person</str>
<lst name="mapping">
<str name="feature">name</str>
<str name="field">uimaname</str>
</lst>
</lst>
</lst>
</lst>
</processor>
<processor class="solr.LogUpdateProcessorFactory"/>
<processor class="solr.RunUpdateProcessorFactory"/>
</updateRequestProcessorChain>
<requestHandler class="solr.UpdateRequestHandler" name="/update">
<lst name="defaults">
<str name="update.processor">uima</str>
</lst>
</requestHandler>
</config>
当我插入数据使用CQL,数据已在Lucene中正确索引,并且搜索正常,但uima注释器不工作国王。另外,当我上传文档到Solr Trought Sol命令时,文档被成功索引,搜索也在CQL中工作,但uima不起作用。我检查了日志,并没有显示任何错误。
我在Solr Apache发行版(v6.0.1)中做了相同的过程,它按预期工作。
我没有看到DSE_HOME中的核心文件以便于编辑文件,并且我没有在DSE Search中成功完成UIMA集成,我在DSE搜索的核心配置中缺少了什么?
通过不遵循Solr文档程序找到了答案,而是使用了DSE文档,特别是Update request processor and field transformer (FIT) [2017-07-17]。
一个例子可在DSE here中找到[2017年7月17日]
的过程形成上述链接显示如何映射而索引字段。通过创建适合UITA项目的jar到FIT项目并将类添加到solrconfig.xml中
此过程允许使用Solr命令和cql与solr_query在添加的元数据上执行搜索。