Skip to main content
Jump to: navigation, search

Difference between revisions of "SMILA/Documentation/LuceneIndexPipelet"

(Configuration files)
m
 
(11 intermediate revisions by 6 users not shown)
Line 1: Line 1:
== Bundle: <tt>org.eclipse.smila.lucene.LuceneIndexService</tt> ==
+
{{Note|Deprecated:
 
+
The Lucene integration is outdated. Please take a look at the new Solr integration <tt>org.eclipse.smila.solr</tt> which is described here: [[SMILA/Documentation/Solr]].}}
=== Description ===
+
This ProcessingService is used to index SMILA records in a Lucene document index. It supports adding, updating and deleting of records.
+
 
+
=== Configuration ===
+
 
+
==== Annotations ====
+
The LuceneIndexService uses the Annotation <tt>org.eclipse.smila.lucene.LuceneIndexService</tt> on records to decide how to handle a record. It supports the following required values.
+
{| border = 1
+
!Name!!Value!!Description
+
|-
+
|indexName||a String||the name of the index to work on
+
|-
+
|executionMode||ADD or DELETE||''ADD'' - add or update the record, ''DELETE'' - delete the record from the index
+
|}
+
 
+
==== Configuration files ====
+
 
+
* <tt>configuration/org.eclipse.smila.search.datadictionary/DataDictionary.xml</tt>
+
Here the Lucene index structure and the search template are configured. It is possible to define more than one index here. The index to work on is set by the Annotation "indexName". The defined "FieldNo" are referenced in LuceneAttributeMapping.xml and LuceneAttachmentMapping.xml. For more information about configuration of DataDictionary.xml see Anyfinder documentation.
+
 
+
 
+
* <tt>configuration/org.eclipse.smila.lucene/Mappings.xml</tt>
+
Here a mapping of attribute and attachment names to Lucene "FieldNo" (defined in DataDictionary.xml) is configured. It is possible to define mappings for multiple indexes in this file, using the same "indexName" as in file DataDictionary.xml.
+
 
+
==== Example ====
+
 
+
The following example was used in the SMILA example application to index records delivered by Filesystem- and WebCrawler.
+
 
+
'''addpipeline.bpel'''
+
<source lang="xml">
+
...
+
<extensionActivity name="invokeLuceneService">
+
    <proc:invokeService>
+
        <proc:service name="LuceneIndexService" />
+
        <proc:variables input="request" output="request" />
+
        <proc:setAnnotations>
+
            <rec:An n="org.eclipse.smila.lucene.LuceneIndexService">
+
                <rec:V n="indexName">test_index</rec:V>
+
                <rec:V n="executionMode">ADD</rec:V>
+
            </rec:An>
+
        </proc:setAnnotations>
+
    </proc:invokeService>
+
</extensionActivity>
+
...
+
</source>
+
 
+
'''DataDictionary.xml'''
+
<source lang="xml">
+
<?xml version="1.0" encoding="UTF-8"?>
+
<AnyFinderDataDictionary xmlns="http://www.anyfinder.de/DataDictionary" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+
  xsi:schemaLocation="http://www.anyfinder.de/DataDictionary ../xml/AnyFinderDataDictionary.xsd">
+
  <Index Name="test_index">
+
    <Connection xmlns="http://www.anyfinder.de/DataDictionary/Connection" MaxConnections="5"/>
+
    <IndexStructure xmlns="http://www.anyfinder.de/IndexStructure" Name="test_index">
+
      <Analyzer ClassName="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
+
      <IndexField FieldNo="5" IndexValue="true" Name="Title" StoreText="true" Tokenize="true" Type="Text"/>
+
      <IndexField FieldNo="4" IndexValue="true" Name="Url" StoreText="true" Tokenize="false" Type="Text">
+
        <Analyzer ClassName="org.apache.lucene.analysis.WhitespaceAnalyzer"/>
+
      </IndexField>
+
      <IndexField FieldNo="3" IndexValue="true" Name="Date" StoreText="true" Tokenize="false" Type="Text"/>
+
      <IndexField FieldNo="2" IndexValue="true" Name="Path" StoreText="true" Tokenize="true" Type="Text"/>
+
      <IndexField FieldNo="1" IndexValue="true" Name="Filename" StoreText="true" Tokenize="true" Type="Text"/>
+
      <IndexField FieldNo="0" IndexValue="true" Name="Content" StoreText="true" Tokenize="true" Type="Text"/>
+
    </IndexStructure>
+
    <Result>
+
      <Field FieldNo="0" Name="ID"/>
+
    </Result>
+
    <Configuration xmlns="http://www.anyfinder.de/DataDictionary/Configuration" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+
      xsi:schemaLocation="http://www.anyfinder.de/DataDictionary/Configuration ../xml/DataDictionaryConfiguration.xsd">
+
      <DefaultConfig>
+
        <Field FieldNo="5">
+
          <FieldConfig Constraint="optional" Weight="1" xsi:type="FTText">
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="OR" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
        <Field FieldNo="4">
+
          <FieldConfig Constraint="optional" Weight="1" xsi:type="FTText">
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="OR" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
        <Field FieldNo="3">
+
          <FieldConfig Constraint="optional" Weight="1" xsi:type="FTText">
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="OR" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
        <Field FieldNo="2">
+
          <FieldConfig Constraint="optional" Weight="1" xsi:type="FTText">
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="OR" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
        <Field FieldNo="1">
+
          <FieldConfig Constraint="optional" Weight="1" xsi:type="FTText">
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="OR" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
        <Field FieldNo="0">
+
          <FieldConfig Constraint="required" Weight="1" xsi:type="FTText">
+
            <NodeTransformer xmlns="http://www.anyfinder.de/Search/ParameterObjects" Name="urn:ExtendedNodeTransformer">
+
              <ParameterSet xmlns="http://www.brox.de/ParameterSet"/>
+
            </NodeTransformer>
+
            <Parameter xmlns="http://www.anyfinder.de/Search/TextField" Operator="AND" Tolerance="exact"/>
+
          </FieldConfig>
+
        </Field>
+
      </DefaultConfig>
+
      <Result Name="">
+
        <ResultField FieldNo="5" Name="Title"/>
+
        <ResultField FieldNo="4" Name="Url"/>
+
        <ResultField FieldNo="3" Name="Date"/>
+
        <ResultField FieldNo="2" Name="Path"/>
+
        <ResultField FieldNo="1" Name="Filename"/>
+
      </Result>
+
      <HighlightingResult Name="">
+
        <HighlightingResultField FieldNo="0" Name="Content" xsi:type="HLTextField">
+
          <HighlightingTransformer Name="urn:Sentence">
+
            <ParameterSet xmlns="http://www.brox.de/ParameterSet">
+
              <Parameter Name="MaxLength" xsi:type="Integer">
+
                <Value>300</Value>
+
              </Parameter>
+
              <Parameter Name="MaxHLElements" xsi:type="Integer">
+
                <Value>999</Value>
+
              </Parameter>
+
              <Parameter Name="MaxSucceedingCharacters" xsi:type="Integer">
+
                <Value>30</Value>
+
              </Parameter>
+
              <Parameter Name="SucceedingCharacters" xsi:type="String">
+
                <Value>...</Value>
+
              </Parameter>
+
              <Parameter Name="SortAlgorithm" xsi:type="String">
+
                <Value>Occurrence</Value>
+
              </Parameter>
+
              <Parameter Name="TextHandling" xsi:type="String">
+
                <Value>ReturnSnipplet</Value>
+
              </Parameter>
+
            </ParameterSet>
+
          </HighlightingTransformer>
+
          <HighlightingParameter xmlns="http://www.anyfinder.de/DataDictionary/Configuration/TextHighlighting"/>
+
        </HighlightingResultField>
+
      </HighlightingResult>
+
    </Configuration>
+
  </Index>
+
  <Index Name="another_index">
+
    ...
+
  </Index>
+
</AnyFinderDataDictionary>
+
</source>
+
 
+
'''Mappings.xml'''
+
<source lang="xml">
+
<?xml version="1.0" encoding="utf-8" ?>
+
<Mappings xmlns="http://www.eclipse.org/smila/lucene">
+
    <Mapping indexName="test_index">
+
        <Attributes>
+
            <Attribute name="Filename" fieldNo="1" />
+
            <Attribute name="Path" fieldNo="2" />   
+
            <Attribute name="LastModifiedDate" fieldNo="3" />
+
            <Attribute name="Url" fieldNo="4" />
+
            <Attribute name="Title" fieldNo="5" />
+
        </Attributes>
+
        <Attachments>
+
            <Attachment name="Text" fieldNo="0" />
+
        </Attachments>
+
    </Mapping>
+
    <Mapping indexName="another_index">
+
        <Attributes>
+
        ...
+
        </Attributes>
+
        <Attachments>
+
        ...
+
        </Attachments>
+
    </Mapping>
+
</Mappings>
+
</source>
+
 
+
 
+
[[Category:SMILA]] [[Category:SMILA/Processing Service]]
+

Latest revision as of 05:51, 19 January 2012

Note.png
Deprecated: The Lucene integration is outdated. Please take a look at the new Solr integration org.eclipse.smila.solr which is described here: SMILA/Documentation/Solr.

Back to the top