config-lucene.xml

<?xml version="1.0"?>
<!--
  ~ Copyright (C) 2001-2016 Food and Agriculture Organization of the
  ~ United Nations (FAO-UN), United Nations World Food Programme (WFP)
  ~ and United Nations Environment Programme (UNEP)
  ~
  ~ This program is free software; you can redistribute it and/or modify
  ~ it under the terms of the GNU General Public License as published by
  ~ the Free Software Foundation; either version 2 of the License, or (at
  ~ your option) any later version.
  ~
  ~ This program is distributed in the hope that it will be useful, but
  ~ WITHOUT ANY WARRANTY; without even the implied warranty of
  ~ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  ~ General Public License for more details.
  ~
  ~ You should have received a copy of the GNU General Public License
  ~ along with this program; if not, write to the Free Software
  ~ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
  ~
  ~ Contact: Jeroen Ticheler - FAO - Viale delle Terme di Caracalla 2,
  ~ Rome - Italy. email: geonetwork@osgeo.org
  -->

<config>
  <index>
    <!--
      The amount of memory to be used for buffering documents in memory.
      48MB seems to be plenty for running at least two long
       indexing jobs (eg. importing 20,000 records) and keeping disk
       activity for lucene index writing to a minimum.
    -->
    <RAMBufferSizeMB>48.0d</RAMBufferSizeMB>

    <!-- Determines how often segment indices are merged by addDocument(). -->
    <MergeFactor>10</MergeFactor>

    <!-- Default Lucene version to use (mainly for Analyzer creation). -->
    <luceneVersion>4_9</luceneVersion>
    <!-- How often to check if a commit is required -->
    <commitInterval>1000</commitInterval>
    <!-- If true then NRTManagerReopenThread will control how often the reader are reopened.
    	 If false then the reader will be opened everytime they are obtained.  -->
    <useNRTManagerReopenThread>true</useNRTManagerReopenThread>
    <!--
    	Only applies if useNRTManagerReopenThread is true
    	Maximum time until a new  reader must be opened; this sets the upper bound
    	on how slowly reopens may occur
    	See NRTManagerReopenThread -->
    <nrtManagerReopenThreadMaxStaleSec>5</nrtManagerReopenThreadMaxStaleSec>
    <!--
    	 Only applies if useNRTManagerReopenThread is true
    	 Minimum time until a new reader can be opened; this sets the lower bound
         on how quickly reopens may occur, when a caller
         is waiting for a specific indexing change to become visible
         See NRTManagerReopenThread-->
    <nrtManagerReopenThreadMinStaleSec>0.1</nrtManagerReopenThreadMinStaleSec>
  </index>


  <!-- Search parameters are applied at search time and does not need
    an index rebuild in order to be take into account. -->
  <search>
    <!-- Score parameters. Turning these parameters to true, affects performance. -->
    <!-- Set track doc score to true if score needs to be displayed in results using
        geonet:info/score element -->
    <trackDocScores>false</trackDocScores>
    <trackMaxScore>false</trackMaxScore>

    <!-- Not used because no Scorer defined -->
    <docsScoredInOrder>false</docsScoredInOrder>

    <!--
            By default Lucene compute score according to search criteria
            and the corresponding result set and their index content.
            In case of search with no criteria, Lucene will return top docs
            in index order (because none are more relevant than others).

            In order to change the score computation, a boost function could
            be define. Boosting query needs to be loaded in classpath.
            * RecencyBoostingQuery will promote recently modified documents
    -->

    <!--
      <boostQuery name="org.fao.geonet.kernel.search.function.RecencyBoostingQuery">
      <Param name="multiplier" type="double" value="2.0"/>
      <Param name="maxDaysAgo" type="int" value="365"/>
      <Param name="dayField" type="java.lang.String" value="_changeDate"/>
      </boostQuery>
     -->


    <!--
      List of fields to dump when using q service. Fields must be stored in the index.

	  The attribute 'multilingualSortField' flag fields that are used for sorting also may have translations.
	  This is the solution for http://trac.osgeo.org/geonetwork/ticket/1112
	  This is an issue where searching by one field and sorting by another will result
	  in an incorrect sorting. The reason is that sorted field may have multiple translations.
	  If the document found is one language (say french) and the UI language is english then
	  then the french translation will be used for sorting even though when the metadata
	  is viewed by user the metadata will be in english.

	  The following fields are the sort field that can have translations and therefore
	  need special care when indexing and sorting.
	   -->
    <dumpFields>
      <field name="_isTemplate" tagName="isTemplate"/>
      <field name="_isHarvested" tagName="isHarvested"/>
      <field name="_popularity" tagName="popularity"/>
      <field name="_rating" tagName="rating"/>
      <field name="feedbackCount" tagName="feedbackCount"/>
      <field name="_displayOrder" tagName="displayOrder"/>
      <field name="_view" tagName="view"/>
      <field name="_notify" tagName="notify"/>
      <field name="_download" tagName="download"/>
      <field name="_dynamic" tagName="dynamic"/>
      <field name="_featured" tagName="featured"/>
      <field name="_owner" tagName="owner"/>
      <field name="_userinfo" tagName="userinfo"/>
      <field name="_ownername" tagName="ownername"/>
      <field name="_cat" tagName="category"/>
      <field name="topicCat" tagName="topicCat"/>
      <field name="inspirethemewithac" tagName="inspirethemewithac"/>
      <field name="_valid" tagName="valid"/>
      <field name="_valid_schematron-rules-geonetwork" tagName="valid_schematron-rules-geonetwork"/>
      <field name="_valid_schematron-rules-iso" tagName="valid_schematron-rules-iso"/>
      <field name="_valid_schematron-rules-inspire" tagName="valid_schematron-rules-inspire"/>
      <field name="_valid_xsd" tagName="valid_xsd"/>
      <field name="_selected" tagName="selected"/>
      <field name="_source" tagName="source"/>
      <field name="_status" tagName="mdStatus"/>
      <field name="_edit" tagName="edit"/>
      <field name="_root" tagName="root"/>
      <field name="_title" tagName="title" multilingualSortField="true"/>
      <field name="_docLocale" tagName="docLocale"/>
      <field name="_locale" tagName="_locale"/>
      <field name="_defaultTitle" tagName="defaultTitle"/>
      <field name="createDate" tagName="creationDate"/>
      <field name="revisionDate" tagName="revisionDate"/>
      <field name="publicationDate" tagName="publicationDate"/>
      <field name="abstract" tagName="abstract" multilingualSortField="true"/>
      <field name="_defaultAbstract" tagName="defaultAbstract"/>
      <field name="keyword" tagName="keyword"/>
      <field name="keywordGroup" tagName="keywordGroup"/>
      <field name="parentUuid" tagName="parentId"/>
      <field name="type" tagName="type"/>
      <field name="identifier" tagName="identifier"/>
      <field name="image" tagName="image"/>
      <field name="link" tagName="link"/>
      <field name="format" tagName="format"/>
      <field name="denominator" tagName="denominator"/>
      <field name="resolution" tagName="resolution"/>
      <field name="crs" tagName="crs"/>
      <field name="crsDetails" tagName="crsDetails"/>
      <field name="credit" tagName="credit"/>
      <field name="cl_status" tagName="status"/>
      <field name="cl_status_text" tagName="status_text"/>
      <field name="updateFrequency" tagName="updateFrequency"/>
      <field name="lineage" tagName="lineage"/>
      <field name="responsibleParty" tagName="responsibleParty"/>
      <field name="MD_LegalConstraintsOtherConstraints" tagName="legalConstraints"/>
      <field name="MD_LegalConstraintsUseLimitation" tagName="legalConstraints"/>
      <field name="MD_SecurityConstraintsUseLimitation" tagName="securityConstraints"/>
      <field name="MD_ConstraintsUseLimitation" tagName="resourceConstraints"/>
      <field name="cl_classification_text" tagName="classification_text"/>
      <field name="cl_maintenanceAndUpdateFrequency_text"
             tagName="maintenanceAndUpdateFrequency_text"/>
      <field name="cl_spatialRepresentationType_text" tagName="spatialRepresentationType_text"/>
      <field name="datasetLang" tagName="datasetLang"/>
      <field name="mdLanguage" tagName="mdLanguage"/>
      <field name="serviceType" tagName="serviceType"/>
      <field name="tempExtentBegin" tagName="tempExtentBegin"/>
      <field name="tempExtentEnd" tagName="tempExtentEnd"/>
      <field name="geoBox" tagName="geoBox"/>
      <field name="extentDesc" tagName="geoDesc"/>
      <field name="geoDescCode" tagName="geoDescCode"/>
      <field name="_indexingError" tagName="idxError"/>
      <field name="_indexingErrorMsg" tagName="idxMsg"/>
      <field name="_op0" tagName="publishedForGroup"/>
      <field name="_groupOwner" tagName="groupOwner"/>
      <field name="_logo" tagName="logo"/>
      <field name="standardName" tagName="standardName"/>
      <field name="_groupWebsite" tagName="groupWebsite"/>
      <field name="attributeTable" tagName="attributeTable"/>
    </dumpFields>
  </search>


  <!-- Default analyzer to use for all fields not defined in the fieldSpecificAnalyzer section.
    If not set, GeoNetwork use a default per field analyzer (ie. fieldSpecificAnalyzer is not
    take into account). The default analyzer is defined in SearchManager.

    Example:
    org.apache.lucene.analysis.fr.FrenchAnalyzer

  <defaultAnalyzer name="org.apache.lucene.analysis.standard.StandardAnalyzer">
  <Param name="version" type="org.apache.lucene.util.Version"/>
  </defaultAnalyzer>
  -->
  <defaultAnalyzer name="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
  <!-- TODO: Add a language specific analyzer according to:
     * metadata language
     * metadata elements language (ie. PT_FreeText elements)
  -->


  <!-- Field analyzer
    Define here specific analyzer for each fields stored in the index

    For example adding a different analyzer for any (ie. full text search)
    could be better than a standard analyzer which has a particular way of
    creating tokens.

    In that situation, when field is "mission AD-T" is tokenized to "mission" "ad" & "t"
    using StandardAnalyzer. A WhiteSpaceTokenizer tokenized to "mission" "AD-T"
    which could be better in some situation. But when field is "mission AD-34T" is tokenized
    to "mission" "ad-34t" using StandardAnalyzer due to number.

    doeleman: UUID must be case insensitive, as its parts are hexadecimal numbers which
    are not case sensitive. StandardAnalyzer is recommended for UUIDS.

    A list of analyzer is available http://lucene.apache.org/java/2_4_0/api/org/apache/lucene/analysis/Analyzer.html
    Commons analyzer:
    * org.apache.lucene.analysis.standard.StandardAnalyzer
    * org.apache.lucene.analysis.WhitespaceAnalyzer
    * org.apache.lucene.analysis.SimpleAnalyzer
    * org.fao.geonet.kernel.search.GeoNetworkAnalyzer (recommended for wildcard query support)

    The analyzer must be in the classpath.

  -->
  <fieldSpecificAnalyzer>
    <Field name="_uuid" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
    <Field name="standardName" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>
    <Field name="parentUuid" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
    <Field name="operatesOn" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
    <Field name="operatesOnIdentifier" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
    <Field name="hassource" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>
    <Field name="hasfeaturecat" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>

    <!--
    <Field name="any" analyzer="org.fao.geonet.kernel.search.GeoNetworkAnalyzer"/>

    <Field name="any" analyzer="org.apache.lucene.analysis.standard.StandardAnalyzer">
      <Param name="version" type="org.apache.lucene.util.Version"/>
      <Param name="stopWords" type="java.io.File" value="/path/to/resources/stopwords/en.txt"/>
    </Field>
    -->
    <Field name="subject" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>
    <Field name="_cat" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>


    <Field name="keyword" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>
    <Field name="inspirerelated" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>
    <Field name="_groupPublished" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>
    <Field name="_source" analyzer="org.apache.lucene.analysis.core.KeywordAnalyzer"/>

  </fieldSpecificAnalyzer>

  <fieldSpecificSearchAnalyzer>
    <!-- Define here analyzers to be overriden from fieldSpecificAnalyzer.
      By default, indexing and searching per field analyzers are the same.

      In some case, an analyzer could be applied at indexing and another
      at searching time. For example when using a SynonymAnalyzer. When adding
      Londres, Londinium, Londona for London at indexing time, then there is no
      need to add those synonyms for search if users search for Londres, it will match.
      We only need synonym expansion during indexing or during searching, not both.
    -->
  </fieldSpecificSearchAnalyzer>

  <!-- Document boosting configuration.

    Document boosting allows to define custom boost factor for a document
    or for document fields at index time which
    will be use for score computation at search time.

    Note: Do not abuse of document boost
    because it may lead to promote too much some kind of documents
    or the contrary and make end-user not so confident of your search engine!

  -->
  <!-- Boosting factor for fields. This parameter will impact queries using OR operator.
  <fieldBoosting>
    <Field name="title" boost="1.5F"/>
  </fieldBoosting>

  It could be relevant to also remove some field from scoring using this:
   * If not, user privileges will be take into account to compute the score.
  -->
  <fieldBoosting>
    <Field name="_op0" boost="0.0F"/>
    <Field name="_op1" boost="0.0F"/>
    <Field name="_op2" boost="0.0F"/>
    <Field name="_dummy" boost="0.0F"/>
    <Field name="_isTemplate" boost="0.0F"/>
    <Field name="_owner" boost="0.0F"/>
  </fieldBoosting>


  <!-- Boosting factor for document based on document values.
    Parameters:
    * fields: A comma separated value of fields.
    * values: A comma separated value of value for each field. Use NOTNULL to check any field values.
    * boost: A comma separated value of boost factor for each field (Float).

    "The boost factor values you should use depend on what you’re trying to achieve;
    you’ll need to do some experimentation and
    tuning to achieve the desired effect." source: Lucene In Action

  <boostDocument name="org.fao.geonet.kernel.search.function.ImportantDocument">
    <!- - Example to promote series and not promote records part of a series - ->
    <Param name="fields" type="java.lang.String" value="type,parentUuid"/>
    <Param name="values" type="java.lang.String" value="series,NOTNULL"/>
    <Param name="boosts" type="java.lang.String" value=".1F,-.3F"/>
    <!- - Example to promote series and service and records with keyword containing elevation
    <Param name="fields" type="java.lang.String" value="type,type,keyword"/>
    <Param name="values" type="java.lang.String" value="series,service,Elevation"/>
    <Param name="boosts" type="java.lang.String" value=".1F,-.3F,.4F"/>- ->
  </boostDocument>
  -->

  <!-- All Lucene fields that are tokenized must be kept here because it
       is impossible unfortunately from Lucene API to work out which fields are
        tokenized and which aren't unless we read documents and we may not have
        an index to do this on so since most fields are not tokenized we
        keep a list of tokenized fields here
   -->
  <tokenized>
    <Field name="any"/>
    <Field name="anylight"/>
    <Field name="abstract"/>
    <Field name="title"/>
    <Field name="altTitle"/>
    <Field name="keywordType"/>
    <!--<Field name="orgName"/>-->
    <Field name="specificationTitle"/>
    <Field name="levelName"/>
    <Field name="subject"/>
  </tokenized>

  <!-- All Lucene numeric fields.
    Use of numeric field will increase index size.
    It could give better search results for numeric values.

    Type attribute : int (default), double, long, float
    Precision attribute : see NumericUtils.PRECISION_STEP_DEFAULT
  -->
  <numeric>
    <Field name="denominator"/>
    <Field name="feedbackCount"/>
    <Field name="_rating"/>
    <Field name="northBL" type="double"/>
    <Field name="eastBL" type="double"/>
    <Field name="southBL" type="double"/>
    <Field name="westBL" type="double"/>
  </numeric>

  <!-- List all of the lucene field names which will have similarity applied to them
       To disable set enabled to false.

       If enabled is false or not present then similarity will be applied to all fields (except some special case instances)
  -->
  <fuzzyMatching enabled="true">
    <Field name="any"/>
    <Field name="anylight"/>
    <Field name="title"/>
    <Field name="altTitle"/>
    <Field name="abstract"/>
    <Field name="specificationTitle"/>
  </fuzzyMatching>
</config>