Sample XML file for configuring Portal Search

You can adapt this sample XML file for purposes.

<?xml version="1.0" encoding="UTF-8" ?> 
<searchServices>
  <searchService id="com.ibm.lotus.search.plugins.pse.PlacesSearchFactoryImp">
    <searchServiceInfo extensionId="com.ibm.lotus.search.plugins.pse.PlacesSearchFactoryImp">
      <serviceName 
        resourceBundle="com.ibm.wps.services.search.messages.SearchConfigMessages">
        default.pse.service.name</serviceName> 
      <property name="propertyName1" value="propertyValue1" /> 
    </searchServiceInfo>
    <collections>
      <collection id="c:/ibm/wp_profiles/PortalServer/collections/stam">
        <collectionInfo removeCommonWords="true">
          <location>c:/ibm/wp_profiles/PortalServer/collections/stam</location> 
          <collectionName 
            resourceBundle="com.ibm.wps.services.search.messages.SearchConfigMessages">
            stam.collection.name</collectionName> 
          <description 
            resourceBundle="com.ibm.wps.services.search.messages.SearchConfigMessages">
            stam.collection.description</description> 
          <defaultLanguage>fr</defaultLanguage> 
          <categorizer>UserDefined</categorizer> 
          <summarizer>Automatic</summarizer> 
        </collectionInfo>
        <crawlers>
          <crawler id="crawler1">
            <crawlerInfo url="http://host:port/seedlist/myserver?Source=Portal">
              <crawlerName 
                resourceBundle="com.ibm.wps.services.search.messages.SearchConfigMessages">
                crawler.name</crawlerName> 
              <contentSourceType>Seedlist</contentSourceType> 
              <level>1</level> 
              <numDocsCollect>-1</numDocsCollect> 
              <completeCrawl>true</completeCrawl> 
              <collectTimeLimit>60</collectTimeLimit> 
              <fetchDocTimeLimit>5</fetchDocTimeLimit> 
              <linksExpirationPeriod>-1</linksExpirationPeriod> 
              <brokenLinksTimeToLive>10</brokenLinksTimeToLive> 
              <numProcesses>5</numProcesses> 
              <encoding alwaysUse="false">Windows-1252</encoding> 
              <addDocsAutomatically>true</addDocsAutomatically> 
              <obeyRobotsTxt>true</obeyRobotsTxt> 
              <proxy server="" port="8080" /> 
              <socks server="" port="1080" /> 
              <securityRealms>
                <realm username="wpsadmin" password="wpsadmin" host="host">realmName</realm> 
              </securityRealms>
            </crawlerInfo>
            <schedulers>
              <scheduler>
                <startTime day="02" month="09" year="2008" hour="24" min="0" /> 
                <period num="1" unit="week" /> 
              </scheduler>
            </schedulers>
            <filters>
              <filter name="rule-1" indexing="true" include="true">
                <basis type="url">http://host:port/seedlist</basis> 
              </filter>
            </filters>
          </crawler>
        </crawlers>
      </collection>
    </collections>
  </searchService>
</searchServices>

 

+

Search Tips   |   Advanced Search