Page History

<?xml version="1.0" encoding="UTF-8"?>
<properties>
  <!-- we're including the <parsers/> element to show that it is a separate element from the
       autoDetectParserConfig element.  If it is not included, the standard default parser will
       be used -->
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.microsoft.OfficeParser"/>
    </parser>
    <parser class="org.apache.tika.parser.microsoft.OfficeParser">
      <params>
        <param name="byteArrayMaxOverride" type="int">700000000</param>
      </params>
    </parser>
  </parsers>  
  <!-- note that the autoDetectParserConfig element is separate from the <parsers/> element.
       The composite parser built in the <parsers/> element is used as the base parser
       for the AutoDetectParser. -->
  <autoDetectParserConfig>
    <!-- note that this is a test class only available in tika-core's test-jar as an example. 
         Specify your own custom factory here -->
    <contentHandlerDecoratorFactory class="org.apache.tika.sax.UpcasingContentHandlerDecoratorFactory"/>
  </autoDetectParserConfig>
</properties>