tika-config.xml

<?xml version="1.0" encoding="UTF-8"?>
<properties>
  <server>
    <!-- If set to 'true', this runs tika server "in process"
    in the legacy 1.x mode.
    This means that the server will be susceptible to infinite loops
    and crashes.
    If set to 'false', the server will spawn a forked
    process and restart the forked process on catastrophic failures
    (this was called -spawnChild mode in 1.x).
    noFork=false is the default in 2.x
    -->
    <noFork>true</noFork>
  </server>
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.microsoft.ooxml.OOXMLParser"/>
      <parser-exclude class="org.apache.tika.parser.microsoft.OfficeParser"/>
    </parser>
    <!-- Raise POI's byte array limit from 100MB to 250MB to handle large
         Office documents with big embedded media (e.g. 14MB PPTX).
         This is a temporary per-parse allocation, not persistent memory. -->
    <parser class="org.apache.tika.parser.microsoft.ooxml.OOXMLParser">
      <params>
        <param name="byteArrayMaxOverride" type="int">250000000</param>
      </params>
    </parser>
    <parser class="org.apache.tika.parser.microsoft.OfficeParser">
      <params>
        <param name="byteArrayMaxOverride" type="int">250000000</param>
      </params>
    </parser>
  </parsers>
</properties>