Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Code Block
languagexml
titleAutoDetectParserConfig
<?xml version="1.0" encoding="UTF-8"?>
<properties>
  <autoDetectParserConfig>
    <params>
      <!-- if the incoming metadata object has a ContentLength entry and it is larger than this
           value, spool the file to disk; this is useful for some file formats that are more efficiently
           processed via a file instead of an InputStream -->
      <spoolToDisk>100000</spoolToDisk>
      <!-- the next four are parameters for the SecureContentHandler -->
      <!-- threshold used in zip bomb detection. This many characters must be written
           before the maximum compression ratio is calculated -->
      <outputThreshold>10000</outputThreshold>
      <!-- maximum compression ratio between output characters and input bytes -->
      <maximumCompressionRation>100<<maximumCompressionRatio>100</maximumCompressionRatio>
      <!-- maximum XML element nesting level -->
      <maximumDepth>100</maximumDepth>
      <!-- maximum embedded file depth -->
      <maximumPackageEntryDepth>100</maximumPackageEntryDepth>
    </params>
    <!-- as of Tika 2.5.x, this is the preferred way to configure digests -->
    <digesterFactory class="org.apache.tika.parser.digestutils.CommonsDigesterFactory">
      <params>
        <markLimit>100000</markLimit>
        <!-- this specifies SHA256, base32 and MD5 -->
        <algorithmString>sha256:32,md5</algorithmString>
      </params>
    </digesterFactory>   
  </autoDetectParserConfig>
</properties>

...