Versions Compared

Key

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

...

Code Block
languagexml
titlePDFParser Configuration
<properties>
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <!-- this is not formally necessary, but prevents loading of unnecessary parser -->
      <parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
    </parser>
    <parser class="org.apache.tika.parser.pdf.PDFParser">
      <params>
        <!-- these are the defaults; you only need to specify the ones you want 
            to modify -->
        <!-- if you want to extract content, whether or not the PDF allows extraction
             at all, do not set this parameter.  If you want to extract content and
             the PDF allows for extraction for accessibility, set this to true.
             If you do not want to extract content when the PDF does not allow extraction
             but does allow extraction for accessibility, set this to false -->
        <param name="allowExtractionForAccessibility" type="bool">true</param>
        <param name="averageCharTolerance" type="float">0.3</param>
        <param name="detectAngles" type="bool">false</param>
        <param name="extractAcroFormContent" type="bool">true</param>
        <param name="extractActions" type="bool">false</param>
        <!-- as of 2.8.0 -->
        <param name="extractIncrementalUpdateInfo" type="bool">false</param>
        <param name="catchIntermediateIOExceptions" type="bool">true</param>
        <param name="dropThreshold" type="float">2.5</param>
        <param name="enableAutoSpace" type="bool">true</param>
        <param name="extractAnnotationText" type="bool">false</param>
        <param name="extractBookmarksText" type="bool">true</param>
        <param name="extractFontNames" type="bool">false</param>
        <param name="extractInlineImages" type="bool">false</param>
        <param name="extractMarkedContent" type="bool">false</param>
        <param name="extractUniqueInlineImagesOnly" type="bool">true</param>
        <param name="ifXFAExtractOnlyXFA" type="bool">false</param>
        <param name="maxMainMemoryBytes" type="long">-1</param>
        <!-- as of 2.8.0 -->
        <param name="maxIncrementalUpdates" type="int">10000</param>
        <param name="ocrDPI" type="int">300</param>
        <param name="ocrImageFormatName" type="string">png</param>
        <param name="ocrImageQuality" type="float">1.0</param>
        <param name="ocrRenderingStrategy" type="string">ALL</param>
        <param name="ocrStrategy" type="string">auto</param>
        <param name="ocrStrategyAuto" type="string">better</param>
        <param name="ocrImageType" type="string">gray</param>
         <!-- as of 2.8.0 -->
        <param name="parseIncrementalUpdates" type="bool">false</param>
        <param name="setKCMS" type="bool">false</param>
        <param name="sortByPosition" type="bool">false</param>
        <param name="spacingTolerance" type="float">0.5</param>
        <param name="suppressDuplicateOverlappingText" type="bool">false</param>
        <!-- as of versions after 2.8.0 -->
        <param name="throwOnEncryptedPayload" type="bool">false</param>
      </params>
    </parser>
  </parsers>
</properties>

...