tika_config.xml

<?xml version="1.0" encoding="UTF-8"?>
<properties>
    <parsers>
        <parser class="org.apache.tika.parser.pdf.PDFParser"/>
        <parser class="org.apache.tika.parser.odf.OpenDocumentParser"/>
        <parser class="org.apache.tika.parser.odf.OpenDocumentContentParser"/>
        <parser class="org.apache.tika.parser.odf.OpenDocumentMetaParser"/>
        <parser class="org.apache.tika.parser.opendocument.OpenOfficeParser"/>
        <parser class="org.apache.tika.parser.microsoft.ooxml.OOXMLParser"/>
        <parser class="org.apache.tika.parser.microsoft.OfficeParser"/>
        <parser class="org.apache.tika.parser.microsoft.OldExcelParser"/>
        <parser class="org.apache.tika.parser.rtf.RTFParser"/>
        <parser class="org.apache.tika.parser.xml.XMLParser"/>
        <parser class="org.apache.tika.parser.epub.EpubParser"/>
        <parser class="org.apache.tika.parser.epub.EpubContentParser"/>
        <parser class="org.apache.tika.parser.chm.ChmParser"/>

        <!--ocr config-->
        <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.ocr.TesseractOCRParser"/>
        </parser>
        <parser class="org.apache.tika.parser.ocr.TesseractOCRParser">
            <params>
                <param name="applyRotation" type="bool">false</param>
                <param name="colorSpace" type="string">gray</param>
                <param name="density" type="int">300</param>
                <param name="depth" type="int">4</param>
                <param name="enableImagePreprocessing" type="bool">false</param>
                <param name="filter" type="string">triangle</param>
                <param name="imageMagickPath" type="string">/usr/local/bin/</param>
                <param name="language" type="string">eng</param>
                <param name="language" type="string">vie</param>
                <param name="maxFileSizeToOcr" type="long">2147483647</param>
                <param name="minFileSizeToOcr" type="long">0</param>
                <param name="pageSegMode" type="string">1</param>
                <param name="pageSeparator" type="string"></param>
                <param name="preserveInterwordSpacing" type="bool">false</param>
                <param name="resize" type="int">200</param>
                <param name="skipOcr" type="bool">false</param>
                <param name="tessdataPath" type="string">/usr/local/Cellar/tesseract/5.2.0/share/tessdata/</param>
                <param name="tesseractPath" type="string">/usr/local/bin/</param>
                <param name="timeoutSeconds" type="int">600</param>
            </params>
        </parser>
        <!--ocr config-->
    </parsers>
    <detectors>
        <detector class="org.apache.tika.mime.MagicDetector"/>
    </detectors>
</properties>