}
    }

    /**
     * Creates and configures a DOM parser with the specified features and properties.
     *
     * @return a configured DOM parser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        try {
            final DOMParser parser = new DOMParser();
            // feature

        final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }

        final Document document = parser.getDocument();
        try {

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.sax.BodyContentHandler;

    }

    /**
     * Disables external resources for the SAX parser to prevent XXE attacks.
     * @param parser the SAX parser to configure
     * @throws SAXNotRecognizedException if the parser doesn't recognize the feature
     * @throws SAXNotSupportedException if the parser doesn't support the feature
     */
    protected void disableExternalResources(final SAXParser parser) throws SAXNotRecognizedException, SAXNotSupportedException {

            spfactory.setFeature(Constants.FEATURE_EXTERNAL_PARAMETER_ENTITIES, false);
            // create a sax parser
            final SAXParser parser = spfactory.newSAXParser();
            try {
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
            } catch (final Exception e) {

    the recipients' rights in the Source Code Form under this License.

3.3. Distribution of a Larger Work

You may create and distribute a Larger Work under terms of Your choice,
provided that You also comply with the requirements of this License for
the Covered Software. If the Larger Work is a combination of Covered
Software with a work governed by one or more Secondary Licenses, and the

        }
    }

    /**
     * Reads the contents of a file into a byte array and returns it.
     * <p>
     * <strong>Note:</strong> This method loads the entire file into memory.
     * For files larger than {@value #MAX_BUF_SIZE} bytes (10MB), an
     * {@link IORuntimeException} will be thrown to prevent OutOfMemoryError.
     * For large files, use streaming APIs instead.
     * </p>
     *
     * @param file

     *
     * @throws Exception
     */
    @Test
    public void testReadBytes_LargeFile() throws Exception {
        final File largeFile = tempFolder.newFile("large.dat");

        // Create a file larger than MAX_BUF_SIZE (10MB)
        // Write 11MB of data
        try (FileOutputStream fos = new FileOutputStream(largeFile)) {
            final byte[] chunk = new byte[1024 * 1024]; // 1MB

        SuggestItem firstItem = items.get(0);
        assertTrue(firstItem.getTags().length >= 2);
    }

    @Test
    public void test_parseDocumentWithLargeText() throws Exception {
        // Test with text larger than maxAnalyzedContentLength
        StringBuilder largeText = new StringBuilder();
        for (int i = 0; i < 2000; i++) {
            largeText.append("テスト ");
        }

   *
   * @param element the element to prepend to the front of {@code array}
   * @param array the array of elements to append
   * @return an array whose size is one larger than {@code array}, with {@code element} occupying
   *     the first position, and the elements of {@code array} occupying the remaining elements.
   */