import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);

        this.mailProperties = mailProperties;
    }

    /**
     * Extracts the body text from a MIME message.
     *
     * @param message the MIME message to extract text from
     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {

        assertContentType("application/pdf", "extractor/test.pdf", "hoge.pdf");

        assertContentType("application/gzip", "extractor/gz/test.tar.gz", "hoge.tar.gz");
        assertContentType("application/zip", "extractor/zip/test.zip", "hoge.zip");
        assertContentType("application/x-lharc", "extractor/lha/test.lzh", "hoge.lzh"); // TODO is it correct?

        assertContentType("application/xml", "extractor/test.mm", "hoge.mm");

    }

    /**
     * Get the extracted data.
     * @param extractor The extractor.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) {
        try {
            return extractor.getText(in, params);

 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>

     * @param outExt the output file extension
     * @return the extracted text content
     * @throws ExtractException if an error occurs while reading the file
     */
    protected String getOutputContent(final File outputFile, final String outExt) {
        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {
            final Map<String, String> params = new HashMap<>();

    // InputStream in =
    // ResourceUtil.getResourceAsStream("extractor/test_pass.pdf");
    // TikaExtractor extractor =
    // (TikaExtractor) getContainer().getComponent(
    // "tikaExtractorForPdfPassword");
    // Map<String, String> params = new HashMap<String, String>();
    // params.put(ExtractData.URL, "http://example.com/test_pass.pdf");
    // ExtractData extractData = extractor.getText(in, params);

            }
        }
    }

    /**
     * Extracts text from the input stream using the API endpoint.
     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;