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");

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.
 *

            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);

    /**
     * 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);
        } catch (final RuntimeException e) {

    // 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);

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.mail.Address;
import jakarta.mail.BodyPart;
import jakarta.mail.Header;
import jakarta.mail.Message;

import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * 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.

        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {
            final Map<String, String> params = new HashMap<>();
            params.put(ExtractData.RESOURCE_NAME_KEY, outputFile.getName());
            try (final FileInputStream in = new FileInputStream(outputFile)) {
                final ExtractData extractData = extractor.getText(in, params);

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;

    /**
     * Constructs a new CommandExtractor.
     */
    public CommandExtractor() {
        // NOP
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {