* @throws ExtractException if extraction fails
     */
    public ExtractData extract() {
        final ExtractorFactory extractorFactory = crawlerContainer.getComponent("extractorFactory");

        DeferredFileOutputStream dfos = null;
        try (DeferredFileOutputStream out = new DeferredFileOutputStream(cacheFileSize, "fess-extractor-", ".out", null)) {

        final ExtractorFactory extractorFactory = getExtractorFactory();
        try {
            final String filename = getDecodeText(bodyPart.getFileName());
            final String mimeType = mimeTypeHelper.getContentType(null, filename);
            if (mimeType != null) {
                final Extractor extractor = extractorFactory.getExtractor(mimeType);
                if (extractor != null) {

                    factory.addClient("file:.*", container.getComponent("fsClient"));
                })
                .singleton("tikaExtractor", TikaExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        final String mimeType = mimeTypeHelper.getContentType(null, filename);
        if (mimeType != null) {
            final Extractor extractor = extractorFactory.getExtractor(mimeType);
            if (extractor != null) {

        container.singleton("mimeTypeHelper", MimeTypeHelperImpl.class)
                .singleton("tikaExtractor", TikaExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);

    filter.addExclude(".*\\.(css|js|png|jpg|gif)$");
});

// Configure content extraction
container.singleton("tikaExtractor", TikaExtractor.class);
container.singleton("extractorFactory", ExtractorFactory.class, factory -> {
    factory.addExtractor("text/html", container.getComponent("tikaExtractor"));
    factory.addExtractor("application/pdf", container.getComponent("tikaExtractor"));
});

import org.codelibs.fess.crawler.client.CrawlerClientCreator;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.dict.DictionaryManager;
import org.codelibs.fess.ds.DataStoreFactory;
import org.codelibs.fess.exception.ContainerNotAvailableException;