});

// 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"));
});

Crawler crawler = container.getComponent("crawler");

    private String filename;

    /** Cache file size threshold in bytes */
    private int cacheFileSize = 1_000_000;

    /** Name of the extractor to use */
    private String extractorName = "tikaExtractor";

    /** Maximum content length allowed */
    private long maxContentLength = -1;

    /**
     * Constructs a new ExtractorBuilder.
     *
     * @param crawlerContainer the crawler container

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">1</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>
	<component name="msWordExtractor"