* processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

    /**
     * Tesseract config file path.
     */
    public static final String TIKA_TESSERACT_CONFIG = "tika.tesseract.config";

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                })//
        ;

        tikaExtractor = container.getComponent("tikaExtractor");
    }

    public void test_getTika_text() {

                tikaExtractor.setMaxSymbolTermSize(getMaxSymbolTermSize());
                tikaExtractor.setReplaceDuplication(isDuplicateTermRemoved());
                tikaExtractor.setSpaceChars(getSpaceChars());
            }
        } catch (final ComponentNotFoundException e) {
            if (logger.isDebugEnabled()) {

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

                .singleton("tikaExtractor", TikaExtractor.class)
                .singleton("textExtractor", TextExtractor.class)
                .singleton("zipExtractor", ZipExtractor.class)
                .singleton("tarExtractor", TarExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {

});

// 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");

### Key Extractors

`TikaExtractor` (1000+ formats), `PdfExtractor`, `MsWordExtractor`, `MsExcelExtractor`, `MsPowerPointExtractor`, `ZipExtractor`, `HtmlExtractor`, etc.

**Registration**:
```java
extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

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.serializer.DataSerializer;
import org.codelibs.fess.crawler.transformer.impl.AbstractTransformer;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

    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

    /**
     * Constructs a new CsvExtractor.
     */
    public CsvExtractor() {
        super();
    }

    @Override
    public int getWeight() {
        return 2; // Higher priority than TikaExtractor (weight=1)
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);

        final Charset charset = getCharset(params);