Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for TikaExtractor (0.13 sec)

  2. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java 

    import org.xml.sax.SAXException;

import jakarta.annotation.PostConstruct;

/**
 * @author shinsuke
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

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

    public static final String TIKA_TESSERACT_CONFIG = "tika.tesseract.config";

    public static final String TIKA_PDF_CONFIG = "tika.pdf.config";
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:41:37 UTC 2024
    - 25K bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/ExtractorFactoryTest.java 

            extractorFactory = container.getComponent("extractorFactory");
        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
        LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
        PasswordBasedExtractor pdfExtractor = container.getComponent("pdfExtractor");
        extractorFactory.addExtractor("application/msword", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-excel", tikaExtractor);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Tue Jun 18 05:49:13 UTC 2024
    - 6.5K bytes
    - Viewed (0)
  4. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/ExtractorBuilder.java 

        private final CrawlerContainer crawlerContainer;

    private String mimeType;

    private String filename;

    private int cacheFileSize = 1_000_000;

    private String extractorName = "tikaExtractor";

    private long maxContentLength = -1;

    protected ExtractorBuilder(final CrawlerContainer crawlerContainer, final InputStream in, final Map<String, String> params) {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 6.3K bytes
    - Viewed (0)
  5. github.com/codelibs/fess

    src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java 

    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.transformer.impl.AbstractTransformer;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;
import org.codelibs.fess.crawler.util.FieldConfigs;
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:11:58 UTC 2024
    - 23.6K bytes
    - Viewed (0)
Back to top