Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 14 for tikaExtractor (0.14 sec)

  1. 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)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractorTest.java

                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        factory.addExtractor("text/plain", tikaExtractor);
                        factory.addExtractor("text/html", tikaExtractor);
                    })//
            ;
    
            tikaExtractor = container.getComponent("tikaExtractor");
        }
    
        public void test_getTika_text() {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 30.5K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractorTest.java

                    .singleton("tikaExtractor", TikaExtractor.class).singleton("zipExtractor", ZipExtractor.class)
                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        ZipExtractor zipExtractor = container.getComponent("zipExtractor");
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 3.6K bytes
    - Viewed (0)
  4. src/main/java/org/codelibs/fess/helper/DocumentHelper.java

            }
            try {
                final TikaExtractor tikaExtractor = ComponentUtil.getComponent("tikaExtractor");
                if (tikaExtractor != null) {
                    tikaExtractor.setMaxAlphanumTermSize(getMaxAlphanumTermSize());
                    tikaExtractor.setMaxSymbolTermSize(getMaxSymbolTermSize());
                    tikaExtractor.setReplaceDuplication(isDuplicateTermRemoved());
                    tikaExtractor.setSpaceChars(getSpaceChars());
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:53:18 UTC 2024
    - 12K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/LhaExtractorTest.java

            container.singleton("mimeTypeHelper", MimeTypeHelperImpl.class).singleton("tikaExtractor", TikaExtractor.class)
                    .singleton("lhaExtractor", LhaExtractor.class)
                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 3.3K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/TextTransformerTest.java

                    .singleton("textTransformer", TextTransformer.class).singleton("tikaExtractor", TikaExtractor.class);
            textTransformer = container.getComponent("textTransformer");
            textTransformer.setName("textTransformer");
            ExtractorFactory extractorFactory = container.getComponent("extractorFactory");
            TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
            extractorFactory.addExtractor("text/plain", tikaExtractor);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 4.6K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/PdfExtractorTest.java

                    .singleton("mimeTypeHelper", MimeTypeHelperImpl.class)//
                    .singleton("tikaExtractor", TikaExtractor.class)//
                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        PdfExtractor pdfExtractor = container.getComponent("pdfExtractor");
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 7.6K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                    }).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);
                    })//
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 18K bytes
    - Viewed (0)
  9. 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)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TarExtractorTest.java

                    .singleton("tikaExtractor", TikaExtractor.class).singleton("tarExtractor", TarExtractor.class)
                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        TarExtractor tarExtractor = container.getComponent("tarExtractor");
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 3.6K bytes
    - Viewed (0)
Back to top