Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 11 for tikaExtractor (0.07 sec)

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

     * 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";
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.7K bytes
    - Viewed (0)
  2. 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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.7K bytes
    - Viewed (0)
  3. 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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.6K bytes
    - Viewed (0)
  4. src/main/java/org/codelibs/fess/helper/DocumentHelper.java

                    tikaExtractor.setMaxSymbolTermSize(getMaxSymbolTermSize());
                    tikaExtractor.setReplaceDuplication(isDuplicateTermRemoved());
                    tikaExtractor.setSpaceChars(getSpaceChars());
                }
            } catch (final ComponentNotFoundException e) {
                if (logger.isDebugEnabled()) {
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Aug 07 03:06:29 UTC 2025
    - 17.2K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/LhaExtractorTest.java

                    .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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/TextTransformerTest.java

                    .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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
  7. 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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 19.1K bytes
    - Viewed (0)
  8. 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 Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.7K bytes
    - Viewed (0)
  9. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java

                    .singleton("tikaExtractor", TikaExtractor.class)
                    .singleton("zipExtractor", ZipExtractor.class)
                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        factory.addExtractor("application/pdf", tikaExtractor);
                    });
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
  10. README.md

    });
    
    // 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");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Aug 31 05:32:52 UTC 2025
    - 15.3K bytes
    - Viewed (0)
Back to top