Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 11 for TikaExtractor (1.13 sec)

  1. src/main/resources/crawler/extractor+tikaExtractor.xml

    <!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">2</property>
    		<property name="maxUncompressionSize">10000000</property>
    	</component>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Aug 25 12:46:12 UTC 2019
    - 461 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: Sat Dec 20 11:21:39 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/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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
  4. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  5. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 7.6K bytes
    - Viewed (0)
  6. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.9K bytes
    - Viewed (0)
  7. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.7K bytes
    - Viewed (0)
  8. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (1)
  9. src/main/java/org/codelibs/fess/crawler/transformer/FessStandardTransformer.java

            if (extractor == null) {
                extractor = ComponentUtil.getComponent("tikaExtractor");
                if (extractor == null) {
                    throw new FessSystemException("Could not find tikaExtractor.");
                }
            }
    
            if (logger.isDebugEnabled()) {
                logger.debug("url={}, extractor={}", responseData.getUrl(), extractor);
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 3.8K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MarkdownExtractor.java

         */
        public MarkdownExtractor() {
            super();
            initializeParser();
        }
    
        @Override
        public int getWeight() {
            return 2; // Higher priority than TikaExtractor (weight=1)
        }
    
        /**
         * Initializes the Markdown parser with extensions.
         */
        protected void initializeParser() {
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 03:46:53 UTC 2025
    - 8.2K bytes
    - Viewed (0)
Back to top