Search Options

Results per page
Sort
Preferred Languages
Advance

Results 21 - 30 of 262 for extractor (0.05 sec)

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

         * @param outExt the output file extension
         * @return the extracted text content
         * @throws ExtractException if an error occurs while reading the file
         */
        protected String getOutputContent(final File outputFile, final String outExt) {
            final Extractor extractor = getExtractor(outExt);
            if (extractor != null) {
                final Map<String, String> params = new HashMap<>();
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.3K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractorTest.java

        // InputStream in =
        // ResourceUtil.getResourceAsStream("extractor/test_pass.pdf");
        // TikaExtractor extractor =
        // (TikaExtractor) getContainer().getComponent(
        // "tikaExtractorForPdfPassword");
        // Map<String, String> params = new HashMap<String, String>();
        // params.put(ExtractData.URL, "http://example.com/test_pass.pdf");
        // ExtractData extractData = extractor.getText(in, params);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 30.6K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TarExtractor.java

    import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
    import org.codelibs.fess.crawler.extractor.Extractor;
    import org.codelibs.fess.crawler.extractor.ExtractorFactory;
    import org.codelibs.fess.crawler.helper.MimeTypeHelper;
    import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;
    
    import jakarta.annotation.Resource;
    
    /**
     * Extracts text content from TAR archives.
     */
    public class TarExtractor extends AbstractExtractor {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 5K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractor.java

    import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
    import org.codelibs.fess.crawler.extractor.Extractor;
    import org.codelibs.fess.crawler.extractor.ExtractorFactory;
    import org.codelibs.fess.crawler.helper.MimeTypeHelper;
    import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;
    
    import jakarta.annotation.Resource;
    
    /**
     * Extracts text content from ZIP archives.
     */
    public class ZipExtractor extends AbstractExtractor {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.5K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractorTest.java

        private TestApiExtractorServer server;
    
        private ApiExtractor extractor;
    
        @Override
        protected void setUp() throws Exception {
            super.setUp();
    
            server = new TestApiExtractorServer(port);
            server.start();
    
            extractor = new ApiExtractor();
            extractor.setUrl("http://127.0.0.1:" + port + "/");
            extractor.init();
        }
    
        @Override
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 5.4K bytes
    - Viewed (0)
  6. src/main/java/org/codelibs/fess/crawler/transformer/FessStandardTransformer.java

        }
    
        /**
         * Gets the appropriate extractor for the given response data.
         * Selects an extractor based on the MIME type or falls back to the Tika extractor.
         *
         * @param responseData the response data containing the document to extract
         * @return the extractor instance for processing the document
         * @throws FessSystemException if no suitable extractor can be found
         */
        @Override
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 17 08:28:31 UTC 2025
    - 3.8K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/LhaExtractorTest.java

     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.extractor.impl;
    
    import java.io.IOException;
    import java.io.InputStream;
    
    import org.apache.logging.log4j.LogManager;
    import org.apache.logging.log4j.Logger;
    import org.codelibs.core.io.CloseableUtil;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/HtmlXpathExtractorTest.java

            final String content = htmlXpathExtractor.getText(in, null).getContent();
            CloseableUtil.closeQuietly(in);
            logger.info(content);
            assertTrue(content.contains("ใƒ†ใ‚นใƒˆ"));
        }
    
        public void test_getHtml_sjis() {
            final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 4.2K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MsVisioExtractor.java

     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.extractor.impl;
    
    import java.io.IOException;
    import java.io.InputStream;
    import java.util.Map;
    
    import org.apache.poi.hdgf.extractor.VisioTextExtractor;
    import org.codelibs.fess.crawler.entity.ExtractData;
    import org.codelibs.fess.crawler.exception.CrawlerSystemException;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 1.9K bytes
    - Viewed (0)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/ExtractorFactoryTest.java

            final Extractor extractor = new Extractor() {
                public ExtractData getText(final InputStream in, final Map<String, String> params) {
                    return null;
                }
            };
    
            assertNull(extractorFactory.getExtractor("test"));
            extractorFactory.addExtractor("test", extractor);
            assertEquals(extractor, extractorFactory.getExtractor("test"));
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.9K bytes
    - Viewed (0)
Back to top