Search Options

Results per page
Sort
Preferred Languages
Advance

Results 31 - 40 of 64 for Extraction (0.05 sec)

  1. src/main/java/org/codelibs/fess/helper/DocumentHelper.java

    /**
     * Helper class for document processing and manipulation in the Fess search system.
     * This class provides utilities for processing document content, titles, and digests,
     * handling text normalization, content extraction, and similar document hash encoding/decoding.
     * It also manages document processing requests and integrates with the crawler system.
     *
     */
    public class DocumentHelper {
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 17.4K bytes
    - Viewed (0)
  2. src/main/java/org/codelibs/fess/crawler/transformer/FessStandardTransformer.java

    import org.codelibs.fess.util.ComponentUtil;
    
    import jakarta.annotation.PostConstruct;
    
    /**
     * Standard transformer implementation for the Fess search engine.
     * This transformer handles document transformation and content extraction using
     * the standard Fess file transformation process with support for various content types.
     *
     * <p>It extends AbstractFessFileTransformer to provide file-specific transformation
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 3.8K bytes
    - Viewed (0)
  3. src/main/java/org/codelibs/fess/app/service/FailureUrlService.java

         * The stack trace is abbreviated if it exceeds the configured maximum length.
         *
         * @param t the throwable to extract the stack trace from
         * @return the stack trace as a string, or empty string if extraction fails
         */
        private String getStackTrace(final Throwable t) {
            final SystemHelper systemHelper = ComponentUtil.getSystemHelper();
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Jul 17 08:28:31 UTC 2025
    - 9.2K bytes
    - Viewed (0)
  4. cmd/handler-utils_test.go

    		if testCase.expectedCode != actualCode {
    			t.Errorf("Test %d: Expected the APIErrCode to be %d, but instead found %d", i+1, testCase.expectedCode, actualCode)
    		}
    	}
    }
    
    // Tests validate metadata extraction from http headers.
    func TestExtractMetadataHeaders(t *testing.T) {
    	testCases := []struct {
    		header     http.Header
    		metadata   map[string]string
    		shouldFail bool
    	}{
    Registered: Sun Dec 28 19:28:13 UTC 2025
    - Last Modified: Wed Apr 09 14:28:39 UTC 2025
    - 6.1K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ArchiveExtractorErrorHandlingTest.java

    import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
    import org.dbflute.utflute.core.PlainTestCase;
    
    /**
     * Test class for archive extractor error handling improvements.
     * Tests partial extraction, error recovery, and improved error messages.
     */
    public class ArchiveExtractorErrorHandlingTest extends PlainTestCase {
        private static final Logger logger = LogManager.getLogger(ArchiveExtractorErrorHandlingTest.class);
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 12.6K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractor.java

                    throw new ExtractException("Failed to extract content from ZIP archive. No entries could be processed.", e);
                }
                if (logger.isWarnEnabled()) {
                    logger.warn("Partial extraction from ZIP archive. Processed: {}, Failed: {}", processedEntries, failedEntries, e);
                }
            }
    
            return new ExtractData(buf.toString().trim());
        }
    
        /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Dec 11 08:38:29 UTC 2025
    - 4.8K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java

         *
         * @param in the input stream to extract text from
         * @param params additional parameters
         * @return the extracted data
         * @throws ExtractException if extraction fails
         */
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            if (logger.isDebugEnabled()) {
                logger.debug("Accessing {}", url);
            }
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 12.2K bytes
    - Viewed (0)
  8. src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java

            }
            return false;
        }
    
        /**
         * Create the parameters for extraction.
         * @param responseData The response data.
         * @param crawlingConfig The crawling configuration.
         * @return The parameters for extraction.
         */
        protected Map<String, String> createExtractParams(final ResponseData responseData, final CrawlingConfig crawlingConfig) {
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 25.7K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TarExtractor.java

                    throw new ExtractException("Failed to extract content from TAR archive. No entries could be processed.", e);
                }
                if (logger.isWarnEnabled()) {
                    logger.warn("Partial extraction from TAR archive. Processed: {}, Failed: {}", processedEntries, failedEntries, e);
                }
            }
    
            return buf.toString().trim();
        }
    
        /**
         * Sets the maximum content size.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Dec 11 08:38:29 UTC 2025
    - 5.1K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/AbstractExtractor.java

     * {@link CrawlerContainer}. It also provides a convenient method for
     * registering the extractor with the {@link ExtractorFactory}.
     * </p>
     *
     * <p>
     * Subclasses should implement the actual extraction logic in their own
     * methods, leveraging the helper methods provided by this abstract class.
     * </p>
     *
     */
    public abstract class AbstractExtractor implements Extractor {
    
        /** The crawler container. */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Wed Nov 19 08:55:01 UTC 2025
    - 4.6K bytes
    - Viewed (0)
Back to top