Search Options

Results per page
Sort
Preferred Languages
Advance

Results 41 - 50 of 115 for from (0.01 sec)

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

    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 {
        private static final Logger logger = LogManager.getLogger(TarExtractor.class);
    
        /**
         * The archive stream factory.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 5K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XmlTransformer.java

    import jakarta.annotation.Resource;
    
    /**
     * <p>
     * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.
     * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
     * </p>
     *
     * <p>
     * This class provides several configuration options to customize the XML parsing process, such as:
     * </p>
     * <ul>
     *   <li>Namespace awareness</li>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 23.9K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/Extractor.java

    /**
     * The Extractor interface defines methods for extracting text data from an input stream.
     * Implementations of this interface should provide the logic for extracting text and
     * optionally override the default weight value.
     */
    public interface Extractor {
    
        /**
         * Extracts text data from the given input stream.
         *
         * @param in the input stream to extract text from
         * @param params a map of parameters to be used during extraction
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 1.6K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/JodExtractor.java

    import org.jodconverter.core.office.OfficeManager;
    import org.jodconverter.local.LocalConverter;
    
    import jakarta.annotation.PostConstruct;
    import jakarta.annotation.PreDestroy;
    
    /**
     * Extracts text content from various document formats using JODConverter.
     */
    public class JodExtractor extends AbstractExtractor {
        /** Logger for this class. */
        private static final Logger logger = LogManager.getLogger(JodExtractor.class);
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.3K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TextUtil.java

                this.spaceChars = spaceChars;
                return this;
            }
        }
    
        /**
         * Normalizes the text from the given Reader.
         *
         * @param reader the Reader from which to read the text to be normalized
         * @return a TextNormalizeContext containing the normalized text
         */
        public static TextNormalizeContext normalizeText(final Reader reader) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/CrawlerClient.java

        void setInitParameterMap(Map<String, Object> params);
    
        /**
         * Executes a request and returns the response data.
         *
         * @param data the request data to be executed
         * @return the response data from the executed request
         */
        ResponseData execute(RequestData data);
    
        /**
         * Closes the crawler client and releases any resources associated with it.
         * This default implementation does nothing.
         *
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 1.8K bytes
    - Viewed (0)
  7. src/main/java/org/codelibs/fess/suggest/index/contents/ContentsParser.java

         * @param fields the fields to extract from the query log
         * @param tagFieldNames the names of the fields to use as tags
         * @param roleFieldName the name of the field to use for roles
         * @param readingConverter the converter to use for reading values
         * @param normalizer the normalizer to use for normalizing values
         * @return a list of suggest items parsed from the query log
         */
    Registered: Fri Sep 19 09:08:11 UTC 2025
    - Last Modified: Sat Mar 15 06:51:20 UTC 2025
    - 4.1K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/impl/LogHelperImpl.java

            final String url = (String) objs[2];
            final Throwable e = (Throwable) objs[3];
            if (logger.isDebugEnabled()) {
                logger.debug("Child URL: {} from {}", url, urlQueue.getUrl(), e);
            }
        }
    
        /**
         * Processes child URLs processing exception log events.
         *
         * @param objs the log objects (should contain UrlQueue and Set of RequestData)
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/smb1/SmbClient.java

     * This client supports authentication, content retrieval, and metadata extraction from SMB files.
     * It handles file access, directory listing, and access control entries (ACEs) processing.
     * </p>
     *
     * <p>
     * The class provides methods to:
     * </p>
     * <ul>
     *   <li>Initialize the client with SMB authentication details.</li>
     *   <li>Retrieve content and metadata from SMB files.</li>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Sep 18 09:30:45 UTC 2025
    - 23K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/log/LogType.java

        /** Indicates checking the last modified date of a resource. */
        CHECK_LAST_MODIFIED,
        /** Indicates the resource has not been modified. */
        NOT_MODIFIED,
        /** Indicates getting content from a resource. */
        GET_CONTENT,
        /** Indicates a redirect location was found. */
        REDIRECT_LOCATION,
        /** Indicates processing a response. */
        PROCESS_RESPONSE,
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.4K bytes
    - Viewed (0)
Back to top