audio/x-mpeg                   mp2              # MP2 Sound File
chemical/x-pdb                 pdb              # PDB Chemistry Model File
chemical/x-xyz                 xyz              # XYZ Chemistry Model File
drawing/x-dwf                  dwf              # AutoCAD
image/gif                      gif              # GIF image file
image/ief                      ief              # Image Exchange

        extensionMap.put("odp", "pdf");
        extensionMap.put("otp", "pdf");
        extensionMap.put("sxi", "pdf");
        extensionMap.put("ppt", "pdf");
        extensionMap.put("pptx", "pdf");
        // Drawing Formats
        extensionMap.put("odg", "svg");
        extensionMap.put("otg", "svg");

        extractorMap.put("pdf", new PdfExtractor());
        extractorMap.put("svg", new XmlExtractor());
    }

    /**

    <glob pattern="*.vss"/>
    <glob pattern="*.vsw"/>
    <sub-class-of type="application/x-tika-msoffice"/>
  </mime-type>

  <mime-type type="application/vnd.ms-visio.drawing">
    <_comment>Office Open XML Visio Drawing (macro-free)</_comment>
    <glob pattern="*.vsdx"/>
    <sub-class-of type="application/x-tika-visio-ooxml"/>
  </mime-type>
  <mime-type type="application/vnd.ms-visio.template">

import org.codelibs.fess.util.ComponentUtil;

/**
 * Job for purging old log entries from the system.
 * This job removes old crawling sessions, search logs, job logs, and user info logs
 * based on configured retention periods. It helps maintain system performance by
 * preventing log tables from growing too large.
 */
public class PurgeLogJob {

    /** Logger instance for this class */

/**
 * Helper class for managing data crawling operations in Fess.
 * This class coordinates the execution of data store crawling processes,
 * managing multiple concurrent crawling threads and handling the indexing
 * of crawled documents into the search engine.
 *
 * <p>The DataIndexHelper supports:</p>
 * <ul>
 *   <li>Concurrent crawling of multiple data configurations</li>

            if (logger.isInfoEnabled()) {
                logger.info("No crawling target urls.");
            }
            return;
        }

        doCrawl(sessionId, webConfigList, fileConfigList);
    }

    /**
     * Performs the actual crawling operation for the provided configurations.
     *
     * @param sessionId The session ID for this crawling operation
     * @param webConfigList List of web configurations to crawl

    /**
     * The unique identifier of the crawling information entry being edited.
     * This is a required field for identifying which crawling info to update.
     */
    @Required
    @Size(max = 1000)
    public String id;

    /**
     * The session identifier of the crawling session.
     * This is a required field that identifies the specific crawling session.
     * Maximum length is 20 characters.
     */

/**
 * Exception thrown when an error occurs during data store crawling operations.
 * This exception provides information about the URL where the error occurred
 * and whether the crawling process should be aborted.
 */
public class DataStoreCrawlingException extends CrawlingAccessException {

    private static final long serialVersionUID = 1L;

    /**
     * The URL where the crawling error occurred.
     */
    private final String url;

        
        // Configure crawling parameters
        crawler.addUrl("https://example.com");
        crawler.crawlerContext.setMaxAccessCount(100);
        crawler.crawlerContext.setNumOfThread(5);
        crawler.urlFilter.addInclude("https://example.com/.*");
        
        // Execute crawling
        String sessionId = crawler.execute();
        System.out.println("Crawling completed. Session ID: " + sessionId);
    }
}

        if (e.isDebugEnabled()) {
            logger.debug("Crawling Access Exception at {}", urlQueue.getUrl(), e);
        } else if (e.isInfoEnabled()) {
            logger.info(e.getMessage());
        } else if (e.isWarnEnabled()) {
            logger.warn("Crawling Access Exception at " + urlQueue.getUrl(), e);
        } else if (e.isErrorEnabled()) {
            logger.error("Crawling Access Exception at " + urlQueue.getUrl(), e);
        }