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">

/**
 * 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

/**
 * 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;

            logger.debug("Crawling access exception at url: {}", urlQueue.getUrl(), e);
        } else if (e.isInfoEnabled()) {
            logger.info(e.getMessage());
        } else if (e.isWarnEnabled()) {
            logger.warn("Crawling access exception at url: {}", urlQueue.getUrl(), e);
        } else if (e.isErrorEnabled()) {
            logger.error("Crawling access exception at url: {}", urlQueue.getUrl(), e);

import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * The Crawler class is the main class for web crawling. It manages the crawling process,
 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,

labels.createdTime=Created Time
labels.depth=Depth
labels.excludedPaths=Excluded Paths for Crawling
labels.excludedUrls=Excluded URLs for Crawling
labels.excludedDocPaths=Excluded Paths for Searching
labels.excludedDocUrls=Excluded URLs for Searching
labels.hostname=Hostname
labels.id=ID
labels.includedPaths=Included Paths for Crawling
labels.includedUrls=Included URLs for Crawling
labels.includedDocPaths=Included Paths for Searching

    /**
     * The namespace identifier for the crawling session.
     * Used to organize and identify crawling activities in the system.
     * Defaults to the system crawling info name.
     */
    protected String namespace = Constants.CRAWLING_INFO_SYSTEM_NAME;

    /**
     * Array of web crawling configuration IDs to process.

 * <ul>
 * <li>Web crawling - crawls web sites and web content</li>
 * <li>File system crawling - crawls file systems and documents</li>
 * <li>Data store crawling - crawls databases and other data sources</li>
 * <li>Combined crawling - runs multiple crawling types simultaneously</li>
 * </ul>
 *
 * <p>Command line usage:
 * <pre>
 * java org.codelibs.fess.exec.Crawler [options...]