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());
    }

    /**

/**
 * 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

    }

    /**
     * Stores crawling information and parameters for the specified session.
     * Creates a new crawling info record if none exists or if create flag is true.
     * Also stores any accumulated information parameters and clears the info map.
     *
     * @param sessionId the session ID for the crawling information
     * @param create if true, creates a new crawling info regardless of existing records

        
        // 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);
    }
}

            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);

    }

    /**
     * Stores (inserts or updates) a crawling information record.
     * Sets up the store conditions including creation time if not already set,
     * then performs an insert or update operation with immediate refresh.
     *
     * @param crawlingInfo the crawling information entity to store
     * @throws FessSystemException if the crawling information is null
     */

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.