* <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...]

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

    @Size(max = 10)
    public String thumbnail;

    /**
     * Types of crawling failures to ignore during crawling operations.
     * Specified failure types will not be logged or counted as errors.
     */
    @Size(max = 1000)
    public String ignoreFailureType;

    /**
     * Threshold for failure count before stopping crawling of a URL.
     * Set to -1 to disable the threshold check.
     */
    @Required

        assertEquals(0, logListAfter.size(), "All crawling info logs should be deleted after calling delete all endpoint");

        // Log the result
        if (sizeBeforeDeletion > 0) {
            logger.info("Successfully deleted {} crawling info log(s) using bulk delete", sizeBeforeDeletion);
        } else {
            logger.info("No crawling info logs to delete (may have been deleted by previous test)");
        }

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

        }
    }

    /**
     * Processes a crawling request for a specific URL.
     * Executes the full crawling pipeline including client execution, rule processing,
     * transformation, and data extraction.
     *
     * @param crawlingConfig the crawling configuration to use
     * @param crawlingInfoId the crawling session ID
     * @param url the URL to process

    /** Property key for incremental crawling configuration. */
    public static final String INCREMENTAL_CRAWLING_PROPERTY = "crawling.incremental";

    /** Property key for crawling thread count configuration. */
    public static final String CRAWLING_THREAD_COUNT_PROPERTY = "crawling.thread.count";

    /** Property key for crawling user agent configuration. */

    /** The key of the message: Start Crawling */
    public static final String LABELS_wizard_start_crawling_title = "{labels.wizard_start_crawling_title}";

    /** The key of the message: Crawler */
    public static final String LABELS_wizard_start_crawler_title = "{labels.wizard_start_crawler_title}";

    /** The key of the message: You can start crawling now by clicking "Start Crawling" button. */

import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing and validating URL protocols in Fess crawling system.
 * This class handles the initialization and validation of web and file protocols
 * used by the crawler to determine which URLs can be crawled.
 */
public class ProtocolHelper {

crawler.document.fullstop.chars=u002eu06d4u2e3cu3002
# Encoding for crawling data.
crawler.crawling.data.encoding=UTF-8
# Supported web protocols for crawling.
crawler.web.protocols=http,https
# Supported file protocols for crawling.
crawler.file.protocols=file,smb,smb1,ftp,storage,s3,gcs
# Pattern for environment variable keys in crawling data.
crawler.data.env.param.key.pattern=^FESS_ENV_.*