import org.codelibs.fess.util.ComponentUtil;

/**
 * Helper class for web and file system crawling and indexing operations.
 * Manages the crawling process for both web configurations and file configurations,
 * coordinating multiple crawler threads and handling indexing operations.
 */
public class WebFsIndexHelper {

    /**
     * Default constructor.
     */
    public WebFsIndexHelper() {

     * @return The key match helper.
     */
    public static KeyMatchHelper getKeyMatchHelper() {
        return getComponent(KEY_MATCH_HELPER);
    }

    /**
     * Gets the indexing helper component.
     * @return The indexing helper.
     */
    public static IndexingHelper getIndexingHelper() {
        if (indexingHelper == null || HotdeployUtil.isHotdeploy()) {
            indexingHelper = getComponent(INDEXING_HELPER);

- **Apache Solr** - Document import via REST API
- **Database Systems** - Direct connection via DataStore plugins
- **File Systems** - SMB, FTP, local file crawling
- **Custom Systems** - REST API for bulk document indexing

---

## Pre-Migration Planning

### 1. Assessment Phase

Before starting migration, assess your current system:

- **Document Count**: Total number of indexed documents

    @Resource
    protected SearchEngineClient searchEngineClient;

    /** Injected helper for web and file system indexing operations. */
    @Resource
    protected WebFsIndexHelper webFsIndexHelper;

    /** Injected helper for data store indexing operations. */
    @Resource
    protected DataIndexHelper dataIndexHelper;

    /** Injected service for managing path mappings during crawling. */

labels.crawling_info_WebFsIndexExecTime=Indexing Execution Time (Web/File)
labels.crawling_info_WebFsIndexSize=Index Size (Web/File)
labels.crawling_info_DataCrawlExecTime=Crawl Execution Time (Data Store)
labels.crawling_info_DataCrawlStartTime=Crawl Start Time (Data Store)
labels.crawling_info_DataCrawlEndTime=Crawl End Time (Data Store)
labels.crawling_info_DataIndexExecTime=Indexing Execution Time (Data Store)

        }
    }

    /**
     * Processes and normalizes a document title.
     * Applies text normalization using configured space characters and returns
     * a clean title suitable for indexing.
     *
     * @param responseData the response data from crawling (not currently used)
     * @param title the raw title text to process
     * @param dataMap additional data map (not currently used)

/**
 * FessCrawlerThread is a specialized crawler thread implementation for the Fess search engine.
 * This class extends the base CrawlerThread and provides Fess-specific functionality for
 * crawling and indexing documents, including incremental crawling capabilities, content
 * modification checking, and integration with the Fess search engine backend.
 *
 * <p>Key features include:</p>
 * <ul>

    private static final String META_NAME_ROBOTS_CONTENT = "//META[@name=\"robots\" or @name=\"ROBOTS\"]/@content";

    /** Robots tag value indicating no indexing or following */
    private static final String ROBOTS_TAG_NONE = "none";

    /** Robots tag value indicating no indexing */
    private static final String ROBOTS_TAG_NOINDEX = "noindex";

    /** Robots tag value indicating no following of links */

    /** The key of the message: Failed to upgrade from {0}. */
    public static final String ERRORS_failed_to_upgrade_from = "{errors.failed_to_upgrade_from}";

    /** The key of the message: Failed to start re-indexing from {0} to {1}. */
    public static final String ERRORS_failed_to_reindex = "{errors.failed_to_reindex}";

    /** The key of the message: Failed to rebuild config indices. */

    /** The key of the message: Crawl End Time (Web/File) */
    public static final String LABELS_crawling_info_WebFsCrawlEndTime = "{labels.crawling_info_WebFsCrawlEndTime}";

    /** The key of the message: Indexing Execution Time (Web/File) */
    public static final String LABELS_crawling_info_WebFsIndexExecTime = "{labels.crawling_info_WebFsIndexExecTime}";

    /** The key of the message: Index Size (Web/File) */