/** 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 name of the web configuration associated with this failure URL.
     * Used to identify which web crawling configuration encountered the failure.
     */
    public String webConfigName;

    /**
     * The name of the file configuration associated with this failure URL.
     * Used to identify which file crawling configuration encountered the failure.
     */
    public String fileConfigName;

    /**

 */
package org.codelibs.fess.app.web.admin.wizard;

/**
 * Form class for starting crawling operations in the admin wizard.
 *
 * This form is used to collect user input and parameters needed to initiate
 * crawling operations through the administrative interface wizard workflow.
 * It serves as a data transfer object between the web layer and the crawling
 * service components.
 */
public class StartCrawlingForm {

    /**

/**
 * Form class for crawling configuration wizard in the admin interface.
 * Contains validation constraints for creating new crawling configurations.
 */
public class CrawlingConfigForm {

    /**
     * Creates a new form instance.
     */
    public CrawlingConfigForm() {
        // Default constructor
    }

    /**
     * Name of the crawling configuration.
     */
    @Required

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

 */
package org.codelibs.fess.app.web.admin.crawlinginfo;

/**
 * The search form for Crawling Info.
 */
public class SearchForm {

    /**
     * Default constructor for SearchForm.
     */
    public SearchForm() {
    }

    /**
     * The session ID field for searching crawling information.
     */
    public String sessionId;

    }

    /**
     * Fetches URL queue list for the specified session with configurable ordering strategy.
     * Supports sequential (default) and random ordering based on crawling configuration.
     *
     * @param sessionId the crawling session identifier
     * @return list of URL queue entries for processing
     */
    @Override
    protected List<OpenSearchUrlQueue> fetchUrlQueueList(final String sessionId) {

┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐
│ ID  │ Pools                           │ Capacity                         │ Status   │
│ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │
└─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘
```

- Graceful degradation (e.g., robots.txt parsing continues on errors)

---

## Key Components

### Crawler (`Crawler.java`)

Main orchestrator for crawling operations.

**Key Methods**:
```java
String execute()                // Start crawling, return session ID
void addUrl(String url)         // Add URL to queue
void cleanup(String sessionId)  // Clean up session
void stop()                     // Stop gracefully

        return ComponentUtil.getIngestFactory();
    }

    /**
     * Processes a result data object for web/file crawling.
     * Default implementation returns the target unchanged.
     *
     * @param target the result data to process
     * @param responseData the response data from crawling
     * @return the processed result data
     */