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

                .status(ApiResult.Status.OK)
                .result());
    }

    /**
     * Retrieves a specific crawling info log by ID.
     *
     * @param id the ID of the crawling info log to retrieve
     * @return JSON response containing the crawling info log data
     */
    // GET /api/admin/crawlinginfo/log/{id}
    @Execute
    public JsonResponse<ApiResult> get$log(final String id) {

import org.codelibs.fess.app.web.api.admin.BaseSearchBody;

/**
 * Search request body for crawling information administration.
 * Extends BaseSearchBody with crawling information-specific search parameters.
 */
public class SearchBody extends BaseSearchBody {

    /** The crawling session ID to search for. */
    public String sessionId;

    /**
     * Default constructor for SearchBody.
     */

import org.codelibs.fess.app.web.api.admin.BaseSearchBody;

/**
 * Search request body for web crawling configuration administration API.
 */
public class SearchBody extends BaseSearchBody {

    /**
     * Default constructor.
     */
    public SearchBody() {
        super();
    }

    /** Name of the web crawling configuration */
    public String name;

    /** URLs to crawl */
    public String urls;

 */
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;

    @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

    /**
     * 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...]

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing crawling configurations.
 * Provides functionality to store, retrieve, and manage different types of crawling configurations
 * including web, file, and data configurations. Supports caching and session-based configuration management.
 */
public class CrawlingConfigHelper {

- 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