/**
 * CrawlJob is responsible for executing the crawling process in Fess.
 * This job launches a separate crawler process that can crawl web sites, file systems,
 * and data sources based on the configured crawling settings.
 *
 * <p>The job supports selective crawling by specifying configuration IDs for different
 * types of crawlers (web, file, data). It manages the crawler process lifecycle,

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;

import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;

            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = getComponent(Crawler.class);
            crawler2.setBackground(true);
            ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
            crawler2.addUrl(url2);
            crawler2.getCrawlerContext().setMaxAccessCount(maxCount);

            crawler1.addUrl(url1);
            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = container.getComponent("crawler");
            crawler2.setSessionId(crawler2.getSessionId() + "2");
            crawler2.setBackground(true);

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.CrawlerStatus;
import org.codelibs.fess.crawler.interval.FessIntervalController;
import org.codelibs.fess.crawler.service.impl.OpenSearchDataService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlFilterService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlQueueService;

  -F "file=@documents.bulk"
```

### 4. Direct Crawler Configuration

Instead of importing documents, configure Fess to crawl your data sources:

**Web Crawling**:
- **Admin Path**: Crawler > Web
- **Supports**: HTTP/HTTPS websites
- **Features**: JavaScript rendering, authentication, custom headers

**File Crawling**:
- **Admin Path**: Crawler > File
- **Supports**: SMB, FTP, local file systems

│   ├── config/                # Config index (crawl configs, schedules)
│   ├── log/                   # Log index
│   ├── user/                  # User index
│   ├── exbhv/                 # Extended behaviors (repositories)
│   └── exentity/              # Extended entities (domain models)
├── helper/                    # Cross-cutting utilities
├── crawler/                   # Crawling engine
├── sso/                       # SSO implementations

 */
package org.codelibs.fess.crawler.processor;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;

### Key File Locations

**Core**: `fess-crawler/src/main/java/org/codelibs/fess/crawler/`
- `Crawler.java`, `CrawlerContext.java`, `CrawlerThread.java`

**Clients**: `fess-crawler/src/main/java/org/codelibs/fess/crawler/client/`
- `http/HcHttpClient.java`, `fs/FileSystemClient.java`, `storage/StorageClient.java`

**DI Config**: `fess-crawler-lasta/src/main/resources/crawler.xml`

### Exception Hierarchy

```