|-----------|------------|
| Web Framework | LastaFlute (MVC framework) |
| DI Container | Lasta Di |
| Data Access | DBFlute (type-safe ORM for OpenSearch) |
| Search Engine | OpenSearch |
| App Server | Embedded Tomcat |
| Crawler | fess-crawler library |
| Scheduler | Lasta Job |
| Logging | Log4j2 |
| Testing | JUnit 4/5, UTFlute, REST Assured |

## Development Commands

### Setup
```bash

        if (artifactType != ArtifactType.CRAWLER) {
            return false;
        }

        if ("fess-crawler".equals(name)//
                || "fess-crawler-db".equals(name)//
                || "fess-crawler-db-h2".equals(name)//
                || "fess-crawler-db-mysql".equals(name)//
                || "fess-crawler-es".equals(name)//
                || "fess-crawler-opensearch".equals(name)//

    /**
     * Interval in milliseconds between crawler thread executions.
     * Used to control the rate at which new crawler threads are started
     * and the frequency of status checks.
     */
    protected long crawlingExecutionInterval = Constants.DEFAULT_CRAWLING_EXECUTION_INTERVAL;

    /**
     * Thread priority for crawler threads.
     * Defaults to normal thread priority.
     */

labels.crawling_info_delete_all_cancel=Cancel
labels.crawling_info_thread_dump=Thread Dump
labels.crawling_info_CrawlerStartTime=Crawler Start Time
labels.crawling_info_CrawlerEndTime=Crawler End Time
labels.crawling_info_CrawlerExecTime=Crawler Execution Time
labels.crawling_info_CrawlerStatus=Crawler Status
labels.crawling_info_WebFsCrawlExecTime=Crawl Execution Time (Web/File)

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<include path="crawler/transformer.xml" />

	<component name="ruleManager"
		class="org.codelibs.fess.crawler.rule.impl.RuleManagerImpl" instance="prototype">
		<postConstruct name="addRule">
			<arg>sitemapsRule</arg>
		</postConstruct>

                                        <la:errors property="crawler"/>
                                        <div class="form-check">
                                            <la:checkbox styleId="crawler" styleClass="form-check-input" property="crawler"/>
                                            <label for="crawler" class="form-check-label">

     */
    @Execute
    @Secured({ ROLE, ROLE + VIEW })
    public HtmlResponse index(final SearchForm form) {
        return asListHtml();
    }

    /**
     * Displays a paginated list of web crawler configurations.
     *
     * @param pageNumber the page number to display (optional)
     * @param form the search form containing filter criteria
     * @return HTML response with the web config list
     */

                case "crawler.hotthread.interval":
                    return "500ms";
                case "crawler.hotthread.snapshots":
                    return "10";
                case "crawler.hotthread.threads":
                    return "3";
                case "crawler.hotthread.timeout":
                    return "30s";
                case "crawler.hotthread.type":
                    return "cpu";

import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.LogHelperImpl;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;

  -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