// Test multiple User-agents in sequence (Bot1, Bot2, Bot3 should share the same rules)
        assertFalse(robotsTxt.allows("/shared/", "Bot1"));
        assertFalse(robotsTxt.allows("/shared/", "Bot2"));
        assertFalse(robotsTxt.allows("/shared/", "Bot3"));

        // Test sitemaps - should parse valid sitemaps and ignore invalid ones

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>
 * This client supports authentication, content retrieval, and metadata extraction from SMB files.

import org.codelibs.jcifs.smb1.util.LogStream;

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

                        "-u", "testuser;test123", //
                        "-s", "public;/share;yes;no;no;testuser1,testuser", //
                        "-s", "users;/srv;no;no;no;testuser1,testuser2", //
                        "-s", "testuser1 private share;/testuser1;no;no;no;testuser1", //
                        "-s", "testuser2 private share;/testuser2;no;no;no;testuser2", //
                        "-s", "empty;/empty;no;no;no;testuser", //

Before starting migration, assess your current system:

- **Document Count**: Total number of indexed documents
- **Index Size**: Storage requirements for search indices
- **Crawl Sources**: URLs, file shares, databases being indexed
- **Custom Configurations**: URL patterns, security rules, metadata fields
- **Search Features**: Facets, suggestions, security filtering, ranking rules

Disallow: /path%20encoded/
Disallow: /path?query=value
Disallow: /path#fragment
Allow: /unicode/日本語/

# Case 10: Multiple User-agents in sequence
User-agent: Bot1
User-agent: Bot2
User-agent: Bot3
Disallow: /shared/

# Case 11: Sitemap with various formats
Sitemap: http://example.com/sitemap.xml
sitemap: http://example.com/sitemap2.xml
SITEMAP: http://example.com/sitemap3.xml
Sitemap:    # empty sitemap (should be ignored)

                        "-s", "public;/share;yes;no;no;testuser1,testuser", //
                        "-s", "users;/srv;no;no;no;testuser1,testuser2", //
                        "-s", "testuser1 private share;/testuser1;no;no;no;testuser1", //
                        "-s", "testuser2 private share;/testuser2;no;no;no;testuser2", //
                        "-g", "log level = 3");

	</modules>
	<build>
		<pluginManagement>
			<plugins>
				<plugin>
					<groupId>org.apache.maven.plugins</groupId>
					<artifactId>maven-shade-plugin</artifactId>
					<executions>
						<execution>
							<phase>package</phase>
							<goals>
								<goal>shade</goal>
							</goals>
							<configuration>
								<artifactSet>
									<includes>
										<include>org.dbflute:dbflute-runtime</include>

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

            { "aliases", "allocation", "count", "fielddata", "health", "indices", "master", "nodeattrs", "nodes", "pending_tasks",
                    "plugins", "recovery", "repositories", "thread_pool", "shards", "segments", "snapshots", "templates" };

    // ===================================================================================
    //                                                                           Attribute