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

### 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)

---

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>

        assertFalse(robotsTxt.allows("/path with spaces/", "SpecialCharBot"));
        assertFalse(robotsTxt.allows("/path%20encoded/", "SpecialCharBot"));
        assertFalse(robotsTxt.allows("/path?query=value", "SpecialCharBot"));

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

                        "-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");

                        "-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", //

 */
package org.codelibs.fess.score;

import java.util.ArrayList;
import java.util.List;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

/**
 * This class updates scores of documents.
 */
public class ScoreUpdater {
    /**
     * Constructor.
     */
    public ScoreUpdater() {
        super();
    }

Disallow: /test/

# Case 9: Special characters in paths
User-agent: SpecialCharBot
Disallow: /path with spaces/
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

    }

    /**
     * Starts a reindex operation with the specified parameters.
     *
     * @param replaceAliases whether to replace aliases after reindexing
     * @param resetDictionaries whether to reset dictionaries during reindexing
     * @param numberOfShards the number of shards for the new index