```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps
**SitemapsHelper**: Sitemap XML parsing, index handling
**MimeTypeHelper**: MIME detection via Tika
**EncodingHelper**: Charset detection with BOM
**UrlConvertHelper**: URL normalization

---

## Development Workflow

### Build Commands

```bash
mvn clean install              # Build all

            }
            return uaType;
        }).orElse(UserAgentType.OTHER);
    }

    /**
     * Enumeration of supported browser types for user agent detection.
     * Each type represents a major browser family that can be detected
     * from the User-Agent header string.
     */
    public enum UserAgentType {
        /** Internet Explorer and Trident-based browsers */

package org.codelibs.fess.crawler.helper;

import java.io.InputStream;
import java.util.Map;

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.
 * It allows content type detection based on the stream's content and/or filename.
 */
public interface MimeTypeHelper {
    /**
     * Determines the content type of the given input stream and filename.
     * @param is the input stream to analyze

- [ ] Create channel binding hash calculation
- [ ] Implement channel establishment protocol
- [ ] Add request distribution algorithm
- [ ] Create channel synchronization mechanism
- [ ] Implement channel failure detection
- [ ] Add automatic channel recovery
- [ ] Create channel performance monitoring

#### 3.3 Integration Points
- Modify `SmbTransportPool` for multiple connections per session

 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic delimiter detection (comma, tab, semicolon, pipe)</li>
 *   <li>Header row detection and extraction</li>
 *   <li>Column name to data value association</li>
 *   <li>Quoted field handling</li>
 *   <li>Column names as metadata</li>

    /**
     * Checks if automatic UTF-8 encoding detection is enabled.
     *
     * @return True if auto-detection is enabled, false otherwise
     */
    public boolean isAutodetectEncoding() {
        return autodetectEncoding;
    }

    /**
     * Sets whether automatic UTF-8 encoding detection is enabled.
     *
     * @param autodetectEncoding True to enable auto-detection, false to disable
     */

import java.util.Arrays;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Utility class for JVM-related operations.
 * This class provides methods for handling JVM options and version detection.
 */
public final class JvmUtil {
    private static final Pattern VERSION_PREFIX_PATTERN = Pattern.compile("([0-9]+)(\\-?):(.*)");

    private JvmUtil() {
        // nothing
    }

    /**

import jakarta.servlet.http.HttpServletRequest;
import jakarta.servlet.http.HttpServletResponse;

/**
 * Base implementation for API managers providing common functionality.
 * Abstract class that provides format detection and response handling for web APIs.
 */
public abstract class BaseApiManager implements WebApiManager {

    private static final String API_FORMAT_TYPE = "apiFormatType";

    /** Path prefix for API endpoints. */

        }
        if (this.options == null) {
            this.options = new HashMap<>();
        }
        this.options.put(key, val);
    }

    Object getOption(final String key) {
        if (key.equals("endpoint")) {
            return this.endpoint;
        }
        if (this.options != null) {
            return this.options.get(key);
        }

            throw new DcerpcException("Bad endpoint: " + endpoint);
        }
        if (options == null) {
            options = new HashMap();
        }
        options.put(key, val);
    }

    Object getOption(final String key) {
        if (key.equals("endpoint")) {
            return endpoint;
        }
        if (options != null) {
            return options.get(key);
        }
        return null;
    }