*
     * @param protocol the protocol name to add (without colon suffix)
     */
    public void addWebProtocol(final String protocol) {
        final String prefix = protocol + ":";
        if (stream(webProtocols).get(stream -> stream.anyMatch(s -> s.equals(prefix)))) {
            logger.debug("Web protocols already contains: protocol={}", protocol);
            return;
        }

        if (StringUtil.isNotBlank(value)) {
            return check(protocols, value);
        }
        return true;
    }

    /**
     * Checks if the given value matches any of the specified protocols.
     *
     * @param protocols the allowed protocols
     * @param value the URI string to validate
     * @return true if the value matches allowed protocols, false otherwise
     */

        return appendQueryParameter(document, url);
    }

    /**
     * Updates file protocol based on user agent type.
     * Handles different browser-specific file protocol formats.
     *
     * @param url the file URL to update
     * @return the updated URL with appropriate file protocol
     */
    protected String updateFileProtocol(String url) {
        final int pos = url.indexOf(':', 5);

    }

    /**
     * Parses and filters URL patterns from text based on protocol types.
     * Processes each line of the input text, filtering URLs based on web and file protocol support.
     *
     * @param text the raw text containing URL patterns, one per line
     * @param web true if web protocol URLs should be included
     * @param file true if file protocol URLs should be included

import com.google.cloud.storage.Storage;
import com.google.cloud.storage.StorageOptions;

/**
 * Handler for the "gcs" protocol, allowing access to objects stored in Google Cloud Storage.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to GCS objects
 * using URLs with the "gcs" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code gcs://bucketName/objectName}.

import software.amazon.awssdk.services.s3.model.S3Exception;

/**
 * Handler for the "s3" protocol, allowing access to objects stored in S3-compatible storage services.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to S3 objects
 * using URLs with the "s3" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code s3://bucketName/objectName}.

        }

        return false;
    }

    /**
     * Converts a crawling path to the appropriate protocol format.
     * Handles various path formats and adds proper protocol prefixes.
     *
     * @param path the original path to convert
     * @return the converted path with appropriate protocol prefix
     */
    protected String convertCrawlingPath(final String path) {

import io.minio.errors.ServerException;
import io.minio.errors.XmlParserException;

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.

├── fess-crawler-lasta/        # LastaFlute DI integration
└── fess-crawler-opensearch/   # OpenSearch backend
```

### Key Design Patterns

**Factory**: `CrawlerClientFactory`, `ExtractorFactory` - protocol/format-specific component selection
**Strategy**: `CrawlerClient`, `Extractor`, `Transformer` - pluggable implementations
**Builder**: `RequestDataBuilder`, `ExtractorBuilder` - fluent construction

    /**
     * Gets the logger instance for this transformer.
     *
     * @return the logger instance
     */
    Logger getLogger();

    /**
     * Extracts the host name from a URL string.
     * Removes protocol and path components to return just the hostname.
     *
     * @param u the URL string to extract host from
     * @return the host name, or empty string if URL is blank, or unknown hostname if parsing fails
     */