}

    /**
     * Adds a new file protocol to the supported protocols list.
     * If the protocol already exists, it will not be added again.
     *
     * @param protocol the protocol name to add (without colon suffix)
     */
    public void addFileProtocol(final String protocol) {
        final String prefix = protocol + ":";

    }

    /**
     * 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

            return redirect(ErrorAction.class);
        }
    }

    /**
     * Checks if the given URL represents a file system path.
     * Determines if the URL uses file system protocols that may require
     * special handling for content serving.
     *
     * @param url the URL to check
     * @return true if the URL is a file system path, false otherwise
     */

        if (maxSiteLength > -1) {
            return StringUtils.abbreviate(value, maxSiteLength);
        }
        return value;
    }

    /**
     * Extracts the filename from a URL, handling various protocols and URL decoding.
     * Processes HTTP, HTTPS, file, SMB, and FTP URLs appropriately.
     *
     * @param url the URL to extract filename from
     * @param encoding the character encoding (currently unused in this method)

        }

        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) {

- **HTTP**: Apache HttpComponents 4.5+
- **Extraction**: Apache Tika 3.0+, POI 5.3+, PDFBox 3.0+
- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### 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

crawler.document.fullstop.chars=u002eu06d4u2e3cu3002
# Encoding for crawling data.
crawler.crawling.data.encoding=UTF-8
# Supported web protocols for crawling.
crawler.web.protocols=http,https
# Supported file protocols for crawling.
crawler.file.protocols=file,smb,smb1,ftp,storage,s3,gcs
# Pattern for environment variable keys in crawling data.
crawler.data.env.param.key.pattern=^FESS_ENV_.*

        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);

    /**
     * Get the value for the key 'crawler.web.protocols'. <br>
     * The value is, e.g. http,https <br>
     * comment: Supported web protocols for crawling.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerWebProtocols();

    /**
     * Get the value for the key 'crawler.file.protocols'. <br>

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}.