return url;
    }

    /**
     * Extracts and processes the site path from a URL with proper encoding handling.
     * Removes protocol, query parameters, and applies URL decoding based on encoding settings.
     *
     * @param u the URL string to process
     * @param encoding the character encoding to use for URL decoding
     * @return the processed site path, abbreviated if necessary
     */

     */
    public void setOsddPath(final String osddPath) {
        this.osddPath = osddPath;
    }

    /**
     * Sets the encoding.
     *
     * @param encoding the encoding
     */
    public void setEncoding(final String encoding) {
        this.encoding = encoding;
    }

    /**
     * Sets the content type.
     *
     * @param contentType the content type
     */

                        logger.debug("Invalid encoding: {}, using default: {}", encodingParam, encoding, e);
                    }
                }
            }
        }
        return Charset.forName(encoding);
    }

    /**
     * Sets the encoding for CSV files.
     *
     * @param encoding the encoding
     */
    public void setEncoding(final String encoding) {
        this.encoding = encoding;
    }

				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.14.0</version>
				<configuration>
					<encoding>UTF-8</encoding>
					<release>21</release>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-javadoc-plugin</artifactId>
				<version>3.11.2</version>
				<configuration>
					<encoding>UTF-8</encoding>
					<docencoding>UTF-8</docencoding>
					<charset>UTF-8</charset>
				</configuration>
			</plugin>

            throw new ExtractException("Failed to extract text content using encoding: " + getEncoding(), e);
        }
    }

    /**
     * Returns the encoding used for text extraction.
     * @return the encoding
     */
    public String getEncoding() {
        return encoding;
    }

    /**
     * Sets the encoding.
     * @param encoding The encoding to set.
     */
    public void setEncoding(final String encoding) {

        }

        return normalizeEncoding(encoding);
    }

    /**
     * Normalizes the encoding name using the encoding helper.
     *
     * @param encoding the encoding name to normalize
     * @return the normalized encoding name
     */
    protected String normalizeEncoding(final String encoding) {
        try {

				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.14.0</version>
				<configuration>
					<encoding>UTF-8</encoding>
					<release>17</release>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-javadoc-plugin</artifactId>
				<version>3.11.2</version>
				<configuration>
					<encoding>UTF-8</encoding>
					<docencoding>UTF-8</docencoding>
					<charset>UTF-8</charset>
				</configuration>
			</plugin>

     * When enabled, frequently searched terms are tracked and displayed.
     */
    @Size(max = 10)
    public String popularWord;

    /**
     * Character encoding to use for CSV file exports.
     * This setting affects the encoding of downloaded CSV files.
     */
    @Required
    @Size(max = 20)
    public String csvFileEncoding;

    /**
     * Number of days to keep search logs before purging.

    }

    /**
     * Encodes a similar document hash using GZIP compression and Base64 encoding.
     * This reduces storage space for hash values while maintaining uniqueness.
     *
     * @param hash the hash string to encode
     * @return the encoded hash string with prefix, or the original hash if encoding fails
     */
    public String encodeSimilarDocHash(final String hash) {

#FESS_JAVA_OPTS="$FESS_JAVA_OPTS -XX:HeapDumpPath=$FESS_HOME/logs/heapdump.hprof"

# Disables explicit GC
FESS_JAVA_OPTS="$FESS_JAVA_OPTS -XX:+DisableExplicitGC"

# Ensure UTF-8 encoding by default (e.g. filenames)
FESS_JAVA_OPTS="$FESS_JAVA_OPTS -Dfile.encoding=UTF-8"

# Application Configuration
if [ "x$APP_NAME" = "x" ]; then
  APP_NAME=fess
fi
if [ "x$SEARCH_ENGINE_HOME" = "x" ]; then
  SEARCH_ENGINE_HOME=$FESS_HOME/es
fi