*   <li>Optionally removing duplicate terms based on a flag.</li>
 *   <li>Limiting the maximum size of alphanumeric and symbol terms.</li>
 * </ul>
 *
 * <p>The {@link TextNormalizeContext} class provides a fluent API to configure the text
 * normalization process, including setting initial buffer capacity, maximum term sizes,
 * duplicate term removal, and custom space characters.
 *
 * <p>Example usage:
 * <pre>{@code

            if (path == null) {
                parent = "/";
                name = null;
            } else {
                final String[] values = path.replaceAll("/+", "/").replaceFirst("/$", "").split("/");
                if (values.length == 1) {
                    parent = "/";
                    name = null;
                } else if (values.length == 2) {
                    parent = "/";
                    name = values[1];

[![Maven Central](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-crawler-parent/badge.svg)](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-crawler-parent)

## Overview

    /**
     * Reference to the parent thread that started the crawler.
     */
    protected Thread parentThread;

    /**
     * The thread group for crawler threads.
     */
    protected ThreadGroup crawlerThreadGroup;

    /**
     * Constructs a new Crawler instance.
     * Initializes the crawler context with a new session ID based on the current timestamp.
     */
    public Crawler() {

    }

    /**
     * Gets the parent URL from which this resource was discovered.
     *
     * @return the parent URL, or null if this is a root URL
     */
    public String getParentUrl() {
        return parentUrl;
    }

    /**
     * Sets the parent URL from which this resource was discovered.
     *
     * @param parentUrl the parent URL to set
     */

 *   <li>{@link #createIndexIfNothing()}: Creates a new index if no index exists.</li>
 *   <li>{@link #createNextIndex()}: Creates a new index and replaces the current update alias with the new index.</li>
 *   <li>{@link #switchIndex()}: Switches the search alias to the current update index.</li>
 *   <li>{@link #removeDisableIndices()}: Removes disabled indices.</li>

	<packaging>jar</packaging>
	<name>Fess Crawler</name>
	<description>Fess Crawler is a crawler framework.</description>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-crawler-parent</artifactId>
		<version>15.3.0-SNAPSHOT</version>
		<relativePath>../pom.xml</relativePath>
	</parent>
	<build>
		<plugins>
			<plugin>
				<artifactId>maven-compiler-plugin</artifactId>
			</plugin>
			<plugin>

            Node parent = namespaceContext;
            String namespace = null;

            if ("xml".equals(prefix)) {
                namespace = "http://www.w3.org/XML/1998/namespace";
            } else {
                int type;
                while (null != parent && null == namespace

    /**
     * Constructs a new FileTransformer.
     */
    public FileTransformer() {
        // Default constructor
    }

    /**
     * A path to store downloaded files. The default path is a current
     * directory.
     */
    protected String path;

    /**
     * A string to replace ?.
     */
    protected String questionStr = "_QUEST_";

    /**
     * A string to replace :.
     */

            }
        }

    }

    /**
     * Stores child URLs to the crawling queue.
     * @param childUrlList The set of child URLs to store.
     * @param url The parent URL.
     * @param depth The depth of the child URLs.
     */
    protected void storeChildUrls(final Set<RequestData> childUrlList, final String url, final int depth) {