/**
     * The feature for external general entities in XML.
     */
    public static final String FEATURE_EXTERNAL_GENERAL_ENTITIES = "http://xml.org/sax/features/external-general-entities";

    /**
     * Feature for external parameter entities in XML.
     */

    /** Indicates processing a child URL due to an exception. */
    PROCESS_CHILD_URL_BY_EXCEPTION,
    /** Indicates an access exception during crawling. */
    CRAWLING_ACCESS_EXCEPTION,
    /** Indicates a general exception during crawling. */
    CRAWLING_EXCEPTION,
    /** Indicates no URL is available in the queue. */
    NO_URL_IN_QUEUE,
    /** Indicates the start of a crawler thread. */
    START_THREAD,

     * both sources differently.
     */
    private String lastmod;

    /**
     * How frequently the page is likely to change. This value provides general
     * information to search engines and may not correlate exactly to how often
     * they crawl the page. Valid values are:
     * <ul>
     * <li>always</li>
     * <li>hourly</li>
     * <li>daily</li>

    }

    /**
     * Returns the most specific directive matching the given user agent.
     * The method finds the longest matching user agent pattern in the directives,
     * excluding the general "*" pattern which matches all bots.
     *
     * @param userAgent the user agent string to match against directives,
     *                 can be null (treated as empty string)

   * The main mime type should be the canonical one, use aliases for any
     other widely used forms
   * Where there's a hierarchy in the types, list it via a parent
   * Highly specific magic matches get a high priority
   * General magic matches which could trigger a false-positive need
     a low one
   * The priority for containers normally need to be higher than for
     the things they contain, so they don't accidently get detected

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![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

							</configuration>
						</execution>
					</executions>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>
	<repositories>
		<repository>
			<id>snapshots.central.sonatype.com</id>
			<url>https://central.sonatype.com/repository/maven-snapshots</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>

			<plugin>
				<groupId>org.jacoco</groupId>
				<artifactId>jacoco-maven-plugin</artifactId>
			</plugin>
		</plugins>
	</build>
	<repositories>
		<repository>
			<id>snapshots.central.sonatype.com</id>
			<url>https://central.sonatype.com/repository/maven-snapshots</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Maven Central](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-suggest/badge.svg)](https://maven-badges.herokuapp.com/maven-central/org.codelibs.fess/fess-suggest)

 *     <li>Handle duplicated file paths by appending a counter.</li>
 *     <li>Store the file path in the result data.</li>
 *     <li>Retrieve the stored file as a File object.</li>
 * </ul>
 *
 * <p>
 * The class uses several configurable properties to customize the file storage behavior,
 * such as the base path, replacement strings for special characters in URLs,