<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
    <include path="crawler/container.xml"/>
    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,

 */
package org.codelibs.fess.crawler.entity;

/**
 * Interface representing the data of an access result.
 *
 * @param <IDTYPE> the type of the identifier
 */
public interface AccessResultData<IDTYPE> {

    /**
     * Retrieves the unique identifier of the access result data.
     *
     * @return the unique identifier of type IDTYPE.
     */
    IDTYPE getId();

    /**

import java.util.regex.Pattern;

/**
 * Service interface for managing URL filters.
 * Provides methods to add and remove include/exclude URL filters,
 * as well as retrieve the patterns of these filters.
 */
public interface UrlFilterService {

    /**
     * Adds a URL to the include filter list for the specified session.
     *
     * @param sessionId the ID of the session for which the URL filter is being added

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<include path="crawler/robotstxt.xml" />
	<include path="crawler/contentlength.xml" />
	<include path="crawler/mimetype.xml" />

	<component name="internalHttpClient" class="org.codelibs.fess.crawler.client.http.HcHttpClient"

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**
     * Retrieves the rule associated with the given response data.
     *
     * @param responseData the response data for which the rule is to be retrieved

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.
     *
     * @param oldSessionId The old session ID.
     * @param newSessionId The new session ID.
     */

 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {

    /**
     * Retrieves the unique identifier of the URL queue.
     *
     * @return the unique identifier of type IDTYPE.
     */
    IDTYPE getId();

    /**

 */
package org.codelibs.fess.crawler.entity;

/**
 * Represents the result of accessing a resource.
 *
 * @param <IDTYPE> the type of the identifier for the access result
 */
public interface AccessResult<IDTYPE> {

    /**
     * Initializes the access result with the given response and result data.
     *
     * @param responseData the response data
     * @param resultData the result data

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">1</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>