"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"
		instance="prototype">
		<property name="connectionTimeout">15000</property>

	<modelVersion>4.0.0</modelVersion>
	<groupId>org.codelibs.fess</groupId>
	<artifactId>fess-crawler-parent</artifactId>
	<version>15.3.0-SNAPSHOT</version>
	<packaging>pom</packaging>
	<name>Fess Crawler Project</name>
	<description>Fess Crawler is Crawler Framework.</description>
	<url>https://github.com/codelibs/fess-crawler</url>
	<inceptionYear>2009</inceptionYear>
	<licenses>
		<license>

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web-Framework
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Job-Scheduler
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web-Crawler

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.service;

import java.util.List;

import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.util.AccessResultCallback;

/**
 * Interface for data service operations related to access results.
 *
 * @param <RESULT> the type of access result

import org.codelibs.fess.app.service.RequestHeaderService;
import org.codelibs.fess.app.service.WebAuthenticationService;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.http.Authentication;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.helper.SystemHelper;
import org.codelibs.fess.mylasta.direction.FessConfig;

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.interval;

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>

    /**
     * Interval in milliseconds between crawler thread executions.
     * Used to control the rate at which new crawler threads are started
     * and the frequency of status checks.
     */
    protected long crawlingExecutionInterval = Constants.DEFAULT_CRAWLING_EXECUTION_INTERVAL;

    /**
     * Thread priority for crawler threads.
     * Defaults to normal thread priority.
     */

 */
package org.codelibs.fess.crawler.service.impl;

import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import org.codelibs.fess.crawler.entity.OpenSearchUrlFilter;