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

	<!-- Converts child links to normalize it. -->
	<component name="urlConvertHelper" class="org.codelibs.fess.crawler.helper.UrlConvertHelper">
	</component>

<!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">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.interval.impl.DefaultIntervalController;
import org.codelibs.fess.helper.IntervalControlHelper;
import org.codelibs.fess.util.ComponentUtil;

/**

/**
 * Helper class for managing and validating URL protocols in Fess crawling system.
 * This class handles the initialization and validation of web and file protocols
 * used by the crawler to determine which URLs can be crawled.
 */
public class ProtocolHelper {
    private static final Logger logger = LogManager.getLogger(ProtocolHelper.class);

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

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

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.

<!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="contentLengthHelper"
		class="org.codelibs.fess.crawler.helper.ContentLengthHelper" instance="singleton">
		<property name="defaultMaxLength">10485760</property><!-- 10M -->
		<postConstruct name="addMaxLength">
			<arg>"text/html"</arg>

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

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

import org.codelibs.core.lang.StringUtil;
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.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;

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

import java.util.Set;

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

/**
 * {@link ChildUrlsException} is thrown when child URLs are found during crawling.

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

/**
 * An exception indicating that the execution of a process has timed out.
 * This exception extends {@link org.codelibs.fess.crawler.exception.ExtractException}.
 *
 */
public class ExecutionTimeoutException extends ExtractException {