<!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>

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

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.

<!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>

    public static final String CRAWLER_START_TIME = "CrawlerStartTime";

    /** Info map key for crawler end time. */
    public static final String CRAWLER_END_TIME = "CrawlerEndTime";

    /** Info map key for crawler execution time. */
    public static final String CRAWLER_EXEC_TIME = "CrawlerExecTime";

    /** Info map key for web/file system crawler start time. */

<!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;

/**
 * Extracts the filename from the parameters.

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

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

import org.apache.poi.hdgf.extractor.VisioTextExtractor;
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.

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

import java.io.Serializable;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic

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

/**
 * Configuration class for OpenSearch crawler settings.
 * This class provides configuration for index names, shards, and replicas
 * for the queue, data, and filter indices used by the crawler.
 */
public class OpenSearchCrawlerConfig {
    /**
     * Constructs a new OpenSearchCrawlerConfig.
     */

import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExecutionTimeoutException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content by executing an external command.
 */