import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */

import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.helper.RobotsTxtHelper;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.codelibs.fess.crawler.service.impl.UrlFilterServiceImpl;
import org.codelibs.fess.crawler.util.CrawlerWebServer;

	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="robotsTxtHelper" class="org.codelibs.fess.crawler.helper.RobotsTxtHelper"
		instance="prototype">
	</component>

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

import org.codelibs.fess.crawler.extractor.impl.PdfExtractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class ExtractorFactoryTest extends PlainTestCase {

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper.impl;

import java.util.Set;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.RequestData;

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper;

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

/**
 * MimeTypeHelper provides methods to determine the content type of a given input stream or file.

import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;

/**
 * SitemapsRule is a rule implementation that extends RegexRule to determine if a given response data
 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class UrlConvertHelperTest extends PlainTestCase {

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.MimeTypeHelper;

import jakarta.annotation.Resource;

/**
 * FileSystemClient is CrawlerClient implementation to crawl files on a file
 * system.
 *
 * @author shinsuke
 *