import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */

 * 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.entity;

import java.util.function.Function;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

public class ResultDataTest extends PlainTestCase {

 * 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.

import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;

infringed only as a consequence of further modification of this
implementation.  If you or your agent or exclusive licensee institute or
order or agree to the institution of patent litigation against any
entity (including a cross-claim or counterclaim in a lawsuit) alleging
that this implementation of Go or any code incorporated within this
implementation of Go constitutes direct or contributory patent

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>

 */
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.
 *
 * @author shinsuke
 *
 */

 * governing permissions and limitations under the License.
 */
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

// that they are interested in preserving.
type Header struct {
	// Typeflag is the type of header entry.
	// The zero value is automatically promoted to either TypeReg or TypeDir
	// depending on the presence of a trailing slash in Name.
	Typeflag byte

	Name     string // Name of file entry
	Linkname string // Target name of link (valid for TypeLink or TypeSymlink)

	Size  int64  // Logical file size in bytes