import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.lang.StringUtil;
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.ExtractException;

/**
 * Abstract base class for XML extractors.

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

import java.util.Map;

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

{
  "title": "Sample Document",
  "author": "John Doe",
  "version": "1.0",
  "published": "2025-01-15",
  "tags": ["crawler", "extractor", "json"],
  "content": {
    "summary": "This is a sample JSON document for testing",
    "body": "The extractor should handle nested objects and arrays properly"
  },
  "metadata": {
    "created_at": "2025-01-01T00:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  }

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

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.util.Arrays;
import java.util.Date;
import java.util.Map;
import java.util.Set;

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

 * 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.List;

/**
 * @author shinsuke
 *
 */
public class TestEntity {
    private String title;

    private String body;

    private List<String> list;

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.client.ftp.FtpClient.FtpInfo;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

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

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.dbflute.utflute.core.PlainTestCase;

/**

 * 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.UrlQueue;

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *

import java.util.regex.Pattern;

import org.apache.commons.io.input.BOMInputStream;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.RobotsTxt;
import org.codelibs.fess.crawler.entity.RobotsTxt.Directive;
import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Parser following RFC 9309 specification.
 *

import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.Queue;

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.dbflute.utflute.core.PlainTestCase;
import org.mockito.InjectMocks;
import org.mockito.Mock;