import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

import org.codelibs.fess.crawler.client.FaultTolerantClient.RequestListener;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

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 as the content.
 *

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

/**
 * CrawlingAccessException is an exception class that represents an issue encountered while accessing a resource during the crawling process.
 * It extends CrawlerSystemException and provides functionality to set and check the log level for the exception.
 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

        final TextExtractor extractor = container.getComponent("textExtractor");

        try {
            extractor.getText(null, null);
            fail("Expected CrawlerSystemException");
        } catch (final CrawlerSystemException e) {
            assertEquals("The inputstream is null.", e.getMessage());
        }
    }

    /**
     * Test that MsWordExtractor throws appropriate exception for invalid data.

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

import java.io.Serializable;
import java.util.Collection;
import java.util.LinkedHashSet;
import java.util.Set;
import java.util.function.Function;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * This class represents the result data of a crawl.
 */
public class ResultData implements Serializable {
    private static final long serialVersionUID = 1L;