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

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 .doc file.
 *
 * @author shinsuke
 *
 */
public class MsWordExtractor extends AbstractExtractor {

    /**

import org.apache.logging.log4j.Logger;
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 TextExtractorTest extends PlainTestCase {

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

import java.util.Set;

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

/**
 * {@link ChildUrlsException} is thrown when child URLs are found during crawling.
 * It extends {@link CrawlerSystemException} and holds a set of {@link RequestData}
 * representing the child URLs that caused the exception.
 *
 */

        runner.ensureYellow();
    }

    @Override
    protected void tearDown() throws Exception {
        runner.close();
        runner.clean();
    }

    public void test_buildWithDefault() throws Exception {
        final String id = "BuildTest";
        final Suggester suggester = Suggester.builder().build(runner.client(), id);

        assertNotNull(suggester);

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

import org.apache.poi.hssf.usermodel.HSSFWorkbook;
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 .xls file.
 *
 * @author shinsuke
 *
 */
public class MsExcelExtractor extends AbstractExtractor {

    /**

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 Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"

        rootLogger.addHandler(handler);
    }

    @Override
    public void tearDown() throws Exception {
        super.tearDown();
        // close runner
        runner.close();
        // delete all files
        runner.clean();
    }

    public void test_executeTx() throws Exception {
        final CrawlerWebServer server = new CrawlerWebServer(7070);
        server.start();

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.RobotsTxt;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
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;

        suggester = Suggester.builder().build(runner.client(), "SuggesterTest");
    }

    @AfterClass
    public static void afterClass() throws Exception {
        runner.close();
        runner.clean();
    }

    @Test
    public void test_normalize() throws Exception {
        Normalizer normalizer = SuggestUtil.createDefaultNormalizer(runner.client(), suggester.settings());

import java.util.concurrent.ConcurrentMap;
import java.util.concurrent.atomic.AtomicLong;

import org.codelibs.core.exception.InterruptedRuntimeException;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.SystemUtil;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;

/**