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

import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

/**
 * @author shinsuke
 *
 */

import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.suggest.analysis.SuggestAnalyzer;
import org.codelibs.fess.suggest.concurrent.Deferred;
import org.codelibs.fess.suggest.constants.FieldNames;
import org.codelibs.fess.suggest.converter.ReadingConverter;
import org.codelibs.fess.suggest.entity.ElevateWord;
import org.codelibs.fess.suggest.entity.SuggestItem;
import org.codelibs.fess.suggest.exception.SuggestIndexException;

<?xml version="1.0" encoding="UTF-8" ?>
<eef>
	<config Schema="2.0" EnterpriseVersion="'7.6.50'">
		<collections Count="3">
			<collection Name="fess">
				<bad_urls><![CDATA[
https://fess.codelibs.org/images/
              ]]></bad_urls>
				<good_urls><![CDATA[
https://fess.codelibs.org/
https://www.codelibs.org/
              ]]></good_urls>
				<prerequisite_results><![CDATA[
20
              ]]></prerequisite_results>

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

import java.io.IOException;
import java.io.InputStream;

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 java.util.stream.Stream;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.annotation.Secured;
import org.codelibs.fess.app.web.base.FessAdminAction;
import org.codelibs.fess.exception.FessSystemException;
import org.codelibs.fess.helper.SystemHelper;
import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.RenderDataUtil;
import org.lastaflute.di.exception.IORuntimeException;

import org.codelibs.core.security.MessageDigestUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.app.service.CrawlingInfoService;
import org.codelibs.fess.es.client.SearchEngineClient;
import org.codelibs.fess.es.config.exentity.CrawlingConfig;
import org.codelibs.fess.es.config.exentity.CrawlingInfo;
import org.codelibs.fess.es.config.exentity.CrawlingInfoParam;
import org.codelibs.fess.exception.FessSystemException;

## Externe Kurse

Obwohl das [Tutorial – Benutzerhandbuch](../tutorial/index.md){.internal-link target=_blank} und dieses **Handbuch für fortgeschrittene Benutzer** als geführtes Tutorial (wie ein Buch) geschrieben sind und für Sie ausreichen sollten, um **FastAPI zu lernen**, möchten Sie sie vielleicht durch zusätzliche Kurse ergänzen.

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

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.
 *

#!/bin/bash

touch $(ls -d ./fess-*/logs)/fess-crawler.log
tail -f ./fess-*/logs/*.log &

mvn test -P integrationTests -Dtest.fess.url="http://localhost:8080" -Dtest.search_engine.url="http://localhost:9201"
ret=$?

if [ $ret != 0 ] ; then
  for f in `find ./target -type f | grep surefire-reports | grep -v /TEST-` ; do
    cat $f
  done
fi

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

import java.io.IOException;
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;

/**