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

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
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;

	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<include path="crawler/robotstxt.xml" />
	<include path="crawler/contentlength.xml" />
	<include path="crawler/mimetype.xml" />

	<component name="internalHttpClient" class="org.codelibs.fess.crawler.client.http.HcHttpClient"
		instance="prototype">
		<property name="connectionTimeout">15000</property>

	<modelVersion>4.0.0</modelVersion>
	<groupId>org.codelibs.fess</groupId>
	<artifactId>fess-crawler-parent</artifactId>
	<version>15.3.0-SNAPSHOT</version>
	<packaging>pom</packaging>
	<name>Fess Crawler Project</name>
	<description>Fess Crawler is Crawler Framework.</description>
	<url>https://github.com/codelibs/fess-crawler</url>
	<inceptionYear>2009</inceptionYear>
	<licenses>
		<license>

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor;

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

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.

        helper.setCrawlerWaitMillis(50);

        // Test when crawler is running
        assertTrue(helper.isCrawlerRunning());
        long start = System.currentTimeMillis();
        helper.checkCrawlerStatus();
        long end = System.currentTimeMillis();
        assertTrue(end - start < 100); // Should return quickly

        // Test when crawler is not running
        helper.setCrawlerRunning(false);

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

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
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;

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

import java.util.Map;

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

/**
 * Interface representing a client for a web crawler.
 * This client is responsible for executing requests and handling responses.

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

                return existingInfo;
            }

            @Override
            public void store(CrawlingInfo entity) {
                // Should not be called for existing info
                fail("Store should not be called for existing info");
            }

            @Override
            public void storeInfo(List<CrawlingInfoParam> crawlingInfoParamList) {

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

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;