}

    public void setVersionNo(final Long version) {
        asDocMeta().version(version);
    }

    public org.codelibs.fess.crawler.client.http.RequestHeader getCrawlerRequestHeader() {
        return new org.codelibs.fess.crawler.client.http.RequestHeader(getName(), getValue());
    }

    public WebConfig getWebConfig() {
        if (webConfig == null) {

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

import java.io.File;

import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.mortbay.jetty.Handler;
import org.mortbay.jetty.Server;
import org.mortbay.jetty.handler.DefaultHandler;

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

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.util.TextUtil.TextNormalizeContext;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<component name="urlQueueService"
		class="org.codelibs.fess.crawler.service.FessUrlQueueService">
		<arg>crawlerConfig</arg>
	</component>

 * 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.function.Function;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

public class ResultDataTest extends PlainTestCase {

    public void test_setRawData() {

 */
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;

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"
  }

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing crawling configurations.
 * Provides functionality to store, retrieve, and manage different types of crawling configurations
 * including web, file, and data configurations. Supports caching and session-based configuration management.
 */
public class CrawlingConfigHelper {