<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">1</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

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

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,

    <!--  files which contain HTML within them, eg mime emails -->
    <magic priority="40">
      <match value="&lt;!DOCTYPE HTML" type="string" offset="0:64"/>
      <match value="&lt;!DOCTYPE html" type="string" offset="0:64"/>
      <match value="&lt;!doctype HTML" type="string" offset="0:64"/>
      <match value="&lt;!doctype html" type="string" offset="0:64"/>
      <match value="&lt;HEAD" type="string" offset="0:64"/>

    }

    /**
     * Logs a message using the provided LogHelper.
     * @param logHelper The LogHelper instance.
     * @param key The LogType key.
     * @param objs The objects to log.
     */
    protected void log(final LogHelper logHelper, final LogType key, final Object... objs) {
        if (logHelper != null) {
            logHelper.log(key, objs);
        }
    }

    /**

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

import org.codelibs.fess.crawler.log.LogType;

/**
 * Interface for logging helper.
 * Provides a method to log messages with a specified log type and additional objects.
 */
public interface LogHelper {

    /**

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.service.UrlFilterService;
import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;
import org.opensearch.action.DocWriteRequest.OpType;
import org.opensearch.index.query.QueryBuilders;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

        super.insert(accessResult, accessResult.getId() == null ? OpType.CREATE : OpType.INDEX);
    }

    /**
     * Updates an access result in the OpenSearch index.
     *
     * @param accessResult The access result to update.
     */
    @Override
    public void update(final OpenSearchAccessResult accessResult) {
        super.insert(accessResult, OpType.INDEX);
    }

    /**

     * @param <T> The type of objects to insert.
     * @param list The list of objects to insert.
     * @param opType The operation type (CREATE, INDEX, etc.).
     * @throws OpenSearchAccessException if the bulk insertion fails.
     */
    protected <T> void insertAll(final List<T> list, final OpType opType) {
        insertAll(list, opType, false);
    }

    /**

        super();
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.helper.LogHelper#log(org.codelibs.fess.crawler.log.LogType,
     * java.lang.Object)
     */
    @Override
    public void log(final LogType key, final Object... objs) {
        switch (key) {
        case START_THREAD:
            processStartThread(objs);
            break;
        case START_CRAWLING:

                final IndexRequestBuilder indexRequestBuilder = new IndexRequestBuilder(client, IndexAction.INSTANCE, index);
                indexRequestBuilder.setId(item.getId())
                        .setOpType(IndexRequest.OpType.INDEX)
                        .setSource(item.getUpdatedSource(getResponse.getSourceAsMap()));
                bulkRequestBuilder.add(indexRequestBuilder);
            } else {