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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.extractor.impl.LhaExtractor;
import org.codelibs.fess.crawler.extractor.impl.PasswordBasedExtractor;
import org.codelibs.fess.crawler.extractor.impl.PdfExtractor;

	if objectSize == -1 {
		objectSize = maxMultipartPutObjectSize
	}

	// object size is larger than supported maximum.
	if objectSize > maxMultipartPutObjectSize {
		err = errors.New("entity too large")
		return
	}

	configuredPartSize := minPartSize
	// Use floats for part size for all calculations to avoid
	// overflows during float64 to int64 conversions.

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;

import org.codelibs.core.io.FileUtil;
import org.codelibs.core.misc.DynamicProperties;
import org.codelibs.fess.Constants;
import org.codelibs.fess.entity.FacetInfo;
import org.codelibs.fess.entity.GeoInfo;
import org.codelibs.fess.entity.QueryContext;
import org.codelibs.fess.entity.SearchRequestParams.SearchRequestType;
import org.codelibs.fess.exception.InvalidQueryException;
import org.codelibs.fess.mylasta.direction.FessConfig;

   * they're defined above -- including logic to add and subtract 1 to map between the values stored
   * in the predecessor/successor arrays and the indexes in the elements array that they identify.
   */

/**
 * Represents a tag configuration for pruning HTML content during document processing.
 * This class defines tag patterns that match HTML elements based on tag name, CSS class, ID, or custom attributes.
 * It is used to identify and remove unwanted HTML elements from crawled documents.
 */
public class PrunedTag {
    /** The HTML tag name to match (e.g., "div", "span", "p") */
    private final String tag;
    /** The ID attribute value to match */

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.client.ftp.FtpClient.FtpInfo;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

import java.util.concurrent.TimeUnit;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.entity.SearchRequestParams.SearchRequestType;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.suggest.exception.SuggesterException;

import org.apache.logging.log4j.Logger;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.WildcardQuery;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.entity.QueryContext;
import org.codelibs.fess.exception.InvalidQueryException;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;
import org.lastaflute.core.message.UserMessages;

import org.apache.logging.log4j.Logger;
import org.codelibs.core.collection.ArrayUtil;
import org.codelibs.core.stream.StreamUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.entity.SearchRequestParams;
import org.codelibs.fess.helper.ViewHelper;
import org.codelibs.fess.mylasta.action.FessUserBean;
import org.codelibs.fess.mylasta.direction.FessConfig;