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

import java.util.HashMap;
import java.util.Map;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * Helper class for managing content length limits based on MIME types.
 * It allows setting default and MIME type-specific maximum content lengths.

        if (this == obj) {
            return true;
        }
        if (!(obj instanceof final SitemapFile sitemapUrl)) {
            return false;
        }
        if (StringUtil.equals(loc, sitemapUrl.loc) && StringUtil.equals(lastmod, sitemapUrl.lastmod)) {
            return true;
        }
        return false;
    }

    /**
     * Returns the hash code value for this SitemapFile.

        try {
            parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
            parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
        } catch (final Exception e) {
            if (logger.isDebugEnabled()) {
                logger.debug("Failed to set a property.", e);
            }

import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
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;

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

import org.codelibs.core.lang.StringUtil;

/**
 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,

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

import java.io.UnsupportedEncodingException;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * Implementation of the {@link AccessResultData} interface.
 *
 * @param <IDTYPE> the type of the identifier
 */

import java.util.Set;
import java.util.concurrent.ConcurrentHashMap;
import java.util.regex.Pattern;
import java.util.stream.Stream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.suggest.analysis.SuggestAnalyzer;
import org.codelibs.fess.suggest.constants.FieldNames;
import org.codelibs.fess.suggest.exception.SuggestSettingsException;

     * @param tagName the HTML tag name
     * @param attrName the attribute name to extract URLs from
     */
    public void addChildUrlRule(final String tagName, final String attrName) {
        if (StringUtil.isNotBlank(tagName) && StringUtil.isNotBlank(attrName)) {
            childUrlRuleMap.put(tagName, attrName);
        }
    }

    /**
     * Gets the XPath API instance for this thread.
     *

        File outputFile = null;
        try {
            inputFile =
                    createTempFile("cmdextin_" + filePrefix + "_", StringUtil.isNotBlank(extention) ? "." + extention : extention, tempDir);
            String ext;
            if (outputExtension == null) {
                if (StringUtil.isNotBlank(extention)) {
                    ext = "." + extention;
                } else {
                    ext = extention;

import java.util.Map;

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.mime.MimeTypes;
import org.apache.tika.mime.MimeTypesFactory;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MimeTypeException;