*/
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *
     * @return a map containing the document's data, or null if there are no more documents to read.
     */
    Map<String, Object> read();

    @Override
    void close();

     * @param off the start offset in array b at which the data is written
     * @param len the maximum number of bytes to read
     * @return the total number of bytes read into the buffer, or -1 if there is no more data
     * @throws IOException if an I/O error occurs
     */
    @Override
    public int read(final byte[] b, final int off, final int len) throws IOException {
        return inputStream.read(b, off, len);
    }

 * 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 org.codelibs.core.lang.StringUtil;

/**
 * Represents a URL entry within a sitemap.
 *
 * <p>
 * This class encapsulates the properties of a URL as defined in the sitemap XML format,

        limitConverter.init();

        assertEquals(5, limitConverter.getMaxReadingNum());

        String text = "test";
        String field = "content";

        // Request more languages than max reading num
        List<String> readings = limitConverter.convert(text, field, "en", "ja", "fr", "de", "es", "it", "pt");

        assertNotNull(readings);

import org.apache.commons.pool2.impl.DefaultPooledObject;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.pool.CrawlerPooledObjectFactory.OnDestroyListener;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for CrawlerPooledObjectFactory.
 * Tests the pooled object factory functionality including object creation,
 * wrapping, destruction, and listener mechanisms.
 */

import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.SystemUtil;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;

import java.util.List;

import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.TermQuery;
import org.codelibs.core.CoreLibConstants;
import org.codelibs.fess.suggest.Suggester;
import org.codelibs.fess.suggest.converter.ReadingConverter;
import org.codelibs.fess.suggest.entity.SuggestItem;

import java.util.concurrent.atomic.AtomicInteger;

import org.codelibs.core.collection.LruHashSet;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for CrawlerContext.

			<version>${slf4j.version}</version>
		</dependency>
		<dependency>
			<groupId>com.fasterxml.jackson.core</groupId>
			<artifactId>jackson-databind</artifactId>
			<version>${jackson.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-core</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;