import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;
import org.opensearch.index.analysis.Analysis;

public class PosConcatenationFilterFactory extends AbstractTokenFilterFactory {

    private final Set<String> posTags = new HashSet<>();

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

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

    /**
     * Pattern for XML encoding.

import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

/**
 * Utility class for managing crawling parameters using ThreadLocal variables.
 * This class provides methods to set and get various parameters related to the crawling process.
 *
 * <p>This class is final and cannot be instantiated.</p>
 *
 * <p>The following parameters are managed:</p>
 * <ul>

        container.singleton("mimeTypeHelper", MimeTypeHelperImpl.class)
                .singleton("tikaExtractor", TikaExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);

<!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="urlFilter"
		class="org.codelibs.fess.crawler.filter.impl.UrlFilterImpl" instance="prototype">
	</component>

import org.codelibs.jcifs.smb.ntlmssp.Type2Message;
import org.codelibs.jcifs.smb.ntlmssp.Type3Message;

/**
 * JcifsEngine is a NTLM Engine implementation based on JCIFS.
 *
 * @author shinsuke
 *
 */
public class JcifsEngine implements NTLMEngine {

    /** Flags for Type 1 NTLM message. */
    protected static final int TYPE_1_FLAGS = NtlmFlags.NTLMSSP_NEGOTIATE_56 | NtlmFlags.NTLMSSP_NEGOTIATE_128

import java.util.regex.Pattern;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class RegexRuleTest extends PlainTestCase {

    public void test_match_default() {
        final RegexRule regexRule = new RegexRule();
        regexRule.defaultRule = true;
        regexRule.allRequired = true;

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
 */
public class AccessResultDataImpl<IDTYPE> implements AccessResultData<IDTYPE> {
    /** The unique identifier for the access result data. */
    protected IDTYPE id;

import org.opensearch.core.xcontent.ToXContent;
import org.opensearch.core.xcontent.XContentBuilder;

/**
 * OpenSearchAccessResultData is an implementation of {@link AccessResultData} for OpenSearch.
 */
public class OpenSearchAccessResultData extends AccessResultDataImpl<String> implements ToXContent {

    /**
     * Field name for ID.
     */
    public static final String ID = "id";

    /**

import org.opensearch.core.xcontent.ToXContent;
import org.opensearch.core.xcontent.XContentBuilder;

/**
 * OpenSearchUrlQueue is an implementation of {@link UrlQueue} for OpenSearch.
 */
public class OpenSearchUrlQueue extends UrlQueueImpl<String> implements ToXContent {

    /**
     * Creates a new instance of OpenSearchUrlQueue.
     */
    public OpenSearchUrlQueue() {
        // NOP
    }

    /**