/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>

 *   <li>{@link #getQueryWordsNum()}: Returns the number of query words in the suggestion index.</li>
 * </ul>
 *
 * <p>Protected Methods:
 * <ul>
 *   <li>{@link #createDefaultIndexer()}: Creates a default SuggestIndexer instance.</li>
 * </ul>
 *
 * <p>Private Methods:
 * <ul>
 *   <li>{@link #getNum(QueryBuilder)}: Returns the number of words matching the given query.</li>

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

/**
 * Implementation of the {@link LogHelper} interface.
 * This class provides methods for logging various events during the crawling process.
 * It uses Log4j2 for logging.
 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>

import org.apache.http.auth.Credentials;
import org.apache.http.auth.MalformedChallengeException;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpUriRequest;
import org.apache.http.message.BasicNameValuePair;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

import org.opensearch.OpenSearchStatusException;
import org.opensearch.action.admin.indices.analyze.AnalyzeAction.AnalyzeToken;

/**
 * DefaultContentsParser is an implementation of the ContentsParser interface.
 * It provides methods to parse search words, query logs, and documents into SuggestItem objects.
 *
 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *

        assertEquals(1, item.getKinds().length);
        assertEquals(SuggestItem.Kind.DOCUMENT, item.getKinds()[0]);
    }

    @Test
    public void testGettersAndSetters() {
        // Test all getter and setter methods
        String[] text = { "initial" };
        String[][] readings = { { "read" } };
        SuggestItem item = new SuggestItem(text, readings, null, 0L, 0L, 1.0f, null, null, null, SuggestItem.Kind.USER);

import org.opensearch.index.query.QueryBuilders;
import org.opensearch.search.SearchHit;
import org.opensearch.transport.client.Client;

/**
 * The ArraySettings class provides methods to manage settings stored in an array format within an OpenSearch index.
 * It allows adding, retrieving, and deleting settings based on keys and values.
 *
 * <p>Constructor:
 * <ul>

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

import java.util.Date;

import org.apache.http.client.methods.HttpUriRequest;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ResponseData;

import org.apache.http.client.AuthCache;
import org.apache.http.client.CredentialsProvider;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.config.RegistryBuilder;
import org.apache.http.entity.mime.HttpMultipartMode;

 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>