* The pattern captures the charset value specified in the content attribute of the meta tag.
     * Example: <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**

     */
    public void addFieldRule(final String name, final String xpath) {
        fieldRuleMap.put(name, xpath);
    }

    /**
     * Returns data as XML content of String.
     *
     * @return XML content of String.
     */
    @Override
    public Object getData(final AccessResultData<?> accessResultData) {
        if (dataClass == null) {
            return super.getData(accessResultData);

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.
 */
public class TextExtractor extends AbstractExtractor {

    /**
     * The encoding for text.
     */
    protected String encoding = Constants.UTF_8;

    /**

     */
    public NTLMSchemeProvider() {
        super();
    }

    /**
     * Creates a new NTLMScheme instance.
     * @param context The HTTP context.
     * @return A new NTLMScheme instance.
     */
    @Override
    public AuthScheme create(final HttpContext context) {
        return new NTLMScheme(new SmbjEngine());
    }

 * 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();
    }

    /**

        } catch (final OfficeException e) {
            throw new ExtractException("Could not extract a content.", e);
        } finally {
            FileUtil.deleteInBackground(inputFile);
            FileUtil.deleteInBackground(outputFile);
        }
    }

    /**
     * Gets the output content from the converted file.
     *
     * @param outputFile the converted output file

    public void test_constructor() {
        CrawlerContext context = new CrawlerContext();
        assertNotNull(context);
        assertNull(context.getSessionId());
        assertEquals(0, context.getActiveThreadCount().intValue());
        assertEquals(0L, context.getAccessCount());
        assertEquals(CrawlerStatus.INITIALIZING, context.getStatus());
        assertNull(context.getUrlFilter());
        assertNull(context.getRuleManager());

import org.opensearch.action.admin.indices.refresh.RefreshResponse;
import org.opensearch.action.search.SearchResponse;
import org.opensearch.cluster.metadata.AliasMetadata;
import org.opensearch.common.xcontent.XContentType;
import org.opensearch.index.query.QueryBuilder;
import org.opensearch.index.query.QueryBuilders;
import org.opensearch.transport.client.Client;

/**

**Screenshots**
If applicable, add screenshots to help explain your problem.

**Environment (please complete the following information):**
 - OS: [e.g. Windows 10]
 - Version [e.g. 3.5.0]

**Additional context**