*/
package org.codelibs.fess.crawler;

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;

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

    /**
     * Extracts text from the Word input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

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

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
import java.util.stream.Stream;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.suggest.constants.FieldNames;
import org.codelibs.fess.suggest.constants.SuggestConstants;

 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**
     * Serial version UID for serialization.
     */
    private static final long serialVersionUID = 1L;

    private static final Logger logger = LogManager.getLogger(SitemapsRule.class);

    /**

 * responseData.setContentType("text/html");
 *
 * boolean matches = rule.match(responseData); // Returns true
 * }
 * </pre>
 *
 */
public class RegexRule extends AbstractRule {

    /** Serial version UID for serialization. */
    private static final long serialVersionUID = 1L;

    /** Whether this rule should match all responses by default. */
    protected boolean defaultRule = false;

     */
    protected ExtractData createExtractData(final String content) {
        return new ExtractData(extractString(content));
    }

    /**
     * Detects the encoding of the input stream.
     * @param bis The buffered input stream.
     * @return The detected encoding.
     */
    protected String getEncoding(final BufferedInputStream bis) {
        final byte[] b = new byte[preloadSizeForCharset];
        try {

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

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

        super();
    }

    /**
     * Extracts text content from an LHA archive input stream.
     *
     * @param in the input stream containing the LHA archive
     * @param params extraction parameters
     * @return the extracted text data
     * @throws CrawlerSystemException if the input stream is null
     * @throws ExtractException if an error occurs during extraction

     * Constructs a new FilenameExtractor.
     */
    public FilenameExtractor() {
        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.
     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.
     * @return An ExtractData object containing the filename as content.
     */
    @Override