import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {

    }

    @ParameterizedTest
    @ValueSource(ints = { TransPeekNamedPipeResponse.STATUS_DISCONNECTED, TransPeekNamedPipeResponse.STATUS_SERVER_END_CLOSED })
    @DisplayName("available() on SMB1 returns 0 and marks closed on disconnected statuses")
    void available_smb1_disconnectedStatuses(int status) throws Exception {
        // Verify SMB1 path: disconnected/server-closed statuses yield 0 and mark fd closed

            } else {
                setAccessResultData(null);
            }
        }
        return accessResultData;
    }

    /**
     * Sets the access result data and marks it as initialized.
     *
     * @param accessResultDataAsOne The access result data to set.
     */
    @Override
    public void setAccessResultData(final AccessResultData<String> accessResultDataAsOne) {

import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import javax.xml.XMLConstants;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;

            }

            // If pattern doesn't end with $, it implicitly matches anything after it
            if (pattern.isEmpty() || pattern.charAt(pattern.length() - 1) != '$') {
                // This makes "/fish" match "/fish", "/fishing", "/fish/", etc.
                // No need to add anything - the pattern naturally continues
            }

            return Pattern.compile(regex.toString());
        }

import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import javax.xml.XMLConstants;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.apache.commons.lang3.StringUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;

        protected long count;

        /**
         * Maximum number of files to purge in a single operation.
         */
        protected final int maxPurgeSize;

        /**
         * List of files marked for deletion.
         */
        protected final List<Path> deletedFileList = new ArrayList<>();

        /**
         * Base path for thumbnail storage.
         */
        protected final Path basePath;

        byte[] body = buildCreateBodyNoContexts((byte) 0, (byte) 0, 0, 0L, 0L, 0L, 0L, 0L, 0L, 0, fileId);
        byte[] packet = buildPacket(header, body, null, null);
        resp.decode(packet, 0, false); // marks as received

        // Create a request that implements both CommonServerMessageBlockRequest and RequestWithFileId
        CommonServerMessageBlockRequest next =

│   │   └── popularwords/           # Popular words requests
│   ├── index/                      # Indexing functionality
│   │   ├── SuggestIndexer.java     # Main indexing API
│   │   ├── contents/               # Content parsers and readers
│   │   └── writer/                 # Index writing strategies
│   ├── converter/                  # Text conversion utilities
│   ├── normalizer/                 # Text normalization