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) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

 */
public interface DocumentReader extends Closeable {
    /**
     * Reads a document and returns its contents as a map.
     *
     * @return a map containing the document's data, or null if there are no more documents to read.
     */
    Map<String, Object> read();

    @Override
    void close();

│   ├── Suggester.java              # Main suggester API
│   ├── SuggesterBuilder.java       # Builder pattern implementation
│   ├── entity/
│   │   ├── SuggestItem.java        # Core suggestion data structure
│   │   └── ElevateWord.java        # Promoted words configuration
│   ├── request/                    # Request/Response handling
│   │   ├── suggest/                # Suggestion requests

            } else if (settings.get("synonyms_path") != null) {
                logger.warn("synonyms_path[{}] is empty.", settings.get("synonyms_path"));
            } else {
                logger.debug("No synonym data.");
            }
        }
    }

    @Override
    public Tokenizer create() {
        return new NGramSynonymTokenizer(n, delimiters, expand, ignoreCase, synonymLoader);
    }

     */
    @Override
    public synchronized void reset() throws IOException {
        fileInputStream.reset();
    }

    /**
     * Skips over and discards {@code n} bytes of data from this input stream.
     * This method delegates to {@link FileInputStream#skip(long)}.
     *
     * @param n the number of bytes to be skipped
     * @return the actual number of bytes skipped

 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.
 * This class encapsulates the essential attributes of a Sitemap entry, allowing for efficient management
 * and processing of Sitemap data.
 * </p>
 *
 * <p>
 * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
 * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers

h[2]===ec[2]&&(h[3]||("http:"===h[1]?"80":"443"))===(ec[3]||("http:"===ec[1]?"80":"443")))),k.data&&k.processData&&"string"!=typeof k.data&&(k.data=n.param(k.data,k.traditional)),sc(nc,k,b,v),2===t)return v;i=k.global,i&&0===n.active++&&n.event.trigger("ajaxStart"),k.type=k.type.toUpperCase(),k.hasContent=!kc.test(k.type),d=k.url,k.hasContent||(k.data&&(d=k.url+=(dc.test(d)?"&":"?")+k.data,delete k.data),k.cache===!1&&(k.url=hc.test(d)?d.replace(hc,"$1_="+cc++):d+(dc.test(d)?"&":"?")+"_="+cc++))...

    public MsVisioExtractor() {
        super();
    }

    /**
     * Extracts text from the Visio 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) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

    /**
     * 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
     * @throws MaxLengthExceededException if the extracted content size exceeds the maximum limit

import java.util.Map;
import java.util.Set;

import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * Represents the response data obtained from a crawled resource.
 * This class encapsulates various details of an HTTP response, including
 * status code, content type, content length, and the response body.