*
 */
public class MsWordExtractor extends AbstractExtractor {

    /**
     * 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 class MsExcelExtractor extends AbstractExtractor {

    /**
     * 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

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.

 * 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>

        super(params);
    }

    /**
     * Delays before processing a URL, ensuring that requests to the same host are not made too frequently.
     * This method extracts the host from the URL and enforces a delay based on the configured
     * delayMillisBeforeProcessing parameter.
     *
     * @throws InterruptedRuntimeException if the thread is interrupted during the delay

 * only one of them (allRequired = false). It also supports a default rule that always matches.
 *
 * <p>
 * The class uses a map of field names to Pattern objects to store the regular expressions.
 * The match method extracts the values of the specified fields from the ResponseData and
 * applies the corresponding regular expressions.
 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code

import jakarta.annotation.Resource;

/**
 * <p>
 * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.
 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>
 * This class provides several configuration options to customize the XML parsing process, such as:
 * </p>
 * <ul>

            } catch (final Exception e) {
                throw new OpenSearchAccessException("response: " + response, e);
            }
        }
        return targetList;
    }

    /**
     * Extracts a field value from OpenSearch results and converts it to the specified type.
     *
     * @param <T> The target type.
     * @param field The field value from OpenSearch.
     * @param clazz The target class.

            }
        } else if (logger.isDebugEnabled()) {
            logger.debug("{} mapping exists.", index);
        }
    }

    /**
     * Extracts a Date object from the source map using the specified field name.
     * Handles various date formats including Date objects, timestamp numbers, and ISO date strings.
     *

import jakarta.annotation.Resource;

/**
 * {@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.