*/
package org.codelibs.fess.suggest.normalizer;

import com.ibm.icu.text.Transliterator;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *
 * <p>This class uses a specified Transliterator to perform text normalization.
 * The Transliterator is initialized with a given ID during the construction of

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke
 *
 */
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.

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;

    /**
     * Creates a new TextExtractor instance.
     */

        assertNotNull(accessResult2);

        accessResult2.setMimeType("text/html");
        dataService.update(accessResult2);

        final AccessResult accessResult3 = dataService.getAccessResult("id1", "http://www.id1.com/");
        assertNotNull(accessResult3);
        assertEquals("text/html", accessResult3.getMimeType());

        dataService.delete("id1");

        /**
         * Analyzes the given text.
         * @param text The text to analyze.
         * @param field The field name.
         * @param lang The language.
         * @return A list of analyzed tokens.
         */
        @Override
        public List<AnalyzeToken> analyze(final String text, final String field, final String lang) {
            if (text == null || text.length() > maxContentLenth) {

            public void init() throws IOException {

            }

            @Override
            public List<String> convert(String text, final String field, String... langs) throws IOException {
                return null;
            }
        };

        final Normalizer normalizer = (text, field, lang) -> null;

        final Suggester suggester = Suggester.builder()

                    ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

                })//
        ;

    void init() throws IOException;

    /**
     * Converts the given text into a list of readings based on the specified field and languages.
     *
     * @param text the text to be converted.
     * @param field the field to be used for conversion.
     * @param langs the languages to be used for conversion.
     * @return a list of readings for the given text.
     * @throws IOException if an I/O error occurs during conversion.
     */

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.

 * chain.add(new SomeNormalizer());
 * chain.add(new AnotherNormalizer());
 * String normalizedText = chain.normalize("input text", "field", "en");
 * </pre>
 *
 * <p>Methods:</p>
 * <ul>
 *   <li>{@link #normalize(String, String, String...)} - Applies all added normalizers to the input text.</li>
 *   <li>{@link #add(Normalizer)} - Adds a new normalizer to the chain.</li>
 * </ul>
 *
 * <p>Fields:</p>
 * <ul>