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.

 * The {@link TikaExtractor} class is responsible for extracting text content and metadata from various file formats
 * 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>

        assertEquals(fooAuth, smbAuthenticationHolder.get("smb://foo:1000/"));
        assertEquals(hogeAuth, smbAuthenticationHolder.get("smb://hoge/text.txt"));
        assertEquals(fugaAuth, smbAuthenticationHolder.get("smb://fuga/text.txt"));
        assertEquals(fooAuth, smbAuthenticationHolder.get("smb://foo:1000/text.txt"));

        assertNull(smbAuthenticationHolder.get(null));
        assertNull(smbAuthenticationHolder.get(""));

                    LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/x-lha", lhaExtractor);

                })//
        ;

        extractor.command = getCommand(scriptFile);
        final Map<String, String> params = new HashMap<String, String>();
        final ExtractData text = extractor.getText(new FileInputStream(contentFile), params);
        assertEquals(content, text.getContent());
    }

    public void test_getText_withUrl() throws IOException {
        final File scriptFile = createScriptTempFile(3);

<map version="0.7.1">
<node TEXT="&#12479;&#12452;&#12488;&#12523;">
<node TEXT="&#12486;&#12473;&#12488;" MODIFIED="1237874353965" STYLE="fork"/>
</node>

        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
        extractorFactory.addExtractor("text/plain", tikaExtractor);
        extractorFactory.addExtractor("text/html", tikaExtractor);
    }

    public void test_name() {
        assertEquals("textTransformer", textTransformer.getName());
    }

import org.apache.commons.io.input.BOMInputStream;
import org.apache.commons.text.translate.AggregateTranslator;
import org.apache.commons.text.translate.CharSequenceTranslator;
import org.apache.commons.text.translate.EntityArrays;
import org.apache.commons.text.translate.LookupTranslator;
import org.apache.commons.text.translate.NumericEntityUnescaper;
import org.apache.logging.log4j.LogManager;

        assertEquals(fooAuth, smbAuthenticationHolder.get("smb1://foo:1000/"));
        assertEquals(hogeAuth, smbAuthenticationHolder.get("smb1://hoge/text.txt"));
        assertEquals(fugaAuth, smbAuthenticationHolder.get("smb1://fuga/text.txt"));
        assertEquals(fooAuth, smbAuthenticationHolder.get("smb1://foo:1000/text.txt"));

        assertNull(smbAuthenticationHolder.get(null));
        assertNull(smbAuthenticationHolder.get(""));

import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extracts text content from various document formats using JODConverter.
 */
public class JodExtractor extends AbstractExtractor {
    /** Logger for this class. */