"roles": {
      "type": "keyword"
    },
    "languages": {
      "type": "keyword"
    },
    "score": {
      "type": "double"
    },
    "tags": {
      "type": "keyword"
    },
    "text": {
      "type": "keyword"
    },
    "userBoost": {
      "type": "double"
    }
  }

  </mime-type>

  <mime-type type="text/csv">
    <glob pattern="*.csv"/>
    <sub-class-of type="text/plain"/>
  </mime-type>

  <mime-type type="text/directory"/>
  <mime-type type="text/dns"/>
  <mime-type type="text/ecmascript"/>
  <mime-type type="text/enriched"/>
  <mime-type type="text/example"/>

  <mime-type type="text/html">

    public List<String> convert(final String text, final String field, final String... lang) {
        final List<String> list = new ArrayList<>();

        final List<StringBuilder> bufList = new ArrayList<>();
        bufList.add(new StringBuilder());
        for (int i = 0; i < text.length();) {
            String[] alphabets;
            if (i + 1 < text.length() && convertMap.get(text.substring(i, i + 2)) != null) {

        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(""));

        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);

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

                })//
        ;

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

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

        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.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;

 * 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>