import java.util.regex.Pattern;

import org.apache.commons.io.ByteOrderMark;
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;

<setting id="org.eclipse.jdt.core.formatter.comment.new_lines_at_block_boundaries" value="true"/>
<setting id="org.eclipse.jdt.core.formatter.insert_space_after_comma_in_constructor_declaration_parameters" value="insert"/>
<setting id="org.eclipse.jdt.core.formatter.comment.insert_new_line_for_parameter" value="insert"/>

<setting id="org.eclipse.wst.jsdt.core.formatter.comment.format_header" value="true"/>
<setting id="org.eclipse.wst.jsdt.core.formatter.insert_space_before_closing_paren_in_method_invocation" value="do not insert"/>
<setting id="org.eclipse.wst.jsdt.core.formatter.never_indent_line_comments_on_first_column" value="false"/>
<setting id="org.eclipse.wst.jsdt.core.formatter.comment.format_block_comments" value="true"/>

 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>
 *   <li>Reading content as plain text if all other methods fail</li>
 *   <li>Applying post-extraction filters</li>
 *   <li>Handling Tika exceptions, including zip bomb exceptions</li>
 * </ul>
 *
 * <p>
 * The class also supports configuration options such as:
 * </p>

      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier

      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier

     <alias type="application/x-cdr"/>
     <alias type="application/cdr"/>
     <alias type="image/x-cdr"/>
     <alias type="image/cdr"/>
     <_comment>CorelDraw</_comment>
     <_comment>cdr: CorelDraw</_comment>
     <_comment>des: CorelDraw X4 and newer</_comment>
     <magic priority="60">
        <match value="RIFF" type="string" offset="0">
           <match value="CDR" type="string" offset="8" />

### Key Features

- **Multi-Protocol Support**: HTTP/HTTPS, File System, FTP, SMB/CIFS, Cloud Storage (MinIO, S3)

        assertEquals(content, text.getContent());
    }

    public void test_getText_withUrl() throws IOException {
        final File scriptFile = createScriptTempFile(3);
        final String content = "TEST";
        final File contentFile = createContentFile(".txt", content.getBytes());

        final CommandExtractor extractor = new CommandExtractor();
        extractor.command = getCommand(scriptFile);

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/zip/test.zip");
        final String content = zipExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {