DataStoreParams paramMap = new DataStoreParams();
        paramMap.put("url_exclude_pattern", ".*\\.pdf$");

        boolean result1 = indexUpdateCallback.isUrlCrawlable(paramMap, "http://example.com/test.html");
        boolean result2 = indexUpdateCallback.isUrlCrawlable(paramMap, "http://example.com/test.pdf");

        assertTrue(result1);
        assertFalse(result2);

 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {
 *     ExtractData extractData = new ExtractorBuilder(crawlerContainer, in, new HashMap<>())
 *         .mimeType("application/pdf")
 *         .filename("example.pdf")
 *         .maxContentLength(1024 * 1024)
 *         .extract();
 *
 *     String content = extractData.getContent();

		</postConstruct>
		<postConstruct name="addRule">
			<arg>"mimeType"</arg>
			<!-- Supported MIME type -->
			<arg>
  "(application/xml"
+ "|application/xhtml+xml"
+ "|application/rdf+xml"
+ "|application/pdf"
+ "|application/x-freemind"
+ "|text/xml"
+ "|text/xml-external-parsed-entity)"
			</arg>
		</postConstruct>
	</component>

	<component name="fsFileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >

        }
    }

    /**
     * Adds or updates a MIME type to file type mapping.
     *
     * @param mimetype the MIME type to map (e.g., "application/pdf")
     * @param filetype the file type classification (e.g., "pdf")
     */
    public void add(final String mimetype, final String filetype) {
        mimetypeMap.put(mimetype, filetype);
    }

    /**

application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File
application/oda                oda
application/pagemaker          pm5 pt5 pm       # PageMaker
application/pdf                pdf              # Adobe Acrobat
application/postscript         ai eps ps        # Postscript File
application/rtf                rtf              # Rich Text File
application/toolbook           tbk              # Toolbook

 *   <li>Maximum term sizes for alphanumeric and symbolic terms</li>
 *   <li>Custom Tika configuration</li>
 *   <li>Tesseract OCR configuration for image-based documents</li>
 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *
 * <p>
 * The {@link TikaDetectParser} inner class extends {@link CompositeParser} to provide auto-detection of the MIME type

    void fakeImplementation_happyPath() {
        // Arrange
        FileEntry e = new TestFileEntry("doc.pdf", 2, 0x10, 10L, 20L, 30L, 4096L, 3);

        // Act & Assert: getters return exactly what was provided
        assertAll(() -> assertEquals("doc.pdf", e.getName()), () -> assertEquals(2, e.getType()),
                () -> assertEquals(0x10, e.getAttributes()), () -> assertEquals(10L, e.createTime()),

application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File
application/oda                oda
application/pagemaker          pm5 pt5 pm       # PageMaker
application/pdf                pdf              # Adobe Acrobat
application/postscript         ai eps ps        # Postscript File
application/rtf                rtf              # Rich Text File
application/toolbook           tbk              # Toolbook

        extractorFactory.addExtractor("application/vnd.ms-powerpoint", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.visio", tikaExtractor);
        extractorFactory.addExtractor("application/pdf", pdfExtractor);
        extractorFactory.addExtractor("application/x-lha", lhaExtractor);
        extractorFactory.addExtractor("application/x-lharc", lhaExtractor);

    }

    public void test_addExtractor() {

```

Default config includes most common highly compressible content extensions and mime-types.

```bash
~ mc admin config set myminio compression extensions=".pdf" mime_types="application/pdf"
```

To show help on setting compression config values.

```bash
~ mc admin config set myminio compression
```

To enable compression for all content, no matter the extension and content type