URL url = new URL("gcs://mybucket/dir1/dir2/file.pdf");
        Handler handler = new Handler();
        URLConnection conn = handler.openConnection(url);

        Handler.GcsURLConnection gcsConn = (Handler.GcsURLConnection) conn;

        assertEquals("mybucket", getField(gcsConn, "bucketName"));
        assertEquals("dir1/dir2/file.pdf", getField(gcsConn, "objectName"));
    }

    /**

        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() {

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

    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()),

 *   <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

						<option value="html" <c:if test="${as.filetype.contains('html')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_html"
							/></option>
						<option value="pdf" <c:if test="${as.filetype.contains('pdf')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_pdf"
							/></option>
						<option value="word" <c:if test="${as.filetype.contains('word')}">selected</c:if>><la:message

        pdfResult.setMethod("GET");
        pdfResult.setMimeType("application/pdf");
        pdfResult.setParentUrl("http://www.parent.com/");
        pdfResult.setRuleId("pdfRule");
        pdfResult.setSessionId(sessionId);
        pdfResult.setStatus(200);
        pdfResult.setUrl("http://www.example.com/document.pdf");
        dataService.store(pdfResult);

        // Filter by MIME type

crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

### URL Filtering

```java
// Include patterns
crawler.urlFilter.addInclude("https://example.com/.*");
crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols

        when(locator.getCanonicalURL()).thenReturn("smb://server/share/");

        // Mock directory listing
        SmbFile file1 = mock(SmbFile.class);
        when(file1.getName()).thenReturn("document.pdf");
        when(file1.isDirectory()).thenReturn(false);
        when(file1.length()).thenReturn(2048L);
        when(file1.lastModified()).thenReturn(System.currentTimeMillis());

        URL url = new URL("storage://mybucket/dir1/dir2/file.pdf");
        Handler handler = new Handler();
        URLConnection conn = handler.openConnection(url);

        Handler.StorageURLConnection storageConn = (Handler.StorageURLConnection) conn;

        assertEquals("mybucket", getField(storageConn, "bucketName"));
        assertEquals("dir1/dir2/file.pdf", getField(storageConn, "objectName"));
    }

    /**