testFileTypeHelper.setTypes(new String[] { "pdf", "doc" });

        // Add existing file type query
        facetQueryView.addQuery("existing_pdf", "filetype:pdf");
        facetQueryView.addQuery("label1", "filetype:html");

        facetQueryView.init();

        Map<String, String> queryMap = facetQueryView.getQueryMap();

        // Should not duplicate existing pdf query

    }

    public void test_createTask_withValidParams() {
        // Test task creation with valid parameters
        String path = "/path/to/document.pdf";
        Map<String, Object> docMap = new HashMap<>();
        docMap.put("mimetype", "application/pdf");
        docMap.put("title", "Test Document");

        Tuple3<String, String, String> task = thumbnailGenerator.createTask(path, docMap);
        assertNotNull(task);

	testCases := []struct {
		objectName string
		sipHash    int
	}{
		// cases which should pass the test.
		// passing in valid object name.
		{"object", 37},
		{"The Shining Script <v1>.pdf", 38},
		{"Cost Benefit Analysis (2009-2010).pptx", 59},
		{"117Gn8rfHL2ACARPAhaFd0AGzic9pUbIA/5OCn5A", 35},
		{"SHØRT", 49},
		{"There are far too many object names, and far too few bucket names!", 8},
		{"a/b/c/", 159},

        String sessionId = "test-session-019";
        urlFilter.init(sessionId);

        urlFilter.addInclude(".*\\.PDF$");

        // Test case sensitivity
        assertFalse(urlFilter.match("https://example.com/document.pdf"));
        assertTrue(urlFilter.match("https://example.com/document.PDF"));
    }

    /**
     * Test very long URL handling
     */
    public void test_veryLongUrl() {

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

        final String tempPath = "/tmp/source.pdf";
        final String outputPath = "/tmp/thumbnail.jpg";

        final String expandedCommand = testCommand.replace("${url}", tempPath).replace("${outputFile}", outputPath);

        assertEquals("convert /tmp/source.pdf -resize 100x100 /tmp/thumbnail.jpg", expandedCommand);

        exception = new SmbOperationException(SmbOperationException.ErrorCode.FILE_EXISTS, "document.pdf already exists");
        assertTrue(exception.getMessage().contains("FILE_EXISTS"));
        assertTrue(exception.getMessage().contains("File already exists"));
        assertTrue(exception.getMessage().contains("document.pdf already exists"));

        // Without custom message

        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());

        UrlPatternRule rule1 = new UrlPatternRule("httpRule", "https?://.*");
        UrlPatternRule rule2 = new UrlPatternRule("exampleRule", ".*example\\.com.*");
        UrlPatternRule rule3 = new UrlPatternRule("pdfRule", ".*\\.pdf$");

        ruleManager.addRule(rule1);
        ruleManager.addRule(rule2);
        ruleManager.addRule(rule3);

        ResponseData responseData1 = new ResponseData();

		hashedOrder []int
	}{
		// cases which should pass the test.
		// passing in valid object name.
		{"object", []int{14, 15, 16, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13}},
		{"The Shining Script <v1>.pdf", []int{16, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}},
		{"Cost Benefit Analysis (2009-2010).pptx", []int{15, 16, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14}},