url = "http://test.com/hoge1.pdf";
        resourceName = null;
        assertNull(tikaExtractor.getPassword(createParams(url, resourceName)));

        url = "http://test.com/hoge1.pdf";
        resourceName = "hoge2.pdf";
        assertNull(tikaExtractor.getPassword(createParams(url, resourceName)));

        url = null;
        resourceName = "hoge2.pdf";

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:

        "fe012443-6ba9-4ef2-bb94-b729d2060c78/test123/testw3c.pdf/xl.meta": {"Versions":[{"Type":1,"V2Obj":{"ID":"aGEA/ZUOR4ueRIZsAgfDqA==","DDir":"9MMwM47bS+K6KvQqN3hlDw==","EcAlgo":1,"EcM":2,"EcN":2,"EcBSize":1048576,"EcIndex":1,"EcDist":[4,1,2,3],"CSumAl...

	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},

        // Presentation Formats
        extensionMap.put("odp", "pdf");
        extensionMap.put("otp", "pdf");
        extensionMap.put("sxi", "pdf");
        extensionMap.put("ppt", "pdf");
        extensionMap.put("pptx", "pdf");
        // Drawing Formats
        extensionMap.put("odg", "svg");
        extensionMap.put("otg", "svg");

        extractorMap.put("pdf", new PdfExtractor());

 * </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();

        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() {

 *   <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

```

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

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