* </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

        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

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

		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}},

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("application/pdf", tikaExtractor);
                });
        emlExtractor = container.getComponent("emlExtractor");
    }

    public void test_getText() throws IOException {

        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();

			<artifactId>tika-parser-ocr-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-pdf-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-pkg-module</artifactId>
			<version>${tika.version}</version>