sample_file = static_dir / "sample.txt"
    sample_file.write_text("This is a sample static file.")
    from docs_src.static_files.tutorial001_py39 import app

    with TestClient(app) as client:
        yield client
    sample_file.unlink()
    static_dir.rmdir()


def test_static_files(client: TestClient):
    response = client.get("/static/sample.txt")
    assert response.status_code == 200, response.text

---
title: Sample Markdown Document
author: John Doe
date: 2025-01-15
tags:
  - crawler
  - extractor
  - markdown
---

# Introduction

This is a sample Markdown document for testing the MarkdownExtractor.

## Features

The extractor should handle:

- YAML front matter extraction
- Heading structure
- **Bold text** and *italic text*
- Lists and other formatting

### Code Examples

                        + "      <video:thumbnail_loc>http://www.example.com/thumbs/123.jpg</video:thumbnail_loc>\n"
                        + "      <video:title>Sample video title</video:title>\n"
                        + "      <video:description>Sample video description</video:description>\n"

        assertTrue(content.contains("title"));
        assertTrue(content.contains("Sample Document"));
        assertTrue(content.contains("author"));
        assertTrue(content.contains("John Doe"));

        // Verify metadata extraction
        assertNotNull(extractData.getValues("title"));
        assertEquals("Sample Document", extractData.getValues("title")[0]);
        assertNotNull(extractData.getValues("author"));

        List<Pattern> mockExcludePatterns = new ArrayList<>();
        mockExcludePatterns.add(Pattern.compile("https://example.com/admin/.*"));
        mockExcludePatterns.add(Pattern.compile("https://example.com/private/.*"));
        mockExcludePatterns.add(Pattern.compile("https://example.com/secret/.*"));

{
  "title": "Sample Document",
  "author": "John Doe",
  "version": "1.0",
  "published": "2025-01-15",
  "tags": ["crawler", "extractor", "json"],
  "content": {
    "summary": "This is a sample JSON document for testing",
    "body": "The extractor should handle nested objects and arrays properly"
  },
  "metadata": {
    "created_at": "2025-01-01T00:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  }

        CloseableUtil.closeQuietly(in);

        final String content = extractData.getContent();

        // Code blocks should be converted to plain text
        assertTrue(content.contains("public class Example") || content.contains("Example"));
    }

        // Verify patterns work correctly
        assertTrue(includePatterns.get(0).matcher("http://example.com/page").matches());
        assertTrue(excludePatterns.get(0).matcher("http://example.com/admin/users").matches());
        assertFalse(excludePatterns.get(0).matcher("http://example.com/page").matches());

        urlFilterService.delete(sessionId);
    }

```

```java
extractorFactory.addExtractor("application/myformat", myExtractor, weight);
```

3. **Add test with sample file** in `src/test/resources/`

### Configuring URL Filtering

```java
// Include patterns (must match)
crawler.urlFilter.addInclude("https://example.com/.*");

// Exclude patterns (must not match)
crawler.urlFilter.addExclude(".*\\.(css|js|png|jpg)$");
```

	if err != nil {
		t.Fatalf("os.Stat:1 %v", err)
	}
	hdr.Typeflag = TypeDir
	// Force a PAX long name to be written. The name was taken from a practical example
	// that fails and replaced ever char through numbers to anonymize the sample.