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"));

        defaultSettings.put("onelogin.saml2.security.logoutrequest_signed", "false");
        defaultSettings.put("onelogin.saml2.security.logoutresponse_signed", "false");
        defaultSettings.put("onelogin.saml2.security.want_messages_signed", "false");
        defaultSettings.put("onelogin.saml2.security.want_assertions_signed", "false");

    private static final Logger logger = LogManager.getLogger(DataStoreFactory.class);

    /**
     * Map containing registered data store instances indexed by their names and class simple names.
     * All keys are stored in lowercase for case-insensitive lookup.
     */
    protected Map<String, DataStore> dataStoreMap = new LinkedHashMap<>();

    /**

{
  "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"
  }

---
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

        assertEquals(expected, XmlUtil.escapeXml(input));
    }

    public void test_escapeXml_noSpecialChars() {
        // Test string without special characters
        String input = "Simple text without special characters";
        assertEquals(input, XmlUtil.escapeXml(input));
    }

    public void test_stripInvalidXMLCharacters_null() {
        // Test null input

    public QueryProcessor() {
        // Default constructor
    }

    private static final Logger logger = LogManager.getLogger(QueryProcessor.class);

    /**
     * Map of query commands indexed by query class simple names.
     * Used to lookup appropriate command handlers for different query types.
     */
    protected Map<String, QueryCommand> queryCommandMap = new HashMap<>();

    /**

				"application/set-registration-initiation",
				"application/sgml",
				"application/sgml-open-catalog",
				"application/shf+xml",
				"application/sieve",
				"application/simple-filter+xml",
				"application/simple-message-summary",
				"application/simplesymbolcontainer",
				"application/slate",
				"application/smil+xml",
				"application/soap+fastinfoset",
				"application/soap+xml",

                + "    <loc>http://www.example.com/sample.html</loc>\n" + "    <image:image>\n"
                + "      <image:loc>http://www.example.com/image.jpg</image:loc>\n"
                + "      <image:caption>Sample image caption</image:caption>\n" + "      <image:title>Sample image title</image:title>\n"
                + "      <image:geo_location>Tokyo, Japan</image:geo_location>\n"

```xml
<component name="myExtractor" class="...MyExtractor" instance="singleton"/>
```

```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)