+ "    <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"

---
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

        String sessionId = "session123";
        List<String> urlList = new ArrayList<>();
        urlList.add("https://example.com/.*");
        urlList.add("https://test.com/.*");
        urlList.add("https://sample.org/.*");

        // Execute
        service.addIncludeUrlFilter(sessionId, urlList);

        // Verify - each URL should be added once

        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"));

{
  "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"
  }

        words.add("apple");
        words.add("banana");
        words.add("cherry");

        PopularWordsResponse response = new PopularWordsResponse("test-index", 100, words, 10, new ArrayList<>());

        assertNotNull(response.getWords());
        assertEquals(3, response.getWords().size());
        assertTrue(response.getWords().contains("apple"));

        logger.info(content);

        // Verify plain text extraction
        assertTrue(content.contains("Introduction"));
        assertTrue(content.contains("This is a sample Markdown document"));
        assertTrue(content.contains("Features"));
        assertTrue(content.contains("Code Examples"));
    }

    public void test_frontMatterExtraction() {

 * it easy to get sample values to use in such tests.
 *
 * This class is pretty fast and loose with default values: it attempts to provide values that are
 * well-formed, but doesn't guarantee values are internally consistent. Callers must take care to
 * configure the factory when sample values impact the correctness of the test.
 */
class TestValueFactory : Closeable {

 */
package okhttp3.internal

import java.io.EOFException
import okio.BufferedSource

/**
 * Returns true if the body in question probably contains human-readable text. Uses a small
 * sample of code points to detect Unicode control characters commonly used in binary file
 * signatures.
 *
 * @param codePointLimit the number of code points to read in order to make a decision.
 */

        words.add("apple");
        words.add("application");
        words.add("apply");

        SuggestResponse response = new SuggestResponse("test-index", 100, words, 10, new ArrayList<>());

        assertNotNull(response.getWords());
        assertEquals(3, response.getWords().size());
        assertTrue(response.getWords().contains("apple"));