* or implied. See the License for the specific language governing permissions and limitations under
 * the License.
 */

/**
 * Interfaces, utilities, and simple implementations of escapers and encoders. The primary type is
 * {@link Escaper}.
 *
 * <p>Additional escapers implementations are found in the applicable packages: {@link

      return (T) in.readObject();
    } catch (IOException | ClassNotFoundException e) {
      throw new AssertionError(e);
    }
  }

  @Override
  public SampleElements<E> samples() {
    return delegate.samples();
  }

  @Override
  public E[] createArray(int length) {
    return delegate.createArray(length);
  }

  @Override
  public Iterable<E> order(List<E> insertionOrder) {

        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"));

        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<>();

    /**

import com.google.common.annotations.GwtIncompatible;
import com.google.common.annotations.J2ktIncompatible;
import java.io.Serializable;
import org.jspecify.annotations.Nullable;

/**
 * Simple base class to verify that we handle generics correctly.
 *
 * @author Kevin Bourrillion
 */
@GwtCompatible
public class BaseComparable implements Comparable<BaseComparable>, Serializable {
  private final String s;

 * handling text normalization, content extraction, and similar document hash encoding/decoding.
 * It also manages document processing requests and integrates with the crawler system.
 *
 */
public class DocumentHelper {
    private static final Logger logger = LogManager.getLogger(DocumentHelper.class);

    /** Prefix used for encoded similar document hashes */
    protected static final String SIMILAR_DOC_HASH_PREFIX = "$";

package com.google.common.testing;

import com.google.common.annotations.GwtCompatible;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.jspecify.annotations.NullMarked;

/**
 * Simple utility for when you want to create a {@link TearDown} that may throw an exception but
 * should not fail a test when it does. (The behavior of a {@code TearDown} that throws an exception

{
  "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