"êtes", "sont", "serai", "seras", "sera", "serons", "serez", "seront", "serais", "serait", "serions", "seriez", "seraient", "étais", "était", "étions", "étiez", "étaient", "fus", "fut", "fûmes", "fûtes", "furent", "sois", "soit", "soyons", "soyez", "soient", "fusse", "fusses", "fût", "fussions", "fussiez", "fussent", "ayant", "eu", "eue", "eues", "eus", "ai", "as", "avons", "avez", "ont", "aurai", "auras", "aura", "aurons", "aurez", "auront", "aurais", "aurait", "aurions", "auriez", "auraient", "avais",...

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.commonmark.ext.front.matter.YamlFrontMatterExtension;
import org.commonmark.ext.front.matter.YamlFrontMatterVisitor;
import org.commonmark.node.AbstractVisitor;
import org.commonmark.node.Heading;
import org.commonmark.node.Link;
import org.commonmark.node.Node;

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

Here is some inline `code` and a code block:

```java
public class Example {

        final InputStream in = ResourceUtil.getResourceAsStream("extractor/markdown/test.md");
        final ExtractData extractData = markdownExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        // Verify front matter metadata
        final String[] titles = extractData.getValues("frontmatter.title");
        assertNotNull(titles);
        assertEquals("Sample Markdown Document", titles[0]);

			<artifactId>commonmark</artifactId>
			<version>${commonmark.version}</version>
		</dependency>
		<dependency>
			<groupId>org.commonmark</groupId>
			<artifactId>commonmark-ext-yaml-front-matter</artifactId>
			<version>${commonmark.version}</version>
		</dependency>
		<dependency>
			<groupId>com.google.cloud</groupId>
			<artifactId>google-cloud-storage</artifactId>

          trailer as string: TRUEVISION-XFILE\\x2E\\x00
          Some .tga files may be conflicting with application/x-123 recognition, 
          therefore this mime-type must be set in front of application/x-123 -->
     <_comment>Targa image data</_comment>
     <magic priority="90">
        <match value="0x01010000" type="big32" offset="1" >

767.98px\n@function breakpoint-max($name, $breakpoints: $grid-breakpoints) {\n  $max: map-get($breakpoints, $name);\n  @return if($max and $max > 0, $max - .02, null);\n}\n\n// Returns a blank string if smallest breakpoint, otherwise returns the name with a dash in front.\n// Useful for making responsive utilities.\n//\n//    >> breakpoint-infix(xs, (xs: 0, sm: 576px, md: 768px, lg: 992px, xl: 1200px, xxl: 1400px))\n//    \"\"  (Returns a blank string)\n//    >> breakpoint-infix(sm, (xs: 0, sm: 576px, md: 768px, lg:...