Merge pull request #4 from ksylvan/0617-fix-checklinks

Handle reference-style links in checkLinks

Author: ksylvan

bin/md-tree.js

@@ -385,13 +385,23 @@ For more information, visit: https://github.com/ksylvan/markdown-tree-parser
     const content = await this.readFile(resolvedPath);
     const tree = await this.parser.parse(content);
     const links = this.parser.selectAll(tree, 'link');
+    const definitions = this.parser.selectAll(tree, 'definition');
+
+    const allUrls = [];
+    for (const link of links) {
+      allUrls.push(link.url);
+    }
+    for (const definition of definitions) {
+      allUrls.push(definition.url);
+    }
+
+    const uniqueUrls = new Set(allUrls);
 
     console.log(
-      `\n🔗 Checking ${links.length} links in ${path.basename(resolvedPath)}:`
+      `\n🔗 Checking ${uniqueUrls.size} unique URLs in ${path.basename(resolvedPath)}:`
     );
 
-    for (const link of links) {
-      const url = link.url;
+    for (const url of uniqueUrls) {
       if (!url || url.startsWith('#')) {
         continue;
       }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kayvan/markdown-tree-parser",
-  "version": "1.5.0",
+  "version": "1.5.1",
   "description": "A powerful JavaScript library and CLI tool for parsing and manipulating markdown files as tree structures using the remark/unified ecosystem",
   "type": "module",
   "main": "index.js",

test/sample.md

@@ -1,153 +1,3 @@
-# Sample Document
+# Sample File
 
-This is a sample markdown document for testing the markdown-tree-parser package.
-
-## Overview
-
-This document demonstrates various markdown features and structures that can be parsed and manipulated.
-
-### Key Features
-
-- **Bold text** and *italic text*
-- `Inline code` and code blocks
-- [Links](https://example.com) and ![images](image.png)
-- Lists and tables
-
-### Architecture
-
-The document follows a hierarchical structure with multiple heading levels.
-
-## Installation
-
-Follow these steps to get started:
-
-### Prerequisites
-
-Make sure you have the following installed:
-
-1. Node.js (version 18 or higher)
-2. npm package manager
-3. A text editor
-
-### Quick Install
-
-```bash
-npm install markdown-tree-parser
-```
-
-### Configuration
-
-You can configure the parser with various options:
-
-```javascript
-const parser = new MarkdownTreeParser({
-  bullet: '-',
-  emphasis: '_'
-});
-```
-
-## Usage Examples
-
-Here are some common usage patterns.
-
-### Basic Usage
-
-```javascript
-import { MarkdownTreeParser } from 'markdown-tree-parser';
-
-const parser = new MarkdownTreeParser();
-const tree = await parser.parse(markdown);
-```
-
-### Advanced Features
-
-For more complex scenarios:
-
-- Extract specific sections
-- Search with CSS selectors
-- Transform document structure
-- Generate statistics
-
-### CLI Usage
-
-The package includes a powerful CLI:
-
-```bash
-md-tree list document.md
-md-tree extract document.md "Installation"
-```
-
-## API Reference
-
-### Core Methods
-
-The main parser class provides these methods:
-
-- `parse(markdown)` - Parse markdown to AST
-- `stringify(tree)` - Convert AST to markdown
-- `extractSection(tree, heading)` - Extract sections
-- `selectAll(tree, selector)` - CSS-like search
-
-### Utility Functions
-
-Additional helper functions:
-
-- `getHeadingsList(tree)` - List all headings
-- `getStats(tree)` - Document statistics
-- `generateTableOfContents(tree)` - Create TOC
-
-## Testing
-
-The package includes comprehensive tests:
-
-```bash
-npm test
-npm run test:cli
-```
-
-### Test Coverage
-
-- Unit tests for all core functions
-- Integration tests for CLI commands
-- End-to-end examples
-
-## Contributing
-
-We welcome contributions from the community!
-
-### Getting Started
-
-1. Fork the repository
-2. Create a feature branch
-3. Make your changes
-4. Run the tests
-5. Submit a pull request
-
-### Code Standards
-
-Please follow these guidelines:
-
-- Use ESLint for code quality
-- Write meaningful commit messages
-- Include tests for new features
-- Update documentation as needed
-
-## Support
-
-Need help? Here are your options:
-
-### Documentation
-
-- Check the README for basic usage
-- Browse the examples directory
-- Read the API documentation
-
-### Community
-
-- Open an issue on GitHub
-- Join our discussions
-- Check Stack Overflow
-
-## License
-
-This project is licensed under the MIT License.
+This is a sample file for testing links.

test/test-email-links.md

@@ -0,0 +1,8 @@
+# Test File for Reference-Style Links
+
+This is a [link to Google][google].
+Here is another [link to a local file][local-doc].
+And an [undefined link][undefined].
+
+[google]: https://www.google.com
+[local-doc]: ./test-dummy-sample.md

test/test-reference-links.md

@@ -5,6 +5,7 @@
  */
 
 import { MarkdownTreeParser, createParser, extractSection } from '../index.js';
+import { MarkdownCLI } from '../bin/md-tree.js'; // Added for checkLinks test
 import fs from 'node:fs/promises';
 import path from 'node:path';
 import { fileURLToPath } from 'node:url';
@@ -583,6 +584,101 @@ Plain text with email@domain.com should not be a link.
     );
   });
 
+  // Test suite for checkLinks
+  await test('Check Links Functionality', async () => {
+    const cli = new MarkdownCLI();
+    const testReferenceLinksFile = path.join(
+      __dirname,
+      'test-reference-links.md'
+    );
+    const testDummySampleFilePath = path.join(
+      __dirname,
+      'test-dummy-sample.md'
+    );
+
+    // Create a unique dummy file for local link checking to pass
+    await fs.writeFile(
+      testDummySampleFilePath,
+      '# Test Dummy Sample File\n\nThis is a test dummy file for testing links.'
+    );
+
+    await test('Check reference-style links', async () => {
+      const markdownContent = await fs.readFile(
+        testReferenceLinksFile,
+        'utf-8'
+      );
+      const tree = await cli.parser.parse(markdownContent);
+      const links = cli.parser.selectAll(tree, 'link');
+      const definitions = cli.parser.selectAll(tree, 'definition');
+
+      const collectedUrls = new Set();
+      for (const link of links) {
+        if (link.url) collectedUrls.add(link.url);
+      }
+      for (const def of definitions) {
+        if (def.url) collectedUrls.add(def.url);
+      }
+
+      assert(
+        collectedUrls.has('https://www.google.com'),
+        'Should find Google link from definition'
+      );
+      assert(
+        collectedUrls.has('./test-dummy-sample.md'),
+        'Should find local-doc link from definition'
+      );
+      assert(
+        !collectedUrls.has('[undefined]'),
+        'Should not treat undefined reference as a URL'
+      );
+      // The following assertions were removed because selectAll(tree, 'link') for reference-style links
+      // correctly returns linkReference nodes which do not have the 'url' property populated directly.
+      // The url is resolved by checkLinks by looking at 'definition' nodes,
+      // which is already tested by the collectedUrls assertions and the checkLinks output assertions.
+      // assert(links.some(link => link.reference === 'google' && link.url === 'https://www.google.com'), 'Link object for google should have url');
+      // assert(links.some(link => link.reference === 'local-doc' && link.url === './sample.md'), 'Link object for local-doc should have url');
+
+      // Test the checkLinks output
+      const originalConsoleLog = console.log;
+      const logs = [];
+      console.log = (...args) => {
+        logs.push(args.join(' '));
+      };
+
+      try {
+        await cli.checkLinks(testReferenceLinksFile);
+      } finally {
+        console.log = originalConsoleLog;
+        // Clean up test dummy file
+        try {
+          await fs.unlink(testDummySampleFilePath);
+        } catch (error) {
+          // Ignore cleanup errors - file might not exist
+          console.warn(
+            `Warning: Could not clean up ${testDummySampleFilePath}:`,
+            error.message
+          );
+        }
+      }
+
+      const output = logs.join('\n');
+      assert(
+        output.includes('🔗 Checking 2 unique URLs'),
+        'Should check 2 unique URLs'
+      );
+      assert(
+        output.includes('✅ https://www.google.com'),
+        'Should successfully check Google link'
+      );
+      // Note: The actual local file path in output might be resolved.
+      // We check for the original URL './test-dummy-sample.md' and the "✅" status.
+      assert(
+        output.includes('✅ ./test-dummy-sample.md'),
+        'Should successfully check local test dummy sample file link'
+      );
+    });
+  });
+
   // Summary
   console.log(`\n📊 Test Results: ${passedTests}/${testCount} passed`);