Add link checker command #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed

ksylvan wants to merge 1 commit into main from codex/add-check-links-command-to-md-tree

README.md

            
                      Original file line number
                      Diff line number
                      Diff line change
                  
    @@ -102,6 +102,13 @@ md-tree stats README.md
  
    md-tree toc README.md --max-level 3

    ```

    ### Check links

    ```bash

    md-tree check-links README.md

    md-tree check-links README.md --recursive

    ```

    ### Complete CLI options

    ```bash

    @@ -144,13 +151,17 @@ console.log(sectionMarkdown);
  
    ### Advanced Usage

    ```javascript

    import { MarkdownTreeParser, createParser, extractSection } from 'markdown-tree-parser';

    import {

      MarkdownTreeParser,

      createParser,

      extractSection,

    } from 'markdown-tree-parser';

    // Create parser with custom options

    const parser = createParser({

      bullet: '-',      // Use '-' for lists

      emphasis: '_',    // Use '_' for emphasis

      strong: '__'      // Use '__' for strong

      bullet: '-', // Use '-' for lists

      emphasis: '_', // Use '_' for emphasis

      strong: '__', // Use '__' for strong

    });

    // Extract all sections at level 2

    @@ -178,8 +189,7 @@ const codeBlocks = parser.selectAll(tree, 'code');
  
    // Custom search

    const customNode = parser.findNode(tree, (node) => {

      return node.type === 'heading' &&

             parser.getHeadingText(node).includes('API');

      return node.type === 'heading' && parser.getHeadingText(node).includes('API');

    });

    // Transform content

    @@ -191,7 +201,9 @@ parser.transform(tree, (node) => {
  
    // Get document statistics

    const stats = parser.getStats(tree);

    console.log(`Document has ${stats.wordCount} words and ${stats.headings.total} headings`);

    console.log(

      `Document has ${stats.wordCount} words and ${stats.headings.total} headings`

    );

    // Generate table of contents

    const toc = parser.generateTableOfContents(tree, 3);

    @@ -234,7 +246,7 @@ for (let i = 0; i < sections.length; i++) {
  
    #### Constructor

    ```javascript

    new MarkdownTreeParser(options = {})

    new MarkdownTreeParser((options = {}));

    ```

    #### Methods

    @@ -265,18 +277,18 @@ The library supports powerful CSS-like selectors for searching:
  
    ```javascript

    // Element selectors

    parser.selectAll(tree, 'heading')     // All headings

    parser.selectAll(tree, 'paragraph')  // All paragraphs

    parser.selectAll(tree, 'link')       // All links

    parser.selectAll(tree, 'heading'); // All headings

    parser.selectAll(tree, 'paragraph'); // All paragraphs

    parser.selectAll(tree, 'link'); // All links

    // Attribute selectors

    parser.selectAll(tree, 'heading[depth=1]')    // H1 headings

    parser.selectAll(tree, 'heading[depth=2]')    // H2 headings

    parser.selectAll(tree, 'link[url*="github"]') // Links containing "github"

    parser.selectAll(tree, 'heading[depth=1]'); // H1 headings

    parser.selectAll(tree, 'heading[depth=2]'); // H2 headings

    parser.selectAll(tree, 'link[url*="github"]'); // Links containing "github"

    // Pseudo selectors

    parser.selectAll(tree, ':first-child')  // First child elements

    parser.selectAll(tree, ':last-child')   // Last child elements

    parser.selectAll(tree, ':first-child'); // First child elements

    parser.selectAll(tree, ':last-child'); // Last child elements

    ```

    ## 🧪 Testing

bin/md-tree.js

-Original file line number
+Diff line change
@@ Expand Up / @@ -46,6 +46,7 @@ const MESSAGES = { @@
       USAGE_SEARCH: '❌ Usage: md-tree search <file> <selector>',
       USAGE_STATS: '❌ Usage: md-tree stats <file>',
       USAGE_TOC: '❌ Usage: md-tree toc <file>',
+      USAGE_CHECK_LINKS: '❌ Usage: md-tree check-links <file>',
       INDEX_NOT_FOUND: 'index.md not found in',
       NO_MAIN_TITLE: 'No main title found in index.md',
       NO_SECTION_FILES: 'No section files found in TOC',
@@ Expand Down Expand Up / @@ -138,6 +139,7 @@ Commands: @@
       search <file> <selector>      Search using CSS-like selectors
       stats <file>                  Show document statistics
       toc <file>                    Generate table of contents
+      check-links <file>            Verify that links are reachable
       version                       Show version information
       help                          Show this help message
@@ Expand All / @@ -146,6 +148,7 @@ Options: @@
       --level, -l <number>          Heading level to work with
       --format, -f <json|text>      Output format (default: text)
       --max-level <number>          Maximum heading level for TOC (default: 3)
+      --recursive, -r               Recursively check linked markdown files
     Examples:
       md-tree list README.md
@@ Expand All / @@ -157,6 +160,7 @@ Examples: @@
       md-tree search README.md "heading[depth=2]"
       md-tree stats README.md
       md-tree toc README.md --max-level 2
+      md-tree check-links README.md --recursive
     For more information, visit: https://github.com/ksylvan/markdown-tree-parser
     `);
@@ Expand Down Expand Up @@
         console.log(`🖼️  Images: ${stats.images}`);
       }
+      async checkLinks(filePath, recursive = false) {
+        const content = await this.readFile(filePath);
+        const tree = await this.parser.parse(content);
+        const results = await this.parser.checkLinks(tree, {
+          baseDir: path.dirname(path.resolve(filePath)),
+          recursive,
+        });
+        console.log(`\n🔗 Checking links in ${path.basename(filePath)}:\n`);
+        const bad = [];
+        results.forEach((r) => {
+          if (r.ok) {
+            console.log(`✅ ${r.url}`);
+          } else {
+            console.log(`❌ ${r.url} - ${r.error || r.status}`);
+            bad.push(r);
+          }
+        });
+        if (bad.length > 0) {
+          console.log(`\n${MESSAGES.WARNING} ${bad.length} broken link(s) found.`);
+          process.exitCode = 1;
+        } else {
+          console.log('\nAll links look good!');
+        }
+      }
       async generateTOC(filePath, maxLevel = 3) {
         const content = await this.readFile(filePath);
         const tree = await this.parser.parse(content);
@@ Expand Down Expand Up @@
           level: 2,
           format: 'text',
           maxLevel: 3,
+          recursive: false,
         };
         // Parse flags
@@ Expand All @@
           } else if (arg === '--max-level') {
             options.maxLevel = parseInt(args[i + 1]) || 3;
             i++; // skip next arg
+          } else if (arg === '--recursive' || arg === '-r') {
+            options.recursive = true;
           } else if (!arg.startsWith('-')) {
             filteredArgs.push(arg);
           }
@@ Expand Down Expand Up @@
         await this.generateTOC(args[1], options.maxLevel);
       }
+      async handleCheckLinksCommand(args, options) {
+        if (args.length < 2) {
+          console.error(MESSAGES.USAGE_CHECK_LINKS);
+          process.exit(1);
+        }
+        await this.checkLinks(args[1], options.recursive);
+      }
       async run() {
         const { command, args, options } = this.parseArgs();
@@ Expand Down Expand Up @@
             case 'toc':
               await this.handleTocCommand(args, options);
               break;
+            case 'check-links':
+              await this.handleCheckLinksCommand(args, options);
+              break;
             default:
               console.error(`${MESSAGES.ERROR} Unknown command: ${command}`);
               console.log('Run "md-tree help" for usage information.');
@@ Expand Down @@

index.js

-Original file line number
+Diff line change
@@ Expand Up @@
       const parser = new MarkdownTreeParser(options);
       const tree = await parser.parse(markdown);
       return parser.generateTableOfContents(tree, maxLevel);
-    }
+    }
+    /**
+     * Quick utility to check links in markdown
+     * @param {string} markdown - Markdown content
+     * @param {Object} options - Parser options
+     * @returns {Promise<Array>} Array of link check results
+     */
+    export async function checkLinks(markdown, options = {}) {
+      const parser = new MarkdownTreeParser(options);
+      const tree = await parser.parse(markdown);
+      return parser.checkLinks(tree, options);
+    }

lib/markdown-parser.js

-Original file line number
+Diff line change
@@ Expand Up / @@ -399,4 +399,63 @@ @@
         return toc;
       }
+      /**
+       * Check that all links in a document are reachable
+       * @param {Object} tree - Parsed markdown AST
+       * @param {Object} options - Options object
+       * @param {string} [options.baseDir='.'] - Base directory for resolving local links
+       * @param {boolean} [options.recursive=false] - Recursively check linked markdown files
+       * @param {Set<string>} [options._visited] - Internal set of visited files to prevent loops
+       * @returns {Promise<Array>} Array of result objects { url, ok, status?, error? }
+       */
+      async checkLinks(
+        tree,
+        { baseDir = '.', recursive = false, _visited = new Set() } = {}
+      ) {
+        const links = [];
+        visit(tree, 'link', (node) => {
+          if (node.url) links.push(node.url);
+        });
+        const results = [];
+        for (const url of links) {
+          if (url.startsWith('http://') || url.startsWith('https://')) {
+            try {
+              const res = await fetch(url, { method: 'HEAD' });
+              results.push({ url, ok: res.ok, status: res.status });
+            } catch (err) {
+              results.push({ url, ok: false, error: err.message });
+            }
+          } else if (url.startsWith('#') || url.startsWith('mailto:')) {
+            // Assume local anchors and mailto links are valid
+            results.push({ url, ok: true });
+          } else {
+            const target = path.resolve(baseDir, url.split('#')[0]);
+            try {
+              await fs.access(target);
+              results.push({ url, ok: true });
+              if (recursive && /\.md$/i.test(target)) {
+                if (!_visited.has(target)) {
+                  _visited.add(target);
+                  const content = await fs.readFile(target, 'utf-8');
+                  const subTree = await this.parse(content);
+                  const subResults = await this.checkLinks(subTree, {
+                    baseDir: path.dirname(target),
+                    recursive,
+                    _visited,
+                  });
+                  results.push(...subResults);
+                }
+              }
+            } catch (err) {
+              results.push({ url, ok: false, error: 'File not found' });
+            }
+          }
+        }
+        return results;
+      }
     }

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add link checker command #3

Uh oh!

Diff view

Diff view

There are no files selected for viewing

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

GitHub Actions / test (22.x)

GitHub Actions / test (18.x)

GitHub Actions / test (20.x)

Uh oh!