Merge pull request #6 from ksylvan/0618-support-cjk-characters

CJK Support Added for Markdown Slug Generation

Author: ksylvan

bin/md-tree.js

@@ -107,7 +107,10 @@ class MarkdownCLI {
   sanitizeText(text) {
     return text
       .toLowerCase()
-      .replace(/[^a-z0-9\s-]/g, '')
+      .replace(
+        /[^a-z0-9\u4e00-\u9fff\u3040-\u309f\u30a0-\u30ff\uac00-\ud7af\s-]/g,
+        ''
+      )
       .replace(/\s+/g, '-')
       .replace(/-+/g, '-')
       .replace(/^-|-$/g, '');

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kayvan/markdown-tree-parser",
-  "version": "1.5.1",
+  "version": "1.6.0",
   "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/test-cjk.md

@@ -0,0 +1,17 @@
+# Document Title
+
+## 章节一
+
+This is the first section.
+
+## 章二
+
+This is the second section.
+
+### セクション 2.1
+
+This is a subsection.
+
+## Another Section
+
+This is another section.

test/test-cli.js

@@ -445,6 +445,42 @@ This document has links too:
     );
   });
 
+  await test('CLI explode command with CJK characters', async () => {
+    const cjkTestFile = path.resolve(__dirname, 'test-cjk.md');
+    const outputDir = path.join(testDir, 'cjk-exploded');
+    const result = await runCLI(['explode', cjkTestFile, outputDir]);
+
+    assert(
+      result.code === 0,
+      `Command should succeed, got exit code ${result.code}\nstderr: ${result.stderr}`
+    );
+
+    const files = await fs.readdir(outputDir);
+    assert(files.includes('index.md'), 'Should create index.md');
+    assert(files.includes('章节一.md'), 'Should create file with Chinese slug');
+    assert(files.includes('章二.md'), 'Should create file with Chinese slug');
+    assert(
+      files.includes('another-section.md'),
+      'Should create file with English slug'
+    );
+
+    // Check the index file for correct links
+    const indexPath = path.join(outputDir, 'index.md');
+    const indexContent = await fs.readFile(indexPath, 'utf-8');
+    assert(
+      indexContent.includes('[章节一](./章节一.md)'),
+      'Should link to Chinese filename'
+    );
+    assert(
+      indexContent.includes('[章二](./章二.md)'),
+      'Should link to Chinese filename'
+    );
+    assert(
+      indexContent.includes('[セクション 2.1](./章二.md#セクション-21)'),
+      'Should link to Japanese subsection'
+    );
+  });
+
   await cleanupTests();
 
   // Summary