Merge pull request #3040 from gaojunran/fix/cjk-markdown-links

fix(markdown): keep CJK/fullwidth punctuation out of bare-URL autolinks

bun.lock

@@ -191,6 +191,7 @@
         "http-proxy-middleware": "^3.0.5",
         "katex": "^0.17.0",
         "marked": "^17.0.3",
+        "marked-linkify-it": "^4.0.2",
         "morphdom": "^2.7.7",
         "motion": "^12.23.24",
         "next-themes": "^0.4.6",
@@ -2431,7 +2432,7 @@
 
     "lightningcss-win32-x64-msvc": ["lightningcss-win32-x64-msvc@1.31.1", "", { "os": "win32", "cpu": "x64" }, "sha512-I9aiFrbd7oYHwlnQDqr1Roz+fTz61oDDJX7n9tYF9FJymH1cIN1DtKw3iYt6b8WZgEjoNwVSncwF4wx/ZedMhw=="],
 
-    "linkify-it": ["linkify-it@5.0.0", "", { "dependencies": { "uc.micro": "^2.0.0" } }, "sha512-5aHCbzQRADcdP+ATqnDuhhJ/MRIqDkZX5pyjFHRRysS8vZ5AbqGEoFIb6pYHPZ+L/OC2Lc+xT8uHVVR5CAK/wQ=="],
+    "linkify-it": ["linkify-it@6.1.0", "", { "dependencies": { "uc.micro": "^3.0.0" } }, "sha512-wJ/TwpSDTLepCrQoYWYIExIKg5Zchex2Nn5yk2mFnB+6PtdkHtyLx742md9csRjjOnGkKIS/RrbY7l8D6gT9Vw=="],
 
     "locate-path": ["locate-path@6.0.0", "", { "dependencies": { "p-locate": "^5.0.0" } }, "sha512-iPZK6eYjbxRu3uB4/WZ3EsEIMJFMqAoopl3R+zuq0UjcAm/MO6KCweDgPfP3elTztoKP3KtnVHxTn2NHBSDVUw=="],
 
@@ -2487,6 +2488,8 @@
 
     "marked": ["marked@17.0.3", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-jt1v2ObpyOKR8p4XaUJVk3YWRJ5n+i4+rjQopxvV32rSndTJXvIzuUdWWIy/1pFQMkQmvTXawzDNqOH/CUmx6A=="],
 
+    "marked-linkify-it": ["marked-linkify-it@4.0.2", "", { "dependencies": { "linkify-it": "^6.1.0" }, "peerDependencies": { "marked": ">=4 <19" } }, "sha512-3nvMW0MHU+ZNBhzSnqRTl+tCkUwIBbg1xbHx5mtJqCH8ieJGLJ0JzV36ESnnufSgZ0mSwO22fBIeNEu5vvYd9w=="],
+
     "matcher": ["matcher@3.0.0", "", { "dependencies": { "escape-string-regexp": "^4.0.0" } }, "sha512-OkeDaAZ/bQCxeFAozM55PKcKU0yJMPGifLwV4Qgjitu+5MoAfSQN4lsLJeXZ1b8w0x+/Emda6MZgXS1jvsapng=="],
 
     "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
@@ -3249,7 +3252,7 @@
 
     "typescript-eslint": ["typescript-eslint@8.56.1", "", { "dependencies": { "@typescript-eslint/eslint-plugin": "8.56.1", "@typescript-eslint/parser": "8.56.1", "@typescript-eslint/typescript-estree": "8.56.1", "@typescript-eslint/utils": "8.56.1" }, "peerDependencies": { "eslint": "^8.57.0 || ^9.0.0 || ^10.0.0", "typescript": ">=4.8.4 <6.0.0" } }, "sha512-U4lM6pjmBX7J5wk4szltF7I1cGBHXZopnAXCMXb3+fZ3B/0Z3hq3wS/CCUB2NZBNAExK92mCU2tEohWuwVMsDQ=="],
 
-    "uc.micro": ["uc.micro@2.1.0", "", {}, "sha512-ARDJmphmdvUk6Glw7y9DQ2bFkKBHwQHLi2lsaH6PPmz/Ka9sFOBsBluozhDltWmnv9u/cF6Rt87znRTPV+yp/A=="],
+    "uc.micro": ["uc.micro@3.0.0", "", {}, "sha512-U3PppEkleoTnIfi8BozMx3yju3qc/L6SwqWo2Sw+54PX+PX0q9I+r1Um5HCmqD7n9VDX5/v3vQH/AjA6deDdtw=="],
 
     "unbox-primitive": ["unbox-primitive@1.1.0", "", { "dependencies": { "call-bound": "^1.0.3", "has-bigints": "^1.0.2", "has-symbols": "^1.1.0", "which-boxed-primitive": "^1.1.1" } }, "sha512-nWJ91DjeOkej/TA8pXQ3myruKpKEYgqvpw9lz4OPHj/NWFNluYrjbz9j01CJ8yKQd2g4jFoOkINCTW2I5LEEyw=="],
 
@@ -3659,6 +3662,10 @@
 
     "markdown-it/entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="],
 
+    "markdown-it/linkify-it": ["linkify-it@5.0.0", "", { "dependencies": { "uc.micro": "^2.0.0" } }, "sha512-5aHCbzQRADcdP+ATqnDuhhJ/MRIqDkZX5pyjFHRRysS8vZ5AbqGEoFIb6pYHPZ+L/OC2Lc+xT8uHVVR5CAK/wQ=="],
+
+    "markdown-it/uc.micro": ["uc.micro@2.1.0", "", {}, "sha512-ARDJmphmdvUk6Glw7y9DQ2bFkKBHwQHLi2lsaH6PPmz/Ka9sFOBsBluozhDltWmnv9u/cF6Rt87znRTPV+yp/A=="],
+
     "mdast-util-find-and-replace/escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],
 
     "micromark-extension-math/katex": ["katex@0.16.45", "", { "dependencies": { "commander": "^8.3.0" }, "bin": { "katex": "cli.js" } }, "sha512-pQpZbdBu7wCTmQUh7ufPmLr0pFoObnGUoL/yhtwJDgmmQpbkg/0HSVti25Fu4rmd1oCR6NGWe9vqTWuWv3GcNA=="],

packages/ui/package.json

@@ -67,6 +67,7 @@
     "http-proxy-middleware": "^3.0.5",
     "katex": "^0.17.0",
     "marked": "^17.0.3",
+    "marked-linkify-it": "^4.0.2",
     "morphdom": "^2.7.7",
     "motion": "^12.23.24",
     "next-themes": "^0.4.6",

packages/ui/src/components/chat/markdown/markdownCore.test.ts

@@ -279,3 +279,30 @@ describe('Markdown images', () => {
     expect(html).not.toContain('data-openchamber-markdown-image');
   });
 });
+
+describe('CJK-aware link parsing', () => {
+  const hrefOf = (html: string): string | null => /<a\b[^>]*href="([^"]*)"/.exec(html)?.[1] ?? null;
+
+  test('bare URL followed by a CJK annotation trims the annotation from the href', () => {
+    const html = renderMarkdownSync('访问 https://example.com/docs（中文说明）了解更多');
+    expect(hrefOf(html)).toBe('https://example.com/docs');
+  });
+
+  test('bare URL followed by CJK punctuation trims the punctuation', () => {
+    expect(hrefOf(renderMarkdownSync('地址 https://example.com/guide，详见'))).toBe(
+      'https://example.com/guide',
+    );
+    expect(hrefOf(renderMarkdownSync('官网 https://example.com。'))).toBe('https://example.com');
+  });
+
+  test('correct links are unaffected', () => {
+    expect(hrefOf(renderMarkdownSync('官方文档见 [这里](https://docs.example.com)（中文说明）'))).toBe(
+      'https://docs.example.com',
+    );
+    expect(hrefOf(renderMarkdownSync('[下载](https://dl.example.com/安装包（正式版）)'))).toBe(
+      'https://dl.example.com/安装包（正式版）',
+    );
+    expect(hrefOf(renderMarkdownSync('[a](url(1))'))).toBe('url(1)');
+    expect(hrefOf(renderMarkdownSync('[a](url "title")'))).toBe('url');
+  });
+});

packages/ui/src/components/chat/markdown/markdownCore.ts

@@ -1,4 +1,5 @@
 import { Marked, marked, type Tokens } from 'marked';
+import markedLinkifyIt from 'marked-linkify-it';
 import remend from 'remend';
 import katex from 'katex';
 import DOMPurify from 'dompurify';
@@ -331,10 +332,15 @@ const blockMathExtension = {
   },
 };
 
-const createParser = (imageMode: MarkdownImageMode) => new Marked().use({
+// marked's GFM autolink swallows CJK punctuation after a bare URL, so switch
-  gfm: true,
+// to marked-linkify-it, which treats Unicode punctuation as a URL boundary.
-  breaks: false,
+// Plain CJK characters right after a URL are still consumed, matching GitHub.
-  extensions: [inlineMathExtension, blockMathExtension],
+const createParser = (imageMode: MarkdownImageMode) => new Marked().use(
+  markedLinkifyIt({ fuzzyLink: false }),
+  {
+    gfm: true,
+    breaks: false,
+    extensions: [inlineMathExtension, blockMathExtension],
   renderer: {
     // Assistant output is untrusted. Markdown constructs still render as HTML,
     // but raw HTML must remain visible text so it cannot introduce active DOM