Drop the custom replace, let marked escape it

src-ui/jest.config.js

@@ -26,7 +26,7 @@ module.exports = {
     'abstract-paperless-service',
   ],
   transformIgnorePatterns: [
-    'node_modules/(?!.*(\\.mjs$|tslib|lodash-es|normalize-diacritics|@angular/common/locales/.*\\.js$))',
+    'node_modules/(?!.*(\\.mjs$|tslib|lodash-es|normalize-diacritics|marked|@angular/common/locales/.*\\.js$))',
   ],
   moduleNameMapper: {
     ...esmPreset.moduleNameMapper,

src-ui/package.json

@@ -30,6 +30,7 @@
     "bootstrap": "^5.3.8",
     "file-saver": "^2.0.5",
     "lodash-es": "^4.18.1",
+    "marked": "~18.0.14",
     "mime-names": "^1.0.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.1.0",

src-ui/pnpm-lock.yaml

@@ -53,6 +53,9 @@ importers:
       lodash-es:
         specifier: ^4.18.1
         version: 4.18.1
+      marked:
+        specifier: ~18.0.14
+        version: 18.0.14
       mime-names:
         specifier: ^1.0.0
         version: 1.0.0
@@ -3226,6 +3229,11 @@ packages:
   make-error@1.3.6:
     resolution: {integrity: sha512-s8UhlNe7vPKomQhC1qFelMokr/Sc3AgNbso3n74mVPA5LTZwkB9NlXf4XPamLxJE8h0gh73rM94xvwRT2CVInw==}
 
+  marked@18.0.14:
+    resolution: {integrity: sha512-mBHK6FBHuBAlhgRe88w9F0O1AbwwXJUcQibUbC/QcdTbVGAD7aWza+xt3N6oT/jCZx3/OMeS+8rnuiHZcQ9s7A==}
+    engines: {node: '>= 20'}
+    hasBin: true
+
   material-colors@1.2.6:
     resolution: {integrity: sha512-6qE4B9deFBIa9YSpOc9O0Sgc43zTeVYbgDT5veRKSlB2+ZuHNoVVxA1L/ckMUayV9Ay9y7Z/SZCLcGteW9i7bg==}
 
@@ -7409,6 +7417,8 @@ snapshots:
 
   make-error@1.3.6: {}
 
+  marked@18.0.14: {}
+
   material-colors@1.2.6: {}
 
   merge-stream@2.0.0: {}

src-ui/src/app/components/chat/chat/chat.component.html

@@ -5,14 +5,16 @@
   </button>
   <div ngbDropdownMenu class="dropdown-menu-end shadow p-3" aria-labelledby="chatDropdown">
     <div class="chat-container bg-light p-2">
-      <div class="chat-messages font-monospace small">
+      <div class="chat-messages small">
         @for (message of messages(); track message) {
           <div class="message d-flex flex-row small" [class.justify-content-end]="message.role === 'user'">
             <div class="p-2 m-2" [class.bg-body]="message.role === 'user'">
-              <span class="text-break">
+              @if (message.role === 'assistant') {
-                {{ message.content }}
+                <div class="chat-markdown text-break text-wrap" [innerHTML]="message.content | markdown"></div>
                 @if (message.isStreaming) { <span class="blinking-cursor">|</span> }
-              </span>
+              } @else {
+                <span class="text-break">{{ message.content }}</span>
+              }
               @if (message.role === 'assistant' && message.references?.length) {
                 <div class="chat-references list-group mt-3">
                   @for (reference of message.references; track reference.id) {

src-ui/src/app/components/chat/chat/chat.component.scss

@@ -8,10 +8,6 @@
   white-space: pre-wrap;
 }
 
-.chat-references {
-  font-family: var(--bs-font-sans-serif);
-}
-
 .dropdown-toggle::after {
   display: none;
 }
@@ -40,3 +36,19 @@
     opacity: 1;
   }
 }
+
+.chat-markdown ::ng-deep {
+  h1, h2, h3, h4, h5, h6 {
+    font-size: 1em;
+    font-weight: bold;
+  }
+
+  th, td {
+    padding: 0.15rem 0.4rem;
+    border: 1px solid var(--bs-border-color);
+  }
+
+  > :last-child {
+    margin-bottom: 0;
+  }
+}

src-ui/src/app/components/chat/chat/chat.component.spec.ts

@@ -207,4 +207,33 @@ describe('ChatComponent', () => {
     component.searchInputKeyDown(event)
     expect(component.sendMessage).not.toHaveBeenCalled()
   })
+
+  it('should render markdown for assistant messages only', () => {
+    component.messages.set([
+      { role: 'user', content: '**user**' },
+      { role: 'assistant', content: '**assistant** <script>x</script>' },
+    ])
+    fixture.detectChanges()
+    const el: HTMLElement = fixture.nativeElement
+    expect(el.querySelector('.chat-markdown strong')?.textContent).toBe(
+      'assistant'
+    )
+    expect(el.querySelector('.chat-markdown script')).toBeNull()
+    expect(el.textContent).toContain('**user**')
+  })
+
+  it('should keep the destination hostname visible after sanitizing chat links', () => {
+    component.messages.set([
+      {
+        role: 'assistant',
+        content:
+          '[View original document](https://otherdomain.example/?data=secret)',
+      },
+    ])
+    fixture.detectChanges()
+    const el: HTMLElement = fixture.nativeElement
+    const link = el.querySelector('.chat-markdown a')
+    expect(link?.textContent).toBe('View original document')
+    expect(link?.nextElementSibling?.textContent).toBe('(otherdomain.example)')
+  })
 })

src-ui/src/app/components/chat/chat/chat.component.ts

@@ -10,6 +10,7 @@ import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { NavigationEnd, Router, RouterModule } from '@angular/router'
 import { NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
+import { MarkdownPipe } from 'src/app/pipes/markdown.pipe'
 import { filter, map } from 'rxjs'
 import {
   ChatMessage,
@@ -25,6 +26,7 @@ import {
     RouterModule,
     NgxBootstrapIconsModule,
     NgbDropdownModule,
+    MarkdownPipe,
   ],
   templateUrl: './chat.component.html',
   styleUrl: './chat.component.scss',

src-ui/src/app/pipes/markdown.pipe.spec.ts

@@ -0,0 +1,90 @@
+import { MarkdownPipe } from './markdown.pipe'
+
+describe('MarkdownPipe', () => {
+  const pipe = new MarkdownPipe()
+
+  it('should return empty string for empty input', () => {
+    expect(pipe.transform(null)).toEqual('')
+    expect(pipe.transform(undefined)).toEqual('')
+    expect(pipe.transform('')).toEqual('')
+  })
+
+  it('should render basic markdown', () => {
+    const html = pipe.transform(
+      '**bold** _em_ `code`\n\n- one\n- two\n\n| a | b |\n|---|---|\n| 1 | 2 |'
+    )
+    expect(html).toContain('<strong>bold</strong>')
+    expect(html).toContain('<em>em</em>')
+    expect(html).toContain('<code>code</code>')
+    expect(html).toContain('<li>one</li>')
+    expect(html).toContain('<table>')
+  })
+
+  it('should escape raw html', () => {
+    const html = pipe.transform(
+      'hi <img src=x onerror="alert(1)"> <b>x</b>\n\n<script>alert(1)</script>'
+    )
+    expect(html).not.toContain('<img')
+    expect(html).not.toContain('<script')
+    expect(html).not.toContain('<b>')
+    expect(html).toContain('&lt;script&gt;')
+  })
+
+  it('should not render images', () => {
+    const html = pipe.transform(
+      '![secret](https://otherdomain.example/x.png?d=1)'
+    )
+    expect(html).not.toContain('<img')
+    expect(html).not.toContain('otherdomain.example')
+    expect(html).toContain('secret')
+  })
+
+  it('should render safe links with target and rel', () => {
+    const html = pipe.transform('[docs](https://docs.paperless-ngx.com "Docs")')
+    expect(html).toContain(
+      '<a target="_blank" rel="noopener noreferrer nofollow" href="https://docs.paperless-ngx.com" title="Docs">docs</a>'
+    )
+    expect(pipe.transform('[mail](mailto:a@b.c)')).toContain(
+      'href="mailto:a@b.c"'
+    )
+  })
+
+  it('should drop unsafe or relative links but keep their text', () => {
+    for (const href of [
+      'javascript:alert(1)',
+      'JaVaScRiPt:alert(1)',
+      'data:text/html,<script>alert(1)</script>',
+      'vbscript:msgbox',
+      '/api/documents/',
+    ]) {
+      const html = pipe.transform(`[click](${href})`)
+      expect(html).not.toContain('<a')
+      expect(html).toContain('click')
+    }
+  })
+
+  it('should show the actual hostname beside web links with misleading labels', () => {
+    for (const protocol of ['http', 'https']) {
+      const html = pipe.transform(
+        `[docs.paperless-ngx.com](${protocol}://docs.paperless-ngx.com@otherdomain.example/path?secret=1)`
+      )
+      expect(html).toContain(
+        '</a> <span class="text-muted small">(otherdomain.example)</span>'
+      )
+      expect(html).not.toContain('(docs.paperless-ngx.com)')
+    }
+  })
+
+  it('should omit the hostname label for mailto links', () => {
+    expect(pipe.transform('[mail](mailto:a@b.c)')).toBe(
+      '<p><a target="_blank" rel="noopener noreferrer nofollow" href="mailto:a@b.c">mail</a></p>\n'
+    )
+  })
+
+  it('should escape link titles', () => {
+    const html = pipe.transform(
+      '[x](https://a.example "a\\" onmouseover=\\"1")'
+    )
+    expect(html).not.toMatch(/"\s*onmouseover=/)
+  })
+})

src-ui/src/app/pipes/markdown.pipe.ts

@@ -0,0 +1,52 @@
+import { Pipe, PipeTransform } from '@angular/core'
+import { Marked, Renderer, Tokens } from 'marked'
+
+const ALLOWED_LINK_PROTOCOLS = new Set(['http:', 'https:', 'mailto:'])
+
+function allowedUrl(href: string): URL | null {
+  try {
+    const url = new URL(href)
+    return ALLOWED_LINK_PROTOCOLS.has(url.protocol) ? url : null
+  } catch {
+    return null
+  }
+}
+
+// Treat chat content as untrusted: no raw HTML, no images, and only
+// absolute links. All escaping is done by marked's default renderer, and
+// Angular's sanitizer runs on top of this as well.
+const renderer: Partial<Renderer> = {
+  html(this: Renderer, { raw, text }: Tokens.HTML | Tokens.Tag): string {
+    return this.text({ type: 'text', raw, text })
+  },
+  image(this: Renderer, { raw, text }: Tokens.Image): string {
+    return this.text({ type: 'text', raw, text })
+  },
+  link(this: Renderer, token: Tokens.Link): string {
+    const url = allowedUrl(token.href)
+    if (!url) return this.parser.parseInline(token.tokens)
+    const anchor = Renderer.prototype.link
+      .call(this, token)
+      .replace('<a ', '<a target="_blank" rel="noopener noreferrer nofollow" ')
+    if (!url.hostname) return anchor
+    const hostname = this.text({ type: 'text', raw: '', text: url.hostname })
+    return `${anchor} <span class="text-muted small">(${hostname})</span>`
+  },
+}
+
+const markdown = new Marked({
+  async: false,
+  gfm: true,
+  breaks: true,
+  renderer,
+})
+
+@Pipe({
+  name: 'markdown',
+})
+export class MarkdownPipe implements PipeTransform {
+  transform(value: string | null | undefined): string {
+    if (!value) return ''
+    return markdown.parse(value) as string
+  }
+}