fix: escape character references in autolink destinations

src/Renderer.ts

@@ -157,18 +157,22 @@ export class _Renderer<ParserOutput = string, RendererOutput = string> {
     return `<del>${this.parser.parseInline(tokens)}</del>` as RendererOutput;
   }
 
-  link({ href, title, tokens }: Tokens.Link): RendererOutput {
-    const text = this.parser.parseInline(tokens) as string;
+  link({ href, title, text, tokens, autolink }: Tokens.Link): RendererOutput {
+    // References are not resolved inside an autolink, so every `&` there is
+    // literal. Elsewhere only an `&` that cannot start one needs escaping.
+    const parsedText = autolink
+      ? escapeHtmlEntities(text, true)
+      : this.parser.parseInline(tokens) as string;
     const cleanHref = cleanUrl(href);
     if (cleanHref === null) {
-      return text as RendererOutput;
+      return parsedText as RendererOutput;
     }
-    href = cleanHref;
+    href = escapeHtmlEntities(cleanHref, autolink);
     let out = '<a href="' + href + '"';
     if (title) {
       out += ' title="' + (escapeHtmlEntities(title)) + '"';
     }
-    out += '>' + text + '</a>';
+    out += '>' + parsedText + '</a>';
     return out as RendererOutput;
   }
 
@@ -182,7 +186,7 @@ export class _Renderer<ParserOutput = string, RendererOutput = string> {
     }
     href = cleanHref;
 
-    let out = `<img src="${href}" alt="${escapeHtmlEntities(text)}"`;
+    let out = `<img src="${escapeHtmlEntities(href)}" alt="${escapeHtmlEntities(text)}"`;
     if (title) {
       out += ` title="${escapeHtmlEntities(title)}"`;
     }

src/Tokenizer.ts

@@ -914,6 +914,7 @@ export class _Tokenizer<ParserOutput = string, RendererOutput = string> {
         raw: cap[0],
         text,
         href,
+        autolink: true,
         tokens: [
           {
             type: 'text',
@@ -951,6 +952,7 @@ export class _Tokenizer<ParserOutput = string, RendererOutput = string> {
         raw: cap[0],
         text,
         href,
+        autolink: true,
         tokens: [
           {
             type: 'text',

src/Tokens.ts

@@ -136,6 +136,11 @@ export namespace Tokens {
     title?: string | null;
     text: string;
     tokens: Token[];
+    /**
+     * Set for autolinks and extended (GFM) urls, where character references are
+     * not resolved, so the destination and text are literal.
+     */
+    autolink?: boolean;
   }
 
   export interface List {

test/specs/new/link_destination_character_references.html

@@ -0,0 +1,15 @@
+<p><a href="https://example.com/?x=1&amp;lt;2">https://example.com/?x=1&amp;lt;2</a></p>
+<p><a href="https://example.com/?y=1&amp;amp;2">https://example.com/?y=1&amp;amp;2</a></p>
+<p><a href="https://example.com/?a=1&amp;b=2">https://example.com/?a=1&amp;b=2</a></p>
+<p><a href="https://example.com/?x=1&amp;lt;2">https://example.com/?x=1&amp;lt;2</a></p>
+<p><a href="https://example.com/?y=1&amp;amp;2">https://example.com/?y=1&amp;amp;2</a></p>
+<p><a href="https://example.com/?a=1&amp;b=2">https://example.com/?a=1&amp;b=2</a></p>
+<p><a href="https://example.com/?x=1&lt;2">https://example.com/?x=1&lt;2</a></p>
+<p><a href="https://example.com/?y=1&amp;2">https://example.com/?y=1&amp;2</a></p>
+<p><a href="https://example.com/?a=1&amp;b=2">https://example.com/?a=1&amp;b=2</a></p>
+<p><a href="https://example.com/?x=1&lt;2">https://example.com/?x=1&lt;2</a></p>
+<p><a href="https://example.com/?y=1&amp;2">https://example.com/?y=1&amp;2</a></p>
+<p><a href="https://example.com/?a=1&amp;b=2">https://example.com/?a=1&amp;b=2</a></p>
+<p><img src="https://example.com/?x=1&lt;2" alt="https://example.com/?x=1&lt;2"></p>
+<p><img src="https://example.com/?y=1&amp;2" alt="https://example.com/?y=1&amp;2"></p>
+<p><img src="https://example.com/?a=1&amp;b=2" alt="https://example.com/?a=1&amp;b=2"></p>

test/specs/new/link_destination_character_references.md

@@ -0,0 +1,45 @@
+---
+# Character references resolve in a link destination but not in an autolink, so
+# the same query string has to be escaped differently depending on where it is
+# written.
+#
+# The `<` inline links, reference links and images below do not match
+# CommonMark. It resolves the reference and percent-encodes the result, giving
+# `?x=1%3C2`, where marked keeps `?x=1<2`. That difference comes from URL
+# encoding rather than from this escaping, and it is the same on `master`.
+# Everything else here matches CommonMark.
+renderExact: true
+---
+https://example.com/?x=1<2
+
+https://example.com/?y=1&2
+
+https://example.com/?a=1&b=2
+
+<https://example.com/?x=1&lt;2>
+
+<https://example.com/?y=1&amp;2>
+
+<https://example.com/?a=1&b=2>
+
+[https://example.com/?x=1&lt;2](https://example.com/?x=1&lt;2)
+
+[https://example.com/?y=1&amp;2](https://example.com/?y=1&amp;2)
+
+[https://example.com/?a=1&b=2](https://example.com/?a=1&b=2)
+
+[https://example.com/?x=1&lt;2][link1]
+
+[https://example.com/?y=1&amp;2][link2]
+
+[https://example.com/?a=1&b=2][link3]
+
+![https://example.com/?x=1&lt;2](https://example.com/?x=1&lt;2)
+
+![https://example.com/?y=1&amp;2](https://example.com/?y=1&amp;2)
+
+![https://example.com/?a=1&b=2](https://example.com/?a=1&b=2)
+
+[link1]: https://example.com/?x=1&lt;2
+[link2]: https://example.com/?y=1&amp;2
+[link3]: https://example.com/?a=1&b=2

test/unit/Lexer.test.js

@@ -2042,6 +2042,7 @@ paragraph
                 raw: '<https://example.com>',
                 text: 'https://example.com',
                 href: 'https://example.com',
+                autolink: true,
                 tokens: [
                   {
                     type: 'text',
@@ -2064,6 +2065,7 @@ paragraph
                 raw: '<test@example.com>',
                 text: 'test@example.com',
                 href: 'mailto:test@example.com',
+                autolink: true,
                 tokens: [
                   {
                     type: 'text',
@@ -2085,6 +2087,7 @@ paragraph
                 raw: 'https://example.com',
                 text: 'https://example.com',
                 href: 'https://example.com',
+                autolink: true,
                 tokens: [
                   {
                     type: 'text',
@@ -2107,6 +2110,7 @@ paragraph
                 raw: 'test@example.com',
                 text: 'test@example.com',
                 href: 'mailto:test@example.com',
+                autolink: true,
                 tokens: [
                   {
                     type: 'text',