Improve worst-case performance of inline.text regex

The old regex may take quadratic time to scan for potential email
addresses starting at every point.  Fix it to avoid scanning from
points that would have been in the middle of a previous scan.

Signed-off-by: Anders Kaseorg <[email protected]>

Author: andersk

lib/marked.js

@@ -615,10 +615,7 @@ inline.gfm = merge({}, inline.normal, {
   url: /^((?:ftp|https?):\/\/|www\.)(?:[a-zA-Z0-9\-]+\.?)+[^\s<]*|^email/,
   _backpedal: /(?:[^?!.,:;*_~()&]+|\([^)]*\)|&(?![a-zA-Z0-9]+;$)|[?!.,:;*_~)]+(?!$))+/,
   del: /^~+(?=\S)([\s\S]*?\S)~+/,
-  text: edit(inline.text)
-    .replace(']|', '~]|')
-    .replace('|$', '|https?://|ftp://|www\\.|[a-zA-Z0-9.!#$%&\'*+/=?^_`{\\|}~-]+@|$')
-    .getRegex()
+  text: /^(`+|[^`])(?:[\s\S]*?(?:(?=[\\<!\[`*~]|\b_| {2,}\n|https?:\/\/|ftp:\/\/|www\.|$)|[^a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-](?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@))|(?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@))/
 });
 
 inline.gfm.url = edit(inline.gfm.url, 'i')

test/specs/gfm/gfm.0.28.json

@@ -141,8 +141,7 @@
     "section": "Autolinks",
     "html": "<p><a href=\"mailto:[email protected]\">[email protected]</a></p>\n<p><a href=\"mailto:[email protected]\">[email protected]</a>.</p>\n<p>[email protected]</p>\n<p>[email protected]_</p>",
     "markdown": "[email protected]\n\n[email protected].\n\n[email protected]\n\n[email protected]_",
-    "example": 607,
-    "shouldFail": true
+    "example": 607
   },
   {
     "section": "Disallowed Raw HTML",