Use possessive quantifiers in excerpt helper regexps to prevent backtracking

[zachasme]

Hopefully fixes Regexp timeouts for very large cards. See https://3.basecamp.com/2914079/buckets/27/card_tables/cards/9700847055

Also cleans up the format_html helper.

[Copilot]

Pull request overview

This PR aims to reduce the risk of Regexp timeouts when generating excerpts from very large card contents by adjusting the excerpt-normalization regexes, and it also refactors the HTML formatting helper to encapsulate scrubber memoization.

Tip

If you aren't ready for review, convert to a draft PR.
Click "Convert to draft" or run gh pr ready --undo.
Click "Ready for review" or run gh pr ready to reengage.

Changes:

• Update format_excerpt regex quantifiers to use possessive *+ in an attempt to reduce backtracking on large inputs.
• Refactor format_html to call a private auto_link_scrubber helper for memoization instead of using an inline instance variable.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
app/helpers/html_helper.rb	Refactors scrubber memoization into a private helper method used by format_html.
app/helpers/excerpt_helper.rb	Adjusts excerpt-normalization regexes to reduce backtracking risk on very large strings.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

In Ruby, the /m flag makes . match newlines, so (.*) here can still span large portions of the string and may still trigger heavy backtracking on very large inputs (which this PR is trying to avoid). Consider removing /m and matching per-line explicitly (e.g., using a negated character class like [^\n]*+ / [^\r\n]*+, or making the trailing quantifier possessive) so the whole pattern stays linear-time on multiline content.

Suggested change

	text = text.gsub(/^>\s*+(.*)$/m, '> \1')
	text = text.gsub(/^\s*+[-+]\s*+(.*)$/m, '• \1')
	text = text.gsub(/^\d+\.\s*+(.*)$/m) { |m| m }
	text = text.gsub(/^>\s*+([^\r\n]*+)$/, '> \1')
	text = text.gsub(/^\s*+[-+]\s*+([^\r\n]*+)$/, '• \1')
	text = text.gsub(/^\d+\.\s*+([^\r\n]*+)$/) { |m| m }

[Copilot]

This gsub is a functional no-op (the block returns the full match unchanged), but it still forces an extra regex scan/allocation on large strings. Either remove it, or change it to actually normalize ordered-list spacing (similar to the quote/bullet replacements) without re-copying the string unnecessarily.

Suggested change

text = text.gsub(/^\d+\.\s*+(.*)$/m) { |m| m }