Normalize hyphens to spaces in frequency list aggregation

[Copilot]

Frequency lists were treating "Jean-Paul Sartre" and "Jean Paul Sartre" as separate answers, fragmenting counts.

Changes

• Add $replaceAll stage in MongoDB aggregation pipeline to normalize hyphens to spaces before grouping
• Add test coverage verifying hyphen normalization

Implementation

The normalization happens after trimming but before grouping:

{ $addFields: { answer_normalized: { $trim: { input: '$regex.match' } } } },
{
  $addFields: {
    // Replace hyphens with spaces to treat them as equivalent
    answer_normalized: { $replaceAll: { input: '$answer_normalized', find: '-', replacement: ' ' } }
  }
},
{ $group: { _id: '$answer_normalized', count: { $sum: 1 } } },

This ensures both "New-York" and "New York" normalize to "New York" and aggregate correctly.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>in frequency-list answerlines, hyphens and spaces should be equivalent</issue_title>
<issue_description></issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes in frequency-list answerlines, hyphens and spaces should be equivalent #427

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.