Fix author parsing in GitHub URLs with path-based author filters

[Copilot]

URLs like https://github.com/microsoft/devhome/pulls/lauren-ciha were not extracting the author filter, causing all open PRs to display instead of filtering by the specified author.

Changes

• SearchHelper.cs: Extract 4th path segment as author when parsing owner/repo/issues/author and owner/repo/pulls/author URL patterns. Added validation to skip empty/whitespace values.

• SearchHelperTests.cs: Added test coverage for author path segment in both pulls and issues URLs.

Example

// Before
ParseSearchStringFromUri("https://github.com/microsoft/devhome/pulls/lauren-ciha")
// => "repo:microsoft/devhome is:pr is:open"

// After
ParseSearchStringFromUri("https://github.com/microsoft/devhome/pulls/lauren-ciha")
// => "repo:microsoft/devhome is:pr is:open author:lauren-ciha"

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Author label in query URL is not parsed properly</issue_title>
<issue_description>To repro:

• Go to 'Saved GitHub queries' > 'Add a query'
• Enter https://github.com/microsoft/devhome/pulls/lauren-ciha
• Activate 'Save' button
• Navigate to the newly added query

Expected:

• An empty list/"No items found"
• Search string would be "repo:microsoft/devhome is:open is:issue author:lauren-ciha" (each filter can be in any order)

Actual:

• The open PRs for the Dev Home repo (four at the writing of this issue)
• Verify that the search string doesn't include "author:lauren-ciha"</issue_description>

<agent_instructions>Resolve this issue. First, write a test to confirm the bug is present in the codebase. Then, update the code as needed to make the test pass.</agent_instructions>

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

• Fixes Author label in query URL is not parsed properly #266

---

💡 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.

[Copilot]

Pull request overview

Fixes parsing of GitHub repository “issues” / “pulls” list URLs that embed an author in the path (e.g., /pulls/<author>), so saved queries correctly include an author: qualifier instead of returning all open items.

Changes:

• Update SearchHelper.ParseSearchStringFromUri to append author:<segment> based on the 4th URL path segment for .../issues/... and .../pulls/... routes.
• Add unit tests covering author-in-path parsing for both pulls and issues URLs.

Reviewed changes

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

File	Description
GitHubExtension/Helpers/SearchHelper.cs	Adds support for deriving author: from the 4th path segment on repo issues/pulls list URLs.
GitHubExtension.Test/HelpersTests/SearchHelperTests.cs	Adds tests validating the new author-in-path parsing behavior.

---

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

[Copilot]

Add a regression test to ensure numeric issue URLs (e.g., https://github.com/<owner>/<repo>/issues/123) and other non-author subpaths don’t get parsed into author:123 (or author:new). This will prevent future changes from reintroducing the bug noted in SearchHelper.ParseSearchStringFromUri.

Suggested change

	[DataRow("https://github.com/microsoft/PowerToys/issues/octocat", "repo:microsoft/PowerToys is:issue is:open author:octocat")]
	[DataRow("https://github.com/microsoft/PowerToys/issues/octocat", "repo:microsoft/PowerToys is:issue is:open author:octocat")]
	[DataRow("https://github.com/microsoft/PowerToys/issues/123", "repo:microsoft/PowerToys is:issue is:open")]
	[DataRow("https://github.com/microsoft/PowerToys/issues/new", "repo:microsoft/PowerToys is:issue is:open")]

[Copilot]

The new path-segment author handling will also treat common non-author subpaths (e.g., an issue URL like /owner/repo/issues/123 or /owner/repo/issues/new) as an author: filter, which changes behavior and can produce incorrect/empty results. Please gate this so the 4th segment is only interpreted as an author filter when it’s not an issue/PR identifier (e.g., skip purely-numeric segments) and ideally exclude known non-filter segments (like new).

Suggested change

	if (pathSegments.Length >= 4 && !string.IsNullOrWhiteSpace(pathSegments[3]))
	{
	bool IsPathSegmentLikelyAuthor(string segment)
	{
	if (string.IsNullOrWhiteSpace(segment))
	{
	return false;
	}
	// Exclude common non-author segments such as numeric IDs (issue/PR numbers)
	// and known keywords like "new".
	if (segment.Equals("new", StringComparison.OrdinalIgnoreCase))
	{
	return false;
	}
	var allDigits = true;
	foreach (var c in segment)
	{
	if (!char.IsDigit(c))
	{
	allDigits = false;
	break;
	}
	}
	if (allDigits)
	{
	return false;
	}
	return true;
	}
	if (pathSegments.Length >= 4 && IsPathSegmentLikelyAuthor(pathSegments[3]))
	{