Skip to content

Addressing PR comments#29

Closed
Copilot wants to merge 6 commits intomasterfrom
copilot/apply-version-diff-13-to-14
Closed

Addressing PR comments#29
Copilot wants to merge 6 commits intomasterfrom
copilot/apply-version-diff-13-to-14

Conversation

Copy link
Contributor

Copilot AI commented Mar 3, 2026

  • Re-evaluate the new PR comment and identify actionable parity checks
  • Inspect current Java vs referenced C# 1.4.0 diffs (Clipper.Core/Engine) for missing changes
  • Apply minimal Java changes for any confirmed parity gaps
  • Run targeted tests for affected engine/core behavior
  • Run code review and security scan
  • Reply to the PR comment with the addressing commit hash

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

Copilot AI and others added 2 commits March 3, 2026 21:14
Co-authored-by: micycle1 <9304234+micycle1@users.noreply.github.com>
Co-authored-by: micycle1 <9304234+micycle1@users.noreply.github.com>
Copilot AI changed the title [WIP] Apply changes from version 1.3.0 to 1.4.0 in Java port Port Clipper2 1.3.0→1.4.0 C# library deltas into Java core/engine/offset/rectclip Mar 3, 2026
@micycle1
Copy link
Owner

micycle1 commented Mar 3, 2026

@copilot double-check your proposed changes vs the diff.

Co-authored-by: micycle1 <9304234+micycle1@users.noreply.github.com>
Copy link
Contributor Author

Copilot AI commented Mar 3, 2026

@copilot double-check your proposed changes vs the diff.

I re-checked the Java port against the upstream 1.3.0→1.4.0 C# diff and found one missed parity condition in ClipperBase.BuildPath: the very-small-triangle rejection now correctly applies only to closed paths (!isOpen), matching upstream. Fixed in 63c7915, then re-ran targeted tests plus full mvn test (all passing). No UI changes in this PR.

@micycle1
Copy link
Owner

micycle1 commented Mar 3, 2026

@codex[agent] There's a diff in Clipper.Engine.cs which hasn't (as as i can tell) been replicated in ClipperBase.java -- changes to IntersectEdges(), etc.

@Codex
Copy link

Codex AI commented Mar 3, 2026

@codex[agent] There's a diff in Clipper.Engine.cs which hasn't (as as i can tell) been replicated in ClipperBase.java -- changes to IntersectEdges(), etc.

Synced IntersectEdges with the C# 1.4.0 diff—method is now void with early returns instead of returning an OutPt, matching upstream logic (d37acbf).

@Codex Codex AI changed the title Port Clipper2 1.3.0→1.4.0 C# library deltas into Java core/engine/offset/rectclip Addressing PR comments Mar 3, 2026
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 63c79152e5

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

if (cnt == 1) {
Point64 pt = p.get(0);
if (deltaCallback != null) {
groupDelta = deltaCallback.calculate(p, normals, 0, 0);

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Reset normals before invoking single-point delta callbacks

In DoGroupOffset, the new cnt == 1 callback path calls deltaCallback.calculate(p, normals, 0, 0) without rebuilding or clearing normals, so if a multi-vertex path was processed just before, the callback receives stale normals from the previous path. This causes incorrect variable offsets for the single-point path (and can break callbacks that assume path_norms matches the current path). Please clear normals or pass an empty normals list before this callback.

Useful? React with 👍 / 👎.

Co-authored-by: micycle1 <9304234+micycle1@users.noreply.github.com>
Copy link
Contributor Author

Copilot AI commented Mar 3, 2026

@copilot another pass.

Here's the .diff file:
...

Applied another parity pass and fixed a missed Core 1.4 delta in Java: Path64/PathD string formatting now matches the upstream separator/trim behavior, with test expectations updated accordingly. Addressed in commit 13ce4ab.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants