From 4a0d96e496d956ae56572c66df613f44a669035f Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@meta.com>
Date: Fri, 31 May 2024 17:57:04 +0000
Subject: [PATCH] Add a GH action to autolabel docathon PRs (#127569)

To ease oncall burden for the docathon PR reviewers and ensure all PRs are correctly labeled, adding this GH action that will look for the issue number in the PR and if that issue has a docathon-h1-2024 label, then it would propagate the labels from the issues into the PR. It should not conflict with the existing labelers because we use ``pull_request.add_to_labels`` - credit @kit1980.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/127569
Approved by: https://github.com/kit1980
---
 .github/scripts/docathon-label-sync.py    | 52 +++++++++++++++++++++++
 .github/workflows/docathon-sync-label.yml | 30 +++++++++++++
 2 files changed, 82 insertions(+)
 create mode 100644 .github/scripts/docathon-label-sync.py
 create mode 100644 .github/workflows/docathon-sync-label.yml

diff --git a/.github/scripts/docathon-label-sync.py b/.github/scripts/docathon-label-sync.py
new file mode 100644
index 00000000000000..a10c3c3f886c84
--- /dev/null
+++ b/.github/scripts/docathon-label-sync.py
@@ -0,0 +1,52 @@
+import os
+import re
+import sys
+
+from github import Github
+
+
+def main() -> None:
+    token = os.environ.get("GITHUB_TOKEN")
+
+    repo_owner = "pytorch"
+    repo_name = "pytorch"
+    pull_request_number = int(sys.argv[1])
+
+    g = Github(token)
+    repo = g.get_repo(f"{repo_owner}/{repo_name}")
+    pull_request = repo.get_pull(pull_request_number)
+    pull_request_body = pull_request.body
+    # PR without description
+    if pull_request_body is None:
+        return
+
+    # get issue number from the PR body
+    if not re.search(r"#\d{1,6}", pull_request_body):
+        print("The pull request does not mention an issue.")
+        return
+    issue_number = int(re.findall(r"#(\d{1,6})", pull_request_body)[0])
+    issue = repo.get_issue(issue_number)
+    issue_labels = issue.labels
+    docathon_label_present = any(
+        label.name == "docathon-h1-2024" for label in issue_labels
+    )
+
+    # if the issue has a docathon label, add all labels from the issue to the PR.
+    if not docathon_label_present:
+        print("The 'docathon-h1-2024' label is not present in the issue.")
+        return
+    pull_request_labels = pull_request.get_labels()
+    pull_request_label_names = [label.name for label in pull_request_labels]
+    issue_label_names = [label.name for label in issue_labels]
+    labels_to_add = [
+        label for label in issue_label_names if label not in pull_request_label_names
+    ]
+    if not labels_to_add:
+        print("The pull request already has the same labels.")
+        return
+    pull_request.add_to_labels(*labels_to_add)
+    print("Labels added to the pull request!")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/.github/workflows/docathon-sync-label.yml b/.github/workflows/docathon-sync-label.yml
new file mode 100644
index 00000000000000..7cb1f608722d6b
--- /dev/null
+++ b/.github/workflows/docathon-sync-label.yml
@@ -0,0 +1,30 @@
+name: Docathon Labels Sync
+
+on:
+  pull_request_target:
+    types: [opened, synchronize, edited]
+    branches: [main]
+
+jobs:
+  check-labels:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 1
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.x
+      - name: Install dependencies
+        run: |
+          pip install requests==2.32.3
+          pip install PyGithub==2.3.0
+      - name: Run Python script
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python ./.github/scripts/docathon-label-sync.py ${{ github.event.pull_request.number }}