Notify merger if PR is incorrectly labeled (#1937)

.github/process_commit.py

+"""
+This script finds the merger responsible for labeling a PR by a commit SHA. It is used by the workflow in
+'.github/workflows/pr-labels.yml'. If there exists no PR associated with the commit or the PR is properly labeled,
+this script is a no-op.
+Note: we ping the merger only, not the reviewers, as the reviewers can sometimes be external to torchaudio
+with no labeling responsibility, so we don't want to bother them.
+"""
+
+import sys
+from typing import Any, Optional, Set, Tuple
+
+import requests
+
+# For a PR to be properly labeled it should have one primary label and one secondary label
+# For a PR with primary label "other", it does not require an additional secondary label
+PRIMARY_LABELS = {
+    "BC-breaking",
+    "deprecation",
+    "bug",
+    "new feature",
+    "improvement",
+    "example",
+    "prototype",
+    "other",
+}
+
+SECONDARY_LABELS = {
+    "module: I/O",
+    "module: ops",
+    "module: models",
+    "module: pipelines",
+    "module: datasets",
+    "module: docs"
+    "module: tests"
+    "build",
+    "style",
+    "perf",
+    "other",
+}
+
+
+def query_torchaudio(cmd: str, *, accept) -> Any:
+    response = requests.get(f"https://api.github.com/repos/pytorch/audio/{cmd}", headers=dict(Accept=accept))
+    return response.json()
+
+
+def get_pr_number(commit_hash: str) -> Optional[int]:
+    # See https://docs.github.com/en/rest/reference/repos#list-pull-requests-associated-with-a-commit
+    data = query_torchaudio(f"commits/{commit_hash}/pulls", accept="application/vnd.github.groot-preview+json")
+    if not data:
+        return None
+    return data[0]["number"]
+
+
+def get_pr_merger_and_labels(pr_number: int) -> Tuple[str, Set[str]]:
+    # See https://docs.github.com/en/rest/reference/pulls#get-a-pull-request
+    data = query_torchaudio(f"pulls/{pr_number}", accept="application/vnd.github.v3+json")
+    merger = data["merged_by"]["login"]
+    labels = {label["name"] for label in data["labels"]}
+    return merger, labels
+
+
+if __name__ == "__main__":
+    commit_hash = sys.argv[1]
+    pr_number = get_pr_number(commit_hash)
+    if not pr_number:
+        sys.exit(0)
+
+    merger, labels = get_pr_merger_and_labels(pr_number)
+    is_properly_labeled = bool(PRIMARY_LABELS.intersection(labels) and SECONDARY_LABELS.intersection(labels))
+
+    if not is_properly_labeled:
+        print(f"@{merger}")

.github/workflows/pr-labels.yml

+name: pr-labels
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  is-properly-labeled:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Set up python
+        uses: actions/setup-python@v2
+
+      - name: Install requests
+        run: pip install requests
+
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Process commit and find merger responsible for labeling
+        id: commit
+        run: echo "::set-output name=merger::$(python .github/process_commit.py ${{ github.sha }})"
+
+      - name: Ping merger responsible for labeling if necessary
+        if: ${{ steps.commit.outputs.merger != '' }}
+        uses: mshick/add-pr-comment@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          message: |
+            Hey ${{ steps.commit.outputs.merger }}!
+            You merged this PR, but no labels were added. The list of valid labels is available at https://github.com/pytorch/audio/blob/main/.github/process_commit.py