add scripts/pr_lgtm_scanner.py — LGTM/KO scanner for pr-iphone-deploy
Standalone Python scanner extracted from the inline python in wait-approval. Embedding multi-line Python in a YAML run: | block scalar is fragile: YAML dedents block-scalar content to the first line's indent, which produced both YAML parse failures and Python IndentationErrors in earlier iterations of this workflow. A standalone script file sidesteps all of that and is testable locally. Behavior preserved: - json.loads + \bLGTM\b / \bKO\b word-boundary regex (case-insensitive) - skip bot comments tagged with <!-- tabatago:ready-to-test --> - KO checked BEFORE LGTM (PR with both signals blocks) Verified locally across 8 scenarios (bot-only, LGTM, KO, both, empty, usage error, KOM/LGTMX non-match, case-insensitive).
This commit is contained in:
70
scripts/pr_lgtm_scanner.py
Normal file
70
scripts/pr_lgtm_scanner.py
Normal file
@@ -0,0 +1,70 @@
|
||||
#!/usr/bin/env python3
|
||||
"""LGTM/KO scanner for the pr-iphone-deploy workflow's wait-approval job.
|
||||
|
||||
Reads a Gitea PR comments JSON array (as returned by
|
||||
``/api/v1/repos/{owner}/{repo}/issues/{pr}/comments``) on argv[1] and prints
|
||||
exactly one of: ``LGTM``, ``KO``, ``PENDING``.
|
||||
|
||||
Rules
|
||||
-----
|
||||
* The bot's own "Ready to test" comment body literally contains the words
|
||||
``LGTM`` and ``KO`` as instructions to the reviewer — without filtering it
|
||||
out, the workflow would self-merge ~30s after deploy. Bot comments are
|
||||
tagged with the sentinel ``<!-- tabatago:ready-to-test -->`` and skipped.
|
||||
* ``KO`` is checked BEFORE ``LGTM`` — a PR with both signals blocks (matches
|
||||
the existing "KO blocks" intent).
|
||||
* Word-boundary regex (``\\bLGTM\\b`` / ``\\bKO\\b``, case-insensitive) so
|
||||
"Tested, LGTM!" counts and "KOM" / "LGTMX" do not.
|
||||
|
||||
This script lives in ``scripts/`` (not inline in the workflow) because
|
||||
embedding multi-line Python inside a YAML ``run: |`` block scalar is fragile:
|
||||
YAML dedents block-scalar content to the first line, which produces either a
|
||||
YAML parse failure or a Python ``IndentationError`` depending on how the
|
||||
body is indented. A standalone file sidesteps all of that.
|
||||
"""
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
|
||||
MARKER = "<!-- tabatago:ready-to-test -->"
|
||||
LGTM_RE = re.compile(r"\bLGTM\b", re.IGNORECASE)
|
||||
KO_RE = re.compile(r"\bKO\b", re.IGNORECASE)
|
||||
|
||||
|
||||
def decide(comments_json: str) -> str:
|
||||
"""Return 'KO', 'LGTM', or 'PENDING' for the given comments JSON payload."""
|
||||
try:
|
||||
comments = json.loads(comments_json or "[]")
|
||||
except Exception:
|
||||
comments = []
|
||||
|
||||
hit_lgtm = False
|
||||
hit_ko = False
|
||||
for comment in comments:
|
||||
body = comment.get("body") or ""
|
||||
if MARKER in body:
|
||||
# Skip the bot's own "Ready to test" comment — its body mentions
|
||||
# LGTM/KO as instructions and would otherwise self-trigger.
|
||||
continue
|
||||
if KO_RE.search(body):
|
||||
hit_ko = True
|
||||
if LGTM_RE.search(body):
|
||||
hit_lgtm = True
|
||||
|
||||
if hit_ko:
|
||||
return "KO"
|
||||
if hit_lgtm:
|
||||
return "LGTM"
|
||||
return "PENDING"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
if len(sys.argv) != 2:
|
||||
print("usage: pr_lgtm_scanner.py <comments_json>", file=sys.stderr)
|
||||
return 2
|
||||
print(decide(sys.argv[1]))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user