Files
seaweedfs/.github/scripts/star_history.py
T
Copilotandchrislusf 73fa85f54f Retry transient failures in star history generation (#12479)
* Initial plan

* Retry transient star history API failures

Co-authored-by: chrislusf <1543151+chrislusf@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: chrislusf <1543151+chrislusf@users.noreply.github.com>
2026-11-07 18:12:34 -08:00

112 lines
3.4 KiB
Python

#!/usr/bin/env python3
"""Render the repository's star history to note/star_history.svg.
Uses the GitHub REST stargazers endpoint with the starred-at accept header,
which caps at 40,000 entries (400 pages of 100). The chart is regenerated on
a schedule; if the repo grows past that cap the script stops at 40,000 and
logs a warning rather than under-reporting.
"""
import json
import os
import sys
import time
import urllib.error
import urllib.request
from datetime import datetime
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt # noqa: E402
from matplotlib.dates import AutoDateLocator, DateFormatter # noqa: E402
REPO = "seaweedfs/seaweedfs"
TOKEN = os.environ["GITHUB_TOKEN"]
OUT = os.environ.get("OUT", "note/star_history.svg")
PAGE_CAP = 400 # GitHub's hard limit on stargazer pagination
REQUEST_ATTEMPTS = 5
RETRYABLE_STATUS_CODES = {429, 500, 502, 503, 504}
def open_url(req):
for attempt in range(REQUEST_ATTEMPTS):
try:
return urllib.request.urlopen(req, timeout=30)
except urllib.error.HTTPError as error:
if error.code not in RETRYABLE_STATUS_CODES or attempt == REQUEST_ATTEMPTS - 1:
raise
retry_after = error.headers.get("Retry-After")
try:
delay = min(float(retry_after), 60) if retry_after else 2**attempt
except ValueError:
delay = 2**attempt
error.close()
except urllib.error.URLError:
if attempt == REQUEST_ATTEMPTS - 1:
raise
delay = 2**attempt
time.sleep(delay)
def fetch_stargazers():
stars = []
page = 1
while page <= PAGE_CAP:
url = f"https://api.github.com/repos/{REPO}/stargazers?per_page=100&page={page}"
req = urllib.request.Request(
url,
headers={
"Accept": "application/vnd.github.star+json",
"Authorization": f"Bearer {TOKEN}",
"X-GitHub-Api-Version": "2022-11-28",
"User-Agent": "seaweedfs-star-history",
},
)
with open_url(req) as resp:
batch = json.load(resp)
if not batch:
break
for u in batch:
sa = u.get("starred_at")
if sa:
stars.append(datetime.fromisoformat(sa.replace("Z", "+00:00")))
if len(batch) < 100:
break
page += 1
if page > PAGE_CAP:
print(
f"::warning::Hit the {PAGE_CAP}-page stargazer pagination cap; "
"chart reflects the first 40,000 stars only."
)
return stars
def render(stars, out):
stars.sort()
counts = list(range(1, len(stars) + 1))
fig, ax = plt.subplots(figsize=(10, 6), dpi=130)
ax.plot(stars, counts, color="#0969da", linewidth=1.6)
ax.set_xlabel("Date")
ax.set_ylabel("Stars")
ax.set_title(f"{REPO} star history")
ax.grid(True, linestyle="--", alpha=0.3)
ax.xaxis.set_major_locator(AutoDateLocator())
ax.xaxis.set_major_formatter(DateFormatter("%Y-%m"))
fig.autofmt_xdate()
fig.tight_layout()
fig.savefig(out, format="svg", transparent=False)
plt.close(fig)
def main():
stars = fetch_stargazers()
if not stars:
print("::error::No stargazers fetched; not updating the chart.")
sys.exit(1)
render(stars, OUT)
print(f"Rendered {len(stars)} stars to {OUT}")
if __name__ == "__main__":
main()