Files
atc-agents/infra/hadoop/s3util.py
T
mo 1147826dee fix(superset): disable Secure session cookie over HTTP so mo/bart can log in
Talisman forced Secure on the session cookie while Superset is served over
plain HTTP, so browsers never returned the cookie and every login failed CSRF
validation ("CSRF session token is missing"). Set session_cookie_secure=False
(+ SESSION_COOKIE_SECURE/WTF_CSRF_SSL_STRICT). Also rename S3 lakehouse prefix
iceberg-warehouse -> hadoop (Trino iceberg.hadoop.historical_sales) and repoint
the Superset dataset. Adds sanitized infra backup scripts.
2026-06-26 15:27:34 +00:00

45 lines
1.4 KiB
Python

"""List/delete objects under a prefix in the Dell ECS S3 bucket.
Credentials are read from the environment so no secrets are committed:
S3_ENDPOINT, S3_ACCESS_KEY, S3_SECRET_KEY, S3_BUCKET (default "data").
ECS rejects bulk delete (Content-MD5), so deletes are done one object at a time.
"""
import os
import sys
import boto3
from botocore.config import Config
s3 = boto3.client(
"s3",
endpoint_url=os.environ["S3_ENDPOINT"],
aws_access_key_id=os.environ["S3_ACCESS_KEY"],
aws_secret_access_key=os.environ["S3_SECRET_KEY"],
config=Config(s3={"addressing_style": "path"}, signature_version="s3v4"),
)
BUCKET = os.environ.get("S3_BUCKET", "data")
def listp(prefix):
p = s3.get_paginator("list_objects_v2")
n = 0
for page in p.paginate(Bucket=BUCKET, Prefix=prefix):
for o in page.get("Contents", []):
print(f"{o['Size']:>12} {o['Key']}")
n += 1
print(f"# total objects under '{prefix}': {n}")
def delp(prefix):
p = s3.get_paginator("list_objects_v2")
n = 0
for page in p.paginate(Bucket=BUCKET, Prefix=prefix):
for o in page.get("Contents", []):
s3.delete_object(Bucket=BUCKET, Key=o["Key"])
n += 1
print(f"# deleted {n} objects under '{prefix}'")
if __name__ == "__main__":
cmd, prefix = sys.argv[1], sys.argv[2]
(listp if cmd == "ls" else delp)(prefix)