ClickHouse/tests/ci/run_check.py

250 lines
8.0 KiB
Python
Raw Normal View History

2021-09-15 12:59:39 +00:00
#!/usr/bin/env python3
import sys
2021-09-15 13:04:29 +00:00
import logging
2022-01-13 11:08:31 +00:00
import re
from github import Github
2021-11-26 14:00:09 +00:00
from env_helper import GITHUB_RUN_ID, GITHUB_REPOSITORY, GITHUB_SERVER_URL
from pr_info import PRInfo
from get_robot_token import get_best_robot_token
2021-11-12 12:36:25 +00:00
from commit_status_helper import get_commit
2021-09-15 12:59:39 +00:00
2022-01-13 11:06:50 +00:00
NAME = "Run Check (actions)"
2021-09-15 12:59:39 +00:00
TRUSTED_ORG_IDS = {
2022-01-13 11:06:50 +00:00
7409213, # yandex
2021-09-15 12:59:39 +00:00
28471076, # altinity
54801242, # clickhouse
}
OK_TEST_LABEL = set(["can be tested", "release", "pr-documentation", "pr-doc-fix"])
DO_NOT_TEST_LABEL = "do not test"
# Individual trusted contirbutors who are not in any trusted organization.
# Can be changed in runtime: we will append users that we learned to be in
# a trusted org, to save GitHub API calls.
2022-01-13 11:06:50 +00:00
TRUSTED_CONTRIBUTORS = {
e.lower()
for e in [
"achimbab",
"adevyatova ", # DOCSUP
"Algunenano", # Raúl Marín, Tinybird
"AnaUvarova", # DOCSUP
"anauvarova", # technical writer, Yandex
"annvsh", # technical writer, Yandex
"atereh", # DOCSUP
"azat",
"bharatnc", # Newbie, but already with many contributions.
"bobrik", # Seasoned contributor, CloundFlare
"BohuTANG",
"codyrobert", # Flickerbox engineer
"cwurm", # Employee
"damozhaeva", # DOCSUP
"den-crane",
"flickerbox-tom", # Flickerbox
"gyuton", # technical writer, Yandex
"hagen1778", # Roman Khavronenko, seasoned contributor
"hczhcz",
"hexiaoting", # Seasoned contributor
"ildus", # adjust, ex-pgpro
"javisantana", # a Spanish ClickHouse enthusiast, ex-Carto
"ka1bi4", # DOCSUP
"kirillikoff", # DOCSUP
"kitaisreal", # Seasoned contributor
"kreuzerkrieg",
"lehasm", # DOCSUP
"michon470", # DOCSUP
"MyroTk", # Tester in Altinity
"myrrc", # Michael Kot, Altinity
"nikvas0",
"nvartolomei",
"olgarev", # DOCSUP
"otrazhenia", # Yandex docs contractor
"pdv-ru", # DOCSUP
"podshumok", # cmake expert from QRator Labs
"s-mx", # Maxim Sabyanin, former employee, present contributor
"sevirov", # technical writer, Yandex
"spongedu", # Seasoned contributor
"ucasFL", # Amos Bird's friend
"vdimir", # Employee
"vzakaznikov",
"YiuRULE",
"zlobober", # Developer of YT
"ilejn", # Arenadata, responsible for Kerberized Kafka
"thomoco", # ClickHouse
"BoloniniD", # Seasoned contributor, HSE
]
}
2021-09-15 12:59:39 +00:00
def pr_is_by_trusted_user(pr_user_login, pr_user_orgs):
if pr_user_login.lower() in TRUSTED_CONTRIBUTORS:
logging.info("User '%s' is trusted", pr_user_login)
2021-09-15 12:59:39 +00:00
return True
logging.info("User '%s' is not trusted", pr_user_login)
2021-09-15 12:59:39 +00:00
for org_id in pr_user_orgs:
if org_id in TRUSTED_ORG_IDS:
2022-01-13 11:06:50 +00:00
logging.info(
"Org '%s' is trusted; will mark user %s as trusted",
org_id,
pr_user_login,
)
2021-09-15 12:59:39 +00:00
return True
logging.info("Org '%s' is not trusted", org_id)
2021-09-15 12:59:39 +00:00
return False
2022-01-13 11:06:50 +00:00
2021-09-15 12:59:39 +00:00
# Returns whether we should look into individual checks for this PR. If not, it
# can be skipped entirely.
def should_run_checks_for_pr(pr_info):
# Consider the labels and whether the user is trusted.
2021-12-22 08:13:04 +00:00
print("Got labels", pr_info.labels)
2022-01-13 11:06:50 +00:00
force_labels = set(["force tests"]).intersection(pr_info.labels)
2021-09-15 12:59:39 +00:00
if force_labels:
2022-01-13 11:06:50 +00:00
return True, "Labeled '{}'".format(", ".join(force_labels))
2021-09-15 12:59:39 +00:00
2022-01-13 11:06:50 +00:00
if "do not test" in pr_info.labels:
2021-09-15 12:59:39 +00:00
return False, "Labeled 'do not test'"
2022-01-13 11:06:50 +00:00
if "can be tested" not in pr_info.labels and not pr_is_by_trusted_user(
pr_info.user_login, pr_info.user_orgs
):
2021-09-15 12:59:39 +00:00
return False, "Needs 'can be tested' label"
2022-01-13 11:06:50 +00:00
if (
"release" in pr_info.labels
or "pr-backport" in pr_info.labels
or "pr-cherrypick" in pr_info.labels
):
2021-09-30 11:26:46 +00:00
return False, "Don't try new checks for release/backports/cherry-picks"
2021-09-15 12:59:39 +00:00
return True, "No special conditions apply"
2021-11-26 14:00:09 +00:00
2022-01-13 11:08:31 +00:00
def check_pr_description(pr_info):
description = pr_info.body
lines = [
line
for line in map(
lambda x: x.strip(), description.split("\n") if description else []
)
]
lines = [re.sub(r"\s+", " ", l) for l in lines]
category = ""
entry = ""
i = 0
while i < len(lines):
if re.match(r"(?i)^[>*_ ]*change\s*log\s*category", lines[i]):
i += 1
if i >= len(lines):
break
# Can have one empty line between header and the category
# itself. Filter it out.
if not lines[i]:
i += 1
if i >= len(lines):
break
category = re.sub(r"^[-*\s]*", "", lines[i])
i += 1
# Should not have more than one category. Require empty line
# after the first found category.
if i >= len(lines):
break
if lines[i]:
second_category = re.sub(r"^[-*\s]*", "", lines[i])
result_status = (
"More than one changelog category specified: '"
+ category
+ "', '"
+ second_category
+ "'"
)
return result_status[:140]
elif re.match(
r"(?i)^[>*_ ]*(short\s*description|change\s*log\s*entry)", lines[i]
):
i += 1
# Can have one empty line between header and the entry itself.
# Filter it out.
if i < len(lines) and not lines[i]:
i += 1
# All following lines until empty one are the changelog entry.
entry_lines = []
while i < len(lines) and lines[i]:
entry_lines.append(lines[i])
i += 1
entry = " ".join(entry_lines)
# Don't accept changelog entries like '...'.
entry = re.sub(r"[#>*_.\- ]", "", entry)
else:
i += 1
if not category:
return "Changelog category is empty"
# Filter out the PR categories that are not for changelog.
if re.match(
r"(?i)doc|((non|in|not|un)[-\s]*significant)|(not[ ]*for[ ]*changelog)",
category,
):
return ""
if not entry:
return "Changelog entry required for category '{}'".format(category)
return ""
2021-09-15 12:59:39 +00:00
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
2021-12-22 07:54:50 +00:00
pr_info = PRInfo(need_orgs=True, labels_from_api=True)
2021-09-15 12:59:39 +00:00
can_run, description = should_run_checks_for_pr(pr_info)
gh = Github(get_best_robot_token())
commit = get_commit(gh, pr_info.sha)
2022-01-13 11:08:31 +00:00
description_report = check_pr_description(pr_info)[:139]
if description_report:
print("::notice ::Cannot run, description does not match the template")
url = (
f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/"
"blob/master/.github/PULL_REQUEST_TEMPLATE.md?plain=1"
)
commit.create_status(
context=NAME,
description=description_report,
state="failure",
target_url=url,
)
sys.exit(1)
2021-11-26 14:00:09 +00:00
url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/actions/runs/{GITHUB_RUN_ID}"
2021-09-15 12:59:39 +00:00
if not can_run:
2021-09-16 10:39:36 +00:00
print("::notice ::Cannot run")
2022-01-13 11:06:50 +00:00
commit.create_status(
context=NAME, description=description, state="failure", target_url=url
)
2021-09-15 12:59:39 +00:00
sys.exit(1)
2021-09-15 13:36:48 +00:00
else:
2022-01-13 11:06:50 +00:00
if "pr-documentation" in pr_info.labels or "pr-doc-fix" in pr_info.labels:
commit.create_status(
context=NAME,
description="Skipping checks for documentation",
state="success",
target_url=url,
)
2021-10-26 10:34:12 +00:00
print("::notice ::Can run, but it's documentation PR, skipping")
else:
print("::notice ::Can run")
2022-01-13 11:06:50 +00:00
commit.create_status(
context=NAME, description=description, state="pending", target_url=url
)