atlas-iac/services/gitea/scripts/gitea_branch_protection_check.py
2026-08-17 07:58:44 -03:00

208 lines
7.9 KiB
Python

#!/usr/bin/env python3
"""Validate the first effective Gitea protection for an Atlas primary branch."""
from __future__ import annotations
import argparse
import datetime
import json
import os
import re
import stat
from pathlib import Path
MAX_INPUT = 1024 * 1024
MAX_RULES = 100
MAX_RULE_NAME = 255
SPECIAL = frozenset("*?\\[]{}")
class PolicyError(RuntimeError):
"""The protection response is ambiguous or violates human review policy."""
def _read_bounded(path: Path) -> bytes:
descriptor = os.open(path, os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0))
try:
metadata = os.fstat(descriptor)
if not stat.S_ISREG(metadata.st_mode) or metadata.st_size > MAX_INPUT:
raise PolicyError("branch protection response exceeds the safe limit")
value = os.read(descriptor, MAX_INPUT + 1)
finally:
os.close(descriptor)
if len(value) != metadata.st_size:
raise PolicyError("branch protection response changed while reading")
return value
def _glob_regex(pattern: str, position: int = 0, terminators: str = "") -> tuple[str, int]:
"""Compile the gobwas/glob syntax Gitea v1.23.8 uses."""
pieces: list[str] = []
while position < len(pattern):
character = pattern[position]
if character in terminators:
break
if character == "\\":
position += 1
if position >= len(pattern):
raise ValueError("trailing escape")
pieces.append(re.escape(pattern[position]))
elif character == "*":
if position + 1 < len(pattern) and pattern[position + 1] == "*":
pieces.append(".*")
position += 1
else:
pieces.append("[^/]*")
elif character == "?":
pieces.append("[^/]")
elif character == "[":
end = pattern.find("]", position + 1)
if end < 0:
raise ValueError("unterminated range")
value = pattern[position + 1 : end]
if not value:
raise ValueError("empty range")
negate = value.startswith("!")
value = value[1:] if negate else value
if not value or "[" in value or "\\" in value:
raise ValueError("invalid range")
if "-" in value:
if value.count("-") != 1 or value.startswith("-") or value.endswith("-"):
raise ValueError("invalid range")
low, high = value.split("-")
if len(low) != 1 or len(high) != 1 or ord(high) < ord(low):
raise ValueError("invalid range")
content = re.escape(low) + "-" + re.escape(high)
else:
content = re.escape(value)
pieces.append("[" + ("^" if negate else "") + content + "]")
position = end
elif character == "{":
alternatives: list[str] = []
position += 1
while True:
alternative, position = _glob_regex(pattern, position, ",}")
alternatives.append(alternative)
if position >= len(pattern):
raise ValueError("unterminated alternatives")
if pattern[position] == "}":
break
position += 1
if len(alternatives) < 2 or any(not item for item in alternatives):
raise ValueError("invalid alternatives")
pieces.append("(?:" + "|".join(alternatives) + ")")
elif character in "]}":
# A closing delimiter outside its grammar context is literal in
# gobwas/glob's lexer.
pieces.append(re.escape(character))
else:
pieces.append(re.escape(character))
position += 1
return "".join(pieces), position
def _is_plain(pattern: str) -> bool:
return not any(character in SPECIAL for character in pattern)
def _matches(pattern: str, branch: str) -> bool:
if not pattern.isascii() or not 1 <= len(pattern) <= MAX_RULE_NAME:
raise PolicyError("branch protection rule name is invalid")
if _is_plain(pattern):
return pattern.casefold() == branch.casefold()
try:
expression, position = _glob_regex(pattern)
if position != len(pattern):
raise ValueError("incomplete glob")
except (re.error, ValueError):
# Gitea quotes an invalid special pattern and matches it literally.
# A literal containing a special byte cannot equal main or master.
return False
return re.fullmatch(expression, branch) is not None
def _created(value: object) -> datetime.datetime:
if not isinstance(value, str) or len(value) > 64:
raise PolicyError("branch protection creation time is invalid")
try:
result = datetime.datetime.fromisoformat(value.replace("Z", "+00:00"))
except ValueError as exc:
raise PolicyError("branch protection creation time is invalid") from exc
if result.tzinfo is None:
raise PolicyError("branch protection creation time is invalid")
return result
def _required(reviewer: str) -> dict[str, object]:
return {
"enable_push": True,
"enable_push_whitelist": True,
"push_whitelist_usernames": [reviewer],
"push_whitelist_deploy_keys": False,
"enable_force_push": False,
"enable_merge_whitelist": True,
"merge_whitelist_usernames": [reviewer],
"enable_approvals_whitelist": True,
"approvals_whitelist_username": [reviewer],
"required_approvals": 1,
"block_on_rejected_reviews": True,
"block_on_outdated_branch": True,
"dismiss_stale_approvals": True,
"block_admin_merge_override": True,
}
def evaluate(value: bytes, branch: str, reviewer: str) -> str:
"""Return PRESENT/ABSENT or fail on ambiguous/effective policy drift."""
if len(value) > MAX_INPUT or branch not in {"main", "master"}:
raise PolicyError("branch protection input is invalid")
data = json.loads(value)
if not isinstance(data, list) or len(data) > MAX_RULES:
raise PolicyError("branch protection response is invalid")
ordered: list[tuple[int, bool, datetime.datetime, int, dict[str, object]]] = []
for index, raw in enumerate(data):
if not isinstance(raw, dict):
raise PolicyError("branch protection entry is invalid")
priority = raw.get("priority")
rule_name = raw.get("rule_name")
if (
not isinstance(priority, int)
or isinstance(priority, bool)
or not 1 <= priority <= 1_000_000
or not isinstance(rule_name, str)
):
raise PolicyError("branch protection priority is ambiguous")
created = _created(raw.get("created_at"))
if _matches(rule_name, branch):
# Gitea v1.23.8 sorts by priority, then puts plain names before
# globs, then uses creation time. The API exposes every component.
ordered.append((priority, not _is_plain(rule_name), created, index, raw))
if not ordered:
return "ABSENT"
effective = min(ordered)[4]
for key, expected in _required(reviewer).items():
if effective.get(key) != expected:
raise PolicyError(
f"effective {branch} protection differs from human-review policy"
)
return "PRESENT"
def main() -> int:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("response", type=Path)
parser.add_argument("branch", choices=("main", "master"))
parser.add_argument("reviewer")
args = parser.parse_args()
try:
value = _read_bounded(args.response)
print(evaluate(value, args.branch, args.reviewer))
except (OSError, json.JSONDecodeError, PolicyError) as exc:
print(f"branch protection check failed: {exc}", file=__import__("sys").stderr)
return 1
return 0
if __name__ == "__main__":
raise SystemExit(main())