fix(deploy): parse backup connection aliases and quoted values safely

This commit is contained in:
cesnimda
2026-11-02 12:11:48 +01:00
parent 653f8d04d4
commit f19e7ebf4a
5 changed files with 191 additions and 11 deletions
+68
View File
@@ -0,0 +1,68 @@
"""Read a deployment connection string from stdin; emit five fields plus a sentinel.
This is a single-host dump contract, not a replacement for MySqlConnector. Reject
ambiguous aliases/control characters instead of choosing a different backup target.
Never include input values in errors or pass the connection string as an argument.
"""
import re
import sys
ALIASES = {
**dict.fromkeys(['server', 'host', 'data source', 'datasource', 'address', 'addr', 'network address'], 'host'),
**dict.fromkeys(['user id', 'userid', 'username', 'uid', 'user name', 'user'], 'user'),
**dict.fromkeys(['password', 'pwd'], 'password'),
**dict.fromkeys(['database', 'initial catalog'], 'database'),
'port': 'port',
}
PAIR = re.compile(r'''\s*([^=;]+?)\s*=\s*(?:"((?:""|[^"])*)"|'((?:''|[^'])*)'|([^;]*))\s*(?:;|$)''')
def parse(connection):
if any(ord(c) < 32 or ord(c) == 127 for c in connection):
raise ValueError('Control characters are unsupported in backup connection settings.')
fields = {}
position = 0
while position < len(connection):
if connection[position] == ';' or connection[position].isspace():
position += 1
continue
match = PAIR.match(connection, position)
if not match:
raise ValueError('Malformed backup connection settings.')
key, double, single, plain = match.groups()
if double is not None:
value = double.replace('""', '"')
elif single is not None:
value = single.replace("''", "'")
else:
value = plain.strip()
if value.startswith(('"', "'")):
raise ValueError('Malformed quoted backup connection value.')
canonical = ALIASES.get(key.strip().lower())
if canonical:
if canonical in fields:
raise ValueError('Duplicate backup connection setting or alias.')
fields[canonical] = value
position = match.end()
if any(not fields.get(key, '').strip() for key in ['host', 'database', 'user']):
raise ValueError('Backup connection requires host, database and user.')
port = fields.get('port', '3306')
if not re.fullmatch(r'[0-9]+', port) or not 1 <= int(port) <= 65535:
raise ValueError('Backup connection port must be between 1 and 65535.')
if any(c in fields['host'] for c in ',/\\'):
raise ValueError('Backup requires one TCP host, not a host list or socket path.')
if any(c in fields['database'] for c in '/\\'):
raise ValueError('Database name cannot contain backup path separators.')
return [fields['host'], str(int(port)), fields['database'], fields['user'], fields.get('password', '')]
if __name__ == '__main__':
try:
values = parse(sys.stdin.buffer.read().decode('utf-8'))
except (ValueError, UnicodeError):
print('Invalid or unsupported backup connection settings.', file=sys.stderr)
sys.exit(1)
sys.stdout.reconfigure(encoding='utf-8', newline='\n')
# Sentinel keeps an empty final password intact through shell command substitution.
sys.stdout.write('\n'.join([*values, 'END']) + '\n')
+89
View File
@@ -0,0 +1,89 @@
"""Exercise the real backup function with a synthetic dump command; never deploy."""
import os
from pathlib import Path
import shlex
import shutil
import subprocess
import sys
import tempfile
import unittest
ROOT = Path(__file__).resolve().parents[1]
BASH = 'C:/Program Files/Git/bin/bash.exe' if os.name == 'nt' else shutil.which('bash')
class BackupConnectionTests(unittest.TestCase):
def backup(self, connection):
source = (ROOT / 'deploy/deploy.sh').read_text(encoding='utf-8')
start = source.index('backup_database() {')
function = source[start:source.index('\n}\n', start) + 3]
with tempfile.TemporaryDirectory() as temporary:
folder = Path(temporary)
script = '\n'.join([
'set -euo pipefail',
'BACKUP_DIR=' + shlex.quote(folder.as_posix()),
'BACKUP_STAMP=synthetic',
'DATABASE_PROVIDER=mariadb',
'JOBTRACKER_CONNECTION_STRING=' + shlex.quote(connection),
'python3() { ' + shlex.quote(Path(sys.executable).as_posix()) + ' "$@"; }',
'docker() { echo "Unexpected Docker call" >&2; return 99; }',
'mariadb-dump() { printf "%s\\0" "$@" > "$BACKUP_DIR/args"; '
'printf "%s" "$MYSQL_PWD" > "$BACKUP_DIR/password"; '
'printf "CREATE TABLE synthetic (id int);\\n-- Dump completed\\n"; }',
'verify_sql_backup() { gzip -t "$1"; }',
function,
'backup_database',
])
result = subprocess.run([BASH, '--noprofile', '--norc'], input=script,
text=True, encoding='utf-8', capture_output=True, cwd=ROOT,
env={**os.environ, 'DEPLOY_SKIP_DB_BACKUP': 'false'})
arguments = (folder / 'args').read_bytes().split(b'\0')[:-1] if (folder / 'args').exists() else None
password = (folder / 'password').read_text(encoding='utf-8') if (folder / 'password').exists() else None
return result, arguments, password
def test_supported_host_alias_and_case_reach_dump_unchanged(self):
for host in ['Server', 'SERVER', 'Host', 'Data Source', 'Address', 'Addr', 'Network Address']:
with self.subTest(host=host):
result, args, password = self.backup(f'{host}=127.0.0.1;DATABASE=synthetic;UID=reader;PWD=dummy-secret')
self.assertEqual(0, result.returncode, result.stderr + result.stdout)
self.assertEqual([b'--host=127.0.0.1', b'--port=3306', b'--user=reader',
b'--single-transaction', b'--routines', b'--events', b'--quick', b'synthetic'], args)
self.assertEqual('dummy-secret', password)
self.assertNotIn('dummy-secret', result.stdout + result.stderr)
def test_quoted_separators_and_shell_characters_remain_data(self):
result, args, password = self.backup('Server=127.0.0.1;Port=3307;Database=synthetic;User ID=reader;Password="semi;eq=quote""$(false)"')
self.assertEqual(0, result.returncode, result.stderr + result.stdout)
self.assertIn(b'--port=3307', args)
self.assertEqual('semi;eq=quote"$(false)', password)
def test_empty_password_is_preserved(self):
result, args, password = self.backup('Server=127.0.0.1;Database=synthetic;User ID=reader;Password=')
self.assertEqual(0, result.returncode, result.stderr + result.stdout)
self.assertIsNotNone(args)
self.assertEqual('', password)
def test_single_quoted_unicode_password_and_database_alias_are_preserved(self):
result, args, password = self.backup("Host=127.0.0.1;Initial Catalog=synthetic;Username=reader;Password='søknad你好;it''s';SslMode=VerifyFull")
self.assertEqual(0, result.returncode, result.stderr + result.stdout)
self.assertEqual(b'synthetic', args[-1])
self.assertEqual("søknad你好;it's", password)
def test_invalid_or_ambiguous_input_never_invokes_dump_or_exposes_input(self):
for connection in [
'Host=127.0.0.1;Database=synthetic;Uid=reader;Port=0;Pwd=dummy-secret',
'Host=127.0.0.1;Database=synthetic;Uid=reader;Port=65536;Pwd=dummy-secret',
'Host=127.0.0.1;Server=other;Database=synthetic;Uid=reader;Pwd=dummy-secret',
'Host=127.0.0.1;Database=synthetic;Uid=reader;Pwd="dummy-secret',
'Host=127.0.0.1;Database=synthetic;Uid=reader;Pwd=dummy-secret\nline',
'Host=127.0.0.1;Uid=reader;Pwd=dummy-secret',
]:
with self.subTest(connection=connection.replace('dummy-secret', 'REDACTED')):
result, args, _ = self.backup(connection)
self.assertNotEqual(0, result.returncode)
self.assertIsNone(args)
self.assertNotIn('dummy-secret', result.stdout + result.stderr)
if __name__ == '__main__':
unittest.main()