39 Commits

Author SHA1 Message Date
2a0e77a754 MyFSIO v0.3.7 Release
Reviewed-on: #30
2026-03-09 06:25:50 +00:00
c6e368324a Update docs.md and docs.html for credential expiry, IAM encryption, admin key env vars, and --reset-cred 2026-03-08 13:38:44 +08:00
7b6c096bb7 Remove the check out the documentation paragraph at login page 2026-03-08 13:18:03 +08:00
03353a0aec Add credential expiry support: per-user expires_at with UI management, presets, and badge indicators; Add credential expiry support: per-user expires_at with UI management, presets, and badge indicators; Fix IAM card dropdown clipped by overflow: remove gradient bar, allow overflow visible 2026-03-08 13:08:57 +08:00
eb0e435a5a MyFSIO v0.3.6 Release
Reviewed-on: #29
2026-03-08 04:46:31 +00:00
72f5d9d70c Restore data integrity guarantees: Content-MD5 validation, fsync durability, atomic metadata writes, concurrent write protection 2026-03-07 17:54:00 +08:00
be63e27c15 Reduce per-request CPU overhead: eliminate double stat(), cache content type and policy context, gate logging, configurable stat intervals 2026-03-07 14:08:23 +08:00
7633007a08 MyFSIO v0.3.5 Release
Reviewed-on: #28
2026-03-07 05:53:02 +00:00
81ef0fe4c7 Fix stale object count in bucket header and metrics dashboard after deletes 2026-03-03 19:42:37 +08:00
5f24bd920d Reduce P99 tail latency: defer etag index writes, eliminate double cache rebuild, skip redundant stat() in bucket config 2026-03-02 22:39:37 +08:00
8552f193de Reduce CPU/lock contention under concurrent uploads: split cache lock, in-memory stats, dict copy, lightweight request IDs, defaultdict metrics 2026-03-02 22:05:54 +08:00
de0d869c9f Merge pull request 'MyFSIO v0.3.4 Release' (#27) from next into main
Reviewed-on: #27
2026-03-02 08:31:32 +00:00
5536330aeb Move performance-critical Python functions to Rust: streaming I/O, multipart assembly, and AES-256-GCM encryption 2026-02-27 22:55:20 +08:00
d4657c389d Fix misleading default credentials in README to match actual random generation behavior 2026-02-27 21:58:10 +08:00
fdd068feee MyFSIO v0.3.3 Release
Reviewed-on: #26
2026-02-27 04:49:32 +00:00
66b7677d2c MyFSIO v0.3.2 Release
Reviewed-on: #25
2026-02-26 10:10:19 +00:00
4d90ead816 Merge pull request 'Fix incorrect Upgrading & Updates section in Docs' (#24) from next into main
Reviewed-on: #24
2026-02-26 09:50:17 +00:00
b37a51ed1d MyFSIO v0.3.1 Release
Reviewed-on: #23
2026-02-26 09:42:37 +00:00
0462a7b62e MyFSIO v0.3.0 Release
Reviewed-on: #22
2026-02-22 10:22:35 +00:00
52660570c1 Merge pull request 'MyFSIO v0.2.9 Release' (#21) from next into main
Reviewed-on: #21
2026-02-15 14:24:14 +00:00
35f61313e0 MyFSIO v0.2.8 Release
Reviewed-on: #20
2026-02-10 14:16:22 +00:00
c470cfb576 MyFSIO v0.2.7 Release
Reviewed-on: #19
2026-02-09 12:22:37 +00:00
jun
d96955deee MyFSIO v0.2.6 Release
Reviewed-on: #18
2026-02-05 16:18:03 +00:00
85181f0be6 Merge pull request 'MyFSIO v0.2.5 Release' (#17) from next into main
Reviewed-on: #17
2026-02-02 05:32:02 +00:00
d5ca7a8be1 Merge pull request 'MyFSIO v0.2.4 Release' (#16) from next into main
Reviewed-on: #16
2026-02-01 10:27:11 +00:00
476dc79e42 MyFSIO v0.2.3 Release
Reviewed-on: #15
2026-01-25 06:05:53 +00:00
bb6590fc5e Merge pull request 'MyFSIO v0.2.2 Release' (#14) from next into main
Reviewed-on: #14
2026-01-19 07:12:15 +00:00
899db3421b Merge pull request 'MyFSIO v0.2.1 Release' (#13) from next into main
Reviewed-on: #13
2026-01-12 08:03:29 +00:00
caf01d6ada Merge pull request 'MyFSIO v0.2.0 Release' (#12) from next into main
Reviewed-on: #12
2026-01-05 15:48:03 +00:00
bb366cb4cd Merge pull request 'MyFSIO v0.1.9 Release' (#10) from next into main
Reviewed-on: #10
2025-12-29 06:49:48 +00:00
a2745ff2ee Merge pull request 'MyFSIO v0.1.8 Release' (#9) from next into main
Reviewed-on: #9
2025-12-23 06:01:32 +00:00
28cb656d94 Merge pull request 'MyFSIO v0.1.7 Release' (#8) from next into main
Reviewed-on: #8
2025-12-22 03:10:35 +00:00
3c44152fc6 Merge pull request 'MyFSIO v0.1.6 Release' (#7) from next into main
Reviewed-on: #7
2025-12-21 06:30:21 +00:00
397515edce Merge pull request 'MyFSIO v0.1.5 Release' (#6) from next into main
Reviewed-on: #6
2025-12-13 15:41:03 +00:00
980fced7e4 Merge pull request 'MyFSIO v0.1.4 Release' (#5) from next into main
Reviewed-on: #5
2025-12-13 08:22:43 +00:00
bae5009ec4 Merge pull request 'Release v0.1.3' (#4) from next into main
Reviewed-on: #4
2025-12-03 04:14:57 +00:00
233780617f Merge pull request 'Release V0.1.2' (#3) from next into main
Reviewed-on: #3
2025-11-26 04:59:15 +00:00
fd8fb21517 Merge pull request 'Prepare for binary release' (#2) from next into main
Reviewed-on: #2
2025-11-22 12:33:38 +00:00
c6cbe822e1 Merge pull request 'Release v0.1.1' (#1) from next into main
Reviewed-on: #1
2025-11-22 12:31:27 +00:00
25 changed files with 1702 additions and 298 deletions

View File

@@ -80,7 +80,7 @@ python run.py --mode api # API only (port 5000)
python run.py --mode ui # UI only (port 5100)
```
**Default Credentials:** `localadmin` / `localadmin`
**Credentials:** Generated automatically on first run and printed to the console. If missed, check the IAM config file at `<STORAGE_ROOT>/.myfsio.sys/config/iam.json`.
- **Web Console:** http://127.0.0.1:5100/ui
- **API Endpoint:** http://127.0.0.1:5000

View File

@@ -1,13 +1,13 @@
from __future__ import annotations
import html as html_module
import itertools
import logging
import mimetypes
import os
import shutil
import sys
import time
import uuid
from logging.handlers import RotatingFileHandler
from pathlib import Path
from datetime import timedelta
@@ -39,6 +39,8 @@ from .storage import ObjectStorage, StorageError
from .version import get_version
from .website_domains import WebsiteDomainStore
_request_counter = itertools.count(1)
def _migrate_config_file(active_path: Path, legacy_paths: List[Path]) -> Path:
"""Migrate config file from legacy locations to the active path.
@@ -128,6 +130,7 @@ def create_app(
Path(app.config["IAM_CONFIG"]),
auth_max_attempts=app.config.get("AUTH_MAX_ATTEMPTS", 5),
auth_lockout_minutes=app.config.get("AUTH_LOCKOUT_MINUTES", 15),
encryption_key=app.config.get("SECRET_KEY"),
)
bucket_policies = BucketPolicyStore(Path(app.config["BUCKET_POLICY_PATH"]))
secret_store = EphemeralSecretStore(default_ttl=app.config.get("SECRET_TTL_SECONDS", 300))
@@ -481,13 +484,9 @@ def _configure_logging(app: Flask) -> None:
@app.before_request
def _log_request_start() -> None:
g.request_id = uuid.uuid4().hex
g.request_id = f"{os.getpid():x}{next(_request_counter):012x}"
g.request_started_at = time.perf_counter()
g.request_bytes_in = request.content_length or 0
app.logger.info(
"Request started",
extra={"path": request.path, "method": request.method, "remote_addr": request.remote_addr},
)
@app.before_request
def _maybe_serve_website():
@@ -616,8 +615,9 @@ def _configure_logging(app: Flask) -> None:
duration_ms = 0.0
if hasattr(g, "request_started_at"):
duration_ms = (time.perf_counter() - g.request_started_at) * 1000
request_id = getattr(g, "request_id", uuid.uuid4().hex)
request_id = getattr(g, "request_id", f"{os.getpid():x}{next(_request_counter):012x}")
response.headers.setdefault("X-Request-ID", request_id)
if app.logger.isEnabledFor(logging.INFO):
app.logger.info(
"Request completed",
extra={

View File

@@ -2,6 +2,7 @@ from __future__ import annotations
import ipaddress
import json
import os
import re
import time
from dataclasses import dataclass, field
@@ -268,7 +269,7 @@ class BucketPolicyStore:
self._last_mtime = self._current_mtime()
# Performance: Avoid stat() on every request
self._last_stat_check = 0.0
self._stat_check_interval = 1.0 # Only check mtime every 1 second
self._stat_check_interval = float(os.environ.get("BUCKET_POLICY_STAT_CHECK_INTERVAL_SECONDS", "2.0"))
def maybe_reload(self) -> None:
# Performance: Skip stat check if we checked recently

View File

@@ -19,6 +19,13 @@ from cryptography.hazmat.primitives import hashes
if sys.platform != "win32":
import fcntl
try:
import myfsio_core as _rc
_HAS_RUST = True
except ImportError:
_rc = None
_HAS_RUST = False
logger = logging.getLogger(__name__)
@@ -338,6 +345,69 @@ class StreamingEncryptor:
output.seek(0)
return output
def encrypt_file(self, input_path: str, output_path: str) -> EncryptionMetadata:
data_key, encrypted_data_key = self.provider.generate_data_key()
base_nonce = secrets.token_bytes(12)
if _HAS_RUST:
_rc.encrypt_stream_chunked(
input_path, output_path, data_key, base_nonce, self.chunk_size
)
else:
with open(input_path, "rb") as stream:
aesgcm = AESGCM(data_key)
with open(output_path, "wb") as out:
out.write(b"\x00\x00\x00\x00")
chunk_index = 0
while True:
chunk = stream.read(self.chunk_size)
if not chunk:
break
chunk_nonce = self._derive_chunk_nonce(base_nonce, chunk_index)
encrypted_chunk = aesgcm.encrypt(chunk_nonce, chunk, None)
out.write(len(encrypted_chunk).to_bytes(self.HEADER_SIZE, "big"))
out.write(encrypted_chunk)
chunk_index += 1
out.seek(0)
out.write(chunk_index.to_bytes(4, "big"))
return EncryptionMetadata(
algorithm="AES256",
key_id=self.provider.KEY_ID if hasattr(self.provider, "KEY_ID") else "local",
nonce=base_nonce,
encrypted_data_key=encrypted_data_key,
)
def decrypt_file(self, input_path: str, output_path: str,
metadata: EncryptionMetadata) -> None:
data_key = self.provider.decrypt_data_key(metadata.encrypted_data_key, metadata.key_id)
base_nonce = metadata.nonce
if _HAS_RUST:
_rc.decrypt_stream_chunked(input_path, output_path, data_key, base_nonce)
else:
with open(input_path, "rb") as stream:
chunk_count_bytes = stream.read(4)
if len(chunk_count_bytes) < 4:
raise EncryptionError("Invalid encrypted stream: missing header")
chunk_count = int.from_bytes(chunk_count_bytes, "big")
aesgcm = AESGCM(data_key)
with open(output_path, "wb") as out:
for chunk_index in range(chunk_count):
size_bytes = stream.read(self.HEADER_SIZE)
if len(size_bytes) < self.HEADER_SIZE:
raise EncryptionError(f"Invalid encrypted stream: truncated at chunk {chunk_index}")
chunk_size = int.from_bytes(size_bytes, "big")
encrypted_chunk = stream.read(chunk_size)
if len(encrypted_chunk) < chunk_size:
raise EncryptionError(f"Invalid encrypted stream: incomplete chunk {chunk_index}")
chunk_nonce = self._derive_chunk_nonce(base_nonce, chunk_index)
try:
decrypted_chunk = aesgcm.decrypt(chunk_nonce, encrypted_chunk, None)
out.write(decrypted_chunk)
except Exception as exc:
raise EncryptionError(f"Failed to decrypt chunk {chunk_index}: {exc}") from exc
class EncryptionManager:
"""Manages encryption providers and operations."""

View File

@@ -1,5 +1,6 @@
from __future__ import annotations
import base64
import hashlib
import hmac
import json
@@ -14,6 +15,8 @@ from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Any, Deque, Dict, Iterable, List, Optional, Sequence, Set, Tuple
from cryptography.fernet import Fernet, InvalidToken
class IamError(RuntimeError):
"""Raised when authentication or authorization fails."""
@@ -107,13 +110,24 @@ class Principal:
policies: List[Policy]
def _derive_fernet_key(secret: str) -> bytes:
raw = hashlib.pbkdf2_hmac("sha256", secret.encode(), b"myfsio-iam-encryption", 100_000)
return base64.urlsafe_b64encode(raw)
_IAM_ENCRYPTED_PREFIX = b"MYFSIO_IAM_ENC:"
class IamService:
"""Loads IAM configuration, manages users, and evaluates policies."""
def __init__(self, config_path: Path, auth_max_attempts: int = 5, auth_lockout_minutes: int = 15) -> None:
def __init__(self, config_path: Path, auth_max_attempts: int = 5, auth_lockout_minutes: int = 15, encryption_key: str | None = None) -> None:
self.config_path = Path(config_path)
self.auth_max_attempts = auth_max_attempts
self.auth_lockout_window = timedelta(minutes=auth_lockout_minutes)
self._fernet: Fernet | None = None
if encryption_key:
self._fernet = Fernet(_derive_fernet_key(encryption_key))
self.config_path.parent.mkdir(parents=True, exist_ok=True)
if not self.config_path.exists():
self._write_default()
@@ -125,7 +139,7 @@ class IamService:
self._secret_key_cache: Dict[str, Tuple[str, float]] = {}
self._cache_ttl = float(os.environ.get("IAM_CACHE_TTL_SECONDS", "5.0"))
self._last_stat_check = 0.0
self._stat_check_interval = 1.0
self._stat_check_interval = float(os.environ.get("IAM_STAT_CHECK_INTERVAL_SECONDS", "2.0"))
self._sessions: Dict[str, Dict[str, Any]] = {}
self._session_lock = threading.Lock()
self._load()
@@ -145,6 +159,19 @@ class IamService:
except OSError:
pass
def _check_expiry(self, access_key: str, record: Dict[str, Any]) -> None:
expires_at = record.get("expires_at")
if not expires_at:
return
try:
exp_dt = datetime.fromisoformat(expires_at)
if exp_dt.tzinfo is None:
exp_dt = exp_dt.replace(tzinfo=timezone.utc)
if datetime.now(timezone.utc) >= exp_dt:
raise IamError(f"Credentials for '{access_key}' have expired")
except (ValueError, TypeError):
pass
def authenticate(self, access_key: str, secret_key: str) -> Principal:
self._maybe_reload()
access_key = (access_key or "").strip()
@@ -161,6 +188,7 @@ class IamService:
if not record or not hmac.compare_digest(stored_secret, secret_key):
self._record_failed_attempt(access_key)
raise IamError("Invalid credentials")
self._check_expiry(access_key, record)
self._clear_failed_attempts(access_key)
return self._build_principal(access_key, record)
@@ -288,12 +316,16 @@ class IamService:
if cached:
principal, cached_time = cached
if now - cached_time < self._cache_ttl:
record = self._users.get(access_key)
if record:
self._check_expiry(access_key, record)
return principal
self._maybe_reload()
record = self._users.get(access_key)
if not record:
raise IamError("Unknown access key")
self._check_expiry(access_key, record)
principal = self._build_principal(access_key, record)
self._principal_cache[access_key] = (principal, now)
return principal
@@ -303,6 +335,7 @@ class IamService:
record = self._users.get(access_key)
if not record:
raise IamError("Unknown access key")
self._check_expiry(access_key, record)
return record["secret_key"]
def authorize(self, principal: Principal, bucket_name: str | None, action: str) -> None:
@@ -347,6 +380,7 @@ class IamService:
{
"access_key": access_key,
"display_name": record["display_name"],
"expires_at": record.get("expires_at"),
"policies": [
{"bucket": policy.bucket, "actions": sorted(policy.actions)}
for policy in record["policies"]
@@ -362,20 +396,25 @@ class IamService:
policies: Optional[Sequence[Dict[str, Any]]] = None,
access_key: str | None = None,
secret_key: str | None = None,
expires_at: str | None = None,
) -> Dict[str, str]:
access_key = (access_key or self._generate_access_key()).strip()
if not access_key:
raise IamError("Access key cannot be empty")
if access_key in self._users:
raise IamError("Access key already exists")
if expires_at:
self._validate_expires_at(expires_at)
secret_key = secret_key or self._generate_secret_key()
sanitized_policies = self._prepare_policy_payload(policies)
record = {
record: Dict[str, Any] = {
"access_key": access_key,
"secret_key": secret_key,
"display_name": display_name or access_key,
"policies": sanitized_policies,
}
if expires_at:
record["expires_at"] = expires_at
self._raw_config.setdefault("users", []).append(record)
self._save()
self._load()
@@ -414,17 +453,43 @@ class IamService:
clear_signing_key_cache()
self._load()
def update_user_expiry(self, access_key: str, expires_at: str | None) -> None:
user = self._get_raw_user(access_key)
if expires_at:
self._validate_expires_at(expires_at)
user["expires_at"] = expires_at
else:
user.pop("expires_at", None)
self._save()
self._principal_cache.pop(access_key, None)
self._secret_key_cache.pop(access_key, None)
self._load()
def update_user_policies(self, access_key: str, policies: Sequence[Dict[str, Any]]) -> None:
user = self._get_raw_user(access_key)
user["policies"] = self._prepare_policy_payload(policies)
self._save()
self._load()
def _decrypt_content(self, raw_bytes: bytes) -> str:
if raw_bytes.startswith(_IAM_ENCRYPTED_PREFIX):
if not self._fernet:
raise IamError("IAM config is encrypted but no encryption key provided. Set SECRET_KEY or use 'python run.py reset-cred'.")
try:
encrypted_data = raw_bytes[len(_IAM_ENCRYPTED_PREFIX):]
return self._fernet.decrypt(encrypted_data).decode("utf-8")
except InvalidToken:
raise IamError("Cannot decrypt IAM config. SECRET_KEY may have changed. Use 'python run.py reset-cred' to reset credentials.")
return raw_bytes.decode("utf-8")
def _load(self) -> None:
try:
self._last_load_time = self.config_path.stat().st_mtime
content = self.config_path.read_text(encoding='utf-8')
raw_bytes = self.config_path.read_bytes()
content = self._decrypt_content(raw_bytes)
raw = json.loads(content)
except IamError:
raise
except FileNotFoundError:
raise IamError(f"IAM config not found: {self.config_path}")
except json.JSONDecodeError as e:
@@ -434,33 +499,47 @@ class IamService:
except (OSError, ValueError) as e:
raise IamError(f"Failed to load IAM config: {e}")
was_plaintext = not raw_bytes.startswith(_IAM_ENCRYPTED_PREFIX)
users: Dict[str, Dict[str, Any]] = {}
for user in raw.get("users", []):
policies = self._build_policy_objects(user.get("policies", []))
users[user["access_key"]] = {
user_record: Dict[str, Any] = {
"secret_key": user["secret_key"],
"display_name": user.get("display_name", user["access_key"]),
"policies": policies,
}
if user.get("expires_at"):
user_record["expires_at"] = user["expires_at"]
users[user["access_key"]] = user_record
if not users:
raise IamError("IAM configuration contains no users")
self._users = users
self._raw_config = {
"users": [
{
raw_users: List[Dict[str, Any]] = []
for entry in raw.get("users", []):
raw_entry: Dict[str, Any] = {
"access_key": entry["access_key"],
"secret_key": entry["secret_key"],
"display_name": entry.get("display_name", entry["access_key"]),
"policies": entry.get("policies", []),
}
for entry in raw.get("users", [])
]
}
if entry.get("expires_at"):
raw_entry["expires_at"] = entry["expires_at"]
raw_users.append(raw_entry)
self._raw_config = {"users": raw_users}
if was_plaintext and self._fernet:
self._save()
def _save(self) -> None:
try:
json_text = json.dumps(self._raw_config, indent=2)
temp_path = self.config_path.with_suffix('.json.tmp')
temp_path.write_text(json.dumps(self._raw_config, indent=2), encoding='utf-8')
if self._fernet:
encrypted = self._fernet.encrypt(json_text.encode("utf-8"))
temp_path.write_bytes(_IAM_ENCRYPTED_PREFIX + encrypted)
else:
temp_path.write_text(json_text, encoding='utf-8')
temp_path.replace(self.config_path)
except (OSError, PermissionError) as e:
raise IamError(f"Cannot save IAM config: {e}")
@@ -475,9 +554,14 @@ class IamService:
def export_config(self, mask_secrets: bool = True) -> Dict[str, Any]:
payload: Dict[str, Any] = {"users": []}
for user in self._raw_config.get("users", []):
record = dict(user)
if mask_secrets and "secret_key" in record:
record["secret_key"] = "••••••••••"
record: Dict[str, Any] = {
"access_key": user["access_key"],
"secret_key": "••••••••••" if mask_secrets else user["secret_key"],
"display_name": user["display_name"],
"policies": user["policies"],
}
if user.get("expires_at"):
record["expires_at"] = user["expires_at"]
payload["users"].append(record)
return payload
@@ -546,8 +630,9 @@ class IamService:
return candidate if candidate in ALLOWED_ACTIONS else ""
def _write_default(self) -> None:
access_key = secrets.token_hex(12)
secret_key = secrets.token_urlsafe(32)
access_key = os.environ.get("ADMIN_ACCESS_KEY", "").strip() or secrets.token_hex(12)
secret_key = os.environ.get("ADMIN_SECRET_KEY", "").strip() or secrets.token_urlsafe(32)
custom_keys = bool(os.environ.get("ADMIN_ACCESS_KEY", "").strip())
default = {
"users": [
{
@@ -560,16 +645,37 @@ class IamService:
}
]
}
self.config_path.write_text(json.dumps(default, indent=2))
json_text = json.dumps(default, indent=2)
if self._fernet:
encrypted = self._fernet.encrypt(json_text.encode("utf-8"))
self.config_path.write_bytes(_IAM_ENCRYPTED_PREFIX + encrypted)
else:
self.config_path.write_text(json_text)
print(f"\n{'='*60}")
print("MYFSIO FIRST RUN - ADMIN CREDENTIALS GENERATED")
print("MYFSIO FIRST RUN - ADMIN CREDENTIALS")
print(f"{'='*60}")
if custom_keys:
print(f"Access Key: {access_key} (from ADMIN_ACCESS_KEY)")
print(f"Secret Key: {'(from ADMIN_SECRET_KEY)' if os.environ.get('ADMIN_SECRET_KEY', '').strip() else secret_key}")
else:
print(f"Access Key: {access_key}")
print(f"Secret Key: {secret_key}")
print(f"{'='*60}")
if self._fernet:
print("IAM config is encrypted at rest.")
print("Lost credentials? Run: python run.py reset-cred")
else:
print(f"Missed this? Check: {self.config_path}")
print(f"{'='*60}\n")
def _validate_expires_at(self, expires_at: str) -> None:
try:
dt = datetime.fromisoformat(expires_at)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
except (ValueError, TypeError):
raise IamError(f"Invalid expires_at format: {expires_at}. Use ISO 8601 (e.g. 2026-12-31T23:59:59Z)")
def _generate_access_key(self) -> str:
return secrets.token_hex(8)
@@ -588,11 +694,15 @@ class IamService:
if cached:
secret_key, cached_time = cached
if now - cached_time < self._cache_ttl:
record = self._users.get(access_key)
if record:
self._check_expiry(access_key, record)
return secret_key
self._maybe_reload()
record = self._users.get(access_key)
if record:
self._check_expiry(access_key, record)
secret_key = record["secret_key"]
self._secret_key_cache[access_key] = (secret_key, now)
return secret_key
@@ -604,11 +714,15 @@ class IamService:
if cached:
principal, cached_time = cached
if now - cached_time < self._cache_ttl:
record = self._users.get(access_key)
if record:
self._check_expiry(access_key, record)
return principal
self._maybe_reload()
record = self._users.get(access_key)
if record:
self._check_expiry(access_key, record)
principal = self._build_principal(access_key, record)
self._principal_cache[access_key] = (principal, now)
return principal

View File

@@ -5,6 +5,7 @@ import logging
import random
import threading
import time
from collections import defaultdict
from dataclasses import dataclass, field
from datetime import datetime, timezone
from pathlib import Path
@@ -138,8 +139,8 @@ class OperationMetricsCollector:
self.interval_seconds = interval_minutes * 60
self.retention_hours = retention_hours
self._lock = threading.Lock()
self._by_method: Dict[str, OperationStats] = {}
self._by_endpoint: Dict[str, OperationStats] = {}
self._by_method: Dict[str, OperationStats] = defaultdict(OperationStats)
self._by_endpoint: Dict[str, OperationStats] = defaultdict(OperationStats)
self._by_status_class: Dict[str, int] = {}
self._error_codes: Dict[str, int] = {}
self._totals = OperationStats()
@@ -211,8 +212,8 @@ class OperationMetricsCollector:
self._prune_old_snapshots()
self._save_history()
self._by_method.clear()
self._by_endpoint.clear()
self._by_method = defaultdict(OperationStats)
self._by_endpoint = defaultdict(OperationStats)
self._by_status_class.clear()
self._error_codes.clear()
self._totals = OperationStats()
@@ -232,12 +233,7 @@ class OperationMetricsCollector:
status_class = f"{status_code // 100}xx"
with self._lock:
if method not in self._by_method:
self._by_method[method] = OperationStats()
self._by_method[method].record(latency_ms, success, bytes_in, bytes_out)
if endpoint_type not in self._by_endpoint:
self._by_endpoint[endpoint_type] = OperationStats()
self._by_endpoint[endpoint_type].record(latency_ms, success, bytes_in, bytes_out)
self._by_status_class[status_class] = self._by_status_class.get(status_class, 0) + 1

View File

@@ -85,6 +85,9 @@ def _bucket_policies() -> BucketPolicyStore:
def _build_policy_context() -> Dict[str, Any]:
cached = getattr(g, "_policy_context", None)
if cached is not None:
return cached
ctx: Dict[str, Any] = {}
if request.headers.get("Referer"):
ctx["aws:Referer"] = request.headers.get("Referer")
@@ -98,6 +101,7 @@ def _build_policy_context() -> Dict[str, Any]:
ctx["aws:SecureTransport"] = str(request.is_secure).lower()
if request.headers.get("User-Agent"):
ctx["aws:UserAgent"] = request.headers.get("User-Agent")
g._policy_context = ctx
return ctx
@@ -1021,11 +1025,15 @@ def _apply_object_headers(
file_stat,
metadata: Dict[str, str] | None,
etag: str,
size_override: int | None = None,
mtime_override: float | None = None,
) -> None:
if file_stat is not None:
if response.status_code != 206:
response.headers["Content-Length"] = str(file_stat.st_size)
response.headers["Last-Modified"] = http_date(file_stat.st_mtime)
effective_size = size_override if size_override is not None else (file_stat.st_size if file_stat is not None else None)
effective_mtime = mtime_override if mtime_override is not None else (file_stat.st_mtime if file_stat is not None else None)
if effective_size is not None and response.status_code != 206:
response.headers["Content-Length"] = str(effective_size)
if effective_mtime is not None:
response.headers["Last-Modified"] = http_date(effective_mtime)
response.headers["ETag"] = f'"{etag}"'
response.headers["Accept-Ranges"] = "bytes"
for key, value in (metadata or {}).items():
@@ -2820,6 +2828,8 @@ def object_handler(bucket_name: str, object_key: str):
if validation_error:
return _error_response("InvalidArgument", validation_error, 400)
metadata["__content_type__"] = content_type or mimetypes.guess_type(object_key)[0] or "application/octet-stream"
try:
meta = storage.put_object(
bucket_name,
@@ -2834,6 +2844,19 @@ def object_handler(bucket_name: str, object_key: str):
if "Bucket" in message:
return _error_response("NoSuchBucket", message, 404)
return _error_response("InvalidArgument", message, 400)
content_md5 = request.headers.get("Content-MD5")
if content_md5 and meta.etag:
try:
expected_md5 = base64.b64decode(content_md5).hex()
except Exception:
storage.delete_object(bucket_name, object_key)
return _error_response("InvalidDigest", "Content-MD5 header is not valid base64", 400)
if expected_md5 != meta.etag:
storage.delete_object(bucket_name, object_key)
return _error_response("BadDigest", "The Content-MD5 you specified did not match what we received", 400)
if current_app.logger.isEnabledFor(logging.INFO):
current_app.logger.info(
"Object uploaded",
extra={"bucket": bucket_name, "key": object_key, "size": meta.size},
@@ -2871,7 +2894,7 @@ def object_handler(bucket_name: str, object_key: str):
except StorageError as exc:
return _error_response("NoSuchKey", str(exc), 404)
metadata = storage.get_object_metadata(bucket_name, object_key)
mimetype = mimetypes.guess_type(object_key)[0] or "application/octet-stream"
mimetype = metadata.get("__content_type__") or mimetypes.guess_type(object_key)[0] or "application/octet-stream"
is_encrypted = "x-amz-server-side-encryption" in metadata
@@ -2963,10 +2986,7 @@ def object_handler(bucket_name: str, object_key: str):
response.headers["Content-Type"] = mimetype
logged_bytes = 0
try:
file_stat = path.stat() if not is_encrypted else None
except (PermissionError, OSError):
file_stat = None
file_stat = stat if not is_encrypted else None
_apply_object_headers(response, file_stat=file_stat, metadata=metadata, etag=etag)
if request.method == "GET":
@@ -2983,6 +3003,7 @@ def object_handler(bucket_name: str, object_key: str):
if value:
response.headers[header] = _sanitize_header_value(value)
if current_app.logger.isEnabledFor(logging.INFO):
action = "Object read" if request.method == "GET" else "Object head"
current_app.logger.info(action, extra={"bucket": bucket_name, "key": object_key, "bytes": logged_bytes})
return response
@@ -3002,6 +3023,7 @@ def object_handler(bucket_name: str, object_key: str):
storage.delete_object(bucket_name, object_key)
lock_service.delete_object_lock_metadata(bucket_name, object_key)
if current_app.logger.isEnabledFor(logging.INFO):
current_app.logger.info("Object deleted", extra={"bucket": bucket_name, "key": object_key})
principal, _ = _require_principal()
@@ -3343,12 +3365,20 @@ def head_object(bucket_name: str, object_key: str) -> Response:
_authorize_action(principal, bucket_name, "read", object_key=object_key)
path = _storage().get_object_path(bucket_name, object_key)
metadata = _storage().get_object_metadata(bucket_name, object_key)
stat = path.stat()
etag = metadata.get("__etag__") or _storage()._compute_etag(path)
cached_size = metadata.get("__size__")
cached_mtime = metadata.get("__last_modified__")
if cached_size is not None and cached_mtime is not None:
size_val = int(cached_size)
mtime_val = float(cached_mtime)
response = Response(status=200)
_apply_object_headers(response, file_stat=None, metadata=metadata, etag=etag, size_override=size_val, mtime_override=mtime_val)
else:
stat = path.stat()
response = Response(status=200)
_apply_object_headers(response, file_stat=stat, metadata=metadata, etag=etag)
response.headers["Content-Type"] = mimetypes.guess_type(object_key)[0] or "application/octet-stream"
response.headers["Content-Type"] = metadata.get("__content_type__") or mimetypes.guess_type(object_key)[0] or "application/octet-stream"
return response
except (StorageError, FileNotFoundError):
return _error_response("NoSuchKey", "Object not found", 404)
@@ -3578,6 +3608,8 @@ def _initiate_multipart_upload(bucket_name: str, object_key: str) -> Response:
return error
metadata = _extract_request_metadata()
content_type = request.headers.get("Content-Type")
metadata["__content_type__"] = content_type or mimetypes.guess_type(object_key)[0] or "application/octet-stream"
try:
upload_id = _storage().initiate_multipart_upload(
bucket_name,
@@ -3630,6 +3662,15 @@ def _upload_part(bucket_name: str, object_key: str) -> Response:
return _error_response("NoSuchUpload", str(exc), 404)
return _error_response("InvalidArgument", str(exc), 400)
content_md5 = request.headers.get("Content-MD5")
if content_md5 and etag:
try:
expected_md5 = base64.b64decode(content_md5).hex()
except Exception:
return _error_response("InvalidDigest", "Content-MD5 header is not valid base64", 400)
if expected_md5 != etag:
return _error_response("BadDigest", "The Content-MD5 you specified did not match what we received", 400)
response = Response(status=200)
response.headers["ETag"] = f'"{etag}"'
return response

View File

@@ -1,6 +1,5 @@
from __future__ import annotations
import copy
import hashlib
import json
import os
@@ -196,7 +195,9 @@ class ObjectStorage:
self.root.mkdir(parents=True, exist_ok=True)
self._ensure_system_roots()
self._object_cache: OrderedDict[str, tuple[Dict[str, ObjectMeta], float, float]] = OrderedDict()
self._cache_lock = threading.Lock()
self._obj_cache_lock = threading.Lock()
self._meta_cache_lock = threading.Lock()
self._registry_lock = threading.Lock()
self._bucket_locks: Dict[str, threading.Lock] = {}
self._cache_version: Dict[str, int] = {}
self._bucket_config_cache: Dict[str, tuple[dict[str, Any], float]] = {}
@@ -209,10 +210,17 @@ class ObjectStorage:
self._meta_read_cache: OrderedDict[tuple, Optional[Dict[str, Any]]] = OrderedDict()
self._meta_read_cache_max = 2048
self._cleanup_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="ParentCleanup")
self._stats_mem: Dict[str, Dict[str, int]] = {}
self._stats_serial: Dict[str, int] = {}
self._stats_mem_time: Dict[str, float] = {}
self._stats_lock = threading.Lock()
self._stats_dirty: set[str] = set()
self._stats_flush_timer: Optional[threading.Timer] = None
self._etag_index_dirty: set[str] = set()
self._etag_index_flush_timer: Optional[threading.Timer] = None
def _get_bucket_lock(self, bucket_id: str) -> threading.Lock:
"""Get or create a lock for a specific bucket. Reduces global lock contention."""
with self._cache_lock:
with self._registry_lock:
if bucket_id not in self._bucket_locks:
self._bucket_locks[bucket_id] = threading.Lock()
return self._bucket_locks[bucket_id]
@@ -260,26 +268,24 @@ class ObjectStorage:
self._system_bucket_root(bucket_path.name).mkdir(parents=True, exist_ok=True)
def bucket_stats(self, bucket_name: str, cache_ttl: int = 60) -> dict[str, int]:
"""Return object count and total size for the bucket (cached).
Args:
bucket_name: Name of the bucket
cache_ttl: Cache time-to-live in seconds (default 60)
"""
bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist")
with self._stats_lock:
if bucket_name in self._stats_mem:
cached_at = self._stats_mem_time.get(bucket_name, 0.0)
if (time.monotonic() - cached_at) < cache_ttl:
return dict(self._stats_mem[bucket_name])
self._stats_mem.pop(bucket_name, None)
self._stats_mem_time.pop(bucket_name, None)
cache_path = self._system_bucket_root(bucket_name) / "stats.json"
cached_stats = None
cache_fresh = False
if cache_path.exists():
try:
cache_fresh = time.time() - cache_path.stat().st_mtime < cache_ttl
cached_stats = json.loads(cache_path.read_text(encoding="utf-8"))
if cache_fresh:
return cached_stats
except (OSError, json.JSONDecodeError):
pass
@@ -348,16 +354,25 @@ class ObjectStorage:
"_cache_serial": existing_serial,
}
with self._stats_lock:
self._stats_mem[bucket_name] = stats
self._stats_mem_time[bucket_name] = time.monotonic()
self._stats_serial[bucket_name] = existing_serial
try:
cache_path.parent.mkdir(parents=True, exist_ok=True)
cache_path.write_text(json.dumps(stats), encoding="utf-8")
self._atomic_write_json(cache_path, stats)
except OSError:
pass
return stats
def _invalidate_bucket_stats_cache(self, bucket_id: str) -> None:
"""Invalidate the cached bucket statistics."""
with self._stats_lock:
self._stats_mem.pop(bucket_id, None)
self._stats_mem_time.pop(bucket_id, None)
self._stats_serial[bucket_id] = self._stats_serial.get(bucket_id, 0) + 1
self._stats_dirty.discard(bucket_id)
cache_path = self._system_bucket_root(bucket_id) / "stats.json"
try:
cache_path.unlink(missing_ok=True)
@@ -373,30 +388,53 @@ class ObjectStorage:
version_bytes_delta: int = 0,
version_count_delta: int = 0,
) -> None:
"""Incrementally update cached bucket statistics instead of invalidating.
with self._stats_lock:
if bucket_id not in self._stats_mem:
self._stats_mem[bucket_id] = {
"objects": 0, "bytes": 0, "version_count": 0,
"version_bytes": 0, "total_objects": 0, "total_bytes": 0,
"_cache_serial": 0,
}
data = self._stats_mem[bucket_id]
data["objects"] = max(0, data["objects"] + objects_delta)
data["bytes"] = max(0, data["bytes"] + bytes_delta)
data["version_count"] = max(0, data["version_count"] + version_count_delta)
data["version_bytes"] = max(0, data["version_bytes"] + version_bytes_delta)
data["total_objects"] = max(0, data["total_objects"] + objects_delta + version_count_delta)
data["total_bytes"] = max(0, data["total_bytes"] + bytes_delta + version_bytes_delta)
data["_cache_serial"] = data["_cache_serial"] + 1
self._stats_serial[bucket_id] = self._stats_serial.get(bucket_id, 0) + 1
self._stats_mem_time[bucket_id] = time.monotonic()
self._stats_dirty.add(bucket_id)
self._schedule_stats_flush()
This avoids expensive full directory scans on every PUT/DELETE by
adjusting the cached values directly. Also signals cross-process cache
invalidation by incrementing _cache_serial.
"""
def _schedule_stats_flush(self) -> None:
if self._stats_flush_timer is None or not self._stats_flush_timer.is_alive():
self._stats_flush_timer = threading.Timer(3.0, self._flush_stats)
self._stats_flush_timer.daemon = True
self._stats_flush_timer.start()
def _flush_stats(self) -> None:
with self._stats_lock:
dirty = list(self._stats_dirty)
self._stats_dirty.clear()
snapshots = {b: dict(self._stats_mem[b]) for b in dirty if b in self._stats_mem}
for bucket_id, data in snapshots.items():
cache_path = self._system_bucket_root(bucket_id) / "stats.json"
try:
cache_path.parent.mkdir(parents=True, exist_ok=True)
if cache_path.exists():
data = json.loads(cache_path.read_text(encoding="utf-8"))
else:
data = {"objects": 0, "bytes": 0, "version_count": 0, "version_bytes": 0, "total_objects": 0, "total_bytes": 0, "_cache_serial": 0}
data["objects"] = max(0, data.get("objects", 0) + objects_delta)
data["bytes"] = max(0, data.get("bytes", 0) + bytes_delta)
data["version_count"] = max(0, data.get("version_count", 0) + version_count_delta)
data["version_bytes"] = max(0, data.get("version_bytes", 0) + version_bytes_delta)
data["total_objects"] = max(0, data.get("total_objects", 0) + objects_delta + version_count_delta)
data["total_bytes"] = max(0, data.get("total_bytes", 0) + bytes_delta + version_bytes_delta)
data["_cache_serial"] = data.get("_cache_serial", 0) + 1
cache_path.write_text(json.dumps(data), encoding="utf-8")
except (OSError, json.JSONDecodeError):
self._atomic_write_json(cache_path, data)
except OSError:
pass
def shutdown_stats(self) -> None:
if self._stats_flush_timer is not None:
self._stats_flush_timer.cancel()
self._flush_stats()
if self._etag_index_flush_timer is not None:
self._etag_index_flush_timer.cancel()
self._flush_etag_indexes()
def delete_bucket(self, bucket_name: str) -> None:
bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists():
@@ -413,13 +451,20 @@ class ObjectStorage:
self._remove_tree(self._system_bucket_root(bucket_id))
self._remove_tree(self._multipart_bucket_root(bucket_id))
self._bucket_config_cache.pop(bucket_id, None)
with self._cache_lock:
with self._obj_cache_lock:
self._object_cache.pop(bucket_id, None)
self._cache_version.pop(bucket_id, None)
self._sorted_key_cache.pop(bucket_id, None)
with self._meta_cache_lock:
stale = [k for k in self._meta_read_cache if k[0] == bucket_id]
for k in stale:
del self._meta_read_cache[k]
with self._stats_lock:
self._stats_mem.pop(bucket_id, None)
self._stats_mem_time.pop(bucket_id, None)
self._stats_serial.pop(bucket_id, None)
self._stats_dirty.discard(bucket_id)
self._etag_index_dirty.discard(bucket_id)
def list_objects(
self,
@@ -834,18 +879,47 @@ class ObjectStorage:
is_overwrite = destination.exists()
existing_size = destination.stat().st_size if is_overwrite else 0
archived_version_size = 0
if self._is_versioning_enabled(bucket_path) and is_overwrite:
archived_version_size = existing_size
self._archive_current_version(bucket_id, safe_key, reason="overwrite")
tmp_dir = self._system_root_path() / self.SYSTEM_TMP_DIR
tmp_dir.mkdir(parents=True, exist_ok=True)
tmp_path = tmp_dir / f"{uuid.uuid4().hex}.tmp"
if _HAS_RUST:
tmp_path = None
try:
tmp_path_str, etag, new_size = _rc.stream_to_file_with_md5(
stream, str(tmp_dir)
)
tmp_path = Path(tmp_path_str)
size_delta = new_size - existing_size
object_delta = 0 if is_overwrite else 1
if enforce_quota:
quota_check = self.check_quota(
bucket_name,
additional_bytes=max(0, size_delta),
additional_objects=object_delta,
)
if not quota_check["allowed"]:
raise QuotaExceededError(
quota_check["message"] or "Quota exceeded",
quota_check["quota"],
quota_check["usage"],
)
except BaseException:
if tmp_path:
try:
tmp_path.unlink(missing_ok=True)
except OSError:
pass
raise
else:
tmp_path = tmp_dir / f"{uuid.uuid4().hex}.tmp"
try:
checksum = hashlib.md5()
with tmp_path.open("wb") as target:
shutil.copyfileobj(stream, target)
shutil.copyfileobj(_HashingReader(stream, checksum), target)
target.flush()
os.fsync(target.fileno())
new_size = tmp_path.stat().st_size
size_delta = new_size - existing_size
@@ -864,31 +938,43 @@ class ObjectStorage:
quota_check["usage"],
)
if _HAS_RUST:
etag = _rc.md5_file(str(tmp_path))
else:
checksum = hashlib.md5()
with tmp_path.open("rb") as f:
while True:
chunk = f.read(1048576)
if not chunk:
break
checksum.update(chunk)
etag = checksum.hexdigest()
shutil.move(str(tmp_path), str(destination))
finally:
except BaseException:
try:
tmp_path.unlink(missing_ok=True)
except OSError:
pass
raise
lock_file_path = self._system_bucket_root(bucket_id) / "locks" / f"{safe_key.as_posix().replace('/', '_')}.lock"
try:
with _atomic_lock_file(lock_file_path):
archived_version_size = 0
if self._is_versioning_enabled(bucket_path) and is_overwrite:
archived_version_size = existing_size
self._archive_current_version(bucket_id, safe_key, reason="overwrite")
shutil.move(str(tmp_path), str(destination))
tmp_path = None
stat = destination.stat()
internal_meta = {"__etag__": etag, "__size__": str(stat.st_size)}
internal_meta = {"__etag__": etag, "__size__": str(stat.st_size), "__last_modified__": str(stat.st_mtime)}
combined_meta = {**internal_meta, **(metadata or {})}
self._write_metadata(bucket_id, safe_key, combined_meta)
except BlockingIOError:
try:
if tmp_path:
tmp_path.unlink(missing_ok=True)
except OSError:
pass
raise StorageError("Another upload to this key is in progress")
finally:
if tmp_path:
try:
tmp_path.unlink(missing_ok=True)
except OSError:
pass
self._update_bucket_stats_cache(
bucket_id,
@@ -1480,18 +1566,16 @@ class ObjectStorage:
temp_path = upload_root / f".{part_filename}.tmp"
try:
if _HAS_RUST:
with temp_path.open("wb") as target:
shutil.copyfileobj(stream, target)
if _HAS_RUST:
part_etag = _rc.md5_file(str(temp_path))
else:
checksum = hashlib.md5()
with temp_path.open("rb") as f:
while True:
chunk = f.read(1048576)
if not chunk:
break
checksum.update(chunk)
with temp_path.open("wb") as target:
shutil.copyfileobj(_HashingReader(stream, checksum), target)
target.flush()
os.fsync(target.fileno())
part_etag = checksum.hexdigest()
temp_path.replace(part_path)
except OSError:
@@ -1525,7 +1609,7 @@ class ObjectStorage:
parts = manifest.setdefault("parts", {})
parts[str(part_number)] = record
manifest_path.write_text(json.dumps(manifest), encoding="utf-8")
self._atomic_write_json(manifest_path, manifest)
break
except OSError as exc:
if attempt < max_retries - 1:
@@ -1618,7 +1702,7 @@ class ObjectStorage:
parts = manifest.setdefault("parts", {})
parts[str(part_number)] = record
manifest_path.write_text(json.dumps(manifest), encoding="utf-8")
self._atomic_write_json(manifest_path, manifest)
break
except OSError as exc:
if attempt < max_retries - 1:
@@ -1702,6 +1786,15 @@ class ObjectStorage:
if versioning_enabled and destination.exists():
archived_version_size = destination.stat().st_size
self._archive_current_version(bucket_id, safe_key, reason="overwrite")
if _HAS_RUST:
part_paths = []
for _, record in validated:
pp = upload_root / record["filename"]
if not pp.exists():
raise StorageError(f"Missing part file {record['filename']}")
part_paths.append(str(pp))
checksum_hex = _rc.assemble_parts_with_md5(part_paths, str(destination))
else:
checksum = hashlib.md5()
with destination.open("wb") as target:
for _, record in validated:
@@ -1715,6 +1808,9 @@ class ObjectStorage:
break
checksum.update(data)
target.write(data)
target.flush()
os.fsync(target.fileno())
checksum_hex = checksum.hexdigest()
except BlockingIOError:
raise StorageError("Another upload to this key is in progress")
@@ -1729,10 +1825,10 @@ class ObjectStorage:
)
stat = destination.stat()
etag = checksum.hexdigest()
etag = checksum_hex
metadata = manifest.get("metadata")
internal_meta = {"__etag__": etag, "__size__": str(stat.st_size)}
internal_meta = {"__etag__": etag, "__size__": str(stat.st_size), "__last_modified__": str(stat.st_mtime)}
combined_meta = {**internal_meta, **(metadata or {})}
self._write_metadata(bucket_id, safe_key, combined_meta)
@@ -2093,19 +2189,19 @@ class ObjectStorage:
now = time.time()
current_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock:
with self._obj_cache_lock:
cached = self._object_cache.get(bucket_id)
if cached:
objects, timestamp, cached_stats_mtime = cached
if now - timestamp < self._cache_ttl and current_stats_mtime == cached_stats_mtime:
self._object_cache.move_to_end(bucket_id)
return objects
cache_version = self._cache_version.get(bucket_id, 0)
bucket_lock = self._get_bucket_lock(bucket_id)
with bucket_lock:
now = time.time()
current_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock:
with self._obj_cache_lock:
cached = self._object_cache.get(bucket_id)
if cached:
objects, timestamp, cached_stats_mtime = cached
@@ -2116,31 +2212,23 @@ class ObjectStorage:
objects = self._build_object_cache(bucket_path)
new_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock:
current_version = self._cache_version.get(bucket_id, 0)
if current_version != cache_version:
objects = self._build_object_cache(bucket_path)
new_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._obj_cache_lock:
while len(self._object_cache) >= self._object_cache_max_size:
self._object_cache.popitem(last=False)
self._object_cache[bucket_id] = (objects, time.time(), new_stats_mtime)
self._object_cache.move_to_end(bucket_id)
self._cache_version[bucket_id] = current_version + 1
self._cache_version[bucket_id] = self._cache_version.get(bucket_id, 0) + 1
self._sorted_key_cache.pop(bucket_id, None)
return objects
def _invalidate_object_cache(self, bucket_id: str) -> None:
"""Invalidate the object cache and etag index for a bucket.
Increments version counter to signal stale reads.
Cross-process invalidation is handled by checking stats.json mtime.
"""
with self._cache_lock:
with self._obj_cache_lock:
self._object_cache.pop(bucket_id, None)
self._cache_version[bucket_id] = self._cache_version.get(bucket_id, 0) + 1
self._etag_index_dirty.discard(bucket_id)
etag_index_path = self._system_bucket_root(bucket_id) / "etag_index.json"
try:
etag_index_path.unlink(missing_ok=True)
@@ -2148,22 +2236,10 @@ class ObjectStorage:
pass
def _get_cache_marker_mtime(self, bucket_id: str) -> float:
"""Get a cache marker combining serial and object count for cross-process invalidation.
Returns a combined value that changes if either _cache_serial or object count changes.
This handles cases where the serial was reset but object count differs.
"""
stats_path = self._system_bucket_root(bucket_id) / "stats.json"
try:
data = json.loads(stats_path.read_text(encoding="utf-8"))
serial = data.get("_cache_serial", 0)
count = data.get("objects", 0)
return float(serial * 1000000 + count)
except (OSError, json.JSONDecodeError):
return 0
return float(self._stats_serial.get(bucket_id, 0))
def _update_object_cache_entry(self, bucket_id: str, key: str, meta: Optional[ObjectMeta]) -> None:
with self._cache_lock:
with self._obj_cache_lock:
cached = self._object_cache.get(bucket_id)
if cached:
objects, timestamp, stats_mtime = cached
@@ -2174,22 +2250,31 @@ class ObjectStorage:
self._cache_version[bucket_id] = self._cache_version.get(bucket_id, 0) + 1
self._sorted_key_cache.pop(bucket_id, None)
self._update_etag_index(bucket_id, key, meta.etag if meta else None)
self._etag_index_dirty.add(bucket_id)
self._schedule_etag_index_flush()
def _update_etag_index(self, bucket_id: str, key: str, etag: Optional[str]) -> None:
def _schedule_etag_index_flush(self) -> None:
if self._etag_index_flush_timer is None or not self._etag_index_flush_timer.is_alive():
self._etag_index_flush_timer = threading.Timer(5.0, self._flush_etag_indexes)
self._etag_index_flush_timer.daemon = True
self._etag_index_flush_timer.start()
def _flush_etag_indexes(self) -> None:
dirty = set(self._etag_index_dirty)
self._etag_index_dirty.clear()
for bucket_id in dirty:
with self._obj_cache_lock:
cached = self._object_cache.get(bucket_id)
if not cached:
continue
objects = cached[0]
index = {k: v.etag for k, v in objects.items() if v.etag}
etag_index_path = self._system_bucket_root(bucket_id) / "etag_index.json"
if not etag_index_path.exists():
return
try:
with open(etag_index_path, 'r', encoding='utf-8') as f:
index = json.load(f)
if etag is None:
index.pop(key, None)
else:
index[key] = etag
etag_index_path.parent.mkdir(parents=True, exist_ok=True)
with open(etag_index_path, 'w', encoding='utf-8') as f:
json.dump(index, f)
except (OSError, json.JSONDecodeError):
except OSError:
pass
def warm_cache(self, bucket_names: Optional[List[str]] = None) -> None:
@@ -2231,6 +2316,23 @@ class ObjectStorage:
):
path.mkdir(parents=True, exist_ok=True)
@staticmethod
def _atomic_write_json(path: Path, data: Any) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
tmp_path = path.with_suffix(".tmp")
try:
with tmp_path.open("w", encoding="utf-8") as f:
json.dump(data, f)
f.flush()
os.fsync(f.fileno())
tmp_path.replace(path)
except BaseException:
try:
tmp_path.unlink(missing_ok=True)
except OSError:
pass
raise
def _multipart_dir(self, bucket_name: str, upload_id: str) -> Path:
return self._multipart_bucket_root(bucket_name) / upload_id
@@ -2247,11 +2349,6 @@ class ObjectStorage:
if cached:
config, cached_time, cached_mtime = cached
if now - cached_time < self._bucket_config_cache_ttl:
try:
current_mtime = config_path.stat().st_mtime if config_path.exists() else 0.0
except OSError:
current_mtime = 0.0
if current_mtime == cached_mtime:
return config.copy()
if not config_path.exists():
@@ -2270,7 +2367,7 @@ class ObjectStorage:
def _write_bucket_config(self, bucket_name: str, payload: dict[str, Any]) -> None:
config_path = self._bucket_config_path(bucket_name)
config_path.parent.mkdir(parents=True, exist_ok=True)
config_path.write_text(json.dumps(payload), encoding="utf-8")
self._atomic_write_json(config_path, payload)
try:
mtime = config_path.stat().st_mtime
except OSError:
@@ -2304,8 +2401,7 @@ class ObjectStorage:
def _write_multipart_manifest(self, upload_root: Path, manifest: dict[str, Any]) -> None:
manifest_path = upload_root / self.MULTIPART_MANIFEST
manifest_path.parent.mkdir(parents=True, exist_ok=True)
manifest_path.write_text(json.dumps(manifest), encoding="utf-8")
self._atomic_write_json(manifest_path, manifest)
def _metadata_file(self, bucket_name: str, key: Path) -> Path:
meta_root = self._bucket_meta_root(bucket_name)
@@ -2321,19 +2417,19 @@ class ObjectStorage:
return meta_root / parent / "_index.json", entry_name
def _get_meta_index_lock(self, index_path: str) -> threading.Lock:
with self._cache_lock:
with self._registry_lock:
if index_path not in self._meta_index_locks:
self._meta_index_locks[index_path] = threading.Lock()
return self._meta_index_locks[index_path]
def _read_index_entry(self, bucket_name: str, key: Path) -> Optional[Dict[str, Any]]:
cache_key = (bucket_name, str(key))
with self._cache_lock:
with self._meta_cache_lock:
hit = self._meta_read_cache.get(cache_key)
if hit is not None:
self._meta_read_cache.move_to_end(cache_key)
cached = hit[0]
return copy.deepcopy(cached) if cached is not None else None
return dict(cached) if cached is not None else None
index_path, entry_name = self._index_file_for_key(bucket_name, key)
if _HAS_RUST:
@@ -2348,16 +2444,16 @@ class ObjectStorage:
except (OSError, json.JSONDecodeError):
result = None
with self._cache_lock:
with self._meta_cache_lock:
while len(self._meta_read_cache) >= self._meta_read_cache_max:
self._meta_read_cache.popitem(last=False)
self._meta_read_cache[cache_key] = (copy.deepcopy(result) if result is not None else None,)
self._meta_read_cache[cache_key] = (dict(result) if result is not None else None,)
return result
def _invalidate_meta_read_cache(self, bucket_name: str, key: Path) -> None:
cache_key = (bucket_name, str(key))
with self._cache_lock:
with self._meta_cache_lock:
self._meta_read_cache.pop(cache_key, None)
def _write_index_entry(self, bucket_name: str, key: Path, entry: Dict[str, Any]) -> None:
@@ -2375,7 +2471,7 @@ class ObjectStorage:
except (OSError, json.JSONDecodeError):
pass
index_data[entry_name] = entry
index_path.write_text(json.dumps(index_data), encoding="utf-8")
self._atomic_write_json(index_path, index_data)
self._invalidate_meta_read_cache(bucket_name, key)
def _delete_index_entry(self, bucket_name: str, key: Path) -> None:
@@ -2396,7 +2492,7 @@ class ObjectStorage:
if entry_name in index_data:
del index_data[entry_name]
if index_data:
index_path.write_text(json.dumps(index_data), encoding="utf-8")
self._atomic_write_json(index_path, index_data)
else:
try:
index_path.unlink()
@@ -2445,7 +2541,7 @@ class ObjectStorage:
"reason": reason,
}
manifest_path = version_dir / f"{version_id}.json"
manifest_path.write_text(json.dumps(record), encoding="utf-8")
self._atomic_write_json(manifest_path, record)
def _read_metadata(self, bucket_name: str, key: Path) -> Dict[str, str]:
entry = self._read_index_entry(bucket_name, key)

View File

@@ -1754,6 +1754,10 @@ def iam_dashboard():
users = iam_service.list_users() if not locked else []
config_summary = iam_service.config_summary()
config_document = json.dumps(iam_service.export_config(mask_secrets=True), indent=2)
from datetime import datetime as _dt, timedelta as _td, timezone as _tz
_now = _dt.now(_tz.utc)
now_iso = _now.isoformat()
soon_iso = (_now + _td(days=7)).isoformat()
return render_template(
"iam.html",
users=users,
@@ -1763,6 +1767,8 @@ def iam_dashboard():
config_summary=config_summary,
config_document=config_document,
disclosed_secret=disclosed_secret,
now_iso=now_iso,
soon_iso=soon_iso,
)
@@ -1782,6 +1788,8 @@ def create_iam_user():
return jsonify({"error": "Display name must be 64 characters or fewer"}), 400
flash("Display name must be 64 characters or fewer", "danger")
return redirect(url_for("ui.iam_dashboard"))
custom_access_key = request.form.get("access_key", "").strip() or None
custom_secret_key = request.form.get("secret_key", "").strip() or None
policies_text = request.form.get("policies", "").strip()
policies = None
if policies_text:
@@ -1792,8 +1800,21 @@ def create_iam_user():
return jsonify({"error": f"Invalid JSON: {exc}"}), 400
flash(f"Invalid JSON: {exc}", "danger")
return redirect(url_for("ui.iam_dashboard"))
expires_at = request.form.get("expires_at", "").strip() or None
if expires_at:
try:
created = _iam().create_user(display_name=display_name, policies=policies)
from datetime import datetime as _dt, timezone as _tz
exp_dt = _dt.fromisoformat(expires_at)
if exp_dt.tzinfo is None:
exp_dt = exp_dt.replace(tzinfo=_tz.utc)
expires_at = exp_dt.isoformat()
except (ValueError, TypeError):
if _wants_json():
return jsonify({"error": "Invalid expiry date format"}), 400
flash("Invalid expiry date format", "danger")
return redirect(url_for("ui.iam_dashboard"))
try:
created = _iam().create_user(display_name=display_name, policies=policies, access_key=custom_access_key, secret_key=custom_secret_key, expires_at=expires_at)
except IamError as exc:
if _wants_json():
return jsonify({"error": str(exc)}), 400
@@ -1967,6 +1988,45 @@ def update_iam_policies(access_key: str):
return redirect(url_for("ui.iam_dashboard"))
@ui_bp.post("/iam/users/<access_key>/expiry")
def update_iam_expiry(access_key: str):
principal = _current_principal()
try:
_iam().authorize(principal, None, "iam:update_policy")
except IamError as exc:
if _wants_json():
return jsonify({"error": str(exc)}), 403
flash(str(exc), "danger")
return redirect(url_for("ui.iam_dashboard"))
expires_at = request.form.get("expires_at", "").strip() or None
if expires_at:
try:
from datetime import datetime as _dt, timezone as _tz
exp_dt = _dt.fromisoformat(expires_at)
if exp_dt.tzinfo is None:
exp_dt = exp_dt.replace(tzinfo=_tz.utc)
expires_at = exp_dt.isoformat()
except (ValueError, TypeError):
if _wants_json():
return jsonify({"error": "Invalid expiry date format"}), 400
flash("Invalid expiry date format", "danger")
return redirect(url_for("ui.iam_dashboard"))
try:
_iam().update_user_expiry(access_key, expires_at)
if _wants_json():
return jsonify({"success": True, "message": f"Updated expiry for {access_key}", "expires_at": expires_at})
label = expires_at if expires_at else "never"
flash(f"Expiry for {access_key} set to {label}", "success")
except IamError as exc:
if _wants_json():
return jsonify({"error": str(exc)}), 400
flash(str(exc), "danger")
return redirect(url_for("ui.iam_dashboard"))
@ui_bp.post("/connections")
def create_connection():
principal = _current_principal()

View File

@@ -1,6 +1,6 @@
from __future__ import annotations
APP_VERSION = "0.3.4"
APP_VERSION = "0.3.7"
def get_version() -> str:

35
docs.md
View File

@@ -145,13 +145,15 @@ All configuration is done via environment variables. The table below lists every
| Variable | Default | Notes |
| --- | --- | --- |
| `IAM_CONFIG` | `data/.myfsio.sys/config/iam.json` | Stores users, secrets, and inline policies. |
| `IAM_CONFIG` | `data/.myfsio.sys/config/iam.json` | Stores users, secrets, and inline policies. Encrypted at rest when `SECRET_KEY` is set. |
| `BUCKET_POLICY_PATH` | `data/.myfsio.sys/config/bucket_policies.json` | Bucket policy store (auto hot-reload). |
| `AUTH_MAX_ATTEMPTS` | `5` | Failed login attempts before lockout. |
| `AUTH_LOCKOUT_MINUTES` | `15` | Lockout duration after max failed attempts. |
| `SESSION_LIFETIME_DAYS` | `30` | How long UI sessions remain valid. |
| `SECRET_TTL_SECONDS` | `300` | TTL for ephemeral secrets (presigned URLs). |
| `UI_ENFORCE_BUCKET_POLICIES` | `false` | Whether the UI should enforce bucket policies. |
| `ADMIN_ACCESS_KEY` | (none) | Custom access key for the admin user on first run or credential reset. If unset, a random key is generated. |
| `ADMIN_SECRET_KEY` | (none) | Custom secret key for the admin user on first run or credential reset. If unset, a random key is generated. |
### CORS (Cross-Origin Resource Sharing)
@@ -277,13 +279,14 @@ API responses for JSON, XML, HTML, CSS, and JavaScript are automatically gzip-co
Before deploying to production, ensure you:
1. **Set `SECRET_KEY`** - Use a strong, unique value (e.g., `openssl rand -base64 32`)
1. **Set `SECRET_KEY`** - Use a strong, unique value (e.g., `openssl rand -base64 32`). This also enables IAM config encryption at rest.
2. **Restrict CORS** - Set `CORS_ORIGINS` to your specific domains instead of `*`
3. **Configure `API_BASE_URL`** - Required for correct presigned URLs behind proxies
4. **Enable HTTPS** - Use a reverse proxy (nginx, Cloudflare) with TLS termination
5. **Review rate limits** - Adjust `RATE_LIMIT_DEFAULT` based on your needs
6. **Secure master keys** - Back up `ENCRYPTION_MASTER_KEY_PATH` if using encryption
7. **Use `--prod` flag** - Runs with Waitress instead of Flask dev server
8. **Set credential expiry** - Assign `expires_at` to non-admin users for time-limited access
### Proxy Configuration
@@ -633,9 +636,10 @@ MyFSIO implements a comprehensive Identity and Access Management (IAM) system th
### Getting Started
1. On first boot, `data/.myfsio.sys/config/iam.json` is created with a randomly generated admin user. The access key and secret key are printed to the console during first startup. If you miss it, check the `iam.json` file directly—credentials are stored in plaintext.
1. On first boot, `data/.myfsio.sys/config/iam.json` is created with a randomly generated admin user. The access key and secret key are printed to the console during first startup. You can set `ADMIN_ACCESS_KEY` and `ADMIN_SECRET_KEY` environment variables to use custom credentials instead of random ones. If `SECRET_KEY` is configured, the IAM config file is encrypted at rest using AES (Fernet). To reset admin credentials later, run `python run.py --reset-cred`.
2. Sign into the UI using the generated credentials, then open **IAM**:
- **Create user**: supply a display name and optional JSON inline policy array.
- **Create user**: supply a display name, optional JSON inline policy array, and optional credential expiry date.
- **Set expiry**: assign an expiration date to any user's credentials. Expired credentials are rejected at authentication time. The UI shows expiry badges and preset durations (1h, 24h, 7d, 30d, 90d).
- **Rotate secret**: generates a new secret key; the UI surfaces it once.
- **Policy editor**: select a user, paste an array of objects (`{"bucket": "*", "actions": ["list", "read"]}`), and submit. Alias support includes AWS-style verbs (e.g., `s3:GetObject`).
3. Wildcard action `iam:*` is supported for admin user definitions.
@@ -653,8 +657,11 @@ The API expects every request to include authentication headers. The UI persists
**Security Features:**
- **Lockout Protection**: After `AUTH_MAX_ATTEMPTS` (default: 5) failed login attempts, the account is locked for `AUTH_LOCKOUT_MINUTES` (default: 15 minutes).
- **Credential Expiry**: Each user can have an optional `expires_at` timestamp (ISO 8601). Once expired, all API requests using those credentials are rejected. Set or clear expiry via the UI or API.
- **IAM Config Encryption**: When `SECRET_KEY` is set, the IAM config file (`iam.json`) is encrypted at rest using Fernet (AES-256-CBC with HMAC). Existing plaintext configs are automatically encrypted on next load.
- **Session Management**: UI sessions remain valid for `SESSION_LIFETIME_DAYS` (default: 30 days).
- **Hot Reload**: IAM configuration changes take effect immediately without restart.
- **Credential Reset**: Run `python run.py --reset-cred` to reset admin credentials. Supports `ADMIN_ACCESS_KEY` and `ADMIN_SECRET_KEY` env vars for deterministic keys.
### Permission Model
@@ -814,7 +821,8 @@ curl -X POST http://localhost:5000/iam/users \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"display_name": "New User",
"policies": [{"bucket": "*", "actions": ["list", "read"]}]
"policies": [{"bucket": "*", "actions": ["list", "read"]}],
"expires_at": "2026-12-31T23:59:59Z"
}'
# Rotate user secret (requires iam:rotate_key)
@@ -827,6 +835,18 @@ curl -X PUT http://localhost:5000/iam/users/<access-key>/policies \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '[{"bucket": "*", "actions": ["list", "read", "write"]}]'
# Update credential expiry (requires iam:update_policy)
curl -X POST http://localhost:5000/iam/users/<access-key>/expiry \
-H "Content-Type: application/x-www-form-urlencoded" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d 'expires_at=2026-12-31T23:59:59Z'
# Remove credential expiry (never expires)
curl -X POST http://localhost:5000/iam/users/<access-key>/expiry \
-H "Content-Type: application/x-www-form-urlencoded" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d 'expires_at='
# Delete a user (requires iam:delete_user)
curl -X DELETE http://localhost:5000/iam/users/<access-key> \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
@@ -838,8 +858,9 @@ When a request is made, permissions are evaluated in this order:
1. **Authentication** Verify the access key and secret key are valid
2. **Lockout Check** Ensure the account is not locked due to failed attempts
3. **IAM Policy Check** Verify the user has the required action for the target bucket
4. **Bucket Policy Check** If a bucket policy exists, verify it allows the action
3. **Expiry Check** Reject requests if the user's credentials have expired (`expires_at`)
4. **IAM Policy Check** Verify the user has the required action for the target bucket
5. **Bucket Policy Check** If a bucket policy exists, verify it allows the action
A request is allowed only if:
- The IAM policy grants the action, AND

View File

@@ -19,3 +19,6 @@ regex = "1"
lru = "0.14"
parking_lot = "0.12"
percent-encoding = "2"
aes-gcm = "0.10"
hkdf = "0.12"
uuid = { version = "1", features = ["v4"] }

192
myfsio_core/src/crypto.rs Normal file
View File

@@ -0,0 +1,192 @@
use aes_gcm::aead::Aead;
use aes_gcm::{Aes256Gcm, KeyInit, Nonce};
use hkdf::Hkdf;
use pyo3::exceptions::{PyIOError, PyValueError};
use pyo3::prelude::*;
use sha2::Sha256;
use std::fs::File;
use std::io::{Read, Seek, SeekFrom, Write};
const DEFAULT_CHUNK_SIZE: usize = 65536;
const HEADER_SIZE: usize = 4;
fn read_exact_chunk(reader: &mut impl Read, buf: &mut [u8]) -> std::io::Result<usize> {
let mut filled = 0;
while filled < buf.len() {
match reader.read(&mut buf[filled..]) {
Ok(0) => break,
Ok(n) => filled += n,
Err(ref e) if e.kind() == std::io::ErrorKind::Interrupted => continue,
Err(e) => return Err(e),
}
}
Ok(filled)
}
fn derive_chunk_nonce(base_nonce: &[u8], chunk_index: u32) -> Result<[u8; 12], String> {
let hkdf = Hkdf::<Sha256>::new(Some(base_nonce), b"chunk_nonce");
let mut okm = [0u8; 12];
hkdf.expand(&chunk_index.to_be_bytes(), &mut okm)
.map_err(|e| format!("HKDF expand failed: {}", e))?;
Ok(okm)
}
#[pyfunction]
#[pyo3(signature = (input_path, output_path, key, base_nonce, chunk_size=DEFAULT_CHUNK_SIZE))]
pub fn encrypt_stream_chunked(
py: Python<'_>,
input_path: &str,
output_path: &str,
key: &[u8],
base_nonce: &[u8],
chunk_size: usize,
) -> PyResult<u32> {
if key.len() != 32 {
return Err(PyValueError::new_err(format!(
"Key must be 32 bytes, got {}",
key.len()
)));
}
if base_nonce.len() != 12 {
return Err(PyValueError::new_err(format!(
"Base nonce must be 12 bytes, got {}",
base_nonce.len()
)));
}
let chunk_size = if chunk_size == 0 {
DEFAULT_CHUNK_SIZE
} else {
chunk_size
};
let inp = input_path.to_owned();
let out = output_path.to_owned();
let key_arr: [u8; 32] = key.try_into().unwrap();
let nonce_arr: [u8; 12] = base_nonce.try_into().unwrap();
py.detach(move || {
let cipher = Aes256Gcm::new(&key_arr.into());
let mut infile = File::open(&inp)
.map_err(|e| PyIOError::new_err(format!("Failed to open input: {}", e)))?;
let mut outfile = File::create(&out)
.map_err(|e| PyIOError::new_err(format!("Failed to create output: {}", e)))?;
outfile
.write_all(&[0u8; 4])
.map_err(|e| PyIOError::new_err(format!("Failed to write header: {}", e)))?;
let mut buf = vec![0u8; chunk_size];
let mut chunk_index: u32 = 0;
loop {
let n = read_exact_chunk(&mut infile, &mut buf)
.map_err(|e| PyIOError::new_err(format!("Failed to read: {}", e)))?;
if n == 0 {
break;
}
let nonce_bytes = derive_chunk_nonce(&nonce_arr, chunk_index)
.map_err(|e| PyValueError::new_err(e))?;
let nonce = Nonce::from_slice(&nonce_bytes);
let encrypted = cipher
.encrypt(nonce, &buf[..n])
.map_err(|e| PyValueError::new_err(format!("Encrypt failed: {}", e)))?;
let size = encrypted.len() as u32;
outfile
.write_all(&size.to_be_bytes())
.map_err(|e| PyIOError::new_err(format!("Failed to write chunk size: {}", e)))?;
outfile
.write_all(&encrypted)
.map_err(|e| PyIOError::new_err(format!("Failed to write chunk: {}", e)))?;
chunk_index += 1;
}
outfile
.seek(SeekFrom::Start(0))
.map_err(|e| PyIOError::new_err(format!("Failed to seek: {}", e)))?;
outfile
.write_all(&chunk_index.to_be_bytes())
.map_err(|e| PyIOError::new_err(format!("Failed to write chunk count: {}", e)))?;
Ok(chunk_index)
})
}
#[pyfunction]
pub fn decrypt_stream_chunked(
py: Python<'_>,
input_path: &str,
output_path: &str,
key: &[u8],
base_nonce: &[u8],
) -> PyResult<u32> {
if key.len() != 32 {
return Err(PyValueError::new_err(format!(
"Key must be 32 bytes, got {}",
key.len()
)));
}
if base_nonce.len() != 12 {
return Err(PyValueError::new_err(format!(
"Base nonce must be 12 bytes, got {}",
base_nonce.len()
)));
}
let inp = input_path.to_owned();
let out = output_path.to_owned();
let key_arr: [u8; 32] = key.try_into().unwrap();
let nonce_arr: [u8; 12] = base_nonce.try_into().unwrap();
py.detach(move || {
let cipher = Aes256Gcm::new(&key_arr.into());
let mut infile = File::open(&inp)
.map_err(|e| PyIOError::new_err(format!("Failed to open input: {}", e)))?;
let mut outfile = File::create(&out)
.map_err(|e| PyIOError::new_err(format!("Failed to create output: {}", e)))?;
let mut header = [0u8; HEADER_SIZE];
infile
.read_exact(&mut header)
.map_err(|e| PyIOError::new_err(format!("Failed to read header: {}", e)))?;
let chunk_count = u32::from_be_bytes(header);
let mut size_buf = [0u8; HEADER_SIZE];
for chunk_index in 0..chunk_count {
infile
.read_exact(&mut size_buf)
.map_err(|e| {
PyIOError::new_err(format!(
"Failed to read chunk {} size: {}",
chunk_index, e
))
})?;
let chunk_size = u32::from_be_bytes(size_buf) as usize;
let mut encrypted = vec![0u8; chunk_size];
infile.read_exact(&mut encrypted).map_err(|e| {
PyIOError::new_err(format!("Failed to read chunk {}: {}", chunk_index, e))
})?;
let nonce_bytes = derive_chunk_nonce(&nonce_arr, chunk_index)
.map_err(|e| PyValueError::new_err(e))?;
let nonce = Nonce::from_slice(&nonce_bytes);
let decrypted = cipher.decrypt(nonce, encrypted.as_ref()).map_err(|e| {
PyValueError::new_err(format!("Decrypt chunk {} failed: {}", chunk_index, e))
})?;
outfile.write_all(&decrypted).map_err(|e| {
PyIOError::new_err(format!("Failed to write chunk {}: {}", chunk_index, e))
})?;
}
Ok(chunk_count)
})
}

View File

@@ -1,7 +1,9 @@
mod crypto;
mod hashing;
mod metadata;
mod sigv4;
mod storage;
mod streaming;
mod validation;
use pyo3::prelude::*;
@@ -38,6 +40,12 @@ mod myfsio_core {
m.add_function(wrap_pyfunction!(storage::search_objects_scan, m)?)?;
m.add_function(wrap_pyfunction!(storage::build_object_cache, m)?)?;
m.add_function(wrap_pyfunction!(streaming::stream_to_file_with_md5, m)?)?;
m.add_function(wrap_pyfunction!(streaming::assemble_parts_with_md5, m)?)?;
m.add_function(wrap_pyfunction!(crypto::encrypt_stream_chunked, m)?)?;
m.add_function(wrap_pyfunction!(crypto::decrypt_stream_chunked, m)?)?;
Ok(())
}
}

View File

@@ -0,0 +1,112 @@
use md5::{Digest, Md5};
use pyo3::exceptions::{PyIOError, PyValueError};
use pyo3::prelude::*;
use std::fs::{self, File};
use std::io::{Read, Write};
use uuid::Uuid;
const DEFAULT_CHUNK_SIZE: usize = 262144;
#[pyfunction]
#[pyo3(signature = (stream, tmp_dir, chunk_size=DEFAULT_CHUNK_SIZE))]
pub fn stream_to_file_with_md5(
py: Python<'_>,
stream: &Bound<'_, PyAny>,
tmp_dir: &str,
chunk_size: usize,
) -> PyResult<(String, String, u64)> {
let chunk_size = if chunk_size == 0 {
DEFAULT_CHUNK_SIZE
} else {
chunk_size
};
fs::create_dir_all(tmp_dir)
.map_err(|e| PyIOError::new_err(format!("Failed to create tmp dir: {}", e)))?;
let tmp_name = format!("{}.tmp", Uuid::new_v4().as_hyphenated());
let tmp_path_buf = std::path::PathBuf::from(tmp_dir).join(&tmp_name);
let tmp_path = tmp_path_buf.to_string_lossy().into_owned();
let mut file = File::create(&tmp_path)
.map_err(|e| PyIOError::new_err(format!("Failed to create temp file: {}", e)))?;
let mut hasher = Md5::new();
let mut total_bytes: u64 = 0;
let result: PyResult<()> = (|| {
loop {
let chunk: Vec<u8> = stream.call_method1("read", (chunk_size,))?.extract()?;
if chunk.is_empty() {
break;
}
hasher.update(&chunk);
file.write_all(&chunk)
.map_err(|e| PyIOError::new_err(format!("Failed to write: {}", e)))?;
total_bytes += chunk.len() as u64;
py.check_signals()?;
}
file.sync_all()
.map_err(|e| PyIOError::new_err(format!("Failed to fsync: {}", e)))?;
Ok(())
})();
if let Err(e) = result {
drop(file);
let _ = fs::remove_file(&tmp_path);
return Err(e);
}
drop(file);
let md5_hex = format!("{:x}", hasher.finalize());
Ok((tmp_path, md5_hex, total_bytes))
}
#[pyfunction]
pub fn assemble_parts_with_md5(
py: Python<'_>,
part_paths: Vec<String>,
dest_path: &str,
) -> PyResult<String> {
if part_paths.is_empty() {
return Err(PyValueError::new_err("No parts to assemble"));
}
let dest = dest_path.to_owned();
let parts = part_paths;
py.detach(move || {
if let Some(parent) = std::path::Path::new(&dest).parent() {
fs::create_dir_all(parent)
.map_err(|e| PyIOError::new_err(format!("Failed to create dest dir: {}", e)))?;
}
let mut target = File::create(&dest)
.map_err(|e| PyIOError::new_err(format!("Failed to create dest file: {}", e)))?;
let mut hasher = Md5::new();
let mut buf = vec![0u8; 1024 * 1024];
for part_path in &parts {
let mut part = File::open(part_path)
.map_err(|e| PyIOError::new_err(format!("Failed to open part {}: {}", part_path, e)))?;
loop {
let n = part
.read(&mut buf)
.map_err(|e| PyIOError::new_err(format!("Failed to read part: {}", e)))?;
if n == 0 {
break;
}
hasher.update(&buf[..n]);
target
.write_all(&buf[..n])
.map_err(|e| PyIOError::new_err(format!("Failed to write: {}", e)))?;
}
}
target.sync_all()
.map_err(|e| PyIOError::new_err(format!("Failed to fsync: {}", e)))?;
Ok(format!("{:x}", hasher.finalize()))
})
}

103
run.py
View File

@@ -23,6 +23,7 @@ from typing import Optional
from app import create_api_app, create_ui_app
from app.config import AppConfig
from app.iam import IamService, IamError, ALLOWED_ACTIONS, _derive_fernet_key
def _server_host() -> str:
@@ -87,21 +88,121 @@ def serve_ui(port: int, prod: bool = False, config: Optional[AppConfig] = None)
app.run(host=_server_host(), port=port, debug=debug)
def reset_credentials() -> None:
import json
import secrets
from cryptography.fernet import Fernet
config = AppConfig.from_env()
iam_path = config.iam_config_path
encryption_key = config.secret_key
access_key = os.environ.get("ADMIN_ACCESS_KEY", "").strip() or secrets.token_hex(12)
secret_key = os.environ.get("ADMIN_SECRET_KEY", "").strip() or secrets.token_urlsafe(32)
custom_keys = bool(os.environ.get("ADMIN_ACCESS_KEY", "").strip())
fernet = Fernet(_derive_fernet_key(encryption_key)) if encryption_key else None
raw_config = None
if iam_path.exists():
try:
raw_bytes = iam_path.read_bytes()
from app.iam import _IAM_ENCRYPTED_PREFIX
if raw_bytes.startswith(_IAM_ENCRYPTED_PREFIX):
if fernet:
try:
content = fernet.decrypt(raw_bytes[len(_IAM_ENCRYPTED_PREFIX):]).decode("utf-8")
raw_config = json.loads(content)
except Exception:
print("WARNING: Could not decrypt existing IAM config. Creating fresh config.")
else:
print("WARNING: IAM config is encrypted but no SECRET_KEY available. Creating fresh config.")
else:
try:
raw_config = json.loads(raw_bytes.decode("utf-8"))
except json.JSONDecodeError:
print("WARNING: Existing IAM config is corrupted. Creating fresh config.")
except OSError:
pass
if raw_config and raw_config.get("users"):
admin_user = None
for user in raw_config["users"]:
policies = user.get("policies", [])
for p in policies:
actions = p.get("actions", [])
if "iam:*" in actions or "*" in actions:
admin_user = user
break
if admin_user:
break
if not admin_user:
admin_user = raw_config["users"][0]
admin_user["access_key"] = access_key
admin_user["secret_key"] = secret_key
else:
raw_config = {
"users": [
{
"access_key": access_key,
"secret_key": secret_key,
"display_name": "Local Admin",
"policies": [
{"bucket": "*", "actions": list(ALLOWED_ACTIONS)}
],
}
]
}
json_text = json.dumps(raw_config, indent=2)
iam_path.parent.mkdir(parents=True, exist_ok=True)
temp_path = iam_path.with_suffix(".json.tmp")
if fernet:
from app.iam import _IAM_ENCRYPTED_PREFIX
encrypted = fernet.encrypt(json_text.encode("utf-8"))
temp_path.write_bytes(_IAM_ENCRYPTED_PREFIX + encrypted)
else:
temp_path.write_text(json_text, encoding="utf-8")
temp_path.replace(iam_path)
print(f"\n{'='*60}")
print("MYFSIO - ADMIN CREDENTIALS RESET")
print(f"{'='*60}")
if custom_keys:
print(f"Access Key: {access_key} (from ADMIN_ACCESS_KEY)")
print(f"Secret Key: {'(from ADMIN_SECRET_KEY)' if os.environ.get('ADMIN_SECRET_KEY', '').strip() else secret_key}")
else:
print(f"Access Key: {access_key}")
print(f"Secret Key: {secret_key}")
print(f"{'='*60}")
if fernet:
print("IAM config saved (encrypted).")
else:
print(f"IAM config saved to: {iam_path}")
print(f"{'='*60}\n")
if __name__ == "__main__":
multiprocessing.freeze_support()
if _is_frozen():
multiprocessing.set_start_method("spawn", force=True)
parser = argparse.ArgumentParser(description="Run the S3 clone services.")
parser.add_argument("--mode", choices=["api", "ui", "both"], default="both")
parser.add_argument("--mode", choices=["api", "ui", "both", "reset-cred"], default="both")
parser.add_argument("--api-port", type=int, default=5000)
parser.add_argument("--ui-port", type=int, default=5100)
parser.add_argument("--prod", action="store_true", help="Run in production mode using Waitress")
parser.add_argument("--dev", action="store_true", help="Force development mode (Flask dev server)")
parser.add_argument("--check-config", action="store_true", help="Validate configuration and exit")
parser.add_argument("--show-config", action="store_true", help="Show configuration summary and exit")
parser.add_argument("--reset-cred", action="store_true", help="Reset admin credentials and exit")
args = parser.parse_args()
if args.reset_cred or args.mode == "reset-cred":
reset_credentials()
sys.exit(0)
if args.check_config or args.show_config:
config = AppConfig.from_env()
config.print_startup_summary()

View File

@@ -1154,39 +1154,20 @@ html.sidebar-will-collapse .sidebar-user {
position: relative;
border: 1px solid var(--myfsio-card-border) !important;
border-radius: 1rem !important;
overflow: hidden;
overflow: visible;
transition: all 0.2s cubic-bezier(0.4, 0, 0.2, 1);
}
.iam-user-card::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
height: 4px;
background: linear-gradient(90deg, #3b82f6, #8b5cf6);
opacity: 0;
transition: opacity 0.2s ease;
}
.iam-user-card:hover {
transform: translateY(-2px);
box-shadow: 0 8px 24px -4px rgba(0, 0, 0, 0.12), 0 4px 8px -4px rgba(0, 0, 0, 0.08);
border-color: var(--myfsio-accent) !important;
}
.iam-user-card:hover::before {
opacity: 1;
}
[data-theme='dark'] .iam-user-card:hover {
box-shadow: 0 8px 24px -4px rgba(0, 0, 0, 0.4), 0 4px 8px -4px rgba(0, 0, 0, 0.3);
}
.iam-admin-card::before {
background: linear-gradient(90deg, #f59e0b, #ef4444);
}
.iam-role-badge {
display: inline-flex;

View File

@@ -321,7 +321,7 @@
`;
};
const bucketTotalObjects = objectsContainer ? parseInt(objectsContainer.dataset.bucketTotalObjects || '0', 10) : 0;
let bucketTotalObjects = objectsContainer ? parseInt(objectsContainer.dataset.bucketTotalObjects || '0', 10) : 0;
const updateObjectCountBadge = () => {
if (!objectCountBadge) return;
@@ -702,6 +702,7 @@
flushPendingStreamObjects();
hasMoreObjects = false;
totalObjectCount = loadedObjectCount;
if (!currentPrefix) bucketTotalObjects = totalObjectCount;
updateObjectCountBadge();
if (objectsLoadingRow && objectsLoadingRow.parentNode) {
@@ -766,6 +767,7 @@
}
totalObjectCount = data.total_count || 0;
if (!append && !currentPrefix) bucketTotalObjects = totalObjectCount;
nextContinuationToken = data.next_continuation_token;
if (!append && objectsLoadingRow) {

View File

@@ -11,9 +11,11 @@ window.IAMManagement = (function() {
var editUserModal = null;
var deleteUserModal = null;
var rotateSecretModal = null;
var expiryModal = null;
var currentRotateKey = null;
var currentEditKey = null;
var currentDeleteKey = null;
var currentExpiryKey = null;
var ALL_S3_ACTIONS = ['list', 'read', 'write', 'delete', 'share', 'policy', 'replication', 'lifecycle', 'cors'];
@@ -65,6 +67,7 @@ window.IAMManagement = (function() {
setupEditUserModal();
setupDeleteUserModal();
setupRotateSecretModal();
setupExpiryModal();
setupFormHandlers();
setupSearch();
setupCopyAccessKeyButtons();
@@ -75,11 +78,13 @@ window.IAMManagement = (function() {
var editModalEl = document.getElementById('editUserModal');
var deleteModalEl = document.getElementById('deleteUserModal');
var rotateModalEl = document.getElementById('rotateSecretModal');
var expiryModalEl = document.getElementById('expiryModal');
if (policyModalEl) policyModal = new bootstrap.Modal(policyModalEl);
if (editModalEl) editUserModal = new bootstrap.Modal(editModalEl);
if (deleteModalEl) deleteUserModal = new bootstrap.Modal(deleteModalEl);
if (rotateModalEl) rotateSecretModal = new bootstrap.Modal(rotateModalEl);
if (expiryModalEl) expiryModal = new bootstrap.Modal(expiryModalEl);
}
function setupJsonAutoIndent() {
@@ -97,6 +102,15 @@ window.IAMManagement = (function() {
});
});
var accessKeyCopyButton = document.querySelector('[data-access-key-copy]');
if (accessKeyCopyButton) {
accessKeyCopyButton.addEventListener('click', async function() {
var accessKeyInput = document.getElementById('disclosedAccessKeyValue');
if (!accessKeyInput) return;
await window.UICore.copyToClipboard(accessKeyInput.value, accessKeyCopyButton, 'Copy');
});
}
var secretCopyButton = document.querySelector('[data-secret-copy]');
if (secretCopyButton) {
secretCopyButton.addEventListener('click', async function() {
@@ -143,6 +157,22 @@ window.IAMManagement = (function() {
});
}
function generateSecureHex(byteCount) {
var arr = new Uint8Array(byteCount);
crypto.getRandomValues(arr);
return Array.from(arr).map(function(b) { return b.toString(16).padStart(2, '0'); }).join('');
}
function generateSecureBase64(byteCount) {
var arr = new Uint8Array(byteCount);
crypto.getRandomValues(arr);
var binary = '';
for (var i = 0; i < arr.length; i++) {
binary += String.fromCharCode(arr[i]);
}
return btoa(binary).replace(/\+/g, '-').replace(/\//g, '_').replace(/=+$/, '');
}
function setupCreateUserModal() {
var createUserPoliciesEl = document.getElementById('createUserPolicies');
@@ -151,6 +181,22 @@ window.IAMManagement = (function() {
applyPolicyTemplate(button.dataset.createPolicyTemplate, createUserPoliciesEl);
});
});
var genAccessKeyBtn = document.getElementById('generateAccessKeyBtn');
if (genAccessKeyBtn) {
genAccessKeyBtn.addEventListener('click', function() {
var input = document.getElementById('createUserAccessKey');
if (input) input.value = generateSecureHex(8);
});
}
var genSecretKeyBtn = document.getElementById('generateSecretKeyBtn');
if (genSecretKeyBtn) {
genSecretKeyBtn.addEventListener('click', function() {
var input = document.getElementById('createUserSecretKey');
if (input) input.value = generateSecureBase64(24);
});
}
}
function setupEditUserModal() {
@@ -271,6 +317,77 @@ window.IAMManagement = (function() {
}
}
function openExpiryModal(key, expiresAt) {
currentExpiryKey = key;
var label = document.getElementById('expiryUserLabel');
var input = document.getElementById('expiryDateInput');
var form = document.getElementById('expiryForm');
if (label) label.textContent = key;
if (expiresAt) {
try {
var dt = new Date(expiresAt);
var local = new Date(dt.getTime() - dt.getTimezoneOffset() * 60000);
if (input) input.value = local.toISOString().slice(0, 16);
} catch(e) {
if (input) input.value = '';
}
} else {
if (input) input.value = '';
}
if (form) form.action = endpoints.updateExpiry.replace('ACCESS_KEY', key);
var modalEl = document.getElementById('expiryModal');
if (modalEl) {
var modal = bootstrap.Modal.getOrCreateInstance(modalEl);
modal.show();
}
}
function setupExpiryModal() {
document.querySelectorAll('[data-expiry-user]').forEach(function(btn) {
btn.addEventListener('click', function(e) {
e.preventDefault();
openExpiryModal(btn.dataset.expiryUser, btn.dataset.expiresAt || '');
});
});
document.querySelectorAll('[data-expiry-preset]').forEach(function(btn) {
btn.addEventListener('click', function() {
var preset = btn.dataset.expiryPreset;
var input = document.getElementById('expiryDateInput');
if (!input) return;
if (preset === 'clear') {
input.value = '';
return;
}
var now = new Date();
var ms = 0;
if (preset === '1h') ms = 3600000;
else if (preset === '24h') ms = 86400000;
else if (preset === '7d') ms = 7 * 86400000;
else if (preset === '30d') ms = 30 * 86400000;
else if (preset === '90d') ms = 90 * 86400000;
var future = new Date(now.getTime() + ms);
var local = new Date(future.getTime() - future.getTimezoneOffset() * 60000);
input.value = local.toISOString().slice(0, 16);
});
});
var expiryForm = document.getElementById('expiryForm');
if (expiryForm) {
expiryForm.addEventListener('submit', function(e) {
e.preventDefault();
window.UICore.submitFormAjax(expiryForm, {
successMessage: 'Expiry updated',
onSuccess: function() {
var modalEl = document.getElementById('expiryModal');
if (modalEl) bootstrap.Modal.getOrCreateInstance(modalEl).hide();
window.location.reload();
}
});
});
}
}
function createUserCardHtml(accessKey, displayName, policies) {
var admin = isAdminUser(policies);
var cardClass = 'card h-100 iam-user-card' + (admin ? ' iam-admin-card' : '');
@@ -324,6 +441,8 @@ window.IAMManagement = (function() {
'<ul class="dropdown-menu dropdown-menu-end">' +
'<li><button class="dropdown-item" type="button" data-edit-user="' + esc(accessKey) + '" data-display-name="' + esc(displayName) + '">' +
'<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-2" viewBox="0 0 16 16"><path d="M12.146.146a.5.5 0 0 1 .708 0l3 3a.5.5 0 0 1 0 .708l-10 10a.5.5 0 0 1-.168.11l-5 2a.5.5 0 0 1-.65-.65l2-5a.5.5 0 0 1 .11-.168l10-10zM11.207 2.5 13.5 4.793 14.793 3.5 12.5 1.207 11.207 2.5zm1.586 3L10.5 3.207 4 9.707V10h.5a.5.5 0 0 1 .5.5v.5h.5a.5.5 0 0 1 .5.5v.5h.293l6.5-6.5z"/></svg>Edit Name</button></li>' +
'<li><button class="dropdown-item" type="button" data-expiry-user="' + esc(accessKey) + '" data-expires-at="">' +
'<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-2" viewBox="0 0 16 16"><path d="M8 3.5a.5.5 0 0 0-1 0V9a.5.5 0 0 0 .252.434l3.5 2a.5.5 0 0 0 .496-.868L8 8.71V3.5z"/><path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm7-8A7 7 0 1 1 1 8a7 7 0 0 1 14 0z"/></svg>Set Expiry</button></li>' +
'<li><button class="dropdown-item" type="button" data-rotate-user="' + esc(accessKey) + '">' +
'<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-2" viewBox="0 0 16 16"><path d="M11.534 7h3.932a.25.25 0 0 1 .192.41l-1.966 2.36a.25.25 0 0 1-.384 0l-1.966-2.36a.25.25 0 0 1 .192-.41zm-11 2h3.932a.25.25 0 0 0 .192-.41L2.692 6.23a.25.25 0 0 0-.384 0L.342 8.59A.25.25 0 0 0 .534 9z"/><path fill-rule="evenodd" d="M8 3c-1.552 0-2.94.707-3.857 1.818a.5.5 0 1 1-.771-.636A6.002 6.002 0 0 1 13.917 7H12.9A5.002 5.002 0 0 0 8 3zM3.1 9a5.002 5.002 0 0 0 8.757 2.182.5.5 0 1 1 .771.636A6.002 6.002 0 0 1 2.083 9H3.1z"/></svg>Rotate Secret</button></li>' +
'<li><hr class="dropdown-divider"></li>' +
@@ -379,6 +498,14 @@ window.IAMManagement = (function() {
});
}
var expiryBtn = cardElement.querySelector('[data-expiry-user]');
if (expiryBtn) {
expiryBtn.addEventListener('click', function(e) {
e.preventDefault();
openExpiryModal(accessKey, '');
});
}
var policyBtn = cardElement.querySelector('[data-policy-editor]');
if (policyBtn) {
policyBtn.addEventListener('click', function() {
@@ -428,10 +555,15 @@ window.IAMManagement = (function() {
'</svg>' +
'<div class="flex-grow-1">' +
'<div class="fw-semibold">New user created: <code>' + window.UICore.escapeHtml(data.access_key) + '</code></div>' +
'<p class="mb-2 small">This secret is only shown once. Copy it now and store it securely.</p>' +
'<p class="mb-2 small">These credentials are only shown once. Copy them now and store them securely.</p>' +
'</div>' +
'<button type="button" class="btn-close" data-bs-dismiss="alert" aria-label="Close"></button>' +
'</div>' +
'<div class="input-group mb-2">' +
'<span class="input-group-text"><strong>Access key</strong></span>' +
'<input class="form-control font-monospace" type="text" value="' + window.UICore.escapeHtml(data.access_key) + '" readonly />' +
'<button class="btn btn-outline-primary" type="button" id="copyNewUserAccessKey">Copy</button>' +
'</div>' +
'<div class="input-group">' +
'<span class="input-group-text"><strong>Secret key</strong></span>' +
'<input class="form-control font-monospace" type="text" value="' + window.UICore.escapeHtml(data.secret_key) + '" readonly id="newUserSecret" />' +
@@ -440,6 +572,9 @@ window.IAMManagement = (function() {
var container = document.querySelector('.page-header');
if (container) {
container.insertAdjacentHTML('afterend', alertHtml);
document.getElementById('copyNewUserAccessKey').addEventListener('click', async function() {
await window.UICore.copyToClipboard(data.access_key, this, 'Copy');
});
document.getElementById('copyNewUserSecret').addEventListener('click', async function() {
await window.UICore.copyToClipboard(data.secret_key, this, 'Copy');
});

View File

@@ -202,6 +202,16 @@ python run.py --mode ui
<td><code>60 per minute</code></td>
<td>Rate limit for admin API endpoints (<code>/admin/*</code>).</td>
</tr>
<tr>
<td><code>ADMIN_ACCESS_KEY</code></td>
<td>(none)</td>
<td>Custom access key for the admin user on first run or credential reset. Random if unset.</td>
</tr>
<tr>
<td><code>ADMIN_SECRET_KEY</code></td>
<td>(none)</td>
<td>Custom secret key for the admin user on first run or credential reset. Random if unset.</td>
</tr>
<tr class="table-secondary">
<td colspan="3" class="fw-semibold">Server Settings</td>
</tr>
@@ -428,7 +438,7 @@ python run.py --mode ui
</table>
</div>
<div class="alert alert-warning mt-3 mb-0 small">
<strong>Production Checklist:</strong> Set <code>SECRET_KEY</code>, restrict <code>CORS_ORIGINS</code>, configure <code>API_BASE_URL</code>, enable HTTPS via reverse proxy, and use <code>--prod</code> flag.
<strong>Production Checklist:</strong> Set <code>SECRET_KEY</code> (also enables IAM config encryption at rest), restrict <code>CORS_ORIGINS</code>, configure <code>API_BASE_URL</code>, enable HTTPS via reverse proxy, use <code>--prod</code> flag, and set credential expiry on non-admin users.
</div>
</div>
</article>
@@ -495,11 +505,12 @@ sudo journalctl -u myfsio -f # View logs</code></pre>
<span class="docs-section-kicker">03</span>
<h2 class="h4 mb-0">Authenticate &amp; manage IAM</h2>
</div>
<p class="text-muted">On first startup, MyFSIO generates random admin credentials and prints them to the console. Missed it? Check <code>data/.myfsio.sys/config/iam.json</code> directly—credentials are stored in plaintext.</p>
<p class="text-muted">On first startup, MyFSIO generates random admin credentials and prints them to the console. Set <code>ADMIN_ACCESS_KEY</code> and <code>ADMIN_SECRET_KEY</code> env vars for custom credentials. When <code>SECRET_KEY</code> is configured, the IAM config is encrypted at rest. To reset credentials, run <code>python run.py --reset-cred</code>.</p>
<div class="docs-highlight mb-3">
<ol class="mb-0">
<li>Check the console output (or <code>iam.json</code>) for the generated <code>Access Key</code> and <code>Secret Key</code>, then visit <code>/ui/login</code>.</li>
<li>Create additional users with descriptive display names and AWS-style inline policies (for example <code>{"bucket": "*", "actions": ["list", "read"]}</code>).</li>
<li>Check the console output for the generated <code>Access Key</code> and <code>Secret Key</code>, then visit <code>/ui/login</code>.</li>
<li>Create additional users with descriptive display names, AWS-style inline policies (for example <code>{"bucket": "*", "actions": ["list", "read"]}</code>), and optional credential expiry dates.</li>
<li>Set credential expiry on users to grant time-limited access. The UI shows expiry badges and provides preset durations (1h, 24h, 7d, 30d, 90d). Expired credentials are rejected at authentication.</li>
<li>Rotate secrets when sharing with CI jobs—new secrets display once and persist to <code>data/.myfsio.sys/config/iam.json</code>.</li>
<li>Bucket policies layer on top of IAM. Apply Private/Public presets or paste custom JSON; changes reload instantly.</li>
</ol>

View File

@@ -50,9 +50,20 @@
New user created: <code>{{ disclosed_secret.access_key }}</code>
{% endif %}
</div>
<p class="mb-2 small">⚠️ This secret is only shown once. Copy it now and store it securely.</p>
<p class="mb-2 small">These credentials are only shown once. Copy them now and store them securely.</p>
</div>
</div>
<div class="input-group mb-2">
<span class="input-group-text"><strong>Access key</strong></span>
<input class="form-control font-monospace" type="text" value="{{ disclosed_secret.access_key }}" readonly id="disclosedAccessKeyValue" />
<button class="btn btn-outline-primary" type="button" data-access-key-copy>
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="bi bi-clipboard" viewBox="0 0 16 16">
<path d="M4 1.5H3a2 2 0 0 0-2 2V14a2 2 0 0 0 2 2h10a2 2 0 0 0 2-2V3.5a2 2 0 0 0-2-2h-1v1h1a1 1 0 0 1 1 1V14a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3.5a1 1 0 0 1 1-1h1v-1z"/>
<path d="M9.5 1a.5.5 0 0 1 .5.5v1a.5.5 0 0 1-.5.5h-3a.5.5 0 0 1-.5-.5v-1a.5.5 0 0 1 .5-.5h3zm-3-1A1.5 1.5 0 0 0 5 1.5v1A1.5 1.5 0 0 0 6.5 4h3A1.5 1.5 0 0 0 11 2.5v-1A1.5 1.5 0 0 0 9.5 0h-3z"/>
</svg>
Copy
</button>
</div>
<div class="input-group">
<span class="input-group-text"><strong>Secret key</strong></span>
<input class="form-control font-monospace" type="text" value="{{ disclosed_secret.secret_key }}" readonly id="disclosedSecretValue" />
@@ -79,7 +90,7 @@
<pre class="policy-preview mb-0" id="iamConfigPreview">{{ config_document }}</pre>
<button class="btn btn-outline-light btn-sm config-copy" type="button" data-copy-target="iamConfigPreview">Copy JSON</button>
</div>
<p class="text-muted small mt-2 mb-0">Secrets are masked above. Access <code>{{ config_summary.path }}</code> directly to view full credentials.</p>
<p class="text-muted small mt-2 mb-0">Secrets are masked above. IAM config is encrypted at rest.</p>
</div>
</div>
</div>
@@ -122,12 +133,20 @@
{% endif %}
<div class="row g-3">
{% for user in users %}
{% set ns = namespace(is_admin=false) %}
{% set ns = namespace(is_admin=false, is_expired=false, is_expiring_soon=false) %}
{% for policy in user.policies %}
{% if 'iam:*' in policy.actions or '*' in policy.actions %}
{% set ns.is_admin = true %}
{% endif %}
{% endfor %}
{% if user.expires_at %}
{% set exp_str = user.expires_at %}
{% if exp_str <= now_iso %}
{% set ns.is_expired = true %}
{% elif exp_str <= soon_iso %}
{% set ns.is_expiring_soon = true %}
{% endif %}
{% endif %}
<div class="col-md-6 col-xl-4 iam-user-item" data-display-name="{{ user.display_name|lower }}" data-access-key-filter="{{ user.access_key|lower }}">
<div class="card h-100 iam-user-card{{ ' iam-admin-card' if ns.is_admin else '' }}">
<div class="card-body">
@@ -146,6 +165,11 @@
{% else %}
<span class="iam-role-badge iam-role-user" data-role-badge>User</span>
{% endif %}
{% if ns.is_expired %}
<span class="badge text-bg-danger" style="font-size: .65rem">Expired</span>
{% elif ns.is_expiring_soon %}
<span class="badge text-bg-warning" style="font-size: .65rem">Expiring soon</span>
{% endif %}
</div>
<div class="d-flex align-items-center gap-1">
<code class="small text-muted text-truncate" title="{{ user.access_key }}">{{ user.access_key }}</code>
@@ -173,6 +197,15 @@
Edit Name
</button>
</li>
<li>
<button class="dropdown-item" type="button" data-expiry-user="{{ user.access_key }}" data-expires-at="{{ user.expires_at or '' }}">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-2" viewBox="0 0 16 16">
<path d="M8 3.5a.5.5 0 0 0-1 0V9a.5.5 0 0 0 .252.434l3.5 2a.5.5 0 0 0 .496-.868L8 8.71V3.5z"/>
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm7-8A7 7 0 1 1 1 8a7 7 0 0 1 14 0z"/>
</svg>
Set Expiry
</button>
</li>
<li>
<button class="dropdown-item" type="button" data-rotate-user="{{ user.access_key }}">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-2" viewBox="0 0 16 16">
@@ -283,6 +316,32 @@
<label class="form-label fw-medium">Display Name</label>
<input class="form-control" type="text" name="display_name" placeholder="Analytics Team" required autofocus />
</div>
<div class="mb-3">
<label class="form-label fw-medium d-flex justify-content-between align-items-center">
Access Key <span class="text-muted fw-normal small">optional</span>
</label>
<div class="input-group">
<input class="form-control font-monospace" type="text" name="access_key" id="createUserAccessKey" placeholder="Leave blank to auto-generate" />
<button class="btn btn-outline-secondary" type="button" id="generateAccessKeyBtn" title="Generate secure access key">Generate</button>
</div>
</div>
<div class="mb-3">
<label class="form-label fw-medium d-flex justify-content-between align-items-center">
Secret Key <span class="text-muted fw-normal small">optional</span>
</label>
<div class="input-group">
<input class="form-control font-monospace" type="text" name="secret_key" id="createUserSecretKey" placeholder="Leave blank to auto-generate" />
<button class="btn btn-outline-secondary" type="button" id="generateSecretKeyBtn" title="Generate secure secret key">Generate</button>
</div>
<div class="form-text">If you set a custom secret key, copy it now. It will be encrypted and cannot be recovered.</div>
</div>
<div class="mb-3">
<label class="form-label fw-medium d-flex justify-content-between align-items-center">
Expiry <span class="text-muted fw-normal small">optional</span>
</label>
<input class="form-control" type="datetime-local" name="expires_at" id="createUserExpiry" />
<div class="form-text">Leave blank for no expiration. Expired users cannot authenticate.</div>
</div>
<div class="mb-3">
<label class="form-label fw-medium">Initial Policies (JSON)</label>
<textarea class="form-control font-monospace" name="policies" id="createUserPolicies" rows="6" spellcheck="false" placeholder='[
@@ -495,6 +554,52 @@
</div>
</div>
<div class="modal fade" id="expiryModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h1 class="modal-title fs-5 fw-semibold">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path d="M8 3.5a.5.5 0 0 0-1 0V9a.5.5 0 0 0 .252.434l3.5 2a.5.5 0 0 0 .496-.868L8 8.71V3.5z"/>
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm7-8A7 7 0 1 1 1 8a7 7 0 0 1 14 0z"/>
</svg>
Set Expiry
</h1>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<form method="post" id="expiryForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
<div class="modal-body">
<p class="text-muted small mb-3">Set expiration for <code id="expiryUserLabel"></code></p>
<div class="mb-3">
<label class="form-label fw-medium">Expires at</label>
<input class="form-control" type="datetime-local" name="expires_at" id="expiryDateInput" />
<div class="form-text">Leave blank to remove expiration (never expires).</div>
</div>
<div class="d-flex flex-wrap gap-2">
<span class="text-muted small me-2 align-self-center">Quick presets:</span>
<button class="btn btn-outline-secondary btn-sm" type="button" data-expiry-preset="1h">1 hour</button>
<button class="btn btn-outline-secondary btn-sm" type="button" data-expiry-preset="24h">24 hours</button>
<button class="btn btn-outline-secondary btn-sm" type="button" data-expiry-preset="7d">7 days</button>
<button class="btn btn-outline-secondary btn-sm" type="button" data-expiry-preset="30d">30 days</button>
<button class="btn btn-outline-secondary btn-sm" type="button" data-expiry-preset="90d">90 days</button>
<button class="btn btn-outline-secondary btn-sm text-danger" type="button" data-expiry-preset="clear">Never</button>
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Cancel</button>
<button class="btn btn-primary" type="submit">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M10.97 4.97a.75.75 0 0 1 1.07 1.05l-3.99 4.99a.75.75 0 0 1-1.08.02L4.324 8.384a.75.75 0 1 1 1.06-1.06l2.094 2.093 3.473-4.425a.267.267 0 0 1 .02-.022z"/>
</svg>
Save Expiry
</button>
</div>
</form>
</div>
</div>
</div>
<script id="iamUsersJson" type="application/json">{{ users | tojson }}</script>
{% endblock %}
@@ -512,7 +617,8 @@
updateUser: "{{ url_for('ui.update_iam_user', access_key='ACCESS_KEY') }}",
deleteUser: "{{ url_for('ui.delete_iam_user', access_key='ACCESS_KEY') }}",
updatePolicies: "{{ url_for('ui.update_iam_policies', access_key='ACCESS_KEY') }}",
rotateSecret: "{{ url_for('ui.rotate_iam_secret', access_key='ACCESS_KEY') }}"
rotateSecret: "{{ url_for('ui.rotate_iam_secret', access_key='ACCESS_KEY') }}",
updateExpiry: "{{ url_for('ui.update_iam_expiry', access_key='ACCESS_KEY') }}"
}
});
</script>

View File

@@ -73,9 +73,6 @@
</svg>
</button>
</form>
<div class="text-center mt-4">
<small class="text-muted">Need help? Check the <a href="{{ url_for('ui.docs_page') }}" class="text-decoration-none">documentation</a></small>
</div>
</div>
</div>
</div>

View File

@@ -43,6 +43,11 @@ def app(tmp_path: Path):
}
)
yield flask_app
storage = flask_app.extensions.get("object_storage")
if storage:
base = getattr(storage, "storage", storage)
if hasattr(base, "shutdown_stats"):
base.shutdown_stats()
@pytest.fixture()

View File

@@ -53,7 +53,9 @@ def test_special_characters_in_metadata(tmp_path: Path):
assert meta["special"] == "!@#$%^&*()"
def test_disk_full_scenario(tmp_path: Path, monkeypatch):
# Simulate disk full by mocking write to fail
import app.storage as _storage_mod
monkeypatch.setattr(_storage_mod, "_HAS_RUST", False)
storage = ObjectStorage(tmp_path)
storage.create_bucket("full")

View File

@@ -0,0 +1,350 @@
import hashlib
import io
import os
import secrets
import sys
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
try:
import myfsio_core as _rc
HAS_RUST = True
except ImportError:
_rc = None
HAS_RUST = False
pytestmark = pytest.mark.skipif(not HAS_RUST, reason="myfsio_core not available")
class TestStreamToFileWithMd5:
def test_basic_write(self, tmp_path):
data = b"hello world" * 1000
stream = io.BytesIO(data)
tmp_dir = str(tmp_path / "tmp")
tmp_path_str, md5_hex, size = _rc.stream_to_file_with_md5(stream, tmp_dir)
assert size == len(data)
assert md5_hex == hashlib.md5(data).hexdigest()
assert Path(tmp_path_str).exists()
assert Path(tmp_path_str).read_bytes() == data
def test_empty_stream(self, tmp_path):
stream = io.BytesIO(b"")
tmp_dir = str(tmp_path / "tmp")
tmp_path_str, md5_hex, size = _rc.stream_to_file_with_md5(stream, tmp_dir)
assert size == 0
assert md5_hex == hashlib.md5(b"").hexdigest()
assert Path(tmp_path_str).read_bytes() == b""
def test_large_data(self, tmp_path):
data = os.urandom(1024 * 1024 * 2)
stream = io.BytesIO(data)
tmp_dir = str(tmp_path / "tmp")
tmp_path_str, md5_hex, size = _rc.stream_to_file_with_md5(stream, tmp_dir)
assert size == len(data)
assert md5_hex == hashlib.md5(data).hexdigest()
def test_custom_chunk_size(self, tmp_path):
data = b"x" * 10000
stream = io.BytesIO(data)
tmp_dir = str(tmp_path / "tmp")
tmp_path_str, md5_hex, size = _rc.stream_to_file_with_md5(
stream, tmp_dir, chunk_size=128
)
assert size == len(data)
assert md5_hex == hashlib.md5(data).hexdigest()
class TestAssemblePartsWithMd5:
def test_basic_assembly(self, tmp_path):
parts = []
combined = b""
for i in range(3):
data = f"part{i}data".encode() * 100
combined += data
p = tmp_path / f"part{i}"
p.write_bytes(data)
parts.append(str(p))
dest = str(tmp_path / "output")
md5_hex = _rc.assemble_parts_with_md5(parts, dest)
assert md5_hex == hashlib.md5(combined).hexdigest()
assert Path(dest).read_bytes() == combined
def test_single_part(self, tmp_path):
data = b"single part data"
p = tmp_path / "part0"
p.write_bytes(data)
dest = str(tmp_path / "output")
md5_hex = _rc.assemble_parts_with_md5([str(p)], dest)
assert md5_hex == hashlib.md5(data).hexdigest()
assert Path(dest).read_bytes() == data
def test_empty_parts_list(self):
with pytest.raises(ValueError, match="No parts"):
_rc.assemble_parts_with_md5([], "dummy")
def test_missing_part_file(self, tmp_path):
with pytest.raises(OSError):
_rc.assemble_parts_with_md5(
[str(tmp_path / "nonexistent")], str(tmp_path / "out")
)
def test_large_parts(self, tmp_path):
parts = []
combined = b""
for i in range(5):
data = os.urandom(512 * 1024)
combined += data
p = tmp_path / f"part{i}"
p.write_bytes(data)
parts.append(str(p))
dest = str(tmp_path / "output")
md5_hex = _rc.assemble_parts_with_md5(parts, dest)
assert md5_hex == hashlib.md5(combined).hexdigest()
assert Path(dest).read_bytes() == combined
class TestEncryptDecryptStreamChunked:
def _python_derive_chunk_nonce(self, base_nonce, chunk_index):
from cryptography.hazmat.primitives.kdf.hkdf import HKDF
from cryptography.hazmat.primitives import hashes
hkdf = HKDF(
algorithm=hashes.SHA256(),
length=12,
salt=base_nonce,
info=chunk_index.to_bytes(4, "big"),
)
return hkdf.derive(b"chunk_nonce")
def test_encrypt_decrypt_roundtrip(self, tmp_path):
data = b"Hello, encryption!" * 500
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
input_path = str(tmp_path / "plaintext")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(data)
chunk_count = _rc.encrypt_stream_chunked(
input_path, encrypted_path, key, base_nonce
)
assert chunk_count > 0
chunk_count_dec = _rc.decrypt_stream_chunked(
encrypted_path, decrypted_path, key, base_nonce
)
assert chunk_count_dec == chunk_count
assert Path(decrypted_path).read_bytes() == data
def test_empty_file(self, tmp_path):
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
input_path = str(tmp_path / "empty")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(b"")
chunk_count = _rc.encrypt_stream_chunked(
input_path, encrypted_path, key, base_nonce
)
assert chunk_count == 0
chunk_count_dec = _rc.decrypt_stream_chunked(
encrypted_path, decrypted_path, key, base_nonce
)
assert chunk_count_dec == 0
assert Path(decrypted_path).read_bytes() == b""
def test_custom_chunk_size(self, tmp_path):
data = os.urandom(10000)
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
input_path = str(tmp_path / "plaintext")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(data)
chunk_count = _rc.encrypt_stream_chunked(
input_path, encrypted_path, key, base_nonce, chunk_size=1024
)
assert chunk_count == 10
_rc.decrypt_stream_chunked(encrypted_path, decrypted_path, key, base_nonce)
assert Path(decrypted_path).read_bytes() == data
def test_invalid_key_length(self, tmp_path):
input_path = str(tmp_path / "in")
Path(input_path).write_bytes(b"data")
with pytest.raises(ValueError, match="32 bytes"):
_rc.encrypt_stream_chunked(
input_path, str(tmp_path / "out"), b"short", secrets.token_bytes(12)
)
def test_invalid_nonce_length(self, tmp_path):
input_path = str(tmp_path / "in")
Path(input_path).write_bytes(b"data")
with pytest.raises(ValueError, match="12 bytes"):
_rc.encrypt_stream_chunked(
input_path, str(tmp_path / "out"), secrets.token_bytes(32), b"short"
)
def test_wrong_key_fails_decrypt(self, tmp_path):
data = b"sensitive data"
key = secrets.token_bytes(32)
wrong_key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
input_path = str(tmp_path / "plaintext")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(data)
_rc.encrypt_stream_chunked(input_path, encrypted_path, key, base_nonce)
with pytest.raises((ValueError, OSError)):
_rc.decrypt_stream_chunked(
encrypted_path, decrypted_path, wrong_key, base_nonce
)
def test_cross_compat_python_encrypt_rust_decrypt(self, tmp_path):
from cryptography.hazmat.primitives.ciphers.aead import AESGCM
data = b"cross compat test data" * 100
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
chunk_size = 1024
encrypted_path = str(tmp_path / "py_encrypted")
with open(encrypted_path, "wb") as f:
f.write(b"\x00\x00\x00\x00")
aesgcm = AESGCM(key)
chunk_index = 0
offset = 0
while offset < len(data):
chunk = data[offset:offset + chunk_size]
nonce = self._python_derive_chunk_nonce(base_nonce, chunk_index)
enc = aesgcm.encrypt(nonce, chunk, None)
f.write(len(enc).to_bytes(4, "big"))
f.write(enc)
chunk_index += 1
offset += chunk_size
f.seek(0)
f.write(chunk_index.to_bytes(4, "big"))
decrypted_path = str(tmp_path / "rust_decrypted")
_rc.decrypt_stream_chunked(encrypted_path, decrypted_path, key, base_nonce)
assert Path(decrypted_path).read_bytes() == data
def test_cross_compat_rust_encrypt_python_decrypt(self, tmp_path):
from cryptography.hazmat.primitives.ciphers.aead import AESGCM
data = b"cross compat reverse test" * 100
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
chunk_size = 1024
input_path = str(tmp_path / "plaintext")
encrypted_path = str(tmp_path / "rust_encrypted")
Path(input_path).write_bytes(data)
chunk_count = _rc.encrypt_stream_chunked(
input_path, encrypted_path, key, base_nonce, chunk_size=chunk_size
)
aesgcm = AESGCM(key)
with open(encrypted_path, "rb") as f:
count_bytes = f.read(4)
assert int.from_bytes(count_bytes, "big") == chunk_count
decrypted = b""
for i in range(chunk_count):
size = int.from_bytes(f.read(4), "big")
enc_chunk = f.read(size)
nonce = self._python_derive_chunk_nonce(base_nonce, i)
decrypted += aesgcm.decrypt(nonce, enc_chunk, None)
assert decrypted == data
def test_large_file_roundtrip(self, tmp_path):
data = os.urandom(1024 * 1024)
key = secrets.token_bytes(32)
base_nonce = secrets.token_bytes(12)
input_path = str(tmp_path / "large")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(data)
_rc.encrypt_stream_chunked(input_path, encrypted_path, key, base_nonce)
_rc.decrypt_stream_chunked(encrypted_path, decrypted_path, key, base_nonce)
assert Path(decrypted_path).read_bytes() == data
class TestStreamingEncryptorFileMethods:
def test_encrypt_file_decrypt_file_roundtrip(self, tmp_path):
from app.encryption import LocalKeyEncryption, StreamingEncryptor
master_key_path = tmp_path / "master.key"
provider = LocalKeyEncryption(master_key_path)
encryptor = StreamingEncryptor(provider, chunk_size=512)
data = b"file method test data" * 200
input_path = str(tmp_path / "input")
encrypted_path = str(tmp_path / "encrypted")
decrypted_path = str(tmp_path / "decrypted")
Path(input_path).write_bytes(data)
metadata = encryptor.encrypt_file(input_path, encrypted_path)
assert metadata.algorithm == "AES256"
encryptor.decrypt_file(encrypted_path, decrypted_path, metadata)
assert Path(decrypted_path).read_bytes() == data
def test_encrypt_file_matches_encrypt_stream(self, tmp_path):
from app.encryption import LocalKeyEncryption, StreamingEncryptor
master_key_path = tmp_path / "master.key"
provider = LocalKeyEncryption(master_key_path)
encryptor = StreamingEncryptor(provider, chunk_size=512)
data = b"stream vs file comparison" * 100
input_path = str(tmp_path / "input")
Path(input_path).write_bytes(data)
file_encrypted_path = str(tmp_path / "file_enc")
metadata_file = encryptor.encrypt_file(input_path, file_encrypted_path)
file_decrypted_path = str(tmp_path / "file_dec")
encryptor.decrypt_file(file_encrypted_path, file_decrypted_path, metadata_file)
assert Path(file_decrypted_path).read_bytes() == data
stream_enc, metadata_stream = encryptor.encrypt_stream(io.BytesIO(data))
stream_dec = encryptor.decrypt_stream(stream_enc, metadata_stream)
assert stream_dec.read() == data