43 Commits

Author SHA1 Message Date
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
67f057ca1c Add static website hosting 2026-02-15 20:57:02 +08:00
35f61313e0 MyFSIO v0.2.8 Release
Reviewed-on: #20
2026-02-10 14:16:22 +00:00
01e79e6993 Fix object browser UI issues 2026-02-10 11:41:02 +08:00
1e3c4b545f Migrate UI backend from direct storage calls to S3 API proxy via boto3 2026-02-09 22:33:47 +08:00
c470cfb576 MyFSIO v0.2.7 Release
Reviewed-on: #19
2026-02-09 12:22:37 +00:00
4ecd32a554 Fix empty UI on large bucket first load: keep loading row during streaming, add progress indicator, throttle renders 2026-02-09 19:29:50 +08:00
aa6d7c4d28 Optimize replication failure caching, batch UI auth checks, add bulk download size limit, background parent cleanup 2026-02-09 18:23:45 +08:00
6e6d6d32bf Optimize KMS: cache AESGCM instance, remove duplicate get_provider 2026-02-09 17:01:19 +08:00
54705ab9c4 Fix Content-Length mismatch on range requests (206 Partial Content) 2026-02-06 16:14:35 +08:00
jun
d96955deee MyFSIO v0.2.6 Release
Reviewed-on: #18
2026-02-05 16:18:03 +00:00
77a46d0725 Binary run fix 2026-02-05 23:49:36 +08:00
0f750b9d89 Optimize object browser for large listings on slow networks 2026-02-05 22:56:00 +08:00
e0dee9db36 Fix UI object browser not showing objects uploaded via S3 API 2026-02-05 22:22:59 +08:00
126657c99f Further debugging of object browser object count delay 2026-02-05 21:45:02 +08:00
07fb1ac773 Fix cross-process cache invalidation on Windows using version counter instead of mtime 2026-02-05 21:32:40 +08:00
147962e1dd Further debugging of object browser object count delay 2026-02-05 21:18:35 +08:00
2643a79121 Debug object browser object count delay 2026-02-05 21:08:18 +08:00
e9a035827b Add _touch_cache_marker for UI object delay count issue 2026-02-05 20:56:42 +08:00
033b8a82be Fix error handlers for API mode; distinguish files from directories in object lookup; Fix UI not showing newly uploaded objects by adding Cache-Control headers 2026-02-05 20:44:11 +08:00
e76c311231 Update install/uninstall scripts with new config options and credential capture 2026-02-05 19:21:18 +08:00
cbdf1a27c8 Pin dockerfile python version to 3.14.3 2026-02-05 19:11:42 +08:00
4a60cb269a Update python version in Dockerfile 2026-02-05 19:11:00 +08:00
ebe7f6222d Fix hardcoded secret key ttl session 2026-02-05 19:08:18 +08:00
70b61fd8e6 Further optimize CPU usage; Improve security and performance; 4 bug fixes. 2026-02-05 17:45:34 +08:00
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
a779b002d7 Optimize CPU usage via caching and reducing ThreadPoolExecutor workers to prevent CPU saturation 2026-02-02 13:30:06 +08:00
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
45d21cce21 Add ALLOW_INTERNAL_ENDPOINTS config for self-hosted internal network deployments 2026-02-01 18:26:14 +08:00
9629507acd Fix auth bypass, user enumeration, xml DoS, multipart race, path traversal unicode, silent permissions failures, data key without AAD, KMS streaming 2026-02-01 18:12:03 +08:00
5d6cb4efa1 Update documentation 2026-02-01 15:18:20 +08:00
56ad83bbaf Fix bidirectional sync UI issues 2026-02-01 14:56:20 +08:00
847933b7c0 Add UI endpoint for bidirectional-status to fix 403 auth error 2026-02-01 14:30:55 +08:00
be55d08c0a Fix bidirectional-status 404 when UI runs separately from API 2026-02-01 14:23:35 +08:00
8c4bf67974 Fix 15 security vulnerabilities across auth, storage, and API modules 2026-01-31 00:55:27 +08:00
9385d1fe1c Add 4 new S3 APIs: UploadPartCopy, Bucket Replication, PostObject, SelectObjectContent 2026-01-29 12:51:00 +08:00
0ea54457e8 Fix 17 security vulnerabilities across encryption, auth, and API modules 2026-01-29 12:05:35 +08:00
ae26d22388 Add bidirectional replication setup verification and improved UX warnings 2026-01-26 23:29:20 +08:00
6b715851b9 Add replication setup wizard and site-level sync dashboard for site registry 2026-01-26 21:39:47 +08:00
62c36f7a6c Add site registry UI and update documentation for geo-distribution 2026-01-26 19:49:23 +08:00
b32f1f94f7 Add configurable env variables for hardcoded timeouts and limits 2026-01-25 23:32:36 +08:00
6e3d280a75 Add SlowDown error code tracking for 429 rate limit responses 2026-01-25 21:29:58 +08:00
704f79dc44 Add configurable rate limits for S3 API endpoints 2026-01-25 20:15:38 +08:00
47 changed files with 9701 additions and 1443 deletions

View File

@@ -1,12 +1,10 @@
# syntax=docker/dockerfile:1.7 FROM python:3.14.3-slim
FROM python:3.12.12-slim
ENV PYTHONDONTWRITEBYTECODE=1 \ ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 PYTHONUNBUFFERED=1
WORKDIR /app WORKDIR /app
# Install build deps for any wheels that need compilation, then clean up
RUN apt-get update \ RUN apt-get update \
&& apt-get install -y --no-install-recommends build-essential \ && apt-get install -y --no-install-recommends build-essential \
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*
@@ -16,10 +14,8 @@ RUN pip install --no-cache-dir -r requirements.txt
COPY . . COPY . .
# Make entrypoint executable
RUN chmod +x docker-entrypoint.sh RUN chmod +x docker-entrypoint.sh
# Create data directory and set permissions
RUN mkdir -p /app/data \ RUN mkdir -p /app/data \
&& useradd -m -u 1000 myfsio \ && useradd -m -u 1000 myfsio \
&& chown -R myfsio:myfsio /app && chown -R myfsio:myfsio /app

View File

@@ -102,6 +102,11 @@ python run.py --mode ui # UI only (port 5100)
| `ENCRYPTION_ENABLED` | `false` | Enable server-side encryption | | `ENCRYPTION_ENABLED` | `false` | Enable server-side encryption |
| `KMS_ENABLED` | `false` | Enable Key Management Service | | `KMS_ENABLED` | `false` | Enable Key Management Service |
| `LOG_LEVEL` | `INFO` | Logging verbosity | | `LOG_LEVEL` | `INFO` | Logging verbosity |
| `SIGV4_TIMESTAMP_TOLERANCE_SECONDS` | `900` | Max time skew for SigV4 requests |
| `PRESIGNED_URL_MAX_EXPIRY_SECONDS` | `604800` | Max presigned URL expiry (7 days) |
| `REPLICATION_CONNECT_TIMEOUT_SECONDS` | `5` | Replication connection timeout |
| `SITE_SYNC_ENABLED` | `false` | Enable bi-directional site sync |
| `OBJECT_TAG_LIMIT` | `50` | Maximum tags per object |
## Data Layout ## Data Layout

View File

@@ -1,6 +1,8 @@
from __future__ import annotations from __future__ import annotations
import html as html_module
import logging import logging
import mimetypes
import shutil import shutil
import sys import sys
import time import time
@@ -10,7 +12,7 @@ from pathlib import Path
from datetime import timedelta from datetime import timedelta
from typing import Any, Dict, List, Optional from typing import Any, Dict, List, Optional
from flask import Flask, g, has_request_context, redirect, render_template, request, url_for from flask import Flask, Response, g, has_request_context, redirect, render_template, request, url_for
from flask_cors import CORS from flask_cors import CORS
from flask_wtf.csrf import CSRFError from flask_wtf.csrf import CSRFError
from werkzeug.middleware.proxy_fix import ProxyFix from werkzeug.middleware.proxy_fix import ProxyFix
@@ -31,8 +33,10 @@ from .notifications import NotificationService
from .object_lock import ObjectLockService from .object_lock import ObjectLockService
from .replication import ReplicationManager from .replication import ReplicationManager
from .secret_store import EphemeralSecretStore from .secret_store import EphemeralSecretStore
from .storage import ObjectStorage from .site_registry import SiteRegistry, SiteInfo
from .storage import ObjectStorage, StorageError
from .version import get_version from .version import get_version
from .website_domains import WebsiteDomainStore
def _migrate_config_file(active_path: Path, legacy_paths: List[Path]) -> Path: def _migrate_config_file(active_path: Path, legacy_paths: List[Path]) -> Path:
@@ -104,6 +108,9 @@ def create_app(
storage = ObjectStorage( storage = ObjectStorage(
Path(app.config["STORAGE_ROOT"]), Path(app.config["STORAGE_ROOT"]),
cache_ttl=app.config.get("OBJECT_CACHE_TTL", 5), cache_ttl=app.config.get("OBJECT_CACHE_TTL", 5),
object_cache_max_size=app.config.get("OBJECT_CACHE_MAX_SIZE", 100),
bucket_config_cache_ttl=app.config.get("BUCKET_CONFIG_CACHE_TTL_SECONDS", 30.0),
object_key_max_length_bytes=app.config.get("OBJECT_KEY_MAX_LENGTH_BYTES", 1024),
) )
if app.config.get("WARM_CACHE_ON_STARTUP", True) and not app.config.get("TESTING"): if app.config.get("WARM_CACHE_ON_STARTUP", True) and not app.config.get("TESTING"):
@@ -137,12 +144,33 @@ def create_app(
) )
connections = ConnectionStore(connections_path) connections = ConnectionStore(connections_path)
replication = ReplicationManager(storage, connections, replication_rules_path, storage_root) replication = ReplicationManager(
storage,
connections,
replication_rules_path,
storage_root,
connect_timeout=app.config.get("REPLICATION_CONNECT_TIMEOUT_SECONDS", 5),
read_timeout=app.config.get("REPLICATION_READ_TIMEOUT_SECONDS", 30),
max_retries=app.config.get("REPLICATION_MAX_RETRIES", 2),
streaming_threshold_bytes=app.config.get("REPLICATION_STREAMING_THRESHOLD_BYTES", 10 * 1024 * 1024),
max_failures_per_bucket=app.config.get("REPLICATION_MAX_FAILURES_PER_BUCKET", 50),
)
site_registry_path = config_dir / "site_registry.json"
site_registry = SiteRegistry(site_registry_path)
if app.config.get("SITE_ID") and not site_registry.get_local_site():
site_registry.set_local_site(SiteInfo(
site_id=app.config["SITE_ID"],
endpoint=app.config.get("SITE_ENDPOINT") or "",
region=app.config.get("SITE_REGION", "us-east-1"),
priority=app.config.get("SITE_PRIORITY", 100),
))
encryption_config = { encryption_config = {
"encryption_enabled": app.config.get("ENCRYPTION_ENABLED", False), "encryption_enabled": app.config.get("ENCRYPTION_ENABLED", False),
"encryption_master_key_path": app.config.get("ENCRYPTION_MASTER_KEY_PATH"), "encryption_master_key_path": app.config.get("ENCRYPTION_MASTER_KEY_PATH"),
"default_encryption_algorithm": app.config.get("DEFAULT_ENCRYPTION_ALGORITHM", "AES256"), "default_encryption_algorithm": app.config.get("DEFAULT_ENCRYPTION_ALGORITHM", "AES256"),
"encryption_chunk_size_bytes": app.config.get("ENCRYPTION_CHUNK_SIZE_BYTES", 64 * 1024),
} }
encryption_manager = EncryptionManager(encryption_config) encryption_manager = EncryptionManager(encryption_config)
@@ -150,7 +178,12 @@ def create_app(
if app.config.get("KMS_ENABLED", False): if app.config.get("KMS_ENABLED", False):
kms_keys_path = Path(app.config.get("KMS_KEYS_PATH", "")) kms_keys_path = Path(app.config.get("KMS_KEYS_PATH", ""))
kms_master_key_path = Path(app.config.get("ENCRYPTION_MASTER_KEY_PATH", "")) kms_master_key_path = Path(app.config.get("ENCRYPTION_MASTER_KEY_PATH", ""))
kms_manager = KMSManager(kms_keys_path, kms_master_key_path) kms_manager = KMSManager(
kms_keys_path,
kms_master_key_path,
generate_data_key_min_bytes=app.config.get("KMS_GENERATE_DATA_KEY_MIN_BYTES", 1),
generate_data_key_max_bytes=app.config.get("KMS_GENERATE_DATA_KEY_MAX_BYTES", 1024),
)
encryption_manager.set_kms_provider(kms_manager) encryption_manager.set_kms_provider(kms_manager)
if app.config.get("ENCRYPTION_ENABLED", False): if app.config.get("ENCRYPTION_ENABLED", False):
@@ -159,7 +192,10 @@ def create_app(
acl_service = AclService(storage_root) acl_service = AclService(storage_root)
object_lock_service = ObjectLockService(storage_root) object_lock_service = ObjectLockService(storage_root)
notification_service = NotificationService(storage_root) notification_service = NotificationService(
storage_root,
allow_internal_endpoints=app.config.get("ALLOW_INTERNAL_ENDPOINTS", False),
)
access_logging_service = AccessLoggingService(storage_root) access_logging_service = AccessLoggingService(storage_root)
access_logging_service.set_storage(storage) access_logging_service.set_storage(storage)
@@ -170,6 +206,7 @@ def create_app(
base_storage, base_storage,
interval_seconds=app.config.get("LIFECYCLE_INTERVAL_SECONDS", 3600), interval_seconds=app.config.get("LIFECYCLE_INTERVAL_SECONDS", 3600),
storage_root=storage_root, storage_root=storage_root,
max_history_per_bucket=app.config.get("LIFECYCLE_MAX_HISTORY_PER_BUCKET", 50),
) )
lifecycle_manager.start() lifecycle_manager.start()
@@ -187,6 +224,20 @@ def create_app(
app.extensions["object_lock"] = object_lock_service app.extensions["object_lock"] = object_lock_service
app.extensions["notifications"] = notification_service app.extensions["notifications"] = notification_service
app.extensions["access_logging"] = access_logging_service app.extensions["access_logging"] = access_logging_service
app.extensions["site_registry"] = site_registry
website_domains_store = None
if app.config.get("WEBSITE_HOSTING_ENABLED", False):
website_domains_path = config_dir / "website_domains.json"
website_domains_store = WebsiteDomainStore(website_domains_path)
app.extensions["website_domains"] = website_domains_store
from .s3_client import S3ProxyClient
api_base = app.config.get("API_BASE_URL") or "http://127.0.0.1:5000"
app.extensions["s3_proxy"] = S3ProxyClient(
api_base_url=api_base,
region=app.config.get("AWS_REGION", "us-east-1"),
)
operation_metrics_collector = None operation_metrics_collector = None
if app.config.get("OPERATION_METRICS_ENABLED", False): if app.config.get("OPERATION_METRICS_ENABLED", False):
@@ -218,17 +269,47 @@ def create_app(
storage_root=storage_root, storage_root=storage_root,
interval_seconds=app.config.get("SITE_SYNC_INTERVAL_SECONDS", 60), interval_seconds=app.config.get("SITE_SYNC_INTERVAL_SECONDS", 60),
batch_size=app.config.get("SITE_SYNC_BATCH_SIZE", 100), batch_size=app.config.get("SITE_SYNC_BATCH_SIZE", 100),
connect_timeout=app.config.get("SITE_SYNC_CONNECT_TIMEOUT_SECONDS", 10),
read_timeout=app.config.get("SITE_SYNC_READ_TIMEOUT_SECONDS", 120),
max_retries=app.config.get("SITE_SYNC_MAX_RETRIES", 2),
clock_skew_tolerance_seconds=app.config.get("SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS", 1.0),
) )
site_sync_worker.start() site_sync_worker.start()
app.extensions["site_sync"] = site_sync_worker app.extensions["site_sync"] = site_sync_worker
@app.errorhandler(500) @app.errorhandler(500)
def internal_error(error): def internal_error(error):
wants_html = request.accept_mimetypes.accept_html
path = request.path or ""
if include_ui and wants_html and (path.startswith("/ui") or path == "/"):
return render_template('500.html'), 500 return render_template('500.html'), 500
error_xml = (
'<?xml version="1.0" encoding="UTF-8"?>'
'<Error>'
'<Code>InternalError</Code>'
'<Message>An internal server error occurred</Message>'
f'<Resource>{path}</Resource>'
f'<RequestId>{getattr(g, "request_id", "-")}</RequestId>'
'</Error>'
)
return error_xml, 500, {'Content-Type': 'application/xml'}
@app.errorhandler(CSRFError) @app.errorhandler(CSRFError)
def handle_csrf_error(e): def handle_csrf_error(e):
wants_html = request.accept_mimetypes.accept_html
path = request.path or ""
if include_ui and wants_html and (path.startswith("/ui") or path == "/"):
return render_template('csrf_error.html', reason=e.description), 400 return render_template('csrf_error.html', reason=e.description), 400
error_xml = (
'<?xml version="1.0" encoding="UTF-8"?>'
'<Error>'
'<Code>CSRFError</Code>'
f'<Message>{e.description}</Message>'
f'<Resource>{path}</Resource>'
f'<RequestId>{getattr(g, "request_id", "-")}</RequestId>'
'</Error>'
)
return error_xml, 400, {'Content-Type': 'application/xml'}
@app.template_filter("filesizeformat") @app.template_filter("filesizeformat")
def filesizeformat(value: int) -> str: def filesizeformat(value: int) -> str:
@@ -289,11 +370,14 @@ def create_app(
if include_api: if include_api:
from .s3_api import s3_api_bp from .s3_api import s3_api_bp
from .kms_api import kms_api_bp from .kms_api import kms_api_bp
from .admin_api import admin_api_bp
app.register_blueprint(s3_api_bp) app.register_blueprint(s3_api_bp)
app.register_blueprint(kms_api_bp) app.register_blueprint(kms_api_bp)
app.register_blueprint(admin_api_bp)
csrf.exempt(s3_api_bp) csrf.exempt(s3_api_bp)
csrf.exempt(kms_api_bp) csrf.exempt(kms_api_bp)
csrf.exempt(admin_api_bp)
if include_ui: if include_ui:
from .ui import ui_bp from .ui import ui_bp
@@ -397,6 +481,128 @@ def _configure_logging(app: Flask) -> None:
extra={"path": request.path, "method": request.method, "remote_addr": request.remote_addr}, extra={"path": request.path, "method": request.method, "remote_addr": request.remote_addr},
) )
@app.before_request
def _maybe_serve_website():
if not app.config.get("WEBSITE_HOSTING_ENABLED"):
return None
if request.method not in {"GET", "HEAD"}:
return None
host = request.host
if ":" in host:
host = host.rsplit(":", 1)[0]
host = host.lower()
store = app.extensions.get("website_domains")
if not store:
return None
bucket = store.get_bucket(host)
if not bucket:
return None
storage = app.extensions["object_storage"]
if not storage.bucket_exists(bucket):
return _website_error_response(404, "Not Found")
website_config = storage.get_bucket_website(bucket)
if not website_config:
return _website_error_response(404, "Not Found")
index_doc = website_config.get("index_document", "index.html")
error_doc = website_config.get("error_document")
req_path = request.path.lstrip("/")
if not req_path or req_path.endswith("/"):
object_key = req_path + index_doc
else:
object_key = req_path
try:
obj_path = storage.get_object_path(bucket, object_key)
except (StorageError, OSError):
if object_key == req_path:
try:
obj_path = storage.get_object_path(bucket, req_path + "/" + index_doc)
object_key = req_path + "/" + index_doc
except (StorageError, OSError):
return _serve_website_error(storage, bucket, error_doc, 404)
else:
return _serve_website_error(storage, bucket, error_doc, 404)
content_type = mimetypes.guess_type(object_key)[0] or "application/octet-stream"
is_encrypted = False
try:
metadata = storage.get_object_metadata(bucket, object_key)
is_encrypted = "x-amz-server-side-encryption" in metadata
except (StorageError, OSError):
pass
if request.method == "HEAD":
response = Response(status=200)
if is_encrypted and hasattr(storage, "get_object_data"):
try:
data, _ = storage.get_object_data(bucket, object_key)
response.headers["Content-Length"] = len(data)
except (StorageError, OSError):
return _website_error_response(500, "Internal Server Error")
else:
try:
stat = obj_path.stat()
response.headers["Content-Length"] = stat.st_size
except OSError:
return _website_error_response(500, "Internal Server Error")
response.headers["Content-Type"] = content_type
return response
if is_encrypted and hasattr(storage, "get_object_data"):
try:
data, _ = storage.get_object_data(bucket, object_key)
response = Response(data, mimetype=content_type)
response.headers["Content-Length"] = len(data)
return response
except (StorageError, OSError):
return _website_error_response(500, "Internal Server Error")
def _stream(file_path):
with file_path.open("rb") as f:
while True:
chunk = f.read(65536)
if not chunk:
break
yield chunk
try:
stat = obj_path.stat()
response = Response(_stream(obj_path), mimetype=content_type, direct_passthrough=True)
response.headers["Content-Length"] = stat.st_size
return response
except OSError:
return _website_error_response(500, "Internal Server Error")
def _serve_website_error(storage, bucket, error_doc_key, status_code):
if not error_doc_key:
return _website_error_response(status_code, "Not Found" if status_code == 404 else "Error")
try:
obj_path = storage.get_object_path(bucket, error_doc_key)
except (StorageError, OSError):
return _website_error_response(status_code, "Not Found")
content_type = mimetypes.guess_type(error_doc_key)[0] or "text/html"
is_encrypted = False
try:
metadata = storage.get_object_metadata(bucket, error_doc_key)
is_encrypted = "x-amz-server-side-encryption" in metadata
except (StorageError, OSError):
pass
if is_encrypted and hasattr(storage, "get_object_data"):
try:
data, _ = storage.get_object_data(bucket, error_doc_key)
response = Response(data, status=status_code, mimetype=content_type)
response.headers["Content-Length"] = len(data)
return response
except (StorageError, OSError):
return _website_error_response(status_code, "Not Found")
try:
data = obj_path.read_bytes()
response = Response(data, status=status_code, mimetype=content_type)
response.headers["Content-Length"] = len(data)
return response
except OSError:
return _website_error_response(status_code, "Not Found")
def _website_error_response(status_code, message):
safe_msg = html_module.escape(str(message))
safe_code = html_module.escape(str(status_code))
body = f"<html><head><title>{safe_code} {safe_msg}</title></head><body><h1>{safe_code} {safe_msg}</h1></body></html>"
return Response(body, status=status_code, mimetype="text/html")
@app.after_request @app.after_request
def _log_request_end(response): def _log_request_end(response):
duration_ms = 0.0 duration_ms = 0.0

771
app/admin_api.py Normal file
View File

@@ -0,0 +1,771 @@
from __future__ import annotations
import ipaddress
import json
import logging
import re
import socket
import time
from typing import Any, Dict, Optional, Tuple
from urllib.parse import urlparse
import requests
from flask import Blueprint, Response, current_app, jsonify, request
from .connections import ConnectionStore
from .extensions import limiter
from .iam import IamError, Principal
from .replication import ReplicationManager
from .site_registry import PeerSite, SiteInfo, SiteRegistry
from .website_domains import WebsiteDomainStore
def _is_safe_url(url: str, allow_internal: bool = False) -> bool:
"""Check if a URL is safe to make requests to (not internal/private).
Args:
url: The URL to check.
allow_internal: If True, allows internal/private IP addresses.
Use for self-hosted deployments on internal networks.
"""
try:
parsed = urlparse(url)
hostname = parsed.hostname
if not hostname:
return False
cloud_metadata_hosts = {
"metadata.google.internal",
"169.254.169.254",
}
if hostname.lower() in cloud_metadata_hosts:
return False
if allow_internal:
return True
blocked_hosts = {
"localhost",
"127.0.0.1",
"0.0.0.0",
"::1",
"[::1]",
}
if hostname.lower() in blocked_hosts:
return False
try:
resolved_ip = socket.gethostbyname(hostname)
ip = ipaddress.ip_address(resolved_ip)
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
return False
except (socket.gaierror, ValueError):
return False
return True
except Exception:
return False
def _validate_endpoint(endpoint: str) -> Optional[str]:
"""Validate endpoint URL format. Returns error message or None."""
try:
parsed = urlparse(endpoint)
if not parsed.scheme or parsed.scheme not in ("http", "https"):
return "Endpoint must be http or https URL"
if not parsed.netloc:
return "Endpoint must have a host"
return None
except Exception:
return "Invalid endpoint URL"
def _validate_priority(priority: Any) -> Optional[str]:
"""Validate priority value. Returns error message or None."""
try:
p = int(priority)
if p < 0 or p > 1000:
return "Priority must be between 0 and 1000"
return None
except (TypeError, ValueError):
return "Priority must be an integer"
def _validate_region(region: str) -> Optional[str]:
"""Validate region format. Returns error message or None."""
if not re.match(r"^[a-z]{2,}-[a-z]+-\d+$", region):
return "Region must match format like us-east-1"
return None
def _validate_site_id(site_id: str) -> Optional[str]:
"""Validate site_id format. Returns error message or None."""
if not site_id or len(site_id) > 63:
return "site_id must be 1-63 characters"
if not re.match(r'^[a-zA-Z0-9][a-zA-Z0-9_-]*$', site_id):
return "site_id must start with alphanumeric and contain only alphanumeric, hyphens, underscores"
return None
logger = logging.getLogger(__name__)
admin_api_bp = Blueprint("admin_api", __name__, url_prefix="/admin")
def _require_principal() -> Tuple[Optional[Principal], Optional[Tuple[Dict[str, Any], int]]]:
from .s3_api import _require_principal as s3_require_principal
return s3_require_principal()
def _require_admin() -> Tuple[Optional[Principal], Optional[Tuple[Dict[str, Any], int]]]:
principal, error = _require_principal()
if error:
return None, error
try:
_iam().authorize(principal, None, "iam:*")
return principal, None
except IamError:
return None, _json_error("AccessDenied", "Admin access required", 403)
def _site_registry() -> SiteRegistry:
return current_app.extensions["site_registry"]
def _connections() -> ConnectionStore:
return current_app.extensions["connections"]
def _replication() -> ReplicationManager:
return current_app.extensions["replication"]
def _iam():
return current_app.extensions["iam"]
def _json_error(code: str, message: str, status: int) -> Tuple[Dict[str, Any], int]:
return {"error": {"code": code, "message": message}}, status
def _get_admin_rate_limit() -> str:
return current_app.config.get("RATE_LIMIT_ADMIN", "60 per minute")
@admin_api_bp.route("/site", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def get_local_site():
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
local_site = registry.get_local_site()
if local_site:
return jsonify(local_site.to_dict())
config_site_id = current_app.config.get("SITE_ID")
config_endpoint = current_app.config.get("SITE_ENDPOINT")
if config_site_id:
return jsonify({
"site_id": config_site_id,
"endpoint": config_endpoint or "",
"region": current_app.config.get("SITE_REGION", "us-east-1"),
"priority": current_app.config.get("SITE_PRIORITY", 100),
"display_name": config_site_id,
"source": "environment",
})
return _json_error("NotFound", "Local site not configured", 404)
@admin_api_bp.route("/site", methods=["PUT"])
@limiter.limit(lambda: _get_admin_rate_limit())
def update_local_site():
principal, error = _require_admin()
if error:
return error
payload = request.get_json(silent=True) or {}
site_id = payload.get("site_id")
endpoint = payload.get("endpoint")
if not site_id:
return _json_error("ValidationError", "site_id is required", 400)
site_id_error = _validate_site_id(site_id)
if site_id_error:
return _json_error("ValidationError", site_id_error, 400)
if endpoint:
endpoint_error = _validate_endpoint(endpoint)
if endpoint_error:
return _json_error("ValidationError", endpoint_error, 400)
if "priority" in payload:
priority_error = _validate_priority(payload["priority"])
if priority_error:
return _json_error("ValidationError", priority_error, 400)
if "region" in payload:
region_error = _validate_region(payload["region"])
if region_error:
return _json_error("ValidationError", region_error, 400)
registry = _site_registry()
existing = registry.get_local_site()
site = SiteInfo(
site_id=site_id,
endpoint=endpoint or "",
region=payload.get("region", "us-east-1"),
priority=payload.get("priority", 100),
display_name=payload.get("display_name", site_id),
created_at=existing.created_at if existing else None,
)
registry.set_local_site(site)
logger.info("Local site updated", extra={"site_id": site_id, "principal": principal.access_key})
return jsonify(site.to_dict())
@admin_api_bp.route("/sites", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def list_all_sites():
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
local = registry.get_local_site()
peers = registry.list_peers()
result = {
"local": local.to_dict() if local else None,
"peers": [peer.to_dict() for peer in peers],
"total_peers": len(peers),
}
return jsonify(result)
@admin_api_bp.route("/sites", methods=["POST"])
@limiter.limit(lambda: _get_admin_rate_limit())
def register_peer_site():
principal, error = _require_admin()
if error:
return error
payload = request.get_json(silent=True) or {}
site_id = payload.get("site_id")
endpoint = payload.get("endpoint")
if not site_id:
return _json_error("ValidationError", "site_id is required", 400)
site_id_error = _validate_site_id(site_id)
if site_id_error:
return _json_error("ValidationError", site_id_error, 400)
if not endpoint:
return _json_error("ValidationError", "endpoint is required", 400)
endpoint_error = _validate_endpoint(endpoint)
if endpoint_error:
return _json_error("ValidationError", endpoint_error, 400)
region = payload.get("region", "us-east-1")
region_error = _validate_region(region)
if region_error:
return _json_error("ValidationError", region_error, 400)
priority = payload.get("priority", 100)
priority_error = _validate_priority(priority)
if priority_error:
return _json_error("ValidationError", priority_error, 400)
registry = _site_registry()
if registry.get_peer(site_id):
return _json_error("AlreadyExists", f"Peer site '{site_id}' already exists", 409)
connection_id = payload.get("connection_id")
if connection_id:
if not _connections().get(connection_id):
return _json_error("ValidationError", f"Connection '{connection_id}' not found", 400)
peer = PeerSite(
site_id=site_id,
endpoint=endpoint,
region=region,
priority=int(priority),
display_name=payload.get("display_name", site_id),
connection_id=connection_id,
)
registry.add_peer(peer)
logger.info("Peer site registered", extra={"site_id": site_id, "principal": principal.access_key})
return jsonify(peer.to_dict()), 201
@admin_api_bp.route("/sites/<site_id>", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def get_peer_site(site_id: str):
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
peer = registry.get_peer(site_id)
if not peer:
return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
return jsonify(peer.to_dict())
@admin_api_bp.route("/sites/<site_id>", methods=["PUT"])
@limiter.limit(lambda: _get_admin_rate_limit())
def update_peer_site(site_id: str):
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
existing = registry.get_peer(site_id)
if not existing:
return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
payload = request.get_json(silent=True) or {}
if "endpoint" in payload:
endpoint_error = _validate_endpoint(payload["endpoint"])
if endpoint_error:
return _json_error("ValidationError", endpoint_error, 400)
if "priority" in payload:
priority_error = _validate_priority(payload["priority"])
if priority_error:
return _json_error("ValidationError", priority_error, 400)
if "region" in payload:
region_error = _validate_region(payload["region"])
if region_error:
return _json_error("ValidationError", region_error, 400)
if "connection_id" in payload:
if payload["connection_id"] and not _connections().get(payload["connection_id"]):
return _json_error("ValidationError", f"Connection '{payload['connection_id']}' not found", 400)
peer = PeerSite(
site_id=site_id,
endpoint=payload.get("endpoint", existing.endpoint),
region=payload.get("region", existing.region),
priority=payload.get("priority", existing.priority),
display_name=payload.get("display_name", existing.display_name),
connection_id=payload.get("connection_id", existing.connection_id),
created_at=existing.created_at,
is_healthy=existing.is_healthy,
last_health_check=existing.last_health_check,
)
registry.update_peer(peer)
logger.info("Peer site updated", extra={"site_id": site_id, "principal": principal.access_key})
return jsonify(peer.to_dict())
@admin_api_bp.route("/sites/<site_id>", methods=["DELETE"])
@limiter.limit(lambda: _get_admin_rate_limit())
def delete_peer_site(site_id: str):
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
if not registry.delete_peer(site_id):
return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
logger.info("Peer site deleted", extra={"site_id": site_id, "principal": principal.access_key})
return Response(status=204)
@admin_api_bp.route("/sites/<site_id>/health", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def check_peer_health(site_id: str):
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
peer = registry.get_peer(site_id)
if not peer:
return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
is_healthy = False
error_message = None
if peer.connection_id:
connection = _connections().get(peer.connection_id)
if connection:
is_healthy = _replication().check_endpoint_health(connection)
else:
error_message = f"Connection '{peer.connection_id}' not found"
else:
error_message = "No connection configured for this peer"
registry.update_health(site_id, is_healthy)
result = {
"site_id": site_id,
"is_healthy": is_healthy,
"checked_at": time.time(),
}
if error_message:
result["error"] = error_message
return jsonify(result)
@admin_api_bp.route("/topology", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def get_topology():
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
local = registry.get_local_site()
peers = registry.list_peers()
sites = []
if local:
sites.append({
**local.to_dict(),
"is_local": True,
"is_healthy": True,
})
for peer in peers:
sites.append({
**peer.to_dict(),
"is_local": False,
})
sites.sort(key=lambda s: s.get("priority", 100))
return jsonify({
"sites": sites,
"total": len(sites),
"healthy_count": sum(1 for s in sites if s.get("is_healthy")),
})
@admin_api_bp.route("/sites/<site_id>/bidirectional-status", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def check_bidirectional_status(site_id: str):
principal, error = _require_admin()
if error:
return error
registry = _site_registry()
peer = registry.get_peer(site_id)
if not peer:
return _json_error("NotFound", f"Peer site '{site_id}' not found", 404)
local_site = registry.get_local_site()
replication = _replication()
local_rules = replication.list_rules()
local_bidir_rules = []
for rule in local_rules:
if rule.target_connection_id == peer.connection_id and rule.mode == "bidirectional":
local_bidir_rules.append({
"bucket_name": rule.bucket_name,
"target_bucket": rule.target_bucket,
"enabled": rule.enabled,
})
result = {
"site_id": site_id,
"local_site_id": local_site.site_id if local_site else None,
"local_endpoint": local_site.endpoint if local_site else None,
"local_bidirectional_rules": local_bidir_rules,
"local_site_sync_enabled": current_app.config.get("SITE_SYNC_ENABLED", False),
"remote_status": None,
"issues": [],
"is_fully_configured": False,
}
if not local_site or not local_site.site_id:
result["issues"].append({
"code": "NO_LOCAL_SITE_ID",
"message": "Local site identity not configured",
"severity": "error",
})
if not local_site or not local_site.endpoint:
result["issues"].append({
"code": "NO_LOCAL_ENDPOINT",
"message": "Local site endpoint not configured (remote site cannot reach back)",
"severity": "error",
})
if not peer.connection_id:
result["issues"].append({
"code": "NO_CONNECTION",
"message": "No connection configured for this peer",
"severity": "error",
})
return jsonify(result)
connection = _connections().get(peer.connection_id)
if not connection:
result["issues"].append({
"code": "CONNECTION_NOT_FOUND",
"message": f"Connection '{peer.connection_id}' not found",
"severity": "error",
})
return jsonify(result)
if not local_bidir_rules:
result["issues"].append({
"code": "NO_LOCAL_BIDIRECTIONAL_RULES",
"message": "No bidirectional replication rules configured on this site",
"severity": "warning",
})
if not result["local_site_sync_enabled"]:
result["issues"].append({
"code": "SITE_SYNC_DISABLED",
"message": "Site sync worker is disabled (SITE_SYNC_ENABLED=false). Pull operations will not work.",
"severity": "warning",
})
if not replication.check_endpoint_health(connection):
result["issues"].append({
"code": "REMOTE_UNREACHABLE",
"message": "Remote endpoint is not reachable",
"severity": "error",
})
return jsonify(result)
allow_internal = current_app.config.get("ALLOW_INTERNAL_ENDPOINTS", False)
if not _is_safe_url(peer.endpoint, allow_internal=allow_internal):
result["issues"].append({
"code": "ENDPOINT_NOT_ALLOWED",
"message": "Peer endpoint points to cloud metadata service (SSRF protection)",
"severity": "error",
})
return jsonify(result)
try:
admin_url = peer.endpoint.rstrip("/") + "/admin/sites"
resp = requests.get(
admin_url,
timeout=10,
headers={
"Accept": "application/json",
"X-Access-Key": connection.access_key,
"X-Secret-Key": connection.secret_key,
},
)
if resp.status_code == 200:
try:
remote_data = resp.json()
if not isinstance(remote_data, dict):
raise ValueError("Expected JSON object")
remote_local = remote_data.get("local")
if remote_local is not None and not isinstance(remote_local, dict):
raise ValueError("Expected 'local' to be an object")
remote_peers = remote_data.get("peers", [])
if not isinstance(remote_peers, list):
raise ValueError("Expected 'peers' to be a list")
except (ValueError, json.JSONDecodeError) as e:
logger.warning("Invalid JSON from remote admin API: %s", e)
result["remote_status"] = {"reachable": True, "invalid_response": True}
result["issues"].append({
"code": "REMOTE_INVALID_RESPONSE",
"message": "Remote admin API returned invalid JSON",
"severity": "warning",
})
return jsonify(result)
result["remote_status"] = {
"reachable": True,
"local_site": remote_local,
"site_sync_enabled": None,
"has_peer_for_us": False,
"peer_connection_configured": False,
"has_bidirectional_rules_for_us": False,
}
for rp in remote_peers:
if not isinstance(rp, dict):
continue
if local_site and (
rp.get("site_id") == local_site.site_id or
rp.get("endpoint") == local_site.endpoint
):
result["remote_status"]["has_peer_for_us"] = True
result["remote_status"]["peer_connection_configured"] = bool(rp.get("connection_id"))
break
if not result["remote_status"]["has_peer_for_us"]:
result["issues"].append({
"code": "REMOTE_NO_PEER_FOR_US",
"message": "Remote site does not have this site registered as a peer",
"severity": "error",
})
elif not result["remote_status"]["peer_connection_configured"]:
result["issues"].append({
"code": "REMOTE_NO_CONNECTION_FOR_US",
"message": "Remote site has us as peer but no connection configured (cannot push back)",
"severity": "error",
})
elif resp.status_code == 401 or resp.status_code == 403:
result["remote_status"] = {
"reachable": True,
"admin_access_denied": True,
}
result["issues"].append({
"code": "REMOTE_ADMIN_ACCESS_DENIED",
"message": "Cannot verify remote configuration (admin access denied)",
"severity": "warning",
})
else:
result["remote_status"] = {
"reachable": True,
"admin_api_error": resp.status_code,
}
result["issues"].append({
"code": "REMOTE_ADMIN_API_ERROR",
"message": f"Remote admin API returned status {resp.status_code}",
"severity": "warning",
})
except requests.RequestException as e:
logger.warning("Remote admin API unreachable: %s", e)
result["remote_status"] = {
"reachable": False,
"error": "Connection failed",
}
result["issues"].append({
"code": "REMOTE_ADMIN_UNREACHABLE",
"message": "Could not reach remote admin API",
"severity": "warning",
})
except Exception as e:
logger.warning("Error checking remote bidirectional status: %s", e, exc_info=True)
result["issues"].append({
"code": "VERIFICATION_ERROR",
"message": "Internal error during verification",
"severity": "warning",
})
error_issues = [i for i in result["issues"] if i["severity"] == "error"]
result["is_fully_configured"] = len(error_issues) == 0 and len(local_bidir_rules) > 0
return jsonify(result)
def _website_domains() -> WebsiteDomainStore:
return current_app.extensions["website_domains"]
def _storage():
return current_app.extensions["object_storage"]
@admin_api_bp.route("/website-domains", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def list_website_domains():
principal, error = _require_admin()
if error:
return error
if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
return jsonify(_website_domains().list_all())
@admin_api_bp.route("/website-domains", methods=["POST"])
@limiter.limit(lambda: _get_admin_rate_limit())
def create_website_domain():
principal, error = _require_admin()
if error:
return error
if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
payload = request.get_json(silent=True) or {}
domain = (payload.get("domain") or "").strip().lower()
bucket = (payload.get("bucket") or "").strip()
if not domain:
return _json_error("ValidationError", "domain is required", 400)
if not bucket:
return _json_error("ValidationError", "bucket is required", 400)
storage = _storage()
if not storage.bucket_exists(bucket):
return _json_error("NoSuchBucket", f"Bucket '{bucket}' does not exist", 404)
store = _website_domains()
existing = store.get_bucket(domain)
if existing:
return _json_error("Conflict", f"Domain '{domain}' is already mapped to bucket '{existing}'", 409)
store.set_mapping(domain, bucket)
logger.info("Website domain mapping created: %s -> %s", domain, bucket)
return jsonify({"domain": domain, "bucket": bucket}), 201
@admin_api_bp.route("/website-domains/<domain>", methods=["GET"])
@limiter.limit(lambda: _get_admin_rate_limit())
def get_website_domain(domain: str):
principal, error = _require_admin()
if error:
return error
if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
bucket = _website_domains().get_bucket(domain)
if not bucket:
return _json_error("NotFound", f"No mapping found for domain '{domain}'", 404)
return jsonify({"domain": domain.lower(), "bucket": bucket})
@admin_api_bp.route("/website-domains/<domain>", methods=["PUT"])
@limiter.limit(lambda: _get_admin_rate_limit())
def update_website_domain(domain: str):
principal, error = _require_admin()
if error:
return error
if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
payload = request.get_json(silent=True) or {}
bucket = (payload.get("bucket") or "").strip()
if not bucket:
return _json_error("ValidationError", "bucket is required", 400)
storage = _storage()
if not storage.bucket_exists(bucket):
return _json_error("NoSuchBucket", f"Bucket '{bucket}' does not exist", 404)
store = _website_domains()
store.set_mapping(domain, bucket)
logger.info("Website domain mapping updated: %s -> %s", domain, bucket)
return jsonify({"domain": domain.lower(), "bucket": bucket})
@admin_api_bp.route("/website-domains/<domain>", methods=["DELETE"])
@limiter.limit(lambda: _get_admin_rate_limit())
def delete_website_domain(domain: str):
principal, error = _require_admin()
if error:
return error
if not current_app.config.get("WEBSITE_HOSTING_ENABLED", False):
return _json_error("InvalidRequest", "Website hosting is not enabled", 400)
if not _website_domains().delete_mapping(domain):
return _json_error("NotFound", f"No mapping found for domain '{domain}'", 404)
logger.info("Website domain mapping deleted: %s", domain)
return Response(status=204)

View File

@@ -6,6 +6,7 @@ import re
import time import time
from dataclasses import dataclass, field from dataclasses import dataclass, field
from fnmatch import fnmatch, translate from fnmatch import fnmatch, translate
from functools import lru_cache
from pathlib import Path from pathlib import Path
from typing import Any, Dict, Iterable, List, Optional, Pattern, Sequence, Tuple from typing import Any, Dict, Iterable, List, Optional, Pattern, Sequence, Tuple
@@ -13,9 +14,14 @@ from typing import Any, Dict, Iterable, List, Optional, Pattern, Sequence, Tuple
RESOURCE_PREFIX = "arn:aws:s3:::" RESOURCE_PREFIX = "arn:aws:s3:::"
@lru_cache(maxsize=256)
def _compile_pattern(pattern: str) -> Pattern[str]:
return re.compile(translate(pattern), re.IGNORECASE)
def _match_string_like(value: str, pattern: str) -> bool: def _match_string_like(value: str, pattern: str) -> bool:
regex = translate(pattern) compiled = _compile_pattern(pattern)
return bool(re.match(regex, value, re.IGNORECASE)) return bool(compiled.match(value))
def _ip_in_cidr(ip_str: str, cidr: str) -> bool: def _ip_in_cidr(ip_str: str, cidr: str) -> bool:

View File

@@ -36,10 +36,11 @@ class GzipMiddleware:
content_type = None content_type = None
content_length = None content_length = None
should_compress = False should_compress = False
passthrough = False
exc_info_holder = [None] exc_info_holder = [None]
def custom_start_response(status: str, headers: List[Tuple[str, str]], exc_info=None): def custom_start_response(status: str, headers: List[Tuple[str, str]], exc_info=None):
nonlocal response_started, status_code, response_headers, content_type, content_length, should_compress nonlocal response_started, status_code, response_headers, content_type, content_length, should_compress, passthrough
response_started = True response_started = True
status_code = int(status.split(' ', 1)[0]) status_code = int(status.split(' ', 1)[0])
response_headers = list(headers) response_headers = list(headers)
@@ -50,18 +51,32 @@ class GzipMiddleware:
if name_lower == 'content-type': if name_lower == 'content-type':
content_type = value.split(';')[0].strip().lower() content_type = value.split(';')[0].strip().lower()
elif name_lower == 'content-length': elif name_lower == 'content-length':
try:
content_length = int(value) content_length = int(value)
except (ValueError, TypeError):
pass
elif name_lower == 'content-encoding': elif name_lower == 'content-encoding':
should_compress = False passthrough = True
return start_response(status, headers, exc_info)
elif name_lower == 'x-stream-response':
passthrough = True
return start_response(status, headers, exc_info) return start_response(status, headers, exc_info)
if content_type and content_type in COMPRESSIBLE_MIMES: if content_type and content_type in COMPRESSIBLE_MIMES:
if content_length is None or content_length >= self.min_size: if content_length is None or content_length >= self.min_size:
should_compress = True should_compress = True
else:
passthrough = True
return start_response(status, headers, exc_info)
return None return None
response_body = b''.join(self.app(environ, custom_start_response)) app_iter = self.app(environ, custom_start_response)
if passthrough:
return app_iter
response_body = b''.join(app_iter)
if not response_started: if not response_started:
return [response_body] return [response_body]

View File

@@ -10,6 +10,23 @@ from dataclasses import dataclass
from pathlib import Path from pathlib import Path
from typing import Any, Dict, Optional from typing import Any, Dict, Optional
import psutil
def _calculate_auto_threads() -> int:
cpu_count = psutil.cpu_count(logical=True) or 4
return max(1, min(cpu_count * 2, 64))
def _calculate_auto_connection_limit() -> int:
available_mb = psutil.virtual_memory().available / (1024 * 1024)
calculated = int(available_mb / 5)
return max(20, min(calculated, 1000))
def _calculate_auto_backlog(connection_limit: int) -> int:
return max(64, min(connection_limit * 2, 4096))
def _validate_rate_limit(value: str) -> str: def _validate_rate_limit(value: str) -> str:
pattern = r"^\d+\s+per\s+(second|minute|hour|day)$" pattern = r"^\d+\s+per\s+(second|minute|hour|day)$"
@@ -63,6 +80,10 @@ class AppConfig:
log_backup_count: int log_backup_count: int
ratelimit_default: str ratelimit_default: str
ratelimit_storage_uri: str ratelimit_storage_uri: str
ratelimit_list_buckets: str
ratelimit_bucket_ops: str
ratelimit_object_ops: str
ratelimit_head_ops: str
cors_origins: list[str] cors_origins: list[str]
cors_methods: list[str] cors_methods: list[str]
cors_allow_headers: list[str] cors_allow_headers: list[str]
@@ -94,9 +115,41 @@ class AppConfig:
server_connection_limit: int server_connection_limit: int
server_backlog: int server_backlog: int
server_channel_timeout: int server_channel_timeout: int
server_threads_auto: bool
server_connection_limit_auto: bool
server_backlog_auto: bool
site_sync_enabled: bool site_sync_enabled: bool
site_sync_interval_seconds: int site_sync_interval_seconds: int
site_sync_batch_size: int site_sync_batch_size: int
sigv4_timestamp_tolerance_seconds: int
presigned_url_min_expiry_seconds: int
presigned_url_max_expiry_seconds: int
replication_connect_timeout_seconds: int
replication_read_timeout_seconds: int
replication_max_retries: int
replication_streaming_threshold_bytes: int
replication_max_failures_per_bucket: int
site_sync_connect_timeout_seconds: int
site_sync_read_timeout_seconds: int
site_sync_max_retries: int
site_sync_clock_skew_tolerance_seconds: float
object_key_max_length_bytes: int
object_cache_max_size: int
bucket_config_cache_ttl_seconds: float
object_tag_limit: int
encryption_chunk_size_bytes: int
kms_generate_data_key_min_bytes: int
kms_generate_data_key_max_bytes: int
lifecycle_max_history_per_bucket: int
site_id: Optional[str]
site_endpoint: Optional[str]
site_region: str
site_priority: int
ratelimit_admin: str
num_trusted_proxies: int
allowed_redirect_hosts: list[str]
allow_internal_endpoints: bool
website_hosting_enabled: bool
@classmethod @classmethod
def from_env(cls, overrides: Optional[Dict[str, Any]] = None) -> "AppConfig": def from_env(cls, overrides: Optional[Dict[str, Any]] = None) -> "AppConfig":
@@ -171,6 +224,10 @@ class AppConfig:
log_backup_count = int(_get("LOG_BACKUP_COUNT", 3)) log_backup_count = int(_get("LOG_BACKUP_COUNT", 3))
ratelimit_default = _validate_rate_limit(str(_get("RATE_LIMIT_DEFAULT", "200 per minute"))) ratelimit_default = _validate_rate_limit(str(_get("RATE_LIMIT_DEFAULT", "200 per minute")))
ratelimit_storage_uri = str(_get("RATE_LIMIT_STORAGE_URI", "memory://")) ratelimit_storage_uri = str(_get("RATE_LIMIT_STORAGE_URI", "memory://"))
ratelimit_list_buckets = _validate_rate_limit(str(_get("RATE_LIMIT_LIST_BUCKETS", "60 per minute")))
ratelimit_bucket_ops = _validate_rate_limit(str(_get("RATE_LIMIT_BUCKET_OPS", "120 per minute")))
ratelimit_object_ops = _validate_rate_limit(str(_get("RATE_LIMIT_OBJECT_OPS", "240 per minute")))
ratelimit_head_ops = _validate_rate_limit(str(_get("RATE_LIMIT_HEAD_OPS", "100 per minute")))
def _csv(value: str, default: list[str]) -> list[str]: def _csv(value: str, default: list[str]) -> list[str]:
if not value: if not value:
@@ -200,14 +257,69 @@ class AppConfig:
operation_metrics_interval_minutes = int(_get("OPERATION_METRICS_INTERVAL_MINUTES", 5)) operation_metrics_interval_minutes = int(_get("OPERATION_METRICS_INTERVAL_MINUTES", 5))
operation_metrics_retention_hours = int(_get("OPERATION_METRICS_RETENTION_HOURS", 24)) operation_metrics_retention_hours = int(_get("OPERATION_METRICS_RETENTION_HOURS", 24))
server_threads = int(_get("SERVER_THREADS", 4)) _raw_threads = int(_get("SERVER_THREADS", 0))
server_connection_limit = int(_get("SERVER_CONNECTION_LIMIT", 100)) if _raw_threads == 0:
server_backlog = int(_get("SERVER_BACKLOG", 1024)) server_threads = _calculate_auto_threads()
server_threads_auto = True
else:
server_threads = _raw_threads
server_threads_auto = False
_raw_conn_limit = int(_get("SERVER_CONNECTION_LIMIT", 0))
if _raw_conn_limit == 0:
server_connection_limit = _calculate_auto_connection_limit()
server_connection_limit_auto = True
else:
server_connection_limit = _raw_conn_limit
server_connection_limit_auto = False
_raw_backlog = int(_get("SERVER_BACKLOG", 0))
if _raw_backlog == 0:
server_backlog = _calculate_auto_backlog(server_connection_limit)
server_backlog_auto = True
else:
server_backlog = _raw_backlog
server_backlog_auto = False
server_channel_timeout = int(_get("SERVER_CHANNEL_TIMEOUT", 120)) server_channel_timeout = int(_get("SERVER_CHANNEL_TIMEOUT", 120))
site_sync_enabled = str(_get("SITE_SYNC_ENABLED", "0")).lower() in {"1", "true", "yes", "on"} site_sync_enabled = str(_get("SITE_SYNC_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
site_sync_interval_seconds = int(_get("SITE_SYNC_INTERVAL_SECONDS", 60)) site_sync_interval_seconds = int(_get("SITE_SYNC_INTERVAL_SECONDS", 60))
site_sync_batch_size = int(_get("SITE_SYNC_BATCH_SIZE", 100)) site_sync_batch_size = int(_get("SITE_SYNC_BATCH_SIZE", 100))
sigv4_timestamp_tolerance_seconds = int(_get("SIGV4_TIMESTAMP_TOLERANCE_SECONDS", 900))
presigned_url_min_expiry_seconds = int(_get("PRESIGNED_URL_MIN_EXPIRY_SECONDS", 1))
presigned_url_max_expiry_seconds = int(_get("PRESIGNED_URL_MAX_EXPIRY_SECONDS", 604800))
replication_connect_timeout_seconds = int(_get("REPLICATION_CONNECT_TIMEOUT_SECONDS", 5))
replication_read_timeout_seconds = int(_get("REPLICATION_READ_TIMEOUT_SECONDS", 30))
replication_max_retries = int(_get("REPLICATION_MAX_RETRIES", 2))
replication_streaming_threshold_bytes = int(_get("REPLICATION_STREAMING_THRESHOLD_BYTES", 10 * 1024 * 1024))
replication_max_failures_per_bucket = int(_get("REPLICATION_MAX_FAILURES_PER_BUCKET", 50))
site_sync_connect_timeout_seconds = int(_get("SITE_SYNC_CONNECT_TIMEOUT_SECONDS", 10))
site_sync_read_timeout_seconds = int(_get("SITE_SYNC_READ_TIMEOUT_SECONDS", 120))
site_sync_max_retries = int(_get("SITE_SYNC_MAX_RETRIES", 2))
site_sync_clock_skew_tolerance_seconds = float(_get("SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS", 1.0))
object_key_max_length_bytes = int(_get("OBJECT_KEY_MAX_LENGTH_BYTES", 1024))
object_cache_max_size = int(_get("OBJECT_CACHE_MAX_SIZE", 100))
bucket_config_cache_ttl_seconds = float(_get("BUCKET_CONFIG_CACHE_TTL_SECONDS", 30.0))
object_tag_limit = int(_get("OBJECT_TAG_LIMIT", 50))
encryption_chunk_size_bytes = int(_get("ENCRYPTION_CHUNK_SIZE_BYTES", 64 * 1024))
kms_generate_data_key_min_bytes = int(_get("KMS_GENERATE_DATA_KEY_MIN_BYTES", 1))
kms_generate_data_key_max_bytes = int(_get("KMS_GENERATE_DATA_KEY_MAX_BYTES", 1024))
lifecycle_max_history_per_bucket = int(_get("LIFECYCLE_MAX_HISTORY_PER_BUCKET", 50))
site_id_raw = _get("SITE_ID", None)
site_id = str(site_id_raw).strip() if site_id_raw else None
site_endpoint_raw = _get("SITE_ENDPOINT", None)
site_endpoint = str(site_endpoint_raw).strip() if site_endpoint_raw else None
site_region = str(_get("SITE_REGION", "us-east-1"))
site_priority = int(_get("SITE_PRIORITY", 100))
ratelimit_admin = _validate_rate_limit(str(_get("RATE_LIMIT_ADMIN", "60 per minute")))
num_trusted_proxies = int(_get("NUM_TRUSTED_PROXIES", 0))
allowed_redirect_hosts_raw = _get("ALLOWED_REDIRECT_HOSTS", "")
allowed_redirect_hosts = [h.strip() for h in str(allowed_redirect_hosts_raw).split(",") if h.strip()]
allow_internal_endpoints = str(_get("ALLOW_INTERNAL_ENDPOINTS", "0")).lower() in {"1", "true", "yes", "on"}
website_hosting_enabled = str(_get("WEBSITE_HOSTING_ENABLED", "0")).lower() in {"1", "true", "yes", "on"}
return cls(storage_root=storage_root, return cls(storage_root=storage_root,
max_upload_size=max_upload_size, max_upload_size=max_upload_size,
ui_page_size=ui_page_size, ui_page_size=ui_page_size,
@@ -225,6 +337,10 @@ class AppConfig:
log_backup_count=log_backup_count, log_backup_count=log_backup_count,
ratelimit_default=ratelimit_default, ratelimit_default=ratelimit_default,
ratelimit_storage_uri=ratelimit_storage_uri, ratelimit_storage_uri=ratelimit_storage_uri,
ratelimit_list_buckets=ratelimit_list_buckets,
ratelimit_bucket_ops=ratelimit_bucket_ops,
ratelimit_object_ops=ratelimit_object_ops,
ratelimit_head_ops=ratelimit_head_ops,
cors_origins=cors_origins, cors_origins=cors_origins,
cors_methods=cors_methods, cors_methods=cors_methods,
cors_allow_headers=cors_allow_headers, cors_allow_headers=cors_allow_headers,
@@ -256,9 +372,41 @@ class AppConfig:
server_connection_limit=server_connection_limit, server_connection_limit=server_connection_limit,
server_backlog=server_backlog, server_backlog=server_backlog,
server_channel_timeout=server_channel_timeout, server_channel_timeout=server_channel_timeout,
server_threads_auto=server_threads_auto,
server_connection_limit_auto=server_connection_limit_auto,
server_backlog_auto=server_backlog_auto,
site_sync_enabled=site_sync_enabled, site_sync_enabled=site_sync_enabled,
site_sync_interval_seconds=site_sync_interval_seconds, site_sync_interval_seconds=site_sync_interval_seconds,
site_sync_batch_size=site_sync_batch_size) site_sync_batch_size=site_sync_batch_size,
sigv4_timestamp_tolerance_seconds=sigv4_timestamp_tolerance_seconds,
presigned_url_min_expiry_seconds=presigned_url_min_expiry_seconds,
presigned_url_max_expiry_seconds=presigned_url_max_expiry_seconds,
replication_connect_timeout_seconds=replication_connect_timeout_seconds,
replication_read_timeout_seconds=replication_read_timeout_seconds,
replication_max_retries=replication_max_retries,
replication_streaming_threshold_bytes=replication_streaming_threshold_bytes,
replication_max_failures_per_bucket=replication_max_failures_per_bucket,
site_sync_connect_timeout_seconds=site_sync_connect_timeout_seconds,
site_sync_read_timeout_seconds=site_sync_read_timeout_seconds,
site_sync_max_retries=site_sync_max_retries,
site_sync_clock_skew_tolerance_seconds=site_sync_clock_skew_tolerance_seconds,
object_key_max_length_bytes=object_key_max_length_bytes,
object_cache_max_size=object_cache_max_size,
bucket_config_cache_ttl_seconds=bucket_config_cache_ttl_seconds,
object_tag_limit=object_tag_limit,
encryption_chunk_size_bytes=encryption_chunk_size_bytes,
kms_generate_data_key_min_bytes=kms_generate_data_key_min_bytes,
kms_generate_data_key_max_bytes=kms_generate_data_key_max_bytes,
lifecycle_max_history_per_bucket=lifecycle_max_history_per_bucket,
site_id=site_id,
site_endpoint=site_endpoint,
site_region=site_region,
site_priority=site_priority,
ratelimit_admin=ratelimit_admin,
num_trusted_proxies=num_trusted_proxies,
allowed_redirect_hosts=allowed_redirect_hosts,
allow_internal_endpoints=allow_internal_endpoints,
website_hosting_enabled=website_hosting_enabled)
def validate_and_report(self) -> list[str]: def validate_and_report(self) -> list[str]:
"""Validate configuration and return a list of warnings/issues. """Validate configuration and return a list of warnings/issues.
@@ -364,9 +512,13 @@ class AppConfig:
print(f" ENCRYPTION: Enabled (Master key: {self.encryption_master_key_path})") print(f" ENCRYPTION: Enabled (Master key: {self.encryption_master_key_path})")
if self.kms_enabled: if self.kms_enabled:
print(f" KMS: Enabled (Keys: {self.kms_keys_path})") print(f" KMS: Enabled (Keys: {self.kms_keys_path})")
print(f" SERVER_THREADS: {self.server_threads}") if self.website_hosting_enabled:
print(f" CONNECTION_LIMIT: {self.server_connection_limit}") print(f" WEBSITE_HOSTING: Enabled")
print(f" BACKLOG: {self.server_backlog}") def _auto(flag: bool) -> str:
return " (auto)" if flag else ""
print(f" SERVER_THREADS: {self.server_threads}{_auto(self.server_threads_auto)}")
print(f" CONNECTION_LIMIT: {self.server_connection_limit}{_auto(self.server_connection_limit_auto)}")
print(f" BACKLOG: {self.server_backlog}{_auto(self.server_backlog_auto)}")
print(f" CHANNEL_TIMEOUT: {self.server_channel_timeout}s") print(f" CHANNEL_TIMEOUT: {self.server_channel_timeout}s")
print("=" * 60) print("=" * 60)
@@ -406,6 +558,10 @@ class AppConfig:
"LOG_BACKUP_COUNT": self.log_backup_count, "LOG_BACKUP_COUNT": self.log_backup_count,
"RATELIMIT_DEFAULT": self.ratelimit_default, "RATELIMIT_DEFAULT": self.ratelimit_default,
"RATELIMIT_STORAGE_URI": self.ratelimit_storage_uri, "RATELIMIT_STORAGE_URI": self.ratelimit_storage_uri,
"RATELIMIT_LIST_BUCKETS": self.ratelimit_list_buckets,
"RATELIMIT_BUCKET_OPS": self.ratelimit_bucket_ops,
"RATELIMIT_OBJECT_OPS": self.ratelimit_object_ops,
"RATELIMIT_HEAD_OPS": self.ratelimit_head_ops,
"CORS_ORIGINS": self.cors_origins, "CORS_ORIGINS": self.cors_origins,
"CORS_METHODS": self.cors_methods, "CORS_METHODS": self.cors_methods,
"CORS_ALLOW_HEADERS": self.cors_allow_headers, "CORS_ALLOW_HEADERS": self.cors_allow_headers,
@@ -432,4 +588,33 @@ class AppConfig:
"SITE_SYNC_ENABLED": self.site_sync_enabled, "SITE_SYNC_ENABLED": self.site_sync_enabled,
"SITE_SYNC_INTERVAL_SECONDS": self.site_sync_interval_seconds, "SITE_SYNC_INTERVAL_SECONDS": self.site_sync_interval_seconds,
"SITE_SYNC_BATCH_SIZE": self.site_sync_batch_size, "SITE_SYNC_BATCH_SIZE": self.site_sync_batch_size,
"SIGV4_TIMESTAMP_TOLERANCE_SECONDS": self.sigv4_timestamp_tolerance_seconds,
"PRESIGNED_URL_MIN_EXPIRY_SECONDS": self.presigned_url_min_expiry_seconds,
"PRESIGNED_URL_MAX_EXPIRY_SECONDS": self.presigned_url_max_expiry_seconds,
"REPLICATION_CONNECT_TIMEOUT_SECONDS": self.replication_connect_timeout_seconds,
"REPLICATION_READ_TIMEOUT_SECONDS": self.replication_read_timeout_seconds,
"REPLICATION_MAX_RETRIES": self.replication_max_retries,
"REPLICATION_STREAMING_THRESHOLD_BYTES": self.replication_streaming_threshold_bytes,
"REPLICATION_MAX_FAILURES_PER_BUCKET": self.replication_max_failures_per_bucket,
"SITE_SYNC_CONNECT_TIMEOUT_SECONDS": self.site_sync_connect_timeout_seconds,
"SITE_SYNC_READ_TIMEOUT_SECONDS": self.site_sync_read_timeout_seconds,
"SITE_SYNC_MAX_RETRIES": self.site_sync_max_retries,
"SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS": self.site_sync_clock_skew_tolerance_seconds,
"OBJECT_KEY_MAX_LENGTH_BYTES": self.object_key_max_length_bytes,
"OBJECT_CACHE_MAX_SIZE": self.object_cache_max_size,
"BUCKET_CONFIG_CACHE_TTL_SECONDS": self.bucket_config_cache_ttl_seconds,
"OBJECT_TAG_LIMIT": self.object_tag_limit,
"ENCRYPTION_CHUNK_SIZE_BYTES": self.encryption_chunk_size_bytes,
"KMS_GENERATE_DATA_KEY_MIN_BYTES": self.kms_generate_data_key_min_bytes,
"KMS_GENERATE_DATA_KEY_MAX_BYTES": self.kms_generate_data_key_max_bytes,
"LIFECYCLE_MAX_HISTORY_PER_BUCKET": self.lifecycle_max_history_per_bucket,
"SITE_ID": self.site_id,
"SITE_ENDPOINT": self.site_endpoint,
"SITE_REGION": self.site_region,
"SITE_PRIORITY": self.site_priority,
"RATE_LIMIT_ADMIN": self.ratelimit_admin,
"NUM_TRUSTED_PROXIES": self.num_trusted_proxies,
"ALLOWED_REDIRECT_HOSTS": self.allowed_redirect_hosts,
"ALLOW_INTERNAL_ENDPOINTS": self.allow_internal_endpoints,
"WEBSITE_HOSTING_ENABLED": self.website_hosting_enabled,
} }

View File

@@ -274,5 +274,11 @@ class EncryptedObjectStorage:
def set_bucket_quota(self, bucket_name: str, *, max_bytes=None, max_objects=None): def set_bucket_quota(self, bucket_name: str, *, max_bytes=None, max_objects=None):
return self.storage.set_bucket_quota(bucket_name, max_bytes=max_bytes, max_objects=max_objects) return self.storage.set_bucket_quota(bucket_name, max_bytes=max_bytes, max_objects=max_objects)
def get_bucket_website(self, bucket_name: str):
return self.storage.get_bucket_website(bucket_name)
def set_bucket_website(self, bucket_name: str, website_config):
return self.storage.set_bucket_website(bucket_name, website_config)
def _compute_etag(self, path: Path) -> str: def _compute_etag(self, path: Path) -> str:
return self.storage._compute_etag(path) return self.storage._compute_etag(path)

View File

@@ -1,15 +1,44 @@
"""Encryption providers for server-side and client-side encryption."""
from __future__ import annotations from __future__ import annotations
import base64 import base64
import io import io
import json import json
import logging
import os
import secrets import secrets
import subprocess
import sys
from dataclasses import dataclass from dataclasses import dataclass
from pathlib import Path from pathlib import Path
from typing import Any, BinaryIO, Dict, Generator, Optional from typing import Any, BinaryIO, Dict, Generator, Optional
from cryptography.hazmat.primitives.ciphers.aead import AESGCM from cryptography.hazmat.primitives.ciphers.aead import AESGCM
from cryptography.hazmat.primitives.kdf.hkdf import HKDF
from cryptography.hazmat.primitives import hashes
if sys.platform != "win32":
import fcntl
logger = logging.getLogger(__name__)
def _set_secure_file_permissions(file_path: Path) -> None:
"""Set restrictive file permissions (owner read/write only)."""
if sys.platform == "win32":
try:
username = os.environ.get("USERNAME", "")
if username:
subprocess.run(
["icacls", str(file_path), "/inheritance:r",
"/grant:r", f"{username}:F"],
check=True, capture_output=True
)
else:
logger.warning("Could not set secure permissions on %s: USERNAME not set", file_path)
except (subprocess.SubprocessError, OSError) as exc:
logger.warning("Failed to set secure permissions on %s: %s", file_path, exc)
else:
os.chmod(file_path, 0o600)
class EncryptionError(Exception): class EncryptionError(Exception):
@@ -75,6 +104,18 @@ class EncryptionProvider:
""" """
raise NotImplementedError raise NotImplementedError
def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
"""Decrypt an encrypted data key.
Args:
encrypted_data_key: The encrypted data key bytes
key_id: Optional key identifier (used by KMS providers)
Returns:
The decrypted data key
"""
raise NotImplementedError
class LocalKeyEncryption(EncryptionProvider): class LocalKeyEncryption(EncryptionProvider):
"""SSE-S3 style encryption using a local master key. """SSE-S3 style encryption using a local master key.
@@ -99,26 +140,46 @@ class LocalKeyEncryption(EncryptionProvider):
return self._master_key return self._master_key
def _load_or_create_master_key(self) -> bytes: def _load_or_create_master_key(self) -> bytes:
"""Load master key from file or generate a new one.""" """Load master key from file or generate a new one (with file locking)."""
lock_path = self.master_key_path.with_suffix(".lock")
lock_path.parent.mkdir(parents=True, exist_ok=True)
try:
with open(lock_path, "w") as lock_file:
if sys.platform == "win32":
import msvcrt
msvcrt.locking(lock_file.fileno(), msvcrt.LK_LOCK, 1)
else:
fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX)
try:
if self.master_key_path.exists(): if self.master_key_path.exists():
try: try:
return base64.b64decode(self.master_key_path.read_text().strip()) return base64.b64decode(self.master_key_path.read_text().strip())
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Failed to load master key: {exc}") from exc raise EncryptionError(f"Failed to load master key: {exc}") from exc
key = secrets.token_bytes(32) key = secrets.token_bytes(32)
try: try:
self.master_key_path.parent.mkdir(parents=True, exist_ok=True)
self.master_key_path.write_text(base64.b64encode(key).decode()) self.master_key_path.write_text(base64.b64encode(key).decode())
_set_secure_file_permissions(self.master_key_path)
except OSError as exc: except OSError as exc:
raise EncryptionError(f"Failed to save master key: {exc}") from exc raise EncryptionError(f"Failed to save master key: {exc}") from exc
return key return key
finally:
if sys.platform == "win32":
import msvcrt
msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
else:
fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
except OSError as exc:
raise EncryptionError(f"Failed to acquire lock for master key: {exc}") from exc
DATA_KEY_AAD = b'{"purpose":"data_key","version":1}'
def _encrypt_data_key(self, data_key: bytes) -> bytes: def _encrypt_data_key(self, data_key: bytes) -> bytes:
"""Encrypt the data key with the master key.""" """Encrypt the data key with the master key."""
aesgcm = AESGCM(self.master_key) aesgcm = AESGCM(self.master_key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
encrypted = aesgcm.encrypt(nonce, data_key, None) encrypted = aesgcm.encrypt(nonce, data_key, self.DATA_KEY_AAD)
return nonce + encrypted return nonce + encrypted
def _decrypt_data_key(self, encrypted_data_key: bytes) -> bytes: def _decrypt_data_key(self, encrypted_data_key: bytes) -> bytes:
@@ -128,11 +189,18 @@ class LocalKeyEncryption(EncryptionProvider):
aesgcm = AESGCM(self.master_key) aesgcm = AESGCM(self.master_key)
nonce = encrypted_data_key[:12] nonce = encrypted_data_key[:12]
ciphertext = encrypted_data_key[12:] ciphertext = encrypted_data_key[12:]
try:
return aesgcm.decrypt(nonce, ciphertext, self.DATA_KEY_AAD)
except Exception:
try: try:
return aesgcm.decrypt(nonce, ciphertext, None) return aesgcm.decrypt(nonce, ciphertext, None)
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Failed to decrypt data key: {exc}") from exc raise EncryptionError(f"Failed to decrypt data key: {exc}") from exc
def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
"""Decrypt an encrypted data key (key_id ignored for local encryption)."""
return self._decrypt_data_key(encrypted_data_key)
def generate_data_key(self) -> tuple[bytes, bytes]: def generate_data_key(self) -> tuple[bytes, bytes]:
"""Generate a data key and its encrypted form.""" """Generate a data key and its encrypted form."""
plaintext_key = secrets.token_bytes(32) plaintext_key = secrets.token_bytes(32)
@@ -145,7 +213,8 @@ class LocalKeyEncryption(EncryptionProvider):
aesgcm = AESGCM(data_key) aesgcm = AESGCM(data_key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
ciphertext = aesgcm.encrypt(nonce, plaintext, None) aad = json.dumps(context, sort_keys=True).encode() if context else None
ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
return EncryptionResult( return EncryptionResult(
ciphertext=ciphertext, ciphertext=ciphertext,
@@ -159,10 +228,11 @@ class LocalKeyEncryption(EncryptionProvider):
"""Decrypt data using envelope encryption.""" """Decrypt data using envelope encryption."""
data_key = self._decrypt_data_key(encrypted_data_key) data_key = self._decrypt_data_key(encrypted_data_key)
aesgcm = AESGCM(data_key) aesgcm = AESGCM(data_key)
aad = json.dumps(context, sort_keys=True).encode() if context else None
try: try:
return aesgcm.decrypt(nonce, ciphertext, None) return aesgcm.decrypt(nonce, ciphertext, aad)
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Failed to decrypt data: {exc}") from exc raise EncryptionError("Failed to decrypt data") from exc
class StreamingEncryptor: class StreamingEncryptor:
@@ -180,12 +250,14 @@ class StreamingEncryptor:
self.chunk_size = chunk_size self.chunk_size = chunk_size
def _derive_chunk_nonce(self, base_nonce: bytes, chunk_index: int) -> bytes: def _derive_chunk_nonce(self, base_nonce: bytes, chunk_index: int) -> bytes:
"""Derive a unique nonce for each chunk. """Derive a unique nonce for each chunk using HKDF."""
hkdf = HKDF(
Performance: Use direct byte manipulation instead of full int conversion. algorithm=hashes.SHA256(),
""" length=12,
# Performance: Only modify last 4 bytes instead of full 12-byte conversion salt=base_nonce,
return base_nonce[:8] + (chunk_index ^ int.from_bytes(base_nonce[8:], "big")).to_bytes(4, "big") info=chunk_index.to_bytes(4, "big"),
)
return hkdf.derive(b"chunk_nonce")
def encrypt_stream(self, stream: BinaryIO, def encrypt_stream(self, stream: BinaryIO,
context: Dict[str, str] | None = None) -> tuple[BinaryIO, EncryptionMetadata]: context: Dict[str, str] | None = None) -> tuple[BinaryIO, EncryptionMetadata]:
@@ -234,10 +306,7 @@ class StreamingEncryptor:
Performance: Writes chunks directly to output buffer instead of accumulating in list. Performance: Writes chunks directly to output buffer instead of accumulating in list.
""" """
if isinstance(self.provider, LocalKeyEncryption): data_key = self.provider.decrypt_data_key(metadata.encrypted_data_key, metadata.key_id)
data_key = self.provider._decrypt_data_key(metadata.encrypted_data_key)
else:
raise EncryptionError("Unsupported provider for streaming decryption")
aesgcm = AESGCM(data_key) aesgcm = AESGCM(data_key)
base_nonce = metadata.nonce base_nonce = metadata.nonce
@@ -310,7 +379,8 @@ class EncryptionManager:
def get_streaming_encryptor(self) -> StreamingEncryptor: def get_streaming_encryptor(self) -> StreamingEncryptor:
if self._streaming_encryptor is None: if self._streaming_encryptor is None:
self._streaming_encryptor = StreamingEncryptor(self.get_local_provider()) chunk_size = self.config.get("encryption_chunk_size_bytes", 64 * 1024)
self._streaming_encryptor = StreamingEncryptor(self.get_local_provider(), chunk_size=chunk_size)
return self._streaming_encryptor return self._streaming_encryptor
def encrypt_object(self, data: bytes, algorithm: str = "AES256", def encrypt_object(self, data: bytes, algorithm: str = "AES256",
@@ -403,7 +473,8 @@ class SSECEncryption(EncryptionProvider):
def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult: def encrypt(self, plaintext: bytes, context: Dict[str, str] | None = None) -> EncryptionResult:
aesgcm = AESGCM(self.customer_key) aesgcm = AESGCM(self.customer_key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
ciphertext = aesgcm.encrypt(nonce, plaintext, None) aad = json.dumps(context, sort_keys=True).encode() if context else None
ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
return EncryptionResult( return EncryptionResult(
ciphertext=ciphertext, ciphertext=ciphertext,
@@ -415,10 +486,11 @@ class SSECEncryption(EncryptionProvider):
def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes, def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
key_id: str, context: Dict[str, str] | None = None) -> bytes: key_id: str, context: Dict[str, str] | None = None) -> bytes:
aesgcm = AESGCM(self.customer_key) aesgcm = AESGCM(self.customer_key)
aad = json.dumps(context, sort_keys=True).encode() if context else None
try: try:
return aesgcm.decrypt(nonce, ciphertext, None) return aesgcm.decrypt(nonce, ciphertext, aad)
except Exception as exc: except Exception as exc:
raise EncryptionError(f"SSE-C decryption failed: {exc}") from exc raise EncryptionError("SSE-C decryption failed") from exc
def generate_data_key(self) -> tuple[bytes, bytes]: def generate_data_key(self) -> tuple[bytes, bytes]:
return self.customer_key, b"" return self.customer_key, b""
@@ -472,7 +544,7 @@ class ClientEncryptionHelper:
} }
@staticmethod @staticmethod
def encrypt_with_key(plaintext: bytes, key_b64: str) -> Dict[str, str]: def encrypt_with_key(plaintext: bytes, key_b64: str, context: Dict[str, str] | None = None) -> Dict[str, str]:
"""Encrypt data with a client-provided key.""" """Encrypt data with a client-provided key."""
key = base64.b64decode(key_b64) key = base64.b64decode(key_b64)
if len(key) != 32: if len(key) != 32:
@@ -480,7 +552,8 @@ class ClientEncryptionHelper:
aesgcm = AESGCM(key) aesgcm = AESGCM(key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
ciphertext = aesgcm.encrypt(nonce, plaintext, None) aad = json.dumps(context, sort_keys=True).encode() if context else None
ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
return { return {
"ciphertext": base64.b64encode(ciphertext).decode(), "ciphertext": base64.b64encode(ciphertext).decode(),
@@ -489,7 +562,7 @@ class ClientEncryptionHelper:
} }
@staticmethod @staticmethod
def decrypt_with_key(ciphertext_b64: str, nonce_b64: str, key_b64: str) -> bytes: def decrypt_with_key(ciphertext_b64: str, nonce_b64: str, key_b64: str, context: Dict[str, str] | None = None) -> bytes:
"""Decrypt data with a client-provided key.""" """Decrypt data with a client-provided key."""
key = base64.b64decode(key_b64) key = base64.b64decode(key_b64)
nonce = base64.b64decode(nonce_b64) nonce = base64.b64decode(nonce_b64)
@@ -499,7 +572,8 @@ class ClientEncryptionHelper:
raise EncryptionError("Key must be 256 bits (32 bytes)") raise EncryptionError("Key must be 256 bits (32 bytes)")
aesgcm = AESGCM(key) aesgcm = AESGCM(key)
aad = json.dumps(context, sort_keys=True).encode() if context else None
try: try:
return aesgcm.decrypt(nonce, ciphertext, None) return aesgcm.decrypt(nonce, ciphertext, aad)
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Decryption failed: {exc}") from exc raise EncryptionError("Decryption failed") from exc

View File

@@ -6,6 +6,7 @@ from typing import Optional, Dict, Any
from xml.etree.ElementTree import Element, SubElement, tostring from xml.etree.ElementTree import Element, SubElement, tostring
from flask import Response, jsonify, request, flash, redirect, url_for, g from flask import Response, jsonify, request, flash, redirect, url_for, g
from flask_limiter import RateLimitExceeded
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -172,9 +173,21 @@ def handle_app_error(error: AppError) -> Response:
return error.to_xml_response() return error.to_xml_response()
def handle_rate_limit_exceeded(e: RateLimitExceeded) -> Response:
g.s3_error_code = "SlowDown"
error = Element("Error")
SubElement(error, "Code").text = "SlowDown"
SubElement(error, "Message").text = "Please reduce your request rate."
SubElement(error, "Resource").text = request.path
SubElement(error, "RequestId").text = getattr(g, "request_id", "")
xml_bytes = tostring(error, encoding="utf-8")
return Response(xml_bytes, status=429, mimetype="application/xml")
def register_error_handlers(app): def register_error_handlers(app):
"""Register error handlers with a Flask app.""" """Register error handlers with a Flask app."""
app.register_error_handler(AppError, handle_app_error) app.register_error_handler(AppError, handle_app_error)
app.register_error_handler(RateLimitExceeded, handle_rate_limit_exceeded)
for error_class in [ for error_class in [
BucketNotFoundError, BucketAlreadyExistsError, BucketNotEmptyError, BucketNotFoundError, BucketAlreadyExistsError, BucketNotEmptyError,

View File

@@ -1,9 +1,12 @@
from __future__ import annotations from __future__ import annotations
import hashlib
import hmac import hmac
import json import json
import math import math
import os
import secrets import secrets
import threading
import time import time
from collections import deque from collections import deque
from dataclasses import dataclass from dataclasses import dataclass
@@ -118,12 +121,15 @@ class IamService:
self._raw_config: Dict[str, Any] = {} self._raw_config: Dict[str, Any] = {}
self._failed_attempts: Dict[str, Deque[datetime]] = {} self._failed_attempts: Dict[str, Deque[datetime]] = {}
self._last_load_time = 0.0 self._last_load_time = 0.0
self._credential_cache: Dict[str, Tuple[str, Principal, float]] = {} self._principal_cache: Dict[str, Tuple[Principal, float]] = {}
self._cache_ttl = 60.0 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._last_stat_check = 0.0
self._stat_check_interval = 1.0 self._stat_check_interval = 1.0
self._sessions: Dict[str, Dict[str, Any]] = {} self._sessions: Dict[str, Dict[str, Any]] = {}
self._session_lock = threading.Lock()
self._load() self._load()
self._load_lockout_state()
def _maybe_reload(self) -> None: def _maybe_reload(self) -> None:
"""Reload configuration if the file has changed on disk.""" """Reload configuration if the file has changed on disk."""
@@ -134,7 +140,8 @@ class IamService:
try: try:
if self.config_path.stat().st_mtime > self._last_load_time: if self.config_path.stat().st_mtime > self._last_load_time:
self._load() self._load()
self._credential_cache.clear() self._principal_cache.clear()
self._secret_key_cache.clear()
except OSError: except OSError:
pass pass
@@ -150,7 +157,8 @@ class IamService:
f"Access temporarily locked. Try again in {seconds} seconds." f"Access temporarily locked. Try again in {seconds} seconds."
) )
record = self._users.get(access_key) record = self._users.get(access_key)
if not record or not hmac.compare_digest(record["secret_key"], secret_key): stored_secret = record["secret_key"] if record else secrets.token_urlsafe(24)
if not record or not hmac.compare_digest(stored_secret, secret_key):
self._record_failed_attempt(access_key) self._record_failed_attempt(access_key)
raise IamError("Invalid credentials") raise IamError("Invalid credentials")
self._clear_failed_attempts(access_key) self._clear_failed_attempts(access_key)
@@ -162,11 +170,46 @@ class IamService:
attempts = self._failed_attempts.setdefault(access_key, deque()) attempts = self._failed_attempts.setdefault(access_key, deque())
self._prune_attempts(attempts) self._prune_attempts(attempts)
attempts.append(datetime.now(timezone.utc)) attempts.append(datetime.now(timezone.utc))
self._save_lockout_state()
def _clear_failed_attempts(self, access_key: str) -> None: def _clear_failed_attempts(self, access_key: str) -> None:
if not access_key: if not access_key:
return return
self._failed_attempts.pop(access_key, None) if self._failed_attempts.pop(access_key, None) is not None:
self._save_lockout_state()
def _lockout_file(self) -> Path:
return self.config_path.parent / "lockout_state.json"
def _load_lockout_state(self) -> None:
"""Load lockout state from disk."""
try:
if self._lockout_file().exists():
data = json.loads(self._lockout_file().read_text(encoding="utf-8"))
cutoff = datetime.now(timezone.utc) - self.auth_lockout_window
for key, timestamps in data.get("failed_attempts", {}).items():
valid = []
for ts in timestamps:
try:
dt = datetime.fromisoformat(ts)
if dt > cutoff:
valid.append(dt)
except (ValueError, TypeError):
continue
if valid:
self._failed_attempts[key] = deque(valid)
except (OSError, json.JSONDecodeError):
pass
def _save_lockout_state(self) -> None:
"""Persist lockout state to disk."""
data: Dict[str, Any] = {"failed_attempts": {}}
for key, attempts in self._failed_attempts.items():
data["failed_attempts"][key] = [ts.isoformat() for ts in attempts]
try:
self._lockout_file().write_text(json.dumps(data), encoding="utf-8")
except OSError:
pass
def _prune_attempts(self, attempts: Deque[datetime]) -> None: def _prune_attempts(self, attempts: Deque[datetime]) -> None:
cutoff = datetime.now(timezone.utc) - self.auth_lockout_window cutoff = datetime.now(timezone.utc) - self.auth_lockout_window
@@ -209,14 +252,21 @@ class IamService:
return token return token
def validate_session_token(self, access_key: str, session_token: str) -> bool: def validate_session_token(self, access_key: str, session_token: str) -> bool:
"""Validate a session token for an access key.""" """Validate a session token for an access key (thread-safe, constant-time)."""
dummy_key = secrets.token_urlsafe(16)
dummy_token = secrets.token_urlsafe(32)
with self._session_lock:
session = self._sessions.get(session_token) session = self._sessions.get(session_token)
if not session: if not session:
hmac.compare_digest(access_key, dummy_key)
hmac.compare_digest(session_token, dummy_token)
return False return False
if session["access_key"] != access_key: key_match = hmac.compare_digest(session["access_key"], access_key)
if not key_match:
hmac.compare_digest(session_token, dummy_token)
return False return False
if time.time() > session["expires_at"]: if time.time() > session["expires_at"]:
del self._sessions[session_token] self._sessions.pop(session_token, None)
return False return False
return True return True
@@ -229,9 +279,9 @@ class IamService:
def principal_for_key(self, access_key: str) -> Principal: def principal_for_key(self, access_key: str) -> Principal:
now = time.time() now = time.time()
cached = self._credential_cache.get(access_key) cached = self._principal_cache.get(access_key)
if cached: if cached:
secret, principal, cached_time = cached principal, cached_time = cached
if now - cached_time < self._cache_ttl: if now - cached_time < self._cache_ttl:
return principal return principal
@@ -240,23 +290,14 @@ class IamService:
if not record: if not record:
raise IamError("Unknown access key") raise IamError("Unknown access key")
principal = self._build_principal(access_key, record) principal = self._build_principal(access_key, record)
self._credential_cache[access_key] = (record["secret_key"], principal, now) self._principal_cache[access_key] = (principal, now)
return principal return principal
def secret_for_key(self, access_key: str) -> str: def secret_for_key(self, access_key: str) -> str:
now = time.time()
cached = self._credential_cache.get(access_key)
if cached:
secret, principal, cached_time = cached
if now - cached_time < self._cache_ttl:
return secret
self._maybe_reload() self._maybe_reload()
record = self._users.get(access_key) record = self._users.get(access_key)
if not record: if not record:
raise IamError("Unknown access key") raise IamError("Unknown access key")
principal = self._build_principal(access_key, record)
self._credential_cache[access_key] = (record["secret_key"], principal, now)
return record["secret_key"] return record["secret_key"]
def authorize(self, principal: Principal, bucket_name: str | None, action: str) -> None: def authorize(self, principal: Principal, bucket_name: str | None, action: str) -> None:
@@ -268,6 +309,18 @@ class IamService:
if not self._is_allowed(principal, normalized, action): if not self._is_allowed(principal, normalized, action):
raise IamError(f"Access denied for action '{action}' on bucket '{bucket_name}'") raise IamError(f"Access denied for action '{action}' on bucket '{bucket_name}'")
def check_permissions(self, principal: Principal, bucket_name: str | None, actions: Iterable[str]) -> Dict[str, bool]:
self._maybe_reload()
bucket_name = (bucket_name or "*").lower() if bucket_name != "*" else (bucket_name or "*")
normalized_actions = {a: self._normalize_action(a) for a in actions}
results: Dict[str, bool] = {}
for original, canonical in normalized_actions.items():
if canonical not in ALLOWED_ACTIONS:
results[original] = False
else:
results[original] = self._is_allowed(principal, bucket_name, canonical)
return results
def buckets_for_principal(self, principal: Principal, buckets: Iterable[str]) -> List[str]: def buckets_for_principal(self, principal: Principal, buckets: Iterable[str]) -> List[str]:
return [bucket for bucket in buckets if self._is_allowed(principal, bucket, "list")] return [bucket for bucket in buckets if self._is_allowed(principal, bucket, "list")]
@@ -328,6 +381,10 @@ class IamService:
new_secret = self._generate_secret_key() new_secret = self._generate_secret_key()
user["secret_key"] = new_secret user["secret_key"] = new_secret
self._save() self._save()
self._principal_cache.pop(access_key, None)
self._secret_key_cache.pop(access_key, None)
from .s3_api import clear_signing_key_cache
clear_signing_key_cache()
self._load() self._load()
return new_secret return new_secret
@@ -346,6 +403,10 @@ class IamService:
raise IamError("User not found") raise IamError("User not found")
self._raw_config["users"] = remaining self._raw_config["users"] = remaining
self._save() self._save()
self._principal_cache.pop(access_key, None)
self._secret_key_cache.pop(access_key, None)
from .s3_api import clear_signing_key_cache
clear_signing_key_cache()
self._load() self._load()
def update_user_policies(self, access_key: str, policies: Sequence[Dict[str, Any]]) -> None: def update_user_policies(self, access_key: str, policies: Sequence[Dict[str, Any]]) -> None:
@@ -480,11 +541,13 @@ class IamService:
return candidate if candidate in ALLOWED_ACTIONS else "" return candidate if candidate in ALLOWED_ACTIONS else ""
def _write_default(self) -> None: def _write_default(self) -> None:
access_key = secrets.token_hex(12)
secret_key = secrets.token_urlsafe(32)
default = { default = {
"users": [ "users": [
{ {
"access_key": "localadmin", "access_key": access_key,
"secret_key": "localadmin", "secret_key": secret_key,
"display_name": "Local Admin", "display_name": "Local Admin",
"policies": [ "policies": [
{"bucket": "*", "actions": list(ALLOWED_ACTIONS)} {"bucket": "*", "actions": list(ALLOWED_ACTIONS)}
@@ -493,6 +556,14 @@ class IamService:
] ]
} }
self.config_path.write_text(json.dumps(default, indent=2)) self.config_path.write_text(json.dumps(default, indent=2))
print(f"\n{'='*60}")
print("MYFSIO FIRST RUN - ADMIN CREDENTIALS GENERATED")
print(f"{'='*60}")
print(f"Access Key: {access_key}")
print(f"Secret Key: {secret_key}")
print(f"{'='*60}")
print(f"Missed this? Check: {self.config_path}")
print(f"{'='*60}\n")
def _generate_access_key(self) -> str: def _generate_access_key(self) -> str:
return secrets.token_hex(8) return secrets.token_hex(8)
@@ -508,25 +579,25 @@ class IamService:
def get_secret_key(self, access_key: str) -> str | None: def get_secret_key(self, access_key: str) -> str | None:
now = time.time() now = time.time()
cached = self._credential_cache.get(access_key) cached = self._secret_key_cache.get(access_key)
if cached: if cached:
secret, principal, cached_time = cached secret_key, cached_time = cached
if now - cached_time < self._cache_ttl: if now - cached_time < self._cache_ttl:
return secret return secret_key
self._maybe_reload() self._maybe_reload()
record = self._users.get(access_key) record = self._users.get(access_key)
if record: if record:
principal = self._build_principal(access_key, record) secret_key = record["secret_key"]
self._credential_cache[access_key] = (record["secret_key"], principal, now) self._secret_key_cache[access_key] = (secret_key, now)
return record["secret_key"] return secret_key
return None return None
def get_principal(self, access_key: str) -> Principal | None: def get_principal(self, access_key: str) -> Principal | None:
now = time.time() now = time.time()
cached = self._credential_cache.get(access_key) cached = self._principal_cache.get(access_key)
if cached: if cached:
secret, principal, cached_time = cached principal, cached_time = cached
if now - cached_time < self._cache_ttl: if now - cached_time < self._cache_ttl:
return principal return principal
@@ -534,6 +605,6 @@ class IamService:
record = self._users.get(access_key) record = self._users.get(access_key)
if record: if record:
principal = self._build_principal(access_key, record) principal = self._build_principal(access_key, record)
self._credential_cache[access_key] = (record["secret_key"], principal, now) self._principal_cache[access_key] = (principal, now)
return principal return principal
return None return None

View File

@@ -2,7 +2,11 @@ from __future__ import annotations
import base64 import base64
import json import json
import logging
import os
import secrets import secrets
import subprocess
import sys
import uuid import uuid
from dataclasses import dataclass, field from dataclasses import dataclass, field
from datetime import datetime, timezone from datetime import datetime, timezone
@@ -13,6 +17,30 @@ from cryptography.hazmat.primitives.ciphers.aead import AESGCM
from .encryption import EncryptionError, EncryptionProvider, EncryptionResult from .encryption import EncryptionError, EncryptionProvider, EncryptionResult
if sys.platform != "win32":
import fcntl
logger = logging.getLogger(__name__)
def _set_secure_file_permissions(file_path: Path) -> None:
"""Set restrictive file permissions (owner read/write only)."""
if sys.platform == "win32":
try:
username = os.environ.get("USERNAME", "")
if username:
subprocess.run(
["icacls", str(file_path), "/inheritance:r",
"/grant:r", f"{username}:F"],
check=True, capture_output=True
)
else:
logger.warning("Could not set secure permissions on %s: USERNAME not set", file_path)
except (subprocess.SubprocessError, OSError) as exc:
logger.warning("Failed to set secure permissions on %s: %s", file_path, exc)
else:
os.chmod(file_path, 0o600)
@dataclass @dataclass
class KMSKey: class KMSKey:
@@ -78,7 +106,7 @@ class KMSEncryptionProvider(EncryptionProvider):
aesgcm = AESGCM(data_key) aesgcm = AESGCM(data_key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
ciphertext = aesgcm.encrypt(nonce, plaintext, ciphertext = aesgcm.encrypt(nonce, plaintext,
json.dumps(context).encode() if context else None) json.dumps(context, sort_keys=True).encode() if context else None)
return EncryptionResult( return EncryptionResult(
ciphertext=ciphertext, ciphertext=ciphertext,
@@ -90,15 +118,26 @@ class KMSEncryptionProvider(EncryptionProvider):
def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes, def decrypt(self, ciphertext: bytes, nonce: bytes, encrypted_data_key: bytes,
key_id: str, context: Dict[str, str] | None = None) -> bytes: key_id: str, context: Dict[str, str] | None = None) -> bytes:
"""Decrypt data using envelope encryption with KMS.""" """Decrypt data using envelope encryption with KMS."""
# Note: Data key is encrypted without context (AAD), so we decrypt without context
data_key = self.kms.decrypt_data_key(key_id, encrypted_data_key, context=None) data_key = self.kms.decrypt_data_key(key_id, encrypted_data_key, context=None)
if len(data_key) != 32:
raise EncryptionError("Invalid data key size")
aesgcm = AESGCM(data_key) aesgcm = AESGCM(data_key)
try: try:
return aesgcm.decrypt(nonce, ciphertext, return aesgcm.decrypt(nonce, ciphertext,
json.dumps(context).encode() if context else None) json.dumps(context, sort_keys=True).encode() if context else None)
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Failed to decrypt data: {exc}") from exc logger.debug("KMS decryption failed: %s", exc)
raise EncryptionError("Failed to decrypt data") from exc
def decrypt_data_key(self, encrypted_data_key: bytes, key_id: str | None = None) -> bytes:
"""Decrypt an encrypted data key using KMS."""
if key_id is None:
key_id = self.key_id
data_key = self.kms.decrypt_data_key(key_id, encrypted_data_key, context=None)
if len(data_key) != 32:
raise EncryptionError("Invalid data key size")
return data_key
class KMSManager: class KMSManager:
@@ -108,27 +147,52 @@ class KMSManager:
Keys are stored encrypted on disk. Keys are stored encrypted on disk.
""" """
def __init__(self, keys_path: Path, master_key_path: Path): def __init__(
self,
keys_path: Path,
master_key_path: Path,
generate_data_key_min_bytes: int = 1,
generate_data_key_max_bytes: int = 1024,
):
self.keys_path = keys_path self.keys_path = keys_path
self.master_key_path = master_key_path self.master_key_path = master_key_path
self.generate_data_key_min_bytes = generate_data_key_min_bytes
self.generate_data_key_max_bytes = generate_data_key_max_bytes
self._keys: Dict[str, KMSKey] = {} self._keys: Dict[str, KMSKey] = {}
self._master_key: bytes | None = None self._master_key: bytes | None = None
self._master_aesgcm: AESGCM | None = None
self._loaded = False self._loaded = False
@property @property
def master_key(self) -> bytes: def master_key(self) -> bytes:
"""Load or create the master key for encrypting KMS keys.""" """Load or create the master key for encrypting KMS keys (with file locking)."""
if self._master_key is None: if self._master_key is None:
lock_path = self.master_key_path.with_suffix(".lock")
lock_path.parent.mkdir(parents=True, exist_ok=True)
with open(lock_path, "w") as lock_file:
if sys.platform == "win32":
import msvcrt
msvcrt.locking(lock_file.fileno(), msvcrt.LK_LOCK, 1)
else:
fcntl.flock(lock_file.fileno(), fcntl.LOCK_EX)
try:
if self.master_key_path.exists(): if self.master_key_path.exists():
self._master_key = base64.b64decode( self._master_key = base64.b64decode(
self.master_key_path.read_text().strip() self.master_key_path.read_text().strip()
) )
else: else:
self._master_key = secrets.token_bytes(32) self._master_key = secrets.token_bytes(32)
self.master_key_path.parent.mkdir(parents=True, exist_ok=True)
self.master_key_path.write_text( self.master_key_path.write_text(
base64.b64encode(self._master_key).decode() base64.b64encode(self._master_key).decode()
) )
_set_secure_file_permissions(self.master_key_path)
finally:
if sys.platform == "win32":
import msvcrt
msvcrt.locking(lock_file.fileno(), msvcrt.LK_UNLCK, 1)
else:
fcntl.flock(lock_file.fileno(), fcntl.LOCK_UN)
self._master_aesgcm = AESGCM(self._master_key)
return self._master_key return self._master_key
def _load_keys(self) -> None: def _load_keys(self) -> None:
@@ -145,8 +209,10 @@ class KMSManager:
encrypted = base64.b64decode(key_data["EncryptedKeyMaterial"]) encrypted = base64.b64decode(key_data["EncryptedKeyMaterial"])
key.key_material = self._decrypt_key_material(encrypted) key.key_material = self._decrypt_key_material(encrypted)
self._keys[key.key_id] = key self._keys[key.key_id] = key
except Exception: except json.JSONDecodeError as exc:
pass logger.error("Failed to parse KMS keys file: %s", exc)
except (ValueError, KeyError) as exc:
logger.error("Invalid KMS key data: %s", exc)
self._loaded = True self._loaded = True
@@ -164,20 +230,19 @@ class KMSManager:
json.dumps({"keys": keys_data}, indent=2), json.dumps({"keys": keys_data}, indent=2),
encoding="utf-8" encoding="utf-8"
) )
_set_secure_file_permissions(self.keys_path)
def _encrypt_key_material(self, key_material: bytes) -> bytes: def _encrypt_key_material(self, key_material: bytes) -> bytes:
"""Encrypt key material with the master key.""" _ = self.master_key
aesgcm = AESGCM(self.master_key)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
ciphertext = aesgcm.encrypt(nonce, key_material, None) ciphertext = self._master_aesgcm.encrypt(nonce, key_material, None)
return nonce + ciphertext return nonce + ciphertext
def _decrypt_key_material(self, encrypted: bytes) -> bytes: def _decrypt_key_material(self, encrypted: bytes) -> bytes:
"""Decrypt key material with the master key.""" _ = self.master_key
aesgcm = AESGCM(self.master_key)
nonce = encrypted[:12] nonce = encrypted[:12]
ciphertext = encrypted[12:] ciphertext = encrypted[12:]
return aesgcm.decrypt(nonce, ciphertext, None) return self._master_aesgcm.decrypt(nonce, ciphertext, None)
def create_key(self, description: str = "", key_id: str | None = None) -> KMSKey: def create_key(self, description: str = "", key_id: str | None = None) -> KMSKey:
"""Create a new KMS key.""" """Create a new KMS key."""
@@ -269,7 +334,7 @@ class KMSManager:
aesgcm = AESGCM(key.key_material) aesgcm = AESGCM(key.key_material)
nonce = secrets.token_bytes(12) nonce = secrets.token_bytes(12)
aad = json.dumps(context).encode() if context else None aad = json.dumps(context, sort_keys=True).encode() if context else None
ciphertext = aesgcm.encrypt(nonce, plaintext, aad) ciphertext = aesgcm.encrypt(nonce, plaintext, aad)
key_id_bytes = key_id.encode("utf-8") key_id_bytes = key_id.encode("utf-8")
@@ -298,17 +363,24 @@ class KMSManager:
encrypted = rest[12:] encrypted = rest[12:]
aesgcm = AESGCM(key.key_material) aesgcm = AESGCM(key.key_material)
aad = json.dumps(context).encode() if context else None aad = json.dumps(context, sort_keys=True).encode() if context else None
try: try:
plaintext = aesgcm.decrypt(nonce, encrypted, aad) plaintext = aesgcm.decrypt(nonce, encrypted, aad)
return plaintext, key_id return plaintext, key_id
except Exception as exc: except Exception as exc:
raise EncryptionError(f"Decryption failed: {exc}") from exc logger.debug("KMS decrypt operation failed: %s", exc)
raise EncryptionError("Decryption failed") from exc
def generate_data_key(self, key_id: str, def generate_data_key(self, key_id: str,
context: Dict[str, str] | None = None) -> tuple[bytes, bytes]: context: Dict[str, str] | None = None,
key_spec: str = "AES_256") -> tuple[bytes, bytes]:
"""Generate a data key and return both plaintext and encrypted versions. """Generate a data key and return both plaintext and encrypted versions.
Args:
key_id: The KMS key ID to use for encryption
context: Optional encryption context
key_spec: Key specification - AES_128 or AES_256 (default)
Returns: Returns:
Tuple of (plaintext_key, encrypted_key) Tuple of (plaintext_key, encrypted_key)
""" """
@@ -319,7 +391,8 @@ class KMSManager:
if not key.enabled: if not key.enabled:
raise EncryptionError(f"Key is disabled: {key_id}") raise EncryptionError(f"Key is disabled: {key_id}")
plaintext_key = secrets.token_bytes(32) key_bytes = 32 if key_spec == "AES_256" else 16
plaintext_key = secrets.token_bytes(key_bytes)
encrypted_key = self.encrypt(key_id, plaintext_key, context) encrypted_key = self.encrypt(key_id, plaintext_key, context)
@@ -331,22 +404,6 @@ class KMSManager:
plaintext, _ = self.decrypt(encrypted_key, context) plaintext, _ = self.decrypt(encrypted_key, context)
return plaintext return plaintext
def get_provider(self, key_id: str | None = None) -> KMSEncryptionProvider:
"""Get an encryption provider for a specific key."""
self._load_keys()
if key_id is None:
if not self._keys:
key = self.create_key("Default KMS Key")
key_id = key.key_id
else:
key_id = next(iter(self._keys.keys()))
if key_id not in self._keys:
raise EncryptionError(f"Key not found: {key_id}")
return KMSEncryptionProvider(self, key_id)
def re_encrypt(self, ciphertext: bytes, destination_key_id: str, def re_encrypt(self, ciphertext: bytes, destination_key_id: str,
source_context: Dict[str, str] | None = None, source_context: Dict[str, str] | None = None,
destination_context: Dict[str, str] | None = None) -> bytes: destination_context: Dict[str, str] | None = None) -> bytes:
@@ -358,6 +415,8 @@ class KMSManager:
def generate_random(self, num_bytes: int = 32) -> bytes: def generate_random(self, num_bytes: int = 32) -> bytes:
"""Generate cryptographically secure random bytes.""" """Generate cryptographically secure random bytes."""
if num_bytes < 1 or num_bytes > 1024: if num_bytes < self.generate_data_key_min_bytes or num_bytes > self.generate_data_key_max_bytes:
raise EncryptionError("Number of bytes must be between 1 and 1024") raise EncryptionError(
f"Number of bytes must be between {self.generate_data_key_min_bytes} and {self.generate_data_key_max_bytes}"
)
return secrets.token_bytes(num_bytes) return secrets.token_bytes(num_bytes)

View File

@@ -71,10 +71,9 @@ class LifecycleExecutionRecord:
class LifecycleHistoryStore: class LifecycleHistoryStore:
MAX_HISTORY_PER_BUCKET = 50 def __init__(self, storage_root: Path, max_history_per_bucket: int = 50) -> None:
def __init__(self, storage_root: Path) -> None:
self.storage_root = storage_root self.storage_root = storage_root
self.max_history_per_bucket = max_history_per_bucket
self._lock = threading.Lock() self._lock = threading.Lock()
def _get_history_path(self, bucket_name: str) -> Path: def _get_history_path(self, bucket_name: str) -> Path:
@@ -95,7 +94,7 @@ class LifecycleHistoryStore:
def save_history(self, bucket_name: str, records: List[LifecycleExecutionRecord]) -> None: def save_history(self, bucket_name: str, records: List[LifecycleExecutionRecord]) -> None:
path = self._get_history_path(bucket_name) path = self._get_history_path(bucket_name)
path.parent.mkdir(parents=True, exist_ok=True) path.parent.mkdir(parents=True, exist_ok=True)
data = {"executions": [r.to_dict() for r in records[:self.MAX_HISTORY_PER_BUCKET]]} data = {"executions": [r.to_dict() for r in records[:self.max_history_per_bucket]]}
try: try:
with open(path, "w") as f: with open(path, "w") as f:
json.dump(data, f, indent=2) json.dump(data, f, indent=2)
@@ -114,14 +113,20 @@ class LifecycleHistoryStore:
class LifecycleManager: class LifecycleManager:
def __init__(self, storage: ObjectStorage, interval_seconds: int = 3600, storage_root: Optional[Path] = None): def __init__(
self,
storage: ObjectStorage,
interval_seconds: int = 3600,
storage_root: Optional[Path] = None,
max_history_per_bucket: int = 50,
):
self.storage = storage self.storage = storage
self.interval_seconds = interval_seconds self.interval_seconds = interval_seconds
self.storage_root = storage_root self.storage_root = storage_root
self._timer: Optional[threading.Timer] = None self._timer: Optional[threading.Timer] = None
self._shutdown = False self._shutdown = False
self._lock = threading.Lock() self._lock = threading.Lock()
self.history_store = LifecycleHistoryStore(storage_root) if storage_root else None self.history_store = LifecycleHistoryStore(storage_root, max_history_per_bucket) if storage_root else None
def start(self) -> None: def start(self) -> None:
if self._timer is not None: if self._timer is not None:

View File

@@ -1,8 +1,10 @@
from __future__ import annotations from __future__ import annotations
import ipaddress
import json import json
import logging import logging
import queue import queue
import socket
import threading import threading
import time import time
import uuid import uuid
@@ -14,6 +16,48 @@ from urllib.parse import urlparse
import requests import requests
def _is_safe_url(url: str, allow_internal: bool = False) -> bool:
"""Check if a URL is safe to make requests to (not internal/private).
Args:
url: The URL to check.
allow_internal: If True, allows internal/private IP addresses.
Use for self-hosted deployments on internal networks.
"""
try:
parsed = urlparse(url)
hostname = parsed.hostname
if not hostname:
return False
cloud_metadata_hosts = {
"metadata.google.internal",
"169.254.169.254",
}
if hostname.lower() in cloud_metadata_hosts:
return False
if allow_internal:
return True
blocked_hosts = {
"localhost",
"127.0.0.1",
"0.0.0.0",
"::1",
"[::1]",
}
if hostname.lower() in blocked_hosts:
return False
try:
resolved_ip = socket.gethostbyname(hostname)
ip = ipaddress.ip_address(resolved_ip)
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
return False
except (socket.gaierror, ValueError):
return False
return True
except Exception:
return False
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -165,8 +209,9 @@ class NotificationConfiguration:
class NotificationService: class NotificationService:
def __init__(self, storage_root: Path, worker_count: int = 2): def __init__(self, storage_root: Path, worker_count: int = 2, allow_internal_endpoints: bool = False):
self.storage_root = storage_root self.storage_root = storage_root
self._allow_internal_endpoints = allow_internal_endpoints
self._configs: Dict[str, List[NotificationConfiguration]] = {} self._configs: Dict[str, List[NotificationConfiguration]] = {}
self._queue: queue.Queue[tuple[NotificationEvent, WebhookDestination]] = queue.Queue() self._queue: queue.Queue[tuple[NotificationEvent, WebhookDestination]] = queue.Queue()
self._workers: List[threading.Thread] = [] self._workers: List[threading.Thread] = []
@@ -299,6 +344,8 @@ class NotificationService:
self._queue.task_done() self._queue.task_done()
def _send_notification(self, event: NotificationEvent, destination: WebhookDestination) -> None: def _send_notification(self, event: NotificationEvent, destination: WebhookDestination) -> None:
if not _is_safe_url(destination.url, allow_internal=self._allow_internal_endpoints):
raise RuntimeError(f"Blocked request to cloud metadata service (SSRF protection): {destination.url}")
payload = event.to_s3_event() payload = event.to_s3_event()
headers = {"Content-Type": "application/json", **destination.headers} headers = {"Content-Type": "application/json", **destination.headers}

View File

@@ -21,16 +21,20 @@ from .storage import ObjectStorage, StorageError
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
REPLICATION_USER_AGENT = "S3ReplicationAgent/1.0" REPLICATION_USER_AGENT = "S3ReplicationAgent/1.0"
REPLICATION_CONNECT_TIMEOUT = 5
REPLICATION_READ_TIMEOUT = 30
STREAMING_THRESHOLD_BYTES = 10 * 1024 * 1024
REPLICATION_MODE_NEW_ONLY = "new_only" REPLICATION_MODE_NEW_ONLY = "new_only"
REPLICATION_MODE_ALL = "all" REPLICATION_MODE_ALL = "all"
REPLICATION_MODE_BIDIRECTIONAL = "bidirectional" REPLICATION_MODE_BIDIRECTIONAL = "bidirectional"
def _create_s3_client(connection: RemoteConnection, *, health_check: bool = False) -> Any: def _create_s3_client(
connection: RemoteConnection,
*,
health_check: bool = False,
connect_timeout: int = 5,
read_timeout: int = 30,
max_retries: int = 2,
) -> Any:
"""Create a boto3 S3 client for the given connection. """Create a boto3 S3 client for the given connection.
Args: Args:
connection: Remote S3 connection configuration connection: Remote S3 connection configuration
@@ -38,9 +42,9 @@ def _create_s3_client(connection: RemoteConnection, *, health_check: bool = Fals
""" """
config = Config( config = Config(
user_agent_extra=REPLICATION_USER_AGENT, user_agent_extra=REPLICATION_USER_AGENT,
connect_timeout=REPLICATION_CONNECT_TIMEOUT, connect_timeout=connect_timeout,
read_timeout=REPLICATION_READ_TIMEOUT, read_timeout=read_timeout,
retries={'max_attempts': 1 if health_check else 2}, retries={'max_attempts': 1 if health_check else max_retries},
signature_version='s3v4', signature_version='s3v4',
s3={'addressing_style': 'path'}, s3={'addressing_style': 'path'},
request_checksum_calculation='when_required', request_checksum_calculation='when_required',
@@ -133,6 +137,7 @@ class ReplicationRule:
stats: ReplicationStats = field(default_factory=ReplicationStats) stats: ReplicationStats = field(default_factory=ReplicationStats)
sync_deletions: bool = True sync_deletions: bool = True
last_pull_at: Optional[float] = None last_pull_at: Optional[float] = None
filter_prefix: Optional[str] = None
def to_dict(self) -> dict: def to_dict(self) -> dict:
return { return {
@@ -145,6 +150,7 @@ class ReplicationRule:
"stats": self.stats.to_dict(), "stats": self.stats.to_dict(),
"sync_deletions": self.sync_deletions, "sync_deletions": self.sync_deletions,
"last_pull_at": self.last_pull_at, "last_pull_at": self.last_pull_at,
"filter_prefix": self.filter_prefix,
} }
@classmethod @classmethod
@@ -158,22 +164,24 @@ class ReplicationRule:
data["sync_deletions"] = True data["sync_deletions"] = True
if "last_pull_at" not in data: if "last_pull_at" not in data:
data["last_pull_at"] = None data["last_pull_at"] = None
if "filter_prefix" not in data:
data["filter_prefix"] = None
rule = cls(**data) rule = cls(**data)
rule.stats = ReplicationStats.from_dict(stats_data) if stats_data else ReplicationStats() rule.stats = ReplicationStats.from_dict(stats_data) if stats_data else ReplicationStats()
return rule return rule
class ReplicationFailureStore: class ReplicationFailureStore:
MAX_FAILURES_PER_BUCKET = 50 def __init__(self, storage_root: Path, max_failures_per_bucket: int = 50) -> None:
def __init__(self, storage_root: Path) -> None:
self.storage_root = storage_root self.storage_root = storage_root
self.max_failures_per_bucket = max_failures_per_bucket
self._lock = threading.Lock() self._lock = threading.Lock()
self._cache: Dict[str, List[ReplicationFailure]] = {}
def _get_failures_path(self, bucket_name: str) -> Path: def _get_failures_path(self, bucket_name: str) -> Path:
return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "replication_failures.json" return self.storage_root / ".myfsio.sys" / "buckets" / bucket_name / "replication_failures.json"
def load_failures(self, bucket_name: str) -> List[ReplicationFailure]: def _load_from_disk(self, bucket_name: str) -> List[ReplicationFailure]:
path = self._get_failures_path(bucket_name) path = self._get_failures_path(bucket_name)
if not path.exists(): if not path.exists():
return [] return []
@@ -185,16 +193,28 @@ class ReplicationFailureStore:
logger.error(f"Failed to load replication failures for {bucket_name}: {e}") logger.error(f"Failed to load replication failures for {bucket_name}: {e}")
return [] return []
def save_failures(self, bucket_name: str, failures: List[ReplicationFailure]) -> None: def _save_to_disk(self, bucket_name: str, failures: List[ReplicationFailure]) -> None:
path = self._get_failures_path(bucket_name) path = self._get_failures_path(bucket_name)
path.parent.mkdir(parents=True, exist_ok=True) path.parent.mkdir(parents=True, exist_ok=True)
data = {"failures": [f.to_dict() for f in failures[:self.MAX_FAILURES_PER_BUCKET]]} data = {"failures": [f.to_dict() for f in failures[:self.max_failures_per_bucket]]}
try: try:
with open(path, "w") as f: with open(path, "w") as f:
json.dump(data, f, indent=2) json.dump(data, f, indent=2)
except OSError as e: except OSError as e:
logger.error(f"Failed to save replication failures for {bucket_name}: {e}") logger.error(f"Failed to save replication failures for {bucket_name}: {e}")
def load_failures(self, bucket_name: str) -> List[ReplicationFailure]:
if bucket_name in self._cache:
return list(self._cache[bucket_name])
failures = self._load_from_disk(bucket_name)
self._cache[bucket_name] = failures
return list(failures)
def save_failures(self, bucket_name: str, failures: List[ReplicationFailure]) -> None:
trimmed = failures[:self.max_failures_per_bucket]
self._cache[bucket_name] = trimmed
self._save_to_disk(bucket_name, trimmed)
def add_failure(self, bucket_name: str, failure: ReplicationFailure) -> None: def add_failure(self, bucket_name: str, failure: ReplicationFailure) -> None:
with self._lock: with self._lock:
failures = self.load_failures(bucket_name) failures = self.load_failures(bucket_name)
@@ -220,6 +240,7 @@ class ReplicationFailureStore:
def clear_failures(self, bucket_name: str) -> None: def clear_failures(self, bucket_name: str) -> None:
with self._lock: with self._lock:
self._cache.pop(bucket_name, None)
path = self._get_failures_path(bucket_name) path = self._get_failures_path(bucket_name)
if path.exists(): if path.exists():
path.unlink() path.unlink()
@@ -233,18 +254,43 @@ class ReplicationFailureStore:
class ReplicationManager: class ReplicationManager:
def __init__(self, storage: ObjectStorage, connections: ConnectionStore, rules_path: Path, storage_root: Path) -> None: def __init__(
self,
storage: ObjectStorage,
connections: ConnectionStore,
rules_path: Path,
storage_root: Path,
connect_timeout: int = 5,
read_timeout: int = 30,
max_retries: int = 2,
streaming_threshold_bytes: int = 10 * 1024 * 1024,
max_failures_per_bucket: int = 50,
) -> None:
self.storage = storage self.storage = storage
self.connections = connections self.connections = connections
self.rules_path = rules_path self.rules_path = rules_path
self.storage_root = storage_root self.storage_root = storage_root
self.connect_timeout = connect_timeout
self.read_timeout = read_timeout
self.max_retries = max_retries
self.streaming_threshold_bytes = streaming_threshold_bytes
self._rules: Dict[str, ReplicationRule] = {} self._rules: Dict[str, ReplicationRule] = {}
self._stats_lock = threading.Lock() self._stats_lock = threading.Lock()
self._executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="ReplicationWorker") self._executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="ReplicationWorker")
self._shutdown = False self._shutdown = False
self.failure_store = ReplicationFailureStore(storage_root) self.failure_store = ReplicationFailureStore(storage_root, max_failures_per_bucket)
self.reload_rules() self.reload_rules()
def _create_client(self, connection: RemoteConnection, *, health_check: bool = False) -> Any:
"""Create an S3 client with the manager's configured timeouts."""
return _create_s3_client(
connection,
health_check=health_check,
connect_timeout=self.connect_timeout,
read_timeout=self.read_timeout,
max_retries=self.max_retries,
)
def shutdown(self, wait: bool = True) -> None: def shutdown(self, wait: bool = True) -> None:
"""Shutdown the replication executor gracefully. """Shutdown the replication executor gracefully.
@@ -280,7 +326,7 @@ class ReplicationManager:
Uses short timeouts to prevent blocking. Uses short timeouts to prevent blocking.
""" """
try: try:
s3 = _create_s3_client(connection, health_check=True) s3 = self._create_client(connection, health_check=True)
s3.list_buckets() s3.list_buckets()
return True return True
except Exception as e: except Exception as e:
@@ -290,6 +336,9 @@ class ReplicationManager:
def get_rule(self, bucket_name: str) -> Optional[ReplicationRule]: def get_rule(self, bucket_name: str) -> Optional[ReplicationRule]:
return self._rules.get(bucket_name) return self._rules.get(bucket_name)
def list_rules(self) -> List[ReplicationRule]:
return list(self._rules.values())
def set_rule(self, rule: ReplicationRule) -> None: def set_rule(self, rule: ReplicationRule) -> None:
old_rule = self._rules.get(rule.bucket_name) old_rule = self._rules.get(rule.bucket_name)
was_all_mode = old_rule and old_rule.mode == REPLICATION_MODE_ALL if old_rule else False was_all_mode = old_rule and old_rule.mode == REPLICATION_MODE_ALL if old_rule else False
@@ -329,7 +378,7 @@ class ReplicationManager:
source_objects = self.storage.list_objects_all(bucket_name) source_objects = self.storage.list_objects_all(bucket_name)
source_keys = {obj.key: obj.size for obj in source_objects} source_keys = {obj.key: obj.size for obj in source_objects}
s3 = _create_s3_client(connection) s3 = self._create_client(connection)
dest_keys = set() dest_keys = set()
bytes_synced = 0 bytes_synced = 0
@@ -395,7 +444,7 @@ class ReplicationManager:
raise ValueError(f"Connection {connection_id} not found") raise ValueError(f"Connection {connection_id} not found")
try: try:
s3 = _create_s3_client(connection) s3 = self._create_client(connection)
s3.create_bucket(Bucket=bucket_name) s3.create_bucket(Bucket=bucket_name)
except ClientError as e: except ClientError as e:
logger.error(f"Failed to create remote bucket {bucket_name}: {e}") logger.error(f"Failed to create remote bucket {bucket_name}: {e}")
@@ -438,7 +487,7 @@ class ReplicationManager:
return return
try: try:
s3 = _create_s3_client(conn) s3 = self._create_client(conn)
if action == "delete": if action == "delete":
try: try:
@@ -481,7 +530,7 @@ class ReplicationManager:
if content_type: if content_type:
extra_args["ContentType"] = content_type extra_args["ContentType"] = content_type
if file_size >= STREAMING_THRESHOLD_BYTES: if file_size >= self.streaming_threshold_bytes:
s3.upload_file( s3.upload_file(
str(path), str(path),
rule.target_bucket, rule.target_bucket,

File diff suppressed because it is too large Load Diff

284
app/s3_client.py Normal file
View File

@@ -0,0 +1,284 @@
from __future__ import annotations
import json
import logging
import threading
import time
from typing import Any, Generator, Optional
import boto3
from botocore.config import Config
from botocore.exceptions import ClientError, EndpointConnectionError, ConnectionClosedError
from flask import current_app, session
logger = logging.getLogger(__name__)
UI_PROXY_USER_AGENT = "MyFSIO-UIProxy/1.0"
_BOTO_ERROR_MAP = {
"NoSuchBucket": 404,
"NoSuchKey": 404,
"NoSuchUpload": 404,
"BucketAlreadyExists": 409,
"BucketAlreadyOwnedByYou": 409,
"BucketNotEmpty": 409,
"AccessDenied": 403,
"InvalidAccessKeyId": 403,
"SignatureDoesNotMatch": 403,
"InvalidBucketName": 400,
"InvalidArgument": 400,
"MalformedXML": 400,
"EntityTooLarge": 400,
"QuotaExceeded": 403,
}
_UPLOAD_REGISTRY_MAX_AGE = 86400
_UPLOAD_REGISTRY_CLEANUP_INTERVAL = 3600
class UploadRegistry:
def __init__(self) -> None:
self._entries: dict[str, tuple[str, str, float]] = {}
self._lock = threading.Lock()
self._last_cleanup = time.monotonic()
def register(self, upload_id: str, bucket_name: str, object_key: str) -> None:
with self._lock:
self._entries[upload_id] = (bucket_name, object_key, time.monotonic())
self._maybe_cleanup()
def get_key(self, upload_id: str, bucket_name: str) -> Optional[str]:
with self._lock:
entry = self._entries.get(upload_id)
if entry is None:
return None
stored_bucket, key, created_at = entry
if stored_bucket != bucket_name:
return None
if time.monotonic() - created_at > _UPLOAD_REGISTRY_MAX_AGE:
del self._entries[upload_id]
return None
return key
def remove(self, upload_id: str) -> None:
with self._lock:
self._entries.pop(upload_id, None)
def _maybe_cleanup(self) -> None:
now = time.monotonic()
if now - self._last_cleanup < _UPLOAD_REGISTRY_CLEANUP_INTERVAL:
return
self._last_cleanup = now
cutoff = now - _UPLOAD_REGISTRY_MAX_AGE
stale = [uid for uid, (_, _, ts) in self._entries.items() if ts < cutoff]
for uid in stale:
del self._entries[uid]
class S3ProxyClient:
def __init__(self, api_base_url: str, region: str = "us-east-1") -> None:
if not api_base_url:
raise ValueError("api_base_url is required for S3ProxyClient")
self._api_base_url = api_base_url.rstrip("/")
self._region = region
self.upload_registry = UploadRegistry()
@property
def api_base_url(self) -> str:
return self._api_base_url
def get_client(self, access_key: str, secret_key: str) -> Any:
if not access_key or not secret_key:
raise ValueError("Both access_key and secret_key are required")
config = Config(
user_agent_extra=UI_PROXY_USER_AGENT,
connect_timeout=5,
read_timeout=30,
retries={"max_attempts": 0},
signature_version="s3v4",
s3={"addressing_style": "path"},
request_checksum_calculation="when_required",
response_checksum_validation="when_required",
)
return boto3.client(
"s3",
endpoint_url=self._api_base_url,
aws_access_key_id=access_key,
aws_secret_access_key=secret_key,
region_name=self._region,
config=config,
)
def _get_proxy() -> S3ProxyClient:
proxy = current_app.extensions.get("s3_proxy")
if proxy is None:
raise RuntimeError(
"S3 proxy not configured. Set API_BASE_URL or run both API and UI servers."
)
return proxy
def _get_session_creds() -> tuple[str, str]:
secret_store = current_app.extensions["secret_store"]
secret_store.purge_expired()
token = session.get("cred_token")
if not token:
raise PermissionError("Not authenticated")
creds = secret_store.peek(token)
if not creds:
raise PermissionError("Session expired")
access_key = creds.get("access_key", "")
secret_key = creds.get("secret_key", "")
if not access_key or not secret_key:
raise PermissionError("Invalid session credentials")
return access_key, secret_key
def get_session_s3_client() -> Any:
proxy = _get_proxy()
access_key, secret_key = _get_session_creds()
return proxy.get_client(access_key, secret_key)
def get_upload_registry() -> UploadRegistry:
return _get_proxy().upload_registry
def handle_client_error(exc: ClientError) -> tuple[dict[str, str], int]:
error_info = exc.response.get("Error", {})
code = error_info.get("Code", "InternalError")
message = error_info.get("Message") or "S3 operation failed"
http_status = _BOTO_ERROR_MAP.get(code)
if http_status is None:
http_status = exc.response.get("ResponseMetadata", {}).get("HTTPStatusCode", 500)
return {"error": message}, http_status
def handle_connection_error(exc: Exception) -> tuple[dict[str, str], int]:
logger.error("S3 API connection failed: %s", exc)
return {"error": "S3 API server is unreachable. Ensure the API server is running."}, 502
def format_datetime_display(dt: Any, display_tz: str = "UTC") -> str:
from .ui import _format_datetime_display
return _format_datetime_display(dt, display_tz)
def format_datetime_iso(dt: Any, display_tz: str = "UTC") -> str:
from .ui import _format_datetime_iso
return _format_datetime_iso(dt, display_tz)
def build_url_templates(bucket_name: str) -> dict[str, str]:
from flask import url_for
preview_t = url_for("ui.object_preview", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
delete_t = url_for("ui.delete_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
presign_t = url_for("ui.object_presign", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
versions_t = url_for("ui.object_versions", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
restore_t = url_for(
"ui.restore_object_version",
bucket_name=bucket_name,
object_key="KEY_PLACEHOLDER",
version_id="VERSION_ID_PLACEHOLDER",
)
tags_t = url_for("ui.object_tags", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
copy_t = url_for("ui.copy_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
move_t = url_for("ui.move_object", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
metadata_t = url_for("ui.object_metadata", bucket_name=bucket_name, object_key="KEY_PLACEHOLDER")
return {
"preview": preview_t,
"download": preview_t + "?download=1",
"presign": presign_t,
"delete": delete_t,
"versions": versions_t,
"restore": restore_t,
"tags": tags_t,
"copy": copy_t,
"move": move_t,
"metadata": metadata_t,
}
def translate_list_objects(
boto3_response: dict[str, Any],
url_templates: dict[str, str],
display_tz: str = "UTC",
versioning_enabled: bool = False,
) -> dict[str, Any]:
objects_data = []
for obj in boto3_response.get("Contents", []):
last_mod = obj["LastModified"]
objects_data.append({
"key": obj["Key"],
"size": obj["Size"],
"last_modified": last_mod.isoformat(),
"last_modified_display": format_datetime_display(last_mod, display_tz),
"last_modified_iso": format_datetime_iso(last_mod, display_tz),
"etag": obj.get("ETag", "").strip('"'),
})
return {
"objects": objects_data,
"is_truncated": boto3_response.get("IsTruncated", False),
"next_continuation_token": boto3_response.get("NextContinuationToken"),
"total_count": boto3_response.get("KeyCount", len(objects_data)),
"versioning_enabled": versioning_enabled,
"url_templates": url_templates,
}
def get_versioning_via_s3(client: Any, bucket_name: str) -> bool:
try:
resp = client.get_bucket_versioning(Bucket=bucket_name)
return resp.get("Status") == "Enabled"
except ClientError as exc:
code = exc.response.get("Error", {}).get("Code", "")
if code != "NoSuchBucket":
logger.warning("Failed to check versioning for %s: %s", bucket_name, code)
return False
def stream_objects_ndjson(
client: Any,
bucket_name: str,
prefix: Optional[str],
url_templates: dict[str, str],
display_tz: str = "UTC",
versioning_enabled: bool = False,
) -> Generator[str, None, None]:
meta_line = json.dumps({
"type": "meta",
"versioning_enabled": versioning_enabled,
"url_templates": url_templates,
}) + "\n"
yield meta_line
yield json.dumps({"type": "count", "total_count": 0}) + "\n"
kwargs: dict[str, Any] = {"Bucket": bucket_name, "MaxKeys": 1000}
if prefix:
kwargs["Prefix"] = prefix
try:
paginator = client.get_paginator("list_objects_v2")
for page in paginator.paginate(**kwargs):
for obj in page.get("Contents", []):
last_mod = obj["LastModified"]
yield json.dumps({
"type": "object",
"key": obj["Key"],
"size": obj["Size"],
"last_modified": last_mod.isoformat(),
"last_modified_display": format_datetime_display(last_mod, display_tz),
"last_modified_iso": format_datetime_iso(last_mod, display_tz),
"etag": obj.get("ETag", "").strip('"'),
}) + "\n"
except ClientError as exc:
error_msg = exc.response.get("Error", {}).get("Message", "S3 operation failed")
yield json.dumps({"type": "error", "error": error_msg}) + "\n"
return
except (EndpointConnectionError, ConnectionClosedError):
yield json.dumps({"type": "error", "error": "S3 API server is unreachable"}) + "\n"
return
yield json.dumps({"type": "done"}) + "\n"

View File

@@ -18,6 +18,18 @@ class EphemeralSecretStore:
self._store[token] = (payload, expires_at) self._store[token] = (payload, expires_at)
return token return token
def peek(self, token: str | None) -> Any | None:
if not token:
return None
entry = self._store.get(token)
if not entry:
return None
payload, expires_at = entry
if expires_at < time.time():
self._store.pop(token, None)
return None
return payload
def pop(self, token: str | None) -> Any | None: def pop(self, token: str | None) -> Any | None:
if not token: if not token:
return None return None

171
app/select_content.py Normal file
View File

@@ -0,0 +1,171 @@
"""S3 SelectObjectContent SQL query execution using DuckDB."""
from __future__ import annotations
import json
from pathlib import Path
from typing import Any, Dict, Generator, Optional
try:
import duckdb
DUCKDB_AVAILABLE = True
except ImportError:
DUCKDB_AVAILABLE = False
class SelectError(Exception):
"""Error during SELECT query execution."""
pass
def execute_select_query(
file_path: Path,
expression: str,
input_format: str,
input_config: Dict[str, Any],
output_format: str,
output_config: Dict[str, Any],
chunk_size: int = 65536,
) -> Generator[bytes, None, None]:
"""Execute SQL query on object content."""
if not DUCKDB_AVAILABLE:
raise SelectError("DuckDB is not installed. Install with: pip install duckdb")
conn = duckdb.connect(":memory:")
try:
if input_format == "CSV":
_load_csv(conn, file_path, input_config)
elif input_format == "JSON":
_load_json(conn, file_path, input_config)
elif input_format == "Parquet":
_load_parquet(conn, file_path)
else:
raise SelectError(f"Unsupported input format: {input_format}")
normalized_expression = expression.replace("s3object", "data").replace("S3Object", "data")
try:
result = conn.execute(normalized_expression)
except duckdb.Error as exc:
raise SelectError(f"SQL execution error: {exc}")
if output_format == "CSV":
yield from _output_csv(result, output_config, chunk_size)
elif output_format == "JSON":
yield from _output_json(result, output_config, chunk_size)
else:
raise SelectError(f"Unsupported output format: {output_format}")
finally:
conn.close()
def _load_csv(conn, file_path: Path, config: Dict[str, Any]) -> None:
"""Load CSV file into DuckDB."""
file_header_info = config.get("file_header_info", "NONE")
delimiter = config.get("field_delimiter", ",")
quote = config.get("quote_character", '"')
header = file_header_info in ("USE", "IGNORE")
path_str = str(file_path).replace("\\", "/")
conn.execute(f"""
CREATE TABLE data AS
SELECT * FROM read_csv('{path_str}',
header={header},
delim='{delimiter}',
quote='{quote}'
)
""")
def _load_json(conn, file_path: Path, config: Dict[str, Any]) -> None:
"""Load JSON file into DuckDB."""
json_type = config.get("type", "DOCUMENT")
path_str = str(file_path).replace("\\", "/")
if json_type == "LINES":
conn.execute(f"""
CREATE TABLE data AS
SELECT * FROM read_json_auto('{path_str}', format='newline_delimited')
""")
else:
conn.execute(f"""
CREATE TABLE data AS
SELECT * FROM read_json_auto('{path_str}', format='array')
""")
def _load_parquet(conn, file_path: Path) -> None:
"""Load Parquet file into DuckDB."""
path_str = str(file_path).replace("\\", "/")
conn.execute(f"CREATE TABLE data AS SELECT * FROM read_parquet('{path_str}')")
def _output_csv(
result,
config: Dict[str, Any],
chunk_size: int,
) -> Generator[bytes, None, None]:
"""Output query results as CSV."""
delimiter = config.get("field_delimiter", ",")
record_delimiter = config.get("record_delimiter", "\n")
quote = config.get("quote_character", '"')
buffer = ""
while True:
rows = result.fetchmany(1000)
if not rows:
break
for row in rows:
fields = []
for value in row:
if value is None:
fields.append("")
elif isinstance(value, str):
if delimiter in value or quote in value or record_delimiter in value:
escaped = value.replace(quote, quote + quote)
fields.append(f'{quote}{escaped}{quote}')
else:
fields.append(value)
else:
fields.append(str(value))
buffer += delimiter.join(fields) + record_delimiter
while len(buffer) >= chunk_size:
yield buffer[:chunk_size].encode("utf-8")
buffer = buffer[chunk_size:]
if buffer:
yield buffer.encode("utf-8")
def _output_json(
result,
config: Dict[str, Any],
chunk_size: int,
) -> Generator[bytes, None, None]:
"""Output query results as JSON Lines."""
record_delimiter = config.get("record_delimiter", "\n")
columns = [desc[0] for desc in result.description]
buffer = ""
while True:
rows = result.fetchmany(1000)
if not rows:
break
for row in rows:
record = dict(zip(columns, row))
buffer += json.dumps(record, default=str) + record_delimiter
while len(buffer) >= chunk_size:
yield buffer[:chunk_size].encode("utf-8")
buffer = buffer[chunk_size:]
if buffer:
yield buffer.encode("utf-8")

177
app/site_registry.py Normal file
View File

@@ -0,0 +1,177 @@
from __future__ import annotations
import json
import time
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, Dict, List, Optional
@dataclass
class SiteInfo:
site_id: str
endpoint: str
region: str = "us-east-1"
priority: int = 100
display_name: str = ""
created_at: Optional[float] = None
updated_at: Optional[float] = None
def __post_init__(self) -> None:
if not self.display_name:
self.display_name = self.site_id
if self.created_at is None:
self.created_at = time.time()
def to_dict(self) -> Dict[str, Any]:
return {
"site_id": self.site_id,
"endpoint": self.endpoint,
"region": self.region,
"priority": self.priority,
"display_name": self.display_name,
"created_at": self.created_at,
"updated_at": self.updated_at,
}
@classmethod
def from_dict(cls, data: Dict[str, Any]) -> SiteInfo:
return cls(
site_id=data["site_id"],
endpoint=data.get("endpoint", ""),
region=data.get("region", "us-east-1"),
priority=data.get("priority", 100),
display_name=data.get("display_name", ""),
created_at=data.get("created_at"),
updated_at=data.get("updated_at"),
)
@dataclass
class PeerSite:
site_id: str
endpoint: str
region: str = "us-east-1"
priority: int = 100
display_name: str = ""
created_at: Optional[float] = None
updated_at: Optional[float] = None
connection_id: Optional[str] = None
is_healthy: Optional[bool] = None
last_health_check: Optional[float] = None
def __post_init__(self) -> None:
if not self.display_name:
self.display_name = self.site_id
if self.created_at is None:
self.created_at = time.time()
def to_dict(self) -> Dict[str, Any]:
return {
"site_id": self.site_id,
"endpoint": self.endpoint,
"region": self.region,
"priority": self.priority,
"display_name": self.display_name,
"created_at": self.created_at,
"updated_at": self.updated_at,
"connection_id": self.connection_id,
"is_healthy": self.is_healthy,
"last_health_check": self.last_health_check,
}
@classmethod
def from_dict(cls, data: Dict[str, Any]) -> PeerSite:
return cls(
site_id=data["site_id"],
endpoint=data.get("endpoint", ""),
region=data.get("region", "us-east-1"),
priority=data.get("priority", 100),
display_name=data.get("display_name", ""),
created_at=data.get("created_at"),
updated_at=data.get("updated_at"),
connection_id=data.get("connection_id"),
is_healthy=data.get("is_healthy"),
last_health_check=data.get("last_health_check"),
)
class SiteRegistry:
def __init__(self, config_path: Path) -> None:
self.config_path = config_path
self._local_site: Optional[SiteInfo] = None
self._peers: Dict[str, PeerSite] = {}
self.reload()
def reload(self) -> None:
if not self.config_path.exists():
self._local_site = None
self._peers = {}
return
try:
with open(self.config_path, "r", encoding="utf-8") as f:
data = json.load(f)
if data.get("local"):
self._local_site = SiteInfo.from_dict(data["local"])
else:
self._local_site = None
self._peers = {}
for peer_data in data.get("peers", []):
peer = PeerSite.from_dict(peer_data)
self._peers[peer.site_id] = peer
except (OSError, json.JSONDecodeError, KeyError):
self._local_site = None
self._peers = {}
def save(self) -> None:
self.config_path.parent.mkdir(parents=True, exist_ok=True)
data = {
"local": self._local_site.to_dict() if self._local_site else None,
"peers": [peer.to_dict() for peer in self._peers.values()],
}
with open(self.config_path, "w", encoding="utf-8") as f:
json.dump(data, f, indent=2)
def get_local_site(self) -> Optional[SiteInfo]:
return self._local_site
def set_local_site(self, site: SiteInfo) -> None:
site.updated_at = time.time()
self._local_site = site
self.save()
def list_peers(self) -> List[PeerSite]:
return list(self._peers.values())
def get_peer(self, site_id: str) -> Optional[PeerSite]:
return self._peers.get(site_id)
def add_peer(self, peer: PeerSite) -> None:
peer.created_at = peer.created_at or time.time()
self._peers[peer.site_id] = peer
self.save()
def update_peer(self, peer: PeerSite) -> None:
if peer.site_id not in self._peers:
raise ValueError(f"Peer {peer.site_id} not found")
peer.updated_at = time.time()
self._peers[peer.site_id] = peer
self.save()
def delete_peer(self, site_id: str) -> bool:
if site_id in self._peers:
del self._peers[site_id]
self.save()
return True
return False
def update_health(self, site_id: str, is_healthy: bool) -> None:
peer = self._peers.get(site_id)
if peer:
peer.is_healthy = is_healthy
peer.last_health_check = time.time()
self.save()

View File

@@ -22,9 +22,6 @@ if TYPE_CHECKING:
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
SITE_SYNC_USER_AGENT = "SiteSyncAgent/1.0" SITE_SYNC_USER_AGENT = "SiteSyncAgent/1.0"
SITE_SYNC_CONNECT_TIMEOUT = 10
SITE_SYNC_READ_TIMEOUT = 120
CLOCK_SKEW_TOLERANCE_SECONDS = 1.0
@dataclass @dataclass
@@ -108,12 +105,18 @@ class RemoteObjectMeta:
) )
def _create_sync_client(connection: "RemoteConnection") -> Any: def _create_sync_client(
connection: "RemoteConnection",
*,
connect_timeout: int = 10,
read_timeout: int = 120,
max_retries: int = 2,
) -> Any:
config = Config( config = Config(
user_agent_extra=SITE_SYNC_USER_AGENT, user_agent_extra=SITE_SYNC_USER_AGENT,
connect_timeout=SITE_SYNC_CONNECT_TIMEOUT, connect_timeout=connect_timeout,
read_timeout=SITE_SYNC_READ_TIMEOUT, read_timeout=read_timeout,
retries={"max_attempts": 2}, retries={"max_attempts": max_retries},
signature_version="s3v4", signature_version="s3v4",
s3={"addressing_style": "path"}, s3={"addressing_style": "path"},
request_checksum_calculation="when_required", request_checksum_calculation="when_required",
@@ -138,6 +141,10 @@ class SiteSyncWorker:
storage_root: Path, storage_root: Path,
interval_seconds: int = 60, interval_seconds: int = 60,
batch_size: int = 100, batch_size: int = 100,
connect_timeout: int = 10,
read_timeout: int = 120,
max_retries: int = 2,
clock_skew_tolerance_seconds: float = 1.0,
): ):
self.storage = storage self.storage = storage
self.connections = connections self.connections = connections
@@ -145,11 +152,24 @@ class SiteSyncWorker:
self.storage_root = storage_root self.storage_root = storage_root
self.interval_seconds = interval_seconds self.interval_seconds = interval_seconds
self.batch_size = batch_size self.batch_size = batch_size
self.connect_timeout = connect_timeout
self.read_timeout = read_timeout
self.max_retries = max_retries
self.clock_skew_tolerance_seconds = clock_skew_tolerance_seconds
self._lock = threading.Lock() self._lock = threading.Lock()
self._shutdown = threading.Event() self._shutdown = threading.Event()
self._sync_thread: Optional[threading.Thread] = None self._sync_thread: Optional[threading.Thread] = None
self._bucket_stats: Dict[str, SiteSyncStats] = {} self._bucket_stats: Dict[str, SiteSyncStats] = {}
def _create_client(self, connection: "RemoteConnection") -> Any:
"""Create an S3 client with the worker's configured timeouts."""
return _create_sync_client(
connection,
connect_timeout=self.connect_timeout,
read_timeout=self.read_timeout,
max_retries=self.max_retries,
)
def start(self) -> None: def start(self) -> None:
if self._sync_thread is not None and self._sync_thread.is_alive(): if self._sync_thread is not None and self._sync_thread.is_alive():
return return
@@ -294,7 +314,7 @@ class SiteSyncWorker:
return {obj.key: obj for obj in objects} return {obj.key: obj for obj in objects}
def _list_remote_objects(self, rule: "ReplicationRule", connection: "RemoteConnection") -> Dict[str, RemoteObjectMeta]: def _list_remote_objects(self, rule: "ReplicationRule", connection: "RemoteConnection") -> Dict[str, RemoteObjectMeta]:
s3 = _create_sync_client(connection) s3 = self._create_client(connection)
result: Dict[str, RemoteObjectMeta] = {} result: Dict[str, RemoteObjectMeta] = {}
paginator = s3.get_paginator("list_objects_v2") paginator = s3.get_paginator("list_objects_v2")
try: try:
@@ -312,7 +332,7 @@ class SiteSyncWorker:
local_ts = local_meta.last_modified.timestamp() local_ts = local_meta.last_modified.timestamp()
remote_ts = remote_meta.last_modified.timestamp() remote_ts = remote_meta.last_modified.timestamp()
if abs(remote_ts - local_ts) < CLOCK_SKEW_TOLERANCE_SECONDS: if abs(remote_ts - local_ts) < self.clock_skew_tolerance_seconds:
local_etag = local_meta.etag or "" local_etag = local_meta.etag or ""
if remote_meta.etag == local_etag: if remote_meta.etag == local_etag:
return "skip" return "skip"
@@ -327,7 +347,7 @@ class SiteSyncWorker:
connection: "RemoteConnection", connection: "RemoteConnection",
remote_meta: RemoteObjectMeta, remote_meta: RemoteObjectMeta,
) -> bool: ) -> bool:
s3 = _create_sync_client(connection) s3 = self._create_client(connection)
tmp_path = None tmp_path = None
try: try:
tmp_dir = self.storage_root / ".myfsio.sys" / "tmp" tmp_dir = self.storage_root / ".myfsio.sys" / "tmp"

View File

@@ -11,6 +11,7 @@ import time
import unicodedata import unicodedata
import uuid import uuid
from collections import OrderedDict from collections import OrderedDict
from concurrent.futures import ThreadPoolExecutor
from contextlib import contextmanager from contextlib import contextmanager
from dataclasses import dataclass from dataclasses import dataclass
from datetime import datetime, timezone from datetime import datetime, timezone
@@ -46,6 +47,34 @@ else:
fcntl.flock(file_handle.fileno(), fcntl.LOCK_UN) fcntl.flock(file_handle.fileno(), fcntl.LOCK_UN)
@contextmanager
def _atomic_lock_file(lock_path: Path, max_retries: int = 10, base_delay: float = 0.1) -> Generator[None, None, None]:
"""Atomically acquire a lock file with exponential backoff.
Uses O_EXCL to ensure atomic creation of the lock file.
"""
lock_path.parent.mkdir(parents=True, exist_ok=True)
fd = None
for attempt in range(max_retries):
try:
fd = os.open(str(lock_path), os.O_CREAT | os.O_EXCL | os.O_WRONLY)
break
except FileExistsError:
if attempt == max_retries - 1:
raise BlockingIOError("Another upload to this key is in progress")
delay = base_delay * (2 ** attempt)
time.sleep(min(delay, 2.0))
try:
yield
finally:
if fd is not None:
os.close(fd)
try:
lock_path.unlink(missing_ok=True)
except OSError:
pass
WINDOWS_RESERVED_NAMES = { WINDOWS_RESERVED_NAMES = {
"CON", "CON",
"PRN", "PRN",
@@ -137,20 +166,30 @@ class ObjectStorage:
BUCKET_VERSIONS_DIR = "versions" BUCKET_VERSIONS_DIR = "versions"
MULTIPART_MANIFEST = "manifest.json" MULTIPART_MANIFEST = "manifest.json"
BUCKET_CONFIG_FILE = ".bucket.json" BUCKET_CONFIG_FILE = ".bucket.json"
DEFAULT_CACHE_TTL = 5
OBJECT_CACHE_MAX_SIZE = 100
def __init__(self, root: Path, cache_ttl: int = DEFAULT_CACHE_TTL) -> None: def __init__(
self,
root: Path,
cache_ttl: int = 5,
object_cache_max_size: int = 100,
bucket_config_cache_ttl: float = 30.0,
object_key_max_length_bytes: int = 1024,
) -> None:
self.root = Path(root) self.root = Path(root)
self.root.mkdir(parents=True, exist_ok=True) self.root.mkdir(parents=True, exist_ok=True)
self._ensure_system_roots() self._ensure_system_roots()
self._object_cache: OrderedDict[str, tuple[Dict[str, ObjectMeta], float]] = OrderedDict() self._object_cache: OrderedDict[str, tuple[Dict[str, ObjectMeta], float, float]] = OrderedDict()
self._cache_lock = threading.Lock() self._cache_lock = threading.Lock()
self._bucket_locks: Dict[str, threading.Lock] = {} self._bucket_locks: Dict[str, threading.Lock] = {}
self._cache_version: Dict[str, int] = {} self._cache_version: Dict[str, int] = {}
self._bucket_config_cache: Dict[str, tuple[dict[str, Any], float]] = {} self._bucket_config_cache: Dict[str, tuple[dict[str, Any], float]] = {}
self._bucket_config_cache_ttl = 30.0 self._bucket_config_cache_ttl = bucket_config_cache_ttl
self._cache_ttl = cache_ttl self._cache_ttl = cache_ttl
self._object_cache_max_size = object_cache_max_size
self._object_key_max_length_bytes = object_key_max_length_bytes
self._sorted_key_cache: Dict[str, tuple[list[str], int]] = {}
self._meta_index_locks: Dict[str, threading.Lock] = {}
self._cleanup_executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix="ParentCleanup")
def _get_bucket_lock(self, bucket_id: str) -> threading.Lock: def _get_bucket_lock(self, bucket_id: str) -> threading.Lock:
"""Get or create a lock for a specific bucket. Reduces global lock contention.""" """Get or create a lock for a specific bucket. Reduces global lock contention."""
@@ -208,10 +247,15 @@ class ObjectStorage:
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
cache_path = self._system_bucket_root(bucket_name) / "stats.json" cache_path = self._system_bucket_root(bucket_name) / "stats.json"
cached_stats = None
cache_fresh = False
if cache_path.exists(): if cache_path.exists():
try: try:
if time.time() - cache_path.stat().st_mtime < cache_ttl: cache_fresh = time.time() - cache_path.stat().st_mtime < cache_ttl
return json.loads(cache_path.read_text(encoding="utf-8")) cached_stats = json.loads(cache_path.read_text(encoding="utf-8"))
if cache_fresh:
return cached_stats
except (OSError, json.JSONDecodeError): except (OSError, json.JSONDecodeError):
pass pass
@@ -220,6 +264,7 @@ class ObjectStorage:
version_count = 0 version_count = 0
version_bytes = 0 version_bytes = 0
try:
for path in bucket_path.rglob("*"): for path in bucket_path.rglob("*"):
if path.is_file(): if path.is_file():
rel = path.relative_to(bucket_path) rel = path.relative_to(bucket_path)
@@ -238,6 +283,14 @@ class ObjectStorage:
stat = path.stat() stat = path.stat()
version_count += 1 version_count += 1
version_bytes += stat.st_size version_bytes += stat.st_size
except OSError:
if cached_stats is not None:
return cached_stats
raise
existing_serial = 0
if cached_stats is not None:
existing_serial = cached_stats.get("_cache_serial", 0)
stats = { stats = {
"objects": object_count, "objects": object_count,
@@ -246,6 +299,7 @@ class ObjectStorage:
"version_bytes": version_bytes, "version_bytes": version_bytes,
"total_objects": object_count + version_count, "total_objects": object_count + version_count,
"total_bytes": total_bytes + version_bytes, "total_bytes": total_bytes + version_bytes,
"_cache_serial": existing_serial,
} }
try: try:
@@ -264,6 +318,39 @@ class ObjectStorage:
except OSError: except OSError:
pass pass
def _update_bucket_stats_cache(
self,
bucket_id: str,
*,
bytes_delta: int = 0,
objects_delta: int = 0,
version_bytes_delta: int = 0,
version_count_delta: int = 0,
) -> None:
"""Incrementally update cached bucket statistics instead of invalidating.
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.
"""
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):
pass
def delete_bucket(self, bucket_name: str) -> None: def delete_bucket(self, bucket_name: str) -> None:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists(): if not bucket_path.exists():
@@ -298,6 +385,8 @@ class ObjectStorage:
Returns: Returns:
ListObjectsResult with objects, truncation status, and continuation token ListObjectsResult with objects, truncation status, and continuation token
""" """
import bisect
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
@@ -305,16 +394,26 @@ class ObjectStorage:
object_cache = self._get_object_cache(bucket_id, bucket_path) object_cache = self._get_object_cache(bucket_id, bucket_path)
cache_version = self._cache_version.get(bucket_id, 0)
cached_entry = self._sorted_key_cache.get(bucket_id)
if cached_entry and cached_entry[1] == cache_version:
all_keys = cached_entry[0]
else:
all_keys = sorted(object_cache.keys()) all_keys = sorted(object_cache.keys())
self._sorted_key_cache[bucket_id] = (all_keys, cache_version)
if prefix: if prefix:
all_keys = [k for k in all_keys if k.startswith(prefix)] lo = bisect.bisect_left(all_keys, prefix)
hi = len(all_keys)
for i in range(lo, len(all_keys)):
if not all_keys[i].startswith(prefix):
hi = i
break
all_keys = all_keys[lo:hi]
total_count = len(all_keys) total_count = len(all_keys)
start_index = 0 start_index = 0
if continuation_token: if continuation_token:
try:
import bisect
start_index = bisect.bisect_right(all_keys, continuation_token) start_index = bisect.bisect_right(all_keys, continuation_token)
if start_index >= total_count: if start_index >= total_count:
return ListObjectsResult( return ListObjectsResult(
@@ -323,8 +422,6 @@ class ObjectStorage:
next_continuation_token=None, next_continuation_token=None,
total_count=total_count, total_count=total_count,
) )
except Exception:
pass
end_index = start_index + max_keys end_index = start_index + max_keys
keys_slice = all_keys[start_index:end_index] keys_slice = all_keys[start_index:end_index]
@@ -364,14 +461,16 @@ class ObjectStorage:
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
bucket_id = bucket_path.name bucket_id = bucket_path.name
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
destination = bucket_path / safe_key destination = bucket_path / safe_key
destination.parent.mkdir(parents=True, exist_ok=True) destination.parent.mkdir(parents=True, exist_ok=True)
is_overwrite = destination.exists() is_overwrite = destination.exists()
existing_size = destination.stat().st_size if is_overwrite else 0 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: 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") self._archive_current_version(bucket_id, safe_key, reason="overwrite")
tmp_dir = self._system_root_path() / self.SYSTEM_TMP_DIR tmp_dir = self._system_root_path() / self.SYSTEM_TMP_DIR
@@ -384,11 +483,10 @@ class ObjectStorage:
shutil.copyfileobj(_HashingReader(stream, checksum), target) shutil.copyfileobj(_HashingReader(stream, checksum), target)
new_size = tmp_path.stat().st_size new_size = tmp_path.stat().st_size
if enforce_quota:
size_delta = new_size - existing_size size_delta = new_size - existing_size
object_delta = 0 if is_overwrite else 1 object_delta = 0 if is_overwrite else 1
if enforce_quota:
quota_check = self.check_quota( quota_check = self.check_quota(
bucket_name, bucket_name,
additional_bytes=max(0, size_delta), additional_bytes=max(0, size_delta),
@@ -416,7 +514,13 @@ class ObjectStorage:
combined_meta = {**internal_meta, **(metadata or {})} combined_meta = {**internal_meta, **(metadata or {})}
self._write_metadata(bucket_id, safe_key, combined_meta) self._write_metadata(bucket_id, safe_key, combined_meta)
self._invalidate_bucket_stats_cache(bucket_id) self._update_bucket_stats_cache(
bucket_id,
bytes_delta=size_delta,
objects_delta=object_delta,
version_bytes_delta=archived_version_size,
version_count_delta=1 if archived_version_size > 0 else 0,
)
obj_meta = ObjectMeta( obj_meta = ObjectMeta(
key=safe_key.as_posix(), key=safe_key.as_posix(),
@@ -431,7 +535,7 @@ class ObjectStorage:
def get_object_path(self, bucket_name: str, object_key: str) -> Path: def get_object_path(self, bucket_name: str, object_key: str) -> Path:
path = self._object_path(bucket_name, object_key) path = self._object_path(bucket_name, object_key)
if not path.exists(): if not path.is_file():
raise ObjectNotFoundError("Object not found") raise ObjectNotFoundError("Object not found")
return path return path
@@ -439,15 +543,18 @@ class ObjectStorage:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists(): if not bucket_path.exists():
return {} return {}
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
return self._read_metadata(bucket_path.name, safe_key) or {} return self._read_metadata(bucket_path.name, safe_key) or {}
def _cleanup_empty_parents(self, path: Path, stop_at: Path) -> None: def _cleanup_empty_parents(self, path: Path, stop_at: Path) -> None:
"""Remove empty parent directories up to (but not including) stop_at. """Remove empty parent directories in a background thread.
On Windows/OneDrive, directories may be locked briefly after file deletion. On Windows/OneDrive, directories may be locked briefly after file deletion.
This method retries with a small delay to handle that case. Running this in the background avoids blocking the request thread with retries.
""" """
self._cleanup_executor.submit(self._do_cleanup_empty_parents, path, stop_at)
def _do_cleanup_empty_parents(self, path: Path, stop_at: Path) -> None:
for parent in path.parents: for parent in path.parents:
if parent == stop_at: if parent == stop_at:
break break
@@ -466,15 +573,24 @@ class ObjectStorage:
path = self._object_path(bucket_name, object_key) path = self._object_path(bucket_name, object_key)
if not path.exists(): if not path.exists():
return return
deleted_size = path.stat().st_size
safe_key = path.relative_to(bucket_path) safe_key = path.relative_to(bucket_path)
bucket_id = bucket_path.name bucket_id = bucket_path.name
archived_version_size = 0
if self._is_versioning_enabled(bucket_path): if self._is_versioning_enabled(bucket_path):
archived_version_size = deleted_size
self._archive_current_version(bucket_id, safe_key, reason="delete") self._archive_current_version(bucket_id, safe_key, reason="delete")
rel = path.relative_to(bucket_path) rel = path.relative_to(bucket_path)
self._safe_unlink(path) self._safe_unlink(path)
self._delete_metadata(bucket_id, rel) self._delete_metadata(bucket_id, rel)
self._invalidate_bucket_stats_cache(bucket_id) self._update_bucket_stats_cache(
bucket_id,
bytes_delta=-deleted_size,
objects_delta=-1,
version_bytes_delta=archived_version_size,
version_count_delta=1 if archived_version_size > 0 else 0,
)
self._update_object_cache_entry(bucket_id, safe_key.as_posix(), None) self._update_object_cache_entry(bucket_id, safe_key.as_posix(), None)
self._cleanup_empty_parents(path, bucket_path) self._cleanup_empty_parents(path, bucket_path)
@@ -487,7 +603,7 @@ class ObjectStorage:
self._safe_unlink(target) self._safe_unlink(target)
self._delete_metadata(bucket_id, rel) self._delete_metadata(bucket_id, rel)
else: else:
rel = self._sanitize_object_key(object_key) rel = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
self._delete_metadata(bucket_id, rel) self._delete_metadata(bucket_id, rel)
version_dir = self._version_dir(bucket_id, rel) version_dir = self._version_dir(bucket_id, rel)
if version_dir.exists(): if version_dir.exists():
@@ -572,10 +688,19 @@ class ObjectStorage:
return lifecycle if isinstance(lifecycle, list) else None return lifecycle if isinstance(lifecycle, list) else None
def set_bucket_lifecycle(self, bucket_name: str, rules: Optional[List[Dict[str, Any]]]) -> None: def set_bucket_lifecycle(self, bucket_name: str, rules: Optional[List[Dict[str, Any]]]) -> None:
"""Set lifecycle configuration for bucket."""
bucket_path = self._require_bucket_path(bucket_name) bucket_path = self._require_bucket_path(bucket_name)
self._set_bucket_config_entry(bucket_path.name, "lifecycle", rules) self._set_bucket_config_entry(bucket_path.name, "lifecycle", rules)
def get_bucket_website(self, bucket_name: str) -> Optional[Dict[str, Any]]:
bucket_path = self._require_bucket_path(bucket_name)
config = self._read_bucket_config(bucket_path.name)
website = config.get("website")
return website if isinstance(website, dict) else None
def set_bucket_website(self, bucket_name: str, website_config: Optional[Dict[str, Any]]) -> None:
bucket_path = self._require_bucket_path(bucket_name)
self._set_bucket_config_entry(bucket_path.name, "website", website_config)
def get_bucket_quota(self, bucket_name: str) -> Dict[str, Any]: def get_bucket_quota(self, bucket_name: str) -> Dict[str, Any]:
"""Get quota configuration for bucket. """Get quota configuration for bucket.
@@ -696,11 +821,15 @@ class ObjectStorage:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
object_path = bucket_path / safe_key object_path = bucket_path / safe_key
if not object_path.exists(): if not object_path.exists():
raise ObjectNotFoundError("Object does not exist") raise ObjectNotFoundError("Object does not exist")
entry = self._read_index_entry(bucket_path.name, safe_key)
if entry is not None:
tags = entry.get("tags")
return tags if isinstance(tags, list) else []
for meta_file in (self._metadata_file(bucket_path.name, safe_key), self._legacy_metadata_file(bucket_path.name, safe_key)): for meta_file in (self._metadata_file(bucket_path.name, safe_key), self._legacy_metadata_file(bucket_path.name, safe_key)):
if not meta_file.exists(): if not meta_file.exists():
continue continue
@@ -719,35 +848,36 @@ class ObjectStorage:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
object_path = bucket_path / safe_key object_path = bucket_path / safe_key
if not object_path.exists(): if not object_path.exists():
raise ObjectNotFoundError("Object does not exist") raise ObjectNotFoundError("Object does not exist")
meta_file = self._metadata_file(bucket_path.name, safe_key) bucket_id = bucket_path.name
existing_entry = self._read_index_entry(bucket_id, safe_key) or {}
existing_payload: Dict[str, Any] = {} if not existing_entry:
meta_file = self._metadata_file(bucket_id, safe_key)
if meta_file.exists(): if meta_file.exists():
try: try:
existing_payload = json.loads(meta_file.read_text(encoding="utf-8")) existing_entry = json.loads(meta_file.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError): except (OSError, json.JSONDecodeError):
pass pass
if tags: if tags:
existing_payload["tags"] = tags existing_entry["tags"] = tags
else: else:
existing_payload.pop("tags", None) existing_entry.pop("tags", None)
if existing_payload.get("metadata") or existing_payload.get("tags"): if existing_entry.get("metadata") or existing_entry.get("tags"):
meta_file.parent.mkdir(parents=True, exist_ok=True) self._write_index_entry(bucket_id, safe_key, existing_entry)
meta_file.write_text(json.dumps(existing_payload), encoding="utf-8") else:
elif meta_file.exists(): self._delete_index_entry(bucket_id, safe_key)
meta_file.unlink() old_meta = self._metadata_file(bucket_id, safe_key)
parent = meta_file.parent try:
meta_root = self._bucket_meta_root(bucket_path.name) if old_meta.exists():
while parent != meta_root and parent.exists() and not any(parent.iterdir()): old_meta.unlink()
parent.rmdir() except OSError:
parent = parent.parent pass
def delete_object_tags(self, bucket_name: str, object_key: str) -> None: def delete_object_tags(self, bucket_name: str, object_key: str) -> None:
"""Delete all tags from an object.""" """Delete all tags from an object."""
@@ -758,7 +888,7 @@ class ObjectStorage:
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
bucket_id = bucket_path.name bucket_id = bucket_path.name
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
version_dir = self._version_dir(bucket_id, safe_key) version_dir = self._version_dir(bucket_id, safe_key)
if not version_dir.exists(): if not version_dir.exists():
version_dir = self._legacy_version_dir(bucket_id, safe_key) version_dir = self._legacy_version_dir(bucket_id, safe_key)
@@ -782,7 +912,7 @@ class ObjectStorage:
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
bucket_id = bucket_path.name bucket_id = bucket_path.name
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
version_dir = self._version_dir(bucket_id, safe_key) version_dir = self._version_dir(bucket_id, safe_key)
data_path = version_dir / f"{version_id}.bin" data_path = version_dir / f"{version_id}.bin"
meta_path = version_dir / f"{version_id}.json" meta_path = version_dir / f"{version_id}.json"
@@ -796,7 +926,12 @@ class ObjectStorage:
if not isinstance(metadata, dict): if not isinstance(metadata, dict):
metadata = {} metadata = {}
destination = bucket_path / safe_key destination = bucket_path / safe_key
if self._is_versioning_enabled(bucket_path) and destination.exists(): restored_size = data_path.stat().st_size
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="restore-overwrite") self._archive_current_version(bucket_id, safe_key, reason="restore-overwrite")
destination.parent.mkdir(parents=True, exist_ok=True) destination.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(data_path, destination) shutil.copy2(data_path, destination)
@@ -805,7 +940,13 @@ class ObjectStorage:
else: else:
self._delete_metadata(bucket_id, safe_key) self._delete_metadata(bucket_id, safe_key)
stat = destination.stat() stat = destination.stat()
self._invalidate_bucket_stats_cache(bucket_id) self._update_bucket_stats_cache(
bucket_id,
bytes_delta=restored_size - existing_size,
objects_delta=0 if is_overwrite else 1,
version_bytes_delta=archived_version_size,
version_count_delta=1 if archived_version_size > 0 else 0,
)
return ObjectMeta( return ObjectMeta(
key=safe_key.as_posix(), key=safe_key.as_posix(),
size=stat.st_size, size=stat.st_size,
@@ -819,7 +960,7 @@ class ObjectStorage:
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
bucket_id = bucket_path.name bucket_id = bucket_path.name
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
version_dir = self._version_dir(bucket_id, safe_key) version_dir = self._version_dir(bucket_id, safe_key)
data_path = version_dir / f"{version_id}.bin" data_path = version_dir / f"{version_id}.bin"
meta_path = version_dir / f"{version_id}.json" meta_path = version_dir / f"{version_id}.json"
@@ -829,6 +970,7 @@ class ObjectStorage:
meta_path = legacy_version_dir / f"{version_id}.json" meta_path = legacy_version_dir / f"{version_id}.json"
if not data_path.exists() and not meta_path.exists(): if not data_path.exists() and not meta_path.exists():
raise StorageError(f"Version {version_id} not found") raise StorageError(f"Version {version_id} not found")
deleted_version_size = data_path.stat().st_size if data_path.exists() else 0
if data_path.exists(): if data_path.exists():
data_path.unlink() data_path.unlink()
if meta_path.exists(): if meta_path.exists():
@@ -836,6 +978,12 @@ class ObjectStorage:
parent = data_path.parent parent = data_path.parent
if parent.exists() and not any(parent.iterdir()): if parent.exists() and not any(parent.iterdir()):
parent.rmdir() parent.rmdir()
if deleted_version_size > 0:
self._update_bucket_stats_cache(
bucket_id,
version_bytes_delta=-deleted_version_size,
version_count_delta=-1,
)
def list_orphaned_objects(self, bucket_name: str) -> List[Dict[str, Any]]: def list_orphaned_objects(self, bucket_name: str) -> List[Dict[str, Any]]:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
@@ -910,7 +1058,7 @@ class ObjectStorage:
if not bucket_path.exists(): if not bucket_path.exists():
raise BucketNotFoundError("Bucket does not exist") raise BucketNotFoundError("Bucket does not exist")
bucket_id = bucket_path.name bucket_id = bucket_path.name
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
upload_id = uuid.uuid4().hex upload_id = uuid.uuid4().hex
upload_root = self._multipart_dir(bucket_id, upload_id) upload_root = self._multipart_dir(bucket_id, upload_id)
upload_root.mkdir(parents=True, exist_ok=False) upload_root.mkdir(parents=True, exist_ok=False)
@@ -995,6 +1143,102 @@ class ObjectStorage:
return record["etag"] return record["etag"]
def upload_part_copy(
self,
bucket_name: str,
upload_id: str,
part_number: int,
source_bucket: str,
source_key: str,
start_byte: Optional[int] = None,
end_byte: Optional[int] = None,
) -> Dict[str, Any]:
"""Copy a range from an existing object as a multipart part."""
if part_number < 1 or part_number > 10000:
raise StorageError("part_number must be between 1 and 10000")
source_path = self.get_object_path(source_bucket, source_key)
source_size = source_path.stat().st_size
if start_byte is None:
start_byte = 0
if end_byte is None:
end_byte = source_size - 1
if start_byte < 0 or end_byte >= source_size or start_byte > end_byte:
raise StorageError("Invalid byte range")
bucket_path = self._bucket_path(bucket_name)
upload_root = self._multipart_dir(bucket_path.name, upload_id)
if not upload_root.exists():
upload_root = self._legacy_multipart_dir(bucket_path.name, upload_id)
if not upload_root.exists():
raise StorageError("Multipart upload not found")
checksum = hashlib.md5()
part_filename = f"part-{part_number:05d}.part"
part_path = upload_root / part_filename
temp_path = upload_root / f".{part_filename}.tmp"
try:
with source_path.open("rb") as src:
src.seek(start_byte)
bytes_to_copy = end_byte - start_byte + 1
with temp_path.open("wb") as target:
remaining = bytes_to_copy
while remaining > 0:
chunk_size = min(65536, remaining)
chunk = src.read(chunk_size)
if not chunk:
break
checksum.update(chunk)
target.write(chunk)
remaining -= len(chunk)
temp_path.replace(part_path)
except OSError:
try:
temp_path.unlink(missing_ok=True)
except OSError:
pass
raise
record = {
"etag": checksum.hexdigest(),
"size": part_path.stat().st_size,
"filename": part_filename,
}
manifest_path = upload_root / self.MULTIPART_MANIFEST
lock_path = upload_root / ".manifest.lock"
max_retries = 3
for attempt in range(max_retries):
try:
with lock_path.open("w") as lock_file:
with _file_lock(lock_file):
try:
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError) as exc:
if attempt < max_retries - 1:
time.sleep(0.1 * (attempt + 1))
continue
raise StorageError("Multipart manifest unreadable") from exc
parts = manifest.setdefault("parts", {})
parts[str(part_number)] = record
manifest_path.write_text(json.dumps(manifest), encoding="utf-8")
break
except OSError as exc:
if attempt < max_retries - 1:
time.sleep(0.1 * (attempt + 1))
continue
raise StorageError(f"Failed to update multipart manifest: {exc}") from exc
return {
"etag": record["etag"],
"last_modified": datetime.fromtimestamp(part_path.stat().st_mtime, timezone.utc),
}
def complete_multipart_upload( def complete_multipart_upload(
self, self,
bucket_name: str, bucket_name: str,
@@ -1034,16 +1278,16 @@ class ObjectStorage:
total_size += record.get("size", 0) total_size += record.get("size", 0)
validated.sort(key=lambda entry: entry[0]) validated.sort(key=lambda entry: entry[0])
safe_key = self._sanitize_object_key(manifest["object_key"]) safe_key = self._sanitize_object_key(manifest["object_key"], self._object_key_max_length_bytes)
destination = bucket_path / safe_key destination = bucket_path / safe_key
is_overwrite = destination.exists() is_overwrite = destination.exists()
existing_size = destination.stat().st_size if is_overwrite else 0 existing_size = destination.stat().st_size if is_overwrite else 0
if enforce_quota:
size_delta = total_size - existing_size size_delta = total_size - existing_size
object_delta = 0 if is_overwrite else 1 object_delta = 0 if is_overwrite else 1
versioning_enabled = self._is_versioning_enabled(bucket_path)
if enforce_quota:
quota_check = self.check_quota( quota_check = self.check_quota(
bucket_name, bucket_name,
additional_bytes=max(0, size_delta), additional_bytes=max(0, size_delta),
@@ -1059,12 +1303,12 @@ class ObjectStorage:
destination.parent.mkdir(parents=True, exist_ok=True) destination.parent.mkdir(parents=True, exist_ok=True)
lock_file_path = self._system_bucket_root(bucket_id) / "locks" / f"{safe_key.as_posix().replace('/', '_')}.lock" lock_file_path = self._system_bucket_root(bucket_id) / "locks" / f"{safe_key.as_posix().replace('/', '_')}.lock"
lock_file_path.parent.mkdir(parents=True, exist_ok=True)
archived_version_size = 0
try: try:
with lock_file_path.open("w") as lock_file: with _atomic_lock_file(lock_file_path):
with _file_lock(lock_file): if versioning_enabled and destination.exists():
if self._is_versioning_enabled(bucket_path) and destination.exists(): archived_version_size = destination.stat().st_size
self._archive_current_version(bucket_id, safe_key, reason="overwrite") self._archive_current_version(bucket_id, safe_key, reason="overwrite")
checksum = hashlib.md5() checksum = hashlib.md5()
with destination.open("wb") as target: with destination.open("wb") as target:
@@ -1079,18 +1323,18 @@ class ObjectStorage:
break break
checksum.update(data) checksum.update(data)
target.write(data) target.write(data)
except BlockingIOError: except BlockingIOError:
raise StorageError("Another upload to this key is in progress") raise StorageError("Another upload to this key is in progress")
finally:
try:
lock_file_path.unlink(missing_ok=True)
except OSError:
pass
shutil.rmtree(upload_root, ignore_errors=True) shutil.rmtree(upload_root, ignore_errors=True)
self._invalidate_bucket_stats_cache(bucket_id) self._update_bucket_stats_cache(
bucket_id,
bytes_delta=size_delta,
objects_delta=object_delta,
version_bytes_delta=archived_version_size,
version_count_delta=1 if archived_version_size > 0 else 0,
)
stat = destination.stat() stat = destination.stat()
etag = checksum.hexdigest() etag = checksum.hexdigest()
@@ -1213,7 +1457,7 @@ class ObjectStorage:
def _object_path(self, bucket_name: str, object_key: str) -> Path: def _object_path(self, bucket_name: str, object_key: str) -> Path:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
safe_key = self._sanitize_object_key(object_key) safe_key = self._sanitize_object_key(object_key, self._object_key_max_length_bytes)
return bucket_path / safe_key return bucket_path / safe_key
def _system_root_path(self) -> Path: def _system_root_path(self) -> Path:
@@ -1300,7 +1544,7 @@ class ObjectStorage:
if entry.is_dir(follow_symlinks=False): if entry.is_dir(follow_symlinks=False):
if check_newer(entry.path): if check_newer(entry.path):
return True return True
elif entry.is_file(follow_symlinks=False) and entry.name.endswith('.meta.json'): elif entry.is_file(follow_symlinks=False) and (entry.name.endswith('.meta.json') or entry.name == '_index.json'):
if entry.stat().st_mtime > index_mtime: if entry.stat().st_mtime > index_mtime:
return True return True
except OSError: except OSError:
@@ -1314,6 +1558,7 @@ class ObjectStorage:
meta_str = str(meta_root) meta_str = str(meta_root)
meta_len = len(meta_str) + 1 meta_len = len(meta_str) + 1
meta_files: list[tuple[str, str]] = [] meta_files: list[tuple[str, str]] = []
index_files: list[str] = []
def collect_meta_files(dir_path: str) -> None: def collect_meta_files(dir_path: str) -> None:
try: try:
@@ -1321,7 +1566,10 @@ class ObjectStorage:
for entry in it: for entry in it:
if entry.is_dir(follow_symlinks=False): if entry.is_dir(follow_symlinks=False):
collect_meta_files(entry.path) collect_meta_files(entry.path)
elif entry.is_file(follow_symlinks=False) and entry.name.endswith('.meta.json'): elif entry.is_file(follow_symlinks=False):
if entry.name == '_index.json':
index_files.append(entry.path)
elif entry.name.endswith('.meta.json'):
rel = entry.path[meta_len:] rel = entry.path[meta_len:]
key = rel[:-10].replace(os.sep, '/') key = rel[:-10].replace(os.sep, '/')
meta_files.append((key, entry.path)) meta_files.append((key, entry.path))
@@ -1330,6 +1578,30 @@ class ObjectStorage:
collect_meta_files(meta_str) collect_meta_files(meta_str)
meta_cache = {}
for idx_path in index_files:
try:
with open(idx_path, 'r', encoding='utf-8') as f:
idx_data = json.load(f)
rel_dir = idx_path[meta_len:]
rel_dir = rel_dir.replace(os.sep, '/')
if rel_dir.endswith('/_index.json'):
dir_prefix = rel_dir[:-len('/_index.json')]
else:
dir_prefix = ''
for entry_name, entry_data in idx_data.items():
if dir_prefix:
key = f"{dir_prefix}/{entry_name}"
else:
key = entry_name
meta = entry_data.get("metadata", {})
etag = meta.get("__etag__")
if etag:
meta_cache[key] = etag
except (OSError, json.JSONDecodeError):
pass
def read_meta_file(item: tuple[str, str]) -> tuple[str, str | None]: def read_meta_file(item: tuple[str, str]) -> tuple[str, str | None]:
key, path = item key, path = item
try: try:
@@ -1347,13 +1619,15 @@ class ObjectStorage:
except (OSError, UnicodeDecodeError): except (OSError, UnicodeDecodeError):
return key, None return key, None
if meta_files: legacy_meta_files = [(k, p) for k, p in meta_files if k not in meta_cache]
meta_cache = {} if legacy_meta_files:
with ThreadPoolExecutor(max_workers=min(64, len(meta_files))) as executor: max_workers = min((os.cpu_count() or 4) * 2, len(legacy_meta_files), 16)
for key, etag in executor.map(read_meta_file, meta_files): with ThreadPoolExecutor(max_workers=max_workers) as executor:
for key, etag in executor.map(read_meta_file, legacy_meta_files):
if etag: if etag:
meta_cache[key] = etag meta_cache[key] = etag
if meta_cache:
try: try:
etag_index_path.parent.mkdir(parents=True, exist_ok=True) etag_index_path.parent.mkdir(parents=True, exist_ok=True)
with open(etag_index_path, 'w', encoding='utf-8') as f: with open(etag_index_path, 'w', encoding='utf-8') as f:
@@ -1402,38 +1676,46 @@ class ObjectStorage:
Uses LRU eviction to prevent unbounded cache growth. Uses LRU eviction to prevent unbounded cache growth.
Thread-safe with per-bucket locks to reduce contention. Thread-safe with per-bucket locks to reduce contention.
Checks stats.json for cross-process cache invalidation.
""" """
now = time.time() now = time.time()
current_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock: with self._cache_lock:
cached = self._object_cache.get(bucket_id) cached = self._object_cache.get(bucket_id)
if cached: if cached:
objects, timestamp = cached objects, timestamp, cached_stats_mtime = cached
if now - timestamp < self._cache_ttl: if now - timestamp < self._cache_ttl and current_stats_mtime == cached_stats_mtime:
self._object_cache.move_to_end(bucket_id) self._object_cache.move_to_end(bucket_id)
return objects return objects
cache_version = self._cache_version.get(bucket_id, 0) cache_version = self._cache_version.get(bucket_id, 0)
bucket_lock = self._get_bucket_lock(bucket_id) bucket_lock = self._get_bucket_lock(bucket_id)
with bucket_lock: with bucket_lock:
current_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock: with self._cache_lock:
cached = self._object_cache.get(bucket_id) cached = self._object_cache.get(bucket_id)
if cached: if cached:
objects, timestamp = cached objects, timestamp, cached_stats_mtime = cached
if now - timestamp < self._cache_ttl: if now - timestamp < self._cache_ttl and current_stats_mtime == cached_stats_mtime:
self._object_cache.move_to_end(bucket_id) self._object_cache.move_to_end(bucket_id)
return objects return objects
objects = self._build_object_cache(bucket_path) objects = self._build_object_cache(bucket_path)
new_stats_mtime = self._get_cache_marker_mtime(bucket_id)
with self._cache_lock: with self._cache_lock:
current_version = self._cache_version.get(bucket_id, 0) current_version = self._cache_version.get(bucket_id, 0)
if current_version != cache_version: if current_version != cache_version:
objects = self._build_object_cache(bucket_path) objects = self._build_object_cache(bucket_path)
while len(self._object_cache) >= self.OBJECT_CACHE_MAX_SIZE: new_stats_mtime = self._get_cache_marker_mtime(bucket_id)
while len(self._object_cache) >= self._object_cache_max_size:
self._object_cache.popitem(last=False) self._object_cache.popitem(last=False)
self._object_cache[bucket_id] = (objects, time.time()) self._object_cache[bucket_id] = (objects, time.time(), new_stats_mtime)
self._object_cache.move_to_end(bucket_id) self._object_cache.move_to_end(bucket_id)
self._cache_version[bucket_id] = current_version + 1
self._sorted_key_cache.pop(bucket_id, None)
return objects return objects
@@ -1441,6 +1723,7 @@ class ObjectStorage:
"""Invalidate the object cache and etag index for a bucket. """Invalidate the object cache and etag index for a bucket.
Increments version counter to signal stale reads. Increments version counter to signal stale reads.
Cross-process invalidation is handled by checking stats.json mtime.
""" """
with self._cache_lock: with self._cache_lock:
self._object_cache.pop(bucket_id, None) self._object_cache.pop(bucket_id, None)
@@ -1452,19 +1735,37 @@ class ObjectStorage:
except OSError: except OSError:
pass 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
def _update_object_cache_entry(self, bucket_id: str, key: str, meta: Optional[ObjectMeta]) -> None: def _update_object_cache_entry(self, bucket_id: str, key: str, meta: Optional[ObjectMeta]) -> None:
"""Update a single entry in the object cache instead of invalidating the whole cache. """Update a single entry in the object cache instead of invalidating the whole cache.
This is a performance optimization - lazy update instead of full invalidation. This is a performance optimization - lazy update instead of full invalidation.
Cross-process invalidation is handled by checking stats.json mtime.
""" """
with self._cache_lock: with self._cache_lock:
cached = self._object_cache.get(bucket_id) cached = self._object_cache.get(bucket_id)
if cached: if cached:
objects, timestamp = cached objects, timestamp, stats_mtime = cached
if meta is None: if meta is None:
objects.pop(key, None) objects.pop(key, None)
else: else:
objects[key] = meta objects[key] = meta
self._cache_version[bucket_id] = self._cache_version.get(bucket_id, 0) + 1
self._sorted_key_cache.pop(bucket_id, None)
def warm_cache(self, bucket_names: Optional[List[str]] = None) -> None: def warm_cache(self, bucket_names: Optional[List[str]] = None) -> None:
"""Pre-warm the object cache for specified buckets or all buckets. """Pre-warm the object cache for specified buckets or all buckets.
@@ -1576,6 +1877,64 @@ class ObjectStorage:
meta_rel = Path(key.as_posix() + ".meta.json") meta_rel = Path(key.as_posix() + ".meta.json")
return meta_root / meta_rel return meta_root / meta_rel
def _index_file_for_key(self, bucket_name: str, key: Path) -> tuple[Path, str]:
meta_root = self._bucket_meta_root(bucket_name)
parent = key.parent
entry_name = key.name
if parent == Path("."):
return meta_root / "_index.json", entry_name
return meta_root / parent / "_index.json", entry_name
def _get_meta_index_lock(self, index_path: str) -> threading.Lock:
with self._cache_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]]:
index_path, entry_name = self._index_file_for_key(bucket_name, key)
if not index_path.exists():
return None
try:
index_data = json.loads(index_path.read_text(encoding="utf-8"))
return index_data.get(entry_name)
except (OSError, json.JSONDecodeError):
return None
def _write_index_entry(self, bucket_name: str, key: Path, entry: Dict[str, Any]) -> None:
index_path, entry_name = self._index_file_for_key(bucket_name, key)
lock = self._get_meta_index_lock(str(index_path))
with lock:
index_path.parent.mkdir(parents=True, exist_ok=True)
index_data: Dict[str, Any] = {}
if index_path.exists():
try:
index_data = json.loads(index_path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError):
pass
index_data[entry_name] = entry
index_path.write_text(json.dumps(index_data), encoding="utf-8")
def _delete_index_entry(self, bucket_name: str, key: Path) -> None:
index_path, entry_name = self._index_file_for_key(bucket_name, key)
if not index_path.exists():
return
lock = self._get_meta_index_lock(str(index_path))
with lock:
try:
index_data = json.loads(index_path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError):
return
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")
else:
try:
index_path.unlink()
except OSError:
pass
def _normalize_metadata(self, metadata: Optional[Dict[str, str]]) -> Optional[Dict[str, str]]: def _normalize_metadata(self, metadata: Optional[Dict[str, str]]) -> Optional[Dict[str, str]]:
if not metadata: if not metadata:
return None return None
@@ -1587,9 +1946,13 @@ class ObjectStorage:
if not clean: if not clean:
self._delete_metadata(bucket_name, key) self._delete_metadata(bucket_name, key)
return return
meta_file = self._metadata_file(bucket_name, key) self._write_index_entry(bucket_name, key, {"metadata": clean})
meta_file.parent.mkdir(parents=True, exist_ok=True) old_meta = self._metadata_file(bucket_name, key)
meta_file.write_text(json.dumps({"metadata": clean}), encoding="utf-8") try:
if old_meta.exists():
old_meta.unlink()
except OSError:
pass
def _archive_current_version(self, bucket_name: str, key: Path, *, reason: str) -> None: def _archive_current_version(self, bucket_name: str, key: Path, *, reason: str) -> None:
bucket_path = self._bucket_path(bucket_name) bucket_path = self._bucket_path(bucket_name)
@@ -1616,6 +1979,10 @@ class ObjectStorage:
manifest_path.write_text(json.dumps(record), encoding="utf-8") manifest_path.write_text(json.dumps(record), encoding="utf-8")
def _read_metadata(self, bucket_name: str, key: Path) -> Dict[str, str]: def _read_metadata(self, bucket_name: str, key: Path) -> Dict[str, str]:
entry = self._read_index_entry(bucket_name, key)
if entry is not None:
data = entry.get("metadata")
return data if isinstance(data, dict) else {}
for meta_file in (self._metadata_file(bucket_name, key), self._legacy_metadata_file(bucket_name, key)): for meta_file in (self._metadata_file(bucket_name, key), self._legacy_metadata_file(bucket_name, key)):
if not meta_file.exists(): if not meta_file.exists():
continue continue
@@ -1646,6 +2013,7 @@ class ObjectStorage:
raise StorageError(message) from last_error raise StorageError(message) from last_error
def _delete_metadata(self, bucket_name: str, key: Path) -> None: def _delete_metadata(self, bucket_name: str, key: Path) -> None:
self._delete_index_entry(bucket_name, key)
locations = ( locations = (
(self._metadata_file(bucket_name, key), self._bucket_meta_root(bucket_name)), (self._metadata_file(bucket_name, key), self._bucket_meta_root(bucket_name)),
(self._legacy_metadata_file(bucket_name, key), self._legacy_meta_root(bucket_name)), (self._legacy_metadata_file(bucket_name, key), self._legacy_meta_root(bucket_name)),
@@ -1764,16 +2132,16 @@ class ObjectStorage:
return name return name
@staticmethod @staticmethod
def _sanitize_object_key(object_key: str) -> Path: def _sanitize_object_key(object_key: str, max_length_bytes: int = 1024) -> Path:
if not object_key: if not object_key:
raise StorageError("Object key required") raise StorageError("Object key required")
if len(object_key.encode("utf-8")) > 1024:
raise StorageError("Object key exceeds maximum length of 1024 bytes")
if "\x00" in object_key: if "\x00" in object_key:
raise StorageError("Object key contains null bytes") raise StorageError("Object key contains null bytes")
object_key = unicodedata.normalize("NFC", object_key)
if len(object_key.encode("utf-8")) > max_length_bytes:
raise StorageError(f"Object key exceeds maximum length of {max_length_bytes} bytes")
if object_key.startswith(("/", "\\")): if object_key.startswith(("/", "\\")):
raise StorageError("Object key cannot start with a slash") raise StorageError("Object key cannot start with a slash")
object_key = unicodedata.normalize("NFC", object_key)
candidate = Path(object_key) candidate = Path(object_key)
if ".." in candidate.parts: if ".." in candidate.parts:

1981
app/ui.py

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
from __future__ import annotations from __future__ import annotations
APP_VERSION = "0.2.3" APP_VERSION = "0.2.9"
def get_version() -> str: def get_version() -> str:

55
app/website_domains.py Normal file
View File

@@ -0,0 +1,55 @@
from __future__ import annotations
import json
import threading
from pathlib import Path
from typing import Dict, List, Optional
class WebsiteDomainStore:
def __init__(self, config_path: Path) -> None:
self.config_path = config_path
self._lock = threading.Lock()
self._domains: Dict[str, str] = {}
self.reload()
def reload(self) -> None:
if not self.config_path.exists():
self._domains = {}
return
try:
with open(self.config_path, "r", encoding="utf-8") as f:
data = json.load(f)
if isinstance(data, dict):
self._domains = {k.lower(): v for k, v in data.items()}
else:
self._domains = {}
except (OSError, json.JSONDecodeError):
self._domains = {}
def _save(self) -> None:
self.config_path.parent.mkdir(parents=True, exist_ok=True)
with open(self.config_path, "w", encoding="utf-8") as f:
json.dump(self._domains, f, indent=2)
def list_all(self) -> List[Dict[str, str]]:
with self._lock:
return [{"domain": d, "bucket": b} for d, b in self._domains.items()]
def get_bucket(self, domain: str) -> Optional[str]:
with self._lock:
return self._domains.get(domain.lower())
def set_mapping(self, domain: str, bucket: str) -> None:
with self._lock:
self._domains[domain.lower()] = bucket
self._save()
def delete_mapping(self, domain: str) -> bool:
with self._lock:
key = domain.lower()
if key not in self._domains:
return False
del self._domains[key]
self._save()
return True

859
docs.md
View File

@@ -7,7 +7,7 @@ This document expands on the README to describe the full workflow for running, c
MyFSIO ships two Flask entrypoints that share the same storage, IAM, and bucket-policy state: MyFSIO ships two Flask entrypoints that share the same storage, IAM, and bucket-policy state:
- **API server** Implements the S3-compatible REST API, policy evaluation, and Signature Version 4 presign service. - **API server** Implements the S3-compatible REST API, policy evaluation, and Signature Version 4 presign service.
- **UI server** Provides the browser console for buckets, IAM, and policies. It proxies to the API for presign operations. - **UI server** Provides the browser console for buckets, IAM, and policies. It proxies all storage operations through the S3 API via boto3 (SigV4-signed), mirroring the architecture used by MinIO and Garage.
Both servers read `AppConfig`, so editing JSON stores on disk instantly affects both surfaces. Both servers read `AppConfig`, so editing JSON stores on disk instantly affects both surfaces.
@@ -136,7 +136,7 @@ All configuration is done via environment variables. The table below lists every
| `MAX_UPLOAD_SIZE` | `1073741824` (1 GiB) | Bytes. Caps incoming uploads in both API + UI. | | `MAX_UPLOAD_SIZE` | `1073741824` (1 GiB) | Bytes. Caps incoming uploads in both API + UI. |
| `UI_PAGE_SIZE` | `100` | `MaxKeys` hint shown in listings. | | `UI_PAGE_SIZE` | `100` | `MaxKeys` hint shown in listings. |
| `SECRET_KEY` | Auto-generated | Flask session key. Auto-generates and persists if not set. **Set explicitly in production.** | | `SECRET_KEY` | Auto-generated | Flask session key. Auto-generates and persists if not set. **Set explicitly in production.** |
| `API_BASE_URL` | `None` | Public URL for presigned URLs. Required behind proxies. | | `API_BASE_URL` | `http://127.0.0.1:5000` | Internal S3 API URL used by the web UI proxy. Also used for presigned URL generation. Set to your public URL if running behind a reverse proxy. |
| `AWS_REGION` | `us-east-1` | Region embedded in SigV4 credential scope. | | `AWS_REGION` | `us-east-1` | Region embedded in SigV4 credential scope. |
| `AWS_SERVICE` | `s3` | Service string for SigV4. | | `AWS_SERVICE` | `s3` | Service string for SigV4. |
@@ -166,15 +166,19 @@ All configuration is done via environment variables. The table below lists every
| Variable | Default | Notes | | Variable | Default | Notes |
| --- | --- | --- | | --- | --- | --- |
| `RATE_LIMIT_DEFAULT` | `200 per minute` | Default rate limit for API endpoints. | | `RATE_LIMIT_DEFAULT` | `200 per minute` | Default rate limit for API endpoints. |
| `RATE_LIMIT_LIST_BUCKETS` | `60 per minute` | Rate limit for listing buckets (`GET /`). |
| `RATE_LIMIT_BUCKET_OPS` | `120 per minute` | Rate limit for bucket operations (PUT/DELETE/GET/POST on `/<bucket>`). |
| `RATE_LIMIT_OBJECT_OPS` | `240 per minute` | Rate limit for object operations (PUT/GET/DELETE/POST on `/<bucket>/<key>`). |
| `RATE_LIMIT_HEAD_OPS` | `100 per minute` | Rate limit for HEAD requests (bucket and object). |
| `RATE_LIMIT_STORAGE_URI` | `memory://` | Storage backend for rate limits. Use `redis://host:port` for distributed setups. | | `RATE_LIMIT_STORAGE_URI` | `memory://` | Storage backend for rate limits. Use `redis://host:port` for distributed setups. |
### Server Configuration ### Server Configuration
| Variable | Default | Notes | | Variable | Default | Notes |
| --- | --- | --- | | --- | --- | --- |
| `SERVER_THREADS` | `4` | Waitress worker threads (1-64). More threads handle more concurrent requests but use more memory. | | `SERVER_THREADS` | `0` (auto) | Waitress worker threads (1-64). Set to `0` for auto-calculation based on CPU cores (×2). |
| `SERVER_CONNECTION_LIMIT` | `100` | Maximum concurrent connections (10-1000). Ensure OS file descriptor limits support this value. | | `SERVER_CONNECTION_LIMIT` | `0` (auto) | Maximum concurrent connections (10-1000). Set to `0` for auto-calculation based on available RAM. |
| `SERVER_BACKLOG` | `1024` | TCP listen backlog (64-4096). Connections queue here when all threads are busy. | | `SERVER_BACKLOG` | `0` (auto) | TCP listen backlog (64-4096). Set to `0` for auto-calculation (connection_limit × 2). |
| `SERVER_CHANNEL_TIMEOUT` | `120` | Seconds before idle connections are closed (10-300). | | `SERVER_CHANNEL_TIMEOUT` | `120` | Seconds before idle connections are closed (10-300). |
### Logging ### Logging
@@ -615,13 +619,15 @@ MyFSIO implements a comprehensive Identity and Access Management (IAM) system th
### Getting Started ### Getting Started
1. On first boot, `data/.myfsio.sys/config/iam.json` is seeded with `localadmin / localadmin` that has wildcard access. 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.
2. Sign into the UI using those credentials, then open **IAM**: 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 and optional JSON inline policy array.
- **Rotate secret**: generates a new secret key; the UI surfaces it once. - **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`). - **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. 3. Wildcard action `iam:*` is supported for admin user definitions.
> **Breaking Change (v0.2.0+):** Previous versions used fixed default credentials (`localadmin/localadmin`). If upgrading from an older version, your existing credentials remain unchanged, but new installations will generate random credentials.
### Authentication ### Authentication
The API expects every request to include authentication headers. The UI persists them in the Flask session after login. The API expects every request to include authentication headers. The UI persists them in the Flask session after login.
@@ -1503,16 +1509,841 @@ The suite covers bucket CRUD, presigned downloads, bucket policy enforcement, an
## 14. API Matrix ## 14. API Matrix
``` ```
# Service Endpoints
GET /myfsio/health # Health check
# Bucket Operations
GET / # List buckets GET / # List buckets
PUT /<bucket> # Create bucket PUT /<bucket> # Create bucket
DELETE /<bucket> # Remove bucket DELETE /<bucket> # Remove bucket
GET /<bucket> # List objects GET /<bucket> # List objects (supports ?list-type=2)
PUT /<bucket>/<key> # Upload object HEAD /<bucket> # Check bucket exists
GET /<bucket>/<key> # Download object POST /<bucket> # POST object upload (HTML form)
DELETE /<bucket>/<key> # Delete object POST /<bucket>?delete # Bulk delete objects
GET /<bucket>?policy # Fetch policy
PUT /<bucket>?policy # Upsert policy # Bucket Configuration
DELETE /<bucket>?policy # Delete policy GET /<bucket>?policy # Fetch bucket policy
PUT /<bucket>?policy # Upsert bucket policy
DELETE /<bucket>?policy # Delete bucket policy
GET /<bucket>?quota # Get bucket quota GET /<bucket>?quota # Get bucket quota
PUT /<bucket>?quota # Set bucket quota (admin only) PUT /<bucket>?quota # Set bucket quota (admin only)
GET /<bucket>?versioning # Get versioning status
PUT /<bucket>?versioning # Enable/disable versioning
GET /<bucket>?lifecycle # Get lifecycle rules
PUT /<bucket>?lifecycle # Set lifecycle rules
DELETE /<bucket>?lifecycle # Delete lifecycle rules
GET /<bucket>?cors # Get CORS configuration
PUT /<bucket>?cors # Set CORS configuration
DELETE /<bucket>?cors # Delete CORS configuration
GET /<bucket>?encryption # Get encryption configuration
PUT /<bucket>?encryption # Set default encryption
DELETE /<bucket>?encryption # Delete encryption configuration
GET /<bucket>?acl # Get bucket ACL
PUT /<bucket>?acl # Set bucket ACL
GET /<bucket>?tagging # Get bucket tags
PUT /<bucket>?tagging # Set bucket tags
DELETE /<bucket>?tagging # Delete bucket tags
GET /<bucket>?replication # Get replication configuration
PUT /<bucket>?replication # Set replication rules
DELETE /<bucket>?replication # Delete replication configuration
GET /<bucket>?logging # Get access logging configuration
PUT /<bucket>?logging # Set access logging
GET /<bucket>?notification # Get event notifications
PUT /<bucket>?notification # Set event notifications (webhooks)
GET /<bucket>?object-lock # Get object lock configuration
PUT /<bucket>?object-lock # Set object lock configuration
GET /<bucket>?website # Get website configuration
PUT /<bucket>?website # Set website configuration
DELETE /<bucket>?website # Delete website configuration
GET /<bucket>?uploads # List active multipart uploads
GET /<bucket>?versions # List object versions
GET /<bucket>?location # Get bucket location/region
# Object Operations
PUT /<bucket>/<key> # Upload object
GET /<bucket>/<key> # Download object (supports Range header)
DELETE /<bucket>/<key> # Delete object
HEAD /<bucket>/<key> # Get object metadata
POST /<bucket>/<key> # POST upload with policy
POST /<bucket>/<key>?select # SelectObjectContent (SQL query)
# Object Configuration
GET /<bucket>/<key>?tagging # Get object tags
PUT /<bucket>/<key>?tagging # Set object tags
DELETE /<bucket>/<key>?tagging # Delete object tags
GET /<bucket>/<key>?acl # Get object ACL
PUT /<bucket>/<key>?acl # Set object ACL
PUT /<bucket>/<key>?retention # Set object retention
GET /<bucket>/<key>?retention # Get object retention
PUT /<bucket>/<key>?legal-hold # Set legal hold
GET /<bucket>/<key>?legal-hold # Get legal hold status
# Multipart Upload
POST /<bucket>/<key>?uploads # Initiate multipart upload
PUT /<bucket>/<key>?uploadId=X&partNumber=N # Upload part
PUT /<bucket>/<key>?uploadId=X&partNumber=N (with x-amz-copy-source) # UploadPartCopy
POST /<bucket>/<key>?uploadId=X # Complete multipart upload
DELETE /<bucket>/<key>?uploadId=X # Abort multipart upload
GET /<bucket>/<key>?uploadId=X # List parts
# Copy Operations
PUT /<bucket>/<key> (with x-amz-copy-source header) # CopyObject
# Admin API
GET /admin/site # Get local site info
PUT /admin/site # Update local site
GET /admin/sites # List peer sites
POST /admin/sites # Register peer site
GET /admin/sites/<site_id> # Get peer site
PUT /admin/sites/<site_id> # Update peer site
DELETE /admin/sites/<site_id> # Unregister peer site
GET /admin/sites/<site_id>/health # Check peer health
GET /admin/topology # Get cluster topology
GET /admin/website-domains # List domain mappings
POST /admin/website-domains # Create domain mapping
GET /admin/website-domains/<domain> # Get domain mapping
PUT /admin/website-domains/<domain> # Update domain mapping
DELETE /admin/website-domains/<domain> # Delete domain mapping
# KMS API
GET /kms/keys # List KMS keys
POST /kms/keys # Create KMS key
GET /kms/keys/<key_id> # Get key details
DELETE /kms/keys/<key_id> # Schedule key deletion
POST /kms/keys/<key_id>/enable # Enable key
POST /kms/keys/<key_id>/disable # Disable key
POST /kms/keys/<key_id>/rotate # Rotate key material
POST /kms/encrypt # Encrypt data
POST /kms/decrypt # Decrypt data
POST /kms/generate-data-key # Generate data key
POST /kms/generate-random # Generate random bytes
``` ```
## 15. Health Check Endpoint
The API exposes a simple health check endpoint for monitoring and load balancer integration:
```bash
# Check API health
curl http://localhost:5000/myfsio/health
# Response
{"status": "ok", "version": "0.1.7"}
```
The response includes:
- `status`: Always `"ok"` when the server is running
- `version`: Current application version from `app/version.py`
Use this endpoint for:
- Load balancer health checks
- Kubernetes liveness/readiness probes
- Monitoring system integration (Prometheus, Datadog, etc.)
## 16. Object Lock & Retention
Object Lock prevents objects from being deleted or overwritten for a specified retention period. MyFSIO supports both GOVERNANCE and COMPLIANCE modes.
### Retention Modes
| Mode | Description |
|------|-------------|
| **GOVERNANCE** | Objects can't be deleted by normal users, but users with `s3:BypassGovernanceRetention` permission can override |
| **COMPLIANCE** | Objects can't be deleted or overwritten by anyone, including root, until the retention period expires |
### Enabling Object Lock
Object Lock must be enabled when creating a bucket:
```bash
# Create bucket with Object Lock enabled
curl -X PUT "http://localhost:5000/my-bucket" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-bucket-object-lock-enabled: true"
# Set default retention configuration
curl -X PUT "http://localhost:5000/my-bucket?object-lock" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"ObjectLockEnabled": "Enabled",
"Rule": {
"DefaultRetention": {
"Mode": "GOVERNANCE",
"Days": 30
}
}
}'
```
### Per-Object Retention
Set retention on individual objects:
```bash
# Set object retention
curl -X PUT "http://localhost:5000/my-bucket/important.pdf?retention" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"Mode": "COMPLIANCE",
"RetainUntilDate": "2025-12-31T23:59:59Z"
}'
# Get object retention
curl "http://localhost:5000/my-bucket/important.pdf?retention" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### Legal Hold
Legal hold provides indefinite protection independent of retention settings:
```bash
# Enable legal hold
curl -X PUT "http://localhost:5000/my-bucket/document.pdf?legal-hold" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{"Status": "ON"}'
# Disable legal hold
curl -X PUT "http://localhost:5000/my-bucket/document.pdf?legal-hold" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{"Status": "OFF"}'
# Check legal hold status
curl "http://localhost:5000/my-bucket/document.pdf?legal-hold" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
## 17. Access Logging
Enable S3-style access logging to track all requests to your buckets.
### Configuration
```bash
# Enable access logging
curl -X PUT "http://localhost:5000/my-bucket?logging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"LoggingEnabled": {
"TargetBucket": "log-bucket",
"TargetPrefix": "logs/my-bucket/"
}
}'
# Get logging configuration
curl "http://localhost:5000/my-bucket?logging" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Disable logging (empty configuration)
curl -X PUT "http://localhost:5000/my-bucket?logging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{}'
```
### Log Format
Access logs are written in S3-compatible format with fields including:
- Timestamp, bucket, key
- Operation (REST.GET.OBJECT, REST.PUT.OBJECT, etc.)
- Request ID, requester, source IP
- HTTP status, error code, bytes sent
- Total time, turn-around time
- Referrer, User-Agent
## 18. Bucket Notifications & Webhooks
Configure event notifications to trigger webhooks when objects are created or deleted.
### Supported Events
| Event Type | Description |
|-----------|-------------|
| `s3:ObjectCreated:*` | Any object creation (PUT, POST, COPY, multipart) |
| `s3:ObjectCreated:Put` | Object created via PUT |
| `s3:ObjectCreated:Post` | Object created via POST |
| `s3:ObjectCreated:Copy` | Object created via COPY |
| `s3:ObjectCreated:CompleteMultipartUpload` | Multipart upload completed |
| `s3:ObjectRemoved:*` | Any object deletion |
| `s3:ObjectRemoved:Delete` | Object deleted |
| `s3:ObjectRemoved:DeleteMarkerCreated` | Delete marker created (versioned bucket) |
### Configuration
```bash
# Set notification configuration
curl -X PUT "http://localhost:5000/my-bucket?notification" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"TopicConfigurations": [
{
"Id": "upload-notify",
"TopicArn": "https://webhook.example.com/s3-events",
"Events": ["s3:ObjectCreated:*"],
"Filter": {
"Key": {
"FilterRules": [
{"Name": "prefix", "Value": "uploads/"},
{"Name": "suffix", "Value": ".jpg"}
]
}
}
}
]
}'
# Get notification configuration
curl "http://localhost:5000/my-bucket?notification" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### Webhook Payload
The webhook receives a JSON payload similar to AWS S3 event notifications:
```json
{
"Records": [
{
"eventVersion": "2.1",
"eventSource": "myfsio:s3",
"eventTime": "2024-01-15T10:30:00.000Z",
"eventName": "ObjectCreated:Put",
"s3": {
"bucket": {"name": "my-bucket"},
"object": {
"key": "uploads/photo.jpg",
"size": 102400,
"eTag": "abc123..."
}
}
}
]
}
```
### Security Notes
- Webhook URLs are validated to prevent SSRF attacks
- Internal/private IP ranges are blocked by default
- Use HTTPS endpoints in production
## 19. SelectObjectContent (SQL Queries)
Query CSV, JSON, or Parquet files directly using SQL without downloading the entire object. Requires DuckDB to be installed.
### Prerequisites
```bash
pip install duckdb
```
### Usage
```bash
# Query a CSV file
curl -X POST "http://localhost:5000/my-bucket/data.csv?select" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"Expression": "SELECT name, age FROM s3object WHERE age > 25",
"ExpressionType": "SQL",
"InputSerialization": {
"CSV": {
"FileHeaderInfo": "USE",
"FieldDelimiter": ","
}
},
"OutputSerialization": {
"JSON": {}
}
}'
# Query a JSON file
curl -X POST "http://localhost:5000/my-bucket/data.json?select" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"Expression": "SELECT * FROM s3object s WHERE s.status = '\"active'\"",
"ExpressionType": "SQL",
"InputSerialization": {"JSON": {"Type": "LINES"}},
"OutputSerialization": {"JSON": {}}
}'
```
### Supported Input Formats
| Format | Options |
|--------|---------|
| **CSV** | `FileHeaderInfo` (USE, IGNORE, NONE), `FieldDelimiter`, `QuoteCharacter`, `RecordDelimiter` |
| **JSON** | `Type` (DOCUMENT, LINES) |
| **Parquet** | Automatic schema detection |
### Output Formats
- **JSON**: Returns results as JSON records
- **CSV**: Returns results as CSV
## 20. PostObject (HTML Form Upload)
Upload objects using HTML forms with policy-based authorization. Useful for browser-based direct uploads.
### Form Fields
| Field | Required | Description |
|-------|----------|-------------|
| `key` | Yes | Object key (can include `${filename}` placeholder) |
| `file` | Yes | The file to upload |
| `policy` | No | Base64-encoded policy document |
| `x-amz-signature` | No | Policy signature |
| `x-amz-credential` | No | Credential scope |
| `x-amz-algorithm` | No | Signing algorithm (AWS4-HMAC-SHA256) |
| `x-amz-date` | No | Request timestamp |
| `Content-Type` | No | MIME type of the file |
| `x-amz-meta-*` | No | Custom metadata |
### Example HTML Form
```html
<form action="http://localhost:5000/my-bucket" method="post" enctype="multipart/form-data">
<input type="hidden" name="key" value="uploads/${filename}">
<input type="hidden" name="Content-Type" value="image/jpeg">
<input type="hidden" name="x-amz-meta-user" value="john">
<input type="file" name="file">
<button type="submit">Upload</button>
</form>
```
### With Policy (Signed Upload)
For authenticated uploads, include a policy document:
```bash
# Generate policy and signature using boto3 or similar
# Then include in form:
# - policy: base64(policy_document)
# - x-amz-signature: HMAC-SHA256(policy, signing_key)
# - x-amz-credential: access_key/date/region/s3/aws4_request
# - x-amz-algorithm: AWS4-HMAC-SHA256
# - x-amz-date: YYYYMMDDTHHMMSSZ
```
## 21. Advanced S3 Operations
### CopyObject
Copy objects within or between buckets:
```bash
# Copy within same bucket
curl -X PUT "http://localhost:5000/my-bucket/copy-of-file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-copy-source: /my-bucket/original-file.txt"
# Copy to different bucket
curl -X PUT "http://localhost:5000/other-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-copy-source: /my-bucket/original-file.txt"
# Copy with metadata replacement
curl -X PUT "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-copy-source: /my-bucket/file.txt" \
-H "x-amz-metadata-directive: REPLACE" \
-H "x-amz-meta-newkey: newvalue"
```
### UploadPartCopy
Copy data from an existing object into a multipart upload part:
```bash
# Initiate multipart upload
UPLOAD_ID=$(curl -X POST "http://localhost:5000/my-bucket/large-file.bin?uploads" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." | jq -r '.UploadId')
# Copy bytes 0-10485759 from source as part 1
curl -X PUT "http://localhost:5000/my-bucket/large-file.bin?uploadId=$UPLOAD_ID&partNumber=1" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-copy-source: /source-bucket/source-file.bin" \
-H "x-amz-copy-source-range: bytes=0-10485759"
# Copy bytes 10485760-20971519 as part 2
curl -X PUT "http://localhost:5000/my-bucket/large-file.bin?uploadId=$UPLOAD_ID&partNumber=2" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-copy-source: /source-bucket/source-file.bin" \
-H "x-amz-copy-source-range: bytes=10485760-20971519"
```
### Range Requests
Download partial content using the Range header:
```bash
# Get first 1000 bytes
curl "http://localhost:5000/my-bucket/large-file.bin" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "Range: bytes=0-999"
# Get bytes 1000-1999
curl "http://localhost:5000/my-bucket/large-file.bin" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "Range: bytes=1000-1999"
# Get last 500 bytes
curl "http://localhost:5000/my-bucket/large-file.bin" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "Range: bytes=-500"
# Get from byte 5000 to end
curl "http://localhost:5000/my-bucket/large-file.bin" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "Range: bytes=5000-"
```
Range responses include:
- HTTP 206 Partial Content status
- `Content-Range` header showing the byte range
- `Accept-Ranges: bytes` header
### Conditional Requests
Use conditional headers for cache validation:
```bash
# Only download if modified since
curl "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "If-Modified-Since: Wed, 15 Jan 2025 10:00:00 GMT"
# Only download if ETag doesn't match (changed)
curl "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "If-None-Match: \"abc123...\""
# Only download if ETag matches
curl "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "If-Match: \"abc123...\""
```
## 22. Access Control Lists (ACLs)
ACLs provide legacy-style permission management for buckets and objects.
### Canned ACLs
| ACL | Description |
|-----|-------------|
| `private` | Owner gets FULL_CONTROL (default) |
| `public-read` | Owner FULL_CONTROL, public READ |
| `public-read-write` | Owner FULL_CONTROL, public READ and WRITE |
| `authenticated-read` | Owner FULL_CONTROL, authenticated users READ |
### Setting ACLs
```bash
# Set bucket ACL using canned ACL
curl -X PUT "http://localhost:5000/my-bucket?acl" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-acl: public-read"
# Set object ACL
curl -X PUT "http://localhost:5000/my-bucket/file.txt?acl" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-acl: private"
# Set ACL during upload
curl -X PUT "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-acl: public-read" \
--data-binary @file.txt
# Get bucket ACL
curl "http://localhost:5000/my-bucket?acl" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Get object ACL
curl "http://localhost:5000/my-bucket/file.txt?acl" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### ACL vs Bucket Policies
- **ACLs**: Simple, limited options, legacy approach
- **Bucket Policies**: Powerful, flexible, recommended for new deployments
For most use cases, prefer bucket policies over ACLs.
## 23. Object & Bucket Tagging
Add metadata tags to buckets and objects for organization, cost allocation, or lifecycle rule filtering.
### Bucket Tagging
```bash
# Set bucket tags
curl -X PUT "http://localhost:5000/my-bucket?tagging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"TagSet": [
{"Key": "Environment", "Value": "Production"},
{"Key": "Team", "Value": "Engineering"}
]
}'
# Get bucket tags
curl "http://localhost:5000/my-bucket?tagging" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Delete bucket tags
curl -X DELETE "http://localhost:5000/my-bucket?tagging" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### Object Tagging
```bash
# Set object tags
curl -X PUT "http://localhost:5000/my-bucket/file.txt?tagging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"TagSet": [
{"Key": "Classification", "Value": "Confidential"},
{"Key": "Owner", "Value": "john@example.com"}
]
}'
# Get object tags
curl "http://localhost:5000/my-bucket/file.txt?tagging" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Delete object tags
curl -X DELETE "http://localhost:5000/my-bucket/file.txt?tagging" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Set tags during upload
curl -X PUT "http://localhost:5000/my-bucket/file.txt" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-H "x-amz-tagging: Environment=Staging&Team=QA" \
--data-binary @file.txt
```
### Tagging Limits
- Maximum 50 tags per object (configurable via `OBJECT_TAG_LIMIT`)
- Tag key: 1-128 Unicode characters
- Tag value: 0-256 Unicode characters
### Use Cases
- **Lifecycle Rules**: Filter objects for expiration by tag
- **Access Control**: Use tag conditions in bucket policies
- **Cost Tracking**: Group objects by project or department
- **Automation**: Trigger actions based on object tags
## 24. CORS Configuration
Configure Cross-Origin Resource Sharing for browser-based applications.
### Setting CORS Rules
```bash
# Set CORS configuration
curl -X PUT "http://localhost:5000/my-bucket?cors" \
-H "Content-Type: application/json" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..." \
-d '{
"CORSRules": [
{
"AllowedOrigins": ["https://example.com", "https://app.example.com"],
"AllowedMethods": ["GET", "PUT", "POST", "DELETE"],
"AllowedHeaders": ["*"],
"ExposeHeaders": ["ETag", "x-amz-meta-*"],
"MaxAgeSeconds": 3600
}
]
}'
# Get CORS configuration
curl "http://localhost:5000/my-bucket?cors" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Delete CORS configuration
curl -X DELETE "http://localhost:5000/my-bucket?cors" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### CORS Rule Fields
| Field | Description |
|-------|-------------|
| `AllowedOrigins` | Origins allowed to access the bucket (required) |
| `AllowedMethods` | HTTP methods allowed (GET, PUT, POST, DELETE, HEAD) |
| `AllowedHeaders` | Request headers allowed in preflight |
| `ExposeHeaders` | Response headers visible to browser |
| `MaxAgeSeconds` | How long browser can cache preflight response |
## 25. List Objects API v2
MyFSIO supports both ListBucketResult v1 and v2 APIs.
### Using v2 API
```bash
# List with v2 (supports continuation tokens)
curl "http://localhost:5000/my-bucket?list-type=2" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# With prefix and delimiter (folder-like listing)
curl "http://localhost:5000/my-bucket?list-type=2&prefix=photos/&delimiter=/" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Pagination with continuation token
curl "http://localhost:5000/my-bucket?list-type=2&max-keys=100&continuation-token=TOKEN" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
# Start after specific key
curl "http://localhost:5000/my-bucket?list-type=2&start-after=photos/2024/" \
-H "X-Access-Key: ..." -H "X-Secret-Key: ..."
```
### v1 vs v2 Differences
| Feature | v1 | v2 |
|---------|----|----|
| Pagination | `marker` | `continuation-token` |
| Start position | `marker` | `start-after` |
| Fetch owner info | Always included | Use `fetch-owner=true` |
| Max keys | 1000 | 1000 |
### Query Parameters
| Parameter | Description |
|-----------|-------------|
| `list-type` | Set to `2` for v2 API |
| `prefix` | Filter objects by key prefix |
| `delimiter` | Group objects (typically `/`) |
| `max-keys` | Maximum results (1-1000, default 1000) |
| `continuation-token` | Token from previous response |
| `start-after` | Start listing after this key |
| `fetch-owner` | Include owner info in response |
| `encoding-type` | Set to `url` for URL-encoded keys
## 26. Static Website Hosting
MyFSIO can serve S3 buckets as static websites via custom domain mappings. When a request arrives with a `Host` header matching a mapped domain, MyFSIO resolves the bucket and serves objects directly.
### Enabling
Set the environment variable:
```bash
WEBSITE_HOSTING_ENABLED=true
```
When disabled, all website hosting endpoints return 400 and domain-based serving is skipped.
### Configuration
| Variable | Default | Description |
|----------|---------|-------------|
| `WEBSITE_HOSTING_ENABLED` | `false` | Master switch for website hosting |
### Setting Up a Website
**Step 1: Configure the bucket website settings**
```bash
curl -X PUT "http://localhost:5000/my-site?website" \
-H "Authorization: ..." \
-d '<?xml version="1.0" encoding="UTF-8"?>
<WebsiteConfiguration>
<IndexDocument><Suffix>index.html</Suffix></IndexDocument>
<ErrorDocument><Key>404.html</Key></ErrorDocument>
</WebsiteConfiguration>'
```
- `IndexDocument` with `Suffix` is required (must not contain `/`)
- `ErrorDocument` is optional
**Step 2: Map a domain to the bucket**
```bash
curl -X POST "http://localhost:5000/admin/website-domains" \
-H "Authorization: ..." \
-H "Content-Type: application/json" \
-d '{"domain": "example.com", "bucket": "my-site"}'
```
**Step 3: Point your domain to MyFSIO**
For HTTP-only (direct access), point DNS to the MyFSIO host on port 5000.
For HTTPS (recommended), use a reverse proxy. The critical requirement is passing the original `Host` header so MyFSIO can match the domain to a bucket.
**nginx example:**
```nginx
server {
server_name example.com;
listen 443 ssl;
ssl_certificate /etc/ssl/certs/example.com.pem;
ssl_certificate_key /etc/ssl/private/example.com.key;
location / {
proxy_pass http://127.0.0.1:5000;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
}
}
```
`proxy_set_header Host $host;` is required — without it, MyFSIO cannot match the incoming domain to a bucket. You do not need any path-based routing rules; MyFSIO handles all object resolution internally.
### How Domain Routing Works
1. A request arrives with `Host: example.com`
2. MyFSIO's `before_request` hook strips the port and looks up the domain in the `WebsiteDomainStore`
3. If a match is found, it loads the bucket's website config (index/error documents)
4. Object key resolution:
- `/` or trailing `/` → append `index_document` (e.g., `index.html`)
- `/path` → try exact match, then try `path/index_document`
- Not found → serve `error_document` with 404 status
5. If no domain match is found, the request falls through to normal S3 API / UI routing
### Domain Mapping Admin API
All endpoints require admin (`iam:*`) permissions.
| Method | Route | Body | Description |
|--------|-------|------|-------------|
| `GET` | `/admin/website-domains` | — | List all mappings |
| `POST` | `/admin/website-domains` | `{"domain": "...", "bucket": "..."}` | Create mapping |
| `GET` | `/admin/website-domains/<domain>` | — | Get single mapping |
| `PUT` | `/admin/website-domains/<domain>` | `{"bucket": "..."}` | Update mapping |
| `DELETE` | `/admin/website-domains/<domain>` | — | Delete mapping |
### Bucket Website API
| Method | Route | Description |
|--------|-------|-------------|
| `PUT` | `/<bucket>?website` | Set website config (XML body) |
| `GET` | `/<bucket>?website` | Get website config (XML response) |
| `DELETE` | `/<bucket>?website` | Remove website config |
### Web UI
- **Per-bucket config:** Bucket Details → Properties tab → "Static Website Hosting" card
- **Domain management:** Sidebar → "Domains" (visible when hosting is enabled and user is admin)

View File

@@ -10,3 +10,4 @@ waitress>=3.0.2
psutil>=7.1.3 psutil>=7.1.3
cryptography>=46.0.3 cryptography>=46.0.3
defusedxml>=0.7.1 defusedxml>=0.7.1
duckdb>=1.4.4

5
run.py
View File

@@ -5,6 +5,7 @@ import argparse
import os import os
import sys import sys
import warnings import warnings
import multiprocessing
from multiprocessing import Process from multiprocessing import Process
from pathlib import Path from pathlib import Path
@@ -87,6 +88,10 @@ def serve_ui(port: int, prod: bool = False, config: Optional[AppConfig] = None)
if __name__ == "__main__": 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 = 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"], default="both")
parser.add_argument("--api-port", type=int, default=5000) parser.add_argument("--api-port", type=int, default=5000)

View File

@@ -192,31 +192,86 @@ cat > "$INSTALL_DIR/myfsio.env" << EOF
# Generated by install.sh on $(date) # Generated by install.sh on $(date)
# Documentation: https://go.jzwsite.com/myfsio # Documentation: https://go.jzwsite.com/myfsio
# Storage paths # =============================================================================
# STORAGE PATHS
# =============================================================================
STORAGE_ROOT=$DATA_DIR STORAGE_ROOT=$DATA_DIR
LOG_DIR=$LOG_DIR LOG_DIR=$LOG_DIR
# Network # =============================================================================
# NETWORK
# =============================================================================
APP_HOST=0.0.0.0 APP_HOST=0.0.0.0
APP_PORT=$API_PORT APP_PORT=$API_PORT
# Security - CHANGE IN PRODUCTION # Public URL (set this if behind a reverse proxy for presigned URLs)
SECRET_KEY=$SECRET_KEY
CORS_ORIGINS=*
# Public URL (set this if behind a reverse proxy)
$(if [[ -n "$API_URL" ]]; then echo "API_BASE_URL=$API_URL"; else echo "# API_BASE_URL=https://s3.example.com"; fi) $(if [[ -n "$API_URL" ]]; then echo "API_BASE_URL=$API_URL"; else echo "# API_BASE_URL=https://s3.example.com"; fi)
# Logging # =============================================================================
# SECURITY
# =============================================================================
# Secret key for session signing (auto-generated if not set)
SECRET_KEY=$SECRET_KEY
# CORS settings - restrict in production
CORS_ORIGINS=*
# Brute-force protection
AUTH_MAX_ATTEMPTS=5
AUTH_LOCKOUT_MINUTES=15
# Reverse proxy settings (set to number of trusted proxies in front)
# NUM_TRUSTED_PROXIES=1
# Allow internal admin endpoints (only enable on trusted networks)
# ALLOW_INTERNAL_ENDPOINTS=false
# Allowed hosts for redirects (comma-separated, empty = restrict all)
# ALLOWED_REDIRECT_HOSTS=
# =============================================================================
# LOGGING
# =============================================================================
LOG_LEVEL=INFO LOG_LEVEL=INFO
LOG_TO_FILE=true LOG_TO_FILE=true
# Rate limiting # =============================================================================
# RATE LIMITING
# =============================================================================
RATE_LIMIT_DEFAULT=200 per minute RATE_LIMIT_DEFAULT=200 per minute
# RATE_LIMIT_LIST_BUCKETS=60 per minute
# RATE_LIMIT_BUCKET_OPS=120 per minute
# RATE_LIMIT_OBJECT_OPS=240 per minute
# RATE_LIMIT_ADMIN=60 per minute
# Optional: Encryption (uncomment to enable) # =============================================================================
# SERVER TUNING (0 = auto-detect based on system resources)
# =============================================================================
# SERVER_THREADS=0
# SERVER_CONNECTION_LIMIT=0
# SERVER_BACKLOG=0
# SERVER_CHANNEL_TIMEOUT=120
# =============================================================================
# ENCRYPTION (uncomment to enable)
# =============================================================================
# ENCRYPTION_ENABLED=true # ENCRYPTION_ENABLED=true
# KMS_ENABLED=true # KMS_ENABLED=true
# =============================================================================
# SITE SYNC / REPLICATION (for multi-site deployments)
# =============================================================================
# SITE_ID=site-1
# SITE_ENDPOINT=https://s3-site1.example.com
# SITE_REGION=us-east-1
# SITE_SYNC_ENABLED=false
# =============================================================================
# OPTIONAL FEATURES
# =============================================================================
# LIFECYCLE_ENABLED=false
# METRICS_HISTORY_ENABLED=false
# OPERATION_METRICS_ENABLED=false
EOF EOF
chmod 600 "$INSTALL_DIR/myfsio.env" chmod 600 "$INSTALL_DIR/myfsio.env"
echo " [OK] Created $INSTALL_DIR/myfsio.env" echo " [OK] Created $INSTALL_DIR/myfsio.env"
@@ -317,11 +372,36 @@ if [[ "$SKIP_SYSTEMD" != true ]]; then
fi fi
echo "" echo ""
sleep 2 echo " Waiting for service initialization..."
sleep 3
echo " Service Status:" echo " Service Status:"
echo " ---------------" echo " ---------------"
if systemctl is-active --quiet myfsio; then if systemctl is-active --quiet myfsio; then
echo " [OK] MyFSIO is running" echo " [OK] MyFSIO is running"
IAM_FILE="$DATA_DIR/.myfsio.sys/config/iam.json"
if [[ -f "$IAM_FILE" ]]; then
echo ""
echo " ============================================"
echo " ADMIN CREDENTIALS (save these securely!)"
echo " ============================================"
if command -v jq &>/dev/null; then
ACCESS_KEY=$(jq -r '.users[0].access_key' "$IAM_FILE" 2>/dev/null)
SECRET_KEY=$(jq -r '.users[0].secret_key' "$IAM_FILE" 2>/dev/null)
else
ACCESS_KEY=$(grep -o '"access_key"[[:space:]]*:[[:space:]]*"[^"]*"' "$IAM_FILE" | head -1 | sed 's/.*"\([^"]*\)"$/\1/')
SECRET_KEY=$(grep -o '"secret_key"[[:space:]]*:[[:space:]]*"[^"]*"' "$IAM_FILE" | head -1 | sed 's/.*"\([^"]*\)"$/\1/')
fi
if [[ -n "$ACCESS_KEY" && -n "$SECRET_KEY" ]]; then
echo " Access Key: $ACCESS_KEY"
echo " Secret Key: $SECRET_KEY"
else
echo " [!] Could not parse credentials from $IAM_FILE"
echo " Check the file manually or view service logs."
fi
echo " ============================================"
fi
else else
echo " [WARNING] MyFSIO may not have started correctly" echo " [WARNING] MyFSIO may not have started correctly"
echo " Check logs with: journalctl -u myfsio -f" echo " Check logs with: journalctl -u myfsio -f"
@@ -346,19 +426,26 @@ echo "Access Points:"
echo " API: http://$(hostname -I 2>/dev/null | awk '{print $1}' || echo "localhost"):$API_PORT" echo " API: http://$(hostname -I 2>/dev/null | awk '{print $1}' || echo "localhost"):$API_PORT"
echo " UI: http://$(hostname -I 2>/dev/null | awk '{print $1}' || echo "localhost"):$UI_PORT/ui" echo " UI: http://$(hostname -I 2>/dev/null | awk '{print $1}' || echo "localhost"):$UI_PORT/ui"
echo "" echo ""
echo "Default Credentials:" echo "Credentials:"
echo " Username: localadmin" echo " Admin credentials were shown above (if service was started)."
echo " Password: localadmin" echo " You can also find them in: $DATA_DIR/.myfsio.sys/config/iam.json"
echo " [!] WARNING: Change these immediately after first login!"
echo "" echo ""
echo "Configuration Files:" echo "Configuration Files:"
echo " Environment: $INSTALL_DIR/myfsio.env" echo " Environment: $INSTALL_DIR/myfsio.env"
echo " IAM Users: $DATA_DIR/.myfsio.sys/config/iam.json" echo " IAM Users: $DATA_DIR/.myfsio.sys/config/iam.json"
echo " Bucket Policies: $DATA_DIR/.myfsio.sys/config/bucket_policies.json" echo " Bucket Policies: $DATA_DIR/.myfsio.sys/config/bucket_policies.json"
echo " Secret Key: $DATA_DIR/.myfsio.sys/config/.secret (auto-generated)"
echo ""
echo "Security Notes:"
echo " - Rate limiting is enabled by default (200 req/min)"
echo " - Brute-force protection: 5 attempts, 15 min lockout"
echo " - Set CORS_ORIGINS to specific domains in production"
echo " - Set NUM_TRUSTED_PROXIES if behind a reverse proxy"
echo "" echo ""
echo "Useful Commands:" echo "Useful Commands:"
echo " Check status: sudo systemctl status myfsio" echo " Check status: sudo systemctl status myfsio"
echo " View logs: sudo journalctl -u myfsio -f" echo " View logs: sudo journalctl -u myfsio -f"
echo " Validate config: $INSTALL_DIR/myfsio --check-config"
echo " Restart: sudo systemctl restart myfsio" echo " Restart: sudo systemctl restart myfsio"
echo " Stop: sudo systemctl stop myfsio" echo " Stop: sudo systemctl stop myfsio"
echo "" echo ""

View File

@@ -88,7 +88,8 @@ echo "The following items will be removed:"
echo "" echo ""
echo " Install directory: $INSTALL_DIR" echo " Install directory: $INSTALL_DIR"
if [[ "$KEEP_DATA" != true ]]; then if [[ "$KEEP_DATA" != true ]]; then
echo " Data directory: $DATA_DIR (ALL YOUR DATA WILL BE DELETED!)" echo " Data directory: $DATA_DIR"
echo " [!] ALL DATA, IAM USERS, AND ENCRYPTION KEYS WILL BE DELETED!"
else else
echo " Data directory: $DATA_DIR (WILL BE KEPT)" echo " Data directory: $DATA_DIR (WILL BE KEPT)"
fi fi
@@ -227,8 +228,15 @@ echo ""
if [[ "$KEEP_DATA" == true ]]; then if [[ "$KEEP_DATA" == true ]]; then
echo "Your data has been preserved at: $DATA_DIR" echo "Your data has been preserved at: $DATA_DIR"
echo "" echo ""
echo "To reinstall MyFSIO with existing data, run:" echo "Preserved files include:"
echo " curl -fsSL https://go.jzwsite.com/myfsio-install | sudo bash" echo " - All buckets and objects"
echo " - IAM configuration: $DATA_DIR/.myfsio.sys/config/iam.json"
echo " - Bucket policies: $DATA_DIR/.myfsio.sys/config/bucket_policies.json"
echo " - Secret key: $DATA_DIR/.myfsio.sys/config/.secret"
echo " - Encryption keys: $DATA_DIR/.myfsio.sys/keys/ (if encryption was enabled)"
echo ""
echo "To reinstall MyFSIO with existing data:"
echo " ./install.sh --data-dir $DATA_DIR"
echo "" echo ""
fi fi

View File

@@ -1081,11 +1081,17 @@ html.sidebar-will-collapse .sidebar-user {
letter-spacing: 0.08em; letter-spacing: 0.08em;
} }
.main-content:has(.docs-sidebar) {
overflow-x: visible;
}
.docs-sidebar { .docs-sidebar {
position: sticky; position: sticky;
top: 1.5rem; top: 1.5rem;
border-radius: 1rem; border-radius: 1rem;
border: 1px solid var(--myfsio-card-border); border: 1px solid var(--myfsio-card-border);
max-height: calc(100vh - 3rem);
overflow-y: auto;
} }
.docs-sidebar-callouts { .docs-sidebar-callouts {
@@ -1282,6 +1288,20 @@ html.sidebar-will-collapse .sidebar-user {
padding: 2rem 1rem; padding: 2rem 1rem;
} }
#preview-text {
padding: 1rem 1.125rem;
max-height: 360px;
overflow: auto;
white-space: pre-wrap;
word-break: break-word;
font-family: 'SFMono-Regular', 'Menlo', 'Consolas', 'Liberation Mono', monospace;
font-size: .8rem;
line-height: 1.6;
tab-size: 4;
color: var(--myfsio-text);
background: transparent;
}
.upload-progress-stack { .upload-progress-stack {
display: flex; display: flex;
flex-direction: column; flex-direction: column;

View File

@@ -101,6 +101,7 @@
const previewImage = document.getElementById('preview-image'); const previewImage = document.getElementById('preview-image');
const previewVideo = document.getElementById('preview-video'); const previewVideo = document.getElementById('preview-video');
const previewAudio = document.getElementById('preview-audio'); const previewAudio = document.getElementById('preview-audio');
const previewText = document.getElementById('preview-text');
const previewIframe = document.getElementById('preview-iframe'); const previewIframe = document.getElementById('preview-iframe');
const downloadButton = document.getElementById('downloadButton'); const downloadButton = document.getElementById('downloadButton');
const presignButton = document.getElementById('presignButton'); const presignButton = document.getElementById('presignButton');
@@ -182,6 +183,9 @@
let visibleItems = []; let visibleItems = [];
let renderedRange = { start: 0, end: 0 }; let renderedRange = { start: 0, end: 0 };
let memoizedVisibleItems = null;
let memoizedInputs = { objectCount: -1, prefix: null, filterTerm: null };
const createObjectRow = (obj, displayKey = null) => { const createObjectRow = (obj, displayKey = null) => {
const tr = document.createElement('tr'); const tr = document.createElement('tr');
tr.dataset.objectRow = ''; tr.dataset.objectRow = '';
@@ -340,7 +344,21 @@
} }
}; };
const computeVisibleItems = () => { const computeVisibleItems = (forceRecompute = false) => {
const currentInputs = {
objectCount: allObjects.length,
prefix: currentPrefix,
filterTerm: currentFilterTerm
};
if (!forceRecompute &&
memoizedVisibleItems !== null &&
memoizedInputs.objectCount === currentInputs.objectCount &&
memoizedInputs.prefix === currentInputs.prefix &&
memoizedInputs.filterTerm === currentInputs.filterTerm) {
return memoizedVisibleItems;
}
const items = []; const items = [];
const folders = new Set(); const folders = new Set();
@@ -381,6 +399,8 @@
return aKey.localeCompare(bKey); return aKey.localeCompare(bKey);
}); });
memoizedVisibleItems = items;
memoizedInputs = currentInputs;
return items; return items;
}; };
@@ -497,6 +517,9 @@
}; };
}; };
let lastStreamRenderTime = 0;
const STREAM_RENDER_THROTTLE_MS = 500;
const flushPendingStreamObjects = () => { const flushPendingStreamObjects = () => {
if (pendingStreamObjects.length === 0) return; if (pendingStreamObjects.length === 0) return;
const batch = pendingStreamObjects.splice(0, pendingStreamObjects.length); const batch = pendingStreamObjects.splice(0, pendingStreamObjects.length);
@@ -513,6 +536,19 @@
loadMoreStatus.textContent = `${loadedObjectCount.toLocaleString()}${countText} loading...`; loadMoreStatus.textContent = `${loadedObjectCount.toLocaleString()}${countText} loading...`;
} }
} }
if (objectsLoadingRow && objectsLoadingRow.parentNode) {
const loadingText = objectsLoadingRow.querySelector('p');
if (loadingText) {
const countText = totalObjectCount > 0 ? ` of ${totalObjectCount.toLocaleString()}` : '';
loadingText.textContent = `Loading ${loadedObjectCount.toLocaleString()}${countText} objects...`;
}
}
const now = performance.now();
if (!streamingComplete && now - lastStreamRenderTime < STREAM_RENDER_THROTTLE_MS) {
streamRenderScheduled = false;
return;
}
lastStreamRenderTime = now;
refreshVirtualList(); refreshVirtualList();
streamRenderScheduled = false; streamRenderScheduled = false;
}; };
@@ -533,7 +569,10 @@
loadedObjectCount = 0; loadedObjectCount = 0;
totalObjectCount = 0; totalObjectCount = 0;
allObjects = []; allObjects = [];
memoizedVisibleItems = null;
memoizedInputs = { objectCount: -1, prefix: null, filterTerm: null };
pendingStreamObjects = []; pendingStreamObjects = [];
lastStreamRenderTime = 0;
streamAbortController = new AbortController(); streamAbortController = new AbortController();
@@ -548,7 +587,10 @@
throw new Error(`HTTP ${response.status}`); throw new Error(`HTTP ${response.status}`);
} }
if (objectsLoadingRow) objectsLoadingRow.remove(); if (objectsLoadingRow) {
const loadingText = objectsLoadingRow.querySelector('p');
if (loadingText) loadingText.textContent = 'Receiving objects...';
}
const reader = response.body.getReader(); const reader = response.body.getReader();
const decoder = new TextDecoder(); const decoder = new TextDecoder();
@@ -576,6 +618,10 @@
break; break;
case 'count': case 'count':
totalObjectCount = msg.total_count || 0; totalObjectCount = msg.total_count || 0;
if (objectsLoadingRow) {
const loadingText = objectsLoadingRow.querySelector('p');
if (loadingText) loadingText.textContent = `Loading 0 of ${totalObjectCount.toLocaleString()} objects...`;
}
break; break;
case 'object': case 'object':
pendingStreamObjects.push(processStreamObject(msg)); pendingStreamObjects.push(processStreamObject(msg));
@@ -609,11 +655,16 @@
} catch (e) { } } catch (e) { }
} }
flushPendingStreamObjects();
streamingComplete = true; streamingComplete = true;
flushPendingStreamObjects();
hasMoreObjects = false; hasMoreObjects = false;
totalObjectCount = loadedObjectCount;
updateObjectCountBadge(); updateObjectCountBadge();
if (objectsLoadingRow && objectsLoadingRow.parentNode) {
objectsLoadingRow.remove();
}
if (loadMoreStatus) { if (loadMoreStatus) {
loadMoreStatus.textContent = `${loadedObjectCount.toLocaleString()} objects`; loadMoreStatus.textContent = `${loadedObjectCount.toLocaleString()} objects`;
} }
@@ -643,6 +694,8 @@
loadedObjectCount = 0; loadedObjectCount = 0;
totalObjectCount = 0; totalObjectCount = 0;
allObjects = []; allObjects = [];
memoizedVisibleItems = null;
memoizedInputs = { objectCount: -1, prefix: null, filterTerm: null };
} }
if (append && loadMoreSpinner) { if (append && loadMoreSpinner) {
@@ -985,13 +1038,15 @@
}; };
const navigateToFolder = (prefix) => { const navigateToFolder = (prefix) => {
if (streamAbortController) {
streamAbortController.abort();
streamAbortController = null;
}
currentPrefix = prefix; currentPrefix = prefix;
if (scrollContainer) scrollContainer.scrollTop = 0; if (scrollContainer) scrollContainer.scrollTop = 0;
refreshVirtualList();
renderBreadcrumb(prefix);
selectedRows.clear(); selectedRows.clear();
if (typeof updateBulkDeleteState === 'function') { if (typeof updateBulkDeleteState === 'function') {
@@ -1001,6 +1056,9 @@
if (previewPanel) previewPanel.classList.add('d-none'); if (previewPanel) previewPanel.classList.add('d-none');
if (previewEmpty) previewEmpty.classList.remove('d-none'); if (previewEmpty) previewEmpty.classList.remove('d-none');
activeRow = null; activeRow = null;
isLoadingObjects = false;
loadObjects(false);
}; };
const renderObjectsView = () => { const renderObjectsView = () => {
@@ -1838,6 +1896,10 @@
el.setAttribute('src', 'about:blank'); el.setAttribute('src', 'about:blank');
} }
}); });
if (previewText) {
previewText.classList.add('d-none');
previewText.textContent = '';
}
previewPlaceholder.classList.remove('d-none'); previewPlaceholder.classList.remove('d-none');
}; };
@@ -1901,11 +1963,28 @@
previewIframe.style.minHeight = '500px'; previewIframe.style.minHeight = '500px';
previewIframe.classList.remove('d-none'); previewIframe.classList.remove('d-none');
previewPlaceholder.classList.add('d-none'); previewPlaceholder.classList.add('d-none');
} else if (previewUrl && lower.match(/\.(txt|log|json|md|csv|xml|html|htm|js|ts|py|java|c|cpp|h|css|scss|yaml|yml|toml|ini|cfg|conf|sh|bat)$/)) { } else if (previewUrl && previewText && lower.match(/\.(txt|log|json|md|csv|xml|html|htm|js|ts|py|java|c|cpp|h|css|scss|yaml|yml|toml|ini|cfg|conf|sh|bat|rs|go|rb|php|sql|r|swift|kt|scala|pl|lua|zig|ex|exs|hs|erl|ps1|psm1|psd1|fish|zsh|env|properties|gradle|makefile|dockerfile|vagrantfile|gitignore|gitattributes|editorconfig|eslintrc|prettierrc)$/)) {
previewIframe.src = previewUrl; previewText.textContent = 'Loading\u2026';
previewIframe.style.minHeight = '200px'; previewText.classList.remove('d-none');
previewIframe.classList.remove('d-none');
previewPlaceholder.classList.add('d-none'); previewPlaceholder.classList.add('d-none');
const currentRow = row;
fetch(previewUrl)
.then((r) => {
if (!r.ok) throw new Error(r.statusText);
const len = parseInt(r.headers.get('Content-Length') || '0', 10);
if (len > 512 * 1024) {
return r.text().then((t) => t.slice(0, 512 * 1024) + '\n\n--- Truncated (file too large for preview) ---');
}
return r.text();
})
.then((text) => {
if (activeRow !== currentRow) return;
previewText.textContent = text;
})
.catch(() => {
if (activeRow !== currentRow) return;
previewText.textContent = 'Failed to load preview';
});
} }
const metadataUrl = row.dataset.metadataUrl; const metadataUrl = row.dataset.metadataUrl;
@@ -4085,6 +4164,13 @@
} }
}); });
interceptForm('websiteForm', {
successMessage: 'Website settings saved',
onSuccess: function (data) {
updateWebsiteCard(data.enabled !== false, data.index_document, data.error_document);
}
});
interceptForm('bucketPolicyForm', { interceptForm('bucketPolicyForm', {
successMessage: 'Bucket policy saved', successMessage: 'Bucket policy saved',
onSuccess: function (data) { onSuccess: function (data) {
@@ -4145,6 +4231,59 @@
}); });
} }
function updateWebsiteCard(enabled, indexDoc, errorDoc) {
var card = document.getElementById('bucket-website-card');
if (!card) return;
var alertContainer = card.querySelector('.alert');
if (alertContainer) {
if (enabled) {
alertContainer.className = 'alert alert-success d-flex align-items-start mb-4';
var detail = 'Index: <code>' + escapeHtml(indexDoc || 'index.html') + '</code>';
if (errorDoc) detail += '<br>Error: <code>' + escapeHtml(errorDoc) + '</code>';
alertContainer.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="me-2 flex-shrink-0" viewBox="0 0 16 16">' +
'<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zm-3.97-3.03a.75.75 0 0 0-1.08.022L7.477 9.417 5.384 7.323a.75.75 0 0 0-1.06 1.06L6.97 11.03a.75.75 0 0 0 1.079-.02l3.992-4.99a.75.75 0 0 0-.01-1.05z"/>' +
'</svg><div><strong>Website hosting is enabled</strong>' +
'<p class="mb-0 small">' + detail + '</p></div>';
} else {
alertContainer.className = 'alert alert-secondary d-flex align-items-start mb-4';
alertContainer.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="me-2 flex-shrink-0" viewBox="0 0 16 16">' +
'<path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/>' +
'<path d="M4.646 4.646a.5.5 0 0 1 .708 0L8 7.293l2.646-2.647a.5.5 0 0 1 .708.708L8.707 8l2.647 2.646a.5.5 0 0 1-.708.708L8 8.707l-2.646 2.647a.5.5 0 0 1-.708-.708L7.293 8 4.646 5.354a.5.5 0 0 1 0-.708z"/>' +
'</svg><div><strong>Website hosting is disabled</strong>' +
'<p class="mb-0 small">Enable website hosting to serve bucket contents as a static website.</p></div>';
}
}
var disableBtn = document.getElementById('disableWebsiteBtn');
if (disableBtn) {
disableBtn.style.display = enabled ? '' : 'none';
}
var submitBtn = document.getElementById('websiteSubmitBtn');
if (submitBtn) {
submitBtn.classList.remove('btn-primary', 'btn-success');
submitBtn.classList.add(enabled ? 'btn-primary' : 'btn-success');
}
var submitLabel = document.getElementById('websiteSubmitLabel');
if (submitLabel) {
submitLabel.textContent = enabled ? 'Save Website Settings' : 'Enable Website Hosting';
}
}
var disableWebsiteBtn = document.getElementById('disableWebsiteBtn');
if (disableWebsiteBtn) {
disableWebsiteBtn.addEventListener('click', function () {
var form = document.getElementById('websiteForm');
if (!form) return;
document.getElementById('websiteAction').value = 'disable';
window.UICore.submitFormAjax(form, {
successMessage: 'Website hosting disabled',
onSuccess: function (data) {
document.getElementById('websiteAction').value = 'enable';
updateWebsiteCard(false, null, null);
}
});
});
}
function reloadReplicationPane() { function reloadReplicationPane() {
var replicationPane = document.getElementById('replication-pane'); var replicationPane = document.getElementById('replication-pane');
if (!replicationPane) return; if (!replicationPane) return;

View File

@@ -94,6 +94,21 @@
</svg> </svg>
<span>Metrics</span> <span>Metrics</span>
</a> </a>
<a href="{{ url_for('ui.sites_dashboard') }}" class="sidebar-link {% if request.endpoint == 'ui.sites_dashboard' %}active{% endif %}">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
<span>Sites</span>
</a>
{% endif %}
{% if website_hosting_nav %}
<a href="{{ url_for('ui.website_domains_dashboard') }}" class="sidebar-link {% if request.endpoint == 'ui.website_domains_dashboard' %}active{% endif %}">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 16 16">
<path d="M4.715 6.542 3.343 7.914a3 3 0 1 0 4.243 4.243l1.828-1.829A3 3 0 0 0 8.586 5.5L8 6.086a1.002 1.002 0 0 0-.154.199 2 2 0 0 1 .861 3.337L6.88 11.45a2 2 0 1 1-2.83-2.83l.793-.792a4.018 4.018 0 0 1-.128-1.287z"/>
<path d="M6.586 4.672A3 3 0 0 0 7.414 9.5l.775-.776a2 2 0 0 1-.896-3.346L9.12 3.55a2 2 0 1 1 2.83 2.83l-.793.792c.112.42.155.855.128 1.287l1.372-1.372a3 3 0 1 0-4.243-4.243L6.586 4.672z"/>
</svg>
<span>Domains</span>
</a>
{% endif %} {% endif %}
</div> </div>
<div class="nav-section"> <div class="nav-section">
@@ -179,6 +194,21 @@
</svg> </svg>
<span class="sidebar-link-text">Metrics</span> <span class="sidebar-link-text">Metrics</span>
</a> </a>
<a href="{{ url_for('ui.sites_dashboard') }}" class="sidebar-link {% if request.endpoint == 'ui.sites_dashboard' %}active{% endif %}" data-tooltip="Sites">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
<span class="sidebar-link-text">Sites</span>
</a>
{% endif %}
{% if website_hosting_nav %}
<a href="{{ url_for('ui.website_domains_dashboard') }}" class="sidebar-link {% if request.endpoint == 'ui.website_domains_dashboard' %}active{% endif %}" data-tooltip="Domains">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 16 16">
<path d="M4.715 6.542 3.343 7.914a3 3 0 1 0 4.243 4.243l1.828-1.829A3 3 0 0 0 8.586 5.5L8 6.086a1.002 1.002 0 0 0-.154.199 2 2 0 0 1 .861 3.337L6.88 11.45a2 2 0 1 1-2.83-2.83l.793-.792a4.018 4.018 0 0 1-.128-1.287z"/>
<path d="M6.586 4.672A3 3 0 0 0 7.414 9.5l.775-.776a2 2 0 0 1-.896-3.346L9.12 3.55a2 2 0 1 1 2.83 2.83l-.793.792c.112.42.155.855.128 1.287l1.372-1.372a3 3 0 1 0-4.243-4.243L6.586 4.672z"/>
</svg>
<span class="sidebar-link-text">Domains</span>
</a>
{% endif %} {% endif %}
</div> </div>
<div class="nav-section"> <div class="nav-section">

View File

@@ -321,7 +321,8 @@
<img id="preview-image" class="img-fluid d-none w-100" alt="Object preview" style="display: block;" /> <img id="preview-image" class="img-fluid d-none w-100" alt="Object preview" style="display: block;" />
<video id="preview-video" class="w-100 d-none" controls style="display: block;"></video> <video id="preview-video" class="w-100 d-none" controls style="display: block;"></video>
<audio id="preview-audio" class="w-100 d-none" controls style="display: block;"></audio> <audio id="preview-audio" class="w-100 d-none" controls style="display: block;"></audio>
<iframe id="preview-iframe" class="w-100 d-none" loading="lazy" style="min-height: 200px;"></iframe> <pre id="preview-text" class="w-100 d-none m-0"></pre>
<iframe id="preview-iframe" class="w-100 d-none" style="min-height: 200px;"></iframe>
</div> </div>
</div> </div>
</div> </div>
@@ -965,6 +966,89 @@
{% endif %} {% endif %}
</div> </div>
</div> </div>
{% if website_hosting_enabled %}
<div class="card shadow-sm mt-4" id="bucket-website-card">
<div class="card-header d-flex align-items-center">
<svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" fill="currentColor" class="text-primary me-2" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
<span class="fw-semibold">Static Website Hosting</span>
</div>
<div class="card-body">
{% if website_config %}
<div class="alert alert-success d-flex align-items-start mb-4" role="alert">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="me-2 flex-shrink-0" viewBox="0 0 16 16">
<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zm-3.97-3.03a.75.75 0 0 0-1.08.022L7.477 9.417 5.384 7.323a.75.75 0 0 0-1.06 1.06L6.97 11.03a.75.75 0 0 0 1.079-.02l3.992-4.99a.75.75 0 0 0-.01-1.05z"/>
</svg>
<div>
<strong>Website hosting is enabled</strong>
<p class="mb-0 small">
Index: <code>{{ website_config.index_document }}</code>
{% if website_config.error_document %}<br>Error: <code>{{ website_config.error_document }}</code>{% endif %}
</p>
</div>
</div>
{% else %}
<div class="alert alert-secondary d-flex align-items-start mb-4" role="alert">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="me-2 flex-shrink-0" viewBox="0 0 16 16">
<path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/>
<path d="M4.646 4.646a.5.5 0 0 1 .708 0L8 7.293l2.646-2.647a.5.5 0 0 1 .708.708L8.707 8l2.647 2.646a.5.5 0 0 1-.708.708L8 8.707l-2.646 2.647a.5.5 0 0 1-.708-.708L7.293 8 4.646 5.354a.5.5 0 0 1 0-.708z"/>
</svg>
<div>
<strong>Website hosting is disabled</strong>
<p class="mb-0 small">Enable website hosting to serve bucket contents as a static website.</p>
</div>
</div>
{% endif %}
{% if can_manage_website %}
<form method="post" action="{{ url_for('ui.update_bucket_website', bucket_name=bucket_name) }}" id="websiteForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
<input type="hidden" name="action" value="enable" id="websiteAction" />
<div class="mb-3">
<label for="index_document" class="form-label fw-medium">Index Document</label>
<input type="text" class="form-control" id="index_document" name="index_document"
value="{{ website_config.index_document if website_config else 'index.html' }}"
placeholder="index.html">
<div class="form-text">The default page served for directory paths (e.g., index.html).</div>
</div>
<div class="mb-4">
<label for="error_document" class="form-label fw-medium">Error Document</label>
<input type="text" class="form-control" id="error_document" name="error_document"
value="{{ website_config.error_document if website_config else '' }}"
placeholder="error.html">
<div class="form-text">Optional. The page served for 404 errors.</div>
</div>
<div class="d-flex gap-2 flex-wrap">
<button class="btn {{ 'btn-primary' if website_config else 'btn-success' }}" type="submit" id="websiteSubmitBtn">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M12.736 3.97a.733.733 0 0 1 1.047 0c.286.289.29.756.01 1.05L7.88 12.01a.733.733 0 0 1-1.065.02L3.217 8.384a.757.757 0 0 1 0-1.06.733.733 0 0 1 1.047 0l3.052 3.093 5.4-6.425a.247.247 0 0 1 .02-.022Z"/>
</svg>
<span id="websiteSubmitLabel">{{ 'Save Website Settings' if website_config else 'Enable Website Hosting' }}</span>
</button>
<button type="button" class="btn btn-outline-danger" id="disableWebsiteBtn"{% if not website_config %} style="display: none;"{% endif %}>
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M4.646 4.646a.5.5 0 0 1 .708 0L8 7.293l2.646-2.647a.5.5 0 0 1 .708.708L8.707 8l2.647 2.646a.5.5 0 0 1-.708.708L8 8.707l-2.646 2.647a.5.5 0 0 1-.708-.708L7.293 8 4.646 5.354a.5.5 0 0 1 0-.708z"/>
</svg>
Disable Website Hosting
</button>
</div>
</form>
{% else %}
<div class="text-center py-3">
<svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="currentColor" class="text-muted mb-2" viewBox="0 0 16 16">
<path d="M8 1a2 2 0 0 1 2 2v4H6V3a2 2 0 0 1 2-2zm3 6V3a3 3 0 0 0-6 0v4a2 2 0 0 0-2 2v5a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V9a2 2 0 0 0-2-2z"/>
</svg>
<p class="text-muted mb-0 small">You do not have permission to modify website hosting for this bucket.</p>
</div>
{% endif %}
</div>
</div>
{% endif %}
</div> </div>
<div class="col-lg-4"> <div class="col-lg-4">
@@ -1459,6 +1543,30 @@
</div> </div>
</div> </div>
<div id="bidirWarningBucket" class="alert alert-warning d-none mb-4" role="alert">
<h6 class="alert-heading fw-bold d-flex align-items-center gap-2 mb-2">
<svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" fill="currentColor" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M1 11.5a.5.5 0 0 0 .5.5h11.793l-3.147 3.146a.5.5 0 0 0 .708.708l4-4a.5.5 0 0 0 0-.708l-4-4a.5.5 0 0 0-.708.708L13.293 11H1.5a.5.5 0 0 0-.5.5zm14-7a.5.5 0 0 1-.5.5H2.707l3.147 3.146a.5.5 0 1 1-.708.708l-4-4a.5.5 0 0 1 0-.708l4-4a.5.5 0 1 1 .708.708L2.707 4H14.5a.5.5 0 0 1 .5.5z"/>
</svg>
Requires Configuration on Both Sites
</h6>
<p class="mb-2 small">For bidirectional sync to work, <strong>both sites</strong> must be configured:</p>
<ol class="mb-2 ps-3 small">
<li>This site: Enable bidirectional replication here</li>
<li>Remote site: Register this site as a peer with a connection</li>
<li>Remote site: Create matching bidirectional rule pointing back</li>
<li>Both sites: Ensure <code>SITE_SYNC_ENABLED=true</code></li>
</ol>
<div class="small">
<a href="{{ url_for('ui.sites_dashboard') }}" class="alert-link">
<svg xmlns="http://www.w3.org/2000/svg" width="12" height="12" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077z"/>
</svg>
Check bidirectional status in Sites Dashboard
</a>
</div>
</div>
<button type="submit" class="btn btn-primary"> <button type="submit" class="btn btn-primary">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16"> <svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 3a5 5 0 1 0 4.546 2.914.5.5 0 0 1 .908-.417A6 6 0 1 1 8 2v1z"/> <path fill-rule="evenodd" d="M8 3a5 5 0 1 0 4.546 2.914.5.5 0 0 1 .908-.417A6 6 0 1 1 8 2v1z"/>
@@ -2569,5 +2677,26 @@ window.BucketDetailConfig = {
bucketsOverview: "{{ url_for('ui.buckets_overview') }}" bucketsOverview: "{{ url_for('ui.buckets_overview') }}"
} }
}; };
(function() {
const bidirWarning = document.getElementById('bidirWarningBucket');
const modeRadios = document.querySelectorAll('input[name="replication_mode"]');
function updateBidirWarning() {
if (!bidirWarning) return;
const selected = document.querySelector('input[name="replication_mode"]:checked');
if (selected && selected.value === 'bidirectional') {
bidirWarning.classList.remove('d-none');
} else {
bidirWarning.classList.add('d-none');
}
}
modeRadios.forEach(function(radio) {
radio.addEventListener('change', updateBidirWarning);
});
updateBidirWarning();
})();
</script> </script>
{% endblock %} {% endblock %}

View File

@@ -141,7 +141,7 @@
let visibleCount = 0; let visibleCount = 0;
bucketItems.forEach(item => { bucketItems.forEach(item => {
const name = item.querySelector('.card-title').textContent.toLowerCase(); const name = item.querySelector('.bucket-name').textContent.toLowerCase();
if (name.includes(term)) { if (name.includes(term)) {
item.classList.remove('d-none'); item.classList.remove('d-none');
visibleCount++; visibleCount++;

View File

@@ -35,6 +35,7 @@
<li><a href="#api">REST endpoints</a></li> <li><a href="#api">REST endpoints</a></li>
<li><a href="#examples">API Examples</a></li> <li><a href="#examples">API Examples</a></li>
<li><a href="#replication">Site Replication &amp; Sync</a></li> <li><a href="#replication">Site Replication &amp; Sync</a></li>
<li><a href="#site-registry">Site Registry</a></li>
<li><a href="#versioning">Object Versioning</a></li> <li><a href="#versioning">Object Versioning</a></li>
<li><a href="#quotas">Bucket Quotas</a></li> <li><a href="#quotas">Bucket Quotas</a></li>
<li><a href="#encryption">Encryption</a></li> <li><a href="#encryption">Encryption</a></li>
@@ -42,6 +43,15 @@
<li><a href="#metrics">Metrics History</a></li> <li><a href="#metrics">Metrics History</a></li>
<li><a href="#operation-metrics">Operation Metrics</a></li> <li><a href="#operation-metrics">Operation Metrics</a></li>
<li><a href="#troubleshooting">Troubleshooting</a></li> <li><a href="#troubleshooting">Troubleshooting</a></li>
<li><a href="#health-check">Health Check</a></li>
<li><a href="#object-lock">Object Lock &amp; Retention</a></li>
<li><a href="#access-logging">Access Logging</a></li>
<li><a href="#notifications">Notifications &amp; Webhooks</a></li>
<li><a href="#select-content">SelectObjectContent</a></li>
<li><a href="#advanced-ops">Advanced Operations</a></li>
<li><a href="#acls">Access Control Lists</a></li>
<li><a href="#tagging">Object &amp; Bucket Tagging</a></li>
<li><a href="#website-hosting">Static Website Hosting</a></li>
</ul> </ul>
</div> </div>
</div> </div>
@@ -88,8 +98,8 @@ python run.py --mode ui
<tbody> <tbody>
<tr> <tr>
<td><code>API_BASE_URL</code></td> <td><code>API_BASE_URL</code></td>
<td><code>None</code></td> <td><code>http://127.0.0.1:5000</code></td>
<td>The public URL of the API. <strong>Required</strong> if running behind a proxy. Ensures presigned URLs are generated correctly.</td> <td>Internal S3 API URL used by the web UI proxy. Also used for presigned URL generation. Set to your public URL if running behind a reverse proxy.</td>
</tr> </tr>
<tr> <tr>
<td><code>STORAGE_ROOT</code></td> <td><code>STORAGE_ROOT</code></td>
@@ -157,23 +167,43 @@ python run.py --mode ui
<td><code>200 per minute</code></td> <td><code>200 per minute</code></td>
<td>Default API rate limit.</td> <td>Default API rate limit.</td>
</tr> </tr>
<tr>
<td><code>RATE_LIMIT_LIST_BUCKETS</code></td>
<td><code>60 per minute</code></td>
<td>Rate limit for listing buckets.</td>
</tr>
<tr>
<td><code>RATE_LIMIT_BUCKET_OPS</code></td>
<td><code>120 per minute</code></td>
<td>Rate limit for bucket operations.</td>
</tr>
<tr>
<td><code>RATE_LIMIT_OBJECT_OPS</code></td>
<td><code>240 per minute</code></td>
<td>Rate limit for object operations.</td>
</tr>
<tr>
<td><code>RATE_LIMIT_HEAD_OPS</code></td>
<td><code>100 per minute</code></td>
<td>Rate limit for HEAD requests.</td>
</tr>
<tr class="table-secondary"> <tr class="table-secondary">
<td colspan="3" class="fw-semibold">Server Settings</td> <td colspan="3" class="fw-semibold">Server Settings</td>
</tr> </tr>
<tr> <tr>
<td><code>SERVER_THREADS</code></td> <td><code>SERVER_THREADS</code></td>
<td><code>4</code></td> <td><code>0</code> (auto)</td>
<td>Waitress worker threads (1-64).</td> <td>Waitress worker threads (1-64). 0 = auto (CPU cores × 2).</td>
</tr> </tr>
<tr> <tr>
<td><code>SERVER_CONNECTION_LIMIT</code></td> <td><code>SERVER_CONNECTION_LIMIT</code></td>
<td><code>100</code></td> <td><code>0</code> (auto)</td>
<td>Max concurrent connections (10-1000).</td> <td>Max concurrent connections (10-1000). 0 = auto (RAM-based).</td>
</tr> </tr>
<tr> <tr>
<td><code>SERVER_BACKLOG</code></td> <td><code>SERVER_BACKLOG</code></td>
<td><code>1024</code></td> <td><code>0</code> (auto)</td>
<td>TCP listen backlog (64-4096).</td> <td>TCP listen backlog (64-4096). 0 = auto (conn_limit × 2).</td>
</tr> </tr>
<tr> <tr>
<td><code>SERVER_CHANNEL_TIMEOUT</code></td> <td><code>SERVER_CHANNEL_TIMEOUT</code></td>
@@ -242,6 +272,115 @@ python run.py --mode ui
<td><code>100</code></td> <td><code>100</code></td>
<td>Max objects to pull per sync cycle.</td> <td>Max objects to pull per sync cycle.</td>
</tr> </tr>
<tr>
<td><code>SITE_SYNC_CONNECT_TIMEOUT_SECONDS</code></td>
<td><code>10</code></td>
<td>Connection timeout for site sync (seconds).</td>
</tr>
<tr>
<td><code>SITE_SYNC_READ_TIMEOUT_SECONDS</code></td>
<td><code>120</code></td>
<td>Read timeout for site sync (seconds).</td>
</tr>
<tr>
<td><code>SITE_SYNC_MAX_RETRIES</code></td>
<td><code>2</code></td>
<td>Max retry attempts for site sync operations.</td>
</tr>
<tr>
<td><code>SITE_SYNC_CLOCK_SKEW_TOLERANCE_SECONDS</code></td>
<td><code>1.0</code></td>
<td>Clock skew tolerance for conflict resolution.</td>
</tr>
<tr class="table-secondary">
<td colspan="3" class="fw-semibold">Replication Settings</td>
</tr>
<tr>
<td><code>REPLICATION_CONNECT_TIMEOUT_SECONDS</code></td>
<td><code>5</code></td>
<td>Connection timeout for replication (seconds).</td>
</tr>
<tr>
<td><code>REPLICATION_READ_TIMEOUT_SECONDS</code></td>
<td><code>30</code></td>
<td>Read timeout for replication (seconds).</td>
</tr>
<tr>
<td><code>REPLICATION_MAX_RETRIES</code></td>
<td><code>2</code></td>
<td>Max retry attempts for replication operations.</td>
</tr>
<tr>
<td><code>REPLICATION_STREAMING_THRESHOLD_BYTES</code></td>
<td><code>10485760</code></td>
<td>Objects larger than this use streaming upload (10 MB).</td>
</tr>
<tr>
<td><code>REPLICATION_MAX_FAILURES_PER_BUCKET</code></td>
<td><code>50</code></td>
<td>Max failure records to keep per bucket.</td>
</tr>
<tr class="table-secondary">
<td colspan="3" class="fw-semibold">Security & Auth Settings</td>
</tr>
<tr>
<td><code>SIGV4_TIMESTAMP_TOLERANCE_SECONDS</code></td>
<td><code>900</code></td>
<td>Max time skew for SigV4 requests (15 minutes).</td>
</tr>
<tr>
<td><code>PRESIGNED_URL_MIN_EXPIRY_SECONDS</code></td>
<td><code>1</code></td>
<td>Minimum presigned URL expiry time.</td>
</tr>
<tr>
<td><code>PRESIGNED_URL_MAX_EXPIRY_SECONDS</code></td>
<td><code>604800</code></td>
<td>Maximum presigned URL expiry time (7 days).</td>
</tr>
<tr class="table-secondary">
<td colspan="3" class="fw-semibold">Storage Limits</td>
</tr>
<tr>
<td><code>OBJECT_KEY_MAX_LENGTH_BYTES</code></td>
<td><code>1024</code></td>
<td>Maximum object key length in bytes.</td>
</tr>
<tr>
<td><code>OBJECT_CACHE_MAX_SIZE</code></td>
<td><code>100</code></td>
<td>Maximum number of objects in cache.</td>
</tr>
<tr>
<td><code>BUCKET_CONFIG_CACHE_TTL_SECONDS</code></td>
<td><code>30</code></td>
<td>Bucket config cache TTL in seconds.</td>
</tr>
<tr>
<td><code>OBJECT_TAG_LIMIT</code></td>
<td><code>50</code></td>
<td>Maximum number of tags per object.</td>
</tr>
<tr>
<td><code>LIFECYCLE_MAX_HISTORY_PER_BUCKET</code></td>
<td><code>50</code></td>
<td>Max lifecycle history records per bucket.</td>
</tr>
<tr>
<td><code>ENCRYPTION_CHUNK_SIZE_BYTES</code></td>
<td><code>65536</code></td>
<td>Chunk size for streaming encryption (64 KB).</td>
</tr>
<tr>
<td><code>KMS_GENERATE_DATA_KEY_MIN_BYTES</code></td>
<td><code>1</code></td>
<td>Minimum data key size for KMS generation.</td>
</tr>
<tr>
<td><code>KMS_GENERATE_DATA_KEY_MAX_BYTES</code></td>
<td><code>1024</code></td>
<td>Maximum data key size for KMS generation.</td>
</tr>
</tbody> </tbody>
</table> </table>
</div> </div>
@@ -313,10 +452,10 @@ sudo journalctl -u myfsio -f # View logs</code></pre>
<span class="docs-section-kicker">03</span> <span class="docs-section-kicker">03</span>
<h2 class="h4 mb-0">Authenticate &amp; manage IAM</h2> <h2 class="h4 mb-0">Authenticate &amp; manage IAM</h2>
</div> </div>
<p class="text-muted">MyFSIO seeds <code>data/.myfsio.sys/config/iam.json</code> with <code>localadmin/localadmin</code>. Sign in once, rotate it, then grant least-privilege access to teammates and tools.</p> <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>
<div class="docs-highlight mb-3"> <div class="docs-highlight mb-3">
<ol class="mb-0"> <ol class="mb-0">
<li>Visit <code>/ui/login</code>, enter the bootstrap credentials, and rotate them immediately from the IAM page.</li> <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>Create additional users with descriptive display names and AWS-style inline policies (for example <code>{"bucket": "*", "actions": ["list", "read"]}</code>).</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>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> <li>Bucket policies layer on top of IAM. Apply Private/Public presets or paste custom JSON; changes reload instantly.</li>
@@ -834,10 +973,174 @@ SITE_SYNC_BATCH_SIZE=100 # Max objects per sync cycle</code></pre>
</div> </div>
</div> </div>
</article> </article>
<article id="versioning" class="card shadow-sm docs-section"> <article id="site-registry" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">09</span> <span class="docs-section-kicker">09</span>
<h2 class="h4 mb-0">Site Registry</h2>
</div>
<p class="text-muted">Track cluster membership and site identity for geo-distributed deployments. The site registry stores local site identity and peer site information.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Connections vs Sites</h3>
<p class="small text-muted mb-3">Understanding the difference between Connections and Sites is key to configuring geo-distribution:</p>
<div class="table-responsive mb-3">
<table class="table table-sm table-bordered small">
<thead class="table-light">
<tr>
<th style="width: 20%;">Aspect</th>
<th style="width: 40%;">Connections</th>
<th style="width: 40%;">Sites</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>Purpose</strong></td>
<td>Store credentials to authenticate with remote S3 endpoints</td>
<td>Track cluster membership and site identity</td>
</tr>
<tr>
<td><strong>Contains</strong></td>
<td>Endpoint URL, access key, secret key, region</td>
<td>Site ID, endpoint, region, priority, display name</td>
</tr>
<tr>
<td><strong>Used by</strong></td>
<td>Replication rules, site sync workers</td>
<td>Geo-distribution awareness, cluster topology</td>
</tr>
<tr>
<td><strong>Analogy</strong></td>
<td><em>"How do I log in to that server?"</em></td>
<td><em>"Who are the members of my cluster?"</em></td>
</tr>
</tbody>
</table>
</div>
<p class="small text-muted">Sites can optionally link to a Connection (via <code>connection_id</code>) to perform health checks against peer sites.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Configuration</h3>
<p class="small text-muted">Set environment variables to bootstrap local site identity on startup:</p>
<div class="table-responsive mb-3">
<table class="table table-sm table-bordered small">
<thead class="table-light">
<tr>
<th>Variable</th>
<th>Default</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>SITE_ID</code></td>
<td><code>None</code></td>
<td>Unique identifier for this site (e.g., <code>us-west-1</code>)</td>
</tr>
<tr>
<td><code>SITE_ENDPOINT</code></td>
<td><code>None</code></td>
<td>Public URL for this site (e.g., <code>https://s3.us-west-1.example.com</code>)</td>
</tr>
<tr>
<td><code>SITE_REGION</code></td>
<td><code>us-east-1</code></td>
<td>AWS-style region identifier</td>
</tr>
<tr>
<td><code>SITE_PRIORITY</code></td>
<td><code>100</code></td>
<td>Routing priority (lower = preferred)</td>
</tr>
</tbody>
</table>
</div>
<pre class="mb-3"><code class="language-bash"># Example: Configure site identity
export SITE_ID=us-west-1
export SITE_ENDPOINT=https://s3.us-west-1.example.com
export SITE_REGION=us-west-1
export SITE_PRIORITY=100
python run.py</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Using the Sites UI</h3>
<p class="small text-muted">Navigate to <a href="{{ url_for('ui.sites_dashboard') }}">Sites</a> in the sidebar to manage site configuration:</p>
<div class="row g-3 mb-3">
<div class="col-md-6">
<div class="card border h-100">
<div class="card-header bg-light py-2"><strong class="small">Local Site Identity</strong></div>
<div class="card-body small">
<ul class="mb-0 ps-3">
<li>Configure this site's ID, endpoint, region, and priority</li>
<li>Display name for easier identification</li>
<li>Changes persist to <code>site_registry.json</code></li>
</ul>
</div>
</div>
</div>
<div class="col-md-6">
<div class="card border h-100">
<div class="card-header bg-light py-2"><strong class="small">Peer Sites</strong></div>
<div class="card-body small">
<ul class="mb-0 ps-3">
<li>Register remote sites in your cluster</li>
<li>Link to a Connection for health checks</li>
<li>View health status (green/red/unknown)</li>
<li>Edit or delete peers as needed</li>
</ul>
</div>
</div>
</div>
</div>
<h3 class="h6 text-uppercase text-muted mt-4">Admin API Endpoints</h3>
<p class="small text-muted">The <code>/admin</code> API provides programmatic access to site registry:</p>
<pre class="mb-3"><code class="language-bash"># Get local site configuration
curl {{ api_base }}/admin/site \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Update local site
curl -X PUT {{ api_base }}/admin/site \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"site_id": "us-west-1", "endpoint": "https://s3.example.com", "region": "us-west-1"}'
# List all peer sites
curl {{ api_base }}/admin/sites \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Add a peer site
curl -X POST {{ api_base }}/admin/sites \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"site_id": "us-east-1", "endpoint": "https://s3.us-east-1.example.com"}'
# Check peer health
curl {{ api_base }}/admin/sites/us-east-1/health \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Get cluster topology
curl {{ api_base }}/admin/topology \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Storage Location</h3>
<p class="small text-muted mb-3">Site registry data is stored at:</p>
<code class="d-block mb-3">data/.myfsio.sys/config/site_registry.json</code>
<div class="alert alert-light border mb-0">
<div class="d-flex gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-info-circle text-muted mt-1 flex-shrink-0" viewBox="0 0 16 16">
<path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/>
<path d="m8.93 6.588-2.29.287-.082.38.45.083c.294.07.352.176.288.469l-.738 3.468c-.194.897.105 1.319.808 1.319.545 0 1.178-.252 1.465-.598l.088-.416c-.2.176-.492.246-.686.246-.275 0-.375-.193-.304-.533L8.93 6.588zM9 4.5a1 1 0 1 1-2 0 1 1 0 0 1 2 0z"/>
</svg>
<div>
<strong>Planned:</strong> The site registry lays the groundwork for features like automatic failover, intelligent routing, and multi-site consistency. Currently it provides cluster awareness and health monitoring.
</div>
</div>
</div>
</div>
</article>
<article id="versioning" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">10</span>
<h2 class="h4 mb-0">Object Versioning</h2> <h2 class="h4 mb-0">Object Versioning</h2>
</div> </div>
<p class="text-muted">Keep multiple versions of objects to protect against accidental deletions and overwrites. Restore previous versions at any time.</p> <p class="text-muted">Keep multiple versions of objects to protect against accidental deletions and overwrites. Restore previous versions at any time.</p>
@@ -917,7 +1220,7 @@ curl "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?versionId=&lt;version-id&gt;" \
<article id="quotas" class="card shadow-sm docs-section"> <article id="quotas" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">10</span> <span class="docs-section-kicker">11</span>
<h2 class="h4 mb-0">Bucket Quotas</h2> <h2 class="h4 mb-0">Bucket Quotas</h2>
</div> </div>
<p class="text-muted">Limit how much data a bucket can hold using storage quotas. Quotas are enforced on uploads and multipart completions.</p> <p class="text-muted">Limit how much data a bucket can hold using storage quotas. Quotas are enforced on uploads and multipart completions.</p>
@@ -985,7 +1288,7 @@ curl -X PUT "{{ api_base }}/bucket/&lt;bucket&gt;?quota" \
<article id="encryption" class="card shadow-sm docs-section"> <article id="encryption" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">11</span> <span class="docs-section-kicker">12</span>
<h2 class="h4 mb-0">Encryption</h2> <h2 class="h4 mb-0">Encryption</h2>
</div> </div>
<p class="text-muted">Protect data at rest with server-side encryption using AES-256-GCM. Objects are encrypted before being written to disk and decrypted transparently on read.</p> <p class="text-muted">Protect data at rest with server-side encryption using AES-256-GCM. Objects are encrypted before being written to disk and decrypted transparently on read.</p>
@@ -1079,7 +1382,7 @@ curl -X DELETE "{{ api_base }}/kms/keys/{key-id}?waiting_period_days=30" \
<article id="lifecycle" class="card shadow-sm docs-section"> <article id="lifecycle" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">12</span> <span class="docs-section-kicker">13</span>
<h2 class="h4 mb-0">Lifecycle Rules</h2> <h2 class="h4 mb-0">Lifecycle Rules</h2>
</div> </div>
<p class="text-muted">Automatically delete expired objects, clean up old versions, and abort incomplete multipart uploads using time-based lifecycle rules.</p> <p class="text-muted">Automatically delete expired objects, clean up old versions, and abort incomplete multipart uploads using time-based lifecycle rules.</p>
@@ -1161,7 +1464,7 @@ curl "{{ api_base }}/&lt;bucket&gt;?lifecycle" \
<article id="metrics" class="card shadow-sm docs-section"> <article id="metrics" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">13</span> <span class="docs-section-kicker">14</span>
<h2 class="h4 mb-0">Metrics History</h2> <h2 class="h4 mb-0">Metrics History</h2>
</div> </div>
<p class="text-muted">Track CPU, memory, and disk usage over time with optional metrics history. Disabled by default to minimize overhead.</p> <p class="text-muted">Track CPU, memory, and disk usage over time with optional metrics history. Disabled by default to minimize overhead.</p>
@@ -1245,7 +1548,7 @@ curl -X PUT "{{ api_base | replace('/api', '/ui') }}/metrics/settings" \
<article id="operation-metrics" class="card shadow-sm docs-section"> <article id="operation-metrics" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">14</span> <span class="docs-section-kicker">15</span>
<h2 class="h4 mb-0">Operation Metrics</h2> <h2 class="h4 mb-0">Operation Metrics</h2>
</div> </div>
<p class="text-muted">Track API request statistics including request counts, latency, error rates, and bandwidth usage. Provides real-time visibility into API operations.</p> <p class="text-muted">Track API request statistics including request counts, latency, error rates, and bandwidth usage. Provides real-time visibility into API operations.</p>
@@ -1352,7 +1655,7 @@ curl "{{ api_base | replace('/api', '/ui') }}/metrics/operations/history?hours=6
<article id="troubleshooting" class="card shadow-sm docs-section"> <article id="troubleshooting" class="card shadow-sm docs-section">
<div class="card-body"> <div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3"> <div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">15</span> <span class="docs-section-kicker">16</span>
<h2 class="h4 mb-0">Troubleshooting &amp; tips</h2> <h2 class="h4 mb-0">Troubleshooting &amp; tips</h2>
</div> </div>
<div class="table-responsive"> <div class="table-responsive">
@@ -1400,8 +1703,498 @@ curl "{{ api_base | replace('/api', '/ui') }}/metrics/operations/history?hours=6
</div> </div>
</div> </div>
</article> </article>
<article id="health-check" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">17</span>
<h2 class="h4 mb-0">Health Check Endpoint</h2>
</div> </div>
<div class="col-xl-4"> <p class="text-muted">The API exposes a health check endpoint for monitoring and load balancer integration.</p>
<pre class="mb-3"><code class="language-bash"># Check API health
curl {{ api_base }}/myfsio/health
# Response
{"status": "ok", "version": "0.1.7"}</code></pre>
<p class="small text-muted mb-3">Use this endpoint for:</p>
<ul class="small text-muted mb-0">
<li>Load balancer health checks</li>
<li>Kubernetes liveness/readiness probes</li>
<li>Monitoring system integration (Prometheus, Datadog, etc.)</li>
</ul>
</div>
</article>
<article id="object-lock" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">18</span>
<h2 class="h4 mb-0">Object Lock &amp; Retention</h2>
</div>
<p class="text-muted">Object Lock prevents objects from being deleted or overwritten for a specified retention period.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Retention Modes</h3>
<div class="table-responsive mb-3">
<table class="table table-sm table-bordered small">
<thead class="table-light">
<tr>
<th>Mode</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>GOVERNANCE</strong></td>
<td>Objects can't be deleted by normal users, but admins with bypass permission can override</td>
</tr>
<tr>
<td><strong>COMPLIANCE</strong></td>
<td>Objects can't be deleted or overwritten by anyone until the retention period expires</td>
</tr>
</tbody>
</table>
</div>
<h3 class="h6 text-uppercase text-muted mt-4">API Usage</h3>
<pre class="mb-3"><code class="language-bash"># Set object retention
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?retention" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"Mode": "GOVERNANCE", "RetainUntilDate": "2025-12-31T23:59:59Z"}'
# Enable legal hold (indefinite protection)
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?legal-hold" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"Status": "ON"}'
# Get legal hold status
curl "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?legal-hold" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"</code></pre>
<div class="alert alert-light border mb-0">
<div class="d-flex gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-info-circle text-muted mt-1 flex-shrink-0" viewBox="0 0 16 16">
<path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/>
<path d="m8.93 6.588-2.29.287-.082.38.45.083c.294.07.352.176.288.469l-.738 3.468c-.194.897.105 1.319.808 1.319.545 0 1.178-.252 1.465-.598l.088-.416c-.2.176-.492.246-.686.246-.275 0-.375-.193-.304-.533L8.93 6.588zM9 4.5a1 1 0 1 1-2 0 1 1 0 0 1 2 0z"/>
</svg>
<div>
<strong>Legal Hold:</strong> Provides indefinite protection independent of retention settings. Use for litigation holds or regulatory requirements.
</div>
</div>
</div>
</div>
</article>
<article id="access-logging" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">19</span>
<h2 class="h4 mb-0">Access Logging</h2>
</div>
<p class="text-muted">Enable S3-style access logging to track all requests to your buckets for audit and analysis.</p>
<pre class="mb-3"><code class="language-bash"># Enable access logging
curl -X PUT "{{ api_base }}/&lt;bucket&gt;?logging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{
"LoggingEnabled": {
"TargetBucket": "log-bucket",
"TargetPrefix": "logs/my-bucket/"
}
}'
# Get logging configuration
curl "{{ api_base }}/&lt;bucket&gt;?logging" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Log Contents</h3>
<p class="small text-muted mb-0">Logs include: timestamp, bucket, key, operation type, request ID, requester, source IP, HTTP status, error codes, bytes transferred, timing, referrer, and User-Agent.</p>
</div>
</article>
<article id="notifications" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">20</span>
<h2 class="h4 mb-0">Notifications &amp; Webhooks</h2>
</div>
<p class="text-muted">Configure event notifications to trigger webhooks when objects are created or deleted.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Supported Events</h3>
<div class="table-responsive mb-3">
<table class="table table-sm table-bordered small">
<thead class="table-light">
<tr>
<th>Event Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>s3:ObjectCreated:*</code></td>
<td>Any object creation (PUT, POST, COPY, multipart)</td>
</tr>
<tr>
<td><code>s3:ObjectRemoved:*</code></td>
<td>Any object deletion</td>
</tr>
</tbody>
</table>
</div>
<pre class="mb-3"><code class="language-bash"># Set notification configuration
curl -X PUT "{{ api_base }}/&lt;bucket&gt;?notification" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{
"TopicConfigurations": [{
"Id": "upload-notify",
"TopicArn": "https://webhook.example.com/s3-events",
"Events": ["s3:ObjectCreated:*"],
"Filter": {
"Key": {
"FilterRules": [
{"Name": "prefix", "Value": "uploads/"},
{"Name": "suffix", "Value": ".jpg"}
]
}
}
}]
}'</code></pre>
<div class="alert alert-warning border-warning bg-warning-subtle mb-0">
<div class="d-flex gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-exclamation-triangle mt-1" viewBox="0 0 16 16">
<path d="M7.938 2.016A.13.13 0 0 1 8.002 2a.13.13 0 0 1 .063.016.146.146 0 0 1 .054.057l6.857 11.667c.036.06.035.124.002.183a.163.163 0 0 1-.054.06.116.116 0 0 1-.066.017H1.146a.115.115 0 0 1-.066-.017.163.163 0 0 1-.054-.06.176.176 0 0 1 .002-.183L7.884 2.073a.147.147 0 0 1 .054-.057zm1.044-.45a1.13 1.13 0 0 0-1.96 0L.165 13.233c-.457.778.091 1.767.98 1.767h13.713c.889 0 1.438-.99.98-1.767L8.982 1.566z"/>
<path d="M7.002 12a1 1 0 1 1 2 0 1 1 0 0 1-2 0zM7.1 5.995a.905.905 0 1 1 1.8 0l-.35 3.507a.552.552 0 0 1-1.1 0L7.1 5.995z"/>
</svg>
<div>
<strong>Security:</strong> Webhook URLs are validated to prevent SSRF attacks. Internal/private IP ranges are blocked.
</div>
</div>
</div>
</div>
</article>
<article id="select-content" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">21</span>
<h2 class="h4 mb-0">SelectObjectContent (SQL)</h2>
</div>
<p class="text-muted">Query CSV, JSON, or Parquet files directly using SQL without downloading the entire object.</p>
<div class="alert alert-info border small mb-3">
<strong>Prerequisite:</strong> Requires DuckDB to be installed (<code>pip install duckdb</code>)
</div>
<pre class="mb-3"><code class="language-bash"># Query a CSV file
curl -X POST "{{ api_base }}/&lt;bucket&gt;/data.csv?select" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{
"Expression": "SELECT name, age FROM s3object WHERE age > 25",
"ExpressionType": "SQL",
"InputSerialization": {
"CSV": {"FileHeaderInfo": "USE", "FieldDelimiter": ","}
},
"OutputSerialization": {"JSON": {}}
}'</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Supported Formats</h3>
<div class="row g-2 mb-0">
<div class="col-md-4">
<div class="bg-light rounded p-2 small text-center">
<strong>CSV</strong><br><span class="text-muted">Headers, delimiters</span>
</div>
</div>
<div class="col-md-4">
<div class="bg-light rounded p-2 small text-center">
<strong>JSON</strong><br><span class="text-muted">Document or lines</span>
</div>
</div>
<div class="col-md-4">
<div class="bg-light rounded p-2 small text-center">
<strong>Parquet</strong><br><span class="text-muted">Auto schema</span>
</div>
</div>
</div>
</div>
</article>
<article id="advanced-ops" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">22</span>
<h2 class="h4 mb-0">Advanced S3 Operations</h2>
</div>
<p class="text-muted">Copy objects, upload part copies, and use range requests for partial downloads.</p>
<h3 class="h6 text-uppercase text-muted mt-4">CopyObject</h3>
<pre class="mb-3"><code class="language-bash"># Copy within same bucket
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/copy-of-file.txt" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-copy-source: /&lt;bucket&gt;/original-file.txt"
# Copy with metadata replacement
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/file.txt" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-copy-source: /&lt;bucket&gt;/file.txt" \
-H "x-amz-metadata-directive: REPLACE" \
-H "x-amz-meta-newkey: newvalue"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">UploadPartCopy</h3>
<p class="small text-muted">Copy data from an existing object into a multipart upload part:</p>
<pre class="mb-3"><code class="language-bash"># Copy bytes 0-10485759 from source as part 1
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?uploadId=X&partNumber=1" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-copy-source: /source-bucket/source-file.bin" \
-H "x-amz-copy-source-range: bytes=0-10485759"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Range Requests</h3>
<pre class="mb-3"><code class="language-bash"># Get first 1000 bytes
curl "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "Range: bytes=0-999"
# Get last 500 bytes
curl "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "Range: bytes=-500"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Conditional Requests</h3>
<div class="table-responsive mb-0">
<table class="table table-sm table-bordered small mb-0">
<thead class="table-light">
<tr>
<th>Header</th>
<th>Behavior</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>If-Modified-Since</code></td>
<td>Only download if changed after date</td>
</tr>
<tr>
<td><code>If-None-Match</code></td>
<td>Only download if ETag differs</td>
</tr>
<tr>
<td><code>If-Match</code></td>
<td>Only download if ETag matches</td>
</tr>
</tbody>
</table>
</div>
</div>
</article>
<article id="acls" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">23</span>
<h2 class="h4 mb-0">Access Control Lists (ACLs)</h2>
</div>
<p class="text-muted">ACLs provide legacy-style permission management for buckets and objects.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Canned ACLs</h3>
<div class="table-responsive mb-3">
<table class="table table-sm table-bordered small">
<thead class="table-light">
<tr>
<th>ACL</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>private</code></td>
<td>Owner gets FULL_CONTROL (default)</td>
</tr>
<tr>
<td><code>public-read</code></td>
<td>Owner FULL_CONTROL, public READ</td>
</tr>
<tr>
<td><code>public-read-write</code></td>
<td>Owner FULL_CONTROL, public READ and WRITE</td>
</tr>
<tr>
<td><code>authenticated-read</code></td>
<td>Owner FULL_CONTROL, authenticated users READ</td>
</tr>
</tbody>
</table>
</div>
<pre class="mb-3"><code class="language-bash"># Set bucket ACL
curl -X PUT "{{ api_base }}/&lt;bucket&gt;?acl" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-acl: public-read"
# Set object ACL during upload
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-acl: private" \
--data-binary @file.txt</code></pre>
<div class="alert alert-light border mb-0">
<strong>Recommendation:</strong> For most use cases, prefer bucket policies over ACLs for more flexible access control.
</div>
</div>
</article>
<article id="tagging" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">24</span>
<h2 class="h4 mb-0">Object &amp; Bucket Tagging</h2>
</div>
<p class="text-muted">Add metadata tags to buckets and objects for organization, cost allocation, or lifecycle rule filtering.</p>
<h3 class="h6 text-uppercase text-muted mt-4">Object Tagging</h3>
<pre class="mb-3"><code class="language-bash"># Set object tags
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?tagging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{
"TagSet": [
{"Key": "Classification", "Value": "Confidential"},
{"Key": "Owner", "Value": "john@example.com"}
]
}'
# Get object tags
curl "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;?tagging" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Set tags during upload
curl -X PUT "{{ api_base }}/&lt;bucket&gt;/&lt;key&gt;" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-H "x-amz-tagging: Environment=Staging&Team=QA" \
--data-binary @file.txt</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Bucket Tagging</h3>
<pre class="mb-3"><code class="language-bash"># Set bucket tags
curl -X PUT "{{ api_base }}/&lt;bucket&gt;?tagging" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{
"TagSet": [
{"Key": "Environment", "Value": "Production"},
{"Key": "Team", "Value": "Engineering"}
]
}'</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">Use Cases</h3>
<div class="row g-2 mb-0">
<div class="col-md-6">
<ul class="small text-muted mb-0 ps-3">
<li>Filter objects for lifecycle expiration by tag</li>
<li>Use tag conditions in bucket policies</li>
</ul>
</div>
<div class="col-md-6">
<ul class="small text-muted mb-0 ps-3">
<li>Group objects by project or department</li>
<li>Trigger automation based on object tags</li>
</ul>
</div>
</div>
</div>
</article>
<article id="website-hosting" class="card shadow-sm docs-section">
<div class="card-body">
<div class="d-flex align-items-center gap-2 mb-3">
<span class="docs-section-kicker">25</span>
<h2 class="h4 mb-0">Static Website Hosting</h2>
</div>
<p class="text-muted">Host static websites directly from S3 buckets with custom index and error pages, served via custom domain mapping.</p>
<div class="alert alert-info small mb-3">
<strong>Prerequisite:</strong> Set <code>WEBSITE_HOSTING_ENABLED=true</code> to enable this feature.
</div>
<h3 class="h6 text-uppercase text-muted mt-4">1. Configure bucket for website hosting</h3>
<pre class="mb-3"><code class="language-bash"># Enable website hosting with index and error documents
curl -X PUT "{{ api_base }}/&lt;bucket&gt;?website" \
-H "Content-Type: application/xml" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '&lt;WebsiteConfiguration&gt;
&lt;IndexDocument&gt;&lt;Suffix&gt;index.html&lt;/Suffix&gt;&lt;/IndexDocument&gt;
&lt;ErrorDocument&gt;&lt;Key&gt;404.html&lt;/Key&gt;&lt;/ErrorDocument&gt;
&lt;/WebsiteConfiguration&gt;'
# Get website configuration
curl "{{ api_base }}/&lt;bucket&gt;?website" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Remove website configuration
curl -X DELETE "{{ api_base }}/&lt;bucket&gt;?website" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">2. Map a custom domain to the bucket</h3>
<pre class="mb-3"><code class="language-bash"># Create domain mapping (admin only)
curl -X POST "{{ api_base }}/admin/website-domains" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"domain": "example.com", "bucket": "my-site"}'
# List all domain mappings
curl "{{ api_base }}/admin/website-domains" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"
# Update a mapping
curl -X PUT "{{ api_base }}/admin/website-domains/example.com" \
-H "Content-Type: application/json" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;" \
-d '{"bucket": "new-site-bucket"}'
# Delete a mapping
curl -X DELETE "{{ api_base }}/admin/website-domains/example.com" \
-H "X-Access-Key: &lt;key&gt;" -H "X-Secret-Key: &lt;secret&gt;"</code></pre>
<h3 class="h6 text-uppercase text-muted mt-4">3. Point your domain</h3>
<p class="small text-muted">MyFSIO handles domain routing natively via the <code>Host</code> header &mdash; no path-based proxy rules needed. Just point your domain to the MyFSIO API server.</p>
<div class="alert alert-secondary small mb-3">
<strong>Direct access (HTTP only):</strong> Point your domain's DNS (A or CNAME) directly to the MyFSIO server on port 5000.
</div>
<p class="small text-muted mb-2">For <strong>HTTPS</strong>, place a reverse proxy in front. The proxy only needs to forward traffic &mdash; MyFSIO handles the domain-to-bucket routing:</p>
<pre class="mb-3"><code class="language-nginx"># nginx example
server {
server_name example.com;
location / {
proxy_pass http://127.0.0.1:5000;
proxy_set_header Host $host; # Required: passes the domain to MyFSIO
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
}
}</code></pre>
<div class="alert alert-warning small mb-3">
<strong>Important:</strong> The <code>proxy_set_header Host $host;</code> directive is required. MyFSIO matches the incoming <code>Host</code> header against domain mappings to determine which bucket to serve.
</div>
<h3 class="h6 text-uppercase text-muted mt-4">How it works</h3>
<div class="row g-2 mb-0">
<div class="col-md-6">
<ul class="small text-muted mb-0 ps-3">
<li><code>/</code> serves the configured index document</li>
<li><code>/about/</code> serves <code>about/index.html</code></li>
<li>Objects served with correct Content-Type</li>
</ul>
</div>
<div class="col-md-6">
<ul class="small text-muted mb-0 ps-3">
<li>Missing objects return the error document with 404</li>
<li>Website endpoints are public (no auth required)</li>
<li>Normal S3 API with auth continues to work</li>
</ul>
</div>
</div>
</div>
</article>
</div>
<div class="col-xl-4 docs-sidebar-col">
<aside class="card shadow-sm docs-sidebar"> <aside class="card shadow-sm docs-sidebar">
<div class="card-body"> <div class="card-body">
<h3 class="h6 text-uppercase text-muted mb-3">On this page</h3> <h3 class="h6 text-uppercase text-muted mb-3">On this page</h3>
@@ -1414,6 +2207,7 @@ curl "{{ api_base | replace('/api', '/ui') }}/metrics/operations/history?hours=6
<li><a href="#api">REST endpoints</a></li> <li><a href="#api">REST endpoints</a></li>
<li><a href="#examples">API Examples</a></li> <li><a href="#examples">API Examples</a></li>
<li><a href="#replication">Site Replication &amp; Sync</a></li> <li><a href="#replication">Site Replication &amp; Sync</a></li>
<li><a href="#site-registry">Site Registry</a></li>
<li><a href="#versioning">Object Versioning</a></li> <li><a href="#versioning">Object Versioning</a></li>
<li><a href="#quotas">Bucket Quotas</a></li> <li><a href="#quotas">Bucket Quotas</a></li>
<li><a href="#encryption">Encryption</a></li> <li><a href="#encryption">Encryption</a></li>
@@ -1421,6 +2215,15 @@ curl "{{ api_base | replace('/api', '/ui') }}/metrics/operations/history?hours=6
<li><a href="#metrics">Metrics History</a></li> <li><a href="#metrics">Metrics History</a></li>
<li><a href="#operation-metrics">Operation Metrics</a></li> <li><a href="#operation-metrics">Operation Metrics</a></li>
<li><a href="#troubleshooting">Troubleshooting</a></li> <li><a href="#troubleshooting">Troubleshooting</a></li>
<li><a href="#health-check">Health Check</a></li>
<li><a href="#object-lock">Object Lock &amp; Retention</a></li>
<li><a href="#access-logging">Access Logging</a></li>
<li><a href="#notifications">Notifications &amp; Webhooks</a></li>
<li><a href="#select-content">SelectObjectContent</a></li>
<li><a href="#advanced-ops">Advanced Operations</a></li>
<li><a href="#acls">Access Control Lists</a></li>
<li><a href="#tagging">Object &amp; Bucket Tagging</a></li>
<li><a href="#website-hosting">Static Website Hosting</a></li>
</ul> </ul>
<div class="docs-sidebar-callouts"> <div class="docs-sidebar-callouts">
<div> <div>
@@ -1428,8 +2231,8 @@ curl "{{ api_base | replace('/api', '/ui') }}/metrics/operations/history?hours=6
<code class="d-block">{{ api_base }}</code> <code class="d-block">{{ api_base }}</code>
</div> </div>
<div> <div>
<div class="small text-uppercase text-muted">Sample user</div> <div class="small text-uppercase text-muted">Initial credentials</div>
<code class="d-block">localadmin / localadmin</code> <span class="text-muted small">Generated on first run (check console)</span>
</div> </div>
<div> <div>
<div class="small text-uppercase text-muted">Logs</div> <div class="small text-uppercase text-muted">Logs</div>

View File

@@ -398,6 +398,14 @@
<option value="24" selected>Last 24 hours</option> <option value="24" selected>Last 24 hours</option>
<option value="168">Last 7 days</option> <option value="168">Last 7 days</option>
</select> </select>
<select class="form-select form-select-sm" id="maxDataPoints" style="width: auto;" title="Maximum data points to display">
<option value="100">100 points</option>
<option value="250">250 points</option>
<option value="500" selected>500 points</option>
<option value="1000">1000 points</option>
<option value="2000">2000 points</option>
<option value="0">Unlimited</option>
</select>
</div> </div>
</div> </div>
<div class="card-body p-4"> <div class="card-body p-4">
@@ -817,8 +825,8 @@
var diskChart = null; var diskChart = null;
var historyStatus = document.getElementById('historyStatus'); var historyStatus = document.getElementById('historyStatus');
var timeRangeSelect = document.getElementById('historyTimeRange'); var timeRangeSelect = document.getElementById('historyTimeRange');
var maxDataPointsSelect = document.getElementById('maxDataPoints');
var historyTimer = null; var historyTimer = null;
var MAX_DATA_POINTS = 500;
function createChart(ctx, label, color) { function createChart(ctx, label, color) {
return new Chart(ctx, { return new Chart(ctx, {
@@ -889,7 +897,8 @@
if (historyStatus) historyStatus.textContent = 'No history data available yet. Data is recorded every ' + (data.interval_minutes || 5) + ' minutes.'; if (historyStatus) historyStatus.textContent = 'No history data available yet. Data is recorded every ' + (data.interval_minutes || 5) + ' minutes.';
return; return;
} }
var history = data.history.slice(-MAX_DATA_POINTS); var maxPoints = maxDataPointsSelect ? parseInt(maxDataPointsSelect.value, 10) : 500;
var history = maxPoints > 0 ? data.history.slice(-maxPoints) : data.history;
var labels = history.map(function(h) { return formatTime(h.timestamp); }); var labels = history.map(function(h) { return formatTime(h.timestamp); });
var cpuData = history.map(function(h) { return h.cpu_percent; }); var cpuData = history.map(function(h) { return h.cpu_percent; });
var memData = history.map(function(h) { return h.memory_percent; }); var memData = history.map(function(h) { return h.memory_percent; });
@@ -927,6 +936,10 @@
timeRangeSelect.addEventListener('change', loadHistory); timeRangeSelect.addEventListener('change', loadHistory);
} }
if (maxDataPointsSelect) {
maxDataPointsSelect.addEventListener('change', loadHistory);
}
document.addEventListener('visibilitychange', function() { document.addEventListener('visibilitychange', function() {
if (document.hidden) { if (document.hidden) {
if (historyTimer) clearInterval(historyTimer); if (historyTimer) clearInterval(historyTimer);

View File

@@ -0,0 +1,270 @@
{% extends "base.html" %}
{% block title %}Set Up Replication - S3 Compatible Storage{% endblock %}
{% block content %}
<div class="page-header d-flex justify-content-between align-items-center mb-4">
<div>
<nav aria-label="breadcrumb">
<ol class="breadcrumb mb-1">
<li class="breadcrumb-item"><a href="{{ url_for('ui.sites_dashboard') }}">Sites</a></li>
<li class="breadcrumb-item active" aria-current="page">Replication Wizard</li>
</ol>
</nav>
<h1 class="h3 mb-1 d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="28" height="28" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path d="M8 4a.5.5 0 0 1 .5.5V6a.5.5 0 0 1-1 0V4.5A.5.5 0 0 1 8 4zM3.732 5.732a.5.5 0 0 1 .707 0l.915.914a.5.5 0 1 1-.708.708l-.914-.915a.5.5 0 0 1 0-.707zM2 10a.5.5 0 0 1 .5-.5h1.586a.5.5 0 0 1 0 1H2.5A.5.5 0 0 1 2 10zm9.5 0a.5.5 0 0 1 .5-.5h1.5a.5.5 0 0 1 0 1H12a.5.5 0 0 1-.5-.5zm.754-4.246a.389.389 0 0 0-.527-.02L7.547 9.31a.91.91 0 1 0 1.302 1.258l3.434-4.297a.389.389 0 0 0-.029-.518z"/>
<path fill-rule="evenodd" d="M0 10a8 8 0 1 1 15.547 2.661c-.442 1.253-1.845 1.602-2.932 1.25C11.309 13.488 9.475 13 8 13c-1.474 0-3.31.488-4.615.911-1.087.352-2.49.003-2.932-1.25A7.988 7.988 0 0 1 0 10zm8-7a7 7 0 0 0-6.603 9.329c.203.575.923.876 1.68.63C4.397 12.533 6.358 12 8 12s3.604.532 4.923.96c.757.245 1.477-.056 1.68-.631A7 7 0 0 0 8 3z"/>
</svg>
Set Up Replication
</h1>
<p class="text-muted mb-0 mt-1">Configure bucket replication to <strong>{{ peer.display_name or peer.site_id }}</strong></p>
</div>
</div>
<div class="row g-4">
<div class="col-lg-4 col-md-5">
<div class="card shadow-sm border-0 mb-4" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8m7.5-6.923c-.67.204-1.335.82-1.887 1.855A8 8 0 0 0 5.145 4H7.5zM4.09 4a9.3 9.3 0 0 1 .64-1.539 7 7 0 0 1 .597-.933A7.03 7.03 0 0 0 2.255 4zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a7 7 0 0 0-.656 2.5zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5zM8.5 5v2.5h2.99a12.5 12.5 0 0 0-.337-2.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5zM5.145 12q.208.58.468 1.068c.552 1.035 1.218 1.65 1.887 1.855V12zm.182 2.472a7 7 0 0 1-.597-.933A9.3 9.3 0 0 1 4.09 12H2.255a7 7 0 0 0 3.072 2.472M3.82 11a13.7 13.7 0 0 1-.312-2.5h-2.49a7 7 0 0 0 .656 2.5zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855q.26-.487.468-1.068zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.7 13.7 0 0 1-.312 2.5m2.802-3.5a7 7 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7 7 0 0 0-3.072-2.472c.218.284.418.598.597.933M10.855 4a8 8 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4z"/>
</svg>
Peer Site
</h5>
</div>
<div class="card-body px-4 pb-4">
<dl class="mb-0">
<dt class="text-muted small">Site ID</dt>
<dd class="mb-2">{{ peer.site_id }}</dd>
<dt class="text-muted small">Endpoint</dt>
<dd class="mb-2 text-truncate" title="{{ peer.endpoint }}">{{ peer.endpoint }}</dd>
<dt class="text-muted small">Region</dt>
<dd class="mb-2"><span class="badge bg-primary bg-opacity-10 text-primary">{{ peer.region }}</span></dd>
<dt class="text-muted small">Connection</dt>
<dd class="mb-0"><span class="badge bg-secondary bg-opacity-10 text-secondary">{{ connection.name }}</span></dd>
</dl>
</div>
</div>
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm.93-9.412-1 4.705c-.07.34.029.533.304.533.194 0 .487-.07.686-.246l-.088.416c-.287.346-.92.598-1.465.598-.703 0-1.002-.422-.808-1.319l.738-3.468c.064-.293.006-.399-.287-.47l-.451-.081.082-.381 2.29-.287zM8 5.5a1 1 0 1 1 0-2 1 1 0 0 1 0 2z"/>
</svg>
Replication Modes
</h5>
</div>
<div class="card-body px-4 pb-4 small">
<p class="mb-2"><strong>New Only:</strong> Only replicate new objects uploaded after the rule is created.</p>
<p class="mb-2"><strong>All Objects:</strong> Replicate all existing objects plus new uploads.</p>
<p class="mb-0"><strong>Bidirectional:</strong> Two-way sync between sites. Changes on either side are synchronized.</p>
</div>
</div>
</div>
<div class="col-lg-8 col-md-7">
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M2.522 5H2a.5.5 0 0 0-.494.574l1.372 9.149A1.5 1.5 0 0 0 4.36 16h7.278a1.5 1.5 0 0 0 1.483-1.277l1.373-9.149A.5.5 0 0 0 14 5h-.522A5.5 5.5 0 0 0 2.522 5zm1.005 0a4.5 4.5 0 0 1 8.945 0H3.527z"/>
</svg>
Select Buckets to Replicate
</h5>
<p class="text-muted small mb-0">Choose which buckets should be replicated to this peer site</p>
</div>
<div class="card-body px-4 pb-4">
{% if buckets %}
<form method="POST" action="{{ url_for('ui.create_peer_replication_rules', site_id=peer.site_id) }}">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="mb-4">
<label for="mode" class="form-label fw-medium">Replication Mode</label>
<select class="form-select" id="mode" name="mode">
<option value="new_only">New Objects Only</option>
<option value="all">All Objects (includes existing)</option>
<option value="bidirectional">Bidirectional Sync</option>
</select>
</div>
<div id="bidirWarning" class="alert alert-warning d-none mb-4" role="alert">
<h6 class="alert-heading fw-bold d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M1 11.5a.5.5 0 0 0 .5.5h11.793l-3.147 3.146a.5.5 0 0 0 .708.708l4-4a.5.5 0 0 0 0-.708l-4-4a.5.5 0 0 0-.708.708L13.293 11H1.5a.5.5 0 0 0-.5.5zm14-7a.5.5 0 0 1-.5.5H2.707l3.147 3.146a.5.5 0 1 1-.708.708l-4-4a.5.5 0 0 1 0-.708l4-4a.5.5 0 1 1 .708.708L2.707 4H14.5a.5.5 0 0 1 .5.5z"/>
</svg>
Bidirectional Sync Requires Configuration on Both Sites
</h6>
<p class="mb-2">For bidirectional sync to work properly, you must configure <strong>both</strong> sites. This wizard only configures one direction.</p>
<hr class="my-2">
<p class="mb-2 fw-semibold">After completing this wizard, you must also:</p>
<ol class="mb-2 ps-3">
<li>Go to <strong>{{ peer.display_name or peer.site_id }}</strong>'s admin UI</li>
<li>Register <strong>this site</strong> as a peer (with a connection)</li>
<li>Create matching bidirectional replication rules pointing back to this site</li>
<li>Ensure <code>SITE_SYNC_ENABLED=true</code> is set on both sites</li>
</ol>
<div class="d-flex align-items-center gap-2 mt-3">
<span class="badge bg-light text-dark border">Local Site ID: <strong>{{ local_site.site_id if local_site else 'Not configured' }}</strong></span>
<span class="badge bg-light text-dark border">Local Endpoint: <strong>{{ local_site.endpoint if local_site and local_site.endpoint else 'Not configured' }}</strong></span>
</div>
{% if not local_site or not local_site.site_id or not local_site.endpoint %}
<div class="alert alert-danger mt-3 mb-0 py-2">
<small><strong>Warning:</strong> Your local site identity is not fully configured. The remote site won't be able to connect back. <a href="{{ url_for('ui.sites_dashboard') }}">Configure it now</a>.</small>
</div>
{% endif %}
</div>
<div class="table-responsive">
<table class="table table-hover align-middle mb-0">
<thead class="table-light">
<tr>
<th scope="col" style="width: 40px;">
<input type="checkbox" class="form-check-input" id="selectAll">
</th>
<th scope="col">Local Bucket</th>
<th scope="col">Target Bucket Name</th>
<th scope="col">Status</th>
</tr>
</thead>
<tbody>
{% for bucket in buckets %}
<tr>
<td>
<input type="checkbox" class="form-check-input bucket-checkbox"
name="buckets" value="{{ bucket.name }}"
{% if bucket.has_rule %}disabled{% endif %}>
</td>
<td>
<div class="d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M2.522 5H2a.5.5 0 0 0-.494.574l1.372 9.149A1.5 1.5 0 0 0 4.36 16h7.278a1.5 1.5 0 0 0 1.483-1.277l1.373-9.149A.5.5 0 0 0 14 5h-.522A5.5 5.5 0 0 0 2.522 5zm1.005 0a4.5 4.5 0 0 1 8.945 0H3.527z"/>
</svg>
<span class="fw-medium">{{ bucket.name }}</span>
</div>
</td>
<td>
<input type="text" class="form-control form-control-sm"
name="target_{{ bucket.name }}"
value="{{ bucket.existing_target or bucket.name }}"
placeholder="{{ bucket.name }}"
{% if bucket.has_rule %}disabled{% endif %}>
</td>
<td>
{% if bucket.has_rule %}
<span class="badge bg-info bg-opacity-10 text-info">
Already configured ({{ bucket.existing_mode }})
</span>
{% else %}
<span class="badge bg-secondary bg-opacity-10 text-secondary">
Not configured
</span>
{% endif %}
</td>
</tr>
{% endfor %}
</tbody>
</table>
</div>
<div class="d-flex gap-2 mt-4 pt-3 border-top">
<button type="submit" class="btn btn-primary" id="submitBtn" disabled>
<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>
Create Replication Rules
</button>
<a href="{{ url_for('ui.sites_dashboard') }}" class="btn btn-outline-secondary">
Skip for Now
</a>
</div>
</form>
{% else %}
<div class="empty-state text-center py-5">
<div class="empty-state-icon mx-auto mb-3">
<svg xmlns="http://www.w3.org/2000/svg" width="48" height="48" fill="currentColor" viewBox="0 0 16 16">
<path d="M2.522 5H2a.5.5 0 0 0-.494.574l1.372 9.149A1.5 1.5 0 0 0 4.36 16h7.278a1.5 1.5 0 0 0 1.483-1.277l1.373-9.149A.5.5 0 0 0 14 5h-.522A5.5 5.5 0 0 0 2.522 5zm1.005 0a4.5 4.5 0 0 1 8.945 0H3.527z"/>
</svg>
</div>
<h5 class="fw-semibold mb-2">No buckets yet</h5>
<p class="text-muted mb-3">Create some buckets first, then come back to set up replication.</p>
<a href="{{ url_for('ui.buckets_overview') }}" class="btn btn-primary">
Go to Buckets
</a>
</div>
{% endif %}
</div>
</div>
</div>
</div>
<script>
(function() {
const selectAllCheckbox = document.getElementById('selectAll');
const bucketCheckboxes = document.querySelectorAll('.bucket-checkbox:not(:disabled)');
const submitBtn = document.getElementById('submitBtn');
const modeSelect = document.getElementById('mode');
const bidirWarning = document.getElementById('bidirWarning');
function updateBidirWarning() {
if (modeSelect && bidirWarning) {
if (modeSelect.value === 'bidirectional') {
bidirWarning.classList.remove('d-none');
} else {
bidirWarning.classList.add('d-none');
}
}
}
if (modeSelect) {
modeSelect.addEventListener('change', updateBidirWarning);
updateBidirWarning();
}
function updateSubmitButton() {
const checkedCount = document.querySelectorAll('.bucket-checkbox:checked').length;
if (submitBtn) {
submitBtn.disabled = checkedCount === 0;
const text = checkedCount > 0
? `Create ${checkedCount} Replication Rule${checkedCount > 1 ? 's' : ''}`
: 'Create Replication Rules';
submitBtn.innerHTML = `
<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>
${text}
`;
}
}
function updateSelectAll() {
if (selectAllCheckbox && bucketCheckboxes.length > 0) {
const allChecked = Array.from(bucketCheckboxes).every(cb => cb.checked);
const someChecked = Array.from(bucketCheckboxes).some(cb => cb.checked);
selectAllCheckbox.checked = allChecked;
selectAllCheckbox.indeterminate = someChecked && !allChecked;
}
}
if (selectAllCheckbox) {
selectAllCheckbox.addEventListener('change', function() {
bucketCheckboxes.forEach(cb => {
cb.checked = this.checked;
});
updateSubmitButton();
});
}
bucketCheckboxes.forEach(cb => {
cb.addEventListener('change', function() {
updateSelectAll();
updateSubmitButton();
});
});
updateSelectAll();
updateSubmitButton();
})();
</script>
{% endblock %}

742
templates/sites.html Normal file
View File

@@ -0,0 +1,742 @@
{% extends "base.html" %}
{% block title %}Sites - S3 Compatible Storage{% endblock %}
{% block content %}
<div class="page-header d-flex justify-content-between align-items-center mb-4">
<div>
<p class="text-uppercase text-muted small mb-1">Geo-Distribution</p>
<h1 class="h3 mb-1 d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="28" height="28" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
Site Registry
</h1>
<p class="text-muted mb-0 mt-1">Configure this site's identity and manage peer sites for geo-distribution.</p>
</div>
<div class="d-none d-md-block">
<span class="badge bg-primary bg-opacity-10 text-primary fs-6 px-3 py-2">
{{ peers|length }} peer{{ 's' if peers|length != 1 else '' }}
</span>
</div>
</div>
<div class="row g-4">
<div class="col-lg-4 col-md-5">
<div class="card shadow-sm border-0 mb-4" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<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 16s6-5.686 6-10A6 6 0 0 0 2 6c0 4.314 6 10 6 10zm0-7a3 3 0 1 1 0-6 3 3 0 0 1 0 6z"/>
</svg>
Local Site Identity
</h5>
<p class="text-muted small mb-0">This site's configuration</p>
</div>
<div class="card-body px-4 pb-4">
<form method="POST" action="{{ url_for('ui.update_local_site') }}">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="mb-3">
<label for="site_id" class="form-label fw-medium">Site ID</label>
<input type="text" class="form-control" id="site_id" name="site_id" required
value="{{ local_site.site_id if local_site else config_site_id or '' }}"
placeholder="us-west-1">
<div class="form-text">Unique identifier for this site</div>
</div>
<div class="mb-3">
<label for="endpoint" class="form-label fw-medium">Endpoint URL</label>
<input type="url" class="form-control" id="endpoint" name="endpoint"
value="{{ local_site.endpoint if local_site else config_site_endpoint or '' }}"
placeholder="https://s3.us-west-1.example.com">
<div class="form-text">Public URL for this site</div>
</div>
<div class="mb-3">
<label for="region" class="form-label fw-medium">Region</label>
<input type="text" class="form-control" id="region" name="region"
value="{{ local_site.region if local_site else config_site_region }}">
</div>
<div class="row mb-3">
<div class="col-6">
<label for="priority" class="form-label fw-medium">Priority</label>
<input type="number" class="form-control" id="priority" name="priority"
value="{{ local_site.priority if local_site else 100 }}" min="0">
<div class="form-text">Lower = preferred</div>
</div>
<div class="col-6">
<label for="display_name" class="form-label fw-medium">Display Name</label>
<input type="text" class="form-control" id="display_name" name="display_name"
value="{{ local_site.display_name if local_site else '' }}"
placeholder="US West Primary">
</div>
</div>
<div class="d-grid">
<button type="submit" class="btn btn-primary">
<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 Local Site
</button>
</div>
</form>
</div>
</div>
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 2a.5.5 0 0 1 .5.5v5h5a.5.5 0 0 1 0 1h-5v5a.5.5 0 0 1-1 0v-5h-5a.5.5 0 0 1 0-1h5v-5A.5.5 0 0 1 8 2Z"/>
</svg>
Add Peer Site
</h5>
<p class="text-muted small mb-0">Register a remote site</p>
</div>
<div class="card-body px-4 pb-4">
<form method="POST" action="{{ url_for('ui.add_peer_site') }}">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="mb-3">
<label for="peer_site_id" class="form-label fw-medium">Site ID</label>
<input type="text" class="form-control" id="peer_site_id" name="site_id" required placeholder="us-east-1">
</div>
<div class="mb-3">
<label for="peer_endpoint" class="form-label fw-medium">Endpoint URL</label>
<input type="url" class="form-control" id="peer_endpoint" name="endpoint" required placeholder="https://s3.us-east-1.example.com">
</div>
<div class="mb-3">
<label for="peer_region" class="form-label fw-medium">Region</label>
<input type="text" class="form-control" id="peer_region" name="region" value="us-east-1">
</div>
<div class="row mb-3">
<div class="col-6">
<label for="peer_priority" class="form-label fw-medium">Priority</label>
<input type="number" class="form-control" id="peer_priority" name="priority" value="100" min="0">
</div>
<div class="col-6">
<label for="peer_display_name" class="form-label fw-medium">Display Name</label>
<input type="text" class="form-control" id="peer_display_name" name="display_name" placeholder="US East DR">
</div>
</div>
<div class="mb-3">
<label for="peer_connection_id" class="form-label fw-medium">Connection</label>
<select class="form-select" id="peer_connection_id" name="connection_id">
<option value="">No connection</option>
{% for conn in connections %}
<option value="{{ conn.id }}">{{ conn.name }} ({{ conn.endpoint_url }})</option>
{% endfor %}
</select>
<div class="form-text">Link to a remote connection for health checks</div>
</div>
<div class="d-grid">
<button type="submit" class="btn btn-primary">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 2a.5.5 0 0 1 .5.5v5h5a.5.5 0 0 1 0 1h-5v5a.5.5 0 0 1-1 0v-5h-5a.5.5 0 0 1 0-1h5v-5A.5.5 0 0 1 8 2Z"/>
</svg>
Add Peer Site
</button>
</div>
</form>
</div>
</div>
</div>
<div class="col-lg-8 col-md-7">
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4 d-flex justify-content-between align-items-center">
<div>
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M6 3.5A1.5 1.5 0 0 1 7.5 2h1A1.5 1.5 0 0 1 10 3.5v1A1.5 1.5 0 0 1 8.5 6v1H14a.5.5 0 0 1 .5.5v1a.5.5 0 0 1-1 0V8h-5v.5a.5.5 0 0 1-1 0V8h-5v.5a.5.5 0 0 1-1 0v-1A.5.5 0 0 1 2 7h5.5V6A1.5 1.5 0 0 1 6 4.5v-1zM8.5 5a.5.5 0 0 0 .5-.5v-1a.5.5 0 0 0-.5-.5h-1a.5.5 0 0 0-.5.5v1a.5.5 0 0 0 .5.5h1zM0 11.5A1.5 1.5 0 0 1 1.5 10h1A1.5 1.5 0 0 1 4 11.5v1A1.5 1.5 0 0 1 2.5 14h-1A1.5 1.5 0 0 1 0 12.5v-1zm1.5-.5a.5.5 0 0 0-.5.5v1a.5.5 0 0 0 .5.5h1a.5.5 0 0 0 .5-.5v-1a.5.5 0 0 0-.5-.5h-1zm4.5.5A1.5 1.5 0 0 1 7.5 10h1a1.5 1.5 0 0 1 1.5 1.5v1A1.5 1.5 0 0 1 8.5 14h-1A1.5 1.5 0 0 1 6 12.5v-1zm1.5-.5a.5.5 0 0 0-.5.5v1a.5.5 0 0 0 .5.5h1a.5.5 0 0 0 .5-.5v-1a.5.5 0 0 0-.5-.5h-1zm4.5.5a1.5 1.5 0 0 1 1.5-1.5h1a1.5 1.5 0 0 1 1.5 1.5v1a1.5 1.5 0 0 1-1.5 1.5h-1a1.5 1.5 0 0 1-1.5-1.5v-1zm1.5-.5a.5.5 0 0 0-.5.5v1a.5.5 0 0 0 .5.5h1a.5.5 0 0 0 .5-.5v-1a.5.5 0 0 0-.5-.5h-1z"/>
</svg>
Peer Sites
</h5>
<p class="text-muted small mb-0">Known remote sites in the cluster</p>
</div>
</div>
<div class="card-body px-4 pb-4">
{% if peers %}
<div class="table-responsive">
<table class="table table-hover align-middle mb-0">
<thead class="table-light">
<tr>
<th scope="col" style="width: 50px;">Health</th>
<th scope="col">Site ID</th>
<th scope="col">Endpoint</th>
<th scope="col">Region</th>
<th scope="col">Priority</th>
<th scope="col">Sync Status</th>
<th scope="col" class="text-end">Actions</th>
</tr>
</thead>
<tbody>
{% for item in peers_with_stats %}
{% set peer = item.peer %}
<tr data-site-id="{{ peer.site_id }}">
<td class="text-center">
<span class="peer-health-status" data-site-id="{{ peer.site_id }}" title="{% if peer.is_healthy == true %}Healthy{% elif peer.is_healthy == false %}Unhealthy{% else %}Unknown{% endif %}">
{% if peer.is_healthy == true %}
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-success" viewBox="0 0 16 16">
<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zm-3.97-3.03a.75.75 0 0 0-1.08.022L7.477 9.417 5.384 7.323a.75.75 0 0 0-1.06 1.06L6.97 11.03a.75.75 0 0 0 1.079-.02l3.992-4.99a.75.75 0 0 0-.01-1.05z"/>
</svg>
{% elif peer.is_healthy == false %}
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-danger" viewBox="0 0 16 16">
<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zM5.354 4.646a.5.5 0 1 0-.708.708L7.293 8l-2.647 2.646a.5.5 0 0 0 .708.708L8 8.707l2.646 2.647a.5.5 0 0 0 .708-.708L8.707 8l2.647-2.646a.5.5 0 0 0-.708-.708L8 7.293 5.354 4.646z"/>
</svg>
{% else %}
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/>
<path d="M5.255 5.786a.237.237 0 0 0 .241.247h.825c.138 0 .248-.113.266-.25.09-.656.54-1.134 1.342-1.134.686 0 1.314.343 1.314 1.168 0 .635-.374.927-.965 1.371-.673.489-1.206 1.06-1.168 1.987l.003.217a.25.25 0 0 0 .25.246h.811a.25.25 0 0 0 .25-.25v-.105c0-.718.273-.927 1.01-1.486.609-.463 1.244-.977 1.244-2.056 0-1.511-1.276-2.241-2.673-2.241-1.267 0-2.655.59-2.75 2.286zm1.557 5.763c0 .533.425.927 1.01.927.609 0 1.028-.394 1.028-.927 0-.552-.42-.94-1.029-.94-.584 0-1.009.388-1.009.94z"/>
</svg>
{% endif %}
</span>
</td>
<td>
<div class="d-flex align-items-center gap-2">
<div class="peer-icon">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5z"/>
</svg>
</div>
<div>
<span class="fw-medium">{{ peer.display_name or peer.site_id }}</span>
{% if peer.display_name and peer.display_name != peer.site_id %}
<br><small class="text-muted">{{ peer.site_id }}</small>
{% endif %}
</div>
</div>
</td>
<td>
<span class="text-muted small text-truncate d-inline-block" style="max-width: 180px;" title="{{ peer.endpoint }}">{{ peer.endpoint }}</span>
</td>
<td><span class="badge bg-primary bg-opacity-10 text-primary">{{ peer.region }}</span></td>
<td><span class="badge bg-secondary bg-opacity-10 text-secondary">{{ peer.priority }}</span></td>
<td class="sync-stats-cell" data-site-id="{{ peer.site_id }}">
{% if item.has_connection %}
<div class="d-flex align-items-center gap-2">
<span class="badge bg-primary bg-opacity-10 text-primary">{{ item.buckets_syncing }} bucket{{ 's' if item.buckets_syncing != 1 else '' }}</span>
{% if item.has_bidirectional %}
<span class="bidir-status-icon" data-site-id="{{ peer.site_id }}" title="Bidirectional sync configured - click to verify">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="text-info" viewBox="0 0 16 16" style="cursor: pointer;">
<path fill-rule="evenodd" d="M1 11.5a.5.5 0 0 0 .5.5h11.793l-3.147 3.146a.5.5 0 0 0 .708.708l4-4a.5.5 0 0 0 0-.708l-4-4a.5.5 0 0 0-.708.708L13.293 11H1.5a.5.5 0 0 0-.5.5zm14-7a.5.5 0 0 1-.5.5H2.707l3.147 3.146a.5.5 0 1 1-.708.708l-4-4a.5.5 0 0 1 0-.708l4-4a.5.5 0 1 1 .708.708L2.707 4H14.5a.5.5 0 0 1 .5.5z"/>
</svg>
</span>
{% endif %}
{% if item.buckets_syncing > 0 %}
<button type="button" class="btn btn-sm btn-outline-secondary btn-load-stats py-0 px-1"
data-site-id="{{ peer.site_id }}" title="Load sync details">
<svg xmlns="http://www.w3.org/2000/svg" width="12" height="12" fill="currentColor" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 3a5 5 0 1 0 4.546 2.914.5.5 0 0 1 .908-.417A6 6 0 1 1 8 2v1z"/>
<path d="M8 4.466V.534a.25.25 0 0 1 .41-.192l2.36 1.966c.12.1.12.284 0 .384L8.41 4.658A.25.25 0 0 1 8 4.466z"/>
</svg>
</button>
{% endif %}
</div>
<div class="sync-stats-detail d-none mt-2 small" id="stats-{{ peer.site_id }}">
<span class="spinner-border spinner-border-sm text-muted" style="width: 12px; height: 12px;"></span>
</div>
{% else %}
<span class="text-muted small">No connection</span>
{% endif %}
</td>
<td class="text-end">
<div class="btn-group btn-group-sm" role="group">
<a href="{{ url_for('ui.replication_wizard', site_id=peer.site_id) }}"
class="btn btn-outline-primary {% if not item.has_connection %}disabled{% endif %}"
title="Set up replication">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" 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>
</a>
<button type="button" class="btn btn-outline-info btn-check-bidir {% if not item.has_connection %}disabled{% endif %}"
data-site-id="{{ peer.site_id }}"
data-display-name="{{ peer.display_name or peer.site_id }}"
title="Check bidirectional sync status">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M1 11.5a.5.5 0 0 0 .5.5h11.793l-3.147 3.146a.5.5 0 0 0 .708.708l4-4a.5.5 0 0 0 0-.708l-4-4a.5.5 0 0 0-.708.708L13.293 11H1.5a.5.5 0 0 0-.5.5zm14-7a.5.5 0 0 1-.5.5H2.707l3.147 3.146a.5.5 0 1 1-.708.708l-4-4a.5.5 0 0 1 0-.708l4-4a.5.5 0 1 1 .708.708L2.707 4H14.5a.5.5 0 0 1 .5.5z"/>
</svg>
</button>
<button type="button" class="btn btn-outline-secondary btn-check-health"
data-site-id="{{ peer.site_id }}"
title="Check health">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" viewBox="0 0 16 16">
<path d="M11.251.068a.5.5 0 0 1 .227.58L9.677 6.5H13a.5.5 0 0 1 .364.843l-8 8.5a.5.5 0 0 1-.842-.49L6.323 9.5H3a.5.5 0 0 1-.364-.843l8-8.5a.5.5 0 0 1 .615-.09z"/>
</svg>
</button>
<button type="button" class="btn btn-outline-secondary"
data-bs-toggle="modal"
data-bs-target="#editPeerModal"
data-site-id="{{ peer.site_id }}"
data-endpoint="{{ peer.endpoint }}"
data-region="{{ peer.region }}"
data-priority="{{ peer.priority }}"
data-display-name="{{ peer.display_name }}"
data-connection-id="{{ peer.connection_id or '' }}"
title="Edit peer">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" 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>
</button>
<button type="button" class="btn btn-outline-danger"
data-bs-toggle="modal"
data-bs-target="#deletePeerModal"
data-site-id="{{ peer.site_id }}"
data-display-name="{{ peer.display_name or peer.site_id }}"
title="Delete peer">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
</button>
</div>
</td>
</tr>
{% endfor %}
</tbody>
</table>
</div>
{% else %}
<div class="empty-state text-center py-5">
<div class="empty-state-icon mx-auto mb-3">
<svg xmlns="http://www.w3.org/2000/svg" width="48" height="48" fill="currentColor" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472z"/>
</svg>
</div>
<h5 class="fw-semibold mb-2">No peer sites yet</h5>
<p class="text-muted mb-0">Add peer sites to enable geo-distribution and site-to-site replication.</p>
</div>
{% endif %}
</div>
</div>
</div>
</div>
<div class="modal fade" id="editPeerModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h5 class="modal-title 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="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.293l6.5-6.5zm-9.761 5.175-.106.106-1.528 3.821 3.821-1.528.106-.106A.5.5 0 0 1 5 12.5V12h-.5a.5.5 0 0 1-.5-.5V11h-.5a.5.5 0 0 1-.468-.325z"/>
</svg>
Edit Peer Site
</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<form method="POST" id="editPeerForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="modal-body">
<div class="mb-3">
<label class="form-label fw-medium">Site ID</label>
<input type="text" class="form-control" id="edit_site_id" readonly>
</div>
<div class="mb-3">
<label for="edit_endpoint" class="form-label fw-medium">Endpoint URL</label>
<input type="url" class="form-control" id="edit_endpoint" name="endpoint" required>
</div>
<div class="mb-3">
<label for="edit_region" class="form-label fw-medium">Region</label>
<input type="text" class="form-control" id="edit_region" name="region" required>
</div>
<div class="row mb-3">
<div class="col-6">
<label for="edit_priority" class="form-label fw-medium">Priority</label>
<input type="number" class="form-control" id="edit_priority" name="priority" min="0">
</div>
<div class="col-6">
<label for="edit_display_name" class="form-label fw-medium">Display Name</label>
<input type="text" class="form-control" id="edit_display_name" name="display_name">
</div>
</div>
<div class="mb-3">
<label for="edit_connection_id" class="form-label fw-medium">Connection</label>
<select class="form-select" id="edit_connection_id" name="connection_id">
<option value="">No connection</option>
{% for conn in connections %}
<option value="{{ conn.id }}">{{ conn.name }} ({{ conn.endpoint_url }})</option>
{% endfor %}
</select>
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Cancel</button>
<button type="submit" class="btn btn-primary">
<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
</button>
</div>
</form>
</div>
</div>
</div>
<div class="modal fade" id="deletePeerModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h5 class="modal-title fw-semibold">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-danger" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
Delete Peer Site
</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<div class="modal-body">
<p>Are you sure you want to delete <strong id="deletePeerName"></strong>?</p>
<div class="alert alert-warning d-flex align-items-start small" role="alert">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="flex-shrink-0 me-2 mt-0" viewBox="0 0 16 16">
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm.93-9.412-1 4.705c-.07.34.029.533.304.533.194 0 .487-.07.686-.246l-.088.416c-.287.346-.92.598-1.465.598-.703 0-1.002-.422-.808-1.319l.738-3.468c.064-.293.006-.399-.287-.47l-.451-.081.082-.381 2.29-.287zM8 5.5a1 1 0 1 1 0-2 1 1 0 0 1 0 2z"/>
</svg>
<div>This will remove the peer from the site registry. Any site sync configurations may be affected.</div>
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Cancel</button>
<form method="POST" id="deletePeerForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<button type="submit" class="btn btn-danger">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
Delete
</button>
</form>
</div>
</div>
</div>
</div>
<div class="modal fade" id="bidirStatusModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered modal-lg">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h5 class="modal-title fw-semibold">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-info me-2" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M1 11.5a.5.5 0 0 0 .5.5h11.793l-3.147 3.146a.5.5 0 0 0 .708.708l4-4a.5.5 0 0 0 0-.708l-4-4a.5.5 0 0 0-.708.708L13.293 11H1.5a.5.5 0 0 0-.5.5zm14-7a.5.5 0 0 1-.5.5H2.707l3.147 3.146a.5.5 0 1 1-.708.708l-4-4a.5.5 0 0 1 0-.708l4-4a.5.5 0 1 1 .708.708L2.707 4H14.5a.5.5 0 0 1 .5.5z"/>
</svg>
Bidirectional Sync Status
</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<div class="modal-body">
<div id="bidirStatusContent">
<div class="text-center py-4">
<span class="spinner-border text-primary" role="status"></span>
<p class="text-muted mt-2 mb-0">Checking configuration...</p>
</div>
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Close</button>
<a href="#" id="bidirWizardLink" class="btn btn-primary d-none">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M9.828.722a.5.5 0 0 1 .354.146l4.95 4.95a.5.5 0 0 1 0 .707c-.48.48-1.072.588-1.503.588-.177 0-.335-.018-.46-.039l-3.134 3.134a5.927 5.927 0 0 1 .16 1.013c.046.702-.032 1.687-.72 2.375a.5.5 0 0 1-.707 0l-2.829-2.828-3.182 3.182c-.195.195-1.219.902-1.414.707-.195-.195.512-1.22.707-1.414l3.182-3.182-2.828-2.829a.5.5 0 0 1 0-.707c.688-.688 1.673-.767 2.375-.72a5.922 5.922 0 0 1 1.013.16l3.134-3.133a2.772 2.772 0 0 1-.04-.461c0-.43.108-1.022.589-1.503a.5.5 0 0 1 .353-.146z"/>
</svg>
Run Setup Wizard
</a>
</div>
</div>
</div>
</div>
<script>
(function() {
const editPeerModal = document.getElementById('editPeerModal');
if (editPeerModal) {
editPeerModal.addEventListener('show.bs.modal', function (event) {
const button = event.relatedTarget;
const siteId = button.getAttribute('data-site-id');
const endpoint = button.getAttribute('data-endpoint');
const region = button.getAttribute('data-region');
const priority = button.getAttribute('data-priority');
const displayName = button.getAttribute('data-display-name');
const connectionId = button.getAttribute('data-connection-id');
document.getElementById('edit_site_id').value = siteId;
document.getElementById('edit_endpoint').value = endpoint;
document.getElementById('edit_region').value = region;
document.getElementById('edit_priority').value = priority;
document.getElementById('edit_display_name').value = displayName;
document.getElementById('edit_connection_id').value = connectionId;
document.getElementById('editPeerForm').action = '/ui/sites/peers/' + encodeURIComponent(siteId) + '/update';
});
}
const deletePeerModal = document.getElementById('deletePeerModal');
if (deletePeerModal) {
deletePeerModal.addEventListener('show.bs.modal', function (event) {
const button = event.relatedTarget;
const siteId = button.getAttribute('data-site-id');
const displayName = button.getAttribute('data-display-name');
document.getElementById('deletePeerName').textContent = displayName;
document.getElementById('deletePeerForm').action = '/ui/sites/peers/' + encodeURIComponent(siteId) + '/delete';
});
}
document.querySelectorAll('.btn-check-health').forEach(function(btn) {
btn.addEventListener('click', function() {
const siteId = this.getAttribute('data-site-id');
const statusSpan = document.querySelector('.peer-health-status[data-site-id="' + siteId + '"]');
statusSpan.innerHTML = '<span class="spinner-border spinner-border-sm text-muted" role="status" style="width: 14px; height: 14px;"></span>';
fetch('/ui/sites/peers/' + encodeURIComponent(siteId) + '/health')
.then(response => response.json())
.then(data => {
if (data.is_healthy) {
statusSpan.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-success" viewBox="0 0 16 16"><path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zm-3.97-3.03a.75.75 0 0 0-1.08.022L7.477 9.417 5.384 7.323a.75.75 0 0 0-1.06 1.06L6.97 11.03a.75.75 0 0 0 1.079-.02l3.992-4.99a.75.75 0 0 0-.01-1.05z"/></svg>';
statusSpan.title = 'Healthy';
if (window.showToast) window.showToast('Peer site is healthy', 'Health Check', 'success');
} else {
statusSpan.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-danger" viewBox="0 0 16 16"><path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zM5.354 4.646a.5.5 0 1 0-.708.708L7.293 8l-2.647 2.646a.5.5 0 0 0 .708.708L8 8.707l2.646 2.647a.5.5 0 0 0 .708-.708L8.707 8l2.647-2.646a.5.5 0 0 0-.708-.708L8 7.293 5.354 4.646z"/></svg>';
statusSpan.title = 'Unhealthy' + (data.error ? ': ' + data.error : '');
if (window.showToast) window.showToast(data.error || 'Peer site is unhealthy', 'Health Check', 'error');
}
})
.catch(err => {
statusSpan.innerHTML = '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-muted" viewBox="0 0 16 16"><path d="M8 15A7 7 0 1 1 8 1a7 7 0 0 1 0 14zm0 1A8 8 0 1 0 8 0a8 8 0 0 0 0 16z"/><path d="M5.255 5.786a.237.237 0 0 0 .241.247h.825c.138 0 .248-.113.266-.25.09-.656.54-1.134 1.342-1.134.686 0 1.314.343 1.314 1.168 0 .635-.374.927-.965 1.371-.673.489-1.206 1.06-1.168 1.987l.003.217a.25.25 0 0 0 .25.246h.811a.25.25 0 0 0 .25-.25v-.105c0-.718.273-.927 1.01-1.486.609-.463 1.244-.977 1.244-2.056 0-1.511-1.276-2.241-2.673-2.241-1.267 0-2.655.59-2.75 2.286zm1.557 5.763c0 .533.425.927 1.01.927.609 0 1.028-.394 1.028-.927 0-.552-.42-.94-1.029-.94-.584 0-1.009.388-1.009.94z"/></svg>';
statusSpan.title = 'Check failed';
if (window.showToast) window.showToast('Failed to check health', 'Health Check', 'error');
});
});
});
document.querySelectorAll('.btn-load-stats').forEach(function(btn) {
btn.addEventListener('click', function() {
const siteId = this.getAttribute('data-site-id');
const detailDiv = document.getElementById('stats-' + siteId);
if (!detailDiv) return;
detailDiv.classList.remove('d-none');
detailDiv.innerHTML = '<span class="spinner-border spinner-border-sm text-muted" style="width: 12px; height: 12px;"></span> Loading...';
fetch('/ui/sites/peers/' + encodeURIComponent(siteId) + '/sync-stats')
.then(response => response.json())
.then(data => {
if (data.error) {
detailDiv.innerHTML = '<span class="text-danger">' + data.error + '</span>';
} else {
const lastSync = data.last_sync_at
? new Date(data.last_sync_at * 1000).toLocaleString()
: 'Never';
detailDiv.innerHTML = `
<div class="d-flex flex-wrap gap-2 mb-1">
<span class="text-success"><strong>${data.objects_synced}</strong> synced</span>
<span class="text-warning"><strong>${data.objects_pending}</strong> pending</span>
<span class="text-danger"><strong>${data.objects_failed}</strong> failed</span>
</div>
<div class="text-muted" style="font-size: 0.75rem;">
Last sync: ${lastSync}
</div>
`;
}
})
.catch(err => {
detailDiv.innerHTML = '<span class="text-danger">Failed to load stats</span>';
});
});
});
document.querySelectorAll('.bidir-status-icon').forEach(function(icon) {
icon.addEventListener('click', function() {
const siteId = this.getAttribute('data-site-id');
const btn = document.querySelector('.btn-check-bidir[data-site-id="' + siteId + '"]');
if (btn) btn.click();
});
});
document.querySelectorAll('.btn-check-bidir').forEach(function(btn) {
btn.addEventListener('click', function() {
const siteId = this.getAttribute('data-site-id');
const displayName = this.getAttribute('data-display-name');
const modal = new bootstrap.Modal(document.getElementById('bidirStatusModal'));
const contentDiv = document.getElementById('bidirStatusContent');
const wizardLink = document.getElementById('bidirWizardLink');
contentDiv.innerHTML = `
<div class="text-center py-4">
<span class="spinner-border text-primary" role="status"></span>
<p class="text-muted mt-2 mb-0">Checking bidirectional configuration with ${displayName}...</p>
</div>
`;
wizardLink.classList.add('d-none');
modal.show();
fetch('/ui/sites/peers/' + encodeURIComponent(siteId) + '/bidirectional-status')
.then(response => response.json())
.then(data => {
let html = '';
if (data.is_fully_configured) {
html += `
<div class="alert alert-success d-flex align-items-center mb-4" role="alert">
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" fill="currentColor" class="flex-shrink-0 me-2" viewBox="0 0 16 16">
<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zm-3.97-3.03a.75.75 0 0 0-1.08.022L7.477 9.417 5.384 7.323a.75.75 0 0 0-1.06 1.06L6.97 11.03a.75.75 0 0 0 1.079-.02l3.992-4.99a.75.75 0 0 0-.01-1.05z"/>
</svg>
<div>
<strong>Bidirectional sync is fully configured!</strong><br>
<small>Both sites are set up to sync data in both directions.</small>
</div>
</div>
`;
} else if (data.issues && data.issues.length > 0) {
const errors = data.issues.filter(i => i.severity === 'error');
const warnings = data.issues.filter(i => i.severity === 'warning');
if (errors.length > 0) {
html += `
<div class="alert alert-danger mb-3" role="alert">
<h6 class="alert-heading fw-bold mb-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M16 8A8 8 0 1 1 0 8a8 8 0 0 1 16 0zM5.354 4.646a.5.5 0 1 0-.708.708L7.293 8l-2.647 2.646a.5.5 0 0 0 .708.708L8 8.707l2.646 2.647a.5.5 0 0 0 .708-.708L8.707 8l2.647-2.646a.5.5 0 0 0-.708-.708L8 7.293 5.354 4.646z"/>
</svg>
Configuration Errors
</h6>
<ul class="mb-0 ps-3">
`;
errors.forEach(issue => {
html += `<li><strong>${issue.code}:</strong> ${issue.message}</li>`;
});
html += '</ul></div>';
}
if (warnings.length > 0) {
html += `
<div class="alert alert-warning mb-3" role="alert">
<h6 class="alert-heading fw-bold mb-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M8.982 1.566a1.13 1.13 0 0 0-1.96 0L.165 13.233c-.457.778.091 1.767.98 1.767h13.713c.889 0 1.438-.99.98-1.767L8.982 1.566zM8 5c.535 0 .954.462.9.995l-.35 3.507a.552.552 0 0 1-1.1 0L7.1 5.995A.905.905 0 0 1 8 5zm.002 6a1 1 0 1 1 0 2 1 1 0 0 1 0-2z"/>
</svg>
Warnings
</h6>
<ul class="mb-0 ps-3">
`;
warnings.forEach(issue => {
html += `<li><strong>${issue.code}:</strong> ${issue.message}</li>`;
});
html += '</ul></div>';
}
}
html += '<div class="row g-3">';
html += `
<div class="col-md-6">
<div class="card h-100">
<div class="card-header bg-light py-2">
<strong>This Site (Local)</strong>
</div>
<div class="card-body small">
<p class="mb-1"><strong>Site ID:</strong> ${data.local_site_id || '<span class="text-danger">Not configured</span>'}</p>
<p class="mb-1"><strong>Endpoint:</strong> ${data.local_endpoint || '<span class="text-danger">Not configured</span>'}</p>
<p class="mb-1"><strong>Site Sync Worker:</strong> ${data.local_site_sync_enabled ? '<span class="text-success">Enabled</span>' : '<span class="text-warning">Disabled</span>'}</p>
<p class="mb-0"><strong>Bidirectional Rules:</strong> ${data.local_bidirectional_rules ? data.local_bidirectional_rules.length : 0}</p>
</div>
</div>
</div>
`;
if (data.remote_status) {
const rs = data.remote_status;
html += `
<div class="col-md-6">
<div class="card h-100">
<div class="card-header bg-light py-2">
<strong>Remote Site (${displayName})</strong>
</div>
<div class="card-body small">
`;
if (rs.admin_access_denied) {
html += '<p class="text-warning mb-0">Admin access denied - cannot verify remote configuration</p>';
} else if (rs.reachable === false) {
html += '<p class="text-danger mb-0">Could not reach remote admin API</p>';
} else {
html += `
<p class="mb-1"><strong>Has Peer Entry for Us:</strong> ${rs.has_peer_for_us ? '<span class="text-success">Yes</span>' : '<span class="text-danger">No</span>'}</p>
<p class="mb-1"><strong>Connection Configured:</strong> ${rs.peer_connection_configured ? '<span class="text-success">Yes</span>' : '<span class="text-danger">No</span>'}</p>
`;
}
html += '</div></div></div>';
} else {
html += `
<div class="col-md-6">
<div class="card h-100">
<div class="card-header bg-light py-2">
<strong>Remote Site (${displayName})</strong>
</div>
<div class="card-body small">
<p class="text-muted mb-0">Could not check remote status</p>
</div>
</div>
</div>
`;
}
html += '</div>';
if (data.local_bidirectional_rules && data.local_bidirectional_rules.length > 0) {
html += `
<div class="mt-3">
<h6 class="fw-semibold">Local Bidirectional Rules</h6>
<table class="table table-sm table-bordered mb-0">
<thead class="table-light">
<tr>
<th>Source Bucket</th>
<th>Target Bucket</th>
<th>Status</th>
</tr>
</thead>
<tbody>
`;
data.local_bidirectional_rules.forEach(rule => {
html += `
<tr>
<td>${rule.bucket_name}</td>
<td>${rule.target_bucket}</td>
<td>${rule.enabled ? '<span class="badge bg-success">Enabled</span>' : '<span class="badge bg-secondary">Disabled</span>'}</td>
</tr>
`;
});
html += '</tbody></table></div>';
}
if (!data.is_fully_configured) {
html += `
<div class="alert alert-info mt-3 mb-0" role="alert">
<h6 class="alert-heading fw-bold">How to Fix</h6>
<ol class="mb-0 ps-3">
<li>Ensure this site has a Site ID and Endpoint URL configured</li>
<li>On the remote site, register this site as a peer with a connection</li>
<li>Create bidirectional replication rules on both sites</li>
<li>Enable SITE_SYNC_ENABLED=true on both sites</li>
</ol>
</div>
`;
const blockingErrors = ['NO_CONNECTION', 'CONNECTION_NOT_FOUND', 'REMOTE_UNREACHABLE', 'ENDPOINT_NOT_ALLOWED'];
const hasBlockingError = data.issues && data.issues.some(i => blockingErrors.includes(i.code));
if (!hasBlockingError) {
wizardLink.href = '/ui/sites/peers/' + encodeURIComponent(siteId) + '/replication-wizard';
wizardLink.classList.remove('d-none');
}
}
contentDiv.innerHTML = html;
})
.catch(err => {
contentDiv.innerHTML = `
<div class="alert alert-danger" role="alert">
<strong>Error:</strong> Failed to check bidirectional status. ${err.message || ''}
</div>
`;
});
});
});
})();
</script>
{% endblock %}

View File

@@ -0,0 +1,287 @@
{% extends "base.html" %}
{% block title %}Website Domains - MyFSIO Console{% endblock %}
{% block content %}
<div class="page-header d-flex justify-content-between align-items-center mb-4">
<div>
<p class="text-uppercase text-muted small mb-1">Website Hosting</p>
<h1 class="h3 mb-1 d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="28" height="28" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
Domain Mappings
</h1>
<p class="text-muted mb-0 mt-1">Map custom domains to buckets for static website hosting.</p>
</div>
<div class="d-none d-md-block">
<span class="badge bg-primary bg-opacity-10 text-primary fs-6 px-3 py-2">
{{ mappings|length }} mapping{{ 's' if mappings|length != 1 else '' }}
</span>
</div>
</div>
<div class="row g-4">
<div class="col-lg-4 col-md-5">
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4">
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-primary" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 2a.5.5 0 0 1 .5.5v5h5a.5.5 0 0 1 0 1h-5v5a.5.5 0 0 1-1 0v-5h-5a.5.5 0 0 1 0-1h5v-5A.5.5 0 0 1 8 2Z"/>
</svg>
Add Domain Mapping
</h5>
<p class="text-muted small mb-0">Point a custom domain to a bucket</p>
</div>
<div class="card-body px-4 pb-4">
<form method="POST" action="{{ url_for('ui.create_website_domain') }}" id="createDomainForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="mb-3">
<label for="domain" class="form-label fw-medium">Domain</label>
<input type="text" class="form-control" id="domain" name="domain" required placeholder="www.example.com">
<div class="form-text">The hostname that will serve website content.</div>
</div>
<div class="mb-3">
<label for="bucket" class="form-label fw-medium">Bucket</label>
{% if buckets %}
<select class="form-select" id="bucket" name="bucket" required>
<option value="" selected disabled>Select a bucket</option>
{% for b in buckets %}
<option value="{{ b }}">{{ b }}</option>
{% endfor %}
</select>
{% else %}
<input type="text" class="form-control" id="bucket" name="bucket" required placeholder="my-site-bucket">
{% endif %}
<div class="form-text">The bucket must have website hosting enabled.</div>
</div>
<div class="d-grid">
<button type="submit" class="btn btn-primary">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path fill-rule="evenodd" d="M8 2a.5.5 0 0 1 .5.5v5h5a.5.5 0 0 1 0 1h-5v5a.5.5 0 0 1-1 0v-5h-5a.5.5 0 0 1 0-1h5v-5A.5.5 0 0 1 8 2Z"/>
</svg>
Add Mapping
</button>
</div>
</form>
</div>
</div>
<div class="card shadow-sm border-0 mt-4" style="border-radius: 1rem;">
<div class="card-body px-4 py-3">
<h6 class="fw-semibold mb-2 d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm.93-9.412-1 4.705c-.07.34.029.533.304.533.194 0 .487-.07.686-.246l-.088.416c-.287.346-.92.598-1.465.598-.703 0-1.002-.422-.808-1.319l.738-3.468c.064-.293.006-.399-.287-.47l-.451-.081.082-.381 2.29-.287zM8 5.5a1 1 0 1 1 0-2 1 1 0 0 1 0 2z"/>
</svg>
How it works
</h6>
<ol class="small text-muted mb-0 ps-3">
<li class="mb-1">Enable website hosting on a bucket (Properties tab)</li>
<li class="mb-1">Create a domain mapping here</li>
<li>Point your DNS (A/CNAME) to this server</li>
</ol>
</div>
</div>
</div>
<div class="col-lg-8 col-md-7">
<div class="card shadow-sm border-0" style="border-radius: 1rem;">
<div class="card-header bg-transparent border-0 pt-4 pb-0 px-4 d-flex justify-content-between align-items-center">
<div>
<h5 class="fw-semibold d-flex align-items-center gap-2 mb-1">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M4.715 6.542 3.343 7.914a3 3 0 1 0 4.243 4.243l1.828-1.829A3 3 0 0 0 8.586 5.5L8 6.086a1.002 1.002 0 0 0-.154.199 2 2 0 0 1 .861 3.337L6.88 11.45a2 2 0 1 1-2.83-2.83l.793-.792a4.018 4.018 0 0 1-.128-1.287z"/>
<path d="M6.586 4.672A3 3 0 0 0 7.414 9.5l.775-.776a2 2 0 0 1-.896-3.346L9.12 3.55a2 2 0 1 1 2.83 2.83l-.793.792c.112.42.155.855.128 1.287l1.372-1.372a3 3 0 1 0-4.243-4.243L6.586 4.672z"/>
</svg>
Active Mappings
</h5>
<p class="text-muted small mb-0">Domains currently serving website content</p>
</div>
</div>
<div class="card-body px-4 pb-4">
{% if mappings %}
<div class="table-responsive">
<table class="table table-hover align-middle mb-0">
<thead class="table-light">
<tr>
<th scope="col">Domain</th>
<th scope="col">Bucket</th>
<th scope="col" class="text-end">Actions</th>
</tr>
</thead>
<tbody>
{% for m in mappings %}
<tr>
<td>
<div class="d-flex align-items-center gap-2">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
<code class="fw-medium">{{ m.domain }}</code>
</div>
</td>
<td><span class="badge bg-primary bg-opacity-10 text-primary">{{ m.bucket }}</span></td>
<td class="text-end">
<div class="btn-group btn-group-sm" role="group">
<button type="button" class="btn btn-outline-secondary"
data-bs-toggle="modal"
data-bs-target="#editDomainModal"
data-domain="{{ m.domain }}"
data-bucket="{{ m.bucket }}"
title="Edit mapping">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" 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>
</button>
<button type="button" class="btn btn-outline-danger"
data-bs-toggle="modal"
data-bs-target="#deleteDomainModal"
data-domain="{{ m.domain }}"
data-bucket="{{ m.bucket }}"
title="Delete mapping">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
</button>
</div>
</td>
</tr>
{% endfor %}
</tbody>
</table>
</div>
{% else %}
<div class="empty-state text-center py-5">
<div class="empty-state-icon mx-auto mb-3">
<svg xmlns="http://www.w3.org/2000/svg" width="48" height="48" fill="currentColor" class="text-muted" viewBox="0 0 16 16">
<path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8zm7.5-6.923c-.67.204-1.335.82-1.887 1.855A7.97 7.97 0 0 0 5.145 4H7.5V1.077zM4.09 4a9.267 9.267 0 0 1 .64-1.539 6.7 6.7 0 0 1 .597-.933A7.025 7.025 0 0 0 2.255 4H4.09zm-.582 3.5c.03-.877.138-1.718.312-2.5H1.674a6.958 6.958 0 0 0-.656 2.5h2.49zM4.847 5a12.5 12.5 0 0 0-.338 2.5H7.5V5H4.847zM8.5 5v2.5h2.99a12.495 12.495 0 0 0-.337-2.5H8.5zM4.51 8.5a12.5 12.5 0 0 0 .337 2.5H7.5V8.5H4.51zm3.99 0V11h2.653c.187-.765.306-1.608.338-2.5H8.5zM5.145 12c.138.386.295.744.468 1.068.552 1.035 1.218 1.65 1.887 1.855V12H5.145zm.182 2.472a6.696 6.696 0 0 1-.597-.933A9.268 9.268 0 0 1 4.09 12H2.255a7.024 7.024 0 0 0 3.072 2.472zM3.82 11a13.652 13.652 0 0 1-.312-2.5h-2.49c.062.89.291 1.733.656 2.5H3.82zm6.853 3.472A7.024 7.024 0 0 0 13.745 12H11.91a9.27 9.27 0 0 1-.64 1.539 6.688 6.688 0 0 1-.597.933zM8.5 12v2.923c.67-.204 1.335-.82 1.887-1.855.173-.324.33-.682.468-1.068H8.5zm3.68-1h2.146c.365-.767.594-1.61.656-2.5h-2.49a13.65 13.65 0 0 1-.312 2.5zm2.802-3.5a6.959 6.959 0 0 0-.656-2.5H12.18c.174.782.282 1.623.312 2.5h2.49zM11.27 2.461c.247.464.462.98.64 1.539h1.835a7.024 7.024 0 0 0-3.072-2.472c.218.284.418.598.597.933zM10.855 4a7.966 7.966 0 0 0-.468-1.068C9.835 1.897 9.17 1.282 8.5 1.077V4h2.355z"/>
</svg>
</div>
<h5 class="fw-semibold mb-2">No domain mappings yet</h5>
<p class="text-muted mb-0">Add your first domain mapping to serve a bucket as a static website.</p>
</div>
{% endif %}
</div>
</div>
</div>
</div>
<div class="modal fade" id="editDomainModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h5 class="modal-title 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="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.293l6.5-6.5zm-9.761 5.175-.106.106-1.528 3.821 3.821-1.528.106-.106A.5.5 0 0 1 5 12.5V12h-.5a.5.5 0 0 1-.5-.5V11h-.5a.5.5 0 0 1-.468-.325z"/>
</svg>
Edit Domain Mapping
</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<form method="POST" id="editDomainForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="modal-body">
<div class="mb-3">
<label class="form-label fw-medium">Domain</label>
<input type="text" class="form-control" id="editDomainName" disabled>
</div>
<div class="mb-3">
<label for="editBucket" class="form-label fw-medium">Bucket</label>
{% if buckets %}
<select class="form-select" id="editBucket" name="bucket" required>
{% for b in buckets %}
<option value="{{ b }}">{{ b }}</option>
{% endfor %}
</select>
{% else %}
<input type="text" class="form-control" id="editBucket" name="bucket" required>
{% endif %}
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Cancel</button>
<button type="submit" class="btn btn-primary">
<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
</button>
</div>
</form>
</div>
</div>
</div>
<div class="modal fade" id="deleteDomainModal" tabindex="-1" aria-hidden="true">
<div class="modal-dialog modal-dialog-centered">
<div class="modal-content">
<div class="modal-header border-0 pb-0">
<h5 class="modal-title fw-semibold">
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" class="text-danger" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
Delete Domain Mapping
</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></button>
</div>
<div class="modal-body">
<p>Are you sure you want to delete the mapping for <strong><code id="deleteDomainName"></code></strong>?</p>
<div class="alert alert-warning d-flex align-items-start small" role="alert">
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="flex-shrink-0 me-2 mt-0" viewBox="0 0 16 16">
<path d="M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16zm.93-9.412-1 4.705c-.07.34.029.533.304.533.194 0 .487-.07.686-.246l-.088.416c-.287.346-.92.598-1.465.598-.703 0-1.002-.422-.808-1.319l.738-3.468c.064-.293.006-.399-.287-.47l-.451-.081.082-.381 2.29-.287zM8 5.5a1 1 0 1 1 0-2 1 1 0 0 1 0 2z"/>
</svg>
<div>This domain will stop serving website content immediately.</div>
</div>
</div>
<div class="modal-footer">
<button type="button" class="btn btn-outline-secondary" data-bs-dismiss="modal">Cancel</button>
<form method="POST" id="deleteDomainForm">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<button type="submit" class="btn btn-danger">
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" fill="currentColor" class="me-1" viewBox="0 0 16 16">
<path d="M5.5 5.5A.5.5 0 0 1 6 6v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm2.5 0a.5.5 0 0 1 .5.5v6a.5.5 0 0 1-1 0V6a.5.5 0 0 1 .5-.5zm3 .5a.5.5 0 0 0-1 0v6a.5.5 0 0 0 1 0V6z"/>
<path fill-rule="evenodd" d="M14.5 3a1 1 0 0 1-1 1H13v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V4h-.5a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1H6a1 1 0 0 1 1-1h2a1 1 0 0 1 1 1h3.5a1 1 0 0 1 1 1v1zM4.118 4 4 4.059V13a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1V4.059L11.882 4H4.118zM2.5 3V2h11v1h-11z"/>
</svg>
Delete
</button>
</form>
</div>
</div>
</div>
</div>
{% endblock %}
{% block extra_scripts %}
<script>
(function () {
var editModal = document.getElementById('editDomainModal');
if (editModal) {
editModal.addEventListener('show.bs.modal', function (event) {
var btn = event.relatedTarget;
var domain = btn.getAttribute('data-domain');
var bucket = btn.getAttribute('data-bucket');
document.getElementById('editDomainName').value = domain;
var editBucket = document.getElementById('editBucket');
if (editBucket.tagName === 'SELECT') {
editBucket.value = bucket;
} else {
editBucket.value = bucket;
}
document.getElementById('editDomainForm').action = '{{ url_for("ui.update_website_domain", domain="__DOMAIN__") }}'.replace('__DOMAIN__', encodeURIComponent(domain));
});
}
var deleteModal = document.getElementById('deleteDomainModal');
if (deleteModal) {
deleteModal.addEventListener('show.bs.modal', function (event) {
var btn = event.relatedTarget;
var domain = btn.getAttribute('data-domain');
document.getElementById('deleteDomainName').textContent = domain;
document.getElementById('deleteDomainForm').action = '{{ url_for("ui.delete_website_domain", domain="__DOMAIN__") }}'.replace('__DOMAIN__', encodeURIComponent(domain));
});
}
})();
</script>
{% endblock %}

View File

@@ -1,191 +0,0 @@
import hashlib
import hmac
import pytest
from datetime import datetime, timedelta, timezone
from urllib.parse import quote
def _sign(key, msg):
return hmac.new(key, msg.encode("utf-8"), hashlib.sha256).digest()
def _get_signature_key(key, date_stamp, region_name, service_name):
k_date = _sign(("AWS4" + key).encode("utf-8"), date_stamp)
k_region = _sign(k_date, region_name)
k_service = _sign(k_region, service_name)
k_signing = _sign(k_service, "aws4_request")
return k_signing
def create_signed_headers(
method,
path,
headers=None,
body=None,
access_key="test",
secret_key="secret",
region="us-east-1",
service="s3",
timestamp=None
):
if headers is None:
headers = {}
if timestamp is None:
now = datetime.now(timezone.utc)
else:
now = timestamp
amz_date = now.strftime("%Y%m%dT%H%M%SZ")
date_stamp = now.strftime("%Y%m%d")
headers["X-Amz-Date"] = amz_date
headers["Host"] = "testserver"
canonical_uri = quote(path, safe="/-_.~")
canonical_query_string = ""
canonical_headers = ""
signed_headers_list = []
for k, v in sorted(headers.items(), key=lambda x: x[0].lower()):
canonical_headers += f"{k.lower()}:{v.strip()}\n"
signed_headers_list.append(k.lower())
signed_headers = ";".join(signed_headers_list)
payload_hash = hashlib.sha256(body or b"").hexdigest()
headers["X-Amz-Content-Sha256"] = payload_hash
canonical_request = f"{method}\n{canonical_uri}\n{canonical_query_string}\n{canonical_headers}\n{signed_headers}\n{payload_hash}"
credential_scope = f"{date_stamp}/{region}/{service}/aws4_request"
string_to_sign = f"AWS4-HMAC-SHA256\n{amz_date}\n{credential_scope}\n{hashlib.sha256(canonical_request.encode('utf-8')).hexdigest()}"
signing_key = _get_signature_key(secret_key, date_stamp, region, service)
signature = hmac.new(signing_key, string_to_sign.encode("utf-8"), hashlib.sha256).hexdigest()
headers["Authorization"] = (
f"AWS4-HMAC-SHA256 Credential={access_key}/{credential_scope}, "
f"SignedHeaders={signed_headers}, Signature={signature}"
)
return headers
def test_sigv4_old_date(client):
# Test with a date 20 minutes in the past
old_time = datetime.now(timezone.utc) - timedelta(minutes=20)
headers = create_signed_headers("GET", "/", timestamp=old_time)
response = client.get("/", headers=headers)
assert response.status_code == 403
assert b"Request timestamp too old" in response.data
def test_sigv4_future_date(client):
# Test with a date 20 minutes in the future
future_time = datetime.now(timezone.utc) + timedelta(minutes=20)
headers = create_signed_headers("GET", "/", timestamp=future_time)
response = client.get("/", headers=headers)
assert response.status_code == 403
assert b"Request timestamp too old" in response.data # The error message is the same
def test_path_traversal_in_key(client, signer):
headers = signer("PUT", "/test-bucket")
client.put("/test-bucket", headers=headers)
# Try to upload with .. in key
headers = signer("PUT", "/test-bucket/../secret.txt", body=b"attack")
response = client.put("/test-bucket/../secret.txt", headers=headers, data=b"attack")
# Should be rejected by storage layer or flask routing
# Flask might normalize it before it reaches the app, but if it reaches, it should fail.
# If Flask normalizes /test-bucket/../secret.txt to /secret.txt, then it hits 404 (bucket not found) or 403.
# But we want to test the storage layer check.
# We can try to encode the dots?
# If we use a key that doesn't get normalized by Flask routing easily.
# But wait, the route is /<bucket_name>/<path:object_key>
# If I send /test-bucket/folder/../file.txt, Flask might pass "folder/../file.txt" as object_key?
# Let's try.
headers = signer("PUT", "/test-bucket/folder/../file.txt", body=b"attack")
response = client.put("/test-bucket/folder/../file.txt", headers=headers, data=b"attack")
# If Flask normalizes it, it becomes /test-bucket/file.txt.
# If it doesn't, it hits our check.
# Let's try to call the storage method directly to verify the check works,
# because testing via client depends on Flask's URL handling.
pass
def test_storage_path_traversal(app):
storage = app.extensions["object_storage"]
from app.storage import StorageError, ObjectStorage
from app.encrypted_storage import EncryptedObjectStorage
# Get the underlying ObjectStorage if wrapped
if isinstance(storage, EncryptedObjectStorage):
storage = storage.storage
with pytest.raises(StorageError, match="Object key contains parent directory references"):
storage._sanitize_object_key("folder/../file.txt")
with pytest.raises(StorageError, match="Object key contains parent directory references"):
storage._sanitize_object_key("..")
def test_head_bucket(client, signer):
headers = signer("PUT", "/head-test")
client.put("/head-test", headers=headers)
headers = signer("HEAD", "/head-test")
response = client.head("/head-test", headers=headers)
assert response.status_code == 200
headers = signer("HEAD", "/non-existent")
response = client.head("/non-existent", headers=headers)
assert response.status_code == 404
def test_head_object(client, signer):
headers = signer("PUT", "/head-obj-test")
client.put("/head-obj-test", headers=headers)
headers = signer("PUT", "/head-obj-test/obj", body=b"content")
client.put("/head-obj-test/obj", headers=headers, data=b"content")
headers = signer("HEAD", "/head-obj-test/obj")
response = client.head("/head-obj-test/obj", headers=headers)
assert response.status_code == 200
assert response.headers["ETag"]
assert response.headers["Content-Length"] == "7"
headers = signer("HEAD", "/head-obj-test/missing")
response = client.head("/head-obj-test/missing", headers=headers)
assert response.status_code == 404
def test_list_parts(client, signer):
# Create bucket
headers = signer("PUT", "/multipart-test")
client.put("/multipart-test", headers=headers)
# Initiate multipart upload
headers = signer("POST", "/multipart-test/obj?uploads")
response = client.post("/multipart-test/obj?uploads", headers=headers)
assert response.status_code == 200
from xml.etree.ElementTree import fromstring
upload_id = fromstring(response.data).find("UploadId").text
# Upload part 1
headers = signer("PUT", f"/multipart-test/obj?partNumber=1&uploadId={upload_id}", body=b"part1")
client.put(f"/multipart-test/obj?partNumber=1&uploadId={upload_id}", headers=headers, data=b"part1")
# Upload part 2
headers = signer("PUT", f"/multipart-test/obj?partNumber=2&uploadId={upload_id}", body=b"part2")
client.put(f"/multipart-test/obj?partNumber=2&uploadId={upload_id}", headers=headers, data=b"part2")
# List parts
headers = signer("GET", f"/multipart-test/obj?uploadId={upload_id}")
response = client.get(f"/multipart-test/obj?uploadId={upload_id}", headers=headers)
assert response.status_code == 200
root = fromstring(response.data)
assert root.tag == "ListPartsResult"
parts = root.findall("Part")
assert len(parts) == 2
assert parts[0].find("PartNumber").text == "1"
assert parts[1].find("PartNumber").text == "2"

View File

@@ -20,7 +20,6 @@ from app.site_sync import (
SyncedObjectInfo, SyncedObjectInfo,
SiteSyncStats, SiteSyncStats,
RemoteObjectMeta, RemoteObjectMeta,
CLOCK_SKEW_TOLERANCE_SECONDS,
) )
from app.storage import ObjectStorage from app.storage import ObjectStorage

View File

@@ -1,8 +1,12 @@
import io import io
import json import json
import threading
from pathlib import Path from pathlib import Path
from werkzeug.serving import make_server
from app import create_app from app import create_app
from app.s3_client import S3ProxyClient
def _build_app(tmp_path: Path): def _build_app(tmp_path: Path):
@@ -26,13 +30,32 @@ def _build_app(tmp_path: Path):
"STORAGE_ROOT": storage_root, "STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config, "IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies, "BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://localhost", "API_BASE_URL": "http://127.0.0.1:0",
"SECRET_KEY": "testing", "SECRET_KEY": "testing",
"WTF_CSRF_ENABLED": False,
} }
) )
server = make_server("127.0.0.1", 0, app)
host, port = server.server_address
api_url = f"http://{host}:{port}"
app.config["API_BASE_URL"] = api_url
app.extensions["s3_proxy"] = S3ProxyClient(api_base_url=api_url)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
app._test_server = server
app._test_thread = thread
return app return app
def _shutdown_app(app):
if hasattr(app, "_test_server"):
app._test_server.shutdown()
app._test_thread.join(timeout=2)
def _login(client): def _login(client):
return client.post( return client.post(
"/ui/login", "/ui/login",
@@ -43,6 +66,7 @@ def _login(client):
def test_bulk_delete_json_route(tmp_path: Path): def test_bulk_delete_json_route(tmp_path: Path):
app = _build_app(tmp_path) app = _build_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("demo") storage.create_bucket("demo")
storage.put_object("demo", "first.txt", io.BytesIO(b"first")) storage.put_object("demo", "first.txt", io.BytesIO(b"first"))
@@ -64,10 +88,13 @@ def test_bulk_delete_json_route(tmp_path: Path):
listing = storage.list_objects_all("demo") listing = storage.list_objects_all("demo")
assert {meta.key for meta in listing} == {"second.txt"} assert {meta.key for meta in listing} == {"second.txt"}
finally:
_shutdown_app(app)
def test_bulk_delete_validation(tmp_path: Path): def test_bulk_delete_validation(tmp_path: Path):
app = _build_app(tmp_path) app = _build_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("demo") storage.create_bucket("demo")
storage.put_object("demo", "keep.txt", io.BytesIO(b"keep")) storage.put_object("demo", "keep.txt", io.BytesIO(b"keep"))
@@ -94,3 +121,5 @@ def test_bulk_delete_validation(tmp_path: Path):
still_there = storage.list_objects_all("demo") still_there = storage.list_objects_all("demo")
assert {meta.key for meta in still_there} == {"keep.txt"} assert {meta.key for meta in still_there} == {"keep.txt"}
finally:
_shutdown_app(app)

View File

@@ -1,10 +1,13 @@
"""Tests for UI-based encryption configuration.""" """Tests for UI-based encryption configuration."""
import json import json
import threading
from pathlib import Path from pathlib import Path
import pytest import pytest
from werkzeug.serving import make_server
from app import create_app from app import create_app
from app.s3_client import S3ProxyClient
def get_csrf_token(response): def get_csrf_token(response):
@@ -43,9 +46,10 @@ def _make_encryption_app(tmp_path: Path, *, kms_enabled: bool = True):
"STORAGE_ROOT": storage_root, "STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config, "IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies, "BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://testserver", "API_BASE_URL": "http://127.0.0.1:0",
"SECRET_KEY": "testing", "SECRET_KEY": "testing",
"ENCRYPTION_ENABLED": True, "ENCRYPTION_ENABLED": True,
"WTF_CSRF_ENABLED": False,
} }
if kms_enabled: if kms_enabled:
@@ -54,17 +58,37 @@ def _make_encryption_app(tmp_path: Path, *, kms_enabled: bool = True):
config["ENCRYPTION_MASTER_KEY_PATH"] = str(tmp_path / "master.key") config["ENCRYPTION_MASTER_KEY_PATH"] = str(tmp_path / "master.key")
app = create_app(config) app = create_app(config)
server = make_server("127.0.0.1", 0, app)
host, port = server.server_address
api_url = f"http://{host}:{port}"
app.config["API_BASE_URL"] = api_url
app.extensions["s3_proxy"] = S3ProxyClient(api_base_url=api_url)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
app._test_server = server
app._test_thread = thread
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
return app return app
def _shutdown_app(app):
if hasattr(app, "_test_server"):
app._test_server.shutdown()
app._test_thread.join(timeout=2)
class TestUIBucketEncryption: class TestUIBucketEncryption:
"""Test bucket encryption configuration via UI.""" """Test bucket encryption configuration via UI."""
def test_bucket_detail_shows_encryption_card(self, tmp_path): def test_bucket_detail_shows_encryption_card(self, tmp_path):
"""Encryption card should be visible on bucket detail page.""" """Encryption card should be visible on bucket detail page."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
@@ -75,21 +99,20 @@ class TestUIBucketEncryption:
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "Default Encryption" in html assert "Default Encryption" in html
assert "Encryption Algorithm" in html or "Default encryption disabled" in html assert "Encryption Algorithm" in html or "Default encryption disabled" in html
finally:
_shutdown_app(app)
def test_enable_aes256_encryption(self, tmp_path): def test_enable_aes256_encryption(self, tmp_path):
"""Should be able to enable AES-256 encryption.""" """Should be able to enable AES-256 encryption."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
response = client.post( response = client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "AES256", "algorithm": "AES256",
}, },
@@ -99,12 +122,13 @@ class TestUIBucketEncryption:
assert response.status_code == 200 assert response.status_code == 200
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "AES-256" in html or "encryption enabled" in html.lower() assert "AES-256" in html or "encryption enabled" in html.lower()
finally:
_shutdown_app(app)
def test_enable_kms_encryption(self, tmp_path): def test_enable_kms_encryption(self, tmp_path):
"""Should be able to enable KMS encryption.""" """Should be able to enable KMS encryption."""
app = _make_encryption_app(tmp_path, kms_enabled=True) app = _make_encryption_app(tmp_path, kms_enabled=True)
client = app.test_client() try:
with app.app_context(): with app.app_context():
kms = app.extensions.get("kms") kms = app.extensions.get("kms")
if kms: if kms:
@@ -113,15 +137,12 @@ class TestUIBucketEncryption:
else: else:
pytest.skip("KMS not available") pytest.skip("KMS not available")
client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
response = client.post( response = client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "aws:kms", "algorithm": "aws:kms",
"kms_key_id": key_id, "kms_key_id": key_id,
@@ -132,33 +153,28 @@ class TestUIBucketEncryption:
assert response.status_code == 200 assert response.status_code == 200
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "KMS" in html or "encryption enabled" in html.lower() assert "KMS" in html or "encryption enabled" in html.lower()
finally:
_shutdown_app(app)
def test_disable_encryption(self, tmp_path): def test_disable_encryption(self, tmp_path):
"""Should be able to disable encryption.""" """Should be able to disable encryption."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
client.post( client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "AES256", "algorithm": "AES256",
}, },
) )
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
response = client.post( response = client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "disable", "action": "disable",
}, },
follow_redirects=True, follow_redirects=True,
@@ -167,21 +183,20 @@ class TestUIBucketEncryption:
assert response.status_code == 200 assert response.status_code == 200
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "disabled" in html.lower() or "Default encryption disabled" in html assert "disabled" in html.lower() or "Default encryption disabled" in html
finally:
_shutdown_app(app)
def test_invalid_algorithm_rejected(self, tmp_path): def test_invalid_algorithm_rejected(self, tmp_path):
"""Invalid encryption algorithm should be rejected.""" """Invalid encryption algorithm should be rejected."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
response = client.post( response = client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "INVALID", "algorithm": "INVALID",
}, },
@@ -191,21 +206,20 @@ class TestUIBucketEncryption:
assert response.status_code == 200 assert response.status_code == 200
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "Invalid" in html or "danger" in html assert "Invalid" in html or "danger" in html
finally:
_shutdown_app(app)
def test_encryption_persists_in_config(self, tmp_path): def test_encryption_persists_in_config(self, tmp_path):
"""Encryption config should persist in bucket config.""" """Encryption config should persist in bucket config."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
client.post( client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "AES256", "algorithm": "AES256",
}, },
@@ -217,7 +231,9 @@ class TestUIBucketEncryption:
assert "Rules" in config assert "Rules" in config
assert len(config["Rules"]) == 1 assert len(config["Rules"]) == 1
assert config["Rules"][0]["ApplyServerSideEncryptionByDefault"]["SSEAlgorithm"] == "AES256" assert config["Rules"][0]["SSEAlgorithm"] == "AES256"
finally:
_shutdown_app(app)
class TestUIEncryptionWithoutPermission: class TestUIEncryptionWithoutPermission:
@@ -226,17 +242,14 @@ class TestUIEncryptionWithoutPermission:
def test_readonly_user_cannot_change_encryption(self, tmp_path): def test_readonly_user_cannot_change_encryption(self, tmp_path):
"""Read-only user should not be able to change encryption settings.""" """Read-only user should not be able to change encryption settings."""
app = _make_encryption_app(tmp_path) app = _make_encryption_app(tmp_path)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "readonly", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "readonly", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/test-bucket?tab=properties")
csrf_token = get_csrf_token(response)
response = client.post( response = client.post(
"/ui/buckets/test-bucket/encryption", "/ui/buckets/test-bucket/encryption",
data={ data={
"csrf_token": csrf_token,
"action": "enable", "action": "enable",
"algorithm": "AES256", "algorithm": "AES256",
}, },
@@ -246,3 +259,5 @@ class TestUIEncryptionWithoutPermission:
assert response.status_code == 200 assert response.status_code == 200
html = response.data.decode("utf-8") html = response.data.decode("utf-8")
assert "Access denied" in html or "permission" in html.lower() or "not authorized" in html.lower() assert "Access denied" in html or "permission" in html.lower() or "not authorized" in html.lower()
finally:
_shutdown_app(app)

View File

@@ -1,15 +1,18 @@
"""Tests for UI pagination of bucket objects.""" """Tests for UI pagination of bucket objects."""
import json import json
import threading
from io import BytesIO from io import BytesIO
from pathlib import Path from pathlib import Path
import pytest import pytest
from werkzeug.serving import make_server
from app import create_app from app import create_app
from app.s3_client import S3ProxyClient
def _make_app(tmp_path: Path): def _make_app(tmp_path: Path):
"""Create an app for testing.""" """Create an app for testing with a live API server."""
storage_root = tmp_path / "data" storage_root = tmp_path / "data"
iam_config = tmp_path / "iam.json" iam_config = tmp_path / "iam.json"
bucket_policies = tmp_path / "bucket_policies.json" bucket_policies = tmp_path / "bucket_policies.json"
@@ -33,29 +36,46 @@ def _make_app(tmp_path: Path):
"STORAGE_ROOT": storage_root, "STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config, "IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies, "BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://127.0.0.1:0",
} }
) )
server = make_server("127.0.0.1", 0, flask_app)
host, port = server.server_address
api_url = f"http://{host}:{port}"
flask_app.config["API_BASE_URL"] = api_url
flask_app.extensions["s3_proxy"] = S3ProxyClient(api_base_url=api_url)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
flask_app._test_server = server
flask_app._test_thread = thread
return flask_app return flask_app
def _shutdown_app(app):
if hasattr(app, "_test_server"):
app._test_server.shutdown()
app._test_thread.join(timeout=2)
class TestPaginatedObjectListing: class TestPaginatedObjectListing:
"""Test paginated object listing API.""" """Test paginated object listing API."""
def test_objects_api_returns_paginated_results(self, tmp_path): def test_objects_api_returns_paginated_results(self, tmp_path):
"""Objects API should return paginated results.""" """Objects API should return paginated results."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
# Create 10 test objects
for i in range(10): for i in range(10):
storage.put_object("test-bucket", f"file{i:02d}.txt", BytesIO(b"content")) storage.put_object("test-bucket", f"file{i:02d}.txt", BytesIO(b"content"))
with app.test_client() as client: with app.test_client() as client:
# Login first
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
# Request first page of 3 objects
resp = client.get("/ui/buckets/test-bucket/objects?max_keys=3") resp = client.get("/ui/buckets/test-bucket/objects?max_keys=3")
assert resp.status_code == 200 assert resp.status_code == 200
@@ -63,22 +83,22 @@ class TestPaginatedObjectListing:
assert len(data["objects"]) == 3 assert len(data["objects"]) == 3
assert data["is_truncated"] is True assert data["is_truncated"] is True
assert data["next_continuation_token"] is not None assert data["next_continuation_token"] is not None
assert data["total_count"] == 10 finally:
_shutdown_app(app)
def test_objects_api_pagination_continuation(self, tmp_path): def test_objects_api_pagination_continuation(self, tmp_path):
"""Objects API should support continuation tokens.""" """Objects API should support continuation tokens."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
# Create 5 test objects
for i in range(5): for i in range(5):
storage.put_object("test-bucket", f"file{i:02d}.txt", BytesIO(b"content")) storage.put_object("test-bucket", f"file{i:02d}.txt", BytesIO(b"content"))
with app.test_client() as client: with app.test_client() as client:
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
# Get first page
resp = client.get("/ui/buckets/test-bucket/objects?max_keys=2") resp = client.get("/ui/buckets/test-bucket/objects?max_keys=2")
assert resp.status_code == 200 assert resp.status_code == 200
data = resp.get_json() data = resp.get_json()
@@ -87,7 +107,6 @@ class TestPaginatedObjectListing:
assert len(first_page_keys) == 2 assert len(first_page_keys) == 2
assert data["is_truncated"] is True assert data["is_truncated"] is True
# Get second page
token = data["next_continuation_token"] token = data["next_continuation_token"]
resp = client.get(f"/ui/buckets/test-bucket/objects?max_keys=2&continuation_token={token}") resp = client.get(f"/ui/buckets/test-bucket/objects?max_keys=2&continuation_token={token}")
assert resp.status_code == 200 assert resp.status_code == 200
@@ -96,16 +115,17 @@ class TestPaginatedObjectListing:
second_page_keys = [obj["key"] for obj in data["objects"]] second_page_keys = [obj["key"] for obj in data["objects"]]
assert len(second_page_keys) == 2 assert len(second_page_keys) == 2
# No overlap between pages
assert set(first_page_keys).isdisjoint(set(second_page_keys)) assert set(first_page_keys).isdisjoint(set(second_page_keys))
finally:
_shutdown_app(app)
def test_objects_api_prefix_filter(self, tmp_path): def test_objects_api_prefix_filter(self, tmp_path):
"""Objects API should support prefix filtering.""" """Objects API should support prefix filtering."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
# Create objects with different prefixes
storage.put_object("test-bucket", "logs/access.log", BytesIO(b"log")) storage.put_object("test-bucket", "logs/access.log", BytesIO(b"log"))
storage.put_object("test-bucket", "logs/error.log", BytesIO(b"log")) storage.put_object("test-bucket", "logs/error.log", BytesIO(b"log"))
storage.put_object("test-bucket", "data/file.txt", BytesIO(b"data")) storage.put_object("test-bucket", "data/file.txt", BytesIO(b"data"))
@@ -113,7 +133,6 @@ class TestPaginatedObjectListing:
with app.test_client() as client: with app.test_client() as client:
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
# Filter by prefix
resp = client.get("/ui/buckets/test-bucket/objects?prefix=logs/") resp = client.get("/ui/buckets/test-bucket/objects?prefix=logs/")
assert resp.status_code == 200 assert resp.status_code == 200
data = resp.get_json() data = resp.get_json()
@@ -121,23 +140,27 @@ class TestPaginatedObjectListing:
keys = [obj["key"] for obj in data["objects"]] keys = [obj["key"] for obj in data["objects"]]
assert all(k.startswith("logs/") for k in keys) assert all(k.startswith("logs/") for k in keys)
assert len(keys) == 2 assert len(keys) == 2
finally:
_shutdown_app(app)
def test_objects_api_requires_authentication(self, tmp_path): def test_objects_api_requires_authentication(self, tmp_path):
"""Objects API should require login.""" """Objects API should require login."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
with app.test_client() as client: with app.test_client() as client:
# Don't login
resp = client.get("/ui/buckets/test-bucket/objects") resp = client.get("/ui/buckets/test-bucket/objects")
# Should redirect to login
assert resp.status_code == 302 assert resp.status_code == 302
assert "/ui/login" in resp.headers.get("Location", "") assert "/ui/login" in resp.headers.get("Location", "")
finally:
_shutdown_app(app)
def test_objects_api_returns_object_metadata(self, tmp_path): def test_objects_api_returns_object_metadata(self, tmp_path):
"""Objects API should return complete object metadata.""" """Objects API should return complete object metadata."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
storage.put_object("test-bucket", "test.txt", BytesIO(b"test content")) storage.put_object("test-bucket", "test.txt", BytesIO(b"test content"))
@@ -152,38 +175,38 @@ class TestPaginatedObjectListing:
assert len(data["objects"]) == 1 assert len(data["objects"]) == 1
obj = data["objects"][0] obj = data["objects"][0]
# Check all expected fields
assert obj["key"] == "test.txt" assert obj["key"] == "test.txt"
assert obj["size"] == 12 # len("test content") assert obj["size"] == 12
assert "last_modified" in obj assert "last_modified" in obj
assert "last_modified_display" in obj assert "last_modified_display" in obj
assert "etag" in obj assert "etag" in obj
# URLs are now returned as templates (not per-object) for performance
assert "url_templates" in data assert "url_templates" in data
templates = data["url_templates"] templates = data["url_templates"]
assert "preview" in templates assert "preview" in templates
assert "download" in templates assert "download" in templates
assert "delete" in templates assert "delete" in templates
assert "KEY_PLACEHOLDER" in templates["preview"] assert "KEY_PLACEHOLDER" in templates["preview"]
finally:
_shutdown_app(app)
def test_bucket_detail_page_loads_without_objects(self, tmp_path): def test_bucket_detail_page_loads_without_objects(self, tmp_path):
"""Bucket detail page should load even with many objects.""" """Bucket detail page should load even with many objects."""
app = _make_app(tmp_path) app = _make_app(tmp_path)
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("test-bucket") storage.create_bucket("test-bucket")
# Create many objects
for i in range(100): for i in range(100):
storage.put_object("test-bucket", f"file{i:03d}.txt", BytesIO(b"x")) storage.put_object("test-bucket", f"file{i:03d}.txt", BytesIO(b"x"))
with app.test_client() as client: with app.test_client() as client:
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
# The page should load quickly (objects loaded via JS)
resp = client.get("/ui/buckets/test-bucket") resp = client.get("/ui/buckets/test-bucket")
assert resp.status_code == 200 assert resp.status_code == 200
html = resp.data.decode("utf-8") html = resp.data.decode("utf-8")
# Should have the JavaScript loading infrastructure (external JS file)
assert "bucket-detail-main.js" in html assert "bucket-detail-main.js" in html
finally:
_shutdown_app(app)

View File

@@ -1,10 +1,13 @@
import io import io
import json import json
import threading
from pathlib import Path from pathlib import Path
import pytest import pytest
from werkzeug.serving import make_server
from app import create_app from app import create_app
from app.s3_client import S3ProxyClient
DENY_LIST_ALLOW_GET_POLICY = { DENY_LIST_ALLOW_GET_POLICY = {
@@ -47,11 +50,25 @@ def _make_ui_app(tmp_path: Path, *, enforce_policies: bool):
"STORAGE_ROOT": storage_root, "STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config, "IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies, "BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://testserver", "API_BASE_URL": "http://127.0.0.1:0",
"SECRET_KEY": "testing", "SECRET_KEY": "testing",
"UI_ENFORCE_BUCKET_POLICIES": enforce_policies, "UI_ENFORCE_BUCKET_POLICIES": enforce_policies,
"WTF_CSRF_ENABLED": False,
} }
) )
server = make_server("127.0.0.1", 0, app)
host, port = server.server_address
api_url = f"http://{host}:{port}"
app.config["API_BASE_URL"] = api_url
app.extensions["s3_proxy"] = S3ProxyClient(api_base_url=api_url)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
app._test_server = server
app._test_thread = thread
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("testbucket") storage.create_bucket("testbucket")
storage.put_object("testbucket", "vid.mp4", io.BytesIO(b"video")) storage.put_object("testbucket", "vid.mp4", io.BytesIO(b"video"))
@@ -60,9 +77,16 @@ def _make_ui_app(tmp_path: Path, *, enforce_policies: bool):
return app return app
def _shutdown_app(app):
if hasattr(app, "_test_server"):
app._test_server.shutdown()
app._test_thread.join(timeout=2)
@pytest.mark.parametrize("enforce", [True, False]) @pytest.mark.parametrize("enforce", [True, False])
def test_ui_bucket_policy_enforcement_toggle(tmp_path: Path, enforce: bool): def test_ui_bucket_policy_enforcement_toggle(tmp_path: Path, enforce: bool):
app = _make_ui_app(tmp_path, enforce_policies=enforce) app = _make_ui_app(tmp_path, enforce_policies=enforce)
try:
client = app.test_client() client = app.test_client()
client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True) client.post("/ui/login", data={"access_key": "test", "secret_key": "secret"}, follow_redirects=True)
response = client.get("/ui/buckets/testbucket", follow_redirects=True) response = client.get("/ui/buckets/testbucket", follow_redirects=True)
@@ -71,11 +95,10 @@ def test_ui_bucket_policy_enforcement_toggle(tmp_path: Path, enforce: bool):
else: else:
assert response.status_code == 200 assert response.status_code == 200
assert b"Access denied by bucket policy" not in response.data assert b"Access denied by bucket policy" not in response.data
# Objects are now loaded via async API - check the objects endpoint
objects_response = client.get("/ui/buckets/testbucket/objects") objects_response = client.get("/ui/buckets/testbucket/objects")
assert objects_response.status_code == 200 assert objects_response.status_code == 403
data = objects_response.get_json() finally:
assert any(obj["key"] == "vid.mp4" for obj in data["objects"]) _shutdown_app(app)
def test_ui_bucket_policy_disabled_by_default(tmp_path: Path): def test_ui_bucket_policy_disabled_by_default(tmp_path: Path):
@@ -99,10 +122,25 @@ def test_ui_bucket_policy_disabled_by_default(tmp_path: Path):
"STORAGE_ROOT": storage_root, "STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config, "IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies, "BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://testserver", "API_BASE_URL": "http://127.0.0.1:0",
"SECRET_KEY": "testing", "SECRET_KEY": "testing",
"WTF_CSRF_ENABLED": False,
} }
) )
server = make_server("127.0.0.1", 0, app)
host, port = server.server_address
api_url = f"http://{host}:{port}"
app.config["API_BASE_URL"] = api_url
app.extensions["s3_proxy"] = S3ProxyClient(api_base_url=api_url)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
app._test_server = server
app._test_thread = thread
try:
storage = app.extensions["object_storage"] storage = app.extensions["object_storage"]
storage.create_bucket("testbucket") storage.create_bucket("testbucket")
storage.put_object("testbucket", "vid.mp4", io.BytesIO(b"video")) storage.put_object("testbucket", "vid.mp4", io.BytesIO(b"video"))
@@ -114,8 +152,7 @@ def test_ui_bucket_policy_disabled_by_default(tmp_path: Path):
response = client.get("/ui/buckets/testbucket", follow_redirects=True) response = client.get("/ui/buckets/testbucket", follow_redirects=True)
assert response.status_code == 200 assert response.status_code == 200
assert b"Access denied by bucket policy" not in response.data assert b"Access denied by bucket policy" not in response.data
# Objects are now loaded via async API - check the objects endpoint
objects_response = client.get("/ui/buckets/testbucket/objects") objects_response = client.get("/ui/buckets/testbucket/objects")
assert objects_response.status_code == 200 assert objects_response.status_code == 403
data = objects_response.get_json() finally:
assert any(obj["key"] == "vid.mp4" for obj in data["objects"]) _shutdown_app(app)

View File

@@ -0,0 +1,442 @@
import io
import json
from pathlib import Path
from xml.etree.ElementTree import fromstring
import pytest
from app import create_api_app
from app.website_domains import WebsiteDomainStore
def _stream(data: bytes):
return io.BytesIO(data)
@pytest.fixture()
def website_app(tmp_path: Path):
storage_root = tmp_path / "data"
iam_config = tmp_path / "iam.json"
bucket_policies = tmp_path / "bucket_policies.json"
iam_payload = {
"users": [
{
"access_key": "test",
"secret_key": "secret",
"display_name": "Test User",
"policies": [{"bucket": "*", "actions": ["list", "read", "write", "delete", "policy", "iam:*"]}],
}
]
}
iam_config.write_text(json.dumps(iam_payload))
flask_app = create_api_app(
{
"TESTING": True,
"SECRET_KEY": "testing",
"STORAGE_ROOT": storage_root,
"IAM_CONFIG": iam_config,
"BUCKET_POLICY_PATH": bucket_policies,
"API_BASE_URL": "http://testserver",
"WEBSITE_HOSTING_ENABLED": True,
}
)
yield flask_app
@pytest.fixture()
def website_client(website_app):
return website_app.test_client()
@pytest.fixture()
def storage(website_app):
return website_app.extensions["object_storage"]
class TestWebsiteDomainStore:
def test_empty_store(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
assert store.list_all() == []
assert store.get_bucket("example.com") is None
def test_set_and_get_mapping(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
store.set_mapping("example.com", "my-site")
assert store.get_bucket("example.com") == "my-site"
def test_case_insensitive(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
store.set_mapping("Example.COM", "my-site")
assert store.get_bucket("example.com") == "my-site"
assert store.get_bucket("EXAMPLE.COM") == "my-site"
def test_list_all(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
store.set_mapping("a.com", "bucket-a")
store.set_mapping("b.com", "bucket-b")
result = store.list_all()
domains = {item["domain"] for item in result}
assert domains == {"a.com", "b.com"}
def test_delete_mapping(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
store.set_mapping("example.com", "my-site")
assert store.delete_mapping("example.com") is True
assert store.get_bucket("example.com") is None
def test_delete_nonexistent(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
assert store.delete_mapping("nope.com") is False
def test_overwrite_mapping(self, tmp_path):
store = WebsiteDomainStore(tmp_path / "domains.json")
store.set_mapping("example.com", "old-bucket")
store.set_mapping("example.com", "new-bucket")
assert store.get_bucket("example.com") == "new-bucket"
def test_persistence(self, tmp_path):
path = tmp_path / "domains.json"
store1 = WebsiteDomainStore(path)
store1.set_mapping("example.com", "my-site")
store2 = WebsiteDomainStore(path)
assert store2.get_bucket("example.com") == "my-site"
def test_corrupt_file(self, tmp_path):
path = tmp_path / "domains.json"
path.write_text("not json")
store = WebsiteDomainStore(path)
assert store.list_all() == []
def test_non_dict_file(self, tmp_path):
path = tmp_path / "domains.json"
path.write_text('["not", "a", "dict"]')
store = WebsiteDomainStore(path)
assert store.list_all() == []
class TestStorageWebsiteConfig:
def test_get_website_no_config(self, storage):
storage.create_bucket("test-bucket")
assert storage.get_bucket_website("test-bucket") is None
def test_set_and_get_website(self, storage):
storage.create_bucket("test-bucket")
config = {"index_document": "index.html", "error_document": "error.html"}
storage.set_bucket_website("test-bucket", config)
result = storage.get_bucket_website("test-bucket")
assert result["index_document"] == "index.html"
assert result["error_document"] == "error.html"
def test_delete_website_config(self, storage):
storage.create_bucket("test-bucket")
storage.set_bucket_website("test-bucket", {"index_document": "index.html"})
storage.set_bucket_website("test-bucket", None)
assert storage.get_bucket_website("test-bucket") is None
def test_nonexistent_bucket(self, storage):
with pytest.raises(Exception):
storage.get_bucket_website("no-such-bucket")
class TestS3WebsiteAPI:
def test_put_website_config(self, website_client, signer):
headers = signer("PUT", "/site-bucket")
assert website_client.put("/site-bucket", headers=headers).status_code == 200
xml_body = b"""<WebsiteConfiguration>
<IndexDocument><Suffix>index.html</Suffix></IndexDocument>
<ErrorDocument><Key>404.html</Key></ErrorDocument>
</WebsiteConfiguration>"""
headers = signer("PUT", "/site-bucket?website",
headers={"Content-Type": "application/xml"}, body=xml_body)
resp = website_client.put("/site-bucket", query_string={"website": ""},
headers=headers, data=xml_body, content_type="application/xml")
assert resp.status_code == 200
def test_get_website_config(self, website_client, signer, storage):
storage.create_bucket("site-bucket")
storage.set_bucket_website("site-bucket", {
"index_document": "index.html",
"error_document": "error.html",
})
headers = signer("GET", "/site-bucket?website")
resp = website_client.get("/site-bucket", query_string={"website": ""}, headers=headers)
assert resp.status_code == 200
root = fromstring(resp.data)
suffix = root.find(".//{http://s3.amazonaws.com/doc/2006-03-01/}Suffix")
if suffix is None:
suffix = root.find(".//Suffix")
assert suffix is not None
assert suffix.text == "index.html"
def test_get_website_config_not_set(self, website_client, signer, storage):
storage.create_bucket("no-website")
headers = signer("GET", "/no-website?website")
resp = website_client.get("/no-website", query_string={"website": ""}, headers=headers)
assert resp.status_code == 404
def test_delete_website_config(self, website_client, signer, storage):
storage.create_bucket("site-bucket")
storage.set_bucket_website("site-bucket", {"index_document": "index.html"})
headers = signer("DELETE", "/site-bucket?website")
resp = website_client.delete("/site-bucket", query_string={"website": ""}, headers=headers)
assert resp.status_code == 204
assert storage.get_bucket_website("site-bucket") is None
def test_put_website_missing_index(self, website_client, signer, storage):
storage.create_bucket("site-bucket")
xml_body = b"""<WebsiteConfiguration>
<ErrorDocument><Key>error.html</Key></ErrorDocument>
</WebsiteConfiguration>"""
headers = signer("PUT", "/site-bucket?website",
headers={"Content-Type": "application/xml"}, body=xml_body)
resp = website_client.put("/site-bucket", query_string={"website": ""},
headers=headers, data=xml_body, content_type="application/xml")
assert resp.status_code == 400
def test_put_website_slash_in_suffix(self, website_client, signer, storage):
storage.create_bucket("site-bucket")
xml_body = b"""<WebsiteConfiguration>
<IndexDocument><Suffix>path/index.html</Suffix></IndexDocument>
</WebsiteConfiguration>"""
headers = signer("PUT", "/site-bucket?website",
headers={"Content-Type": "application/xml"}, body=xml_body)
resp = website_client.put("/site-bucket", query_string={"website": ""},
headers=headers, data=xml_body, content_type="application/xml")
assert resp.status_code == 400
def test_put_website_malformed_xml(self, website_client, signer, storage):
storage.create_bucket("site-bucket")
xml_body = b"not xml at all"
headers = signer("PUT", "/site-bucket?website",
headers={"Content-Type": "application/xml"}, body=xml_body)
resp = website_client.put("/site-bucket", query_string={"website": ""},
headers=headers, data=xml_body, content_type="application/xml")
assert resp.status_code == 400
def test_website_disabled(self, client, signer):
headers = signer("PUT", "/test-bucket")
assert client.put("/test-bucket", headers=headers).status_code == 200
headers = signer("GET", "/test-bucket?website")
resp = client.get("/test-bucket", query_string={"website": ""}, headers=headers)
assert resp.status_code == 400
assert b"not enabled" in resp.data
class TestAdminWebsiteDomains:
def _admin_headers(self, signer):
return signer("GET", "/admin/website-domains")
def test_list_empty(self, website_client, signer):
headers = self._admin_headers(signer)
resp = website_client.get("/admin/website-domains", headers=headers)
assert resp.status_code == 200
assert resp.get_json() == []
def test_create_mapping(self, website_client, signer, storage):
storage.create_bucket("my-site")
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"},
body=json.dumps({"domain": "example.com", "bucket": "my-site"}).encode())
resp = website_client.post("/admin/website-domains",
headers=headers,
json={"domain": "example.com", "bucket": "my-site"})
assert resp.status_code == 201
data = resp.get_json()
assert data["domain"] == "example.com"
assert data["bucket"] == "my-site"
def test_create_duplicate(self, website_client, signer, storage):
storage.create_bucket("my-site")
body = json.dumps({"domain": "dup.com", "bucket": "my-site"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
website_client.post("/admin/website-domains", headers=headers,
json={"domain": "dup.com", "bucket": "my-site"})
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
resp = website_client.post("/admin/website-domains", headers=headers,
json={"domain": "dup.com", "bucket": "my-site"})
assert resp.status_code == 409
def test_create_missing_domain(self, website_client, signer, storage):
storage.create_bucket("my-site")
body = json.dumps({"bucket": "my-site"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
resp = website_client.post("/admin/website-domains", headers=headers,
json={"bucket": "my-site"})
assert resp.status_code == 400
def test_create_nonexistent_bucket(self, website_client, signer):
body = json.dumps({"domain": "x.com", "bucket": "no-such"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
resp = website_client.post("/admin/website-domains", headers=headers,
json={"domain": "x.com", "bucket": "no-such"})
assert resp.status_code == 404
def test_get_mapping(self, website_client, signer, storage):
storage.create_bucket("my-site")
body = json.dumps({"domain": "get.com", "bucket": "my-site"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
website_client.post("/admin/website-domains", headers=headers,
json={"domain": "get.com", "bucket": "my-site"})
headers = signer("GET", "/admin/website-domains/get.com")
resp = website_client.get("/admin/website-domains/get.com", headers=headers)
assert resp.status_code == 200
assert resp.get_json()["bucket"] == "my-site"
def test_get_nonexistent(self, website_client, signer):
headers = signer("GET", "/admin/website-domains/nope.com")
resp = website_client.get("/admin/website-domains/nope.com", headers=headers)
assert resp.status_code == 404
def test_update_mapping(self, website_client, signer, storage):
storage.create_bucket("old-bucket")
storage.create_bucket("new-bucket")
body = json.dumps({"domain": "upd.com", "bucket": "old-bucket"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
website_client.post("/admin/website-domains", headers=headers,
json={"domain": "upd.com", "bucket": "old-bucket"})
body = json.dumps({"bucket": "new-bucket"}).encode()
headers = signer("PUT", "/admin/website-domains/upd.com",
headers={"Content-Type": "application/json"}, body=body)
resp = website_client.put("/admin/website-domains/upd.com", headers=headers,
json={"bucket": "new-bucket"})
assert resp.status_code == 200
assert resp.get_json()["bucket"] == "new-bucket"
def test_delete_mapping(self, website_client, signer, storage):
storage.create_bucket("del-bucket")
body = json.dumps({"domain": "del.com", "bucket": "del-bucket"}).encode()
headers = signer("POST", "/admin/website-domains",
headers={"Content-Type": "application/json"}, body=body)
website_client.post("/admin/website-domains", headers=headers,
json={"domain": "del.com", "bucket": "del-bucket"})
headers = signer("DELETE", "/admin/website-domains/del.com")
resp = website_client.delete("/admin/website-domains/del.com", headers=headers)
assert resp.status_code == 204
def test_delete_nonexistent(self, website_client, signer):
headers = signer("DELETE", "/admin/website-domains/nope.com")
resp = website_client.delete("/admin/website-domains/nope.com", headers=headers)
assert resp.status_code == 404
def test_disabled(self, website_client, signer):
with website_client.application.test_request_context():
website_client.application.config["WEBSITE_HOSTING_ENABLED"] = False
headers = signer("GET", "/admin/website-domains")
resp = website_client.get("/admin/website-domains", headers=headers)
assert resp.status_code == 400
website_client.application.config["WEBSITE_HOSTING_ENABLED"] = True
class TestWebsiteServing:
def _setup_website(self, storage, website_app):
storage.create_bucket("my-site")
storage.put_object("my-site", "index.html", _stream(b"<h1>Home</h1>"))
storage.put_object("my-site", "about.html", _stream(b"<h1>About</h1>"))
storage.put_object("my-site", "assets/style.css", _stream(b"body { color: red; }"))
storage.put_object("my-site", "sub/index.html", _stream(b"<h1>Sub</h1>"))
storage.put_object("my-site", "404.html", _stream(b"<h1>Not Found</h1>"))
storage.set_bucket_website("my-site", {
"index_document": "index.html",
"error_document": "404.html",
})
store = website_app.extensions["website_domains"]
store.set_mapping("mysite.example.com", "my-site")
def test_serve_index(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert b"<h1>Home</h1>" in resp.data
assert "text/html" in resp.content_type
def test_serve_specific_file(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/about.html", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert b"<h1>About</h1>" in resp.data
def test_serve_css(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/assets/style.css", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert b"body { color: red; }" in resp.data
assert "text/css" in resp.content_type
def test_serve_subdirectory_index(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/sub/", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert b"<h1>Sub</h1>" in resp.data
def test_serve_subdirectory_no_trailing_slash(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/sub", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert b"<h1>Sub</h1>" in resp.data
def test_serve_error_document(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/nonexistent.html", headers={"Host": "mysite.example.com"})
assert resp.status_code == 404
assert b"<h1>Not Found</h1>" in resp.data
def test_unmapped_host_passes_through(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/", headers={"Host": "unknown.example.com"})
assert resp.status_code != 200 or b"<h1>Home</h1>" not in resp.data
def test_head_request(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.head("/index.html", headers={"Host": "mysite.example.com"})
assert resp.status_code == 200
assert "Content-Length" in resp.headers
assert resp.data == b""
def test_post_not_intercepted(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.post("/index.html", headers={"Host": "mysite.example.com"})
assert resp.status_code != 200 or b"<h1>Home</h1>" not in resp.data
def test_bucket_deleted(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
for obj in storage.list_objects_all("my-site"):
storage.delete_object("my-site", obj.key)
storage.delete_bucket("my-site")
resp = website_client.get("/", headers={"Host": "mysite.example.com"})
assert resp.status_code == 404
def test_no_website_config(self, website_client, storage, website_app):
storage.create_bucket("bare-bucket")
store = website_app.extensions["website_domains"]
store.set_mapping("bare.example.com", "bare-bucket")
resp = website_client.get("/", headers={"Host": "bare.example.com"})
assert resp.status_code == 404
def test_host_with_port(self, website_client, storage, website_app):
self._setup_website(storage, website_app)
resp = website_client.get("/", headers={"Host": "mysite.example.com:5000"})
assert resp.status_code == 200
assert b"<h1>Home</h1>" in resp.data
def test_no_error_document(self, website_client, storage, website_app):
storage.create_bucket("no-err")
storage.put_object("no-err", "index.html", _stream(b"<h1>Home</h1>"))
storage.set_bucket_website("no-err", {"index_document": "index.html"})
store = website_app.extensions["website_domains"]
store.set_mapping("noerr.example.com", "no-err")
resp = website_client.get("/missing.html", headers={"Host": "noerr.example.com"})
assert resp.status_code == 404
assert b"Not Found" in resp.data