Files
planet/backend/app/services/datasource_connectivity.py
linkong fbca381512
Some checks failed
ci / backend (push) Has been cancelled
ci / frontend (push) Has been cancelled
ci / delivery (push) Has been cancelled
release / images (push) Has been cancelled
release: bump version to 0.62.0
2026-05-21 01:37:32 +08:00

466 lines
17 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Connectivity validation helpers for built-in datasource overrides."""
from __future__ import annotations
from datetime import UTC, datetime
import hashlib
import json
import os
from typing import Any
import httpx
from sqlalchemy import func, select
from app.core.data_sources import get_data_sources_config
from app.core.datasource_defaults import DEFAULT_DATASOURCES
from app.models.collected_data import CollectedData
from app.models.datasource import DataSource
from app.models.datasource_config import DataSourceConfig
from app.models.system_setting import SystemSetting
from app.services.barentswatch import (
BarentsWatchConfig,
_read_zshrc_env,
fetch_barentswatch_access_token,
resolve_barentswatch_config,
)
CONNECTIVITY_VALIDATION_KEY = "connectivity_validation"
CONNECTIVITY_STORE_CATEGORY = "datasource_connectivity_validations"
SUPPORTED_CREDENTIAL_PROVIDERS = {"barentswatch", "spacetrack", "aisstream"}
def _sha256_json(payload: Any) -> str:
encoded = json.dumps(payload, ensure_ascii=False, sort_keys=True, default=str).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
def _resolve_spacetrack_credentials() -> tuple[str, str, str]:
zshrc_env = _read_zshrc_env()
username = os.getenv("SPACETRACK_USERNAME") or zshrc_env.get("SPACETRACK_USERNAME") or ""
password = os.getenv("SPACETRACK_PASSWORD") or zshrc_env.get("SPACETRACK_PASSWORD") or ""
source = "environment" if os.getenv("SPACETRACK_USERNAME") or os.getenv("SPACETRACK_PASSWORD") else ""
if not source and (username or password):
source = "~/.zshrc"
return username, password, source or "missing"
def _resolve_spacetrack_credentials_with_override(
credential_override: dict[str, str] | None = None,
) -> tuple[str, str, str]:
if credential_override and (
credential_override.get("username") or credential_override.get("password")
):
return (
str(credential_override.get("username") or ""),
str(credential_override.get("password") or ""),
"draft",
)
return _resolve_spacetrack_credentials()
async def _resolve_aisstream_api_key(
db=None,
credential_override: dict[str, str] | None = None,
) -> tuple[str, str]:
if credential_override and credential_override.get("api_key"):
return str(credential_override["api_key"]), "draft"
env_key = os.getenv("AISSTREAM_API_KEY")
zshrc_key = _read_zshrc_env().get("AISSTREAM_API_KEY")
if db is not None:
result = await db.execute(
select(DataSourceConfig)
.where(DataSourceConfig.name == "aisstream_vessels")
.where(DataSourceConfig.is_active.is_(True))
)
record = result.scalar_one_or_none()
if record:
auth_config = record.auth_config or {}
runtime_config = record.config or {}
api_key = auth_config.get("api_key") or runtime_config.get("api_key")
if api_key:
return str(api_key), "datasource_config"
if env_key:
return env_key, "environment"
if zshrc_key:
return zshrc_key, "~/.zshrc"
return "", "missing"
def strip_connectivity_validation(config: dict | None) -> dict:
cleaned = dict(config or {})
cleaned.pop(CONNECTIVITY_VALIDATION_KEY, None)
return cleaned
def merge_connectivity_validation(existing_config: dict | None, next_config: dict | None) -> dict:
merged = strip_connectivity_validation(next_config)
validation = (existing_config or {}).get(CONNECTIVITY_VALIDATION_KEY)
if validation:
merged[CONNECTIVITY_VALIDATION_KEY] = validation
return merged
def get_connectivity_validation(config: DataSourceConfig | None) -> dict | None:
validation = (config.config or {}).get(CONNECTIVITY_VALIDATION_KEY) if config else None
return validation if isinstance(validation, dict) else None
async def build_builtin_connectivity_checksum(
source: str,
endpoint: str,
auth_type: str,
headers: dict | None,
config: dict | None,
db=None,
credential_override: dict[str, str] | None = None,
) -> tuple[str, dict[str, Any]]:
defaults = DEFAULT_DATASOURCES.get(source, {})
credential_provider = defaults.get("credential_provider")
credential_fingerprint = ""
credential_source = "none"
has_credentials = not defaults.get("requires_credentials", False)
if credential_provider == "barentswatch":
if credential_override:
client_id = credential_override.get("client_id", "")
client_secret = credential_override.get("client_secret", "")
credential_source = "draft"
else:
barentswatch_config = await resolve_barentswatch_config(db)
client_id = barentswatch_config.client_id
client_secret = barentswatch_config.client_secret
credential_source = barentswatch_config.credential_source
has_credentials = bool(client_id and client_secret)
credential_fingerprint = _sha256_json(
{
"client_id": client_id,
"client_secret": client_secret,
}
)
elif credential_provider == "spacetrack":
username, password, credential_source = _resolve_spacetrack_credentials_with_override(
credential_override
)
has_credentials = bool(username and password)
credential_fingerprint = _sha256_json(
{
"username": username,
"password": password,
}
)
elif credential_provider == "aisstream":
api_key, credential_source = await _resolve_aisstream_api_key(db, credential_override)
has_credentials = bool(api_key)
credential_fingerprint = _sha256_json({"api_key": api_key})
elif defaults.get("requires_credentials"):
credential_source = str(credential_provider or "unsupported")
checksum_payload = {
"source": source,
"endpoint": endpoint,
"auth_type": "none",
"headers": headers or {},
"config": strip_connectivity_validation(config),
"credential_provider": credential_provider or "none",
"credential_fingerprint": credential_fingerprint,
}
return _sha256_json(checksum_payload), {
"requires_credentials": bool(defaults.get("requires_credentials", False)),
"credential_provider": credential_provider,
"credential_source": credential_source,
"has_credentials": has_credentials,
}
async def test_builtin_connectivity(
source: str,
endpoint: str,
auth_type: str,
headers: dict | None,
config: dict | None,
db=None,
credential_override: dict[str, str] | None = None,
) -> dict[str, Any]:
defaults = DEFAULT_DATASOURCES.get(source)
if not defaults:
return {
"success": False,
"message": "未知内置采集器,无法执行连接校验。",
}
checksum, credential_context = await build_builtin_connectivity_checksum(
source,
endpoint,
auth_type,
headers,
config,
db,
credential_override,
)
if credential_context["requires_credentials"] and not credential_context["has_credentials"]:
return {
"success": False,
"checksum": checksum,
"stage": "credentials",
"message": "该采集器需要凭证,请先到采集器凭证设置中配置。",
"settings_tab": "collector_credentials",
**credential_context,
}
if (
credential_context["requires_credentials"]
and credential_context["credential_provider"] not in SUPPORTED_CREDENTIAL_PROVIDERS
):
return {
"success": False,
"checksum": checksum,
"stage": "credentials",
"message": "该采集器的凭证链路尚未接入,暂时无法完成连接校验。",
"settings_tab": "collector_credentials",
**credential_context,
}
request_headers = {str(key): str(value) for key, value in (headers or {}).items()}
request_config = strip_connectivity_validation(config)
timeout = float(request_config.get("timeout") or 30)
request_endpoint = endpoint
if credential_context["credential_provider"] == "aisstream":
if not str(request_endpoint).startswith(("ws://", "wss://")):
return {
"success": False,
"checksum": checksum,
"stage": "endpoint",
"message": "AISStream endpoint 必须是 ws:// 或 wss:// WebSocket 地址。",
**credential_context,
}
return {
"success": True,
"checksum": checksum,
"stage": "credentials",
"message": "AISStream 凭证已配置WebSocket endpoint 格式有效。",
**credential_context,
}
try:
async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
if credential_context["credential_provider"] == "barentswatch":
if credential_override:
barentswatch_config = BarentsWatchConfig(
endpoint=str(request_endpoint or ""),
client_id=str(credential_override.get("client_id") or ""),
client_secret=str(credential_override.get("client_secret") or ""),
credential_source="draft",
endpoint_source="draft",
)
else:
barentswatch_config = await resolve_barentswatch_config(db)
token = await fetch_barentswatch_access_token(client, barentswatch_config)
if not token:
return {
"success": False,
"checksum": checksum,
"stage": "token",
"message": "凭证可读取,但 token 响应中没有 access_token。",
"settings_tab": "collector_credentials",
**credential_context,
}
request_headers["Authorization"] = f"Bearer {token}"
elif credential_context["credential_provider"] == "spacetrack":
username, password, _source = _resolve_spacetrack_credentials_with_override(
credential_override
)
login_url = "https://www.space-track.org/ajaxauth/login"
login_response = await client.post(
login_url,
data={
"identity": username,
"password": password,
},
)
login_response.raise_for_status()
started = datetime.now(UTC)
async with client.stream("GET", request_endpoint, headers=request_headers) as response:
response.raise_for_status()
status_code = response.status_code
elapsed_ms = (datetime.now(UTC) - started).total_seconds() * 1000
return {
"success": True,
"checksum": checksum,
"stage": "endpoint",
"message": "连接验证成功。",
"status_code": status_code,
"response_time_ms": elapsed_ms,
**credential_context,
}
except httpx.HTTPStatusError as exc:
return {
"success": False,
"checksum": checksum,
"stage": "endpoint",
"message": f"连接验证失败HTTP {exc.response.status_code}",
"error": f"HTTP Error: {exc.response.status_code}",
**credential_context,
}
except httpx.HTTPError as exc:
return {
"success": False,
"checksum": checksum,
"stage": "network",
"message": f"连接验证失败:{exc.__class__.__name__}",
"error": str(exc),
**credential_context,
}
def make_success_validation(checksum: str, result: dict[str, Any]) -> dict[str, Any]:
return {
"checksum": checksum,
"status": "success",
"validated_at": datetime.now(UTC).isoformat(),
"status_code": result.get("status_code"),
"credential_source": result.get("credential_source"),
}
def is_builtin_validation_current(config: DataSourceConfig | None, checksum: str) -> bool:
validation = get_connectivity_validation(config)
return bool(
validation
and validation.get("status") == "success"
and validation.get("checksum") == checksum
)
async def get_connectivity_store(db) -> dict[str, Any]:
result = await db.execute(
select(SystemSetting).where(SystemSetting.category == CONNECTIVITY_STORE_CATEGORY)
)
record = result.scalar_one_or_none()
return dict(record.payload or {}) if record and isinstance(record.payload, dict) else {}
async def save_connectivity_success(
db,
source: str,
checksum: str,
result: dict[str, Any],
*,
connected_by: str,
) -> dict[str, Any]:
store = await get_connectivity_store(db)
validation = {
**make_success_validation(checksum, result),
"connected_by": connected_by,
}
store[source] = validation
existing = await db.execute(
select(SystemSetting).where(SystemSetting.category == CONNECTIVITY_STORE_CATEGORY)
)
record = existing.scalar_one_or_none()
if record is None:
db.add(SystemSetting(category=CONNECTIVITY_STORE_CATEGORY, payload=store))
else:
record.payload = store
return validation
async def load_builtin_override_config(db, source: str) -> DataSourceConfig | None:
result = await db.execute(
select(DataSourceConfig)
.where(DataSourceConfig.name == source)
.where(DataSourceConfig.is_active.is_(True))
)
return result.scalar_one_or_none()
async def get_builtin_effective_candidate(db, source: str) -> dict[str, Any]:
override = await load_builtin_override_config(db, source)
default_endpoint = get_data_sources_config().get_yaml_url(source)
return {
"name": source,
"endpoint": (override.endpoint if override and override.endpoint else default_endpoint) or "",
"auth_type": override.auth_type if override else "none",
"headers": override.headers if override else {},
"config": strip_connectivity_validation(override.config if override else {}),
}
async def has_collected_data(db, source: str) -> bool:
result = await db.execute(select(func.count(CollectedData.id)).where(CollectedData.source == source))
if (result.scalar() or 0) > 0:
return True
datasource_result = await db.execute(select(DataSource).where(DataSource.source == source))
datasource = datasource_result.scalar_one_or_none()
return bool(datasource and datasource.last_status == "success")
async def get_builtin_connection_status(
db,
source: str,
endpoint: str,
auth_type: str,
headers: dict | None,
config: dict | None,
) -> dict[str, Any]:
checksum, credential_context = await build_builtin_connectivity_checksum(
source,
endpoint,
auth_type,
headers,
config,
db,
)
store = await get_connectivity_store(db)
validation = store.get(source)
if isinstance(validation, dict) and validation.get("status") == "success":
if validation.get("checksum") == checksum:
return {
"connected": True,
"checksum": checksum,
"connected_by": validation.get("connected_by") or "connection_button",
"message": "当前配置已完成连接验证。",
**credential_context,
}
effective = await get_builtin_effective_candidate(db, source)
effective_checksum, _ = await build_builtin_connectivity_checksum(
source,
effective["endpoint"],
effective["auth_type"],
effective["headers"],
effective["config"],
db,
)
if checksum == effective_checksum and await has_collected_data(db, source):
return {
"connected": True,
"checksum": checksum,
"connected_by": "collection",
"message": "当前配置已有成功采集数据,视为已连接。",
**credential_context,
}
if isinstance(validation, dict) and validation.get("status") == "success":
return {
"connected": False,
"checksum": checksum,
"connected_by": None,
"message": "接口地址或凭证指纹已变化,请重新点击连接验证。",
**credential_context,
}
return {
"connected": False,
"checksum": checksum,
"connected_by": None,
"message": "当前配置尚未连接,请点击连接验证。",
**credential_context,
}