fix: drop some type fixme (#20344)

This commit is contained in:
yihong
2025-05-30 14:10:09 +08:00
committed by GitHub
parent 9b47f9f786
commit 5a991295e0
10 changed files with 43 additions and 45 deletions

View File

@ -1,5 +1,6 @@
from typing import Optional
from typing import Any, Optional
from core.ops.entities.config_entity import BaseTracingConfig
from core.ops.ops_trace_manager import OpsTraceManager, provider_config_map
from extensions.ext_database import db
from models.model import App, TraceAppConfig
@ -92,13 +93,12 @@ class OpsService:
except KeyError:
return {"error": f"Invalid tracing provider: {tracing_provider}"}
config_class, other_keys = (
provider_config_map[tracing_provider]["config_class"],
provider_config_map[tracing_provider]["other_keys"],
)
# FIXME: ignore type error
default_config_instance = config_class(**tracing_config) # type: ignore
for key in other_keys: # type: ignore
provider_config: dict[str, Any] = provider_config_map[tracing_provider]
config_class: type[BaseTracingConfig] = provider_config["config_class"]
other_keys: list[str] = provider_config["other_keys"]
default_config_instance: BaseTracingConfig = config_class(**tracing_config)
for key in other_keys:
if key in tracing_config and tracing_config[key] == "":
tracing_config[key] = getattr(default_config_instance, key, None)

View File

@ -173,26 +173,27 @@ class WebsiteService:
return crawl_status_data
@classmethod
def get_crawl_url_data(cls, job_id: str, provider: str, url: str, tenant_id: str) -> dict[Any, Any] | None:
def get_crawl_url_data(cls, job_id: str, provider: str, url: str, tenant_id: str) -> dict[str, Any] | None:
credentials = ApiKeyAuthService.get_auth_credentials(tenant_id, "website", provider)
# decrypt api_key
api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
# FIXME data is redefine too many times here, use Any to ease the type checking, fix it later
data: Any
if provider == "firecrawl":
crawl_data: list[dict[str, Any]] | None = None
file_key = "website_files/" + job_id + ".txt"
if storage.exists(file_key):
d = storage.load_once(file_key)
if d:
data = json.loads(d.decode("utf-8"))
stored_data = storage.load_once(file_key)
if stored_data:
crawl_data = json.loads(stored_data.decode("utf-8"))
else:
firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
result = firecrawl_app.check_crawl_status(job_id)
if result.get("status") != "completed":
raise ValueError("Crawl job is not completed")
data = result.get("data")
if data:
for item in data:
crawl_data = result.get("data")
if crawl_data:
for item in crawl_data:
if item.get("source_url") == url:
return dict(item)
return None
@ -211,23 +212,24 @@ class WebsiteService:
raise ValueError("Failed to crawl")
return dict(response.json().get("data", {}))
else:
api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
response = requests.post(
# Get crawl status first
status_response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id},
)
data = response.json().get("data", {})
if data.get("status") != "completed":
status_data = status_response.json().get("data", {})
if status_data.get("status") != "completed":
raise ValueError("Crawl job is not completed")
response = requests.post(
# Get processed data
data_response = requests.post(
"https://adaptivecrawlstatus-kir3wx7b3a-uc.a.run.app",
headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"},
json={"taskId": job_id, "urls": list(data.get("processed", {}).keys())},
json={"taskId": job_id, "urls": list(status_data.get("processed", {}).keys())},
)
data = response.json().get("data", {})
for item in data.get("processed", {}).values():
processed_data = data_response.json().get("data", {})
for item in processed_data.get("processed", {}).values():
if item.get("data", {}).get("url") == url:
return dict(item.get("data", {}))
return None