apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-10 22:32:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

refactor(connectors): remove legacy web-crawler KB indexer paths (keep enums)

Browse source
This commit is contained in:
CREDO23 2026-07-03 11:53:33 +02:00
parent e3ed3b2be3
commit ab6be6cbda
14 changed files with 4 additions and 1456 deletions
Download patch file Download diff file Expand all files Collapse all files

15
surfsense_backend/app/utils/validators.py
View file

@ -469,14 +469,6 @@ def validate_connector_config(
if not isinstance(value, list) or not value:
raise ValueError(f"{field_name} must be a non-empty list of strings")
def validate_initial_urls() -> None:
initial_urls = config.get("INITIAL_URLS", "")
if initial_urls and initial_urls.strip():
urls = [url.strip() for url in initial_urls.split("\n") if url.strip()]
for url in urls:
if not validators.url(url):
raise ValueError(f"Invalid URL format in INITIAL_URLS: {url}")
# Lookup table for connector validation rules
connector_rules = {
"SERPER_API": {"required": ["SERPER_API_KEY"], "validators": {}},
@ -562,13 +554,6 @@ def validate_connector_config(
# "validators": {}
# },
"LUMA_CONNECTOR": {"required": ["LUMA_API_KEY"], "validators": {}},
"WEBCRAWLER_CONNECTOR": {
"required": [], # No required fields - URLs are optional
"optional": ["INITIAL_URLS"],
"validators": {
"INITIAL_URLS": lambda: validate_initial_urls(),
},
},
}
rules = connector_rules.get(connector_type_str)