apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-26 23:51:14 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: validate web.crawl start URLs

Browse source
This commit is contained in:
CREDO23 2026-07-23 18:52:32 +02:00
parent 797dd2df47
commit a123c95703
2 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
surfsense_backend/app/capabilities/web/crawl/schemas.py
View file

@ -18,6 +18,8 @@ from typing import Literal
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
from app.capabilities.core.validation import HttpUrlStr
MAX_START_URLS = 20 MAX_START_URLS = 20
"""Per-call cap on seed URLs: bounds a synchronous request's fan-out (05).""" """Per-call cap on seed URLs: bounds a synchronous request's fan-out (05)."""
@ -29,7 +31,7 @@ MAX_CRAWL_PAGES = 200
class CrawlInput(BaseModel): class CrawlInput(BaseModel):
startUrls: list[str] = Field( startUrls: list[HttpUrlStr] = Field(
min_length=1, min_length=1,
max_length=MAX_START_URLS, max_length=MAX_START_URLS,
description=( description=(

5
surfsense_backend/tests/unit/capabilities/web/crawl/test_schemas.py
View file

@ -20,6 +20,11 @@ def test_requires_at_least_one_start_url() -> None:
CrawlInput(startUrls=[]) CrawlInput(startUrls=[])
def test_rejects_malformed_start_url() -> None:
with pytest.raises(ValidationError):
CrawlInput(startUrls=["not-a-url"])
def test_camelcase_fields_and_defaults() -> None: def test_camelcase_fields_and_defaults() -> None:
model = CrawlInput(startUrls=["https://e.com"]) model = CrawlInput(startUrls=["https://e.com"])
assert model.startUrls == ["https://e.com"] assert model.startUrls == ["https://e.com"]