mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-10 21:27:14 +01:00
Krzysztof kuhy Rudnicki
a0fb279b1b
New agent_ready/ package (dist and live-url modes, 100% branch coverage) checks robots, sitemap, llms.txt, ai-catalog, 404, no-JS text, markdown mirrors and JSON-LD. repo_contract gains web-repo detection and installs the agent-ready pre-commit hook, CI workflow and check_agent_ready.sh shim; scripts/check_agent_ready.sh is the shared entry point. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NBScELfMUiieK9ManFbS3Y
76 lines
2.2 KiB
Python
76 lines
2.2 KiB
Python
"""Backend edge cases: URL mapping, memoized failures, traversal, deadline."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from agent_ready.backends import DirSite, HttpSite, Response, Site
|
|
from agent_ready.report import Undeterminable
|
|
from agent_ready.tests.fakes import FakeHttp, resp
|
|
|
|
|
|
class FlakySite(Site):
|
|
"""Raises Undeterminable on every fetch and counts the attempts."""
|
|
|
|
live = True
|
|
|
|
def __init__(self) -> None:
|
|
super().__init__("https://flaky.test")
|
|
self.attempts = 0
|
|
|
|
def _fetch(self, path: str, ua: str) -> Response:
|
|
self.attempts += 1
|
|
raise Undeterminable(f"{path}: boom")
|
|
|
|
|
|
def test_to_path_rejects_offsite_and_non_http(tmp_path: Path) -> None:
|
|
site = DirSite(tmp_path)
|
|
assert site.to_path("https://other.test/x") is None
|
|
assert site.to_path("mailto:a@b.test") is None
|
|
assert site.to_path("/rel/") == "/rel/"
|
|
assert site.to_path("https://dist.invalid") == "/"
|
|
|
|
|
|
def test_failures_are_memoized() -> None:
|
|
site = FlakySite()
|
|
for _ in range(2):
|
|
with pytest.raises(Undeterminable, match="boom"):
|
|
site.get("/x")
|
|
assert site.attempts == 1
|
|
|
|
|
|
def test_prefetch_swallows_failures_then_get_raises() -> None:
|
|
site = FlakySite()
|
|
site.prefetch(["/a", "/b", "/a"])
|
|
assert site.attempts == 2
|
|
with pytest.raises(Undeterminable):
|
|
site.get("/a")
|
|
|
|
|
|
def test_base_fetch_is_abstract() -> None:
|
|
with pytest.raises(NotImplementedError):
|
|
Site("https://x.test")._fetch("/", "ua")
|
|
|
|
|
|
def test_dist_never_serves_outside_root(tmp_path: Path) -> None:
|
|
root = tmp_path / "dist"
|
|
root.mkdir()
|
|
(tmp_path / "secret.txt").write_text("nope")
|
|
site = DirSite(root)
|
|
assert site.file_for("/../secret.txt") is None
|
|
assert site.get("/../secret.txt").status == 404
|
|
|
|
|
|
def test_exhausted_budget_is_undeterminable() -> None:
|
|
site = HttpSite("https://budget.test/anything", budget=0)
|
|
with pytest.raises(Undeterminable, match="time budget"):
|
|
site.get("/")
|
|
|
|
|
|
def test_fake_http_serves_canned_pages() -> None:
|
|
site = FakeHttp({"/": resp("hi")})
|
|
assert site.get("/").text == "hi"
|
|
assert site.get("/nope").status == 404
|