mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-10 18:07:24 +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
203 lines
6.6 KiB
Python
203 lines
6.6 KiB
Python
"""End-to-end tests of ``check.py`` in dist and url mode."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
import runpy
|
|
import subprocess
|
|
import sys
|
|
from collections.abc import Callable
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from agent_ready.check import main
|
|
from agent_ready.tests import sitegen
|
|
|
|
LINE = re.compile(r"^(PASS|FAIL|SKIP) AR-(FIND|READ|ACT)-\d\d \S")
|
|
PKG = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
def run(capsys: pytest.CaptureFixture[str], *argv: str) -> tuple[int, list[str]]:
|
|
"""Run the CLI in-process; return exit code and output lines."""
|
|
code = main(list(argv))
|
|
lines = capsys.readouterr().out.splitlines()
|
|
bad = [ln for ln in lines if not LINE.match(ln)]
|
|
assert not bad, bad
|
|
return code, lines
|
|
|
|
|
|
def statuses(lines: list[str], ar_id: str) -> set[str]:
|
|
"""Return the set of statuses reported for ``ar_id``."""
|
|
return {ln.split()[0] for ln in lines if ln.split()[1] == ar_id}
|
|
|
|
|
|
def test_dist_good_passes(capsys: pytest.CaptureFixture[str], good_dir: Path) -> None:
|
|
code, lines = run(capsys, "dist", str(good_dir))
|
|
assert code == 0, "\n".join(lines)
|
|
assert not [ln for ln in lines if ln.startswith("FAIL")]
|
|
for ar_id in (
|
|
"AR-FIND-01",
|
|
"AR-FIND-03",
|
|
"AR-FIND-04",
|
|
"AR-READ-01",
|
|
"AR-READ-02",
|
|
"AR-READ-07",
|
|
"AR-READ-09",
|
|
):
|
|
found = statuses(lines, ar_id)
|
|
assert "PASS" in found and "FAIL" not in found, ar_id
|
|
assert statuses(lines, "AR-READ-11") == {"SKIP"}
|
|
assert statuses(lines, "AR-ACT-10") == {"SKIP"}
|
|
|
|
|
|
def test_dist_bad_fails_every_item(
|
|
capsys: pytest.CaptureFixture[str], bad_dir: Path
|
|
) -> None:
|
|
code, lines = run(capsys, "dist", str(bad_dir))
|
|
assert code == 1
|
|
for ar_id in (
|
|
"AR-FIND-01",
|
|
"AR-FIND-03",
|
|
"AR-FIND-04",
|
|
"AR-READ-01",
|
|
"AR-READ-02",
|
|
"AR-READ-03",
|
|
"AR-READ-06",
|
|
"AR-READ-07",
|
|
"AR-READ-08",
|
|
"AR-READ-09",
|
|
):
|
|
assert "FAIL" in statuses(lines, ar_id), ar_id
|
|
assert any("gptbot" in ln for ln in lines if "AR-FIND-01" in ln)
|
|
|
|
|
|
def test_dist_untagged_code_fails(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path
|
|
) -> None:
|
|
about = good_dir / "about/index.html"
|
|
about.write_text(about.read_text().replace(' class="language-python"', ""))
|
|
code, lines = run(capsys, "dist", str(good_dir))
|
|
assert code == 1
|
|
assert "FAIL" in statuses(lines, "AR-READ-05")
|
|
|
|
|
|
def test_dist_act_opt_in(capsys: pytest.CaptureFixture[str], good_dir: Path) -> None:
|
|
code, lines = run(capsys, "dist", str(good_dir), "--act")
|
|
assert code == 1
|
|
assert "FAIL" in statuses(lines, "AR-ACT-02")
|
|
|
|
|
|
def test_usage_errors(capsys: pytest.CaptureFixture[str], tmp_path: Path) -> None:
|
|
assert main(["dist", str(tmp_path / "missing")]) == 2
|
|
assert main(["url", "not-a-url"]) == 2
|
|
with pytest.raises(SystemExit) as exc:
|
|
main([])
|
|
assert exc.value.code == 2
|
|
|
|
|
|
def test_url_good_passes(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
code, lines = run(capsys, "url", serve(good_dir))
|
|
assert code == 0, "\n".join(lines)
|
|
assert statuses(lines, "AR-READ-02") == {"PASS"}
|
|
|
|
|
|
def test_url_spa_fallback_fails(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
"""Every path 200 text/html: a status-only check would wrongly pass."""
|
|
code, lines = run(capsys, "url", serve(good_dir, "spa"))
|
|
assert code == 1
|
|
for ar_id in (
|
|
"AR-FIND-01",
|
|
"AR-FIND-03",
|
|
"AR-FIND-04",
|
|
"AR-READ-01",
|
|
"AR-READ-02",
|
|
"AR-READ-07",
|
|
"AR-READ-09",
|
|
):
|
|
assert "FAIL" in statuses(lines, ar_id), ar_id
|
|
assert any("text/html" in ln for ln in lines if "AR-FIND-01" in ln)
|
|
assert any(
|
|
"does not exist" in ln for ln in lines if "AR-READ-06" in ln
|
|
) # HTML fallback != file
|
|
|
|
|
|
def test_url_json_404(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
code, lines = run(capsys, "url", serve(good_dir, "json404"))
|
|
assert code == 1
|
|
assert statuses(lines, "AR-READ-02") == {"PASS"}
|
|
assert "FAIL" in statuses(lines, "AR-FIND-01")
|
|
|
|
|
|
def test_url_blocked_agent(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
code, lines = run(capsys, "url", serve(good_dir, block_ua="GPTBot"))
|
|
assert code == 1
|
|
assert any(ln.startswith("FAIL AR-FIND-01") and "GPTBot" in ln for ln in lines)
|
|
|
|
|
|
def test_url_unreachable_is_3(
|
|
capsys: pytest.CaptureFixture[str], dead_url: str
|
|
) -> None:
|
|
assert main(["url", dead_url]) == 3
|
|
|
|
|
|
def test_entry_points_from_other_cwd(good_dir: Path, tmp_path: Path) -> None:
|
|
for cmd in (
|
|
["bash", str(PKG / "check.sh")],
|
|
[sys.executable, str(PKG / "check.py")],
|
|
):
|
|
proc = subprocess.run(
|
|
[*cmd, "dist", str(good_dir)],
|
|
cwd=tmp_path,
|
|
capture_output=True,
|
|
text=True,
|
|
check=False,
|
|
)
|
|
assert proc.returncode == 0, proc.stdout + proc.stderr
|
|
|
|
|
|
def test_dist_checks_every_page_url_caps_visibly(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
"""Dist mode ignores --max-pages; url mode names the cap instead of hiding it."""
|
|
sitegen.add_pages(good_dir, 6, broken_last=True)
|
|
code, lines = run(capsys, "dist", str(good_dir), "--max-pages", "3")
|
|
assert code == 1
|
|
assert any(ln.startswith("FAIL AR-READ-01") and "/p5/" in ln for ln in lines)
|
|
code, lines = run(capsys, "url", serve(good_dir), "--max-pages", "3")
|
|
assert any(ln.startswith("SKIP AR-READ-01 checked 3 of 8 pages") for ln in lines), (
|
|
lines
|
|
)
|
|
|
|
|
|
def test_url_act_mcp(
|
|
capsys: pytest.CaptureFixture[str], good_dir: Path, serve: Callable[..., str]
|
|
) -> None:
|
|
_, lines = run(capsys, "url", serve(good_dir), "--act")
|
|
assert statuses(lines, "AR-ACT-03") == {"PASS"}
|
|
assert statuses(lines, "AR-ACT-10") == {"PASS"}
|
|
assert "FAIL" in statuses(lines, "AR-ACT-07")
|
|
code, lines = run(capsys, "url", serve(good_dir, "spa"), "--act")
|
|
assert code == 1
|
|
assert statuses(lines, "AR-ACT-03") == {"FAIL"}
|
|
assert statuses(lines, "AR-ACT-10") == {"FAIL"}
|
|
|
|
|
|
def test_script_entry_point_in_process(good_dir: Path) -> None:
|
|
"""Run check.py as ``__main__`` here so the guard lines count for coverage."""
|
|
argv = ["check.py", "dist", str(good_dir)]
|
|
with pytest.MonkeyPatch.context() as patch:
|
|
patch.setattr(sys, "argv", argv)
|
|
patch.setattr(sys, "path", list(sys.path)) # check.py prepends to it
|
|
with pytest.raises(SystemExit) as exc:
|
|
runpy.run_path(str(PKG / "check.py"), run_name="__main__")
|
|
assert exc.value.code == 0
|