dp-zp-agent/test/test_rebuild_index.py
2026-07-28 23:56:03 +02:00

159 lines
3.9 KiB
Python

from __future__ import annotations
import multiprocessing
import subprocess
from pathlib import Path
import pytest
import scripts.rebuild_index as rebuild
def hold_lock(lock_path: str, ready, release) -> None:
with rebuild.acquire_reindex_lock(Path(lock_path)):
ready.set()
release.wait(timeout=10)
def test_only_one_process_can_reindex(tmp_path: Path) -> None:
lock_file = tmp_path / "reindex.lock"
context = multiprocessing.get_context("fork")
ready = context.Event()
release = context.Event()
process = context.Process(
target=hold_lock,
args=(str(lock_file), ready, release),
)
process.start()
try:
assert ready.wait(timeout=5)
with pytest.raises(
rebuild.ReindexInProgressError,
match="už prebieha",
):
with rebuild.acquire_reindex_lock(lock_file):
pass
finally:
release.set()
process.join(timeout=5)
assert process.exitcode == 0
with rebuild.acquire_reindex_lock(lock_file):
pass
def test_rebuild_runs_pipeline_in_correct_order(
tmp_path: Path,
monkeypatch: pytest.MonkeyPatch,
) -> None:
calls: list[str] = []
monkeypatch.setattr(
rebuild,
"git_pull",
lambda: calls.append("git_pull"),
)
monkeypatch.setattr(
rebuild,
"scan_pages",
lambda: calls.append("scan") or [{"path": "a"}],
)
monkeypatch.setattr(
rebuild,
"build_chunks",
lambda: calls.append("chunks") or [{"chunk_id": "a::0"}],
)
monkeypatch.setattr(
rebuild,
"build_database",
lambda: calls.append("database")
or {
"documents": 1,
"chunks": 1,
"fts_chunks": 1,
"tags": 0,
"categories": 0,
},
)
result = rebuild.rebuild_index(
pull_git=True,
lock_file=tmp_path / "lock",
)
assert calls == ["git_pull", "scan", "chunks", "database"]
assert result["documents_scanned"] == 1
assert result["chunks_created"] == 1
assert result["counts"]["fts_chunks"] == 1
def test_git_pull_uses_fast_forward_only(
tmp_path: Path,
monkeypatch: pytest.MonkeyPatch,
) -> None:
repo = tmp_path / "repo"
(repo / ".git").mkdir(parents=True)
captured = {}
def fake_run(args, **kwargs):
captured["args"] = args
captured["kwargs"] = kwargs
return subprocess.CompletedProcess(args, 0, stdout="OK", stderr="")
monkeypatch.setattr(rebuild.subprocess, "run", fake_run)
rebuild.git_pull(repo)
assert captured["args"] == ["git", "pull", "--ff-only"]
assert captured["kwargs"]["cwd"] == repo
assert captured["kwargs"]["timeout"] == rebuild.GIT_PULL_TIMEOUT_SECONDS
def test_git_pull_rejects_non_repository(tmp_path: Path) -> None:
directory = tmp_path / "not-repo"
directory.mkdir()
with pytest.raises(RuntimeError, match="Nie je to git repozitár"):
rebuild.git_pull(directory)
def test_git_pull_reports_timeout(
tmp_path: Path,
monkeypatch: pytest.MonkeyPatch,
) -> None:
repo = tmp_path / "repo"
(repo / ".git").mkdir(parents=True)
def timeout(*args, **kwargs):
raise subprocess.TimeoutExpired(cmd="git pull", timeout=120)
monkeypatch.setattr(rebuild.subprocess, "run", timeout)
with pytest.raises(RuntimeError, match="prekročil limit"):
rebuild.git_pull(repo)
def test_git_pull_reports_nonzero_exit(
tmp_path: Path,
monkeypatch: pytest.MonkeyPatch,
) -> None:
repo = tmp_path / "repo"
(repo / ".git").mkdir(parents=True)
monkeypatch.setattr(
rebuild.subprocess,
"run",
lambda *args, **kwargs: subprocess.CompletedProcess(
args[0],
1,
stdout="",
stderr="chyba",
),
)
with pytest.raises(RuntimeError, match="návratovým kódom 1"):
rebuild.git_pull(repo)