mirror of
https://github.com/calibrain/shelfmark.git
synced 2026-11-15 08:28:25 +00:00
splitsec2
a430341a93
I went through what Shelfmark does per search and per cover and measured the pieces that showed up. Four of them are cheap to fix, so this is one PR. Shelfmark runs on a single gevent worker, so any of these blocks every other request while it runs, and I'm assuming a lot of people run it on small hardware (a Pi, say). Cover cache. Every cache hit rewrote the whole `cache_index.json` just to bump the entry's last-access time. On my box that is 3.7 ms of CPU per hit at 500 entries and about 100 ms at 15,000 (2.2 MB written each time), and a results page asks for around 40 covers. The access time now stays in memory and the index is written at most every 30 seconds, or whenever something else saves it. A crash inside that window loses some access times, which only changes eviction order. Settings reload. `config.refresh()` rebuilt the cache by reading and parsing a tab's JSON file once per field, so about 250 parses per refresh, 100 ms of CPU, and the metadata search, providers and config routes each trigger it. It now reads each file once per rebuild (several tabs share `settings.json`, so the memo is keyed on the file path). Library match. When the library check is on, each search result is compared against every library entry, and the title was split into words again for every entry. The words are now computed once per result. I measured 33 ms per result at 5,000 library entries and 106 ms at 20,000, which is a second or more per page of 40 results. The matching itself is unchanged. Cover URL probe. `is_covers_cache_enabled()` creates and deletes a file in the config directory to check it is writable, and it runs for every cover, queue task and history row. The answer is remembered for 60 seconds. The probe is 0.045 ms on its own, but it is called a few hundred times per request in the worst case. Each change has a test that fails without it (call counts on the index saves, file opens during a refresh, tokenisation calls, and probe calls). Ruff, basedpyright on the changed files and the non-e2e suite pass. The timings are from a dev machine with an empty config, so the real numbers depend on cache and library size.
124 lines
4.0 KiB
Python
124 lines
4.0 KiB
Python
"""Tests for config file persistence, corruption recovery, and permissions."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import stat
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
|
|
def test_save_config_file_merges_existing_values_and_preserves_unknown_keys(tmp_path):
|
|
from shelfmark.core.settings_registry import load_config_file, save_config_file
|
|
|
|
config_dir = tmp_path
|
|
plugins_dir = config_dir / "plugins"
|
|
plugins_dir.mkdir(parents=True)
|
|
(plugins_dir / "downloads.json").write_text(
|
|
'{"existing": "value", "unknown": {"nested": true}}'
|
|
)
|
|
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", config_dir)
|
|
assert save_config_file("downloads", {"existing": "updated", "new": "value"}) is True
|
|
result = load_config_file("downloads")
|
|
|
|
assert result == {
|
|
"existing": "updated",
|
|
"new": "value",
|
|
"unknown": {"nested": True},
|
|
}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("filename", "contents"),
|
|
[
|
|
("missing", None),
|
|
("empty", ""),
|
|
("broken", "{ invalid json }"),
|
|
("partial", '{"key": "value"'),
|
|
],
|
|
)
|
|
def test_load_config_file_returns_empty_dict_for_missing_or_corrupted_files(
|
|
tmp_path: Path,
|
|
filename: str,
|
|
contents: str | None,
|
|
):
|
|
from shelfmark.core.settings_registry import load_config_file
|
|
|
|
plugins_dir = tmp_path / "plugins"
|
|
plugins_dir.mkdir(parents=True)
|
|
if contents is not None:
|
|
(plugins_dir / f"{filename}.json").write_text(contents)
|
|
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", tmp_path)
|
|
result = load_config_file(filename)
|
|
|
|
assert result == {}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"tab_name",
|
|
["../escape", "nested/plugin", "..", "."],
|
|
)
|
|
def test_get_config_file_path_rejects_path_traversal(tmp_path: Path, tab_name: str):
|
|
from shelfmark.core.settings_registry import _get_config_file_path
|
|
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", tmp_path)
|
|
with pytest.raises(ValueError, match="Invalid tab name"):
|
|
_get_config_file_path(tab_name)
|
|
|
|
|
|
def test_is_config_dir_writable_tracks_directory_state(tmp_path: Path):
|
|
from shelfmark.config.env import _is_config_dir_writable
|
|
|
|
writable_dir = tmp_path / "writable"
|
|
writable_dir.mkdir()
|
|
missing_dir = tmp_path / "missing"
|
|
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", writable_dir)
|
|
assert _is_config_dir_writable() is True
|
|
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", missing_dir)
|
|
assert _is_config_dir_writable() is False
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
hasattr(os, "geteuid") and os.geteuid() == 0, reason="Permission tests are unreliable as root"
|
|
)
|
|
def test_save_config_file_returns_false_when_config_dir_is_not_writable(tmp_path: Path):
|
|
from shelfmark.core.settings_registry import save_config_file
|
|
|
|
config_dir = tmp_path / "readonly"
|
|
config_dir.mkdir()
|
|
config_dir.chmod(stat.S_IRUSR | stat.S_IXUSR)
|
|
|
|
try:
|
|
with pytest.MonkeyPatch.context() as monkeypatch:
|
|
monkeypatch.setattr("shelfmark.config.env.CONFIG_DIR", config_dir)
|
|
assert save_config_file("downloads", {"key": "value"}) is False
|
|
finally:
|
|
config_dir.chmod(stat.S_IRWXU)
|
|
|
|
|
|
def test_covers_cache_probe_is_remembered_for_a_short_time(monkeypatch):
|
|
from shelfmark.config import env
|
|
|
|
probes: list[int] = []
|
|
monkeypatch.setattr(env, "_is_config_dir_writable", lambda: (probes.append(1), True)[1])
|
|
clock = [1000.0]
|
|
monkeypatch.setattr(env.time, "monotonic", lambda: clock[0])
|
|
|
|
for _ in range(5):
|
|
assert env._config_dir_writable_cached() is True
|
|
assert probes == [1]
|
|
|
|
clock[0] += env._WRITABLE_PROBE_TTL_SECONDS + 1
|
|
assert env._config_dir_writable_cached() is True
|
|
assert probes == [1, 1]
|