mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-10 22:27:01 +01:00
Krzysztof kuhy Rudnicki
89ed9bc95d
New package. Walks every thread on 4chan's /wsg/, downloads each video it has
not seen, and reviews them one at a time: mpv embedded in a Tk window via --wid
with Keep/Pass/Undo directly beneath the picture.
Dedupe is structural rather than a convention. Every post carrying a file also
carries md5 -- base64 MD5 of the whole file -- so it is the sqlite primary key.
An already-seen video costs zero bytes to skip and a byte-identical repost in
another thread collapses onto the existing row. Verified against a live file:
the API's Nz9OEKdMuMZEdYE6eLTKmA== matched base64(md5(bytes)) exactly.
Undo is unbounded and survives quitting: the verdict trail lives in the index,
not in memory, so yesterday's decisions can still be taken back.
No downloaded video is ever deleted. A pass moves the file to trash/ and leaves
it there; files.apply_move refuses to overwrite an existing destination, so the
guarantee holds by construction rather than per caller.
Three bugs only running it could find, each caught from evidence rather than
guesswork:
- the video stayed black: a <Configure> handler set mpv's geometry, fighting
the automatic sizing --wid already does
- playback never advanced: refresh() ran every tick and re-sent loadfile ~7x
a second, restarting the video continuously
- it froze on one video around the 26th while filenames kept advancing: mpv
pushes an event stream down the same socket and nothing drained it, so the
buffer filled and mpv stopped reading commands. Isolated to command #35
without a drain thread; all 60 honoured with one.
A five-lens review then found nine more, all reproduced before fixing: a failed
mpv start stranded the non-daemon worker forever; undo could clobber a file in
incoming/; a NUL-bearing md5 poisoned the index permanently; an oversized int
killed the worker with no event; gzip bombs on both hosts were accepted; the
board endpoints were fetched unconditionally forever; and Session.missing could
corrupt the undo trail.
mpv runs as a subprocess over its JSON IPC socket rather than via python-mpv,
which resolves libmpv at import time and would fail on CI while passing here.
Third-party surface is requests alone, already declared.
277 package tests, 100% branch coverage on all 22 modules, no suppressions.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
91 lines
2.9 KiB
Python
91 lines
2.9 KiB
Python
"""Tests for the file lifecycle transition function."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from python_pkg.wsg_grabber.constants import MAX_ATTEMPTS
|
|
from python_pkg.wsg_grabber.states import (
|
|
CLAIMABLE,
|
|
TERMINAL,
|
|
FileEvent,
|
|
FileState,
|
|
is_terminal,
|
|
next_state,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize("state", sorted(CLAIMABLE))
|
|
def test_claiming_starts_a_download(state: FileState) -> None:
|
|
assert next_state(state, FileEvent.CLAIMED, 0) is FileState.DOWNLOADING
|
|
|
|
|
|
@pytest.mark.parametrize("state", sorted(CLAIMABLE))
|
|
def test_upstream_deletion_before_download_is_terminal(state: FileState) -> None:
|
|
assert next_state(state, FileEvent.DELETED_UPSTREAM, 0) is FileState.GONE
|
|
|
|
|
|
def test_completed_download_becomes_reviewable() -> None:
|
|
assert next_state(FileState.DOWNLOADING, FileEvent.COMPLETED, 1) is FileState.READY
|
|
|
|
|
|
def test_missing_upstream_file_is_never_retried() -> None:
|
|
assert next_state(FileState.DOWNLOADING, FileEvent.NOT_FOUND, 1) is FileState.GONE
|
|
|
|
|
|
def test_transient_error_retries_until_the_attempt_budget_runs_out() -> None:
|
|
assert (
|
|
next_state(FileState.DOWNLOADING, FileEvent.TRANSIENT_ERROR, 1)
|
|
is FileState.FAILED
|
|
)
|
|
assert (
|
|
next_state(FileState.DOWNLOADING, FileEvent.TRANSIENT_ERROR, MAX_ATTEMPTS)
|
|
is FileState.GONE
|
|
)
|
|
|
|
|
|
def test_checksum_mismatch_retries_until_the_attempt_budget_runs_out() -> None:
|
|
assert (
|
|
next_state(FileState.DOWNLOADING, FileEvent.CHECKSUM_MISMATCH, 1)
|
|
is FileState.CORRUPT
|
|
)
|
|
assert (
|
|
next_state(FileState.DOWNLOADING, FileEvent.CHECKSUM_MISMATCH, MAX_ATTEMPTS)
|
|
is FileState.GONE
|
|
)
|
|
|
|
|
|
def test_verdicts_are_terminal() -> None:
|
|
assert next_state(FileState.READY, FileEvent.KEPT, 1) is FileState.KEPT
|
|
assert next_state(FileState.READY, FileEvent.PASSED, 1) is FileState.PASSED
|
|
|
|
|
|
def test_a_vanished_local_file_is_written_off() -> None:
|
|
assert next_state(FileState.READY, FileEvent.MISSING_LOCALLY, 1) is FileState.GONE
|
|
|
|
|
|
def test_ready_ignores_upstream_deletion() -> None:
|
|
"""The bytes are already ours; the post being deleted is irrelevant."""
|
|
with pytest.raises(ValueError, match="ready"):
|
|
next_state(FileState.READY, FileEvent.DELETED_UPSTREAM, 1)
|
|
|
|
|
|
def test_illegal_transition_out_of_downloading_raises() -> None:
|
|
with pytest.raises(ValueError, match="downloading"):
|
|
next_state(FileState.DOWNLOADING, FileEvent.KEPT, 1)
|
|
|
|
|
|
def test_illegal_transition_from_a_terminal_state_raises() -> None:
|
|
with pytest.raises(ValueError, match="illegal transition"):
|
|
next_state(FileState.GONE, FileEvent.CLAIMED, 0)
|
|
|
|
|
|
def test_terminal_states_are_exactly_the_three_end_points() -> None:
|
|
assert {FileState.KEPT, FileState.PASSED, FileState.GONE} == TERMINAL
|
|
for state in TERMINAL:
|
|
assert is_terminal(state)
|
|
for state in CLAIMABLE:
|
|
assert not is_terminal(state)
|
|
assert not is_terminal(FileState.READY)
|
|
assert not is_terminal(FileState.DOWNLOADING)
|