2aff3dc210
The earlier validation-only filter only ran in the auto-search scoring path. SoundCloud preview snippets still leaked through: - The candidate-review modal cached raw search results (pre-validation), so previews were visible and clickable for manual retry — and the manual-pick download path bypassed validation entirely, downloading the preview anyway. - The not-found raw-results cache stored unfiltered top-20s. Lift the preview filter into a reusable filter_soundcloud_previews() helper and apply it at every entry point: validation scoring (still), modal-cache fallback when validation drops everything, and the not-found raw-results path. Previews now never reach the cache, the matcher, or the manual-pick UI. Drops candidates < 35s or below half the expected duration, gated on expected > 60s so genuine short tracks still pass. 7 new unit tests pin the helper. Also fixed a silent regression in core/downloads/task_worker.py's hybrid-fallback path. Cin-5 dropped the per-source attrs from the orchestrator (orch.soulseek, orch.youtube, etc.), but the fallback loop still resolved sources via getattr(orch, '<src>', None) — every lookup silently returned None, so remaining_sources came back empty and the fallback never ran. Now uses orch.client(name) like the rest of the codebase. Updated the test fake to expose client() too — the old test was passing because the loop was effectively dead.
92 lines
3.5 KiB
Python
92 lines
3.5 KiB
Python
"""Tests for core/downloads/validation.py — SoundCloud preview filter.
|
|
|
|
The SoundCloud anonymous tier serves a ~30s preview clip for tracks
|
|
gated behind Go+ / login. ``filter_soundcloud_previews`` drops these
|
|
candidates before they reach the matcher, the modal cache, or the
|
|
manual-pick download path.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
from core.downloads.validation import filter_soundcloud_previews
|
|
|
|
|
|
@dataclass
|
|
class _Track:
|
|
duration_ms: int
|
|
|
|
|
|
@dataclass
|
|
class _Candidate:
|
|
username: str
|
|
duration: Optional[int] # milliseconds
|
|
title: str = ''
|
|
|
|
|
|
def test_drops_soundcloud_30s_preview_when_expected_long():
|
|
"""A 30s SC candidate against a 5-minute expected track is the
|
|
canonical preview-snippet case — must be dropped."""
|
|
expected = _Track(duration_ms=338_000) # ~5:38
|
|
cands = [
|
|
_Candidate(username='soundcloud', duration=30_000, title='Preview'),
|
|
_Candidate(username='soundcloud', duration=338_000, title='Real'),
|
|
]
|
|
result = filter_soundcloud_previews(cands, expected)
|
|
assert len(result) == 1
|
|
assert result[0].title == 'Real'
|
|
|
|
|
|
def test_drops_under_half_expected_duration():
|
|
"""SC candidate at 100s against 300s expected = clearly truncated /
|
|
wrong content. Must be dropped even if not at the 30s boundary."""
|
|
expected = _Track(duration_ms=300_000)
|
|
cand = _Candidate(username='soundcloud', duration=100_000)
|
|
assert filter_soundcloud_previews([cand], expected) == []
|
|
|
|
|
|
def test_keeps_soundcloud_when_expected_track_is_short():
|
|
"""Genuinely short SC tracks (intros, sound effects, sub-minute
|
|
songs) must pass through when the expected track is also short.
|
|
Filter only kicks in when expected > 60s."""
|
|
expected = _Track(duration_ms=45_000) # 45s expected
|
|
cand = _Candidate(username='soundcloud', duration=30_000)
|
|
result = filter_soundcloud_previews([cand], expected)
|
|
assert result == [cand]
|
|
|
|
|
|
def test_does_not_filter_non_soundcloud_sources():
|
|
"""A 30s candidate from another streaming source isn't a SoundCloud
|
|
preview — leave it for the generic matching engine to score."""
|
|
expected = _Track(duration_ms=338_000)
|
|
yt = _Candidate(username='youtube', duration=30_000)
|
|
tidal = _Candidate(username='tidal', duration=30_000)
|
|
assert filter_soundcloud_previews([yt, tidal], expected) == [yt, tidal]
|
|
|
|
|
|
def test_returns_input_unchanged_without_expected_duration():
|
|
"""Without a Spotify-track / expected duration we can't reason
|
|
about previews — pass everything through."""
|
|
cands = [
|
|
_Candidate(username='soundcloud', duration=30_000),
|
|
_Candidate(username='soundcloud', duration=300_000),
|
|
]
|
|
assert filter_soundcloud_previews(cands, None) == cands
|
|
assert filter_soundcloud_previews(cands, _Track(duration_ms=0)) == cands
|
|
|
|
|
|
def test_empty_input_returns_empty_list():
|
|
assert filter_soundcloud_previews([], _Track(duration_ms=200_000)) == []
|
|
|
|
|
|
def test_keeps_soundcloud_candidate_at_threshold():
|
|
"""Boundary check: 35s candidate against 200s expected — exactly
|
|
at the 35s preview boundary, but 35s is also above
|
|
expected*0.5 (100s) check (35 < 100, so still drops). Use a
|
|
higher value to confirm the just-above threshold passes."""
|
|
expected = _Track(duration_ms=200_000) # 200s
|
|
# 110s passes both checks: > 35s AND > 100s (half of 200s)
|
|
cand = _Candidate(username='soundcloud', duration=110_000)
|
|
assert filter_soundcloud_previews([cand], expected) == [cand]
|