adminandClaude Opus 5
c91264c253
Pure move, no behaviour change. web.py 1221 -> 807 lines.
The reason is not file size but isolation of change. CLAUDE.md records
that the next step for detection, should flagging ever need improving, is
a spectral filter or an optional Silero VAD over candidate sections —
that work now lands entirely in isrweb/loudness.py and never has to open
the HTTP layer. The byte-level format code (FLAC frame parsing, CRC-8,
live header patching) is a second self-contained cluster, touched only
when a container format misbehaves.
isrweb/loudness.py 229 detector + its tuning constants
isrweb/audiofile.py 250 filename clock, WAV/FLAC headers, MIME types
web.py 807 cache, listing, handler, main()
Import direction is strictly web.py -> {loudness, audiofile}; the two
leaves import neither each other nor web.py, which is what lets the
detector be imported and tested without an HTTP server.
A package rather than flat modules because `audiofile` is a real PyPI
name and `detect` is generic enough to collide; a local file silently
shadows an installed one, which fails confusingly rather than loudly.
web.py stays at the repo root so `python web.py`, the docker-compose
command and the webui.html lookup are all unchanged.
Each module keeps its own optional numpy/soundfile try-import rather than
sharing one. That block cannot meaningfully diverge — if numpy is
installed every copy says True — and sharing it would stop isr.py being a
standalone file you can drop on a Pi and run.
Tests mirror the modules: test_loudness.py, test_audiofile.py, test_web.py
(+ unchanged test_isr.py). New tests/conftest.py owns the sys.path setup
that was previously an inline hack in test_isr.py — which only worked for
the other modules because that file happened to import first — and
provides the write_wav fixture the split would otherwise have duplicated.
Verified:
* 78 passed, same count as before the split; each test file also passes
standalone.
* All 21 moved functions diffed against HEAD:web.py — byte-identical.
* Import graph asserted acyclic; both leaves import with `web` absent
from sys.modules.
* An analysis cache written *before* the split still hits afterwards,
with identical sections — the one way a "pure" move could quietly
invalidate every user's cache.
* Endpoint smoke (analyze bounds, cache hit, cached_analysis in the
listing, clip Content-Length, 8-bit rejection) and the byte-serving
harness (ranges, download Range, HEAD, 405, live-header patching whole
and straddling) both re-run green.
* Dockerfile COPY set verified by building the image's file tree in a
temp dir and importing web.py with nothing else present.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
177 lines
6.6 KiB
Python
177 lines
6.6 KiB
Python
"""Tests for the adaptive loud-section detector in isrweb/loudness.py."""
|
||
|
||
import math
|
||
import wave
|
||
|
||
from isrweb.loudness import _loud_sections, _noise_floor_db, analyze_wav
|
||
|
||
WINDOW_DUR = 0.1 # 100 ms windows, as produced by WINDOW_SAMPLES at 48 kHz
|
||
|
||
|
||
def _run(rms, margin_db=12.0, min_gap=2.0, min_duration=0.5):
|
||
duration = len(rms) * WINDOW_DUR
|
||
return _loud_sections(rms, WINDOW_DUR, duration, margin_db, min_gap, min_duration)
|
||
|
||
|
||
def test_burst_above_quiet_floor_is_detected():
|
||
rms = [0.002] * 1200 # 2 min of quiet ambience (−54 dBFS)
|
||
rms[600:610] = [0.05] * 10 # 1 s burst at −26 dBFS (+28 dB)
|
||
sections = _run(rms)
|
||
assert len(sections) == 1
|
||
s = sections[0]
|
||
assert s['start'] == 60.0
|
||
assert 60.5 <= s['end'] <= 62.0
|
||
assert 26.0 <= s['score'] <= 30.0
|
||
|
||
|
||
def test_slow_ambience_swell_is_not_detected():
|
||
# Level rises 20 dB over 10 minutes and back down — e.g. rain setting in.
|
||
# The old fixed threshold would have flagged the entire loud half.
|
||
up = [0.002 * 10 ** (i / 6000 * 1.0) for i in range(6000)] # −54 → −34 dB
|
||
down = list(reversed(up))
|
||
assert _run(up + down) == []
|
||
|
||
|
||
def test_burst_still_detected_on_loud_ambience():
|
||
# Same +28 dB prominence as the quiet test, but on a 20 dB louder floor.
|
||
rms = [0.02] * 1200
|
||
rms[600:610] = [0.5] * 10
|
||
sections = _run(rms)
|
||
assert len(sections) == 1
|
||
assert sections[0]['start'] == 60.0
|
||
|
||
|
||
def test_min_rms_floor_suppresses_blips_in_digital_silence():
|
||
rms = [0.000001] * 1200
|
||
rms[600:605] = [0.004] * 5 # −48 dBFS: audible blip, but below MIN_RMS+12dB
|
||
assert _run(rms) == []
|
||
rms[600:605] = [0.05] * 5 # −26 dBFS clearly clears the clamped floor
|
||
assert len(_run(rms)) == 1
|
||
|
||
|
||
def test_min_gap_merges_nearby_bursts():
|
||
rms = [0.002] * 1200
|
||
rms[600:605] = [0.05] * 5
|
||
rms[615:620] = [0.05] * 5 # 1 s gap < 2 s min_gap → one section
|
||
rms[900:905] = [0.05] * 5 # 28 s away → separate section
|
||
sections = _run(rms)
|
||
assert len(sections) == 2
|
||
assert sections[0]['start'] == 60.0
|
||
assert sections[0]['end'] >= 61.5
|
||
assert sections[1]['start'] == 90.0
|
||
|
||
|
||
def test_min_duration_drops_subsecond_blips():
|
||
# Isolated single-window pops (clicks, single raindrops) spaced wider than
|
||
# min_gap must not each become their own section — this is what used to
|
||
# produce thousands of zero-length sections per day.
|
||
rms = [0.002] * 1200
|
||
for i in range(600, 660, 30): # 0.1 s blips, 3 s apart (> min_gap)
|
||
rms[i] = 0.05
|
||
assert _run(rms) == []
|
||
# With the filter disabled they are all reported
|
||
assert len(_run(rms, min_duration=0.0)) == 2
|
||
|
||
|
||
def test_min_duration_keeps_sections_at_or_above_it():
|
||
rms = [0.002] * 1200
|
||
rms[600:605] = [0.05] * 5 # exactly 0.5 s
|
||
sections = _run(rms, min_duration=0.5)
|
||
assert len(sections) == 1
|
||
assert sections[0]['start'] == 60.0
|
||
|
||
|
||
def test_min_duration_applies_after_gap_merging():
|
||
# Two sub-min_duration blips within min_gap merge into one section whose
|
||
# loud span exceeds min_duration — the merged section must survive.
|
||
rms = [0.002] * 1200
|
||
rms[600] = 0.05
|
||
rms[610] = 0.05 # 1 s apart < 2 s min_gap → merged, 1.1 s span
|
||
sections = _run(rms, min_duration=1.0)
|
||
assert len(sections) == 1
|
||
assert sections[0]['start'] == 60.0
|
||
assert sections[0]['end'] >= 61.0
|
||
|
||
|
||
def test_slow_swell_scores_near_zero_sharp_burst_scores_high():
|
||
# A ~10 s swell rises faster than the 30 s floor blocks can track, so it
|
||
# still flags — but its score must collapse (onset cap) so it ranks at the
|
||
# bottom, while a sharp burst with the same peak keeps its full score.
|
||
rms = [0.002] * 1200
|
||
for k in range(80): # rise −54 → −28 dB over 8 s
|
||
rms[400 + k] = 0.002 * 10 ** (26 * (k / 80) / 20)
|
||
rms[480:500] = [0.04] * 20 # hold 2 s at −28 dB
|
||
for k in range(80): # fall back over 8 s
|
||
rms[500 + k] = 0.04 * 10 ** (-26 * (k / 80) / 20)
|
||
rms[900:910] = [0.04] * 10 # sharp 1 s burst, same peak
|
||
sections = _run(rms)
|
||
assert len(sections) == 2
|
||
swell, burst = sections
|
||
assert swell['start'] < 50.0 < 90.0 <= burst['start']
|
||
assert burst['score'] >= 24.0 # ≈ full 26 dB prominence
|
||
assert swell['score'] <= 5.0 # capped by its slow onset
|
||
assert swell['score'] < burst['score']
|
||
|
||
|
||
def test_burst_at_file_start_keeps_full_score():
|
||
# No pre-event history to measure a rise against: the onset cap falls back
|
||
# to prominence above the floor, so events cut off by a file split are not
|
||
# punished as swells.
|
||
rms = [0.05] * 10 + [0.002] * 1190
|
||
sections = _run(rms)
|
||
assert len(sections) == 1
|
||
assert sections[0]['start'] == 0.0
|
||
assert sections[0]['score'] >= 24.0
|
||
|
||
|
||
def test_section_open_at_eof_ends_at_last_loud_window():
|
||
# Burst ends 1 s before EOF — less than min_gap, so the section is still
|
||
# open when the windows run out. It must end where the sound ended, not at
|
||
# the file duration; otherwise the clip carries a second of trailing
|
||
# silence and disagrees with every section closed mid-file.
|
||
rms = [0.002] * 1200
|
||
rms[1180:1190] = [0.05] * 10 # loud 118.0 → 119.0, file is 120.0 s
|
||
sections = _run(rms)
|
||
assert len(sections) == 1
|
||
assert sections[0]['start'] == 118.0
|
||
assert sections[0]['end'] == 119.0
|
||
|
||
|
||
def test_section_running_to_the_very_end_is_capped_at_duration():
|
||
rms = [0.002] * 1200
|
||
rms[1190:1200] = [0.05] * 10 # loud right up to EOF
|
||
sections = _run(rms)
|
||
assert len(sections) == 1
|
||
assert sections[0]['end'] == 120.0
|
||
|
||
|
||
def test_noise_floor_tracks_blocks_and_ignores_short_events():
|
||
quiet_db = 20 * math.log10(0.002)
|
||
db = [quiet_db] * 1200
|
||
db[600:650] = [-20.0] * 50 # 5 s event must not raise its own floor
|
||
floor = _noise_floor_db(db, WINDOW_DUR)
|
||
assert len(floor) == len(db)
|
||
assert all(abs(f - quiet_db) < 1.0 for f in floor)
|
||
|
||
|
||
def test_non_16_bit_wav_is_rejected_rather_than_misread(tmp_path, write_wav):
|
||
# RMS windowing decodes as int16 regardless of the declared sample width,
|
||
# so an 8-bit file used to produce meaningless sections with no warning.
|
||
path = tmp_path / 'eight_bit.wav'
|
||
with wave.open(str(path), 'wb') as wf:
|
||
wf.setnchannels(1)
|
||
wf.setsampwidth(1)
|
||
wf.setframerate(8000)
|
||
wf.writeframes(b'\x80' * 8000)
|
||
result = analyze_wav(path)
|
||
assert 'error' in result
|
||
assert '16-bit' in result['error']
|
||
|
||
|
||
def test_16_bit_wav_still_analyses(tmp_path, write_wav):
|
||
path = tmp_path / 'ok.wav'
|
||
write_wav(path)
|
||
assert 'error' not in analyze_wav(path)
|
||
|
||
|