Files
music-mirror/tests/test_music_mirror.py
T
Emma Thorpe d5f67c6de5
Build and publish container / build (pull_request) Successful in 2m16s
feat: shorten paths that exceed the device's limit
Rockbox's MAX_PATH is 260, defined in firmware/include/fs_defines.h and used to
size the directory entry buffer in dir.h. It bounds the path as the device sees
it, so the directory the mirror is copied into spends part of the same budget;
--device-prefix accounts for that and defaults to /Music.

Over-budget paths are shortened from the deepest component outward. The track
name carries the least navigational value and the artist directory the most, so
the filename is cut first and the artist only if nothing else will serve. A
shortened component keeps its extension and gains four hex digits of the
original name: two long titles sharing a prefix cut to the same string
otherwise, and a silent collision between two tracks is a worse outcome than an
ugly filename.

The result is stable. The same source always yields the same shortened name, so
one pass does not rename what the last one wrote -- an unstable scheme would
churn the whole mirror every six hours. A path too deeply nested to fit without
reducing every component to nonsense is left alone and reported rather than
mangled.

Migration now tries more than one previous naming, because there is more than
one. A mirror already running with --fat32-safe holds sanitised but unshortened
paths, and matching only the original unsanitised name would have re-encoded
every one of them instead of moving it.

The checker gains the same two options, since it was measuring the
mirror-relative path against a limit that applies to the device-absolute one,
and so under-reported by the length of the destination directory.
2026-08-25 11:46:26 +01:00

708 lines
22 KiB
Python

import os
import shutil
import stat
import subprocess
import time
from pathlib import Path
import pytest
import music_mirror
def run(source, mirror, *extra):
return music_mirror.main(["--source", str(source), "--mirror", str(mirror), *extra])
def test_parse_quality_accepts_vbr_and_cbr():
assert music_mirror.parse_quality("V0") == ["-q:a", "0"]
assert music_mirror.parse_quality("v2") == ["-q:a", "2"]
assert music_mirror.parse_quality("256") == ["-b:a", "256k"]
def test_parse_quality_rejects_nonsense():
with pytest.raises(ValueError):
music_mirror.parse_quality("best")
def test_parse_interval_units():
assert music_mirror.parse_interval("90") == 90
assert music_mirror.parse_interval("30m") == 1800
assert music_mirror.parse_interval("6h") == 21600
assert music_mirror.parse_interval("1d") == 86400
def test_encodes_and_preserves_layout_and_tags(tmp_path, make_flac, probe_tag):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Test Artist" / "Test Album" / "03 Song.flac")
assert run(source, mirror) == 0
output = mirror / "Test Artist" / "Test Album" / "03 Song.mp3"
assert output.is_file()
assert probe_tag(output, "title") == "Test Title"
assert probe_tag(output, "album") == "Test Album"
def test_output_is_mp3(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
codec = subprocess.run(
[
"ffprobe",
"-v",
"error",
"-select_streams",
"a:0",
"-show_entries",
"stream=codec_name",
"-of",
"csv=p=0",
str(mirror / "a.mp3"),
],
check=True,
capture_output=True,
text=True,
).stdout.strip()
assert codec == "mp3"
def test_second_pass_skips_unchanged_files(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
first = (mirror / "a.mp3").stat().st_mtime_ns
run(source, mirror)
assert (mirror / "a.mp3").stat().st_mtime_ns == first
def test_changed_source_is_re_encoded(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
track = make_flac(source / "a.flac")
run(source, mirror)
before = (mirror / "a.mp3").stat().st_mtime
# A replaced file with a newer mtime is what a Lidarr quality upgrade
# looks like on disk.
later = time.time() + 120
os.utime(track, (later, later))
run(source, mirror)
assert (mirror / "a.mp3").stat().st_mtime > before
def test_deleted_source_is_pruned(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "a.flac")
make_flac(source / "Album" / "b.flac")
run(source, mirror)
(source / "Album" / "b.flac").unlink()
run(source, mirror)
assert (mirror / "Album" / "a.mp3").is_file()
assert not (mirror / "Album" / "b.mp3").exists()
def test_emptied_directory_is_removed(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Gone" / "a.flac")
run(source, mirror)
(source / "Gone" / "a.flac").unlink()
run(source, mirror)
assert not (mirror / "Gone").exists()
def test_no_prune_keeps_orphans(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
(source / "a.flac").unlink()
run(source, mirror, "--no-prune")
assert (mirror / "a.mp3").is_file()
def test_existing_mp3_is_copied_not_re_encoded(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
flac = make_flac(source / "a.flac")
subprocess.run(
["ffmpeg", "-loglevel", "error", "-y", "-i", str(flac), str(source / "b.mp3")],
check=True,
capture_output=True,
)
flac.unlink()
run(source, mirror)
assert (mirror / "b.mp3").read_bytes() == (source / "b.mp3").read_bytes()
def test_interrupted_copy_leaves_nothing_behind(tmp_path, make_flac, monkeypatch):
"""copy2 reproduces the source mtime, so a truncated copy left in the mirror
would be read as current by every later pass."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
flac = make_flac(source / "a.flac")
subprocess.run(
["ffmpeg", "-loglevel", "error", "-y", "-i", str(flac), str(source / "b.mp3")],
check=True,
capture_output=True,
)
flac.unlink()
def truncated(src, destination, **kwargs):
Path(destination).write_bytes(Path(src).read_bytes()[:64])
raise OSError("no space left on device")
monkeypatch.setattr(music_mirror.shutil, "copy2", truncated)
assert run(source, mirror) == 1
assert not (mirror / "b.mp3").exists()
assert list(mirror.rglob("*.part")) == []
def test_encoded_file_is_group_readable(tmp_path, make_flac, tight_umask):
"""mkstemp creates 0600 whatever the umask, so the bit has to be added."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
assert (mirror / "a.mp3").stat().st_mode & stat.S_IRGRP
def test_copied_file_is_group_readable(tmp_path, make_flac, tight_umask):
"""copy2 carries the source's mode across, and the source may be private."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
flac = make_flac(source / "a.flac")
subprocess.run(
["ffmpeg", "-loglevel", "error", "-y", "-i", str(flac), str(source / "b.mp3")],
check=True,
capture_output=True,
)
flac.unlink()
(source / "b.mp3").chmod(0o600)
run(source, mirror)
assert (mirror / "b.mp3").stat().st_mode & stat.S_IRGRP
def test_mirror_directories_are_group_traversable(tmp_path, make_flac, tight_umask):
"""A readable file is unreachable if the group cannot enter its directory."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Artist" / "Album" / "a.flac")
run(source, mirror)
for directory in (mirror, mirror / "Artist", mirror / "Artist" / "Album"):
mode = directory.stat().st_mode
assert mode & stat.S_IRGRP, directory
assert mode & stat.S_IXGRP, directory
def test_mirror_directories_survive_an_owner_hostile_umask(
tmp_path, make_flac, owner_hostile_umask
):
"""A umask carrying 0400 otherwise builds a tree the run cannot read back."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Artist" / "Album" / "a.flac")
# Applied only now: the library already exists, and the umask under test is
# the one the container starts this run with.
owner_hostile_umask()
run(source, mirror)
for directory in (mirror, mirror / "Artist", mirror / "Artist" / "Album"):
mode = directory.stat().st_mode
assert mode & stat.S_IRUSR, directory
assert mode & stat.S_IXUSR, directory
assert mode & stat.S_IRGRP, directory
assert mode & stat.S_IXGRP, directory
def test_private_mirror_file_is_repaired_without_re_encoding(tmp_path, make_flac):
"""A mirror written by an older version has a correct mtime, so nothing
else in the pass would revisit it."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
output = mirror / "a.mp3"
output.chmod(output.stat().st_mode & ~stat.S_IRGRP)
before = output.stat().st_mtime_ns
run(source, mirror)
assert output.stat().st_mode & stat.S_IRGRP
assert output.stat().st_mtime_ns == before
def test_dry_run_does_not_change_permissions(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
run(source, mirror)
output = mirror / "a.mp3"
output.chmod(output.stat().st_mode & ~stat.S_IRGRP)
run(source, mirror, "--dry-run")
assert not output.stat().st_mode & stat.S_IRGRP
def test_format_upgrade_replaces_rather_than_duplicating(tmp_path, make_flac):
"""Lidarr replacing an MP3 with a FLAC must not leave two mirror files."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
flac = make_flac(source / "Album" / "01 Song.flac")
subprocess.run(
["ffmpeg", "-loglevel", "error", "-y", "-i", str(flac), str(source / "Album" / "01 Song.mp3")],
check=True,
capture_output=True,
)
flac.unlink()
run(source, mirror)
assert sorted(p.name for p in (mirror / "Album").iterdir()) == ["01 Song.mp3"]
# The upgrade: the MP3 goes, a FLAC arrives at the same stem.
(source / "Album" / "01 Song.mp3").unlink()
make_flac(source / "Album" / "01 Song.flac", title="Upgraded")
run(source, mirror)
assert sorted(p.name for p in (mirror / "Album").iterdir()) == ["01 Song.mp3"]
def test_renamed_album_leaves_nothing_behind(tmp_path, make_flac):
"""A Lidarr rename is a delete plus an add; the old tree must not linger."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Artist" / "Album (2019)" / "01 Song.flac")
run(source, mirror)
(source / "Artist" / "Album (2019)").rename(source / "Artist" / "Album (2020)")
run(source, mirror)
assert (mirror / "Artist" / "Album (2020)" / "01 Song.mp3").is_file()
assert not (mirror / "Artist" / "Album (2019)").exists()
def test_competing_sources_pick_the_lossless_one_and_stay_stable(tmp_path, make_flac, probe_tag):
"""Both a FLAC and an MP3 at one stem: the FLAC wins, and stays won."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac", title="From FLAC")
other = make_flac(tmp_path / "scratch" / "other.flac", title="From MP3")
subprocess.run(
["ffmpeg", "-loglevel", "error", "-y", "-i", str(other), str(source / "a.mp3")],
check=True,
capture_output=True,
)
# Age the loser well beyond the mtime tolerance, so "is it current?" gives
# a definite answer for it rather than one that depends on the clock.
older = time.time() - 3600
os.utime(source / "a.mp3", (older, older))
run(source, mirror)
assert probe_tag(mirror / "a.mp3", "title") == "From FLAC"
# The loser must not make the mirror look stale on the next pass, or every
# run would re-encode for ever.
first = (mirror / "a.mp3").stat().st_mtime_ns
run(source, mirror)
assert (mirror / "a.mp3").stat().st_mtime_ns == first
def test_uppercase_extension_is_not_pruned_and_re_encoded(tmp_path, make_flac):
"""A .FLAC source must not be treated as an orphan on the next pass."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
made = make_flac(source / "a.flac")
made.rename(source / "a.FLAC")
run(source, mirror)
first = (mirror / "a.mp3").stat().st_mtime_ns
run(source, mirror)
assert (mirror / "a.mp3").is_file()
assert (mirror / "a.mp3").stat().st_mtime_ns == first
def test_whole_library_deleted_empties_the_mirror(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "A" / "one.flac")
make_flac(source / "B" / "two.flac")
run(source, mirror)
shutil.rmtree(source / "A")
shutil.rmtree(source / "B")
run(source, mirror)
assert list(mirror.rglob("*.mp3")) == []
assert not (mirror / "A").exists()
assert not (mirror / "B").exists()
def test_dry_run_writes_nothing(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "a.flac")
assert run(source, mirror, "--dry-run") == 0
assert not (mirror / "a.mp3").exists()
def test_subdir_limits_the_pass_and_does_not_prune(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "One" / "a.flac")
make_flac(source / "Two" / "b.flac")
assert run(source, mirror, "--subdir", "One") == 0
assert (mirror / "One" / "a.mp3").is_file()
# Outside the requested directory: neither encoded nor treated as an orphan.
assert not (mirror / "Two").exists()
def test_external_cover_is_embedded(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "a.flac")
subprocess.run(
[
"ffmpeg",
"-loglevel",
"error",
"-y",
"-f",
"lavfi",
"-i",
"color=c=red:s=64x64:d=1",
"-frames:v",
"1",
str(source / "Album" / "cover.jpg"),
],
check=True,
capture_output=True,
)
run(source, mirror)
streams = subprocess.run(
[
"ffprobe",
"-v",
"error",
"-select_streams",
"v",
"-show_entries",
"stream=codec_name",
"-of",
"csv=p=0",
str(mirror / "Album" / "a.mp3"),
],
check=True,
capture_output=True,
text=True,
).stdout.strip()
assert streams # a picture stream is present
def test_mirror_inside_source_is_refused(tmp_path, make_flac):
source = tmp_path / "src"
make_flac(source / "a.flac")
assert run(source, source / "mp3") == 2
def test_missing_source_is_refused(tmp_path):
assert run(tmp_path / "nope", tmp_path / "dst") == 2
@pytest.mark.parametrize(
("name", "expected"),
[
("Kick Out the Epic Motherf**ker", "Kick Out the Epic Motherf__ker"),
("Where Are You?", "Where Are You_"),
("Song: Part 2", "Song_ Part 2"),
('"Heroes"', "_Heroes_"),
("trailing dot.", "trailing dot"),
("trailing space ", "trailing space"),
("...", "_"),
("Mötley Crüe", "Mötley Crüe"),
("perfectly ordinary", "perfectly ordinary"),
],
)
def test_fat32_safe_names(name, expected):
"""A name FAT32 will not take is a track that silently does not arrive."""
assert music_mirror.fat32_safe(name) == expected
def test_a_reserved_character_is_replaced_in_the_mirror_path(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Dada Life" / "Album" / "Kick Out the Epic Motherf**ker.flac")
run(source, mirror, "--fat32-safe")
assert (mirror / "Dada Life" / "Album" / "Kick Out the Epic Motherf__ker.mp3").is_file()
def test_without_the_flag_the_name_is_left_alone(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
assert (mirror / "Album" / "Where Are You?.mp3").is_file()
def test_an_existing_mirror_is_renamed_not_re_encoded(tmp_path, make_flac):
"""Turning the flag on changes the path of every track holding a reserved
character. Re-encoding those would be hours of work to produce files that
already exist byte for byte."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
before = mirror / "Album" / "Where Are You?.mp3"
contents = before.read_bytes()
stamp = before.stat().st_mtime_ns
run(source, mirror, "--fat32-safe")
after = mirror / "Album" / "Where Are You_.mp3"
assert after.is_file()
assert not before.exists()
assert after.read_bytes() == contents, "it was re-encoded rather than moved"
assert after.stat().st_mtime_ns == stamp
def test_names_colliding_only_by_case_are_caught(tmp_path, make_flac):
"""Two files here, one file on FAT32. Better found now than as a silent
overwrite partway through the copy."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Song.flac")
make_flac(source / "Album" / "SONG.flac")
run(source, mirror, "--fat32-safe")
written = sorted(p.name for p in (mirror / "Album").glob("*.mp3"))
assert len(written) == 1, written
def test_the_album_cover_is_copied_beside_the_tracks(tmp_path, make_flac, make_cover):
"""Rockbox looks for art on the filesystem; its search never touches the
picture embedded in the tag."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "a.flac")
make_cover(source / "Album" / "cover.jpg")
run(source, mirror)
assert (mirror / "Album" / "cover.jpg").is_file()
def test_a_copied_cover_is_group_readable(tmp_path, make_flac, make_cover, tight_umask):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "a.flac")
make_cover(source / "Album" / "cover.jpg")
run(source, mirror)
assert (mirror / "Album" / "cover.jpg").stat().st_mode & stat.S_IRGRP
def test_a_cover_left_without_tracks_is_pruned(tmp_path, make_flac, make_cover):
"""Otherwise the directory never looks empty and never goes."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Gone" / "a.flac")
make_cover(source / "Gone" / "cover.jpg")
run(source, mirror)
assert (mirror / "Gone" / "cover.jpg").is_file()
shutil.rmtree(source / "Gone")
run(source, mirror)
assert not (mirror / "Gone").exists()
def test_a_dry_run_reports_a_rename_not_an_encode(tmp_path, make_flac, caplog):
"""The difference between moving a file and re-encoding it is the
difference between a minute and an afternoon, so a dry run must not
describe the first as the second."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
with caplog.at_level("INFO"):
run(source, mirror, "--fat32-safe", "--dry-run")
assert "would rename" in caplog.text
assert "would encode" not in caplog.text
def test_a_dry_run_does_not_call_the_old_paths_orphans(tmp_path, make_flac, caplog):
"""Nothing was renamed, so they are still there -- but they are the files a
real run would move, not files it would delete."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
with caplog.at_level("INFO"):
run(source, mirror, "--fat32-safe", "--dry-run")
assert "would remove orphan" not in caplog.text
def test_a_dry_run_moves_nothing(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
run(source, mirror, "--fat32-safe", "--dry-run")
assert (mirror / "Album" / "Where Are You?.mp3").is_file()
assert not (mirror / "Album" / "Where Are You_.mp3").exists()
def test_renames_are_counted_separately_from_encodes(tmp_path, make_flac, caplog):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / "Where Are You?.flac")
run(source, mirror)
with caplog.at_level("INFO"):
run(source, mirror, "--fat32-safe")
assert "1 renamed" in caplog.text
assert "0 encoded" in caplog.text
def test_a_long_path_is_shortened_from_the_deepest_component(tmp_path, make_flac):
"""The track name carries the least navigational value and the artist the
most, so the filename is sacrificed before the album."""
artist = "A" * 60
album = "B" * 60
title = "C" * 150
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / artist / album / f"{title}.flac")
run(source, mirror, "--fat32-safe", "--max-path", "160", "--device-prefix", "/Music")
written = list(mirror.rglob("*.mp3"))
assert len(written) == 1
relative = written[0].relative_to(mirror)
assert relative.parts[0] == artist, "the artist directory should be untouched"
assert relative.parts[1] == album, "the album directory should be untouched"
assert len(str(relative)) <= 160 - len("Music") - 2
def test_shortening_is_stable_across_passes(tmp_path, make_flac):
"""An unstable name would rename every file on every pass, for ever."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / ("D" * 80) / ("E" * 80) / f"{'F' * 120}.flac")
run(source, mirror, "--fat32-safe", "--max-path", "180")
first = sorted(str(p.relative_to(mirror)) for p in mirror.rglob("*.mp3"))
stamp = next(mirror.rglob("*.mp3")).stat().st_mtime_ns
run(source, mirror, "--fat32-safe", "--max-path", "180")
assert sorted(str(p.relative_to(mirror)) for p in mirror.rglob("*.mp3")) == first
assert next(mirror.rglob("*.mp3")).stat().st_mtime_ns == stamp
def test_two_long_names_do_not_collide_after_shortening(tmp_path, make_flac):
"""They share a prefix and cut to the same string; the hash is what keeps
them apart."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
shared = "G" * 140
make_flac(source / "Album" / f"{shared}one.flac")
make_flac(source / "Album" / f"{shared}two.flac")
run(source, mirror, "--fat32-safe", "--max-path", "120")
assert len(list(mirror.rglob("*.mp3"))) == 2
def test_a_sanitised_mirror_is_renamed_rather_than_re_encoded_when_shortening(
tmp_path, make_flac
):
"""The previous naming is sanitised-but-not-shortened, not the original."""
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Album" / f"Where Are You? {'H' * 140}.flac")
run(source, mirror, "--fat32-safe", "--max-path", "400")
before = next(mirror.rglob("*.mp3"))
contents = before.read_bytes()
run(source, mirror, "--fat32-safe", "--max-path", "120")
after = next(mirror.rglob("*.mp3"))
assert after != before
assert after.read_bytes() == contents, "it was re-encoded rather than moved"
def test_shortening_only_applies_when_over_budget(tmp_path, make_flac):
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / "Artist" / "Album" / "Short Name.flac")
run(source, mirror, "--fat32-safe")
assert (mirror / "Artist" / "Album" / "Short Name.mp3").is_file()
def test_a_path_that_cannot_be_made_to_fit_is_reported(tmp_path, make_flac, caplog):
"""Too deeply nested to shorten without making every component unreadable."""
deep = Path(*["I" * 20 for _ in range(10)])
source = tmp_path / "src"
mirror = tmp_path / "dst"
make_flac(source / deep / "track.flac")
with caplog.at_level("WARNING"):
run(source, mirror, "--fat32-safe", "--max-path", "80")
assert "too" in caplog.text and "nested" in caplog.text