Emma Thorpe
658c70a3dc
Build and publish container / build (pull_request) Successful in 3m8s
Lidarr renames an artist or album folder, music-mirror prunes the old path and encodes the new one, and every entry in Apple Music pointing at the old path dies. Music offers no view of those, and the exclamation mark only appears once a track is touched. Reads the XML from Music's own Export Library rather than asking Music itself. A broken track makes AppleScript's `location` raise instead of returning a value, so a bulk query dies on the first one with error -1728 and a per-track loop costs an Apple event apiece. Checked against a single directory walk rather than a test per file. On a fifty-thousand-track library that is around seven thousand directory reads instead of fifty thousand stat calls, and over SMB each of those stats is a network round trip -- which is the difference between seconds and minutes. Two comparisons have to be loosened or most of the library reads as missing. macOS stores filenames decomposed while the share composes them, so the umlauts in Motley Crue are two different byte strings depending on which side wrote the name; both are normalised to NFC. And the share is very likely case-insensitive, so a file is not missing because someone capitalised it differently. The test stage now copies tools/ as well, since the suite covers this and the runtime image deliberately does not carry it.
116 lines
3.9 KiB
Python
Executable File
116 lines
3.9 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Report tracks in a Music library whose files are no longer on disk.
|
|
|
|
Reads the XML from Music's File > Library > Export Library. Asking Music itself
|
|
does not work: a broken track makes AppleScript's `location` raise rather than
|
|
return a value, so a bulk query dies on the first one with error -1728, and a
|
|
per-track loop costs an Apple event apiece.
|
|
|
|
The library is checked against a single directory walk rather than by testing
|
|
each file. Over SMB a per-file test is one network round trip per track --
|
|
fifty thousand of them -- where a walk reads each directory once and gets every
|
|
name in it back at once.
|
|
"""
|
|
|
|
import argparse
|
|
import os
|
|
import plistlib
|
|
import sys
|
|
import unicodedata
|
|
import urllib.parse
|
|
from pathlib import Path
|
|
|
|
|
|
def location_of(track):
|
|
"""Return the filesystem path a track points at, or None if it has none."""
|
|
location = track.get("Location")
|
|
if not location or not location.startswith("file://"):
|
|
return None
|
|
return Path(urllib.parse.unquote(urllib.parse.urlparse(location).path))
|
|
|
|
|
|
def key_for(path):
|
|
"""Return a comparison key for a path.
|
|
|
|
Normalised to NFC because macOS stores filenames decomposed and most
|
|
everything else composes them, so "Motley Crue" with its umlauts is two
|
|
different byte strings depending on which side wrote it. Casefolded because
|
|
the share is very likely case-insensitive and a file is not missing merely
|
|
because someone capitalised it differently.
|
|
"""
|
|
return unicodedata.normalize("NFC", str(path)).casefold()
|
|
|
|
|
|
def existing_under(roots):
|
|
"""Return every file below the given roots, keyed for comparison."""
|
|
found = set()
|
|
for root in roots:
|
|
for base, _, names in os.walk(root):
|
|
for name in names:
|
|
found.add(key_for(os.path.join(base, name)))
|
|
return found
|
|
|
|
|
|
def roots_of(paths, given):
|
|
"""Return the directories worth walking."""
|
|
if given:
|
|
return [Path(root) for root in given]
|
|
try:
|
|
return [Path(os.path.commonpath([str(path) for path in paths]))]
|
|
except ValueError:
|
|
# Tracks spread across separate volumes have no common parent.
|
|
return sorted({path.parents[-2] for path in paths if len(path.parents) > 1})
|
|
|
|
|
|
def main(argv=None):
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("library", help="Library.xml exported from Music")
|
|
parser.add_argument("--root", action="append", help="directory to scan; repeatable")
|
|
parser.add_argument("--limit", type=int, default=0, help="show at most this many")
|
|
args = parser.parse_args(argv)
|
|
|
|
with open(args.library, "rb") as handle:
|
|
library = plistlib.load(handle)
|
|
|
|
tracks = [
|
|
(track, location_of(track)) for track in library.get("Tracks", {}).values()
|
|
]
|
|
local = [(track, path) for track, path in tracks if path is not None]
|
|
if not local:
|
|
print("no local files in this library", file=sys.stderr)
|
|
return 0
|
|
|
|
roots = roots_of([path for _, path in local], args.root)
|
|
print(f"scanning {', '.join(str(root) for root in roots)}", file=sys.stderr)
|
|
present = existing_under(roots)
|
|
|
|
gone = [(track, path) for track, path in local if key_for(path) not in present]
|
|
for track, path in gone[: args.limit or None]:
|
|
print(
|
|
"\t".join(
|
|
(
|
|
track.get("Artist", ""),
|
|
track.get("Album", ""),
|
|
track.get("Name", ""),
|
|
str(path),
|
|
)
|
|
)
|
|
)
|
|
|
|
print(
|
|
f"\n{len(gone)} of {len(local)} local tracks are missing their file"
|
|
f" ({len(tracks) - len(local)} have no file at all)",
|
|
file=sys.stderr,
|
|
)
|
|
if gone and len(gone) == len(local):
|
|
print(
|
|
"Every single one is missing, which almost certainly means the share"
|
|
" is not mounted rather than that the library is empty.",
|
|
file=sys.stderr,
|
|
)
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|