You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
SoulSync/core/imports/filename.py

93 lines
2.8 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

"""Filename parsing helpers used by import flows."""
from __future__ import annotations
import os
import re
from typing import Any, Dict
_TRACK_PATTERNS = (
r"^(\d+)\s*[-\.]\s*(.+?)\s*[-]\s*(.+)$",
r"^(.+?)\s*[-]\s*(.+)$",
r"^(\d+)\s*[-\.]\s*(.+)$",
)
def extract_track_number_from_filename(filename: str, title: str = None) -> int:
"""Extract track number from a filename. Returns 1 if not found."""
basename = os.path.splitext(os.path.basename(filename))[0].strip()
match = re.match(r"^\d[\-\.](\d{1,2})\s*[\-\.]\s*", basename)
if match:
num = int(match.group(1))
if 1 <= num <= 99:
return num
match = re.match(r"^\(?(\d{1,3})\)?\s*[\-\.)\]]\s*", basename)
if match:
num = int(match.group(1))
if 1 <= num <= 999:
return num
return 1
def parse_filename_metadata(filename: str) -> Dict[str, Any]:
"""Extract artist/title/album hints from a loose filename."""
raw_path = str(filename or "")
normalized_path = raw_path.replace("\\", "/")
base_name = os.path.splitext(os.path.basename(normalized_path))[0]
result: Dict[str, Any] = {
"artist": "",
"title": "",
"album": "",
"track_number": None,
}
if not base_name:
return result
for pattern in _TRACK_PATTERNS:
match = re.match(pattern, base_name)
if not match:
continue
groups = match.groups()
if len(groups) == 3:
try:
result["track_number"] = int(groups[0])
result["artist"] = result["artist"] or groups[1].strip()
result["title"] = result["title"] or groups[2].strip()
except ValueError:
result["artist"] = result["artist"] or groups[0].strip()
result["title"] = result["title"] or f"{groups[1]} - {groups[2]}".strip()
elif len(groups) == 2:
if groups[0].isdigit():
try:
result["track_number"] = int(groups[0])
result["title"] = result["title"] or groups[1].strip()
except ValueError:
pass
else:
result["artist"] = result["artist"] or groups[0].strip()
result["title"] = result["title"] or groups[1].strip()
break
if not result["title"]:
result["title"] = base_name
if not result["album"] and "/" in normalized_path:
path_parts = normalized_path.split("/")
for part in reversed(path_parts[:-1]):
if not part or part.startswith("@"):
continue
cleaned = re.sub(r"^\d+\s*[-\.]\s*", "", part).strip()
if len(cleaned) > 3:
result["album"] = cleaned
break
return result