ingest.py

import pandas as pd
import plistlib
from dataclasses import dataclass, field
from typing import Optional
from pathlib import Path

@dataclass

class Track:
    track_id: int
    name: str
    artist: str
    album: str
    genre: Optional[str] = None
    year: Optional[int] = None
    play_count: Optional[int] = None
    loved: bool = False
    rating: Optional[int] = None
    duration: Optional[int] = None

def load_library(xml_path):
    xml_path = Path(xml_path)
    if not xml_path.exists():
        raise FileNotFoundError(f'File whose path is {xml_path}, could not be found.')

    with open(xml_path, "rb") as file:
        plist = plistlib.load(file)
    

    raw_tracks = plist.get("Tracks", {})
    tracks = []

    for tid, info in raw_tracks.items():
        if info.get('Podcast') or info.get('AudioBook') or info.get('Has Video'):
            continue
            
        tracks.append(Track(
            track_id= int(tid),
            name= info.get('Name', ''),
            artist= info.get('Artist', ''),
            album= info.get('Album', ''),
            genre= info.get('Genre'),
            year= info.get('Year'),
            play_count= info.get('Play Count', 0),
            loved= info.get('Loved', False),
            rating= info.get('Rating'),
            duration= info.get('Total Time'), 
        ))

    print(f'\n[ingest] | Loaded {len(tracks)} tracks from {xml_path} successfully.')

    return tracks

def filter_favourites(tracks, filter_by):

    if filter_by == 'loved':
        filtered = [track for track in tracks if track.loved]
    elif filter_by == 'rated':
        filtered = [track for track in tracks if track.rating and track.rating >= 50]
    elif filter_by == 'time played':
        counts = sorted([track.play_count or 0 for track in tracks])
        limit = counts[int(len(counts) * 0.75)]
        filtered = [track for track in tracks if (track.play_count or 0) >= limit]
    elif filter_by == 'all':
        filtered = tracks
    else:
        raise ValueError(f'Could not filter by that feature: {filter_by}')
    
    print(f'[filter] | Filtered the list of tracks by {filter_by} giving {len(filtered)} items.')
    
    return filtered

def convert_dataframe(tracks):
    return pd.DataFrame([vars(track) for track in tracks])