Server-scripts/audiobook_metadata/metadata_rank_from_list.py

#!/usr/bin/env python3

import argparse
import re
import subprocess
from pathlib import Path
from difflib import SequenceMatcher

AUDIO_EXTENSIONS = {
    ".mp3",
    ".m4b",
    ".m4a",
}

RED = "\033[31m"
GREEN = "\033[32m"
RESET = "\033[0m"
USE_KID3 = True
def normalize(text: str) -> str:
    return re.sub(r"[^a-z0-9]", "", text.lower())


def get_tag(path, tag):
    if USE_KID3:
        result = subprocess.run(
            ["kid3-cli", "-c", f"get {tag}", str(path)],
            capture_output=True,
            text=True,
            check=True,
        )
        return result.stdout.strip()

    # id3v2 frame mapping
    frames = {
        "album": "TALB",
        "artist": "TPE1",
        "title": "TIT2",
        "year": "TYER",
        "grouping": "TIT1",  # Content group description
        "work": "TIT1",      # No separate WORK frame in id3v2
    }

    frame = frames[tag]

    result = subprocess.run(
        ["id3v2", "-R", str(path)],
        capture_output=True,
        text=True,
        check=True,
    )

    for line in result.stdout.splitlines():
        if line.startswith(frame):
            return line.split(":", 1)[1].strip()

    return ""

def tag_file(path: Path, rank: int, year: str, dry_run: bool, replace_pattern: str=r"Top 100 SciFi Books" )
    work = get_tag(path, "work")
    grouping = get_tag(path, "grouping")
    existing_year = get_tag(path, "year")

    if work:
        tag = "work"
        existing = work
    elif grouping:
        tag = "grouping"
        existing = grouping
    else:
        tag = "grouping"
        existing = ""
    pattern = f"{replace_pattern} #\d+(?:\.\d+)?"

    if existing:
        if re.search(pattern, existing):
            new_group = re.sub(
                pattern,
                f"{replace} #{rank};",
                existing,
            )
        else:
            new_group = f"{existing}; {replace} #{rank};"
    else:
        new_group = f"{replace} #{rank};"

    new_group = re.sub(r";+", ";", new_group)
    # Skip if nothing changes
    if existing == new_group and existing_year == str(year):
        print("Skipping (already tagged)")
        return "skip"
    print(f"Would tag {path.name}: {new_group} {year}")

    if dry_run:
        return

    subprocess.run(
        [
            "kid3-cli",
            "-c", f'set {tag} "{new_group}"',
            "-c", f"set year {year}",
            str(path),
        ],
        check=True,
    )

def main():
    parser = argparse.ArgumentParser()

    parser.add_argument("library")
    parser.add_argument("booklist")
    parser.add_argument("--dry-run", action="store_true")
    parser.add_argument("--find-missing", action="store_true")

    args = parser.parse_args()

    library = Path(args.library)
    replace_pattern=Path(args.booklist).stem
    found = set()

    with open(args.booklist, encoding="utf-8") as f:
        books = [
            line.strip()
            for line in f
            if line.strip() and not line.startswith("#")
        ]

    author_dirs = {
        normalize(p.name): p
        for p in library.iterdir()
        if p.is_dir()
    }
    rank_list=[]
#    print(books)
    for line in books:
        line = line.strip()

        if not line:
            continue  # skip empty lines

        parts = line.split(" - ")

        if len(parts) == 4:
            rank, title, author, year = parts
        elif len(parts) == 3:
            rank, title, author = parts
            year = None
        else:
            raise ValueError(f"Invalid line: {line}")
        author_key = normalize(author)
        title_key = normalize(title)
        rank_list.append(rank)
        author_dir = author_dirs.get(author_key)

        if author_dir is None:
            print(f"{RED}AUTHOR{RESET} {author} ")
            continue

        book_dir = None
        best_score = 0.0

        for subdir in author_dir.rglob("*"):
            if not subdir.is_dir():
                continue
            score = SequenceMatcher(
                None,
                title_key,
                normalize(subdir.name),
            ).ratio()

            if score > best_score:
                best_score = score
                book_dir = subdir

        if best_score < 0.6:
            book_dir = None
            print(f"{RED}TITLE{RESET} {title}, Score {best_score} ")
            for subdir in author_dir.rglob("*"):
                if not subdir.is_dir():
                    continue
                else:
                    print(subdir)

            continue

        found.add(rank)

        print(f"{GREEN}FOUND{RESET}   #{rank:3} {title} in {book_dir}")

        if args.find_missing:
            continue

        for file in book_dir.iterdir():
            if file.suffix.lower() not in AUDIO_EXTENSIONS:
                continue

            ret=tag_file(file, rank, year, args.dry_run, replace_pattern)
            if ret == "skip":
                break
        #print("next")

if __name__ == "__main__":
    main()