ghibili/transform_files.py

import json
import os
import re

def sanitize_filename(name):
    # Remove illegal characters for most filesystems and Jellyfin
    name = re.sub(r'[\\/:*?"<>|]', '', name)
    name = name.replace('【', '').replace('】', '')
    name = name.replace('《', '').replace('》', '')
    name = name.replace('（', '').replace('）', '')
    name = name.replace(' ', '.')
    name = re.sub(r'\.+', '.', name)  # Replace multiple dots with one
    return name.strip('.')


def transform_entry(entry):
    # Try to extract year and english title for Jellyfin
    year = None
    title = entry.get("english") or entry.get("chinese")
    chinese = entry.get("chinese", "")
    tmdb_id = entry.get("tmdb_id")
    # Extract year from chinese field if present
    m = re.match(r"(\d{4})[- ]", chinese)
    if m:
        year = m.group(1)
    # Build new filename: English.Title.Year.[tmdbid-<id>].ext
    transformed_files = []
    for f in entry.get("media_files", []):
        ext = os.path.splitext(f)[1]
        # If extension ends with '1' (e.g., .mp41, .mkv1), strip the '1'
        if len(ext) > 1 and ext[-1] == "1":
            ext = ext[:-1]
        if title:
            base = sanitize_filename(title)
            parts = [base]
            if year:
                parts.append(year)
            if tmdb_id:
                parts.append(f"[tmdbid-{tmdb_id}]")
            new_name = ".".join(parts) + ext
            transformed_files.append({
                "original": f,
                "suggested": os.path.join(os.path.dirname(f), new_name)
            })
        else:
            transformed_files.append({
                "original": f,
                "suggested": f
            })
    # Add Jellyfin-friendly fields
    result = dict(entry)
    result["jellyfin_title"] = sanitize_filename(title) if title else None
    result["jellyfin_year"] = year
    result["jellyfin_media_files"] = transformed_files
    return result


# def transform_entry(entry):
#     # Try to extract year and english title for Jellyfin
#     year = None
#     title = entry.get("english") or entry.get("chinese")
#     chinese = entry.get("chinese", "")
#     tmdb_id = entry.get("tmdb_id")
#     # Extract year from chinese field if present
#     m = re.match(r"(\d{4})[- ]", chinese)
#     if m:
#         year = m.group(1)
#     # Build new filename: English.Title.Year.[tmdbid-<id>].ext
#     transformed_files = []
#     for f in entry.get("media_files", []):
#         ext = os.path.splitext(f)[1]
#         if title:
#             base = sanitize_filename(title)
#             parts = [base]
#             if year:
#                 parts.append(year)
#             if tmdb_id:
#                 parts.append(f"[tmdbid-{tmdb_id}]")
#             new_name = ".".join(parts) + ext
#             transformed_files.append({
#                 "original": f,
#                 "suggested": os.path.join(os.path.dirname(f), new_name)
#             })
#         else:
#             transformed_files.append({
#                 "original": f,
#                 "suggested": f
#             })
#     # Add Jellyfin-friendly fields
#     result = dict(entry)
#     result["jellyfin_title"] = sanitize_filename(title) if title else None
#     result["jellyfin_year"] = year
#     result["jellyfin_media_files"] = transformed_files
#     return result


# def transform_entry(entry):
#     # Try to extract year and english title for Jellyfin
#     year = None
#     title = entry.get("english") or entry.get("chinese")
#     chinese = entry.get("chinese", "")
#     # Extract year from chinese field if present
#     m = re.match(r"(\d{4})[- ]", chinese)
#     if m:
#         year = m.group(1)
#     # Build new filename: English.Title.(Year).ext
#     transformed_files = []
#     for f in entry.get("media_files", []):
#         ext = os.path.splitext(f)[1]
#         if title:
#             if year:
#                 new_name = f"{sanitize_filename(title)}.{year}{ext}"
#             else:
#                 new_name = f"{sanitize_filename(title)}{ext}"
#             transformed_files.append({
#                 "original": f,
#                 "suggested": os.path.join(os.path.dirname(f), new_name)
#             })
#         else:
#             transformed_files.append({
#                 "original": f,
#                 "suggested": f
#             })
#     # Add Jellyfin-friendly fields
#     result = dict(entry)
#     result["jellyfin_title"] = sanitize_filename(title) if title else None
#     result["jellyfin_year"] = year
#     result["jellyfin_media_files"] = transformed_files
#     return result

def main():
    with open("ghibli_imdb_results.json", "r", encoding="utf-8") as f:
        data = json.load(f)
    transformed = {"matched": [], "unmatched": []}
    for section in ["matched", "unmatched"]:
        for entry in data.get(section, []):
            transformed[section].append(transform_entry(entry))
    with open("ghibli_jellyfin_ready.json", "w", encoding="utf-8") as f:
        json.dump(transformed, f, ensure_ascii=False, indent=2)

if __name__ == "__main__":
    main()