Sone-162-javhd-today-04192024-javhd-today02-23-... Apr 2026

"filename_cleaned": "SONE-162 04192024", "has_date": true, "has_javhd": true, "word_count": 5, "digit_group_count": 3, "possible_quality": "unknown", "possible_part": 2

# Extract source (e.g., JAVHD) if "JAVHD" in filename.upper(): features["source"] = "JAVHD" SONE-162-JAVHD-TODAY-04192024-JAVHD-TODAY02-23-...

If you're building a classifier or search feature: "filename_cleaned": "SONE-162 04192024"

"raw_filename": "SONE-162-JAVHD-TODAY-04192024-JAVHD-TODAY02-23-...", "movie_id": "SONE-162", "source": "JAVHD", "release_date": "2024-04-19", "segment": "23", "is_duplicate_tag": True "possible_part": 2 # Extract source (e.g.

# Detect duplicate JAVHD-TODAY pattern if filename.count("JAVHD-TODAY") > 1: features["is_duplicate_tag"] = True

return features filename = "SONE-162-JAVHD-TODAY-04192024-JAVHD-TODAY02-23-..." print(parse_jav_filename(filename))