videocut/find_duplicates.py

129 lines
3.8 KiB
Python

#!/usr/bin/env python3
"""
Find duplicate files that share the same base ID (e.g., [LETTERS]-[DIGITS])
but differ only by extra suffix characters.
Examples:
NACR-996.mp4 vs NACR-996J.mp4 -> same base: NACR-996
NDWQ-008-C.mp4 vs NDWQ-008.mp4 -> same base: NDWQ-008
"""
import os
import re
import argparse
from collections import defaultdict
def extract_base_id(filename: str) -> str | None:
"""
Extract the base ID from a filename.
Matches pattern: [letters]-[digits], case-insensitive.
Returns the matched base ID (uppercased for case-insensitive comparison),
or None if no match.
"""
# Remove file extension first so suffixes in the stem don't confuse matching.
# But we need to match within the full filename (without extension).
stem, _ = os.path.splitext(filename)
# Match: one or more letters, a hyphen, one or more digits
# This is the core ID. We take the FIRST such match in the stem.
match = re.search(r'[a-zA-Z]+-\d+', stem)
if not match:
return None
return match.group(0).upper()
def find_duplicates(
folder: str,
extensions: set[str] | None = None,
skip_extensions: set[str] | None = None,
) -> dict[str, list[str]]:
"""
Scan `folder` for files, group by base ID, and return groups with >1 file.
Args:
folder: Path to the directory to scan.
extensions: If provided, only consider files with these extensions
(e.g., {'.mp4', '.mkv', '.avi'}). Case-insensitive.
skip_extensions: Extensions to always ignore (e.g., {'.srt'}).
Returns:
Dict mapping base_id -> list of filenames (duplicate groups).
"""
if skip_extensions is None:
skip_extensions = set()
groups: dict[str, list[str]] = defaultdict(list)
for entry in sorted(os.listdir(folder)):
full_path = os.path.join(folder, entry)
if not os.path.isfile(full_path):
continue
_, ext = os.path.splitext(entry)
ext_lower = ext.lower()
if ext_lower in skip_extensions:
continue
if extensions and ext_lower not in extensions:
continue
base_id = extract_base_id(entry)
if base_id:
groups[base_id].append(entry)
# Only return groups with duplicates
return {bid: files for bid, files in groups.items() if len(files) > 1}
def main():
parser = argparse.ArgumentParser(
description="Find duplicate files by base ID (e.g., NACR-996 / NACR-996J)"
)
parser.add_argument(
"folder",
nargs="?",
default=".",
help="Folder to scan (default: current directory)",
)
parser.add_argument(
"-e", "--extensions",
nargs="+",
default=None,
help="Only check files with these extensions (e.g., -e .mp4 .mkv)",
)
parser.add_argument(
"-s", "--skip",
nargs="+",
default=[".srt"],
help="Extensions to ignore (default: .srt)",
)
args = parser.parse_args()
folder = os.path.abspath(args.folder)
if not os.path.isdir(folder):
print(f"Error: '{folder}' is not a directory.", flush=True)
return
exts = {e.lower() if e.startswith('.') else f'.{e.lower()}' for e in args.extensions} if args.extensions else None
skips = {e.lower() if e.startswith('.') else f'.{e.lower()}' for e in args.skip}
dupes = find_duplicates(folder, exts, skips)
if not dupes:
print("No duplicate files found.", flush=True)
return
print(f"Found {len(dupes)} duplicate group(s):\n", flush=True)
for base_id, files in sorted(dupes.items()):
print(f" Base ID: {base_id}", flush=True)
for f in files:
print(f" -> {f}", flush=True)
print(flush=True)
if __name__ == "__main__":
main()