sizes.py

#! /bin/python3

from dataclasses import dataclass
from os import walk, stat
from os.path import join
from typing import Dict

sdk_dir="/mnt/c/Program Files/dotnet/sdk/9.0.100-preview.3.24204.13"

@dataclass
class DuplicateResult:
    file: str
    count: int
    size: int

    def __eq__(self, other: object) -> bool:
        return self.file == other.file
    
    def __ne__(self, value: object) -> bool:
        return self.file != value.file
    
    def __hash__(self) -> int:
        return hash(self.file)        

    def potential_win(self) -> int:
        return (self.count - 1) * self.size

all_files: Dict[str, DuplicateResult]=dict()

for (root, dirs, files) in walk(sdk_dir, topdown=True):
    for f in files:
        if f.endswith("resources.dll"):
            continue
        
        if f in all_files:
            all_files[f].count += 1
        else:
            stats=stat(join(root, f))
            all_files[f] = DuplicateResult(f, 1, stats.st_size)

def potential(f: DuplicateResult):
    return f.potential_win()

valid_files = [all_files[f] for f in all_files if all_files[f].count > 1]

valid_files.sort(reverse=True, key=potential)

for file in valid_files:
    print(f"{file.count}\t{file.potential_win()}\t{file.file}")