Compare Multiple File Name With The Prefix Of Name In Same Directory

I have multiple .png and .json file in same directory . And I want to check where the files available in the directory are of same name or not like a.png & a.json, b.png &

Solution 1:

You may try this:

import os

_, _ ,files = os.walk('.').next()
json = [f[:-5] for f in files if f.endswith('.json')]
png  = [f[:-4] for f in files if f.endswith('.png')]

json_only = set(json) - set(png)
png_only = set(png) - set(json)

json_and_png = set(json) & set(png)

... etc...

Solution 2:

from pathlib import Path
print("TEST CASE::NAMING CONVENTIONS SHOULD BE START WITH GAME PREFIX ")
def get_invalid_files_from(directory: str) -> []:
    dir_path = Path(r"E:\abc\\xyz")
    parent_folder = dir_path.stem
    files = dir_path.rglob('*')
    return [str(f) for f in files if is_file_invalid(f, prefix=parent_folder)]

def is_file_invalid(file: Path, prefix: str) -> bool:
    return file.suffix.lower() in ['.png', '.json'] and not file.name.startswith(prefix)
testcase = True
invalid_files = get_invalid_files_from(r'E:\abc\\xyz')
#assert not invalid_files, 'Invalid file paths:\n' + '\n'.join(invalid_files)if invalid_files :
    testcase = Falseprint(r'Below given File found with invalid prefix:')
    print('\n'.join(invalid_files))
if not testcase:
    print("test case failed ")
else:
    print("Test Case Passed ")

Solution 3:

@lenik is on the right track, I believe using sets is the easiest way to get what you want. Here's a complete and tested solution using the pathlib module that lists any png/json files that do not have a matching pair in the provided folder and all sub-folders:

defget_unpaired_files(directory: str) -> []:
    dir_path = Path(directory).resolve()
    json_files = get_files_without_extension(dir_path, pattern='*.json')
    png_files = get_files_without_extension(dir_path, pattern='*.png')
    return [str(f) for f inset(json_files) ^ set(png_files)]

defget_files_without_extension(dir_path: Path, pattern: str) -> []:
    return [f.with_suffix('') for f in dir_path.rglob(pattern)]

Usage:

unpaired_files = get_unpaired_files(r'E:\abc')

if unpaired_files :
    print('Unpaired file paths were found:')
    print('\n'.join(unpaired_files))