pathlibutil 0.1.4

inherits from pathlib.Path with methods for hashing, copying, deleting and more

pathlibutil

---

pathlibutil.Path inherits from pathlib.Path with some useful built-in python functions from shutil and hashlib

• Path.hexdigest() to calculate and Path.verify() for verification of hexdigest from a file
• Path.default_hash to configurate default hash algorithm for Path class (default: 'md5')
• Path.size() to get size in bytes of a file or directory
• Path.read_lines() to yield over all lines from a file until EOF
• contextmanager to change current working directory with with statement
• Path.copy() copy a file or directory to a new path destination
• Path.delete() delete a file or directory-tree
• Path.move() move a file or directory to a new path destination
• Path.make_archive() creates and Path.unpack_archive() uncompresses an archive from a file or directory
• Path.archive_formats to get all available archive formats

Installation

pip install pathlibutil

7zip support

to handle 7zip archives, an extra package py7zr>=0.20.2 is required!

# install as extra dependency
pip install pathlibutil[7z]

Usage

from pathlibutil import Path

readme = Path('README.md')

print(f'File size: {readme.size()} Bytes')

Example 1

Read a file and print its content and some file information to stdout.

Path().read_lines()

from pathlib import Path

readme = Path('README.md')

print('File content'.center(80, '='))

for line in readme.read_lines(encoding='utf-8'):
   print(line, end='')

print('EOF'.center(80, '='))

Example 2

Write a file with md5 checksums of all python files in the pathlibutil-directory.

Path().hexdigest()

from pathlib import Path

file = Path('pathlibutil.md5')

algorithm = file.suffix[1:]

with file.open('w') as f:
   f.write(
      f'# {algorithm} checksums generated with pathlibutil (https://pypi.org/project/pathlibutil/)\n\n')

   i = 0
   for i, filename in enumerate(Path('./pathlibutil').glob('*.py'), start=1):
      f.write(f'{filename.hexdigest(algorithm)} *{filename}\n')

print(f'\nwritten: {i:>5} {algorithm}-hashes to: {file}')

Example 3

Read a file with md5 checksums and verify them.

Path().verify(), Path.default_hash and contextmanager

from pathlib import Path

file = Path('pathlibutil.md5')

Path.default_hash = file.suffix[1:]

def no_comment(line: str) -> bool:
   return not line.startswith('#')

with file.parent as cwd:

   for line in filter(no_comment, file.read_lines()):
      try:
            digest, filename = line.strip().split(' *')
            verification = Path(filename).verify(digest)
      except ValueError as split_failed:
            continue
      except FileNotFoundError as verify_failed:
            tag = 'missing'
      else:
            tag = 'ok' if verification else 'fail

      print(f'{tag.ljust(len(digest), ".")} *{filename}')

Example 4

Search all pycache directories and free the memory.

Path().delete() and Path().size()

from pathlib import Path

mem = 0
i = 0

for i, cache in enumerate(Path('.').rglob('*/__pycache__/'), start=1):
      cache_size = cache.size()
      try:
            cache.delete(recursive=True)
      except OSError:
            print(f'Failed to delete {cache}')
      else:
            mem += cache_size

print(f'{i} cache directories deleted, {mem / 2**20:.2f} MB freed.')

Example 5

Inherit from pathlibutil.Path to register new a archive format. Specify a archive as keyword argument in the new subclass, which has to be the suffix without . of the archives. Implement a classmethod _register_archive_format() to register new archive formats.

Path().make_archive(), Path.archive_formats and Path().move()

import shutil
import pathlibutil

class RegisterFooBarFormat(pathlibutil.Path, archive='foobar'):
      @classmethod
      def _register_archive_format(cls):
      """ 
            implement new register functions for given `archive`
      """
      try:
            import <required_package_name>
      except ModuleNotFoundError:
            raise ModuleNotFoundError(
                  'pip install <required_package_name>'
            )

      def pack_foobar(base_name, base_dir, owner=None, group=None, dry_run=None, logger=None) -> str:
            """callable that will be used to unpack archives.

            Args:
                  base_name (`str`): name of the file to create
                  base_dir (`str`): directory to start archiving from, defaults to `os.curdir`
                  owner (`Any`, optional): as passed in `make_archive(*args, owner=None, **kwargs)`. Defaults to None.
                  group (`Any`, optional): as passed in `make_archive(*args, group=None, **kwargs)`. Defaults to None.
                  dry_run (`Any`, optional): as passed in `make_archive(*args, dry_run=None, **kwargs)`. 
                        Defaults to None.
                  logger (`logging.Logger`, optional): as passed in `make_archive(*args, logger=None, **kwargs)`. 
                        Defaults to None.
            
            Returns:
                  str: path of the new created archive
            """
            raise NotImplementedError('implement your own pack function')

      def unpack_foobar(archive, path, filter=None, extra_args=None) -> None:
            """callable that will be used to unpack archives. 

            Args:
                  archive (`str`): path of the archive
                  path (`str`): directory the archive must be extracted to
                  filter (`Any`, optional): as passed in `unpack_archive(*args, filter=None, **kwargs)`.
                        Defaults to None.
                  extra_args (`Sequence[Tuple[name, value]]`, optional): additional keyword arguments. 
                        as passd in `register_unpack_format(*args, extra_args=None, **kwargs)`. Defaults to None.
            """
            raise NotImplementedError('implement your own unpack function')

      shutil.register_archive_format(
            'foobar', pack_foobar, description='foobar archives'
      )
      shutil.register_unpack_format(
            'foobar', ['.foo.bar'], unpack_foobar
      )

file = pathlibutil.Path('README.md')

print(f"available archive formats: {file.archive_formats}")

archive = file.make_archive('README.foo.bar')

backup = archive.move('./backup/')

print(f'archive created: {archive.name} and moved to: {backup.parent}')