2018-04-01 12:06:50 +02:00
|
|
|
import abc
|
2018-04-30 23:46:37 +02:00
|
|
|
import os
|
2018-06-04 23:32:13 +02:00
|
|
|
from typing import Set, Dict
|
2018-04-01 12:06:50 +02:00
|
|
|
|
2018-06-04 20:43:28 +02:00
|
|
|
assert Set # make pyflakes happy
|
|
|
|
|
2018-04-04 23:21:48 +02:00
|
|
|
|
2018-04-01 12:06:50 +02:00
|
|
|
class AbstractParser(abc.ABC):
|
2018-08-30 23:11:35 +02:00
|
|
|
""" This is the base class of every parser.
|
|
|
|
It might yield `ValueError` on instantiation on invalid files.
|
2018-07-19 23:10:27 +02:00
|
|
|
"""
|
2018-06-04 20:39:27 +02:00
|
|
|
meta_list = set() # type: Set[str]
|
|
|
|
mimetypes = set() # type: Set[str]
|
2018-03-20 01:20:11 +01:00
|
|
|
|
2018-06-04 20:39:27 +02:00
|
|
|
def __init__(self, filename: str) -> None:
|
2018-07-19 23:10:27 +02:00
|
|
|
"""
|
|
|
|
:raises ValueError: Raised upon an invalid file
|
|
|
|
"""
|
2018-03-06 23:20:18 +01:00
|
|
|
self.filename = filename
|
2018-04-30 23:46:37 +02:00
|
|
|
fname, extension = os.path.splitext(filename)
|
|
|
|
self.output_filename = fname + '.cleaned' + extension
|
2018-03-06 23:20:18 +01:00
|
|
|
|
2018-04-01 12:06:50 +02:00
|
|
|
@abc.abstractmethod
|
2018-06-04 23:32:13 +02:00
|
|
|
def get_meta(self) -> Dict[str, str]:
|
2018-06-10 00:43:25 +02:00
|
|
|
pass # pragma: no cover
|
2018-03-06 23:20:18 +01:00
|
|
|
|
2018-04-01 12:06:50 +02:00
|
|
|
@abc.abstractmethod
|
2018-04-01 01:04:06 +02:00
|
|
|
def remove_all(self) -> bool:
|
2018-06-10 00:43:25 +02:00
|
|
|
pass # pragma: no cover
|
2018-04-14 21:23:31 +02:00
|
|
|
|
|
|
|
def remove_all_lightweight(self) -> bool:
|
2018-07-19 23:10:27 +02:00
|
|
|
""" This method removes _SOME_ metadata.
|
2018-07-21 02:46:48 +02:00
|
|
|
It might be useful to implement it for fileformats that do
|
2018-07-19 23:10:27 +02:00
|
|
|
not support non-destructive cleaning.
|
|
|
|
"""
|
2018-04-14 21:23:31 +02:00
|
|
|
return self.remove_all()
|