security-and-privacy/mat2
security-and-privacy/mat2
1
0
Fork 0
mirror of synced 2024-11-22 09:14:23 +01:00
Code Releases Activity

Parallelize the cli

Browse Source
This commit is contained in:
jvoisin 2019-06-05 13:28:34 -07:00
parent 13d71a2565
commit 88b95923ab
1 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
mat2
View File

@ -1,12 +1,13 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
import os import os
from typing import Tuple, Generator, List, Union from typing import Tuple, List, Union, Set
import sys import sys
import mimetypes import mimetypes
import argparse import argparse
import logging import logging
import unicodedata import unicodedata
import concurrent.futures
try: try:
from libmat2 import parser_factory, UNSUPPORTED_EXTENSIONS from libmat2 import parser_factory, UNSUPPORTED_EXTENSIONS
@ -18,6 +19,7 @@ except ValueError as e:
__version__ = '0.9.0' __version__ = '0.9.0'
# Make pyflakes happy # Make pyflakes happy
assert Set
assert Tuple assert Tuple
assert Union assert Union
@ -142,16 +144,18 @@ def show_parsers():
print('\n'.join(sorted(formats))) print('\n'.join(sorted(formats)))
def __get_files_recursively(files: List[str]) -> Generator[str, None, None]: def __get_files_recursively(files: List[str]) -> List[str]:
ret = set() # type: Set[str]
for f in files: for f in files:
if os.path.isdir(f): if os.path.isdir(f):
for path, _, _files in os.walk(f): for path, _, _files in os.walk(f):
for _f in _files: for _f in _files:
fname = os.path.join(path, _f) fname = os.path.join(path, _f)
if __check_file(fname): if __check_file(fname):
yield fname ret.add(fname)
elif __check_file(f): elif __check_file(f):
yield f ret.add(f)
return list(ret)
def main() -> int: def main() -> int:
arg_parser = create_arg_parser() arg_parser = create_arg_parser()
@ -184,9 +188,16 @@ def main() -> int:
logging.warning('Keeping unknown member files may leak metadata in the resulting file!') logging.warning('Keeping unknown member files may leak metadata in the resulting file!')
no_failure = True no_failure = True
for f in __get_files_recursively(args.files): files = __get_files_recursively(args.files)
if clean_meta(f, args.lightweight, policy) is False: # We have to use Processes instead of Threads, since
no_failure = False # we're using tempfile.mkdtemp, which isn't thread-safe.
with concurrent.futures.ProcessPoolExecutor() as executor:
futures = list()
for f in files:
future = executor.submit(clean_meta, f, args.lightweight, policy)
futures.append(future)
for future in concurrent.futures.as_completed(futures):
no_failure &= future.result()
return 0 if no_failure is True else -1 return 0 if no_failure is True else -1