security-and-privacy/mat2
security-and-privacy/mat2
1
0
Fork 0
mirror of synced 2024-11-22 17:24:23 +01:00
Code Releases Activity

office: create policy for what to do about unknown members

Browse Source 
previously, encountering an unknown member meant that any parser of
this type would abort.

now, the user can set parser.unknown_member_policy to either 'omit' or
'keep' if they don't want the current action of 'abort'

note that this causes pylint to complain about branching depth for
remove_all() because of the nuanced error-handling.  I've disabled
this check.
This commit is contained in:
Daniel Kahn Gillmor 2018-08-31 15:25:46 -04:00
parent 9ce458cb3b
commit 4192a2daa3
1 changed files with 25 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
libmat2/office.py
View File

@ -40,6 +40,10 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
# no matter if they are supported or not. # no matter if they are supported or not.
files_to_omit = set() # type: Set[Pattern] files_to_omit = set() # type: Set[Pattern]
# what should the parser do if it encounters an unknown file in
# the archive? valid policies are 'abort', 'omit', 'keep'
unknown_member_policy = 'abort' # type: str
def __init__(self, filename): def __init__(self, filename):
super().__init__(filename) super().__init__(filename)
try: # better fail here than later try: # better fail here than later
@ -79,6 +83,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
return metadata return metadata
def remove_all(self) -> bool: def remove_all(self) -> bool:
# pylint: disable=too-many-branches
with zipfile.ZipFile(self.filename) as zin,\ with zipfile.ZipFile(self.filename) as zin,\
zipfile.ZipFile(self.output_filename, 'w') as zout: zipfile.ZipFile(self.output_filename, 'w') as zout:
@ -107,12 +112,24 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
# supported files that we want to clean then add # supported files that we want to clean then add
tmp_parser, mtype = parser_factory.get_parser(full_path) # type: ignore tmp_parser, mtype = parser_factory.get_parser(full_path) # type: ignore
if not tmp_parser: if not tmp_parser:
if self.unknown_member_policy == 'omit':
logging.warning("In file %s, omitting unknown element %s (format: %s)",
self.filename, item.filename, mtype)
continue
elif self.unknown_member_policy == 'keep':
logging.warning("In file %s, keeping unknown element %s (format: %s)",
self.filename, item.filename, mtype)
else:
if self.unknown_member_policy != 'abort':
logging.warning("Invalid unknown_member_policy %s, " +
"treating as 'abort'", self.unknown_member_policy)
shutil.rmtree(temp_folder) shutil.rmtree(temp_folder)
os.remove(self.output_filename) os.remove(self.output_filename)
logging.error("In file %s, element %s's format (%s) " + logging.error("In file %s, element %s's format (%s) " +
"isn't supported", "isn't supported",
self.filename, item.filename, mtype) self.filename, item.filename, mtype)
return False return False
if tmp_parser:
tmp_parser.remove_all() tmp_parser.remove_all()
os.rename(tmp_parser.output_filename, full_path) os.rename(tmp_parser.output_filename, full_path)