security-and-privacy/mat2
security-and-privacy
/
mat2
mirror of
1
0
Fork 0
Code Releases Activity

Fix the type annotations

This commit is contained in:
jvoisin 2023-01-28 15:57:20 +00:00
parent 1f73a16ef3
commit 39fb254e01
14 changed files with 81 additions and 77 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
libmat2/__init__.py
View File

@ -2,7 +2,7 @@
import enum
import importlib
from typing import Optional, Union
from typing import Optional, Union, Dict
from . import exiftool, video
@ -66,8 +66,9 @@ CMD_DEPENDENCIES = {
},
}
def check_dependencies() -> dict[str, dict[str, bool]]:
ret = dict() # type: dict[str, dict]
def check_dependencies() -> Dict[str, Dict[str, bool]]:
ret = dict() # type: Dict[str, Dict]
for key, value in DEPENDENCIES.items():
ret[key] = {

8
libmat2/abstract.py
View File

@ -1,7 +1,7 @@
import abc
import os
import re
from typing import Union
from typing import Union, Set, Dict
class AbstractParser(abc.ABC):
@ -9,8 +9,8 @@ class AbstractParser(abc.ABC):
It might yield `ValueError` on instantiation on invalid files,
and `RuntimeError` when something went wrong in `remove_all`.
"""
meta_list = set() # type: set[str]
mimetypes = set() # type: set[str]
meta_list = set() # type: Set[str]
mimetypes = set() # type: Set[str]
def __init__(self, filename: str) -> None:
"""
@ -33,7 +33,7 @@ class AbstractParser(abc.ABC):
self.sandbox = True
@abc.abstractmethod
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
"""Return all the metadata of the current file"""
@abc.abstractmethod

32
libmat2/archive.py
View File

@ -7,7 +7,7 @@ import tempfile
import os
import logging
import shutil
from typing import Pattern, Union, Any
from typing import Pattern, Union, Any, Set, Dict, List
from . import abstract, UnknownMemberPolicy, parser_factory
@ -44,16 +44,16 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
def __init__(self, filename):
super().__init__(filename)
# We ignore typing here because mypy is too stupid
self.archive_class = None # type: ignore
self.member_class = None # type: ignore
self.archive_class = None # type: ignore
self.member_class = None # type: ignore
# Those are the files that have a format that _isn't_
# supported by mat2, but that we want to keep anyway.
self.files_to_keep = set() # type: set[Pattern]
self.files_to_keep = set() # type: Set[Pattern]
# Those are the files that we _do not_ want to keep,
# no matter if they are supported or not.
self.files_to_omit = set() # type: set[Pattern]
self.files_to_omit = set() # type: Set[Pattern]
# what should the parser do if it encounters an unknown file in
# the archive?
@ -72,7 +72,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
# pylint: disable=unused-argument
return True # pragma: no cover
def _specific_get_meta(self, full_path: str, file_path: str) -> dict[str, Any]:
def _specific_get_meta(self, full_path: str, file_path: str) -> Dict[str, Any]:
""" This method can be used to extract specific metadata
from files present in the archive."""
# pylint: disable=unused-argument
@ -87,7 +87,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
@staticmethod
@abc.abstractmethod
def _get_all_members(archive: ArchiveClass) -> list[ArchiveMember]:
def _get_all_members(archive: ArchiveClass) -> List[ArchiveMember]:
"""Return all the members of the archive."""
@staticmethod
@ -97,7 +97,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
@staticmethod
@abc.abstractmethod
def _get_member_meta(member: ArchiveMember) -> dict[str, str]:
def _get_member_meta(member: ArchiveMember) -> Dict[str, str]:
"""Return all the metadata of a given member."""
@staticmethod
@ -128,8 +128,8 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
# pylint: disable=unused-argument
return member
def get_meta(self) -> dict[str, Union[str, dict]]:
meta = dict() # type: dict[str, Union[str, dict]]
def get_meta(self) -> dict[str, Union[str, Dict]]:
meta = dict() # type: Dict[str, Union[str, Dict]]
with self.archive_class(self.filename) as zin:
temp_folder = tempfile.mkdtemp()
@ -264,6 +264,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
class TarParser(ArchiveBasedAbstractParser):
mimetypes = {'application/x-tar'}
def __init__(self, filename):
super().__init__(filename)
# yes, it's tarfile.open and not tarfile.TarFile,
@ -336,7 +337,7 @@ class TarParser(ArchiveBasedAbstractParser):
return member
@staticmethod
def _get_member_meta(member: ArchiveMember) -> dict[str, str]:
def _get_member_meta(member: ArchiveMember) -> Dict[str, str]:
assert isinstance(member, tarfile.TarInfo) # please mypy
metadata = {}
if member.mtime != 0:
@ -358,7 +359,7 @@ class TarParser(ArchiveBasedAbstractParser):
archive.add(full_path, member.name, filter=TarParser._clean_member) # type: ignore
@staticmethod
def _get_all_members(archive: ArchiveClass) -> list[ArchiveMember]:
def _get_all_members(archive: ArchiveClass) -> List[ArchiveMember]:
assert isinstance(archive, tarfile.TarFile) # please mypy
return archive.getmembers() # type: ignore
@ -391,7 +392,8 @@ class TarXzParser(TarParser):
class ZipParser(ArchiveBasedAbstractParser):
mimetypes = {'application/zip'}
def __init__(self, filename):
def __init__(self, filename: str):
super().__init__(filename)
self.archive_class = zipfile.ZipFile
self.member_class = zipfile.ZipInfo
@ -412,7 +414,7 @@ class ZipParser(ArchiveBasedAbstractParser):
return member
@staticmethod
def _get_member_meta(member: ArchiveMember) -> dict[str, str]:
def _get_member_meta(member: ArchiveMember) -> Dict[str, str]:
assert isinstance(member, zipfile.ZipInfo) # please mypy
metadata = {}
if member.create_system == 3: # this is Linux
@ -439,7 +441,7 @@ class ZipParser(ArchiveBasedAbstractParser):
compress_type=member.compress_type)
@staticmethod
def _get_all_members(archive: ArchiveClass) -> list[ArchiveMember]:
def _get_all_members(archive: ArchiveClass) -> List[ArchiveMember]:
assert isinstance(archive, zipfile.ZipFile) # please mypy
return archive.infolist() # type: ignore

15
libmat2/audio.py
View File

@ -2,7 +2,7 @@ import mimetypes
import os
import shutil
import tempfile
from typing import Union
from typing import Union, Dict
import mutagen
@ -18,10 +18,10 @@ class MutagenParser(abstract.AbstractParser):
except mutagen.MutagenError:
raise ValueError
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
f = mutagen.File(self.filename)
if f.tags:
return {k:', '.join(map(str, v)) for k, v in f.tags.items()}
return {k: ', '.join(map(str, v)) for k, v in f.tags.items()}
return {}
def remove_all(self) -> bool:
@ -38,8 +38,8 @@ class MutagenParser(abstract.AbstractParser):
class MP3Parser(MutagenParser):
mimetypes = {'audio/mpeg', }
def get_meta(self) -> dict[str, Union[str, dict]]:
metadata = {} # type: dict[str, Union[str, dict]]
def get_meta(self) -> Dict[str, Union[str, Dict]]:
metadata = {} # type: Dict[str, Union[str, Dict]]
meta = mutagen.File(self.filename).tags
if not meta:
return metadata
@ -68,12 +68,12 @@ class FLACParser(MutagenParser):
f.save(deleteid3=True)
return True
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
meta = super().get_meta()
for num, picture in enumerate(mutagen.File(self.filename).pictures):
name = picture.desc if picture.desc else 'Cover %d' % num
extension = mimetypes.guess_extension(picture.mime)
if extension is None: # pragma: no cover
if extension is None: # pragma: no cover
meta[name] = 'harmful data'
continue
@ -98,6 +98,7 @@ class WAVParser(video.AbstractFFmpegParser):
'MIMEType', 'NumChannels', 'SampleRate', 'SourceFile',
}
class AIFFParser(video.AbstractFFmpegParser):
mimetypes = {'audio/aiff', 'audio/x-aiff'}
meta_allowlist = {'AvgBytesPerSec', 'BitsPerSample', 'Directory',

4
libmat2/bubblewrap.py
View File

@ -12,7 +12,7 @@ import shutil
import subprocess
import tempfile
import functools
from typing import Optional
from typing import Optional, List
__all__ = ['PIPE', 'run', 'CalledProcessError']
@ -33,7 +33,7 @@ def _get_bwrap_path() -> str:
def _get_bwrap_args(tempdir: str,
input_filename: str,
output_filename: Optional[str] = None) -> list[str]:
output_filename: Optional[str] = None) -> List[str]:
ro_bind_args = []
cwd = os.getcwd()

7
libmat2/epub.py
View File

@ -3,10 +3,11 @@ import re
import uuid
import zipfile
import xml.etree.ElementTree as ET # type: ignore
from typing import Any
from typing import Any, Dict
from . import archive, office
class EPUBParser(archive.ZipParser):
mimetypes = {'application/epub+zip', }
metadata_namespace = '{http://purl.org/dc/elements/1.1/}'
@ -28,7 +29,6 @@ class EPUBParser(archive.ZipParser):
}))
self.uniqid = uuid.uuid4()
def is_archive_valid(self):
super().is_archive_valid()
with zipfile.ZipFile(self.filename) as zin:
@ -37,7 +37,7 @@ class EPUBParser(archive.ZipParser):
if member_name.endswith('META-INF/encryption.xml'):
raise ValueError('the file contains encrypted fonts')
def _specific_get_meta(self, full_path, file_path) -> dict[str, Any]:
def _specific_get_meta(self, full_path, file_path) -> Dict[str, Any]:
if not file_path.endswith('.opf'):
return {}
@ -73,7 +73,6 @@ class EPUBParser(archive.ZipParser):
short_empty_elements=False)
return True
def __handle_tocncx(self, full_path: str) -> bool:
try:
tree, namespace = office._parse_xml(full_path)

6
libmat2/exiftool.py
View File

@ -4,7 +4,7 @@ import logging
import os
import shutil
import subprocess
from typing import Union
from typing import Union, Set, Dict
from . import abstract
from . import bubblewrap
@ -15,9 +15,9 @@ class ExiftoolParser(abstract.AbstractParser):
from a import file, hence why several parsers are re-using its `get_meta`
method.
"""
meta_allowlist = set() # type: set[str]
meta_allowlist = set() # type: Set[str]
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
try:
if self.sandbox:
out = bubblewrap.run([_get_exiftool_path(), '-json',

4
libmat2/harmless.py
View File

@ -1,5 +1,5 @@
import shutil
from typing import Union
from typing import Union, Dict
from . import abstract
@ -7,7 +7,7 @@ class HarmlessParser(abstract.AbstractParser):
""" This is the parser for filetypes that can not contain metadata. """
mimetypes = {'text/plain', 'image/x-ms-bmp'}
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
return dict()
def remove_all(self) -> bool:

13
libmat2/images.py
View File

@ -1,6 +1,6 @@
import os
import re
from typing import Union, Any
from typing import Union, Any, Dict
import cairo
@ -48,7 +48,7 @@ class SVGParser(exiftool.ExiftoolParser):
surface.finish()
return True
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
meta = super().get_meta()
# The namespace is mandatory, but only the …/2000/svg is valid.
@ -57,6 +57,7 @@ class SVGParser(exiftool.ExiftoolParser):
meta.pop('Xmlns')
return meta
class PNGParser(exiftool.ExiftoolParser):
mimetypes = {'image/png', }
meta_allowlist = {'SourceFile', 'ExifToolVersion', 'FileName',
@ -156,11 +157,12 @@ class TiffParser(GdkPixbufAbstractParser):
'FileTypeExtension', 'ImageHeight', 'ImageSize',
'ImageWidth', 'MIMEType', 'Megapixels', 'SourceFile'}
class PPMParser(abstract.AbstractParser):
mimetypes = {'image/x-portable-pixmap'}
def get_meta(self) -> dict[str, Union[str, dict]]:
meta = {} # type: dict[str, Union[str, dict[Any, Any]]]
def get_meta(self) -> Dict[str, Union[str, Dict]]:
meta = {} # type: Dict[str, Union[str, Dict[Any, Any]]]
with open(self.filename) as f:
for idx, line in enumerate(f):
if line.lstrip().startswith('#'):
@ -176,9 +178,10 @@ class PPMParser(abstract.AbstractParser):
fout.write(line)
return True
class HEICParser(exiftool.ExiftoolParser):
mimetypes = {'image/heic'}
meta_allowlist = {'SourceFile', 'ExifToolVersion', 'FileName','Directory',
meta_allowlist = {'SourceFile', 'ExifToolVersion', 'FileName', 'Directory',
'FileSize', 'FileModifyDate', 'FileAccessDate',
'FileInodeChangeDate', 'FilePermissions', 'FileType',
'FileTypeExtension', 'MIMEType', 'MajorBrand', 'MinorVersion',

15
libmat2/office.py
View File

@ -4,7 +4,7 @@ import logging
import os
import re
import zipfile
from typing import Pattern, Any
from typing import Pattern, Any, Tuple, Dict
import xml.etree.ElementTree as ET # type: ignore
@ -12,7 +12,8 @@ from .archive import ZipParser
# pylint: disable=line-too-long
def _parse_xml(full_path: str) -> tuple[ET.ElementTree, dict[str, str]]:
def _parse_xml(full_path: str) -> Tuple[ET.ElementTree, Dict[str, str]]:
""" This function parses XML, with namespace support. """
namespace_map = dict()
for _, (key, value) in ET.iterparse(full_path, ("start-ns", )):
@ -68,7 +69,6 @@ class MSOfficeParser(ZipParser):
'application/vnd.openxmlformats-officedocument.wordprocessingml.settings+xml',
}
def __init__(self, filename):
super().__init__(filename)
@ -218,7 +218,7 @@ class MSOfficeParser(ZipParser):
if 'w' not in namespace:
return True
parent_map = {c:p for p in tree.iter() for c in p}
parent_map = {c: p for p in tree.iter() for c in p}
elements_to_remove = list()
for element in tree.iterfind('.//w:nsid', namespace):
@ -229,7 +229,6 @@ class MSOfficeParser(ZipParser):
tree.write(full_path, xml_declaration=True)
return True
@staticmethod
def __remove_revisions(full_path: str) -> bool:
try:
@ -319,7 +318,6 @@ class MSOfficeParser(ZipParser):
for i in re.findall(r'<p:cNvPr id="([0-9]+)"', content):
self.__counters['cNvPr'].add(int(i))
@staticmethod
def __randomize_creationId(full_path: str) -> bool:
try:
@ -441,8 +439,8 @@ class MSOfficeParser(ZipParser):
with open(full_path, encoding='utf-8') as f:
try:
results = re.findall(r"<(.+)>(.+)</\1>", f.read(), re.I|re.M)
return {k:v for (k, v) in results}
results = re.findall(r"<(.+)>(.+)</\1>", f.read(), re.I | re.M)
return {k: v for (k, v) in results}
except (TypeError, UnicodeDecodeError):
# We didn't manage to parse the xml file
return {file_path: 'harmful content', }
@ -459,7 +457,6 @@ class LibreOfficeParser(ZipParser):
'application/vnd.oasis.opendocument.image',
}
def __init__(self, filename):
super().__init__(filename)

7
libmat2/pdf.py
View File

@ -7,7 +7,7 @@ import re
import logging
import tempfile
import io
from typing import Union
from typing import Union, Dict
import cairo
import gi
@ -18,6 +18,7 @@ from . import abstract
FIXED_PDF_VERSION = cairo.PDFVersion.VERSION_1_5
class PDFParser(abstract.AbstractParser):
mimetypes = {'application/pdf', }
meta_list = {'author', 'creation-date', 'creator', 'format', 'keywords',
@ -140,13 +141,13 @@ class PDFParser(abstract.AbstractParser):
return True
@staticmethod
def __parse_metadata_field(data: str) -> dict[str, str]:
def __parse_metadata_field(data: str) -> Dict[str, str]:
metadata = {}
for (_, key, value) in re.findall(r"<(xmp|pdfx|pdf|xmpMM):(.+)>(.+)</\1:\2>", data, re.I):
metadata[key] = value
return metadata
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
""" Return a dict with all the meta of the file
"""
metadata = {}

16
libmat2/torrent.py
View File

@ -1,5 +1,5 @@
import logging
from typing import Union
from typing import Union, Dict, List, Tuple
from . import abstract
@ -15,7 +15,7 @@ class TorrentParser(abstract.AbstractParser):
if self.dict_repr is None:
raise ValueError
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
metadata = {}
for key, value in self.dict_repr.items():
if key not in self.allowlist:
@ -56,7 +56,7 @@ class _BencodeHandler:
}
@staticmethod
def __decode_int(s: bytes) -> tuple[int, bytes]:
def __decode_int(s: bytes) -> Tuple[int, bytes]:
s = s[1:]
next_idx = s.index(b'e')
if s.startswith(b'-0'):
@ -66,7 +66,7 @@ class _BencodeHandler:
return int(s[:next_idx]), s[next_idx+1:]
@staticmethod
def __decode_string(s: bytes) -> tuple[bytes, bytes]:
def __decode_string(s: bytes) -> Tuple[bytes, bytes]:
colon = s.index(b':')
# FIXME Python3 is broken here, the call to `ord` shouldn't be needed,
# but apparently it is. This is utterly idiotic.
@ -76,7 +76,7 @@ class _BencodeHandler:
s = s[1:]
return s[colon:colon+str_len], s[colon+str_len:]
def __decode_list(self, s: bytes) -> tuple[list, bytes]:
def __decode_list(self, s: bytes) -> Tuple[List, bytes]:
ret = list()
s = s[1:] # skip leading `l`
while s[0] != ord('e'):
@ -84,7 +84,7 @@ class _BencodeHandler:
ret.append(value)
return ret, s[1:]
def __decode_dict(self, s: bytes) -> tuple[dict, bytes]:
def __decode_dict(self, s: bytes) -> Tuple[Dict, bytes]:
ret = dict()
s = s[1:] # skip leading `d`
while s[0] != ord(b'e'):
@ -113,10 +113,10 @@ class _BencodeHandler:
ret += self.__encode_func[type(value)](value)
return b'd' + ret + b'e'
def bencode(self, s: Union[dict, list, bytes, int]) -> bytes:
def bencode(self, s: Union[Dict, List, bytes, int]) -> bytes:
return self.__encode_func[type(s)](s)
def bdecode(self, s: bytes) -> Union[dict, None]:
def bdecode(self, s: bytes) -> Union[Dict, None]:
try:
ret, trail = self.__decode_func[s[0]](s)
except (IndexError, KeyError, ValueError) as e:

8
libmat2/video.py
View File

@ -3,7 +3,7 @@ import functools
import shutil
import logging
from typing import Union
from typing import Union, Dict
from . import exiftool
from . import bubblewrap
@ -12,7 +12,7 @@ from . import bubblewrap
class AbstractFFmpegParser(exiftool.ExiftoolParser):
""" Abstract parser for all FFmpeg-based ones, mainly for video. """
# Some fileformats have mandatory metadata fields
meta_key_value_allowlist = {} # type: dict[str, Union[str, int]]
meta_key_value_allowlist = {} # type: Dict[str, Union[str, int]]
def remove_all(self) -> bool:
if self.meta_key_value_allowlist:
@ -45,10 +45,10 @@ class AbstractFFmpegParser(exiftool.ExiftoolParser):
return False
return True
def get_meta(self) -> dict[str, Union[str, dict]]:
def get_meta(self) -> Dict[str, Union[str, Dict]]:
meta = super().get_meta()
ret = dict() # type: dict[str, Union[str, dict]]
ret = dict() # type: Dict[str, Union[str, Dict]]
for key, value in meta.items():
if key in self.meta_key_value_allowlist:
if value == self.meta_key_value_allowlist[key]:

16
libmat2/web.py
View File

@ -1,5 +1,5 @@
from html import parser, escape
from typing import Any, Optional
from typing import Any, Optional, Dict, List, Tuple, Set
import re
import string
@ -25,7 +25,7 @@ class CSSParser(abstract.AbstractParser):
f.write(cleaned)
return True
def get_meta(self) -> dict[str, Any]:
def get_meta(self) -> Dict[str, Any]:
metadata = {}
with open(self.filename, encoding='utf-8') as f:
try:
@ -44,10 +44,10 @@ class CSSParser(abstract.AbstractParser):
class AbstractHTMLParser(abstract.AbstractParser):
tags_blocklist = set() # type: set[str]
tags_blocklist = set() # type: Set[str]
# In some html/xml-based formats some tags are mandatory,
# so we're keeping them, but are discarding their content
tags_required_blocklist = set() # type: set[str]
tags_required_blocklist = set() # type: Set[str]
def __init__(self, filename):
super().__init__(filename)
@ -57,7 +57,7 @@ class AbstractHTMLParser(abstract.AbstractParser):
self.__parser.feed(f.read())
self.__parser.close()
def get_meta(self) -> dict[str, Any]:
def get_meta(self) -> Dict[str, Any]:
return self.__parser.get_meta()
def remove_all(self) -> bool:
@ -112,7 +112,7 @@ class _HTMLParser(parser.HTMLParser):
"""
raise ValueError(message)
def handle_starttag(self, tag: str, attrs: list[tuple[str, Optional[str]]]):
def handle_starttag(self, tag: str, attrs: List[Tuple[str, Optional[str]]]):
# Ignore the type, because mypy is too stupid to infer
# that get_starttag_text() can't return None.
original_tag = self.get_starttag_text() # type: ignore
@ -159,7 +159,7 @@ class _HTMLParser(parser.HTMLParser):
self.__textrepr += escape(data)
def handle_startendtag(self, tag: str,
attrs: list[tuple[str, Optional[str]]]):
attrs: List[Tuple[str, Optional[str]]]):
if tag in self.tag_required_blocklist | self.tag_blocklist:
meta = {k:v for k, v in attrs}
name = meta.get('name', 'harmful metadata')
@ -184,7 +184,7 @@ class _HTMLParser(parser.HTMLParser):
f.write(self.__textrepr)
return True
def get_meta(self) -> dict[str, Any]:
def get_meta(self) -> Dict[str, Any]:
if self.__validation_queue:
raise ValueError("Some tags (%s) were left unclosed in %s" % (
', '.join(self.__validation_queue),