Add more typing and use mypy in the CI

.gitlab-ci.yml

@@ -18,6 +18,14 @@ pyflakes:
   - apt-get -qqy install --no-install-recommends pyflakes3
   - pyflakes3 ./libmat2
 
+mypy:
+  stage: linting
+  script:
+  - apt-get -qqy update
+  - apt-get -qqy install --no-install-recommends python3-pip
+  - pip3 install mypy
+  - mypy mat2 libmat2/*.py --ignore-missing-imports
+
 tests:
   stage: test
   script:

libmat2/harmless.py

@@ -1,17 +1,18 @@
+from typing import Dict
 from . import abstract
 
 
 class HarmlessParser(abstract.AbstractParser):
     """ This is the parser for filetypes that do not contain metadata. """
-    mimetypes = {'application/xml', 'text/plain'}
+    mimetypes = {'application/xml', 'text/plain', 'application/rdf+xml'}
 
     def __init__(self, filename: str) -> None:
         super().__init__(filename)
         self.filename = filename
         self.output_filename = filename
 
-    def get_meta(self):
+    def get_meta(self) -> Dict[str, str]:
         return dict()
 
-    def remove_all(self):
+    def remove_all(self) -> bool:
         return True

libmat2/office.py

@@ -4,11 +4,15 @@ import shutil
 import tempfile
 import datetime
 import zipfile
+from typing import Dict, Set
 
 from . import abstract, parser_factory
 
+assert Set   # make pyflakes happy
 
 class ArchiveBasedAbstractParser(abstract.AbstractParser):
+    whitelist = set()  # type: Set[str]
+
     def _clean_zipinfo(self, zipinfo: zipfile.ZipInfo) -> zipfile.ZipInfo:
         zipinfo.compress_type = zipfile.ZIP_DEFLATED
         zipinfo.create_system = 3  # Linux
@@ -16,7 +20,7 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
         zipinfo.date_time = (1980, 1, 1, 0, 0, 0)
         return zipinfo
 
-    def _get_zipinfo_meta(self, zipinfo: zipfile.ZipInfo) -> dict:
+    def _get_zipinfo_meta(self, zipinfo: zipfile.ZipInfo) -> Dict[str, str]:
         metadata = {}
         if zipinfo.create_system == 3:
             #metadata['create_system'] = 'Linux'
@@ -27,25 +31,31 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
             metadata['create_system'] = 'Weird'
 
         if zipinfo.comment:
-            metadata['comment'] = zipinfo.comment
+            metadata['comment'] = zipinfo.comment  # type: ignore
 
         if zipinfo.date_time != (1980, 1, 1, 0, 0, 0):
-            metadata['date_time'] = datetime.datetime(*zipinfo.date_time)
+            metadata['date_time'] =str(datetime.datetime(*zipinfo.date_time))
 
         return metadata
 
 
     def _clean_internal_file(self, item: zipfile.ZipInfo, temp_folder: str,
                              zin: zipfile.ZipFile, zout: zipfile.ZipFile):
+        output = ''
         zin.extract(member=item, path=temp_folder)
-        tmp_parser, mtype = parser_factory.get_parser(os.path.join(temp_folder, item.filename))
+        if item.filename not in self.whitelist:
+            full_path = os.path.join(temp_folder, item.filename)
+            tmp_parser, mtype = parser_factory.get_parser(full_path)  # type: ignore
             if not tmp_parser:
                 print("%s's format (%s) isn't supported" % (item.filename, mtype))
                 return
             tmp_parser.remove_all()
-        zinfo = zipfile.ZipInfo(item.filename)
+            output = tmp_parser.output_filename
+        else:
+            output = os.path.join(temp_folder, item.filename)
+        zinfo = zipfile.ZipInfo(item.filename)  # type: ignore
         clean_zinfo = self._clean_zipinfo(zinfo)
-        with open(tmp_parser.output_filename, 'rb') as f:
+        with open(output, 'rb') as f:
             zout.writestr(clean_zinfo, f.read())
 
 
@@ -72,7 +82,8 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
                 if not metadata:  # better safe than sorry
                     metadata[item] = 'harmful content'
 
-            metadata = {**metadata, **self._get_zipinfo_meta(item)}
+            for key, value in self._get_zipinfo_meta(item).items():
+                metadata[key] = value
         zipin.close()
         return metadata
 
@@ -112,6 +123,8 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
         'application/vnd.oasis.opendocument.formula',
         'application/vnd.oasis.opendocument.image',
     }
+    whitelist = {'mimetype', 'manifest.rdf'}
+
 
     def get_meta(self):
         """
@@ -127,7 +140,8 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
                     metadata[key] = value
                 if not metadata:  # better safe than sorry
                     metadata[item] = 'harmful content'
-            metadata = {**metadata, **self._get_zipinfo_meta(item)}
+            for key, value in self._get_zipinfo_meta(item).items():
+                metadata[key] = value
         zipin.close()
         return metadata
 

libmat2/parser_factory.py

@@ -2,10 +2,12 @@ import glob
 import os
 import mimetypes
 import importlib
-from typing import TypeVar, List
+from typing import TypeVar, List, Tuple, Optional
 
 from . import abstract, unsupported_extensions
 
+assert Tuple  # make pyflakes happy
+
 T = TypeVar('T', bound='abstract.AbstractParser')
 
 def __load_all_parsers():
@@ -28,14 +30,14 @@ def _get_parsers() -> List[T]:
     return __get_parsers(abstract.AbstractParser)
 
 
-def get_parser(filename: str) -> (T, str):
+def get_parser(filename: str) -> Tuple[Optional[T], Optional[str]]:
     mtype, _ = mimetypes.guess_type(filename)
 
     _, extension = os.path.splitext(filename)
     if extension in unsupported_extensions:
         return None, mtype
 
-    for c in _get_parsers():
+    for c in _get_parsers():  # type: ignore
         if mtype in c.mimetypes:
             try:
                 return c(filename), mtype

libmat2/pdf.py

@@ -131,5 +131,6 @@ class PDFParser(abstract.AbstractParser):
                 metadata[key] = document.get_property(key)
         if 'metadata' in metadata:
             parsed_meta = self.__parse_metadata_field(metadata['metadata'])
-            return {**metadata, **parsed_meta}
+            for key, value in parsed_meta.items():
+                metadata[key] = value
         return metadata

libmat2/torrent.py

@@ -1,11 +1,12 @@
+from typing import Union, Tuple, Dict
 from . import abstract
 
 
 class TorrentParser(abstract.AbstractParser):
-    mimetypes = {b'application/x-bittorrent', }
+    mimetypes = {'application/x-bittorrent', }
     whitelist = {b'announce', b'announce-list', b'info'}
 
-    def get_meta(self) -> dict:
+    def get_meta(self) -> Dict[str, str]:
         metadata = {}
         with open(self.filename, 'rb') as f:
             d = _BencodeHandler().bdecode(f.read())
@@ -54,7 +55,7 @@ class _BencodeHandler(object):
         }
 
     @staticmethod
-    def __decode_int(s: str) -> (int, str):
+    def __decode_int(s: bytes) -> Tuple[int, bytes]:
         s = s[1:]
         next_idx = s.index(b'e')
         if s.startswith(b'-0'):
@@ -64,7 +65,7 @@ class _BencodeHandler(object):
         return int(s[:next_idx]), s[next_idx+1:]
 
     @staticmethod
-    def __decode_string(s: str) -> (str, str):
+    def __decode_string(s: bytes) -> Tuple[bytes, bytes]:
         sep = s.index(b':')
         str_len = int(s[:sep])
         if str_len < 0:
@@ -74,7 +75,7 @@ class _BencodeHandler(object):
         s = s[1:]
         return s[sep:sep+str_len], s[sep+str_len:]
 
-    def __decode_list(self, s: str) -> (list, str):
+    def __decode_list(self, s: bytes) -> Tuple[list, bytes]:
         r = list()
         s = s[1:]  # skip leading `l`
         while s[0] != ord('e'):
@@ -82,7 +83,7 @@ class _BencodeHandler(object):
             r.append(v)
         return r, s[1:]
 
-    def __decode_dict(self, s: str) -> (dict, str):
+    def __decode_dict(self, s: bytes) -> Tuple[dict, bytes]:
         r = dict()
         s = s[1:]  # skip leading `d`
         while s[0] != ord(b'e'):
@@ -91,11 +92,11 @@ class _BencodeHandler(object):
         return r, s[1:]
 
     @staticmethod
-    def __encode_int(x: str) -> bytes:
+    def __encode_int(x: bytes) -> bytes:
         return b'i' + bytes(str(x), 'utf-8') + b'e'
 
     @staticmethod
-    def __encode_string(x: str) -> bytes:
+    def __encode_string(x: bytes) -> bytes:
         return bytes((str(len(x))), 'utf-8') + b':' + x
 
     def __encode_list(self, x: str) -> bytes:
@@ -104,17 +105,17 @@ class _BencodeHandler(object):
             ret += self.__encode_func[type(i)](i)
         return b'l' + ret + b'e'
 
-    def __encode_dict(self, x: str) -> bytes:
+    def __encode_dict(self, x: dict) -> bytes:
         ret = b''
         for k, v in sorted(x.items()):
             ret += self.__encode_func[type(k)](k)
             ret += self.__encode_func[type(v)](v)
         return b'd' + ret + b'e'
 
-    def bencode(self, s: str) -> bytes:
+    def bencode(self, s: Union[dict, list, bytes, int]) -> bytes:
         return self.__encode_func[type(s)](s)
 
-    def bdecode(self, s: str):
+    def bdecode(self, s: bytes) -> Union[dict, None]:
         try:
             r, l = self.__decode_func[s[0]](s)
         except (IndexError, KeyError, ValueError) as e:

mat2

@@ -44,7 +44,7 @@ def show_meta(filename: str):
     if not __check_file(filename):
         return
 
-    p, mtype = parser_factory.get_parser(filename)
+    p, mtype = parser_factory.get_parser(filename)  # type: ignore
     if p is None:
         print("[-] %s's format (%s) is not supported" % (filename, mtype))
         return
@@ -61,7 +61,7 @@ def clean_meta(params: Tuple[str, bool]) -> bool:
     if not __check_file(filename, os.R_OK|os.W_OK):
         return False
 
-    p, mtype = parser_factory.get_parser(filename)
+    p, mtype = parser_factory.get_parser(filename)  # type: ignore
     if p is None:
         print("[-] %s's format (%s) is not supported" % (filename, mtype))
         return False

tests/test_climat2.py

@@ -67,6 +67,13 @@ class TestCleanMeta(unittest.TestCase):
         os.remove('./tests/data/clean.jpg')
 
 
+class TestIsSupported(unittest.TestCase):
+    def test_pdf(self):
+        proc = subprocess.Popen(['./mat2', '--show', './tests/data/dirty.pdf'],
+                stdout=subprocess.PIPE)
+        stdout, _ = proc.communicate()
+        self.assertNotIn(b"isn't supported", stdout)
+
 class TestGetMeta(unittest.TestCase):
     def test_pdf(self):
         proc = subprocess.Popen(['./mat2', '--show', './tests/data/dirty.pdf'],