Add py 3.14 support

.github/workflows/install.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.12", "3.13"]
+        python-version: ["3.12", "3.13", "3.14"]
     env:
       PYTHONPATH: "."
     steps:

.github/workflows/mypy.yml

@@ -26,4 +26,4 @@ jobs:
     - name: Run mypy on all files
       run: |
         mkdir .mypy_cache
-        poetry run mypy --install-types --cache-dir .mypy_cache --non-interactive -p dftimewolf
+        poetry run mypy --install-types --non-interactive --config-file ./mypy.ini

.github/workflows/pytype.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.13"]
+        python-version: ["3.12"]  # Pytype won't suppoer higher than 3.12 - https://github.com/google/pytype/tree/main
 
     steps:
     - uses: actions/checkout@v2

.github/workflows/unittests.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.12", "3.13"]
+        python-version: ["3.12", "3.13", "3.14"]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}

.pylintrc

@@ -41,7 +41,7 @@ ignore-patterns=^\.#
 
 # Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
 # number of processors available to use.
-jobs=1
+jobs=0
 
 # Control the amount of potential inferred values when inferring a single
 # object. This can help the performance when dealing with large functions or
@@ -57,7 +57,7 @@ persistent=yes
 
 # Minimum Python version to use for version dependent checks. Will default to
 # the version used to run pylint.
-py-version=3.12
+py-version=3.13
 
 # Discover python modules and packages in the file system subtree.
 recursive=yes
@@ -436,7 +436,7 @@ indent-after-paren=4
 indent-string='  '
 
 # Maximum number of characters on a single line.
-max-line-length=80
+max-line-length=140
 
 # Maximum number of lines in a module.
 max-module-lines=1000

dftimewolf/lib/auth.py

@@ -31,8 +31,7 @@ def GetGoogleOauth2Credential(
   with lock:
     if os.path.exists(credentials_path):
       credentials = Credentials.from_authorized_user_file(
-          credentials_path, scopes
-      )
+          credentials_path, scopes)  # type: ignore[no-untyped-call]
 
     # If there are no (valid) credentials available, let the user log in.
     if not credentials or not credentials.valid:

dftimewolf/lib/collectors/gcp_logging.py

@@ -25,7 +25,7 @@
 
 def _CustomToAPIRepr(self: entries.ProtobufEntry) -> Dict[str, Any]:
   """API repr (JSON format) for entry."""
-  info = super(entries.ProtobufEntry, self).to_api_repr()
+  info = super(entries.ProtobufEntry, self).to_api_repr()  # type: ignore[no-untyped-call]
   info['protoPayload'] = self.payload  # type: ignore
   return info  # type: ignore
 
@@ -70,9 +70,8 @@ def SetupLoggingClient(self) -> Any:
       logging.Client: A GCP logging client
     """
     if self._project_name:
-      return logging.Client(_use_grpc=False,
-                                        project=self._project_name)
-    return logging.Client(_use_grpc=False)
+      return logging.Client(_use_grpc=False, project=self._project_name)  # type: ignore[no-untyped-call]
+    return logging.Client(_use_grpc=False)  # type: ignore[no-untyped-call]
 
   def ListPages(self, logging_client: Any) -> Any:
     """Returns pages based on a Cloud Logging filter

dftimewolf/lib/collectors/grr_hosts.py

@@ -7,7 +7,7 @@
 import re
 import stat
 import time
-from concurrent.futures import ThreadPoolExecutor
+from concurrent import futures
 from typing import List, Optional, Tuple, Type, Callable
 
 import pandas as pd
@@ -1422,7 +1422,7 @@ def Process(self, container: containers.Host
     osquery_containers = self.GetContainers(containers.OsqueryQuery)
 
     host_osquery_futures = []
-    with ThreadPoolExecutor(self.GetQueryThreadPoolSize()) as executor:
+    with futures.ThreadPoolExecutor(self.GetQueryThreadPoolSize()) as executor:
       for osquery_container in osquery_containers:
         host_osquery_future = executor.submit(
           self._ProcessQuery, container.hostname, client, osquery_container)

dftimewolf/lib/collectors/gsheets.py

@@ -151,7 +151,7 @@ def _GetCredentials(self) -> Optional[Credentials]:
       if os.path.exists(credentials_path):
         try:
           credentials = Credentials.from_authorized_user_file(
-              credentials_path, self.SCOPES)
+              credentials_path, self.SCOPES)  # type: ignore[no-untyped-call]
         except ValueError as exception:
           self.logger.warning(f'Unable to load credentials: {exception}')
           credentials = None

dftimewolf/lib/collectors/workspace_audit.py

@@ -84,7 +84,7 @@ def _GetCredentials(self) -> Optional[Credentials]:
       if os.path.exists(credentials_path):
         try:
           credentials = Credentials.from_authorized_user_file(
-              credentials_path, self.SCOPES)
+              credentials_path, self.SCOPES)  # type: ignore[no-untyped-call]
         except ValueError as exception:
           self.logger.warning(
               f'Unable to load credentials: {exception:s}')

dftimewolf/lib/processors/llmproviders/gemini.py

@@ -57,9 +57,7 @@ def _configure(self) -> None:
         sa_content = json.loads(sa_file.read())
       sa_credential = (
           service_account.Credentials.from_service_account_info(
-              sa_content
-          )
-      )
+              sa_content))  # type: ignore[no-untyped-call]
       genai.configure(credentials=sa_credential)  # type: ignore
     else:
       raise RuntimeError(

dftimewolf/lib/processors/llmproviders/vertex_ai.py

@@ -62,7 +62,7 @@ def _configure(self) -> None:
       with open(service_account_path) as sa_file:
         info = json.loads(sa_file.read())
       sa_credential = (
-          service_account.Credentials.from_service_account_info(info))
+          service_account.Credentials.from_service_account_info(info))  # type: ignore[no-untyped-call]
       vertexai.init(
           credentials=sa_credential,
           api_key=api_key,

dftimewolf/lib/processors/turbinia_base.py

@@ -292,7 +292,7 @@ def GetCredentials(self, credentials_path: str,
     if os.path.exists(credentials_path):
       try:
         credentials = Credentials.from_authorized_user_file(
-            credentials_path, scopes)
+            credentials_path, scopes)  # type: ignore[no-untyped-call]
       except ValueError as exception:
         msg = f'Error loading credentials: {exception!s}'
         self.ModuleError(msg, critical=True)
@@ -330,7 +330,7 @@ def GetCredentials(self, credentials_path: str,
     # Save credentials
     if credentials:
       with open(credentials_path, 'w', encoding='utf-8') as token:
-        token.write(credentials.to_json())
+        token.write(credentials.to_json())  # type: ignore[no-untyped-call]
 
     return credentials
 

mypy.ini

@@ -1,7 +1,8 @@
 [mypy]
-python_version = 3.10
+python_version = 3.13
+packages = dftimewolf
 disable_error_code = override
 ignore_missing_imports = True
 strict = True
 exclude = _pb2.py|tests
-disallow_untyped_calls = False
+cache_dir = .mypy_cache