Fix typechecking errors around a few places (#4945)

dvc/cache/base.py

@@ -3,6 +3,7 @@ import json
 import logging
 from concurrent.futures import ThreadPoolExecutor
 from copy import copy
+from typing import Optional
 
 from funcy import decorator
 from shortuuid import uuid
@@ -16,7 +17,9 @@ from dvc.exceptions import (
     DvcException,
 )
 from dvc.progress import Tqdm
-from dvc.remote.slow_link_detection import slow_link_guard
+from dvc.remote.slow_link_detection import (  # type: ignore[attr-defined]
+    slow_link_guard,
+)
 
 from ..tree.base import RemoteActionNotImplemented
 
@@ -41,7 +44,7 @@ class CloudCache:
     """Cloud cache class."""
 
     DEFAULT_CACHE_TYPES = ["copy"]
-    CACHE_MODE = None
+    CACHE_MODE: Optional[int] = None
 
     def __init__(self, tree):
         self.tree = tree

dvc/external_repo.py

@@ -4,7 +4,7 @@ import tempfile
 import threading
 from contextlib import contextmanager
 from distutils.dir_util import copy_tree
-from typing import Iterable
+from typing import Dict, Iterable
 
 from funcy import cached_property, reraise, retry, wrap_with
 
@@ -73,8 +73,8 @@ def external_repo(url, rev=None, for_write=False, **kwargs):
             _remove(path)
 
 
-CLONES = {}
-CACHE_DIRS = {}
+CLONES: Dict[str, str] = {}
+CACHE_DIRS: Dict[str, str] = {}
 
 
 def clean_repos():

dvc/hash_info.py

@@ -1,19 +1,22 @@
 from collections import OrderedDict
 from dataclasses import dataclass, field
+from typing import Dict, Optional
 
 HASH_DIR_SUFFIX = ".dir"
 
+DirInfo = Dict[str, str]
+
 
 @dataclass
 class HashInfo:
     PARAM_SIZE = "size"
     PARAM_NFILES = "nfiles"
 
-    name: str
-    value: str
-    dir_info: dict = field(default=None, compare=False)
-    size: int = field(default=None, compare=False)
-    nfiles: int = field(default=None, compare=False)
+    name: Optional[str]
+    value: Optional[str]
+    dir_info: Optional[DirInfo] = field(default=None, compare=False)
+    size: Optional[int] = field(default=None, compare=False)
+    nfiles: Optional[int] = field(default=None, compare=False)
 
     def __bool__(self):
         return bool(self.value)

dvc/path_info.py

@@ -2,6 +2,7 @@
 import os
 import pathlib
 import posixpath
+from typing import Callable
 from urllib.parse import urlparse
 
 from funcy import cached_property
@@ -253,7 +254,7 @@ class CloudURLInfo(URLInfo):
 
 
 class HTTPURLInfo(URLInfo):
-    __hash__ = URLInfo.__hash__
+    __hash__: Callable[["HTTPURLInfo"], int] = URLInfo.__hash__
 
     def __init__(self, url):
         p = urlparse(url)

dvc/scm/base.py

@@ -41,7 +41,7 @@ class Base:
         self._root_dir = os.path.realpath(root_dir)
 
     @property
-    def root_dir(self):
+    def root_dir(self) -> str:
         return self._root_dir
 
     def __repr__(self):

dvc/scm/git.py

@@ -90,7 +90,7 @@ class Git(Base):
         self.files_to_track = set()
 
     @property
-    def root_dir(self):
+    def root_dir(self) -> str:
         return self.repo.working_tree_dir
 
     @staticmethod

dvc/stage/__init__.py

@@ -133,11 +133,11 @@ class Stage(params.StageParams):
         self.desc = desc
 
     @property
-    def path(self):
+    def path(self) -> str:
         return self._path
 
     @path.setter
-    def path(self, path):
+    def path(self, path: str):
         self._path = path
         self.__dict__.pop("path_in_repo", None)
         self.__dict__.pop("relpath", None)
@@ -169,7 +169,7 @@ class Stage(params.StageParams):
         return f"stage: '{self.addressing}'"
 
     @property
-    def addressing(self):
+    def addressing(self) -> str:
         """
         Useful for alternative presentations where we don't need
         `Stage:` prefix.

dvc/stage/serialize.py

@@ -1,7 +1,7 @@
 from collections import OrderedDict
 from functools import partial
 from operator import attrgetter
-from typing import TYPE_CHECKING, List
+from typing import TYPE_CHECKING, List, no_type_check
 
 from funcy import post_processing
 
@@ -57,6 +57,7 @@ def _serialize_out(out):
     return out.def_path if not flags else {out.def_path: flags}
 
 
+@no_type_check
 def _serialize_outs(outputs: List[BaseOutput]):
     outs, metrics, plots = [], [], []
     for out in sort_by_path(outputs):
@@ -95,6 +96,7 @@ def _serialize_params_keys(params):
     return keys
 
 
+@no_type_check
 def _serialize_params_values(params: List[ParamsDependency]):
     """Returns output of following format, used for lockfile:
         {'params.yaml': {'lr': '1', 'train': 2}, {'params2.yaml': {'lr': '1'}}