more typing checks to pre-commit (#37539)

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -119,6 +119,36 @@ repos:
         entry: python scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module"
         types: [python]
         exclude: ^(asv_bench|pandas/tests|doc)/
+    -   id: FrameOrSeriesUnion
+        name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
+        entry: Union\[.*(Series.*DataFrame|DataFrame.*Series).*\]
+        language: pygrep
+        types: [python]
+        exclude: ^pandas/_typing\.py$
+    -   id: type-not-class
+        name: Check for use of foo.__class__ instead of type(foo)
+        entry: \.__class__
+        language: pygrep
+        files: \.(py|pyx)$
+    -   id: unwanted-typing
+        name: Check for use of comment-based annotation syntax and missing error codes
+        entry: |
+            (?x)
+            \#\ type:\ (?!ignore)|
+            \#\ type:\s?ignore(?!\[)
+        language: pygrep
+        types: [python]
+    -   id: no-os-remove
+        name: Check code for instances of os.remove
+        entry: os\.remove
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
+        exclude: |
+            (?x)^
+            pandas/tests/io/excel/test_writers\.py|
+            pandas/tests/io/pytables/common\.py|
+            pandas/tests/io/pytables/test_store\.py$
 -   repo: https://github.com/asottile/yesqa
     rev: v1.2.2
     hooks:

ci/code_checks.sh

@@ -122,29 +122,6 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     # -------------------------------------------------------------------------
-    # Type annotations
-
-    MSG='Check for use of comment-based annotation syntax' ; echo $MSG
-    invgrep -R --include="*.py" -P '# type: (?!ignore)' pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    MSG='Check for missing error codes with # type: ignore' ; echo $MSG
-    invgrep -R --include="*.py" -P '# type:\s?ignore(?!\[)' pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    MSG='Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias' ; echo $MSG
-    invgrep -R --include="*.py" --exclude=_typing.py -E 'Union\[.*(Series.*DataFrame|DataFrame.*Series).*\]' pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    # -------------------------------------------------------------------------
-    MSG='Check for use of foo.__class__ instead of type(foo)' ; echo $MSG
-    invgrep -R --include=*.{py,pyx} '\.__class__' pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    MSG='Check code for instances of os.remove' ; echo $MSG
-    invgrep -R --include="*.py*" --exclude "common.py" --exclude "test_writers.py" --exclude "test_store.py" -E "os\.remove" pandas/tests/
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     MSG='Check for inconsistent use of pandas namespace in tests' ; echo $MSG
     for class in "Series" "DataFrame" "Index" "MultiIndex" "Timestamp" "Timedelta" "TimedeltaIndex" "DatetimeIndex" "Categorical"; do
         check_namespace ${class}

scripts/validate_unwanted_patterns.py

@@ -474,7 +474,7 @@ def main(
 
     sys.exit(
         main(
-            function=globals().get(args.validation_type),  # type: ignore
+            function=globals().get(args.validation_type),
             source_path=args.paths,
             output_format=args.format,
         )