Enable strict type checking (#615)

Author: cthoyt

pyproject.toml

@@ -24,7 +24,6 @@ dependencies = [
     "deprecation>=2.1.0",
     "pyyaml>=6.0.1",
     "rdflib>=6.0.0",
-    "importlib-resources>=6.1.1",
 ]
 
 # see https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#dependencies-optional-dependencies

src/sssom/__init__.py

@@ -8,11 +8,11 @@
     # package is not installed
     __version__ = "0.0.0"  # pragma: no cover
 
-from sssom_schema import Mapping, MappingSet, slots  # noqa:401
+from sssom_schema import Mapping, MappingSet, slots
 
-from sssom.io import get_metadata_and_prefix_map  # noqa:401
-from sssom.sssom_document import MappingSetDocument  # noqa:401
-from sssom.util import (  # noqa:401
+from sssom.io import get_metadata_and_prefix_map
+from sssom.sssom_document import MappingSetDocument
+from sssom.util import (
     MappingSetDataFrame,
     collapse,
     compare_dataframes,
@@ -22,6 +22,30 @@
     reconcile_prefix_and_data,
 )
 
-from .constants import generate_mapping_set_id, get_default_metadata  # noqa:401
-from .parsers import parse_csv, parse_sssom_table, parse_tsv  # noqa:401
-from .writers import write_json, write_owl, write_rdf, write_tsv  # noqa:401
+from .constants import generate_mapping_set_id, get_default_metadata
+from .parsers import parse_csv, parse_sssom_table, parse_tsv
+from .writers import write_json, write_owl, write_rdf, write_tsv
+
+__all__ = [
+    "write_json",
+    "write_owl",
+    "write_rdf",
+    "write_tsv",
+    "parse_csv",
+    "generate_mapping_set_id",
+    "get_default_metadata",
+    "parse_sssom_table",
+    "parse_tsv",
+    "Mapping",
+    "MappingSet",
+    "MappingSetDocument",
+    "MappingSetDataFrame",
+    "slots",
+    "get_metadata_and_prefix_map",
+    "collapse",
+    "compare_dataframes",
+    "dataframe_to_ptable",
+    "filter_redundant_rows",
+    "group_mappings",
+    "reconcile_prefix_and_data",
+]

src/sssom/cli.py

@@ -11,6 +11,8 @@
 .. seealso:: https://click.palletsprojects.com/en/8.0.x/setuptools/
 """
 
+from __future__ import annotations
+
 import logging as _logging
 import os
 import sys
@@ -214,7 +216,7 @@ def parse(
     strict_clean_prefixes: bool,
     output: TextIO,
     embedded_mode: bool,
-    mapping_predicate_filter: Optional[tuple],
+    mapping_predicate_filter: list[str],
 ) -> None:
     """Parse a file in one of the supported formats (such as obographs) into an SSSOM TSV file."""
     parse_file(
@@ -239,7 +241,7 @@ def parse(
     multiple=True,
     default=DEFAULT_VALIDATION_TYPES,
 )
-def validate(input: str, validation_types: List[SchemaValidationType]):
+def validate(input: str, validation_types: List[SchemaValidationType]) -> None:
     """Produce an error report for an SSSOM file."""
     validation_type_list = [t for t in validation_types]
     validate_file(input_path=input, validation_types=validation_type_list)
@@ -262,7 +264,7 @@ def split(input: str, output_directory: str) -> None:
     type=click.FloatRange(0, 1),
     help="Default confidence to be assigned if absent.",
 )
-def ptable(input, output: TextIO, inverse_factor: float, default_confidence: float) -> None:
+def ptable(input: str, output: TextIO, inverse_factor: float, default_confidence: float) -> None:
     """Convert an SSSOM file to a ptable for kboom/`boomer <https://github.com/INCATools/boomer>`_."""
     # TODO should maybe move to boomer (but for now it can live here, so cjm can tweak
     msdf = parse_sssom_table(input)
@@ -347,10 +349,10 @@ def dosql(query: str, inputs: List[str], output: TextIO) -> None:
 @click.option("-P", "--prefix", type=click.Tuple([str, str]), multiple=True)
 @output_option
 def sparql(
-    url: str,
-    config,
-    graph: str,
-    limit: int,
+    url: str | None,
+    config: TextIO | None,
+    graph: str | None,
+    limit: int | None,
     object_labels: bool,
     prefix: List[Tuple[str, str]],
     output: TextIO,
@@ -403,9 +405,7 @@ def diff(inputs: Tuple[str, str], output: TextIO) -> None:
     msdf = MappingSetDataFrame.with_converter(
         df=d.combined_dataframe.drop_duplicates(), converter=converter
     )
-    msdf.metadata[  # type:ignore
-        "comment"
-    ] = (
+    msdf.metadata["comment"] = (
         f"Diff between {input1} and {input2}. See comment column for information."
     )
     write_table(msdf, output)

src/sssom/constants.py

@@ -2,20 +2,21 @@
 
 from __future__ import annotations
 
+import importlib.resources
 import pathlib
 import uuid
 from enum import Enum
 from functools import cached_property, lru_cache
 from typing import Any, ClassVar, Dict, List, Literal, Mapping, Set, TextIO, Union, cast
 
-import importlib_resources
 import yaml
 from linkml_runtime.utils.schema_as_dict import schema_as_dict
 from linkml_runtime.utils.schemaview import SchemaView
 
 HERE = pathlib.Path(__file__).parent.resolve()
 
-SCHEMA_YAML = importlib_resources.files("sssom_schema").joinpath("schema/sssom_schema.yaml")
+SCHEMA_RESOURCES = importlib.resources.files("sssom_schema")
+SCHEMA_YAML = SCHEMA_RESOURCES.joinpath("schema/sssom_schema.yaml")
 EXTENDED_PREFIX_MAP = HERE / "obo.epm.json"
 
 OWL_EQUIV_CLASS_URI = "http://www.w3.org/2002/07/owl#equivalentClass"
@@ -240,12 +241,12 @@ def view(self) -> SchemaView:
     @cached_property
     def dict(self) -> Dict[str, Any]:
         """Return SchemaView as a dictionary."""
-        return schema_as_dict(self.view.schema)
+        return schema_as_dict(self.view.schema)  # type:ignore
 
     @cached_property
     def mapping_slots(self) -> List[str]:
         """Return list of mapping slots."""
-        return self.view.get_class("mapping").slots
+        return self.view.get_class("mapping").slots  # type:ignore
 
     @cached_property
     def mapping_set_slots(self) -> List[str]:
@@ -270,7 +271,7 @@ def mapping_enum_keys(self) -> Set[str]:
     @cached_property
     def slots(self) -> Dict[str, str]:
         """Return the slots for SSSOMSchemaView object."""
-        return self.dict["slots"]
+        return self.dict["slots"]  # type:ignore
 
     @cached_property
     def double_slots(self) -> Set[str]:
@@ -292,9 +293,7 @@ def propagatable_slots(self) -> List[str]:
 def _get_sssom_schema_object() -> SSSOMSchemaView:
     """Get a view over the SSSOM schema."""
     sssom_sv_object = (
-        SSSOMSchemaView.instance
-        if hasattr(SSSOMSchemaView, "instance")
-        else SSSOMSchemaView()  # type:ignore[misc]
+        SSSOMSchemaView.instance if hasattr(SSSOMSchemaView, "instance") else SSSOMSchemaView()
     )
     return sssom_sv_object
 

src/sssom/context.py

@@ -1,16 +1,17 @@
 """Utilities for loading JSON-LD contexts."""
 
+from __future__ import annotations
+
 import json
 from functools import lru_cache
-from typing import Any, Mapping, Union
+from typing import Any, Mapping, Union, cast
 
 import curies
-import importlib_resources
 from curies import Converter
 from rdflib.namespace import is_ncname
 from typing_extensions import TypeAlias
 
-from .constants import EXTENDED_PREFIX_MAP
+from .constants import EXTENDED_PREFIX_MAP, SCHEMA_RESOURCES
 
 __all__ = [
     "SSSOM_BUILT_IN_PREFIXES",
@@ -20,9 +21,7 @@
 ]
 
 SSSOM_BUILT_IN_PREFIXES = ("sssom", "owl", "rdf", "rdfs", "skos", "semapv")
-SSSOM_CONTEXT = importlib_resources.files("sssom_schema").joinpath(
-    "context/sssom_schema.context.jsonld"
-)
+SSSOM_CONTEXT = SCHEMA_RESOURCES.joinpath("context/sssom_schema.context.jsonld")
 
 
 @lru_cache(1)
@@ -47,8 +46,8 @@ def _get_default_converter() -> Converter:
 
 
 def _load_sssom_context() -> Context:
-    with open(SSSOM_CONTEXT) as file:
-        return json.load(file, strict=False)
+    with SSSOM_CONTEXT.open() as file:
+        return cast(Context, json.load(file, strict=False))
 
 
 @lru_cache(1)

src/sssom/io.py

@@ -1,5 +1,7 @@
 """I/O utilities for SSSOM."""
 
+from __future__ import annotations
+
 import logging
 import os
 import re
@@ -33,6 +35,9 @@
 from .util import MappingSetDataFrame, are_params_slots, augment_metadata, raise_for_bad_path
 from .writers import get_writer_function, write_table, write_tables
 
+VV = Union[str, Path]
+RecursivePathList: TypeAlias = Union[VV, Iterable[Union[VV, "RecursivePathList"]]]
+
 
 def convert_file(
     input_path: str,
@@ -62,7 +67,7 @@ def parse_file(
     clean_prefixes: bool = True,
     strict_clean_prefixes: bool = True,
     embedded_mode: bool = True,
-    mapping_predicate_filter: tuple = None,
+    mapping_predicate_filter: RecursivePathList | None = None,
 ) -> None:
     """Parse an SSSOM metadata file and write to a table.
 
@@ -131,7 +136,7 @@ def split_file(input_path: str, output_directory: Union[str, Path]) -> None:
     write_tables(splitted, output_directory)
 
 
-@deprecated(
+@deprecated(  # type:ignore[misc]
     deprecated_in="0.4.3",
     details="This functionality for loading SSSOM metadata from a YAML file is deprecated from the "
     "public API since it has internal assumptions which are usually not valid for downstream users.",
@@ -178,10 +183,6 @@ def _merge_converter(
     raise ValueError(f"Invalid prefix map mode: {prefix_map_mode}")
 
 
-VV = Union[str, Path]
-RecursivePathList: TypeAlias = Union[VV, Iterable[Union[VV, "RecursivePathList"]]]
-
-
 def extract_iris(input: RecursivePathList, converter: Converter) -> List[str]:
     """
     Recursively extracts a list of IRIs from a string or file.