add utf-8

Author: voorhs

autointent/_dataset/_reader.py

@@ -95,5 +95,5 @@ def _read(self, filepath: str | Path) -> DatasetReader:
         Returns:
             DatasetReader: A validated dataset representation.
         """
-        with Path(filepath).open() as file:
+        with Path(filepath).open(encoding="utf-8") as file:
             return DatasetReader.model_validate(json.load(file))

autointent/_dump_tools.py

@@ -179,7 +179,7 @@ def load(  # noqa: C901, PLR0912, PLR0915
             if child.name == Dumper.tags:
                 tags = {tags_dump.name: TagsList.load(tags_dump) for tags_dump in child.iterdir()}
             elif child.name == Dumper.simple_attrs:
-                with child.open() as file:
+                with child.open(encoding="utf-8") as file:
                     simple_attrs = json.load(file)
             elif child.name == Dumper.arrays:
                 arrays = dict(np.load(child))

autointent/_embedder.py

@@ -164,7 +164,7 @@ def load(cls, path: Path | str, override_config: EmbedderConfig | None = None) -
             path: Path to the directory where the model is stored.
             override_config: one can override presaved settings
         """
-        with (Path(path) / cls._metadata_dict_name).open() as file:
+        with (Path(path) / cls._metadata_dict_name).open(encoding="utf-8") as file:
             metadata: EmbedderDumpMetadata = json.load(file)
 
         if override_config is not None:

autointent/_logging/setup.py

@@ -20,7 +20,7 @@ def setup_logging(level: LogLevel | str, log_filename: Path | str | None = None)
         log_filename: specify location of logfile, omit extension as suffix ``.log.jsonl`` will be appended.
     """
     config_file = ires.files("autointent._logging").joinpath("config.yaml")
-    with config_file.open() as f_in:
+    with config_file.open(encoding="utf-8") as f_in:
         config = yaml.safe_load(f_in)
 
     level = LogLevel(level)

autointent/_pipeline/_pipeline.py

@@ -123,7 +123,7 @@ def from_optimization_config(cls, config: dict[str, Any] | Path | str | Optimiza
             if isinstance(config, dict):
                 dict_params = config
             else:
-                with Path(config).open() as file:
+                with Path(config).open(encoding="utf-8") as file:
                     dict_params = yaml.safe_load(file)
             optimization_config = OptimizationConfig(**dict_params)
 
@@ -330,7 +330,7 @@ def load(
             embedder_config: one can override presaved settings
             cross_encoder_config: one can override presaved settings
         """
-        with (Path(path) / "inference_config.yaml").open() as file:
+        with (Path(path) / "inference_config.yaml").open(encoding="utf-8") as file:
             inference_nodes_configs: list[dict[str, Any]] = yaml.safe_load(file)
 
         inference_config = [

autointent/_ranker.py

@@ -280,7 +280,7 @@ def load(cls, path: Path, override_config: CrossEncoderConfig | None = None) ->
         """
         clf = joblib.load(path / cls._classifier_file_name)
 
-        with (path / cls._metadata_file_name).open() as file:
+        with (path / cls._metadata_file_name).open(encoding="utf-8") as file:
             metadata: CrossEncoderMetadata = json.load(file)
 
         if override_config is not None:

autointent/_vector_index.py

@@ -221,7 +221,7 @@ def load(
             embedder_batch_size: Batch size for the embedding model.
             embedder_use_cache: Whether to use caching for the embedding model.
         """
-        with (dir_path / cls._meta_data_file).open() as file:
+        with (dir_path / cls._meta_data_file).open(encoding="utf-8") as file:
             metadata: VectorIndexMetadata = json.load(file)
 
         instance = cls(
@@ -234,7 +234,7 @@ def load(
             )
         )
 
-        with (dir_path / cls._data_file).open() as file:
+        with (dir_path / cls._data_file).open(encoding="utf-8") as file:
             data: VectorIndexData = json.load(file)
 
         instance.add(**data)

autointent/modules/regex/_simple.py

@@ -262,7 +262,7 @@ def load(
     ) -> "SimpleRegex":
         instance = cls()
 
-        with (Path(path) / "regex_patterns.json").open() as file:
+        with (Path(path) / "regex_patterns.json").open(encoding="utf-8") as file:
             serialized: list[dict[str, Any]] = json.load(file)
 
         instance._compile_regex_patterns(serialized)  # noqa: SLF001

autointent/schemas/_schemas.py

@@ -38,7 +38,7 @@ def dump(self, path: Path) -> None:
     @classmethod
     def load(cls, path: Path) -> "TagsList":
         """Load pydantic model from file system."""
-        with path.open() as file:
+        with path.open(encoding="utf-8") as file:
             serialized: list[dict[str, Any]] = json.load(file)
         parsed = [Tag(**t) for t in serialized]
         return cls(parsed)

autointent/utils.py

@@ -19,7 +19,7 @@ def load_search_space(path_or_str: Path | str) -> list[dict[str, Any]]:
         List of dictionaries representing the search space.
     """
     if isinstance(path_or_str, Path):
-        with path_or_str.open() as file:
+        with path_or_str.open(encoding="utf-8") as file:
             return yaml.safe_load(file)  # type: ignore[no-any-return]
     else:
         # string representation of the search space
@@ -36,5 +36,5 @@ def load_preset(name: SearchSpacePreset) -> dict[str, Any]:
         Dictionary representing the preset search space.
     """
     path = ires.files("autointent._presets").joinpath(name + ".yaml")
-    with path.open() as file:
+    with path.open(encoding="utf-8") as file:
         return yaml.safe_load(file)  # type: ignore[no-any-return]