chore: improve coverage and clean entry points

edsnlp/patch_spacy_dot_components.py

@@ -5,7 +5,6 @@
 from spacy.errors import Errors
 from spacy.language import FactoryMeta
 from spacy.pipe_analysis import validate_attrs
-from spacy.pipeline import Pipe
 from spacy.util import SimpleFrozenDict, SimpleFrozenList, registry
 
 
@@ -51,10 +50,11 @@ def factory(
     if not isinstance(name, str):
         raise ValueError(Errors.E963.format(decorator="factory"))
     if not isinstance(default_config, dict):
-        err = Errors.E962.format(
-            style="default config", name=name, cfg_type=type(default_config)
+        raise ValueError(
+            Errors.E962.format(
+                style="default config", name=name, cfg_type=type(default_config)
+            )
         )
-        raise ValueError(err)
 
     def add_factory(factory_func: Callable) -> Callable:
         internal_name = cls.get_factory_name(name)
@@ -102,77 +102,4 @@ def add_factory(factory_func: Callable) -> Callable:
     return add_factory
 
 
-@classmethod
-def component(
-    cls,
-    name: str,
-    *,
-    assigns: Iterable[str] = SimpleFrozenList(),
-    requires: Iterable[str] = SimpleFrozenList(),
-    retokenizes: bool = False,
-    func: Optional["Pipe"] = None,
-) -> Callable[..., Any]:
-    """
-    Patched from spaCy to allow back dots in factory
-    names (https://github.com/aphp/edsnlp/pull/152)
-
-    Register a new pipeline component. Can be used for stateless function
-    components that don't require a separate factory. Can be used as a
-    decorator on a function or classmethod, or called as a function with the
-    factory provided as the func keyword argument. To create a component and
-    add it to the pipeline, you can use nlp.add_pipe(name).
-
-    name (str): The name of the component factory.
-    assigns (Iterable[str]): Doc/Token attributes assigned by this component,
-        e.g. "token.ent_id". Used for pipeline analysis.
-    requires (Iterable[str]): Doc/Token attributes required by this component,
-        e.g. "token.ent_id". Used for pipeline analysis.
-    retokenizes (bool): Whether the component changes the tokenization.
-        Used for pipeline analysis.
-    func (Optional[Callable]): Factory function if not used as a decorator.
-
-    DOCS: https://spacy.io/api/language#component
-    """
-    if name is not None:
-        if not isinstance(name, str):
-            raise ValueError(Errors.E963.format(decorator="component"))
-    component_name = name if name is not None else util.get_object_name(func)
-
-    def add_component(component_func: "Pipe") -> Callable:
-        if isinstance(func, type):  # function is a class
-            raise ValueError(Errors.E965.format(name=component_name))
-
-        def factory_func(nlp, name: str) -> "Pipe":
-            return component_func
-
-        internal_name = cls.get_factory_name(name)
-        if internal_name in registry.factories:
-            # We only check for the internal name here – it's okay if it's a
-            # subclass and the base class has a factory of the same name. We
-            # also only raise if the function is different to prevent raising
-            # if module is reloaded. It's hacky, but we need to check the
-            # existing functure for a closure and whether that's identical
-            # to the component function (because factory_func created above
-            # will always be different, even for the same function)
-            existing_func = registry.factories.get(internal_name)
-            closure = existing_func.__closure__
-            wrapped = [c.cell_contents for c in closure][0] if closure else None
-            if util.is_same_func(wrapped, component_func):
-                factory_func = existing_func  # noqa: F811
-
-        cls.factory(
-            component_name,
-            assigns=assigns,
-            requires=requires,
-            retokenizes=retokenizes,
-            func=factory_func,
-        )
-        return component_func
-
-    if func is not None:  # Support non-decorator use cases
-        return add_component(func)
-    return add_component
-
-
 spacy.Language.factory = factory
-spacy.Language.component = component

edsnlp/pipelines/core/normalizer/normalizer.py

@@ -4,9 +4,9 @@
 from spacy.tokens import Doc
 
 from .accents.accents import AccentsConverter
-from .lowercase.factory import remove_lowercase
 from .pollution.pollution import PollutionTagger
 from .quotes.quotes import QuotesConverter
+from .remove_lowercase.factory import remove_lowercase
 from .spaces.spaces import SpacesTagger
 
 

edsnlp/pipelines/core/normalizer/remove_lowercase/factory.py

@@ -0,0 +1,47 @@
+from spacy.language import Language
+from spacy.tokens import Doc
+
+from edsnlp.utils.deprecation import deprecated_factory
+
+
+def remove_lowercase(doc: Doc):
+    """
+    Add case on the `NORM` custom attribute. Should always be applied first.
+
+    Parameters
+    ----------
+    doc : Doc
+        The spaCy `Doc` object.
+
+    Returns
+    -------
+    Doc
+        The document, with case put back in `NORM`.
+    """
+
+    for token in doc:
+        token.norm_ = token.text
+
+    return doc
+
+
+@deprecated_factory("remove-lowercase", "eds.remove_lowercase", assigns=["token.norm"])
+@deprecated_factory(
+    "eds.remove-lowercase", "eds.remove_lowercase", assigns=["token.norm"]
+)
+@Language.factory("eds.remove_lowercase", assigns=["token.norm"])
+def create_component(
+    nlp: Language,
+    name: str,
+):
+    """
+    Add case on the `NORM` custom attribute. Should always be applied first.
+
+    Parameters
+    ----------
+    nlp : Language
+        The pipeline object.
+    name : str
+        The name of the component.
+    """
+    return remove_lowercase  # pragma: no cover

edsnlp/pipelines/factories.py

@@ -6,9 +6,11 @@
 from .core.matcher.factory import create_component as matcher
 from .core.normalizer.accents.factory import create_component as accents
 from .core.normalizer.factory import create_component as normalizer
-from .core.normalizer.lowercase.factory import remove_lowercase
 from .core.normalizer.pollution.factory import create_component as pollution
 from .core.normalizer.quotes.factory import create_component as quotes
+from .core.normalizer.remove_lowercase.factory import (
+    create_component as remove_lowercase,
+)
 from .core.normalizer.spaces.factory import create_component as spaces
 from .core.sentences.factory import create_component as sentences
 from .core.terminology.factory import create_component as terminology