Implement overwrite param for all custom lemmatizers (#6794)

spacy/lang/bn/__init__.py

@@ -23,11 +23,13 @@ class Bengali(Language):
 @Bengali.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return Lemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return Lemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Bengali"]

spacy/lang/el/__init__.py

@@ -28,11 +28,13 @@ class Greek(Language):
 @Greek.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return GreekLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return GreekLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Greek"]

spacy/lang/en/__init__.py

@@ -26,11 +26,13 @@ class English(Language):
 @English.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return EnglishLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return EnglishLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["English"]

spacy/lang/fa/__init__.py

@@ -26,11 +26,13 @@ class Persian(Language):
 @Persian.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return Lemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return Lemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Persian"]

spacy/lang/fr/__init__.py

@@ -31,11 +31,13 @@ class French(Language):
 @French.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return FrenchLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return FrenchLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["French"]

spacy/lang/mk/__init__.py

@@ -38,11 +38,13 @@ class Macedonian(Language):
 @Macedonian.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return MacedonianLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return MacedonianLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Macedonian"]

spacy/lang/nb/__init__.py

@@ -26,11 +26,13 @@ class Norwegian(Language):
 @Norwegian.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return Lemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return Lemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Norwegian"]

spacy/lang/nl/__init__.py

@@ -27,11 +27,13 @@ class Dutch(Language):
 @Dutch.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return DutchLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return DutchLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Dutch"]

spacy/lang/pl/__init__.py

@@ -33,11 +33,13 @@ class Polish(Language):
 @Polish.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "pos_lookup"},
+    default_config={"model": None, "mode": "pos_lookup", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return PolishLemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return PolishLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Polish"]

spacy/lang/ru/__init__.py

@@ -22,7 +22,7 @@ class Russian(Language):
 @Russian.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "pymorphy2"},
+    default_config={"model": None, "mode": "pymorphy2", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
 def make_lemmatizer(
@@ -30,7 +30,7 @@ def make_lemmatizer(
     model: Optional[Model],
     name: str,
     mode: str,
-    overwrite: bool = False,
+    overwrite: bool,
 ):
     return RussianLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 

spacy/lang/sv/__init__.py

@@ -29,11 +29,13 @@ class Swedish(Language):
 @Swedish.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "rule"},
+    default_config={"model": None, "mode": "rule", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
-def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
+def make_lemmatizer(
-    return Lemmatizer(nlp.vocab, model, name, mode=mode)
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return Lemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
 
 
 __all__ = ["Swedish"]

spacy/lang/uk/__init__.py

@@ -23,11 +23,11 @@ class Ukrainian(Language):
 @Ukrainian.factory(
     "lemmatizer",
     assigns=["token.lemma"],
-    default_config={"model": None, "mode": "pymorphy2"},
+    default_config={"model": None, "mode": "pymorphy2", "overwrite": False},
     default_score_weights={"lemma_acc": 1.0},
 )
 def make_lemmatizer(
-    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool = False
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
 ):
     return UkrainianLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)