New version of spacy requires a bigger model (sm -> md)

Makefile

@@ -5,7 +5,7 @@ VENV=.venv
 PY_VER=python3.11
 PYTHON=./$(VENV)/bin/$(PY_VER)
 PIP_INSTALL=$(PYTHON) -m pip install
-SPACY_MODEL=$(PYTHON) -m spacy download en_core_web_sm
+SPACY_MODEL=$(PYTHON) -m spacy download en_core_web_md
 
 test: activate
 	$(PYTHON) -m unittest discover
@@ -19,7 +19,6 @@ dev: venv activate base
 	$(PIP_INSTALL) -e ../../misc/common_utils
 	$(PIP_INSTALL) -e .[dev]
 	$(SPACY_MODEL)
-	pre-commit install
 
 activate:
 	. $(VENV)/bin/activate

tests/rules/test_sentence.py

@@ -34,7 +34,7 @@ def test_sentencizer_04(self):
     def test_sentencizer_05(self):
         text = shorten(
             """
-            Plants perennial (rhizomatous), usually glabrous, sometimes sparsely hairy.
+           Plants perennial (rhizomatous), usually glabrous, sometimes sparsely hairy.
             Stems [10–]30–70[–100] cm. Leaves: stipules lanceolate to oblong.
             """,
         )

traiter/pylib/pipeline.py

@@ -14,7 +14,7 @@
 def build():
     extensions.add_extensions()
 
-    nlp = spacy.load("en_core_web_sm", exclude=["ner", "lemmatizer", "tok2vec"])
+    nlp = spacy.load("en_core_web_md", exclude=["ner", "lemmatizer", "tok2vec"])
 
     tokenizer.setup_tokenizer(nlp)
 

traiter/pylib/pipes/sentence.py

@@ -13,7 +13,7 @@
 
 @Language.factory(SENTENCES)
 class Sentence:
-    def __init__(self, nlp: Language, name: str, base_model: str = "en_core_web_sm"):
+    def __init__(self, nlp: Language, name: str, base_model: str = "en_core_web_md"):
         self.nlp = nlp
         self.name = name