Fix init for pymorphy2_lookup lemmatizer mode (#11631)

spacy/lang/ru/lemmatizer.py

@@ -23,7 +23,7 @@ class RussianLemmatizer(Lemmatizer):
         overwrite: bool = False,
         scorer: Optional[Callable] = lemmatizer_score,
     ) -> None:
-        if mode == "pymorphy2":
+        if mode in {"pymorphy2", "pymorphy2_lookup"}:
             try:
                 from pymorphy2 import MorphAnalyzer
             except ImportError:

spacy/lang/uk/lemmatizer.py

@@ -18,7 +18,7 @@ class UkrainianLemmatizer(RussianLemmatizer):
         overwrite: bool = False,
         scorer: Optional[Callable] = lemmatizer_score,
     ) -> None:
-        if mode == "pymorphy2":
+        if mode in {"pymorphy2", "pymorphy2_lookup"}:
             try:
                 from pymorphy2 import MorphAnalyzer
             except ImportError:

spacy/tests/conftest.py

@@ -343,6 +343,14 @@ def ru_lemmatizer():
     return get_lang_class("ru")().add_pipe("lemmatizer")
 
 
+@pytest.fixture
+def ru_lookup_lemmatizer():
+    pytest.importorskip("pymorphy2")
+    return get_lang_class("ru")().add_pipe(
+        "lemmatizer", config={"mode": "pymorphy2_lookup"}
+    )
+
+
 @pytest.fixture(scope="session")
 def sa_tokenizer():
     return get_lang_class("sa")().tokenizer
@@ -422,6 +430,15 @@ def uk_lemmatizer():
     return get_lang_class("uk")().add_pipe("lemmatizer")
 
 
+@pytest.fixture
+def uk_lookup_lemmatizer():
+    pytest.importorskip("pymorphy2")
+    pytest.importorskip("pymorphy2_dicts_uk")
+    return get_lang_class("uk")().add_pipe(
+        "lemmatizer", config={"mode": "pymorphy2_lookup"}
+    )
+
+
 @pytest.fixture(scope="session")
 def ur_tokenizer():
     return get_lang_class("ur")().tokenizer

spacy/tests/lang/ru/test_lemmatizer.py

@@ -78,3 +78,17 @@ def test_ru_lemmatizer_punct(ru_lemmatizer):
     assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"']
     doc = Doc(ru_lemmatizer.vocab, words=["»"], pos=["PUNCT"])
     assert ru_lemmatizer.pymorphy2_lemmatize(doc[0]) == ['"']
+
+
+def test_ru_doc_lookup_lemmatization(ru_lookup_lemmatizer):
+    words = ["мама", "мыла", "раму"]
+    pos = ["NOUN", "VERB", "NOUN"]
+    morphs = [
+        "Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing",
+        "Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act",
+        "Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing",
+    ]
+    doc = Doc(ru_lookup_lemmatizer.vocab, words=words, pos=pos, morphs=morphs)
+    doc = ru_lookup_lemmatizer(doc)
+    lemmas = [token.lemma_ for token in doc]
+    assert lemmas == ["мама", "мыла", "раму"]

spacy/tests/lang/uk/test_lemmatizer.py

@@ -9,3 +9,11 @@ def test_uk_lemmatizer(uk_lemmatizer):
     """Check that the default uk lemmatizer runs."""
     doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"])
     uk_lemmatizer(doc)
+    assert [token.lemma for token in doc]
+
+
+def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer):
+    """Check that the lookup uk lemmatizer runs."""
+    doc = Doc(uk_lookup_lemmatizer.vocab, words=["a", "b", "c"])
+    uk_lookup_lemmatizer(doc)
+    assert [token.lemma for token in doc]