simplify is_known() function (#126)

* feat: simplify is_known function as an alias of DictionaryLookupStrategy

* fix: use _legacy_dictionary_factory in is_known check

* fix: removed unused greedy option from is_known

* test: add multilingual test for is_known function

simplemma/lemmatizer.py

@@ -80,30 +80,6 @@ def __init__(
         self._fallback_lemmatization_strategy = fallback_lemmatization_strategy
         self._cached_lemmatize = lru_cache(maxsize=cache_max_size)(self._lemmatize)
 
-    def is_known(
-        self,
-        token: str,
-        lang: Union[str, Tuple[str, ...]],
-    ) -> bool:
-        """Check if a token is known in the specified language(s).
-
-        Args:
-            token: The token to check.
-            lang: The language or languages to check in.
-
-        Returns:
-            bool: True if the token is known, False otherwise.
-        """
-
-        _control_input_type(token)
-        lang = validate_lang_input(lang)
-
-        dictionary_lookup = DictionaryLookupStrategy()
-        return any(
-            dictionary_lookup.get_lemma(token, lang_code) is not None
-            for lang_code in lang
-        )
-
     def lemmatize(
         self,
         token: str,
@@ -179,9 +155,7 @@ def get_lemmas_in_text(
 )
 
 
-def is_known(
-    token: str, lang: Union[str, Tuple[str, ...]], greedy: bool = False
-) -> bool:
+def is_known(token: str, lang: Union[str, Tuple[str, ...]]) -> bool:
     """Check if a token is known in the specified language(s).
 
     Args:
@@ -191,8 +165,14 @@ def is_known(
     Returns:
         bool: True if the token is known, False otherwise.
     """
-    lemmatizer = _legacy_lemmatizer if not greedy else _legacy_greedy_lemmatizer
-    return lemmatizer.is_known(token, lang)
+
+    _control_input_type(token)
+    lang = validate_lang_input(lang)
+
+    dictionary_lookup = DictionaryLookupStrategy(_legacy_dictionary_factory)
+    return any(
+        dictionary_lookup.get_lemma(token, lang_code) is not None for lang_code in lang
+    )
 
 
 def lemmatize(

tests/test_lemmatizer.py

@@ -452,27 +452,16 @@ def test_subwords() -> None:
 
 
 def test_is_known() -> None:
-    # logic
-    with pytest.raises(TypeError):
-        assert Lemmatizer().is_known(None, lang="en") is None  # type: ignore[arg-type]
     with pytest.raises(TypeError):
         assert is_known(None, lang="en") is None  # type: ignore[arg-type]
-    with pytest.raises(ValueError):
-        assert Lemmatizer().is_known("", lang="en") is None
     with pytest.raises(ValueError):
         assert is_known("", lang="en") is None
 
-    assert (
-        Lemmatizer().is_known("FanCY", lang="en")
-        == is_known("FanCY", lang="en")
-        == True
-    )
-    # known words
-    assert (
-        Lemmatizer().is_known("Fancy-String", lang="en")
-        == is_known("Fancy-String", lang="en")
-        == False
-    )
+    assert is_known("FanCY", lang="en") == True
+    assert is_known("Fancy-String", lang="en") == False
+
+    assert is_known("espejos", lang=("es", "de")) == True
+    assert is_known("espejos", lang=("de", "es")) == True
 
 
 def test_get_lemmas_in_text() -> None: