From eb2a437a1a21fc80cd2f3168fb2f53a5e1176b67 Mon Sep 17 00:00:00 2001
From: Juanjo Diaz <juanjo.diazmo@gmail.com>
Date: Wed, 15 May 2024 21:43:55 +0200
Subject: [PATCH 1/4] feat: simplify is_known function as an alias of
 DictionaryLookupStrategy

---
 simplemma/lemmatizer.py  | 34 ++++++++--------------------------
 tests/test_lemmatizer.py | 18 ++----------------
 2 files changed, 10 insertions(+), 42 deletions(-)

diff --git a/simplemma/lemmatizer.py b/simplemma/lemmatizer.py
index 18e55d1..4bae121 100644
--- a/simplemma/lemmatizer.py
+++ b/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,
@@ -191,8 +167,14 @@ 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()
+    return any(
+        dictionary_lookup.get_lemma(token, lang_code) is not None for lang_code in lang
+    )
 
 
 def lemmatize(
diff --git a/tests/test_lemmatizer.py b/tests/test_lemmatizer.py
index fb27002..88a0899 100644
--- a/tests/test_lemmatizer.py
+++ b/tests/test_lemmatizer.py
@@ -452,27 +452,13 @@ 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
 
 
 def test_get_lemmas_in_text() -> None:

From 92c477a5395c8b7e782170ae272435f792b78f58 Mon Sep 17 00:00:00 2001
From: Juanjo Diaz <juanjo.diazmo@gmail.com>
Date: Wed, 15 May 2024 21:45:30 +0200
Subject: [PATCH 2/4] fix: use _legacy_dictionary_factory in is_known check

---
 simplemma/lemmatizer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/simplemma/lemmatizer.py b/simplemma/lemmatizer.py
index 4bae121..91ad0b4 100644
--- a/simplemma/lemmatizer.py
+++ b/simplemma/lemmatizer.py
@@ -171,7 +171,7 @@ def is_known(
     _control_input_type(token)
     lang = validate_lang_input(lang)
 
-    dictionary_lookup = DictionaryLookupStrategy()
+    dictionary_lookup = DictionaryLookupStrategy(_legacy_dictionary_factory)
     return any(
         dictionary_lookup.get_lemma(token, lang_code) is not None for lang_code in lang
     )

From 126a3a4cea31f0b3c438b5ca32e882c2b2f478cf Mon Sep 17 00:00:00 2001
From: Juanjo Diaz <juanjo.diazmo@gmail.com>
Date: Wed, 15 May 2024 21:47:05 +0200
Subject: [PATCH 3/4] fix: removed unused greedy option from is_known

---
 simplemma/lemmatizer.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/simplemma/lemmatizer.py b/simplemma/lemmatizer.py
index 91ad0b4..9355768 100644
--- a/simplemma/lemmatizer.py
+++ b/simplemma/lemmatizer.py
@@ -155,9 +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:

From a0bef86241ce1fb1e8d6b09bf33849f2430bbb46 Mon Sep 17 00:00:00 2001
From: Juanjo Diaz <juanjo.diazmo@gmail.com>
Date: Thu, 16 May 2024 20:43:05 +0200
Subject: [PATCH 4/4] test: add multilingual test for is_known function

---
 tests/test_lemmatizer.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tests/test_lemmatizer.py b/tests/test_lemmatizer.py
index 88a0899..caa26c1 100644
--- a/tests/test_lemmatizer.py
+++ b/tests/test_lemmatizer.py
@@ -460,6 +460,9 @@ def test_is_known() -> None:
     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:
     # text lemmatization