Minor renaming / refactoring

* Rename loader to `spacy.LookupsDataLoader.v1`, add debugging message
* Make `Vocab.lookups` a property

spacy/language.py

@@ -87,8 +87,9 @@ def create_tokenizer() -> Callable[["Language"], Tokenizer]:
     return tokenizer_factory
 
 
-@registry.misc("spacy.LoadLookupsData.v1")
+@registry.misc("spacy.LookupsDataLoader.v1")
 def load_lookups_data(lang, tables):
+    util.logger.debug(f"Loading lookups from spacy-lookups-data: {tables}")
     lookups = load_lookups(lang=lang, tables=tables)
     return lookups
 

spacy/util.py

@@ -258,7 +258,7 @@ def load_vocab_data_into_model(
 ) -> None:
     """Load vocab data."""
     if lookups:
-        nlp.vocab.load_lookups(lookups)
+        nlp.vocab.lookups = lookups
 
 
 def load_model(

spacy/vocab.pxd

@@ -28,7 +28,7 @@ cdef class Vocab:
     cpdef readonly StringStore strings
     cpdef public Morphology morphology
     cpdef public object vectors
-    cpdef public object lookups
+    cpdef public object _lookups
     cpdef public object writing_system
     cpdef public object get_noun_chunks
     cdef readonly int length

spacy/vocab.pyx

@@ -417,13 +417,18 @@ cdef class Vocab:
             orth = self.strings.add(orth)
         return orth in self.vectors
 
-    def load_lookups(self, lookups):
-        self.lookups = lookups
-        if lookups.has_table("lexeme_norm"):
-            self.lex_attr_getters[NORM] = util.add_lookups(
-                self.lex_attr_getters[NORM],
-                lookups.get_table("lexeme_norm"),
-            )
+    property lookups:
+        def __get__(self):
+            return self._lookups
+
+        def __set__(self, lookups):
+            self._lookups = lookups
+            if lookups.has_table("lexeme_norm"):
+                self.lex_attr_getters[NORM] = util.add_lookups(
+                    self.lex_attr_getters.get(NORM, LEX_ATTRS[NORM]),
+                    self.lookups.get_table("lexeme_norm"),
+                )
+
 
     def to_disk(self, path, *, exclude=tuple()):
         """Save the current state to a directory.