feat(normalizer): classify_name + NameClass

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

tools/import-normalizer/tests/test_persons.py

@@ -1,5 +1,6 @@
 import config
 import persons
+from persons import NameClass
 
 def test_slugify():
     assert persons.slugify("de Gruyter", "Eugenie") == "de-gruyter-eugenie"
@@ -82,3 +83,39 @@ def test_alias_index_first_name_only_when_unambiguous():
     assert idx.resolve("Clara") == people[0].person_id   # unique first name resolves
     assert idx.resolve("Walter") is None                 # ambiguous first name does NOT resolve
     assert idx.display(people[0].person_id) == "Clara Cram"
+
+
+GIVEN = {"ella", "anita", "kurt", "georg", "clara", "eugenie"}
+
+def test_classify_unknown():
+    assert persons.classify_name("?", GIVEN) is NameClass.UNKNOWN
+    assert persons.classify_name("A. Kredell?", GIVEN) is NameClass.UNKNOWN
+    assert persons.classify_name("unbekannt", GIVEN) is NameClass.UNKNOWN
+
+def test_classify_prose():
+    assert persons.classify_name("Adressenliste v Clara Cram zur Kondolenz", GIVEN) is NameClass.PROSE
+    assert persons.classify_name("Clara de Gruyter(*1871)", GIVEN) is NameClass.PROSE  # digit
+    assert persons.classify_name('"Cramiade" Gedicht', GIVEN) is NameClass.PROSE        # quote
+
+def test_classify_collective():
+    assert persons.classify_name("Familie", GIVEN) is NameClass.COLLECTIVE
+    assert persons.classify_name("Fam.Cram", GIVEN) is NameClass.COLLECTIVE
+    assert persons.classify_name("Eltern Cram", GIVEN) is NameClass.COLLECTIVE
+    assert persons.classify_name("seine Kinder", GIVEN) is NameClass.COLLECTIVE
+
+def test_classify_relational():
+    assert persons.classify_name("Cousine Emmy Haniel", GIVEN) is NameClass.RELATIONAL
+    assert persons.classify_name("Schwester Hanni", GIVEN) is NameClass.RELATIONAL
+
+def test_classify_single_token():
+    assert persons.classify_name("Agnes", GIVEN) is NameClass.SINGLE_TOKEN
+    assert persons.classify_name("A.B.", GIVEN) is NameClass.SINGLE_TOKEN
+
+def test_classify_ambiguous_pair():
+    assert persons.classify_name("Ella Anita", GIVEN) is NameClass.AMBIGUOUS_PAIR
+    assert persons.classify_name("Kurt Georg", GIVEN) is NameClass.AMBIGUOUS_PAIR
+
+def test_classify_resolvable_single_person():
+    # first + surname (surname not a given name) -> one real person, NOT ambiguous
+    assert persons.classify_name("Mieze Schefold", GIVEN) is NameClass.RESOLVABLE
+    assert persons.classify_name("Adolf Butenandt", GIVEN) is NameClass.RESOLVABLE