Filter unsafe automatic terminology constraints before book translation

tests/test_regressions.py

@@ -97,6 +97,25 @@ def test_name_aliases_do_not_match_common_lowercase_words():
     assert set(glossary.relevant([entry('<p>Jobs invested in ARM.</p>')])) == {'Jobs', 'ARM'}
 
 
+def test_automatic_glossary_does_not_force_generic_senses_or_implicit_surnames():
+    from src.translation.glossary import sanitize_automatic_terms
+    terms, excluded = sanitize_automatic_terms([
+        {'source': 'Otosan', 'target': '爸爸', 'aliases': ['Father']},
+        {'source': 'face', 'target': '面子'},
+        {'source': 'carried interest', 'target': '绩效分成', 'aliases': ['carry']},
+        {'source': 'World Health Organization', 'target': '世界卫生组织', 'aliases': ['WHO']},
+        {'source': 'Sun Microsystems', 'target': '太阳微系统公司', 'aliases': ['Sun']},
+        {'source': 'Sun Yafang', 'target': '孙亚芳'}], set())
+    assert excluded
+    glossary = BookGlossary(terms)
+    assert not glossary.validate('Father had a smile on his face and could carry a bag.', '父亲面带微笑，可以提包。')
+    assert not glossary.validate('WHO AM I?', '我是谁？')
+    assert not glossary.validate('Sun Yafang visited. Sun gave a talk.', '孙亚芳到访并发表演讲。')
+    assert glossary.validate('carried interest', '费用')
+    assert glossary.validate('Otosan', '广告')
+    assert not BookGlossary([{'source': 'Fortune', 'target': '《财富》'}]).validate('Fortune', '据《财富》报道。')
+
+
 @pytest.mark.parametrize('html', [
     '<p>Hello <em><b>world</b></em>.</p>',
     '<p>The angle φ = 10, and φ1φ is literal mathematical text.</p>',