Avoid matching named aliases against ordinary lowercase words

tests/test_regressions.py

@@ -78,6 +78,25 @@ def test_shared_surname_is_removed_from_both_distinct_entities():
     assert glossary.validate('Sun Microsystems supplied computers.', '孙先生提供了电脑。')
 
 
+def test_acronyms_do_not_match_ordinary_pronouns():
+    glossary = BookGlossary([
+        {'source': 'World Health Organization', 'target': '世界卫生组织', 'aliases': ['WHO']},
+        {'source': 'United States', 'target': '美国', 'aliases': ['US']},
+        {'source': 'information technology', 'target': '信息技术', 'aliases': ['IT']}])
+    assert not glossary.validate('The people who helped us did it.', '帮助我们的人做了这件事。')
+    assert not glossary.relevant([entry('<p>Who helped us do it?</p>')])
+    assert glossary.validate('WHO met the US IT team.', '他们会见了团队。')
+    assert matches('WHO', 'The WHO report') and not matches('WHO', 'people who helped')
+
+
+def test_name_aliases_do_not_match_common_lowercase_words():
+    glossary = BookGlossary([{'source': 'Steve Jobs', 'target': '乔布斯', 'aliases': ['Jobs']},
+                            {'source': 'Arm Holdings', 'target': '安谋', 'aliases': ['Arm', 'ARM']}])
+    assert not glossary.validate('More jobs in its US arm.', '其美国分部增加就业。')
+    assert glossary.validate('Jobs bought Arm.', '他收购了这家公司。')
+    assert set(glossary.relevant([entry('<p>Jobs invested in ARM.</p>')])) == {'Jobs', 'ARM'}
+
+
 @pytest.mark.parametrize('html', [
     '<p>Hello <em><b>world</b></em>.</p>',
     '<p>The angle φ = 10, and φ1φ is literal mathematical text.</p>',