Avoid matching named aliases against ordinary lowercase words

src/translation/glossary.py

@@ -21,7 +21,14 @@ def matches(source, text):
         escaped = r'(?<!\w)' + escaped
     if source and source[-1].isascii() and source[-1].isalnum():
         escaped += r'(?!\w)'
-    return re.search(escaped, text, re.IGNORECASE) is not None
+    return re.search(escaped, text, matching_flags(source)) is not None
+
+
+def matching_flags(alias):
+    # WHO/who, US/us, Jobs/jobs and Arm/arm are different words. Single Latin
+    # named tokens keep their case; full phrases retain tolerant matching.
+    named_token = alias.isascii() and not re.search(r'\s', alias) and any(c.isupper() for c in alias)
+    return 0 if named_token else re.IGNORECASE
 
 
 class BookGlossary:
@@ -59,7 +66,7 @@ class BookGlossary:
                     pattern = r'(?<!\w)' + pattern
                 if alias[-1].isascii() and alias[-1].isalnum():
                     pattern += r'(?!\w)'
-                for match in re.finditer(pattern, text, re.IGNORECASE):
+                for match in re.finditer(pattern, text, matching_flags(alias)):
                     start, end = match.span()
                     if any(start < right and end > left for left, right in excluded):
                         continue
@@ -98,7 +105,7 @@ class BookGlossary:
         return errors
 
     def fingerprint(self):
-        return hashlib.sha256(json.dumps(self.terms, sort_keys=True, ensure_ascii=False).encode()).hexdigest()
+        return hashlib.sha256(json.dumps(['case-sensitive-named-tokens-v3', self.terms], sort_keys=True, ensure_ascii=False).encode()).hexdigest()
 
 
 def merge_proposal(terms, proposal, conflicts, ambiguous_aliases):