fix math term detection

handler.py

@@ -265,23 +265,29 @@ def load_math_terms():
             math_terms_dict[f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)"] = term
             math_terms.append(f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)")
         else:
-            math_terms_dict[f"(^|[^a-zA-Z]){term}([^a-zA-Z]|$)"] = term
-            math_terms.append(f"(^|[^a-zA-Z]){term}([^a-zA-Z]|$)")
+            math_terms.append(term)
+            math_terms_dict[term] = term
     return math_terms, math_terms_dict
 
 def run_math_density(transcript):
     math_terms, math_terms_dict = load_math_terms()
-    for i, utt in enumerate(transcript.utterances): 
-        found_math_terms = set()
+    sorted_terms = sorted(math_terms, key=len, reverse=True)
+    for i, utt in enumerate(transcript.utterances):
         text = utt.get_clean_text(remove_punct=False)
-        num_math_terms = 0
-        for term in math_terms:
-            count = len(re.findall(term, text))
-            if count > 0:
-                found_math_terms.add(math_terms_dict[term])
-            num_math_terms += count
-        utt.num_math_terms = num_math_terms
-        utt.math_terms = list(found_math_terms)
+        num_matches = 0
+        matched_positions = set()
+        match_list = []
+        for term in sorted_terms:
+            matches = list(re.finditer(term, text, re.IGNORECASE))
+            # Filter out matches that share positions with longer terms
+            matches = [match for match in matches if not any(match.start() in range(existing[0], existing[1]) for existing in matched_positions)]
+            if len(matches) > 0:
+                match_list.append(math_terms_dict[term])
+            # Update existing match positions
+            matched_positions.update((match.start(), match.end()) for match in matches)
+            num_matches += len(matches)
+        utt.num_math_terms = num_matches
+        utt.math_terms = match_list
 
 class EndpointHandler():
     def __init__(self, path="."):