Update app.py

app.py

@@ -15,34 +15,38 @@ def identify_nouns_verbs(text):
     # Process the text with spaCy
     doc = nlp(text)
     
-    # Extract nouns and verbs
-    nouns = [token.text for token in doc if token.pos_ == "NOUN"]
-    verbs = [token.text for token in doc if token.pos_ == "VERB"]
+    # Extract nouns and verbs with their positions
+    nouns = [{"text": token.text, "begin_offset": token.idx} for token in doc if token.pos_ == "NOUN"]
+    verbs = [{"text": token.text, "begin_offset": token.idx} for token in doc if token.pos_ == "VERB"]
     
     return {"Nouns": nouns, "Verbs": verbs}
 
 def calculate_similarity(nouns_verbs, input_list):
     similarities = {"Nouns": {}, "Verbs": {}}
     
+    def add_similarity(word, similar_word, score, pos):
+        if word not in similarities[pos]:
+            similarities[pos][word] = []
+        if similar_word not in [sim[0] for sim in similarities[pos][word]]:
+            similarities[pos][word].append((similar_word, score))
+
     for noun in nouns_verbs["Nouns"]:
-        noun_token = nlp(noun)
+        noun_text = noun["text"]
+        noun_token = nlp(noun_text)
         for word in input_list["Nouns"]:
             word_token = nlp(word)
             similarity = noun_token.similarity(word_token)
             if similarity > 0.7:  # Adjust threshold as needed
-                if noun not in similarities["Nouns"]:
-                    similarities["Nouns"][noun] = []
-                similarities["Nouns"][noun].append((word, similarity))
+                add_similarity(noun_text, word, similarity, "Nouns")
     
     for verb in nouns_verbs["Verbs"]:
-        verb_token = nlp(verb)
+        verb_text = verb["text"]
+        verb_token = nlp(verb_text)
         for word in input_list["Verbs"]:
             word_token = nlp(word)
             similarity = verb_token.similarity(word_token)
             if similarity > 0.7:  # Adjust threshold as needed
-                if verb not in similarities["Verbs"]:
-                    similarities["Verbs"][verb] = []
-                similarities["Verbs"][verb].append((word, similarity))
+                add_similarity(verb_text, word, similarity, "Verbs")
     
     return similarities