Update app.py

app.py

@@ -1,5 +1,54 @@
 import gradio as gr
+import nltk
+import simplemma
+from nltk.tokenize import word_tokenize
+from nltk.tokenize import sent_tokenize
+from nltk.probability import FreqDist
+from simplemma import text_lemmatizer
+nltk.download('punkt')
 
+file = "text.txt"
+
+def get_lists(file):
+  with open(file, 'r', encoding='utf-8') as f:
+    text = f.read()
+
+  word_tokenized_text = word_tokenize(text, language='italian')
+  word_tokenized_text_lower = [word.lower() for word in word_tokenized_text]
+
+  sent_tokenized_text = sent_tokenize(text, language='italian')
+  sent_tokenized_text_lower = [sent.lower() for sent in sent_tokenized_text]
+
+  return word_tokenized_text, word_tokenized_text_lower, sent_tokenized_text, sent_tokenized_text_lower
+
+words, words_lower, sentences, sentences_lower = get_lists(file)
+
+def search_engine(sentences_lower, sentences, round=False):
+  if round == False:
+    target=input("Inserisci una o più parole da cercare.\n")
+  else:
+    target=input("Inserisci un'altra parola da cercare.\n")
+
+
+  result = []
+  for i,sent in enumerate(sentences_lower):
+    if target.lower() in sent:
+      result.append(sentences[i])
+
+  if len(result) == 0:
+    print(f"Non ho trovato la parola '{target}' nei testi.\n")
+    search_engine(round = True)
+  
+  else:
+    print(f"""Ho trovato {len(result)} {"frasi" if len(result) > 1 else "frase"} in cui è presente la parola {target}.\n""")
+    show = input("Quante frasi vuoi vedere? Scrivi un numero oppure 'tutte', se vuoi vederle tutte :-) \n")
+
+    try:
+      for num,sent in enumerate(result[:int(show)]):
+        print(f"{num+1}: {sent}")
+    except:
+      for num,sent in enumerate(result):
+        print(f"{num+1}: {sent}")
 
 def sentence_builder(cerca_una_parola, place, activity_list, morning):
     return f"""The {cerca_una_parola}s went to the {place} where they {" and ".join(activity_list)} until the {"morning" if morning else "night"}"""