Update app.py

app.py

@@ -53,34 +53,42 @@ for filepath in glob.glob("data/*.txt"):
 
 combined_text = "\n".join(all_texts)
 
+#with open("food_brand_options.txt", "r", encoding:"utf-8") as f:
+   # brand_options = f.read()
+#with open("foods_not_safe.txt", "r", encoding:"utf-8") as file:
+ #   not_safe
+
 
-def preprocess_text(text):
-    cleaned_text = text.strip()
-    chunks = cleaned_text.split("\n")
-    cleaned_chunks = [chunk.strip() for chunk in chunks if chunk.strip()]
-    print(cleaned_chunks)
-    print(len(cleaned_chunks))
-    return cleaned_chunks
-    
 #def preprocess_text(text):
+#    cleaned_text = text.strip()
+#    chunks = cleaned_text.split("\n")
+#    cleaned_chunks = [chunk.strip() for chunk in chunks if chunk.strip()]
+#    print(cleaned_chunks)
+#    print(len(cleaned_chunks))
+ #   return cleaned_chunks
+
+
+def preprocess_text(text):
   # Strip extra whitespace from the beginning and the end of the text
-  #cleaned_text = text.strip()
+  cleaned_text = text.strip()
   # Split the cleaned_text by every newline character (\n)
-  #chunks = cleaned_text.split("\n")
+  chunks = cleaned_text.split("\n")
 
   # Create an empty list to store cleaned chunks
-  #cleaned_chunks = [chunk.strip() for chunk in chunks if chunk.strip()]
+  cleaned_chunks = []
 
-  # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
+  for chunk in chunks: 
+      stripped_chunk = chunk.strip() 
+      cleaned_chunks.append(stripped_chunk)
 
   # Print cleaned_chunks
-  #print(cleaned_chunks)
+  print(cleaned_chunks)
 
   # Print the length of cleaned_chunks
- # print(len(cleaned_chunks))
+ print(len(cleaned_chunks))
 
   # Return the cleaned_chunks
-  #return cleaned_chunks
+  return cleaned_chunks
 
 cleaned_chunks = preprocess_text(combined_text)