testing new preprocess

app.py

@@ -26,22 +26,49 @@ def zero_shot(doc, candidates):
 #         return match.group(1).strip()
 #     return None
 
-def preprocess(transaction):
-    remove_words = ["pos", "mps", "bil", "onl"]
+# def preprocess(transaction):
+#     remove_words = ["pos", "mps", "bil", "onl"]
 
-    # Convert to lowercase
-    transaction = transaction.lower()
+#     # Convert to lowercase
+#     transaction = transaction.lower()
 
-    # Remove unwanted words
-    for word in remove_words:
-        transaction = transaction.replace(word, "")
+#     # Remove unwanted words
+#     for word in remove_words:
+#         transaction = transaction.replace(word, "")
 
-    # Remove special characters and digits
-    transaction = re.sub(r"[^a-z\s]+", "", transaction)
+#     # Remove special characters and digits
+#     transaction = re.sub(r"[^a-z\s]+", "", transaction)
 
+#     # Remove extra spaces
+#     transaction = re.sub(r"\s+", " ", transaction).strip()
+#     return transaction
+
+def preprocess(text):
+    # Remove digits
+    cleaned_text = re.sub(r'\d', '', text)
+    
+    # Remove special characters except spaces and letters
+    cleaned_text = re.sub(r'[^a-zA-Z\s]', ' ', cleaned_text)
+    
     # Remove extra spaces
-    transaction = re.sub(r"\s+", " ", transaction).strip()
-    return transaction
+    cleaned_text = re.sub(r'\s+', ' ', cleaned_text).strip()
+    
+    # Convert to uppercase
+    cleaned_text = cleaned_text.upper()
+    
+    # Remove last word if it matches "PVT", "LTD", "INDIA"
+    last_word = cleaned_text.split()[-1]
+    if last_word in ["PVT", "LTD", "INDIA"]:
+        cleaned_text = " ".join(cleaned_text.split()[:-1])
+    
+    # Remove unwanted words
+    words_to_remove = ["MPS", "POS", "BIL", "ONL"]
+    cleaned_text = " ".join([word for word in cleaned_text.split() if word not in words_to_remove])
+    
+    # Convert to lowercase
+    cleaned_text = cleaned_text.lower()
+    
+    return cleaned_text
 
 
 #create input and output objects