Update functions.py

functions.py

@@ -121,7 +121,6 @@ def preprocess_text(text):
     return text
 
 
-
 def generate_variants(keyword):
     # Split the keyword into individual words
     words = keyword.split()
@@ -145,7 +144,6 @@ def generate_variants(keyword):
     return [original, all_upper, all_lower, no_space_title, no_space_upper, no_space_lower, initials]
 
 
-
 # Function to check if a cell contains any excluded keywords
 def contains_excluded_keywords(cell, excluded_keywords):
     if isinstance(cell, np.ndarray):
@@ -157,7 +155,6 @@ def contains_excluded_keywords(cell, excluded_keywords):
     return 
 
 
-
 # Function to extract terms from a cell
 def extract_terms(cell):
     if isinstance(cell, np.ndarray):
@@ -167,4 +164,24 @@ def extract_terms(cell):
         # Split the string by commas and strip whitespace from each term
         return [term.strip() for term in cell.split(',') if term.strip()]
     else:
-        return []
+        return []
+ 
+    
+def remove_excluded_from_list(keywords_list, excluded_keywords):
+    """
+    Remove items from the keywords_list if they contain any of the excluded keywords.
+    This function checks for partial matches in a case-insensitive manner.
+    """
+    if not isinstance(keywords_list, list):
+        return keywords_list  # If it's not a list, return as is
+
+    filtered_list = []
+    for item in keywords_list:
+        # Check if item contains any excluded keyword (case-insensitive)
+        if any(kw.lower() in item.lower() for kw in excluded_keywords):
+            # Skip this item if it matches an excluded keyword
+            continue
+        else:
+            filtered_list.append(item)
+
+    return filtered_list