Fix warning output and revert change to query docstring

src/scribe_data/check/check_query_forms.py

@@ -410,7 +410,7 @@ def check_defined_return_forms(query_text: str) -> str:
     return ""
 
 
-# MARK: forms order within the query
+# MARK: Forms Order
 
 
 def check_forms_order(query_text: str) -> bool:
@@ -420,47 +420,48 @@ def check_forms_order(query_text: str) -> bool:
 
     Parameters
     ----------
-    query_file : str
-        The SPARQL query text as a string.
+        query_file : str
+            The SPARQL query text as a string.
 
     Returns
     -------
-    bool
-        True if the order of the matches, False otherwise.
+        bool
+            True if the order of the matches, False otherwise.
     """
-
-    # Regex pattern to capture the variables in the SELECT statement.
     select_pattern = r"SELECT\s+(.*?)\s+WHERE"
 
     # Extracting the variables from the SELECT statement.
     if select_match := re.search(select_pattern, query_text, flags=re.DOTALL):
-        select_vars = re.findall(r"\?(\w+)", select_match.group(1))
+        select_vars = re.findall(r"\?(\w+)", select_match[1])
+
     else:
-        return False  # invalid query format if no SELECT match.
+        return False  # invalid query format if no SELECT match
 
-    # Exclude the first two variables from select_vars
+    # Exclude the first two variables from select_vars.
     select_vars = select_vars[2:]
     # Regex pattern to capture the variables in the WHERE clause.
     dt_pattern = r"WHERE\s*\{[^}]*?wikibase:lemma\s*\?\s*(\w+)\s*[;.]\s*"
     forms_pattern = r"ontolex:representation \?([^ ;]+)"
     where_vars = []
 
-    # Extracting variables from the WHERE clause
+    # Extracting variables from the WHERE clause.
     dt_match = re.findall(dt_pattern, query_text)
     if dt_match == ["lemma"]:
         where_vars.append("preposition")
+
     elif dt_match:
         where_vars.append(dt_match[0])
+
     where_vars += re.findall(forms_pattern, query_text)
 
-    # Handling labels provided by the labeling service  like 'case' and 'gender' in the same order as in select_vars
+    # Handling labels provided by the labeling service  like 'case' and 'gender' in the same order as in select_vars.
     for var in ["case", "gender", "auxiliaryVerb"]:
         if var in select_vars:
-            # Insert in the corresponding index of where_vars
+            # Insert in the corresponding index of where_vars.
             index = select_vars.index(var)
             where_vars.insert(index, var)
 
-    # Check if the order of variables matches
+    # Check if the order of variables matches.
     return select_vars == where_vars
 
 
@@ -500,7 +501,7 @@ def check_query_forms() -> None:
         # Check the order of variables in the WHERE and SELECT clauses.
         select_where_labels_matching = check_forms_order(query_text)
         if not select_where_labels_matching:
-            error_output += f"\n{index}. {query_file_str}: The order of variables in the SELECT statement does not match the WHERE clause.\n"
+            error_output += f"\n{index}. {query_file_str}:\n  - The order of variables in the SELECT statement does not match their order in the query.\n"
             index += 1
 
         if extract_forms_from_sparql(query_file):

src/scribe_data/wikidata/language_data_extraction/italian/proper_nouns/query_proper_nouns.sparql

@@ -1,5 +1,5 @@
 # tool: scribe-data
-# All Italian (Q652) nouns (Q1084) and the given forms.
+# All Italian (Q652) proper nouns (Q147276) and the given forms.
 # Enter this query at https://query.wikidata.org/.
 
 SELECT