Added regex to delete new lines and * from ObjectURI

Scripts/DataCleaning/filter.py

@@ -182,3 +182,9 @@ class PipelineApplier():
         # as input two dataframe, one with 2 column  
         return None
 
+    def regex_on_objects(self, RDF: pd.DataFrame) -> pd.DataFrame:
+        RDF["ObjectURI"] = (RDF["ObjectURI"].astype("string")
+                   .str.replace(r"\r?\n+", ", ", regex=True)   # newlines -> ", "
+                   .str.replace(r"\*", "", regex=True))        # delete all asterisks
+
+        return RDF

Scripts/DataCleaning/pipeline.py

@@ -92,6 +92,8 @@ class Pipeline():
             # other filter
             #
             RDF = self.filter_applier.delete_relationship_by_list_filter(RDF)
+            # regex on ObjectURI
+            RDF = self.filter_applier.regex_on_objects(RDF)
             if RDF.empty:
                 continue
             RDF = self.filter_applier.rdf_add_special_token(RDF)  # WARNING, THIS MUST BE DONE AFTER FILTER BY FREQUENCE