Refactor method for manual rsID

app.py

@@ -106,9 +106,10 @@ if uploaded_files and submit:
                 with ThreadPoolExecutor() as executor:
                     result_text = executor.submit(process.get_entity, (chunks, 'alls')).result()
                     result_table = executor.submit(process.get_table, pdf.name).result()
-                
+                    result_rsid = executor.submit(process.get_rsid, passage).result()
+
                 # Manually search for rsID
-                result_text = process.get_rsid(result_text, passage)
+                result_text = pd.concat([result_text, result_rsid]).fillna('').reset_index(drop=True)
 
                 # Combine two results
                 result_text['Source'] = 'Text'

process.py

@@ -158,10 +158,10 @@ class Process():
 
         return df_result
     
-    def get_rsid(self, df, text):
+    def get_rsid(self, text):
 
         rsids = re.findall('(rs[\d]{3,})', text)
+        rsids = list(set(rsids))
         df_rsid = pd.DataFrame(rsids, columns=['rsID'])
-        df = pd.concat([df, df_rsid]).fillna('').reset_index(drop=True)
 
-        return df
+        return df_rsid