clean_original_article = [char for char in original_article if char not in "、，。！？；：「」『』（）《》【】'\n''\r'"]

app.py

@@ -147,7 +147,12 @@ def load_csv(file):
         first_row = df.iloc[0]
         lesson_words = first_row['lesson_words']
         original_article = first_row['lesson_article']
-        original_word_count = len(original_article.replace(" ", "").replace("\n", ""))
+        clean_original_article = [char for char in original_article if char not in "、，。！？；：「」『』（）《》【】'\n''\r'"]
+        print("====clean_original_article====")
+        print(clean_original_article)
+        print("===============================")
+        original_word_count = len(clean_original_article)
+        print(f"original_word_count: {original_word_count}")
         base_chars = ''  # This should be defined or extracted from some column or external source
         return lesson_words, original_article, original_word_count, base_chars
     return "", "", 0, ""