Update src/text_processing.py

src/text_processing.py

@@ -122,7 +122,7 @@ def generate_explaination_for_chunks(chunks, analysis_level='basic', writting_st
 def text_processing(file_path, analysis_level='basic', writting_style='academic', word_lower_limit = 100, word_upper_limit = 150):
     # Trích xuất văn bản từ file PDF
     text = extract_text_from_file(file_path=file_path)
-    with open("./data/text/text.txt", "w", encoding="utf-8") as f:
+    with open("./text/text.txt", "w", encoding="utf-8") as f:
         f.write(text)  
     # Tách văn bản theo ngữ nghĩa
     semantic_chunks = split_text_by_semantics(text)
@@ -131,7 +131,7 @@ def text_processing(file_path, analysis_level='basic', writting_style='academic'
     explanations = generate_explaination_for_chunks(semantic_chunks, analysis_level=analysis_level, writting_style = writting_style, word_lower_limit = word_lower_limit, word_upper_limit=word_upper_limit)
 
     # Tạo thư mục nếu chưa tồn tại
-    output_dir = "./data/text/"
+    output_dir = "./text/"
     os.makedirs(output_dir, exist_ok=True)
 
     # Lưu từng câu vào file riêng biệt
@@ -148,4 +148,4 @@ def text_processing(file_path, analysis_level='basic', writting_style='academic'
                 print(f"Đã lưu: {output_file}")
 ####################### - MAIN CODE - #######################
 if __name__ == "__main__":
-    text_processing(file_path = "./data/input/sample_3.pdf")
+    text_processing(file_path = "./input/sample_3.pdf")