Update common.py

magic_pdf/tools/common.py

@@ -73,9 +73,6 @@ def do_parse(
     image_writer, md_writer = DiskReaderWriter(
         local_image_dir), DiskReaderWriter(local_md_dir)
     image_dir = str(os.path.basename(local_image_dir))
-    # logger.info(f'model_list:{model_list}')
-    # logger.info(f'local_image_dir:::{local_image_dir}')
-    # logger.info(f'image_dir:::{image_dir}')
     if parse_method == 'auto':
         jso_useful_key = {'_pdf_type': '', 'model_list': model_list}
         pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True,
@@ -96,7 +93,6 @@ def do_parse(
     if len(model_list) == 0:
         if model_config.__use_inside_model__:
             pipe.pipe_analyze()
-            # logger.info(f'执行pipe.pipe_analyze()之后的pipe.model_list:{pipe.model_list}')
             orig_model_list = copy.deepcopy(pipe.model_list)
         else:
             logger.error('need model list input')
@@ -106,11 +102,6 @@ def do_parse(
     pdf_info = pipe.pdf_mid_data['pdf_info']
     if f_draw_layout_bbox:
         draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
-    # if f_draw_span_bbox:
-    #     draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
-    # if f_draw_model_bbox:
-    #     drow_model_bbox(copy.deepcopy(orig_model_list), pdf_bytes, local_md_dir, pdf_file_name)
-
     md_content = pipe.pipe_mk_markdown(config_path,local_image_dir,
                                        drop_mode=DropMode.NONE,
                                        md_make_mode=f_make_md_mode)
@@ -121,55 +112,25 @@ def do_parse(
             path=f'{pdf_file_name}.txt',
             mode=AbsReaderWriter.MODE_TXT,
         )
-    except Exception as e:
-        logger.info(f'{pdf_file_name}导出txt文件失败，具体原因为：\n{e}')
-    filepath = os.path.join(str(local_md_dir), f'{pdf_file_name}.txt')
-    logger.info(f'txt文件保存在filepath:{filepath}')
-    remove_empty_lines_from_file(filepath)
-    # if f_dump_md:
-    #     md_writer.write(
-    #         content=md_content,
-    #         path=f'{pdf_file_name}.md',
-    #         mode=AbsReaderWriter.MODE_TXT,
-    #     )
-    #
-    # if f_dump_middle_json:
-    #     md_writer.write(
-    #         content=json_parse.dumps(pipe.pdf_mid_data,
-    #                                  ensure_ascii=False,
-    #                                  indent=4),
-    #         path=f'{pdf_file_name}_middle.json',
-    #         mode=AbsReaderWriter.MODE_TXT,
-    #     )
-    #
-    # if f_dump_model_json:
-    #     md_writer.write(
-    #         content=json_parse.dumps(orig_model_list,
-    #                                  ensure_ascii=False,
-    #                                  indent=4),
-    #         path=f'{pdf_file_name}_model.json',
-    #         mode=AbsReaderWriter.MODE_TXT,
-    #     )
-    #
-    if f_dump_orig_pdf:
-        md_writer.write(
-            content=pdf_bytes,
-            path=f'{pdf_file_name}_origin.pdf',
-            mode=AbsReaderWriter.MODE_BIN,
-        )
-    #
-    # content_list = pipe.pipe_mk_uni_format(image_dir, drop_mode=DropMode.NONE)
-    # if f_dump_content_list:
-    #     md_writer.write(
-    #         content=json_parse.dumps(content_list,
-    #                                  ensure_ascii=False,
-    #                                  indent=4),
-    #         path=f'{pdf_file_name}_content_list.json',
-    #         mode=AbsReaderWriter.MODE_TXT,
-    #     )
+        filepath = os.path.join(str(local_md_dir), f'{pdf_file_name}.txt')
+        logger.info(f'txt文件保存在filepath:{filepath}')
+        remove_empty_lines_from_file(filepath)
 
-    logger.info(f'local output dir is {local_md_dir}')
+        if f_dump_orig_pdf:
+            md_writer.write(
+                content=pdf_bytes,
+                path=f'{pdf_file_name}_origin.pdf',
+                mode=AbsReaderWriter.MODE_BIN,
+            )
+
+        logger.info(f'local output dir is {local_md_dir}')
+
+        return filepath
+    except Exception as e:
+        logger.error(f'{pdf_file_name}导出txt文件失败，具体原因为：\n{e}')
+        return None
 
 
 parse_pdf_methods = click.Choice(['ocr', 'txt', 'auto'])
 
+