Update common_parse.py

magic_pdf/parse/common_parse.py

@@ -29,63 +29,67 @@ def parse_args():
     return args
 
 
+import os
+import requests
+
+def process_file(file_path, pdf_ocr, excel_ocr, output_dir):
+    """Process a single file for OCR based on its extension."""
+    try:
+        res = ''
+        if file_path.endswith('.pdf'):
+            res = pdf_ocr.ocr_pdf_client(path=file_path, output_dir=output_dir)
+        elif file_path.endswith('.xls') or file_path.endswith('.xlsx'):
+            res = excel_ocr.parse(file_path, output_dir)
+
+        if res:
+            logger.info(f"文件处理成功，输出文件路径为: '{res}'")
+        else:
+            logger.warning(f"文件处理结果为空: '{file_path}'")
+    except requests.exceptions.RequestException as req_err:
+        logger.error(f"请求错误，文件: '{file_path}'，错误信息: {req_err}")
+    except Exception as err:
+        logger.error(f"处理文件时发生未知错误: '{file_path}'，错误信息: {err}")
+
+def normalize_path(input_path):
+    """Normalize file paths to use forward slashes."""
+    return input_path.replace('\\', '/')
+
+def determine_output_dir(output_dir):
+    """Determine if the output directory is an absolute path, else make it absolute."""
+    if not os.path.isabs(output_dir):
+        current_working_directory = os.getcwd()
+        return os.path.join(current_working_directory, output_dir)
+    return output_dir
+
+def process_input(input_path, pdf_ocr, excel_ocr, output_dir):
+    """Process the input path, which can be a directory or a single file."""
+    if os.path.isdir(input_path):
+        for root, _, files in os.walk(input_path):
+            for file in files:
+                file_path = os.path.join(root, file)
+                logger.info(f'正在处理文件: {file_path}')
+                process_file(file_path, pdf_ocr, excel_ocr, output_dir)
+    else:
+        logger.info(f'正在处理单个文件: {input_path}')
+        process_file(input_path, pdf_ocr, excel_ocr, output_dir)
+
 def main():
     args = parse_args()
-    input_path = args.path
+    input_path = normalize_path(args.path)
+    output_dir = determine_output_dir(args.output_dir)
+
     pdf_ocr = ocrPdfClient(args.url)
     excel_ocr = ExcelParser()
-    if not os.path.isabs(args.output_dir):
-        current_working_directory = os.getcwd()
-        output_dir = os.path.join(current_working_directory, args.output_dir)
-        # logger.info(f'相对路径output_dir:{output_dir}')
-    else:
-        output_dir = args.output_dir
 
-    if '\\' in input_path:
-        input_path = input_path.replace('\\', '/')
-    logger.info(f'输入目录或文件的路径为:{input_path}')
-    logger.info(f'output_dir:{output_dir}')
+    logger.info(f'输入目录或文件的路径为: {input_path}')
+    logger.info(f'输出目录为: {output_dir}')
 
-    if os.path.isdir(input_path):
-        for root, dirs, files in os.walk(input_path):
-            # 查找所有的pdf文件
-            for file in files:
-                # 打印pdf文件的完整路径
-                doc_path = os.path.join(root, file)
-                logger.info(f'正在解析：{doc_path}')
-                try:
-                    res = ''
-                    if file.endswith('.pdf'):
-                        res = pdf_ocr.ocr_pdf_client(path=doc_path,output_dir=output_dir)
-                    elif file.endswith('.xls') or file.endswith('.xlsx'):
-                        res = excel_ocr.parse(doc_path,output_dir)
-                    if res:
-                        logger.info(f"输出文件的的路径为: '{res}'")
-                    else:
-                        logger.warning("None")
-                except requests.exceptions.RequestException as e:
-                    logger.error(f"Error while making request to reranker service: {e}")
-                except Exception as e:
-                    logger.error(f"Unexpected error occurred: {e}")
+    process_input(input_path, pdf_ocr, excel_ocr, output_dir)
 
-    else:
-        try:
-            res = ''
-            if input_path.endswith('.pdf'):
-                res = pdf_ocr.ocr_pdf_client(path=input_path, output_dir=output_dir)
-            elif input_path.endswith('.xls') or input_path.endswith('.xlsx'):
-                res = excel_ocr.parse(input_path,output_dir)
-            if res:
-                logger.info(f"output_dir: '{res}'")
-            else:
-                logger.warning("None")
-        except requests.exceptions.RequestException as e:
-            logger.error(f"Error while making request to reranker service: {e}")
-        except Exception as e:
-            logger.error(f"Unexpected error occurred: {e}")
+# Example usage:
+# main()
 
 
 if __name__ == "__main__":
     main()
 
-