ltgt part 1

周伟奇
Showing 1 changed file with 35 additions and 24 deletions
src/apps/doc/management/commands/folder_ltgt_process.py
--- a/src/apps/doc/management/commands/folder_ltgt_process.py
View file @f417660
+++ b/src/apps/doc/management/commands/folder_ltgt_process.py
View file @f417660
@@ -74,12 +74,12 @@ class Command(BaseCommand, LoggerMixin):
        # seperate folder name
        self.seperate_map = {
            consts.IC_CLASSIFY: 'IDCard',
-            consts.BC_CLASSIFY: 'BankCard'
+            consts.MVC_CLASSIFY: 'GreenBook',
+            consts.CONTRACT_CLASSIFY: 'Contract',
        }
        self.field_map = {
            consts.VAT_CLASSIFY: (consts.VAT_CN_NAME, None, None, consts.VATS_FIELD_ORDER),
            consts.IC_CLASSIFY: (consts.IC_CN_NAME, '有效期限', consts.IC_FIELD_ORDER_3, consts.IC_FIELD_ORDER_2),
-            consts.BC_CLASSIFY: (consts.BC_CN_NAME, None, None, consts.BC_FIELD_ORDER_2)
        }
        # ocr相关
        self.ocr_url = conf.OCR_URL_FOLDER
@@ -312,28 +312,31 @@ class Command(BaseCommand, LoggerMixin):
    def pdf_process(self, name, path, classify, img_output_dir, wb_output_dir, pdf_output_dir, seperate_dir):
        if os.path.exists(path):
            rebuild_res = None
-            try:
+            if classify == consts.CONTRACT_CLASSIFY:
-                img_save_path, excel_path, pdf_save_path, seperate_path = self.get_path(
+                pass
-                    name, img_output_dir, wb_output_dir, pdf_output_dir, seperate_dir)
-                self.folder_log.info('{0} [pdf to img start] [path={1}]'.format(self.log_base, path))
-                pdf_handler = PDFHandler(path, img_save_path)
-                if classify in self.ltgt_classify_mapping:
-                    pdf_handler.extract_page_image()
-                else:
-                    pdf_handler.extract_image()
-                self.folder_log.info('{0} [pdf to img end] [path={1}]'.format(self.log_base, path))
-            except Exception as e:
-                self.folder_log.error('{0} [pdf to img error] [path={1}] [error={2}]'.format(
-                    self.log_base, path, traceback.format_exc()))
-                raise e
            else:
-                if classify in self.ltgt_classify_mapping:
+                try:
-                    rebuild_res = self.ltgt_process(pdf_handler.img_path_list, self.ltgt_classify_mapping[classify],
+                    img_save_path, excel_path, pdf_save_path, seperate_path = self.get_path(
-                                                    excel_path, path)
+                        name, img_output_dir, wb_output_dir, pdf_output_dir, seperate_dir)
+                    self.folder_log.info('{0} [pdf to img start] [path={1}]'.format(self.log_base, path))
+                    pdf_handler = PDFHandler(path, img_save_path)
+                    if classify in self.ltgt_classify_mapping:
+                        pdf_handler.extract_page_image()
+                    else:
+                        pdf_handler.extract_image()
+                    self.folder_log.info('{0} [pdf to img end] [path={1}]'.format(self.log_base, path))
+                except Exception as e:
+                    self.folder_log.error('{0} [pdf to img error] [path={1}] [error={2}]'.format(
+                        self.log_base, path, traceback.format_exc()))
+                    raise e
                else:
-                    rebuild_res = self.images_process(pdf_handler.img_path_list, classify, excel_path, seperate_path)
+                    if classify in self.ltgt_classify_mapping:
-                shutil.move(path, pdf_save_path)
+                        rebuild_res = self.ltgt_process(pdf_handler.img_path_list, self.ltgt_classify_mapping[classify],
-                return rebuild_res
+                                                        excel_path, path)
+                    else:
+                        rebuild_res = self.images_process(pdf_handler.img_path_list, classify, excel_path, seperate_path)
+                    shutil.move(path, pdf_save_path)
+                    return rebuild_res
    def tif_process(self, name, path, classify, img_output_dir, wb_output_dir, tiff_output_dir, seperate_dir):
        if os.path.exists(path):
@@ -434,7 +437,6 @@ class Command(BaseCommand, LoggerMixin):
            else:
                return
        output_dir = os.path.join(os.path.dirname(input_dir), 'Output')
-        seperate_dir = os.path.join(output_dir, self.seperate_map.get(classify, 'Unknown')) if is_combined else None
        img_output_dir = os.path.join(output_dir, 'image')
        wb_output_dir = os.path.join(output_dir, 'excel')
        pdf_output_dir = os.path.join(output_dir, 'pdf')
@@ -446,8 +448,13 @@ class Command(BaseCommand, LoggerMixin):
        os.makedirs(pdf_output_dir, exist_ok=True)
        os.makedirs(tiff_output_dir, exist_ok=True)
        os.makedirs(failed_output_dir, exist_ok=True)
-        if seperate_dir is not None:
+        if is_combined:
+            seperate_dir = os.path.join(output_dir, self.seperate_map.get(classify, 'Unknown'))
            os.makedirs(seperate_dir, exist_ok=True)
+        else:
+            seperate_dir = None
        os_error_filename_set = set()
        while self.switch:
            # if not os.path.isdir(input_dir):
@@ -474,9 +481,13 @@ class Command(BaseCommand, LoggerMixin):
                            result = self.pdf_process(name, path, classify, img_output_dir, wb_output_dir,
                                                      pdf_output_dir, seperate_dir)
                        elif name.endswith('.tif') or name.endswith('.TIF'):
+                            if classify == consts.CONTRACT_CLASSIFY:
+                                raise LTGTException('e-contract must be pdf')
                            result = self.tif_process(name, path, classify, img_output_dir, wb_output_dir,
                                                      tiff_output_dir, seperate_dir)
                        else:
+                            if classify == consts.CONTRACT_CLASSIFY:
+                                raise LTGTException('e-contract must be pdf')
                            result = self.img_process(name, path, classify, wb_output_dir, img_output_dir,
                                                      pdf_output_dir, seperate_dir)
                        self.folder_log.info('{0} [file end] [path={1}]'.format(self.log_base, path))