modify max sleep time

周伟奇
Showing 1 changed file with 14 additions and 12 deletions
src/apps/doc/management/commands/doc_process.py
--- a/src/apps/doc/management/commands/doc_process.py
View file @e325cfc
+++ b/src/apps/doc/management/commands/doc_process.py
View file @e325cfc
@@ -184,9 +184,9 @@ class Command(BaseCommand, LoggerMixin):
                start = i + 1
        return img_il_list
-    def handle(self, *args, **kwargs):
+    def handle(self, *args, **kwargs):  # TODO 调用接口重试
        sleep_second = 5
-        max_sleep_second = 300
+        max_sleep_second = 60
        while self.switch:
            # 从队列获取文件信息
            doc_info = self.get_doc_info()
@@ -206,7 +206,7 @@ class Command(BaseCommand, LoggerMixin):
                with fitz.Document(pdf_path) as pdf:
                    self.cronjob_log.info('{0} [pdf_path={1}] [metadata={2}]'.format(
                        self.log_base, pdf_path, pdf.metadata))
-                    # xref_list = []  # TODO 图片去重
+                    # xref_list = []  # TODO 图片去重 特殊pdf：如电子发票
                    for pno in range(pdf.pageCount):
                        il = pdf.getPageImageList(pno)
                        il.sort(key=lambda x: x[0])
@@ -219,8 +219,8 @@ class Command(BaseCommand, LoggerMixin):
                            save_path = os.path.join(img_save_path, 'page_{0}_img_0.png'.format(page.number))
                            pm.writePNG(save_path)
                            img_path_list.append(save_path)
-                            self.cronjob_log.info('{0} [page to img success] [pdf_path={1}] [page={2}]'.format(
+                            self.cronjob_log.info('{0} [page to img success] [doc_id={1}] [pdf_path={2}] '
-                                self.log_base, pdf_path, page.number))
+                                                  '[page={3}]'.format(self.log_base, doc_id, pdf_path, page.number))
                        else:  # 提取图片
                            for img_index, img_il in enumerate(img_il_list):
                                if len(img_il) == 1:  # 当只有一张图片时， 简化处理
@@ -232,8 +232,8 @@ class Command(BaseCommand, LoggerMixin):
                                        f.write(img_data)
                                    img_path_list.append(save_path)
                                    self.cronjob_log.info(
-                                        '{0} [extract img success] [pdf_path={1}] [page={2}] [img_index={3}]'.format(
+                                        '{0} [extract img success] [doc_id={1}] [pdf_path={2}] [page={3}] '
-                                            self.log_base, pdf_path, pno, img_index))
+                                        '[img_index={4}]'.format(self.log_base, doc_id, pdf_path, pno, img_index))
                                else:  # 多张图片，竖向拼接
                                    height_sum = 0
                                    im_list = []
@@ -262,9 +262,9 @@ class Command(BaseCommand, LoggerMixin):
                                    res.save(save_path)
                                    img_path_list.append(save_path)
                                    self.cronjob_log.info(
-                                        '{0} [extract img success] [pdf_path={1}] [page={2}] [img_index={3}]'.format(
+                                        '{0} [extract img success] [doc_id={1}] [pdf_path={2}] [page={3}] '
-                                            self.log_base, pdf_path, pno, img_index))
+                                        '[img_index={4}]'.format(self.log_base, doc_id, pdf_path, pno, img_index))
-                    self.cronjob_log.info('{0} [pdf to img success]'.format(self.log_base))
+                    self.cronjob_log.info('{0} [pdf to img success] [doc_id={1}]'.format(self.log_base, doc_id))
                write_zip_file(img_save_path, os.path.join(doc_data_path, '{0}_img.zip'.format(doc_id)))
                # 图片调用算法判断是否为银行流水, 图片调用算法OCR为excel文件
@@ -273,11 +273,13 @@ class Command(BaseCommand, LoggerMixin):
                tasks = [self.img_ocr_excel(wb, img_path) for img_path in img_path_list]
                loop.run_until_complete(asyncio.wait(tasks))
                # loop.close()
-                wb.save(excel_path)
+                wb.save(excel_path)  # TODO no sheet (res always [])
                # 整合excel文件上传至EDMS
            except Exception as e:
                UploadDocRecords.objects.filter(id=doc_id).update(status=DocStatus.PROCESS_FAILED.value)
-                self.cronjob_log.error('{0} [process failed] [err={1}]'.format(self.log_base, e))
+                self.cronjob_log.error('{0} [process failed] [doc_id={1}] [err={2}]'.format(self.log_base, doc_id, e))
            else:
                UploadDocRecords.objects.filter(id=doc_id).update(status=DocStatus.COMPLETE.value)
                self.cronjob_log.info('{0} [doc process complete] [doc_id={1}]'.format(self.log_base, doc_id))
+        self.cronjob_log.info('{0} [stop safely]')