Merge branch 'feature/CHINARPA-5619'

@@ -65,6 +65,7 @@ from celery_compare.tasks import compare, fsm_compare
 from prese.compare import get_empty_result
 from prese.compare import get_empty_result
 from apps.doc.ocr.ecm import ECM
 from apps.doc.ocr.ecm import ECM
 import time
 import time
+from PIL import Image
 
 
 
 
 class CustomDate(fields.Date):
 class CustomDate(fields.Date):
@@ -1125,10 +1126,19 @@ class DocView(DocGenericView, DocHandler):
         random_int = random.randint(0, consts.TIME_NUM)
         random_int = random.randint(0, consts.TIME_NUM)
         metadata_version_id = str(int(time.time()) - random_int)
         metadata_version_id = str(int(time.time()) - random_int)
 
 
+        # 现在不只接受pdf 图片也接收
         pdf_file = request.FILES.get('pdf_file')
         pdf_file = request.FILES.get('pdf_file')
+        file_suffux = ''
         if isinstance(pdf_file.name, str):
         if isinstance(pdf_file.name, str):
-            if not pdf_file.name.endswith('pdf') and not pdf_file.name.endswith('PDF'):
-                self.invalid_params(msg='invalid params: not a PDF file')
+            # if not pdf_file.name.endswith('pdf') and not pdf_file.name.endswith('PDF'):
+            #     self.invalid_params(msg='invalid params: not a PDF file')
+            if '.' in pdf_file.name:
+                file_suffux = pdf_file.name.split('.')[-1]
+            else:
+                self.invalid_params(msg='invalid params: invalid file name')
+        else:
+            self.invalid_params(msg='invalid params: invalid file name')
+
 
 
         business_type = request.POST.get('business_type', '')
         business_type = request.POST.get('business_type', '')
         document_scheme = request.POST.get('document_scheme', '')
         document_scheme = request.POST.get('document_scheme', '')
@@ -1139,7 +1149,19 @@ class DocView(DocGenericView, DocHandler):
         # business_type = random.choice(consts.BUSINESS_TYPE_LIST)
         # business_type = random.choice(consts.BUSINESS_TYPE_LIST)
         # business_type = consts.BUSINESS_TYPE_LIST[0]
         # business_type = consts.BUSINESS_TYPE_LIST[0]
         tmp_save_path = os.path.join(conf.DATA_DIR, business_type, '{0}.pdf'.format(metadata_version_id))
         tmp_save_path = os.path.join(conf.DATA_DIR, business_type, '{0}.pdf'.format(metadata_version_id))
-        file_write(pdf_file, tmp_save_path)
+        # real_save_path 是实际后缀名的保存路径，tmp_save_path 后缀名一定是pdf，是为了后续流程保持原有逻辑保留的
+        real_save_path = os.path.join(conf.DATA_DIR, business_type, '{0}.{1}'.format(metadata_version_id, file_suffux.lower()))
+        file_write(pdf_file, real_save_path)
+        if file_suffux.lower() != 'pdf':
+            try:
+                image = Image.open(pdf_file)
+                image = image.convert("RGB")
+                image.save(tmp_save_path, "PDF", resolution=100.0)
+                self.running_log.info('[mock upload img] [图片已成功转换为 PDF 文件={0}] [path={1}]'.format(pdf_file.name, tmp_save_path))
+            except Exception as e:
+                self.running_log.info('[mock upload img fail] [不支持的文件类型={0}]'.format(pdf_file.name))
+                self.invalid_params(msg='invalid params: not support file type')
+        
 
 
         try:
         try:
             file = fitz.Document(tmp_save_path)
             file = fitz.Document(tmp_save_path)