fix doc list

周伟奇
Showing 3 changed files with 47 additions and 29 deletions
src/apps/doc/management/commands/doc_process.py
src/apps/doc/views.py
src/settings/__init__.py
--- a/src/apps/doc/management/commands/doc_process.py
View file @f8904dc
+++ b/src/apps/doc/management/commands/doc_process.py
View file @f8904dc
@@ -8,7 +8,7 @@ from io import BytesIO
 from django.core.management import BaseCommand
 from common.mixins import LoggerMixin
 from common.redis_cache import redis_handler as rh
-from apps.doc.models import UploadDocRecords
+from apps.doc.models import UploadDocRecords, DocStatus
 from settings import conf
@@ -31,26 +31,32 @@ class Command(BaseCommand, LoggerMixin):
    def signal_handler(self, sig, frame):
        self.switch = False  # 停止处理文件
-    def get_task_info(self):  # TODO 优先队列 & status modify
+    def get_doc_info(self):  # TODO 优先队列
-        task_id = rh.dequeue()
+        doc_id = rh.dequeue()
-        if task_id is None:
+        if doc_id is None:
-            self.cronjob_log.info('{0} [get_task_info] [queue empty]'.format(self.log_base))
+            self.cronjob_log.info('{0} [get_doc_info] [queue empty]'.format(self.log_base))
            return
-        task_info = UploadDocRecords.objects.filter(id=task_id).values(
+        doc_info = UploadDocRecords.objects.filter(id=doc_id).values(
            'id', 'metadata_version_id', 'document_name').first()
-        if task_info is None:
+        if doc_info is None:
-            self.cronjob_log.warn('{0} [get_task_info] [task not found] [task_id={1}]'.format(self.log_base, task_id))
+            self.cronjob_log.warn('{0} [get_doc_info] [doc not found] [doc_id={1}]'.format(self.log_base, doc_id))
-        self.cronjob_log.info('{0} [get_task_info success] [task_info={1}]'.format(self.log_base, task_info))
+            return
-        return task_info
+        UploadDocRecords.objects.filter(id=doc_id).update(status=DocStatus.PROCESSING.value)
+        self.cronjob_log.info('{0} [get_task_info success] [doc_info={1}]'.format(self.log_base, doc_info))
+        return doc_info
-    def pdf_download(self, task_info):
+    def pdf_download(self, doc_info):
-        if task_info is None:
+        if doc_info is None:
            return
        # TODO EDMS下载pdf
-        pdf_path = '/Users/clay/Desktop/biz/biz_logic/data/2/横版-表格-工商银行CH-B008802400.pdf'
+        # pdf_path = '/Users/clay/Desktop/biz/biz_logic/data/2/横版-表格-工商银行CH-B008802400.pdf'
-        self.cronjob_log.info('{0} [pdf download success] [task_info={1}] [pdf_path={2}]'.format(
+        # doc_data_path = os.path.dirname(pdf_path)
-            self.log_base, task_info, pdf_path))
+        doc_id = doc_info['id']
-        return pdf_path
+        doc_data_path = os.path.join(self.data_dir, str(doc_id))
+        pdf_path = os.path.join(doc_data_path, '{0}.pdf'.format(doc_id))
+        self.cronjob_log.info('{0} [pdf download success] [doc_info={1}] [pdf_path={2}]'.format(
+            self.log_base, doc_info, pdf_path))
+        return pdf_path, doc_data_path
    @staticmethod
    def getimage(pix):
@@ -135,15 +141,15 @@ class Command(BaseCommand, LoggerMixin):
    def handle(self, *args, **kwargs):
        while self.switch:
            # 从队列获取文件信息
-            task_info = self.get_task_info()
+            doc_info = self.get_doc_info()
            # 从EDMS获取PDF文件
-            pdf_path = self.pdf_download(task_info)
+            pdf_path, doc_data_path = self.pdf_download(doc_info)
            # 队列为空时的处理
            if pdf_path is None:
                time.sleep(10)
                continue
            # PDF文件提取图片
-            img_save_path = os.path.join(os.path.dirname(pdf_path), 'img')
+            img_save_path = os.path.join(doc_data_path, 'img')
            os.makedirs(img_save_path, exist_ok=True)
            with fitz.Document(pdf_path) as pdf:
                self.cronjob_log.info('{0} [pdf_path={1}] [pdf_metadata={2}]'.format(
@@ -159,8 +165,7 @@ class Command(BaseCommand, LoggerMixin):
                        page = pdf.loadPage(pno)
                        pm = page.getPixmap(matrix=self.trans, alpha=False)
                        save_path = os.path.join(img_save_path, 'page_{0}_img_0.png'.format(page.number))
-                        # pm.writePNG(save_path)
+                        pm.writePNG(save_path)
-                        pm.writeImage(save_path)
                    else:  # 提取图片
                        for img_count, img_il in enumerate(img_il_list):
                            if len(img_il) == 1:  # 当只有一张图片时， 简化处理
--- a/src/apps/doc/views.py
View file @f8904dc
+++ b/src/apps/doc/views.py
View file @f8904dc
@@ -61,8 +61,10 @@ doc_list_args = {
    'application_id': fields.Str(required=False, validate=validate.Length(max=64)),
    'data_source': fields.Str(required=False, validate=validate.Length(max=64)),
    'business_type': fields.Str(required=False, validate=validate.Length(max=64)),
-    'upload_finish_time': fields.Date(required=False),
+    'upload_time_start': fields.Date(required=False),
-    'create_time': fields.Date(required=False),
+    'upload_time_end': fields.Date(required=False),
+    'create_time_start': fields.Date(required=False),
+    'create_time_end': fields.Date(required=False),
 }
 upload_pdf_args = {
@@ -133,18 +135,23 @@ class DocView(GenericView, DocHandler):
        application_id = args.get('application_id')
        data_source = args.get('data_source')
        business_type = args.get('business_type')
-        upload_finish_time = args.get('upload_finish_time')
+        upload_time_start = args.get('upload_time_start')
-        create_time = args.get('create_time')
+        upload_time_end = args.get('upload_time_end')
+        create_time_start = args.get('create_time_start')
+        create_time_end = args.get('create_time_end')
        status_query = Q(status=status) if status else Q()
        application_id_query = Q(application_id=application_id) if application_id else Q()
        data_source_query = Q(data_source=data_source) if data_source else Q()
        business_type_query = Q(business_type=business_type) if business_type else Q()
-        upload_finish_time_query = Q(upload_finish_time=upload_finish_time) if upload_finish_time else Q()
+        upload_finish_time_query = Q(upload_finish_time__gte=upload_time_start, upload_finish_time__lte=upload_time_end)\
-        create_time_query = Q(create_time=create_time) if create_time else Q()
+            if upload_time_start and upload_time_end else Q()
+        create_time_query = Q(create_time__gte=create_time_start, create_time__lte=create_time_end)\
+            if create_time_start and create_time_end else Q()
        query = status_query & application_id_query & data_source_query & business_type_query\
                & upload_finish_time_query & create_time_query
-        doc_queryset = UploadDocRecords.objects.filter(query).values(
+        val_tuple = ('id', 'application_id', 'upload_finish_time', 'create_time',
-            'id', 'application_id', 'upload_finish_time', 'create_time', 'business_type', 'data_source', 'status')
+                     'business_type', 'data_source', 'status')
+        doc_queryset = UploadDocRecords.objects.filter(query).values(*val_tuple).order_by('-upload_finish_time')
        doc_list = self.get_doc_list(doc_queryset)
        total = len(doc_list)
--- a/src/settings/__init__.py
View file @f8904dc
+++ b/src/settings/__init__.py
View file @f8904dc
@@ -41,6 +41,7 @@ INSTALLED_APPS = [
    'django.contrib.sessions',
    'django.contrib.messages',
    'django.contrib.staticfiles',
+    # 'corsheaders',
    'rest_framework',
    'common',
    'apps.account',
@@ -48,6 +49,7 @@ INSTALLED_APPS = [
 ]
 MIDDLEWARE = [
+    # 'corsheaders.middleware.CorsMiddleware',
    'django.middleware.security.SecurityMiddleware',
    'django.contrib.sessions.middleware.SessionMiddleware',
    'django.middleware.common.CommonMiddleware',
@@ -166,3 +168,7 @@ JWT_AUTH = {
    'JWT_VERIFY_EXPIRATION': True,
    'JWT_ALLOW_REFRESH': True,
 }
+# 跨域设置
+# CORS_ORIGIN_ALLOW_ALL = True
+# CORS_ALLOW_CREDENTIALS = True