Implement file uploader

doccano/app/server/data/test.jsonl

@@ -0,0 +1,18 @@
+{"id": 5, "label": "2", "text": "\u30a2\u30f3\u30d1\u30b5\u30f3\u30c9", "manual": true, "prob": 0.5, "manual": true, "prob": 0.5}
+{"id": 10, "label": "2", "text": "\u8a00\u8a9e", "manual": true, "prob": 0.5}
+{"id": 11, "label": "1", "text": "\u65e5\u672c\u8a9e", "manual": true, "prob": 0.5}
+{"id": 12, "label": "1", "text": "\u5730\u7406\u5b66", "manual": true, "prob": 0.5}
+{"id": 23, "label": "2", "text": "\u56fd\u306e\u4e00\u89a7", "manual": false, "prob": 0.5}
+{"id": 31, "label": "2", "text": "\u30d1\u30ea", "manual": false, "prob": 0.5}
+{"id": 32, "label": "3", "text": "\u30e8\u30fc\u30ed\u30c3\u30d1", "manual": false, "prob": 0.5}
+{"id": 42, "label": "2", "text": "\u751f\u7269", "manual": true, "prob": 0.5}
+{"id": 43, "label": "3", "text": "\u30b3\u30b1\u690d\u7269", "manual": false, "prob": 0.5}
+{"id": 47, "label": "3", "text": "\u793e\u4f1a\u5b66", "manual": true, "prob": 0.5}
+{"id": 111, "label": "1", "text": "\u65e5\u672c\u8a9e", "manual": true, "prob": 0.5}
+{"id": 112, "label": "1", "text": "\u5730\u7406\u5b66", "manual": true, "prob": 0.5}
+{"id": 123, "label": "2", "text": "\u56fd\u306e\u4e00\u89a7", "manual": false, "prob": 0.5}
+{"id": 131, "label": "2", "text": "\u30d1\u30ea", "manual": false, "prob": 0.5}
+{"id": 132, "label": "3", "text": "\u30e8\u30fc\u30ed\u30c3\u30d1", "manual": true, "prob": 0.5}
+{"id": 142, "label": "2", "text": "\u751f\u7269", "manual": true, "prob": 0.5}
+{"id": 143, "label": "1", "text": "\u30b3\u30b1\u690d\u7269", "manual": false, "prob": 0.5}
+{"id": 147, "label": "3", "text": "\u793e\u4f1a\u5b66", "manual": true, "prob": 0.5}

doccano/app/server/tests.py

@@ -1,6 +1,9 @@
-from django.test import TestCase
+import os
 
-from .models import Project
+from django.test import TestCase, Client
+from django.urls import reverse
+
+from .models import Project, RawData
 
 
 class ProjectModelTest(TestCase):
@@ -8,3 +11,25 @@ class ProjectModelTest(TestCase):
     def test_string_representation(self):
         project = Project(name='my project', description='my description')
         self.assertEqual(str(project), project.name)
+
+
+class TestRawDataAPI(TestCase):
+
+    def test_get(self):
+        client = Client()
+        res = client.get(reverse('data_api', args=[1]))
+        self.assertEqual(res.status_code, 200)
+        self.assertIsInstance(res.json(), dict)
+        self.assertIn('data', res.json())
+        self.assertEqual(res.json()['data'], [])
+
+    def test_post(self):
+        self.assertEqual(RawData.objects.count(), 0)
+
+        filename = os.path.join(os.path.dirname(__file__), 'data/test.jsonl')
+        client = Client()
+        with open(filename) as f:
+            client.post(reverse('data_api', args=[1]),
+                        {'name': 'fred', 'attachment': f})
+
+        self.assertGreater(RawData.objects.count(), 0)

doccano/app/server/urls.py

@@ -1,7 +1,7 @@
 from django.urls import path
 
 from .views import AnnotationView, AnnotationAPIView, MetaInfoAPI, SearchAPI
-from .views import ProjectListView, ProjectDetailView, ProjectAdminView
+from .views import ProjectListView, ProjectDetailView, ProjectAdminView, RawDataAPI
 
 urlpatterns = [
     path('', ProjectListView.as_view(), name='project-list'),
@@ -9,6 +9,7 @@ urlpatterns = [
     path('<int:pk>/admin', ProjectAdminView.as_view()),
     path('<int:project_id>/docs', AnnotationView.as_view()),
     path('<int:project_id>/apis/data', AnnotationAPIView.as_view()),
+    path('<int:pk>/apis/raw_data', RawDataAPI.as_view(), name='data_api'),
     path('<int:project_id>/apis/label', MetaInfoAPI.as_view()),
     path('<int:project_id>/apis/search', SearchAPI.as_view()),
 ]

doccano/app/server/views.py

@@ -110,8 +110,12 @@ class RawDataAPI(View):
 
     def post(self, request, *args, **kwargs):
         """Upload data."""
-        print(request.FILES['file'])
-        # RawData().save()
+        f = request.FILES['attachment']
+        content = ''.join(chunk.decode('utf-8') for chunk in f.chunks())
+        for line in content.split('\n'):
+            j = json.loads(line)
+            RawData(text=j['text']).save()
+
         return JsonResponse({'status': 'ok'})