diff --git a/arkindex/dataimport/api.py b/arkindex/dataimport/api.py
index aa7218e88df7fe643fbf99b7c420bf4dfef4f9cd..38cbe780d827881cfc808e66a1551a4d7a7870b5 100644
--- a/arkindex/dataimport/api.py
+++ b/arkindex/dataimport/api.py
@@ -183,7 +183,6 @@ class DataImportFromFiles(CreateAPIView):
folder_name = serializer.validated_data.get('folder_name')
folder_type_slug = serializer.validated_data.get('folder_type')
element_type_slug = serializer.validated_data.get('element_type')
- pdf_engine = serializer.validated_data.get('pdf_engine')
ml_tools = serializer.validated_data.get('ml_tools')
if folder:
@@ -212,10 +211,6 @@ class DataImportFromFiles(CreateAPIView):
if folder:
payload['folder_id'] = str(folder.id)
- if mode == DataImportMode.PDF:
- assert pdf_engine is not None, 'PDF engine does not exist'
- payload['pdf_engine'] = pdf_engine.value
-
self.dataimport = corpus.imports.create(
creator=self.request.user,
mode=mode,
diff --git a/arkindex/dataimport/models.py b/arkindex/dataimport/models.py
index 57b47f1c50ea6b75c0ddea8bf20eb65566ef3e2e..001c4446940f54c29f2abeffcfa88a583d2cceaf 100644
--- a/arkindex/dataimport/models.py
+++ b/arkindex/dataimport/models.py
@@ -4,7 +4,7 @@ from django.conf import settings
from django.utils.functional import cached_property
from rest_framework.exceptions import ValidationError
from enumfields import EnumField, Enum
-from arkindex_common.enums import DataImportMode, DataImportPDFEngine
+from arkindex_common.enums import DataImportMode
from arkindex_common.ml_tool import MLToolType
from arkindex.project.aws import S3FileModelMixin
from arkindex.project.models import IndexableModel
@@ -47,14 +47,6 @@ class DataImport(IndexableModel):
else:
return self.workflow.state
- @property
- def pdf_engine(self):
- if not self.payload:
- return
- if not self.payload.get('pdf_engine'):
- return DataImportPDFEngine.Convert
- return DataImportPDFEngine(self.payload.get('pdf_engine'))
-
def build_workflow(self):
'''
Create a ponos workflow with a recipe according to configuration
diff --git a/arkindex/dataimport/serializers/imports.py b/arkindex/dataimport/serializers/imports.py
index 6d06845f208779922ca58d39ed4b9c5f09a1f970..49b56cee5ea5dfcbb3fbd55cf64494fb5dac023e 100644
--- a/arkindex/dataimport/serializers/imports.py
+++ b/arkindex/dataimport/serializers/imports.py
@@ -4,7 +4,7 @@ from rest_framework.utils import model_meta
from django.conf import settings
from django.db.models import Q
from ponos.models import State
-from arkindex_common.enums import DataImportMode, DataImportPDFEngine
+from arkindex_common.enums import DataImportMode
from arkindex.project.serializer_fields import EnumField, BestClassField
from arkindex.documents.models import Corpus, Element, Classification, ClassificationState
from arkindex.dataimport.models import DataImport, DataFile
@@ -43,14 +43,6 @@ class ImagesPayloadSerializer(serializers.Serializer):
ml_tools = MLToolTaskSerializer(many=True, required=False, default=list)
-class PDFPayloadSerializer(ImagesPayloadSerializer):
- """
- Serialize a pdf importing payload
- """
-
- pdf_engine = EnumField(DataImportPDFEngine, default=DataImportPDFEngine.Convert)
-
-
class DataImportSerializer(DataImportLightSerializer):
"""
Serialize a data importing workflow with its payload
@@ -68,7 +60,6 @@ class DataImportSerializer(DataImportLightSerializer):
return
payload_serializers = {
DataImportMode.Images: ImagesPayloadSerializer,
- DataImportMode.PDF: PDFPayloadSerializer,
}
self.fields['payload'] = payload_serializers.get(self.instance.mode, serializers.JSONField)()
@@ -105,7 +96,6 @@ class DataImportFromFilesSerializer(serializers.Serializer):
folder_name = serializers.CharField(max_length=250, required=False, allow_null=True)
folder_type = serializers.SlugField(required=False, allow_null=True)
element_type = serializers.SlugField()
- pdf_engine = EnumField(DataImportPDFEngine, default=DataImportPDFEngine.Convert)
ml_tools = MLToolTaskSerializer(many=True, required=False, allow_null=True)
default_error_messages = {
diff --git a/arkindex/dataimport/tests/test_imports.py b/arkindex/dataimport/tests/test_imports.py
index fa93f12447ea28086affd69cc46b71cd28eafcca..2473317e73f164d0271ca784489a89af2a5b3683 100644
--- a/arkindex/dataimport/tests/test_imports.py
+++ b/arkindex/dataimport/tests/test_imports.py
@@ -2,7 +2,7 @@ from unittest.mock import patch, call, MagicMock
from django.urls import reverse
from rest_framework import status
from arkindex_common.ml_tool import MLToolType
-from arkindex_common.enums import DataImportMode, DataImportPDFEngine
+from arkindex_common.enums import DataImportMode
from arkindex.dataimport.models import DataImport, DataFile
from arkindex.documents.models import Element, Corpus
from arkindex.project.tests import FixtureAPITestCase
@@ -276,40 +276,6 @@ class TestImports(FixtureAPITestCase):
self.assertListEqual(list(dataimport.files.all()), [self.pdf_df])
self.assertEqual(Element.objects.get(id=dataimport.payload['folder_id']).name, 'Import pdf test')
- def test_from_files_pdf_convert(self):
- self.client.force_login(self.user)
- response = self.client.post(reverse('api:import-from-files'), {
- 'files': [str(self.pdf_df.id)],
- 'mode': 'pdf',
- 'pdf_engine': 'convert',
- 'folder_type': 'volume',
- 'element_type': 'page',
- }, format='json')
- self.assertEqual(response.status_code, status.HTTP_201_CREATED)
- data = response.json()
- dataimport = DataImport.objects.get(id=data['id'])
- self.assertEqual(dataimport.mode, DataImportMode.PDF)
- self.assertListEqual(list(dataimport.files.all()), [self.pdf_df])
- self.assertEqual(dataimport.pdf_engine, DataImportPDFEngine.Convert)
- self.assertEqual(Element.objects.get(id=dataimport.payload['folder_id']).name, 'Import pdf test')
-
- def test_from_files_pdf_poppler(self):
- self.client.force_login(self.user)
- response = self.client.post(reverse('api:import-from-files'), {
- 'files': [str(self.pdf_df.id)],
- 'mode': 'pdf',
- 'pdf_engine': 'poppler',
- 'folder_type': 'volume',
- 'element_type': 'page',
- }, format='json')
- self.assertEqual(response.status_code, status.HTTP_201_CREATED)
- data = response.json()
- dataimport = DataImport.objects.get(id=data['id'])
- self.assertEqual(dataimport.mode, DataImportMode.PDF)
- self.assertListEqual(list(dataimport.files.all()), [self.pdf_df])
- self.assertEqual(dataimport.pdf_engine, DataImportPDFEngine.Poppler)
- self.assertEqual(Element.objects.get(id=dataimport.payload['folder_id']).name, 'Import pdf test')
-
def test_from_files_iiif(self):
self.client.force_login(self.user)
response = self.client.post(reverse('api:import-from-files'), {