Source code for nlpmed_portal.annotations.api.viewsets.imports

# SPDX-FileCopyrightText: Copyright (C) 2026 Omid Jafari <omidjafari.com>
# SPDX-License-Identifier: AGPL-3.0-or-later
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

from pathlib import Path

from rest_framework import status
from rest_framework.decorators import action
from rest_framework.exceptions import ValidationError
from rest_framework.permissions import IsAuthenticated
from rest_framework.response import Response

from nlpmed_portal.annotations import task_dispatch
from nlpmed_portal.annotations.api.serializers import ImportJobSerializer
from nlpmed_portal.annotations.api.viewsets.base import BaseViewSet
from nlpmed_portal.annotations.models import ImportJob
from nlpmed_portal.annotations.permissions import MethodBasePermission
from nlpmed_portal.annotations.permissions import has_permission
from nlpmed_portal.annotations.utils import get_required_fields_for_import
from nlpmed_portal.annotations.utils import read_dataframe


[docs] class ImportJobViewSet(BaseViewSet): serializer_class = ImportJobSerializer queryset = ImportJob.objects.select_related("user", "project").all() permission_classes = [IsAuthenticated, MethodBasePermission] required_perms = { "GET": "view_importjob", "HEAD": "view_importjob", "OPTIONS": "view_importjob", "POST": "add_importjob", "PUT": "change_importjob", "PATCH": "change_importjob", "DELETE": "delete_importjob", }
[docs] def get_queryset(self): required_perm = self.required_perms.get("GET") queryset = super().get_queryset() project_id = self.request.query_params.get("project_id") if project_id: if not project_id.isdigit(): raise ValidationError( {"project_id": "Invalid project_id. Must be an integer."}, ) queryset = queryset.filter(project_id=project_id) return self.filter_queryset_by_scope( queryset, required_perm, project_field="project", )
[docs] def create(self, request, *args, **kwargs): serializer = self.get_serializer(data=request.data) serializer.is_valid(raise_exception=True) job: ImportJob = serializer.save(user=request.user) import_target_perm = f"import_{job.import_target}" if not has_permission( user=request.user, codename=import_target_perm, project=job.project, ): return Response( {"error": f"No permission to import {job.import_target}"}, status=status.HTTP_403_FORBIDDEN, ) try: df_preview = read_dataframe( Path(job.import_file.path), job.import_format, nrows=5, ) preview_data = { "columns": list(df_preview.columns), "rows": df_preview.values.tolist(), } except Exception as exc: # ruff: ignore[blind-except] job.job_status = "failed" job.error_message = str(exc) job.save() job.delete_import_file() return Response( {"error": f"Failed to parse preview: {exc}"}, status=status.HTTP_400_BAD_REQUEST, ) job_data = self.get_serializer(job).data job_data["preview_data"] = preview_data required_fields = get_required_fields_for_import( import_target=job.import_target, import_missing_patients=job.import_missing_patients, ) if not required_fields: job.job_status = "failed" job.error_message = f"Unsupported import target: {job.import_target}" job.save() job.delete_import_file() return Response( {"error": f"Invalid import_target={job.import_target}"}, status=status.HTTP_400_BAD_REQUEST, ) job_data["required_fields"] = required_fields return Response(job_data, status=status.HTTP_201_CREATED)
[docs] @action(detail=True, methods=["POST"]) def confirm(self, request, pk=None): job: ImportJob = self.get_object() import_target_perm = f"import_{job.import_target}" if not has_permission( user=request.user, codename=import_target_perm, project=job.project, ): return Response( {"error": f"No permission to import {job.import_target}"}, status=status.HTTP_403_FORBIDDEN, ) if job.job_status != "uploaded": return Response( {"error": f"Cannot confirm import in status {job.job_status}."}, status=status.HTTP_400_BAD_REQUEST, ) job.column_map = request.data.get("column_map", {}) job.date_format_map = request.data.get("date_format_map", {}) job.job_status = "in_progress" job.save() task_dispatch.dispatch_import_job(job.id) return Response({"detail": "Import job started."}, status=status.HTTP_200_OK)
[docs] @action(detail=True, methods=["GET"]) def status(self, request, pk=None): job: ImportJob = self.get_object() data = self.get_serializer(job).data return Response(data, status=status.HTTP_200_OK)