def get(self, request, pk: int, index: str, document_id: str):
validate_index_and_project_perms(request, pk, index)
ed = ElasticDocument(index)
document = ed.get(document_id)
if not document:
raise NotFound(f"Could not find document with ID '{document_id}' from index '{index}'!")
return Response(document)
def post(self, request, pk: int, index: str, document_id: str):
validate_index_and_project_perms(request, pk, index)
serializer = self.get_serializer(data=request.data)
if serializer.is_valid(raise_exception=True):
ed = ElasticDocument(index)
document = ed.get(document_id, fields=[TEXTA_TAGS_KEY])
if not document:
raise NotFound(
f"Could not find document with ID '{document_id}' from index '{index}'!"
)
document = document.get("_source")
target_facts = serializer.validated_data.get("facts", [])
existing_facts = document.get(TEXTA_TAGS_KEY, [])
new_facts = []
for index_count, existing_fact in enumerate(existing_facts):
for fact in target_facts:
if not (fact.items() <= existing_fact.items()):
new_facts.append(existing_fact)
document[TEXTA_TAGS_KEY] = new_facts
ed.update(index, document_id, doc=document)
return Response({
"message":
f"Removed given facts from document with the ID of {document_id}!"
})
def pull_document_by_id(self, request, pk=None, project_pk=None):
annotator: Annotator = self.get_object()
serializer = self.get_serializer(data=request.data)
serializer.is_valid(raise_exception=True)
ed = ElasticDocument(index=annotator.get_indices())
document_id = serializer.validated_data["document_id"]
document = ed.get(document_id)
if document:
document = self._process_document_output(document, annotator)
return Response(document)
else:
return Response({"message": "No such document!"},
status=status.HTTP_404_NOT_FOUND)
def post(self, request, project_pk: int):
project: Project = get_object_or_404(Project, pk=project_pk)
self.check_object_permissions(request, project)
serializer = ProjectDocumentSerializer(data=request.data)
if not serializer.is_valid():
raise SerializerNotValid(detail=serializer.errors)
indices = project.get_available_or_all_project_indices(serializer.validated_data["indices"])
if not indices:
raise ProjectValidationFailed(detail="No indices supplied and project has no indices")
doc_id = serializer.validated_data["doc_id"]
if not doc_id:
raise InvalidInputDocument(detail="No doc_id supplied")
es = ElasticDocument(index=indices)
results = es.get(doc_id)
return Response(results, status=status.HTTP_200_OK)
def skip_document(self, request, pk=None, project_pk=None):
serializer: DocumentIDSerializer = self.get_serializer(
data=request.data)
serializer.is_valid(raise_exception=True)
annotator: Annotator = self.get_object()
ed = ElasticDocument(index=annotator.get_indices())
document_id = serializer.validated_data["document_id"]
document = ed.get(document_id)
texta_annotations = document["_source"].get("texta_annotator", [])
processed_timestamp = None
if texta_annotations:
for texta_annotation in texta_annotations:
processed_timestamp = texta_annotation.get(
"processed_timestamp_utc", None)
if processed_timestamp:
return Response({
"detail":
f"Document with ID: {serializer.validated_data['document_id']} is already annotated"
})
annotator.skip_document(serializer.validated_data["document_id"],
serializer.validated_data["index"],
user=request.user)
return Response({
"detail":
f"Skipped document with ID: {serializer.validated_data['document_id']}"
})
else:
annotator.skip_document(serializer.validated_data["document_id"],
serializer.validated_data["index"],
user=request.user)
return Response({
"detail":
f"Skipped document with ID: {serializer.validated_data['document_id']}"
})