Fix: type edit_pdf operations via a nested serializer (#14116)

operations was a ListField with no child, so both EditPdfDocumentsSerializer
and BulkEditSerializer._validate_parameters_edit_pdf hand-checked each entry
with isinstance(). That accepted booleans (isinstance(True, int) is true) and
passed through any extra keys.

Adds PdfEditOperationSerializer (page >= 1, doc >= 0, rotate a multiple of
90) and uses it as the ListField child on both paths, dropping the manual
type checks and the now-redundant negative/page < 1 bounds checks. Rotations
that are not a multiple of 90 previously passed validation and then failed
inside the task when QPDF refused them.
This commit is contained in:
Trenton H
2026-09-15 15:43:21 +00:00
committed by GitHub
parent d2170f1267
commit 970eb55a70
2 changed files with 119 additions and 49 deletions
+37 -41
View File
@@ -1749,8 +1749,23 @@ class MergeDocumentsAsVersionsSerializer(DocumentListSerializer):
return attrs
class PdfEditOperationSerializer(serializers.Serializer[dict[str, int]]):
page = serializers.IntegerField(min_value=1)
rotate = serializers.IntegerField(required=False)
doc = serializers.IntegerField(required=False, min_value=0)
def validate_rotate(self, value: int) -> int:
if value % 90 != 0:
raise serializers.ValidationError("rotate must be a multiple of 90")
return value
class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
operations = serializers.ListField(required=True, allow_empty=False)
operations = serializers.ListField(
child=PdfEditOperationSerializer(),
required=True,
allow_empty=False,
)
delete_original = serializers.BooleanField(required=False, default=False)
update_document = serializers.BooleanField(required=False, default=False)
include_metadata = serializers.BooleanField(required=False, default=True)
@@ -1768,18 +1783,9 @@ class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMix
)
operations = attrs["operations"]
if not isinstance(operations, list):
raise serializers.ValidationError("operations must be a list")
for op in operations:
if not isinstance(op, dict):
raise serializers.ValidationError("invalid operation entry")
if "page" not in op or not isinstance(op["page"], int):
raise serializers.ValidationError("page must be an integer")
if "rotate" in op and not isinstance(op["rotate"], int):
raise serializers.ValidationError("rotate must be an integer")
if "doc" in op and not isinstance(op["doc"], int):
raise serializers.ValidationError("doc must be an integer")
if any(op.get("doc", 0) >= len(operations) for op in operations):
raise serializers.ValidationError("doc index is out of bounds")
if attrs["update_document"]:
max_idx = max(op.get("doc", 0) for op in operations)
@@ -1788,16 +1794,10 @@ class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMix
"update_document only allowed with a single output document",
)
if any(
op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
for op in operations
):
raise serializers.ValidationError("doc index is out of bounds")
doc = Document.objects.get(id=documents[0])
if doc.page_count:
for op in operations:
if op["page"] < 1 or op["page"] > doc.page_count:
if op["page"] > doc.page_count:
raise serializers.ValidationError(
f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
)
@@ -2128,19 +2128,18 @@ class BulkEditSerializer(
def _validate_parameters_edit_pdf(self, parameters, document_id) -> None:
if "operations" not in parameters:
raise serializers.ValidationError("operations not specified")
if not isinstance(parameters["operations"], list):
raise serializers.ValidationError("operations must be a list")
if not parameters["operations"]:
raise serializers.ValidationError("operations must not be empty")
for op in parameters["operations"]:
if not isinstance(op, dict):
raise serializers.ValidationError("invalid operation entry")
if "page" not in op or not isinstance(op["page"], int):
raise serializers.ValidationError("page must be an integer")
if "rotate" in op and not isinstance(op["rotate"], int):
raise serializers.ValidationError("rotate must be an integer")
if "doc" in op and not isinstance(op["doc"], int):
raise serializers.ValidationError("doc must be an integer")
operations_field = serializers.ListField(
child=PdfEditOperationSerializer(),
allow_empty=False,
)
try:
operations = operations_field.run_validation(parameters["operations"])
except serializers.ValidationError as e:
# Key the errors under "operations" so they match what the
# dedicated edit_pdf endpoint returns
raise serializers.ValidationError({"operations": e.detail}) from e
parameters["operations"] = operations
if "update_document" in parameters:
if not isinstance(parameters["update_document"], bool):
raise serializers.ValidationError("update_document must be a boolean")
@@ -2152,24 +2151,21 @@ class BulkEditSerializer(
else:
parameters["include_metadata"] = True
if any(op.get("doc", 0) >= len(operations) for op in operations):
raise serializers.ValidationError("doc index is out of bounds")
if parameters["update_document"]:
max_idx = max(op.get("doc", 0) for op in parameters["operations"])
max_idx = max(op.get("doc", 0) for op in operations)
if max_idx > 0:
raise serializers.ValidationError(
"update_document only allowed with a single output document",
)
if any(
op.get("doc", 0) < 0 or op.get("doc", 0) >= len(parameters["operations"])
for op in parameters["operations"]
):
raise serializers.ValidationError("doc index is out of bounds")
doc = Document.objects.get(id=document_id)
# doc existence is already validated
if doc.page_count:
for op in parameters["operations"]:
if op["page"] < 1 or op["page"] > doc.page_count:
for op in operations:
if op["page"] > doc.page_count:
raise serializers.ValidationError(
f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
)