Skip to content

DGS-22077 Handle evolution during field transformation #2121

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 6, 2025
Merged

DGS-22077 Handle evolution during field transformation #2121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
04073d9
DGS-22077 Handle evolution during field transformation
rayokota Nov 4, 2025
8e295e3
Minor fix
rayokota Nov 4, 2025
5b6f983
Minor cleanup
rayokota Nov 5, 2025
0e4c02c
Add new header
rayokota Nov 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/confluent_kafka/schema_registry/_async/schema_registry_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,7 +457,7 @@ async def send_request(
body_str = json.dumps(body)
headers = {'Content-Length': str(len(body_str)),
'Content-Type': "application/vnd.schemaregistry.v1+json",
'Accept-Version': "8.0"}
'Confluent-Accept-Unknown-Properties': "true"}

if self.bearer_auth_credentials_source:
await self.handle_bearer_auth(headers)
Expand Down
2 changes: 1 addition & 1 deletion src/confluent_kafka/schema_registry/_sync/schema_registry_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,7 +457,7 @@ def send_request(
body_str = json.dumps(body)
headers = {'Content-Length': str(len(body_str)),
'Content-Type': "application/vnd.schemaregistry.v1+json",
'Accept-Version': "8.0"}
'Confluent-Accept-Unknown-Properties': "true"}

if self.bearer_auth_credentials_source:
self.handle_bearer_auth(headers)
Expand Down
2 changes: 2 additions & 0 deletions src/confluent_kafka/schema_registry/common/avro.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,8 @@ def transform(
return message
fields = schema["fields"]
for field in fields:
if field["name"] not in message:
continue
_transform_field(ctx, schema, field, message, field_transform)
return message

Expand Down
62 changes: 62 additions & 0 deletions tests/schema_registry/_async/test_avro_serdes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -737,6 +737,68 @@ async def test_avro_cel_field_transform():
assert obj2 == newobj


async def test_avro_cel_field_transform_missing_prop():
conf = {'url': _BASE_URL}
client = AsyncSchemaRegistryClient.new_client(conf)
ser_conf = {'auto.register.schemas': False, 'use.latest.version': True}
schema = {
'type': 'record',
'name': 'test',
'fields': [
{'name': 'intField', 'type': 'int'},
{'name': 'doubleField', 'type': 'double'},
{'name': 'stringField', 'type': 'string'},
{'name': 'booleanField', 'type': 'boolean'},
{'name': 'bytesField', 'type': 'bytes'},
{'name': 'missing', 'type': ['null', 'string'], 'default': None},
]
}

rule = Rule(
"test-cel",
"",
RuleKind.TRANSFORM,
RuleMode.WRITEREAD,
"CEL_FIELD",
None,
None,
"name == 'stringField' ; value + '-suffix'",
None,
None,
False
)
await client.register_schema(_SUBJECT, Schema(
json.dumps(schema),
"AVRO",
[],
None,
RuleSet(None, [rule])
))

obj = {
'intField': 123,
'doubleField': 45.67,
'stringField': 'hi',
'booleanField': True,
'bytesField': b'foobar',
}
ser = await AsyncAvroSerializer(client, schema_str=None, conf=ser_conf)
ser_ctx = SerializationContext(_TOPIC, MessageField.VALUE)
obj_bytes = await ser(obj, ser_ctx)

obj2 = {
'intField': 123,
'doubleField': 45.67,
'stringField': 'hi-suffix-suffix',
'booleanField': True,
'bytesField': b'foobar',
'missing': None,
}
deser = await AsyncAvroDeserializer(client)
newobj = await deser(obj_bytes, ser_ctx)
assert obj2 == newobj


async def test_avro_cel_field_transform_disable():
conf = {'url': _BASE_URL}
client = AsyncSchemaRegistryClient.new_client(conf)
Expand Down
62 changes: 62 additions & 0 deletions tests/schema_registry/_sync/test_avro_serdes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -737,6 +737,68 @@ def test_avro_cel_field_transform():
assert obj2 == newobj


def test_avro_cel_field_transform_missing_prop():
conf = {'url': _BASE_URL}
client = SchemaRegistryClient.new_client(conf)
ser_conf = {'auto.register.schemas': False, 'use.latest.version': True}
schema = {
'type': 'record',
'name': 'test',
'fields': [
{'name': 'intField', 'type': 'int'},
{'name': 'doubleField', 'type': 'double'},
{'name': 'stringField', 'type': 'string'},
{'name': 'booleanField', 'type': 'boolean'},
{'name': 'bytesField', 'type': 'bytes'},
{'name': 'missing', 'type': ['null', 'string'], 'default': None},
]
}

rule = Rule(
"test-cel",
"",
RuleKind.TRANSFORM,
RuleMode.WRITEREAD,
"CEL_FIELD",
None,
None,
"name == 'stringField' ; value + '-suffix'",
None,
None,
False
)
client.register_schema(_SUBJECT, Schema(
json.dumps(schema),
"AVRO",
[],
None,
RuleSet(None, [rule])
))

obj = {
'intField': 123,
'doubleField': 45.67,
'stringField': 'hi',
'booleanField': True,
'bytesField': b'foobar',
}
ser = AvroSerializer(client, schema_str=None, conf=ser_conf)
ser_ctx = SerializationContext(_TOPIC, MessageField.VALUE)
obj_bytes = ser(obj, ser_ctx)

obj2 = {
'intField': 123,
'doubleField': 45.67,
'stringField': 'hi-suffix-suffix',
'booleanField': True,
'bytesField': b'foobar',
'missing': None,
}
deser = AvroDeserializer(client)
newobj = deser(obj_bytes, ser_ctx)
assert obj2 == newobj


def test_avro_cel_field_transform_disable():
conf = {'url': _BASE_URL}
client = SchemaRegistryClient.new_client(conf)
Expand Down