Skip to content

Issue #449: AvroConsumer: provide method to get schemas from last message decode #475

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.

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

Closed
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
15 changes: 15 additions & 0 deletions confluent_kafka/avro/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -124,6 +124,7 @@ def __init__(self, config, schema_registry=None, reader_key_schema=None, reader_

super(AvroConsumer, self).__init__(ap_conf)
self._serializer = MessageSerializer(schema_registry, reader_key_schema, reader_value_schema)
self.last_decode_schema_ids = (None, None)

def poll(self, timeout=None):
"""
Expand All @@ -142,16 +143,30 @@ def poll(self, timeout=None):

if not message.error():
try:
last_value_schema_id = last_key_schema_id = None
if message.value() is not None:
decoded_value = self._serializer.decode_message(message.value(), is_key=False)
last_value_schema_id = self._serializer.last_decode_schema_id
message.set_value(decoded_value)
if message.key() is not None:
decoded_key = self._serializer.decode_message(message.key(), is_key=True)
last_key_schema_id = self._serializer.last_decode_schema_id
message.set_key(decoded_key)
self.last_decode_schema_ids = (last_key_schema_id, last_value_schema_id)
except SerializerError as e:
raise SerializerError("Message deserialization failed for message at {} [{}] offset {}: {}".format(
message.topic(),
message.partition(),
message.offset(),
e))
return message

def last_decode_schemas(self):
"""
Get the (key and value) schemas used for last decoded message
:return: tuple with key and value Avro schemas (either can be None if no schema is used)
"""
return tuple(
self._serializer.registry_client.get_by_id(sid) if sid else None
for sid in self.last_decode_schema_ids
)
2 changes: 2 additions & 0 deletions confluent_kafka/avro/serializer/message_serializer.py
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ def __init__(self, registry_client, reader_key_schema=None, reader_value_schema=
self.id_to_writers = {}
self.reader_key_schema = reader_key_schema
self.reader_value_schema = reader_value_schema
self.last_decode_schema_id = None

# Encoder support
def _get_encoder_func(self, writer_schema):
Expand Down Expand Up @@ -224,4 +225,5 @@ def decode_message(self, message, is_key=False):
if magic != MAGIC_BYTE:
raise SerializerError("message does not start with magic byte")
decoder_func = self._get_decoder_func(schema_id, payload, is_key)
self.last_decode_schema_id = schema_id
return decoder_func(payload)