Skip to content

fix(parser): make key attribute optional in Kafka model #6523

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

Merged
merged 4 commits into from
Apr 20, 2025
Merged
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
23 changes: 17 additions & 6 deletions aws_lambda_powertools/utilities/data_classes/kafka_event.py
Original file line number Diff line number Diff line change
Expand Up @@ -37,14 +37,25 @@ def timestamp_type(self) -> str:
return self["timestampType"]

@property
def key(self) -> str:
"""The raw (base64 encoded) Kafka record key."""
return self["key"]
def key(self) -> str | None:
"""
The raw (base64 encoded) Kafka record key.

This key is optional; if not provided,
a round-robin algorithm will be used to determine
the partition for the message.
"""

return self.get("key")

@property
def decoded_key(self) -> bytes:
"""Decode the base64 encoded key as bytes."""
return base64.b64decode(self.key)
def decoded_key(self) -> bytes | None:
"""
Decode the base64 encoded key as bytes.

If the key is not provided, this will return None.
"""
return None if self.key is None else base64.b64decode(self.key)

@property
def value(self) -> str:
Expand Down
12 changes: 8 additions & 4 deletions aws_lambda_powertools/utilities/parser/models/kafka.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
from datetime import datetime
from typing import Dict, List, Literal, Type, Union
from typing import Dict, List, Literal, Optional, Type, Union

from pydantic import BaseModel, field_validator

Expand All @@ -14,12 +14,16 @@ class KafkaRecordModel(BaseModel):
offset: int
timestamp: datetime
timestampType: str
key: bytes
key: Optional[bytes] = None
value: Union[str, Type[BaseModel]]
headers: List[Dict[str, bytes]]

# Added type ignore to keep compatibility between Pydantic v1 and v2
_decode_key = field_validator("key")(base64_decode) # type: ignore[type-var, unused-ignore]
# key is optional; only decode if not None
@field_validator("key", mode="before")
def decode_key(cls, value):
if value is not None:
return base64_decode(value)
return value

@field_validator("value", mode="before")
def data_base64_decode(cls, value):
Expand Down
51 changes: 51 additions & 0 deletions tests/events/kafkaEventMsk.json
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,57 @@
]
}
]
},
{
"topic":"mytopic",
"partition":0,
"offset":15,
"timestamp":1545084650987,
"timestampType":"CREATE_TIME",
"value":"eyJrZXkiOiJ2YWx1ZSJ9",
"headers":[
{
"headerKey":[
104,
101,
97,
100,
101,
114,
86,
97,
108,
117,
101
]
}
]
},
{
"topic":"mytopic",
"partition":0,
"offset":15,
"timestamp":1545084650987,
"timestampType":"CREATE_TIME",
"key": null,
"value":"eyJrZXkiOiJ2YWx1ZSJ9",
"headers":[
{
"headerKey":[
104,
101,
97,
100,
101,
114,
86,
97,
108,
117,
101
]
}
]
}
]
}
Expand Down
51 changes: 51 additions & 0 deletions tests/events/kafkaEventSelfManaged.json
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,57 @@
]
}
]
},
{
"topic": "mytopic",
"partition": 0,
"offset": 15,
"timestamp": 1545084650987,
"timestampType": "CREATE_TIME",
"value": "eyJrZXkiOiJ2YWx1ZSJ9",
"headers": [
{
"headerKey": [
104,
101,
97,
100,
101,
114,
86,
97,
108,
117,
101
]
}
]
},
{
"topic": "mytopic",
"partition": 0,
"offset": 15,
"timestamp": 1545084650987,
"timestampType": "CREATE_TIME",
"key": null,
"value": "eyJrZXkiOiJ2YWx1ZSJ9",
"headers": [
{
"headerKey": [
104,
101,
97,
100,
101,
114,
86,
97,
108,
117,
101
]
}
]
}
]
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ def test_kafka_msk_event():
assert parsed_event.decoded_bootstrap_servers == bootstrap_servers_list

records = list(parsed_event.records)
assert len(records) == 1
assert len(records) == 3
record = records[0]
raw_record = raw_event["records"]["mytopic-0"][0]
assert record.topic == raw_record["topic"]
Expand All @@ -36,6 +36,9 @@ def test_kafka_msk_event():
assert record.decoded_headers["HeaderKey"] == b"headerValue"

assert parsed_event.record == records[0]
for i in range(1, 3):
record = records[i]
assert record.key is None


def test_kafka_self_managed_event():
Expand All @@ -52,7 +55,7 @@ def test_kafka_self_managed_event():
assert parsed_event.decoded_bootstrap_servers == bootstrap_servers_list

records = list(parsed_event.records)
assert len(records) == 1
assert len(records) == 3
record = records[0]
raw_record = raw_event["records"]["mytopic-0"][0]
assert record.topic == raw_record["topic"]
Expand All @@ -68,14 +71,18 @@ def test_kafka_self_managed_event():

assert parsed_event.record == records[0]

for i in range(1, 3):
record = records[i]
assert record.key is None


def test_kafka_record_property_with_stopiteration_error():
# GIVEN a kafka event with one record
raw_event = load_event("kafkaEventMsk.json")
parsed_event = KafkaEvent(raw_event)

# WHEN calling record property twice
# WHEN calling record property thrice
# THEN raise StopIteration
with pytest.raises(StopIteration):
assert parsed_event.record.topic is not None
assert parsed_event.record.partition is not None
for _ in range(4):
assert parsed_event.record.topic is not None
21 changes: 13 additions & 8 deletions tests/unit/parser/_pydantic/test_kafka.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,9 @@ def test_kafka_msk_event_with_envelope():
model=MyLambdaKafkaBusiness,
envelope=envelopes.KafkaEnvelope,
)

assert parsed_event[0].key == "value"
assert len(parsed_event) == 1
for i in range(3):
assert parsed_event[i].key == "value"
assert len(parsed_event) == 3


def test_kafka_self_managed_event_with_envelope():
Expand All @@ -27,9 +27,9 @@ def test_kafka_self_managed_event_with_envelope():
model=MyLambdaKafkaBusiness,
envelope=envelopes.KafkaEnvelope,
)

assert parsed_event[0].key == "value"
assert len(parsed_event) == 1
for i in range(3):
assert parsed_event[i].key == "value"
assert len(parsed_event) == 3


def test_self_managed_kafka_event():
Expand All @@ -41,7 +41,7 @@ def test_self_managed_kafka_event():
assert parsed_event.bootstrapServers == raw_event["bootstrapServers"].split(",")

records = list(parsed_event.records["mytopic-0"])
assert len(records) == 1
assert len(records) == 3
record: KafkaRecordModel = records[0]
raw_record = raw_event["records"]["mytopic-0"][0]
assert record.topic == raw_record["topic"]
Expand All @@ -55,6 +55,8 @@ def test_self_managed_kafka_event():
assert record.value == '{"key":"value"}'
assert len(record.headers) == 1
assert record.headers[0]["headerKey"] == b"headerValue"
record: KafkaRecordModel = records[1]
assert record.key is None


def test_kafka_msk_event():
Expand All @@ -66,7 +68,7 @@ def test_kafka_msk_event():
assert parsed_event.eventSourceArn == raw_event["eventSourceArn"]

records = list(parsed_event.records["mytopic-0"])
assert len(records) == 1
assert len(records) == 3
record: KafkaRecordModel = records[0]
raw_record = raw_event["records"]["mytopic-0"][0]
assert record.topic == raw_record["topic"]
Expand All @@ -80,3 +82,6 @@ def test_kafka_msk_event():
assert record.value == '{"key":"value"}'
assert len(record.headers) == 1
assert record.headers[0]["headerKey"] == b"headerValue"
for i in range(1, 3):
record: KafkaRecordModel = records[i]
assert record.key is None
Loading