Skip to content
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
6 changes: 6 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.

The format is based on [Keep a Changelog](http://keepachangelog.com/) and this project adheres to [Semantic Versioning](https://semver.org/)

## [Unreleased]

### Changed

- yield messages after confirming they were complete to ensure to corrupt data

## [3.4.0] 2025-10-20

### Changed
Expand Down
37 changes: 24 additions & 13 deletions cmem_plugin_kafka/kafka_handlers.py
Original file line number Diff line number Diff line change
Expand Up @@ -187,15 +187,22 @@ def _aggregate_data(self) -> Generator:
"""Generate json file with kafka messages"""
if not self._kafka_consumer:
raise ValueError("Kafka consumer is None")
try:
yield b"["
for count, message in enumerate(self._kafka_consumer.poll()):
if count > 0:
yield b","
yield get_message_with_json_wrapper(message).encode()
yield b"]"
except json.decoder.JSONDecodeError as ex:
raise ValueError("Kafka Message is not in expected format ") from ex
yield b"["
first = True
for message in self._kafka_consumer.poll():
try:
validated_message = get_message_with_json_wrapper(message)
serialized = validated_message.encode("utf-8")
except (json.JSONDecodeError, UnicodeDecodeError, ValueError) as ex:
raise ValueError(
f"Invalid or incomplete message at offset {message.offset}: {ex}"
) from ex

if not first:
yield b","
first = False
yield serialized
yield b"]"


class KafkaXMLDataHandler(KafkaDatasetHandler):
Expand Down Expand Up @@ -227,13 +234,17 @@ def __init__(

def _aggregate_data(self) -> Generator:
"""Generate xml file with kafka messages"""
if not self._kafka_consumer:
raise ValueError("Kafka consumer is None")
yield b'<?xml version="1.0" encoding="UTF-8"?>\n'
yield b"<KafkaMessages>"
for message in self._kafka_consumer.poll():
yield get_message_with_xml_wrapper(message).encode()

try:
validated_message = get_message_with_xml_wrapper(message)
serialized = validated_message.encode("utf-8")
except (UnicodeDecodeError, ValueError) as ex:
raise ValueError(
f"Invalid or incomplete message at offset {message.offset}: {ex}"
) from ex
yield serialized
yield b"</KafkaMessages>"

def _split_data(self, data: Response) -> Generator[KafkaMessage]:
Expand Down
Loading
Loading