Merge branch 'master' into feature/skip_control_batch

Author: wbarnha

.github/workflows/python-package.yml

@@ -68,9 +68,6 @@ jobs:
           - "3.12"
           - "pypy3.9"
         experimental: [ false ]
-        include:
-          - python-version: "~3.13.0-0"
-            experimental: true
     steps:
       - name: Checkout the source code
         uses: actions/checkout@v4
@@ -110,7 +107,7 @@ jobs:
           KAFKA_VERSION: ${{ env.KAFKA_LATEST }}
 
   test-kafka:
-    name: Tests for Kafka ${{ matrix.kafka-version }}
+    name: Tests for Kafka ${{ matrix.kafka-version }} (Python ${{ matrix.python-version }})
     needs:
       - build-sdist
     runs-on: ubuntu-latest
@@ -127,10 +124,17 @@ jobs:
           - "2.4.0"
           - "2.5.0"
           - "2.6.0"
+        python-version: ['3.12']
         experimental: [false]
         include:
           - kafka-version: '0.8.2.2'
             experimental: true
+            python-version: "3.12"
+          - kafka-version: '0.8.2.2'
+            experimental: false
+            python-version: "3.10"
+    env:
+      PYTHON_LATEST: ${{ matrix.python-version }}
     continue-on-error: ${{ matrix.experimental }}
     steps:
       - name: Checkout the source code
@@ -145,7 +149,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ env.PYTHON_LATEST }}
+          python-version: ${{ matrix.python-version }}
           cache: pip
           cache-dependency-path: |
             requirements-dev.txt

README.rst

@@ -32,13 +32,19 @@ check code (perhaps using zookeeper or consul). For older brokers, you can
 achieve something similar by manually assigning different partitions to each
 consumer instance with config management tools like chef, ansible, etc. This
 approach will work fine, though it does not support rebalancing on failures.
-See <https://kafka-python-ng.readthedocs.io/en/master/compatibility.html>
+
+See https://kafka-python.readthedocs.io/en/master/compatibility.html
+
 for more details.
 
 Please note that the master branch may contain unreleased features. For release
 documentation, please see readthedocs and/or python's inline help.
 
->>> pip install kafka-python-ng
+
+.. code-block:: bash 
+
+    $  pip install kafka-python-ng
+
 
 
 KafkaConsumer
@@ -48,89 +54,123 @@ KafkaConsumer is a high-level message consumer, intended to operate as similarly
 as possible to the official java client. Full support for coordinated
 consumer groups requires use of kafka brokers that support the Group APIs: kafka v0.9+.
 
-See <https://kafka-python-ng.readthedocs.io/en/master/apidoc/KafkaConsumer.html>
+
+See https://kafka-python.readthedocs.io/en/master/apidoc/KafkaConsumer.html
+
 for API and configuration details.
 
 The consumer iterator returns ConsumerRecords, which are simple namedtuples
 that expose basic message attributes: topic, partition, offset, key, and value:
 
->>> from kafka import KafkaConsumer
->>> consumer = KafkaConsumer('my_favorite_topic')
->>> for msg in consumer:
-...     print (msg)
+.. code-block:: python
 
->>> # join a consumer group for dynamic partition assignment and offset commits
->>> from kafka import KafkaConsumer
->>> consumer = KafkaConsumer('my_favorite_topic', group_id='my_favorite_group')
->>> for msg in consumer:
-...     print (msg)
+    from kafka import KafkaConsumer
+    consumer = KafkaConsumer('my_favorite_topic')
+    for msg in consumer:
+        print (msg)
 
->>> # manually assign the partition list for the consumer
->>> from kafka import TopicPartition
->>> consumer = KafkaConsumer(bootstrap_servers='localhost:1234')
->>> consumer.assign([TopicPartition('foobar', 2)])
->>> msg = next(consumer)
+.. code-block:: python
 
->>> # Deserialize msgpack-encoded values
->>> consumer = KafkaConsumer(value_deserializer=msgpack.loads)
->>> consumer.subscribe(['msgpackfoo'])
->>> for msg in consumer:
-...     assert isinstance(msg.value, dict)
+    # join a consumer group for dynamic partition assignment and offset commits
+    from kafka import KafkaConsumer
+    consumer = KafkaConsumer('my_favorite_topic', group_id='my_favorite_group')
+    for msg in consumer:
+        print (msg)
 
->>> # Access record headers. The returned value is a list of tuples
->>> # with str, bytes for key and value
->>> for msg in consumer:
-...     print (msg.headers)
+.. code-block:: python
 
->>> # Get consumer metrics
->>> metrics = consumer.metrics()
+    # manually assign the partition list for the consumer
+    from kafka import TopicPartition
+    consumer = KafkaConsumer(bootstrap_servers='localhost:1234')
+    consumer.assign([TopicPartition('foobar', 2)])
+    msg = next(consumer)
+
+.. code-block:: python
+
+    # Deserialize msgpack-encoded values
+    consumer = KafkaConsumer(value_deserializer=msgpack.loads)
+    consumer.subscribe(['msgpackfoo'])
+    for msg in consumer:
+        assert isinstance(msg.value, dict)
+
+.. code-block:: python
+
+    # Access record headers. The returned value is a list of tuples
+    # with str, bytes for key and value
+    for msg in consumer:
+        print (msg.headers)
+
+.. code-block:: python
+
+    # Get consumer metrics
+    metrics = consumer.metrics()
 
 
 KafkaProducer
 *************
 
 KafkaProducer is a high-level, asynchronous message producer. The class is
 intended to operate as similarly as possible to the official java client.
-See <https://kafka-python-ng.readthedocs.io/en/master/apidoc/KafkaProducer.html>
+
+See https://kafka-python.readthedocs.io/en/master/apidoc/KafkaProducer.html
+
 for more details.
 
->>> from kafka import KafkaProducer
->>> producer = KafkaProducer(bootstrap_servers='localhost:1234')
->>> for _ in range(100):
-...     producer.send('foobar', b'some_message_bytes')
+.. code-block:: python
+
+    from kafka import KafkaProducer
+    producer = KafkaProducer(bootstrap_servers='localhost:1234')
+    for _ in range(100):
+        producer.send('foobar', b'some_message_bytes')
+
+.. code-block:: python
+
+    # Block until a single message is sent (or timeout)
+    future = producer.send('foobar', b'another_message')
+    result = future.get(timeout=60)
+
+.. code-block:: python
+
+    # Block until all pending messages are at least put on the network
+    # NOTE: This does not guarantee delivery or success! It is really
+    # only useful if you configure internal batching using linger_ms
+    producer.flush()
+
+.. code-block:: python
 
->>> # Block until a single message is sent (or timeout)
->>> future = producer.send('foobar', b'another_message')
->>> result = future.get(timeout=60)
+    # Use a key for hashed-partitioning
+    producer.send('foobar', key=b'foo', value=b'bar')
 
->>> # Block until all pending messages are at least put on the network
->>> # NOTE: This does not guarantee delivery or success! It is really
->>> # only useful if you configure internal batching using linger_ms
->>> producer.flush()
+.. code-block:: python
 
->>> # Use a key for hashed-partitioning
->>> producer.send('foobar', key=b'foo', value=b'bar')
+    # Serialize json messages
+    import json
+    producer = KafkaProducer(value_serializer=lambda v: json.dumps(v).encode('utf-8'))
+    producer.send('fizzbuzz', {'foo': 'bar'})
 
->>> # Serialize json messages
->>> import json
->>> producer = KafkaProducer(value_serializer=lambda v: json.dumps(v).encode('utf-8'))
->>> producer.send('fizzbuzz', {'foo': 'bar'})
+.. code-block:: python
 
->>> # Serialize string keys
->>> producer = KafkaProducer(key_serializer=str.encode)
->>> producer.send('flipflap', key='ping', value=b'1234')
+    # Serialize string keys
+    producer = KafkaProducer(key_serializer=str.encode)
+    producer.send('flipflap', key='ping', value=b'1234')
 
->>> # Compress messages
->>> producer = KafkaProducer(compression_type='gzip')
->>> for i in range(1000):
-...     producer.send('foobar', b'msg %d' % i)
+.. code-block:: python
 
->>> # Include record headers. The format is list of tuples with string key
->>> # and bytes value.
->>> producer.send('foobar', value=b'c29tZSB2YWx1ZQ==', headers=[('content-encoding', b'base64')])
+    # Compress messages
+    producer = KafkaProducer(compression_type='gzip')
+    for i in range(1000):
+        producer.send('foobar', b'msg %d' % i)
 
->>> # Get producer performance metrics
->>> metrics = producer.metrics()
+.. code-block:: python
+
+    # Include record headers. The format is list of tuples with string key
+    # and bytes value.
+    producer.send('foobar', value=b'c29tZSB2YWx1ZQ==', headers=[('content-encoding', b'base64')])
+
+.. code-block:: python
+
+    # Get producer performance metrics
+    metrics = producer.metrics()
 
 
 Thread safety
@@ -154,16 +194,19 @@ kafka-python-ng supports the following compression formats:
 - Zstandard (zstd)
 
 gzip is supported natively, the others require installing additional libraries.
-See <https://kafka-python-ng.readthedocs.io/en/master/install.html> for more information.
+
+See https://kafka-python.readthedocs.io/en/master/install.html for more information.
+
 
 
 Optimized CRC32 Validation
 **************************
 
 Kafka uses CRC32 checksums to validate messages. kafka-python-ng includes a pure
 python implementation for compatibility. To improve performance for high-throughput
-applications, kafka-python-ng will use `crc32c` for optimized native code if installed.
-See <https://kafka-python-ng.readthedocs.io/en/master/install.html> for installation instructions.
+applications, kafka-python will use `crc32c` for optimized native code if installed.
+See https://kafka-python.readthedocs.io/en/master/install.html for installation instructions.
+
 See https://pypi.org/project/crc32c/ for details on the underlying crc32c lib.