ruby-kafka 0.7.10 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5aa84a39ade791c3bce57152d426e95cb7d29575af3e8a9cb29fcded1c6cdad5
-  data.tar.gz: 46be738fb1a2b71bbbd5d5d3b2fc95b705aef5740f666095eeaf40c9a6980fc4
+  metadata.gz: '037679129d871686838235c368d870493439212f9aed0e897c1254fbfd5e4751'
+  data.tar.gz: bf61f193e97eb326b62a47b525a865911f1a7307983b6e765c08cc95e368a262
 SHA512:
-  metadata.gz: 42e8059ab9b49e16a8e9c70e5739c9694d2142d5d440f8e2c18477cc151a24183536ae1548aed66a7e7ee6ea64c96ff2c9aacb63366ed92bd1612af6e52d8300
-  data.tar.gz: 5008c803cc61fbea993f7f2a22ca7ac3ebb448f91cbdca40d540b9f4604dab8b4e38fcf4b20006a16641b5239e78d6045ccbec70168171219b716090ea72ba09
+  metadata.gz: 8d53ee98b08cda3c8b64dd44ccb27d16fe6f9c5b65986115ce1db8c6d4fae03543fb9f83dc5765f40e4455e23986c323593fc8b9fc89e14a5dae4ec912a83981
+  data.tar.gz: 48229b285251618f66f55963074285e01de96c71be4f65a2340a4c34e394db494aea76c3f8254075eb5670881a43a2ed51b2874d0c188c94d9bac9d7f27d38df

data/.circleci/config.yml

@@ -7,6 +7,7 @@ jobs:
           LOG_LEVEL: DEBUG
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec
       - run: bundle exec rubocop
@@ -40,6 +41,7 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -72,6 +74,7 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -104,6 +107,7 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -136,6 +140,7 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -168,6 +173,7 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -200,6 +206,174 @@ jobs:
           KAFKA_DELETE_TOPIC_ENABLE: true
     steps:
       - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
+      - run: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.3:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: wurstmeister/zookeeper
+      - image: wurstmeister/kafka:2.12-2.3.1
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9092
+          KAFKA_PORT: 9092
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.3.1
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9093
+          KAFKA_PORT: 9093
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.3.1
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9094
+          KAFKA_PORT: 9094
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+    steps:
+      - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
+      - run: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.4:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: wurstmeister/zookeeper
+      - image: wurstmeister/kafka:2.12-2.4.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9092
+          KAFKA_PORT: 9092
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.4.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9093
+          KAFKA_PORT: 9093
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.4.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9094
+          KAFKA_PORT: 9094
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+    steps:
+      - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
+      - run: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.5:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: wurstmeister/zookeeper
+      - image: wurstmeister/kafka:2.12-2.5.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9092
+          KAFKA_PORT: 9092
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.5.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9093
+          KAFKA_PORT: 9093
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.12-2.5.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9094
+          KAFKA_PORT: 9094
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+    steps:
+      - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
+      - run: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.6:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: wurstmeister/zookeeper
+      - image: wurstmeister/kafka:2.13-2.6.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9092
+          KAFKA_PORT: 9092
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.13-2.6.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9093
+          KAFKA_PORT: 9093
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: wurstmeister/kafka:2.13-2.6.0
+        environment:
+          KAFKA_ADVERTISED_HOST_NAME: localhost
+          KAFKA_ADVERTISED_PORT: 9094
+          KAFKA_PORT: 9094
+          KAFKA_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+    steps:
+      - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
+      - run: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.7:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: bitnami/zookeeper
+        environment:
+          ALLOW_ANONYMOUS_LOGIN: yes
+      - image: bitnami/kafka:2.7.0
+        environment:
+          ALLOW_PLAINTEXT_LISTENER: yes
+          KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://localhost:9092
+          KAFKA_LISTENERS: PLAINTEXT://0.0.0.0:9092
+          KAFKA_CFG_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: bitnami/kafka:2.7.0
+        environment:
+          ALLOW_PLAINTEXT_LISTENER: yes
+          KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://localhost:9093
+          KAFKA_LISTENERS: PLAINTEXT://0.0.0.0:9093
+          KAFKA_CFG_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+      - image: bitnami/kafka:2.7.0
+        environment:
+          ALLOW_PLAINTEXT_LISTENER: yes
+          KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://localhost:9094
+          KAFKA_LISTENERS: PLAINTEXT://0.0.0.0:9094
+          KAFKA_CFG_ZOOKEEPER_CONNECT: localhost:2181
+          KAFKA_DELETE_TOPIC_ENABLE: true
+    steps:
+      - checkout
+      - run: sudo apt-get update && sudo apt-get install -y cmake # For installing snappy
       - run: bundle install --path vendor/bundle
       - run: bundle exec rspec --profile --tag functional spec/functional
 
@@ -214,3 +388,8 @@ workflows:
       - kafka-2.0
       - kafka-2.1
       - kafka-2.2
+      - kafka-2.3
+      - kafka-2.4
+      - kafka-2.5
+      - kafka-2.6
+      - kafka-2.7

data/.github/workflows/stale.yml

@@ -0,0 +1,19 @@
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: "0 0 * * *"
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/stale@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'Issue has been marked as stale due to a lack of activity.'
+        stale-pr-message: 'Pull request has been marked as stale due to a lack of activity.'
+        stale-issue-label: 'no-issue-activity'
+        stale-pr-label: 'no-pr-activity'

data/.ruby-version

@@ -1 +1 @@
-2.5.1
+2.7.1

data/CHANGELOG.md

@@ -2,6 +2,46 @@
 
 Changes and additions to the library will be listed here.
 
+## Unreleased
+
+## 1.5.0
+- Add support for AWS IAM Authentication to an MSK cluster (#907).
+- Added session token to the IAM mechanism; necessary for auth via temporary credentials (#937)
+
+## 1.4.0
+
+- Refresh a stale cluster's metadata if necessary on `Kafka::Client#deliver_message` (#901).
+- Fix `Kafka::TransactionManager#send_offsets_to_txn` (#866).
+- Add support for `murmur2` based partitioning.
+- Add `resolve_seed_brokers` option to support seed brokers' hostname with multiple addresses (#877).
+- Handle SyncGroup responses with a non-zero error and no assignments (#896).
+- Add support for non-identical topic subscriptions within the same consumer group (#525 / #764).
+
+## 1.3.0
+
+- Support custom assignment strategy (#846).
+- Improved Exceptions in TransactionManager (#862).
+
+## 1.2.0
+
+- Add producer consumer interceptors (#837).
+- Add support for configuring the client partitioner (#848).
+
+## 1.1.0
+
+- Extra sanity checking when marking offsets as processed (#824).
+- Make `verify_hostname` settable for SSL contexts (#828).
+- Instrument `create_time` from last message in batch (#811).
+- Add client function for fetching topic replica count (#822).
+- Allow consumers to refresh the topic lists (#818).
+- Disconnect after leaving a group (#817).
+- Use `max_wait_time` as the sleep instead of hardcoded 2 seconds (#825).
+
+## 1.0.0
+
+- Add client methods to manage configs (#759)
+- Support Kafka 2.3 and 2.4.
+
 ## 0.7.10
 
 - Fix logger again (#762)

data/README.md

@@ -26,6 +26,7 @@ A Ruby client library for [Apache Kafka](http://kafka.apache.org/), a distribute
         4. [Shutting Down a Consumer](#shutting-down-a-consumer)
         5. [Consuming Messages in Batches](#consuming-messages-in-batches)
         6. [Balancing Throughput and Latency](#balancing-throughput-and-latency)
+        7. [Customizing Partition Assignment Strategy](#customizing-partition-assignment-strategy)
     4. [Thread Safety](#thread-safety)
     5. [Logging](#logging)
     6. [Instrumentation](#instrumentation)
@@ -113,6 +114,31 @@ Or install it yourself as:
     <td>Limited support</td>
     <td>Limited support</td>
   </tr>
+  <tr>
+    <th>Kafka 2.3</th>
+    <td>Limited support</td>
+    <td>Limited support</td>
+  </tr>
+  <tr>
+    <th>Kafka 2.4</th>
+    <td>Limited support</td>
+    <td>Limited support</td>
+  </tr>
+  <tr>
+    <th>Kafka 2.5</th>
+    <td>Limited support</td>
+    <td>Limited support</td>
+  </tr>
+  <tr>
+    <th>Kafka 2.6</th>
+    <td>Limited support</td>
+    <td>Limited support</td>
+  </tr>
+  <tr>
+    <th>Kafka 2.7</th>
+    <td>Limited support</td>
+    <td>Limited support</td>
+  </tr>
 </table>
 
 This library is targeting Kafka 0.9 with the v0.4.x series and Kafka 0.10 with the v0.5.x series. There's limited support for Kafka 0.8, and things should work with Kafka 0.11, although there may be performance issues due to changes in the protocol.
@@ -124,6 +150,12 @@ This library is targeting Kafka 0.9 with the v0.4.x series and Kafka 0.10 with t
 - **Kafka 1.0:** Everything that works with Kafka 0.11 should still work, but so far no features specific to Kafka 1.0 have been added.
 - **Kafka 2.0:** Everything that works with Kafka 1.0 should still work, but so far no features specific to Kafka 2.0 have been added.
 - **Kafka 2.1:** Everything that works with Kafka 2.0 should still work, but so far no features specific to Kafka 2.1 have been added.
+- **Kafka 2.2:** Everything that works with Kafka 2.1 should still work, but so far no features specific to Kafka 2.2 have been added.
+- **Kafka 2.3:** Everything that works with Kafka 2.2 should still work, but so far no features specific to Kafka 2.3 have been added.
+- **Kafka 2.4:** Everything that works with Kafka 2.3 should still work, but so far no features specific to Kafka 2.4 have been added.
+- **Kafka 2.5:** Everything that works with Kafka 2.4 should still work, but so far no features specific to Kafka 2.5 have been added.
+- **Kafka 2.6:** Everything that works with Kafka 2.5 should still work, but so far no features specific to Kafka 2.6 have been added.
+- **Kafka 2.7:** Everything that works with Kafka 2.6 should still work, but so far no features specific to Kafka 2.7 have been added.
 
 This library requires Ruby 2.1 or higher.
 
@@ -144,6 +176,12 @@ require "kafka"
 kafka = Kafka.new(["kafka1:9092", "kafka2:9092"], client_id: "my-application")
 ```
 
+You can also use a hostname with seed brokers' IP addresses:
+
+```ruby
+kafka = Kafka.new("seed-brokers:9092", client_id: "my-application", resolve_seed_brokers: true)
+```
+
 ### Producing Messages to Kafka
 
 The simplest way to write a message to a Kafka topic is to call `#deliver_message`:
@@ -330,6 +368,36 @@ partition = PartitioningScheme.assign(partitions, event)
 producer.produce(event, topic: "events", partition: partition)
 ```
 
+Another option is to configure a custom client partitioner that implements `call(partition_count, message)` and uses the same schema as the other client. For example:
+
+```ruby
+class CustomPartitioner
+  def call(partition_count, message)
+    ...
+  end
+end
+  
+partitioner = CustomPartitioner.new
+Kafka.new(partitioner: partitioner, ...)
+```
+
+Or, simply create a Proc handling the partitioning logic instead of having to add a new class. For example:
+
+```ruby
+partitioner = -> (partition_count, message) { ... }
+Kafka.new(partitioner: partitioner, ...)
+```
+
+##### Supported partitioning schemes
+
+In order for semantic partitioning to work a `partition_key` must map to the same partition number every time. The general approach, and the one used by this library, is to hash the key and mod it by the number of partitions. There are many different algorithms that can be used to calculate a hash. By default `crc32` is used. `murmur2` is also supported for compatibility with Java based Kafka producers.
+
+To use `murmur2` hashing pass it as an argument to `Partitioner`. For example:
+
+```ruby
+Kafka.new(partitioner: Kafka::Partitioner.new(hash_function: :murmur2))
+```
+
 #### Buffering and Error Handling
 
 The producer is designed for resilience in the face of temporary network errors, Kafka broker failovers, and other issues that prevent the client from writing messages to the destination topics. It does this by employing local, in-memory buffers. Only when messages are acknowledged by a Kafka broker will they be removed from the buffer.
@@ -704,6 +772,88 @@ consumer.each_message do |message|
 end
 ```
 
+#### Customizing Partition Assignment Strategy
+
+In some cases, you might want to assign more partitions to some consumers. For example, in applications inserting some records to a database, the consumers running on hosts nearby the database can process more messages than the consumers running on other hosts.
+You can use a custom assignment strategy by passing an object that implements `#call` as the argument `assignment_strategy` like below:
+
+```ruby
+class CustomAssignmentStrategy
+  def initialize(user_data)
+    @user_data = user_data
+  end
+
+  # Assign the topic partitions to the group members.
+  #
+  # @param cluster [Kafka::Cluster]
+  # @param members [Hash<String, Kafka::Protocol::JoinGroupResponse::Metadata>] a hash
+  #   mapping member ids to metadata
+  # @param partitions [Array<Kafka::ConsumerGroup::Assignor::Partition>] a list of
+  #   partitions the consumer group processes
+  # @return [Hash<String, Array<Kafka::ConsumerGroup::Assignor::Partition>] a hash
+  #   mapping member ids to partitions.
+  def call(cluster:, members:, partitions:)
+    ...
+  end
+end
+
+strategy = CustomAssignmentStrategy.new("some-host-information")
+consumer = kafka.consumer(group_id: "some-group", assignment_strategy: strategy)
+```
+
+`members` is a hash mapping member IDs to metadata, and partitions is a list of partitions the consumer group processes. The method `call` must return a hash mapping member IDs to partitions. For example, the following strategy assigns partitions randomly:
+
+```ruby
+class RandomAssignmentStrategy
+  def call(cluster:, members:, partitions:)
+    member_ids = members.keys
+    partitions.each_with_object(Hash.new {|h, k| h[k] = [] }) do |partition, partitions_per_member|
+      partitions_per_member[member_ids[rand(member_ids.count)]] << partition
+    end
+  end
+end
+```
+
+If the strategy needs user data, you should define the method `user_data` that returns user data on each consumer. For example, the following strategy uses the consumers' IP addresses as user data:
+
+```ruby
+class NetworkTopologyAssignmentStrategy
+  def user_data
+    Socket.ip_address_list.find(&:ipv4_private?).ip_address
+  end
+
+  def call(cluster:, members:, partitions:)
+    # Display the pair of the member ID and IP address
+    members.each do |id, metadata|
+      puts "#{id}: #{metadata.user_data}"
+    end
+
+    # Assign partitions considering the network topology
+    ...
+  end
+end
+```
+
+Note that the strategy uses the class name as the default protocol name. You can change it by defining the method `protocol_name`:
+
+```ruby
+class NetworkTopologyAssignmentStrategy
+  def protocol_name
+    "networktopology"
+  end
+
+  def user_data
+    Socket.ip_address_list.find(&:ipv4_private?).ip_address
+  end
+
+  def call(cluster:, members:, partitions:)
+    ...
+  end
+end
+```
+
+As the method `call` might receive different user data from what it expects, you should avoid using the same protocol name as another strategy that uses different user data.
+
 
 ### Thread Safety
 
@@ -933,6 +1083,8 @@ This configures the store to look up CA certificates from the system default cer
 
 In order to authenticate the client to the cluster, you need to pass in a certificate and key created for the client and trusted by the brokers.
 
+**NOTE**: You can disable hostname validation by passing `ssl_verify_hostname: false`.
+
 ```ruby
 kafka = Kafka.new(
   ["kafka1:9092"],
@@ -940,6 +1092,7 @@ kafka = Kafka.new(
   ssl_client_cert: File.read('my_client_cert.pem'),
   ssl_client_cert_key: File.read('my_client_cert_key.pem'),
   ssl_client_cert_key_password: 'my_client_cert_key_password',
+  ssl_verify_hostname: false,
   # ...
 )
 ```
@@ -968,6 +1121,20 @@ kafka = Kafka.new(
 )
 ```
 
+##### AWS MSK (IAM)
+In order to authenticate using IAM w/ an AWS MSK cluster, set your access key, secret key, and region when initializing the Kafka client:
+
+```ruby
+k = Kafka.new(
+  ["kafka1:9092"],
+  sasl_aws_msk_iam_access_key_id: 'iam_access_key',
+  sasl_aws_msk_iam_secret_key_id: 'iam_secret_key',
+  sasl_aws_msk_iam_aws_region: 'us-west-2',
+  ssl_ca_certs_from_system: true,
+  # ...
+)
+```
+
 ##### PLAIN
 In order to authenticate using PLAIN, you must set your username and password when initializing the Kafka client: