ruby-kafka 0.7.9 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9facc22cb8739a683d4be6ee8389f0e2c6e7a6530e17e855ee6333aabdf428f0
-  data.tar.gz: d0e979d9e2e0ccf776d7d062e807367ff6380fa4f2863ecf6c414f3a7a3dc1fa
+  metadata.gz: 0f8391cc7b1989cb5f669796bc4ad647b77d882e6506fae42bab18acb8a6bcc6
+  data.tar.gz: 012baaff5d2cc9eb17e3a7b7342f49f7c905a5f91d26078fa0ecf2f0fa81a2ad
 SHA512:
-  metadata.gz: b339415a8ba234fe78d0fce1c36933f7d39e79561dfd296a1cdb580877f3e5ab7fe5c8119709458b5207f9dc9375638d7a1e93c5c24adc155841dca07b783e5b
-  data.tar.gz: b54e211a11096e98c6460958de7097c4293fdee3dac18e117f75e9ce2c1eeb6b749a8a8f2b5ba8e559ee75c4fa33a8a299c68e37bab9a1f7e16194d8dd8ef92f
+  metadata.gz: 7f4e9302ca0ab41a6fded75f95ed866d959a2a027b90051ed7f3d7fba573aa63e57be7692d004dbeb3bacd99fe44b24188f81b0f3bed50f68e1da5189262271f
+  data.tar.gz: 7266bdd50e66a7ab9b3c71025468af0a4bea778fd312c41d4c699e2609420c11c28accb3246407ce98330bf521c109691bd1d4943dd532a44ee6732f1a410922

data/.circleci/config.yml

@@ -145,21 +145,149 @@ jobs:
         environment:
           LOG_LEVEL: DEBUG
       - image: wurstmeister/zookeeper
-      - image: wurstmeister/kafka:2.12-2.1.0
+      - image: wurstmeister/kafka:2.12-2.1.1
         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:2.12-2.1.0
+      - image: wurstmeister/kafka:2.12-2.1.1
         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:2.12-2.1.0
+      - image: wurstmeister/kafka:2.12-2.1.1
+        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: bundle install --path vendor/bundle
+      - run: bundle exec rspec --profile --tag functional spec/functional
+
+  kafka-2.2:
+    docker:
+      - image: circleci/ruby:2.5.1-node
+        environment:
+          LOG_LEVEL: DEBUG
+      - image: wurstmeister/zookeeper
+      - image: wurstmeister/kafka:2.12-2.2.1
+        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:2.12-2.2.1
+        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:2.12-2.2.1
+        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: 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: 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: 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
@@ -181,3 +309,7 @@ workflows:
       - kafka-1.1
       - kafka-2.0
       - kafka-2.1
+      - kafka-2.2
+      - kafka-2.3
+      - kafka-2.4
+      - kafka-2.5

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 +2,32 @@
 
 Changes and additions to the library will be listed here.
 
+## Unreleased
+
+## 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)
+
 ## 0.7.9
 
 - Fix SSL authentication for ruby < 2.4.0 (#742)

data/README.md

@@ -108,6 +108,26 @@ Or install it yourself as:
     <td>Limited support</td>
     <td>Limited support</td>
   </tr>
+  <tr>
+    <th>Kafka 2.2</th>
+    <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>
 </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.
@@ -119,6 +139,10 @@ 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.
 
 This library requires Ruby 2.1 or higher.
 
@@ -325,6 +349,26 @@ 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, ...)
+```
+
 #### 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.
@@ -928,6 +972,8 @@ 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 `verify_hostname: false`.
+
 ```ruby
 kafka = Kafka.new(
   ["kafka1:9092"],

data/lib/kafka/async_producer.rb

@@ -103,6 +103,9 @@ module Kafka
     # @raise [BufferOverflow] if the message queue is full.
     # @return [nil]
     def produce(value, topic:, **options)
+      # We want to fail fast if `topic` isn't a String
+      topic = topic.to_str
+
       ensure_threads_running!
 
       if @queue.size >= @max_queue_size
@@ -243,10 +246,10 @@ module Kafka
 
       private
 
-      def produce(*args)
+      def produce(value, **kwargs)
         retries = 0
         begin
-          @producer.produce(*args)
+          @producer.produce(value, **kwargs)
         rescue BufferOverflow => e
           deliver_messages
           if @max_retries == -1

data/lib/kafka/client.rb

@@ -62,16 +62,25 @@ module Kafka
     #
     # @param sasl_over_ssl [Boolean] whether to enforce SSL with SASL
     #
+    # @param ssl_ca_certs_from_system [Boolean] whether to use the CA certs from the
+    #   system's default certificate store.
+    #
+    # @param partitioner [Partitioner, nil] the partitioner that should be used by the client.
+    #
     # @param sasl_oauth_token_provider [Object, nil] OAuthBearer Token Provider instance that
     #   implements method token. See {Sasl::OAuth#initialize}
     #
+    # @param ssl_verify_hostname [Boolean, true] whether to verify that the host serving
+    #   the SSL certificate and the signing chain of the certificate have the correct domains
+    #   based on the CA certificate
+    #
     # @return [Client]
     def initialize(seed_brokers:, client_id: "ruby-kafka", logger: nil, connect_timeout: nil, socket_timeout: nil,
                    ssl_ca_cert_file_path: nil, ssl_ca_cert: nil, ssl_client_cert: nil, ssl_client_cert_key: nil,
                    ssl_client_cert_key_password: nil, ssl_client_cert_chain: nil, sasl_gssapi_principal: nil,
                    sasl_gssapi_keytab: nil, sasl_plain_authzid: '', sasl_plain_username: nil, sasl_plain_password: nil,
                    sasl_scram_username: nil, sasl_scram_password: nil, sasl_scram_mechanism: nil,
-                   sasl_over_ssl: true, ssl_ca_certs_from_system: false, sasl_oauth_token_provider: nil, ssl_verify_hostname: true)
+                   sasl_over_ssl: true, ssl_ca_certs_from_system: false, partitioner: nil, sasl_oauth_token_provider: nil, ssl_verify_hostname: true)
       @logger = TaggedLogger.new(logger)
       @instrumenter = Instrumenter.new(client_id: client_id)
       @seed_brokers = normalize_seed_brokers(seed_brokers)
@@ -115,6 +124,7 @@ module Kafka
       )
 
       @cluster = initialize_cluster
+      @partitioner = partitioner || Partitioner.new
     end
 
     # Delivers a single message to the Kafka cluster.
@@ -138,6 +148,9 @@ module Kafka
     def deliver_message(value, key: nil, headers: {}, topic:, partition: nil, partition_key: nil, retries: 1)
       create_time = Time.now
 
+      # We want to fail fast if `topic` isn't a String
+      topic = topic.to_str
+
       message = PendingMessage.new(
         value: value,
         key: key,
@@ -150,7 +163,7 @@ module Kafka
 
       if partition.nil?
         partition_count = @cluster.partitions_for(topic).count
-        partition = Partitioner.partition_for_key(partition_count, message)
+        partition = @partitioner.call(partition_count, message)
       end
 
       buffer = MessageBuffer.new
@@ -241,6 +254,9 @@ module Kafka
     #   be in a message set before it should be compressed. Note that message sets
     #   are per-partition rather than per-topic or per-producer.
     #
+    # @param interceptors [Array<Object>] a list of producer interceptors the implement
+    #   `call(Kafka::PendingMessage)`.
+    #
     # @return [Kafka::Producer] the Kafka producer.
     def producer(
       compression_codec: nil,
@@ -254,7 +270,8 @@ module Kafka
       idempotent: false,
       transactional: false,
       transactional_id: nil,
-      transactional_timeout: 60
+      transactional_timeout: 60,
+      interceptors: []
     )
       cluster = initialize_cluster
       compressor = Compressor.new(
@@ -284,6 +301,8 @@ module Kafka
         retry_backoff: retry_backoff,
         max_buffer_size: max_buffer_size,
         max_buffer_bytesize: max_buffer_bytesize,
+        partitioner: @partitioner,
+        interceptors: interceptors
       )
     end
 
@@ -333,15 +352,23 @@ module Kafka
     # @param fetcher_max_queue_size [Integer] max number of items in the fetch queue that
     #   are stored for further processing. Note, that each item in the queue represents a
     #   response from a single broker.
+    # @param refresh_topic_interval [Integer] interval of refreshing the topic list.
+    #   If it is 0, the topic list won't be refreshed (default)
+    #   If it is n (n > 0), the topic list will be refreshed every n seconds
+    # @param interceptors [Array<Object>] a list of consumer interceptors that implement
+    #   `call(Kafka::FetchedBatch)`.
     # @return [Consumer]
     def consumer(
         group_id:,
         session_timeout: 30,
+        rebalance_timeout: 60,
         offset_commit_interval: 10,
         offset_commit_threshold: 0,
         heartbeat_interval: 10,
         offset_retention_time: nil,
-        fetcher_max_queue_size: 100
+        fetcher_max_queue_size: 100,
+        refresh_topic_interval: 0,
+        interceptors: []
     )
       cluster = initialize_cluster
 
@@ -357,6 +384,7 @@ module Kafka
         logger: @logger,
         group_id: group_id,
         session_timeout: session_timeout,
+        rebalance_timeout: rebalance_timeout,
         retention_time: retention_time,
         instrumenter: instrumenter,
       )
@@ -394,6 +422,8 @@ module Kafka
         fetcher: fetcher,
         session_timeout: session_timeout,
         heartbeat: heartbeat,
+        refresh_topic_interval: refresh_topic_interval,
+        interceptors: interceptors
       )
     end
 
@@ -530,6 +560,24 @@ module Kafka
       end
     end
 
+    # Describe broker configs
+    #
+    # @param broker_id [int] the id of the broker
+    # @param configs [Array] array of config keys.
+    # @return [Array<Kafka::Protocol::DescribeConfigsResponse::ConfigEntry>]
+    def describe_configs(broker_id, configs = [])
+      @cluster.describe_configs(broker_id, configs)
+    end
+
+    # Alter broker configs
+    #
+    # @param broker_id [int] the id of the broker
+    # @param configs [Array] array of config strings.
+    # @return [nil]
+    def alter_configs(broker_id, configs = [])
+      @cluster.alter_configs(broker_id, configs)
+    end
+
     # Creates a topic in the cluster.
     #
     # @example Creating a topic with log compaction
@@ -615,6 +663,14 @@ module Kafka
       @cluster.describe_group(group_id)
     end
 
+    # Fetch all committed offsets for a consumer group
+    #
+    # @param group_id [String] the id of the consumer group
+    # @return [Hash<String, Hash<Integer, Kafka::Protocol::OffsetFetchResponse::PartitionOffsetInfo>>]
+    def fetch_group_offsets(group_id)
+      @cluster.fetch_group_offsets(group_id)
+    end
+
     # Create partitions for a topic.
     #
     # @param name [String] the name of the topic.
@@ -663,6 +719,14 @@ module Kafka
       @cluster.partitions_for(topic).count
     end
 
+    # Counts the number of replicas for a topic's partition
+    #
+    # @param topic [String]
+    # @return [Integer] the number of replica nodes for the topic's partition
+    def replica_count_for(topic)
+      @cluster.partitions_for(topic).first.replicas.count
+    end
+
     # Retrieve the offset of the last message in a partition. If there are no
     # messages in the partition -1 is returned.
     #