logstash-integration-kafka 10.9.0-java → 11.3.2-java

data/lib/logstash/plugin_mixins/kafka/avro_schema_registry.rb

@@ -0,0 +1,139 @@
+require 'manticore'
+
+module LogStash module PluginMixins module Kafka
+  module AvroSchemaRegistry
+
+    def self.included(base)
+      base.extend(self)
+      base.setup_schema_registry_config
+    end
+
+    def setup_schema_registry_config
+      # Option to set key to access Schema Registry.
+      config :schema_registry_key, :validate => :string
+
+      # Option to set secret to access Schema Registry.
+      config :schema_registry_secret, :validate => :password
+
+      # Option to set the endpoint of the Schema Registry.
+      # This option permit the usage of Avro Kafka deserializer which retrieve the schema of the Avro message from an
+      # instance of schema registry. If this option has value `value_deserializer_class` nor `topics_pattern` could be valued
+      config :schema_registry_url, :validate => :uri
+
+      # Option to set the proxy of the Schema Registry.
+      # This option permits to define a proxy to be used to reach the schema registry service instance.
+      config :schema_registry_proxy, :validate => :uri
+
+      # If schema registry client authentication is required, this setting stores the keystore path.
+      config :schema_registry_ssl_keystore_location, :validate => :string
+
+      # The keystore password.
+      config :schema_registry_ssl_keystore_password, :validate => :password
+
+      # The keystore type
+      config :schema_registry_ssl_keystore_type, :validate => ['jks', 'PKCS12'], :default => "jks"
+
+      # The JKS truststore path to validate the Schema Registry's certificate.
+      config :schema_registry_ssl_truststore_location, :validate => :string
+
+      # The truststore password.
+      config :schema_registry_ssl_truststore_password, :validate => :password
+
+      # The truststore type
+      config :schema_registry_ssl_truststore_type, :validate => ['jks', 'PKCS12'], :default => "jks"
+
+      # Option to skip validating the schema registry during registration. This can be useful when using
+      # certificate based auth
+      config :schema_registry_validation, :validate => ['auto', 'skip'], :default => 'auto'
+    end
+
+    def check_schema_registry_parameters
+      if @schema_registry_url
+        check_for_schema_registry_conflicts
+        @schema_registry_proxy_host, @schema_registry_proxy_port  = split_proxy_into_host_and_port(schema_registry_proxy)
+        check_for_key_and_secret
+        check_for_schema_registry_connectivity_and_subjects if schema_registry_validation?
+      end
+    end
+
+    def schema_registry_validation?
+      return false if schema_registry_validation.to_s == 'skip'
+      return false if using_kerberos? # pre-validation doesn't support kerberos
+
+      true
+    end
+
+    def using_kerberos?
+      security_protocol == "SASL_PLAINTEXT" || security_protocol == "SASL_SSL"
+    end
+
+    private
+    def check_for_schema_registry_conflicts
+      if @value_deserializer_class != LogStash::Inputs::Kafka::DEFAULT_DESERIALIZER_CLASS
+        raise LogStash::ConfigurationError, 'Option schema_registry_url prohibit the customization of value_deserializer_class'
+      end
+      if @topics_pattern && !@topics_pattern.empty?
+       raise LogStash::ConfigurationError, 'Option schema_registry_url prohibit the customization of topics_pattern'
+      end
+    end
+
+    private
+    def check_for_schema_registry_connectivity_and_subjects
+      options = {}
+      if schema_registry_proxy && !schema_registry_proxy.empty?
+        options[:proxy] = schema_registry_proxy.to_s
+      end
+      if schema_registry_key and !schema_registry_key.empty?
+        options[:auth] = {:user => schema_registry_key, :password => schema_registry_secret.value}
+      end
+      if schema_registry_ssl_truststore_location and !schema_registry_ssl_truststore_location.empty?
+        options[:ssl] = {} unless options.key?(:ssl)
+        options[:ssl][:truststore] = schema_registry_ssl_truststore_location unless schema_registry_ssl_truststore_location.nil?
+        options[:ssl][:truststore_password] = schema_registry_ssl_truststore_password.value unless schema_registry_ssl_truststore_password.nil?
+        options[:ssl][:truststore_type] = schema_registry_ssl_truststore_type unless schema_registry_ssl_truststore_type.nil?
+      end
+      if schema_registry_ssl_keystore_location and !schema_registry_ssl_keystore_location.empty?
+        options[:ssl] = {} unless options.key? :ssl
+        options[:ssl][:keystore] = schema_registry_ssl_keystore_location unless schema_registry_ssl_keystore_location.nil?
+        options[:ssl][:keystore_password] = schema_registry_ssl_keystore_password.value unless schema_registry_ssl_keystore_password.nil?
+        options[:ssl][:keystore_type] = schema_registry_ssl_keystore_type unless schema_registry_ssl_keystore_type.nil?
+      end
+
+      client = Manticore::Client.new(options)
+      begin
+        response = client.get(@schema_registry_url.uri.to_s + '/subjects').body
+      rescue Manticore::ManticoreException => e
+        raise LogStash::ConfigurationError.new("Schema registry service doesn't respond, error: #{e.message}")
+      end
+      registered_subjects = JSON.parse response
+      expected_subjects = @topics.map { |t| "#{t}-value"}
+      if (expected_subjects & registered_subjects).size != expected_subjects.size
+        undefined_topic_subjects = expected_subjects - registered_subjects
+        raise LogStash::ConfigurationError, "The schema registry does not contain definitions for required topic subjects: #{undefined_topic_subjects}"
+      end
+    end
+
+    def split_proxy_into_host_and_port(proxy_uri)
+      return nil unless proxy_uri && !proxy_uri.empty?
+
+      port = proxy_uri.port
+
+      host_spec = ""
+      host_spec << proxy_uri.scheme || "http"
+      host_spec << "://"
+      host_spec << "#{proxy_uri.userinfo}@" if proxy_uri.userinfo
+      host_spec << proxy_uri.host
+
+      [host_spec, port]
+    end
+
+    def check_for_key_and_secret
+      if schema_registry_key and !schema_registry_key.empty?
+        if !schema_registry_secret or schema_registry_secret.value.empty?
+          raise LogStash::ConfigurationError, "Setting `schema_registry_secret` is required when `schema_registry_key` is provided."
+        end
+      end
+    end
+
+  end
+end end end

data/lib/logstash/plugin_mixins/kafka/common.rb

@@ -0,0 +1,55 @@
+module LogStash module PluginMixins module Kafka
+  module Common
+
+    def self.included(base)
+      # COMMON CONFIGURATION SUPPORTED BY BOTH PRODUCER/CONSUMER
+
+      # Close idle connections after the number of milliseconds specified by this config.
+      base.config :connections_max_idle_ms, :validate => :number, :default => 540_000 # (9m) Kafka default
+
+      # The period of time in milliseconds after which we force a refresh of metadata even if
+      # we haven't seen any partition leadership changes to proactively discover any new brokers or partitions
+      base.config :metadata_max_age_ms, :validate => :number, :default => 300_000 # (5m) Kafka default
+
+      # The configuration controls the maximum amount of time the client will wait for the response of a request.
+      # If the response is not received before the timeout elapses the client will resend the request if necessary
+      # or fail the request if retries are exhausted.
+      base.config :request_timeout_ms, :validate => :number, :default => 40_000 # Kafka default
+    end
+
+    def set_trustore_keystore_config(props)
+      props.put("ssl.truststore.type", ssl_truststore_type) unless ssl_truststore_type.nil?
+      props.put("ssl.truststore.location", ssl_truststore_location) unless ssl_truststore_location.nil?
+      props.put("ssl.truststore.password", ssl_truststore_password.value) unless ssl_truststore_password.nil?
+
+      # Client auth stuff
+      props.put("ssl.keystore.type", ssl_keystore_type) unless ssl_keystore_type.nil?
+      props.put("ssl.key.password", ssl_key_password.value) unless ssl_key_password.nil?
+      props.put("ssl.keystore.location", ssl_keystore_location) unless ssl_keystore_location.nil?
+      props.put("ssl.keystore.password", ssl_keystore_password.value) unless ssl_keystore_password.nil?
+      props.put("ssl.endpoint.identification.algorithm", ssl_endpoint_identification_algorithm) unless ssl_endpoint_identification_algorithm.nil?
+    end
+
+    def set_sasl_config(props)
+      java.lang.System.setProperty("java.security.auth.login.config", jaas_path) unless jaas_path.nil?
+      java.lang.System.setProperty("java.security.krb5.conf", kerberos_config) unless kerberos_config.nil?
+
+      props.put("sasl.mechanism", sasl_mechanism)
+      if sasl_mechanism == "GSSAPI" && sasl_kerberos_service_name.nil?
+        raise LogStash::ConfigurationError, "sasl_kerberos_service_name must be specified when SASL mechanism is GSSAPI"
+      end
+
+      props.put("sasl.kerberos.service.name", sasl_kerberos_service_name) unless sasl_kerberos_service_name.nil?
+      props.put("sasl.jaas.config", sasl_jaas_config) unless sasl_jaas_config.nil?
+    end
+
+    def reassign_dns_lookup
+      if @client_dns_lookup == "default"
+        @client_dns_lookup = "use_all_dns_ips"
+        logger.warn("client_dns_lookup setting 'default' value is deprecated, forced to 'use_all_dns_ips', please update your configuration")
+        deprecation_logger.deprecated("Deprecated value `default` for `client_dns_lookup` option; use `use_all_dns_ips` instead.")
+      end
+    end
+
+  end
+end end end

data/lib/logstash-integration-kafka_jars.rb

@@ -1,17 +1,12 @@
 # AUTOGENERATED BY THE GRADLE SCRIPT. DO NOT EDIT.
 
 require 'jar_dependencies'
-require_jar('io.confluent', 'kafka-avro-serializer', '5.5.1')
-require_jar('io.confluent', 'kafka-schema-serializer', '5.5.1')
-require_jar('io.confluent', 'common-config', '5.5.1')
-require_jar('org.apache.avro', 'avro', '1.9.2')
-require_jar('io.confluent', 'kafka-schema-registry-client', '5.5.1')
-require_jar('org.apache.kafka', 'kafka_2.12', '2.5.1')
-require_jar('io.confluent', 'common-utils', '5.5.1')
-require_jar('javax.ws.rs', 'javax.ws.rs-api', '2.1.1')
-require_jar('org.glassfish.jersey.core', 'jersey-common', '2.33')
-require_jar('org.apache.kafka', 'kafka-clients', '2.5.1')
-require_jar('com.github.luben', 'zstd-jni', '1.4.4-7')
-require_jar('org.slf4j', 'slf4j-api', '1.7.30')
-require_jar('org.lz4', 'lz4-java', '1.7.1')
-require_jar('org.xerial.snappy', 'snappy-java', '1.1.7.3')
+require_jar('io.confluent', 'kafka-avro-serializer', '7.4.0')
+require_jar('io.confluent', 'kafka-schema-serializer', '7.4.0')
+require_jar('org.apache.avro', 'avro', '1.11.3')
+require_jar('io.confluent', 'kafka-schema-registry-client', '7.4.0')
+require_jar('org.apache.kafka', 'kafka-clients', '3.4.1')
+require_jar('org.slf4j', 'slf4j-api', '1.7.36')
+require_jar('com.github.luben', 'zstd-jni', '1.5.5-4')
+require_jar('org.lz4', 'lz4-java', '1.8.0')
+require_jar('org.xerial.snappy', 'snappy-java', '1.1.10.5')

data/logstash-integration-kafka.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name            = 'logstash-integration-kafka'
-  s.version         = '10.9.0'
+  s.version         = '11.3.2'
   s.licenses        = ['Apache-2.0']
   s.summary         = "Integration with Kafka - input and output plugins"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline "+
@@ -41,7 +41,7 @@ Gem::Specification.new do |s|
 
   # Gem dependencies
   s.add_runtime_dependency "logstash-core-plugin-api", ">= 1.60", "<= 2.99"
-  s.add_runtime_dependency "logstash-core", ">= 6.5.0"
+  s.add_runtime_dependency "logstash-core", ">= 8.3.0"
 
   s.add_runtime_dependency 'logstash-codec-json'
   s.add_runtime_dependency 'logstash-codec-plain'

data/spec/integration/inputs/kafka_spec.rb

@@ -79,6 +79,7 @@ describe "inputs/kafka", :integration => true do
     producer = org.apache.kafka.clients.producer.KafkaProducer.new(props)
 
     producer.send(record)
+    producer.flush
     producer.close
   end
 
@@ -185,10 +186,105 @@ describe "inputs/kafka", :integration => true do
       end
     end
   end
+
+  context "static membership 'group.instance.id' setting" do
+    let(:base_config) do
+      {
+        "topics" => ["logstash_integration_static_membership_topic"],
+        "group_id" => "logstash",
+        "consumer_threads" => 1,
+        # this is needed because the worker thread could be executed little after the producer sent the "up" message
+        "auto_offset_reset" => "earliest",
+        "group_instance_id" => "test_static_group_id"
+      }
+    end
+    let(:consumer_config) { base_config }
+    let(:logger) { double("logger") }
+    let(:queue) { java.util.concurrent.ArrayBlockingQueue.new(10) }
+    let(:kafka_input) { LogStash::Inputs::Kafka.new(consumer_config) }
+    before :each do
+      allow(LogStash::Inputs::Kafka).to receive(:logger).and_return(logger)
+      [:error, :warn, :info, :debug].each do |level|
+        allow(logger).to receive(level)
+      end
+
+      kafka_input.register
+    end
+
+    it "input plugin disconnects from the broker when another client with same static membership connects" do
+      expect(logger).to receive(:error).with("Another consumer with same group.instance.id has connected", anything)
+
+      input_worker = java.lang.Thread.new { kafka_input.run(queue) }
+      begin
+        input_worker.start
+        wait_kafka_input_is_ready("logstash_integration_static_membership_topic", queue)
+        saboteur_kafka_consumer = create_consumer_and_start_consuming("test_static_group_id")
+        saboteur_kafka_consumer.run # ask to be scheduled
+        saboteur_kafka_consumer.join
+
+        expect(saboteur_kafka_consumer.value).to eq("saboteur exited")
+      ensure
+        input_worker.join(30_000)
+      end
+    end
+
+    context "when the plugin is configured with multiple consumer threads" do
+      let(:consumer_config) { base_config.merge({"consumer_threads" => 2}) }
+
+      it "should avoid to connect with same 'group.instance.id'" do
+        expect(logger).to_not receive(:error).with("Another consumer with same group.instance.id has connected", anything)
+
+        input_worker = java.lang.Thread.new { kafka_input.run(queue) }
+        begin
+          input_worker.start
+          wait_kafka_input_is_ready("logstash_integration_static_membership_topic", queue)
+        ensure
+          kafka_input.stop
+          input_worker.join(1_000)
+        end
+      end
+    end
+  end
+end
+
+# return consumer Ruby Thread
+def create_consumer_and_start_consuming(static_group_id)
+  props = java.util.Properties.new
+  kafka = org.apache.kafka.clients.consumer.ConsumerConfig
+  props.put(kafka::BOOTSTRAP_SERVERS_CONFIG, "localhost:9092")
+  props.put(kafka::KEY_DESERIALIZER_CLASS_CONFIG, LogStash::Inputs::Kafka::DEFAULT_DESERIALIZER_CLASS)
+  props.put(kafka::VALUE_DESERIALIZER_CLASS_CONFIG, LogStash::Inputs::Kafka::DEFAULT_DESERIALIZER_CLASS)
+  props.put(kafka::GROUP_ID_CONFIG, "logstash")
+  props.put(kafka::GROUP_INSTANCE_ID_CONFIG, static_group_id)
+  consumer = org.apache.kafka.clients.consumer.KafkaConsumer.new(props)
+
+  Thread.new do
+    LogStash::Util::set_thread_name("integration_test_simple_consumer")
+    begin
+      consumer.subscribe(["logstash_integration_static_membership_topic"])
+      records = consumer.poll(java.time.Duration.ofSeconds(3))
+      "saboteur exited"
+    rescue => e
+      e # return the exception reached in thread.value
+    ensure
+      consumer.close
+    end
+  end
 end
 
 private
 
+def wait_kafka_input_is_ready(topic, queue)
+  # this is needed to give time to the kafka input to be up and running
+  header = org.apache.kafka.common.header.internals.RecordHeader.new("name", "Ping Up".to_java_bytes)
+  record = org.apache.kafka.clients.producer.ProducerRecord.new(topic, 0, "key", "value", [header])
+  send_message(record)
+
+  # Wait the message is processed
+  message = queue.poll(1, java.util.concurrent.TimeUnit::MINUTES)
+  expect(message).to_not eq(nil)
+end
+
 def consume_messages(config, queue: Queue.new, timeout:, event_count:)
   kafka_input = LogStash::Inputs::Kafka.new(config)
   kafka_input.register
@@ -257,10 +353,13 @@ describe "schema registry connection options" do
   end
 end
 
-def save_avro_schema_to_schema_registry(schema_file, subject_name)
+def save_avro_schema_to_schema_registry(schema_file, subject_name, proto = 'http', port = 8081, manticore_options = {})
   raw_schema = File.readlines(schema_file).map(&:chomp).join
   raw_schema_quoted = raw_schema.gsub('"', '\"')
-  response = Manticore.post("http://localhost:8081/subjects/#{subject_name}/versions",
+
+  client = Manticore::Client.new(manticore_options)
+
+  response = client.post("#{proto}://localhost:#{port}/subjects/#{subject_name}/versions",
           body: '{"schema": "' + raw_schema_quoted + '"}',
           headers: {"Content-Type" => "application/vnd.schemaregistry.v1+json"})
   response
@@ -282,8 +381,17 @@ def startup_schema_registry(schema_registry, auth=false)
   end
 end
 
-describe "Schema registry API", :integration => true do
-  schema_registry = Manticore::Client.new
+shared_examples 'it has endpoints available to' do |tls|
+  let(:port) { tls ? 8083 : 8081 }
+  let(:proto) { tls ? 'https' : 'http' }
+
+  manticore_options = {
+    :ssl => {
+      :truststore => File.join(Dir.pwd, "tls_repository/clienttruststore.jks"),
+      :truststore_password => "changeit"
+    }
+  }
+  schema_registry = Manticore::Client.new(manticore_options)
 
   before(:all) do
     startup_schema_registry(schema_registry)
@@ -295,36 +403,53 @@ describe "Schema registry API", :integration => true do
 
   context 'listing subject on clean instance' do
     it "should return an empty set" do
-      subjects = JSON.parse schema_registry.get('http://localhost:8081/subjects').body
+      subjects = JSON.parse schema_registry.get("#{proto}://localhost:#{port}/subjects").body
       expect( subjects ).to be_empty
     end
   end
 
   context 'send a schema definition' do
     it "save the definition" do
-      response = save_avro_schema_to_schema_registry(File.join(Dir.pwd, "spec", "unit", "inputs", "avro_schema_fixture_payment.asvc"), "schema_test_1")
+      response = save_avro_schema_to_schema_registry(File.join(Dir.pwd, "spec", "unit", "inputs", "avro_schema_fixture_payment.asvc"), "schema_test_1", proto, port, manticore_options)
       expect( response.code ).to be(200)
       delete_remote_schema(schema_registry, "schema_test_1")
     end
 
     it "delete the schema just added" do
-      response = save_avro_schema_to_schema_registry(File.join(Dir.pwd, "spec", "unit", "inputs", "avro_schema_fixture_payment.asvc"), "schema_test_1")
+      response = save_avro_schema_to_schema_registry(File.join(Dir.pwd, "spec", "unit", "inputs", "avro_schema_fixture_payment.asvc"), "schema_test_1", proto, port, manticore_options)
       expect( response.code ).to be(200)
 
-      expect( schema_registry.delete('http://localhost:8081/subjects/schema_test_1?permanent=false').code ).to be(200)
+      expect( schema_registry.delete("#{proto}://localhost:#{port}/subjects/schema_test_1?permanent=false").code ).to be(200)
       sleep(1)
-      subjects = JSON.parse schema_registry.get('http://localhost:8081/subjects').body
+      subjects = JSON.parse schema_registry.get("#{proto}://localhost:#{port}/subjects").body
       expect( subjects ).to be_empty
     end
   end
 end
 
+describe "Schema registry API", :integration => true do
+
+  context "when exposed with HTTPS" do
+    it_behaves_like 'it has endpoints available to', true
+  end
+
+  context "when exposed with plain HTTP" do
+    it_behaves_like 'it has endpoints available to', false
+  end
+end
+
 def shutdown_schema_registry
   system('./stop_schema_registry.sh')
 end
 
 describe "Deserializing with the schema registry", :integration => true do
-  schema_registry = Manticore::Client.new
+  manticore_options = {
+    :ssl => {
+      :truststore => File.join(Dir.pwd, "tls_repository/clienttruststore.jks"),
+      :truststore_password => "changeit"
+    }
+  }
+  schema_registry = Manticore::Client.new(manticore_options)
 
   shared_examples 'it reads from a topic using a schema registry' do |with_auth|
 
@@ -423,28 +548,57 @@ describe "Deserializing with the schema registry", :integration => true do
     end
   end
 
-  context 'with an unauthed schema registry' do
+  shared_examples 'with an unauthed schema registry' do |tls|
+    let(:port) { tls ? 8083 : 8081 }
+    let(:proto) { tls ? 'https' : 'http' }
+
     let(:auth) { false }
     let(:avro_topic_name) { "topic_avro" }
-    let(:subject_url) { "http://localhost:8081/subjects" }
-    let(:plain_config)  { base_config.merge!({'schema_registry_url' => "http://localhost:8081"}) }
+    let(:subject_url) { "#{proto}://localhost:#{port}/subjects" }
+    let(:plain_config)  { base_config.merge!({
+      'schema_registry_url' => "#{proto}://localhost:#{port}",
+      'schema_registry_ssl_truststore_location' => File.join(Dir.pwd, "tls_repository/clienttruststore.jks"),
+      'schema_registry_ssl_truststore_password' => 'changeit',
+    }) }
 
     it_behaves_like 'it reads from a topic using a schema registry', false
   end
 
-  context 'with an authed schema registry' do
+  context 'with an unauthed schema registry' do
+    context "accessed through HTTPS" do
+      it_behaves_like 'with an unauthed schema registry', true
+    end
+
+    context "accessed through HTTPS" do
+      it_behaves_like 'with an unauthed schema registry', false
+    end
+  end
+
+  shared_examples 'with an authed schema registry' do |tls|
+    let(:port) { tls ? 8083 : 8081 }
+    let(:proto) { tls ? 'https' : 'http' }
     let(:auth) { true }
     let(:user) { "barney" }
     let(:password) { "changeme" }
     let(:avro_topic_name) { "topic_avro_auth" }
-    let(:subject_url) { "http://#{user}:#{password}@localhost:8081/subjects" }
+    let(:subject_url) { "#{proto}://#{user}:#{password}@localhost:#{port}/subjects" }
+    let(:tls_base_config) do
+      if tls
+        base_config.merge({
+          'schema_registry_ssl_truststore_location' => ::File.join(Dir.pwd, "tls_repository/clienttruststore.jks"),
+          'schema_registry_ssl_truststore_password' => 'changeit',
+        })
+      else
+        base_config
+      end
+    end
 
     context 'using schema_registry_key' do
       let(:plain_config) do
-        base_config.merge!({
-          'schema_registry_url' => "http://localhost:8081",
+        tls_base_config.merge!({
+          'schema_registry_url' => "#{proto}://localhost:#{port}",
           'schema_registry_key' => user,
-          'schema_registry_secret' => password
+          'schema_registry_secret' => password,
         })
       end
 
@@ -453,12 +607,22 @@ describe "Deserializing with the schema registry", :integration => true do
 
     context 'using schema_registry_url' do
       let(:plain_config) do
-        base_config.merge!({
-          'schema_registry_url' => "http://#{user}:#{password}@localhost:8081"
+        tls_base_config.merge!({
+          'schema_registry_url' => "#{proto}://#{user}:#{password}@localhost:#{port}",
         })
       end
 
       it_behaves_like 'it reads from a topic using a schema registry', true
     end
   end
+
+  context 'with an authed schema registry' do
+    context "accessed through HTTPS" do
+      it_behaves_like 'with an authed schema registry', true
+    end
+
+    context "accessed through HTTPS" do
+      it_behaves_like 'with an authed schema registry', false
+    end
+  end
 end

data/spec/integration/outputs/kafka_spec.rb

@@ -28,7 +28,8 @@ describe "outputs/kafka", :integration => true do
     let(:num_events) { 3 }
 
     before :each do
-      config = base_config.merge({"topic_id" => test_topic})
+      # NOTE: the connections_max_idle_ms is irrelevant just testing that configuration works ...
+      config = base_config.merge({"topic_id" => test_topic, "connections_max_idle_ms" => 540_000})
       load_kafka_data(config)
     end
 
@@ -139,6 +140,25 @@ describe "outputs/kafka", :integration => true do
     # end
   end
 
+  context 'when using zstd compression' do
+    let(:test_topic) { 'logstash_integration_zstd_topic' }
+
+    before :each do
+      config = base_config.merge({"topic_id" => test_topic, "compression_type" => "zstd"})
+      load_kafka_data(config)
+    end
+
+    # NOTE: depends on zstd-ruby gem which is using a C-extension
+    # it 'should have data integrity' do
+    #   messages = fetch_messages(test_topic)
+    #
+    #   expect(messages.size).to eq(num_events)
+    #   messages.each do |m|
+    #     expect(m.value).to eq(event.to_s)
+    #   end
+    # end
+  end
+
   context 'when using multi partition topic' do
     let(:num_events) { 100 } # ~ more than (batch.size) 16,384 bytes
     let(:test_topic) { 'logstash_integration_topic3' }

data/spec/unit/inputs/kafka_spec.rb

@@ -83,6 +83,16 @@ describe LogStash::Inputs::Kafka do
     it "should register" do
       expect { subject.register }.to_not raise_error
     end
+
+    context "when the deprecated `default` is specified" do
+      let(:config) { common_config.merge('client_dns_lookup' => 'default') }
+
+      it 'should fallback `client_dns_lookup` to `use_all_dns_ips`' do
+        subject.register
+
+        expect(subject.client_dns_lookup).to eq('use_all_dns_ips')
+      end
+    end
   end
 
   describe '#running' do
@@ -277,6 +287,19 @@ describe LogStash::Inputs::Kafka do
       subject.register
       expect(subject.metadata_mode).to include(:record_props)
     end
+
+    context "guards against nil header" do
+      let(:header) { double(:value => nil, :key => "k") }
+      let(:headers) { [ header ] }
+      let(:record) { double(:headers => headers, :topic => "topic", :partition => 0,
+                            :offset => 123456789, :key => "someId", :timestamp => nil ) }
+
+      it "does not raise error when key is nil" do
+        subject.register
+        evt = LogStash::Event.new('message' => 'Hello')
+        expect { subject.maybe_set_metadata(evt, record) }.not_to raise_error
+      end
+    end
   end
 
   context 'with client_rack' do
@@ -287,7 +310,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('client.rack' => 'EU-R1')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-0') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-0', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -299,7 +322,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('session.timeout.ms' => '25000', 'max.poll.interval.ms' => '345000')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-1') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-1', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -311,7 +334,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('session.timeout.ms' => '25200', 'max.poll.interval.ms' => '123000')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-2') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-2', 'group_instance_id') ).to be kafka_client
     end
   end
 
@@ -323,7 +346,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('enable.auto.commit' => 'false', 'check.crcs' => 'true')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-3') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-3', 'group_instance_id') ).to be kafka_client
       expect( subject.enable_auto_commit ).to be false
     end
   end
@@ -336,7 +359,7 @@ describe LogStash::Inputs::Kafka do
           to receive(:new).with(hash_including('enable.auto.commit' => 'true', 'check.crcs' => 'false')).
               and_return kafka_client = double('kafka-consumer')
 
-      expect( subject.send(:create_consumer, 'sample_client-4') ).to be kafka_client
+      expect( subject.send(:create_consumer, 'sample_client-4', 'group_instance_id') ).to be kafka_client
       expect( subject.enable_auto_commit ).to be true
     end
   end