You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nifi.apache.org by pv...@apache.org on 2018/09/19 13:50:29 UTC
[5/5] nifi git commit: NIFI-5518: Added processors for integrating
with Apache Kafka 2.0
NIFI-5518: Added processors for integrating with Apache Kafka 2.0
Signed-off-by: Pierre Villard <pi...@gmail.com>
This closes #2948.
Project: http://git-wip-us.apache.org/repos/asf/nifi/repo
Commit: http://git-wip-us.apache.org/repos/asf/nifi/commit/0da4f50e
Tree: http://git-wip-us.apache.org/repos/asf/nifi/tree/0da4f50e
Diff: http://git-wip-us.apache.org/repos/asf/nifi/diff/0da4f50e
Branch: refs/heads/master
Commit: 0da4f50ea03eaf887981de6d654ea9eb6532cd32
Parents: 1dea8fa
Author: Mark Payne <ma...@hotmail.com>
Authored: Tue Aug 14 13:35:58 2018 -0400
Committer: Pierre Villard <pi...@gmail.com>
Committed: Wed Sep 19 15:50:08 2018 +0200
----------------------------------------------------------------------
nifi-assembly/pom.xml | 36 +-
.../nifi-kafka-2-0-nar/pom.xml | 41 ++
.../nifi-kafka-2-0-processors/pom.xml | 101 +++
.../kafka/pubsub/ConsumeKafkaRecord_2_0.java | 413 +++++++++++
.../kafka/pubsub/ConsumeKafka_2_0.java | 399 +++++++++++
.../processors/kafka/pubsub/ConsumerLease.java | 711 +++++++++++++++++++
.../processors/kafka/pubsub/ConsumerPool.java | 372 ++++++++++
.../kafka/pubsub/InFlightMessageTracker.java | 179 +++++
.../kafka/pubsub/KafkaProcessorUtils.java | 389 ++++++++++
.../processors/kafka/pubsub/Partitioners.java | 62 ++
.../kafka/pubsub/PublishKafkaRecord_2_0.java | 450 ++++++++++++
.../kafka/pubsub/PublishKafka_2_0.java | 457 ++++++++++++
.../processors/kafka/pubsub/PublishResult.java | 46 ++
.../processors/kafka/pubsub/PublisherLease.java | 292 ++++++++
.../processors/kafka/pubsub/PublisherPool.java | 115 +++
.../org.apache.nifi.processor.Processor | 18 +
.../additionalDetails.html | 143 ++++
.../additionalDetails.html | 143 ++++
.../additionalDetails.html | 144 ++++
.../additionalDetails.html | 156 ++++
.../kafka/pubsub/ConsumerPoolTest.java | 235 ++++++
.../kafka/pubsub/ITConsumeKafka_2_0.java | 135 ++++
.../pubsub/TestConsumeKafkaRecord_2_0.java | 216 ++++++
.../kafka/pubsub/TestConsumeKafka_2_0.java | 128 ++++
.../pubsub/TestInFlightMessageTracker.java | 89 +++
.../pubsub/TestPublishKafkaRecord_2_0.java | 300 ++++++++
.../kafka/pubsub/TestPublishKafka_2_0.java | 250 +++++++
.../kafka/pubsub/TestPublisherLease.java | 289 ++++++++
.../kafka/pubsub/TestPublisherPool.java | 68 ++
.../kafka/pubsub/util/MockRecordParser.java | 105 +++
.../kafka/pubsub/util/MockRecordWriter.java | 128 ++++
.../src/test/resources/log4j.properties | 21 +
.../src/test/resources/server.properties | 121 ++++
.../src/test/resources/zookeeper.properties | 20 +
nifi-nar-bundles/nifi-kafka-bundle/pom.xml | 8 +
35 files changed, 6765 insertions(+), 15 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/nifi/blob/0da4f50e/nifi-assembly/pom.xml
----------------------------------------------------------------------
diff --git a/nifi-assembly/pom.xml b/nifi-assembly/pom.xml
index 1b21421..7a7373f 100755
--- a/nifi-assembly/pom.xml
+++ b/nifi-assembly/pom.xml
@@ -1,13 +1,13 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor
-license agreements. See the NOTICE file distributed with this work for additional
-information regarding copyright ownership. The ASF licenses this file to
-You under the Apache License, Version 2.0 (the "License"); you may not use
-this file except in compliance with the License. You may obtain a copy of
-the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required
-by applicable law or agreed to in writing, software distributed under the
-License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
-OF ANY KIND, either express or implied. See the License for the specific
+<!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor
+license agreements. See the NOTICE file distributed with this work for additional
+information regarding copyright ownership. The ASF licenses this file to
+You under the Apache License, Version 2.0 (the "License"); you may not use
+this file except in compliance with the License. You may obtain a copy of
+the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required
+by applicable law or agreed to in writing, software distributed under the
+License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
+OF ANY KIND, either express or implied. See the License for the specific
language governing permissions and limitations under the License. -->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
@@ -225,6 +225,12 @@ language governing permissions and limitations under the License. -->
</dependency>
<dependency>
<groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-kafka-2-0-nar</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ <type>nar</type>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
<artifactId>nifi-confluent-platform-nar</artifactId>
<version>1.8.0-SNAPSHOT</version>
<type>nar</type>
@@ -903,11 +909,11 @@ language governing permissions and limitations under the License. -->
<mapping>
<directory>/opt/nifi/nifi-${project.version}/lib</directory>
</mapping>
- <!-- The lib excludes and lib/bootstrap
- includes are computed by looking at the desired contents of lib vs the desired
- contents of bootstrap directories. The bootstrap directory should be comprised
- of explicitly included items as found from the lib/bootstrap of a non rpm
- build and the lib folder should be specific excludes being those which we
+ <!-- The lib excludes and lib/bootstrap
+ includes are computed by looking at the desired contents of lib vs the desired
+ contents of bootstrap directories. The bootstrap directory should be comprised
+ of explicitly included items as found from the lib/bootstrap of a non rpm
+ build and the lib folder should be specific excludes being those which we
want in bootstrap and NOT in lib. -->
<mapping>
<directory>/opt/nifi/nifi-${project.version}/lib</directory>
@@ -941,7 +947,7 @@ language governing permissions and limitations under the License. -->
<!-- must be in lib <exclude>ch.qos.logback:logback-core</exclude> -->
<exclude>org.apache.nifi:nifi-security-utils</exclude>
<exclude>org.apache.nifi:nifi-utils</exclude>
- <!-- Items to not include
+ <!-- Items to not include
which are also not in bootstrap -->
<exclude>org.apache.nifi:nifi-resources</exclude>
<exclude>org.apache.nifi:nifi-docs</exclude>
http://git-wip-us.apache.org/repos/asf/nifi/blob/0da4f50e/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-nar/pom.xml
----------------------------------------------------------------------
diff --git a/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-nar/pom.xml b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-nar/pom.xml
new file mode 100644
index 0000000..621ff55
--- /dev/null
+++ b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-nar/pom.xml
@@ -0,0 +1,41 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+ <!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+ http://www.apache.org/licenses/LICENSE-2.0
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+ -->
+ <modelVersion>4.0.0</modelVersion>
+ <parent>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-kafka-bundle</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ </parent>
+ <artifactId>nifi-kafka-2-0-nar</artifactId>
+ <packaging>nar</packaging>
+ <description>NiFi NAR for interacting with Apache Kafka 2.0</description>
+ <properties>
+ <maven.javadoc.skip>true</maven.javadoc.skip>
+ <source.skip>true</source.skip>
+ </properties>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-kafka-2-0-processors</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-standard-services-api-nar</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ <type>nar</type>
+ </dependency>
+ </dependencies>
+</project>
http://git-wip-us.apache.org/repos/asf/nifi/blob/0da4f50e/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/pom.xml
----------------------------------------------------------------------
diff --git a/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/pom.xml b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/pom.xml
new file mode 100644
index 0000000..19a7575
--- /dev/null
+++ b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/pom.xml
@@ -0,0 +1,101 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+ <!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+ http://www.apache.org/licenses/LICENSE-2.0
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+ -->
+ <parent>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-kafka-bundle</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ </parent>
+ <modelVersion>4.0.0</modelVersion>
+ <artifactId>nifi-kafka-2-0-processors</artifactId>
+ <packaging>jar</packaging>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-api</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-record-serialization-service-api</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-record</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-processor-utils</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-utils</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-ssl-context-service-api</artifactId>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-kerberos-credentials-service-api</artifactId>
+ </dependency>
+
+ <dependency>
+ <groupId>org.apache.kafka</groupId>
+ <artifactId>kafka-clients</artifactId>
+ <version>${kafka2.0.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.kafka</groupId>
+ <artifactId>kafka_2.11</artifactId>
+ <version>${kafka2.0.version}</version>
+ <scope>test</scope>
+ <exclusions>
+ <!-- Transitive dependencies excluded because they are located
+ in a legacy Maven repository, which Maven 3 doesn't support. -->
+ <exclusion>
+ <groupId>javax.jms</groupId>
+ <artifactId>jms</artifactId>
+ </exclusion>
+ <exclusion>
+ <groupId>com.sun.jdmk</groupId>
+ <artifactId>jmxtools</artifactId>
+ </exclusion>
+ <exclusion>
+ <groupId>com.sun.jmx</groupId>
+ <artifactId>jmxri</artifactId>
+ </exclusion>
+ </exclusions>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.nifi</groupId>
+ <artifactId>nifi-mock</artifactId>
+ <version>1.8.0-SNAPSHOT</version>
+ <scope>test</scope>
+ </dependency>
+ <dependency>
+ <groupId>commons-io</groupId>
+ <artifactId>commons-io</artifactId>
+ <version>2.6</version>
+ <scope>test</scope>
+ </dependency>
+ <dependency>
+ <groupId>org.slf4j</groupId>
+ <artifactId>slf4j-simple</artifactId>
+ <scope>test</scope>
+ </dependency>
+ </dependencies>
+</project>
http://git-wip-us.apache.org/repos/asf/nifi/blob/0da4f50e/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafkaRecord_2_0.java
----------------------------------------------------------------------
diff --git a/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafkaRecord_2_0.java b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafkaRecord_2_0.java
new file mode 100644
index 0000000..2cafd97
--- /dev/null
+++ b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafkaRecord_2_0.java
@@ -0,0 +1,413 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nifi.processors.kafka.pubsub;
+
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.errors.WakeupException;
+import org.apache.kafka.common.serialization.ByteArrayDeserializer;
+import org.apache.nifi.annotation.behavior.DynamicProperty;
+import org.apache.nifi.annotation.behavior.InputRequirement;
+import org.apache.nifi.annotation.behavior.WritesAttribute;
+import org.apache.nifi.annotation.behavior.WritesAttributes;
+import org.apache.nifi.annotation.documentation.CapabilityDescription;
+import org.apache.nifi.annotation.documentation.SeeAlso;
+import org.apache.nifi.annotation.documentation.Tags;
+import org.apache.nifi.annotation.lifecycle.OnStopped;
+import org.apache.nifi.annotation.lifecycle.OnUnscheduled;
+import org.apache.nifi.components.AllowableValue;
+import org.apache.nifi.components.PropertyDescriptor;
+import org.apache.nifi.components.PropertyDescriptor.Builder;
+import org.apache.nifi.components.ValidationContext;
+import org.apache.nifi.components.ValidationResult;
+import org.apache.nifi.expression.ExpressionLanguageScope;
+import org.apache.nifi.logging.ComponentLog;
+import org.apache.nifi.processor.AbstractProcessor;
+import org.apache.nifi.processor.ProcessContext;
+import org.apache.nifi.processor.ProcessSession;
+import org.apache.nifi.processor.Relationship;
+import org.apache.nifi.processor.exception.ProcessException;
+import org.apache.nifi.processor.util.StandardValidators;
+import org.apache.nifi.serialization.RecordReaderFactory;
+import org.apache.nifi.serialization.RecordSetWriterFactory;
+
+import java.nio.charset.Charset;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.concurrent.TimeUnit;
+import java.util.regex.Pattern;
+
+@CapabilityDescription("Consumes messages from Apache Kafka specifically built against the Kafka 2.0 Consumer API. "
+ + "The complementary NiFi processor for sending messages is PublishKafkaRecord_2_0. Please note that, at this time, the Processor assumes that "
+ + "all records that are retrieved from a given partition have the same schema. If any of the Kafka messages are pulled but cannot be parsed or written with the "
+ + "configured Record Reader or Record Writer, the contents of the message will be written to a separate FlowFile, and that FlowFile will be transferred to the "
+ + "'parse.failure' relationship. Otherwise, each FlowFile is sent to the 'success' relationship and may contain many individual messages within the single FlowFile. "
+ + "A 'record.count' attribute is added to indicate how many messages are contained in the FlowFile. No two Kafka messages will be placed into the same FlowFile if they "
+ + "have different schemas, or if they have different values for a message header that is included by the <Headers to Add as Attributes> property.")
+@Tags({"Kafka", "Get", "Record", "csv", "avro", "json", "Ingest", "Ingress", "Topic", "PubSub", "Consume", "2.0"})
+@WritesAttributes({
+ @WritesAttribute(attribute = "record.count", description = "The number of records received"),
+ @WritesAttribute(attribute = "mime.type", description = "The MIME Type that is provided by the configured Record Writer"),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_PARTITION, description = "The partition of the topic the records are from"),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_TOPIC, description = "The topic records are from")
+})
+@InputRequirement(InputRequirement.Requirement.INPUT_FORBIDDEN)
+@DynamicProperty(name = "The name of a Kafka configuration property.", value = "The value of a given Kafka configuration property.",
+ description = "These properties will be added on the Kafka configuration after loading any provided configuration properties."
+ + " In the event a dynamic property represents a property that was already set, its value will be ignored and WARN message logged."
+ + " For the list of available Kafka properties please refer to: http://kafka.apache.org/documentation.html#configuration.",
+ expressionLanguageScope = ExpressionLanguageScope.VARIABLE_REGISTRY)
+@SeeAlso({ConsumeKafka_2_0.class, PublishKafka_2_0.class, PublishKafkaRecord_2_0.class})
+public class ConsumeKafkaRecord_2_0 extends AbstractProcessor {
+
+ static final AllowableValue OFFSET_EARLIEST = new AllowableValue("earliest", "earliest", "Automatically reset the offset to the earliest offset");
+ static final AllowableValue OFFSET_LATEST = new AllowableValue("latest", "latest", "Automatically reset the offset to the latest offset");
+ static final AllowableValue OFFSET_NONE = new AllowableValue("none", "none", "Throw exception to the consumer if no previous offset is found for the consumer's group");
+ static final AllowableValue TOPIC_NAME = new AllowableValue("names", "names", "Topic is a full topic name or comma separated list of names");
+ static final AllowableValue TOPIC_PATTERN = new AllowableValue("pattern", "pattern", "Topic is a regex using the Java Pattern syntax");
+
+ static final PropertyDescriptor TOPICS = new Builder()
+ .name("topic")
+ .displayName("Topic Name(s)")
+ .description("The name of the Kafka Topic(s) to pull from. More than one can be supplied if comma separated.")
+ .required(true)
+ .addValidator(StandardValidators.NON_BLANK_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .build();
+
+ static final PropertyDescriptor TOPIC_TYPE = new Builder()
+ .name("topic_type")
+ .displayName("Topic Name Format")
+ .description("Specifies whether the Topic(s) provided are a comma separated list of names or a single regular expression")
+ .required(true)
+ .allowableValues(TOPIC_NAME, TOPIC_PATTERN)
+ .defaultValue(TOPIC_NAME.getValue())
+ .build();
+
+ static final PropertyDescriptor RECORD_READER = new Builder()
+ .name("record-reader")
+ .displayName("Record Reader")
+ .description("The Record Reader to use for incoming FlowFiles")
+ .identifiesControllerService(RecordReaderFactory.class)
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .required(true)
+ .build();
+
+ static final PropertyDescriptor RECORD_WRITER = new Builder()
+ .name("record-writer")
+ .displayName("Record Writer")
+ .description("The Record Writer to use in order to serialize the data before sending to Kafka")
+ .identifiesControllerService(RecordSetWriterFactory.class)
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .required(true)
+ .build();
+
+ static final PropertyDescriptor GROUP_ID = new Builder()
+ .name("group.id")
+ .displayName("Group ID")
+ .description("A Group ID is used to identify consumers that are within the same consumer group. Corresponds to Kafka's 'group.id' property.")
+ .required(true)
+ .addValidator(StandardValidators.NON_BLANK_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .build();
+
+ static final PropertyDescriptor AUTO_OFFSET_RESET = new Builder()
+ .name("auto.offset.reset")
+ .displayName("Offset Reset")
+ .description("Allows you to manage the condition when there is no initial offset in Kafka or if the current offset does not exist any "
+ + "more on the server (e.g. because that data has been deleted). Corresponds to Kafka's 'auto.offset.reset' property.")
+ .required(true)
+ .allowableValues(OFFSET_EARLIEST, OFFSET_LATEST, OFFSET_NONE)
+ .defaultValue(OFFSET_LATEST.getValue())
+ .build();
+
+ static final PropertyDescriptor MAX_POLL_RECORDS = new Builder()
+ .name("max.poll.records")
+ .displayName("Max Poll Records")
+ .description("Specifies the maximum number of records Kafka should return in a single poll.")
+ .required(false)
+ .defaultValue("10000")
+ .addValidator(StandardValidators.POSITIVE_INTEGER_VALIDATOR)
+ .build();
+
+ static final PropertyDescriptor MAX_UNCOMMITTED_TIME = new Builder()
+ .name("max-uncommit-offset-wait")
+ .displayName("Max Uncommitted Time")
+ .description("Specifies the maximum amount of time allowed to pass before offsets must be committed. "
+ + "This value impacts how often offsets will be committed. Committing offsets less often increases "
+ + "throughput but also increases the window of potential data duplication in the event of a rebalance "
+ + "or JVM restart between commits. This value is also related to maximum poll records and the use "
+ + "of a message demarcator. When using a message demarcator we can have far more uncommitted messages "
+ + "than when we're not as there is much less for us to keep track of in memory.")
+ .required(false)
+ .defaultValue("1 secs")
+ .addValidator(StandardValidators.TIME_PERIOD_VALIDATOR)
+ .build();
+ static final PropertyDescriptor COMMS_TIMEOUT = new Builder()
+ .name("Communications Timeout")
+ .displayName("Communications Timeout")
+ .description("Specifies the timeout that the consumer should use when communicating with the Kafka Broker")
+ .required(true)
+ .defaultValue("60 secs")
+ .addValidator(StandardValidators.TIME_PERIOD_VALIDATOR)
+ .build();
+ static final PropertyDescriptor HONOR_TRANSACTIONS = new Builder()
+ .name("honor-transactions")
+ .displayName("Honor Transactions")
+ .description("Specifies whether or not NiFi should honor transactional guarantees when communicating with Kafka. If false, the Processor will use an \"isolation level\" of "
+ + "read_uncomitted. This means that messages will be received as soon as they are written to Kafka but will be pulled, even if the producer cancels the transactions. If "
+ + "this value is true, NiFi will not receive any messages for which the producer's transaction was canceled, but this can result in some latency since the consumer must wait "
+ + "for the producer to finish its entire transaction instead of pulling as the messages become available.")
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .allowableValues("true", "false")
+ .defaultValue("true")
+ .required(true)
+ .build();
+ static final PropertyDescriptor MESSAGE_HEADER_ENCODING = new Builder()
+ .name("message-header-encoding")
+ .displayName("Message Header Encoding")
+ .description("Any message header that is found on a Kafka message will be added to the outbound FlowFile as an attribute. "
+ + "This property indicates the Character Encoding to use for deserializing the headers.")
+ .addValidator(StandardValidators.CHARACTER_SET_VALIDATOR)
+ .defaultValue("UTF-8")
+ .required(false)
+ .build();
+ static final PropertyDescriptor HEADER_NAME_REGEX = new Builder()
+ .name("header-name-regex")
+ .displayName("Headers to Add as Attributes (Regex)")
+ .description("A Regular Expression that is matched against all message headers. "
+ + "Any message header whose name matches the regex will be added to the FlowFile as an Attribute. "
+ + "If not specified, no Header values will be added as FlowFile attributes. If two messages have a different value for the same header and that header is selected by "
+ + "the provided regex, then those two messages must be added to different FlowFiles. As a result, users should be cautious about using a regex like "
+ + "\".*\" if messages are expected to have header values that are unique per message, such as an identifier or timestamp, because it will prevent NiFi from bundling "
+ + "the messages together efficiently.")
+ .addValidator(StandardValidators.REGULAR_EXPRESSION_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .required(false)
+ .build();
+
+ static final Relationship REL_SUCCESS = new Relationship.Builder()
+ .name("success")
+ .description("FlowFiles received from Kafka. Depending on demarcation strategy it is a flow file per message or a bundle of messages grouped by topic and partition.")
+ .build();
+ static final Relationship REL_PARSE_FAILURE = new Relationship.Builder()
+ .name("parse.failure")
+ .description("If a message from Kafka cannot be parsed using the configured Record Reader, the contents of the "
+ + "message will be routed to this Relationship as its own individual FlowFile.")
+ .build();
+
+ static final List<PropertyDescriptor> DESCRIPTORS;
+ static final Set<Relationship> RELATIONSHIPS;
+
+ private volatile ConsumerPool consumerPool = null;
+ private final Set<ConsumerLease> activeLeases = Collections.synchronizedSet(new HashSet<>());
+
+ static {
+ List<PropertyDescriptor> descriptors = new ArrayList<>();
+ descriptors.add(KafkaProcessorUtils.BOOTSTRAP_SERVERS);
+ descriptors.add(TOPICS);
+ descriptors.add(TOPIC_TYPE);
+ descriptors.add(RECORD_READER);
+ descriptors.add(RECORD_WRITER);
+ descriptors.add(HONOR_TRANSACTIONS);
+ descriptors.add(KafkaProcessorUtils.SECURITY_PROTOCOL);
+ descriptors.add(KafkaProcessorUtils.KERBEROS_CREDENTIALS_SERVICE);
+ descriptors.add(KafkaProcessorUtils.JAAS_SERVICE_NAME);
+ descriptors.add(KafkaProcessorUtils.USER_PRINCIPAL);
+ descriptors.add(KafkaProcessorUtils.USER_KEYTAB);
+ descriptors.add(KafkaProcessorUtils.SSL_CONTEXT_SERVICE);
+ descriptors.add(GROUP_ID);
+ descriptors.add(AUTO_OFFSET_RESET);
+ descriptors.add(MESSAGE_HEADER_ENCODING);
+ descriptors.add(HEADER_NAME_REGEX);
+ descriptors.add(MAX_POLL_RECORDS);
+ descriptors.add(MAX_UNCOMMITTED_TIME);
+ descriptors.add(COMMS_TIMEOUT);
+ DESCRIPTORS = Collections.unmodifiableList(descriptors);
+
+ final Set<Relationship> rels = new HashSet<>();
+ rels.add(REL_SUCCESS);
+ rels.add(REL_PARSE_FAILURE);
+ RELATIONSHIPS = Collections.unmodifiableSet(rels);
+ }
+
+ @Override
+ public Set<Relationship> getRelationships() {
+ return RELATIONSHIPS;
+ }
+
+ @Override
+ protected List<PropertyDescriptor> getSupportedPropertyDescriptors() {
+ return DESCRIPTORS;
+ }
+
+ @OnStopped
+ public void close() {
+ final ConsumerPool pool = consumerPool;
+ consumerPool = null;
+
+ if (pool != null) {
+ pool.close();
+ }
+ }
+
+ @Override
+ protected PropertyDescriptor getSupportedDynamicPropertyDescriptor(final String propertyDescriptorName) {
+ return new Builder()
+ .description("Specifies the value for '" + propertyDescriptorName + "' Kafka Configuration.")
+ .name(propertyDescriptorName)
+ .addValidator(new KafkaProcessorUtils.KafkaConfigValidator(ConsumerConfig.class))
+ .dynamic(true)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .build();
+ }
+
+ @Override
+ protected Collection<ValidationResult> customValidate(final ValidationContext validationContext) {
+ return KafkaProcessorUtils.validateCommonProperties(validationContext);
+ }
+
+ private synchronized ConsumerPool getConsumerPool(final ProcessContext context) {
+ ConsumerPool pool = consumerPool;
+ if (pool != null) {
+ return pool;
+ }
+
+ return consumerPool = createConsumerPool(context, getLogger());
+ }
+
+ protected ConsumerPool createConsumerPool(final ProcessContext context, final ComponentLog log) {
+ final int maxLeases = context.getMaxConcurrentTasks();
+ final long maxUncommittedTime = context.getProperty(MAX_UNCOMMITTED_TIME).asTimePeriod(TimeUnit.MILLISECONDS);
+
+ final Map<String, Object> props = new HashMap<>();
+ KafkaProcessorUtils.buildCommonKafkaProperties(context, ConsumerConfig.class, props);
+ props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "false");
+ props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class.getName());
+ props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class.getName());
+ final String topicListing = context.getProperty(ConsumeKafkaRecord_2_0.TOPICS).evaluateAttributeExpressions().getValue();
+ final String topicType = context.getProperty(ConsumeKafkaRecord_2_0.TOPIC_TYPE).evaluateAttributeExpressions().getValue();
+ final List<String> topics = new ArrayList<>();
+ final String securityProtocol = context.getProperty(KafkaProcessorUtils.SECURITY_PROTOCOL).getValue();
+ final String bootstrapServers = context.getProperty(KafkaProcessorUtils.BOOTSTRAP_SERVERS).evaluateAttributeExpressions().getValue();
+
+ final RecordReaderFactory readerFactory = context.getProperty(RECORD_READER).asControllerService(RecordReaderFactory.class);
+ final RecordSetWriterFactory writerFactory = context.getProperty(RECORD_WRITER).asControllerService(RecordSetWriterFactory.class);
+ final boolean honorTransactions = context.getProperty(HONOR_TRANSACTIONS).asBoolean();
+ final int commsTimeoutMillis = context.getProperty(COMMS_TIMEOUT).asTimePeriod(TimeUnit.MILLISECONDS).intValue();
+ props.put(ConsumerConfig.DEFAULT_API_TIMEOUT_MS_CONFIG, commsTimeoutMillis);
+
+ final String charsetName = context.getProperty(MESSAGE_HEADER_ENCODING).evaluateAttributeExpressions().getValue();
+ final Charset charset = Charset.forName(charsetName);
+
+ final String headerNameRegex = context.getProperty(HEADER_NAME_REGEX).getValue();
+ final Pattern headerNamePattern = headerNameRegex == null ? null : Pattern.compile(headerNameRegex);
+
+ if (topicType.equals(TOPIC_NAME.getValue())) {
+ for (final String topic : topicListing.split(",", 100)) {
+ final String trimmedName = topic.trim();
+ if (!trimmedName.isEmpty()) {
+ topics.add(trimmedName);
+ }
+ }
+
+ return new ConsumerPool(maxLeases, readerFactory, writerFactory, props, topics, maxUncommittedTime, securityProtocol,
+ bootstrapServers, log, honorTransactions, charset, headerNamePattern);
+ } else if (topicType.equals(TOPIC_PATTERN.getValue())) {
+ final Pattern topicPattern = Pattern.compile(topicListing.trim());
+ return new ConsumerPool(maxLeases, readerFactory, writerFactory, props, topicPattern, maxUncommittedTime, securityProtocol,
+ bootstrapServers, log, honorTransactions, charset, headerNamePattern);
+ } else {
+ getLogger().error("Subscription type has an unknown value {}", new Object[] {topicType});
+ return null;
+ }
+ }
+
+ @OnUnscheduled
+ public void interruptActiveThreads() {
+ // There are known issues with the Kafka client library that result in the client code hanging
+ // indefinitely when unable to communicate with the broker. In order to address this, we will wait
+ // up to 30 seconds for the Threads to finish and then will call Consumer.wakeup() to trigger the
+ // thread to wakeup when it is blocked, waiting on a response.
+ final long nanosToWait = TimeUnit.SECONDS.toNanos(5L);
+ final long start = System.nanoTime();
+ while (System.nanoTime() - start < nanosToWait && !activeLeases.isEmpty()) {
+ try {
+ Thread.sleep(100L);
+ } catch (final InterruptedException ie) {
+ Thread.currentThread().interrupt();
+ return;
+ }
+ }
+
+ if (!activeLeases.isEmpty()) {
+ int count = 0;
+ for (final ConsumerLease lease : activeLeases) {
+ getLogger().info("Consumer {} has not finished after waiting 30 seconds; will attempt to wake-up the lease", new Object[] {lease});
+ lease.wakeup();
+ count++;
+ }
+
+ getLogger().info("Woke up {} consumers", new Object[] {count});
+ }
+
+ activeLeases.clear();
+ }
+
+ @Override
+ public void onTrigger(ProcessContext context, ProcessSession session) throws ProcessException {
+ final ConsumerPool pool = getConsumerPool(context);
+ if (pool == null) {
+ context.yield();
+ return;
+ }
+
+ try (final ConsumerLease lease = pool.obtainConsumer(session, context)) {
+ if (lease == null) {
+ context.yield();
+ return;
+ }
+
+ activeLeases.add(lease);
+ try {
+ while (this.isScheduled() && lease.continuePolling()) {
+ lease.poll();
+ }
+ if (this.isScheduled() && !lease.commit()) {
+ context.yield();
+ }
+ } catch (final WakeupException we) {
+ getLogger().warn("Was interrupted while trying to communicate with Kafka with lease {}. "
+ + "Will roll back session and discard any partially received data.", new Object[] {lease});
+ } catch (final KafkaException kex) {
+ getLogger().error("Exception while interacting with Kafka so will close the lease {} due to {}",
+ new Object[]{lease, kex}, kex);
+ } catch (final Throwable t) {
+ getLogger().error("Exception while processing data from kafka so will close the lease {} due to {}",
+ new Object[]{lease, t}, t);
+ } finally {
+ activeLeases.remove(lease);
+ }
+ }
+ }
+}
http://git-wip-us.apache.org/repos/asf/nifi/blob/0da4f50e/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafka_2_0.java
----------------------------------------------------------------------
diff --git a/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafka_2_0.java b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafka_2_0.java
new file mode 100644
index 0000000..bafce53
--- /dev/null
+++ b/nifi-nar-bundles/nifi-kafka-bundle/nifi-kafka-2-0-processors/src/main/java/org/apache/nifi/processors/kafka/pubsub/ConsumeKafka_2_0.java
@@ -0,0 +1,399 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nifi.processors.kafka.pubsub;
+
+import org.apache.kafka.clients.consumer.ConsumerConfig;
+import org.apache.kafka.common.KafkaException;
+import org.apache.kafka.common.errors.WakeupException;
+import org.apache.kafka.common.serialization.ByteArrayDeserializer;
+import org.apache.nifi.annotation.behavior.DynamicProperty;
+import org.apache.nifi.annotation.behavior.InputRequirement;
+import org.apache.nifi.annotation.behavior.WritesAttribute;
+import org.apache.nifi.annotation.behavior.WritesAttributes;
+import org.apache.nifi.annotation.documentation.CapabilityDescription;
+import org.apache.nifi.annotation.documentation.Tags;
+import org.apache.nifi.annotation.lifecycle.OnStopped;
+import org.apache.nifi.annotation.lifecycle.OnUnscheduled;
+import org.apache.nifi.components.AllowableValue;
+import org.apache.nifi.components.PropertyDescriptor;
+import org.apache.nifi.components.ValidationContext;
+import org.apache.nifi.components.ValidationResult;
+import org.apache.nifi.expression.ExpressionLanguageScope;
+import org.apache.nifi.logging.ComponentLog;
+import org.apache.nifi.processor.AbstractProcessor;
+import org.apache.nifi.processor.ProcessContext;
+import org.apache.nifi.processor.ProcessSession;
+import org.apache.nifi.processor.Relationship;
+import org.apache.nifi.processor.exception.ProcessException;
+import org.apache.nifi.processor.util.StandardValidators;
+
+import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.concurrent.TimeUnit;
+import java.util.regex.Pattern;
+
+import static org.apache.nifi.processors.kafka.pubsub.KafkaProcessorUtils.HEX_ENCODING;
+import static org.apache.nifi.processors.kafka.pubsub.KafkaProcessorUtils.UTF8_ENCODING;
+
+@CapabilityDescription("Consumes messages from Apache Kafka specifically built against the Kafka 2.0 Consumer API. "
+ + "The complementary NiFi processor for sending messages is PublishKafka_2_0.")
+@Tags({"Kafka", "Get", "Ingest", "Ingress", "Topic", "PubSub", "Consume", "2.0"})
+@WritesAttributes({
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_COUNT, description = "The number of messages written if more than one"),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_KEY, description = "The key of message if present and if single message. "
+ + "How the key is encoded depends on the value of the 'Key Attribute Encoding' property."),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_OFFSET, description = "The offset of the message in the partition of the topic."),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_PARTITION, description = "The partition of the topic the message or message bundle is from"),
+ @WritesAttribute(attribute = KafkaProcessorUtils.KAFKA_TOPIC, description = "The topic the message or message bundle is from")
+})
+@InputRequirement(InputRequirement.Requirement.INPUT_FORBIDDEN)
+@DynamicProperty(name = "The name of a Kafka configuration property.", value = "The value of a given Kafka configuration property.",
+ description = "These properties will be added on the Kafka configuration after loading any provided configuration properties."
+ + " In the event a dynamic property represents a property that was already set, its value will be ignored and WARN message logged."
+ + " For the list of available Kafka properties please refer to: http://kafka.apache.org/documentation.html#configuration. ")
+public class ConsumeKafka_2_0 extends AbstractProcessor {
+
+ static final AllowableValue OFFSET_EARLIEST = new AllowableValue("earliest", "earliest", "Automatically reset the offset to the earliest offset");
+
+ static final AllowableValue OFFSET_LATEST = new AllowableValue("latest", "latest", "Automatically reset the offset to the latest offset");
+
+ static final AllowableValue OFFSET_NONE = new AllowableValue("none", "none", "Throw exception to the consumer if no previous offset is found for the consumer's group");
+
+ static final AllowableValue TOPIC_NAME = new AllowableValue("names", "names", "Topic is a full topic name or comma separated list of names");
+
+ static final AllowableValue TOPIC_PATTERN = new AllowableValue("pattern", "pattern", "Topic is a regex using the Java Pattern syntax");
+
+ static final PropertyDescriptor TOPICS = new PropertyDescriptor.Builder()
+ .name("topic")
+ .displayName("Topic Name(s)")
+ .description("The name of the Kafka Topic(s) to pull from. More than one can be supplied if comma separated.")
+ .required(true)
+ .addValidator(StandardValidators.NON_BLANK_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .build();
+
+ static final PropertyDescriptor TOPIC_TYPE = new PropertyDescriptor.Builder()
+ .name("topic_type")
+ .displayName("Topic Name Format")
+ .description("Specifies whether the Topic(s) provided are a comma separated list of names or a single regular expression")
+ .required(true)
+ .allowableValues(TOPIC_NAME, TOPIC_PATTERN)
+ .defaultValue(TOPIC_NAME.getValue())
+ .build();
+
+ static final PropertyDescriptor GROUP_ID = new PropertyDescriptor.Builder()
+ .name(ConsumerConfig.GROUP_ID_CONFIG)
+ .displayName("Group ID")
+ .description("A Group ID is used to identify consumers that are within the same consumer group. Corresponds to Kafka's 'group.id' property.")
+ .required(true)
+ .addValidator(StandardValidators.NON_BLANK_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .build();
+
+ static final PropertyDescriptor AUTO_OFFSET_RESET = new PropertyDescriptor.Builder()
+ .name(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG)
+ .displayName("Offset Reset")
+ .description("Allows you to manage the condition when there is no initial offset in Kafka or if the current offset does not exist any "
+ + "more on the server (e.g. because that data has been deleted). Corresponds to Kafka's 'auto.offset.reset' property.")
+ .required(true)
+ .allowableValues(OFFSET_EARLIEST, OFFSET_LATEST, OFFSET_NONE)
+ .defaultValue(OFFSET_LATEST.getValue())
+ .build();
+
+ static final PropertyDescriptor KEY_ATTRIBUTE_ENCODING = new PropertyDescriptor.Builder()
+ .name("key-attribute-encoding")
+ .displayName("Key Attribute Encoding")
+ .description("FlowFiles that are emitted have an attribute named '" + KafkaProcessorUtils.KAFKA_KEY + "'. This property dictates how the value of the attribute should be encoded.")
+ .required(true)
+ .defaultValue(UTF8_ENCODING.getValue())
+ .allowableValues(UTF8_ENCODING, HEX_ENCODING)
+ .build();
+
+ static final PropertyDescriptor MESSAGE_DEMARCATOR = new PropertyDescriptor.Builder()
+ .name("message-demarcator")
+ .displayName("Message Demarcator")
+ .required(false)
+ .addValidator(StandardValidators.NON_EMPTY_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.VARIABLE_REGISTRY)
+ .description("Since KafkaConsumer receives messages in batches, you have an option to output FlowFiles which contains "
+ + "all Kafka messages in a single batch for a given topic and partition and this property allows you to provide a string (interpreted as UTF-8) to use "
+ + "for demarcating apart multiple Kafka messages. This is an optional property and if not provided each Kafka message received "
+ + "will result in a single FlowFile which "
+ + "time it is triggered. To enter special character such as 'new line' use CTRL+Enter or Shift+Enter depending on the OS")
+ .build();
+ static final PropertyDescriptor HEADER_NAME_REGEX = new PropertyDescriptor.Builder()
+ .name("header-name-regex")
+ .displayName("Headers to Add as Attributes (Regex)")
+ .description("A Regular Expression that is matched against all message headers. "
+ + "Any message header whose name matches the regex will be added to the FlowFile as an Attribute. "
+ + "If not specified, no Header values will be added as FlowFile attributes. If two messages have a different value for the same header and that header is selected by "
+ + "the provided regex, then those two messages must be added to different FlowFiles. As a result, users should be cautious about using a regex like "
+ + "\".*\" if messages are expected to have header values that are unique per message, such as an identifier or timestamp, because it will prevent NiFi from bundling "
+ + "the messages together efficiently.")
+ .addValidator(StandardValidators.REGULAR_EXPRESSION_VALIDATOR)
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .required(false)
+ .build();
+
+ static final PropertyDescriptor MAX_POLL_RECORDS = new PropertyDescriptor.Builder()
+ .name("max.poll.records")
+ .displayName("Max Poll Records")
+ .description("Specifies the maximum number of records Kafka should return in a single poll.")
+ .required(false)
+ .defaultValue("10000")
+ .addValidator(StandardValidators.POSITIVE_INTEGER_VALIDATOR)
+ .build();
+
+ static final PropertyDescriptor MAX_UNCOMMITTED_TIME = new PropertyDescriptor.Builder()
+ .name("max-uncommit-offset-wait")
+ .displayName("Max Uncommitted Time")
+ .description("Specifies the maximum amount of time allowed to pass before offsets must be committed. "
+ + "This value impacts how often offsets will be committed. Committing offsets less often increases "
+ + "throughput but also increases the window of potential data duplication in the event of a rebalance "
+ + "or JVM restart between commits. This value is also related to maximum poll records and the use "
+ + "of a message demarcator. When using a message demarcator we can have far more uncommitted messages "
+ + "than when we're not as there is much less for us to keep track of in memory.")
+ .required(false)
+ .defaultValue("1 secs")
+ .addValidator(StandardValidators.TIME_PERIOD_VALIDATOR)
+ .build();
+ static final PropertyDescriptor COMMS_TIMEOUT = new PropertyDescriptor.Builder()
+ .name("Communications Timeout")
+ .displayName("Communications Timeout")
+ .description("Specifies the timeout that the consumer should use when communicating with the Kafka Broker")
+ .required(true)
+ .defaultValue("60 secs")
+ .addValidator(StandardValidators.TIME_PERIOD_VALIDATOR)
+ .build();
+ static final PropertyDescriptor HONOR_TRANSACTIONS = new PropertyDescriptor.Builder()
+ .name("honor-transactions")
+ .displayName("Honor Transactions")
+ .description("Specifies whether or not NiFi should honor transactional guarantees when communicating with Kafka. If false, the Processor will use an \"isolation level\" of "
+ + "read_uncomitted. This means that messages will be received as soon as they are written to Kafka but will be pulled, even if the producer cancels the transactions. If "
+ + "this value is true, NiFi will not receive any messages for which the producer's transaction was canceled, but this can result in some latency since the consumer must wait "
+ + "for the producer to finish its entire transaction instead of pulling as the messages become available.")
+ .expressionLanguageSupported(ExpressionLanguageScope.NONE)
+ .allowableValues("true", "false")
+ .defaultValue("true")
+ .required(true)
+ .build();
+ static final PropertyDescriptor MESSAGE_HEADER_ENCODING = new PropertyDescriptor.Builder()
+ .name("message-header-encoding")
+ .displayName("Message Header Encoding")
+ .description("Any message header that is found on a Kafka message will be added to the outbound FlowFile as an attribute. "
+ + "This property indicates the Character Encoding to use for deserializing the headers.")
+ .addValidator(StandardValidators.CHARACTER_SET_VALIDATOR)
+ .defaultValue("UTF-8")
+ .required(false)
+ .build();
+
+
+ static final Relationship REL_SUCCESS = new Relationship.Builder()
+ .name("success")
+ .description("FlowFiles received from Kafka. Depending on demarcation strategy it is a flow file per message or a bundle of messages grouped by topic and partition.")
+ .build();
+
+ static final List<PropertyDescriptor> DESCRIPTORS;
+ static final Set<Relationship> RELATIONSHIPS;
+
+ private volatile ConsumerPool consumerPool = null;
+ private final Set<ConsumerLease> activeLeases = Collections.synchronizedSet(new HashSet<>());
+
+ static {
+ List<PropertyDescriptor> descriptors = new ArrayList<>();
+ descriptors.addAll(KafkaProcessorUtils.getCommonPropertyDescriptors());
+ descriptors.add(TOPICS);
+ descriptors.add(TOPIC_TYPE);
+ descriptors.add(HONOR_TRANSACTIONS);
+ descriptors.add(GROUP_ID);
+ descriptors.add(AUTO_OFFSET_RESET);
+ descriptors.add(KEY_ATTRIBUTE_ENCODING);
+ descriptors.add(MESSAGE_DEMARCATOR);
+ descriptors.add(MESSAGE_HEADER_ENCODING);
+ descriptors.add(HEADER_NAME_REGEX);
+ descriptors.add(MAX_POLL_RECORDS);
+ descriptors.add(MAX_UNCOMMITTED_TIME);
+ descriptors.add(COMMS_TIMEOUT);
+ DESCRIPTORS = Collections.unmodifiableList(descriptors);
+ RELATIONSHIPS = Collections.singleton(REL_SUCCESS);
+ }
+
+ @Override
+ public Set<Relationship> getRelationships() {
+ return RELATIONSHIPS;
+ }
+
+ @Override
+ protected List<PropertyDescriptor> getSupportedPropertyDescriptors() {
+ return DESCRIPTORS;
+ }
+
+ @OnStopped
+ public void close() {
+ final ConsumerPool pool = consumerPool;
+ consumerPool = null;
+ if (pool != null) {
+ pool.close();
+ }
+ }
+
+ @Override
+ protected PropertyDescriptor getSupportedDynamicPropertyDescriptor(final String propertyDescriptorName) {
+ return new PropertyDescriptor.Builder()
+ .description("Specifies the value for '" + propertyDescriptorName + "' Kafka Configuration.")
+ .name(propertyDescriptorName).addValidator(new KafkaProcessorUtils.KafkaConfigValidator(ConsumerConfig.class)).dynamic(true)
+ .build();
+ }
+
+ @Override
+ protected Collection<ValidationResult> customValidate(final ValidationContext validationContext) {
+ return KafkaProcessorUtils.validateCommonProperties(validationContext);
+ }
+
+ private synchronized ConsumerPool getConsumerPool(final ProcessContext context) {
+ ConsumerPool pool = consumerPool;
+ if (pool != null) {
+ return pool;
+ }
+
+ return consumerPool = createConsumerPool(context, getLogger());
+ }
+
+ protected ConsumerPool createConsumerPool(final ProcessContext context, final ComponentLog log) {
+ final int maxLeases = context.getMaxConcurrentTasks();
+ final long maxUncommittedTime = context.getProperty(MAX_UNCOMMITTED_TIME).asTimePeriod(TimeUnit.MILLISECONDS);
+ final byte[] demarcator = context.getProperty(ConsumeKafka_2_0.MESSAGE_DEMARCATOR).isSet()
+ ? context.getProperty(ConsumeKafka_2_0.MESSAGE_DEMARCATOR).evaluateAttributeExpressions().getValue().getBytes(StandardCharsets.UTF_8)
+ : null;
+ final Map<String, Object> props = new HashMap<>();
+ KafkaProcessorUtils.buildCommonKafkaProperties(context, ConsumerConfig.class, props);
+ props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "false");
+ props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class.getName());
+ props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class.getName());
+
+ final String topicListing = context.getProperty(ConsumeKafka_2_0.TOPICS).evaluateAttributeExpressions().getValue();
+ final String topicType = context.getProperty(ConsumeKafka_2_0.TOPIC_TYPE).evaluateAttributeExpressions().getValue();
+ final List<String> topics = new ArrayList<>();
+ final String keyEncoding = context.getProperty(KEY_ATTRIBUTE_ENCODING).getValue();
+ final String securityProtocol = context.getProperty(KafkaProcessorUtils.SECURITY_PROTOCOL).getValue();
+ final String bootstrapServers = context.getProperty(KafkaProcessorUtils.BOOTSTRAP_SERVERS).evaluateAttributeExpressions().getValue();
+ final boolean honorTransactions = context.getProperty(HONOR_TRANSACTIONS).asBoolean();
+ final int commsTimeoutMillis = context.getProperty(COMMS_TIMEOUT).asTimePeriod(TimeUnit.MILLISECONDS).intValue();
+ props.put(ConsumerConfig.DEFAULT_API_TIMEOUT_MS_CONFIG, commsTimeoutMillis);
+
+ final String charsetName = context.getProperty(MESSAGE_HEADER_ENCODING).evaluateAttributeExpressions().getValue();
+ final Charset charset = Charset.forName(charsetName);
+
+ final String headerNameRegex = context.getProperty(HEADER_NAME_REGEX).getValue();
+ final Pattern headerNamePattern = headerNameRegex == null ? null : Pattern.compile(headerNameRegex);
+
+ if (topicType.equals(TOPIC_NAME.getValue())) {
+ for (final String topic : topicListing.split(",", 100)) {
+ final String trimmedName = topic.trim();
+ if (!trimmedName.isEmpty()) {
+ topics.add(trimmedName);
+ }
+ }
+
+ return new ConsumerPool(maxLeases, demarcator, props, topics, maxUncommittedTime, keyEncoding, securityProtocol,
+ bootstrapServers, log, honorTransactions, charset, headerNamePattern);
+ } else if (topicType.equals(TOPIC_PATTERN.getValue())) {
+ final Pattern topicPattern = Pattern.compile(topicListing.trim());
+ return new ConsumerPool(maxLeases, demarcator, props, topicPattern, maxUncommittedTime, keyEncoding, securityProtocol,
+ bootstrapServers, log, honorTransactions, charset, headerNamePattern);
+ } else {
+ getLogger().error("Subscription type has an unknown value {}", new Object[] {topicType});
+ return null;
+ }
+ }
+
+ @OnUnscheduled
+ public void interruptActiveThreads() {
+ // There are known issues with the Kafka client library that result in the client code hanging
+ // indefinitely when unable to communicate with the broker. In order to address this, we will wait
+ // up to 30 seconds for the Threads to finish and then will call Consumer.wakeup() to trigger the
+ // thread to wakeup when it is blocked, waiting on a response.
+ final long nanosToWait = TimeUnit.SECONDS.toNanos(5L);
+ final long start = System.nanoTime();
+ while (System.nanoTime() - start < nanosToWait && !activeLeases.isEmpty()) {
+ try {
+ Thread.sleep(100L);
+ } catch (final InterruptedException ie) {
+ Thread.currentThread().interrupt();
+ return;
+ }
+ }
+
+ if (!activeLeases.isEmpty()) {
+ int count = 0;
+ for (final ConsumerLease lease : activeLeases) {
+ getLogger().info("Consumer {} has not finished after waiting 30 seconds; will attempt to wake-up the lease", new Object[] {lease});
+ lease.wakeup();
+ count++;
+ }
+
+ getLogger().info("Woke up {} consumers", new Object[] {count});
+ }
+
+ activeLeases.clear();
+ }
+
+ @Override
+ public void onTrigger(ProcessContext context, ProcessSession session) throws ProcessException {
+ final ConsumerPool pool = getConsumerPool(context);
+ if (pool == null) {
+ context.yield();
+ return;
+ }
+
+ try (final ConsumerLease lease = pool.obtainConsumer(session, context)) {
+ if (lease == null) {
+ context.yield();
+ return;
+ }
+
+ activeLeases.add(lease);
+ try {
+ while (this.isScheduled() && lease.continuePolling()) {
+ lease.poll();
+ }
+ if (this.isScheduled() && !lease.commit()) {
+ context.yield();
+ }
+ } catch (final WakeupException we) {
+ getLogger().warn("Was interrupted while trying to communicate with Kafka with lease {}. "
+ + "Will roll back session and discard any partially received data.", new Object[] {lease});
+ } catch (final KafkaException kex) {
+ getLogger().error("Exception while interacting with Kafka so will close the lease {} due to {}",
+ new Object[]{lease, kex}, kex);
+ } catch (final Throwable t) {
+ getLogger().error("Exception while processing data from kafka so will close the lease {} due to {}",
+ new Object[]{lease, t}, t);
+ } finally {
+ activeLeases.remove(lease);
+ }
+ }
+ }
+}