Merge pull request #5567 from markusgulden/master

BAEL-1658

libraries-data/src/main/kafka-connect/01_Quick_Start/connect-file-sink.properties

@@ -0,0 +1,20 @@
+# 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.
+
+name=local-file-sink
+connector.class=FileStreamSink
+tasks.max=1
+file=test.sink.txt
+topics=connect-test

libraries-data/src/main/kafka-connect/01_Quick_Start/connect-file-source.properties

@@ -0,0 +1,20 @@
+# 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.
+
+name=local-file-source
+connector.class=FileStreamSource
+tasks.max=1
+file=test.txt
+topic=connect-test

libraries-data/src/main/kafka-connect/01_Quick_Start/connect-standalone.properties

@@ -0,0 +1,44 @@
+# 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.
+
+# These are defaults. This file just demonstrates how to override some settings.
+bootstrap.servers=localhost:9092
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=false
+value.converter.schemas.enable=false
+
+offset.storage.file.filename=/tmp/connect.offsets
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000
+
+# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
+# (connectors, converters, transformations). The list should consist of top level directories that include 
+# any combination of: 
+# a) directories immediately containing jars with plugins and their dependencies
+# b) uber-jars with plugins and their dependencies
+# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
+# Note: symlinks will be followed to discover dependencies or plugins.
+# Examples: 
+# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
+# Replace the relative path below with an absolute path if you are planning to start Kafka Connect from within a
+# directory other than the home directory of Confluent Platform.
+plugin.path=C:\Software\confluent-5.0.0\share\java
+#plugin.path=./share/java

libraries-data/src/main/kafka-connect/02_Distributed/connect-distributed.properties

@@ -0,0 +1,88 @@
+##
+# 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.
+##
+
+# This file contains some of the configurations for the Kafka Connect distributed worker. This file is intended
+# to be used with the examples, and some settings may differ from those used in a production system, especially
+# the `bootstrap.servers` and those specifying replication factors.
+
+# A list of host/port pairs to use for establishing the initial connection to the Kafka cluster.
+bootstrap.servers=localhost:9092
+
+# unique name for the cluster, used in forming the Connect cluster group. Note that this must not conflict with consumer group IDs
+group.id=connect-cluster
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=true
+value.converter.schemas.enable=true
+
+# Topic to use for storing offsets. This topic should have many partitions and be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+offset.storage.topic=connect-offsets
+offset.storage.replication.factor=1
+#offset.storage.partitions=25
+
+# Topic to use for storing connector and task configurations; note that this should be a single partition, highly replicated,
+# and compacted topic. Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+config.storage.topic=connect-configs
+config.storage.replication.factor=1
+
+# Topic to use for storing statuses. This topic can have multiple partitions and should be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+status.storage.topic=connect-status
+status.storage.replication.factor=1
+#status.storage.partitions=5
+
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000
+
+# These are provided to inform the user about the presence of the REST host and port configs 
+# Hostname & Port for the REST API to listen on. If this is set, it will bind to the interface used to listen to requests.
+#rest.host.name=
+#rest.port=8083
+
+# The Hostname & Port that will be given out to other workers to connect to i.e. URLs that are routable from other servers.
+#rest.advertised.host.name=
+#rest.advertised.port=
+
+# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
+# (connectors, converters, transformations). The list should consist of top level directories that include 
+# any combination of: 
+# a) directories immediately containing jars with plugins and their dependencies
+# b) uber-jars with plugins and their dependencies
+# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
+# Examples: 
+# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
+# Replace the relative path below with an absolute path if you are planning to start Kafka Connect from within a
+# directory other than the home directory of Confluent Platform.
+plugin.path=./share/java

libraries-data/src/main/kafka-connect/02_Distributed/connect-file-sink.json

@@ -0,0 +1,9 @@
+{
+    "name": "local-file-sink",
+    "config": {
+        "connector.class": "FileStreamSink",
+        "tasks.max": 1,
+        "file": "test-distributed.sink.txt",
+        "topics": "connect-distributed"
+    }
+}

libraries-data/src/main/kafka-connect/02_Distributed/connect-file-source.json

@@ -0,0 +1,9 @@
+{
+    "name": "local-file-source",
+    "config": {
+        "connector.class": "FileStreamSource",
+        "tasks.max": 1,
+        "file": "test-distributed.txt",
+        "topic": "connect-distributed"
+    }
+}

libraries-data/src/main/kafka-connect/03_Transform/connect-distributed.properties

@@ -0,0 +1,88 @@
+##
+# 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.
+##
+
+# This file contains some of the configurations for the Kafka Connect distributed worker. This file is intended
+# to be used with the examples, and some settings may differ from those used in a production system, especially
+# the `bootstrap.servers` and those specifying replication factors.
+
+# A list of host/port pairs to use for establishing the initial connection to the Kafka cluster.
+bootstrap.servers=localhost:9092
+
+# unique name for the cluster, used in forming the Connect cluster group. Note that this must not conflict with consumer group IDs
+group.id=connect-cluster
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=false
+value.converter.schemas.enable=false
+
+# Topic to use for storing offsets. This topic should have many partitions and be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+offset.storage.topic=connect-offsets
+offset.storage.replication.factor=1
+#offset.storage.partitions=25
+
+# Topic to use for storing connector and task configurations; note that this should be a single partition, highly replicated,
+# and compacted topic. Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+config.storage.topic=connect-configs
+config.storage.replication.factor=1
+
+# Topic to use for storing statuses. This topic can have multiple partitions and should be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+status.storage.topic=connect-status
+status.storage.replication.factor=1
+#status.storage.partitions=5
+
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000
+
+# These are provided to inform the user about the presence of the REST host and port configs 
+# Hostname & Port for the REST API to listen on. If this is set, it will bind to the interface used to listen to requests.
+#rest.host.name=
+#rest.port=8083
+
+# The Hostname & Port that will be given out to other workers to connect to i.e. URLs that are routable from other servers.
+#rest.advertised.host.name=
+#rest.advertised.port=
+
+# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
+# (connectors, converters, transformations). The list should consist of top level directories that include 
+# any combination of: 
+# a) directories immediately containing jars with plugins and their dependencies
+# b) uber-jars with plugins and their dependencies
+# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
+# Examples: 
+# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
+# Replace the relative path below with an absolute path if you are planning to start Kafka Connect from within a
+# directory other than the home directory of Confluent Platform.
+plugin.path=./share/java

libraries-data/src/main/kafka-connect/03_Transform/connect-file-source-transform.json

@@ -0,0 +1,15 @@
+{
+    "name": "local-file-source",
+    "config": {
+        "connector.class": "FileStreamSource",
+        "tasks.max": 1,
+        "file": "transformation.txt",
+        "topic": "connect-transformation",
+        "transforms": "MakeMap,InsertSource",
+        "transforms.MakeMap.type": "org.apache.kafka.connect.transforms.HoistField$Value",
+        "transforms.MakeMap.field": "line",
+        "transforms.InsertSource.type": "org.apache.kafka.connect.transforms.InsertField$Value",
+        "transforms.InsertSource.static.field": "data_source",
+        "transforms.InsertSource.static.value": "test-file-source"
+    }
+}

libraries-data/src/main/kafka-connect/04_Custom/connect-distributed.properties

@@ -0,0 +1,88 @@
+##
+# 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.
+##
+
+# This file contains some of the configurations for the Kafka Connect distributed worker. This file is intended
+# to be used with the examples, and some settings may differ from those used in a production system, especially
+# the `bootstrap.servers` and those specifying replication factors.
+
+# A list of host/port pairs to use for establishing the initial connection to the Kafka cluster.
+bootstrap.servers=localhost:9092
+
+# unique name for the cluster, used in forming the Connect cluster group. Note that this must not conflict with consumer group IDs
+group.id=connect-cluster
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=true
+value.converter.schemas.enable=true
+
+# Topic to use for storing offsets. This topic should have many partitions and be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+offset.storage.topic=connect-offsets
+offset.storage.replication.factor=1
+#offset.storage.partitions=25
+
+# Topic to use for storing connector and task configurations; note that this should be a single partition, highly replicated,
+# and compacted topic. Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+config.storage.topic=connect-configs
+config.storage.replication.factor=1
+
+# Topic to use for storing statuses. This topic can have multiple partitions and should be replicated and compacted.
+# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
+# the topic before starting Kafka Connect if a specific topic configuration is needed.
+# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
+# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
+# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
+status.storage.topic=connect-status
+status.storage.replication.factor=1
+#status.storage.partitions=5
+
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000
+
+# These are provided to inform the user about the presence of the REST host and port configs 
+# Hostname & Port for the REST API to listen on. If this is set, it will bind to the interface used to listen to requests.
+#rest.host.name=
+#rest.port=8083
+
+# The Hostname & Port that will be given out to other workers to connect to i.e. URLs that are routable from other servers.
+#rest.advertised.host.name=
+#rest.advertised.port=
+
+# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
+# (connectors, converters, transformations). The list should consist of top level directories that include 
+# any combination of: 
+# a) directories immediately containing jars with plugins and their dependencies
+# b) uber-jars with plugins and their dependencies
+# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
+# Examples: 
+# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
+# Replace the relative path below with an absolute path if you are planning to start Kafka Connect from within a
+# directory other than the home directory of Confluent Platform.
+plugin.path=./share/java

libraries-data/src/main/kafka-connect/04_Custom/connect-mongodb-sink.json

@@ -0,0 +1,22 @@
+{
+    "firstName": "John",
+    "lastName": "Smith",
+    "age": 25,
+    "address": {
+        "streetAddress": "21 2nd Street",
+        "city": "New York",
+        "state": "NY",
+        "postalCode": "10021"
+    },
+    "phoneNumber": [{
+            "type": "home",
+            "number": "212 555-1234"
+        }, {
+            "type": "fax",
+            "number": "646 555-4567"
+        }
+    ],
+    "gender": {
+        "type": "male"
+    }
+}

libraries-data/src/main/kafka-connect/04_Custom/connect-mqtt-source.json

@@ -0,0 +1,11 @@
+{
+    "name": "mqtt-source",
+    "config": {
+        "connector.class": "io.confluent.connect.mqtt.MqttSourceConnector",
+        "tasks.max": 1,
+        "mqtt.server.uri": "ws://broker.hivemq.com:8000/mqtt",
+        "mqtt.topics": "baeldung",
+        "kafka.topic": "connect-custom",
+        "value.converter": "org.apache.kafka.connect.converters.ByteArrayConverter"
+    }
+}