Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Ingesting Golden Gate Records From Apache Kafka and Automagically Populating Any JDBC Tables

DZone's Guide to

Ingesting Golden Gate Records From Apache Kafka and Automagically Populating Any JDBC Tables

As long as they have proper header data and records in JSON, it's really easy to process any number of table changes sent from tools via Apache Kafka in Apache NiFi.

· Big Data Zone ·
Free Resource

The open source HPCC Systems platform is a proven, easy to use solution for managing data at scale. Visit our Easy Guide to learn more about this completely free platform, test drive some code in the online Playground, and get started today.

Sometimes, you need to process any number of table changes sent from tools via Apache Kafka. As long as they have proper header data and records in JSON, it's really easy in Apache NiFi.

Requirements:

  1. Process each partition separately.
  2. Process records in order, as each message is an insert, update, or delete to an existing table in our receiving JDBC store.
  3. Re-process if data lost.

The main processor for routing must only run on the Primary Node.

Enforcing Order

We use kafka.offset to order the records, which makes sense in Apache Kafka topics.

After insert, update, and delete queries are built, let's confirm and enforce that strict ordering.

To further confirm processing in order, we make each connection in the flow FirstInFirstOutPrioritizer.

We route each partition to a different processor group (one local, the other remote):

Let's store some data in HDFS for each table:

Connect to Kafka and grab from our topic:

Let's connect to our JDBC store:

Let's do an update (table name is dynamic):

The Jolt processor has an awesome tester for trying out Jolt:

Make sure we connect our remote partitions:

Routing from routing server (Primary Node):

For processing partition 0 (run on the routing server):

We infer the schema with InferAvroSchema, so we don't need to know the embedded table layouts before a record arrives. In production, it makes sense to know all these in advance and to do integration tests and versioning of schemas. This is where Hortonworks Schema Registry is awesome. We name the Avro record after the table dynamically. We can get and store permanent schemas in the Hortonworks Schema Registry.

Process partition 1 (we can have one server or cluster per partition):

Process the partition 1 Kafka records from the topic:

This flow will convert our embedded JSON table record into New SQL:

Input: {"ID":2001,"GD":"F","DPTID":2,"FIRSTNAME":"Tim","LAST":"Spann"}
Output: INSERT INTO THETABLE (ID, GD, DPTID, FIRSTNAME, LAST) VALUES (?, ?, ?, ?, ?)
sql.args.5.value Spann
sql.table THETABLE

With all the field being parameters for a SQL Injection-safe parameter-based insert, update, or delete based on the control sent.

Golden Gate messages:

{"table": "SCHEMA1.TABLE7","op_type": "I","op_ts": "2017-11-01 04:31:56.000000","current_ts": "2017-11-01T04:32:04.754000","pos": "00000000310000020884","after": {"ID":1,"CODE": "B","NAME":"STUFF","DESCR" :"Department","ACTIVE":1}}

Using a simple EvaluateJsonPath, we pull out these control fields; for example, $.before.

The table name for ConvertJSONtoSQL is ${table:substringAfter('.')}. This is to remove all leading schema/tablespace names. From the drop-down for each of the three, we pick either UPDATEINSERT, or DELETE based on the op_type.

We follow this with a PutSQL, which will execute on our destination JDBC database sink.

After that, I collect all the attributes, convert them to a JSON flow file, and save that to HDFS for logging and reporting. This step could be skipped or could be in another format or sent elsewhere.

Control Fields

  • pos: Position

  • table: Table to update in the data warehouse

  • current_ts: Timestamp

  • op_ts: Timestamp

  • op_type: Operation type (I=insert, U=update, D=delete)

Important Apache NiFi system fields:

  • kafka.offset

  • kafka.partition

  • kafka.topic

We can route and process these for special handling.

To create HDFS directories for changes:

su hdfs <br>hdfs dfs -mkdir -p /new/T1 <br>hdfs dfs -mkdir -p /new/T2 <br>hdfs dfs -mkdir -p /poc/T3
hdfs dfs -chmod -R 777 /new <br>hdfs dfs -ls -R /new

To create a test Apache Kafka topic:

./bin/kafka-topics.sh --create \
    --zookeeper localhost:2181 \
    --replication-factor 1 \
    --partitions 2 \
    --topic goldengate

Creating a MySQL Database as recipient JDBC server:

wget https://dev.mysql.com/get/Downloads/Connector-J/mysql-connector-java-5.1.45.tar.gz
mysql
create database mydw;
CREATE USER 'nifi'@'%' IDENTIFIED BY 'MyPassWordIsSoAwesome!!!!';
GRANT ALL PRIVILEGES ON *.* TO 'nifi'@'%' WITH GRANT OPTION;
commit;
SHOW GRANTS FOR 'nifi'@'%';


#Create some tables in the database for your records.


create table ALOG (
AID VARCHAR(1),
TIMESEC INT,
SOMEVAL VARCHAR(255),
PRIMARY KEY (AID, TIMESEC)
);

Jolt filter:

Attribute: afterJolt
${op_type:equalsIgnoreCase("D"):ifElse("none", "after")}
Attribute: beforeJolt
${op_type:equalsIgnoreCase("D"):ifElse("before", "none")}

Jolt script to transform JSON:

[   {
    "operation": "shift",     
     "spec": {
      "${beforeJolt}": {
        "*": "&"
      },
      "${afterJolt}": {
        "*": "&"
      }
    }
  },   {
    "operation": "shift",
    "spec": {
      "*": "&"
    }
   } ]

And that's it!

Managing data at scale doesn’t have to be hard. Find out how the completely free, open source HPCC Systems platform makes it easier to update, easier to program, easier to integrate data, and easier to manage clusters. Download and get started today.

Topics:
apache nifi ,big data ,apache kafka ,tutorial ,data processing ,jolt

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}