Mongock, Mongo and Java

Originally posted on my blog

Database Migration tools are essential with applications where you need to migrate data into a database, change a schema, update a record/document across all environments and where it is tedious to do it manually (almost always?). These can also help you with keeping a track of the changes made, just like version control.

With Java there are various libraries you can use for the purpose. There's Liquibase, Flyway, Mongock and maybe more.

When using MongoDB as the database for the application, I found that Mongock would be the best to go for.

Mongobee seems to be outdated and not being maintained anymore.

To use the same with a Java, you would need the following dependencies (in addition to the Mongo Java Driver/Spring Mongo data that you'd use to set up the application anyways):

• Mongock BOM
• Mongock runner
• Mongock driver
• MongoDB driver sync

Make sure not to import Mongock Core along with the above dependencies, as it will lead you into having multiple versions of a library in your classpath. Read more on this here

On importing the above, all you need to do is:

• Annote the Application Class with @EnableMongock
• Specify the package(s) where you'd localte your Changelog classes on your application.yml or application.properties under mongock.change-logs-scan-package

With this, the application should be ready to be run, without an issue. If you face any, leave a comment or visit the issues section on Github, and you'd most likely find a solution for it.

To add a changelog, create a changelog class in the package mentioned in the properties file. Annotate the class with @Changelog(order = "001..."). The order defines the order in which the changelog classes will be executed in case there are multiple. The class should now contain the changesets. The changesets are nothing but Java methods. You can create collections, insert a document, or do whatever you'd want to that you can do via a Java method. The method would run at the Startup and the changes (if any) would get executed (if not already).

Example class:

@ChangeLog(order = "001")
public class Changelog {
    @ChangeSet(order = "001", id="001", author = "pradipta")
    public void dummyChangeSet() {
        System.out.println("Dummy changeset");
    }

    @ChangeSet(order = "002", id="create collection", author = "pradipta")
    public void createCollection(MongoDatabase db) {
        MongoCollection<Document> mycollection = db.getCollection("dummycollection");
        Document doc = new Document("k1", "v1").append("k2", "v2");
        mycollection.insertOne(doc);
    }

    @ChangeSet(order = "003", id = "insert document", author = "pradipta")
    public void insertDocument(MongockTemplate mongockTemplate) {
        User user = new User("Name", "Email", "Phone");
        //User is an entity with a collection already defined
        mongockTemplate.save(user);
    }
}

There is also another method where you write the builder yourself and not annotate the application with @EnableMongock. You'd want to do it if you want to have a control over the beans and configure things. Read the documentation for more info.

With these, you can be sure to have the changes being executed onto the DB on a successful deployment to any environment.

Happy coding.