Did you just begin to learn Object-Oriented Design/Programming recently? Are you struggling to grasp the general idea of Abstraction, Generalisation, Decomposition and Encapsulation? Are you not sure about the differences between each concept?
If that sounds like you, you are not alone! For newbies, there are so many concepts to remember and it can be overwhelming.
In this post, we'll be looking at the summary of each principle and then move onto each of them. To help us remember the concepts in one go, we will be looking at the four main principles in a setting simulating a retail company similar to IKEA.
As a result, we'll be able to grasp the general ideas and understand why they are useful.
|Abstraction||Reduces complexity by showing only relevant information||abstract class, abstract method, extend||A row header for chairs|
|Generalization||Reduces complexity by having an umbrella term||superclass, subclass, interface, implements, extends||Furniture for chairs, tables and chests|
|Decomposition||Reduces complexity by separating problems||association, aggregation, composition||Fitted Kitchen|
|Encapsulation||Restrict access to data to protect them and reduce complexity||getter method, setter method, private, protected, public||System of a restaurant section|
Now let's dive into details.
Abstraction can reduce complexity by hiding irrelevant information of things. In other words, it clarfy things by showing only relevant information.
Let's look at examples.
Imagine we sell chairs in our retail company. On our website, we listed our products and information to help customers to make purchase decisions. The product pages of chairs would contain those information listed below without having concepts of abstraction:
What do you think about the representation? Are some of them irrelevant to customers to make purchase decisions?
In such a situation, we usually show only relevant information to help make our customer's purchase decisions without confusion.
What we can see here is a much less complex structure because irrelevant information were ignored and rest of them are organized.
Abstraction is like creating the row header in the picture. They can become attributes within a Chair class. As a result, it is much easier to create a new type of chair because you have column headers, which is a class in OOP, as a template.
Generalization can reduce complexity by creating an umbrella term. In other words, having an umbrella term can reduce redundancy and improve efficiency.
Now, let us continue to use the example of the retail company to look at how generalization can be used.
At the moment, we sell chairs, tables and chests in the retail section of our company. At the moment, we have a column header for chairs including
Max. seat height,
When we looked at each title carefully, you may notice that some of them are obviously necessary for tables and wardrobes as well, but others are only applicable for chairs.
For instance, it is clear that
Height must be included in any products we have, because they are the key factors for any furniture to evaluate if it is compatible with the customer's usage.
If that's the case, we can state that
Height as well as
Product name and
Type are must-have information to include in an umbrella term which we could name it
Decomposition can reduce the complexity of a problem by separating it into smaller chunks.
Imagine we started selling more products including kitchen appliances in our retail company. Now, we are planning to sell fitted kitchens and set the fitted kitchen samples at our shop.
So far, we have specified what to include in a fitted kitchen sample without decomposition.
What do you think of it? Isn't it complicated and unclear? For now, the list is small enough for the sake of simplicity, but what could happen if we include all the functionalities?
Without decomposition, an object could have too many responsibilities and purpose.
In such a situation, we usually separate the responsibilities into smaller chunks to make things clearer and easier to maintain.
There are three types of relationships between the decomposed Fitted Kitchen object and its components, namely Composition, Aggregation and Association.
Composition creates the strongest relationship. In the example above, the Fitted Kitchen could have a relationship with
Dimension because when the Fitted Kitchen is destroyed,
Dimension should also be destroyed. In other words,
Dimension cannot exist without the Fitted Kitchen itself.
Aggregation is a looser relationship than composition. In the example, Tap, Ventilation fan, Oven, Hob, Fridge, Freezer and Cupboard could have aggregation relationships with Fitted Kitchen if we decide that Fitted Kitchen should not be presented to customers without one of the components. That being said, each component can exist or be sold individually even though the Fitted Kitchen is destroyed.
Association is a loose relationship. In the example,
Designer could have an association relationship with the Fitted Kitchen, if the existence of Designer does not affect the existence of the Fitted Kitchen and vice versa. In other words, the Designer can exist and do their job even though the Fitted Kitchen is destroyed.
Encapsulation can reduce the complexity of issues by bundling data and the methods that work on the data within one unit.
Let's say we are planning to have a restaurant section in our retail company like IKEA does.
We decided to have three menus like below:
|Dish Name||Comes with||Price|
|Grilled Salmon||Small soup, French fries||8.50|
|Vegetable Soup||Small Salad, A slice of soda bread||8.00|
|Beef Sandwich||Small Salad, Crisps||8.50|
Without encapsulation, we are forced to have a buffet-style bar that customer can serve themselves freely. To put it another way, a customer is able to change the Small Salad to Grilled Salmon as the side, because they are set to
public. As a result, the price and the system of the restaurant would break.
Encapsulation enables the restaurant system to have staff who control the changes in the dishes. In other words, each component of the dish is set to protected or private. They can allow a customer's request if it's allowed, or reject if they cannot change so that prevent direct changes and mistakes.
As I found these design principles terms a bit demotivating to remember at first, I prefer to include all of them in a single setting. I hope those examples help you to remember and distinguish the differences!
Object-Oriented Design - Coursera
What is Abstraction in OOPs? Java Abstract Class & Method - Guru99
OOP Concept for Beginners: What is Abstraction? - Stackify
What's the difference between abstraction and generalization? - Stackoverflow
Generalization - SAN JOSÉ STATE UNIVERSITY
Premature Generalization Is Evil - Wiki Wiki Web
Decomposition - BBC Bitesize
OOP Concept for Beginners: What is Encapsulation - Stackify