Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Scala 3 by Example - Algebraic Data Types for D...

Scala 3 by Example - Algebraic Data Types for Domain Driven Design - Part 1

slides can look grainy and/or out of focus when seen on slideshare - download for flawless quality - Based on Scott Wlaschin’s great book 'Domain Modeling Made Functional' and on Martin Odersky's talk 'A Tour of Scala 3'.

Keywords: adt, algebraic data type, algebraic type system, and type, composition, ddd, domain driven design, enum, enumeration, f sharp, f#, functional data structure, martin odersky, opaque type, or type, product type, scala, scala 3, scott wlaschin, sum type

Philip Schwarz

January 25, 2020
Tweet

More Decks by Philip Schwarz

Other Decks in Programming

Transcript

  1. Scala 3 by Example - ADTs for DDD Algebraic Data

    Types for Domain Driven Design based on Scott Wlaschin’s book Domain Modeling Made Functional - Part 1 - @ScottWlaschin Martin Odersky @odersky A Tour of Scala 3 @philip_schwarz slides by https://www.slideshare.net/pjschwarz
  2. @ScottWlaschin Composition of Types You’ll hear the word “composition” used

    a lot in functional programming—it’s the foundation of functional design. Composition just means that you can combine two things to make a bigger thing, like using Lego blocks. In the functional programming world, we use composition to build new functions from smaller functions and new types from smaller types. … In F#, new types are built from smaller types in two ways: • By _AND_ing them together • By _OR_ing them together “AND” Types Let’s start with building types using AND. For example, we might say that to make fruit salad you need an apple and a banana and some cherries: In F# this kind of type is called a record. Here’s how the definition of a FruitSalad record type would be written in F#: type FruitSalad = { Apple: AppleVariety Banana: BananaVariety Cherries: CherryVariety } The curly braces indicate that it is a record type, and the three fields are Apple, Banana, and Cherries.
  3. In Scala we can define an AND type with a

    case class. @philip_schwarz case class FruitSalad ( apple: AppleVariety, banana: BananaVariety, cherries: CherryVariety ) type FruitSalad = { Apple: AppleVariety Banana: BananaVariety Cherries: CherryVariety } AND Types
  4. “OR” Types The other way of building new types is

    by using OR. For example, we might say that for a fruit snack you need an apple or a banana or some cherries: These kinds of “choice” types will be incredibly useful for modeling (as we will see throughout this book). Here is the definition of a FruitSnack using a choice type: type FruitSnack = | Apple of AppleVariety | Banana of BananaVariety | Cherries of CherryVariety A choice type like this is called a discriminated union in F#. It can be read like this: • A FruitSnack is either an AppleVariety (tagged with Apple) or a BananaVariety (tagged with Banana) or a CherryVariety (tagged with Cherries). The vertical bar separates each choice, and the tags (such as Apple and Banana) are needed because sometimes the two or more choices may have the same type and so tags are needed to distinguish them. @ScottWlaschin
  5. In Scala we can define an OR type with a

    sealed trait plus case classes or case objects. See the next slide for an example that uses both. In this case we only need case classes. sealed trait FruitSnack case class Apple(variety: AppleVariety) extends FruitSnack case class Banana(variety: BananaVariety) extends FruitSnack case class Cherry(variety: CherryVariety) extends FruitSnack type FruitSnack = | Apple of AppleVariety | Banana of BananaVariety | Cherries of CherryVariety OR Types
  6. Defining functional data structures A functional data structure is (not

    surprisingly) operated on using only pure functions. Remember, a pure function must not change data in place or perform other side effects. Therefore, functional data structures are by definition immutable. … let’s examine what’s probably the most ubiquitous functional data structure, the singly linked list. The definition here is identical in spirit to (though simpler than) the List data type defined in Scala’s standard library. … Let’s look first at the definition of the data type, which begins with the keywords sealed trait. In general, we introduce a data type with the trait keyword. A trait is an abstract interface that may optionally contain implementations of some methods. Here we’re declaring a trait, called List, with no methods on it. Adding sealed in front means that all implementations of the trait must be declared in this file.1 There are two such implementations, or data constructors, of List (each introduced with the keyword case) declared next, to represent the two possible forms a List can take. As the figure…shows, a List can be empty, denoted by the data constructor Nil, or it can be nonempty, denoted by the data constructor Cons (traditionally short for construct). A nonempty list consists of an initial element, head, followed by a List (possibly empty) of remaining elements (the tail). 1 We could also say abstract class here instead of trait. The distinction between the two is not at all significant for our purposes right now. … sealed trait List[+A] case object Nil extends List[Nothing] case class Cons[+A](head: A, tail: List[A]) extends List[A] Functional Programming in Scala (by Paul Chiusano and Runar Bjarnason) @pchiusano @runarorama
  7. But in Scala 3 we can also define an OR

    type in a simpler way, using an enum. type FruitSnack = | Apple of AppleVariety | Banana of BananaVariety | Cherries of CherryVariety enum FruitSnack { case Apple(appleVariety: AppleVariety) case Banana(bananaVariety: BananaVariety) case Cherry(cherryVariety: CherryVariety) } OR Types sealed trait FruitSnack case class Apple(variety: AppleVariety) extends FruitSnack case class Banana(variety: BananaVariety) extends FruitSnack case class Cherry(variety: CherryVariety) extends FruitSnack
  8. The varieties of fruit are themselves defined as OR types,

    which in this case is used similarly to an enum in other languages. type AppleVariety = | GoldenDelicious | GrannySmith | Fuji type BananaVariety = | Cavendish | GrosMichel | Manzano type CherryVariety = | Montmorency | Bing This can be read as: • An AppleVariety is either a GoldenDelicious or a GrannySmith or a Fuji, and so on. @ScottWlaschin Jargon Alert: “Product Types” and “Sum Types” The types that are built using AND are called product types. The types that are built using OR are called sum types or tagged unions or, in F# terminology, discriminated unions. In this book I will often call them choice types, because I think that best describes their role in domain modeling.
  9. type AppleVariety = | GoldenDelicious | GrannySmith | Fuji type

    BananaVariety = | Cavendish | GrosMichel | Manzano type CherryVariety = | Montmorency | Bing enum AppleVariety { case GoldenDelicious, GrannySmith, Fuji } enum BananaVariety { case Cavendish, GrosMichel, Manzano } enum CherryVariety { case Montmorency, Bing } It seems that in Scala 3 we can also use enums to define these basic OR types. OR Types @philip_schwarz
  10. Simple Types We will often define a choice type with

    only one choice, such as this: type ProductCode = | ProductCode of string This type is almost always simplified to this: type ProductCode = ProductCode of string Why would we create such a type? Because it’s an easy way to create a “wrapper”— a type that contains a primitive (such as a string or int) as an inner value. We’ll be seeing a lot of these kinds of types when we do domain modeling. In this book I will label these single-case unions as “simple types,” as opposed to compound types like records and discriminated unions. More discussion of them is available in the section on Simple Types. @ScottWlaschin
  11. Simple Types Let’s have a go at defining simple types

    using Scala 3 opaque types. type ProductCode = ProductCode of string opaque type ProductCode = String object ProductCode { def apply(code: String): ProductCode = code }
  12. As a recap, here are the Scala 3 AND types

    (product types), OR types (sum types) and Simple types for FruitSnack and FruitSalad. And on the next slide you can see this code again but without braces and with a very simple example of its usage. AND type OR type Simple type
  13. Algebraic Type Systems Now we can define what we mean

    by an “algebraic type system.” It’s not as scary as it sounds—an algebraic type system is simply one where every compound type is composed from smaller types by AND-ing or OR-ing them together. F#, like most functional languages (but unlike OO languages), has a built-in algebraic type system. Using AND and OR to build new data types should feel familiar—we used the same kind of AND and OR to document our domain. We’ll see shortly that an algebraic type system is indeed an excellent tool for domain modeling. @ScottWlaschin
  14. Remember the List functional data structure from Functional Programming in

    Scala (FPiS) that we looked at a few slides ago as an example of an OR type implemented using case classes and case objects? Let’s see how FPiS describes algebraic data types. 3.5 Trees List is just one example of what’s called an algebraic data type (ADT). (Somewhat confusingly, ADT is sometimes used elsewhere to stand for abstract data type.) An ADT is just a data type defined by one or more data constructors, each of which may contain zero or more arguments. We say that the data type is the sum or union of its data constructors, and each data constructor is the product of its arguments, hence the name algebraic data type.14 14 The naming is not coincidental. There’s a deep connection, beyond the scope of this book, between the “addition” and “multiplication” of types to form an ADT and addition and multiplication of numbers. Tuple types in Scala Pairs and tuples of other arities are also algebraic data types. They work just like the ADTs we’ve been writing here, but have special syntax… Algebraic data types can be used to define other data structures. Let’s define a simple binary tree data structure: sealed trait Tree[+A] case class Leaf[A](value: A) extends Tree[A] case class Branch[A](left: Tree[A], right: Tree[A]) extends Tree[A] … Functional Programming in Scala (by Paul Chiusano and Runar Bjarnason) @pchiusano @runarorama sealed trait List[+A] case object Nil extends List[Nothing] case class Cons[+A](head: A, tail: List[A]) extends List[A]
  15. • The List algebraic data type is the sum of

    its data constructors, Nil and Cons. • The Nil constructor has no arguments. • The Cons constructor is the product of its arguments head: A and tail: List[A]. sealed trait List[+A] case object Nil extends List[Nothing] case class Cons[+A](head: A, tail: List[A]) extends List[A] • The Tree algebraic data type is the sum of its data constructors, Leaf and Branch. • The Leaf constructor has a single argument. • The Branch constructor is the product of its arguments left: Tree[A] and right: Tree[A] sealed trait Tree[+A] case class Leaf[A](value: A) extends Tree[A] case class Branch[A](left: Tree[A], right: Tree[A]) extends Tree[A] Let’s recap (informally) what we just saw in FPiS. SUM SUM PRODUCT PRODUCT @philip_schwarz
  16. sealed trait FruitSnack case class Apple(variety: AppleVariety) extends FruitSnack case

    class Banana(variety: BananaVariety) extends FruitSnack case class Cherry(variety: CherryVariety) extends FruitSnack enum FruitSnack with case Apple(variety: AppleVariety) case Banana(variety: BananaVariety) case Cherry(variety: CherryVariety) Here is how the notions of sum type and product type apply to FruitSnack SUM SUM PRODUCT PRODUCT degenerate product – single argument degenerate product – single argument
  17. AND type OR type Simple type products (AND) degenerate products

    - single argument Revisiting a previous diagram to indicate that each constructor of an OR type can be viewed as a product of its arguments
  18. Building a Domain Model by Composing Types A composable type

    system is a great aid in doing domain-driven design because we can quickly create a complex model simply by mixing types together in different combinations. For example, say that we want to track payments for an e-commerce site. Let’s see how this might be sketched out in code during a design session. … So there you go. In about 25 lines of code, we have defined a pretty useful set of types already. Of course, there is no behavior directly associated with these types because this is a functional model, not an object-oriented model. To document the actions that can be taken, we instead define types that represent functions. @ScottWlaschin Here is my translation of Scott Wlaschin’s F# code into Scala 3. See the next slide for a better illustration of its usage of AND types, OR types and Simple types.
  19. AND type AND type Simple type Simple type Simple type

    OR type OR type OR type degenerate products - single or no argument products (AND)
  20. Here is the whole code again plus a very simple

    example of its usage. @philip_schwarz
  21. When Scott Wlaschin showed us OR types, I translated them

    to Scala 3 enums. For the motivation, let’s look at how Martin Odersky introduced enums in his talk: A Tour of Scala 3.
  22. So what is the #1 Scala 3 feature for beginners?

    Clearly for me #1 is enums. enums is such a nice and simple way to define a new type with a finite number of values or constructors. So, enum Color, case Red, Green, Blue, finished: that’s all you need. Right now, in Scala, it wasn’t actually that simple to set up something like that. There were libraries, there was an enumeration type in the standard library, that sort of worked, there was a package called enumeratum that also sort of worked, but it is just much much more straightforward to have this in the language. A Tour of Scala 3 – by Martin Odersky Martin Odersky @odersky
  23. Furthermore, what you have is not just the simple things,

    that was the simplest example, but you can actually add everything to it that a Java enum would do, so you can have enums that have parameters, like this one here, you can have cases that pass parameters, so here the planets give you the mass and radius, you can have fields, you can have methods in these enums. And in fact you can be fully Java compatible. That is done here just by extending java.lang.Enum. So that’s essentially a sign to the compiler that is should generate code so that this enum is for Java an honest enum that can be used like any other enums. A Tour of Scala 3 – by Martin Odersky Martin Odersky @odersky
  24. OK, so this is, again, cool, now we have parity

    with Java, but we can actually go way further. enums can not only have value parameters, they also can have type parameters, like this. So you can have an enum Option with a covariant type parameter T and then two cases Some and None. So that of course gives you what people call an Algebraic Data Type, or ADT. Scala so far was lacking a simple way to write an ADT. What you had to do is essentially what the compiler would translate this to. A Tour of Scala 3 – by Martin Odersky Martin Odersky @odersky
  25. So the compiler would take this ADT that you have

    seen here and translate it into essentially this: And so far, if you wanted something like that, you would have written essentially the same thing. So a sealed abstract class or a sealed abstract trait, Option, with a case class as one case, and as the other case, here it is a val, but otherwise you could also use a case object. And that of course is completely workable, but it is kind of tedious. When Scala started, one of the main motivations, was to avoid pointless boilerplate. So that’s why case classes were invented, and a lot of other innovations that just made code more pleasant to write and more compact than Java code, the standard at the time. A Tour of Scala 3 – by Martin Odersky Martin Odersky @odersky
  26. sealed trait Option[+A] case class Some[+A](get: A) extends Option[A] case

    object None extends Option[Nothing] In FP in Scala we can see an example of the alternative that Martin Odersky just mentioned, in which the second case of the Option ADT is a case object rather than a val. Functional Programming in Scala (by Paul Chiusano and Runar Bjarnason) @pchiusano @runarorama Martin Odersky @odersky
  27. And one has to recognise that during all these years,

    the software world has shifted also a little bit and it is now much more functional than before, so an ADT would have been something very foreign at the time, 2003 – 2004, when Scala came out, but now it is pretty common. People write them and write more and more of them because also, with essentially more static typing, you want to write more and more types, and more and more case hierarchies, and ADTs are just a lovely, simple way to do that. So in the spirit of reducing boilerplate, it was about time to have something that makes this case simple and straightforward to express. But that’s not even the end of it. We can do more. We can also do Generalized ADTs (GADTs). They are different from normal ADTs in that the cases can inherit the base class at different types… Martin Odersky @odersky A Tour of Scala 3 – by Martin Odersky
  28. Hmmm, I have a nagging doubt that some of the

    OR types I have implemented using the Scala 3 enum may not be bona fide ADTs. I have used enums for two ‘kinds’ of OR types: In the case of AppleVariety, I think I might have got too carried away with the word enum when Scott Wlaschin said the following: The varieties of fruit are themselves defined as OR types, which in this case is used similarly to an enum in other languages. Maybe a plain enum is not technically considered an ADT. Maybe I should have defined AppleVariety as follows: enum AppleVariety with case GoldenDelicious case GrannySmith case Fuji enum AppleVariety with case GoldenDelicious, GrannySmith, Fuji enum FruitSnack with case Apple(variety: AppleVariety) case Banana(variety: BananaVariety) case Cherry(variety: CherryVariety) @philip_schwarz
  29. I say that because when explaining enum, Martin Odersky only

    started mentioning ADTs when he discussed the Option enum. There was no mention of ADTs in his first enum example, the Color enum. Also, in the following dotty github issue he seems to emphasize a clear distinction between enumerations, as found in other languages, and ADTs/GADTs Add enum construct - 13 Feb 2017 https://github.com/lampepfl/dotty/issues/1970 This is a proposal to add an enum construct to Scala's syntax. The construct is intended to serve at the same time as a native implementation of enumerations as found in other languages and as a more concise notation for ADTs and GADTs. … Martin Odersky @odersky
  30. So I asked the following on the dotty gitter channel:

    and it turns out that the two definitions of AppleVariety are equivalent, because in the current dotty documentation pages we find the following desugaring rule: So one definition is syntactic sugar for the other. Good to know!
  31. From https://bartoszmilewski.com/2015/01/13/simple-algebraic-data-types/ Sum types are pretty common in Haskell, but

    their C++ equivalents, unions or variants, are much less common. There are several reasons for that. First of all, the simplest sum types are just enumerations and are implemented using enum in C++. The equivalent of the Haskell sum type: data Color = Red | Green | Blue is the C++: enum { Red, Green, Blue }; An even simpler sum type: data Bool = True | False is the primitive bool in C++. From https://en.wikipedia.org/wiki/Algebraic_data_type Enumerated types are a special case of sum types in which the constructors take no arguments, as exactly one value is defined for each constructor. What we just saw is consistent with the following @BartoszMilewski Bartosz Milewski
  32. That’s all for part 1. When Scott Wlaschin showed us

    Simple types, I translated them to Scala 3 opaque types. Why? We’ll look at that in part 2. Another thing we’ll do in part 2 is take a look at what Scott has to say about working with Simple values and constraining Simple values. That’s not all we’ll be covering in Part 2 – there will be more. @philip_schwarz