DEV Community

Cover image for The quest for REST
Nicolas Frankel
Nicolas Frankel

Posted on • Originally published at blog.frankel.ch

The quest for REST

Since I started working for Apache APISIX, I have tried to deepen my understanding of REST via various means. Did you read my review of API Design Patterns book?

In the current literature, REST is generally promoted as the best thing since sliced bread. Yet, it comes with lots of challenges. In 2010(!), Martin Fowler wrote a post on the glory of REST. He lists three steps for an API to become truly REST:

In each of these steps, issues lurk. This blog post focuses on listing some of them and providing hints at ways to solve them.

Resources

REST emerged from the cons of SOAP. SOAP provides a single endpoint and executes code depending on the payload. The idea of REST is to provide multiple endpoints, which each executes different code.

I'll be honest; there are few issues at this stage. The biggest one relates to guessing one identity from an existing one. If resource ids are sequential or even only numeric, it's easy to guess other resources' endpoints, e.g., from /customers/1 to /customers/2. The solution is to use non-sequential non-numeric ids, i.e., Universally unique identifiers.

Let's walk up the REST maturity model.

HTTP verbs

HTTP verbs are the next step toward the glory of REST. They come from interactions with HTML "back in the days". Interactions came from CRUD operations.

It's pretty straightforward:

Operation Verb
Create POST
Read GET
Update PUT
PATCH
Delete DELETE

The main problem with APIs is that you need to go beyond CRUD. Let's imagine a concrete example with a bank transfer: it takes money from an account and moves it to another one. How shall we model it?

We could use the origin account as the resource, e.g., /accounts/a1b2c3d4e5f6. The target account, the amount, etc., can be passed as query parameters or in the body. But what HTTP verb shall we use?

It changes the identified resource indeed, but it has "side-effects": it also changes another resource, the target account. Here are a couple of options on how to manage the HTTP verb:

  • Use POST because it changes the source resource. It's misleading because it doesn't tell about side effects.
  • Use a dedicated HTTP verb, e.g., TRANSFER. It's not self-explanatory and is opposite to REST principles.
  • Use POST with a so-called custom method. Custom methods are a Google API Improvement Proposal:

    Custom methods should only be used for functionality that can not be easily expressed via standard methods; prefer standard methods if possible, due to their consistent semantics.

    The HTTP URI must use a : character followed by the custom verb.

    Here's our bank account transfer URI: /accounts/a1b2c3d4e5f6:transfer.

    What's the best alternative? "It depends".

Hypermedia

Fowler describes Hypermedia Controls as the ultimate step to reaching the glory of REST. It's nowadays known as HATEOAS:

With HATEOAS, a client interacts with a network application whose application servers provide information dynamically through hypermedia. A REST client needs little to no prior knowledge about how to interact with an application or server beyond a generic understanding of hypermedia.

-- HATEOAS on Wikipedia

HATEOAS is a concept; here's a possible implementation taken from Wikipedia. When one requests a bank account, say /accounts/a1b2c3d4e5f6, the response contains links to actions possible with this specific bank account:

{
  "account": {
    "account_number": "a1b2c3d4e5f6",
    "balance": {
      "currency": "USD",
      "value": 100.00
    },
    "links": {
      "_self": "/accounts/a1b2c3d4e5f6",
      "deposit": "/accounts/a1b2c3d4e5f6:deposit",
      "withdrawal": "/accounts/a1b2c3d4e5f6:withdrawal",
      "transfer": "/accounts/a1b2c3d4e5f6:transfer",
      "close-request": "/accounts/a1b2c3d4e5f6:close-request"
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

If the balance is negative, only the deposit link will be available:

{
  "account": {
    "account_number": "a1b2c3d4e5f6",
    "balance": {
      "currency": "USD",
      "value": 100.00
    },
    "links": {
      "_self": "/accounts/a1b2c3d4e5f6",
      "deposit": "/accounts/a1b2c3d4e5f6:deposit",
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

A common issue with REST is the lack of standards; HATEOAS is no different. The first attempt to bring some degree of standardization was the JSON Hypertext Application Language, aka HAL. Note that it was incepted in 2012; the latest version dates from 2016, and it's still in draft.

Here's a quick diagram that summarizes the proposal:

HAL model

We can rework the above with HAL as the following:

GET /accounts/a1b2c3d4e5f6 HTTP/1.1
Accept: application/hal+json

HTTP/1.1 200 OK
Content-Type: application/hal+json

{
  "account": {
    "account_number": "a1b2c3d4e5f6",
    "balance": {
      "currency": "USD",
      "value": 100.00
    },
    "_links": {                                    <1>
      "self": {                                    <2>
        "href" : "/accounts/a1b2c3d4e5f6",
        "methods": ["GET"]                         <3>
      },
      "deposit": {
        "href" : "/accounts/a1b2c3d4e5f6:deposit", <4>
        "methods": ["POST"]                        <3>
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode
  1. Available links
  2. Link to self
  3. Tell which HTTP verb can be used
  4. Link to deposit

Another attempt at standardization is RFC 8288, aka Web Linking. It describes the format and contains a link relationship registry, e.g., alternate and copyright. The most significant difference with HAL is that RFC 8288 communicates links via HTTP response headers.

Web Linking model

HTTP/2 200 OK

Link: </accounts/a1b2c3d4e5f6> rel="self";
                               method="GET",                           <1>
      </accounts/a1b2c3d4e5f6:deposit> rel="https://my.bank/deposit";
                                       title="Deposit";
                                       method="POST"                   <2>
{
  "account": {
    "account_number": "a1b2c3d4e5f6",
    "balance": {
      "currency": "USD",
      "value": 100.00
    }
  }
}
Enter fullscreen mode Exit fullscreen mode
  1. Link to the current resource with the non-standard self relation type
  2. Link to deposit with the extension https://my.bank/deposit relation type and an arbitrary title target attribute

Other alternative media types specifications are available.

Name Description Provided by
Uniform Basis for Exchanging Representations
The UBER document format is a minimal read/write hypermedia type designed to support simple state transfers and ad-hoc hypermedia-based transitions. This specification describes both the XML and JSON variants of the format and provides guidelines for supporting UBER-encoded messages over the HTTP protocol.
Individuals
Collection+JSON
Collection+JSON is a JSON-based read/write hypermedia-type designed to support management and querying of simple collections.
Individual
JSON:API
JSON:API is a specification for how a client should request that resources be fetched or modified, and how a server should respond to those requests. JSON:API can be easily extended with extensions and profiles.
Individuals
Siren
Siren is a hypermedia specification for representing entities. As HTML is used for visually representing documents on a Web site, Siren is a specification for presenting entities via a Web API. Siren offers structures to communicate information about entities, actions for executing state transitions, and links for client navigation.
Individual
Application-Level Profile Semantics
An ALPS document can be used as a profile to explain the application semantics of a document with an application-agnostic media type (such as HTML, HAL, Collection+JSON, Siren, etc.). This increases the reusability of profile documents across media types.
IETF

Bonus: HTTP response status

What Fowler's post doesn't mention is the HTTP response status. Most readers are familiar with the status ranges:

  • Informational responses: 100 – 199
  • Successful responses: 200 – 299
  • Redirection messages: 300 – 399
  • Client error responses: 400 – 499
  • Server error responses: 500 – 599

Likewise, most are also with regularly-found HTTP status:

The problem is that beyond these simple cases, it's a mess. For example, look at this StackOverflow question: "Which HTTP status code means Not Ready Yet, Try Again Later?" Here is a summary of the proposed answers, from the most upvoted to the lowest:

  • 503 Service Unavailable
  • 202 Accepted (accepted answer)
  • 423 Locked
  • 404 Not Found
  • 302 Found
  • 409 Conflict
  • 501 Not Implemented (downvoted)

It's not a straightforward answer; there was a lot of debate around the alternatives. For the record, I think the accepted answer is the right one.

That's already a lot on the designer side, but the client side contains a lot of uncertainty, too, as some big APIs providers use their own HTTP status codes.

Conclusion

The "glory of REST" doesn't mean much. There's no univocal semantics to rely on, despite any opposite claim. As it is, it depends mainly on the implementation and interpretation: both require documenting the custom behavior instead of relying on a shared specification.

SOAP's biggest flaw was its complexity and its focus on big companies, but it at least provided a shared set of standard specifications. The industry replaced it with REST, not a specification but an architectural site. REST is simpler and, thus, more approachable, but it requires a lot of custom effort, which changes from project to project.

There are initiatives to provide some standardization, but they are few, and some are at odds with others. Moreover, they have low traction, so people don't know them, which creates a vicious circle. I hardly advocate getting back to SOAP though I sure miss it sometimes.

Originally published at A Java Geek on January 22nd, 2023

Top comments (6)

Collapse
 
gbhorwood profile image
grant horwood

i spent almost two years trying to get the frontend devs in my group interested in using hateoas returns and they were having absolutely none of it. i feel like if we actually want this to become a common component of api design, we're preaching to the wrong people.

Collapse
 
alxgrk profile image
Alexander Girke

Totally agree, imo the problem lies in the adoption on the client side. Tbh, with all the tooling that exists to consume APIs in a non-hateoas-conformant way (looking at Retrofit on Android as an example), it's hard to convince a frontend dev to create a true hateoas client - whatever this means, I've not seen such library anywhere so far.

To give some examples of what I think is missing to improve adoption:

  1. if I use easily guessable URI (like in the post) following the pattern /accounts/{id}, people might think it's easier to just build the URL themselves by pasting the ID - instead of following a link. A solution could be something like opaque URLs.
  2. as long as the documentation published contains a list of all available endpoints (i.e. an OpenAPI spec) and it's possible to generate client-code from that, people will do it and expect to be able to call all endpoints any time - not leveraging the power of links being there or not depending on the context. Maybe documentation should just state the root URL, allowed transitions and maybe the request/response models.

There might be more examples. What I want to say is, I've never found any opinionated client-side tooling/framework that could serve as a blueprint for how frontend devs should consume HATEOAS-conformant APIs. And that's probably the most problematic part regardings it's adoption.

Collapse
 
leob profile image
leob

The theory is great, as with many theories, but who's really using it ... solution in search of a problem?

Collapse
 
bklau2006 profile image
BK Lau • Edited

HATEOAS seems like could be implemented using AI like ChatGPT or something similar.
The problem with HATEOAS is that its passing of control to one of the navigable link used to be driven by a smart human AI: you or me.
How can a next logical link be driven by machine?
Some smart contexts need to be provided at runtime.
That can only mean AI or we hardcoded a limited set of contexts and lots of "if-else" conditions to select the best possible link navigation.

Collapse
 
nfrankel profile image
Nicolas Frankel

AI is far from the answer to every problem

Collapse
 
cubiclesocial profile image
cubiclesocial • Edited

The other major problem with SOAP is that it was always so painfully slow. Every SOAP interface I've ever used ran like molasses. REST runs fast by comparison.*

The problem I see with the _links idea is that every client is required to follow a trail of requests to the resource that the user wants to get to. That violates the principle of just going straight to the destination to get the resource. I also don't really see a problem with incrementing integers. Integer comparison performance is always faster than string comparison performance. When performance matters, every clock cycle matters.

** When I say "REST runs fast by comparison" that doesn't mean REST is actually fast or useful. One of the biggest problems with REST APIs is that they don't handle bulk data transfers very well. Most paginate their results because large JSON consumes a lot of resources. It would be better to have a preamble JSON + each record emitted as its own line of encoded JSON. That way an application could easily dump 10,000 records.