test(web): strengthen nuqs testing infrastructure and documentation#32340
Conversation
dosubot
Bot
added
the
size:L
Summary of ChangesHello @lyzno1, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the testing infrastructure for Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a standardized testing infrastructure for nuqs hooks, which is a great initiative to reduce boilerplate and ensure consistency. The changes include a new shared testing utility, migration of existing tests to use this utility, and comprehensive documentation updates. My review focuses on improving the new utility and ensuring consistency in the documentation examples. Overall, this is a solid improvement for the project's testing practices.
…ore/nuqs-testing-infra-hardening
b27b346
into
refactor/datasets-document-list-nuqs-migration
|
|
||
| // Render helper wrapping with NuqsTestingAdapter | ||
| // Render helper wrapping with shared nuqs testing helper. | ||
| const onUrlUpdate = vi.fn<(event: UrlUpdateEvent) => void>() |
There was a problem hiding this comment.
onUrlUpdate is created at the top level of the module and shared across all tests. However, there is no beforeEach(() => onUrlUpdate.mockClear()) to reset it, which could lead to state leakage between tests.
| default: () => <div data-testid="search-box-wrapper">SearchBoxWrapper</div>, | ||
| })) | ||
|
|
||
| const { wrapper: NuqsWrapper } = createNuqsTestWrapper() |
There was a problem hiding this comment.
same thing. it would be better to create in beforeEach
2 participants
Problem
nuqshooks require an adapter in tests, but our test setup was inconsistent: many specs used ad-hoc wrappers, URL sync assertions were uneven, and docs/skill guidance did not fully encode the same testing model.Decision
Standardize
nuqstesting around one shared helper and align project guidance with that approach.Model
web/test/nuqs-testing.tsxas the canonical test utility:createNuqsTestWrapperrenderWithNuqsrenderHookWithNuqs(includinginitialPropssupport)NuqsTestingAdapterusage to shared helpers (apps, datasets, explore, marketplace, tools, context, hooks).web/docs/test.mdandfrontend-testingskill references to require adapter-based URL-state testing andonUrlUpdateassertions.Impact
Validation
cd web && pnpm type-check:tsgo