4e31a4e38d
Currently, all backend integration tests transitively depend on the client bundle. This results in rebuilds of the closure, and a (likely) cache miss on the test, when modifying any client-side files.
Given that the client bundle isnt needed for these tests, we can create targets that don't include the client bundle in its transitive closure, which should in theory improve the cache hit for backend integration tests by not having client side changes invalidate it. This would also be beneficial in local env, to keep frontend rebuilds down
To do this, we still need to create a `web.manifest.json` file due to some unfortunate requirement on that file existing as part of initializing the sourcegraph instance. For this I just create an empty json file, `select` this instead of the client bundle target in client/web/dist/BUILD.bazel based on a `//:integration_testing_enabled` config setting, and creating a `go_binary`-wrapping bazel rule + macro that automatically applies a transition to set this to true `go_binary_nobundle`, and using that rule for the specific `//cmd/{server,frontend}:{server,frontend}_nobundle` binary rules (along with the relevant `oci_{image,tarball}` etc rules to consume it).
## Test plan
- Integration tests in CI still work
- `bazel cquery 'kind("js_library", deps(//cmd/frontend:image_nobundle))'`, `bazel cquery 'kind("js_library", deps(//cmd/server:image_nobundle))'`, ``bazel cquery 'kind("js_library", deps(//testing:backend_integration_test))'` etc all return empty set
- Release test with marker in web bundle to ensure released images contain the web bundle via `sg release run test --version 5.4.2` (commenting out other tests for brevity)
|
||
|---|---|---|
| .. | ||
| branded | ||
| browser | ||
| build-config | ||
| client-api | ||
| codeintellify | ||
| cody-context-filters-test-dataset | ||
| cody-shared | ||
| cody-ui | ||
| common | ||
| eslint-plugin-wildcard | ||
| extension-api | ||
| extension-api-types | ||
| http-client | ||
| jetbrains | ||
| observability-client | ||
| observability-server | ||
| shared | ||
| storybook | ||
| template-parser | ||
| testing | ||
| vscode | ||
| web | ||
| web-sveltekit | ||
| wildcard | ||
| BUILD.bazel | ||
| README.md | ||
Frontend packages
List
- web: The web application deployed to http://sourcegraph.com/
- browser: The Sourcegraph browser extension adds tooltips to code on different code hosts.
- vscode: The Sourcegraph VS Code extension.
- extension-api: The Sourcegraph extension API types for the Sourcegraph extensions. Published as
sourcegraph. - extension-api-types: The Sourcegraph extension API types for client applications that embed Sourcegraph extensions and need to communicate with them. Published as
@sourcegraph/extension-api-types. - sandboxes: All demos-mvp (minimum viable product) for the Sourcegraph web application.
- shared: Contains common TypeScript/React/SCSS client code shared between the browser extension and the web app. Everything in this package is code-host agnostic.
- branded: Contains React components and implements the visual design language we use across our web app and e.g. in the options menu of the browser extension. Over time, components from
sharedandbrandedpackages should be moved into thewildcardpackage. - wildcard: Package that encapsulates storybook configuration and contains our Wildcard design system components. If we're using a component in two or more different areas (e.g.
web-appandbrowser-extension) then it should live in thewildcardpackage. Otherwise the components should be better colocated with the code where they're actually used. - search: Search-related code that may be shared between all clients, both branded (e.g. web, VS Code extension) and unbranded (e.g. browser extension)
- storybook: Storybook configuration.
Further migration plan
-
Fix circular dependency in TS project-references graph wildcard package should not rely on web and probably shared, branded too. Ideally it should be an independent self-contained package.
-
Decide on package naming and update existing package names. Especially it should be done for a shared package because we have multiple
sharedfolders inside of other packages. It's hard to understand from where dependency is coming from and it's not possible to refactor import paths using find-and-replace. -
Investigate if we can painlessly switch to
npmworkspaces. -
Content of packages shared and branded should be moved to wildcard and refactored using the latest FE rules and conventions. Having different packages clearly communicates the migration plan. Developers first should look for components in the wildcard package and then fall-back to legacy packages if wildcard doesn't have the solution to their problem yet.
-
shared contains utility functions, types, polyfills, etc which is not a part of the Wildcard component library. These modules should be moved into utils package and other new packages: e.g. api for GraphQL client and type generators, etc.
-
Packages should use package name (e.g.
@sourcegraph/wildcard) for imports instead of the relative paths (e.g.../../../../wildcard/src/components/Markdown) to avoid long relative-paths and make dependency graph between packages clear. (Typescript will warn if packages have circular dependencies). It's easy to refactor such isolated packages, extract functionality into new ones, or even into new repositories.