Support for namespace URIs rather than short namespace names was added in
https://github.com/angular/angular/commit/2b9cc8503d48173492c29f5a271b61126104fbdb to
support how Ivy passed around the namespace URI rather than short name at the time.
As a side-effect, this meant that namespace URIs were supported by the
default dom renderer as part of the public API (likely unintentionally).
It did not, however extend the support to other parts of the system (setAttribute, setAttribute,
and the ServerRenderer). In the future we should decide what exactly the
semantics for dealing with namespaces should be and make it consistent.
fixes#44028
PR Close#44914
This commit updates a type used in the transplanted views perf tests, to make the test compatible with strict template type-checking.
Currently, compiling the perf test results in the following TS error:
```
error TS2322: Type 'TemplateRef<{}>' is not assignable to type 'TemplateRef<NgForOfContext<any, any[]>>'.
17 <ng-container *ngFor="let n of views; template: template; trackBy: trackByIndex"></ng-container>
~~~~~~~~
```
PR Close#44905
Currently, `ngModel` calls` setValue` after the `resolvedPromise` is resolved.
The promise is resolved _after_ the child template executes. The change detection
is run but `OnPush` views are not updated because they are not marked as dirty.
PR Close#44886
Previously, some NgModules that were added to the delayed scoping queue, never got removed from the queue before unit test execution. That resulted in some components (declared in those NgModules) missing their scope (which components/directives/pipes were matched).
This commit adds the logic to invoke delayed scoping queue flushing before starting a test to avoid missing/incomplete scopes for Components used in a test.
PR Close#44814
Attempting to run as is fails because we have `"type": "module"`. `shelljs` is a CommonJS module however, so we need to do a default import and destructure.
```
$ node packages/compiler-cli/test/compliance/update_all_goldens.js
const {exec} = require('shelljs');
^
ReferenceError: require is not defined in ES module scope, you can use import instead
This file is being treated as an ES module because it has a '.js' file extension and '/home/douglasparker/Source/ng/packages/compiler-cli/package.json' contains "type": "module". To treat it as a CommonJS script, rename it to use the '.cjs' file extension.
at file:///home/douglasparker/Source/ng/packages/compiler-cli/test/compliance/update_all_goldens.js:11:16
at ModuleJob.run (node:internal/modules/esm/module_job:183:25)
at async Loader.import (node:internal/modules/esm/loader:178:24)
at async Object.loadESM (node:internal/process/esm_loader:68:5)
at async handleMainPromise (node:internal/modules/run_main:63:12)
```
PR Close#44916
Fixes formatting in one of the Zone BUILD files.
The lint check on the renovate branch did not check
formatting as it seems. Needs more investigation as
the PR was green.
PR Close#44911
Previously with ESBuild 0.14.11, when a file had dynamic requires to
builtin NodeJS modules like `url`, the resolution completed successfully
regardless of `--platform browser`. This seems to be fixed in ESBuild now.
This unveiled some resolution errors with our Saucelabs bundle generation
because the framework code sometimes switches dynamically to `require('url')`
if `window.URL` is not defined. Previously this just didn't matter, but now
the `require('url')` is checked and a module resolution error is reported given
`url` not being available in the browser as a builtin module.
We fix this by marking the module as external. We will not hit this code path
anyway in the browser saucelabs code. Similarly we exclude all platform-server
files from the bundle. This is not strictly needed after the `url` module being
marked as external, but the issue showed that lots of unnecessary code for the
server platform is included. This can be omitted (unfortunately not from the TS
compilation without over-complicating things significantly more; experimented with
that).
PR Close#44911
Updates the postinstall patch for the benchmark macro rule from dev-infra.
We moved the ZoneJS setup to the bundler. This was necessary in order to
switch away from the Go-based (windows-incompatible, m1-incompatible)
concatjs devserver to a rather basic HTTP server (also provided by dev-infra now).
PR Close#44911
TypeScript configures `strictNullChecks` to be disabled by default, so the nullish
coalescing check should follow the same default. The rule actively depends on
`strictNullChecks`, as TypeScript doesn't include `null`/`undefined` in its types
otherwise so the check wouldn't have a way to differentiate between them.
This commit also takes the `strict` flag into account when `strictNullChecks` itself
is not configured.
PR Close#44862
Previously, when the notification text did not fit on the viewport
width, it got truncated and it was not possible to see the whole text.
This commit fixes this by making the notification scrollable when the
text overflows.
PR Close#44900
On smaller screens, the action button in `NotificationComponent` is
hidden (due to limited horizontal screen "real estate"). Thus, the only
way to perform the action is to click on the notification message, which
is typically a link.
Previously, the link inside the notification did not take up the whole
height of the notification bar. As a result, clicking outside the link
would dismiss the notification without following the link.
This commit makes it easier to interact with the notification (esp. on
smaller screens) by ensuring the link covers the whole notification bar
(width and height).
PR Close#44900
The initial commit e9124b42d5 stored the errors rather than
throwing but did not store them in a place that was accessible to consumers. Instead,
the errors should be added to the IndexedComponent so they can be surfaced where the
index results are consumed
PR Close#44884
The jasmine types for `spyObj.calls().all()` seem to be more specific,
relying on `ThisType<Fn>` to determine the context/receiver for an invoked
spy. This type does not work as expected with class members as it seems.
This commit fixes three of these type checking failures by explicitly casting
the spy context to the actual class owning the method member.
PR Close#44876
Recently, the [CLI repository][1] switched to not prefixing tag names
with a `v`. Update the `versionInfo` generated for CLI commands docs, so
that the links to the source code (which include the tag name) are
correct.
Fixes#44822
[1]: https://github.com/angular/angular-cli
PR Close#44835
This functionally dead code was originally introduced via pull request
were added to verify the fix, and the many comments on that issue after
it was closed indicate that it wasn't actually resolved.
In fact, setting `selectedIndex` does absolutely nothing here, since
the selected index is immediately overridden by setting the `value`
property. A working fix (with tests) for the IE/Safari bug is in pull
request #23784. Originally this dead code was removed as part of that PR,
but @AndrewKushnir recommended creating a separate PR for the cleanup.
PR Close#37614
The survey id is used as a key in the local storage to keep the state (don't show the message again). Reusing this survey id will make the message invisible to some users who already have that key in local storage.
PR Close#44865
To speed up the components CI job (avoiding it being a bottleneck in FW),
we will stop building everything in `src/...`, but rather only build targets
which are needed to run all tests within `src/...`.
This notably should avoid unnecessary NPM package building. Arguably that
part would also be valuable to have, but we already test the `ng_package`
rule in FW itself, plus we run snapshot tests in the components repo as well.
PR Close#44832
Re-enables the components-repo unit tests job that we previously
disabled due to the devmode target change that caused conflicts
with `angular/components` patching `ng_module.bzl` of `@angular/bazel`.
PR Close#44832
When the indexer encounters a location where the source span doesn't
match up with the expected identifier, the current visitor code throws
an error. Instead, this change creates an error and moves on to the next
template item. This allows the indexer to continue analysis even when
there are errors in the source mapping. In addition, it still allows callers
to surface those errors in their own way while still providing as much indexed
information as possible about a node.
PR Close#44825
It's best to disable this optional migration in the minor release, although it shouldn't run anyway -- we don't want people accidentally running it.
This PR will be rolled back after the minor is out.
PR Close#44828
An `ng-template` with an inline template (i.e. has a structural
directive) would previously not get an `undefined` `tagName` because the
logic assumed the element would be `t.Element` or `t.Content` and read
the tag name from the `name` property. For a `t.Template`, this exists
instead on the `t.tagName`. The final result would be an `tagName` of `undefined`
for the parent `t.Template`, causing failures in the indexer downstream.
This `undefined` value is actually expected in the renderer code, even
though the type does not specify this possibility. This change updates
the type of `tagName` to be `string|null` and explicitly handles the
case where there is a structural directive on an `ng-template`. You can
see how the two are differentiated in the compliance code that was
modified in this commit.
PR Close#44788
Andrew Scott