`AsyncTestZoneSpec` triggers jasmine `done()` function multiple times
and causes warning
```
An asynchronous function called its 'done' callback more than once. This is a bug in the spec, beforeAll, beforeEach, afterAll, or afterEach function in question. This will be treated as an error in a future version. See<https://jasmine.github.io/tutorials/upgrading_to_Jasmine_4.0#deprecations-due-to-calling-done-multiple-times> for more information
```
The reproduce case will be running some `Zone.run()` inside
`waitForAsync()`.
```
it('multiple done', waitForAsync(() => {
Zone.current.run(() => {});
Zone.current.run(() => {});
}));
```
The reason the `done()` is called in the `onInvoke()` hook is to handle
the case that the testBody is totally sync, but we should only do this
check for the entry function not for all `Zone.run()` scenario.
Another issue is if we run nested zone inside `waitForAsync()`, the
`onHasTask()` hook will be triggered multiple times, and cause `done()`
be triggered multiple times, so we need to only trigger the `done()`
when the zone is `AsyncTestZone`.
PR Close#45025
Before Ivy, it was only possible to call the `ViewContainerRef.createComponent` function with the ComponentFactory as the first argument. An instance of a `ComponentFactory` resolved via `ComponentFactoryResolver` contained a reference to an `NgModule` where the component is declared. As a result, the component maintained a DI connection with the module injector tree (by retrieving an instance of `NgModuleRef` internally), even when the custom injector was provided (we try to find a token in a custom injector first and consult module injector after that).
With Ivy, we expanded the `ViewContainerRef.createComponent` function API to support direct references to the Component classes without going through the factory resolution step. As a result, there was no connection to the NgModule that declares the component. Thus, if you provide a custom injector, this is the only injector that is taken into account.
This commit updates the logic for the factory-less case to try retrieving an instance of an `NgModuleRef` using the DI tree which `ViewContainerRef` belongs to. The `NgModuleRef` instance is then used to get a hold of a module injector tree. This brings the factory-less and factory-based logic to more consistent state.
Closes#44897.
PR Close#44966
In templates with several levels of nested nodes, it's common for several `elementStart`/`elementEnd` instructions to show up in a row which can be optimized away.
These changes add chaining support for `elementStart`, `elementEnd`, `elementContainerStart` and `elementContainerEnd` to shave off some bytes when possible.
PR Close#44994
Previously the logic for generating chained instructions was somewhat rigid, because we had to collect all of the calls ahead of time and then call one of the chained instruction helpers. This doesn't work for something like `elementStart`, because we have to descend into other elements that could add to the chain.
These changes refactor the code so that we collect the list of instructions in a flat array and we do the chaining only once at the end when we have the entire instruction set for the code block.
The new approach has the advantage of being (almost) entirely configuration-based via the `CHAINABLE_INSTRUCTIONS` array and being more flexible in allowing us to chain instructions that span across elements.
PR Close#44994
This commit updates various places in the repo (mostly tests/examples) to drop all `.ngfactory` and `.ngsummary` imports as they are no longer needed in Ivy.
PR Close#44957
When an `NgModel` is created within a `form`, it receives an `NgControl` based on its `name`, but
the control doesn't get swapped out if the name changes. This can lead to problems if the `NgModel`
is part of an `ngFor`, because the name can change based on its position in the list and a new
control can be defined with the same name, leading us to having multiple directives pointing to
the same control. For example, if we start off with a list like :
```
[0, 1, 2]; -> [NgModel(0), NgModel(1), NgModel(2)]
```
Then we remove the second item:
```
[0, 2]; -> [NgModel(0), NgModel(2)]
```
And finally, if we decide to add an item to the end of the list, we'll already have a control for
index 2, causing the list to look like:
```
[0, 2, 3]; -> [NgModel(0), NgModel(2), NgModel(2)]
```
These changes fix the issue by removing the old control when the `name` of the directive changes.
Fixes#38465.
Fixes#37920.
PR Close#40459
This commit updates the `PatternValidator` class to inherit `AbstractValidatorDirective` to make it conistent with other validators.
Closes angular#42267
PR Close#44887
BREAKING CHANGE: Forms [email] input coercion
Forms [email] input value will be considered as true if it is defined with any value rather
than false and 'false'.
PR Close#42803
For two-way-bindings that use the banana-in-a-box syntax, the compiler
synthesizes an event assignment expression from the primary expression.
It is valid for the primary expression to be terminated by the non-null
operator, however naive string substitution is used for the synthesized
expression, such that the `!` would immediately precede the `=` token,
resulting in the valid `!=` operator token. The expression would still
parse correctly but it doesn't implement the proper semantics, resulting
in incorrect runtime behavior.
Changing the expression substitution to force a space between the
primary expression and the assignment avoids this mistake, but it
uncovers a new issue. The grammar does not allow for the LHS of an
assignment to be the non-null operator, so the synthesized expression
would fail to parse. To alleviate this, the synthesized expression is
parsed with a special parser flag to allow for this syntax.
Fixes#36551
PR Close#37809
This commit updates `DebugNode` and `DebugElement` implementaitons to cleanup ViewEngine removal artifacts. There is no need for a separate interface and implementation class, so we can combine them now. This comment also gets rid of `R3` suffixes (denoting Ivy) in helper methods.
PR Close#44270
Since According to ISO8601 the Year is minimum of 4 digits, we should support years greater than 9999. (This is similar to the change in input.js: e157d6fa69)
Changed /^(\d{4}) to /^(\d{4,})
PR Close#43622
Form required validator should not reject objects that contain a length attribute set to zero.
Fixes#30718.
Co-authored-by: Dylan Hunn <dylhunn@gmail.com>
BREAKING CHANGE: objects with a length key set to zero will no longer validate as empty.
This is technically a breaking change, since objects with a key `length` and value `0` will no longer validate as empty. This is a very minor change, and any reliance on this behavior is probably a bug anyway.
PR Close#33729
Make `StateKey` typesafe by narrowing the type.
BREAKING CHANGE: This may break invalid calls to `TransferState` methods.
This tightens parameter types of `TransferState` usage, and is a minor breaking change which may reveal existing problematic calls.
PR Close#23020
BREAKING CHANGE:
* The type of `initialUrl` is set to `string|UrlTree` but in reality,
the `Router` only sets it to a value that will always be `UrlTree`
* `initialUrl` is documented as "The target URL passed into the
`Router#navigateByUrl()` call before navigation" but the value
actually gets set to something completely different. It's set to the
current internal `UrlTree` of the Router at the time navigation
occurs.
With this change, there is no exact replacement for the old value of
`initialUrl` because it was enver intended to be exposed.
`Router.url` is likely the best replacement for this.
In more specific use-cases, tracking the `finalUrl` between successful
navigations can also be used as a replacement.
PR Close#43863
fix the transition function accepting a delay in its AnimationOptions
input but not acting on it by adding such delay to all the transition's
timelines
(note: adding the delay to all the transition's timelines is the only
way to accomplish this since transitions have their own logic and do not
have their own timelines like other animation functions have)
resolves#29762
PR Close#44799
This commit implements the first phase of standalone components in the Angular
compiler. This mainly includes the scoping rules for standalone components
(`@Component({imports})`).
Significant functionality from the design is _not_ implemented by this PR,
including:
* imports of standalone components into NgModules.
* the provider aspect of standalone components
Future commits will address these issues, as we proceed with the design of
this feature.
PR Close#44812
In preparation for standalone components, this commit moves the logic which
determines the potential set of components/directives/pipes in a template into
a separate function. This is a simple but crucial refactoring that breaks the
assumption that all template scopes come from NgModules.
PR Close#44812
Previously each `DecoratorHandler` in the compiler was stored in a single file
in the 'annotations' package. The `ComponentDecoratorHandler` in particular was
several thousand lines long.
Prior to implementing the new standalone functionality for components, this
commit refactors 'annotations' to split these large files into their own build
targets with multiple separate files. This should make the implementation of
standalone significantly cleaner.
PR Close#44812
Refs http://b/214103351.
This happens if a user writes `<span i18n>Message</span>`. This is accepted as an internationalized message, but without a description. JSCompiler will throw an error in this situation because descriptions are generally required. Now, the Angular compiler will generate a suppression annotation so JSCompiler allows the syntax. This will ease an internal migration to JSCompiler-based i18n.
PR Close#44787
This code mimics behavior that Google Analytics has been using to
prevent duplicate navigations. They set up their own `HybridRoutingService`
location sync to avoid duplicate navigations that came from the Angular
router. This would happen because the Angular router would trigger a
navigation, which would then get picked up by the `$locationShim`, which
would trigger a `$locationChangeStart`, which would then be picked up by
the `setUpLocationSync` watcher here, which would again trigger a
navigation in the Angular Router.
All of this can be prevented by checking if the `navigationId` exists on
the history state object. This property is added by the Angular router
during navigations.
fixes#21610
PR Close#43441
This updates the router upgrade tests to use less mocked behavior. The
test upgrade location module is copied from the one that's used in the
common package. This update to the tests verifies more real behavior of
the upgrade module.
PR Close#43441
The Hammer.JS might be loaded asynchronously if the `HAMMER_LOADER` token is provided.
Its loading causes additional change detection cycles when the script `load` event is fired
and the `import()` promise resolves. Its loading doesn't have to require Angular running `tick()`
since the Hammer instance is created outside of the Angular zone anyway.
BREAKING CHANGE:
This change may cause a breaking change in unit tests that are implicitly depending on a specific
number and sequence of change detections in order for their assertions to pass.
PR Close#44921
The logical filesystem would store a cached result based on the canonical path,
where the cached value contains the physical path that was originally provided.
This meant that other physical paths with an identical canonical path would use
a cached result derived from another physical path.
This inconsistency is not known to result in actual issues but is primarily
being made as a performance improvement, as using the provided physical paths
as cache key avoids the need to canonicalize the path if its result is already
cached.
PR Close#44798
The generated imports should normally use module specifiers that are valid for
use in production code, where arbitrary relative imports into e.g. node_modules
are not allowed. For template type-checking code it is however acceptable to
use relative imports, as such files are never emitted to JS code. It is
desirable to allow a filesystem relative import as fallback if an import would
otherwise fail to be generated, as doing so allows fewer situations from
needing an inline type constructor.
PR Close#44798
This commit removes the leftover `Identifiers` class that was used in the
ViewEngine compiler. The remaining usages of the `inlineInterpolate` and
`interpolate` instructions were refactored to make use of an
`InterpolationExpression` output expression to capture the argument list of an
interpolation expression. An attempt was made to refactor this further by
converting to the desired interpolation instruction immediately, but some
downstream consumers are designed in a way where the argument list itself is
needed, e.g. as other arguments need to be prepended/appended.
PR Close#44676
When `HttpTestingController.verify` is used to verify that there are not open,
unexpected requests it would throw an error with the method and URL of all pending
requests, excluding the query parameters. This is confusing, as e.g. `expectOne`
matches a URL including its query parameters and `expectOne` does include the
query parameters when it reports when no request could be matched.
This commit changes the error that is reported by `verify` to include the query
parameters.
Closes#19974
PR Close#44917
This commit updates the logic of the `NgComponentOutlet` class to allow passing an `NgModule` as an input instead of passing an `NgModule` factory.
DEPRECATED:
The `ngModuleFactory` input of the `NgComponentOutlet` directive is deprecated in favor of a newly added `ngModule` input. The `ngModule` input accepts references to the NgModule class directly, without the need to resolve module factory first.
PR Close#44815
When using `ng update` users cannot update multiple major versions at the same time. Therefore migrations that are not targeting version 14 cannot be run and therefore we are removing them.
PR Close#44857
This commit refactors the `RuntimeError` class to support a short version of providing error messages:
```
throw new RuntimeError(
RuntimeErrorCode.INJECTOR_ALREADY_DESTROYED,
ngDevMode && 'Injector has already been destroyed.');
```
In prod mode, the second argument becomes `false` andn this commit extends the typings to support that.
This commit also contains a couple places were the `RuntimeError` class is used to demostrate the compact form.
PR Close#44783
So-called "Quote expressions" were added in b6ec2387b3
to support foreign syntax to be used in Angular templates, requiring a custom
template transform to convert them somehow during compilation. Support for template
transforms was originally implemented in a43ed79ee7 but
has since been dropped. Since the compiler is not public API the quote expressions
should not have any usages anymore. Removing support for them can improve error
reporting for expressions that contain a `:`, e.g. binding to a URL without quotes:
```html
<a [href]="http://google.com">Click me</a>
```
Here, `http` would be parsed as foreign "http" quote expression with `//google.com` as
value, later reporting the error "Quotes are not supported for evaluation!" because
there was no template transform to convert that code.
Closes#40398
PR Close#44915
This implementation change was originally proposed as part of Typed Forms, and will have major consequences for that project as described in the design doc. Submitting it separately will greatly simplify the risk of landing Typed Forms. This change should have no visible impact on normal users of FormControl.
See the Typed Forms design doc here: https://docs.google.com/document/d/1cWuBE-oo5WLtwkLFxbNTiaVQGNk8ipgbekZcKBeyxxo.
PR Close#44316
PR Close#44806
Support for namespace URIs rather than short namespace names was added in
2b9cc8503d 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
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
