This change allows ReflectiveInjector to be tree shaken resulting
in not needed Reflect polyfil and smaller bundles.
Code savings for HelloWorld using Closure:
Reflective: bundle.js: 105,864(34,190 gzip)
Static: bundle.js: 154,889(33,555 gzip)
645( 2%)
BREAKING CHANGE:
`platformXXXX()` no longer accepts providers which depend on reflection.
Specifically the method signature when from `Provider[]` to
`StaticProvider[]`.
Example:
Before:
```
[
MyClass,
{provide: ClassA, useClass: SubClassA}
]
```
After:
```
[
{provide: MyClass, deps: [Dep1,...]},
{provide: ClassA, useClass: SubClassA, deps: [Dep1,...]}
]
```
NOTE: This only applies to platform creation and providers for the JIT
compiler. It does not apply to `@Compotent` or `@NgModule` provides
declarations.
Benchpress note: Previously Benchpress also supported reflective
provides, which now require static providers.
DEPRECATION:
- `ReflectiveInjector` is now deprecated as it will be remove. Use
`Injector.create` as a replacement.
closes#18496
Problem description: when using ngTemplateOutlet with context as
an object literal in a template and binding to the context's property
the embedded view would get re-created even if context object remains
essentially the same (the same shape, just update to one properties).
This happens since currently change detection will re-create object
references when an object literal is used and one of its properties
gets updated through a binding.
Solution: this commit changes ngTemplateOutlet logic so we take
context object shape into account before deciding if we should
re-create view or just update existing context.
Fixes#13407
By default, the value and validation status of a `FormControl` updates
whenever its value changes. If an application has heavy validation
requirements, updating on every text change can sometimes be too expensive.
This commit introduces a new option that improves performance by delaying
form control updates until the "blur" event. To use it, set the `updateOn`
option to `blur` when instantiating the `FormControl`.
```ts
// example without validators
const c = new FormControl(, { updateOn: blur });
// example with validators
const c= new FormControl(, {
validators: Validators.required,
updateOn: blur
});
```
Like in AngularJS, setting `updateOn` to `blur` will delay the update of
the value as well as the validation status. Updating value and validity
together keeps the system easy to reason about, as the two will always be
in sync. It's also worth noting that the value/validation pipeline does
still run when the form is initialized (in order to support initial values).
Closes#7113
The static reflectory check for macro function recursion was too
agressive and disallowed calling a function with argument that also
calls the same function. For example, it disallowed nested animation
groups.
Fixes: #17467
FormControls, FormGroups, and FormArrays now optionally accept an options
object as their second argument. Validators and async validators can be
passed in as part of this options object (though they can still be passed
in as the second and third arg as before).
```ts
const c = new FormControl(, {
validators: [Validators.required],
asyncValidators: [myAsyncValidator]
});
```
This commit also adds support for passing arrays of validators and async
validators to FormGroups and FormArrays, which formerly only accepted
individual functions.
```ts
const g = new FormGroup({
one: new FormControl()
}, [myPasswordValidator, myOtherValidator]);
```
This change paves the way for adding more options to AbstractControls,
such as more fine-grained control of validation timing.
Angular can make many assumptions about its event handlers. As a result
the bookkeeping for native addEventListener is significantly cheaper
than Zone's addEventLister which can't make such assumptions.
This change bypasses the Zone's addEventListener if present and always
uses the native addEventHandler. As a result registering event listeners
is about 3 times faster.
PR Close#18107
In previous version of tsickle abstract class methods were materialized.
The change resulted in 6Kb savings in angular.io bundle.
This change also required the removal of `@private` and `@return` type
annotation as it is explicitly dissalowed by tsickle.
NOTE: removed casts in front of `makeDecorator` due to:
https://github.com/angular/devkit/issues/45
```
14938 Jul 19 13:16 0.b19e913fbdd6507d346b.chunk.js
1535 Jul 19 13:16 inline.d8e019ea3cfdd86c2bd0.bundle.js
589178 Jul 19 13:16 main.54c97bcb6f254776b678.bundle.js
34333 Jul 19 13:16 polyfills.4a3c9ca9481d53803157.bundle.js
14938 Jul 18 16:55 0.b19e913fbdd6507d346b.chunk.js
1535 Jul 18 16:55 inline.0c83abb44fad9a2768a7.bundle.js
582786 Jul 18 16:55 main.ea290db71b051813e156.bundle.js
34333 Jul 18 16:55 polyfills.4a3c9ca9481d53803157.bundle.js
main savings: 589178 - 582786 = 6,392
```
PR Close#18236
In Node.JS console.log/error/warn functions actually resuls in a socket
write which in turn is considered by Zone.js as an async task.
This means that if there is any exception during change detection in a platform-server
application the error handler will make the Angular Zone unstable which
in turn will cause change detection to run on next tick and cause an
infinite loop.
It is also better to run the error handler outside of the Angular Zone
in general on all platforms so that an error in the error handler itself doesn't cause an
infinite loop.
Fixes#17073, #7774.
PR Close#18269
Note 4.3 only!
Prior to this fix when [@.disabled] was used in a component that
contained zero animation code it wouldn't register properly because the
renderer associated with that component was not an animation renderer.
This patch ensures that it gets registered even when there are no
animations set.
Note 4.3 only!
Prior to this fix when [@.disabled] was used in a component that
contained zero animation code it wouldn't register properly because the
renderer associated with that component was not an animation renderer.
This patch ensures that it gets registered even when there are no
animations set.
HttpClient is an evolution of the existing Angular HTTP API, which exists
alongside of it in a separate package, @angular/common/http. This structure
ensures that existing codebases can slowly migrate to the new API.
The new API improves significantly on the ergonomics and features of the legacy
API. A partial list of new features includes:
* Typed, synchronous response body access, including support for JSON body types
* JSON is an assumed default and no longer needs to be explicitly parsed
* Interceptors allow middleware logic to be inserted into the pipeline
* Immutable request/response objects
* Progress events for both request upload and response download
* Post-request verification & flush based testing framework
`Object.assign` is not available in all supported browsers and one had to
provide a polyfill. This commit replaces `Object.assign` with the spread
operator (`...`), which TypeScript will transpile to ES5-compatible code.
(#17971)
This commit changes the dynamic version of ngUpgrade to use `UpgradeHelper`,
thus bringing its behavior (wrt upgraded components) much closer to
`upgrade/static`. Fixes/features include:
- Fix template compilation: Now takes place in the correct DOM context, instead
of in a detached node (thus has access to required ancestors etc).
- Fix support for the `$onInit()` lifecycle hook.
- Fix single-slot transclusion (including optional transclusion and fallback
content).
- Add support for multi-slot transclusion (inclusing optional slots and fallback
content).
- Add support for binding required controllers to the directive's controller
(and make the `require` behavior more consistent with AngularJS).
- Add support for pre-/post-linking functions.
(This also ports the fixes from #16627 to the dynamic version.)
Fixes#11044
(#17971)
Although, pre- and post-linking functions are correctly called during directive
linking, directives with `link.post` would throw an error. Interestingly, having
`link.pre` only or defining `link: fn` (which is an alias for `link.post: fn`)
would not throw.
This commit removes this check and allows directives with pre- and/or
post-linking functions to work.
Previously, only simple, single-slot transclusion worked on upgraded components.
This commit fixes/adds support for the following:
- Multi-slot transclusion.
- Using fallback content when no transclusion content is provided.
- Destroy unused scope (when using fallback content).
Fixes#13271
- /deep/ is deprecated and being removed from Chrome
- >>> is semantically invalid in a stylesheet
- sass will no longer support either in any version of sass
-> use ::ng-deep in emulated shadow DOM mode
Because the deep combinator is deprecated in the CSS spec,
`/deep/`, `>>>` and `::ng-deep` are also deprecated in emulated shadow DOM mode
and will be removed in the future.
see https://www.chromestatus.com/features/6750456638341120
Destructuring of the form:
function foo({a, b}: {a?, b?} = {})
breaks strictNullChecks, due to the TypeScript bug https://github.com/microsoft/typescript/issues/10078.
This change eliminates usage of destructuring in function argument lists in cases where it would leak
into the public API .d.ts.
toString() from DefaultKeyValueDiffer is only used in tests and should not
be part of the production code. toString() methods from differs add
~ 0.3KB (min+gzip) to the production bundle size.
With 4.2, we introduced the min and max validator directives. This was actually a breaking change because their selectors could include custom value accessors using the min/max properties for their own purposes.
For now, we are rolling back the change by removing the exports. At the least, we should wait to add them until a major version. In the meantime, we will have further discussion about what the best solution is going forward for all validator directives.
Closes#17491.
----
PR #17551 tried to roll this back, but did not remove the dead code. This failed internal tests that were checking that all declared directives were used.
This PR rolls back the original PR and commit the same as #17551 while also removing the dead code.
With 4.2, we introduced the min and max validator directives. This was actually a breaking change because
their selectors could include custom value accessors using the min/max properties for their own purposes.
For now, we are rolling back the change by removing the exports.
Closes#17491.