improve the error message for non-standalone components which are not
exported from their module, and that are also imported directly as if
they were standalone
this change simply adds the suggestion to the developer to import the
ngModule instead
resolves#46004
PR Close#46114
* Adds a short note about how service workers report request timeouts
* Updated heading levels to present a clearer hierarchy and cleaner local TOC
* Removed documentation lint errors
* Moves the service worker service timeout paragraph to a more logical topic in service-worker-devops
* Removes line error from the more logical topic.
* address feedback from PR review comments
fixes#46445
PR Close#46882
The source map tests rely on asynchronous logic from the `source-map`
package. The tests itself are written using `fakeAsync` but this
unnecessarily complicates the interaction with the asynchronous
source-map helpers/package.
To fix this, we just make the tests use async/await as we don't intend
to test fakeAsync in this `describe` block..
PR Close#46888
The sourcemap test in the e2e playground is now using async/await code.
This results in errors now with the Bazel TS compilation because it
detects that `expect` is returning a promise and should be awaited.
This happens due to the jasminewd2 types. We should just use the actual
jasmine types and not rely on the deprecated selenium control flow,
using explicit async/await in the whole test. This also solves the issue
with the source-map types being async/await now.
PR Close#46888
The source-map package now requires the
`SourceMapConsumer`/`SourceMapGenerator` classes to be instantiated
asynchronously. This commit updates our tests to account for that.
PR Close#46888
The source-map package is no longer explicitly used in the
`compiler-cli` package and therefore can be removed from the ESBuild
bundling, denoting it as external. This should be a noop.
PR Close#46888
The source-map package is updated as part #46707, but the minor
version bump introduced breaking changes. This commit extracts the
update so that we can handle it separately accounting for the breaking
changes. Also removing the caret since this package apparently makes
breaking changes in minor segment bumps.
PR Close#46888
The implementation of the `DefaultTitleStrategy` was modeled after the
existing strategy patterns in the Router. These patterns were developed
before the `providedIn` syntax for injectables. We can simplify the
model a lot by providing the default in the factory of the abstract
class.
Note that the other strategy patterns aren't touched in this PR due to
how long they've existed. Because they have been there for such a long
time, it's possible there will need to be some adjustments to code
if/when they are refactored to do the same.
PR Close#46876
style values get added to the `_globalTimelineStyles` map in order to keep
them so that they can be used across different timelines
`_globalTimelineStyles` was previously a plain object but has been
refactored to a map in #44482, as part of the update a check has been
changed from a ternary operation to an or (||), causing falsy values (as 0)
not to be added to the map anymore, apply the nullish coalescing operator (??)
instead to make sure only `undefined` and `null` are filtered out
also since this aspect was clearly not covered by tests, add a new test
to ensure that such regression doesn't happen in the future
resolves#46833
PR Close#46863
There are some ZoneJS tests that fork the zone from the `describe` block
for testing the zone patching. This does cause the Jasmine `done`
function later in `it` specs to be invoked in the sync-test zone from
the original `describe` block. The `done` implementation now has
changed with the Karma Jasmine update and breaks because it now causes
tasks to be scheduled.
It is conceptually incorrect/invalid to take the describe sync zone and
run test logic with that sync zone.
```
An error was thrown in afterAll
error properties: Object({ originalStack: 'Error: Cannot call jasmine.execute().forceTask from within a sync test (syncTestZone for jasmine.describe#FileReader).
at new ZoneAwareError (packages/zone.js/test/browser_test_rollup.umd.js:98:37)
at e.onScheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:158:196)
at e.scheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:7529)
at t.scheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:3539)
at t.scheduleMicroTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:3791)
at r.execute (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:166:4312)
at queueRunnerFa ...
at <Jasmine>
```
As mentioned in the previous commit that ensured that the Zone name is
included in errors raised by the `SyncTestZoneSpec`, we can now include
the Jasmine describe block descriptions in such errors.
Errors can often happen when users accidentally try to set up Angular
tests without an `it` block. Resulting in errors where it's not clear
at all which describe block (of potentially a large repository) is
involved:
```
An error was thrown in afterAll
error properties: Object({ originalStack: 'Error: Cannot call XX from within a sync test.
at new ZoneAwareError (packages/zone.js/test/browser_test_rollup.umd.js:98:37)
at e.onScheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:158:196)
at e.scheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:7529)
at t.scheduleTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:3539)
at t.scheduleMicroTask (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:14:3791)
at r.execute (packages/zone.js/bundles/zone-testing-bundle.umd.min.js:166:4372)
at queueRunnerFa ...
at <Jasmine>
```
We now include the describe block description in the error, so that it
is easier to figure out the location of the culprit code.
The sync-test zone is used in e.g. `describe` to raise an error when
there is asynchronous code scheduled in describe blocks. This commit
includes the zone name in such thrown errors to allow for us to include
the jasmine describe name in the error. This will be wired up in the
jasmine zonejs patches separately.
In the fake async test for `zone.js` there is some logic to test various
prefixes of the request animation frame functions. This logic does not
have any effect currently, except for generating the same test at
maximum three times.
This commit fixes the test to actually test what it meant to do
initially.
Karma jasmine updated the `jasmine-core` dependency. Jasmine is now more
strict when:
* The done callback is invoked multiple times
* The done callback is used, while a promise is also returned
* The done callback is treated as error when e.g. a number is returned
as first argument. This was the case with `requestAnimationFrame`.
Currently tests written using `waitForAsync` would be prone to Jasmine
warnings or errors (depending on the version) for tests incorrectly
invoking asynchronous jasmine `done` callbacks multiple times.
This can happen because the async test zone logic schedules the
`done` callback to be called using `setTimeout`, but this could
be invoked multiple times, causing multiple `done` invocations to
be scheduled. Most of the issues have been resolved with #45025,
but it does not solve the case of multiple tasks finished and callbacks
being scheduled.
Technically, the current logic is built in way that _should_ result in
`_finishCallbackIfDone` and eventually the `done` callback to be invoked
at maximium once. This is unfortunately not the case in some rather
advanced/unexpected scenarios (like our AngularJS upgrade tests) where
the scenario is the following (and microtasks from before the actual
`waitForAsync` spec are still completing -- which is valid):
```
1. A test `beforeEach` schedules a microtask in the ProxyZone.
2. An actual empty `it` spec executes in the AsyncTestZone` (using e.g. `waitForAsync`).
3. The `onInvoke` invokes `_finishCallbackIfDone` because the spec runs synchronously.
4. We wait the scheduled timeout (see below) to account for unhandled promises.
5. The microtask from (1) finishes and `onHasTask` is invoked.
--> We register a second `_finishCallbackIfDone` even though we have scheduled a timeout.
--> we execute the `done` callback twice because the async zone spec state is "stable"
```
With the recent lock file maintenance, the `@types/angular` dependency
ended up being duplicated. This seems to happen because we locked our
type dependency, but other Angular deps like `angular-route` had a
looser dependency, resulting in e.g. `1.7` types and `1.8` types to be
loaded.
This ultimately ended up breaking TypeScript's auto-discovering
of types and broke some example compilations e.g.
```
app/app.animations.ts(3,3): error TS2339: Property 'animation' does not exist on type 'IModule'.
app/app.config.ts(5,45): error TS2694: Namespace 'angular' has no exported member 'route'.
app/phone-detail/phone-detail.component.ajs.ts(10,37): error TS2694: Namespace 'angular' has no exported member 'route'.
```
We fix this by loosening the type dependency ranges, updating all of
these. Also we update AngularJS itself to the final version.
PR Close#46840
The AIO payload size has been reduced with lock file maintenance which
resulted in updates of Angular framework and Angular devkit/CLI.
The same reduction is already visible in the `aio-local` job because
it was already using the latest FW packages (obviously -- given it being
from HEAD).
PR Close#46840
Currently if the `ENVIRONMENT_INITIALIZER` token is not configured with `multi: true` flag, the code fails while trying to iterate over the value. This commit checks whether the `ENVIRONMENT_INITIALIZER` token value type is an array and throws a helpful error message.
PR Close#46829
The `Directive` and `Component` decorators support `inputs` and `outputs` fields which accept an array in the format of `"someInput"` or `"someInput: someAlias"`, however the parsing during JIT compilation was splitting on commas, not on colons, which resulted in incorrect parsing. E.g. `inputs: ["someInput: someAlias"]` was being parsed into `{"someInput: someAlias": "someInput: someAlias"}` instead of `{someInput: "someAlias"}`.
The feature was working by accident, because there's some logic further down in the compiler pipeline that was splitting the strings again.
PR Close#46813
move the check for non-animatable properties from the animation building
phase to the application of the animation's transition instead, in such
a way we can check it against the keyframes of the transition's timeline
in order to only provide warnings for properties which are being
animated, thus not providing any warning for non-animatable properties
being applied to elements via the style function
this change has the benfit just mentioned above but it comes with two
drawbacks:
- the warning handling is not done in the building time so it is a bit
inconsistent with other type of validations (such as the unsupported css
properties one for example)
- before the warning was being applied only when the animation's data
was being parsed, so it happed only once but now since it is applied
when the animation is actually being prepared to be played, it happens
each time the animation runs
resolves#46602
PR Close#46666
After a bugfix in #46096, the compiler is now better capable of detecting pipes
which require an inline type constructor. However, there is an issue in how all
pipes are considered when verifying the inline type-ctor requirement: it should
only check actually used pipes.
Fixes#46747
PR Close#46807
Most of the increase comes from code being moved from `index.html`
to the main bundle. A small increase comes from the additional `gtag.js`
loading logic, but other than that the size is effectively increased
due to the untracked code from `index.html` being moved into the
`main.js` bundle.
PR Close#46801
This is acceptable because `gtag.js` is also only loaded as part of the
service, similary `ga` is only registered in the service (so the
reporting was a noop if errors are thrown before -- no change here)
We can benefit from downleveling etc. and do not need to be careful
with the inline script in the `index.html`
PR Close#46801
We currently use Universal Analytics. This is deprecated in favor of
Google Analytics 4 and UA will stop processing hits in October 2023.
This change intends to prepare us for this migration, and to already
pre-populate our GA4 property (there is no way to migrate existing data
/properties into a GA4 property -- a new one needs to be created).
This will help us minimize the data gap so that we can:
* Continue to look at the UA property with the full time span until
October 2023
* Can start using the GA4 property long-term in the future, starting
with data even before Universal Analytics stops processing new data.
We need to keep the existing `analytics.js` setup. Initially we have
considered using `gtag.js` for both the UA and GA4 properties, as it
supports that, but that doesn't work with our strict trusted types
enforcement because it results in multiple `gtag.js` scripts (specific
versions for UA or GA4) that recreate the same trusted type policies.
This causes runtime errors and breaks the setup.
Instead, with continued use of `analytics.js` we have the benefit of
a good separation of trusted types + events and configuration. There is
some problematic with translation of Universal Analytics Events to GA4,
or the other way around (even though we don't use custom events
currenlty)
We also do not need to send page views for our GA4 property because GA4
with gtag supports this automatically (respecting the history state --
using the `Enhanced measurement events` setting in the UI).
For our UA legacy instance we continue to dispatch events manually. This
logic can be removed in the future.
More details can be found here:
https://docs.google.com/document/d/1aK8u4ZlXbqQ2wMqmgSX7Ces8iLgamC13oCoG6VeBruA/edit?usp=sharing&resourcekey=0-EVe-Rhnme3bj_pkz2RcOmw.
PR Close#46801
Andrew Kushnir