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#46716
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#46716
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#46716
Remove or reframe references to the obsolete HeroListComponent component that was taken from an old version of the Tour of Heroes tutorial.
Incorporates review feedback.
Fix#44662
PR Close#46647
The integration test rule now always executes tests in a directory
outside of the execroot. This ensures a more hermetic test environment
on platforms without a sandbox, or when tests are run with `tags:
local`.
As part of this change, an issue with Yarn 1.x. and `nodejs_binary`
unveiled. Yarn 1.x. is resolved properly using the tool mapping but
when Yarn inside Yarn is invoked (e.g. using `package.json` scripts),
then the second nested Yarn invocation fails due to an unknown path.
This happens because Yarn in the original invocation creates another
directory in the `/tmp` directory and modifies the `PATH` so that
the same `yarn` can be invoked again. This makes sense conceptually
but breaks in our case because the Yarn Bash script put into the `/tmp`
directory tries to resolve our vendored Yarn script relatively (which
is the wrong spot here). It worked previously in the execroot because
`nodejs_binary` invoked Yarn through `<external>/../node.sh
<absolute-path-to-yarn-cjs-script>`, but outside the execroot it invoked
Yarn using a relative path (which then ended up being preserved in the
Yarn temporary directory).
We can fix this by updating the Bazel NodeJS repository which seems to
have coincidentally have a fix for the path resolution. See:
https://github.com/bazelbuild/rules_nodejs/pull/3493#event-6870301735.
PR Close#46778
Import `AsyncStackTaggingZoneSpec` if the user imported
`zone.js/plugins/async-stack-tagging` bundle. So the user can
use `console.trace` to output the `async task` information more
clearly.
PR Close#46693
Chrome has an experimental API to improve the debug experience of the
async tasks.
The details can be found here https://bugs.chromium.org/p/chromium/issues/detail?id=332624#c29
This commit add the `async stack tagging` support in the `zone.js`.
User can `import 'zone.js/plugins/async-stack-tagging';` to enable this
feature.
PR Close#46693
Before this commit, the `NavigationCancellationCode` would always be set
to `Redirect` when encountering a "navigationcancelingError". However,
this error can also be thrown when `CanLoad` guars reject. This commit
ensures these cancellation errors have a code as well so this mistake
cannot be made again.
PR Close#46752
The existing logic does something similar but in a more roundabout way.
It reads _the whole array_. If it encounters a pending value, it ignores
the remaining ones. If it hasn't encountered a pending value by the time
it hits false/UrlTree, it returns that result.
The new logic is the same, but reverses what we're looking for. Instead
of processing the whole array, we stop when we encounter an initial
value. When we encounter one that isn't `true`, that gets returned. If
we get to the end and everything was `true`, return `true`.
PR Close#46745
PR Close#46745
The existing logic does something similar but in a more roundabout way.
It reads _the whole array_. If it encounters a pending value, it ignores
the remaining ones. If it hasn't encountered a pending value by the time
it hits false/UrlTree, it returns that result.
The new logic is the same, but reverses what we're looking for. Instead
of processing the whole array, we stop when we encounter an initial
value. When we encounter one that isn't `true`, that gets returned. If
we get to the end and everything was `true`, return `true`.
PR Close#46745
This commit adds an extended diagnostic which warns when style suffixes such as '.px'
are used with attribute bindings (attr.width.px).
Fixes#36256
PR Close#46651
For the branch rename migration we temporarily had to work
from a forked-off branch. Now that all the migration and cleanup
Is complete, we can switch to the actual new main branch.
This is the last remaining cleanup in the organization as it seems.
PR Close#46743
This commit adds the target `RouterStateSnapshot` to the
`NavigationError` so error handlers/subscribers can more easily
determine which navigation failed, including the matched `Route` configs
for the navigation. This information was previously not available
(neither in `NavigationError` nor the `Router#getCurrentNavigation()`).
fixes#27626
PR Close#46731
Add a section regarding component view encapsulations in the complex animation
sequences guide to let developers know how animations work in regard to
view encapsulations.
This section is used to both add information to the guide but also to
take a stand on how the animations should behave in regard to the
shadow dom view encapsulation.
This relates to PR #46488 which by trying to make sure the query
function works with shadow dom elements proved that having the
animations implementation work with shadow dom would increase the
complexity of the code and would have a negative impact on performance,
such facts alongide the small adoption of shadow dom by users influenced
the decision to keep the current functionalities and simply discourage
the use of animations and shadow dom components.
PR Close#46738
This reverts commit b417370383.
The change applied is no longer appropriate since the use of animations
and shadow dom components is discouraged (as of #46738)
PR Close#46739
There are legitimate cases where access to an EnvironmentInjector
of a bootstrapped application is required / convenient. It will be also
required for support of standalone components with Angular elements.
PR Close#46665
In the case that a user accidentally forgot the let keyword, they dont get a very clear indicator of there being a problem.
They get an issue in the template iteration at runtime. This diagnostic will warn the user when the let keyword is missing.
PR Close#46683
`--project` is unwritten standard to provide the project name. With this change we allow the project name to be provided using the `--project` command line argument and remove the ambiguity with other schematics.
PR Close#46664
Removes the Renovate changes group as the respective code-owners. i.e.
dev-infra or docs-infra should be responsible for reviewing changes.
The caretaker does not necessarily have context when e.g. Jasmine
should be updated or not/ if this needs coordination with other parts
of the organization etc.
Also updates are not always trivial, see recent updates for Angular
(involing size updates, CLI commands fixups etc.) and e.g. Karma-Jasmine
requiring debugging of ZoneJS.
The Renovate group is also not easy to keep now that we use a custom
robot account that doesn't necessarily only do Renovate..
(we could check the branch name -- but I believe the group can just be
removed)
PR Close#46676
