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
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
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
This commit removes CSS keyframes-based code that was used to support animations in old browsers. With IE11 deprecation, all supported browsers have native WebAnimations support, so the old code can be removed. This results in ~7KB decrease of the animations package bundle size, since most of the code was non-tree-shakable.
Closes#44520.
PR Close#44903
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
Switches the benchpress NPM package to APF with ESM. This
is necessary as benchpress relies on framework APF strict ESM
packages. CommonJS packages like benchpress currently are not
able to import from strict ESM packages without adding a CJS/ESM
interop that complicates code unnecessarily.
The best way forward is to just switch the benchpress package from
CommonJS to the modern ESM output, matching with the Angular ecosystem.
PR Close#44893
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
We were using a number of generic objects as if they were maps and relying on delete to remove
properties. In order to improve performance, these have been switched to native maps.
PR Close#44482
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
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#44912
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#44830
Bumps the version for benchpress to v0.2.2 so that a new version
is available on NPM with Angular v13 support. This would be needed
for dev-infra which exposes tooling for benchmarks relying on the
Angular benchpress NPM package.
PR Close#44879
This new feature allows negative indices to wrap around from the back, just like ES2021 `Array.at`. In particular, the following methods accept negative indices, and behave like corresponding Array methods:
* `FormArray.at(index)`: behaves the same as `Array.at(index)`
* `FormArray.insert(index, control)`: behaves the same as `Array.splice(index, 0, control)`
* `FormArray.setControl(index, control)`: behaves the same as `Array.splice(index, 1, control)`
* `FormArray.removeAt(index, control)`: behaves the same as `Array.splice(index, 1)`
Previous work in #44746 and #44631 (by @amitbeck).
Issue #44642.
Co-authored-by: Amit Beckenstein <amitbeck@gmail.com>
PR Close#44848
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
This commit provides a service, `PageTitleStrategy` for setting
the document page title after a successful router navigation.
Users can provide custom strategies by extending `TitleStrategy` and
adding a provider which overrides it.
The strategy takes advantage of the pre-existing `data` and `resolve` concepts
in the Router implementation:
We can copy the `Route.title` into `data`/`resolve` in a
non-breaking way by using a `symbol` as the key. This ensures that we
do not have any collisions with pre-existing property names. By using
`data` and `resolve`, we do not have to add anything more to
the router navigation pipeline to support this feature.
resolves#7630
PR Close#43307
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
This reverts commit 894fa759f1. In that commit, the migration was completely diabled in order to prevent users from selecting it for the 13.2 release. This revert commit restores the migration to its previous (fully optional) state, in order to continue migration-focused work.
PR Close#44834
Previously devtools used a nested workspace for its bazel configurations. This meant framework dependencies were consumed via npm.
Now devtools is part of the root bazel directory that all other files in this codebase fall under. This allows us to build devtools using local angular packages, removing the need to consume these dependencies with npn. This is useful because we no longer have to update these dependencies with an automated tool like renovate, and our CI tests will always run against the most up to date framework packages.
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
Add a new option for configuring data-groups, `cacheOpaqueResponses`,
that determines whether opaque responses are cached or not. This allows
greater flexibility in configuring the behavior of data-groups, while
still keeping the current defaults as fallbacks.
Fixes#44246
PR Close#44723
Make the `MockResponse` class used in tests behave more similarly to how
real responses work by making the following improvements:
- Use an empty `statusText` (`''`) when provided, instead of the default
`'OK'` value. This allows better representing opaque responses.
- Preserve more properties (`redirected`, `type`, `url`) when cloning a
`MockResponse`.
PR Close#44723
Modified required validator and checkbox validator to inherit abstractValidator.
For every validato type different PR will be raised as discussed in #42378.
Closes#42267
PR Close#44162
When the user opts into the noop `NgZone`, they usually still interact with the static methods on the non-noop class. This change adds a check to handle the case where zone.js hasn't been loaded.
Fixes#44784.
PR Close#44800
The previous fix for correcting spans with comments in
https://github.com/angular/angular/commit/59eef29a6c5d568ca80595cd7018e21ad406c85d
had the unfortunate side effect of _breaking_ the spans with comments
when there was leading whitespace. This happened because the previous
fix was testing one without a comment, identifying that the offset shouldn't
have anything added to it, and then removing that offset adjustment
(`offsets[i] + (expressionText.length - sourceToLex.length)`).
Upon further investigation, this offset adjustment _was actually
necessary_ for when the input had comments, but this was only because
the `stripComments` function used `trim` to remove whitespace for these
cases. This is the real problem -- not only does it create a ton of confusion
but also it means that the behavior of the lexer and resulting spans is
different between inputs with comments and inputs without comments.
After reviewing how the `inputLength` of `_ParseAST` was used, it
appears that the correct behavior would be to _not_ trim the input. The
`inputLength` is used to advance the current index beyond points which
have been processed. This _should_ include any whitespace. Additionally,
`inputLength` doesn't appear to be needed at all. When there was no
comment in the input, it was always equal to the `input.length` anyways.
When there _is_ a comment, it should include that comment anyways to
advance the index beyond the comment.
PR Close#44785
Dylan Hunn