NEW(eslint): @W-18495508@: Implement the "no-user-config" scenario for ESLint v9 by stephen-carter-at-sf · Pull Request #301 · forcedotcom/code-analyzer-core

stephen-carter-at-sf · 2025-05-29T21:33:30Z

No description provided.

stephen-carter-at-sf · 2025-05-29T21:34:45Z

+ *   C: and D:, then null is returned (to allow the client of this function to handle this case without try/catch).
+ * @param paths It is assumed that paths is a non-empty array of absolute value paths.
+ */
+export function calculateLongestCommonParentFolderOf(paths: string[]): string | null {


Note that this was just moved (not modified in any way).
I had to share this utility with the eslint9 engine to help with the calculation of the base directory for ESLint 9. This meant a change to the engine-api package which meant all the engines in this monorepo needed to increment their dependency on it. Sorry for the noise.

stephen-carter-at-sf · 2025-05-29T21:36:49Z

    "eslint": "^9.26.0",
    "eslint-plugin-import": "^2.31.0",
    "eslint-plugin-jest": "^28.11.0",
+    "tmp": "^0.2.3",


I look forward to the day I have time to do W-17875752 so that we can just have core pass in the temp folder so that we don't need to have the tmp dependency on all our engines.

stephen-carter-at-sf · 2025-05-29T21:46:05Z

        severity: SeverityLevel.High,
        tags: [/* NOT RECOMMENDED */    COMMON_TAGS.CATEGORIES.ERROR_PRONE,    COMMON_TAGS.LANGUAGES.JAVASCRIPT] // Not available with TypeScript
    },
+    "no-useless-assignment": {


ESLint v9 has removed a few rules and added a few rules for base javascript and typescript. So the the updates to the gold files and rule-mappings reflect this.

stephen-carter-at-sf · 2025-05-29T21:57:03Z

+        // TODO: We should make our DescribeRulesProgressEvents more refined while calculating the eslint context information
+        expect(describeRulesProgressEvents.map(e => e.percentComplete)).toEqual([0, 10, 90, 95, 100]);


This file was filled with the tests for the default (no user config) case...and it's really great that the only thing behavior change was the progress events (which I plan on enhancing at some point by the way) and gold files.
This proves that between v8 and v9 - I have successfully maintained the default behavior!

jfeingold35 · 2025-05-30T14:29:08Z

+    replacer: (value: unknown, path: string) => unknown = v => v
+): object | null | string | number | boolean
+{
+    const seen = new WeakMap<object, string>();


Just to make sure I understand, is the WeakMap being used here so that entries added during recursive calls fall out as the recursion un-nests?

I just know from experience that you need to use a WeakMap when doing infinite loop detection. I'll let chatGPT answer this one for me:

jfeingold35 · 2025-05-30T14:57:48Z

+        return configs;
+    }
+
+    private useJsConfig(): boolean {


Could we maybe call these methods something like useBaseJsConfig etc for clarity's sake?

Sure. Done.

jfeingold35 · 2025-05-30T15:03:47Z

+
        const userConfigInfo: UserConfigInfo = this.getUserConfigInfo(describeOptions.workspace);
-        this.emitLogEvent(LogLevel.Fine, `Detected the following regarding the user's eslint configuration files: ${userConfigInfo}`);
+        this.emitLogEvent(LogLevel.Fine, `Detected the following user's ESLint configuration state: ${userConfigInfo}`);


"Following user's configuration state" sounds like it's indicating who the configuration state belongs to, not that it's indicating the configuration state itself. Maybe "Following user-provided configuration state"?

Sure I can fix the wording here.

Done.

jfeingold35 · 2025-05-30T15:08:51Z

+}
+
+function toSeverityLevelForCustomRule(metadata: RulesMeta, status: ESLintRuleStatus): SeverityLevel {
+    if (status === ESLintRuleStatus.WARN) {


I understand why you made the choices you made, but it feels really weird to me that warn produces a lower-severity violation than layout. I feel like if warn is being turned to info, then so should layout.

An ESLint warn is meant to not fail eslint in any way but to just inform the user about something. This is indeed a lower severity that layout errors.

I didn't change these - these came from our original eslint 8 engine design which we already had reviewed, etc. Keeping the rules the exact same as they were before.

jfeingold35 · 2025-05-30T15:13:39Z

@@ -0,0 +1,37 @@
+// This declaration adds in the missing types for "@lwc/eslint-plugin-lwc-platform" whose package.json file's main field points to:
+//     node_modules/@lwc/eslint-plugin-lwc-platform/lib/index.js
+declare module '@lwc/eslint-plugin-lwc-platform' {


Is this being declared on top of modules that already exist, or are we declaring these modules from whole cloth?

See https://salesforce-internal.slack.com/archives/C5W3E40TC/p1746136385115359

We depend on those packages but they have no types. Until the other team adds in types for typescript, I created the types for them here locally with our own .d.ts file.

…r ESLint v9

stephen-carter-at-sf requested review from jfeingold35 and randi274 May 29, 2025 21:33

stephen-carter-at-sf commented May 29, 2025

View reviewed changes

stephen-carter-at-sf force-pushed the sc/eslintUpdates branch from 5c71df0 to e7b976a Compare May 29, 2025 21:54

stephen-carter-at-sf commented May 29, 2025

View reviewed changes

stephen-carter-at-sf force-pushed the sc/eslintUpdates branch from e7b976a to 7135d52 Compare May 30, 2025 14:08

jfeingold35 reviewed May 30, 2025

View reviewed changes

stephen-carter-at-sf force-pushed the sc/eslintUpdates branch from 7135d52 to ab9386b Compare May 30, 2025 15:48

NEW(eslint): @W-18495508@: Implement the "no-user-config" scenario fo…

fffc2d1

…r ESLint v9

stephen-carter-at-sf force-pushed the sc/eslintUpdates branch from ab9386b to fffc2d1 Compare May 30, 2025 15:51

jfeingold35 approved these changes May 30, 2025

View reviewed changes

stephen-carter-at-sf merged commit cf29fdb into dev May 30, 2025
7 checks passed

		// TODO: We should make our DescribeRulesProgressEvents more refined while calculating the eslint context information
		expect(describeRulesProgressEvents.map(e => e.percentComplete)).toEqual([0, 10, 90, 95, 100]);

Uh oh!

Conversation

stephen-carter-at-sf commented May 29, 2025

Uh oh!

stephen-carter-at-sf May 29, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

stephen-carter-at-sf May 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

stephen-carter-at-sf May 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

stephen-carter-at-sf May 29, 2025 •

edited

Loading

stephen-carter-at-sf May 30, 2025 •

edited

Loading

stephen-carter-at-sf May 30, 2025 •

edited

Loading