fix(oxc_ecmascript): `+[false]` and `+[true]` should evaluate to `NaN` by Copilot · Pull Request #19174 · oxc-project/oxc

Copilot · 2026-02-09T11:00:29Z

Fix minifier incorrectly handling `+[false]` and `+[true]`

Summary:
Fixed a bug where +[false] and +[true] were incorrectly minified to 0 and 1 instead of NaN. The issue was in the to_number implementation for arrays in oxc_ecmascript, which was bypassing the proper ECMAScript conversion chain (array → string → number). Now correctly converts arrays to strings first via to_js_string, then converts the string to a number.

Original prompt

This section details on the original issue you should resolve

<issue_title>minifier: +[false] and +[true] are incorrectly minified</issue_title>
<issue_description>
I was messing around with jsfuck and found out that oxc_minifier doesn't minify +[false] or +[true] correctly. It is supposed to evalutate to NaN, but Oxc just grabs the boolean and uses that. This makes the 'minified' jsfuck code invalid (not that I'm using jsfuck on a day to day basis)

Original:
const a = +[false]
const b = +[true]
Oxc minified:
const a = 0
const b = 1;
Expected:
const a = NaN
const b = NaN;
Playground (enable minify syntax)

</issue_description>

<agent_instructions>probably there a bug in the constant evaluator in oxc_ecmascript that handles UnaryExpression</agent_instructions>

Comments on the Issue (you are @copilot in this section)

Fixes minifier: +[false] and +[true] are incorrectly minified #19084

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

crates/oxc_minifier/tests/peephole/fold_constants.rs

crates/oxc_ecmascript/src/to_number.rs

codspeed-hq · 2026-02-09T11:51:43Z

CodSpeed Performance Report

Merging this PR will not alter performance

_{Comparing copilot/fix-minifier-boolean-evaluation (04e6bc3) with main (e19bc45)¹}

Summary

✅ 47 untouched benchmarks
⏩ 3 skipped benchmarks²

No successful run was found on main (23c0753) during the generation of this report, so e19bc45 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩
3 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

sapphi-red · 2026-02-09T12:08:26Z

Merge activity

Feb 9, 12:08 PM UTC: The merge label '0-merge' was detected. This PR will be added to the Graphite merge queue once it meets the requirements.
Feb 9, 12:08 PM UTC: sapphi-red added this pull request to the Graphite merge queue.
Feb 9, 12:11 PM UTC: sapphi-red removed this pull request from the Graphite merge queue.
Feb 9, 12:38 PM UTC: The merge label '0-merge' was detected. This PR will be added to the Graphite merge queue once it meets the requirements.
Feb 9, 12:38 PM UTC: Boshen added this pull request to the Graphite merge queue.
Feb 9, 12:45 PM UTC: Merged by the Graphite merge queue.

#19174) ## Fix minifier incorrectly handling `+[false]` and `+[true]` - [x] Explore repository structure and locate the bug - [x] Identify the root cause in `to_number` implementation for arrays - [x] Add test case for the bug in minifier fold_constants tests - [x] Add test case in to_number unit tests - [x] Fix the bug in `to_number.rs` to properly convert arrays to strings first - [x] Run tests to verify the fix - all tests passing - [x] Manual verification with minifier example - outputs NaN correctly - [x] Run code review - no issues found - [x] Run security check - no vulnerabilities found - [x] Comprehensive testing of all array conversion cases - all correct - [x] Apply cargo fmt to fix formatting - [x] Address PR feedback: hoist use statements, simplify comments and code **Summary:** Fixed a bug where `+[false]` and `+[true]` were incorrectly minified to `0` and `1` instead of `NaN`. The issue was in the `to_number` implementation for arrays in `oxc_ecmascript`, which was bypassing the proper ECMAScript conversion chain (array → string → number). Now correctly converts arrays to strings first via `to_js_string`, then converts the string to a number.  <details> <summary>Original prompt</summary> > > ---- > > *This section details on the original issue you should resolve* > > <issue_title>minifier: `+[false]` and `+[true]` are incorrectly minified</issue_title> > <issue_description> > I was messing around with [jsfuck](https://jsfuck.com/) and found out that oxc_minifier doesn't minify `+[false]` or `+[true]` correctly. It is supposed to evalutate to `NaN`, but Oxc just grabs the boolean and uses that. This makes the 'minified' jsfuck code invalid (not that I'm using jsfuck on a day to day basis) > > Original: > ```ts > const a = +[false] > const b = +[true] > ``` > > Oxc minified: > ```ts > const a = 0 > const b = 1; > ``` > > Expected: > ```ts > const a = NaN > const b = NaN; > ``` > > [Playground](https://playground.oxc.rs/?code=const+a+%3D+%2B%5Bfalse%5D%0Aconst+b+%3D+%2B%5Btrue%5D) (enable minify syntax) > > </issue_description> > > <agent_instructions>probably there a bug in the constant evaluator in oxc_ecmascript that handles `UnaryExpression`</agent_instructions> > > ## Comments on the Issue (you are @copilot in this section) > > <comments> > </comments> > </details>  - Fixes #19084  --- 💬 We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).

Copilot

Pull request overview

Fixes constant folding / ToNumber semantics for array literals so expressions like +[false] and +[true] correctly evaluate to NaN (via array → string → number conversion), aligning minifier output with ECMAScript behavior.

Changes:

Update oxc_ecmascript::ToNumber for ArrayExpression to convert via to_js_string then string_to_number, with a fast-path for multi-element arrays.
Add minifier peephole regression tests ensuring +[false] / +[true] fold to NaN.
Add to_number unit tests for arrays containing boolean elements.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
crates/oxc_minifier/tests/peephole/fold_constants.rs	Adds regression folding assertions for `+[false]` / `+[true]` to ensure minifier outputs `NaN`.
crates/oxc_minifier/tests/ecmascript/to_number.rs	Extends `ToNumber` unit tests to cover array literals containing booleans.
crates/oxc_ecmascript/src/to_number.rs	Fixes array `ToNumber` implementation to follow array→string→number conversion semantics.

crates/oxc_ecmascript/src/to_number.rs

crates/oxc_minifier/tests/peephole/fold_constants.rs

crates/oxc_ecmascript/src/to_number.rs

Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.

#19174) ## Fix minifier incorrectly handling `+[false]` and `+[true]` - [x] Explore repository structure and locate the bug - [x] Identify the root cause in `to_number` implementation for arrays - [x] Add test case for the bug in minifier fold_constants tests - [x] Add test case in to_number unit tests - [x] Fix the bug in `to_number.rs` to properly convert arrays to strings first - [x] Run tests to verify the fix - all tests passing - [x] Manual verification with minifier example - outputs NaN correctly - [x] Run code review - no issues found - [x] Run security check - no vulnerabilities found - [x] Comprehensive testing of all array conversion cases - all correct - [x] Apply cargo fmt to fix formatting - [x] Address PR feedback: hoist use statements, simplify comments and code - [x] Address bot feedback: optimize count, remove redundant import, add test coverage **Summary:** Fixed a bug where `+[false]` and `+[true]` were incorrectly minified to `0` and `1` instead of `NaN`. The issue was in the `to_number` implementation for arrays in `oxc_ecmascript`, which was bypassing the proper ECMAScript conversion chain (array → string → number). Now correctly converts arrays to strings first via `to_js_string`, then converts the string to a number.  <details> <summary>Original prompt</summary> > > ---- > > *This section details on the original issue you should resolve* > > <issue_title>minifier: `+[false]` and `+[true]` are incorrectly minified</issue_title> > <issue_description> > I was messing around with [jsfuck](https://jsfuck.com/) and found out that oxc_minifier doesn't minify `+[false]` or `+[true]` correctly. It is supposed to evalutate to `NaN`, but Oxc just grabs the boolean and uses that. This makes the 'minified' jsfuck code invalid (not that I'm using jsfuck on a day to day basis) > > Original: > ```ts > const a = +[false] > const b = +[true] > ``` > > Oxc minified: > ```ts > const a = 0 > const b = 1; > ``` > > Expected: > ```ts > const a = NaN > const b = NaN; > ``` > > [Playground](https://playground.oxc.rs/?code=const+a+%3D+%2B%5Bfalse%5D%0Aconst+b+%3D+%2B%5Btrue%5D) (enable minify syntax) > > </issue_description> > > <agent_instructions>probably there a bug in the constant evaluator in oxc_ecmascript that handles `UnaryExpression`</agent_instructions> > > ## Comments on the Issue (you are @copilot in this section) > > <comments> > </comments> > </details>  - Fixes #19084  --- 💬 We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).

### 💥 BREAKING CHANGES - 2bf7293 mangler: [**BREAKING**] Enable `top_level` by default for modules and commonjs (#18278) (sapphi-red) - 48b0542 span: [**BREAKING**] SourceType::ts should set module to unambigious (#18873) (Boshen) ### 🚀 Features - 500d071 minifier: Local traverse ctx and generated minifier traverse (#19106) (Boshen) - 142a1be parser: Detect binary files with TS1490 error (#19047) (Boshen) - e316857 allocator/bitset: Add `Ones` iterator to `BitSet` (#19027) (sapphi-red) - 742ad3f minifier: Default `invalid_import_side_effects` to `false` (#18916) (sapphi-red) - 0eff6be parser: Error JSX-like type assertions and generics in `.mts`/`.cts` (#18910) (Boshen) - 18320c6 span: Store file extension in `SourceType` (#18893) (Boshen) ### 🐛 Bug Fixes - a7514e4 isolated-declarations: Preserve const context in literal type inference (#19178) (camc314) - 312e756 isolated-declarations: Preserve readonly literal initializers (#19177) (camc314) - d0ca8d0 isolated-declarations: Skip parenthesis when inferring type (#19176) (camc314) - 110c300 oxc_ecmascript: `+[false]` and `+[true]` should evaluate to `NaN` (#19174) (copilot-swe-agent) - f32ea19 semantic: Report redeclaration error for import bindings conflicting with value declarations (#19068) (Boshen) - 3aeba7a semantic: Report redeclaration error for `function a() {} var a` in module mode (#19041) (Boshen) - 35e32c6 coverage: Match Babel's options.json inheritance for test fixtures (#19002) (Boshen) - 463d60d semantic: Skip TS2391 for standalone computed-name class methods (#19025) (Boshen) - 56c086b parser: Add modifier ordering validation (TS1029) (#19024) (Boshen) - 6067a49 linter/jsdoc: False positive in `check-tag-names` for `@` in email addresses and npm scopes (#19021) (Boshen) - b13bb70 semantic/jsdoc: Inline tags like `{@link}` break jsdoc parsing (#19019) (Boshen) - e3609e3 regular_expression: Preserve UnicodeEscape CharacterKind in string literals (#18998) (Boshen) - 57917ee parser: Parse decorators on rest parameters (#18938) (Boshen) - 487601b napi: Disable mimalloc on Windows to fix worker_threads crash (#18923) (Boshen) - 1f6b193 parser: Validate TypeScript import type options (#18889) (Boshen) - 1663184 parser: Allow conditional types in function type parameters (#18886) (Boshen) - 5758046 parser: Error on property access after instantiation expression (#18887) (Boshen) - 5eb4a94 parser: Handle `<<` as two `<` tokens in type argument contexts (#18885) (Boshen) ### ⚡ Performance - ed8c054 oxc_str: Add precomputed hash to Ident for fast HashMap lookups (#19143) (Boshen) - d4a0867 transformer_plugins: Switch ReplaceGlobalDefines from Traverse to VisitMut (#19146) (Boshen) - 9eb16b3 syntax: Pack ASCII identifier tables into single bitflag table (#19088) (Boshen) - e7595d1 mangler: Use BitSet for exported symbols set (#19023) (sapphi-red) - 2537924 semantic: Optimize scope resolution with fast paths and inlining (#19029) (Boshen) - 69a8d85 mangler: Use BitSet for keep_names symbols set (#19028) (sapphi-red) - f78c525 parser: Try hybrid parsing for jsx children and closing element/fragments (#18789) (camchenry) Co-authored-by: camc314 <18101008+camc314@users.noreply.github.com>

### 💥 BREAKING CHANGES - 2bf7293 mangler: [**BREAKING**] Enable `top_level` by default for modules and commonjs (oxc-project#18278) (sapphi-red) - 48b0542 span: [**BREAKING**] SourceType::ts should set module to unambigious (oxc-project#18873) (Boshen) ### 🚀 Features - 500d071 minifier: Local traverse ctx and generated minifier traverse (oxc-project#19106) (Boshen) - 142a1be parser: Detect binary files with TS1490 error (oxc-project#19047) (Boshen) - e316857 allocator/bitset: Add `Ones` iterator to `BitSet` (oxc-project#19027) (sapphi-red) - 742ad3f minifier: Default `invalid_import_side_effects` to `false` (oxc-project#18916) (sapphi-red) - 0eff6be parser: Error JSX-like type assertions and generics in `.mts`/`.cts` (oxc-project#18910) (Boshen) - 18320c6 span: Store file extension in `SourceType` (oxc-project#18893) (Boshen) ### 🐛 Bug Fixes - a7514e4 isolated-declarations: Preserve const context in literal type inference (oxc-project#19178) (camc314) - 312e756 isolated-declarations: Preserve readonly literal initializers (oxc-project#19177) (camc314) - d0ca8d0 isolated-declarations: Skip parenthesis when inferring type (oxc-project#19176) (camc314) - 110c300 oxc_ecmascript: `+[false]` and `+[true]` should evaluate to `NaN` (oxc-project#19174) (copilot-swe-agent) - f32ea19 semantic: Report redeclaration error for import bindings conflicting with value declarations (oxc-project#19068) (Boshen) - 3aeba7a semantic: Report redeclaration error for `function a() {} var a` in module mode (oxc-project#19041) (Boshen) - 35e32c6 coverage: Match Babel's options.json inheritance for test fixtures (oxc-project#19002) (Boshen) - 463d60d semantic: Skip TS2391 for standalone computed-name class methods (oxc-project#19025) (Boshen) - 56c086b parser: Add modifier ordering validation (TS1029) (oxc-project#19024) (Boshen) - 6067a49 linter/jsdoc: False positive in `check-tag-names` for `@` in email addresses and npm scopes (oxc-project#19021) (Boshen) - b13bb70 semantic/jsdoc: Inline tags like `{@link}` break jsdoc parsing (oxc-project#19019) (Boshen) - e3609e3 regular_expression: Preserve UnicodeEscape CharacterKind in string literals (oxc-project#18998) (Boshen) - 57917ee parser: Parse decorators on rest parameters (oxc-project#18938) (Boshen) - 487601b napi: Disable mimalloc on Windows to fix worker_threads crash (oxc-project#18923) (Boshen) - 1f6b193 parser: Validate TypeScript import type options (oxc-project#18889) (Boshen) - 1663184 parser: Allow conditional types in function type parameters (oxc-project#18886) (Boshen) - 5758046 parser: Error on property access after instantiation expression (oxc-project#18887) (Boshen) - 5eb4a94 parser: Handle `<<` as two `<` tokens in type argument contexts (oxc-project#18885) (Boshen) ### ⚡ Performance - ed8c054 oxc_str: Add precomputed hash to Ident for fast HashMap lookups (oxc-project#19143) (Boshen) - d4a0867 transformer_plugins: Switch ReplaceGlobalDefines from Traverse to VisitMut (oxc-project#19146) (Boshen) - 9eb16b3 syntax: Pack ASCII identifier tables into single bitflag table (oxc-project#19088) (Boshen) - e7595d1 mangler: Use BitSet for exported symbols set (oxc-project#19023) (sapphi-red) - 2537924 semantic: Optimize scope resolution with fast paths and inlining (oxc-project#19029) (Boshen) - 69a8d85 mangler: Use BitSet for keep_names symbols set (oxc-project#19028) (sapphi-red) - f78c525 parser: Try hybrid parsing for jsx children and closing element/fragments (oxc-project#18789) (camchenry) Co-authored-by: camc314 <18101008+camc314@users.noreply.github.com>

Copilot AI assigned Copilot and sapphi-red Feb 9, 2026

Copilot started work on behalf of sapphi-red February 9, 2026 11:00 View session

Copilot AI changed the title ~~[WIP] Fix minifier to handle +[false] and +[true] correctly~~ Fix minifier: +[false] and +[true] should evaluate to NaN Feb 9, 2026

Copilot AI requested a review from sapphi-red February 9, 2026 11:10

Copilot finished work on behalf of sapphi-red February 9, 2026 11:10

sapphi-red reviewed Feb 9, 2026

View reviewed changes

crates/oxc_minifier/tests/peephole/fold_constants.rs Outdated Show resolved Hide resolved

crates/oxc_ecmascript/src/to_number.rs Outdated Show resolved Hide resolved

crates/oxc_ecmascript/src/to_number.rs Outdated Show resolved Hide resolved

Copilot started work on behalf of sapphi-red February 9, 2026 11:27 View session

Copilot finished work on behalf of sapphi-red February 9, 2026 11:31

Copilot AI requested a review from sapphi-red February 9, 2026 11:31

sapphi-red approved these changes Feb 9, 2026

View reviewed changes

sapphi-red changed the title ~~Fix minifier: +[false] and +[true] should evaluate to NaN~~ fix(oxc_ecmascript): +[false] and +[true] should evaluate to NaN Feb 9, 2026

github-actions bot added A-minifier Area - Minifier C-bug Category - Bug labels Feb 9, 2026

sapphi-red marked this pull request as ready for review February 9, 2026 12:07

Copilot AI review requested due to automatic review settings February 9, 2026 12:07

Copilot started reviewing on behalf of sapphi-red February 9, 2026 12:08 View session

sapphi-red added 0-merge Merge with Graphite Merge Queue and removed 0-merge Merge with Graphite Merge Queue labels Feb 9, 2026

graphite-app bot force-pushed the copilot/fix-minifier-boolean-evaluation branch from 67f3a9e to 68c7dd2 Compare February 9, 2026 12:08

Copilot AI reviewed Feb 9, 2026

View reviewed changes

crates/oxc_ecmascript/src/to_number.rs Show resolved Hide resolved

crates/oxc_minifier/tests/peephole/fold_constants.rs Show resolved Hide resolved

crates/oxc_ecmascript/src/to_number.rs Outdated Show resolved Hide resolved

Copilot started work on behalf of sapphi-red February 9, 2026 12:12 View session

sapphi-red requested a review from Copilot February 9, 2026 12:16

Copilot started reviewing on behalf of sapphi-red February 9, 2026 12:17 View session

Copilot AI reviewed Feb 9, 2026

View reviewed changes

Copilot AI requested a review from sapphi-red February 9, 2026 12:38

Copilot finished work on behalf of sapphi-red February 9, 2026 12:38

Boshen added the 0-merge Merge with Graphite Merge Queue label Feb 9, 2026

graphite-app bot force-pushed the copilot/fix-minifier-boolean-evaluation branch from 04e6bc3 to 110c300 Compare February 9, 2026 12:39

graphite-app bot merged commit 110c300 into main Feb 9, 2026
21 checks passed

graphite-app bot deleted the copilot/fix-minifier-boolean-evaluation branch February 9, 2026 12:45

graphite-app bot removed the 0-merge Merge with Graphite Merge Queue label Feb 9, 2026

Boshen mentioned this pull request Feb 10, 2026

release(crates): oxc v0.113.0 #19210

Merged

Boshen mentioned this pull request Feb 10, 2026

release(crates): oxc v0.113.0 #19215

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(oxc_ecmascript): `+[false]` and `+[true]` should evaluate to `NaN`#19174

fix(oxc_ecmascript): `+[false]` and `+[true]` should evaluate to `NaN`#19174
graphite-app[bot] merged 1 commit intomainfrom
copilot/fix-minifier-boolean-evaluation

Copilot AI commented Feb 9, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codspeed-hq bot commented Feb 9, 2026 •

edited

Loading

Uh oh!

sapphi-red commented Feb 9, 2026 •

edited by graphite-app bot

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Uh oh!

Conversation

Copilot AI commented Feb 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Fix minifier incorrectly handling +[false] and +[true]

Comments on the Issue (you are @copilot in this section)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codspeed-hq bot commented Feb 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

CodSpeed Performance Report

Merging this PR will not alter performance

Summary

Footnotes

Uh oh!

sapphi-red commented Feb 9, 2026 • edited by graphite-app bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merge activity

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Copilot AI commented Feb 9, 2026 •

edited

Loading

Fix minifier incorrectly handling `+[false]` and `+[true]`

codspeed-hq bot commented Feb 9, 2026 •

edited

Loading

sapphi-red commented Feb 9, 2026 •

edited by graphite-app bot

Loading