Fix broken unicode escape sequence in JSX text

[Copilot]

Fixes a bug where unicode characters on standalone lines in JSX text were being corrupted and output as \uFFFD (the Unicode replacement character) instead of their correct escape sequences.

Problem

When JSX contained unicode characters on separate lines, they were being incorrectly encoded:

export const Component = () => {
    return (<div><span>⚠</span>
        ⚠
    </div>)
}

Before (broken):

return (jsx_runtime_1.jsxs("div", { children: [jsx_runtime_1.jsx("span", { children: "\u26A0" }), "\uFFFD"] }));

After (fixed):

return (jsx_runtime_1.jsxs("div", { children: [jsx_runtime_1.jsx("span", { children: "\u26A0" }), "\u26A0"] }));

Root Cause

The issue was in the fixupWhitespaceAndDecodeEntities function in internal/transformers/jsxtransforms/jsx.go. The code was using byte indices to track character positions but slicing strings at byte boundaries, which corrupted multi-byte UTF-8 characters.

For the 3-byte UTF-8 sequence ⚠ (E2 9A A0), the code was only including the first byte (E2) when slicing, resulting in an invalid UTF-8 sequence that gets replaced with \uFFFD.

Solution

Fixed the string slicing logic to properly handle multi-byte UTF-8 characters by tracking the end byte position (i + size - 1) instead of just the start position (i) of non-whitespace characters. This ensures that when slicing the string, we include complete UTF-8 character sequences.

The fix is minimal and surgical - only changing the variable name and assignment to make the byte boundary handling correct.

Testing

Added comprehensive test coverage in jsxUnicodeEscapeSequence.tsx that verifies:

• Inline unicode characters (already worked)
• Standalone unicode characters on separate lines (the bug case)
• Multiple unicode characters (also affected)

All existing tests continue to pass, confirming no regressions.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>broken unicode escape sequence in jsx</issue_title>
<issue_description>## Steps to reproduce

tsconfig.json

{
    "compilerOptions": {
        "outDir": "./dist",
        "declaration": true,
        "moduleResolution": "node",
        "strict": true,
        "skipLibCheck": true,
        "jsx": "react-jsx"
    }
}

repro.tsx

export const Repro = () => {
    return (<div><span>⚠</span>
        ⚠
    </div>)
}

Behavior with [email protected]

> tsc
> grep children dist/repro.js
    return ((0, jsx_runtime_1.jsxs)("div", { children: [(0, jsx_runtime_1.jsx)("span", { children: "\u26A0" }), "\u26A0"] }));

Behavior with tsgo

> tsgo
> grep children dist/repro.js
    return (jsx_runtime_1.jsxs("div", { children: [jsx_runtime_1.jsx("span", { children: "\u26A0" }), "\uFFFD"] }));

Its worth noting that the issue happens with the unicode character on a line by itself but not when there is other stuff in the same line.</issue_description>

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

@jakebailey Probably related to #1701 but, why have you done this? 😭 @jakebailey I see, you're saying it's literally https://www.compart.com/en/unicode/U+26A0. @jakebailey Yeah, it's just a bug then, this is a valid character so not sure where it's gone wrong.

Fixes #1715

---

💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.

[jakebailey]

Shockingly I think it successfully got there.

[Copilot]

Pull Request Overview

This PR fixes a bug where unicode characters on standalone lines in JSX text were being corrupted and output as \uFFFD (the Unicode replacement character) instead of their correct escape sequences.

• Fixed string slicing logic in fixupWhitespaceAndDecodeEntities to properly handle multi-byte UTF-8 characters
• Changed byte boundary tracking to use end position instead of start position for non-whitespace characters
• Added comprehensive test coverage for unicode characters in JSX text content

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
testdata/tests/cases/compiler/jsxUnicodeEscapeSequence.tsx	Added test cases covering inline, standalone, and multiple unicode characters in JSX
testdata/baselines/reference/compiler/jsxUnicodeEscapeSequence.types	Reference baseline for type checking output
testdata/baselines/reference/compiler/jsxUnicodeEscapeSequence.symbols	Reference baseline for symbol resolution output
testdata/baselines/reference/compiler/jsxUnicodeEscapeSequence.js	Reference baseline showing correctly encoded unicode escape sequences
testdata/baselines/reference/compiler/jsxUnicodeEscapeSequence.errors.txt	Reference baseline for expected JSX type errors
internal/transformers/jsxtransforms/jsx.go	Fixed unicode character handling by tracking end byte position instead of start position

[weswigham]

Otherwise, looks good.