From dd622f83c1e410e987587cab7568ac6bc06b5f74 Mon Sep 17 00:00:00 2001 From: Trevin Chow Date: Sun, 19 Apr 2026 10:05:48 -0700 Subject: [PATCH] fix(annotations): use Unicode script properties for CJK detection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Address review feedback on #471 from @coderabbitai. The BMP-only codepoint ranges missed two classes of characters: - Non-BMP Han extensions (CJK Unified Ideographs Extension B, C, D, E, F) such as 𠀀. A long string of Extension-B characters would still be tokenized as a single unbreakable unit and overflow the box. - Halfwidth Katakana (U+FF65-U+FF9F) such as ｶ. Same failure mode. Switch to Unicode script property escapes (\\p{Script=Han}, \\p{Script=Hiragana}, \\p{Script=Katakana}, \\p{Script=Hangul}) which cover these cases without enumerating ranges. tsconfig target is ES2020; property escapes require ES2018+ so this is safe. Verified coverage: 漢 あ ア 가 𠀀 ｶ all match; A and digits do not. --- src/lib/exporter/annotationRenderer.ts | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/src/lib/exporter/annotationRenderer.ts b/src/lib/exporter/annotationRenderer.ts index 0b895a0..c0d5657 100644 --- a/src/lib/exporter/annotationRenderer.ts +++ b/src/lib/exporter/annotationRenderer.ts @@ -10,12 +10,12 @@ import { let blurScratchCanvas: HTMLCanvasElement | null = null; let blurScratchCtx: CanvasRenderingContext2D | null = null; -// Matches a single code point in Hiragana, Katakana, CJK Unified Ideographs -// Extension A, CJK Unified Ideographs, Hangul Syllables, or CJK Compatibility -// Ideographs. Used to split CJK text at character boundaries during wrap, -// since CJK scripts have no word-separating whitespace. -const CJK_CHAR = - /[\u3040-\u309f\u30a0-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uac00-\ud7af\uf900-\ufaff]/u; +// Matches a single code point whose script is Han (including non-BMP +// Extension A-F), Hiragana, Katakana (including halfwidth forms), or +// Hangul. Used to split CJK text at character boundaries during wrap, +// since CJK scripts have no word-separating whitespace. Unicode script +// property escapes require ES2018+; tsconfig target is ES2020. +const CJK_CHAR = /[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Hangul}]/u; function tokenizeForWrap(line: string): string[] { // Split Latin text on whitespace (preserving the whitespace as its own token,