Files
mindfulness/client/src/features/textWrap/core/joinTokens.ts
2026-02-10 11:39:33 +08:00

38 lines
1.1 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import type { Token } from './types';
/**
* 从 token 区间 `[start..end)` 重组回文本(跨端口径)。
*
* - 默认:用单空格 join适用于 whitespacePolicy=NORMALIZE
* - 若传入 rawSeparators按原始分隔符拼接适用于 whitespacePolicy=PRESERVE
*
* 说明:
* - `start/end` 为半开区间
* - 空区间返回空字符串;上层需要用硬约束避免空行
*/
export function joinTokens(tokens: Token[], start: number, end: number, rawSeparators?: string[]): string {
const s = Math.max(0, start | 0);
const e = Math.max(0, end | 0);
if (!Array.isArray(tokens) || tokens.length === 0) return '';
if (s >= e) return '';
const slice = tokens.slice(s, e).map((t) => t.text);
if (!rawSeparators) {
return slice.join(' ');
}
// rawSeparators[i] 表示 tokens[i] 与 tokens[i+1] 之间的分隔符
// 这里只实现最小可用:若 separators 缺失则回退到单空格。
let out = '';
for (let idx = s; idx < e; idx++) {
const t = tokens[idx];
if (!t) continue;
out += t.text;
if (idx < e - 1) {
out += rawSeparators[idx] ?? ' ';
}
}
return out;
}