dekun
206673fd90
Decode <0xE5><0xA7><0xA4> style model output to proper characters; add prompt rule to use normal Chinese text. Co-authored-by: Cursor <cursoragent@cursor.com>
21 lines
655 B
TypeScript
21 lines
655 B
TypeScript
/**
|
|
* 部分模型会把 UTF-8 汉字输出成 <0xE5><0xA7><0xA4> 形式，还原为正常文字。
|
|
* 例：<0xE5><0xA7><0xA4> → 姤
|
|
*/
|
|
export function decodeHexByteEscapes(text: string): string {
|
|
return text.replace(/(?:<0x[0-9A-Fa-f]{2}>)+/gi, (match) => {
|
|
const parts = match.match(/<0x([0-9A-Fa-f]{2})>/gi);
|
|
if (!parts?.length) {
|
|
return match;
|
|
}
|
|
const bytes = Uint8Array.from(
|
|
parts.map((part) => parseInt(part.slice(3, 5), 16)),
|
|
);
|
|
try {
|
|
return new TextDecoder("utf-8", { fatal: true }).decode(bytes);
|
|
} catch {
|
|
return new TextDecoder("utf-8", { fatal: false }).decode(bytes);
|
|
}
|
|
});
|
|
}
|