Unicode 编解码

复制import json

# \uXXXX 转 Unicode 字符
unicode_escape = "\\u4e2d\\u6587"
text = json.loads(f'"{unicode_escape}"')
print(text)  # 中文

# Unicode 字符转 \uXXXX
text = "中文"
escaped = text.encode("unicode_escape").decode("ascii")
print(escaped)  # \u4e2d\u6587

# &#NNN; 转 Unicode 字符
html_entity = "中文"
import html
text = html.unescape(html_entity)
print(text)  # 中文

# Unicode 字符转 &#NNN;
text = "中文"
entities = "".join(f"&#{ord(c)};" for c in text)
print(entities)  # 中文

复制package main

import (
	"fmt"
	"strconv"
	"strings"
)

func main() {
	// \uXXXX 转 Unicode 字符
	unicodeEscape := "\\u4e2d\\u6587"
	unquoted, _ := strconv.Unquote(`"` + unicodeEscape + `"`)
	fmt.Println(unquoted) // 中文

	// Unicode 字符转 \uXXXX
	text := "中文"
	escaped := ""
	for _, r := range text {
		escaped += fmt.Sprintf("\\u%04x", r)
	}
	fmt.Println(escaped) // \u4e2d\u6587

	// &#NNN; 转 Unicode 字符
	htmlEntity := "中文"
	var sb strings.Builder
	parts := strings.Split(htmlEntity, ";")
	for _, p := range parts {
		if strings.HasPrefix(p, "&#") {
			code, _ := strconv.Atoi(p[2:])
			sb.WriteRune(rune(code))
		}
	}
	fmt.Println(sb.String()) // 中文

	// Unicode 字符转 &#NNN;
	text2 := "中文"
	var sb2 strings.Builder
	for _, r := range text2 {
		sb2.WriteString(fmt.Sprintf("&#%d;", r))
	}
	fmt.Println(sb2.String()) // 中文
}

复制// \uXXXX 转 Unicode 字符
const unicodeEscape = '\\u4e2d\\u6587';
const text = JSON.parse(`"${unicodeEscape}"`);
console.log(text); // 中文

// Unicode 字符转 \uXXXX
const text2 = '中文';
const escaped = text2.split('').map(c => '\\u' + c.charCodeAt(0).toString(16).padStart(4, '0')).join('');
console.log(escaped); // \u4e2d\u6587

// &#NNN; 转 Unicode 字符
const htmlEntity = '中文';
const parser = new DOMParser();
const doc = parser.parseFromString(htmlEntity, 'text/html');
console.log(doc.body.textContent); // 中文

// Unicode 字符转 &#NNN;
const text3 = '中文';
const entities = text3.split('').map(c => `&#${c.charCodeAt(0)};`).join('');
console.log(entities); // 中文