wechat-api/internal/utils/charset.go

package utils

import (
	"bytes"
	"fmt"
	"github.com/saintfish/chardet"
	"golang.org/x/text/encoding"
	"golang.org/x/text/encoding/charmap"
	"golang.org/x/text/encoding/japanese"
	"golang.org/x/text/encoding/korean"
	"golang.org/x/text/encoding/simplifiedchinese"
	"golang.org/x/text/encoding/traditionalchinese"
	"golang.org/x/text/encoding/unicode"
	"golang.org/x/text/transform"
	"io"
	"strings"
)

// TransCharset 自动检测编码并转换为 UTF-8
func TransCharset(s string) string {
	// 1. 自动检测编码
	detector := chardet.NewTextDetector()
	result, err := detector.DetectBest([]byte(s))
	if err != nil {
		fmt.Println("Encoding detection failed:", err)
		return s
	}

	// 2. 找到相应的编码
	fmt.Println("result.Charset:", result.Charset)
	enc := getEncoding(result.Charset)
	fmt.Println("enc:", enc)
	if enc == nil {
		// 直接返回原始字符串
		fmt.Println("Unsupported charset:", result.Charset)
		return s
	}

	// 3. 转换为 UTF-8
	rd := transform.NewReader(bytes.NewReader([]byte(s)), enc.NewDecoder())
	utf8Bytes, err := io.ReadAll(rd)
	if err != nil {
		fmt.Println("Encoding conversion failed:", err)
		return s
	}

	// 4. 返回转换后的 UTF-8 字符串
	return string(utf8Bytes)
}

// 根据字符集名称获取 `encoding.Encoding`
func getEncoding(charset string) encoding.Encoding {
	switch charset {
	case "UTF-8", "ASCII":
		return encoding.Nop // 无需转换
	case "ISO-8859-1":
		return charmap.ISO8859_1
	case "ISO-8859-2":
		return charmap.ISO8859_2
	case "ISO-8859-15":
		return charmap.ISO8859_15
	case "Windows-1252":
		return charmap.Windows1252
	case "Big5":
		return traditionalchinese.Big5
	case "GB-2312", "GBK", "GB-18030":
		return simplifiedchinese.GBK
	case "Shift_JIS":
		return japanese.ShiftJIS
	case "EUC-JP":
		return japanese.EUCJP
	case "EUC-KR":
		return korean.EUCKR
	case "UTF-16LE":
		return unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM)
	case "UTF-16BE":
		return unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM)
	default:
		return nil
	}
}

func Trim(s string) string {
	return strings.Trim(s, " \r\n\t")
}