eta_crawler/utils/mail/charset_reader.go

package mail

import (
	"fmt"
	"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/transform"
	"io"
	"strings"
)

var charsetMap = map[string]transform.Transformer{
	"gb2312":         simplifiedchinese.GBK.NewDecoder(),
	"gbk":            simplifiedchinese.GBK.NewDecoder(),
	"ibm037":         charmap.CodePage037.NewDecoder(),
	"ibm437":         charmap.CodePage437.NewDecoder(),
	"ibm850":         charmap.CodePage850.NewDecoder(),
	"ibm852":         charmap.CodePage852.NewDecoder(),
	"ibm855":         charmap.CodePage855.NewDecoder(),
	"ibm858":         charmap.CodePage858.NewDecoder(),
	"ibm860":         charmap.CodePage860.NewDecoder(),
	"ibm862":         charmap.CodePage862.NewDecoder(),
	"ibm863":         charmap.CodePage863.NewDecoder(),
	"ibm865":         charmap.CodePage865.NewDecoder(),
	"ibm866":         charmap.CodePage866.NewDecoder(),
	"ibm1047":        charmap.CodePage1047.NewDecoder(),
	"ibm1140":        charmap.CodePage1140.NewDecoder(),
	"iso-8859-1":     charmap.ISO8859_1.NewDecoder(),
	"iso-8859-2":     charmap.ISO8859_2.NewDecoder(),
	"iso-8859-3":     charmap.ISO8859_3.NewDecoder(),
	"iso-8859-4":     charmap.ISO8859_4.NewDecoder(),
	"iso-8859-5":     charmap.ISO8859_5.NewDecoder(),
	"iso-8859-6":     charmap.ISO8859_6.NewDecoder(),
	"iso-8859-7":     charmap.ISO8859_7.NewDecoder(),
	"iso-8859-8":     charmap.ISO8859_8.NewDecoder(),
	"iso-8859-9":     charmap.ISO8859_9.NewDecoder(),
	"iso-8859-10":    charmap.ISO8859_10.NewDecoder(),
	"iso-8859-13":    charmap.ISO8859_13.NewDecoder(),
	"iso-8859-14":    charmap.ISO8859_14.NewDecoder(),
	"iso-8859-15":    charmap.ISO8859_15.NewDecoder(),
	"iso-8859-16":    charmap.ISO8859_16.NewDecoder(),
	"koi8-r":         charmap.KOI8R.NewDecoder(),
	"koi8-u":         charmap.KOI8U.NewDecoder(),
	"macintosh":      charmap.Macintosh.NewDecoder(),
	"x-mac-cyrillic": charmap.MacintoshCyrillic.NewDecoder(),
	"windows-874":    charmap.Windows874.NewDecoder(),
	"windows-1250":   charmap.Windows1250.NewDecoder(),
	"windows-1251":   charmap.Windows1251.NewDecoder(),
	"windows-1252":   charmap.Windows1252.NewDecoder(),
	"windows-1253":   charmap.Windows1253.NewDecoder(),
	"windows-1254":   charmap.Windows1254.NewDecoder(),
	"windows-1255":   charmap.Windows1255.NewDecoder(),
	"windows-1257":   charmap.Windows1257.NewDecoder(),
	"windows-1258":   charmap.Windows1258.NewDecoder(),
	"x-user-defined": charmap.XUserDefined.NewDecoder(),
	"euc-jp":         japanese.EUCJP.NewDecoder(),
	"iso-2022-jp":    japanese.ISO2022JP.NewDecoder(),
	"shift_jis":      japanese.ShiftJIS.NewDecoder(),
	"ks_c_5601-1987": korean.EUCKR.NewDecoder(),
	"euc-kr":         korean.EUCKR.NewDecoder(),
}

// 定义一个自定义的 CharsetReader 函数，它能够处理 gb2312 和 gbk 字符集
func myCharsetReader(charset string, input io.Reader) (io.Reader, error) {
	charset = strings.ToLower(charset)
	newDecoder, ok := charsetMap[charset]
	if ok {
		reader := transform.NewReader(input, newDecoder)
		return reader, nil
	}
	if charset == `utf-8` {
		return input, nil
	}

	switch strings.ToLower(charset) {
	case "gb2312", "gbk":
		reader := transform.NewReader(input, simplifiedchinese.GBK.NewDecoder())
		return reader, nil
	case "utf-8":
		return input, nil
	case "iso-8859-1":
		reader := transform.NewReader(input, charmap.ISO8859_1.NewDecoder())

		return reader, nil
	case "windows-1252":
		reader := transform.NewReader(input, charmap.Windows1252.NewDecoder())
		return reader, nil
	default:
	}
	return input, fmt.Errorf("unsupported charset: %s", charset)

}