C# 字符串與unicode互相轉換實戰案例
我就廢話不多說瞭,大傢還是直接看代碼吧~
/// <summary> /// 字符串轉Unicode /// </summary> /// <param name="source">源字符串</param> /// <returns>Unicode編碼後的字符串</returns> public static string String2Unicode(string source) { var bytes = Encoding.Unicode.GetBytes(source); var stringBuilder = new StringBuilder(); for (var i = 0; i < bytes.Length; i += 2) { stringBuilder.AppendFormat("\\u{0:x2}{1:x2}", bytes[i + 1], bytes[i]); } return stringBuilder.ToString(); } /// <summary> /// 字符串轉為UniCode碼字符串 /// </summary> /// <param name="s"></param> /// <returns></returns> public static string StringToUnicode(string s) { char[] charbuffers = s.ToCharArray(); byte[] buffer; StringBuilder sb = new StringBuilder(); for (int i = 0; i < charbuffers.Length; i++) { buffer = System.Text.Encoding.Unicode.GetBytes(charbuffers[i].ToString()); sb.Append(String.Format("\\u{0:X2}{1:X2}", buffer[1], buffer[0])); } return sb.ToString(); } /// <summary> /// Unicode字符串轉為正常字符串 /// </summary> /// <param name="srcText"></param> /// <returns></returns> public static string UnicodeToString(string srcText) { string dst = ""; string src = srcText; int len = srcText.Length / 6; for (int i = 0; i <= len - 1; i++) { string str = ""; str = src.Substring(0, 6).Substring(2); src = src.Substring(6); byte[] bytes = new byte[2]; bytes[1] = byte.Parse(int.Parse(str.Substring(0, 2), System.Globalization.NumberStyles.HexNumber).ToString()); bytes[0] = byte.Parse(int.Parse(str.Substring(2, 2), System.Globalization.NumberStyles.HexNumber).ToString()); dst += Encoding.Unicode.GetString(bytes); } return dst; }
補充:C# unicode string 轉換 codepoint
C# 的string和StringBuilder都支持使用codepoint直接構造字符串。unicode的字符串形式一般都是’\u1234’這種轉義模式。 其中‘1234’就是unicode codepoint的16進制形式。
通過計算,可以把這種形式的字符串,直接轉化為int32類型的codepoint。
/// <summary> /// Get the unicode code point /// </summary> private static int GetUnicodeCodePoint(char c1, char c2, char c3, char c4) { return UnicodeCharToInt(c1) * 0x1000 + UnicodeCharToInt(c2) * 0x100 + UnicodeCharToInt(c3) * 0x10 + UnicodeCharToInt(c4); } /// <summary> /// Single unicode char convert to int /// </summary> private static int UnicodeCharToInt(char c) { switch (c) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': return c - '0'; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': return c - 'a' + 10; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': return c - 'A' + 10; } throw new Exception(string.Format("Unicode char '{0}' error", c)); }
使用的時候codepoint需要強轉為char類型。比如:
StringBuilder sb = new StringBuilder(); sb.Append((char) GetUnicodeCodePoint(c1, c2, c3, c4));
以上為個人經驗,希望能給大傢一個參考,也希望大傢多多支持WalkonNet。如有錯誤或未考慮完全的地方,望不吝賜教。
推薦閱讀:
- C#移除字符串中的不可見Unicode字符 案例代碼
- emoji表情與unicode編碼互轉的實現(JS,JAVA,C#)
- C# Unicode編碼解碼的實現
- C# string轉換為幾種不同編碼的Byte[]的問題解讀
- C#實現Base64編碼與解碼及規則