最近在做项目时,碰到含有中英文混在一起的字符串,而存入数据库(DB2)又是限定长度的,找到了一个比较好的截取指定长度中英文字符方法:
#region 截取指定长度中英文字符串
/// <summary>
/// 截取指定长度中英文字符串
/// </summary>
/// <param name="stringToSub">字符串</param>
/// <param name="length">截取长度</param>
/// <returns>返回字符串</returns>
public static string FormatString(string stringToSub, int length)
{
Regex regex = new Regex("[\u4e00-\u9fa5]+", RegexOptions.Compiled);
char[] stringChar = stringToSub.ToCharArray();
StringBuilder sb = new StringBuilder();
int nLength = 0;
for (int i = 0; i < stringChar.Length; i++)
{
if (nLength == length - 1)
{
if (regex.IsMatch((stringChar[i]).ToString()))
{
break;
}
}
if (regex.IsMatch((stringChar[i]).ToString()))
{
sb.Append(stringChar[i]);
nLength += 2;
}
else
{
sb.Append(stringChar[i]);
nLength = nLength + 1;
}
if (nLength >= length)
{
break;
}
}
return sb.ToString();
}
#endregion