public static class SomeString
{
/// <summary>
/// 根据中英文 截取字符 (慎用!)
/// </summary>
/// <param name="obj"></param>
/// <param name="count">截取的长度,注意:长度为英文长度,即一汉字等于二英文长度</param>
/// <returns></returns>
public static string ToSomeString(this object obj, int count = 0)
{
string str = obj.ToString();
if (count == 0)
return string.Empty;
int temp = 0;
//中文 英文 字符
string ptn = "[a-zA-Z]+|[0-9]+|[\u4e00-\u9fa5]+|[^a-zA-Z0-9\u4e00-\u9fa5]+"; //"[\u4e00-\u9fa5]+|[a-zA-Z\\s]+";
System.Text.RegularExpressions.Regex reg = new System.Text.RegularExpressions.Regex(ptn);
//匹配中文
System.Text.RegularExpressions.Regex regTemp = new System.Text.RegularExpressions.Regex("[\u4e00-\u9fa5]+");
List<string> list = new List<string>();
for (int i = 0; i < reg.Matches(str).Count; i++)
{
string value = reg.Matches(str)[i].Value;
//中文
if (!string.IsNullOrWhiteSpace(regTemp.Match(value).Value))
{
//判断当前字符长度是否已经超过截取长度
if (value.Length * 2 <= count - temp)
{
list.Add(value);
}
else
{
if (temp < count)
list.Add(value.Substring(0, ((count - temp) / 2)) + "…");
}
temp += value.Length * 2;
}
else
{
if (value.Length <= count - temp)
{
list.Add(value);
}
else
{
if (temp < count)
list.Add(value.Substring(0, (count - temp)) + "…");
}
temp += value.Length;
}
}
System.Text.StringBuilder sb = new System.Text.StringBuilder();
foreach (string a in list)
{
sb.Append(a);
}
return sb.ToString();
}
}
主要思想:用正则表达式匹配字符段,讲不同编码的字符分割开,然后根据字节长度,逐个处理,然后添加到字符串中,如果长度大约限定长度,则截取,并追加"..."。