SiteFactory 通用程序集中(PowerEasy.Common)的常用字符串处理函数
以下是常用字符处理类StringHelper的各方法,这里给方法添加了简单的注释
---------------------
/// <summary>
/// 使用逗号分割符,扩充字符串
/// </summary>
/// <param name="sb"></param>
/// <param name="append"></param>
public static void AppendString(StringBuilder sb, string append)
{
AppendString(sb, append, ",");
}
/// <summary>
/// 使用分割符,扩充字符串
/// </summary>
/// <param name="sb"></param>
/// <param name="append"></param>
/// <param name="split"></param>
public static void AppendString(StringBuilder sb, string append, string split)
{
if (sb.Length == 0)
{
sb.Append(append);
}
else
{
sb.Append(split);
sb.Append(append);
}
}
/// <summary>
/// 从Base64字符串中还原字符串
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string Base64StringDecode(string input)
{
byte[] bytes = Convert.FromBase64String(input);
return Encoding.UTF8.GetString(bytes);
}
/// <summary>
/// 将字符串保存为Base64编码序列
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string Base64StringEncode(string input)
{
return Convert.ToBase64String(Encoding.UTF8.GetBytes(input));
}
/// <summary>
/// 将使用long表示的Ip转换为字符串表示
/// </summary>
/// <param name="ip"></param>
/// <returns></returns>
public static string DecodeIP(long ip)
{
string[] strArray = new string[] { ((ip >> 0x18) & 0xffL).ToString(), ".", ((ip >> 0x10) & 0xffL).ToString(), ".", ((ip >> 8) & 0xffL).ToString(), ".", (ip & 0xffL).ToString() };
return string.Concat(strArray);
}
/// <summary>
/// 将使用字符串表示的IP转换为使用数字值
/// </summary>
/// <param name="sip"></param>
/// <returns></returns>
public static double EncodeIP(string sip)
{
if (string.IsNullOrEmpty(sip))
{
return 0.0;
}
string[] strArray = sip.Split(new char[] { '.' });
long num = 0L;
foreach (string str in strArray)
{
byte num2;
if (byte.TryParse(str, out num2))
{
num = (num << 8) | num2;
}
else
{
return 0.0;
}
}
return num;
}
/// <summary>
/// 过滤标签,正则匹配时使用非贪婪模式
/// </summary>
/// <param name="conStr">待处理的文本数据</param>
/// <param name="tagName">标签名称如,html,Script等</param>
/// <param name="fType">过滤方式,可以取(1|2|3)
/// 1:是单个标签如img等,
/// 2:表示配对出现的标签如div等将清除此标签已经标签内的全部文本,
/// 3:表示也是针对配对出现的标签,但是保留标签内的内容.
/// </param>
/// <returns></returns>
public static string CollectionFilter(string conStr, string tagName, int fType)
{
string input = conStr;
switch (fType)
{
case 1:
return Regex.Replace(input, "<" + tagName + "([^>])*>", "", RegexOptions.IgnoreCase);
case 2:
return Regex.Replace(input, "<" + tagName + "([^>])*>.*?</" + tagName + "([^>])*>", "", RegexOptions.IgnoreCase);
case 3:
return Regex.Replace(Regex.Replace(input, "<" + tagName + "([^>])*>", "", RegexOptions.IgnoreCase), "</" + tagName + "([^>])*>", "", RegexOptions.IgnoreCase);
}
return input;
}
/// <summary>
/// 过滤指定的标签
/// </summary>
/// <param name="conStr">待过滤文本数据</param>
/// <param name="filterItem">需要过滤的列表用","阁开如:Iframe,Object,Style,Script,Div</param>
/// <returns></returns>
public static string FilterScript(string conStr, string filterItem)
{
string str = conStr.Replace("\r", "{$Chr13}").Replace("\n", "{$Chr10}");
string[] strArray = filterItem.Split(new char[] { ',' }, StringSplitOptions.RemoveEmptyEntries);
foreach (string str2 in strArray)
{
switch (str2)
{
case "Iframe":
str = CollectionFilter(str, str2, 2);
break;
case "Object":
str = CollectionFilter(str, str2, 2);
break;
case "Script":
str = CollectionFilter(str, str2, 2);
break;
case "Style":
str = CollectionFilter(str, str2, 2);
break;
case "Div":
str = CollectionFilter(str, str2, 3);
break;
case "Span":
str = CollectionFilter(str, str2, 3);
break;
case "Table":
str = CollectionFilter(CollectionFilter(CollectionFilter(CollectionFilter(CollectionFilter(str, str2, 3), "Tbody", 3), "Tr", 3), "Td", 3), "Th", 3);
break;
case "Img":
str = CollectionFilter(str, str2, 1);
break;
case "Font":
str = CollectionFilter(str, str2, 3);
break;
case "A":
str = CollectionFilter(str, str2, 3);
break;
case "Html":
str = StripTags(str);
goto Label_0218;
}
}
Label_0218:
return str.Replace("{$Chr13}", "\r").Replace("{$Chr10}", "\n");
}
public static bool FoundCharInArr(string checkStr, string findStr)
{
return FoundCharInArr(checkStr, findStr, ",");
}
public static bool FoundCharInArr(string checkStr, string findStr, string split)
{
bool flag = false;
if (string.IsNullOrEmpty(split))
{
split = ",";
}
if (string.IsNullOrEmpty(checkStr))
{
return false;
}
if (checkStr.IndexOf(split) != -1)
{
string[] strArray;
if (findStr.IndexOf(split) != -1)
{
strArray = checkStr.Split(new char[] { Convert.ToChar(split) });
string[] strArray2 = findStr.Split(new char[] { Convert.ToChar(split) });
foreach (string str in strArray)
{
foreach (string str2 in strArray2)
{
if (string.Compare(str, str2) == 0)
{
flag = true;
break;
}
}
if (flag)
{
return flag;
}
}
return flag;
}
strArray = checkStr.Split(new char[] { Convert.ToChar(split) });
foreach (string str in strArray)
{
if (string.Compare(str, findStr) == 0)
{
return true;
}
}
return flag;
}
if (string.Compare(checkStr, findStr) == 0)
{
flag = true;
}
return flag;
}
/// <summary>
/// 在字符串序列中(使用分割符连接的)查找指定值
/// </summary>
/// <param name="checkStr"></param>
/// <param name="findStr"></param>
/// <param name="split"></param>
/// <returns></returns>
public static bool FoundInArr(string checkStr, string findStr, string split)
{
bool flag = false;
if (checkStr.IndexOf(findStr) != -1)
{
string[] strArray = checkStr.Split(new string[] { split }, StringSplitOptions.RemoveEmptyEntries);
foreach (string str in strArray)
{
if (string.Compare(str, findStr) == 0)
{
return true;
}
}
return flag;
}
if (string.Compare(checkStr, findStr) == 0)
{
flag = true;
}
return flag;
}
/// <summary>
/// 返回字符串首字符,如果字符串首字符是汉字则返回其拼音的第一个字符(A-Z)
/// </summary>
/// <param name="testTxt"></param>
/// <returns></returns>
private static string GetGbkX(string testTxt)
{
if (testTxt.CompareTo("吖") >= 0)
{
if (testTxt.CompareTo("八") < 0)
{
return "A";
}
if (testTxt.CompareTo("嚓") < 0)
{
return "B";
}
if (testTxt.CompareTo("咑") < 0)
{
return "C";
}
if (testTxt.CompareTo("妸") < 0)
{
return "D";
}
if (testTxt.CompareTo("发") < 0)
{
return "E";
}
if (testTxt.CompareTo("旮") < 0)
{
return "F";
}
if (testTxt.CompareTo("铪") < 0)
{
return "G";
}
if (testTxt.CompareTo("讥") < 0)
{
return "H";
}
if (testTxt.CompareTo("咔") < 0)
{
return "J";
}
if (testTxt.CompareTo("垃") < 0)
{
return "K";
}
if (testTxt.CompareTo("嘸") < 0)
{
return "L";
}
if (testTxt.CompareTo("拏") < 0)
{
return "M";
}
if (testTxt.CompareTo("噢") < 0)
{
return "N";
}
if (testTxt.CompareTo("妑") < 0)
{
return "O";
}
if (testTxt.CompareTo("七") < 0)
{
return "P";
}
if (testTxt.CompareTo("亽") < 0)
{
return "Q";
}
if (testTxt.CompareTo("仨") < 0)
{
return "R";
}
if (testTxt.CompareTo("他") < 0)
{
return "S";
}
if (testTxt.CompareTo("哇") < 0)
{
return "T";
}
if (testTxt.CompareTo("夕") < 0)
{
return "W";
}
if (testTxt.CompareTo("丫") < 0)
{
return "X";
}
if (testTxt.CompareTo("帀") < 0)
{
return "Y";
}
if (testTxt.CompareTo("咗") < 0)
{
return "Z";
}
}
return testTxt;
}
/// <summary>
/// 返回字串的拼音首字母序列(字串中的英文直接返回)
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static string GetInitial(string str)
{
StringBuilder builder = new StringBuilder();
for (int i = 0; i < str.Length; i++)
{
builder.Append(GetOneIndex(str.Substring(i, 1)));
}
return builder.ToString();
}
private static string GetOneIndex(string testTxt)
{
if ((Convert.ToChar(testTxt) >= '\0') && (Convert.ToChar(testTxt) < 'Ā'))
{
return testTxt;
}
return GetGbkX(testTxt);
}
/// <summary>
/// 是否包含中文
/// </summary>
/// <param name="inputData"></param>
/// <returns></returns>
public static bool IsIncludeChinese(string inputData)
{
Regex regex = new Regex("[一-龥]");
return regex.Match(inputData).Success;
}
/// <summary>
/// 计算MD5散列
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string MD5(string input)
{
using (MD5CryptoServiceProvider provider = new MD5CryptoServiceProvider())
{
return BitConverter.ToString(provider.ComputeHash(Encoding.UTF8.GetBytes(input))).Replace("-", "").ToLower();
}
}
public static int MD5D(string strText)
{
using (MD5CryptoServiceProvider provider = new MD5CryptoServiceProvider())
{
byte[] bytes = Encoding.Default.GetBytes(strText);
bytes = provider.ComputeHash(bytes);
StringBuilder builder = new StringBuilder();
foreach (byte num in bytes)
{
builder.Append(num.ToString("D").ToLower());
}
string input = builder.ToString();
if (input.Length >= 9)
{
input = "9" + input.Substring(1, 8);
}
else
{
input = "9" + input;
}
provider.Clear();
return CLng(input);
}
}
private static int CLng(string input)
{
int num;
int.TryParse(input, out num);
return num;
}
/// <summary>
/// 使用GB2312编码来计算字符号的MD5值,返回32位序列
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string MD5gb2312(string input)
{
using (MD5CryptoServiceProvider provider = new MD5CryptoServiceProvider())
{
return BitConverter.ToString(provider.ComputeHash(Encoding.GetEncoding("gb2312").GetBytes(input))).Replace("-", "").ToLower();
}
}
public static string RemoveXss(string input)
{
string str;
input = Regex.Replace(input, @"(&#*\w+)[\x00-\x20]+;", "$1;");
input = Regex.Replace(input, "(&#x*[0-9A-F]+);*", "$1;", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "&(amp|lt|gt|nbsp|quot);", "&$1;");
input = HttpUtility.HtmlDecode(input);
input = Regex.Replace(input, @"[\x00-\x08\x0b-\x0c\x0e-\x19]", "");
input = Regex.Replace(input, "(<[^>]+[\\x00-\\x20\"'/])(on|xmlns)[^>]*>", "$1>", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "([a-z]*)[\\x00-\\x20]*=[\\x00-\\x20]*([`'\"]*)[\\x00-\\x20]*j[\\x00-\\x20]*a[\\x00-\\x20]*v[\\x00-\\x20]*a[\\x00-\\x20]*s[\\x00-\\x20]*c[\\x00-\\x20]*r[\\x00-\\x20]*i[\\x00-\\x20]*p[\\x00-\\x20]*t[\\x00-\\x20]*:", "$1=$2nojavascript...", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "([a-z]*)[\\x00-\\x20]*=[\\x00-\\x20]*([`'\"]*)[\\x00-\\x20]*v[\\x00-\\x20]*b[\\x00-\\x20]*s[\\x00-\\x20]*c[\\x00-\\x20]*r[\\x00-\\x20]*i[\\x00-\\x20]*p[\\x00-\\x20]*t[\\x00-\\x20]*:", "$1=$2novbscript...", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "(<[^>]+)style[\\x00-\\x20]*=[\\x00-\\x20]*([`'\"]*).*expression[\\x00-\\x20]*\\([^>]*>", "$1>", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "(<[^>]+)style[\\x00-\\x20]*=[\\x00-\\x20]*([`'\"]*).*behaviour[\\x00-\\x20]*\\([^>]*>", "$1>", RegexOptions.IgnoreCase);
input = Regex.Replace(input, "(<[^>]+)style[\\x00-\\x20]*=[\\x00-\\x20]*([`'\"]*).*s[\\x00-\\x20]*c[\\x00-\\x20]*r[\\x00-\\x20]*i[\\x00-\\x20]*p[\\x00-\\x20]*t[\\x00-\\x20]*:*[^>]*>", "$1>", RegexOptions.IgnoreCase);
input = Regex.Replace(input, @"</*\w+:\w[^>]*>", "");
do
{
str = input;
input = Regex.Replace(input, "</*(applet|meta|xml|blink|link|style|script|embed|object|iframe|frame|frameset|ilayer|layer|bgsound|title|base)[^>]*>", "", RegexOptions.IgnoreCase);
}
while (str != input);
return input;
}
/// <summary>
/// 不区分大小写来替换字符串
/// </summary>
/// <param name="input"></param>
/// <param name="oldValue"></param>
/// <param name="newValue"></param>
/// <returns></returns>
public static string ReplaceIgnoreCase(string input, string oldValue, string newValue)
{
return Strings.Replace(input, oldValue, newValue, 1, -1, CompareMethod.Text);
}
/// <summary>
/// 使用SHA1计算字符串的散列值
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string SHA1(string input)
{
using (SHA1CryptoServiceProvider provider = new SHA1CryptoServiceProvider())
{
return BitConverter.ToString(provider.ComputeHash(Encoding.UTF8.GetBytes(input))).Replace("-", "").ToLower();
}
}
/// <summary>
/// 过滤使用使用尖括号括起来的标签,不包括全部HTML定义如( 等实体)
/// </summary>
/// <param name="input"></param>
/// <returns></returns>
public static string StripTags(string input)
{
Regex regex = new Regex("<([^<]|\n)+?>");
return regex.Replace(input, "");
}
/// <summary>
/// 按汉字计2,其他字符计1来取指定长度字符号串
/// </summary>
/// <param name="demand">需要截断的字符串</param>
/// <param name="length">需要的长度</param>
/// <param name="substitute">省略后替代的字符如:"..."等</param>
/// <returns></returns>
public static string SubString(string demand, int length, string substitute)
{
if (Encoding.Default.GetBytes(demand).Length <= length)
{
return demand;
}
ASCIIEncoding encoding = new ASCIIEncoding();
length -= Encoding.Default.GetBytes(substitute).Length;
int num = 0;
StringBuilder builder = new StringBuilder();
byte[] bytes = encoding.GetBytes(demand);
for (int i = 0; i < bytes.Length; i++)
{
if (bytes[i] == 0x3f)
{
num += 2;
}
else
{
num++;
}
if (num > length)
{
break;
}
builder.Append(demand.Substring(i, 1));
}
builder.Append(substitute);
return builder.ToString();
}
/// <summary>
/// 返回字串长度,中文字符为计2,其他计1
/// 使用ASCII将字符串转化为字节数组时(byte[]),数组长度跟字符串长度相同
/// 非中文字符取其ASCII码,中文ASCII码为63即?(十六进制为0x3F)
/// </summary>
/// <param name="strValue"></param>
/// <returns></returns>
public static int StringLength(string strValue)
{
if (string.IsNullOrEmpty(strValue))
{
return 0;
}
int num = 0;
byte[] bytes = Encoding.ASCII.GetBytes(strValue);
for (int i = 0; i < bytes.Length; i++)
{
if (bytes[i] == 0x3f)
{
num += 2;
}
else
{
num++;
}
}
return num;
}
/// <summary>
/// 去除字串两边的空格,当字串为Null Or Empty时,返回 String.Empty
/// </summary>
/// <param name="returnStr"></param>
/// <returns></returns>
public static string Trim(string returnStr)
{
if (!string.IsNullOrEmpty(returnStr))
{
return returnStr.Trim();
}
return string.Empty;
}
/// <summary>
/// 将传入的password参数与md5Value参数进行比较(分别截取md5Valude的16位与32位)
/// </summary>
/// <param name="password">MD5后的哈希值</param>
/// <param name="md5Value">MD5后的哈希值</param>
/// <returns></returns>
public static bool ValidateMD5(string password, string md5Value)
{
return ((string.Compare(password, md5Value) == 0) || (string.Compare(password, md5Value.Substring(8, 0x10)) == 0));
}