我有一个糟糕的单词替换VB.net的脚本，导致了许多问题。经过多次反复试验后，当前代码可以正常运行，但不会过滤掉有上限的单词。
Private Function CheckForBadWords(ByVal InputString As String) As String
Dim r As Regex
Dim element As String
Dim eLength As Integer
Dim x As Integer
Dim AttachtoEnd As String
For Each element In alWordList
r = New Regex("\b" & element)
eLength = element.Length
For x = 3 To eLength - 1
AttachtoEnd = AttachtoEnd & "*"
Next
InputString = r.Replace(InputString, element, Left(element, 3) & AttachtoEnd)
AttachtoEnd = ""
Next
Return InputString
End Function
如何检查带有大写字母的单词？例如：phuck将检查Phuck或PHUCK不会被检查的位置。
我尝试过本教程，但它在C＃中，我几乎不知道VB.net： http://www.dreamincode.net/forums/topic/67129-creating-a-bad-word-filter-functionality-in-aspnet-wc%23/
添加更多细节：通过一些帮助，这似乎在多次调整之后起作用，但错误仍然存在，特别是引号和双引号或＆lt; br＆gt; s。
Private Function CheckForBadWords(ByVal InputString As String) As String
Dim starPosition As Integer = 0
Dim element As String
Dim eLength As Integer
Dim x As Integer
Dim AttachtoEnd As String
Dim strArray = InputString.Split(" ")
Dim specialChars As New List(Of String)(New String() {"@", "!", ".", ",", "(", ")", "/", "#", "$", "&", "+", "-", "_", "=", ":", "'", "*", "^", "`", "<", ">", "[", "]", "{", "}", "\", "|", ControlChars.Quote})
Dim firstChars As String = ""
Dim LastChars As String = ""
InputString = String.Empty
For Each item As String In strArray
Dim str As String = item
firstChars = String.Empty
LastChars = String.Empty
For Each ch As Char In str
If Not specialChars.Contains(ch) Then
Exit For
Else
firstChars += ch
End If
Next
For Each spChar As Char In firstChars.ToCharArray()
str = str.Trim(spChar)
Next
For i As Integer = str.Length - 1 To 0 Step -1
If Not specialChars.Contains(str(i)) Then
Exit For
Else
LastChars = str(i) + LastChars
End If
Next
For Each spChar As String In specialChars
str = str.Trim(spChar)
Next
If Not String.IsNullOrWhiteSpace(str) Then
For Each element In alWordList
If element.ToLower = str.ToLower Then
str = str.Trim()
eLength = element.Length
For x = 3 To eLength - 1
AttachtoEnd = AttachtoEnd & "*"
starPosition += 1
Next
str = str.Substring(0, str.Length - starPosition) & AttachtoEnd
End If
AttachtoEnd = ""
starPosition = 0
Next
End If
InputString += firstChars + str + LastChars & " "
Next
Return InputString
End Function
所以现在我认为最好回到正则表达式，这非常有效，只需要处理大写字母。
最后一个注释......要检查的词语是作为一个arraylist进入。
答案 0 :(得分：3)
如果你想用一个前3个字母保留的方式替换字符串中的所有＆＃34;坏单词和＃34;单词替换为phu***之类的星号，你想要比较不区分大小写的;没有内置方法。你可以用
Regex.Replace RegexOptions.IgnoreCase或Microsoft.VisualBasic.Strings.Replace与CompareMethod.Text。 但两者都有缺点，即他们会用新值替换旧值，而新值不会保留旧案例。如果这个词是PHUCK而你的＆＃34;坏词＆＃34;在列表中Phuck它将替换为Ph***而不是PH***。
由于您评论说这很重要，唯一的方法是编写自定义方法：
Module StringExtensions
<Extension()>
Public Function ReplaceBadWords(ByVal str As String, ByVal badWords As IEnumerable(Of String), ByVal comparison As StringComparison, ByVal Optional showClearTextLength As Integer = 3, ByVal Optional obfuscateChar As Char = "*"c) As String
Dim sb As StringBuilder = New StringBuilder(str)
For Each badWord As String In badWords
Dim index As Integer = str.IndexOf(badWord, comparison)
While index <> -1
Dim oldValue As String = str.Substring(index, badWord.Length)
Dim newValue As String
If badWord.Length > showClearTextLength Then
newValue = oldValue.Remove(showClearTextLength) & New String(obfuscateChar, oldValue.Length - showClearTextLength)
Else
newValue = New String(obfuscateChar, oldValue.Length)
End If
For i As Integer = index To index + newValue.Length - 1
sb(i) = newValue(i - index)
Next
index += newValue.Length
index = str.IndexOf(badWord, index, comparison)
End While
Next
Return sb.ToString()
End Function
End Module
你的（愚蠢）样本：
Dim replaced = "phuck will get check where as Phuck or PHUCK".
ReplaceBadWords({ "Phuck", "ILL" }, StringComparison.CurrentCultureIgnoreCase)
结果：
phu** w*** get check where as Phu** or PHU**
如果您有大量＆＃34;坏词＆＃34;：
，则为并行版本<Extension()>
Public Function ReplaceBadWordsParallel(ByVal str As String, ByVal badWords As IEnumerable(Of String), ByVal comparison As StringComparison, ByVal Optional showClearTextLength As Integer = 3, ByVal Optional obfuscateChar As Char = "*"c) As String
Dim sb As StringBuilder = New StringBuilder(str)
Parallel.ForEach(badWords,
Sub(badWord)
Dim index As Integer = str.IndexOf(badWord, comparison)
While index <> -1
Dim oldValue As String = str.Substring(index, badWord.Length)
Dim newValue As String
If badWord.Length > showClearTextLength Then
newValue = oldValue.Remove(showClearTextLength) & New String(obfuscateChar, oldValue.Length - showClearTextLength)
Else
newValue = New String(obfuscateChar, oldValue.Length)
End If
For i As Integer = index To index + newValue.Length - 1
sb(i) = newValue(i - index)
Next
index += newValue.Length
index = str.IndexOf(badWord, index, comparison)
End While
End Sub)
Return sb.ToString()
End Function
请注意，我还没有检查并行版本是否是线程安全的。
C＃版本如果有人有兴趣：
public static string ReplaceBadWords(this string str, IEnumerable<string> badWords, StringComparison comparison, int showClearTextLength = 3, char obfuscateChar = '*')
{
StringBuilder sb = new StringBuilder(str);
foreach (string badWord in badWords)
{
int index = str.IndexOf(badWord, comparison);
while (index != -1)
{
string oldValue = str.Substring(index, badWord.Length);
string newValue;
if (badWord.Length > showClearTextLength)
{
newValue = oldValue.Remove(showClearTextLength) + new string(obfuscateChar, oldValue.Length - showClearTextLength);
}
else
{
newValue = new string(obfuscateChar, oldValue.Length);
}
for (int i = index; i < index + newValue.Length; i++)
sb[i] = newValue[i - index];
index += newValue.Length;
index = str.IndexOf(badWord, index, comparison);
}
}
return sb.ToString();
}
答案 1 :(得分：1)
如果您的初始代码有效，只需使Regex不区分大小写：
r = New Regex("\b" & element, RegexOptions.IgnoreCase)
不区分大小写表示正则表达式不关心大写或小写。
有关详细信息，请参阅Regular Expression Options的文档。