如何计算子字符串的出现次数？ [复制]
Posted
技术标签:
【中文标题】如何计算子字符串的出现次数？ [复制]【英文标题】：How to count of sub-string occurrences? [duplicate] 【发布时间】：2013-03-12 17:31:14 【问题描述】：假设我有一个像这样的字符串：
MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
然后我想知道这个字符串中子字符串“OU=”出现了多少次。使用单个字符，也许有类似的东西：
int count = MyString.Split("OU=").Length - 1;
但Split 仅适用于char，不适用于string。
另外如何找到n次出现的位置？比如第二个"OU="在字符串中的位置？
如何解决这个问题？
【问题讨论】：
String.Split 有几个重载允许您按字符串拆分。见msdn.microsoft.com/en-us/library/tabh47cf.aspx
split 不适用于字符...
您可以使用 Multiple Delim 完成此操作 我非常乐意为您发布一个简单的编码示例以供将来使用。 and Split does work on a stringRemember that Split() returns an Array so in the case of string it would return string[] you would need to create new string[] "somestring", "someotherString"..etc..
【参考方案1】：
Regex.Matches(input, "OU=").Count
【讨论】：
谢谢。还有如何找到n次出现的位置？比如字符串中第二次“OU=”的位置？ 戳了一下，发现这个问题应该可以帮助你：***.com/questions/767767/… 一般来说，如果要匹配的子字符串包含正则表达式字符怎么办？ Regex.Matches(input, Regex.Escape(subString)).Count 适用于所有可能的子字符串。 一般来说使用Regex.Escape(...)是明智的，所以抽象版本：Regex.Matches(input, Regex.Escape("string_which_isnt_a_regex")).Count
以字符串aaaaaa和子字符串aa为例。这个答案产生的计数为 3，其中子字符串 aa 的实际计数为 5。【参考方案2】：
您可以使用IndexOf 找到所有出现及其位置：
string MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
string stringToFind = "OU=";
List<int> positions = new List<int>();
int pos = 0;
while ((pos < MyString.Length) && (pos = MyString.IndexOf(stringToFind, pos)) != -1)
positions.Add(pos);
pos += stringToFind.Length();
Console.WriteLine("0 occurrences", positions.Count);
foreach (var p in positions)
Console.WriteLine(p);
你可以从一个正则表达式得到同样的结果：
var matches = Regex.Matches(MyString, "OU=");
Console.WriteLine("0 occurrences", matches.Count);
foreach (var m in matches)
Console.WriteLine(m.Index);
主要区别：
正则表达式代码更短 Regex 代码分配一个集合和多个字符串。 可以编写 IndexOf 代码以立即输出位置，而无需创建集合。 Regex 代码在隔离时可能会更快，但如果多次使用，字符串分配的综合开销可能会导致垃圾收集器的负载更高。如果我是在线编写这个不经常使用的东西，我可能会使用正则表达式解决方案。如果我将它作为经常使用的东西放入库中，我可能会选择 IndexOf 解决方案。
【讨论】：
小错字？列表（剪辑模式：开启）
您似乎正在解析 LDAP 查询！
你想解析它吗：
手动？转到“SplittingAndParsing” 自动通过 Win32 调用？转到“通过 PInvoke 使用 Win32”（剪辑模式：关闭）
“SplittingAndParsing”：
var MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
var chunksAsKvps = MyString
.Split(',')
.Select(chunk =>
var bits = chunk.Split('=');
return new KeyValuePair<string,string>(bits[0], bits[1]);
);
var allOUs = chunksAsKvps
.Where(kvp => kvp.Key.Equals("OU", StringComparison.OrdinalIgnoreCase));
“通过 PInvoke 使用 Win32”：
用法：
var parsedDn = Win32LDAP.ParseDN(str);
var allOUs2 = parsedDn
.Where(dn => dn.Key.Equals("OU", StringComparison.OrdinalIgnoreCase));
实用程序代码：
// I don't remember where I got this from, honestly...I *think* it came
// from another SO user long ago, but those details I've lost to history...
public class Win32LDAP
#region Constants
public const int ERROR_SUCCESS = 0;
public const int ERROR_BUFFER_OVERFLOW = 111;
#endregion Constants
#region DN Parsing
[DllImport("ntdsapi.dll", CharSet = CharSet.Unicode)]
protected static extern int DsGetRdnW(
ref IntPtr ppDN,
ref int pcDN,
out IntPtr ppKey,
out int pcKey,
out IntPtr ppVal,
out int pcVal
);
public static KeyValuePair<string, string> GetName(string distinguishedName)
IntPtr pDistinguishedName = Marshal.StringToHGlobalUni(distinguishedName);
try
IntPtr pDN = pDistinguishedName, pKey, pVal;
int cDN = distinguishedName.Length, cKey, cVal;
int lastError = DsGetRdnW(ref pDN, ref cDN, out pKey, out cKey, out pVal, out cVal);
if(lastError == ERROR_SUCCESS)
string key, value;
if(cKey < 1)
key = string.Empty;
else
key = Marshal.PtrToStringUni(pKey, cKey);
if(cVal < 1)
value = string.Empty;
else
value = Marshal.PtrToStringUni(pVal, cVal);
return new KeyValuePair<string, string>(key, value);
else
throw new Win32Exception(lastError);
finally
Marshal.FreeHGlobal(pDistinguishedName);
public static IEnumerable<KeyValuePair<string, string>> ParseDN(string distinguishedName)
List<KeyValuePair<string, string>> components = new List<KeyValuePair<string, string>>();
IntPtr pDistinguishedName = Marshal.StringToHGlobalUni(distinguishedName);
try
IntPtr pDN = pDistinguishedName, pKey, pVal;
int cDN = distinguishedName.Length, cKey, cVal;
do
int lastError = DsGetRdnW(ref pDN, ref cDN, out pKey, out cKey, out pVal, out cVal);
if(lastError == ERROR_SUCCESS)
string key, value;
if(cKey < 0)
key = null;
else if(cKey == 0)
key = string.Empty;
else
key = Marshal.PtrToStringUni(pKey, cKey);
if(cVal < 0)
value = null;
else if(cVal == 0)
value = string.Empty;
else
value = Marshal.PtrToStringUni(pVal, cVal);
components.Add(new KeyValuePair<string, string>(key, value));
pDN = (IntPtr)(pDN.ToInt64() + UnicodeEncoding.CharSize); //skip over comma
cDN--;
else
throw new Win32Exception(lastError);
while(cDN > 0);
return components;
finally
Marshal.FreeHGlobal(pDistinguishedName);
[DllImport("ntdsapi.dll", CharSet = CharSet.Unicode)]
protected static extern int DsQuoteRdnValueW(
int cUnquotedRdnValueLength,
string psUnquotedRdnValue,
ref int pcQuotedRdnValueLength,
IntPtr psQuotedRdnValue
);
public static string QuoteRDN(string rdn)
if (rdn == null) return null;
int initialLength = rdn.Length;
int quotedLength = 0;
IntPtr pQuotedRDN = IntPtr.Zero;
int lastError = DsQuoteRdnValueW(initialLength, rdn, ref quotedLength, pQuotedRDN);
switch (lastError)
case ERROR_SUCCESS:
return string.Empty;
case ERROR_BUFFER_OVERFLOW:
break; //continue
default:
throw new Win32Exception(lastError);
pQuotedRDN = Marshal.AllocHGlobal(quotedLength * UnicodeEncoding.CharSize);
try
lastError = DsQuoteRdnValueW(initialLength, rdn, ref quotedLength, pQuotedRDN);
switch(lastError)
case ERROR_SUCCESS:
return Marshal.PtrToStringUni(pQuotedRDN, quotedLength);
default:
throw new Win32Exception(lastError);
finally
if(pQuotedRDN != IntPtr.Zero)
Marshal.FreeHGlobal(pQuotedRDN);
[DllImport("ntdsapi.dll", CharSet = CharSet.Unicode)]
protected static extern int DsUnquoteRdnValueW(
int cQuotedRdnValueLength,
string psQuotedRdnValue,
ref int pcUnquotedRdnValueLength,
IntPtr psUnquotedRdnValue
);
public static string UnquoteRDN(string rdn)
if (rdn == null) return null;
int initialLength = rdn.Length;
int unquotedLength = 0;
IntPtr pUnquotedRDN = IntPtr.Zero;
int lastError = DsUnquoteRdnValueW(initialLength, rdn, ref unquotedLength, pUnquotedRDN);
switch (lastError)
case ERROR_SUCCESS:
return string.Empty;
case ERROR_BUFFER_OVERFLOW:
break; //continue
default:
throw new Win32Exception(lastError);
pUnquotedRDN = Marshal.AllocHGlobal(unquotedLength * UnicodeEncoding.CharSize);
try
lastError = DsUnquoteRdnValueW(initialLength, rdn, ref unquotedLength, pUnquotedRDN);
switch(lastError)
case ERROR_SUCCESS:
return Marshal.PtrToStringUni(pUnquotedRDN, unquotedLength);
default:
throw new Win32Exception(lastError);
finally
if(pUnquotedRDN != IntPtr.Zero)
Marshal.FreeHGlobal(pUnquotedRDN);
#endregion DN Parsing
public class DNComponent
public string Type get; protected set;
public string EscapedValue get; protected set;
public string UnescapedValue get; protected set;
public string WholeComponent get; protected set;
public DNComponent(string component, bool isEscaped)
string[] tokens = component.Split(new char[] '=' , 2);
setup(tokens[0], tokens[1], isEscaped);
public DNComponent(string key, string value, bool isEscaped)
setup(key, value, isEscaped);
private void setup(string key, string value, bool isEscaped)
Type = key;
if(isEscaped)
EscapedValue = value;
UnescapedValue = Win32LDAP.UnquoteRDN(value);
else
EscapedValue = Win32LDAP.QuoteRDN(value);
UnescapedValue = value;
WholeComponent = Type + "=" + EscapedValue;
public override bool Equals(object obj)
if (obj is DNComponent)
DNComponent dnObj = (DNComponent)obj;
return dnObj.WholeComponent.Equals(this.WholeComponent, StringComparison.CurrentCultureIgnoreCase);
return base.Equals(obj);
public override int GetHashCode()
return WholeComponent.GetHashCode();
public class DistinguishedName
public DNComponent[] Components
get
return components.ToArray();
private List<DNComponent> components;
private string cachedDN;
public DistinguishedName(string distinguishedName)
cachedDN = distinguishedName;
components = new List<DNComponent>();
foreach (KeyValuePair<string, string> kvp in Win32LDAP.ParseDN(distinguishedName))
components.Add(new DNComponent(kvp.Key, kvp.Value, true));
public DistinguishedName(IEnumerable<DNComponent> dnComponents)
components = new List<DNComponent>(dnComponents);
cachedDN = GetWholePath(",");
public bool Contains(DNComponent dnComponent)
return components.Contains(dnComponent);
public string GetDNSDomainName()
List<string> dcs = new List<string>();
foreach (DNComponent dnc in components)
if(dnc.Type.Equals("DC", StringComparison.CurrentCultureIgnoreCase))
dcs.Add(dnc.UnescapedValue);
return string.Join(".", dcs.ToArray());
public string GetDomainDN()
List<string> dcs = new List<string>();
foreach (DNComponent dnc in components)
if(dnc.Type.Equals("DC", StringComparison.CurrentCultureIgnoreCase))
dcs.Add(dnc.WholeComponent);
return string.Join(",", dcs.ToArray());
public string GetWholePath()
return GetWholePath(",");
public string GetWholePath(string separator)
List<string> parts = new List<string>();
foreach (DNComponent component in components)
parts.Add(component.WholeComponent);
return string.Join(separator, parts.ToArray());
public DistinguishedName GetParent()
if(components.Count == 1)
return null;
List<DNComponent> tempList = new List<DNComponent>(components);
tempList.RemoveAt(0);
return new DistinguishedName(tempList);
public override bool Equals(object obj)
if(obj is DistinguishedName)
DistinguishedName objDN = (DistinguishedName)obj;
if (this.Components.Length == objDN.Components.Length)
for (int i = 0; i < this.Components.Length; i++)
if (!this.Components[i].Equals(objDN.Components[i]))
return false;
return true;
return false;
return base.Equals(obj);
public override int GetHashCode()
return cachedDN.GetHashCode();
【讨论】：
【参考方案4】：这个扩展比正则表达式需要更少的资源。
public static int CountSubstring(this string text, string value)
int count = 0, minIndex = text.IndexOf(value, 0);
while (minIndex != -1)
minIndex = text.IndexOf(value, minIndex + value.Length);
count++;
return count;
用法：
MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
int count = MyString.CountSubstring("OU=");
【讨论】：
【参考方案5】：下面应该可以工作
MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
int count = Regex.Matches(MyString, "OU=").Count
【讨论】：
【参考方案6】：int count = myString.Split(new []',')
.Count(item => item.StartsWith(
"OU=", StringComparison.OrdinalIgnoreCase))
【讨论】：
不要自吹自擂，但这取决于逗号分隔。当然，它适用于这种非常具体的场景，但我的正则表达式解决方案更简单、更动态。 是的，我同意，只是提供一个替代方案。 当然，我很感激。 +1【参考方案7】：这里有两个示例说明如何获得所需的结果
var MyString = "OU=Level3,OU=Level2,OU=Level1,DC=domain,DC=com";
这个你会看到一个分隔的值列表，但它会让 DC 只是一个想法 表明使用 String 的拆分确实有效`
var split = MyString.Split(new string[] "OU=", "," , StringSplitOptions.RemoveEmptyEntries);
这将拆分并将仅 3 个项目返回到一个列表中，这样如果您不依赖计数，您可以直观地验证它返回 3 个级别的 `OU=``
var lstSplit = MyString.Split(new[] ',' )
.Where(splitItem => splitItem.StartsWith(
"OU=", StringComparison.OrdinalIgnoreCase)).ToList();
【讨论】：
【参考方案8】：public static int CountOccurences(string needle, string haystack)
return (haystack.Length - haystack.Replace(needle, "").Length) / needle.Length;
将其与此处的其他答案（正则表达式之一和“IndexOf”之一）进行基准测试，运行速度更快。
【讨论】：
那只是***.com/questions/541954/…的副本至少添加一个参考以上是关于如何计算子字符串的出现次数？ [复制]的主要内容，如果未能解决你的问题，请参考以下文章