我正在做一些事情，我意识到我想要在一个字符串中找到多少个/s，然后我突然想到，有几种方法可以做到这一点，但不能决定哪种是最好的(或最简单的)。
目前我想说的是:
string source = "/once/upon/a/time/";
int count = source.Length - source.Replace("/", "").Length;
但我一点都不喜欢，有人愿意吗?
我并不想为此挖掘出正则表达式，对吧?
我知道我的字符串将包含我要搜索的项，所以你可以假设…
当然对于长度为> 1的字符串，
string haystack = "/once/upon/a/time";
string needle = "/";
int needleCount = ( haystack.Length - haystack.Replace(needle,"").Length ) / needle.Length;
当前回答
查找字符计数与查找字符串计数有很大不同。另外，这也取决于你是否想要检查不止一个。如果你想检查各种不同的字符计数，像这样的东西可以工作:
var charCounts =
haystack
.GroupBy(c => c)
.ToDictionary(g => g.Key, g => g.Count());
var needleCount = charCounts.ContainsKey(needle) ? charCounts[needle] : 0;
注1:分组到字典中非常有用，因此为它编写GroupToDictionary扩展方法非常有意义。
注意2:拥有自己的字典实现也很有用，它允许默认值，然后您可以自动为不存在的键获取0。
其他回答
对于任何想要使用String扩展方法的人，
以下是我使用的基于张贴的最好的答案:
public static class StringExtension
{
/// <summary> Returns the number of occurences of a string within a string, optional comparison allows case and culture control. </summary>
public static int Occurrences(this System.String input, string value, StringComparison stringComparisonType = StringComparison.Ordinal)
{
if (String.IsNullOrEmpty(value)) return 0;
int count = 0;
int position = 0;
while ((position = input.IndexOf(value, position, stringComparisonType)) != -1)
{
position += value.Length;
count += 1;
}
return count;
}
/// <summary> Returns the number of occurences of a single character within a string. </summary>
public static int Occurrences(this System.String input, char value)
{
int count = 0;
foreach (char c in input) if (c == value) count += 1;
return count;
}
}
我觉得我们缺少某些类型的子字符串计数，比如不安全的逐字节比较。我把原始海报的方法和我能想到的任何方法结合在一起。
这些是我做的字符串扩展。
namespace Example
{
using System;
using System.Text;
public static class StringExtensions
{
public static int CountSubstr(this string str, string substr)
{
return (str.Length - str.Replace(substr, "").Length) / substr.Length;
}
public static int CountSubstr(this string str, char substr)
{
return (str.Length - str.Replace(substr.ToString(), "").Length);
}
public static int CountSubstr2(this string str, string substr)
{
int substrlen = substr.Length;
int lastIndex = str.IndexOf(substr, 0, StringComparison.Ordinal);
int count = 0;
while (lastIndex != -1)
{
++count;
lastIndex = str.IndexOf(substr, lastIndex + substrlen, StringComparison.Ordinal);
}
return count;
}
public static int CountSubstr2(this string str, char substr)
{
int lastIndex = str.IndexOf(substr, 0);
int count = 0;
while (lastIndex != -1)
{
++count;
lastIndex = str.IndexOf(substr, lastIndex + 1);
}
return count;
}
public static int CountChar(this string str, char substr)
{
int length = str.Length;
int count = 0;
for (int i = 0; i < length; ++i)
if (str[i] == substr)
++count;
return count;
}
public static int CountChar2(this string str, char substr)
{
int count = 0;
foreach (var c in str)
if (c == substr)
++count;
return count;
}
public static unsafe int CountChar3(this string str, char substr)
{
int length = str.Length;
int count = 0;
fixed (char* chars = str)
{
for (int i = 0; i < length; ++i)
if (*(chars + i) == substr)
++count;
}
return count;
}
public static unsafe int CountChar4(this string str, char substr)
{
int length = str.Length;
int count = 0;
fixed (char* chars = str)
{
for (int i = length - 1; i >= 0; --i)
if (*(chars + i) == substr)
++count;
}
return count;
}
public static unsafe int CountSubstr3(this string str, string substr)
{
int length = str.Length;
int substrlen = substr.Length;
int count = 0;
fixed (char* strc = str)
{
fixed (char* substrc = substr)
{
int n = 0;
for (int i = 0; i < length; ++i)
{
if (*(strc + i) == *(substrc + n))
{
++n;
if (n == substrlen)
{
++count;
n = 0;
}
}
else
n = 0;
}
}
}
return count;
}
public static int CountSubstr3(this string str, char substr)
{
return CountSubstr3(str, substr.ToString());
}
public static unsafe int CountSubstr4(this string str, string substr)
{
int length = str.Length;
int substrLastIndex = substr.Length - 1;
int count = 0;
fixed (char* strc = str)
{
fixed (char* substrc = substr)
{
int n = substrLastIndex;
for (int i = length - 1; i >= 0; --i)
{
if (*(strc + i) == *(substrc + n))
{
if (--n == -1)
{
++count;
n = substrLastIndex;
}
}
else
n = substrLastIndex;
}
}
}
return count;
}
public static int CountSubstr4(this string str, char substr)
{
return CountSubstr4(str, substr.ToString());
}
}
}
接下来是测试代码…
static void Main()
{
const char matchA = '_';
const string matchB = "and";
const string matchC = "muchlongerword";
const string testStrA = "_and_d_e_banna_i_o___pfasd__and_d_e_banna_i_o___pfasd_";
const string testStrB = "and sdf and ans andeians andano ip and and sdf and ans andeians andano ip and";
const string testStrC =
"muchlongerword amuchlongerworsdfmuchlongerwordsdf jmuchlongerworijv muchlongerword sdmuchlongerword dsmuchlongerword";
const int testSize = 1000000;
Console.WriteLine(testStrA.CountSubstr('_'));
Console.WriteLine(testStrA.CountSubstr2('_'));
Console.WriteLine(testStrA.CountSubstr3('_'));
Console.WriteLine(testStrA.CountSubstr4('_'));
Console.WriteLine(testStrA.CountChar('_'));
Console.WriteLine(testStrA.CountChar2('_'));
Console.WriteLine(testStrA.CountChar3('_'));
Console.WriteLine(testStrA.CountChar4('_'));
Console.WriteLine(testStrB.CountSubstr("and"));
Console.WriteLine(testStrB.CountSubstr2("and"));
Console.WriteLine(testStrB.CountSubstr3("and"));
Console.WriteLine(testStrB.CountSubstr4("and"));
Console.WriteLine(testStrC.CountSubstr("muchlongerword"));
Console.WriteLine(testStrC.CountSubstr2("muchlongerword"));
Console.WriteLine(testStrC.CountSubstr3("muchlongerword"));
Console.WriteLine(testStrC.CountSubstr4("muchlongerword"));
var timer = new Stopwatch();
timer.Start();
for (int i = 0; i < testSize; ++i)
testStrA.CountSubstr(matchA);
timer.Stop();
Console.WriteLine("CS1 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrB.CountSubstr(matchB);
timer.Stop();
Console.WriteLine("CS1 and: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrC.CountSubstr(matchC);
timer.Stop();
Console.WriteLine("CS1 mlw: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountSubstr2(matchA);
timer.Stop();
Console.WriteLine("CS2 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrB.CountSubstr2(matchB);
timer.Stop();
Console.WriteLine("CS2 and: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrC.CountSubstr2(matchC);
timer.Stop();
Console.WriteLine("CS2 mlw: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountSubstr3(matchA);
timer.Stop();
Console.WriteLine("CS3 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrB.CountSubstr3(matchB);
timer.Stop();
Console.WriteLine("CS3 and: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrC.CountSubstr3(matchC);
timer.Stop();
Console.WriteLine("CS3 mlw: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountSubstr4(matchA);
timer.Stop();
Console.WriteLine("CS4 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrB.CountSubstr4(matchB);
timer.Stop();
Console.WriteLine("CS4 and: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrC.CountSubstr4(matchC);
timer.Stop();
Console.WriteLine("CS4 mlw: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountChar(matchA);
timer.Stop();
Console.WriteLine("CC1 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountChar2(matchA);
timer.Stop();
Console.WriteLine("CC2 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountChar3(matchA);
timer.Stop();
Console.WriteLine("CC3 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
timer.Restart();
for (int i = 0; i < testSize; ++i)
testStrA.CountChar4(matchA);
timer.Stop();
Console.WriteLine("CC4 chr: " + timer.Elapsed.TotalMilliseconds + "ms");
}
结果:CSX与CountSubstrX对应，CCX与CountCharX对应。“chr”搜索字符串中的“_”，“and”搜索字符串中的“and”，“mlw”搜索字符串中的“muchlongerword”
CS1 chr: 824.123ms
CS1 and: 586.1893ms
CS1 mlw: 486.5414ms
CS2 chr: 127.8941ms
CS2 and: 806.3918ms
CS2 mlw: 497.318ms
CS3 chr: 201.8896ms
CS3 and: 124.0675ms
CS3 mlw: 212.8341ms
CS4 chr: 81.5183ms
CS4 and: 92.0615ms
CS4 mlw: 116.2197ms
CC1 chr: 66.4078ms
CC2 chr: 64.0161ms
CC3 chr: 65.9013ms
CC4 chr: 65.8206ms
最后，我有了一个包含360万个字符的文件。“derp adfderdserp dfaerpderp deasderp”重复了10万次。我用上述方法在文件中搜索“derp”100次，得到这些结果。
CS1Derp: 1501.3444ms
CS2Derp: 1585.797ms
CS3Derp: 376.0937ms
CS4Derp: 271.1663ms
所以我的第四种方法肯定是赢家，但是，实际上，如果一个360万个字符的文件100次只需要1586ms作为最坏的情况，那么所有这些都是可以忽略不计的。
顺便说一下，我还用100次CountSubstr和CountChar方法在360万个字符的文件中扫描了'd'字符。结果……
CS1 d : 2606.9513ms
CS2 d : 339.7942ms
CS3 d : 960.281ms
CS4 d : 233.3442ms
CC1 d : 302.4122ms
CC2 d : 280.7719ms
CC3 d : 299.1125ms
CC4 d : 292.9365ms
原来海报的方法是非常糟糕的单个字符针在一个大草堆根据这一点。
注:所有值更新为发布版本输出。在我第一次发布这篇文章时，我不小心忘记了建立发布模式。我的一些声明已经被修改了。
string source = "/once/upon/a/time/";
int count = 0, n = 0;
while ((n = source.IndexOf('/', n) + 1) != 0) count++;
这是Richard Watson的答案的一个变体，char在字符串中出现的次数越多，效率就会提高一点，代码也会更少!
虽然我必须说，在没有广泛测试每个场景的情况下，我确实看到了使用以下方法的显著速度提升:
int count = 0;
for (int n = 0; n < source.Length; n++) if (source[n] == '/') count++;
我想我会把我的扩展方法扔到戒指(更多信息见评论)。我没有做过任何正式的基准测试，但我认为在大多数情况下必须非常快。
EDIT: OK - so this SO question got me to wondering how the performance of our current implementation would stack up against some of the solutions presented here. I decided to do a little bench marking and found that our solution was very much in line with the performance of the solution provided by Richard Watson up until you are doing aggressive searching with large strings (100 Kb +), large substrings (32 Kb +) and many embedded repetitions (10K +). At that point our solution was around 2X to 4X slower. Given this and the fact that we really like the solution presented by Richard Watson, we have refactored our solution accordingly. I just wanted to make this available for anyone that might benefit from it.
我们最初的解决方案:
/// <summary>
/// Counts the number of occurrences of the specified substring within
/// the current string.
/// </summary>
/// <param name="s">The current string.</param>
/// <param name="substring">The substring we are searching for.</param>
/// <param name="aggressiveSearch">Indicates whether or not the algorithm
/// should be aggressive in its search behavior (see Remarks). Default
/// behavior is non-aggressive.</param>
/// <remarks>This algorithm has two search modes - aggressive and
/// non-aggressive. When in aggressive search mode (aggressiveSearch =
/// true), the algorithm will try to match at every possible starting
/// character index within the string. When false, all subsequent
/// character indexes within a substring match will not be evaluated.
/// For example, if the string was 'abbbc' and we were searching for
/// the substring 'bb', then aggressive search would find 2 matches
/// with starting indexes of 1 and 2. Non aggressive search would find
/// just 1 match with starting index at 1. After the match was made,
/// the non aggressive search would attempt to make it's next match
/// starting at index 3 instead of 2.</remarks>
/// <returns>The count of occurrences of the substring within the string.</returns>
public static int CountOccurrences(this string s, string substring,
bool aggressiveSearch = false)
{
// if s or substring is null or empty, substring cannot be found in s
if (string.IsNullOrEmpty(s) || string.IsNullOrEmpty(substring))
return 0;
// if the length of substring is greater than the length of s,
// substring cannot be found in s
if (substring.Length > s.Length)
return 0;
var sChars = s.ToCharArray();
var substringChars = substring.ToCharArray();
var count = 0;
var sCharsIndex = 0;
// substring cannot start in s beyond following index
var lastStartIndex = sChars.Length - substringChars.Length;
while (sCharsIndex <= lastStartIndex)
{
if (sChars[sCharsIndex] == substringChars[0])
{
// potential match checking
var match = true;
var offset = 1;
while (offset < substringChars.Length)
{
if (sChars[sCharsIndex + offset] != substringChars[offset])
{
match = false;
break;
}
offset++;
}
if (match)
{
count++;
// if aggressive, just advance to next char in s, otherwise,
// skip past the match just found in s
sCharsIndex += aggressiveSearch ? 1 : substringChars.Length;
}
else
{
// no match found, just move to next char in s
sCharsIndex++;
}
}
else
{
// no match at current index, move along
sCharsIndex++;
}
}
return count;
}
这是我们修改后的解决方案:
/// <summary>
/// Counts the number of occurrences of the specified substring within
/// the current string.
/// </summary>
/// <param name="s">The current string.</param>
/// <param name="substring">The substring we are searching for.</param>
/// <param name="aggressiveSearch">Indicates whether or not the algorithm
/// should be aggressive in its search behavior (see Remarks). Default
/// behavior is non-aggressive.</param>
/// <remarks>This algorithm has two search modes - aggressive and
/// non-aggressive. When in aggressive search mode (aggressiveSearch =
/// true), the algorithm will try to match at every possible starting
/// character index within the string. When false, all subsequent
/// character indexes within a substring match will not be evaluated.
/// For example, if the string was 'abbbc' and we were searching for
/// the substring 'bb', then aggressive search would find 2 matches
/// with starting indexes of 1 and 2. Non aggressive search would find
/// just 1 match with starting index at 1. After the match was made,
/// the non aggressive search would attempt to make it's next match
/// starting at index 3 instead of 2.</remarks>
/// <returns>The count of occurrences of the substring within the string.</returns>
public static int CountOccurrences(this string s, string substring,
bool aggressiveSearch = false)
{
// if s or substring is null or empty, substring cannot be found in s
if (string.IsNullOrEmpty(s) || string.IsNullOrEmpty(substring))
return 0;
// if the length of substring is greater than the length of s,
// substring cannot be found in s
if (substring.Length > s.Length)
return 0;
int count = 0, n = 0;
while ((n = s.IndexOf(substring, n, StringComparison.InvariantCulture)) != -1)
{
if (aggressiveSearch)
n++;
else
n += substring.Length;
count++;
}
return count;
}
var conditionalStatement = conditionSetting.Value;
//order of replace matters, remove == before =, incase of ===
conditionalStatement = conditionalStatement.Replace("==", "~").Replace("!=", "~").Replace('=', '~').Replace('!', '~').Replace('>', '~').Replace('<', '~').Replace(">=", "~").Replace("<=", "~");
var listOfValidConditions = new List<string>() { "!=", "==", ">", "<", ">=", "<=" };
if (conditionalStatement.Count(x => x == '~') != 1)
{
result.InvalidFieldList.Add(new KeyFieldData(batch.DECurrentField, "The IsDoubleKeyCondition does not contain a supported conditional statement. Contact System Administrator."));
result.Status = ValidatorStatus.Fail;
return result;
}
需要做一些类似于从字符串测试条件语句的事情。
用单个字符替换我正在寻找的内容，并计算单个字符的实例数。
显然，在发生这种情况之前，您需要检查您正在使用的单个字符是否存在于字符串中，以避免错误计数。
