将多余的空白替换为一个空白的最快方法是什么?
例如
从
foo bar
至
foo bar
最快的方法?遍历字符串并StringBuilder
逐个字符地构建第二个副本,每组空格只复制一个空格。
更容易键入的Replace
变体将创建大量额外字符串(或浪费时间构建正则表达式 DFA)。
编辑比较结果:
使用http://ideone.com/NV6EzU, n=50 (必须在 ideone 上减少它,因为他们不得不杀死我的进程需要很长时间),我得到:
正则表达式:7771 毫秒。
字符串生成器:894 毫秒。
这确实如预期的那样,Regex
对于这么简单的事情来说效率非常低。
您可以使用正则表达式:
static readonly Regex trimmer = new Regex(@"\s\s+");
s = trimmer.Replace(s, " ");
为了增加性能,通过RegexOptions.Compiled
.
有点晚了,但我已经做了一些基准测试以获得最快的方法来删除额外的空格。如果有更快的答案,我很乐意添加它们。
结果:
代码:
public class RemoveExtraWhitespaces
{
public static string WithRegex(string text)
{
return Regex.Replace(text, @"\s+", " ");
}
public static string WithRegexCompiled(Regex compiledRegex, string text)
{
return compiledRegex.Replace(text, " ");
}
public static string NormalizeWhiteSpace(string input)
{
if (string.IsNullOrEmpty(input))
return string.Empty;
int current = 0;
char[] output = new char[input.Length];
bool skipped = false;
foreach (char c in input.ToCharArray())
{
if (char.IsWhiteSpace(c))
{
if (!skipped)
{
if (current > 0)
output[current++] = ' ';
skipped = true;
}
}
else
{
skipped = false;
output[current++] = c;
}
}
return new string(output, 0, current);
}
public static string NormalizeWhiteSpaceForLoop(string input)
{
int len = input.Length,
index = 0,
i = 0;
var src = input.ToCharArray();
bool skip = false;
char ch;
for (; i < len; i++)
{
ch = src[i];
switch (ch)
{
case '\u0020':
case '\u00A0':
case '\u1680':
case '\u2000':
case '\u2001':
case '\u2002':
case '\u2003':
case '\u2004':
case '\u2005':
case '\u2006':
case '\u2007':
case '\u2008':
case '\u2009':
case '\u200A':
case '\u202F':
case '\u205F':
case '\u3000':
case '\u2028':
case '\u2029':
case '\u0009':
case '\u000A':
case '\u000B':
case '\u000C':
case '\u000D':
case '\u0085':
if (skip) continue;
src[index++] = ch;
skip = true;
continue;
default:
skip = false;
src[index++] = ch;
continue;
}
}
return new string(src, 0, index);
}
}
测试:
[TestFixture]
public class RemoveExtraWhitespacesTest
{
private const string _text = "foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo ";
private const string _expected = "foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo foo bar foobar moo ";
private const int _iterations = 10000;
[Test]
public void Regex()
{
var result = TimeAction("Regex", () => RemoveExtraWhitespaces.WithRegex(_text));
Assert.AreEqual(_expected, result);
}
[Test]
public void RegexCompiled()
{
var compiledRegex = new Regex(@"\s+", RegexOptions.Compiled);
var result = TimeAction("RegexCompiled", () => RemoveExtraWhitespaces.WithRegexCompiled(compiledRegex, _text));
Assert.AreEqual(_expected, result);
}
[Test]
public void NormalizeWhiteSpace()
{
var result = TimeAction("NormalizeWhiteSpace", () => RemoveExtraWhitespaces.NormalizeWhiteSpace(_text));
Assert.AreEqual(_expected, result);
}
[Test]
public void NormalizeWhiteSpaceForLoop()
{
var result = TimeAction("NormalizeWhiteSpaceForLoop", () => RemoveExtraWhitespaces.NormalizeWhiteSpaceForLoop(_text));
Assert.AreEqual(_expected, result);
}
public string TimeAction(string name, Func<string> func)
{
var timer = Stopwatch.StartNew();
string result = string.Empty; ;
for (int i = 0; i < _iterations; i++)
{
result = func();
}
timer.Stop();
Console.WriteLine(string.Format("{0}: {1} ms", name, timer.ElapsedMilliseconds));
return result;
}
}
我使用以下方法 - 它们不仅处理空格,还处理所有空格字符,修剪前导和尾随空格,删除多余的空格,并将所有空格替换为空格字符(因此我们有统一的空格分隔符)。而且这些方法很快。
public static String CompactWhitespaces( String s )
{
StringBuilder sb = new StringBuilder( s );
CompactWhitespaces( sb );
return sb.ToString();
}
public static void CompactWhitespaces( StringBuilder sb )
{
if( sb.Length == 0 )
return;
// set [start] to first not-whitespace char or to sb.Length
int start = 0;
while( start < sb.Length )
{
if( Char.IsWhiteSpace( sb[ start ] ) )
start++;
else
break;
}
// if [sb] has only whitespaces, then return empty string
if( start == sb.Length )
{
sb.Length = 0;
return;
}
// set [end] to last not-whitespace char
int end = sb.Length - 1;
while( end >= 0 )
{
if( Char.IsWhiteSpace( sb[ end ] ) )
end--;
else
break;
}
// compact string
int dest = 0;
bool previousIsWhitespace = false;
for( int i = start; i <= end; i++ )
{
if( Char.IsWhiteSpace( sb[ i ] ) )
{
if( !previousIsWhitespace )
{
previousIsWhitespace = true;
sb[ dest ] = ' ';
dest++;
}
}
else
{
previousIsWhitespace = false;
sb[ dest ] = sb[ i ];
dest++;
}
}
sb.Length = dest;
}
string q = " Hello how are you doing?";
string a = String.Join(" ", q.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries));
string text = "foo bar";
text = Regex.Replace(text, @"\s+", " ");
// text = "foo bar"
此解决方案适用于空格、制表符和换行符。如果只需要空格,请将 '\s' 替换为 ' '。
我需要其中一个来处理更大的字符串,并想出了下面的例程。
任何连续的空格(包括制表符、换行符)都将替换为normalizeTo
. 前导/尾随空格被删除。
它比我的 5k->5mil 字符字符串的 RegEx 快 8 倍左右。
internal static string NormalizeWhiteSpace(string input, char normalizeTo = ' ')
{
if (string.IsNullOrEmpty(input))
return string.Empty;
int current = 0;
char[] output = new char[input.Length];
bool skipped = false;
foreach (char c in input.ToCharArray())
{
if (char.IsWhiteSpace(c))
{
if (!skipped)
{
if (current > 0)
output[current++] = normalizeTo;
skipped = true;
}
}
else
{
skipped = false;
output[current++] = c;
}
}
return new string(output, 0, skipped ? current - 1 : current);
}
string yourWord = "beep boop baap beep boop baap beep";
yourWord = yourWord .Replace(" ", " |").Replace("| ", "").Replace("|", "");
我尝试使用 StringBuilder 来:
这是我发现的性能和可读性的最佳平衡(使用 100,000 次迭代计时运行)。有时这比不那么易读的版本测试得更快,最多慢 5%。在我的小测试字符串上,正则表达式需要 4.24 倍的时间。
public static string RemoveExtraWhitespace(string str)
{
var sb = new StringBuilder();
var prevIsWhitespace = false;
foreach (var ch in str)
{
var isWhitespace = char.IsWhiteSpace(ch);
if (prevIsWhitespace && isWhitespace)
{
continue;
}
sb.Append(ch);
prevIsWhitespace = isWhitespace;
}
return sb.ToString();
}
这段代码效果很好。我没有衡量性能。
string text = " hello - world, here we go !!! a bc ";
string.Join(" ", text.Split().Where(x => x != ""));
// Output
// "hello - world, here we go !!! a bc"
它并不快,但如果简单有帮助,这很有效:
while (text.Contains(" ")) text=text.Replace(" ", " ");
我已经尝试过使用数组并且没有if
.
PS C:\dev\Spaces> dotnet run -c release
// .NETCoreApp,Version=v3.0
Seed=7, n=20, s.Length=2828670
Regex by SLaks 1407ms, len=996757
StringBuilder by Blindy 154ms, len=996757
Array 130ms, len=996757
NoIf 91ms, len=996757
All match!
private static string WithNoIf(string s)
{
var dst = new char[s.Length];
uint end = 0;
char prev = char.MinValue;
for (int k = 0; k < s.Length; ++k)
{
var c = s[k];
dst[end] = c;
// We'll move forward if the current character is not ' ' or if prev char is not ' '
// To avoid 'if' let's get diffs for c and prev and then use bitwise operatios to get
// 0 if n is 0 or 1 if n is non-zero
uint x = (uint)(' ' - c) + (uint)(' ' - prev); // non zero if any non-zero
end += ((x | (~x + 1)) >> 31) & 1; // https://stackoverflow.com/questions/3912112/check-if-a-number-is-non-zero-using-bitwise-operators-in-c by ruslik
prev = c;
}
return new string(dst, 0, (int)end);
}
private static string WithArray(string s)
{
var dst = new char[s.Length];
int end = 0;
char prev = char.MinValue;
for (int k = 0; k < s.Length; ++k)
{
char c = s[k];
if (c != ' ' || prev != ' ') dst[end++] = c;
prev = c;
}
return new string(dst, 0, end);
}
public static void Main()
{
const int n = 20;
const int seed = 7;
string s = GetTestString(seed);
var fs = new (string Name, Func<string, string> Func)[]{
("Regex by SLaks", WithRegex),
("StringBuilder by Blindy", WithSb),
("Array", WithArray),
("NoIf", WithNoIf),
};
Console.WriteLine($"Seed={seed}, n={n}, s.Length={s.Length}");
var d = new Dictionary<string, string>(); // method, result
var sw = new Stopwatch();
foreach (var f in fs)
{
sw.Restart();
var r = "";
for( int i = 0; i < n; i++) r = f.Func(s);
sw.Stop();
d[f.Name] = r;
Console.WriteLine($"{f.Name,-25} {sw.ElapsedMilliseconds,4}ms, len={r.Length}");
}
Console.WriteLine(d.Values.All( v => v == d.Values.First()) ? "All match!" : "Not all match! BAD");
}
private static string GetTestString(int seed)
{
// by blindy from https://stackoverflow.com/questions/6442421/c-sharp-fastest-way-to-remove-extra-white-spaces
var rng = new Random(seed);
// random 1mb+ string (it's slow enough...)
StringBuilder ssb = new StringBuilder(1 * 1024 * 1024);
for (int i = 0; i < 1 * 1024 * 1024; ++i)
if (rng.Next(5) == 0)
ssb.Append(new string(' ', rng.Next(20)));
else
ssb.Append((char)(rng.Next(128 - 32) + 32));
string s = ssb.ToString();
return s;
}
尝试这个:
System.Text.RegularExpressions.Regex.Replace(input, @"\s+", " ");
这个问题有一些要求不清楚,值得深思。
这是一个非常有效的版本,它用一个空格替换所有空格,并在 for 循环之前删除任何前导和尾随空格。
public static string WhiteSpaceToSingleSpaces(string input)
{
if (input.Length < 2)
return input;
StringBuilder sb = new StringBuilder();
input = input.Trim();
char lastChar = input[0];
bool lastCharWhiteSpace = false;
for (int i = 1; i < input.Length; i++)
{
bool whiteSpace = char.IsWhiteSpace(input[i]);
//Skip duplicate whitespace characters
if (whiteSpace && lastCharWhiteSpace)
continue;
//Replace all whitespace with a single space.
if (whiteSpace)
sb.Append(' ');
else
sb.Append(input[i]);
//Keep track of the last character's whitespace status
lastCharWhiteSpace = whiteSpace;
}
return sb.ToString();
}
我不知道这是否是最快的方法,但我使用它,这对我有用:
/// <summary>
/// Remove all extra spaces and tabs between words in the specified string!
/// </summary>
/// <param name="str">The specified string.</param>
public static string RemoveExtraSpaces(string str)
{
str = str.Trim();
StringBuilder sb = new StringBuilder();
bool space = false;
foreach (char c in str)
{
if (char.IsWhiteSpace(c) || c == (char)9) { space = true; }
else { if (space) { sb.Append(' '); }; sb.Append(c); space = false; };
}
return sb.ToString();
}
这很有趣,但在我的 PC 上,以下方法与 Sergey Povalyaev 的 StringBulder 方法一样快 - (1000 次重复约 282 毫秒,10k src 字符串)。虽然不确定内存使用情况。
string RemoveExtraWhiteSpace(string src, char[] wsChars){
return string.Join(" ",src.Split(wsChars, StringSplitOptions.RemoveEmptyEntries));
}
显然它适用于任何字符 - 不仅仅是空格。
虽然这不是 OP 所要求的 - 但如果您真正需要的是仅用一个实例替换字符串中的特定连续字符,您可以使用这种相对有效的方法:
string RemoveDuplicateChars(string src, char[] dupes){
var sd = (char[])dupes.Clone();
Array.Sort(sd);
var res = new StringBuilder(src.Length);
for(int i = 0; i<src.Length; i++){
if( i==0 || src[i]!=src[i-1] || Array.BinarySearch(sd,src[i])<0){
res.Append(src[i]);
}
}
return res.ToString();
}
public string GetCorrectString(string IncorrectString)
{
string[] strarray = IncorrectString.Split(' ');
var sb = new StringBuilder();
foreach (var str in strarray)
{
if (str != string.Empty)
{
sb.Append(str).Append(' ');
}
}
return sb.ToString().Trim();
}
我对 C# 不是很熟悉,因此我的代码不是优雅/最有效的代码。我来这里是为了找到一个适合我用例的答案,但我找不到(或者我想不出一个)。
对于我的用例,我需要使用以下条件规范化所有空白 (WS:{ space
, tab
, cr lf
}):
tab
在某些情况下需要保留(例如,一个制表符分隔的文件,在这种情况下,还需要保留重复的制表符)。但在大多数情况下,它们必须转换为空格。所以这是一个示例输入和一个预期输出(免责声明:我的代码仅针对此示例进行测试)
Every night in my dreams I see you, I feel you
That's how I know you go on
Far across the distance and places between us
You have come to show you go on
被转换成
Every night in my dreams I see you, I feel you
That's how I know you go on
Far across the distance and places between us
You have come to show you go on
这是我的代码
using System;
using System.Text.RegularExpressions;
public class Program
{
public static void Main(string text)
{
bool preserveTabs = false;
//[Step 1]: Clean up white spaces around the text
text = text.Trim();
//Console.Write("\nTrim\n======\n" + text);
//[Step 2]: Reduce repeated spaces to single space.
text = Regex.Replace(text, @" +", " ");
// Console.Write("\nNo repeated spaces\n======\n" + text);
//[Step 3]: Hande Tab spaces. Tabs needs to treated with care because
//in some files tabs have special meaning (for eg Tab seperated files)
if(preserveTabs)
{
text = Regex.Replace(text, @" *\t *", "\t");
}
else
{
text = Regex.Replace(text, @"[ \t]+", " ");
}
//Console.Write("\nTabs preserved\n======\n" + text);
//[Step 4]: Reduce repeated new lines (and other white spaces around them)
//into a single new line.
text = Regex.Replace(text, @"([\t ]*(\n)+[\t ]*)+", "\n");
Console.Write("\nClean New Lines\n======\n" + text);
}
}
在此处查看此代码:https ://dotnetfiddle.net/eupjIU
我知道这真的很旧,但是压缩空格的最简单方法(用单个“空格”字符替换任何重复出现的空格字符)如下:
public static string CompactWhitespace(string astring)
{
if (!string.IsNullOrEmpty(astring))
{
bool found = false;
StringBuilder buff = new StringBuilder();
foreach (char chr in astring.Trim())
{
if (char.IsWhiteSpace(chr))
{
if (found)
{
continue;
}
found = true;
buff.Append(' ');
}
else
{
if (found)
{
found = false;
}
buff.Append(chr);
}
}
return buff.ToString();
}
return string.Empty;
}
我刚刷了这个,还没有测试过。但我觉得这很优雅,并且避免了正则表达式:
/// <summary>
/// Removes extra white space.
/// </summary>
/// <param name="s">
/// The string
/// </param>
/// <returns>
/// The string, with only single white-space groupings.
/// </returns>
public static string RemoveExtraWhiteSpace(this string s)
{
if (s.Length == 0)
{
return string.Empty;
}
var stringBuilder = new StringBuilder();
var whiteSpaceCount = 0;
foreach (var character in s)
{
if (char.IsWhiteSpace(character))
{
whiteSpaceCount++;
}
else
{
whiteSpaceCount = 0;
}
if (whiteSpaceCount > 1)
{
continue;
}
stringBuilder.Append(character);
}
return stringBuilder.ToString();
}
我在这里错过了什么吗?我想出了这个:
// Input: "HELLO BEAUTIFUL WORLD!"
private string NormalizeWhitespace(string inputStr)
{
// First split the string on the spaces but exclude the spaces themselves
// Using the input string the length of the array will be 3. If the spaces
// were not filtered out they would be included in the array
var splitParts = inputStr.Split(' ').Where(x => x != "").ToArray();
// Now iterate over the parts in the array and add them to the return
// string. If the current part is not the last part, add a space after.
for (int i = 0; i < splitParts.Count(); i++)
{
retVal += splitParts[i];
if (i != splitParts.Count() - 1)
{
retVal += " ";
}
}
return retVal;
}
// Would return "HELLO BEAUTIFUL WORLD!"
我知道我在这里创建了第二个字符串来返回它以及创建 splitParts 数组。只是觉得这很简单。也许我没有考虑到一些潜在的情况。
您可以使用 indexOf 首先获取空白序列的开始位置,然后使用替换方法将空白更改为“”。从那里,您可以使用您抓取的索引并在该位置放置一个空白字符。
如果你调整 famos 算法——在这种情况下是比较“相似”的字符串——不区分大小写并且不关心多个空格并且也可以忍受 NULL。不要相信基准——这一项被投入到一项数据比较密集的任务中,大约。1/4GB 数据和加速在整个动作中约为 100%(评论部分与此算法 5/10 分钟)。其中一些这里的差异较小,约为 30%。会告诉构建最佳算法需要反汇编并检查编译器在发布或调试构建中将做什么。这里也有一半简单的 fulltrim作为类似 (C question) 的答案,但区分大小写。
public static bool Differs(string srcA, string srcB)
{
//return string.Join(" ", (a?.ToString()??String.Empty).ToUpperInvariant().Split(new char[0], StringSplitOptions.RemoveEmptyEntries).ToList().Select(x => x.Trim()))
// != string.Join(" ", (b?.ToString()??String.Empty).ToUpperInvariant().Split(new char[0], StringSplitOptions.RemoveEmptyEntries).ToList().Select(x => x.Trim()));
if (srcA == null) { if (srcB == null) return false; else srcA = String.Empty; } // A == null + B == null same or change A to empty string
if (srcB == null) { if (srcA == null) return false; else srcB = String.Empty; }
int dstIdxA = srcA.Length, dstIdxB = srcB.Length; // are there any remaining (front) chars in a string ?
int planSpaceA = 0, planSpaceB = 0; // state automaton 1 after non-WS, 2 after WS
bool validA, validB; // are there any remaining (front) chars in a array ?
char chA = '\0', chB = '\0';
spaceLoopA:
if (validA = (dstIdxA > 0)) {
chA = srcA[--dstIdxA];
switch (chA) {
case '!': case '"': case '#': case '$': case '%': case '&': case '\'': case '(': case ')': case '*': case '+': case ',': case '-':
case '.': case '/': case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': case ':':
case ';': case '<': case '=': case '>': case '?': case '@': case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z': case '[': case '\\': case ']': case '^': case '_': case '`': // a-z will be | 32 to Upper
case '{': case '|': case '}': case '~':
break; // ASCII except lowercase
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i':
case 'j': case 'k': case 'l': case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x': case 'y': case 'z':
chA = (Char)(chA & ~0x20);
break;
case '\u0020': case '\u00A0': case '\u1680': case '\u2000': case '\u2001':
case '\u2002': case '\u2003': case '\u2004': case '\u2005': case '\u2006':
case '\u2007': case '\u2008': case '\u2009': case '\u200A': case '\u202F':
case '\u205F': case '\u3000': case '\u2028': case '\u2029': case '\u0009':
case '\u000A': case '\u000B': case '\u000C': case '\u000D': case '\u0085':
if (planSpaceA == 1) planSpaceA = 2; // cycle here to address multiple WS before non-WS part
goto spaceLoopA;
default:
chA = Char.ToUpper(chA);
break;
}}
spaceLoopB:
if (validB = (dstIdxB > 0)) { // 2nd string / same logic
chB = srcB[--dstIdxB];
switch (chB) {
case '!': case '"': case '#': case '$': case '%': case '&': case '\'': case '(': case ')': case '*': case '+': case ',': case '-':
case '.': case '/': case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': case ':':
case ';': case '<': case '=': case '>': case '?': case '@': case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z': case '[': case '\\': case ']': case '^': case '_': case '`': // a-z will be | 32 to Upper
break;
case '{': case '|': case '}': case '~':
break; // ASCII except lowercase
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i':
case 'j': case 'k': case 'l': case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x': case 'y': case 'z':
chB = (Char)(chB & ~0x20);
break;
case '\u0020': case '\u00A0': case '\u1680': case '\u2000': case '\u2001':
case '\u2002': case '\u2003': case '\u2004': case '\u2005': case '\u2006':
case '\u2007': case '\u2008': case '\u2009': case '\u200A': case '\u202F':
case '\u205F': case '\u3000': case '\u2028': case '\u2029': case '\u0009':
case '\u000A': case '\u000B': case '\u000C': case '\u000D': case '\u0085':
if (planSpaceB == 1) planSpaceB = 2;
goto spaceLoopB;
default:
chB = Char.ToUpper(chB);
break;
}}
if (planSpaceA != planSpaceB) return true; // both should/not have space now (0 init / 1 last non-WS / 2 last was WS)
if (validA) { // some (non-WS) in A still
if (validB) {
if (chA != chB) return true; // both have another char to compare, are they different ?
} else return true; // not in B not - they are different
} else { // A done, current last pair equal => continue 2 never ending loop till B end (by WS only to be same)
if (!validB) return false; // done and end-up here without leaving by difference => both are same except some WSs arround
else return true; // A done, but non-WS remains in B - different
} // A done, B had no non-WS or non + WS last follow - never ending loop continue
planSpaceA = 1; planSpaceB = 1;
goto spaceLoopA; // performs better
}
}
public static string RemoveExtraSpaces(string input)
{
input = input.Trim();
string output = "";
bool WasLastCharSpace = false;
for (int i = 0; i < input.Length; i++)
{
if (input[i] == ' ' && WasLastCharSpace)
continue;
WasLastCharSpace = input[i] == ' ';
output += input[i];
}
return output;
}
对于那些只想复制并继续的人:
private string RemoveExcessiveWhitespace(string value)
{
if (value == null) { return null; }
var builder = new StringBuilder();
var ignoreWhitespace = false;
foreach (var c in value)
{
if (!ignoreWhitespace || c != ' ')
{
builder.Append(c);
}
ignoreWhitespace = c == ' ';
}
return builder.ToString();
}
我的版本(根据 Stian 的回答改进)。应该非常快。
public static string TrimAllExtraWhiteSpaces(this string input)
{
if (string.IsNullOrEmpty(input))
{
return input;
}
var current = 0;
char[] output = new char[input.Length];
var charArray = input.ToCharArray();
for (var i = 0; i < charArray.Length; i++)
{
if (!char.IsWhiteSpace(charArray[i]))
{
if (current > 0 && i > 0 && char.IsWhiteSpace(charArray[i - 1]))
{
output[current++] = ' ';
}
output[current++] = charArray[i];
}
}
return new string(output, 0, current);
}
不需要复杂的代码!这是一个简单的代码,它将删除所有重复项:
public static String RemoveCharOccurence(String s, char[] remove)
{
String s1 = s;
foreach(char c in remove)
{
s1 = RemoveCharOccurence(s1, c);
}
return s1;
}
public static String RemoveCharOccurence(String s, char remove)
{
StringBuilder sb = new StringBuilder(s.Length);
Boolean removeNextIfMatch = false;
foreach(char c in s)
{
if(c == remove)
{
if(removeNextIfMatch)
continue;
else
removeNextIfMatch = true;
}
else
removeNextIfMatch = false;
sb.Append(c);
}
return sb.ToString();
}
很简单,使用.Replace()
方法即可:
string words = "Hello world!";
words = words.Replace("\\s+", " ");
输出 >>> “你好世界!”
我能想到的最简单的方法:
Text = Text.Replace("\<Space>\<Space>", "\<Space>").Replace("\<Space>\<Space>", "\<Space>");
// Replace 2 \<Space>s with 1 space, twice