Let's say I have a string such as:
"Hello how are you doing?"
I would like a function that turns multiple spaces into one space.
So I would get:
"Hello how are you doing?"
I know I could use regex or call
string s = "Hello how are you doing?".replace(" "," ");
But I would have to call it multiple times to make sure all sequential whitespaces are replaced with only one.
Is there already a built in method for this?
A fast extra whitespace remover by Felipe Machado. (Modified by RW for multi-space removal)
static string DuplicateWhiteSpaceRemover(string str)
{
var len = str.Length;
var src = str.ToCharArray();
int dstIdx = 0;
bool lastWasWS = false; //Added line
for (int i = 0; i < len; i++)
{
var ch = src[i];
switch (ch)
{
case '\u0020': //SPACE
case '\u00A0': //NO-BREAK SPACE
case '\u1680': //OGHAM SPACE MARK
case '\u2000': // EN QUAD
case '\u2001': //EM QUAD
case '\u2002': //EN SPACE
case '\u2003': //EM SPACE
case '\u2004': //THREE-PER-EM SPACE
case '\u2005': //FOUR-PER-EM SPACE
case '\u2006': //SIX-PER-EM SPACE
case '\u2007': //FIGURE SPACE
case '\u2008': //PUNCTUATION SPACE
case '\u2009': //THIN SPACE
case '\u200A': //HAIR SPACE
case '\u202F': //NARROW NO-BREAK SPACE
case '\u205F': //MEDIUM MATHEMATICAL SPACE
case '\u3000': //IDEOGRAPHIC SPACE
case '\u2028': //LINE SEPARATOR
case '\u2029': //PARAGRAPH SEPARATOR
case '\u0009': //[ASCII Tab]
case '\u000A': //[ASCII Line Feed]
case '\u000B': //[ASCII Vertical Tab]
case '\u000C': //[ASCII Form Feed]
case '\u000D': //[ASCII Carriage Return]
case '\u0085': //NEXT LINE
if (lastWasWS == false) //Added line
{
src[dstIdx++] = ' '; // Updated by Ryan
lastWasWS = true; //Added line
}
continue;
default:
lastWasWS = false; //Added line
src[dstIdx++] = ch;
break;
}
}
return new string(src, 0, dstIdx);
}
The benchmarks...
| | Time | TEST 1 | TEST 2 | TEST 3 | TEST 4 | TEST 5 |
| Function Name |(ticks)| dup. spaces | spaces+tabs | spaces+CR/LF| " " -> " " | " " -> " " |
|---------------------------|-------|-------------|-------------|-------------|-------------|-------------|
| SwitchStmtBuildSpaceOnly | 5.2 | PASS | FAIL | FAIL | PASS | PASS |
| InPlaceCharArraySpaceOnly | 5.6 | PASS | FAIL | FAIL | PASS | PASS |
| DuplicateWhiteSpaceRemover| 7.0 | PASS | PASS | PASS | PASS | PASS |
| SingleSpacedTrim | 11.8 | PASS | PASS | PASS | FAIL | FAIL |
| Fubo(StringBuilder) | 13 | PASS | FAIL | FAIL | PASS | PASS |
| User214147 | 19 | PASS | PASS | PASS | FAIL | FAIL |
| RegExWithCompile | 28 | PASS | FAIL | FAIL | PASS | PASS |
| SwitchStmtBuild | 34 | PASS | FAIL | FAIL | PASS | PASS |
| SplitAndJoinOnSpace | 55 | PASS | FAIL | FAIL | FAIL | FAIL |
| RegExNoCompile | 120 | PASS | PASS | PASS | PASS | PASS |
| RegExBrandon | 137 | PASS | FAIL | PASS | PASS | PASS |
Benchmark notes: Release Mode, no-debugger attached, i7 processor, avg of 4 runs, only short strings tested
SwitchStmtBuildSpaceOnly by Felipe Machado 2015 and modified by Sunsetquest
InPlaceCharArraySpaceOnly by Felipe Machado 2015 and modified by Sunsetquest
SwitchStmtBuild by Felipe Machado 2015 and modified by Sunsetquest
SwitchStmtBuild2 by Felipe Machado 2015 and modified by Sunsetquest
SingleSpacedTrim by David S 2013
Fubo(StringBuilder) by fubo 2014
SplitAndJoinOnSpace by Jon Skeet 2009
RegExWithCompile by Jon Skeet 2009
User214147 by user214147
RegExBrandon by Brandon
RegExNoCompile by Tim Hoolihan
I'm sharing what I use, because it appears I've come up with something different. I've been using this for a while and it is fast enough for me. I'm not sure how it stacks up against the others. I uses it in a delimited file writer and run large datatables one field at a time through it.
public static string NormalizeWhiteSpace(string S)
{
string s = S.Trim();
bool iswhite = false;
int iwhite;
int sLength = s.Length;
StringBuilder sb = new StringBuilder(sLength);
foreach(char c in s.ToCharArray())
{
if(Char.IsWhiteSpace(c))
{
if (iswhite)
{
//Continuing whitespace ignore it.
continue;
}
else
{
//New WhiteSpace
//Replace whitespace with a single space.
sb.Append(" ");
//Set iswhite to True and any following whitespace will be ignored
iswhite = true;
}
}
else
{
sb.Append(c.ToString());
//reset iswhitespace to false
iswhite = false;
}
}
return sb.ToString();
}
You can try this:
/// <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();
}
Replacement groups provide impler approach resolving replacement of multiple white space characters with same single one:
public static void WhiteSpaceReduce()
{
string t1 = "a b c d";
string t2 = "a b\n\nc\nd";
Regex whiteReduce = new Regex(@"(?<firstWS>\s)(?<repeatedWS>\k<firstWS>+)");
Console.WriteLine("{0}", t1);
//Console.WriteLine("{0}", whiteReduce.Replace(t1, x => x.Value.Substring(0, 1)));
Console.WriteLine("{0}", whiteReduce.Replace(t1, @"${firstWS}"));
Console.WriteLine("\nNext example ---------");
Console.WriteLine("{0}", t2);
Console.WriteLine("{0}", whiteReduce.Replace(t2, @"${firstWS}"));
Console.WriteLine();
}
Please notice the second example keeps single \n while accepted answer would replace end of line with space.
If you need to replace any combination of white space characters with the first one, just remove the back-reference \k from the pattern.