How do I go from this string: "ThisIsMyCapsDelimitedString"
...to this string: "This Is My Caps Delimited String"
Fewest lines of code in VB.net is preferred but C# is also welcome.
Cheers!
17 Answers
I made this a while ago. It matches each component of a CamelCase name.
/([A-Z]+(?=$|[A-Z][a-z])|[A-Z]?[a-z]+)/g
For example:
"SimpleHTTPServer" => ["Simple", "HTTP", "Server"]
"camelCase" => ["camel", "Case"]
To convert that to just insert spaces between the words:
Regex.Replace(s, "([a-z](?=[A-Z])|[A-Z](?=[A-Z][a-z]))", "$1 ")
If you need to handle digits:
/([A-Z]+(?=$|[A-Z][a-z]|[0-9])|[A-Z]?[a-z]+|[0-9]+)/g
Regex.Replace(s,"([a-z](?=[A-Z]|[0-9])|[A-Z](?=[A-Z][a-z]|[0-9])|[0-9](?=[^0-9]))","$1 ")
Great answer, MizardX! I tweaked it slightly to treat numerals as separate words, so that "AddressLine1" would become "Address Line 1" instead of "Address Line1":
Regex.Replace(s, "([a-z](?=[A-Z0-9])|[A-Z](?=[A-Z][a-z]))", "$1 ")
Just for a little variety... Here's an extension method that doesn't use a regex.
public static class CamelSpaceExtensions
{
public static string SpaceCamelCase(this String input)
{
return new string(Enumerable.Concat(
input.Take(1), // No space before initial cap
InsertSpacesBeforeCaps(input.Skip(1))
).ToArray());
}
private static IEnumerable<char> InsertSpacesBeforeCaps(IEnumerable<char> input)
{
foreach (char c in input)
{
if (char.IsUpper(c))
{
yield return ' ';
}
yield return c;
}
}
}
Grant Wagner's excellent comment aside:
Dim s As String = RegularExpressions.Regex.Replace("ThisIsMyCapsDelimitedString", "([A-Z])", " $1")
For more variety, using plain old C# objects, the following produces the same output as @MizardX's excellent regular expression.
public string FromCamelCase(string camel)
{ // omitted checking camel for null
StringBuilder sb = new StringBuilder();
int upperCaseRun = 0;
foreach (char c in camel)
{ // append a space only if we're not at the start
// and we're not already in an all caps string.
if (char.IsUpper(c))
{
if (upperCaseRun == 0 && sb.Length != 0)
{
sb.Append(' ');
}
upperCaseRun++;
}
else if( char.IsLower(c) )
{
if (upperCaseRun > 1) //The first new word will also be capitalized.
{
sb.Insert(sb.Length - 1, ' ');
}
upperCaseRun = 0;
}
else
{
upperCaseRun = 0;
}
sb.Append(c);
}
return sb.ToString();
}
string s = "ThisIsMyCapsDelimitedString";
string t = Regex.Replace(s, "([A-Z])", " $1").Substring(1);
Regex is about 10-12 times slower than a simple loop:
public static string CamelCaseToSpaceSeparated(this string str)
{
if (string.IsNullOrEmpty(str))
{
return str;
}
var res = new StringBuilder();
res.Append(str[0]);
for (var i = 1; i < str.Length; i++)
{
if (char.IsUpper(str[i]))
{
res.Append(' ');
}
res.Append(str[i]);
}
return res.ToString();
}
Naive regex solution. Will not handle O'Conner, and adds a space at the start of the string as well.
s = "ThisIsMyCapsDelimitedString"
split = Regex.Replace(s, "[A-Z0-9]", " $&");
There's probably a more elegant solution, but this is what I come up with off the top of my head:
string myString = "ThisIsMyCapsDelimitedString";
for (int i = 1; i < myString.Length; i++)
{
if (myString[i].ToString().ToUpper() == myString[i].ToString())
{
myString = myString.Insert(i, " ");
i++;
}
}
Procedural and fast impl:
/// <summary>
/// Get the words in a code <paramref name="identifier"/>.
/// </summary>
/// <param name="identifier">The code <paramref name="identifier"/></param> to extract words from.
public static string[] GetWords(this string identifier) {
Contract.Ensures(Contract.Result<string[]>() != null, "returned array of string is not null but can be empty");
if (identifier == null) { return new string[0]; }
if (identifier.Length == 0) { return new string[0]; }
const int MIN_WORD_LENGTH = 2; // Ignore one letter or one digit words
var length = identifier.Length;
var list = new List<string>(1 + length/2); // Set capacity, not possible more words since we discard one char words
var sb = new StringBuilder();
CharKind cKindCurrent = GetCharKind(identifier[0]); // length is not zero here
CharKind cKindNext = length == 1 ? CharKind.End : GetCharKind(identifier[1]);
for (var i = 0; i < length; i++) {
var c = identifier[i];
CharKind cKindNextNext = (i >= length - 2) ? CharKind.End : GetCharKind(identifier[i + 2]);
// Process cKindCurrent
switch (cKindCurrent) {
case CharKind.Digit:
case CharKind.LowerCaseLetter:
sb.Append(c); // Append digit or lowerCaseLetter to sb
if (cKindNext == CharKind.UpperCaseLetter) {
goto TURN_SB_INTO_WORD; // Finish word if next char is upper
}
goto CHAR_PROCESSED;
case CharKind.Other:
goto TURN_SB_INTO_WORD;
default: // charCurrent is never Start or End
Debug.Assert(cKindCurrent == CharKind.UpperCaseLetter);
break;
}
// Here cKindCurrent is UpperCaseLetter
// Append UpperCaseLetter to sb anyway
sb.Append(c);
switch (cKindNext) {
default:
goto CHAR_PROCESSED;
case CharKind.UpperCaseLetter:
// "SimpleHTTPServer" when we are at 'P' we need to see that NextNext is 'e' to get the word!
if (cKindNextNext == CharKind.LowerCaseLetter) {
goto TURN_SB_INTO_WORD;
}
goto CHAR_PROCESSED;
case CharKind.End:
case CharKind.Other:
break; // goto TURN_SB_INTO_WORD;
}
//------------------------------------------------
TURN_SB_INTO_WORD:
string word = sb.ToString();
sb.Length = 0;
if (word.Length >= MIN_WORD_LENGTH) {
list.Add(word);
}
CHAR_PROCESSED:
// Shift left for next iteration!
cKindCurrent = cKindNext;
cKindNext = cKindNextNext;
}
string lastWord = sb.ToString();
if (lastWord.Length >= MIN_WORD_LENGTH) {
list.Add(lastWord);
}
return list.ToArray();
}
private static CharKind GetCharKind(char c) {
if (char.IsDigit(c)) { return CharKind.Digit; }
if (char.IsLetter(c)) {
if (char.IsUpper(c)) { return CharKind.UpperCaseLetter; }
Debug.Assert(char.IsLower(c));
return CharKind.LowerCaseLetter;
}
return CharKind.Other;
}
enum CharKind {
End, // For end of string
Digit,
UpperCaseLetter,
LowerCaseLetter,
Other
}
Tests:
[TestCase((string)null, "")]
[TestCase("", "")]
// Ignore one letter or one digit words
[TestCase("A", "")]
[TestCase("4", "")]
[TestCase("_", "")]
[TestCase("Word_m_Field", "Word Field")]
[TestCase("Word_4_Field", "Word Field")]
[TestCase("a4", "a4")]
[TestCase("ABC", "ABC")]
[TestCase("abc", "abc")]
[TestCase("AbCd", "Ab Cd")]
[TestCase("AbcCde", "Abc Cde")]
[TestCase("ABCCde", "ABC Cde")]
[TestCase("Abc42Cde", "Abc42 Cde")]
[TestCase("Abc42cde", "Abc42cde")]
[TestCase("ABC42Cde", "ABC42 Cde")]
[TestCase("42ABC", "42 ABC")]
[TestCase("42abc", "42abc")]
[TestCase("abc_cde", "abc cde")]
[TestCase("Abc_Cde", "Abc Cde")]
[TestCase("_Abc__Cde_", "Abc Cde")]
[TestCase("ABC_CDE_FGH", "ABC CDE FGH")]
[TestCase("ABC CDE FGH", "ABC CDE FGH")] // Should not happend (white char) anything that is not a letter/digit/'_' is considered as a separator
[TestCase("ABC,CDE;FGH", "ABC CDE FGH")] // Should not happend (,;) anything that is not a letter/digit/'_' is considered as a separator
[TestCase("abc<cde", "abc cde")]
[TestCase("abc<>cde", "abc cde")]
[TestCase("abc<D>cde", "abc cde")] // Ignore one letter or one digit words
[TestCase("abc<Da>cde", "abc Da cde")]
[TestCase("abc<cde>", "abc cde")]
[TestCase("SimpleHTTPServer", "Simple HTTP Server")]
[TestCase("SimpleHTTPS2erver", "Simple HTTPS2erver")]
[TestCase("camelCase", "camel Case")]
[TestCase("m_Field", "Field")]
[TestCase("mm_Field", "mm Field")]
public void Test_GetWords(string identifier, string expectedWordsStr) {
var expectedWords = expectedWordsStr.Split(' ');
if (identifier == null || identifier.Length <= 1) {
expectedWords = new string[0];
}
var words = identifier.GetWords();
Assert.IsTrue(words.SequenceEqual(expectedWords));
}
A simple solution, which should be order(s) of magnitude faster than a regex solution (based on the tests I ran against the top solutions in this thread), especially as the size of the input string grows:
string s1 = "ThisIsATestStringAbcDefGhiJklMnoPqrStuVwxYz";
string s2;
StringBuilder sb = new StringBuilder();
foreach (char c in s1)
sb.Append(char.IsUpper(c)
? " " + c.ToString()
: c.ToString());
s2 = sb.ToString();
Related