I need to perform Wildcard (*
, ?
, etc.) search on a string.
This is what I have done:
string input = "Message";
string pattern = "d*";
Regex regex = new Regex(pattern, RegexOptions.IgnoreCase);
if (regex.IsMatch(input))
{
MessageBox.Show("Found");
}
else
{
MessageBox.Show("Not Found");
}
With the above code "Found" block is hitting but actually it should not!
If my pattern is "e*" then only "Found" should hit.
My understanding or requirement is d* search should find the text containing "d" followed by any characters.
Should I change my pattern as "d.*" and "e.*"? Is there any support in .NET for Wild Card which internally does it while using Regex class?
From http://www.codeproject.com/KB/recipes/wildcardtoregex.aspx:
public static string WildcardToRegex(string pattern)
{
return "^" + Regex.Escape(pattern)
.Replace(@"\*", ".*")
.Replace(@"\?", ".")
+ "$";
}
So something like foo*.xls?
will get transformed to ^foo.*\.xls.$
.
You may want to use WildcardPattern
from System.Management.Automation
assembly. See my answer here.
public class Wildcard
{
private readonly string _pattern;
public Wildcard(string pattern)
{
_pattern = pattern;
}
public static bool Match(string value, string pattern)
{
int start = -1;
int end = -1;
return Match(value, pattern, ref start, ref end);
}
public static bool Match(string value, string pattern, char[] toLowerTable)
{
int start = -1;
int end = -1;
return Match(value, pattern, ref start, ref end, toLowerTable);
}
public static bool Match(string value, string pattern, ref int start, ref int end)
{
return new Wildcard(pattern).IsMatch(value, ref start, ref end);
}
public static bool Match(string value, string pattern, ref int start, ref int end, char[] toLowerTable)
{
return new Wildcard(pattern).IsMatch(value, ref start, ref end, toLowerTable);
}
public bool IsMatch(string str)
{
int start = -1;
int end = -1;
return IsMatch(str, ref start, ref end);
}
public bool IsMatch(string str, char[] toLowerTable)
{
int start = -1;
int end = -1;
return IsMatch(str, ref start, ref end, toLowerTable);
}
public bool IsMatch(string str, ref int start, ref int end)
{
if (_pattern.Length == 0) return false;
int pindex = 0;
int sindex = 0;
int pattern_len = _pattern.Length;
int str_len = str.Length;
start = -1;
while (true)
{
bool star = false;
if (_pattern[pindex] == '*')
{
star = true;
do
{
pindex++;
}
while (pindex < pattern_len && _pattern[pindex] == '*');
}
end = sindex;
int i;
while (true)
{
int si = 0;
bool breakLoops = false;
for (i = 0; pindex + i < pattern_len && _pattern[pindex + i] != '*'; i++)
{
si = sindex + i;
if (si == str_len)
{
return false;
}
if (str[si] == _pattern[pindex + i])
{
continue;
}
if (si == str_len)
{
return false;
}
if (_pattern[pindex + i] == '?' && str[si] != '.')
{
continue;
}
breakLoops = true;
break;
}
if (breakLoops)
{
if (!star)
{
return false;
}
sindex++;
if (si == str_len)
{
return false;
}
}
else
{
if (start == -1)
{
start = sindex;
}
if (pindex + i < pattern_len && _pattern[pindex + i] == '*')
{
break;
}
if (sindex + i == str_len)
{
if (end <= start)
{
end = str_len;
}
return true;
}
if (i != 0 && _pattern[pindex + i - 1] == '*')
{
return true;
}
if (!star)
{
return false;
}
sindex++;
}
}
sindex += i;
pindex += i;
if (start == -1)
{
start = sindex;
}
}
}
public bool IsMatch(string str, ref int start, ref int end, char[] toLowerTable)
{
if (_pattern.Length == 0) return false;
int pindex = 0;
int sindex = 0;
int pattern_len = _pattern.Length;
int str_len = str.Length;
start = -1;
while (true)
{
bool star = false;
if (_pattern[pindex] == '*')
{
star = true;
do
{
pindex++;
}
while (pindex < pattern_len && _pattern[pindex] == '*');
}
end = sindex;
int i;
while (true)
{
int si = 0;
bool breakLoops = false;
for (i = 0; pindex + i < pattern_len && _pattern[pindex + i] != '*'; i++)
{
si = sindex + i;
if (si == str_len)
{
return false;
}
char c = toLowerTable[str[si]];
if (c == _pattern[pindex + i])
{
continue;
}
if (si == str_len)
{
return false;
}
if (_pattern[pindex + i] == '?' && c != '.')
{
continue;
}
breakLoops = true;
break;
}
if (breakLoops)
{
if (!star)
{
return false;
}
sindex++;
if (si == str_len)
{
return false;
}
}
else
{
if (start == -1)
{
start = sindex;
}
if (pindex + i < pattern_len && _pattern[pindex + i] == '*')
{
break;
}
if (sindex + i == str_len)
{
if (end <= start)
{
end = str_len;
}
return true;
}
if (i != 0 && _pattern[pindex + i - 1] == '*')
{
return true;
}
if (!star)
{
return false;
}
sindex++;
continue;
}
}
sindex += i;
pindex += i;
if (start == -1)
{
start = sindex;
}
}
}
}
Use:
var ismatch2 = Wildcard.Match("xmlfsdfsd", "xml*");
The correct regular expression formulation of the glob expression d*
is ^d
, which means match anything that starts with d
.
string input = "Message";
string pattern = @"^d";
Regex regex = new Regex(pattern, RegexOptions.IgnoreCase);
(The @
quoting is not necessary in this case, but good practice since many regexes use backslash escapes that need to be left alone, and it also indicates to the reader that this string is special).
I think @Dmitri has nice solution at Matching strings with wildcard https://stackoverflow.com/a/30300521/1726296
Based on his solution, I have created two extension methods. (credit goes to him)
May be helpful.
public static String WildCardToRegular(this String value)
{
return "^" + Regex.Escape(value).Replace("\\?", ".").Replace("\\*", ".*") + "$";
}
public static bool WildCardMatch(this String value,string pattern,bool ignoreCase = true)
{
if (ignoreCase)
return Regex.IsMatch(value, WildCardToRegular(pattern), RegexOptions.IgnoreCase);
return Regex.IsMatch(value, WildCardToRegular(pattern));
}
Usage:
string pattern = "file.*";
var isMatched = "file.doc".WildCardMatch(pattern)
or
string xlsxFile = "file.xlsx"
var isMatched = xlsxFile.WildCardMatch(pattern)
You need to convert your wildcard expression to a regular expression. For example:
private bool WildcardMatch(String s, String wildcard, bool case_sensitive)
{
// Replace the * with an .* and the ? with a dot. Put ^ at the
// beginning and a $ at the end
String pattern = "^" + Regex.Escape(wildcard).Replace(@"\*", ".*").Replace(@"\?", ".") + "$";
// Now, run the Regex as you already know
Regex regex;
if(case_sensitive)
regex = new Regex(pattern);
else
regex = new Regex(pattern, RegexOptions.IgnoreCase);
return(regex.IsMatch(s));
}
You must escape special Regex symbols in input wildcard pattern (for example pattern *.txt
will equivalent to ^.*\.txt$
)
So slashes, braces and many special symbols must be replaced with @"\" + s
, where s
- special Regex symbol.
Windows and *nux treat wildcards differently. *
, ?
and .
are processed in a very complex way by Windows, one's presence or position would change another's meaning. While *nux keeps it simple, all it does is just one simple pattern match. Besides that, Windows matches ?
for 0 or 1 chars, Linux matches it for exactly 1 chars.
I didn't find authoritative documents on this matter, here is just my conclusion based on days of tests on Windows 8/XP (command line, dir
command to be specific, and the Directory.GetFiles
method uses the same rules too) and Ubuntu Server 12.04.1 (ls
command). I made tens of common and uncommon cases work, although there'are many failed cases too.
The current answer by Gabe, works like *nux. If you also want a Windows style one, and are willing to accept the imperfection, then here it is:
/// <summary>
/// <para>Tests if a file name matches the given wildcard pattern, uses the same rule as shell commands.</para>
/// </summary>
/// <param name="fileName">The file name to test, without folder.</param>
/// <param name="pattern">A wildcard pattern which can use char * to match any amount of characters; or char ? to match one character.</param>
/// <param name="unixStyle">If true, use the *nix style wildcard rules; otherwise use windows style rules.</param>
/// <returns>true if the file name matches the pattern, false otherwise.</returns>
public static bool MatchesWildcard(this string fileName, string pattern, bool unixStyle)
{
if (fileName == null)
throw new ArgumentNullException("fileName");
if (pattern == null)
throw new ArgumentNullException("pattern");
if (unixStyle)
return WildcardMatchesUnixStyle(pattern, fileName);
return WildcardMatchesWindowsStyle(fileName, pattern);
}
private static bool WildcardMatchesWindowsStyle(string fileName, string pattern)
{
var dotdot = pattern.IndexOf("..", StringComparison.Ordinal);
if (dotdot >= 0)
{
for (var i = dotdot; i < pattern.Length; i++)
if (pattern[i] != '.')
return false;
}
var normalized = Regex.Replace(pattern, @"\.+$", "");
var endsWithDot = normalized.Length != pattern.Length;
var endWeight = 0;
if (endsWithDot)
{
var lastNonWildcard = normalized.Length - 1;
for (; lastNonWildcard >= 0; lastNonWildcard--)
{
var c = normalized[lastNonWildcard];
if (c == '*')
endWeight += short.MaxValue;
else if (c == '?')
endWeight += 1;
else
break;
}
if (endWeight > 0)
normalized = normalized.Substring(0, lastNonWildcard + 1);
}
var endsWithWildcardDot = endWeight > 0;
var endsWithDotWildcardDot = endsWithWildcardDot && normalized.EndsWith(".");
if (endsWithDotWildcardDot)
normalized = normalized.Substring(0, normalized.Length - 1);
normalized = Regex.Replace(normalized, @"(?!^)(\.\*)+$", @".*");
var escaped = Regex.Escape(normalized);
string head, tail;
if (endsWithDotWildcardDot)
{
head = "^" + escaped;
tail = @"(\.[^.]{0," + endWeight + "})?$";
}
else if (endsWithWildcardDot)
{
head = "^" + escaped;
tail = "[^.]{0," + endWeight + "}$";
}
else
{
head = "^" + escaped;
tail = "$";
}
if (head.EndsWith(@"\.\*") && head.Length > 5)
{
head = head.Substring(0, head.Length - 4);
tail = @"(\..*)?" + tail;
}
var regex = head.Replace(@"\*", ".*").Replace(@"\?", "[^.]?") + tail;
return Regex.IsMatch(fileName, regex, RegexOptions.IgnoreCase);
}
private static bool WildcardMatchesUnixStyle(string pattern, string text)
{
var regex = "^" + Regex.Escape(pattern)
.Replace("\\*", ".*")
.Replace("\\?", ".")
+ "$";
return Regex.IsMatch(text, regex);
}
There's a funny thing, even the Windows API PathMatchSpec does not agree with FindFirstFile. Just try a1*.
, FindFirstFile
says it matches a1
, PathMatchSpec
says not.
You can do a simple wildcard mach without RegEx using a Visual Basic function called LikeString.
using Microsoft.VisualBasic;
using Microsoft.VisualBasic.CompilerServices;
if (Operators.LikeString("This is just a test", "*just*", CompareMethod.Text))
{
Console.WriteLine("This matched!");
}
If you use CompareMethod.Text
it will compare case-insensitive. For case-sensitive comparison, you can use CompareMethod.Binary
.
More info here: http://www.henrikbrinch.dk/Blog/2012/02/14/Wildcard-matching-in-C
d*
means that it should match zero or more "d
" characters. So any string is a valid match. Try d+
instead!
In order to have support for wildcard patterns I would replace the wildcards with the RegEx equivalents. Like *
becomes .*
and ?
becomes .?
. Then your expression above becomes d.*
All upper code is not correct to the end.
This is because when searching zz*foo* or zz* you will not get correct results.
And if you search "abcd*" in "abcd" in TotalCommander will he find a abcd file so all upper code is wrong.
Here is the correct code.
public string WildcardToRegex(string pattern)
{
string result= Regex.Escape(pattern).
Replace(@"\*", ".+?").
Replace(@"\?", ".");
if (result.EndsWith(".+?"))
{
result = result.Remove(result.Length - 3, 3);
result += ".*";
}
return result;
}
Source: Stackoverflow.com