I would like to match strings with a wildcard (*), where the wildcard means "any". For example:
*X = string must end with X
X* = string must start with X
*X* = string must contain X
Also, some compound uses such as:
*X*YZ* = string contains X and contains YZ
X*YZ*P = string starts with X, contains YZ and ends with P.
Is there a simple algorithm to do this? I'm unsure about using regex (though it is a possibility).
To clarify, the users will type in the above to a filter box (as simple a filter as possible), I don't want them to have to write regular expressions themselves. So something I can easily transform from the above notation would be good.
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;
}
}
}
}
*X*YZ* = string contains X and contains YZ
@".*X.*YZ"
X*YZ*P = string starts with X, contains YZ and ends with P.
@"^X.*YZ.*P$"
Often, wild cards operate with two type of jokers:
? - any character (one and only one)
* - any characters (zero or more)
so you can easily convert these rules into appropriate regular expression:
// If you want to implement both "*" and "?"
private static String WildCardToRegular(String value) {
return "^" + Regex.Escape(value).Replace("\\?", ".").Replace("\\*", ".*") + "$";
}
// If you want to implement "*" only
private static String WildCardToRegular(String value) {
return "^" + Regex.Escape(value).Replace("\\*", ".*") + "$";
}
And then you can use Regex as usual:
String test = "Some Data X";
Boolean endsWithEx = Regex.IsMatch(test, WildCardToRegular("*X"));
Boolean startsWithS = Regex.IsMatch(test, WildCardToRegular("S*"));
Boolean containsD = Regex.IsMatch(test, WildCardToRegular("*D*"));
// Starts with S, ends with X, contains "me" and "a" (in that order)
Boolean complex = Regex.IsMatch(test, WildCardToRegular("S*me*a*X"));
A wildcard * can be translated as .* or .*? regex pattern.
You might need to use a singleline mode to match newline symbols, and in this case, you can use (?s) as part of the regex pattern.
You can set it for the whole or part of the pattern:
X* = > @"X(?s:.*)"
*X = > @"(?s:.*)X"
*X* = > @"(?s).*X.*"
*X*YZ* = > @"(?s).*X.*YZ.*"
X*YZ*P = > @"(?s:X.*YZ.*P)"
Using of WildcardPattern from System.Management.Automation may be an option.
pattern = new WildcardPattern(patternString);
pattern.IsMatch(stringToMatch);
Visual Studio UI may not allow you to add System.Management.Automation assembly to References of your project. Feel free to add it manually, as described here.
C# Console application sample
Command line Sample:
C:/> App_Exe -Opy PythonFile.py 1 2 3
Console output:
Argument list: -Opy PythonFile.py 1 2 3
Found python filename: PythonFile.py
using System;
using System.Text.RegularExpressions; //Regex
namespace ConsoleApp1
{
class Program
{
static void Main(string[] args)
{
string cmdLine = String.Join(" ", args);
bool bFileExtFlag = false;
int argIndex = 0;
Regex regex;
foreach (string s in args)
{
//Search for the 1st occurrence of the "*.py" pattern
regex = new Regex(@"(?s:.*)\056py", RegexOptions.IgnoreCase);
bFileExtFlag = regex.IsMatch(s);
if (bFileExtFlag == true)
break;
argIndex++;
};
Console.WriteLine("Argument list: " + cmdLine);
if (bFileExtFlag == true)
Console.WriteLine("Found python filename: " + args[argIndex]);
else
Console.WriteLine("Python file with extension <.py> not found!");
}
}
}
It is necessary to take into consideration, that Regex IsMatch gives true with XYZ, when checking match with Y*. To avoid it, I use "^" anchor
isMatch(str1, "^" + str2.Replace("*", ".*?"));
So, full code to solve your problem is
bool isMatchStr(string str1, string str2)
{
string s1 = str1.Replace("*", ".*?");
string s2 = str2.Replace("*", ".*?");
bool r1 = Regex.IsMatch(s1, "^" + s2);
bool r2 = Regex.IsMatch(s2, "^" + s1);
return r1 || r2;
}
Source: Stackoverflow.com