public double GetMatchPercentage(string source, string target)
{
if (string.IsNullOrEmpty(source) || string.IsNullOrEmpty(target))
{
return(0);
}
double matchingCharacters = 0;
var sourceStrings = source.Split(' ');
var targetStrings = target.Split(' ');
var sourceIsLarger = source.Length >= target.Length;
matchingCharacters =
CalculateMatchingCharacters(matchingCharacters, sourceStrings, targetStrings, sourceIsLarger);
var sourceWhiteSpaceCount = source.Count(char.IsWhiteSpace);
var targetWhiteSpaceCount = target.Count(char.IsWhiteSpace);
matchingCharacters += sourceIsLarger ? sourceWhiteSpaceCount : targetWhiteSpaceCount;
var amount = matchingCharacters / (sourceIsLarger ? source.Length : target.Length) * 100;
var wrappedAmount = _parser?.GetMatchPercentage(source, target) ?? 0;
return(amount > wrappedAmount ? amount : wrappedAmount);
}
//https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Levenshtein_distance#C#
public int GetDistance(string source, string target)
{
if (string.IsNullOrEmpty(source))
{
if (string.IsNullOrEmpty(target))
{
return(0);
}
return(target.Length);
}
if (string.IsNullOrEmpty(target))
{
return(source.Length);
}
if (source.Length > target.Length)
{
var temp = target;
target = source;
source = temp;
}
var m = target.Length;
var n = source.Length;
var distance = new int[2, m + 1];
// Initialize the distance matrix
for (var j = 1; j <= m; j++)
{
distance[0, j] = j;
}
var currentRow = 0;
for (var i = 1; i <= n; ++i)
{
currentRow = i & 1;
distance[currentRow, 0] = i;
var previousRow = currentRow ^ 1;
for (var j = 1; j <= m; j++)
{
var cost = target[j - 1] == source[i - 1] ? 0 : 1;
distance[currentRow, j] = Math.Min(Math.Min(
distance[previousRow, j] + 1,
distance[currentRow, j - 1] + 1),
distance[previousRow, j - 1] + cost);
}
}
var distancing = distance[currentRow, m];
if (distancing >= 20)
{
return(0);
}
var parsing = _parser?.GetMatchPercentage(source, target) ?? 0;
return(distancing >= parsing ? distancing : Convert.ToInt32(parsing));
}
public IEnumerable <IMatch> GetMatches <T1, T2>(IEnumerable <T1> sourceCollection,
IEnumerable <T2> targetCollection, Func <T1, string> sourceSelector, Func <T2, string> targetSelector,
IEqualityComparer <T1> distinctComparer = null)
{
var matches = new List <Match>();
var collection = targetCollection as T2[] ?? targetCollection.ToArray();
foreach (var source in sourceCollection.Distinct(distinctComparer))
{
foreach (var target in collection)
{
var sourceString = sourceSelector(source);
var targetString = targetSelector(target);
var percentage = _matchParser.GetMatchPercentage(sourceString?.ToUpper(), targetString?.ToUpper());
matches.Add(new Match(sourceString, targetString, percentage));
}
}
return(matches);
}