public double Score(string input1, string input2, PreprocessMode preprocessMode)
{
var preprocessor = StringPreprocessorFactory.GetPreprocessor(preprocessMode);
input1 = preprocessor(input1);
input2 = preprocessor(input2);
return(Score(input1, input2));
}
public static Func <string, string> GetPreprocessor(PreprocessMode mode)
{
switch (mode)
{
case PreprocessMode.Full:
return(Default);
case PreprocessMode.None:
return(s => s);
default:
throw new InvalidOperationException($"Invalid string preprocessor mode: {mode}");
}
}
/// <summary>
/// Inconsistent substrings lead to problems in matching. This ratio
/// uses a heuristic called "best partial" for when two strings
/// are of noticeably different lengths.
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static int PartialRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <PartialRatioScorer>().Score(input1, input2, preprocessMode));
}
/// <summary>
/// Find all alphanumeric tokens in the string and sort
/// those tokens and then take ratio of resulting
/// joined strings.
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static int TokenSortRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <TokenSortScorer>().Score(input1, input2, preprocessMode));
}
/// <summary>
/// Splits longer string into tokens and takes the initialism and compares it to the shorter
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static int PartialTokenInitialismRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <PartialTokenInitialismScorer>().Score(input1, input2));
}
/// <summary>
/// Calculates a weighted ratio between the different algorithms for best results
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static double WeightedRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <WeightedRatioScorer>().Score(input1, input2, preprocessMode));
}
/// <summary>
/// Similarity ratio that attempts to determine whether one strings tokens are an abbreviation
/// of the other strings tokens. One string must have all its characters in order in the other string
/// to even be considered.
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static double PartialTokenAbbreviationRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <PartialTokenAbbreviationScorer>().Score(input1, input2, preprocessMode));
}
/// <summary>
/// Splits longer string into tokens and takes the initialism and compares it to the shorter
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static double TokenInitialismRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <TokenInitialismScorer>().Score(input1, input2, preprocessMode));
}
/// <summary>
/// Splits the strings into tokens and computes the ratio on those tokens (not the individual chars,
/// but the strings themselves)
/// </summary>
/// <param name="input1"></param>
/// <param name="input2"></param>
/// <param name="preprocessMode"></param>
/// <returns></returns>
public static double PartialTokenDifferenceRatio(string input1, string input2, PreprocessMode preprocessMode)
{
return(ScorerCache.Get <PartialTokenDifferenceScorer>().Score(input1, input2, preprocessMode));
}
