public void ConstructorTest()
{
var normalizedString = new NormalizedString("abcd");
Assert.AreEqual("ABCD", normalizedString.Value);
Assert.AreEqual("ABCD", normalizedString.ToString());
}
/// <summary>
/// Initializes a new instance of the <see cref="Tokenizer" /> class.
/// </summary>
/// <param name="normalizedText">The normalized text.</param>
public Tokenizer(NormalizedString normalizedText)
{
var tokens = normalizedText.Value.Split(new[] { ' ' });
_tokensEnumerator = ((IEnumerable <string>)tokens).GetEnumerator();
;
}
public void SpecialSymbolRemovingTest()
{
const string stringWithSpecialSymbols = @"?><:|!*[]=)(abcd)&^%$#@!~/\";
var normalizedString = new NormalizedString(stringWithSpecialSymbols);
Assert.AreEqual("ABCD", normalizedString.Value);
Assert.AreEqual("ABCD", normalizedString.ToString());
}
public void CtorToken()
{
const string tokenTest = "token";
var normalizedToken = new NormalizedString(tokenTest);
var token = new Token(tokenTest);
var tokenFromNormalizedString = new Token(normalizedToken);
Assert.AreEqual(token.Value, tokenTest);
Assert.AreEqual(tokenFromNormalizedString.Value, normalizedToken.Value);
}
public void RemoveCzechDiactriticsTest()
{
// czech diacritics
const string stringWithCzechDiactritics = "ěščřžýáíóéúůďťň";
const string expectedNormCzechDiacritics = "ESCRZYAIOEUUDTN";
var normalizedCzechString = new NormalizedString(stringWithCzechDiactritics);
Assert.AreEqual(expectedNormCzechDiacritics, normalizedCzechString.Value);
Assert.AreEqual(expectedNormCzechDiacritics, normalizedCzechString.ToString());
}
public void RemoveGermanDiactriticsTest()
{
// germany diacritics
const string stringWithGermanDiacritics = "ßüabcdöä";
var expectedNormGermanDiactritics = ("ß").ToUpperInvariant() + "UABCDOA";
var normalizedGermanyString = new NormalizedString(stringWithGermanDiacritics);
Assert.AreEqual(expectedNormGermanDiactritics, normalizedGermanyString.Value);
Assert.AreEqual(expectedNormGermanDiactritics, normalizedGermanyString);
}
public void EmptySpaceTest()
{
const string twoTokens = "e - Levenshtein";
var normTwoTokens = new NormalizedString(twoTokens);
normTwoTokens.Value.Split(' ').Length.Should().Be(2);
const string emptyRemove = " systems,[1] ";
var emptyRemoveString = new NormalizedString(emptyRemove);
emptyRemoveString.Value.Split(' ').Length.Should().Be(2);
}
/// <summary>
/// Get the normalized similarity score from 0 to 1 where 1 is total similarity
/// </summary>
/// <param name="first">pattern string</param>
/// <param name="second">text string</param>
/// <returns>returns the similarity score between 0 and 1</returns>
public double GetSimilarity(NormalizedString first, NormalizedString second)
{
return(GetSimilarity(first.Value, second.Value));
}
/// <summary>
/// Offers the same behavior as <see cref="Levenshtein.GetDistance(NormalizedString, NormalizedString)" />
/// and extends for transposition of two character that will have only 1 distance
/// </summary>
/// <example>
/// return 1 for transposition two character ABC => ACB
/// </example>
/// <param name="first">the pattern normalized string</param>
/// <param name="second">the text normalized string</param>
/// <returns>return the number of edit distance</returns>
public int GetDistance(NormalizedString first, NormalizedString second)
{
return(GetDistance(first.Value, second.Value));
}
/// <summary>
/// </summary>
/// <param name="normalizedString"></param>
public QGramSet(NormalizedString normalizedString)
: this(normalizedString.Value)
{
// TODO: check the exception
//Contract.Requires<ArgumentNullException>(normalizedString != null, "normalizedString");
}
