public WordnetDictionary(string searchDirectory)
{
mEngine = new DataFileEngine(searchDirectory);
Dictionary <string, string[][]> suffixMap = new Dictionary <string, string[][]>();
suffixMap.Add("noun", new string[][] { new string[] { "s", "" }, new string[] { "ses", "s" }, new string[] { "xes", "x" }, new string[] { "zes", "z" }, new string[] { "ches", "ch" }, new string[] { "shes", "sh" }, new string[] { "men", "man" }, new string[] { "ies", "y" } });
suffixMap.Add("verb", new string[][] { new string[] { "s", "" }, new string[] { "ies", "y" }, new string[] { "es", "e" }, new string[] { "es", "" }, new string[] { "ed", "e" }, new string[] { "ed", "" }, new string[] { "ing", "e" }, new string[] { "ing", "" } });
suffixMap.Add("adjective", new string[][] { new string[] { "er", "" }, new string[] { "est", "" }, new string[] { "er", "e" }, new string[] { "est", "e" } });
DetachSuffixesOperation tokDso = new DetachSuffixesOperation(suffixMap);
tokDso.AddDelegate(DetachSuffixesOperation.Operations, new IOperation[] { new LookupIndexWordOperation(mEngine), new LookupExceptionsOperation(mEngine) });
TokenizerOperation tokOp = new TokenizerOperation(mEngine, new string[] { " ", "-" });
tokOp.AddDelegate(TokenizerOperation.TokenOperations, new IOperation[] { new LookupIndexWordOperation(mEngine), new LookupExceptionsOperation(mEngine), tokDso });
DetachSuffixesOperation morphDso = new DetachSuffixesOperation(suffixMap);
morphDso.AddDelegate(DetachSuffixesOperation.Operations, new IOperation[] { new LookupIndexWordOperation(mEngine), new LookupExceptionsOperation(mEngine) });
mDefaultOperations = new IOperation[] { new LookupExceptionsOperation(mEngine), morphDso, tokOp };
}
public string Lemmatize(string lemma, string partOfSpeech)
{
if (mDefaultOperations == null)
{
var suffixMap = new Dictionary <string, string[][]>
{
{
"noun", new string[][]
{
new string[] { "s", "" }, new string[] { "ses", "s" }, new string[] { "xes", "x" },
new string[] { "zes", "z" }, new string[] { "ches", "ch" }, new string[] { "shes", "sh" },
new string[] { "men", "man" }, new string[] { "ies", "y" }
}
}
,
{
"verb", new string[][]
{
new string[] { "s", "" }, new string[] { "ies", "y" }, new string[] { "es", "e" },
new string[] { "es", "" }, new string[] { "ed", "e" }, new string[] { "ed", "" },
new string[] { "ing", "e" }, new string[] { "ing", "" }
}
}
//,
//{
// "adjective", new string[][]
// {
// new string[] {"er", ""}, new string[] {"est", ""}, new string[] {"er", "e"},
// new string[] {"est", "e"}
// }
//}
};
var tokDso = new DetachSuffixesOperation(suffixMap);
tokDso.AddDelegate(DetachSuffixesOperation.Operations, new IOperation[] { new LookupIndexWordOperation(this), new LookupExceptionsOperation(this) });
var tokOp = new TokenizerOperation(this, new string[] { " ", "-" });
tokOp.AddDelegate(TokenizerOperation.TokenOperations, new IOperation[] { new LookupIndexWordOperation(this), new LookupExceptionsOperation(this), tokDso });
var morphDso = new DetachSuffixesOperation(suffixMap);
morphDso.AddDelegate(DetachSuffixesOperation.Operations, new IOperation[] { new LookupIndexWordOperation(this), new LookupExceptionsOperation(this) });
mDefaultOperations = new IOperation[] { new LookupExceptionsOperation(this), morphDso, tokOp };
}
return(Lemmatize(lemma, partOfSpeech, mDefaultOperations));
}