/// <summary>
/// 创建分析器
/// </summary>
/// <param name="language">语言</param>
/// <param name="useIndexSynonyms">true表示在创建索引时，将同义词，近义词，相关词存入索引；false表示不使用。</param>
public AnalyzerBus(string language, bool useIndexSynonyms = false)
{
this._EnableStopPositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(global::Lucene.Net.Util.Version.LUCENE_30);
this._Language = language;
this._UseIndexSynonyms = useIndexSynonyms;
this._SymbolAnalyzer = new SymbolAnalyzer();
this._Analyzer = AnalyzerDict.GetAnalyzer(language.ToUpper());
this._StopCharArraySet = StopWord.StopWordList;
}
/// <summary>
/// 将字分成字的数组
/// </summary>
/// <param name="word"></param>
/// <returns></returns>
public static string[] SplitWord(string word)
{
List <string> list = new List <string>();
if (string.IsNullOrEmpty(word))
{
return(list.ToArray());
}
using (SymbolAnalyzer simple = new SymbolAnalyzer())
{
using (TokenStream ts = simple.ReusableTokenStream("", new StringReader(word)))//只显示分词信息,不需要使用FieldName
{
while (ts.IncrementToken())
{
ITermAttribute attribute = ts.GetAttribute <ITermAttribute>();
list.Add(attribute.Term);
}
}
}
return(list.ToArray());
}