中文 IKAnalyzer 分詞

package NaviveBayesClassify;

import java.io.IOException;

import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.TokenStream;

import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import org.wltea.analyzer.lucene.IKAnalyzer;

public class ChineseSpliter {

/**

* 對給定的文本進行中文分詞

* 

* @param text

*            給定的文本

* @param splitToken

*            用於分割的標記,如"|"

* @return 分詞完畢的文本

* @throws IOException

*/

public static String split(String text, String splitToken) throws IOException {

String result = null;

// 建立分詞對象

@SuppressWarnings("resource")

Analyzer analyzer = new IKAnalyzer(true);

StringReader reader = new StringReader(text);

// 分詞

TokenStream ts = analyzer.tokenStream("", reader);

CharTermAttribute term = ts.getAttribute(CharTermAttribute.class);

// 遍歷分詞數據

while (ts.incrementToken()) {

System.out.print(term.toString() + splitToken);

result = term.toString() + splitToken + result;

}

reader.close();

return result; 

}

}