日期:2014-05-19  浏览次数:20488 次

lucene 获取分词后的关键字
下面代码可以输出关键字, 但是方法已经过期了, 现在用什么代替?
用的是3.5
Java code

@Test
public void test() throws Exception{
    analyze(new StandardAnalyzer(Version.LUCENE_35), "What's your a name?");
}
private void analyze(Analyzer analyzer, String text) throws Exception {
    TokenStream ts = analyzer.reusableTokenStream("content", new StringReader(text));
    while (ts.incrementToken()) {
        Token t = ts.get
        TermAttribute ta = ts.getAttribute(TermAttribute.class);
        System.out.println(ta.term());
    } 
}



------解决方案--------------------
OffsetAttribute offsetAttr = tokens.getAttribute(OffsetAttribute.class);
CharTermAttribute charTermAttr = tokens.getAttribute(CharTermAttribute.class);
PositionIncrementAttribute posIncrAttr = tokens.addAttribute(PositionIncrementAttribute.class);
TypeAttribute typeAttr = tokens.addAttribute(TypeAttribute.class);
while (tokens.incrementToken()) {
charBuf = charTermAttr.buffer();
termIncr = posIncrAttr.getPositionIncrement();
String term = new String(charBuf, 0, offsetAttr.endOffset() - offsetAttr.startOffset());
 System.out.println(term );
}
tokens.close();