3 Lucene笔记（三）：测试分词器的拆分规则

packagech.lucene.app;

importjava.io.StringReader;

importorg.apache.lucene.analysis.Analyzer;

importorg.apache.lucene.analysis.TokenStream;

importorg.apache.lucene.analysis.cjk.CJKAnalyzer;

importorg.apache.lucene.analysis.tokenattributes.TermAttribute;

importch.lucene.utils.LuceneUtils;

publicclassTestAnalyzer {    

     privatestaticvoidtestAnalyzer(Analyzer analyzer, String text) throws Exception {

          System.out.println("当前使用的分词器：" + analyzer.getClass());

          TokenStreamtokenStream = analyzer.tokenStream("content",newStringReader(text));

           tokenStream.addAttribute(TermAttribute.class);

           while ( tokenStream.incrementToken()) {

              TermAttributetermAttribute = tokenStream.getAttribute(TermAttribute.class);

              System.out.println(termAttribute.term());

          }

     }

     publicstaticvoidmain(String[] args) throws Exception {

           //testAnalyzer(new StandardAnalyzer(LuceneUtils.getVersion()), "当前所用分词器的拆分规则");

           testAnalyzer(newCJKAnalyzer(LuceneUtils.getVersion()),"当前所用分词器的拆分规则，这是什么？" );

     }

}