"); createIKToken("可恶的Google。我终于找到了一个合适的中文分词器IK Analyzer。"); } /** * 创建IKAnalyzer分词器 * * @param source */ private void createIKToken(String source) { IKAnalyzer analyzer = new IKAnalyzer(); TokenStream tokenStream = null; try { //使用ik的智能分词 analyzer.setUseSmart(true); // lucene 7以上版本TokenStream的构造方法有所修改，需要使用以下两行代码 // org.apache.lucene.analysis.Analyzer.TokenStreamComponents // res = analyzer.createComponents("content", new StringReader(text)); tokenStream = analyzer.tokenStream("content", source); CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class); tokenStream.reset(); while (tokenStream.incrementToken()) { System.out.println(charTermAttribute.toString()); } tokenStream.end(); tokenStream.close(); } catch (IOException e) { e.printStackTrace(); } }}