ucene的中文分词器到现在还没有好的解决办法。下边介绍了两个lucene自己提供的分词器和一个javaeye上的网友实现的分词器。关于各个分词器的不同见代码中的print信息。直接运行得到console的输出结果更容易对比不同。
package analyzer;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.cn.ChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.mira.lucene.analysis.IK_CAnalyzer;
import org.mira.lucene.analysis.MIK_CAnalyzer;
import com.sohospace.lucene.analysis.xanalyzer.XAnalyzer;
import com.sohospace.lucene.analysis.xanalyzer.XFactory;
import com.sohospace.lucene.analysis.xanalyzer.XTokenizer;
//中文分词使用了Paoding的分词技术,特表示感谢
public class TestCJKAnalyzer {
private static String testString1 = "中华人民共和国在1949年建立,从此开始了新中国的伟大篇章";
private static String testString2 = "比尔盖茨从事餐饮业和服务业方面的工作";
public static void testStandard(String testString) throws Exception{
Analyzer analyzer = new StandardAnalyzer();
Reader r = new StringReader(testString);
StopFilter sf = (StopFilter) analyzer.tokenStream("", r);
System.err.println("=====standard analyzer====");
System.err.println("分析方法:默认没有词只有字");
Token t;
while ((t = sf.next()) != null) {
System.out.println(t.termText());
}
}
public static void testCJK(String testString) throws Exception{
Analyzer analyzer = new CJKAnalyzer();
Reader r = new StringReader(testString);
StopFilter sf = (StopFilter) analyzer.tokenStream("", r);
System.err.println("=====cjk analyzer====");
System.err.println("分析方法:交叉双字分割");
Token t;
while ((t = sf.next()) != null) {
System.out.println(t.termText());
}
}
public static void testChiniese(String testString) throws Exception{
Analyzer analyzer = new ChineseAnalyzer();
Reader r = new StringReader(testString);
TokenFilter tf = (TokenFilter) analyzer.tokenStream("", r);
System.err.println("=====chinese analyzer====");
System.err.println("分析方法:基本等同StandardAnalyzer");
Token t;
while ((t = tf.next()) != null) {
System.out.println(t.termText());
}
}
public static void testPaoding(String testString) throws Exception{
XAnalyzer analyzer = XFactory.getQueryAnalyzer();
Reader r = new StringReader(testString);
XTokenizer ts = (XTokenizer) analyzer.tokenStream("", r);
System.err.println("=====paoding analyzer====");
System.err.println("分析方法:字典分词,去掉停止词。在字典不能匹配的情况下使用CJKAnalyzer的分割发。");
Token t;
while ((t = ts.next()) != null) {
System.out.println(t.termText());
}
}
public static void testJe(String testString) throws Exception{
// Analyzer analyzer = new MIK_CAnalyzer();
Analyzer analyzer = new IK_CAnalyzer();
Reader r = new StringReader(testString);
TokenStream ts = (TokenStream)analyzer.tokenStream("", r);
System.err.println("=====je analyzer====");
System.err.println("分析方法:字典分词,正反双向搜索,具体不明");
Token t;
while ((t = ts.next()) != null) {
System.out.println(t.termText());
}
}
public static void main(String[] args) throws Exception{
// String testString = testString1;
String testString = testString1;
System.out.println(testString);
testStandard(testString);
testCJK(testString);
testPaoding(testString);
// testChiniese(testString);
// testJe(testString);
}
}