import?java.io.StringReader;
import?org.apache.lucene.analysis.*;
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.MIK_CAnalyzer;
public?class?JeAnalyzer?{
public?static?void?testStandard(String?testString)?{
try?{
Analyzer?analyzer?=?new?StandardAnalyzer();
Reader?r?=?new?StringReader(testString);
StopFilter?sf?=?(StopFilter)?analyzer.tokenStream("",?r);
System.err.println("=====standard?analyzer====");
Token?t;
while?((t?=?sf.next())?!=?null)?{
System.out.println(t.termText());
}
}?catch?(Exception?e)?{
e.printStackTrace();
}
}
public?static?void?testCJK(String?testString)?{
try?{
Analyzer?analyzer?=?new?CJKAnalyzer();
Reader?r?=?new?StringReader(testString);
StopFilter?sf?=?(StopFilter)?analyzer.tokenStream("",?r);
System.err.println("=====cjk?analyzer====");
Token?t;
while?((t?=?sf.next())?!=?null)?{
System.out.println(t.termText());
}
}?catch?(Exception?e)?{
e.printStackTrace();
}
}
public?static?void?testChiniese(String?testString)?{
try?{
Analyzer?analyzer?=?new?ChineseAnalyzer();
Reader?r?=?new?StringReader(testString);
TokenFilter?tf?=?(TokenFilter)?analyzer.tokenStream("",?r);
System.err.println("=====chinese?analyzer====");
Token?t;
while?((t?=?tf.next())?!=?null)?{
System.out.println(t.termText());
}
}?catch?(Exception?e)?{
e.printStackTrace();
}
}
public?static?String?transJe(String?testString,?String?c1,?String?c2)?{
String?result?=?"";
try?{
Analyzer?analyzer?=?new?MIK_CAnalyzer();
Reader?r?=?new?StringReader(testString);
TokenStream?ts?=?(TokenStream)?analyzer.tokenStream("",?r);
Token?t;
while?((t?=?ts.next())?!=?null)?{
result?+=?t.termText()?+?",";
}
}?catch?(Exception?e)?{
e.printStackTrace();
}
return?result;
}
public?static?void?main(String[]?args)?{
try?{
String?testString?=?"中文分詞的方法其實不局限於中文應用，也被應用到英文處理，如手寫識別，單詞之間的空格就很清楚，中文分詞方法可以幫助判別英文單詞的邊界";
System.out.println("測試的語句"+testString);
String?sResult[]?=?transJe(testString,?"gb2312",?"utf-8").split(",");
for?(int?i?=?0;?i?<?sResult.length;?i++)?{
System.out.println(sResult[i]);
}
}?catch?(Exception?e)?{
e.printStackTrace();
}
}
}
jar包?
lucene-analyzers-2.4.1.jar
lucene-core-2.4.1.jar
IKAnalyzer2.0.2OBF.jar