JAVA中文分詞算法

原文地址：http://hi.baidu.com/lewutian/blog/item/ee6d9dd7780bf8d1a144dfef.html
下面是demo,記得要加lucene-core-2.3.2.jar和lucene-Analyzer.jar以及IKAnalyzer.jar這幾個包

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;

public class TestJeAnalyzer {
private static String testString1 = "冗長的代碼常常是複雜性會導致代碼難以測試和維護.";
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：默認沒有詞只有字");
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:交叉雙字分割");
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 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:字典分詞,具體不明");
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);
}

}