lucene 分词处理中文

package lia.analysis.i18n;


import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.cn.ChineseAnalyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.util.Version;

import java.awt.Font;
import java.awt.FontMetrics;
import java.awt.Frame;
import java.awt.Label;
import java.io.IOException;
import java.io.StringReader;

// From chapter 4
public class ChineseDemo {
  private static String[] strings = {"道德經"};  //A

  private static Analyzer[] analyzers = {
    new SimpleAnalyzer(),
    new StandardAnalyzer(Version.LUCENE_30),
    new ChineseAnalyzer (),    //B
    new CJKAnalyzer (Version.LUCENE_30)
  };

  public static void main(String args[]) throws Exception {

    for (String string : strings) {
      for (Analyzer analyzer : analyzers) {
        analyze(string, analyzer);
      }
    }

  }

  private static void analyze(String string, Analyzer analyzer)
         throws IOException {
    StringBuffer buffer = new StringBuffer();

    TokenStream stream = analyzer.tokenStream("contents",
                                              new StringReader(string));
    TermAttribute term = stream.addAttribute(TermAttribute.class);

    while(stream.incrementToken()) {   //C
      buffer.append("[");
      buffer.append(term.term());
      buffer.append("] ");
    }

    String output = buffer.toString();

    Frame f = new Frame();
    f.setTitle(analyzer.getClass().getSimpleName() + " : " + string);
    f.setResizable(true);

    Font font = new Font(null, Font.PLAIN, 36);
    int width = getWidth(f.getFontMetrics(font), output);

    f.setSize((width < 250) ? 250 : width + 50, 75);

    // NOTE: if Label doesn't render the Chinese characters
    // properly, try using javax.swing.JLabel instead
    Label label = new Label(output);   //D
    label.setSize(width, 75);
    label.setAlignment(Label.CENTER);
    label.setFont(font);
    f.add(label);

    f.setVisible(true);
  }

  private static int getWidth(FontMetrics metrics, String s) {
    int size = 0;
    int length = s.length();
		for (int i = 0; i < length; i++) {
      size += metrics.charWidth(s.charAt(i));
    }

    return size;
  }
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值