生成索引的 Java 代码：

/**
* PHPDocIndexer.java
* 用于对 PHPDoc 的 HTML 页面生成索引文件。
*/
import java.io.File;
import java.io.FileReader;
import java.io.BufferedReader;
import java.io.IOException;
import java.util.Date;
import java.text.DateFormat;
import java.lang.*;

import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.DateField;

class PHPDocIndexer
{
    public static void main(String[] args) throws ClassNotFoundException, IOException
    {
        try {
            Date start = new Date();

            IndexWriter writer = new IndexWriter(”/home/nio/indexes-phpdoc”, new CJKAnalyzer(), true); //索引保存目录，必须存在
            indexDocs(writer, new File(”/home/nio/phpdoc-zh”)); //HTML 文件保存目录

            System.out.println(”Optimizing ….”);
            writer.optimize();
            writer.close();

            Date end = new Date();

            System.out.print(”Total time: “);
            System.out.println(end.getTime() - start.getTime());
        } catch (Exception e) {
            System.out.println(”Class ” + e.getClass() + ” throws error!n  errmsg: ” + e.getMessage());
        }   //end try
    }   //end main

    public static void indexDocs(IndexWriter writer, File file) throws Exception
    {
        if (file.isDirectory()) {
            String[] files = file.list();
            for (int i = 0; i < files.length; i++) {
                indexDocs(writer, new File(file, files[i]));
            }   //end for
        } else if (file.getPath().endsWith(”.html”)) {  //只对 HTML 文件做索引          
            System.out.print(”Add file:” + file + ” ….”);
            // Add html file ….
            Document doc = new Document();
            doc.add(Field.UnIndexed(”file”, file.getName()));    //索引文件名
            doc.add(Field.UnIndexed(”modified”, DateFormat.getDateTimeInstance().format(new Date(file.lastModified()))));   //索引最后修改时间

            String title = “”;
            String content = “”;
            String status = “start”;

            FileReader fReader = new FileReader(file);
            BufferedReader bReader = new BufferedReader(fReader);
            String line = bReader.readLine();

            while (line != null) {               
                content += line;
                //截取 HTML 标题 <title>
                if (”start” == status && line.equalsIgnoreCase(”><TITLE”)) {
                    status = “match”;
                } else if (”match” == status) {
                    title = line.substring(1, line.length() - 7);
                    doc.add(Field.Text(”title”, title));    //索引标题
                    status = “end”;
                }   //end if
                line = bReader.readLine();
            }   //end while
            bReader.close();
            fReader.close();
            doc.add(Field.Text(”content”, content.replaceAll(”<[^<>]+>”, “”)));  //索引内容
            writer.addDocument(doc);
            System.out.println(” [OK]”);
        }   //end if
    }

}   //end class