htmldocument.java

来自「反ajax原代码」· Java 代码 · 共 52 行

// Decompiled by Jad v1.5.7g. Copyright 2000 Pavel Kouznetsov.
// Jad home page: http://www.geocities.com/SiliconValley/Bridge/8617/jad.html
// Decompiler options: packimports(3) fieldsfirst ansi 
// Source File Name:   HTMLDocument.java

package com.laoer.bbscs.lucene;

import com.laoer.bbscs.lucene.html.HTMLParser;
import com.laoer.bbscs.sys.Constant;
import java.io.File;
import java.io.IOException;
import org.apache.lucene.document.*;

public class HTMLDocument
{

    static char dirSep = System.getProperty("file.separator").charAt(0);

    public static String uid(File f)
    {
        return f.getPath().replace(dirSep, '\0') + "\0" + DateField.timeToString(f.lastModified());
    }

    public static String uid2url(String uid)
    {
        String url = uid.replace('\0', '/');
        return url.substring(0, url.lastIndexOf(47));
    }

    public static Document Document(File f)
        throws IOException, InterruptedException
    {
        Document doc = new Document();
        String url = f.getPath().replace(dirSep, '/');
        if(url.startsWith(Constant.ROOTPATH))
            url = url.substring(Constant.ROOTPATH.length(), url.length());
        doc.add(Field.UnIndexed("url", url));
        doc.add(Field.Keyword("modified", DateField.timeToString(f.lastModified())));
        doc.add(new Field("uid", uid(f), false, true, false));
        HTMLParser parser = new HTMLParser(f);
        doc.add(Field.Text("contents", parser.getReader()));
        doc.add(Field.UnIndexed("summary", parser.getSummary()));
        doc.add(Field.Text("title", parser.getTitle()));
        return doc;
    }

    private HTMLDocument()
    {
    }

}