使用Lucene进行全文检索(二)---得到有效的内容(转载)

 /**
 * 解析一个html页面,返回一个html页面类.
 *
 * @param resource 文件路径或者网址
 */
    public static searchhtmlpage parsehtmlpage(string resource)
    {
        string title = "";
        string body = "";
        try
        {
            parser myparser = new parser(resource);

            //设置编码:根据实际情况修改
            myparser.setencoding("gbk");

            htmlpage visitor = new htmlpage(myparser);

            myparser.visitallnodeswith(visitor);

            title = visitor.gettitle();

            body = combinenodetext(visitor.getbody().tonodearray());
        }
        catch (parserexception e)
        {
            logman.error("parse html page " + resource + " error!");
        }

        searchhtmlpage result = new searchhtmlpage(title, body);

        return result;
    }

    /**
     * 解析html内容,得到普通文本和链接的内容.
     *
     * @param content 要解析的内容
     * @return 返回解析后的内容
     */
    public static string parsehtmlcontent(string content)
    {
        parser myparser;
        nodelist nodelist = null;

        myparser = parser.createparser(content, "gbk");

        nodefilter textfilter = new nodeclassfilter(textnode.class);
        nodefilter linkfilter = new nodeclassfilter(linktag.class);

        //暂时不处理 meta
        //nodefilter metafilter = new nodeclassfilter(metatag.class);

        orfilter lastfilter = new orfilter();
        lastfilter.setpredicates(new nodefilter[] { textfilter, linkfilter });

        try
        {
            nodelist = myparser.parse(lastfilter);
        }
        catch (parserexception e)
        {
            logman.warn("parse content error", e);
        }

        //中场退出了
        if (null == nodelist)
        {
            return "";
        }

        node[] nodes = nodelist.tonodearray();

        string result = combinenodetext(nodes);
        return result;
    }

 //合并节点的有效内容
    private static string combinenodetext(node[] nodes)
    {
        stringbuffer result = new stringbuffer();

        for (int i = 0; i < nodes.length; i++)
        {
            node anode = (node) nodes[i];

            string line = "";
            if (anode instanceof textnode)
            {
                textnode textnode = (textnode) anode;
                //line = textnode.toplaintextstring().trim();
                line = textnode.gettext();
            }
            else if (anode instanceof linktag)
            {
                linktag linknode = (linktag) anode;

                line = linknode.getlink();
                //过滤jsp标签
                line = stringfunc.replace(line, "", "");
            }

            if (stringfunc.istrimempty(line)) continue;

            result.append(" ").append(line);
        }

        return result.tostring();
    }