使用dotlucene多条件检索数据库
using System;
using System.Data;
using System.Configuration;
using System.Collections;
using System.Web;
using System.IO;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Text.RegularExpressions;
using Lucene.Net.Search;
using Lucene.Net.Index;
using Lucene.Net.QueryParsers;
using Lucene.Net.Analysis.Standard;
using Lucene.Net.Search.Highlight;
using Lucene.Net.Documents;
using System.Data.SqlClient;
using Lucene.Net.Analysis.Cn;
public partial class Search : System.Web.UI.Page
{
/// <summary>
/// 搜索返回的结果集
/// </summary>
protected DataTable Results = new DataTable();
/// <summary>
/// 搜索返回的结果总数
/// </summary>
private int total;
/// <summary>
/// 搜索的结果每页显示多少记录条数
/// </summary>
private readonly int maxResults = 10;
/// <summary>
/// 本次搜索所花费的时间
/// </summary>
private TimeSpan duration;
/// <summary>
/// 本次搜索是从哪条数据开始的,这个东西很重要，通过他基本上可以得到一切
/// </summary>
private int startAt;
/// <summary>
/// 本页显示的数据是从哪条开始的,他总是startAt+1
/// </summary>
private int fromItem;
/// <summary>
/// 本页显示的数据记录到哪条结束
/// </summary>
private int toItem;
protected void Page_Load(object sender, EventArgs e)
{
//给搜索按牛注册下隐藏事件
// this.Page.ClientScript.RegisterHiddenField("__EVENTTARGET","buttonSearch");
if (!IsPostBack)
{
if (this.Query != null)
{
search();
DataBind();
}
else
{
Response.Redirect("./");//如果没有传入查询字符则定向到开始页面
}
}
}
protected void search()
{
DateTime start = DateTime.Now;//搜索的开始时间
//得到索引所在的目录,我们在上个console程序里把索引放到了index目录下
string indexDirectory = Server.MapPath("index");
//创建个索引搜索器
IndexSearcher searcher = new IndexSearcher(indexDirectory);
string[] b = this.Query.Split(' ');
BooleanQuery m_BooleanQuery = new BooleanQuery();
//分词并解析索引的text字段以便搜索,多条件检索
for (int i = 0; i < b.Length; i++)
{
Query thisQuery = QueryParser.Parse(b[i], "text", new ChineseAnalyzer());
m_BooleanQuery.Add(thisQuery, true, false);
}
//为要绑定输出到页面的results建立几列
this.Results.Columns.Add("path",typeof(string));
this.Results.Columns.Add("sample",typeof(string));
this.Results.Columns.Add("title",typeof(string));
//开始搜索
Hits hits = searcher.Search(m_BooleanQuery);
//得到搜索返回的记录总数
this.total = hits.Length();
//创建一个高亮
QueryHighlightExtractor highlighter = new QueryHighlightExtractor(m_BooleanQuery, new ChineseAnalyzer(), "<b>", "</b>");
//初始化startAt,以便得到要显示的结果集
this.startAt = initStartAt();
//得到当前页要显示的记录数量，包括以前所有页的记录数，这样把他与this.startAt结合就能够很好的知道当前页要显示的记录数了
int resultsCount = smallOf(this.total,this.startAt+this.maxResults);
//开始循环得到当前页要显示的记录ex
string pp = "";
//for (int i = this.startAt; i < resultsCount; i++)
//for (int i = this.startAt ; i <resultsCount; i+exit+)
for (int i = this.total - this.startAt-1; i >= this.total - resultsCount; i--)
{
//得到每一行Hits的Document,因为Hits的没一行都是个Document对象
Document doc = hits.Doc(i);
//得到doc里面的列path的值
string path = doc.Get("path");
pp += path + ",";
//再得到这个路径在web程序的路径，我们原来把文档放到了web根目录的documents目录下的
string location = Server.MapPath(@"documents\" + path);
//用StreamReader读取文档，因为我们不能够直接从索引中得到text字段的值，因为我们建立索引的时候没有存储他的
string plainText;
//using (StreamReader sr = new StreamReader(location, System.Text.Encoding.Default))
//{
// plainText = ParseHtml(sr.ReadToEnd());
//}
//为结果集DataTable,Results添加个新行
}
if (pp.Length > 0)
pp = pp.Substring(0, pp.Length - 1);
//Response.Write(pp);
//string ppp = pp.Split(',');
//string kk = "";
//if (kk.Length > 0)
// kk = kk.Substring(0, kk.Length - 1);
//for (int i = this.startAt; i < resultsCount; i++)
// kk += ppp[i] + ",";
if (pp.Length > 0)
{
SqlConnection conn = new SqlConnection("server=.;uid=sa;pwd=liugehao;dataｂａｓｅ=yaowanggu;");
//取出10条记录
SqlCommand cmd = new SqlCommand("select z_id,z_name,z_lx,z_pzwh,z_sccs,z_jx,z_gg,z_yfyl,z_zsqy,z_dltj,z_tgzc,z_dwmc,z_lxdh,z_lxr from ywg_zhaoshang where z_id in (" + pp + ") order by z_id desc", conn);
conn.Open();
SqlDataReader sdr = cmd.ExecuteReader(System.Data.CommandBehavior.CloseConnection);
while (sdr.Read())
{
DataRow dr = this.Results.NewRow();
dr["title"] = sdr[1].ToString();
dr["path"] = @"documents/" + sdr[0].ToString();
dr["sample"] = highlighter.GetBestFragment(sdr[1].ToString() + sdr[2].ToString() + sdr[3].ToString() + sdr[4].ToString() + sdr[5].ToString() + sdr[6].ToString() +
sdr[7].ToString() + sdr[8].ToString() + sdr[9].ToString() + sdr[10].ToString() + sdr[11].ToString() + sdr[12].ToString() + sdr[13].ToString(),100);
//把行添加进DataTable
this.Results.Rows.Add(dr);
}
conn.Close();
}
//循环完毕，关闭搜索
searcher.Close();
//搜索花费多少时间
this.duration = DateTime.Now - start;
//给fromItem赋值，他总是startAt+1
this.fromItem = this.startAt + 1;
//给toItem赋值
this.toItem = smallOf(this.total,this.startAt+this.maxResults);
}
private string ParseHtml(string html)
{
string temp = Regex.Replace(html,"<[^>]*>","");
return temp.Replace(" "," ");
}
/// <summary>
/// 开始分页
/// </summary>
/// <returns></returns>
protected DataTable Paging
{
get
{
//知道了startAt,分页也很容易了,现在根据startAt得到当前是第几页,注意，现在这里的页数也是暂时从0开始的
int pageNumber = (this.startAt + this.maxResults - 1) / this.maxResults;
DataTable dt = new DataTable();
dt.Columns.Add("html");
DataRow dr = dt.NewRow();
//暂时得到当前页的html连接,注意这里当真正显示页数的时候要+1
dr["html"] = pagingNumberHtml(startAt,pageNumber+1,false);
dt.Rows.Add(dr);
//前面显示10页，如果有的话
int previousPagesCount = 10;
//循环把前面页的html连接插到前面去
for (int i = pageNumber - 1; i >= 0 && i >= pageNumber - previousPagesCount; i--)
{
DataRow r = dt.NewRow();
r["html"] = pagingNumberHtml(i*this.maxResults,i+1,true);
dt.Rows.InsertAt(r,0);;
}
//后面也显示10页，如果有的话
int nextPagesCount = 10;
for (int i = pageNumber + 1; i <= this.pageCount && i <= pageNumber + nextPagesCount; i++)
{
DataRow r = dt.NewRow();
r["html"] = pagingNumberHtml(i*this.maxResults,i+1,true);
dt.Rows.Add(r);
}
//添加下一页的超级连接
DataRow lastRow = dt.NewRow();
lastRow["html"] = "<a href='Search.aspx?q=" + HttpUtility.UrlEncode(this.Query) + "&start=" + (pageNumber + 1) * this.maxResults + "'>下一页</a>";
dt.Rows.Add(lastRow);
return dt;
}
}
/// <summary>
/// 得到某一页的html连接字符串
/// </summary>
/// <param name="start">页是从那条记录开始搜索的</param>
/// <param name="number">页数</param>
/// <param name="active">是不是个超级连接</param>
/// <returns></returns>
private string pagingNumberHtml(int start, int number, bool active)
{
if (active)
{
return "<a href='Search.aspx?q="+HttpUtility.UrlEncode(this.Query)+"&start="+start+"'>"+number+"</a>";
}
else
{
return "<span style='font-weight:bold;'>'+number+'</span>';
}
}
private int smallOf(int first, int second)
{
return first < second ? first : second;//得到两个数之间的较少数
}
private int initStartAt()
{
try
{
int sa = Convert.ToInt32(this.Request.Params["start"]);
if (sa < 0)
return 0;
if (sa >= this.total - 1)
return lastPageStartAt;//如果不足以显示三条，从最后页的第0条开始显示
return sa;
}
catch
{
return 0;//如果输入非法非数字，那么从第0条开始显示
}
}
private int pageCount
{
get
{
return (this.total - 1) / this.maxResults;//总页数，记住都是从0开始的
}
}
private int lastPageStartAt
{
get
{
return pageCount * this.maxResults;//返回最末页的第0条的序号
}
}
protected string Query
{
get
{
string query = HttpUtility.UrlDecode(this.Request.Params["q"]);
if (query == string.Empty)
return null;
return query;
}
}
protected string Summary
{
get
{
if (this.total > 0)
return "共有结果<span style='color:red;'>' + this.total + '</span>,当前从第<span style='color:red;'>' + this.fromItem + '</span>条到第<span style='color:red;'>' + this.toItem + '</span>条,本次搜索耗时<span style='color:red;'>' + this.duration.TotalSeconds + '</span>秒';
else
return "对不起，本次搜索没有找到任何结果";
}
}
protected void buttonSearch_Click(object sender, EventArgs e)
{
this.Response.Redirect("Search.aspx?q="+HttpUtility.UrlEncode(this.textboxQuery.Text));
}
}
编辑推荐DotLucene搜索引擎文章列表：
全文搜索解决方案：DotLucene搜索引擎之创建索引
http://www.xueit.com/html/2009-02/21_606_00.html
DotLucene搜索引擎之搜索索引Demo
http://www.xueit.com/html/2009-02/21_607_00.html
全文搜索技术：dotLucene中文分词的highlight显示
http://www.xueit.com/html/2009-02/21_608_00.html
Lucene.NET增加中文分词
http://www.xueit.com/html/2009-02/21_609_00.html
全文搜索之Lucene增加中文分词功能方法
http://www.xueit.com/html/2009-02/21_610_00.html
简介下基于.NET的全文索引引擎Lucene.NET
http://www.xueit.com/html/2009-02/21_611_00.html
使用dotlucene为数据库建立全文索引
http://www.xueit.com/html/2009-02/21_612_00.html
使用dotlucene多条件检索数据库
http://www.xueit.com/html/2009-02/21_613_00.html
Lucene中文分词实现方法：基于StopWord分割分词
http://www.xueit.com/html/2009-02/21_614_00.html
dotLucene实现增量索引源代码
http://www.xueit.com/html/2009-02/21_615_00.html