• 关于Lucene.net 中高亮显示关键词的深究


    这几天一直在学习lucene,也写了3篇自己总结的知识点,本以为很容易上手的东西,但是却遇到了一个很棘手的问题,借此,希望可以跟大家探讨一下

    问题:使用盘古高亮显示组件后,如搜索“mp3 player”,搜索词中间包含空格,但是搜出来的结果,经过高亮后,空格莫名其妙的没了,具体不知道是怎么回事,如果去掉高亮的话,搜出来的结果中就有空格

    代码:

    ////用于搜索的代码

    Lucene.Net.Store.FSDirectory dir = Lucene.Net.Store.FSDirectory.GetDirectory(basePath);
    Lucene.Net.Search.IndexSearcher search = new Lucene.Net.Search.IndexSearcher(dir, true);
    Lucene.Net.Search.BooleanQuery boolQuery = new Lucene.Net.Search.BooleanQuery();

    Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser(Lucene.Net.Util.Version.LUCENE_29, "title", pgAnalyzer);
    boolQuery.Add(parser.Parse(kw), Lucene.Net.Search.BooleanClause.Occur.MUST);

    parser = new Lucene.Net.QueryParsers.QueryParser(Lucene.Net.Util.Version.LUCENE_29, "keywords", pgAnalyzer);
    boolQuery.Add(parser.Parse(kw), Lucene.Net.Search.BooleanClause.Occur.SHOULD);

    parser = new Lucene.Net.QueryParsers.QueryParser(Lucene.Net.Util.Version.LUCENE_29, "productsummary", pgAnalyzer);
    boolQuery.Add(parser.Parse(kw), Lucene.Net.Search.BooleanClause.Occur.SHOULD);

    Lucene.Net.Search.Hits hits = search.Search(boolQuery);
    List<ProductInfo> lists = PageList(hits, pageIndex, pageSize);
    if (lists != null && lists.Count > 0)
    {
    records = hits.Length();
    rptList.DataSource = lists;
    rptList.DataBind();
    }
    dir.Close();

    ///分页显示的结果处理,其中ProductInfo是自己定义的一个数据结果体

    public List<ProductInfo> PageList(Lucene.Net.Search.Hits hits, int pageIndex, int pageSize)
    {
    List<ProductInfo> lists = new List<ProductInfo>();
    if (hits == null)
    return null;
    if (hits.Length() <= 0)
    return null;
    int totalPages = hits.Length() % pageSize == 0 ? hits.Length() / pageSize : hits.Length() / pageSize + 1;//总页数
    if (pageIndex <= 0)
    pageIndex = 1;
    if (pageIndex > totalPages)
    pageIndex = totalPages;
    for (int i = (pageIndex - 1) * pageSize; i < pageIndex * pageSize && i < hits.Length(); i++)
    {
    Lucene.Net.Documents.Document doc = hits.Doc(i);
    ProductInfo item = new ProductInfo();
    item.AttributeCustom = doc.Get("attributecustom");
    item.BusinessType = doc.Get("businesstype");
    item.CompanyName = doc.Get("companyname");
    item.CountryName = doc.Get("countryname");
    item.Guid = doc.Get("guid");
    item.LocalPic = doc.Get("localpic");
    item.MemberId = doc.Get("memberid");
    item.ProductSummary = doc.Get("productsummary");
    item.Title = doc.Get("title");
    item.UrlTitle = doc.Get("urltitle");
    lists.Add(item);
    }
    return lists;
    }

    ///高亮方法,在repeter绑定数据源时传入当前的title调用

    protected string hightLightTitle(string title)
    {
    if (string.IsNullOrEmpty(title))
    return string.Empty;
    if (string.IsNullOrEmpty(title))
    return string.Empty;
    PanGu.HighLight.Highlighter highter = new PanGu.HighLight.Highlighter(formatter, new PanGu.Segment());
    highter.FragmentSize = 100;
    return highter.GetBestFragment(kw, title);
    }

    比如:搜索 “China Shine Globe”,出来的结果如下

    关键词中的空格莫名其妙的没了,真的很让人费解,小弟研究了好久叶没搞明白,希望各位大侠可以指导指导

  • 相关阅读:
    poj3372 Candy Distribution
    poj3270 Cow Sorting
    poj2888 Magic Bracelet
    poj2429 GCD & LCM Inverse
    poj1811 Prime Test
    poj2689 Prime Distance
    【思维】2017多校训练七 HDU6121 Build a tree
    【字符串+BFS】Problem 7. James Bond
    【dfs】codeforces Journey
    【思维+贪心】codeforces Game of the Rows
  • 原文地址:https://www.cnblogs.com/xiaoshouzi/p/3199650.html
Copyright © 2020-2023  润新知