Lucene全文检索-从零开始（3）

1.传入要检索的关键字和需要检索的字段

/// <Contents>
    /// 全文检索
    /// </Contents>
    /// <param name="keyword">关键词</param>
    /// <param name="field">搜索字段</param>
    public List<China.Model.LuceneIndexArticle> SearchIndex(string keyword, List<string> field)
    {
        Dictionary<string, string> dic = new Dictionary<string, string>();
        BooleanQuery bQuery = new BooleanQuery();
        foreach (string str in field)
        {
            string key = GetKeyWordsSplitBySpace(keyword);//处理搜索词
            QueryParser parse = new QueryParser(str, PanGuAnalyzer);//盘古分词
            Query query = parse.Parse(key);
            parse.SetDefaultOperator(QueryParser.Operator.AND);
            bQuery.Add(query, BooleanClause.Occur.SHOULD);
            dic.Add(str, keyword);
        }
        if (bQuery != null && bQuery.GetClauses().Length > 0)
        {
            return GetSearchResult(bQuery, dic, keyword);
        }
        else
        {
            return null;
        }
    }

2.获取搜索结果

 /// <Contents>
    /// 获取搜索结果
    /// </Contents>
    /// <param name="bQuery"></param>
    public List<China.Model.LuceneIndexArticle> GetSearchResult(BooleanQuery bQuery, Dictionary<string, string> dicKeywords, string keyword)
    {
        //打开索引位置
        IndexSearcher search = new IndexSearcher(IndexDic, true);
        //运行时间
        Stopwatch stopwatch = Stopwatch.StartNew();
        TopScoreDocCollector collector = TopScoreDocCollector.create(10, true);
        search.Search(bQuery, null, collector);//根据query查询条件进行查询，查询结果放入collector容器
        //TopDocs 指定0到GetTotalHits() 即所有查询结果中的文档 如果TopDocs(20,10)则意味着获取第20-30之间文档内容 达到分页的效果
        ScoreDoc[] docs = collector.TopDocs(0, collector.GetTotalHits()).scoreDocs;
        List<China.Model.LuceneIndexArticle> list = new List<China.Model.LuceneIndexArticle>();
        ///TopDocs docs = search.Search(bQuery, (Filter)null, 1000);
        stopwatch.Stop();
        //搜索结果条数
        count = docs.Length;
        if (docs != null && docs.Length > 0)
        {
            //运行时间
            lSearchTime = stopwatch.ElapsedMilliseconds;
            foreach (ScoreDoc sd in docs)
            {
                Document doc = search.Doc(sd.doc);
                string title = doc.Get("Title");
                string content = doc.Get("Contents");
                China.Model.LuceneIndexArticle ar = new China.Model.LuceneIndexArticle();
                {
                    ar.ID = Convert.ToInt32(doc.Get("ID"));
                    ar.Title = doc.Get("Title").ToString();
                    ar.Contents = ReplaceHtmlTag(doc.Get("Contents").ToString());
                };
                PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter = new PanGu.HighLight.SimpleHTMLFormatter("<font color="red">", "</font>");
                PanGu.HighLight.Highlighter highlighter = new PanGu.HighLight.Highlighter(simpleHTMLFormatter, new PanGu.Segment());
                highlighter.FragmentSize = 200;
                string Contentshighlight = highlighter.GetBestFragment(keyword, ar.Contents);
                string titlehighlight = highlighter.GetBestFragment(keyword, ar.Title);
                if (Contentshighlight == "")
                {
                    if (ar.Contents.Length > 200)
                    {
                        ar.Contents = ar.Contents.Substring(0, 200);
                    }
                    else
                    {
                        ar.Contents = ar.Contents.Substring(0, ar.Contents.Length);
                    }
                }
                else
                {
                    ar.Contents = Contentshighlight;
                }
                if (titlehighlight != "") ar.Title = titlehighlight;
                list.Add(ar);
            }
        }
        return list;
    }

随便检索一条数据

按照常理，我们的数据是有变动的，比如新增数据，对数据的修改、删除。那我们的索引也要随着这些操作而改变，从而保证整个系统数据的一致性。