1  public static void BuildIndex(string indexPath,bool isCreated,bool isOptimize,List<Document> docs)
 2         {
 3             //创建盘古分词器
 4             PanGuAnalyzer analyzer = new PanGuAnalyzer();
 5
 6             //创建写索引器(索引路径、分词器实例、是覆盖索引还是追加索引)
 7             IndexWriter writer = new IndexWriter(indexPath, analyzer, isCreated);
 8
 9             try
10             {
11                 //将记录写入索引
12                 foreach (Document doc in docs)
13                 {
14                     writer.AddDocument(doc);
15                 }
16
17                 //优化创建索引
18                 if (isOptimize)
19                 {
20                     writer.Optimize();
21                 }
22             }
23             finally {
24
25                 //关闭写索引器
26                 writer.Close();
27             }
28         }

 1  public static void DeleteIndex(string indexPath,Term term)
 2         {
 3              //创建盘古分词器
 4             PanGuAnalyzer analyzer = new PanGuAnalyzer();
 5
 6             //创建写索引器(索引路径、分词器实例、是覆盖索引还是追加索引)
 7             IndexWriter writer = new IndexWriter(indexPath, analyzer, isCreated);
 8             write.DeleteDocuments(term);
 9             write.Close();
10         }

 1 public static void UpdateIndex(string indexPath, Term term, Document document)
 2         {
 3             //创建盘古分词器
 4             PanGuAnalyzer analyzer = new PanGuAnalyzer();
 5
 6             //创建写索引器(索引路径、分词器实例、是覆盖索引还是追加索引)
 7             IndexWriter writer = new IndexWriter(indexPath, analyzer, isCreated);
 8             write.UpdateDocument(term, document);
 9             write.Close();
10         }

 1         /// <summary>
 2         /// 查询
 3         /// </summary>
 4         /// <param name="indexPath">索引物理路径</param>
 5         /// <param name="Query">查询对象</param>
 6         /// <param name="sort">排序对象</param>
 7         /// <param name="pageIndex">当前页码</param>
 8         /// <param name="pageSize">每页大小</param>
 9         /// <returns>Document对象集合</returns>
10         public static List<Document> QuerySearch(string indexPath, Query query,Filter filter,Sort sort,int pageIndex,int pageSize,out int totalRecord,out string totalTime)
11         {
12             Stopwatch stopwatch = new Stopwatch();
13
14             //创建读索引器及索引搜索器
15             IndexReader reader=null;
16             IndexSearcher searcher = SearchIntance(indexPath,out reader);
17
18             //搜索
19             stopwatch.Start();
20             Hits hits = searcher.Search(query,filter,sort);
21             stopwatch.Stop();
22
23             //对搜索结果进行分页处理
24             List<Document> documents = pagingDocument(pageIndex, pageSize, hits);
25
26             //总记录数和总耗时
27             totalRecord = hits.Length();
28             totalTime = stopwatch.Elapsed.TotalMilliseconds.ToString();
29
30             //关闭读索引器及索引搜索器
31             SearchClose(searcher, reader);
32
33             return documents;
34         }
35
36         /// <summary>
37         /// 对搜索结果进行分页处理
38         /// </summary>
39         /// <param name="pageIndex">当前页码</param>
40         /// <param name="pageSize">每页大小</param>
41         /// <param name="hits">searcher.Search的搜索结果集</param>
42         /// <returns>Document对象集合</returns>
43         private static List<Document> pagingDocument(int pageIndex, int pageSize, Hits hits)
44         {
45             //对结果进行分页
46             List<Document> documents = new List<Document>();
47             int currentIndex = (pageIndex - 1) * pageSize;
48             int maxIndex = pageIndex * pageSize - 1;
49             for (int i = 0; i < hits.Length(); i++)
50             {
51                 if (i < currentIndex)
52                 {
53                     continue;
54                 }
55                 documents.Add(hits.Doc(i));
56                 if (i > maxIndex)
57                 {
58                     break;
59                 }
60             }
61             return documents;
62         }

 1  protected void Button1_Click(object sender, EventArgs e)
 2     {
 3         string indexPath=Server.MapPath("~/App_Data/Blog");
 4
 5         Document document = new Document();
 6         document.Add(new Field("ID",TextBox1.Text,Field.Store.YES,Field.Index.UN_TOKENIZED));
 7         document.Add(new Field("Title", TextBox2.Text, Field.Store.YES, Field.Index.TOKENIZED));
 8         document.Add(new Field("Content", TextBox3.Text, Field.Store.YES, Field.Index.TOKENIZED));
 9         document.Add(new Field("Author", TextBox4.Text, Field.Store.YES, Field.Index.UN_TOKENIZED));
10         document.Add(new Field("HitCount", TextBox11.Text, Field.Store.YES, Field.Index.UN_TOKENIZED));
11         document.Add(new Field("DateCreated",DateTime.Now.ToString(),Field.Store.YES, Field.Index.UN_TOKENIZED));
12
13         List<Document> documents = new List<Document>();
14         documents.Add(document);
15
16         LuceneIndex.BuildIndex(indexPath, true, true,documents);
17     }

 1     protected void Button4_Click(object sender, EventArgs e)
 2     {
 3         string indexPath = Server.MapPath("~/App_Data/Blog");
 4
 5         Document document = new Document();
 6         document.Add(new Field("ID", TextBox7.Text, Field.Store.YES, Field.Index.TOKENIZED));
 7         document.Add(new Field("Title", TextBox8.Text, Field.Store.YES, Field.Index.TOKENIZED));
 8         document.Add(new Field("Content", TextBox9.Text, Field.Store.YES, Field.Index.TOKENIZED));
 9         document.Add(new Field("Author", TextBox10.Text, Field.Store.YES, Field.Index.UN_TOKENIZED));
10         document.Add(new Field("HitCount", TextBox13.Text, Field.Store.YES, Field.Index.UN_TOKENIZED));
11         document.Add(new Field("DateCreated", DateTime.Now.ToString(), Field.Store.YES, Field.Index.UN_TOKENIZED));
12
13         Term term = new Term("ID",TextBox7.Text);
14
15         LuceneIndex.UpdateIndex(indexPath, term, document);
16     }

1     protected void Button5_Click(object sender, EventArgs e)
2     {
3         string indexPath = Server.MapPath("~/App_Data/Blog");
4
5          Term term = new Term("ID",TextBox14.Text);
6
7          LuceneIndex.DeleteIndex(indexPath, term);
8     }

 1     protected void Button3_Click(object sender, EventArgs e)
 2     {
 3         string keyword = TextBox5.Text;
 4
 5         string indexPath = Server.MapPath("~/App_Data/Blog");
 6
 7         string[] panguKeywords = LuceneIndex.GetKeyWordSplitBySpace(keyword,true).Split(',');
 8         BooleanQuery booleanQuery = new BooleanQuery();
 9         booleanQuery.Add(new TermQuery(new Term("Title", keyword)), BooleanClause.Occur.SHOULD);
10         booleanQuery.Add(new TermQuery(new Term("Content", keyword)), BooleanClause.Occur.SHOULD);
11         booleanQuery.Add(new TermQuery(new Term("Author", keyword)), BooleanClause.Occur.SHOULD);
12         foreach (string panguKeyword in panguKeywords)
13         {
14             if (!string.IsNullOrEmpty(panguKeyword))
15             {
16                 booleanQuery.Add(new TermQuery(new Term("Title", panguKeyword)), BooleanClause.Occur.SHOULD);
17                 booleanQuery.Add(new TermQuery(new Term("Content", panguKeyword)), BooleanClause.Occur.SHOULD);
18                 booleanQuery.Add(new TermQuery(new Term("Author", panguKeyword)), BooleanClause.Occur.SHOULD);
19             }
20         }
21
22         Sort sort=new Sort();
23         if (!string.IsNullOrEmpty(TextBox6.Text) || !string.IsNullOrEmpty(TextBox12.Text))
24         {
25             SortField sf = null;
26             if (!string.IsNullOrEmpty(TextBox6.Text))
27             {
28                 sf = new SortField("DateCreated", SortField.STRING, bool.Parse(TextBox6.Text));
29             }
30             if (!string.IsNullOrEmpty(TextBox12.Text))
31             {
32                 sf = new SortField("HitCount", SortField.INT, bool.Parse(TextBox12.Text));
33             }
34             sort.SetSort(sf);
35         }
36
37         if (!string.IsNullOrEmpty(TextBox15.Text) || !string.IsNullOrEmpty(TextBox16.Text))
38         {
39             Term startTime=new Term("DateCreated",TextBox15.Text);
40             Term endTime=new Term("DateCreated",TextBox16.Text);
41             RangeQuery rangeQuery = new RangeQuery(startTime, endTime, false);
42             booleanQuery.Add(rangeQuery, BooleanClause.Occur.MUST);
43         }
44
45         int totalRecord = 0;
46         string totalTime = null;
47         List<Document> documents = LuceneIndex.QuerySearch(indexPath,booleanQuery,null,sort,1,10000,out totalRecord,out totalTime);
48
49         Label1.Text = totalRecord.ToString();
50         Label2.Text = totalTime+"毫秒";
51         string htmlStr = null;
52         foreach (Document document in documents)
53         {
54             htmlStr += "<div><br/><span>ID:" + document.Get("ID") + "</span><br/><br/>" +
55                 "<span>作者:" + LuceneIndex.HighLight(keyword, document.Get("Author"),100) + "</span><br/><br/>" +
56                 "<span>时间:" + LuceneIndex.HighLight(keyword, document.Get("DateCreated"), 100) + "</span><br/><br/>" +
57                 "<span>点击:" + LuceneIndex.HighLight(keyword, document.Get("HitCount"), 100) + "</span><br/><br/>" +
58                 "<span>标题:" + LuceneIndex.HighLight(keyword, document.Get("Title"),100) + "</span><br/><br/></div>" +
59                 "<div>内容:" + LuceneIndex.HighLight(keyword,document.Get("Content"),1000) + "</div>";
60         }
61
62         Label3.Text = htmlStr;
63     }

 1 /// <summary>
 2         /// 对关键字进行分词(分词后得到的字符串进行查询可参考下面注释掉的代码)
 3         /// </summary>
 4         /// <param name="keyWords">要搜索的词</param>
 5         /// <param name="IsComma">分的词用逗号分隔true 以{0}^{1}.0的形式false</param>
 6         /// <returns>分词后的结果</returns>
 7         public static string GetKeyWordSplitBySpace(string keyWords,bool IsComma)
 8         {
 9             PanGuTokenizer panGuTokenizer = new PanGuTokenizer();
10
11             StringBuilder result = new StringBuilder();
12             ICollection<WordInfo> words = panGuTokenizer.SegmentToWordInfos(keyWords);
13
14             foreach (WordInfo word in words)
15             {
16                 if (word == null)
17                 {
18                     continue;
19                 }
20                 if (IsComma)
21                 {
22                     result.Append(word.Word + ",");
23                 }
24                 else
25                 {
26                     result.AppendFormat("{0}^{1}.0 ", word.Word, (int)Math.Pow(3, word.Rank));
27                 }
28             }
29
30             return result.ToString().Trim();
31
32             //keyWords = GetKeyWordsSplitBySpace(keyWords, new PanGuTokenizer());
33             //QueryParser queryParser = new QueryParser("contents", new PanGuAnalyzer(true));
34             //Query query = queryParser.Parse(keyWords);
35
36             //QueryParser titleQueryParser = new QueryParser("title", new PanGuAnalyzer(true));
37             //Query titleQuery = titleQueryParser.Parse(keyWords);
38
39             //BooleanQuery bq = new BooleanQuery();
40             //bq.Add(query, BooleanClause.Occur.SHOULD);
41             //bq.Add(titleQuery, BooleanClause.Occur.SHOULD);
42
43             //Hits hits = search.Search(bq);
44         }

<?xml version="1.0" encoding="utf-8"?>
<PanGuSettings xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns="http://www.codeplex.com/pangusegment"><DictionaryPath>Dictionaries</DictionaryPath><MatchOptions><ChineseNameIdentify>true</ChineseNameIdentify><!--中文名识别--><FrequencyFirst>true</FrequencyFirst><!--词频优先--><MultiDimensionality>true</MultiDimensionality><!--多元分词--><EnglishMultiDimensionality>false</EnglishMultiDimensionality><!--英文多元分词，这个开关，会将英文中的字母与数字分开--><FilterStopWords>true</FilterStopWords><!--过滤停用词--><IgnoreSpace>true</IgnoreSpace><!---忽略空格、回车、Tab--><ForceSingleWord>false</ForceSingleWord><!--强制一元分词--><TraditionalChineseEnabled>false</TraditionalChineseEnabled><!--繁体字分词--><OutputSimplifiedTraditional>false</OutputSimplifiedTraditional><!--同时输出简体和繁体--><UnknowWordIdentify>true</UnknowWordIdentify><!--未登录词识别--><FilterEnglish>false</FilterEnglish><!--过滤英文,这个选项只有在过滤停用词选项生效时才有效--><FilterNumeric>false</FilterNumeric><!--过滤数字,这个选项只有在过滤停用词选项生效时才有效--><IgnoreCapital>false</IgnoreCapital><!--忽略英文大小写--><EnglishSegment>true</EnglishSegment><!--英文分词--><SynonymOutput>false</SynonymOutput><!--同义词输出,一般用于对搜索字符串的分词,不建议在索引时使用--><WildcardOutput>false</WildcardOutput><!--通配符匹配输出,一般用于对搜索字符串的分词,不建议在索引时使用--><WildcardSegment>false</WildcardSegment><!--对通配符匹配的结果分词--><CustomRule>false</CustomRule><!--是否进行用户自定义规则匹配--></MatchOptions><Parameters><Redundancy>0</Redundancy><!--多元分词冗余度--><UnknowRank>1</UnknowRank><!--未登录词权值--><BestRank>5</BestRank><!--最匹配词权值--><SecRank>3</SecRank><!--次匹配词权值--><ThirdRank>2</ThirdRank><!--再次匹配词权值--><SingleRank>1</SingleRank><!--强行输出的单字权值--><NumericRank>1</NumericRank><!--数字的权值--><EnglishRank>5</EnglishRank><!--英文词汇的权值--><SymbolRank>1</SymbolRank><!--符号的权值 --><SimplifiedTraditionalRank>1</SimplifiedTraditionalRank><!--强制同时输出简繁汉字时，非原来文本的汉字输出权值(比如原来文本是简体，这里就是输出的繁体字的权值，反之亦然。)--><SynonymRank>1</SynonymRank><!--同义词权值--><WildcardRank>1</WildcardRank><!--通配符匹配结果的权值--><FilterEnglishLength>50</FilterEnglishLength><!--过滤英文选项生效时，过滤大于这个长度的英文。--><FilterNumericLength>50</FilterNumericLength><!--过滤数字选项生效时，过滤大于这个长度的数字。--></Parameters>
</PanGuSettings>

 1 /// <summary>
 2         /// 高亮
 3         /// </summary>
 4         /// <param name="keyword">要高亮的字符串</param>
 5         /// <param name="content">content</param>
 6         /// <param name="fragmentSize">每个摘要字段的字符数</param>
 7         /// <returns>高亮后的content</returns>
 8         public static string HighLight(string keyword,string content,int fragmentSize)
 9         {
10             //创建HTMLFormatter,参数为高亮搜索词的HTML代码
11             SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
12
13             //创建高亮，输入HTML代码和 盘古对象Semgent
14             Highlighter highter = new Highlighter(simpleHTMLFormatter, new Segment());
15             //设置每个摘要字段的字符数
16             highter.FragmentSize = fragmentSize;
17
18             string highlightStr = highter.GetBestFragment(keyword, content);
19
20             if (string.IsNullOrEmpty(highlightStr))
21                 return content;
22
23             return highlightStr;
24         }